diff --git a/Documentation/ABI/testing/sysfs-fs-erofs b/Documentation/ABI/testing/sysfs-fs-erofs index e4cf6fc6a1066d..0b8b4354e40b8e 100644 --- a/Documentation/ABI/testing/sysfs-fs-erofs +++ b/Documentation/ABI/testing/sysfs-fs-erofs @@ -5,7 +5,7 @@ Description: Shows all enabled kernel features. Supported features: compr_cfgs, big_pcluster, chunked_file, device_table, compr_head2, sb_chksum, ztailpacking, dedupe, fragments, - 48bit, metabox. + xattr_prefixes, 48bit, metabox. What: /sys/fs/erofs//sync_decompress Date: November 2021 diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index e8ff36982d97bc..d0f1742883651b 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -4922,18 +4922,6 @@ Kernel parameters Set to non-zero if a chip is present that snoops speed changes. Disabled by default. - pata_legacy.ht6560a= [HW,LIBATA] - Format: - Set to 1, 2, or 3 for HT 6560A on the primary channel, - the secondary channel, or both channels respectively. - Disabled by default. - - pata_legacy.ht6560b= [HW,LIBATA] - Format: - Set to 1, 2, or 3 for HT 6560B on the primary channel, - the secondary channel, or both channels respectively. - Disabled by default. - pata_legacy.iordy_mask= [HW,LIBATA] Format: IORDY enable mask. Set individual bits to allow IORDY @@ -4946,18 +4934,6 @@ Kernel parameters with the sequence. By default IORDY is allowed across all channels. - pata_legacy.opti82c46x= [HW,LIBATA] - Format: - Set to 1, 2, or 3 for Opti 82c611A on the primary - channel, the secondary channel, or both channels - respectively. Disabled by default. - - pata_legacy.opti82c611a= [HW,LIBATA] - Format: - Set to 1, 2, or 3 for Opti 82c465MV on the primary - channel, the secondary channel, or both channels - respectively. Disabled by default. - pata_legacy.pio_mask= [HW,LIBATA] Format: PIO mode mask for autospeed devices. Set individual @@ -4981,19 +4957,6 @@ Kernel parameters the first port in the list above (0x1f0), and so on. By default all supported ports are probed. - pata_legacy.qdi= [HW,LIBATA] - Format: - Set to non-zero to probe QDI controllers. By default - set to 1 if CONFIG_PATA_QDI_MODULE, 0 otherwise. - - pata_legacy.winbond= [HW,LIBATA] - Format: - Set to non-zero to probe Winbond controllers. Use - the standard I/O port (0x130) if 1, otherwise the - value given is the I/O port to use (typically 0x1b0). - By default set to 1 if CONFIG_PATA_WINBOND_VLB_MODULE, - 0 otherwise. - pata_platform.pio_mask= [HW,LIBATA] Format: Supported PIO mode mask. Set individual bits to allow diff --git a/Documentation/hwmon/gpd-fan.rst b/Documentation/hwmon/gpd-fan.rst index 29527a77fe882f..b27657d3305633 100644 --- a/Documentation/hwmon/gpd-fan.rst +++ b/Documentation/hwmon/gpd-fan.rst @@ -67,7 +67,7 @@ pwm1_enable at full speed. Write "1" to set to manual, write "2" to let the EC control decide fan speed. Read this attribute to see current status. - NB：In consideration of the safety of the device, when setting to manual mode, + NB: In consideration of the safety of the device, when setting to manual mode, the pwm speed will be set to the maximum value (255) by default. You can set a different value by writing pwm1 later. diff --git a/Documentation/hwmon/hwmon-kernel-api.rst b/Documentation/hwmon/hwmon-kernel-api.rst index 9fcde32a140df6..c3eb433a78f61e 100644 --- a/Documentation/hwmon/hwmon-kernel-api.rst +++ b/Documentation/hwmon/hwmon-kernel-api.rst @@ -42,6 +42,9 @@ register/unregister functions:: char *devm_hwmon_sanitize_name(struct device *dev, const char *name); + int hwmon_notify_event(struct device *dev, enum hwmon_sensor_types type, + u32 attr, int channel); + void hwmon_lock(struct device *dev); void hwmon_unlock(struct device *dev); @@ -90,6 +93,18 @@ implemented in the driver, or debugfs functions, hwmon_lock() and hwmon_unlock() can be used to ensure that calls to those functions are serialized. Those functions also support guard() and scoped_guard() variants. +Drivers can call hwmon_notify_event() to notify userspace and the thermal +subsystem when a hardware monitoring event (such as an alarm or a fault +condition) occurs or clears. The parameters are the hwmon device, the sensor +type, the attribute identifier associated with the event (such as +hwmon_temp_max_alarm or hwmon_fan_fault), and the sensor channel number. +hwmon_notify_event() generates a sysfs event (calling sysfs_notify()) and a +udev event with the attribute name passed in the NAME environment property +(e.g., "NAME=temp1_max_alarm"). If the event is for a temperature sensor and +the sensor is attached to a thermal zone, it also notifies the thermal +subsystem to update the thermal zone. hwmon_notify_event() returns 0 on +success or a negative error code on failure. + Using devm_hwmon_device_register_with_info() -------------------------------------------- diff --git a/Documentation/netlink/specs/rt-link.yaml b/Documentation/netlink/specs/rt-link.yaml index 68c26a70bb6492..c75731ecbe1af8 100644 --- a/Documentation/netlink/specs/rt-link.yaml +++ b/Documentation/netlink/specs/rt-link.yaml @@ -898,6 +898,8 @@ attribute-sets: - name: txqlen type: u32 + checks: + max: 32767 - name: map type: binary diff --git a/Documentation/scheduler/sched-ext.rst b/Documentation/scheduler/sched-ext.rst index 2771ea4cc14af9..96ff66c91ceb26 100644 --- a/Documentation/scheduler/sched-ext.rst +++ b/Documentation/scheduler/sched-ext.rst @@ -229,7 +229,7 @@ optional. The following modified excerpt is from void BPF_STRUCT_OPS(simple_exit, struct scx_exit_info *ei) { - exit_type = ei->type; + exit_type = ei->kind; } SEC(".struct_ops") diff --git a/MAINTAINERS b/MAINTAINERS index 8014b9f8253edf..95cd976a068c09 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -26241,6 +26241,7 @@ R: Andy Shevchenko L: linux-i2c@vger.kernel.org S: Supported F: drivers/i2c/busses/i2c-designware-* +F: include/linux/designware_i2c.h SYNOPSYS DESIGNWARE I2C DRIVER - AMDISP M: Nirujogi Pratap diff --git a/Makefile b/Makefile index 73e7bac7527e69..c28f11c617a481 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 7 PATCHLEVEL = 2 -SUBLEVEL = 6 +SUBLEVEL = 7 EXTRAVERSION = NAME = Baby Opossum Posse diff --git a/arch/arm/mach-ux500/cpu-db8500.c b/arch/arm/mach-ux500/cpu-db8500.c index b1a70f203372bd..0d7530fb6ad074 100644 --- a/arch/arm/mach-ux500/cpu-db8500.c +++ b/arch/arm/mach-ux500/cpu-db8500.c @@ -12,7 +12,7 @@ #include #include #include -#include +#include #include #include #include @@ -81,7 +81,7 @@ static void __init ux500_init_irq(void) struct resource r; irqchip_init(); - prcmu_early_init(); + db8500_prcmu_early_init(); np = of_find_compatible_node(NULL, NULL, "stericsson,db8500-prcmu"); of_address_to_resource(np, 0, &r); of_node_put(np); @@ -101,7 +101,7 @@ static void ux500_restart(enum reboot_mode mode, const char *cmd) local_irq_disable(); local_fiq_disable(); - prcmu_system_reset(0); + db8500_prcmu_system_reset(0); } static const struct of_device_id u8500_local_bus_nodes[] = { diff --git a/arch/arm64/kernel/machine_kexec.c b/arch/arm64/kernel/machine_kexec.c index c5693a32e49b06..8f9bc2327dc856 100644 --- a/arch/arm64/kernel/machine_kexec.c +++ b/arch/arm64/kernel/machine_kexec.c @@ -129,7 +129,8 @@ int machine_kexec_post_load(struct kimage *kimage) } /* Create a copy of the linear map */ - rc = trans_pgd_create_copy(&info, &trans_pgd, PAGE_OFFSET, PAGE_END); + rc = trans_pgd_create_copy(&info, &trans_pgd, + _PAGE_OFFSET(vabits_actual), PAGE_END); if (rc) return rc; kimage->arch.ttbr1 = __pa(trans_pgd); diff --git a/arch/arm64/tools/sysreg b/arch/arm64/tools/sysreg index 7cb61aca3797fa..03f5e1755a6333 100644 --- a/arch/arm64/tools/sysreg +++ b/arch/arm64/tools/sysreg @@ -3736,7 +3736,9 @@ Sysreg ICC_CR0_EL1 3 1 12 0 1 Res0 63:39 Field 38 PID Field 37:32 IPPT -Res0 31:1 +Res0 31:3 +Field 2 LINK_IDLE +Field 1 LINK Field 0 EN EndSysreg diff --git a/arch/powerpc/include/asm/entry-common.h b/arch/powerpc/include/asm/entry-common.h index c5adb50063610a..8e91489fdf2bb7 100644 --- a/arch/powerpc/include/asm/entry-common.h +++ b/arch/powerpc/include/asm/entry-common.h @@ -222,8 +222,6 @@ static inline void arch_interrupt_enter_prepare(struct pt_regs *regs) if (user_mode(regs)) { kuap_lock(); - account_cpu_user_entry(); - account_stolen_time(); } else { kuap_save_and_lock(regs); /* @@ -270,7 +268,7 @@ static inline void arch_interrupt_exit_prepare(struct pt_regs *regs) } /* irqentry_exit expects to be called with interrupts disabled */ - local_irq_disable(); + hard_irq_disable(); } static inline void arch_interrupt_async_enter_prepare(struct pt_regs *regs) @@ -515,8 +513,14 @@ static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs, #ifdef CONFIG_PPC_TRANSACTIONAL_MEM local_paca->tm_scratch = regs->msr; #endif - /* Restore user access locks last */ - kuap_user_restore(regs); + /* + * Do not restore KUAP here. Generic entry might treat this as the last + * arch step before userspace but PowerPC still has kernel work after + * irqentry_exit()/syscall_exit_to_user_mode() i.e. in + * interrupt_exit_user_prepare() / syscall_exit_prepare() may enable + * IRQs and retry. Those functions restore KUAP immediately before rfi, + * which is where it should belong. + */ } #define arch_exit_to_user_mode_prepare arch_exit_to_user_mode_prepare diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index 028f6915853234..d64cce17a4e069 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -533,9 +533,7 @@ static void eeh_rmv_device(struct eeh_dev *edev, void *userdata) if (rmv_data) list_add(&edev->rmv_entry, &rmv_data->removed_vf_list); } else { - pci_lock_rescan_remove(); pci_stop_and_remove_bus_device(dev); - pci_unlock_rescan_remove(); } } diff --git a/arch/powerpc/kernel/interrupt.c b/arch/powerpc/kernel/interrupt.c index 5b88bf72786c74..55f9c0c9922acf 100644 --- a/arch/powerpc/kernel/interrupt.c +++ b/arch/powerpc/kernel/interrupt.c @@ -175,7 +175,7 @@ again: current_thread_info()->exit_flags &= ~_TIF_RESTOREALL; regs->exit_result |= ret; - return ret; + return regs->exit_result; } #endif diff --git a/arch/powerpc/kexec/file_load_64.c b/arch/powerpc/kexec/file_load_64.c index 6075b1c88511a0..d990880b77dfd2 100644 --- a/arch/powerpc/kexec/file_load_64.c +++ b/arch/powerpc/kexec/file_load_64.c @@ -57,7 +57,7 @@ int arch_check_excluded_range(struct kimage *image, unsigned long start, emem = image->arch.exclude_ranges; for (i = 0; i < emem->nr_ranges; i++) - if (start < emem->ranges[i].end && end > emem->ranges[i].start) + if (start <= emem->ranges[i].end && end >= emem->ranges[i].start) return 1; return 0; @@ -113,7 +113,7 @@ static int add_usable_mem(struct umem_info *um_info, u64 base, u64 end) loc_end = um_info->ranges[i].end; if (loc_base >= base && loc_end <= end) add = true; - else if (base < loc_end && end > loc_base) { + else if (base <= loc_end && end >= loc_base) { if (loc_base < base) loc_base = base; if (loc_end > end) diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index f9380ef657500d..dd128b293992b5 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -6124,12 +6124,12 @@ static int kvmppc_irq_bypass_add_producer_hv(struct irq_bypass_consumer *cons, struct kvm_kernel_irqfd *irqfd = container_of(cons, struct kvm_kernel_irqfd, consumer); - irqfd->producer = prod; - ret = kvmppc_set_passthru_irq(irqfd->kvm, prod->irq, irqfd->gsi); if (ret) pr_info("kvmppc_set_passthru_irq (irq %d, gsi %d) fails: %d\n", prod->irq, irqfd->gsi, ret); + else + irqfd->producer = prod; return ret; } diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 32ecbc46e74b9d..728a5610d16755 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -1623,15 +1623,13 @@ int64_t pnv_opal_pci_msi_eoi(struct irq_data *d) return opal_pci_msi_eoi(phb->opal_id, d->parent_data->hwirq); } -static struct irq_chip pnv_pci_msi_irq_chip; - /* * Returns true iff chip is something that we could call * pnv_opal_pci_msi_eoi for. */ bool is_pnv_opal_msi(struct irq_chip *chip) { - return chip == &pnv_pci_msi_irq_chip; + return chip && chip->name && str_has_prefix(chip->name, "PNV-"); } EXPORT_SYMBOL_GPL(is_pnv_opal_msi); @@ -1728,7 +1726,7 @@ static const struct msi_parent_ops pnv_msi_parent_ops = { .chip_flags = MSI_CHIP_FLAG_SET_EOI, .bus_select_token = DOMAIN_BUS_NEXUS, .bus_select_mask = MATCH_PCI_MSI, - .prefix = "PNV-", + .prefix = "PNV-", /* Note: is_pnv_opal_msi() uses this */ .init_dev_msi_info = pnv_init_dev_msi_info, }; diff --git a/arch/powerpc/platforms/ps3/repository.c b/arch/powerpc/platforms/ps3/repository.c index b8c030eab1384e..0cc755ac3e7f5d 100644 --- a/arch/powerpc/platforms/ps3/repository.c +++ b/arch/powerpc/platforms/ps3/repository.c @@ -6,6 +6,8 @@ * Copyright 2006 Sony Corp. */ +#include + #include #include "platform.h" @@ -74,8 +76,9 @@ static void _dump_node(unsigned int lpar_id, u64 n1, u64 n2, u64 n3, u64 n4, static u64 make_first_field(const char *text, u64 index) { u64 n = 0; + size_t len = min(strlen(text), sizeof(n)); - memcpy((char *)&n, text, strnlen(text, sizeof(n))); + memcpy(&n, text, len); return PS3_VENDOR_ID_NONE + (n >> 32) + index; } diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c index b2df7f72241a5f..7cc5a6a5c02062 100644 --- a/arch/riscv/kernel/process.c +++ b/arch/riscv/kernel/process.c @@ -349,10 +349,8 @@ long set_tagged_addr_ctrl(struct task_struct *task, unsigned long arg) if (arg & PR_TAGGED_ADDR_ENABLE && (tagged_addr_disabled || !pmlen)) return -EINVAL; - if (!(arg & PR_TAGGED_ADDR_ENABLE)) { + if (!(arg & PR_TAGGED_ADDR_ENABLE)) pmlen = PMLEN_0; - pmm = ENVCFG_PMM_PMLEN_0; - } if (mmap_write_lock_killable(mm)) return -EINTR; diff --git a/arch/riscv/kernel/sys_hwprobe.c b/arch/riscv/kernel/sys_hwprobe.c index caf6762427c87e..d2bb70fed8b9f7 100644 --- a/arch/riscv/kernel/sys_hwprobe.c +++ b/arch/riscv/kernel/sys_hwprobe.c @@ -295,6 +295,8 @@ static u64 hwprobe_vec_misaligned(const struct cpumask *cpus) static void hwprobe_one_pair(struct riscv_hwprobe *pair, const struct cpumask *cpus) { + pair->value = 0; + switch (pair->key) { case RISCV_HWPROBE_KEY_MVENDORID: case RISCV_HWPROBE_KEY_MARCHID: @@ -329,17 +331,14 @@ static void hwprobe_one_pair(struct riscv_hwprobe *pair, break; case RISCV_HWPROBE_KEY_ZICBOZ_BLOCK_SIZE: - pair->value = 0; if (hwprobe_ext0_has(cpus, RISCV_HWPROBE_EXT_ZICBOZ)) pair->value = riscv_cboz_block_size; break; case RISCV_HWPROBE_KEY_ZICBOM_BLOCK_SIZE: - pair->value = 0; if (hwprobe_ext0_has(cpus, RISCV_HWPROBE_EXT_ZICBOM)) pair->value = riscv_cbom_block_size; break; case RISCV_HWPROBE_KEY_ZICBOP_BLOCK_SIZE: - pair->value = 0; if (hwprobe_ext0_has(cpus, RISCV_HWPROBE_EXT_ZICBOP)) pair->value = riscv_cbop_block_size; break; diff --git a/arch/s390/boot/ipl_parm.c b/arch/s390/boot/ipl_parm.c index 6bc950b92be766..59eabf4a2de050 100644 --- a/arch/s390/boot/ipl_parm.c +++ b/arch/s390/boot/ipl_parm.c @@ -23,6 +23,7 @@ struct parmarea parmarea __section(".parmarea") = { }; char __bootdata(early_command_line)[COMMAND_LINE_SIZE]; +static char command_line_buf[COMMAND_LINE_SIZE]; unsigned int __bootdata_preserved(zlib_dfltcc_support) = ZLIB_DFLTCC_FULL; struct ipl_parameter_block __bootdata_preserved(ipl_block); @@ -135,31 +136,29 @@ out: static void append_ipl_block_parm(void) { - char *parm, *delim; - size_t len, rc = 0; + size_t len, extra = 0; + char *delim; len = strlen(early_command_line); - - delim = early_command_line + len; /* '\0' character position */ - parm = early_command_line + len + 1; /* append right after '\0' */ + delim = early_command_line + len; /* '\0' character position */ switch (ipl_block.pb0_hdr.pbt) { case IPL_PBT_CCW: - rc = ipl_block_get_ascii_vmparm( - parm, COMMAND_LINE_SIZE - len - 1, &ipl_block); + extra = ipl_block_get_ascii_vmparm(command_line_buf, sizeof(command_line_buf), &ipl_block); break; case IPL_PBT_FCP: case IPL_PBT_NVME: case IPL_PBT_ECKD: - rc = ipl_block_get_ascii_scpdata( - parm, COMMAND_LINE_SIZE - len - 1, &ipl_block); + extra = ipl_block_get_ascii_scpdata(command_line_buf, sizeof(command_line_buf), &ipl_block); break; } - if (rc) { - if (*parm == '=') - memmove(early_command_line, parm + 1, rc); - else + if (extra) { + if (command_line_buf[0] == '=') { + memmove(early_command_line, command_line_buf + 1, extra); + } else if (len < COMMAND_LINE_SIZE - 2) { *delim = ' '; /* replace '\0' with space */ + sized_strscpy(delim + 1, command_line_buf, COMMAND_LINE_SIZE - len - 1); + } } } @@ -245,7 +244,6 @@ static void modify_fac_list(char *str) check_cleared_facilities(); } -static char command_line_buf[COMMAND_LINE_SIZE]; void parse_boot_command_line(void) { char *param, *val; diff --git a/arch/s390/boot/physmem_info.c b/arch/s390/boot/physmem_info.c index 1f2ca5435838e8..0ebb2174713f22 100644 --- a/arch/s390/boot/physmem_info.c +++ b/arch/s390/boot/physmem_info.c @@ -141,7 +141,7 @@ static int tprot(unsigned long addr) static unsigned long search_mem_end(void) { - unsigned long range = 1 << (MAX_PHYSMEM_BITS - 20); /* in 1MB blocks */ + unsigned long range = 1UL << (MAX_PHYSMEM_BITS - 20); /* in 1MB blocks */ unsigned long offset = 0; unsigned long pivot; diff --git a/arch/s390/crypto/aes_s390.c b/arch/s390/crypto/aes_s390.c index 62edc66d54788e..0be6fa779d2ccb 100644 --- a/arch/s390/crypto/aes_s390.c +++ b/arch/s390/crypto/aes_s390.c @@ -26,14 +26,14 @@ #include #include #include -#include #include +#include #include #include #include static u8 *ctrblk; -static DEFINE_MUTEX(ctrblk_lock); +static DEFINE_SEMAPHORE(ctrblk_sem, 1); static cpacf_mask_t km_functions, kmc_functions, kmctr_functions, kma_functions; @@ -129,7 +129,7 @@ static int ecb_aes_crypt(struct skcipher_request *req, unsigned long modifier) return fallback_skcipher_crypt(sctx, req, modifier); ret = skcipher_walk_virt(&walk, req, false); - while ((nbytes = walk.nbytes) != 0) { + while (!ret && ((nbytes = walk.nbytes) != 0)) { /* only use complete blocks */ n = nbytes & ~(AES_BLOCK_SIZE - 1); cpacf_km(sctx->fc | modifier, sctx->key, @@ -233,7 +233,7 @@ static int cbc_aes_crypt(struct skcipher_request *req, unsigned long modifier) return ret; memcpy(param.iv, walk.iv, AES_BLOCK_SIZE); memcpy(param.key, sctx->key, sctx->key_len); - while ((nbytes = walk.nbytes) != 0) { + while (!ret && ((nbytes = walk.nbytes) != 0)) { /* only use complete blocks */ n = nbytes & ~(AES_BLOCK_SIZE - 1); cpacf_kmc(sctx->fc | modifier, ¶m, @@ -359,7 +359,7 @@ static int xts_aes_crypt(struct skcipher_request *req, unsigned long modifier) memcpy(xts_param.key + offset, xts_ctx->key, xts_ctx->key_len); memcpy(xts_param.init, pcc_param.xts, 16); - while ((nbytes = walk.nbytes) != 0) { + while (!ret && ((nbytes = walk.nbytes) != 0)) { /* only use complete blocks */ n = nbytes & ~(AES_BLOCK_SIZE - 1); cpacf_km(xts_ctx->fc | modifier, xts_param.key + offset, @@ -487,7 +487,7 @@ static int fullxts_aes_crypt(struct skcipher_request *req, unsigned long modifi memcpy(fxts_param.tweak, req->iv, AES_BLOCK_SIZE); fxts_param.nap[0] = 0x01; /* initial alpha power (1, little-endian) */ - while ((nbytes = walk.nbytes) != 0) { + while (!ret && ((nbytes = walk.nbytes) != 0)) { /* only use complete blocks */ n = nbytes & ~(AES_BLOCK_SIZE - 1); cpacf_km(xts_ctx->fc | modifier, fxts_param.key + offset, @@ -562,48 +562,64 @@ static unsigned int __ctrblk_init(u8 *ctrptr, u8 *iv, unsigned int nbytes) return n; } +static int __ctr_aes_crypt(struct s390_aes_ctx *sctx, + struct skcipher_walk *walk, bool locked) +{ + unsigned int n, nbytes; + int ret = 0; + u8 *ctrptr; + + while (!ret && ((nbytes = walk->nbytes) >= AES_BLOCK_SIZE)) { + n = AES_BLOCK_SIZE; + if (nbytes >= 2 * AES_BLOCK_SIZE && locked) + n = __ctrblk_init(ctrblk, walk->iv, nbytes); + ctrptr = (n > AES_BLOCK_SIZE) ? ctrblk : walk->iv; + cpacf_kmctr(sctx->fc, sctx->key, walk->dst.virt.addr, + walk->src.virt.addr, n, ctrptr); + if (ctrptr == ctrblk) + memcpy(walk->iv, ctrptr + n - AES_BLOCK_SIZE, + AES_BLOCK_SIZE); + crypto_inc(walk->iv, AES_BLOCK_SIZE); + ret = skcipher_walk_done(walk, nbytes - n); + } + + return ret; +} + static int ctr_aes_crypt(struct skcipher_request *req) { struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); struct s390_aes_ctx *sctx = crypto_skcipher_ctx(tfm); - u8 buf[AES_BLOCK_SIZE], *ctrptr; struct skcipher_walk walk; - unsigned int n, nbytes; - int ret, locked; + u8 buf[AES_BLOCK_SIZE]; + int ret; if (unlikely(!sctx->fc)) return fallback_skcipher_crypt(sctx, req, 0); - locked = mutex_trylock(&ctrblk_lock); - ret = skcipher_walk_virt(&walk, req, false); - while ((nbytes = walk.nbytes) >= AES_BLOCK_SIZE) { - n = AES_BLOCK_SIZE; + if (ret) + return ret; - if (nbytes >= 2*AES_BLOCK_SIZE && locked) - n = __ctrblk_init(ctrblk, walk.iv, nbytes); - ctrptr = (n > AES_BLOCK_SIZE) ? ctrblk : walk.iv; - cpacf_kmctr(sctx->fc, sctx->key, walk.dst.virt.addr, - walk.src.virt.addr, n, ctrptr); - if (ctrptr == ctrblk) - memcpy(walk.iv, ctrptr + n - AES_BLOCK_SIZE, - AES_BLOCK_SIZE); - crypto_inc(walk.iv, AES_BLOCK_SIZE); - ret = skcipher_walk_done(&walk, nbytes - n); + if (down_trylock(&ctrblk_sem) == 0) { + ret = __ctr_aes_crypt(sctx, &walk, true); + up(&ctrblk_sem); + } else { + ret = __ctr_aes_crypt(sctx, &walk, false); } - if (locked) - mutex_unlock(&ctrblk_lock); + /* * final block may be < AES_BLOCK_SIZE, copy only nbytes */ - if (nbytes) { + if (!ret && walk.nbytes > 0) { memset(buf, 0, AES_BLOCK_SIZE); - memcpy(buf, walk.src.virt.addr, nbytes); + memcpy(buf, walk.src.virt.addr, walk.nbytes); cpacf_kmctr(sctx->fc, sctx->key, buf, buf, AES_BLOCK_SIZE, walk.iv); - memcpy(walk.dst.virt.addr, buf, nbytes); + memcpy(walk.dst.virt.addr, buf, walk.nbytes); crypto_inc(walk.iv, AES_BLOCK_SIZE); ret = skcipher_walk_done(&walk, 0); + memzero_explicit(buf, sizeof(buf)); } return ret; @@ -895,10 +911,14 @@ static int gcm_aes_crypt(struct aead_request *req, unsigned int flags) gw_in.ptr, aad_bytes); n = aad_bytes + pc_bytes; - if (gcm_in_walk_done(&gw_in, n) != n) - return -ENOMEM; - if (gcm_out_walk_done(&gw_out, n) != n) - return -ENOMEM; + if (gcm_in_walk_done(&gw_in, n) != n) { + ret = -ENOMEM; + goto out; + } + if (gcm_out_walk_done(&gw_out, n) != n) { + ret = -ENOMEM; + goto out; + } aadlen -= aad_bytes; pclen -= pc_bytes; } while (aadlen + pclen > 0); @@ -910,7 +930,10 @@ static int gcm_aes_crypt(struct aead_request *req, unsigned int flags) } else scatterwalk_map_and_copy(param.t, req->dst, len, taglen, 1); +out: memzero_explicit(¶m, sizeof(param)); + memzero_explicit(gw_in.buf, sizeof(gw_in.buf)); + memzero_explicit(gw_out.buf, sizeof(gw_out.buf)); return ret; } diff --git a/arch/s390/crypto/paes_s390.c b/arch/s390/crypto/paes_s390.c index 8cfe6166c193c3..240c7b87a048b3 100644 --- a/arch/s390/crypto/paes_s390.c +++ b/arch/s390/crypto/paes_s390.c @@ -220,6 +220,10 @@ static inline int convert_key(const u8 *key, unsigned int keylen, xflags); } + /* But finally map -EBUSY to -EIO to indicate an IO failure */ + if (rc == -EBUSY) + rc = -EIO; + out: pr_debug("rc=%d\n", rc); return rc; @@ -568,7 +572,7 @@ static int ecb_paes_do_one_request(struct crypto_engine *engine, void *areq) atomic_dec(&ctx->via_engine_ctr); crypto_finalize_skcipher_request(engine, req, rc); local_bh_enable(); - return rc; + return 0; } static struct skcipher_engine_alg ecb_paes_alg = { @@ -576,6 +580,7 @@ static struct skcipher_engine_alg ecb_paes_alg = { .base.cra_name = "ecb(paes)", .base.cra_driver_name = "ecb-paes-s390", .base.cra_priority = 401, /* combo: aes + ecb + 1 */ + .base.cra_flags = CRYPTO_ALG_ASYNC | CRYPTO_ALG_NO_FALLBACK, .base.cra_blocksize = AES_BLOCK_SIZE, .base.cra_ctxsize = sizeof(struct s390_paes_ctx), .base.cra_module = THIS_MODULE, @@ -834,7 +839,7 @@ static int cbc_paes_do_one_request(struct crypto_engine *engine, void *areq) atomic_dec(&ctx->via_engine_ctr); crypto_finalize_skcipher_request(engine, req, rc); local_bh_enable(); - return rc; + return 0; } static struct skcipher_engine_alg cbc_paes_alg = { @@ -842,6 +847,7 @@ static struct skcipher_engine_alg cbc_paes_alg = { .base.cra_name = "cbc(paes)", .base.cra_driver_name = "cbc-paes-s390", .base.cra_priority = 402, /* cbc-paes-s390 + 1 */ + .base.cra_flags = CRYPTO_ALG_ASYNC | CRYPTO_ALG_NO_FALLBACK, .base.cra_blocksize = AES_BLOCK_SIZE, .base.cra_ctxsize = sizeof(struct s390_paes_ctx), .base.cra_module = THIS_MODULE, @@ -1034,6 +1040,7 @@ static int ctr_paes_do_crypt(struct s390_paes_ctx *ctx, } out: + memzero_explicit(buf, sizeof(buf)); pr_debug("rc=%d\n", rc); return rc; } @@ -1142,7 +1149,7 @@ static int ctr_paes_do_one_request(struct crypto_engine *engine, void *areq) atomic_dec(&ctx->via_engine_ctr); crypto_finalize_skcipher_request(engine, req, rc); local_bh_enable(); - return rc; + return 0; } static struct skcipher_engine_alg ctr_paes_alg = { @@ -1150,6 +1157,7 @@ static struct skcipher_engine_alg ctr_paes_alg = { .base.cra_name = "ctr(paes)", .base.cra_driver_name = "ctr-paes-s390", .base.cra_priority = 402, /* ecb-paes-s390 + 1 */ + .base.cra_flags = CRYPTO_ALG_ASYNC | CRYPTO_ALG_NO_FALLBACK, .base.cra_blocksize = 1, .base.cra_ctxsize = sizeof(struct s390_paes_ctx), .base.cra_module = THIS_MODULE, @@ -1364,7 +1372,7 @@ static inline int __xts_2keys_prep_param(struct s390_pxts_ctx *ctx, memcpy(param->init, pcc_param.xts, 16); } - memzero_explicit(pcc_param.key, sizeof(pcc_param.key)); + memzero_explicit(&pcc_param, sizeof(pcc_param)); return rc; } @@ -1585,7 +1593,7 @@ static int xts_paes_do_one_request(struct crypto_engine *engine, void *areq) atomic_dec(&ctx->via_engine_ctr); crypto_finalize_skcipher_request(engine, req, rc); local_bh_enable(); - return rc; + return 0; } static struct skcipher_engine_alg xts_paes_alg = { @@ -1593,6 +1601,7 @@ static struct skcipher_engine_alg xts_paes_alg = { .base.cra_name = "xts(paes)", .base.cra_driver_name = "xts-paes-s390", .base.cra_priority = 402, /* ecb-paes-s390 + 1 */ + .base.cra_flags = CRYPTO_ALG_ASYNC | CRYPTO_ALG_NO_FALLBACK, .base.cra_blocksize = AES_BLOCK_SIZE, .base.cra_ctxsize = sizeof(struct s390_pxts_ctx), .base.cra_module = THIS_MODULE, diff --git a/arch/s390/crypto/phmac_s390.c b/arch/s390/crypto/phmac_s390.c index 03ca33ffe6ccfa..44817c3d25cf2e 100644 --- a/arch/s390/crypto/phmac_s390.c +++ b/arch/s390/crypto/phmac_s390.c @@ -62,8 +62,10 @@ static inline int hwh_prepare(struct ahash_request *req, */ static inline int hwh_advance(struct hash_walk_helper *hwh, int n) { - if (n < 0) + if (n < 0) { + hwh->walkbytes = n; return crypto_hash_walk_done(&hwh->walk, n); + } hwh->walkbytes -= n; hwh->walkaddr += n; @@ -339,6 +341,10 @@ static inline int convert_key(const u8 *key, unsigned int keylen, xflags); } + /* But finally map -EBUSY to -EIO to indicate an IO failure */ + if (rc == -EBUSY) + rc = -EIO; + out: pr_debug("rc=%d\n", rc); return rc; @@ -606,6 +612,7 @@ static int phmac_update(struct ahash_request *req) struct phmac_tfm_ctx *tfm_ctx = crypto_ahash_ctx(tfm); struct kmac_sha2_ctx *kmac_ctx = &req_ctx->kmac_ctx; struct hash_walk_helper *hwh = &req_ctx->hwh; + bool cleanup = true; int rc; /* prep the walk in the request context */ @@ -629,12 +636,15 @@ static int phmac_update(struct ahash_request *req) req_ctx->async_op = OP_UPDATE; atomic_inc(&tfm_ctx->via_engine_ctr); rc = crypto_transfer_hash_request_to_engine(phmac_crypto_engine, req); - if (rc != -EINPROGRESS) + if (rc == -EINPROGRESS || rc == -EBUSY) + cleanup = false; + else atomic_dec(&tfm_ctx->via_engine_ctr); } - if (rc != -EINPROGRESS) { - hwh_advance(hwh, rc); + if (cleanup) { + if (hwh->walkbytes > 0) + hwh_advance(hwh, rc); memzero_explicit(kmac_ctx, sizeof(*kmac_ctx)); } @@ -649,6 +659,7 @@ static int phmac_final(struct ahash_request *req) struct crypto_ahash *tfm = crypto_ahash_reqtfm(req); struct phmac_tfm_ctx *tfm_ctx = crypto_ahash_ctx(tfm); struct kmac_sha2_ctx *kmac_ctx = &req_ctx->kmac_ctx; + bool cleanup = true; int rc = 0; /* Try synchronous operation if no active engine usage */ @@ -667,12 +678,14 @@ static int phmac_final(struct ahash_request *req) req_ctx->async_op = OP_FINAL; atomic_inc(&tfm_ctx->via_engine_ctr); rc = crypto_transfer_hash_request_to_engine(phmac_crypto_engine, req); - if (rc != -EINPROGRESS) + if (rc == -EINPROGRESS || rc == -EBUSY) + cleanup = false; + else atomic_dec(&tfm_ctx->via_engine_ctr); } out: - if (rc != -EINPROGRESS) + if (cleanup) memzero_explicit(kmac_ctx, sizeof(*kmac_ctx)); pr_debug("rc=%d\n", rc); return rc; @@ -685,6 +698,7 @@ static int phmac_finup(struct ahash_request *req) struct phmac_tfm_ctx *tfm_ctx = crypto_ahash_ctx(tfm); struct kmac_sha2_ctx *kmac_ctx = &req_ctx->kmac_ctx; struct hash_walk_helper *hwh = &req_ctx->hwh; + bool cleanup = true; int rc; /* prep the walk in the request context */ @@ -716,15 +730,17 @@ static int phmac_finup(struct ahash_request *req) /* req->async_op has been set to either OP_FINUP or OP_FINAL */ atomic_inc(&tfm_ctx->via_engine_ctr); rc = crypto_transfer_hash_request_to_engine(phmac_crypto_engine, req); - if (rc != -EINPROGRESS) + if (rc == -EINPROGRESS || rc == -EBUSY) + cleanup = false; + else atomic_dec(&tfm_ctx->via_engine_ctr); } - if (rc != -EINPROGRESS) + if (cleanup && hwh->walkbytes > 0) hwh_advance(hwh, rc); out: - if (rc != -EINPROGRESS) + if (cleanup) memzero_explicit(kmac_ctx, sizeof(*kmac_ctx)); pr_debug("rc=%d\n", rc); return rc; @@ -933,7 +949,7 @@ out: atomic_dec(&tfm_ctx->via_engine_ctr); crypto_finalize_hash_request(engine, req, rc); local_bh_enable(); - return rc; + return 0; } #define S390_ASYNC_PHMAC_ALG(x) \ diff --git a/arch/s390/include/asm/pai.h b/arch/s390/include/asm/pai.h index 534d0320e2aa09..a3456a36aaa729 100644 --- a/arch/s390/include/asm/pai.h +++ b/arch/s390/include/asm/pai.h @@ -76,7 +76,6 @@ static __always_inline void pai_kernel_exit(struct pt_regs *regs) } #define PAI_SAVE_AREA(x) ((x)->hw.event_base) -#define PAI_CPU_MASK(x) ((x)->hw.addr_filters) #define PAI_PMU_IDX(x) ((x)->hw.last_tag) #define PAI_SWLIST(x) (&(x)->hw.tp_list) diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c index 14d2b58ad09304..e06abf1dbc218c 100644 --- a/arch/s390/kernel/debug.c +++ b/arch/s390/kernel/debug.c @@ -1074,9 +1074,6 @@ static void _debug_set_level(debug_info_t *id, int new_level) { unsigned long flags; - if (!id) - return; - if (new_level == DEBUG_OFF_LEVEL) { pr_info("%s: switched off\n", id->name); } else if ((new_level > DEBUG_MAX_LEVEL) || (new_level < 0)) { @@ -1101,6 +1098,9 @@ static void _debug_set_level(debug_info_t *id, int new_level) */ void debug_set_level(debug_info_t *id, int new_level) { + if (!id) + return; + /* Level specified via kernel parameter takes precedence */ debug_get_param(id->name, &new_level, NULL); diff --git a/arch/s390/kernel/diag/diag324.c b/arch/s390/kernel/diag/diag324.c index fe325c2a2d0dca..3eec0cc8fb9e0e 100644 --- a/arch/s390/kernel/diag/diag324.c +++ b/arch/s390/kernel/diag/diag324.c @@ -182,8 +182,7 @@ long diag324_pibbuf(unsigned long arg) goto out; rc = copy_to_user((void __user *)address, data->pib, data->pib->len); rc |= put_user(data->sequence, &udata->sequence); - if (rc) - rc = -EFAULT; + rc = rc ? -EFAULT : data->rc; out: mutex_unlock(&pibmutex); return rc; diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c index 3c346b02ceb953..68fdd5616dfe1b 100644 --- a/arch/s390/kernel/ipl.c +++ b/arch/s390/kernel/ipl.c @@ -1157,6 +1157,8 @@ static struct attribute_group reipl_nss_attr_group = { void set_os_info_reipl_block(void) { + if (!reipl_block_actual) + return; os_info_entry_add_data(OS_INFO_REIPL_BLOCK, reipl_block_actual, reipl_block_actual->hdr.len); } @@ -1927,7 +1929,8 @@ static struct shutdown_action __refdata dump_action = { static void dump_reipl_run(struct shutdown_trigger *trigger) { struct lowcore *abs_lc; - unsigned int csum; + unsigned long ipib = 0; + unsigned int csum = 0; /* * Set REIPL_CLEAR flag in os_info flags entry indicating @@ -1943,9 +1946,12 @@ static void dump_reipl_run(struct shutdown_trigger *trigger) reipl_type == IPL_TYPE_UNKNOWN) os_info_flags |= OS_INFO_FLAG_REIPL_CLEAR; os_info_entry_add_data(OS_INFO_FLAGS_ENTRY, &os_info_flags, sizeof(os_info_flags)); - csum = (__force unsigned int)cksm(reipl_block_actual, reipl_block_actual->hdr.len, 0); + if (reipl_block_actual) { + ipib = __pa(reipl_block_actual); + csum = (__force unsigned int)cksm(reipl_block_actual, reipl_block_actual->hdr.len, 0); + } abs_lc = get_abs_lowcore(); - abs_lc->ipib = __pa(reipl_block_actual); + abs_lc->ipib = ipib; abs_lc->ipib_checksum = csum; put_abs_lowcore(abs_lc); dump_run(trigger); diff --git a/arch/s390/kernel/perf_pai.c b/arch/s390/kernel/perf_pai.c index cdb8006220ca06..25228b46cdf4e2 100644 --- a/arch/s390/kernel/perf_pai.c +++ b/arch/s390/kernel/perf_pai.c @@ -67,6 +67,7 @@ struct pai_mapptr { static struct pai_root { /* Anchor to per CPU data */ refcount_t refcnt; /* Overall active events */ + atomic_t tskctx; /* Overall per-task events */ struct pai_mapptr __percpu *mapptr; } pai_root[PAI_PMU_MAX]; @@ -93,14 +94,15 @@ struct pai_pmu { /* Define PAI PMU characteristics */ static struct pai_pmu pai_pmu[]; /* Forward declaration */ /* Free per CPU data when the last event is removed. */ -static void pai_root_free(int idx) +static void pai_root_free(int idx, int tasks) { - if (refcount_dec_and_test(&pai_root[idx].refcnt)) { + if (refcount_sub_and_test(tasks, &pai_root[idx].refcnt)) { free_percpu(pai_root[idx].mapptr); pai_root[idx].mapptr = NULL; } - debug_sprintf_event(paidbg, 5, "%s root[%d].refcount %d\n", __func__, - idx, refcount_read(&pai_root[idx].refcnt)); + debug_sprintf_event(paidbg, 5, "%s root[%d].refcount %d tskctx %d\n", + __func__, idx, refcount_read(&pai_root[idx].refcnt), + atomic_read(&pai_root[idx].tskctx)); } /* @@ -137,40 +139,54 @@ static void pai_free(struct pai_mapptr *mp) mp->mapptr = NULL; } -/* Adjust usage counters and remove allocated memory when all users are - * gone. - */ -static void pai_event_destroy_cpu(struct perf_event *event, int cpu) +/* Called under mutex_lock */ +static void pai_event_destroy_cpu(int idx, int cpu, bool hotplug) { - int idx = PAI_PMU_IDX(event); - struct pai_mapptr *mp = per_cpu_ptr(pai_root[idx].mapptr, cpu); - struct pai_map *cpump = mp->mapptr; + struct pai_mapptr *mp; + struct pai_map *cpump; + int tasks = 1; - mutex_lock(&pai_reserve_mutex); - debug_sprintf_event(paidbg, 5, "%s event %#llx idx %d cpu %d users %d " - "refcnt %u\n", __func__, event->attr.config, idx, - event->cpu, cpump->active_events, - refcount_read(&cpump->refcnt)); - if (refcount_dec_and_test(&cpump->refcnt)) + /* Check reference count and return when all gone. + * 1. An event is installed on online CPU X. + * 2. CPU x is offlined and the per-CPU data is removed. + * 3. Event is destroyed via close system call. + */ + if (!refcount_read(&pai_root[idx].refcnt)) + return; /* No events at all */ + mp = per_cpu_ptr(pai_root[idx].mapptr, cpu); + if (!mp || !mp->mapptr) /* No events on that CPU */ + return; + + /* When hotplug is true, invocation is from CPU hotplug callback. + * Delete per-CPU resource and adjust refcnt when per-task events + * are currently active. This can be more than one. + * In this case adjust counters. + */ + if (hotplug) + tasks = atomic_read(&pai_root[idx].tskctx); + + cpump = mp->mapptr; + if (refcount_sub_and_test(tasks, &cpump->refcnt)) pai_free(mp); - pai_root_free(idx); - mutex_unlock(&pai_reserve_mutex); + pai_root_free(idx, tasks); } static void pai_event_destroy(struct perf_event *event) { - int cpu; + int cpu = 0, idx = PAI_PMU_IDX(event); free_page(PAI_SAVE_AREA(event)); + cpus_read_lock(); + mutex_lock(&pai_reserve_mutex); if (event->cpu == -1) { - struct cpumask *mask = PAI_CPU_MASK(event); - - for_each_cpu(cpu, mask) - pai_event_destroy_cpu(event, cpu); - kfree(mask); + atomic_dec(&pai_root[idx].tskctx); + for_each_online_cpu(cpu) + pai_event_destroy_cpu(idx, cpu, false); } else { - pai_event_destroy_cpu(event, event->cpu); + pai_event_destroy_cpu(idx, event->cpu, false); } + mutex_unlock(&pai_reserve_mutex); + cpus_read_unlock(); } static void paicrypt_event_destroy(struct perf_event *event) @@ -234,25 +250,30 @@ static u64 paicrypt_getall(struct perf_event *event) return sum; } -/* Check concurrent access of counting and sampling for crypto events. - * This function is called in process context and it is save to block. - * When the event initialization functions fails, no other call back will - * be invoked. - * - * Allocate the memory for the event. - */ -static int pai_alloc_cpu(struct perf_event *event, int cpu) +/* Called under mutex_lock */ +static int pai_alloc_cpu(int idx, int cpu, bool hotplug) { - int rc, idx = PAI_PMU_IDX(event); struct pai_map *cpump = NULL; bool need_paiext_cb = false; struct pai_mapptr *mp; + int tasks = 1, rc = 0; + + /* When hotplug is true, invocation is from CPU hotplug callback. + * Allocate per-CPU resource when per-task events are currently active. + * This can be more than one. In this case adjust all reference + * counters. Otherwise return, this ensures memory is only allocated + * when needed. + */ + if (hotplug) { + tasks = atomic_read(&pai_root[idx].tskctx); + if (!tasks) + goto out; + } - mutex_lock(&pai_reserve_mutex); /* Allocate root node */ rc = pai_root_alloc(idx); if (rc) - goto unlock; + goto out; /* Allocate node for this event */ mp = per_cpu_ptr(pai_root[idx].mapptr, cpu); @@ -296,28 +317,45 @@ static int pai_alloc_cpu(struct perf_event *event, int cpu) goto undo; } INIT_LIST_HEAD(&cpump->syswide_list); - refcount_set(&cpump->refcnt, 1); + refcount_set(&cpump->refcnt, tasks); rc = 0; } else { - refcount_inc(&cpump->refcnt); + refcount_add(tasks, &cpump->refcnt); } + /* If tasks is greater than 1, we are called from CPU hotplug path + * and need to adjust the pai_root[idx].refcnt by the number of + * per-process events. Function pai_root_alloc(idx) already + * incremented by one. Adjust for the rest. + */ + if (tasks > 1) + refcount_add(tasks - 1, &pai_root[idx].refcnt); undo: if (rc) { /* Error in allocation of event, decrement anchor. Since * the event in not created, its destroy() function is never * invoked. Adjust the reference counter for the anchor. + * The failure happened in the case of variable + * cpump == NULL branch above. The pai_root[XXX].refcnt has + * been incremented by one. Then the per-CPU allocation + * failed, so decrement it by one, regardless of tasks. */ - pai_root_free(idx); + pai_root_free(idx, 1); } -unlock: - mutex_unlock(&pai_reserve_mutex); +out: /* If rc is non-zero, no increment of counter/sampler was done. */ return rc; } +/* Check concurrent access of counting and sampling for PAI events. + * This function is called in process context and it is safe to block. + * When the event initialization functions fails, no other call back will + * be invoked. + * Called under mutex_lock. + */ static int pai_alloc(struct perf_event *event) { + int idx = PAI_PMU_IDX(event); struct cpumask *maskptr; int cpu, rc = -ENOMEM; @@ -326,24 +364,20 @@ static int pai_alloc(struct perf_event *event) goto out; for_each_online_cpu(cpu) { - rc = pai_alloc_cpu(event, cpu); + rc = pai_alloc_cpu(idx, cpu, false); if (rc) { for_each_cpu(cpu, maskptr) - pai_event_destroy_cpu(event, cpu); - kfree(maskptr); - goto out; + pai_event_destroy_cpu(idx, cpu, false); + goto undo; } cpumask_set_cpu(cpu, maskptr); } - /* - * On error all cpumask are freed and all events have been destroyed. - * Save of which CPUs data structures have been allocated for. - * Release them in pai_event_destroy call back function - * for this event. - */ - PAI_CPU_MASK(event) = maskptr; rc = 0; + /* Trace per-task events for CPU hotplug. */ + atomic_inc(&pai_root[idx].tskctx); +undo: + kfree(maskptr); out: return rc; } @@ -391,10 +425,14 @@ static int pai_event_init(struct perf_event *event, int idx) } } + cpus_read_lock(); + mutex_lock(&pai_reserve_mutex); if (event->cpu >= 0) - rc = pai_alloc_cpu(event, event->cpu); + rc = pai_alloc_cpu(idx, event->cpu, false); else rc = pai_alloc(event); + mutex_unlock(&pai_reserve_mutex); + cpus_read_unlock(); if (rc) { free_page(PAI_SAVE_AREA(event)); goto out; @@ -1218,23 +1256,61 @@ static int __init paipmu_setup(void) return install_ok; } +static int pai_online_cpu(unsigned int cpu) +{ + int rc; + + mutex_lock(&pai_reserve_mutex); + rc = pai_alloc_cpu(PAI_PMU_CRYPTO, cpu, true); + if (rc) + goto out; + rc = pai_alloc_cpu(PAI_PMU_EXT, cpu, true); + if (rc) + pai_event_destroy_cpu(PAI_PMU_CRYPTO, cpu, true); +out: + mutex_unlock(&pai_reserve_mutex); + return rc; +} + +static int pai_offline_cpu(unsigned int cpu) +{ + mutex_lock(&pai_reserve_mutex); + pai_event_destroy_cpu(PAI_PMU_CRYPTO, cpu, true); + pai_event_destroy_cpu(PAI_PMU_EXT, cpu, true); + mutex_unlock(&pai_reserve_mutex); + return 0; +} + static int __init pai_init(void) { + int state, rc; + /* Setup s390dbf facility */ - paidbg = debug_register("pai", 32, 256, 128); + paidbg = debug_register("pai", 1, 1, 128); if (!paidbg) { pr_err("Registration of s390dbf pai failed\n"); return -ENOMEM; } debug_register_view(paidbg, &debug_sprintf_view); - if (!paipmu_setup()) { - /* No PMU registration, no need for debug buffer */ - debug_unregister_view(paidbg, &debug_sprintf_view); - debug_unregister(paidbg); - return -ENODEV; - } + /* CPUHP_BP_PREPARE_DYN --> before CPU is brought online */ + state = cpuhp_setup_state(CPUHP_BP_PREPARE_DYN, "perf/pai:prepare", + pai_online_cpu, pai_offline_cpu); + rc = state < 0 ? state : 0; + if (rc < 0) + goto out_debug; + + rc = -ENODEV; + if (!paipmu_setup()) + goto out_cpuhp; return 0; + +out_cpuhp: + cpuhp_remove_state(state); +out_debug: + debug_unregister_view(paidbg, &debug_sprintf_view); + debug_unregister(paidbg); + return rc; } device_initcall(pai_init); diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c index d804e1140c2e98..efcbf406f03e73 100644 --- a/arch/s390/kernel/vtime.c +++ b/arch/s390/kernel/vtime.c @@ -32,7 +32,7 @@ static atomic64_t virt_timer_elapsed; DEFINE_PER_CPU(u64, mt_cycles[8]); static DEFINE_PER_CPU(u64, mt_scaling_mult) = { 1 }; static DEFINE_PER_CPU(u64, mt_scaling_div) = { 1 }; -static DEFINE_PER_CPU(u64, mt_scaling_jiffies); +static DEFINE_PER_CPU(unsigned long, mt_scaling_jiffies); static inline void set_vtimer(u64 expires) { @@ -81,7 +81,7 @@ static void update_mt_scaling(void) memcpy(cycles_old, cycles_new, sizeof(u64) * (smp_cpu_mtid + 1)); } - __this_cpu_write(mt_scaling_jiffies, jiffies_64); + __this_cpu_write(mt_scaling_jiffies, jiffies); } static inline u64 update_tsk_timer(unsigned long *tsk_vtime, u64 new) @@ -144,7 +144,7 @@ static int do_account_vtime(struct task_struct *tsk) lc->system_timer += timer; /* Update MT utilization calculation */ - if (smp_cpu_mtid && time_after64(jiffies_64, __this_cpu_read(mt_scaling_jiffies))) + if (smp_cpu_mtid && time_after(jiffies, __this_cpu_read(mt_scaling_jiffies))) update_mt_scaling(); /* Calculate cputime delta */ diff --git a/arch/x86/crypto/aria-aesni-avx2-asm_64.S b/arch/x86/crypto/aria-aesni-avx2-asm_64.S index ed53d4f46bd7c3..fda8cb8a99a8a1 100644 --- a/arch/x86/crypto/aria-aesni-avx2-asm_64.S +++ b/arch/x86/crypto/aria-aesni-avx2-asm_64.S @@ -982,6 +982,7 @@ SYM_TYPED_FUNC_START(aria_aesni_avx2_encrypt_32way) %ymm8, %ymm9, %ymm10, %ymm11, %ymm12, %ymm13, %ymm14, %ymm15, %rax); + vzeroupper; FRAME_END RET; SYM_FUNC_END(aria_aesni_avx2_encrypt_32way) @@ -1007,6 +1008,7 @@ SYM_TYPED_FUNC_START(aria_aesni_avx2_decrypt_32way) %ymm8, %ymm9, %ymm10, %ymm11, %ymm12, %ymm13, %ymm14, %ymm15, %rax); + vzeroupper; FRAME_END RET; SYM_FUNC_END(aria_aesni_avx2_decrypt_32way) @@ -1209,6 +1211,7 @@ SYM_TYPED_FUNC_START(aria_aesni_avx2_ctr_crypt_32way) %ymm8, %ymm9, %ymm10, %ymm11, %ymm12, %ymm13, %ymm14, %ymm15, %r10); + vzeroupper; FRAME_END RET; SYM_FUNC_END(aria_aesni_avx2_ctr_crypt_32way) @@ -1359,6 +1362,7 @@ SYM_TYPED_FUNC_START(aria_aesni_avx2_gfni_encrypt_32way) %ymm8, %ymm9, %ymm10, %ymm11, %ymm12, %ymm13, %ymm14, %ymm15, %rax); + vzeroupper; FRAME_END RET; SYM_FUNC_END(aria_aesni_avx2_gfni_encrypt_32way) @@ -1384,6 +1388,7 @@ SYM_TYPED_FUNC_START(aria_aesni_avx2_gfni_decrypt_32way) %ymm8, %ymm9, %ymm10, %ymm11, %ymm12, %ymm13, %ymm14, %ymm15, %rax); + vzeroupper; FRAME_END RET; SYM_FUNC_END(aria_aesni_avx2_gfni_decrypt_32way) @@ -1428,6 +1433,7 @@ SYM_TYPED_FUNC_START(aria_aesni_avx2_gfni_ctr_crypt_32way) %ymm8, %ymm9, %ymm10, %ymm11, %ymm12, %ymm13, %ymm14, %ymm15, %r10); + vzeroupper; FRAME_END RET; SYM_FUNC_END(aria_aesni_avx2_gfni_ctr_crypt_32way) diff --git a/arch/x86/crypto/aria-gfni-avx512-asm_64.S b/arch/x86/crypto/aria-gfni-avx512-asm_64.S index 860887e5d02ed6..ca83eb126e065b 100644 --- a/arch/x86/crypto/aria-gfni-avx512-asm_64.S +++ b/arch/x86/crypto/aria-gfni-avx512-asm_64.S @@ -800,6 +800,7 @@ SYM_TYPED_FUNC_START(aria_gfni_avx512_encrypt_64way) %zmm9, %zmm8, %zmm11, %zmm10, %zmm12, %zmm13, %zmm14, %zmm15, %rax); + vzeroupper; FRAME_END RET; SYM_FUNC_END(aria_gfni_avx512_encrypt_64way) @@ -825,6 +826,7 @@ SYM_TYPED_FUNC_START(aria_gfni_avx512_decrypt_64way) %zmm9, %zmm8, %zmm11, %zmm10, %zmm12, %zmm13, %zmm14, %zmm15, %rax); + vzeroupper; FRAME_END RET; SYM_FUNC_END(aria_gfni_avx512_decrypt_64way) @@ -966,6 +968,7 @@ SYM_TYPED_FUNC_START(aria_gfni_avx512_ctr_crypt_64way) %zmm9, %zmm8, %zmm11, %zmm10, %zmm12, %zmm13, %zmm14, %zmm15, %r10); + vzeroupper; FRAME_END RET; SYM_FUNC_END(aria_gfni_avx512_ctr_crypt_64way) diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 5116b15438a211..24c1f40595449e 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -3125,6 +3125,27 @@ static void intel_pmu_del_event(struct perf_event *event) this_cpu_ptr(&cpu_hw_events)->n_late_setup--; } +int __intel_pmu_quiesce(void) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + int pmu_enabled = cpuc->enabled; + + cpuc->enabled = 0; + if (pmu_enabled) + intel_pmu_disable_all(); + + return pmu_enabled; +} + +void __intel_pmu_resume(int pmu_enabled) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + + cpuc->enabled = pmu_enabled; + if (pmu_enabled) + intel_pmu_enable_all(0); +} + static int icl_set_topdown_event_period(struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; @@ -3316,16 +3337,13 @@ static void intel_pmu_read_event(struct perf_event *event) if (event->hw.flags & (PERF_X86_EVENT_AUTO_RELOAD | PERF_X86_EVENT_TOPDOWN) || is_pebs_counter_event_group(event)) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); - bool pmu_enabled = cpuc->enabled; + int pmu_enabled; /* Only need to call update_topdown_event() once for group read. */ if (is_metric_event(event) && (cpuc->txn_flags & PERF_PMU_TXN_READ)) return; - cpuc->enabled = 0; - if (pmu_enabled) - intel_pmu_disable_all(); - + pmu_enabled = __intel_pmu_quiesce(); /* * If the PEBS counters snapshotting is enabled, * the topdown event is available in PEBS records. @@ -3334,10 +3352,7 @@ static void intel_pmu_read_event(struct perf_event *event) static_call(intel_pmu_update_topdown_event)(event, NULL); else intel_pmu_drain_pebs_buffer(); - - cpuc->enabled = pmu_enabled; - if (pmu_enabled) - intel_pmu_enable_all(0); + __intel_pmu_resume(pmu_enabled); return; } diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index 91a093d8cf2e77..3dcd7dfc92b1c1 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -1242,8 +1242,11 @@ unlock: void intel_pmu_drain_pebs_buffer(void) { + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct perf_sample_data data; + WARN_ON_ONCE(cpuc->enabled); + static_call(x86_pmu_drain_pebs)(NULL, &data); } @@ -1877,8 +1880,11 @@ static void intel_pmu_pebs_via_pt_enable(struct perf_event *event) static inline void intel_pmu_drain_large_pebs(struct cpu_hw_events *cpuc) { if (cpuc->n_pebs == cpuc->n_large_pebs && - cpuc->n_pebs != cpuc->n_pebs_via_pt) + cpuc->n_pebs != cpuc->n_pebs_via_pt) { + int enabled = __intel_pmu_quiesce(); intel_pmu_drain_pebs_buffer(); + __intel_pmu_resume(enabled); + } } static void __intel_pmu_pebs_enable(struct perf_event *event) @@ -2445,7 +2451,7 @@ static inline void __setup_pebs_basic_group(struct perf_event *event, { /* The ip in basic is EventingIP */ set_linear_ip(regs, ip); - regs->flags = PERF_EFLAGS_EXACT; + regs->flags |= PERF_EFLAGS_EXACT; setup_pebs_time(event, data, tsc); if (sample_type & PERF_SAMPLE_WEIGHT_STRUCT) @@ -2457,9 +2463,17 @@ static inline void __setup_pebs_gpr_group(struct perf_event *event, struct pebs_gprs *gprs, u64 sample_type) { + /* + * Update flags with PEBS data. PERF_EFLAGS_EXACT must be set + * in previous basic group handling. + */ + regs->flags = gprs->flags | PERF_EFLAGS_EXACT; + if (event->attr.precise_ip < 2) { set_linear_ip(regs, gprs->ip); regs->flags &= ~PERF_EFLAGS_EXACT; + } else if (regs->flags & X86_VM_MASK) { + regs->flags ^= (PERF_EFLAGS_VM | X86_VM_MASK); } if (sample_type & (PERF_SAMPLE_REGS_INTR | PERF_SAMPLE_REGS_USER)) diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index a8afea8d38f0c3..680220d311a71f 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -1644,6 +1644,9 @@ static __always_inline void __intel_pmu_lbr_disable(void) wrmsrq(MSR_IA32_DEBUGCTLMSR, debugctl); } +extern int __intel_pmu_quiesce(void); +extern void __intel_pmu_resume(int pmu_enabled); + int intel_pmu_save_and_restart(struct perf_event *event); struct event_constraint * diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index ac295ca6c92f99..b44d24c6eb63f9 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -806,7 +806,7 @@ static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot) pmdval_t val = pmd_val(pmd), oldval = val; pmd_t pmd_result; - val &= (_HPAGE_CHG_MASK & ~_PAGE_DIRTY); + val &= _HPAGE_CHG_MASK; val |= check_pgprot(newprot) & ~_HPAGE_CHG_MASK; val = flip_protnone_guard(oldval, val, PHYSICAL_PMD_PAGE_MASK); diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 62936a3bde19b8..b0b576ab2fa6eb 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -6,6 +6,9 @@ #include #include #include +#include +#include +#include #include #include @@ -1207,6 +1210,41 @@ static bool cfi_debug __ro_after_init; bool cfi_bhi __ro_after_init = false; #endif +#ifdef CONFIG_FINEIBT +/* + * : + * 0: f3 0f 1e fa endbr64 + * 4: 2d 78 56 34 12 sub $0x12345678, %eax + * 9: 2e 0f 85 03 00 00 00 jne,pn 13 + * 10: 0f 1f 40 d6 nopl -0x2a(%rax) + * + * Note that the JNE target is the 0xD6 byte inside the NOPL, this decodes as + * UDB on x86_64 and raises #UD. + */ +asm( ".pushsection .rodata \n" + "fineibt_preamble_start: \n" + " endbr64 \n" + " subl $0x12345678, %eax \n" + "fineibt_preamble_bhi: \n" + " cs jne.d32 fineibt_preamble_start+0x13 \n" + "#fineibt_func: \n" + " nopl -42(%rax) \n" + "fineibt_preamble_end: \n" + ".popsection\n" +); + +extern u8 fineibt_preamble_start[]; +extern u8 fineibt_preamble_bhi[]; +extern u8 fineibt_preamble_end[]; + +#define fineibt_preamble_size (fineibt_preamble_end - fineibt_preamble_start) +#define fineibt_preamble_bhi (fineibt_preamble_bhi - fineibt_preamble_start) +#define fineibt_preamble_ud 0x13 +#define fineibt_preamble_hash 5 + +#define fineibt_prefix_size (fineibt_preamble_size - ENDBR_INSN_SIZE) +#endif /* CONFIG_FINEIBT */ + #ifdef CONFIG_CFI u32 cfi_get_func_hash(void *func) { @@ -1214,9 +1252,11 @@ u32 cfi_get_func_hash(void *func) func -= cfi_get_offset(); switch (cfi_mode) { +#ifdef CONFIG_FINEIBT case CFI_FINEIBT: - func += 7; + func += fineibt_preamble_hash; break; +#endif case CFI_KCFI: func += 1; break; @@ -1358,39 +1398,6 @@ early_param("cfi", cfi_parse_cmdline); * processors. Therefore, it is good to place the most frequent branch first" */ -/* - * : - * 0: f3 0f 1e fa endbr64 - * 4: 2d 78 56 34 12 sub $0x12345678, %eax - * 9: 2e 0f 85 03 00 00 00 jne,pn 13 - * 10: 0f 1f 40 d6 nopl -0x2a(%rax) - * - * Note that the JNE target is the 0xD6 byte inside the NOPL, this decodes as - * UDB on x86_64 and raises #UD. - */ -asm( ".pushsection .rodata \n" - "fineibt_preamble_start: \n" - " endbr64 \n" - " subl $0x12345678, %eax \n" - "fineibt_preamble_bhi: \n" - " cs jne.d32 fineibt_preamble_start+0x13 \n" - "#fineibt_func: \n" - " nopl -42(%rax) \n" - "fineibt_preamble_end: \n" - ".popsection\n" -); - -extern u8 fineibt_preamble_start[]; -extern u8 fineibt_preamble_bhi[]; -extern u8 fineibt_preamble_end[]; - -#define fineibt_preamble_size (fineibt_preamble_end - fineibt_preamble_start) -#define fineibt_preamble_bhi (fineibt_preamble_bhi - fineibt_preamble_start) -#define fineibt_preamble_ud 0x13 -#define fineibt_preamble_hash 5 - -#define fineibt_prefix_size (fineibt_preamble_size - ENDBR_INSN_SIZE) - /* * : * 0: b8 78 56 34 12 mov $0x12345678, %eax @@ -2543,6 +2550,38 @@ static void text_poke_memset(void *dst, const void *src, size_t len) typedef void text_poke_f(void *dst, const void *src, size_t len); +static void __poke_vmalloc_pages(struct page **pages, void *addr, + bool cross_page_boundary) +{ + pages[0] = vmalloc_to_page(addr); + if (cross_page_boundary) + pages[1] = vmalloc_to_page(addr + PAGE_SIZE); +} + +static void poke_vmalloc_pages(struct page **pages, void *addr, + bool cross_page_boundary) +{ + if (in_dbg_master()) { + /* + * If called from kgdb cannot sleep, but all other CPUs stopped + * anyway so safe to proceed without locks + */ + __poke_vmalloc_pages(pages, addr, cross_page_boundary); + } else { + /* + * execmem ROX ranges are shared between modules and can be + * collapsed to huge PMD entries, and this collapse can happen + * concurrently with a racing set_memory_rox(). + * + * Prevent vmalloc_to_page() from racing by acquiring an + * init_mm read lock which pairs with the init_mm write lock in + * cpa_collapse_large_pages(). + */ + guard(mmap_read_lock)(&init_mm); + __poke_vmalloc_pages(pages, addr, cross_page_boundary); + } +} + static void *__text_poke(text_poke_f func, void *addr, const void *src, size_t len) { bool cross_page_boundary = offset_in_page(addr) + len > PAGE_SIZE; @@ -2560,9 +2599,7 @@ static void *__text_poke(text_poke_f func, void *addr, const void *src, size_t l BUG_ON(!after_bootmem); if (!core_kernel_text((unsigned long)addr)) { - pages[0] = vmalloc_to_page(addr); - if (cross_page_boundary) - pages[1] = vmalloc_to_page(addr + PAGE_SIZE); + poke_vmalloc_pages(pages, addr, cross_page_boundary); } else { pages[0] = virt_to_page(addr); WARN_ON(!PageReserved(pages[0])); diff --git a/arch/x86/kernel/amd_node.c b/arch/x86/kernel/amd_node.c index 0be01725a2a458..b7926ba3610a33 100644 --- a/arch/x86/kernel/amd_node.c +++ b/arch/x86/kernel/amd_node.c @@ -38,7 +38,6 @@ static struct pci_dev **amd_roots; /* Protect the PCI config register pairs used for SMN. */ static DEFINE_MUTEX(smn_mutex); -static bool smn_exclusive; #define SMN_INDEX_OFFSET 0x60 #define SMN_DATA_OFFSET 0x64 @@ -91,11 +90,16 @@ static int __amd_smn_rw(u8 i_off, u8 d_off, u16 node, u32 address, u32 *value, b if (node >= amd_num_nodes()) return err; - root = amd_roots[node]; - if (!root) + /* + * Uninitialized amd_roots indicates pci_request_config_region_exclusive() + * didn't run or failed and thus the kernel cannot rely on having + * exclusive access to SMN registers so prevent that. + */ + if (!amd_roots) return err; - if (!smn_exclusive) + root = amd_roots[node]; + if (!root) return err; guard(mutex)(&smn_mutex); @@ -247,7 +251,7 @@ __setup("amd_smn_debugfs_enable", amd_smn_enable_dfs); static int __init amd_smn_init(void) { u16 count, num_roots, roots_per_node, node, num_nodes; - struct pci_dev *root; + struct pci_dev *root __free(pci_dev_put) = NULL; if (!cpu_feature_enabled(X86_FEATURE_ZEN)) return 0; @@ -258,7 +262,6 @@ static int __init amd_smn_init(void) return 0; num_roots = 0; - root = NULL; while ((root = get_next_root(root))) { pci_dbg(root, "Reserving PCI config space\n"); @@ -287,17 +290,21 @@ static int __init amd_smn_init(void) return -ENOMEM; roots_per_node = num_roots / num_nodes; + if (!roots_per_node) { + if (!cpu_feature_enabled(X86_FEATURE_HYPERVISOR)) + pr_warn(FW_BUG "Error detecting roots per node.\n"); + roots_per_node = 1; + } count = 0; node = 0; - root = NULL; while (node < num_nodes && (root = get_next_root(root))) { /* Use one root for each node and skip the rest. */ if (count++ % roots_per_node) continue; pci_dbg(root, "is root for AMD node %u\n", node); - amd_roots[node++] = root; + amd_roots[node++] = pci_dev_get(root); } if (enable_dfs) { @@ -308,8 +315,6 @@ static int __init amd_smn_init(void) debugfs_create_file("value", 0600, debugfs_dir, NULL, &smn_value_fops); } - smn_exclusive = true; - return 0; } diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c index 36e0df4d1342d9..fd878bc7ff080d 100644 --- a/arch/x86/kernel/cpu/mce/amd.c +++ b/arch/x86/kernel/cpu/mce/amd.c @@ -864,7 +864,7 @@ static void amd_deferred_error_interrupt(void) void mce_amd_handle_storm(unsigned int bank, bool on) { - threshold_restart_bank(bank, on); + threshold_restart_bank(bank, !on); } static void amd_reset_thr_limit(unsigned int bank) diff --git a/arch/x86/kernel/itmt.c b/arch/x86/kernel/itmt.c index 243a769fdd97b9..85ebde361d6ae9 100644 --- a/arch/x86/kernel/itmt.c +++ b/arch/x86/kernel/itmt.c @@ -110,18 +110,14 @@ int sched_set_itmt_support(void) arch_debugfs_dir, &sysctl_sched_itmt_enabled, &dfs_sched_itmt_fops); - if (IS_ERR_OR_NULL(dfs_sched_itmt)) { + if (IS_ERR(dfs_sched_itmt)) dfs_sched_itmt = NULL; - return -ENOMEM; - } dfs_sched_core_prio = debugfs_create_file("sched_core_priority", 0644, arch_debugfs_dir, NULL, &sched_core_priority_fops); - if (IS_ERR_OR_NULL(dfs_sched_core_prio)) { + if (IS_ERR(dfs_sched_core_prio)) dfs_sched_core_prio = NULL; - return -ENOMEM; - } sched_itmt_capable = true; diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c index 3b7e807e803c36..f8d5cdbb68714b 100644 --- a/arch/x86/mm/pat/set_memory.c +++ b/arch/x86/mm/pat/set_memory.c @@ -22,6 +22,7 @@ #include #include #include +#include #include #include @@ -49,7 +50,8 @@ struct cpa_data { unsigned int flags; unsigned int force_split : 1, force_static_prot : 1, - force_flush_all : 1; + force_flush_all : 1, + init_mm_read_locked : 1; struct page **pages; }; @@ -62,18 +64,18 @@ enum cpa_warn { static const int cpa_warn_level = CPA_PROTECT; /* - * Serialize cpa() (for !DEBUG_PAGEALLOC which uses large identity mappings) - * using cpa_lock. So that we don't allow any other cpu, with stale large tlb - * entries change the page attribute in parallel to some other cpu - * splitting a large page entry along with changing the attribute. + * Serialize cpa() using cpa_lock so that we don't allow any other cpu, with + * stale large tlb entries, to change the page attribute in parallel to some + * other cpu splitting a large page entry along with changing the attribute. */ static DEFINE_SPINLOCK(cpa_lock); -#define CPA_FLUSHTLB 1 -#define CPA_ARRAY 2 -#define CPA_PAGES_ARRAY 4 -#define CPA_NO_CHECK_ALIAS 8 /* Do not search for aliases */ -#define CPA_COLLAPSE 16 /* try to collapse large pages */ +#define CPA_FLUSHTLB 0x01 +#define CPA_ARRAY 0x02 +#define CPA_PAGES_ARRAY 0x04 +#define CPA_NO_CHECK_ALIAS 0x08 /* Do not search for aliases */ +#define CPA_COLLAPSE 0x10 /* try to collapse large pages */ +#define CPA_DEBUG_PAGEALLOC 0x20 static inline pgprot_t cachemode2pgprot(enum page_cache_mode pcm) { @@ -410,7 +412,7 @@ static void __cpa_flush_tlb(void *data) static int collapse_large_pages(unsigned long addr, struct list_head *pgtables); -static void cpa_collapse_large_pages(struct cpa_data *cpa) +static void __cpa_collapse_large_pages(struct cpa_data *cpa) { unsigned long start, addr, end; struct ptdesc *ptdesc, *tmp; @@ -442,12 +444,32 @@ static void cpa_collapse_large_pages(struct cpa_data *cpa) list_for_each_entry_safe(ptdesc, tmp, &pgtables, pt_list) { list_del(&ptdesc->pt_list); - pagetable_free(ptdesc); + /* + * Only early alloc'd direct map should not be flagged PG_table + * here and those shouldn't be collapsed. However be abundantly + * cautious and handle the !PG_table case too. + */ + if (PageTable((ptdesc_page(ptdesc)))) + pagetable_dtor_free(ptdesc); + else + pagetable_free(ptdesc); } spin_unlock(&cpa_lock); } +static void cpa_collapse_large_pages(struct cpa_data *cpa) +{ + /* + * Take the mmap write lock on init_mm to: + * - Avoid a use-after-free if raced by ptdump (which takes its own + * write lock on init_mm). + * - Serialise concurrent CPA walkers. + */ + scoped_guard(mmap_write_lock, &init_mm) + __cpa_collapse_large_pages(cpa); +} + static void cpa_flush(struct cpa_data *cpa, int cache) { unsigned int i; @@ -1131,11 +1153,10 @@ set: static int __split_large_page(struct cpa_data *cpa, pte_t *kpte, unsigned long address, - struct ptdesc *ptdesc) + pte_t *pbase) { unsigned long lpaddr, lpinc, ref_pfn, pfn, pfninc = 1; - struct page *base = ptdesc_page(ptdesc); - pte_t *pbase = (pte_t *)page_address(base); + struct page *base = virt_to_page(pbase); unsigned int i, level; pgprot_t ref_prot; bool nx, rw; @@ -1239,18 +1260,20 @@ __split_large_page(struct cpa_data *cpa, pte_t *kpte, unsigned long address, static int split_large_page(struct cpa_data *cpa, pte_t *kpte, unsigned long address) { - struct ptdesc *ptdesc; + pte_t *pte; - if (!debug_pagealloc_enabled()) - spin_unlock(&cpa_lock); - ptdesc = pagetable_alloc(GFP_KERNEL, 0); - if (!debug_pagealloc_enabled()) - spin_lock(&cpa_lock); - if (!ptdesc) + spin_unlock(&cpa_lock); + if (cpa->init_mm_read_locked) + mmap_read_unlock(&init_mm); + pte = pte_alloc_one_kernel(&init_mm); + if (cpa->init_mm_read_locked) + mmap_read_lock(&init_mm); + spin_lock(&cpa_lock); + if (!pte) return -ENOMEM; - if (__split_large_page(cpa, kpte, address, ptdesc)) - pagetable_free(ptdesc); + if (__split_large_page(cpa, kpte, address, pte)) + pte_free_kernel(&init_mm, pte); return 0; } @@ -2010,6 +2033,7 @@ static int __change_page_attr_set_clr(struct cpa_data *cpa, int primary) { unsigned long numpages = cpa->numpages; unsigned long rempages = numpages; + bool lock = true; int ret = 0; /* @@ -2019,6 +2043,29 @@ static int __change_page_attr_set_clr(struct cpa_data *cpa, int primary) !cpa->force_split) return ret; + /* + * DEBUG_PAGEALLOC is special; it is called from any context the + * page-allocator is, which violates the normal cpa_lock locking + * rules. + * + * However, since it is part of the page-allocator, things are still + * properly serialized by the page-allocator locking and the fact that + * when a page is owned by the page-allocator, it isn't owned by + * anybody else. That is, you *SHOULD NOT* be calling cpa() on memory + * that isn't allocated. + * + * Additionally, DEBUG_PAGEALLOC ensures (per probe_page_size_mask()) + * that the kernel mapping is 4k pages, therefore there are no large + * pages to split/collapse. + * + * Furthermore, the page-allocator strictly manages pages that + * *exist*, avoiding pgd_lock. + * + * Therefore, it is safe to not take cpa_lock. + */ + if (debug_pagealloc_enabled() && (cpa->flags & CPA_DEBUG_PAGEALLOC)) + lock = false; + while (rempages) { /* * Store the remaining nr of pages for the large page @@ -2029,11 +2076,12 @@ static int __change_page_attr_set_clr(struct cpa_data *cpa, int primary) if (cpa->flags & (CPA_ARRAY | CPA_PAGES_ARRAY)) cpa->numpages = 1; - if (!debug_pagealloc_enabled()) - spin_lock(&cpa_lock); - ret = __change_page_attr(cpa, primary); - if (!debug_pagealloc_enabled()) - spin_unlock(&cpa_lock); + if (lock) { + guard(spinlock)(&cpa_lock); + ret = __change_page_attr(cpa, primary); + } else { + ret = __change_page_attr(cpa, primary); + } if (ret) goto out; @@ -2115,7 +2163,11 @@ static int change_page_attr_set_clr(unsigned long *addr, int numpages, cpa.curpage = 0; cpa.force_split = force_split; - ret = __change_page_attr_set_clr(&cpa, 1); + /* Avoid race with concurrent CPA collapse. */ + cpa.init_mm_read_locked = true; + scoped_guard(mmap_read_lock, &init_mm) + ret = __change_page_attr_set_clr(&cpa, 1); + cpa.init_mm_read_locked = false; /* * Check whether we really changed something: @@ -2612,7 +2664,7 @@ int set_pages_rw(struct page *page, int numpages) return set_memory_rw(addr, numpages); } -static int __set_pages_p(struct page *page, int numpages) +static int __set_pages_p(struct page *page, int numpages, unsigned int cpa_flags) { unsigned long tempaddr = (unsigned long) page_address(page); struct cpa_data cpa = { .vaddr = &tempaddr, @@ -2620,7 +2672,7 @@ static int __set_pages_p(struct page *page, int numpages) .numpages = numpages, .mask_set = __pgprot(_PAGE_PRESENT | _PAGE_RW), .mask_clr = __pgprot(0), - .flags = CPA_NO_CHECK_ALIAS }; + .flags = CPA_NO_CHECK_ALIAS | cpa_flags }; /* * No alias checking needed for setting present flag. otherwise, @@ -2631,7 +2683,7 @@ static int __set_pages_p(struct page *page, int numpages) return __change_page_attr_set_clr(&cpa, 1); } -static int __set_pages_np(struct page *page, int numpages) +static int __set_pages_np(struct page *page, int numpages, unsigned int cpa_flags) { unsigned long tempaddr = (unsigned long) page_address(page); struct cpa_data cpa = { .vaddr = &tempaddr, @@ -2639,7 +2691,7 @@ static int __set_pages_np(struct page *page, int numpages) .numpages = numpages, .mask_set = __pgprot(0), .mask_clr = __pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY), - .flags = CPA_NO_CHECK_ALIAS }; + .flags = CPA_NO_CHECK_ALIAS | cpa_flags }; /* * No alias checking needed for setting not present flag. otherwise, @@ -2652,20 +2704,20 @@ static int __set_pages_np(struct page *page, int numpages) int set_direct_map_invalid_noflush(struct page *page) { - return __set_pages_np(page, 1); + return __set_pages_np(page, 1, 0); } int set_direct_map_default_noflush(struct page *page) { - return __set_pages_p(page, 1); + return __set_pages_p(page, 1, 0); } int set_direct_map_valid_noflush(struct page *page, unsigned nr, bool valid) { if (valid) - return __set_pages_p(page, nr); + return __set_pages_p(page, nr, 0); - return __set_pages_np(page, nr); + return __set_pages_np(page, nr, 0); } #ifdef CONFIG_DEBUG_PAGEALLOC @@ -2684,15 +2736,23 @@ void __kernel_map_pages(struct page *page, int numpages, int enable) * and hence no memory allocations during large page split. */ if (enable) - __set_pages_p(page, numpages); + __set_pages_p(page, numpages, CPA_DEBUG_PAGEALLOC); else - __set_pages_np(page, numpages); + __set_pages_np(page, numpages, CPA_DEBUG_PAGEALLOC); /* - * We should perform an IPI and flush all tlbs, - * but that can deadlock->flush only current cpu. - * Preemption needs to be disabled around __flush_tlb_all() due to - * CR3 reload in __native_flush_tlb(). + * We should perform an IPI and flush all tlbs, but that can + * deadlock, settle for a local flush. + * + * Not doing a global TLB flush means that remote CPUs will retain + * stale TLB entries. In case of P->NP (on free) this means the remote + * CPUs will not take the faults, making the debug scheme less + * reliable. On the NP->P (on alloc) this means the remote CPUs can + * take a spurious fault. However spurious_kernel_fault() will observe + * *_present() and fix it up. + * + * Preemption needs to be disabled around __flush_tlb_all() due to CR3 + * reload in __native_flush_tlb(). */ preempt_disable(); __flush_tlb_all(); diff --git a/block/bio.c b/block/bio.c index 5018a6fc2f36b7..bdcb60cb8d88f6 100644 --- a/block/bio.c +++ b/block/bio.c @@ -859,6 +859,7 @@ static int __bio_clone(struct bio *bio, struct bio *bio_src, gfp_t gfp) bio->bi_ioprio = bio_src->bi_ioprio; bio->bi_write_hint = bio_src->bi_write_hint; bio->bi_write_stream = bio_src->bi_write_stream; + bio->bi_bvec_gap_bit = bio_src->bi_bvec_gap_bit; bio->bi_iter = bio_src->bi_iter; if (bio->bi_bdev) { @@ -1913,6 +1914,14 @@ struct bio *bio_split(struct bio *bio, int sectors, bio_advance(bio, split->bi_iter.bi_size); + /* + * The gap bit is set when splitting to limits and only applies to the + * front bio that was split off. The remaining bio will calcualte its + * gap value when it is subsequently split to limits, so it is safe to + * re-initialize the value back to 0. + */ + bio->bi_bvec_gap_bit = 0; + if (bio_flagged(bio, BIO_TRACE_COMPLETION)) bio_set_flag(split, BIO_TRACE_COMPLETION); diff --git a/drivers/accel/amdxdna/aie2_message.c b/drivers/accel/amdxdna/aie2_message.c index dfe0fbdf066d2c..b4c49259a1a23b 100644 --- a/drivers/accel/amdxdna/aie2_message.c +++ b/drivers/accel/amdxdna/aie2_message.c @@ -994,7 +994,7 @@ int aie2_cmdlist_multi_execbuf(struct amdxdna_hwctx *hwctx, } ccnt = payload->command_count; - if (payload_len < struct_size(payload, data, ccnt)) { + if (!ccnt || payload_len < struct_size(payload, data, ccnt)) { XDNA_DBG(xdna, "Invalid command count %d", ccnt); return -EINVAL; } diff --git a/drivers/accel/amdxdna/amdxdna_ctx.c b/drivers/accel/amdxdna/amdxdna_ctx.c index 31a414c3f0d967..888e857ec55820 100644 --- a/drivers/accel/amdxdna/amdxdna_ctx.c +++ b/drivers/accel/amdxdna/amdxdna_ctx.c @@ -183,8 +183,10 @@ int amdxdna_cmd_set_error(struct amdxdna_gem_obj *abo, if (!abo) return -EINVAL; cmd = amdxdna_gem_vmap(abo); - if (!cmd) + if (!cmd) { + amdxdna_gem_put_obj(abo); return -ENOMEM; + } } memset(cmd->data, 0xff, abo->mem.size - sizeof(*cmd)); diff --git a/drivers/accel/amdxdna/amdxdna_ctx.h b/drivers/accel/amdxdna/amdxdna_ctx.h index b6bef3af7dab46..6e78bab8a02c03 100644 --- a/drivers/accel/amdxdna/amdxdna_ctx.h +++ b/drivers/accel/amdxdna/amdxdna_ctx.h @@ -55,7 +55,7 @@ struct amdxdna_cmd_chain { u32 submit_index; u32 error_index; u32 reserved[3]; - u64 data[] __counted_by(command_count); + u64 data[]; }; /* diff --git a/drivers/accel/amdxdna/amdxdna_gem.c b/drivers/accel/amdxdna/amdxdna_gem.c index 2a16de96e6a4ea..4b0d58d0329b75 100644 --- a/drivers/accel/amdxdna/amdxdna_gem.c +++ b/drivers/accel/amdxdna/amdxdna_gem.c @@ -758,9 +758,15 @@ static int amdxdna_gem_dev_obj_vmap(struct drm_gem_object *obj, struct iosys_map return 0; } +static struct dma_buf *amdxdna_gem_dev_obj_export(struct drm_gem_object *gobj, int flags) +{ + return ERR_PTR(-EOPNOTSUPP); +} + static const struct drm_gem_object_funcs amdxdna_gem_dev_obj_funcs = { .free = amdxdna_gem_dev_obj_free, .vmap = amdxdna_gem_dev_obj_vmap, + .export = amdxdna_gem_dev_obj_export, }; static const struct drm_gem_object_funcs amdxdna_gem_shmem_funcs = { @@ -1240,6 +1246,9 @@ static int amdxdna_flush_bo(struct amdxdna_gem_obj *abo, u64 offset, u64 size) { u64 end; + if (is_import_bo(abo)) + return -EOPNOTSUPP; + if (offset >= abo->mem.size) return -EINVAL; @@ -1250,9 +1259,7 @@ static int amdxdna_flush_bo(struct amdxdna_gem_obj *abo, u64 offset, u64 size) if (!size) return 0; - if (is_import_bo(abo)) - drm_clflush_sg(abo->base.sgt); - else if (amdxdna_gem_vmap(abo)) + if (amdxdna_gem_vmap(abo)) drm_clflush_virt_range(amdxdna_gem_vmap(abo) + offset, size); else if (abo->base.pages) drm_clflush_pages(abo->base.pages, abo->mem.size >> PAGE_SHIFT); diff --git a/drivers/accel/ethosu/ethosu_device.h b/drivers/accel/ethosu/ethosu_device.h index b189fa783d6a3f..cf53964a4f04b5 100644 --- a/drivers/accel/ethosu/ethosu_device.h +++ b/drivers/accel/ethosu/ethosu_device.h @@ -68,6 +68,7 @@ struct gen_pool; #define PROT_ACTIVE_CSL BIT(1) enum ethosu_cmds { + NPU_OP_STOP = 0x0, NPU_OP_CONV = 0x2, NPU_OP_DEPTHWISE = 0x3, NPU_OP_POOL = 0x5, diff --git a/drivers/accel/ethosu/ethosu_drv.c b/drivers/accel/ethosu/ethosu_drv.c index b2901eb8a7a03e..ff11d7b2795309 100644 --- a/drivers/accel/ethosu/ethosu_drv.c +++ b/drivers/accel/ethosu/ethosu_drv.c @@ -274,8 +274,6 @@ static int ethosu_device_suspend(struct device *dev) static int ethosu_sram_init(struct ethosu_device *ethosudev) { - ethosudev->npu_info.sram_size = 0; - ethosudev->srampool = of_gen_pool_get(ethosudev->base.dev->of_node, "sram", 0); if (!ethosudev->srampool) return 0; @@ -286,6 +284,7 @@ static int ethosu_sram_init(struct ethosu_device *ethosudev) ethosudev->npu_info.sram_size, ðosudev->sramphys); if (!ethosudev->sram) { + ethosudev->npu_info.sram_size = 0; dev_err(ethosudev->base.dev, "failed to allocate from SRAM pool\n"); return -ENOMEM; } diff --git a/drivers/accel/ethosu/ethosu_gem.c b/drivers/accel/ethosu/ethosu_gem.c index d50fed64d4d937..9afe2549ec84db 100644 --- a/drivers/accel/ethosu/ethosu_gem.c +++ b/drivers/accel/ethosu/ethosu_gem.c @@ -204,7 +204,7 @@ static u64 feat_matrix_length(struct ethosu_device *edev, struct feat_matrix *fm, u32 x, u32 y, u32 c, bool ofm) { - u32 element_size, storage = fm->precision >> 14; + u32 element_size, storage = ethosu_is_u65(edev) ? 0 : fm->precision >> 14; int tile = 0; u64 addr; @@ -390,6 +390,7 @@ static int ethosu_gem_cmdstream_copy_and_validate(struct drm_device *ddev, struct ethosu_validated_cmdstream_info __free(kfree) *info = kzalloc_obj(*info); struct ethosu_device *edev = to_ethosu_device(ddev); u32 *bocmds = bo->base.vaddr; + bool ends_with_stop = false; struct cmd_state st; int i, ret; @@ -426,6 +427,11 @@ static int ethosu_gem_cmdstream_copy_and_validate(struct drm_device *ddev, } switch (cmd) { + case NPU_OP_STOP: + if (i != size / 4 - 1) + return -EINVAL; + ends_with_stop = true; + break; case NPU_OP_DMA_START: srclen = dma_length(info, &st.dma, &st.dma.src); dstlen = dma_length(info, &st.dma, &st.dma.dst); @@ -688,6 +694,9 @@ static int ethosu_gem_cmdstream_copy_and_validate(struct drm_device *ddev, } } + if (!ends_with_stop) + return -EINVAL; + for (i = 0; i < NPU_BASEP_REGION_MAX; i++) { if (!info->region_size[i]) continue; diff --git a/drivers/accel/ethosu/ethosu_job.c b/drivers/accel/ethosu/ethosu_job.c index 1e4b65f6293348..3365d2e6d51b20 100644 --- a/drivers/accel/ethosu/ethosu_job.c +++ b/drivers/accel/ethosu/ethosu_job.c @@ -325,7 +325,7 @@ int ethosu_job_init(struct ethosu_device *edev) ret = devm_request_threaded_irq(dev, edev->irq, ethosu_job_irq_handler, ethosu_job_irq_handler_thread, - IRQF_SHARED, KBUILD_MODNAME, + 0, KBUILD_MODNAME, edev); if (ret) { dev_err(dev, "failed to request irq\n"); @@ -356,12 +356,10 @@ int ethosu_job_open(struct ethosu_file_priv *ethosu_priv) { struct ethosu_device *dev = ethosu_priv->edev; struct drm_gpu_scheduler *sched = &dev->sched; - int ret; - ret = drm_sched_entity_init(ðosu_priv->sched_entity, - DRM_SCHED_PRIORITY_NORMAL, - &sched, 1, NULL); - return WARN_ON(ret); + return drm_sched_entity_init(ðosu_priv->sched_entity, + DRM_SCHED_PRIORITY_NORMAL, + &sched, 1, NULL); } void ethosu_job_close(struct ethosu_file_priv *ethosu_priv) @@ -427,13 +425,13 @@ static int ethosu_ioctl_submit_job(struct drm_device *dev, struct drm_file *file if (!cmd_info->region_size[i]) continue; if (i == ETHOSU_SRAM_REGION) { - if (cmd_info->region_size[i] <= edev->npu_info.sram_size) + if (cmd_info->region_size[i] <= ejob->sram_size) continue; dev_err(dev->dev, - "cmd stream region %d size greater than SRAM size (%llu > %u)\n", + "cmd stream region %d size greater than job SRAM size (%llu > %u)\n", i, cmd_info->region_size[i], - edev->npu_info.sram_size); + ejob->sram_size); ret = -EINVAL; goto out_cleanup_job; } diff --git a/drivers/accel/ivpu/ivpu_fw_log.c b/drivers/accel/ivpu/ivpu_fw_log.c index 716467aa315670..9eafc42120b6ae 100644 --- a/drivers/accel/ivpu/ivpu_fw_log.c +++ b/drivers/accel/ivpu/ivpu_fw_log.c @@ -26,10 +26,17 @@ MODULE_PARM_DESC(fw_log_level, " error=" __stringify(IVPU_FW_LOG_ERROR) " fatal=" __stringify(IVPU_FW_LOG_FATAL)); +struct ivpu_fw_log_desc { + struct vpu_tracing_buffer_header *log; + u32 header_size; + u32 size; +}; + static int fw_log_from_bo(struct ivpu_device *vdev, struct ivpu_bo *bo, u32 *offset, - struct vpu_tracing_buffer_header **out_log) + struct ivpu_fw_log_desc *desc) { struct vpu_tracing_buffer_header *log; + u32 header_size, size; if ((*offset + sizeof(*log)) > ivpu_bo_size(bo)) return -EINVAL; @@ -39,26 +46,32 @@ static int fw_log_from_bo(struct ivpu_device *vdev, struct ivpu_bo *bo, u32 *off if (log->vpu_canary_start != VPU_TRACING_BUFFER_CANARY) return -EINVAL; - if (log->header_size < sizeof(*log) || log->header_size > 1024) { - ivpu_dbg(vdev, FW_BOOT, "Invalid header size 0x%x\n", log->header_size); + header_size = READ_ONCE(log->header_size); + size = READ_ONCE(log->size); + + if (header_size < sizeof(*log) || header_size > 1024) { + ivpu_dbg(vdev, FW_BOOT, "Invalid header size 0x%x\n", header_size); return -EINVAL; } - if (log->size < log->header_size) { - ivpu_dbg(vdev, FW_BOOT, "Invalid log size 0x%x\n", log->size); + if ((char *)log + size > (char *)ivpu_bo_vaddr(bo) + ivpu_bo_size(bo)) { + ivpu_dbg(vdev, FW_BOOT, "Invalid log size 0x%x\n", size); return -EINVAL; } - if ((char *)log + log->size > (char *)ivpu_bo_vaddr(bo) + ivpu_bo_size(bo)) { - ivpu_dbg(vdev, FW_BOOT, "Invalid log size 0x%x\n", log->size); + if (size < header_size) { + ivpu_dbg(vdev, FW_BOOT, "Invalid log size 0x%x < header size 0x%x\n", + size, header_size); return -EINVAL; } - *out_log = log; - *offset += log->size; + desc->log = log; + desc->header_size = header_size; + desc->size = size; + *offset += size; ivpu_dbg(vdev, FW_BOOT, - "FW log name \"%s\", write offset 0x%x size 0x%x, wrap count %d, hdr version %d size %d format %d, alignment %d", - log->name, log->write_index, log->size, log->wrap_count, log->header_version, - log->header_size, log->format, log->alignment); + "FW log name \"%.*s\", write offset 0x%x size 0x%x, wrap count %d, hdr version %d size %d format %d, alignment %d", + (int)ARRAY_SIZE(log->name), log->name, log->write_index, size, log->wrap_count, + log->header_version, header_size, log->format, log->alignment); return 0; } @@ -94,11 +107,12 @@ static void fw_log_print_lines(char *buffer, u32 size, struct drm_printer *p) drm_printf(p, "%s", line); } -static void fw_log_print_buffer(struct vpu_tracing_buffer_header *log, const char *prefix, +static void fw_log_print_buffer(struct ivpu_fw_log_desc *desc, const char *prefix, bool only_new_msgs, struct drm_printer *p) { - char *log_data = (void *)log + log->header_size; - u32 data_size = log->size - log->header_size; + struct vpu_tracing_buffer_header *log = desc->log; + char *log_data = (void *)log + desc->header_size; + u32 data_size = desc->size - desc->header_size; u32 log_start = only_new_msgs ? READ_ONCE(log->read_index) : 0; u32 log_end = READ_ONCE(log->write_index); @@ -109,7 +123,8 @@ static void fw_log_print_buffer(struct vpu_tracing_buffer_header *log, const cha if (log->wrap_count == log->read_wrap_count) { if (log_end <= log_start) { - drm_printf(p, "==== %s \"%s\" log empty ====\n", prefix, log->name); + drm_printf(p, "==== %s \"%.*s\" log empty ====\n", prefix, + (int)ARRAY_SIZE(log->name), log->name); return; } } else if (log->wrap_count == log->read_wrap_count + 1) { @@ -119,7 +134,8 @@ static void fw_log_print_buffer(struct vpu_tracing_buffer_header *log, const cha log_start = log_end; } - drm_printf(p, "==== %s \"%s\" log start ====\n", prefix, log->name); + drm_printf(p, "==== %s \"%.*s\" log start ====\n", prefix, (int)ARRAY_SIZE(log->name), + log->name); if (log_end > log_start) { fw_log_print_lines(log_data + log_start, log_end - log_start, p); } else { @@ -127,18 +143,19 @@ static void fw_log_print_buffer(struct vpu_tracing_buffer_header *log, const cha fw_log_print_lines(log_data, log_end, p); } drm_printf(p, "\n\x1b[0m"); /* add new line and clear formatting */ - drm_printf(p, "==== %s \"%s\" log end ====\n", prefix, log->name); + drm_printf(p, "==== %s \"%.*s\" log end ====\n", prefix, (int)ARRAY_SIZE(log->name), + log->name); } static void fw_log_print_all_in_bo(struct ivpu_device *vdev, const char *name, struct ivpu_bo *bo, bool only_new_msgs, struct drm_printer *p) { - struct vpu_tracing_buffer_header *log; + struct ivpu_fw_log_desc desc; u32 next = 0; - while (fw_log_from_bo(vdev, bo, &next, &log) == 0) - fw_log_print_buffer(log, name, only_new_msgs, p); + while (fw_log_from_bo(vdev, bo, &next, &desc) == 0) + fw_log_print_buffer(&desc, name, only_new_msgs, p); } void ivpu_fw_log_print(struct ivpu_device *vdev, bool only_new_msgs, struct drm_printer *p) @@ -149,36 +166,36 @@ void ivpu_fw_log_print(struct ivpu_device *vdev, bool only_new_msgs, struct drm_ void ivpu_fw_log_mark_read(struct ivpu_device *vdev) { - struct vpu_tracing_buffer_header *log; + struct ivpu_fw_log_desc desc; u32 next; next = 0; - while (fw_log_from_bo(vdev, vdev->fw->mem_log_crit, &next, &log) == 0) { - log->read_index = READ_ONCE(log->write_index); - log->read_wrap_count = READ_ONCE(log->wrap_count); + while (fw_log_from_bo(vdev, vdev->fw->mem_log_crit, &next, &desc) == 0) { + desc.log->read_index = READ_ONCE(desc.log->write_index); + desc.log->read_wrap_count = READ_ONCE(desc.log->wrap_count); } next = 0; - while (fw_log_from_bo(vdev, vdev->fw->mem_log_verb, &next, &log) == 0) { - log->read_index = READ_ONCE(log->write_index); - log->read_wrap_count = READ_ONCE(log->wrap_count); + while (fw_log_from_bo(vdev, vdev->fw->mem_log_verb, &next, &desc) == 0) { + desc.log->read_index = READ_ONCE(desc.log->write_index); + desc.log->read_wrap_count = READ_ONCE(desc.log->wrap_count); } } void ivpu_fw_log_reset(struct ivpu_device *vdev) { - struct vpu_tracing_buffer_header *log; + struct ivpu_fw_log_desc desc; u32 next; next = 0; - while (fw_log_from_bo(vdev, vdev->fw->mem_log_crit, &next, &log) == 0) { - log->read_index = 0; - log->read_wrap_count = 0; + while (fw_log_from_bo(vdev, vdev->fw->mem_log_crit, &next, &desc) == 0) { + desc.log->read_index = 0; + desc.log->read_wrap_count = 0; } next = 0; - while (fw_log_from_bo(vdev, vdev->fw->mem_log_verb, &next, &log) == 0) { - log->read_index = 0; - log->read_wrap_count = 0; + while (fw_log_from_bo(vdev, vdev->fw->mem_log_verb, &next, &desc) == 0) { + desc.log->read_index = 0; + desc.log->read_wrap_count = 0; } } diff --git a/drivers/accel/ivpu/ivpu_gem.h b/drivers/accel/ivpu/ivpu_gem.h index 0c3350f22b5586..b1ae020a4fc216 100644 --- a/drivers/accel/ivpu/ivpu_gem.h +++ b/drivers/accel/ivpu/ivpu_gem.h @@ -87,15 +87,23 @@ static inline bool ivpu_bo_is_resident(struct ivpu_bo *bo) return !!bo->base.pages; } -static inline void *ivpu_to_cpu_addr(struct ivpu_bo *bo, u32 vpu_addr) +static inline void *ivpu_to_cpu_addr(struct ivpu_bo *bo, u64 vpu_addr, u64 size) { + u64 bo_size = ivpu_bo_size(bo); + u64 offset; + if (vpu_addr < bo->vpu_addr) return NULL; - if (vpu_addr >= (bo->vpu_addr + ivpu_bo_size(bo))) + if (size > bo_size) + return NULL; + + offset = vpu_addr - bo->vpu_addr; + + if (offset > bo_size - size) return NULL; - return ivpu_bo_vaddr(bo) + (vpu_addr - bo->vpu_addr); + return ivpu_bo_vaddr(bo) + offset; } static inline u32 cpu_to_vpu_addr(struct ivpu_bo *bo, void *cpu_addr) diff --git a/drivers/accel/ivpu/ivpu_ipc.c b/drivers/accel/ivpu/ivpu_ipc.c index 978bc3d8704fb9..8f69fb133e2e90 100644 --- a/drivers/accel/ivpu/ivpu_ipc.c +++ b/drivers/accel/ivpu/ivpu_ipc.c @@ -79,7 +79,7 @@ ivpu_ipc_tx_prepare(struct ivpu_device *vdev, struct ivpu_ipc_consumer *cons, return -ENOMEM; } - tx_buf = ivpu_to_cpu_addr(ipc->mem_tx, tx_buf_vpu_addr); + tx_buf = ivpu_to_cpu_addr(ipc->mem_tx, tx_buf_vpu_addr, sizeof(*tx_buf)); if (drm_WARN_ON(&vdev->drm, !tx_buf)) { gen_pool_free(ipc->mm_tx, tx_buf_vpu_addr, sizeof(*tx_buf)); return -EIO; @@ -420,7 +420,7 @@ void ivpu_ipc_irq_handler(struct ivpu_device *vdev) return; } - ipc_hdr = ivpu_to_cpu_addr(ipc->mem_rx, vpu_addr); + ipc_hdr = ivpu_to_cpu_addr(ipc->mem_rx, vpu_addr, sizeof(*ipc_hdr)); if (!ipc_hdr) { ivpu_warn_ratelimited(vdev, "IPC msg 0x%x out of range\n", vpu_addr); continue; @@ -429,7 +429,8 @@ void ivpu_ipc_irq_handler(struct ivpu_device *vdev) jsm_msg = NULL; if (ipc_hdr->channel != IVPU_IPC_CHAN_BOOT_MSG) { - jsm_msg = ivpu_to_cpu_addr(ipc->mem_rx, ipc_hdr->data_addr); + jsm_msg = ivpu_to_cpu_addr(ipc->mem_rx, ipc_hdr->data_addr, + sizeof(*jsm_msg)); if (!jsm_msg) { ivpu_warn_ratelimited(vdev, "JSM msg 0x%x out of range\n", ipc_hdr->data_addr); diff --git a/drivers/accel/qaic/qaic_control.c b/drivers/accel/qaic/qaic_control.c index 50bf3340e49ce5..2ccc55486aac07 100644 --- a/drivers/accel/qaic/qaic_control.c +++ b/drivers/accel/qaic/qaic_control.c @@ -963,11 +963,13 @@ static int decode_status(struct qaic_device *qdev, void *trans, struct manage_ms static int decode_message(struct qaic_device *qdev, struct manage_msg *user_msg, struct wire_msg *msg, struct ioctl_resources *resources, - struct qaic_user *usr) + struct qaic_user *usr, bool orphaned_deactivate) { + u32 msg_hdr_count = le32_to_cpu(msg->hdr.count); u32 msg_hdr_len = le32_to_cpu(msg->hdr.len); struct wire_trans_hdr *trans_hdr; u32 msg_len = 0; + int trans_type; int ret; int i; @@ -975,10 +977,12 @@ static int decode_message(struct qaic_device *qdev, struct manage_msg *user_msg, msg_hdr_len > QAIC_MANAGE_MAX_MSG_LENGTH) return -EINVAL; - user_msg->len = 0; - user_msg->count = le32_to_cpu(msg->hdr.count); + if (user_msg) { + user_msg->len = 0; + user_msg->count = msg_hdr_count; + } - for (i = 0; i < user_msg->count; ++i) { + for (i = 0; i < msg_hdr_count; ++i) { u32 hdr_len; if (msg_len > msg_hdr_len - sizeof(*trans_hdr)) @@ -990,7 +994,20 @@ static int decode_message(struct qaic_device *qdev, struct manage_msg *user_msg, size_add(msg_len, hdr_len) > msg_hdr_len) return -EINVAL; - switch (le32_to_cpu(trans_hdr->type)) { + trans_type = le32_to_cpu(trans_hdr->type); + /* + * orphaned_deactivate is the case where a deactivate response + * is received from the device after the user owning the DBC, + * and the message requesting deactivation, has gone away. + * In this case, only process QAIC_TRANS_DEACTIVATE_FROM_DEV + * transaction and skip the others. + */ + if (orphaned_deactivate && trans_type != QAIC_TRANS_DEACTIVATE_FROM_DEV) { + msg_len += hdr_len; + continue; + } + + switch (trans_type) { case QAIC_TRANS_PASSTHROUGH_FROM_DEV: ret = decode_passthrough(qdev, trans_hdr, user_msg, &msg_len); break; @@ -1281,7 +1298,7 @@ dma_xfer_continue: goto dma_cont_failed; } - ret = decode_message(qdev, user_msg, rsp, &resources, usr); + ret = decode_message(qdev, user_msg, rsp, &resources, usr, false); dma_cont_failed: free_dbc_buf(qdev, &resources); @@ -1446,22 +1463,7 @@ static void resp_worker(struct work_struct *work) * response to the QAIC_TRANS_TERMINATE_TO_DEV transaction, * otherwise, the user can issue an soc_reset to the device. */ - u32 msg_count = le32_to_cpu(msg->hdr.count); - u32 msg_len = le32_to_cpu(msg->hdr.len); - u32 len = 0; - int j; - - for (j = 0; j < msg_count && len < msg_len; ++j) { - struct wire_trans_hdr *trans_hdr; - - trans_hdr = (struct wire_trans_hdr *)(msg->data + len); - if (le32_to_cpu(trans_hdr->type) == QAIC_TRANS_DEACTIVATE_FROM_DEV) { - if (decode_deactivate(qdev, trans_hdr, &len, NULL)) - len += le32_to_cpu(trans_hdr->len); - } else { - len += le32_to_cpu(trans_hdr->len); - } - } + decode_message(qdev, NULL, msg, NULL, NULL, true); /* request must have timed out, drop packet */ kfree(msg); } diff --git a/drivers/block/sunvdc.c b/drivers/block/sunvdc.c index 020bd9f1a7b6a1..24ad56536ed60e 100644 --- a/drivers/block/sunvdc.c +++ b/drivers/block/sunvdc.c @@ -525,6 +525,23 @@ static int __send_request(struct request *req) err = __vdc_tx_trigger(port); if (err < 0) { printk(KERN_ERR PFX "vdc_tx_trigger() failure, err=%d\n", err); + /* + * If the port was reset (-ENOTCONN), the dring and the + * LDC channel including all of its mappings are already + * torn down and reallocated - there is nothing to undo + * and @desc must not be touched. + * + * For any other failure the descriptor was never handed + * to the peer: unmap the cookies and free the descriptor + * again, so that a later retry of the request does not + * leak LDC map table entries. + */ + if (err != -ENOTCONN) { + ldc_unmap(port->vio.lp, desc->cookies, + desc->ncookies); + desc->hdr.state = VIO_DESC_FREE; + rqe->req = NULL; + } } else { port->req_id++; dr->prod = vio_dring_next(dr, dr->prod); diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index b71283588ea772..d879e8492d59c6 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -3040,6 +3040,7 @@ static void ublk_queue_reset_io_flags(struct ublk_queue *ubq) ubq->canceling = false; spin_unlock(&ubq->cancel_lock); ubq->fail_io = false; + ubq->force_abort = false; } /* device can only be started after all IOs are ready */ diff --git a/drivers/bluetooth/btintel.c b/drivers/bluetooth/btintel.c index cc2234470960a7..96a55d5badda1a 100644 --- a/drivers/bluetooth/btintel.c +++ b/drivers/bluetooth/btintel.c @@ -570,12 +570,44 @@ int btintel_version_info_tlv(struct hci_dev *hdev, } EXPORT_SYMBOL_GPL(btintel_version_info_tlv); +static u8 btintel_version_tlv_min_len(u8 type) +{ + switch (type) { + case INTEL_TLV_CNVI_TOP: + case INTEL_TLV_CNVR_TOP: + case INTEL_TLV_CNVI_BT: + case INTEL_TLV_CNVR_BT: + case INTEL_TLV_BUILD_NUM: + case INTEL_TLV_GIT_SHA1: + return sizeof(u32); + case INTEL_TLV_DEV_REV_ID: + case INTEL_TLV_TIME_STAMP: + return sizeof(u16); + case INTEL_TLV_IMAGE_TYPE: + case INTEL_TLV_BUILD_TYPE: + case INTEL_TLV_SECURE_BOOT: + case INTEL_TLV_OTP_LOCK: + case INTEL_TLV_API_LOCK: + case INTEL_TLV_DEBUG_LOCK: + case INTEL_TLV_LIMITED_CCE: + case INTEL_TLV_SBE_TYPE: + return sizeof(u8); + case INTEL_TLV_MIN_FW: + return 3; + case INTEL_TLV_OTP_BDADDR: + return sizeof(bdaddr_t); + default: + return 0; + } +} + int btintel_parse_version_tlv(struct hci_dev *hdev, struct intel_version_tlv *version, struct sk_buff *skb) { /* Consume Command Complete Status field */ - skb_pull(skb, 1); + if (!skb_pull(skb, 1)) + return -EINVAL; /* Event parameters contain multiple TLVs. Read each of them * and only keep the required data. Also, it use existing legacy @@ -595,6 +627,9 @@ int btintel_parse_version_tlv(struct hci_dev *hdev, if (skb->len < tlv->len + sizeof(*tlv)) return -EINVAL; + if (tlv->len < btintel_version_tlv_min_len(tlv->type)) + return -EINVAL; + switch (tlv->type) { case INTEL_TLV_CNVI_TOP: version->cnvi_top = get_unaligned_le32(tlv->val); @@ -666,7 +701,7 @@ int btintel_parse_version_tlv(struct hci_dev *hdev, break; case INTEL_TLV_FW_ID: snprintf(version->fw_id, sizeof(version->fw_id), - "%s", tlv->val); + "%.*s", tlv->len, tlv->val); break; default: /* Ignore rest of information */ diff --git a/drivers/bluetooth/btintel_pcie.c b/drivers/bluetooth/btintel_pcie.c index 2b7231be5973d3..c64e96fe889766 100644 --- a/drivers/bluetooth/btintel_pcie.c +++ b/drivers/bluetooth/btintel_pcie.c @@ -1099,7 +1099,7 @@ static void btintel_pcie_msix_tx_handle(struct btintel_pcie_data *data) urbd0 = &txq->urbd0s[cr_tia]; - if (urbd0->tfd_index > txq->count) + if (urbd0->tfd_index >= txq->count) return; cr_tia = (cr_tia + 1) % txq->count; @@ -1537,7 +1537,9 @@ static int btintel_pcie_submit_rx_work(struct btintel_pcie_data *data, u8 status rfh_hdr = buf; len = rfh_hdr->packet_len; - if (len <= 0) { + if (len == 0 || len > BTINTEL_PCIE_BUFFER_SIZE - sizeof(*rfh_hdr)) { + bt_dev_err(data->hdev, "Invalid packet_len %d (max %zu)", len, + BTINTEL_PCIE_BUFFER_SIZE - sizeof(*rfh_hdr)); ret = -EINVAL; goto resubmit; } @@ -1634,6 +1636,9 @@ static irqreturn_t btintel_pcie_irq_msix_handler(int irq, void *dev_id) if (unlikely(!(intr_fh | intr_hw))) { /* Ignore interrupt, inta == 0 */ + bt_warn_ratelimited("Bluetooth: btintel_pcie: Received spurious interrupt\n"); + btintel_pcie_wr_reg32(data, BTINTEL_PCIE_CSR_MSIX_AUTOMASK_ST, + BIT(entry->entry)); return IRQ_NONE; } diff --git a/drivers/bluetooth/btmtk.c b/drivers/bluetooth/btmtk.c index c0ed51567ed4dd..26d525acd65907 100644 --- a/drivers/bluetooth/btmtk.c +++ b/drivers/bluetooth/btmtk.c @@ -1374,16 +1374,6 @@ int btmtk_usb_setup(struct hci_dev *hdev) break; case 0x7922: case 0x7925: - /* - * A remote wakeup could cause the device completely unresponsive, and - * recovering from such a state needs a power cycle. - * - * Since the remote wakeup capability is super broken, just disable it - * to get rid of the troubles. The device can still be autosuspended - * when the bluetooth interface is closed. - */ - device_set_wakeup_capable(&btmtk_data->udev->dev, false); - fallthrough; case 0x7961: case 0x7902: case 0x6639: @@ -1587,5 +1577,6 @@ MODULE_FIRMWARE(FIRMWARE_MT7663); MODULE_FIRMWARE(FIRMWARE_MT7668); MODULE_FIRMWARE(FIRMWARE_MT7922); MODULE_FIRMWARE(FIRMWARE_MT7961); +MODULE_FIRMWARE(FIRMWARE_MT7920); MODULE_FIRMWARE(FIRMWARE_MT7925); MODULE_FIRMWARE(FIRMWARE_MT7927); diff --git a/drivers/bluetooth/btmtk.h b/drivers/bluetooth/btmtk.h index c83c24897c9541..bc26148ec5442a 100644 --- a/drivers/bluetooth/btmtk.h +++ b/drivers/bluetooth/btmtk.h @@ -7,6 +7,7 @@ #define FIRMWARE_MT7922 "mediatek/BT_RAM_CODE_MT7922_1_1_hdr.bin" #define FIRMWARE_MT7902 "mediatek/BT_RAM_CODE_MT7902_1_1_hdr.bin" #define FIRMWARE_MT7961 "mediatek/BT_RAM_CODE_MT7961_1_2_hdr.bin" +#define FIRMWARE_MT7920 "mediatek/BT_RAM_CODE_MT7961_1a_2_hdr.bin" #define FIRMWARE_MT7925 "mediatek/mt7925/BT_RAM_CODE_MT7925_1_1_hdr.bin" #define FIRMWARE_MT7927 "mediatek/mt7927/BT_RAM_CODE_MT6639_2_1_hdr.bin" diff --git a/drivers/bluetooth/btqcomsmd.c b/drivers/bluetooth/btqcomsmd.c index d2e13fcb6babfc..d669ea4eb3eb07 100644 --- a/drivers/bluetooth/btqcomsmd.c +++ b/drivers/bluetooth/btqcomsmd.c @@ -188,7 +188,10 @@ static int btqcomsmd_probe(struct platform_device *pdev) return 0; hci_free_dev: + rpmsg_destroy_ept(btq->cmd_channel); + rpmsg_destroy_ept(btq->acl_channel); hci_free_dev(hdev); + return ret; destroy_cmd_channel: rpmsg_destroy_ept(btq->cmd_channel); destroy_acl_channel: @@ -202,10 +205,11 @@ static void btqcomsmd_remove(struct platform_device *pdev) struct btqcomsmd *btq = platform_get_drvdata(pdev); hci_unregister_dev(btq->hdev); - hci_free_dev(btq->hdev); rpmsg_destroy_ept(btq->cmd_channel); rpmsg_destroy_ept(btq->acl_channel); + + hci_free_dev(btq->hdev); } static const struct of_device_id btqcomsmd_of_match[] = { diff --git a/drivers/bluetooth/btrtl.c b/drivers/bluetooth/btrtl.c index 03fa9409e3ee49..d29813331603ba 100644 --- a/drivers/bluetooth/btrtl.c +++ b/drivers/bluetooth/btrtl.c @@ -591,7 +591,7 @@ static int rtlbt_parse_firmware_v2(struct hci_dev *hdev, * headers. */ if (!key_id) - break; + continue; rc = btrtl_parse_section(hdev, btrtl_dev, opcode, ptr, section_len); break; @@ -600,8 +600,7 @@ static int rtlbt_parse_firmware_v2(struct hci_dev *hdev, ptr, section_len); break; default: - rc = 0; - break; + continue; } if (rc < 0) { rtl_dev_err(hdev, "RTL: Parse section (%u) err %d", diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index a3d6d3194b15b6..84f55f67523e0a 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -6,6 +6,7 @@ * Copyright (C) 2005-2008 Marcel Holtmann */ +#include #include #include #include @@ -968,6 +969,8 @@ struct qca_dump_info { #define BTUSB_USE_ALT3_FOR_WBS 15 #define BTUSB_ALT6_CONTINUOUS_TX 16 #define BTUSB_HW_SSR_ACTIVE 17 +#define BTUSB_WAKEUP_BROKEN 18 +#define BTUSB_RESET 19 struct btusb_data { struct hci_dev *hdev; @@ -1044,13 +1047,15 @@ static void btusb_reset(struct hci_dev *hdev) int err; data = hci_get_drvdata(hdev); - /* This is not an unbalanced PM reference since the device will reset */ err = usb_autopm_get_interface(data->intf); if (err) { bt_dev_err(hdev, "Failed usb_autopm_get_interface: %d", err); return; } + if (test_and_set_bit(BTUSB_RESET, &data->flags)) + usb_autopm_put_interface_no_suspend(data->intf); + bt_dev_err(hdev, "Resetting usb device."); usb_queue_reset_device(data->intf); } @@ -2072,18 +2077,24 @@ static int btusb_close(struct hci_dev *hdev) BT_DBG("%s", hdev->name); - cancel_delayed_work(&data->rx_work); cancel_work_sync(&data->work); cancel_work_sync(&data->waker); - skb_queue_purge(&data->acl_q); - clear_bit(BTUSB_ISOC_RUNNING, &data->flags); clear_bit(BTUSB_BULK_RUNNING, &data->flags); clear_bit(BTUSB_INTR_RUNNING, &data->flags); clear_bit(BTUSB_DIAG_RUNNING, &data->flags); btusb_stop_traffic(data); + + /* rx_work must only be canceled once the URBs that can rearm it are + * gone, and it must be canceled synchronously since btusb_disconnect() + * frees the btusb_data it dereferences right after hci_unregister_dev(). + */ + cancel_delayed_work_sync(&data->rx_work); + + skb_queue_purge(&data->acl_q); + btusb_free_frags(data); err = usb_autopm_get_interface(data->intf); @@ -2109,7 +2120,7 @@ static int btusb_flush(struct hci_dev *hdev) BT_DBG("%s", hdev->name); - cancel_delayed_work(&data->rx_work); + cancel_delayed_work_sync(&data->rx_work); skb_queue_purge(&data->acl_q); @@ -2903,8 +2914,11 @@ static int btusb_mtk_reset(struct hci_dev *hdev, void *rst_data) } err = usb_autopm_get_interface(data->intf); - if (err < 0) + if (err < 0) { + bt_dev_err(hdev, "Failed usb_autopm_get_interface: %d", err); + clear_bit(BTMTK_HW_RESET_ACTIVE, &btmtk_data->flags); return err; + } /* Release MediaTek ISO data interface */ btusb_mtk_release_iso_intf(hdev); @@ -2927,6 +2941,11 @@ static int btusb_mtk_reset(struct hci_dev *hdev, void *rst_data) err = btmtk_usb_subsys_reset(hdev, btmtk_data->dev_id); + if (test_and_set_bit(BTUSB_RESET, &data->flags)) { + bt_dev_err(hdev, "last usb reset failed? Resetting again"); + usb_autopm_put_interface_no_suspend(data->intf); + } + usb_queue_reset_device(data->intf); clear_bit(BTMTK_HW_RESET_ACTIVE, &btmtk_data->flags); @@ -2950,10 +2969,25 @@ static int btusb_send_frame_mtk(struct hci_dev *hdev, struct sk_buff *skb) } } +static inline bool platform_is_ryzen(void) +{ +#ifdef CONFIG_X86 + return boot_cpu_has(X86_FEATURE_ZEN); +#else + return false; +#endif +} + +static inline bool is_direct_child_of_root_hub(struct usb_device *udev) +{ + return udev->parent == udev->bus->root_hub; +} + static int btusb_mtk_setup(struct hci_dev *hdev) { struct btusb_data *data = hci_get_drvdata(hdev); struct btmtk_data *btmtk_data = hci_get_priv(hdev); + int err; /* MediaTek WMT vendor cmd requiring below USB resources to * complete the handshake. @@ -2970,7 +3004,40 @@ static int btusb_mtk_setup(struct hci_dev *hdev) btusb_mtk_claim_iso_intf(data); } - return btmtk_usb_setup(hdev); + err = btmtk_usb_setup(hdev); + if (err) + return err; + + switch (btmtk_data->dev_id) { + case 0x7922: + case 0x7925: + /* + * All reports seen to be relevant to Ryzen-based laptops. These + * NICs are usually used as OEM components thanks to some sort + * of reference designs. + * + * Their popularity on other platforms is unclear. While there + * is still a chance that the quirk may exist on other + * platforms, be cautious and only apply the quirk to direct + * children of Ryzen platforms's root hubs for the time being. + * + * In most cases the root hub is on the SoC or PCH, which needs + * the quirk. Unfortunately, this can't distinguish root hubs on + * PCIe add-in cards. Such roughness should be acceptable, as + * PCIe USB controller add-in cards are less commonly used + * nowadays. On the other hand, applying the quirk doesn't hurt + * any functionalities either, as the device can still be used + * as a wakeup source if desired. + * + * Theoretically, we could retrieve the root hub's PCI vendor ID + * with some hierarchy magic, but that's too intrusive... + */ + if (platform_is_ryzen() && is_direct_child_of_root_hub(data->udev)) + set_bit(BTUSB_WAKEUP_BROKEN, &data->flags); + break; + } + + return 0; } static int btusb_mtk_shutdown(struct hci_dev *hdev) @@ -4516,6 +4583,9 @@ static void btusb_disconnect(struct usb_interface *intf) if (data->reset_gpio) gpiod_put(data->reset_gpio); + if (test_and_clear_bit(BTUSB_RESET, &data->flags)) + usb_autopm_put_interface_no_suspend(data->intf); + if (intf == data->intf) { if (data->isoc) usb_driver_release_interface(&btusb_driver, data->isoc); @@ -4541,11 +4611,26 @@ static int btusb_suspend(struct usb_interface *intf, pm_message_t message) BT_DBG("intf %p", intf); - /* Don't auto-suspend if there are connections or discovery in - * progress; external suspend calls shall never fail. + /* + * It is reported that remote wakeup events could sometimes cause some + * adapters completely unresponsive. Resetting the xHCI root hub doesn't + * help at all, and recovering from such a state needs a power cycle. + * Since disabling remote wakeup simply causes the USB core to gate + * runtime autosuspend as well due to needs_remote_wakeup == 1, let's do + * this ourselves to make our life easier. The interface can be safely + * autosuspended as long as remote wakeup is disabled, i.e., after + * closing the HCI device. + * + * Don't auto-suspend if there are connections or discovery in progress. + * + * External suspend calls shall never fail. Specifically, a device with + * broken remote wakeup may still take the advantage of remote wakeup in + * order to wake up the system from sleep if userspace has enabled it as + * a wakeup source. */ if (PMSG_IS_AUTO(message) && - (hci_conn_count(data->hdev) || hci_discovery_active(data->hdev))) + ((test_bit(BTUSB_WAKEUP_BROKEN, &data->flags) && data->intf->needs_remote_wakeup) || + hci_conn_count(data->hdev) || hci_discovery_active(data->hdev))) return -EBUSY; if (data->suspend_count++) diff --git a/drivers/bluetooth/hci_mrvl.c b/drivers/bluetooth/hci_mrvl.c index 516b8f74c43406..5798a8db016ee0 100644 --- a/drivers/bluetooth/hci_mrvl.c +++ b/drivers/bluetooth/hci_mrvl.c @@ -307,9 +307,8 @@ static int mrvl_load_firmware(struct hci_dev *hdev, const char *name) err = wait_on_bit_timeout(&mrvl->flags, STATE_FW_REQ_PENDING, TASK_INTERRUPTIBLE, msecs_to_jiffies(2000)); - if (err == 1) { + if (err == -EINTR) { bt_dev_err(hdev, "Firmware load interrupted"); - err = -EINTR; break; } else if (err) { bt_dev_err(hdev, "Firmware request timeout"); diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c index 198b9731416803..1ec5b25d1a9aeb 100644 --- a/drivers/char/virtio_console.c +++ b/drivers/char/virtio_console.c @@ -1891,13 +1891,28 @@ static const struct file_operations portdev_fops = { static void remove_vqs(struct ports_device *portdev) { struct virtqueue *vq; + bool multiport = use_multiport(portdev); virtio_device_for_each_vq(portdev->vdev, vq) { struct port_buffer *buf; + unsigned int len; - flush_bufs(vq, true); - while ((buf = virtqueue_detach_unused_buf(vq))) - free_buf(buf, true); + /* + * c_ovq cookies are &portdev->cpkt, not port_buffer. + * Detach them but do not free_buf(). + */ + if (multiport && vq == portdev->c_ovq) { + spin_lock(&portdev->c_ovq_lock); + while (virtqueue_get_buf(vq, &len)) + ; + while (virtqueue_detach_unused_buf(vq)) + ; + spin_unlock(&portdev->c_ovq_lock); + } else { + flush_bufs(vq, true); + while ((buf = virtqueue_detach_unused_buf(vq))) + free_buf(buf, true); + } cond_resched(); } portdev->vdev->config->del_vqs(portdev->vdev); diff --git a/drivers/clk/ux500/clk-prcmu.c b/drivers/clk/ux500/clk-prcmu.c index ddc86551bf5749..ac96c46bd1bbf7 100644 --- a/drivers/clk/ux500/clk-prcmu.c +++ b/drivers/clk/ux500/clk-prcmu.c @@ -7,7 +7,7 @@ */ #include -#include +#include #include #include #include @@ -35,13 +35,13 @@ static int clk_prcmu_prepare(struct clk_hw *hw) { struct clk_prcmu *clk = to_clk_prcmu(hw); - return prcmu_request_clock(clk->cg_sel, true); + return db8500_prcmu_request_clock(clk->cg_sel, true); } static void clk_prcmu_unprepare(struct clk_hw *hw) { struct clk_prcmu *clk = to_clk_prcmu(hw); - if (prcmu_request_clock(clk->cg_sel, false)) + if (db8500_prcmu_request_clock(clk->cg_sel, false)) pr_err("clk_prcmu: %s failed to disable %s.\n", __func__, clk_hw_get_name(hw)); } @@ -86,7 +86,7 @@ static int clk_prcmu_opp_prepare(struct clk_hw *hw) clk->opp_requested = 1; } - err = prcmu_request_clock(clk->cg_sel, true); + err = db8500_prcmu_request_clock(clk->cg_sel, true); if (err) { prcmu_qos_remove_requirement(PRCMU_QOS_APE_OPP, (char *)clk_hw_get_name(hw)); @@ -101,7 +101,7 @@ static void clk_prcmu_opp_unprepare(struct clk_hw *hw) { struct clk_prcmu *clk = to_clk_prcmu(hw); - if (prcmu_request_clock(clk->cg_sel, false)) { + if (db8500_prcmu_request_clock(clk->cg_sel, false)) { pr_err("clk_prcmu: %s failed to disable %s.\n", __func__, clk_hw_get_name(hw)); return; @@ -120,7 +120,7 @@ static int clk_prcmu_opp_volt_prepare(struct clk_hw *hw) struct clk_prcmu *clk = to_clk_prcmu(hw); if (!clk->opp_requested) { - err = prcmu_request_ape_opp_100_voltage(true); + err = db8500_prcmu_request_ape_opp_100_voltage(true); if (err) { pr_err("clk_prcmu: %s fail req APE OPP VOLT for %s.\n", __func__, clk_hw_get_name(hw)); @@ -129,9 +129,9 @@ static int clk_prcmu_opp_volt_prepare(struct clk_hw *hw) clk->opp_requested = 1; } - err = prcmu_request_clock(clk->cg_sel, true); + err = db8500_prcmu_request_clock(clk->cg_sel, true); if (err) { - prcmu_request_ape_opp_100_voltage(false); + db8500_prcmu_request_ape_opp_100_voltage(false); clk->opp_requested = 0; return err; } @@ -143,14 +143,14 @@ static void clk_prcmu_opp_volt_unprepare(struct clk_hw *hw) { struct clk_prcmu *clk = to_clk_prcmu(hw); - if (prcmu_request_clock(clk->cg_sel, false)) { + if (db8500_prcmu_request_clock(clk->cg_sel, false)) { pr_err("clk_prcmu: %s failed to disable %s.\n", __func__, clk_hw_get_name(hw)); return; } if (clk->opp_requested) { - prcmu_request_ape_opp_100_voltage(false); + db8500_prcmu_request_ape_opp_100_voltage(false); clk->opp_requested = 0; } } diff --git a/drivers/clk/ux500/u8500_of_clk.c b/drivers/clk/ux500/u8500_of_clk.c index 6f78808387b101..d2499815226f0a 100644 --- a/drivers/clk/ux500/u8500_of_clk.c +++ b/drivers/clk/ux500/u8500_of_clk.c @@ -9,7 +9,7 @@ #include #include #include -#include +#include #include "clk.h" #include "prcc.h" diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index b898b6544069f8..196c50f26fe0d6 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -1249,7 +1249,7 @@ static struct cpufreq_policy *cpufreq_policy_alloc(unsigned int cpu) if (!policy) return NULL; - if (!alloc_cpumask_var(&policy->cpus, GFP_KERNEL)) + if (!zalloc_cpumask_var(&policy->cpus, GFP_KERNEL)) goto err_free_policy; if (!zalloc_cpumask_var(&policy->related_cpus, GFP_KERNEL)) @@ -1258,6 +1258,8 @@ static struct cpufreq_policy *cpufreq_policy_alloc(unsigned int cpu) if (!zalloc_cpumask_var(&policy->real_cpus, GFP_KERNEL)) goto err_free_rcpumask; + init_rwsem(&policy->rwsem); + init_completion(&policy->kobj_unregister); ret = kobject_init_and_add(&policy->kobj, &ktype_cpufreq, cpufreq_global_kobject, "policy%u", cpu); @@ -1272,8 +1274,6 @@ static struct cpufreq_policy *cpufreq_policy_alloc(unsigned int cpu) goto err_free_real_cpus; } - init_rwsem(&policy->rwsem); - freq_constraints_init(&policy->constraints); policy->nb_min.notifier_call = cpufreq_notifier_min; diff --git a/drivers/cpuidle/cpuidle-ux500.c b/drivers/cpuidle/cpuidle-ux500.c index f7d778580e9be6..6d6c52c0bcc2d7 100644 --- a/drivers/cpuidle/cpuidle-ux500.c +++ b/drivers/cpuidle/cpuidle-ux500.c @@ -11,7 +11,7 @@ #include #include #include -#include +#include #include #include @@ -66,7 +66,7 @@ static inline int ux500_enter_idle(struct cpuidle_device *dev, /* Go to the retention state, the prcmu will wait for the * cpu to go WFI and this is what happens after exiting this * 'master' critical section */ - if (prcmu_set_power_state(PRCMU_AP_IDLE, true, true)) + if (db8500_prcmu_set_power_state(PRCMU_AP_IDLE, true, true)) goto out; /* When we switch to retention, the prcmu is in charge @@ -109,7 +109,7 @@ static struct cpuidle_driver ux500_idle_driver = { static int dbx500_cpuidle_probe(struct platform_device *pdev) { /* Configure wake up reasons */ - prcmu_enable_wakeups(PRCMU_WAKEUP(ARM) | PRCMU_WAKEUP(RTC) | + db8500_prcmu_enable_wakeups(PRCMU_WAKEUP(ARM) | PRCMU_WAKEUP(RTC) | PRCMU_WAKEUP(ABB)); return cpuidle_register(&ux500_idle_driver, NULL); diff --git a/drivers/dibs/dibs_main.c b/drivers/dibs/dibs_main.c index 2b53a9d277dcaf..20c50997a7cf23 100644 --- a/drivers/dibs/dibs_main.c +++ b/drivers/dibs/dibs_main.c @@ -251,13 +251,19 @@ static int __init dibs_init(void) rc = class_register(&dibs_class); if (rc) - return rc; + goto err; rc = dibs_loopback_init(); if (rc) - pr_err("%s fails with %d\n", __func__, rc); + goto err_unregister; return rc; + +err_unregister: + class_unregister(&dibs_class); +err: + pr_err("%s fails with %d\n", __func__, rc); + return rc; } static void __exit dibs_exit(void) diff --git a/drivers/edac/altera_edac.c b/drivers/edac/altera_edac.c index 4edd2088c2db6f..5914b2fd94d9c5 100644 --- a/drivers/edac/altera_edac.c +++ b/drivers/edac/altera_edac.c @@ -1533,7 +1533,7 @@ static int altr_portb_setup(struct altr_edac_device_dev *device) altdev = dci->pvt_info; *altdev = *device; - if (!devres_open_group(&altdev->ddev, altr_portb_setup, GFP_KERNEL)) + if (!devres_open_group(device->edac->dev, altr_portb_setup, GFP_KERNEL)) return -ENOMEM; /* Update PortB specific values */ @@ -1562,7 +1562,7 @@ static int altr_portb_setup(struct altr_edac_device_dev *device) rc = -ENODEV; goto err_release_group_1; } - rc = devm_request_irq(&altdev->ddev, altdev->sb_irq, + rc = devm_request_irq(device->edac->dev, altdev->sb_irq, prv->ecc_irq_handler, IRQF_TRIGGER_HIGH, ecc_name, altdev); if (rc) { @@ -1585,7 +1585,7 @@ static int altr_portb_setup(struct altr_edac_device_dev *device) rc = -ENODEV; goto err_release_group_1; } - rc = devm_request_irq(&altdev->ddev, altdev->db_irq, + rc = devm_request_irq(device->edac->dev, altdev->db_irq, prv->ecc_irq_handler, IRQF_TRIGGER_HIGH, ecc_name, altdev); if (rc) { @@ -1605,13 +1605,13 @@ static int altr_portb_setup(struct altr_edac_device_dev *device) list_add(&altdev->next, &altdev->edac->a10_ecc_devices); - devres_remove_group(&altdev->ddev, altr_portb_setup); + devres_remove_group(device->edac->dev, altr_portb_setup); return 0; err_release_group_1: edac_device_free_ctl_info(dci); - devres_release_group(&altdev->ddev, altr_portb_setup); + devres_release_group(device->edac->dev, altr_portb_setup); edac_printk(KERN_ERR, EDAC_DEVICE, "%s:Error setting up EDAC device: %d\n", ecc_name, rc); return rc; diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c index c6aa69dbd9fb12..475235c402e888 100644 --- a/drivers/edac/amd64_edac.c +++ b/drivers/edac/amd64_edac.c @@ -4173,6 +4173,8 @@ static int __init amd64_edac_init(void) goto err_pci; } + request_module_nowait("amd_atl"); + /* register stuff with EDAC MCE */ if (boot_cpu_data.x86 >= 0x17) { amd_register_ecc_decoder(decode_umc_error); diff --git a/drivers/edac/edac_device_sysfs.c b/drivers/edac/edac_device_sysfs.c index b1c2717cd0237b..6995ce039db97d 100644 --- a/drivers/edac/edac_device_sysfs.c +++ b/drivers/edac/edac_device_sysfs.c @@ -88,14 +88,21 @@ static ssize_t edac_device_ctl_poll_msec_store(struct edac_device_ctl_info *ctl_info, const char *data, size_t count) { - unsigned long value; + unsigned int value; + int ret; /* get the value and enforce that it is non-zero, must be at least * one millisecond for the delay period, between scans * Then cancel last outstanding delay for the work request * and set a new one. */ - value = simple_strtoul(data, NULL, 0); + ret = kstrtouint(data, 0, &value); + if (ret < 0) + return ret; + + if (value < 1) + return -EINVAL; + edac_device_reset_delay_period(ctl_info, value); return count; diff --git a/drivers/edac/igen6_edac.c b/drivers/edac/igen6_edac.c index f1fc20d4ebf611..12d718a50e1c9b 100644 --- a/drivers/edac/igen6_edac.c +++ b/drivers/edac/igen6_edac.c @@ -175,8 +175,6 @@ static struct res_config { /* Set imc->dimm_{l_size,s_size,l_map}[chan]. */ void (*set_dimm_params)(struct igen6_imc *imc, int chan); bool (*ibecc_available)(struct pci_dev *pdev); - /* Extract error address logged in IBECC */ - u64 (*err_addr)(u64 ecclog); /* Convert error address logged in IBECC to system physical address */ u64 (*err_addr_to_sys_addr)(u64 eaddr, int mc); /* Convert error address logged in IBECC to integrated memory controller address */ @@ -522,11 +520,6 @@ static u64 adl_err_addr_to_imc_addr(u64 eaddr, int mc) return imc_addr; } -static u64 rpl_p_err_addr(u64 ecclog) -{ - return field_get(res_cfg->reg_eccerrlog_addr_mask, ecclog); -} - static enum mem_type ptl_h_get_mem_type(struct igen6_imc *imc) { u32 mtype, val; @@ -716,22 +709,6 @@ static struct res_config adl_n_cfg = { .err_addr_to_imc_addr = adl_err_addr_to_imc_addr, }; -static struct res_config rpl_p_cfg = { - .machine_check = true, - .num_imc = 2, - .reg_mchbar_mask = GENMASK_ULL(41, 17), - .reg_tom_mask = GENMASK_ULL(41, 20), - .reg_touud_mask = GENMASK_ULL(41, 20), - .reg_eccerrlog_addr_mask = GENMASK_ULL(45, 5), - .imc_base = 0xd800, - .ibecc_base = 0xd400, - .ibecc_error_log_offset = 0x68, - .ibecc_available = tgl_ibecc_available, - .err_addr = rpl_p_err_addr, - .err_addr_to_sys_addr = adl_err_addr_to_sys_addr, - .err_addr_to_imc_addr = adl_err_addr_to_imc_addr, -}; - static struct res_config mtl_ps_cfg = { .machine_check = true, .num_imc = 2, @@ -877,11 +854,11 @@ static struct pci_device_id igen6_pci_tbl[] = { { PCI_VDEVICE(INTEL, DID_ASL_SKU1), .driver_data = (kernel_ulong_t)&adl_n_cfg }, { PCI_VDEVICE(INTEL, DID_ASL_SKU2), .driver_data = (kernel_ulong_t)&adl_n_cfg }, { PCI_VDEVICE(INTEL, DID_ASL_SKU3), .driver_data = (kernel_ulong_t)&adl_n_cfg }, - { PCI_VDEVICE(INTEL, DID_RPL_P_SKU1), .driver_data = (kernel_ulong_t)&rpl_p_cfg }, - { PCI_VDEVICE(INTEL, DID_RPL_P_SKU2), .driver_data = (kernel_ulong_t)&rpl_p_cfg }, - { PCI_VDEVICE(INTEL, DID_RPL_P_SKU3), .driver_data = (kernel_ulong_t)&rpl_p_cfg }, - { PCI_VDEVICE(INTEL, DID_RPL_P_SKU4), .driver_data = (kernel_ulong_t)&rpl_p_cfg }, - { PCI_VDEVICE(INTEL, DID_RPL_P_SKU5), .driver_data = (kernel_ulong_t)&rpl_p_cfg }, + { PCI_VDEVICE(INTEL, DID_RPL_P_SKU1), .driver_data = (kernel_ulong_t)&adl_cfg }, + { PCI_VDEVICE(INTEL, DID_RPL_P_SKU2), .driver_data = (kernel_ulong_t)&adl_cfg }, + { PCI_VDEVICE(INTEL, DID_RPL_P_SKU3), .driver_data = (kernel_ulong_t)&adl_cfg }, + { PCI_VDEVICE(INTEL, DID_RPL_P_SKU4), .driver_data = (kernel_ulong_t)&adl_cfg }, + { PCI_VDEVICE(INTEL, DID_RPL_P_SKU5), .driver_data = (kernel_ulong_t)&adl_cfg }, { PCI_VDEVICE(INTEL, DID_MTL_PS_SKU1), .driver_data = (kernel_ulong_t)&mtl_ps_cfg }, { PCI_VDEVICE(INTEL, DID_MTL_PS_SKU2), .driver_data = (kernel_ulong_t)&mtl_ps_cfg }, { PCI_VDEVICE(INTEL, DID_MTL_PS_SKU3), .driver_data = (kernel_ulong_t)&mtl_ps_cfg }, @@ -1009,14 +986,22 @@ static void set_dimm_params(struct igen6_imc *imc, int chan) static int decode_chan_idx(u64 addr, u64 mask, int intlv_bit) { - u64 hash_addr = addr & mask, hash = 0; - u64 intlv = (addr >> intlv_bit) & 1; + u64 hash_addr, hash = 0; int i; + /* + * In hash mode, the @intlv_bit is the lowest selected bit of @addr + * to be XORed. While @mask may or may not include this @intlv_bit, + * we enforce that @mask includes @intlv_bit to ensure @intlv_bit is + * XORed exactly once. + */ + mask |= 1 << intlv_bit; + hash_addr = addr & mask; + for (i = 6; i < 20; i++) hash ^= (hash_addr >> i) & 1; - return (int)hash ^ intlv; + return (int)hash; } static u64 decode_channel_addr(u64 addr, int intlv_bit) @@ -1035,19 +1020,18 @@ static void decode_addr(u64 addr, u32 hash, u64 s_size, int l_map, { int intlv_bit = CHANNEL_HASH_LSB_MASK_BIT(hash) + 6; - if (addr > 2 * s_size) { + if (addr >= 2 * s_size) { *sub_addr = addr - s_size; *idx = l_map; return; } - if (CHANNEL_HASH_MODE(hash)) { - *sub_addr = decode_channel_addr(addr, intlv_bit); + *sub_addr = decode_channel_addr(addr, intlv_bit); + + if (CHANNEL_HASH_MODE(hash)) *idx = decode_chan_idx(addr, CHANNEL_HASH_MASK(hash), intlv_bit); - } else { - *sub_addr = decode_channel_addr(addr, 6); - *idx = GET_BITFIELD(addr, 6, 6); - } + else + *idx = GET_BITFIELD(addr, intlv_bit, intlv_bit); } static int igen6_decode(struct decoded_addr *res) @@ -1230,11 +1214,7 @@ static void ecclog_work_cb(struct work_struct *work) llist_for_each_entry_safe(node, tmp, head, llnode) { memset(&res, 0, sizeof(res)); - if (res_cfg->err_addr) - eaddr = res_cfg->err_addr(node->ecclog); - else - eaddr = node->ecclog & res_cfg->reg_eccerrlog_addr_mask; - + eaddr = node->ecclog & res_cfg->reg_eccerrlog_addr_mask; res.mc = node->mc; res.sys_addr = res_cfg->err_addr_to_sys_addr(eaddr, res.mc); res.imc_addr = res_cfg->err_addr_to_imc_addr(eaddr, res.mc); diff --git a/drivers/gpu/drm/adp/Kconfig b/drivers/gpu/drm/adp/Kconfig index 9fcc27eb200dbc..acfa21ee06d228 100644 --- a/drivers/gpu/drm/adp/Kconfig +++ b/drivers/gpu/drm/adp/Kconfig @@ -6,7 +6,6 @@ config DRM_ADP select DRM_KMS_HELPER select DRM_BRIDGE_CONNECTOR select DRM_DISPLAY_HELPER - select DRM_KMS_DMA_HELPER select DRM_GEM_DMA_HELPER select DRM_PANEL_BRIDGE select VIDEOMODE_HELPERS diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index eaa86e32912e59..ea416749138d84 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -190,6 +190,8 @@ amdgpu_ttm_job_submit(struct amdgpu_device *adev, struct amdgpu_ttm_buffer_entit * @tmz: if we should setup a TMZ enabled mapping * @size: in number of bytes to map, out number of bytes mapped * @addr: resulting address inside the MC address space + * @vm_needs_flush: out, set true if a GART window was programmed (VMID 0 flush + * needed) or false for a direct address * * Setup one of the GART windows to access a specific piece of memory or return * the physical address for local memory. @@ -199,7 +201,8 @@ static int amdgpu_ttm_map_buffer(struct amdgpu_ttm_buffer_entity *entity, struct ttm_resource *mem, struct amdgpu_res_cursor *mm_cur, unsigned int window, - bool tmz, uint64_t *size, uint64_t *addr) + bool tmz, uint64_t *size, uint64_t *addr, + bool *vm_needs_flush) { struct amdgpu_device *adev = amdgpu_ttm_adev(bo->bdev); unsigned int offset, num_pages, num_dw, num_bytes; @@ -220,9 +223,12 @@ static int amdgpu_ttm_map_buffer(struct amdgpu_ttm_buffer_entity *entity, if (!tmz && mem->start != AMDGPU_BO_INVALID_OFFSET) { *addr = amdgpu_ttm_domain_start(adev, mem->mem_type) + mm_cur->start; + *vm_needs_flush = false; return 0; } + /* A GART window is programmed below, so its VMID 0 TLB needs a flush */ + *vm_needs_flush = true; /* * If start begins at an offset inside the page, then adjust the size @@ -322,6 +328,7 @@ static int amdgpu_ttm_copy_mem_to_mem(struct amdgpu_device *adev, while (src_mm.remaining) { uint64_t from, to, cur_size, tiling_flags; uint32_t num_type, data_format, max_com, write_compress_disable; + bool src_vm_flush, dst_vm_flush; struct dma_fence *next; /* Never copy more than 256MiB at once to avoid a timeout */ @@ -329,12 +336,12 @@ static int amdgpu_ttm_copy_mem_to_mem(struct amdgpu_device *adev, /* Map src to window 0 and dst to window 1. */ r = amdgpu_ttm_map_buffer(entity, src->bo, src->mem, &src_mm, - 0, tmz, &cur_size, &from); + 0, tmz, &cur_size, &from, &src_vm_flush); if (r) goto error; r = amdgpu_ttm_map_buffer(entity, dst->bo, dst->mem, &dst_mm, - 1, tmz, &cur_size, &to); + 1, tmz, &cur_size, &to, &dst_vm_flush); if (r) goto error; @@ -362,7 +369,7 @@ static int amdgpu_ttm_copy_mem_to_mem(struct amdgpu_device *adev, } r = amdgpu_copy_buffer(adev, entity, from, to, cur_size, resv, - &next, true, copy_flags); + &next, src_vm_flush || dst_vm_flush, copy_flags); if (r) goto error; @@ -2580,6 +2587,7 @@ int amdgpu_ttm_clear_buffer(struct amdgpu_ttm_buffer_entity *entity, struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev); struct dma_fence *fence = NULL; struct amdgpu_res_cursor dst; + bool vm_needs_flush = false; int r; if (!entity) @@ -2601,13 +2609,13 @@ int amdgpu_ttm_clear_buffer(struct amdgpu_ttm_buffer_entity *entity, cur_size = min(dst.size, 256ULL << 20); r = amdgpu_ttm_map_buffer(entity, &bo->tbo, bo->tbo.resource, &dst, - 0, false, &cur_size, &to); + 0, false, &cur_size, &to, &vm_needs_flush); if (r) goto error; r = amdgpu_ttm_fill_mem(adev, entity, 0, to, cur_size, resv, - &next, true, k_job_id); + &next, vm_needs_flush, k_job_id); if (r) goto error; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 170c6b8d0a5f67..5ba196dd9d7add 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -3925,6 +3925,10 @@ static int dm_resume(struct amdgpu_ip_block *ip_block) /* On resume we need to rewrite the MSTM control bits to enable MST*/ s3_handle_mst(ddev, false); + /* Exit IPS before the detection loop's first AUX/DDC access. */ + scoped_guard(mutex, &dm->dc_lock) + dc_exit_ips_for_hw_access(dm->dc); + /* Do detection*/ drm_connector_list_iter_begin(ddev, &iter); drm_for_each_connector_iter(connector, &iter) { @@ -6891,10 +6895,14 @@ get_output_color_space(const struct dc_crtc_timing *dc_crtc_timing, break; case DRM_MODE_COLORIMETRY_BT2020_RGB: case DRM_MODE_COLORIMETRY_BT2020_YCC: - if (dc_crtc_timing->pixel_encoding == PIXEL_ENCODING_RGB) - color_space = COLOR_SPACE_2020_RGB_FULLRANGE; - else + if (dc_crtc_timing->pixel_encoding == PIXEL_ENCODING_RGB) { + if (connector_state->hdmi.broadcast_rgb == DRM_HDMI_BROADCAST_RGB_LIMITED) + color_space = COLOR_SPACE_2020_RGB_LIMITEDRANGE; + else + color_space = COLOR_SPACE_2020_RGB_FULLRANGE; + } else { color_space = COLOR_SPACE_2020_YCBCR_LIMITED; + } break; case DRM_MODE_COLORIMETRY_DEFAULT: // ITU601 default: diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c index 7db38ad3f84879..8b0fe5c3a3e8c9 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c @@ -196,7 +196,6 @@ static ssize_t dp_link_settings_read(struct file *f, char __user *buf, char *rd_buf_ptr = NULL; const uint32_t rd_buf_size = 100; uint32_t result = 0; - uint8_t str_len = 0; int r; if (*pos & 3 || size & 3) @@ -208,29 +207,26 @@ static ssize_t dp_link_settings_read(struct file *f, char __user *buf, rd_buf_ptr = rd_buf; - str_len = strlen("Current: %d 0x%x %d "); - snprintf(rd_buf_ptr, str_len, "Current: %d 0x%x %d ", + rd_buf_ptr += scnprintf(rd_buf_ptr, rd_buf_size - (rd_buf_ptr - rd_buf), + "Current: %d 0x%x %d ", link->cur_link_settings.lane_count, link->cur_link_settings.link_rate, link->cur_link_settings.link_spread); - rd_buf_ptr += str_len; - str_len = strlen("Verified: %d 0x%x %d "); - snprintf(rd_buf_ptr, str_len, "Verified: %d 0x%x %d ", + rd_buf_ptr += scnprintf(rd_buf_ptr, rd_buf_size - (rd_buf_ptr - rd_buf), + "Verified: %d 0x%x %d ", link->verified_link_cap.lane_count, link->verified_link_cap.link_rate, link->verified_link_cap.link_spread); - rd_buf_ptr += str_len; - str_len = strlen("Reported: %d 0x%x %d "); - snprintf(rd_buf_ptr, str_len, "Reported: %d 0x%x %d ", + rd_buf_ptr += scnprintf(rd_buf_ptr, rd_buf_size - (rd_buf_ptr - rd_buf), + "Reported: %d 0x%x %d ", link->reported_link_cap.lane_count, link->reported_link_cap.link_rate, link->reported_link_cap.link_spread); - rd_buf_ptr += str_len; - str_len = strlen("Preferred: %d 0x%x %d "); - snprintf(rd_buf_ptr, str_len, "Preferred: %d 0x%x %d\n", + rd_buf_ptr += scnprintf(rd_buf_ptr, rd_buf_size - (rd_buf_ptr - rd_buf), + "Preferred: %d 0x%x %d\n", link->preferred_link_setting.lane_count, link->preferred_link_setting.link_rate, link->preferred_link_setting.link_spread); diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c index 41aa8f9bb152bb..fe5b97e6f9603e 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c @@ -197,6 +197,7 @@ enum dc_edid_status dm_helpers_parse_edid_caps( edid_caps->edid_hdmi = connector->display_info.is_hdmi; if (edid_caps->edid_hdmi) { + edid_caps->qs_bit = connector->display_info.rgb_quant_range_selectable; populate_hdmi_info_from_connector(link->dc->config.enable_frl, &connector->display_info.hdmi, edid_caps); drm_dbg_driver(connector->dev, "%s: HDMI_FRL [%s] max_frl_rate %d\n", __func__, connector->name, edid_caps->max_frl_rate); if (edid_caps->frl_dsc_support) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index e25b94b65daca5..ebfed18e780c59 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -3122,6 +3122,7 @@ static struct surface_update_descriptor check_update_surfaces_for_stream( } if ((stream_update->hdr_static_metadata && !stream_update->stream->use_dynamic_meta) || + stream_update->output_color_space || stream_update->vrr_infopacket || stream_update->vsc_infopacket || stream_update->vsp_infopacket || @@ -4090,6 +4091,7 @@ static void commit_planes_do_stream_update_sequence(struct dc *dc, hwss_add_setup_periodic_interrupt(&seq_state, dc, pipe_ctx); if ((stream_update->hdr_static_metadata && !stream->use_dynamic_meta) || + stream_update->output_color_space || stream_update->vrr_infopacket || stream_update->vsc_infopacket || stream_update->vsp_infopacket || @@ -4272,6 +4274,7 @@ static void commit_planes_do_stream_update(struct dc *dc, dc->hwss.setup_periodic_interrupt(dc, pipe_ctx); if ((stream_update->hdr_static_metadata && !stream->use_dynamic_meta) || + stream_update->output_color_space || stream_update->vrr_infopacket || stream_update->vsc_infopacket || stream_update->vsp_infopacket || diff --git a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c index e5e89294958a87..68a1e78cd4b821 100644 --- a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c +++ b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c @@ -348,7 +348,8 @@ int amdgpu_dpm_switch_power_profile(struct amdgpu_device *adev, const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs; int ret = 0; - if (amdgpu_sriov_vf(adev)) + if (amdgpu_sriov_vf(adev) || + amdgpu_in_reset(adev)) return 0; if (pp_funcs && pp_funcs->switch_power_profile) { @@ -367,7 +368,8 @@ int amdgpu_dpm_pause_power_profile(struct amdgpu_device *adev, const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs; int ret = 0; - if (amdgpu_sriov_vf(adev)) + if (amdgpu_sriov_vf(adev) || + amdgpu_in_reset(adev)) return 0; if (pp_funcs && pp_funcs->pause_power_profile) { diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c index 0be34fbdac266d..4177211f32dcaf 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c @@ -2094,8 +2094,6 @@ static ssize_t smu_v13_0_0_get_gpu_metrics(struct smu_context *smu, if ((mp1_ver == IP_VERSION(13, 0, 0) && smu->smc_fw_version <= 0x004e1e00) || (mp1_ver == IP_VERSION(13, 0, 10) && smu->smc_fw_version <= 0x00500800)) gpu_metrics->energy_accumulator = metrics->EnergyAccumulator; - else - gpu_metrics->energy_accumulator = UINT_MAX; if (metrics->AverageGfxActivity <= SMU_13_0_0_BUSY_THRESHOLD) gpu_metrics->average_gfxclk_frequency = metrics->AverageGfxclkFrequencyPostDs; diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c index 5d11ed8be4c323..845bd00c9df856 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c @@ -2096,8 +2096,8 @@ static ssize_t smu_v13_0_7_get_gpu_metrics(struct smu_context *smu, metrics->Vcn1ActivityPercentage); gpu_metrics->average_socket_power = metrics->AverageSocketPower; - gpu_metrics->energy_accumulator = smu->smc_fw_version <= 0x00521400 ? - metrics->EnergyAccumulator : UINT_MAX; + if (smu->smc_fw_version <= 0x00521400) + gpu_metrics->energy_accumulator = metrics->EnergyAccumulator; if (metrics->AverageGfxActivity <= SMU_13_0_7_BUSY_THRESHOLD) gpu_metrics->average_gfxclk_frequency = metrics->AverageGfxclkFrequencyPostDs; diff --git a/drivers/gpu/drm/bridge/tc358768.c b/drivers/gpu/drm/bridge/tc358768.c index 0f2820b3730292..d18136a4b5c6d5 100644 --- a/drivers/gpu/drm/bridge/tc358768.c +++ b/drivers/gpu/drm/bridge/tc358768.c @@ -1262,10 +1262,13 @@ tc358768_atomic_get_input_bus_fmts(struct drm_bridge *bridge, return input_fmts; } -static bool tc358768_mode_fixup(struct drm_bridge *bridge, - const struct drm_display_mode *mode, - struct drm_display_mode *adjusted_mode) +static int tc358768_bridge_atomic_check(struct drm_bridge *bridge, + struct drm_bridge_state *bridge_state, + struct drm_crtc_state *crtc_state, + struct drm_connector_state *conn_state) { + struct drm_display_mode *adjusted_mode = &crtc_state->adjusted_mode; + /* Default to positive sync */ if (!(adjusted_mode->flags & @@ -1276,13 +1279,15 @@ static bool tc358768_mode_fixup(struct drm_bridge *bridge, (DRM_MODE_FLAG_PVSYNC | DRM_MODE_FLAG_NVSYNC))) adjusted_mode->flags |= DRM_MODE_FLAG_PVSYNC; - return true; + bridge_state->input_bus_cfg.flags = bridge->timings->input_bus_flags; + + return 0; } static const struct drm_bridge_funcs tc358768_bridge_funcs = { .attach = tc358768_bridge_attach, .mode_valid = tc358768_bridge_mode_valid, - .mode_fixup = tc358768_mode_fixup, + .atomic_check = tc358768_bridge_atomic_check, .atomic_pre_enable = tc358768_bridge_atomic_pre_enable, .atomic_enable = tc358768_bridge_atomic_enable, .atomic_disable = tc358768_bridge_atomic_disable, diff --git a/drivers/gpu/drm/bridge/ti-sn65dsi83.c b/drivers/gpu/drm/bridge/ti-sn65dsi83.c index 42b451432bbb61..9f530cd05d2f32 100644 --- a/drivers/gpu/drm/bridge/ti-sn65dsi83.c +++ b/drivers/gpu/drm/bridge/ti-sn65dsi83.c @@ -403,7 +403,7 @@ retry: drm_modeset_drop_locks(&ctx); drm_modeset_acquire_fini(&ctx); - return 0; + return err; } static void sn65dsi83_reset_work(struct work_struct *ws) @@ -419,11 +419,13 @@ static void sn65dsi83_reset_work(struct work_struct *ws) ret = sn65dsi83_reset_pipe(ctx); if (ret) { dev_err(ctx->dev, "reset pipe failed %pe\n", ERR_PTR(ret)); - return; + goto bridge_exit; } + if (ctx->irq) enable_irq(ctx->irq); +bridge_exit: drm_bridge_exit(idx); } diff --git a/drivers/gpu/drm/drm_exec.c b/drivers/gpu/drm/drm_exec.c index 7988f5e7d56a3e..2abc5c623fffd2 100644 --- a/drivers/gpu/drm/drm_exec.c +++ b/drivers/gpu/drm/drm_exec.c @@ -322,6 +322,19 @@ int drm_exec_prepare_array(struct drm_exec *exec, { int ret; + /* + * Make sure to lock a contended object even when no objects are + * given, otherwise drm_exec_retry_on_contention() would loop + * forever on patterns like: + * + * ret = drm_exec_prepare_array(exec, objs, num_objects, ...); + * drm_exec_retry_on_contention(exec); + * + * with num_objects == 0. + */ + if (!num_objects) + return drm_exec_lock_contended(exec); + for (unsigned int i = 0; i < num_objects; ++i) { ret = drm_exec_prepare_obj(exec, objects[i], num_fences); if (unlikely(ret)) diff --git a/drivers/gpu/drm/drm_pagemap.c b/drivers/gpu/drm/drm_pagemap.c index 05eb7254028f76..89e1ddff84dd28 100644 --- a/drivers/gpu/drm/drm_pagemap.c +++ b/drivers/gpu/drm/drm_pagemap.c @@ -1195,12 +1195,117 @@ void drm_pagemap_put(struct drm_pagemap *dpagemap) } EXPORT_SYMBOL(drm_pagemap_put); +/** + * drm_pagemap_page_get_flags() - Read flags from a device-private folio + * @page: Pointer to a page of the device-private folio + * + * Return: The DRM_PAGEMAP_ZDD_FLAG_* bits encoded in zone_device_data. + */ +static unsigned long drm_pagemap_page_get_flags(struct page *page) +{ + struct folio *folio = page_folio(page); + + return (unsigned long)folio_zone_device_data(folio) & + DRM_PAGEMAP_ZDD_FLAG_MASK; +} + +/** + * drm_pagemap_page_set_flags() - Set flags on a device-private folio + * @page: Pointer to a page of the device-private folio + * @flags: DRM_PAGEMAP_ZDD_FLAG_* bits to set + * + * Preserve any flags already encoded alongside the ZDD pointer. + */ +static void drm_pagemap_page_set_flags(struct page *page, + unsigned long flags) +{ + struct folio *folio = page_folio(page); + unsigned long old; + + if (WARN_ON_ONCE(flags & ~DRM_PAGEMAP_ZDD_FLAG_MASK)) + return; + + old = (unsigned long)folio_zone_device_data(folio); + folio_set_zone_device_data(folio, (void *)(old | flags)); +} + +/** + * drm_pagemap_retire_migrated_pages() - Record migrated device-private folios + * @src_pfns: source array after migrate_vma_pages() or migrate_device_pages() + * @npages: number of entries in @src_pfns + * + * Flag device-private folios successfully migrated to RAM before finalize + * unlocks the sources. The migrated state is stored in the physical folio, so + * it survives later folio splits and subsequent migrations can skip it. + */ +static void drm_pagemap_retire_migrated_pages(unsigned long *src_pfns, + unsigned long npages) +{ + unsigned long i = 0; + + while (i < npages) { + struct page *page = migrate_pfn_to_page(src_pfns[i]); + unsigned long nr = 1; + + if (!page) { + i++; + continue; + } + + if (src_pfns[i] & MIGRATE_PFN_COMPOUND) + nr = folio_nr_pages(page_folio(page)); + + if ((src_pfns[i] & MIGRATE_PFN_MIGRATE) && + is_device_private_page(page)) + drm_pagemap_page_set_flags(page, + DRM_PAGEMAP_ZDD_FLAG_MIGRATED); + + i += nr; + } +} + +/** + * drm_pagemap_skip_retired_pages() - Skip retired device-private folios + * @src_pfns: MIGRATE_PFN-encoded source array + * @npages: number of entries in @src_pfns + * + * Skip source folios already migrated to RAM, identified by the migrated flag + * stored in the physical folio's zone_device_data. + */ +static void drm_pagemap_skip_retired_pages(unsigned long *src_pfns, + unsigned long npages) +{ + unsigned long i = 0; + + while (i < npages) { + struct page *page = migrate_pfn_to_page(src_pfns[i]); + unsigned long nr = 1; + + if (!page) { + i++; + continue; + } + + if (src_pfns[i] & MIGRATE_PFN_COMPOUND) + nr = folio_nr_pages(page_folio(page)); + + if ((src_pfns[i] & MIGRATE_PFN_MIGRATE) && + is_device_private_page(page) && + (drm_pagemap_page_get_flags(page) & + DRM_PAGEMAP_ZDD_FLAG_MIGRATED)) + src_pfns[i] &= ~MIGRATE_PFN_MIGRATE; + + i += nr; + } +} + /** * drm_pagemap_evict_to_ram() - Evict GPU SVM range to RAM * @devmem_allocation: Pointer to the device memory allocation * - * Similar to __drm_pagemap_migrate_to_ram but does not require mmap lock and - * migration done via migrate_device_* functions. + * Similar to __drm_pagemap_migrate_to_ram(), but uses the + * migrate_device_* helpers and does not require the mmap lock. + * Device-private PFNs already migrated to RAM by either path are skipped. * * Return: 0 on success, negative error code on failure. */ @@ -1208,7 +1313,7 @@ int drm_pagemap_evict_to_ram(struct drm_pagemap_devmem *devmem_allocation) { const struct drm_pagemap_devmem_ops *ops = devmem_allocation->ops; struct drm_pagemap_iova_state state = {}; - unsigned long npages, mpages = 0; + unsigned long npages, mpages; struct page **pages; unsigned long *src, *dst; struct drm_pagemap_addr *pagemap_addr; @@ -1219,6 +1324,7 @@ int drm_pagemap_evict_to_ram(struct drm_pagemap_devmem *devmem_allocation) npages = devmem_allocation->size >> PAGE_SHIFT; retry: + mpages = 0; if (!mmget_not_zero(devmem_allocation->mm)) return -EFAULT; @@ -1241,6 +1347,8 @@ retry: if (err) goto err_free; + drm_pagemap_skip_retired_pages(src, npages); + err = drm_pagemap_migrate_populate_ram_pfn(NULL, NULL, npages, &mpages, src, dst, 0); if (err || !mpages) @@ -1263,6 +1371,7 @@ err_finalize: if (err) drm_pagemap_migration_unlock_put_pages(npages, dst); migrate_device_pages(src, dst, npages); + drm_pagemap_retire_migrated_pages(src, npages); migrate_device_finalize(src, dst, npages); drm_pagemap_migrate_unmap_pages(devmem_allocation->dev, pagemap_addr, dst, npages, DMA_FROM_DEVICE, &state); @@ -1360,13 +1469,15 @@ static int __drm_pagemap_migrate_to_ram(struct vm_area_struct *vas, if (!migrate.cpages) goto err_free; + drm_pagemap_skip_retired_pages(migrate.src, npages); + ops = zdd->devmem_allocation->ops; dev = zdd->devmem_allocation->dev; err = drm_pagemap_migrate_populate_ram_pfn(vas, page, npages, &mpages, migrate.src, migrate.dst, start); - if (err) + if (err || !mpages) goto err_finalize; err = drm_pagemap_migrate_map_system_pages(dev, pagemap_addr, @@ -1386,6 +1497,7 @@ err_finalize: if (err) drm_pagemap_migration_unlock_put_pages(npages, migrate.dst); migrate_vma_pages(&migrate); + drm_pagemap_retire_migrated_pages(migrate.src, npages); migrate_vma_finalize(&migrate); if (dev) drm_pagemap_migrate_unmap_pages(dev, pagemap_addr, migrate.dst, @@ -1438,13 +1550,19 @@ static vm_fault_t drm_pagemap_migrate_to_ram(struct vm_fault *vmf) static void drm_pagemap_folio_split(struct folio *orig_folio, struct folio *new_folio) { struct drm_pagemap_zdd *zdd; + unsigned long orig_data, new_data; if (!new_folio) return; new_folio->pgmap = orig_folio->pgmap; - zdd = folio_zone_device_data(orig_folio); - folio_set_zone_device_data(new_folio, drm_pagemap_zdd_get(zdd)); + + orig_data = (unsigned long)folio_zone_device_data(orig_folio); + zdd = (struct drm_pagemap_zdd *)(orig_data & ~DRM_PAGEMAP_ZDD_FLAG_MASK); + + new_data = (unsigned long)drm_pagemap_zdd_get(zdd); + new_data |= orig_data & DRM_PAGEMAP_ZDD_FLAG_MASK; + folio_set_zone_device_data(new_folio, (void *)new_data); } static const struct dev_pagemap_ops drm_pagemap_pagemap_ops = { diff --git a/drivers/gpu/drm/drm_panic_qr.rs b/drivers/gpu/drm/drm_panic_qr.rs index ac27e86c601c8c..4d7eb75a3afc15 100644 --- a/drivers/gpu/drm/drm_panic_qr.rs +++ b/drivers/gpu/drm/drm_panic_qr.rs @@ -407,8 +407,8 @@ impl DecFifo { for i in (0..self.len).rev() { self.decimals[i + len] = self.decimals[i]; } - for i in 0..len { - self.decimals[i] = (chunk % 10) as u8; + for decimal in &mut self.decimals[..len] { + *decimal = (chunk % 10) as u8; chunk = div10(chunk); } self.len += len; diff --git a/drivers/gpu/drm/gud/gud_drv.c b/drivers/gpu/drm/gud/gud_drv.c index 89bd6ca36003f3..3a1b9e2a2eaa19 100644 --- a/drivers/gpu/drm/gud/gud_drv.c +++ b/drivers/gpu/drm/gud/gud_drv.c @@ -289,6 +289,8 @@ static int gud_plane_add_properties(struct gud_device *gdrm) * but mask out any additions on future devices. */ val &= GUD_ROTATION_MASK; + if (!(val & GUD_ROTATION_0)) + continue; ret = drm_plane_create_rotation_property(&gdrm->plane, DRM_MODE_ROTATE_0, val); break; diff --git a/drivers/gpu/drm/i915/display/intel_cdclk.c b/drivers/gpu/drm/i915/display/intel_cdclk.c index 7bc9b956554ba3..40ecad20d32be5 100644 --- a/drivers/gpu/drm/i915/display/intel_cdclk.c +++ b/drivers/gpu/drm/i915/display/intel_cdclk.c @@ -2366,8 +2366,10 @@ static void bxt_sanitize_cdclk(struct intel_display *display) * dividers both syncing to an active pipe, or asynchronously * (PIPE_NONE). */ - cdctl &= ~bxt_cdclk_cd2x_pipe(display, INVALID_PIPE); - cdctl |= bxt_cdclk_cd2x_pipe(display, INVALID_PIPE); + if (DISPLAY_VER(display) < 30) { + cdctl &= ~bxt_cdclk_cd2x_pipe(display, INVALID_PIPE); + cdctl |= bxt_cdclk_cd2x_pipe(display, INVALID_PIPE); + } if (cdctl != expected) { if (DISPLAY_VER(display) < 20) { @@ -2697,8 +2699,8 @@ static void intel_set_cdclk(struct intel_display *display, } } -static bool dg2_power_well_count(struct intel_display *display, - const struct intel_cdclk_state *cdclk_state) +static int dg2_power_well_count(struct intel_display *display, + const struct intel_cdclk_state *cdclk_state) { return display->platform.dg2 ? hweight8(cdclk_state->active_pipes) : 0; } diff --git a/drivers/gpu/drm/i915/display/intel_display_types.h b/drivers/gpu/drm/i915/display/intel_display_types.h index c21e0c0ef0b121..96422641ae441b 100644 --- a/drivers/gpu/drm/i915/display/intel_display_types.h +++ b/drivers/gpu/drm/i915/display/intel_display_types.h @@ -1947,6 +1947,8 @@ struct intel_dp { bool colorimetry_support; + bool sst_split_sdp_support; + struct { enum transcoder transcoder; struct mutex lock; diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c index 5733d2e7ac7f13..ba0b19d1163cf9 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.c +++ b/drivers/gpu/drm/i915/display/intel_dp.c @@ -3518,12 +3518,22 @@ intel_dp_audio_compute_config(struct intel_encoder *encoder, struct intel_crtc_state *pipe_config, struct drm_connector_state *conn_state) { + struct intel_dp *intel_dp = enc_to_intel_dp(encoder); + pipe_config->has_audio = intel_dp_has_audio(encoder, conn_state) && intel_audio_compute_config(encoder, pipe_config, conn_state); pipe_config->sdp_split_enable = pipe_config->has_audio && intel_dp_is_uhbr(pipe_config); + + /* + * SDP splitting for UHBR audio requires explicit sink capability in + * SST mode, whereas in MST mode it is inherently supported. + */ + if (pipe_config->sdp_split_enable && + !intel_crtc_has_type(pipe_config, INTEL_OUTPUT_DP_MST)) + pipe_config->sdp_split_enable = intel_dp->sst_split_sdp_support; } void @@ -4566,16 +4576,25 @@ void intel_dp_configure_protocol_converter(struct intel_dp *intel_dp, str_enable_disable(tmp)); } -static bool intel_dp_get_colorimetry_status(struct intel_dp *intel_dp) +static u8 intel_dp_read_dprx_feature_enum(struct intel_dp *intel_dp) { u8 dprx = 0; - if (drm_dp_dpcd_readb(&intel_dp->aux, DP_DPRX_FEATURE_ENUMERATION_LIST, - &dprx) != 1) - return false; + drm_dp_dpcd_read_data(&intel_dp->aux, DP_DPRX_FEATURE_ENUMERATION_LIST, + &dprx, sizeof(dprx)); + return dprx; +} + +static bool intel_dp_get_colorimetry_status(u8 dprx) +{ return dprx & DP_VSC_SDP_EXT_FOR_COLORIMETRY_SUPPORTED; } +static bool intel_dp_get_sst_split_sdp_status(u8 dprx) +{ + return dprx & DP_SST_SPLIT_SDP_CAP; +} + static int intel_dp_read_dsc_dpcd(struct drm_dp_aux *aux, u8 dsc_dpcd[DP_DSC_RECEIVER_CAP_SIZE]) { @@ -4875,6 +4894,7 @@ intel_edp_init_dpcd(struct intel_dp *intel_dp, struct intel_connector *connector { struct intel_display *display = to_intel_display(intel_dp); int ret; + u8 dprx; /* this function is meant to be called only once */ drm_WARN_ON(display->drm, intel_dp->dpcd[DP_DPCD_REV] != 0); @@ -4886,8 +4906,13 @@ intel_edp_init_dpcd(struct intel_dp *intel_dp, struct intel_connector *connector drm_dp_is_branch(intel_dp->dpcd)); intel_init_dpcd_quirks(intel_dp, &intel_dp->desc.ident); + dprx = intel_dp_read_dprx_feature_enum(intel_dp); + intel_dp->colorimetry_support = - intel_dp_get_colorimetry_status(intel_dp); + intel_dp_get_colorimetry_status(dprx); + + intel_dp->sst_split_sdp_support = + intel_dp_get_sst_split_sdp_status(dprx); /* * Read the eDP display control registers. @@ -4978,13 +5003,20 @@ intel_dp_get_dpcd(struct intel_dp *intel_dp) * the OUI/ID since we know it won't change. */ if (!intel_dp_is_edp(intel_dp)) { + u8 dprx; + drm_dp_read_desc(&intel_dp->aux, &intel_dp->desc, drm_dp_is_branch(intel_dp->dpcd)); intel_init_dpcd_quirks(intel_dp, &intel_dp->desc.ident); + dprx = intel_dp_read_dprx_feature_enum(intel_dp); + intel_dp->colorimetry_support = - intel_dp_get_colorimetry_status(intel_dp); + intel_dp_get_colorimetry_status(dprx); + + intel_dp->sst_split_sdp_support = + intel_dp_get_sst_split_sdp_status(dprx); intel_dp_update_sink_caps(intel_dp); } diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.c b/drivers/gpu/drm/i915/display/intel_dp_mst.c index 0aa3e6b4c781d8..bcdc504913471a 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_mst.c +++ b/drivers/gpu/drm/i915/display/intel_dp_mst.c @@ -722,10 +722,6 @@ static int mst_stream_compute_config(struct intel_encoder *encoder, pipe_config->sink_format = INTEL_OUTPUT_FORMAT_RGB; pipe_config->output_format = INTEL_OUTPUT_FORMAT_RGB; - ret = intel_pfit_compute_config(pipe_config, conn_state); - if (ret) - return ret; - ret = intel_pfit_compute_config(pipe_config, conn_state); if (ret) return ret; diff --git a/drivers/gpu/drm/i915/i915_query.c b/drivers/gpu/drm/i915/i915_query.c index 0c55fb6e9727d6..11157fb14db313 100644 --- a/drivers/gpu/drm/i915/i915_query.c +++ b/drivers/gpu/drm/i915/i915_query.c @@ -403,8 +403,10 @@ static int query_perf_config_list(struct drm_i915_private *i915, ids = krealloc(oa_config_ids, n_configs * sizeof(*oa_config_ids), GFP_KERNEL); - if (!ids) + if (!ids) { + kfree(oa_config_ids); return -ENOMEM; + } alloc = fetch_and_zero(&n_configs); diff --git a/drivers/gpu/drm/logicvc/Kconfig b/drivers/gpu/drm/logicvc/Kconfig index 579a358ed5cf33..11aae1626199bc 100644 --- a/drivers/gpu/drm/logicvc/Kconfig +++ b/drivers/gpu/drm/logicvc/Kconfig @@ -4,7 +4,6 @@ config DRM_LOGICVC depends on OF || COMPILE_TEST select DRM_CLIENT_SELECTION select DRM_KMS_HELPER - select DRM_KMS_DMA_HELPER select DRM_GEM_DMA_HELPER select REGMAP select REGMAP_MMIO diff --git a/drivers/gpu/drm/rockchip/Kconfig b/drivers/gpu/drm/rockchip/Kconfig index e7f49fe845eaec..4e58685f58ff9e 100644 --- a/drivers/gpu/drm/rockchip/Kconfig +++ b/drivers/gpu/drm/rockchip/Kconfig @@ -68,6 +68,7 @@ config ROCKCHIP_CDN_DP config ROCKCHIP_DW_DP bool "Rockchip specific extensions for Synopsys DW DP" + select DRM_BRIDGE_CONNECTOR help This selects support for Rockchip SoC specific extensions to enable Synopsys DesignWare Cores based DisplayPort transmit @@ -145,6 +146,8 @@ config ROCKCHIP_RGB config ROCKCHIP_RK3066_HDMI bool "Rockchip specific extensions for RK3066 HDMI" depends on DRM_ROCKCHIP + select DRM_DISPLAY_HELPER + select DRM_BRIDGE_CONNECTOR help This selects support for Rockchip SoC specific extensions for the RK3066 HDMI driver. If you want to enable diff --git a/drivers/gpu/drm/rockchip/analogix_dp-rockchip.c b/drivers/gpu/drm/rockchip/analogix_dp-rockchip.c index b1ed25cefe5ed2..d638785ee5abca 100644 --- a/drivers/gpu/drm/rockchip/analogix_dp-rockchip.c +++ b/drivers/gpu/drm/rockchip/analogix_dp-rockchip.c @@ -241,10 +241,11 @@ static void rockchip_dp_drm_encoder_enable(struct drm_encoder *encoder, of_graph_get_remote_port(endpoint.local_node); of_property_read_u32(remote_port, "reg", &port_id); - sprintf(name, "%s vp%d", remote_port_parent->full_name, port_id); + snprintf(name, sizeof(name), "%s vp%d", + remote_port_parent->full_name, port_id); } else { - sprintf(name, "%s %s", - remote_port_parent->full_name, endpoint.id ? "vopl" : "vopb"); + snprintf(name, sizeof(name), "%s %s", + remote_port_parent->full_name, endpoint.id ? "vopl" : "vopb"); } DRM_DEV_DEBUG(dp->dev, "vop %s output to dp\n", (ret) ? "LIT" : "BIG"); diff --git a/drivers/gpu/drm/scheduler/tests/mock_scheduler.c b/drivers/gpu/drm/scheduler/tests/mock_scheduler.c index 8e9ae7d980eb2e..2dfa3efef2100f 100644 --- a/drivers/gpu/drm/scheduler/tests/mock_scheduler.c +++ b/drivers/gpu/drm/scheduler/tests/mock_scheduler.c @@ -1,6 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2025 Valve Corporation */ +#include + #include "sched_tests.h" /* @@ -288,6 +290,7 @@ static const struct drm_sched_backend_ops drm_mock_scheduler_ops = { */ struct drm_mock_scheduler *drm_mock_sched_new(struct kunit *test, long timeout) { + static unsigned int instance; struct drm_sched_init_args args = { .ops = &drm_mock_scheduler_ops, .num_rqs = DRM_SCHED_PRIORITY_COUNT, @@ -297,11 +300,19 @@ struct drm_mock_scheduler *drm_mock_sched_new(struct kunit *test, long timeout) .name = "drm-mock-scheduler", }; struct drm_mock_scheduler *sched; + struct device *dev; + char name[64]; int ret; sched = kunit_kzalloc(test, sizeof(*sched), GFP_KERNEL); KUNIT_ASSERT_NOT_NULL(test, sched); + snprintf(name, sizeof(name), "%s-%u", args.name, instance++); + dev = kunit_device_register(test, name); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, dev); + + args.dev = dev; + ret = drm_sched_init(&sched->base, &args); KUNIT_ASSERT_EQ(test, ret, 0); diff --git a/drivers/gpu/drm/tiny/cirrus-qemu.c b/drivers/gpu/drm/tiny/cirrus-qemu.c index 075221b431d376..3bf23fcf657496 100644 --- a/drivers/gpu/drm/tiny/cirrus-qemu.c +++ b/drivers/gpu/drm/tiny/cirrus-qemu.c @@ -582,6 +582,9 @@ static int cirrus_pci_probe(struct pci_dev *pdev, struct cirrus_device *cirrus; int ret; + if (pci_resource_len(pdev, 0) < CIRRUS_VRAM_SIZE) + return -ENODEV; + ret = aperture_remove_conflicting_pci_devices(pdev, cirrus_driver.name); if (ret) return ret; diff --git a/drivers/gpu/drm/virtio/virtgpu_display.c b/drivers/gpu/drm/virtio/virtgpu_display.c index 44ffffec550fdc..85ea252c658e32 100644 --- a/drivers/gpu/drm/virtio/virtgpu_display.c +++ b/drivers/gpu/drm/virtio/virtgpu_display.c @@ -344,7 +344,7 @@ virtio_gpu_user_framebuffer_create(struct drm_device *dev, if (ret) { kfree(virtio_gpu_fb); drm_gem_object_put(obj); - return NULL; + return ERR_PTR(ret); } return &virtio_gpu_fb->base; diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.h b/drivers/gpu/drm/virtio/virtgpu_drv.h index 7449907754a430..88fb4be92cf3ef 100644 --- a/drivers/gpu/drm/virtio/virtgpu_drv.h +++ b/drivers/gpu/drm/virtio/virtgpu_drv.h @@ -43,6 +43,8 @@ #include #include +#include + #define DRIVER_NAME "virtio_gpu" #define DRIVER_DESC "virtio GPU" @@ -60,6 +62,24 @@ /* See virtio_gpu_ctx_create. One additional character for NULL terminator. */ #define DEBUG_NAME_MAX_LEN 65 +/* + * Whether the host must be told about resource backing pages by DMA address + * rather than guest-physical address. + * + * This mirrors vring_use_map_api() in drivers/virtio/virtio_ring.c, including + * its xen_domain() case. + */ +static inline bool virtio_gpu_use_dma_api(const struct virtio_device *vdev) +{ + if (!virtio_has_dma_quirk(vdev)) + return true; + + if (xen_domain()) + return true; + + return false; +} + struct virtio_gpu_object_params { unsigned long size; bool dumb; diff --git a/drivers/gpu/drm/virtio/virtgpu_object.c b/drivers/gpu/drm/virtio/virtgpu_object.c index ec9efacc691959..1527c62be88ba8 100644 --- a/drivers/gpu/drm/virtio/virtgpu_object.c +++ b/drivers/gpu/drm/virtio/virtgpu_object.c @@ -163,7 +163,7 @@ static int virtio_gpu_object_shmem_init(struct virtio_gpu_device *vgdev, struct virtio_gpu_mem_entry **ents, unsigned int *nents) { - bool use_dma_api = !virtio_has_dma_quirk(vgdev->vdev); + bool use_dma_api = virtio_gpu_use_dma_api(vgdev->vdev); struct scatterlist *sg; struct sg_table *pages; int si; diff --git a/drivers/gpu/drm/virtio/virtgpu_vq.c b/drivers/gpu/drm/virtio/virtgpu_vq.c index e5e1af8b8e8a0a..2b7af8e4e9e618 100644 --- a/drivers/gpu/drm/virtio/virtgpu_vq.c +++ b/drivers/gpu/drm/virtio/virtgpu_vq.c @@ -724,7 +724,7 @@ int virtio_gpu_panic_cmd_transfer_to_host_2d(struct virtio_gpu_device *vgdev, struct virtio_gpu_object *bo = gem_to_virtio_gpu_obj(objs->objs[0]); struct virtio_gpu_transfer_to_host_2d *cmd_p; struct virtio_gpu_vbuffer *vbuf; - bool use_dma_api = !virtio_has_dma_quirk(vgdev->vdev); + bool use_dma_api = virtio_gpu_use_dma_api(vgdev->vdev); if (virtio_gpu_is_shmem(bo) && use_dma_api) dma_sync_sgtable_for_device(vgdev->vdev->dev.parent, @@ -755,7 +755,7 @@ void virtio_gpu_cmd_transfer_to_host_2d(struct virtio_gpu_device *vgdev, struct virtio_gpu_object *bo = gem_to_virtio_gpu_obj(objs->objs[0]); struct virtio_gpu_transfer_to_host_2d *cmd_p; struct virtio_gpu_vbuffer *vbuf; - bool use_dma_api = !virtio_has_dma_quirk(vgdev->vdev); + bool use_dma_api = virtio_gpu_use_dma_api(vgdev->vdev); if (virtio_gpu_is_shmem(bo) && use_dma_api) dma_sync_sgtable_for_device(vgdev->vdev->dev.parent, @@ -1188,7 +1188,7 @@ void virtio_gpu_cmd_transfer_to_host_3d(struct virtio_gpu_device *vgdev, struct virtio_gpu_object *bo = gem_to_virtio_gpu_obj(objs->objs[0]); struct virtio_gpu_transfer_host_3d *cmd_p; struct virtio_gpu_vbuffer *vbuf; - bool use_dma_api = !virtio_has_dma_quirk(vgdev->vdev); + bool use_dma_api = virtio_gpu_use_dma_api(vgdev->vdev); if (virtio_gpu_is_shmem(bo) && use_dma_api) dma_sync_sgtable_for_device(vgdev->vdev->dev.parent, diff --git a/drivers/gpu/drm/xe/Makefile b/drivers/gpu/drm/xe/Makefile index 8e7b146880f465..a11c619080659a 100644 --- a/drivers/gpu/drm/xe/Makefile +++ b/drivers/gpu/drm/xe/Makefile @@ -152,7 +152,9 @@ xe-y += xe_bb.o \ xe_wait_user_fence.o \ xe_wopcm.o -xe-$(CONFIG_I2C) += xe_i2c.o +xe-$(CONFIG_I2C) += xe_i2c.o \ + xe_amc.o + xe-$(CONFIG_DRM_XE_GPUSVM) += xe_svm.o xe-$(CONFIG_DRM_GPUSVM) += xe_userptr.o diff --git a/drivers/gpu/drm/xe/instructions/xe_gpu_commands.h b/drivers/gpu/drm/xe/instructions/xe_gpu_commands.h index 18d0fde8c98f95..faf8d7e2c5c11d 100644 --- a/drivers/gpu/drm/xe/instructions/xe_gpu_commands.h +++ b/drivers/gpu/drm/xe/instructions/xe_gpu_commands.h @@ -46,6 +46,7 @@ #define GFX_OP_PIPE_CONTROL(len) ((0x3<<29)|(0x3<<27)|(0x2<<24)|((len)-2)) #define PIPE_CONTROL0_QUEUE_DRAIN_MODE BIT(12) +#define PIPE_CONTROL0_UNTYPED_DATAPORT_CACHE_FLUSH BIT(11) /* gen12 */ #define PIPE_CONTROL0_L3_READ_ONLY_CACHE_INVALIDATE BIT(10) /* gen12 */ #define PIPE_CONTROL0_HDC_PIPELINE_FLUSH BIT(9) /* gen12 */ diff --git a/drivers/gpu/drm/xe/regs/xe_i2c_regs.h b/drivers/gpu/drm/xe/regs/xe_i2c_regs.h index f2e455e2bfe45c..37550e4a20f804 100644 --- a/drivers/gpu/drm/xe/regs/xe_i2c_regs.h +++ b/drivers/gpu/drm/xe/regs/xe_i2c_regs.h @@ -20,4 +20,6 @@ #define I2C_CONFIG_CMD XE_REG(I2C_CONFIG_SPACE_OFFSET + PCI_COMMAND) #define I2C_CONFIG_PMCSR XE_REG(I2C_CONFIG_SPACE_OFFSET + 0x84) +#define I2C_REG(reg) XE_REG((reg) + I2C_MEM_SPACE_OFFSET) + #endif /* _XE_I2C_REGS_H_ */ diff --git a/drivers/gpu/drm/xe/xe_amc.c b/drivers/gpu/drm/xe/xe_amc.c new file mode 100644 index 00000000000000..8ecadee6eea39e --- /dev/null +++ b/drivers/gpu/drm/xe/xe_amc.c @@ -0,0 +1,197 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2026 Intel Corporation. + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +#include "regs/xe_i2c_regs.h" + +#include "xe_amc.h" +#include "xe_device.h" +#include "xe_i2c.h" +#include "xe_mmio.h" + +/** + * DOC: Add-In Management Controller (AMC) + * + * Handler for the SMBus Alerts from the AMC. All the alerts from AMC will cause + * the device to be declared wedged. + */ + +#define AMC_COMMAND 0x0f +#define AMC_GPU_I2C_ADDR 0x8f +#define AMC_VERSION_V1 0x01 +#define AMC_DESTINATION_ID 12 +#define AMC_SOURCE_ID 8 +#define AMC_FLAGS 0xc8 + +#define AMC_MSG_TYPE 0x7e +#define AMC_GET_ALERT_REASON 0x01 + +enum xe_amc_alert { + AMC_ALERT_UNKNOWN, + AMC_ALERT_FW_DOWNLOAD, + AMC_ALERT_THERMAL_TRIP, + AMC_ALERT_OOB_REQUEST, + AMC_ALERT_OOB_RESET, + AMC_ALERT_CATERR, +}; + +static const char * const amc_alert[] = { + [AMC_ALERT_FW_DOWNLOAD] = "Firmware Download", + [AMC_ALERT_THERMAL_TRIP] = "Thermal Trip", + [AMC_ALERT_OOB_REQUEST] = "OOB Request", + [AMC_ALERT_OOB_RESET] = "OOB Reset", + [AMC_ALERT_CATERR] = "Catastrophic", +}; + +struct xe_amc { + struct xe_i2c *i2c; + struct work_struct work; +}; + +struct amc_header { + u8 command; + u8 len; + u8 address; + u8 version; + u8 destination; + u8 source; + u8 flags; +} __packed; + +struct amc_message { + u8 type; + u16 vendor; + u8 command; +} __packed; + +struct amc_request { + struct amc_header header; + struct amc_message message; + u32 reserved; +} __packed; + +struct amc_response { + struct amc_header header; + struct amc_message message; + u8 error; + u8 value; +} __packed; + +static const struct amc_request amc_get_alert_reason = { + .header = { + .command = AMC_COMMAND, + .len = sizeof(struct amc_request) - 2, + .address = AMC_GPU_I2C_ADDR, + .version = AMC_VERSION_V1, + .destination = AMC_DESTINATION_ID, + .source = AMC_SOURCE_ID, + .flags = AMC_FLAGS, + }, + .message = { + .type = AMC_MSG_TYPE, + .vendor = htons(PCI_VENDOR_ID_INTEL), + .command = AMC_GET_ALERT_REASON, + }, +}; + +static void xe_amc_work(struct work_struct *work) +{ + const struct amc_request *request = &amc_get_alert_reason; + struct xe_amc *amc = from_work(amc, work, work); + u8 alert_reason = AMC_ALERT_UNKNOWN; + struct amc_response response; + struct i2c_client *client; + int ret; + + client = amc->i2c->client[XE_I2C_CLIENT_AMC]; + if (IS_ERR_OR_NULL(client)) + goto out_reassert_interrupt; + + ret = i2c_master_send(client, (u8 *)request, sizeof(*request)); + if (ret < 0) { + dev_err(&client->dev, "failed to send request (%d)\n", ret); + goto out_reassert_interrupt; + } + + /* AMC needs 20ms to generate the response. */ + fsleep(20 * USEC_PER_MSEC); + + ret = i2c_master_recv(client, (u8 *)&response, sizeof(response)); + if (ret < 0) { + dev_err(&client->dev, "failed to read response (%d)\n", ret); + goto out_reassert_interrupt; + } + + if (!response.header.len) { + dev_err(&client->dev, "empty response from AMC\n"); + goto out_reassert_interrupt; + } + + if (memcmp(&response.message, &request->message, sizeof(struct amc_message))) { + dev_err(&client->dev, "response does not match the request\n"); + goto out_reassert_interrupt; + } + + if (response.error) { + dev_err(&client->dev, "AMC error 0x%02x\n", response.error); + goto out_reassert_interrupt; + } + + alert_reason = response.value; + dev_dbg(&client->dev, "Alert reason: %d\n", alert_reason); + +out_reassert_interrupt: + xe_mmio_rmw32(amc->i2c->mmio, I2C_CONFIG_CMD, PCI_COMMAND_INTX_DISABLE, 0); + + switch (alert_reason) { + case AMC_ALERT_FW_DOWNLOAD: + case AMC_ALERT_THERMAL_TRIP: + case AMC_ALERT_OOB_REQUEST: + case AMC_ALERT_OOB_RESET: + case AMC_ALERT_CATERR: + dev_warn(amc->i2c->drm_dev, "AMC Alert: %s\n", amc_alert[alert_reason]); + xe_device_declare_wedged(i2c_client_to_xe_device(client)); + break; + default: + dev_warn(amc->i2c->drm_dev, "unknown AMC alert: %d\n", alert_reason); + break; + } +} + +void xe_amc_handle_alert(struct xe_i2c *i2c) +{ + queue_work(system_long_wq, &i2c->amc->work); +} + +int xe_amc_init(struct xe_i2c *i2c) +{ + struct xe_amc *amc; + + amc = kzalloc(sizeof(*amc), GFP_KERNEL); + if (!amc) + return -ENOMEM; + + INIT_WORK(&amc->work, xe_amc_work); + i2c->amc = amc; + amc->i2c = i2c; + + return 0; +} + +void xe_amc_exit(struct xe_i2c *i2c) +{ + if (i2c->amc) { + cancel_work_sync(&i2c->amc->work); + kfree(i2c->amc); + } +} diff --git a/drivers/gpu/drm/xe/xe_amc.h b/drivers/gpu/drm/xe/xe_amc.h new file mode 100644 index 00000000000000..b1d5311fee536f --- /dev/null +++ b/drivers/gpu/drm/xe/xe_amc.h @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _XE_AMC_H_ +#define _XE_AMC_H_ + +#include + +#include "xe_device.h" + +struct xe_i2c; + +static inline struct xe_device *i2c_adapter_to_xe_device(struct i2c_adapter *adapter) +{ + return kdev_to_xe_device(adapter->dev.parent->parent); +} + +static inline struct xe_device *i2c_client_to_xe_device(struct i2c_client *client) +{ + return i2c_adapter_to_xe_device(client->adapter); +} + +int xe_amc_init(struct xe_i2c *i2c); +void xe_amc_exit(struct xe_i2c *i2c); +void xe_amc_handle_alert(struct xe_i2c *i2c); + +#endif /* _XE_AMC_H_ */ diff --git a/drivers/gpu/drm/xe/xe_i2c.c b/drivers/gpu/drm/xe/xe_i2c.c index f05f23221c1b7b..5504cd9dd3596a 100644 --- a/drivers/gpu/drm/xe/xe_i2c.c +++ b/drivers/gpu/drm/xe/xe_i2c.c @@ -12,8 +12,6 @@ #include #include #include -#include -#include #include #include #include @@ -24,9 +22,12 @@ #include #include +#include + #include "regs/xe_i2c_regs.h" #include "regs/xe_irq_regs.h" +#include "xe_amc.h" #include "xe_device.h" #include "xe_i2c.h" #include "xe_mmio.h" @@ -61,16 +62,32 @@ static inline void xe_i2c_read_endpoint(struct xe_mmio *mmio, void *ep) val[1] = xe_mmio_read32(mmio, REG_SG_REMAP_ADDR_POSTFIX); } +static void xe_i2c_handle_smbus_alert(struct xe_i2c *i2c) +{ + u32 stat; + + stat = xe_mmio_read32(i2c->mmio, I2C_REG(DW_IC_SMBUS_INTR_STAT)); + if (!stat) + return; + + xe_mmio_write32(i2c->mmio, I2C_REG(DW_IC_CLR_SMBUS_INTR), stat); + + if (stat & DW_IC_SMBUS_INTR_ALERT && i2c->amc) + xe_amc_handle_alert(i2c); + else + xe_mmio_rmw32(i2c->mmio, I2C_CONFIG_CMD, PCI_COMMAND_INTX_DISABLE, 0); +} + static void xe_i2c_client_work(struct work_struct *work) { struct xe_i2c *i2c = container_of(work, struct xe_i2c, work); struct i2c_board_info info = { .type = "amc", .flags = I2C_CLIENT_HOST_NOTIFY, - .addr = i2c->ep.addr[1], + .addr = i2c->ep.addr[XE_I2C_CLIENT_AMC], }; - i2c->client[0] = i2c_new_client_device(i2c->adapter, &info); + i2c->client[XE_I2C_CLIENT_AMC] = i2c_new_client_device(i2c->adapter, &info); } static int xe_i2c_notifier(struct notifier_block *nb, unsigned long action, void *data) @@ -115,16 +132,6 @@ static int xe_i2c_register_adapter(struct xe_i2c *i2c) goto err_fwnode_remove; } - if (i2c->adapter_irq) { - struct resource res; - - res = DEFINE_RES_IRQ_NAMED(i2c->adapter_irq, "xe_i2c"); - - ret = platform_device_add_resources(pdev, &res, 1); - if (ret) - goto err_pdev_put; - } - pdev->dev.parent = i2c->drm_dev; pdev->dev.fwnode = fwnode; i2c->adapter_node = fwnode; @@ -166,7 +173,8 @@ bool xe_i2c_present(struct xe_device *xe) static bool xe_i2c_irq_present(struct xe_device *xe) { - return xe->i2c && xe->i2c->adapter_irq; + return xe->i2c && xe->i2c->ep.capabilities & XE_I2C_EP_CAP_IRQ && + !xe_survivability_mode_is_boot_enabled(xe); } /** @@ -179,18 +187,10 @@ static bool xe_i2c_irq_present(struct xe_device *xe) */ void xe_i2c_irq_handler(struct xe_device *xe, u32 master_ctl) { - struct xe_mmio *mmio = xe_root_tile_mmio(xe); - if (!(master_ctl & I2C_IRQ) || !xe_i2c_irq_present(xe)) return; - /* Forward interrupt to I2C adapter */ - generic_handle_irq_safe(xe->i2c->adapter_irq); - - /* Deassert after I2C adapter clears the interrupt */ - xe_mmio_rmw32(mmio, I2C_CONFIG_CMD, 0, PCI_COMMAND_INTX_DISABLE); - /* Reassert to allow subsequent interrupt generation */ - xe_mmio_rmw32(mmio, I2C_CONFIG_CMD, PCI_COMMAND_INTX_DISABLE, 0); + xe_i2c_handle_smbus_alert(xe->i2c); } void xe_i2c_irq_reset(struct xe_device *xe) @@ -215,45 +215,6 @@ void xe_i2c_irq_postinstall(struct xe_device *xe) xe_mmio_rmw32(mmio, I2C_CONFIG_CMD, PCI_COMMAND_INTX_DISABLE, 0); } -static int xe_i2c_irq_map(struct irq_domain *h, unsigned int virq, - irq_hw_number_t hw_irq_num) -{ - irq_set_chip_and_handler(virq, &dummy_irq_chip, handle_simple_irq); - return 0; -} - -static const struct irq_domain_ops xe_i2c_irq_ops = { - .map = xe_i2c_irq_map, -}; - -static int xe_i2c_create_irq(struct xe_device *xe) -{ - struct xe_i2c *i2c = xe->i2c; - struct irq_domain *domain; - - if (!(i2c->ep.capabilities & XE_I2C_EP_CAP_IRQ) || - xe_survivability_mode_is_boot_enabled(xe)) - return 0; - - domain = irq_domain_create_linear(dev_fwnode(i2c->drm_dev), 1, &xe_i2c_irq_ops, NULL); - if (!domain) - return -ENOMEM; - - i2c->adapter_irq = irq_create_mapping(domain, 0); - i2c->irqdomain = domain; - - return 0; -} - -static void xe_i2c_remove_irq(struct xe_i2c *i2c) -{ - if (!i2c->irqdomain) - return; - - irq_dispose_mapping(i2c->adapter_irq); - irq_domain_remove(i2c->irqdomain); -} - static int xe_i2c_read(void *context, unsigned int reg, unsigned int *val) { struct xe_i2c *i2c = context; @@ -267,8 +228,16 @@ static int xe_i2c_write(void *context, unsigned int reg, unsigned int val) { struct xe_i2c *i2c = context; - xe_mmio_write32(i2c->mmio, XE_REG(reg + I2C_MEM_SPACE_OFFSET), val); + switch (reg) { + case DW_IC_SMBUS_INTR_MASK: + /* Make sure the Alert is never masked. */ + val |= DW_IC_SMBUS_INTR_ALERT; + break; + default: + break; + } + xe_mmio_write32(i2c->mmio, I2C_REG(reg), val); return 0; } @@ -310,12 +279,15 @@ static void xe_i2c_remove(void *data) struct xe_i2c *i2c = data; unsigned int i; - for (i = 0; i < XE_I2C_MAX_CLIENTS; i++) + xe_amc_exit(i2c); + + for (i = 0; i < XE_I2C_MAX_CLIENTS; i++) { i2c_unregister_device(i2c->client[i]); + i2c->client[i] = NULL; + } bus_unregister_notifier(&i2c_bus_type, &i2c->bus_notifier); xe_i2c_unregister_adapter(i2c); - xe_i2c_remove_irq(i2c); } /** @@ -366,22 +338,18 @@ int xe_i2c_probe(struct xe_device *xe) if (ret) return ret; - ret = xe_i2c_create_irq(xe); - if (ret) - goto err_unregister_notifier; - ret = xe_i2c_register_adapter(i2c); - if (ret) - goto err_remove_irq; + if (ret) { + bus_unregister_notifier(&i2c_bus_type, &i2c->bus_notifier); + return ret; + } + + ret = xe_amc_init(i2c); + if (ret) { + xe_i2c_remove(i2c); + return ret; + } xe_i2c_irq_postinstall(xe); return devm_add_action_or_reset(drm_dev, xe_i2c_remove, i2c); - -err_remove_irq: - xe_i2c_remove_irq(i2c); - -err_unregister_notifier: - bus_unregister_notifier(&i2c_bus_type, &i2c->bus_notifier); - - return ret; } diff --git a/drivers/gpu/drm/xe/xe_i2c.h b/drivers/gpu/drm/xe/xe_i2c.h index 425d8160835f46..b200966b004849 100644 --- a/drivers/gpu/drm/xe/xe_i2c.h +++ b/drivers/gpu/drm/xe/xe_i2c.h @@ -11,18 +11,21 @@ struct device; struct fwnode_handle; struct i2c_adapter; struct i2c_client; -struct irq_domain; struct platform_device; +struct xe_amc; struct xe_device; struct xe_mmio; -#define XE_I2C_MAX_CLIENTS 3 - #define XE_I2C_EP_COOKIE_DEVICE 0xde /* Endpoint Capabilities */ #define XE_I2C_EP_CAP_IRQ BIT(0) +enum XE_I2C_CLIENT { + XE_I2C_CLIENT_AMC = 1, + XE_I2C_MAX_CLIENTS = 3, +}; + struct xe_i2c_endpoint { u8 cookie; u8 capabilities; @@ -38,13 +41,11 @@ struct xe_i2c { struct notifier_block bus_notifier; struct work_struct work; - struct irq_domain *irqdomain; - int adapter_irq; - struct xe_i2c_endpoint ep; struct device *drm_dev; struct xe_mmio *mmio; + struct xe_amc *amc; }; #if IS_ENABLED(CONFIG_I2C) diff --git a/drivers/gpu/drm/xe/xe_oa.c b/drivers/gpu/drm/xe/xe_oa.c index 18d990c5d4ec42..e5b0f3e2f3894b 100644 --- a/drivers/gpu/drm/xe/xe_oa.c +++ b/drivers/gpu/drm/xe/xe_oa.c @@ -2431,9 +2431,9 @@ int xe_oa_add_config_ioctl(struct drm_device *dev, u64 data, struct drm_file *fi oa_config->id = idr_alloc(&oa->metrics_idr, oa_config, 1, 0, GFP_KERNEL); if (oa_config->id < 0) { - drm_dbg(&oa->xe->drm, "Failed to create sysfs entry for OA config\n"); + drm_dbg(&oa->xe->drm, "Failed to allocate id for OA config\n"); err = oa_config->id; - goto sysfs_err; + goto id_alloc_err; } id = oa_config->id; @@ -2444,6 +2444,8 @@ int xe_oa_add_config_ioctl(struct drm_device *dev, u64 data, struct drm_file *fi return id; +id_alloc_err: + sysfs_remove_group(oa->metrics_kobj, &oa_config->sysfs_metric); sysfs_err: mutex_unlock(&oa->metrics_lock); reg_err: diff --git a/drivers/gpu/drm/xe/xe_pagefault.c b/drivers/gpu/drm/xe/xe_pagefault.c index dbf8f71d3328a7..a4986df8328d60 100644 --- a/drivers/gpu/drm/xe/xe_pagefault.c +++ b/drivers/gpu/drm/xe/xe_pagefault.c @@ -16,6 +16,7 @@ #include "xe_hw_engine.h" #include "xe_pagefault.h" #include "xe_pagefault_types.h" +#include "xe_pm.h" #include "xe_svm.h" #include "xe_trace_bo.h" #include "xe_vm.h" @@ -292,9 +293,17 @@ static void xe_pagefault_queue_work(struct work_struct *w) { struct xe_pagefault_queue *pf_queue = container_of(w, typeof(*pf_queue), worker); + struct xe_device *xe = pf_queue->xe; struct xe_pagefault pf; unsigned long threshold; + /* + * A live VM holds a PM reference, but a torn-down VM does not. + * Guard the entire worker loop to safely drain stale faults and + * prevent autosuspends from desyncing batched CT flushes. + */ + guard(xe_pm_runtime)(xe); + #define USM_QUEUE_MAX_RUNTIME_MS 20 threshold = jiffies + msecs_to_jiffies(USM_QUEUE_MAX_RUNTIME_MS); @@ -365,6 +374,7 @@ static int xe_pagefault_queue_init(struct xe_device *xe, drm_dbg(&xe->drm, "xe_pagefault_entry_size=%d, total_num_eus=%d, pf_queue->size=%u", xe_pagefault_entry_size(), total_num_eus, pf_queue->size); + pf_queue->xe = xe; spin_lock_init(&pf_queue->lock); INIT_WORK(&pf_queue->worker, xe_pagefault_queue_work); diff --git a/drivers/gpu/drm/xe/xe_pagefault_types.h b/drivers/gpu/drm/xe/xe_pagefault_types.h index c4ee625b93dddf..f63a12aa0d4f7a 100644 --- a/drivers/gpu/drm/xe/xe_pagefault_types.h +++ b/drivers/gpu/drm/xe/xe_pagefault_types.h @@ -8,6 +8,7 @@ #include +struct xe_device; struct xe_gt; struct xe_pagefault; @@ -118,6 +119,8 @@ struct xe_pagefault { * queue to absorb the device’s worst-case number of outstanding faults. */ struct xe_pagefault_queue { + /** @xe: Back-pointer to the Xe device */ + struct xe_device *xe; /** * @data: Data in queue containing struct xe_pagefault, protected by * @lock diff --git a/drivers/gpu/drm/xe/xe_ring_ops.c b/drivers/gpu/drm/xe/xe_ring_ops.c index 39a670e91ba722..08b4a4283e96a2 100644 --- a/drivers/gpu/drm/xe/xe_ring_ops.c +++ b/drivers/gpu/drm/xe/xe_ring_ops.c @@ -212,6 +212,7 @@ static int emit_render_cache_flush(struct xe_sched_job *job, u32 *dw, int i) { struct xe_exec_queue *q = job->q; struct xe_gt *gt = q->gt; + struct xe_device *xe = gt_to_xe(gt); bool lacks_render = !(gt->info.engine_mask & XE_HW_ENGINE_RCS_MASK); u32 flags0, flags1; @@ -220,6 +221,16 @@ static int emit_render_cache_flush(struct xe_sched_job *job, u32 *dw, int i) LRC_PPHWSP_FLUSH_INVAL_SCRATCH_ADDR, 0); flags0 = PIPE_CONTROL0_HDC_PIPELINE_FLUSH; + /* + * Prior to MTL, HDC Pipeline Flush reliably also flushes the LSC + * untyped L1 dataport cache, provided HDC_CHICKEN0 is programmed + * correctly. Starting with MTL that coupling no longer holds + * regardless of how HDC_CHICKEN0 is programmed, but explicitly + * requesting the flush via PIPE_CONTROL is itself only reliable + * from Xe2 onward, so only gate it in on Xe2+. + */ + if (GRAPHICS_VERx100(xe) >= 2000) + flags0 |= PIPE_CONTROL0_UNTYPED_DATAPORT_CACHE_FLUSH; flags1 = (PIPE_CONTROL_TILE_CACHE_FLUSH | PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH | PIPE_CONTROL_DEPTH_CACHE_FLUSH | diff --git a/drivers/hwmon/applesmc.c b/drivers/hwmon/applesmc.c index 90a14a7f2c4c0c..bfe9c5b0c4f14e 100644 --- a/drivers/hwmon/applesmc.c +++ b/drivers/hwmon/applesmc.c @@ -1249,12 +1249,17 @@ static void applesmc_release_light_sensor(void) static int applesmc_create_key_backlight(void) { + int ret; + if (!smcreg.has_key_backlight) return 0; applesmc_led_wq = create_singlethread_workqueue("applesmc-led"); if (!applesmc_led_wq) return -ENOMEM; - return led_classdev_register(&pdev->dev, &applesmc_backlight); + ret = led_classdev_register(&pdev->dev, &applesmc_backlight); + if (ret) + destroy_workqueue(applesmc_led_wq); + return ret; } static void applesmc_release_key_backlight(void) diff --git a/drivers/hwmon/aspeed-pwm-tacho.c b/drivers/hwmon/aspeed-pwm-tacho.c index 1c5945d4ba3777..bfce589c3fb1f1 100644 --- a/drivers/hwmon/aspeed-pwm-tacho.c +++ b/drivers/hwmon/aspeed-pwm-tacho.c @@ -934,7 +934,9 @@ static int aspeed_pwm_tacho_probe(struct platform_device *pdev) "missing or invalid reset controller device tree entry"); return PTR_ERR(priv->rst); } - reset_control_deassert(priv->rst); + ret = reset_control_deassert(priv->rst); + if (ret) + return ret; ret = devm_add_action_or_reset(dev, aspeed_pwm_tacho_remove, priv); if (ret) diff --git a/drivers/hwmon/asus_rog_ryujin.c b/drivers/hwmon/asus_rog_ryujin.c index 10a1f5aca988d8..f352036f0e52e6 100644 --- a/drivers/hwmon/asus_rog_ryujin.c +++ b/drivers/hwmon/asus_rog_ryujin.c @@ -18,15 +18,25 @@ #define USB_VENDOR_ID_ASUS_ROG 0x0b05 #define USB_PRODUCT_ID_RYUJIN_AIO 0x1988 /* ASUS ROG RYUJIN II 360 */ +struct rog_ryujin_device_info { + u8 temp_offset; + u8 pump_speed_offset; + u8 fan_speed_offset; + u8 duty_channel; + bool has_controller; +}; + +static const struct rog_ryujin_device_info rog_ryujin_ii_360_info = { + .temp_offset = 3, + .pump_speed_offset = 5, + .fan_speed_offset = 7, + .duty_channel = 0, + .has_controller = true, +}; + #define STATUS_VALIDITY 1500 /* ms */ #define MAX_REPORT_LENGTH 65 -/* Cooler status report offsets */ -#define RYUJIN_TEMP_SENSOR_1 3 -#define RYUJIN_TEMP_SENSOR_2 4 -#define RYUJIN_PUMP_SPEED 5 -#define RYUJIN_INTERNAL_FAN_SPEED 7 - /* Cooler duty report offsets */ #define RYUJIN_PUMP_DUTY 4 #define RYUJIN_INTERNAL_FAN_DUTY 5 @@ -81,6 +91,7 @@ static const char *const rog_ryujin_speed_label[] = { struct rog_ryujin_data { struct hid_device *hdev; struct device *hwmon_dev; + const struct rog_ryujin_device_info *info; /* For reinitializing the completions below */ spinlock_t status_report_request_lock; struct completion cooler_status_received; @@ -112,6 +123,8 @@ static int rog_ryujin_pwm_to_percent(long val) static umode_t rog_ryujin_is_visible(const void *data, enum hwmon_sensor_types type, u32 attr, int channel) { + const struct rog_ryujin_data *priv = data; + switch (type) { case hwmon_temp: switch (attr) { @@ -123,6 +136,8 @@ static umode_t rog_ryujin_is_visible(const void *data, } break; case hwmon_fan: + if (channel >= 2 && !priv->info->has_controller) + return 0; switch (attr) { case hwmon_fan_label: case hwmon_fan_input: @@ -132,6 +147,8 @@ static umode_t rog_ryujin_is_visible(const void *data, } break; case hwmon_pwm: + if (channel >= 2 && !priv->info->has_controller) + return 0; switch (attr) { case hwmon_pwm_input: return 0644; @@ -156,6 +173,7 @@ static int rog_ryujin_write_expanded(struct rog_ryujin_data *priv, const u8 *cmd static int rog_ryujin_execute_cmd(struct rog_ryujin_data *priv, const u8 *cmd, int cmd_length, struct completion *status_completion) { + unsigned long flags; int ret; /* @@ -163,9 +181,9 @@ static int rog_ryujin_execute_cmd(struct rog_ryujin_data *priv, const u8 *cmd, i * completion. Reinit is done because hidraw could have triggered * the raw event parsing and marked the passed in completion as done. */ - spin_lock_bh(&priv->status_report_request_lock); + spin_lock_irqsave(&priv->status_report_request_lock, flags); reinit_completion(status_completion); - spin_unlock_bh(&priv->status_report_request_lock); + spin_unlock_irqrestore(&priv->status_report_request_lock, flags); /* Send command for getting data */ ret = rog_ryujin_write_expanded(priv, cmd, cmd_length); @@ -198,12 +216,14 @@ static int rog_ryujin_get_status(struct rog_ryujin_data *priv) if (ret < 0) return ret; - /* Retrieve controller status (speeds) */ - ret = - rog_ryujin_execute_cmd(priv, get_controller_speed_cmd, GET_CMD_LENGTH, - &priv->controller_status_received); - if (ret < 0) - return ret; + if (priv->info->has_controller) { + /* Retrieve controller status (speeds) */ + ret = rog_ryujin_execute_cmd(priv, get_controller_speed_cmd, + GET_CMD_LENGTH, + &priv->controller_status_received); + if (ret < 0) + return ret; + } /* Retrieve cooler duty */ ret = @@ -212,12 +232,14 @@ static int rog_ryujin_get_status(struct rog_ryujin_data *priv) if (ret < 0) return ret; - /* Retrieve controller duty */ - ret = - rog_ryujin_execute_cmd(priv, get_controller_duty_cmd, GET_CMD_LENGTH, - &priv->controller_duty_received); - if (ret < 0) - return ret; + if (priv->info->has_controller) { + /* Retrieve controller duty */ + ret = rog_ryujin_execute_cmd(priv, get_controller_duty_cmd, + GET_CMD_LENGTH, + &priv->controller_duty_received); + if (ret < 0) + return ret; + } priv->updated = jiffies; return 0; @@ -289,6 +311,7 @@ static int rog_ryujin_write_fixed_duty(struct rog_ryujin_data *priv, int channel return ret; memcpy(set_cmd, set_cooler_duty_cmd, SET_CMD_LENGTH); + set_cmd[2] = priv->info->duty_channel; /* Cooler duties are set as 0-100% */ val = rog_ryujin_pwm_to_percent(val); @@ -388,20 +411,33 @@ static int rog_ryujin_raw_event(struct hid_device *hdev, struct hid_report *repo int size) { struct rog_ryujin_data *priv = hid_get_drvdata(hdev); + unsigned long flags; - if (data[0] != RYUJIN_CMD_PREFIX) + if (size < 2 || data[0] != RYUJIN_CMD_PREFIX) return 0; + spin_lock_irqsave(&priv->status_report_request_lock, flags); + if (data[1] == RYUJIN_GET_COOLER_STATUS_CMD_RESPONSE) { + if (size <= priv->info->temp_offset + 1 || + size <= priv->info->pump_speed_offset + 1 || + size <= priv->info->fan_speed_offset + 1) + goto unlock; + /* Received coolant temp and speeds of pump and internal fan */ - priv->temp_input[0] = - data[RYUJIN_TEMP_SENSOR_1] * 1000 + data[RYUJIN_TEMP_SENSOR_2] * 100; - priv->speed_input[0] = get_unaligned_le16(data + RYUJIN_PUMP_SPEED); - priv->speed_input[1] = get_unaligned_le16(data + RYUJIN_INTERNAL_FAN_SPEED); + priv->temp_input[0] = data[priv->info->temp_offset] * 1000 + + data[priv->info->temp_offset + 1] * 100; + priv->speed_input[0] = + get_unaligned_le16(data + priv->info->pump_speed_offset); + priv->speed_input[1] = + get_unaligned_le16(data + priv->info->fan_speed_offset); if (!completion_done(&priv->cooler_status_received)) complete_all(&priv->cooler_status_received); } else if (data[1] == RYUJIN_GET_CONTROLLER_SPEED_CMD_RESPONSE) { + if (size <= RYUJIN_CONTROLLER_SPEED_3 + 1) + goto unlock; + /* Received speeds of four fans attached to the controller */ priv->speed_input[2] = get_unaligned_le16(data + RYUJIN_CONTROLLER_SPEED_1); priv->speed_input[3] = get_unaligned_le16(data + RYUJIN_CONTROLLER_SPEED_2); @@ -411,6 +447,9 @@ static int rog_ryujin_raw_event(struct hid_device *hdev, struct hid_report *repo if (!completion_done(&priv->controller_status_received)) complete_all(&priv->controller_status_received); } else if (data[1] == RYUJIN_GET_COOLER_DUTY_CMD_RESPONSE) { + if (size <= RYUJIN_INTERNAL_FAN_DUTY) + goto unlock; + /* Received report for pump and internal fan duties (in %) */ if (data[RYUJIN_PUMP_DUTY] == 0 && data[RYUJIN_INTERNAL_FAN_DUTY] == 0) { /* @@ -428,7 +467,7 @@ static int rog_ryujin_raw_event(struct hid_device *hdev, struct hid_report *repo * We're expecting a report, so parse it. */ goto read_cooler_duty; - return 0; + goto unlock; } read_cooler_duty: priv->duty_input[0] = rog_ryujin_percent_to_pwm(data[RYUJIN_PUMP_DUTY]); @@ -437,6 +476,9 @@ read_cooler_duty: if (!completion_done(&priv->cooler_duty_received)) complete_all(&priv->cooler_duty_received); } else if (data[1] == RYUJIN_GET_CONTROLLER_DUTY_CMD_RESPONSE) { + if (size <= RYUJIN_CONTROLLER_DUTY) + goto unlock; + /* Received report for controller duty for fans (in PWM) */ if (data[RYUJIN_CONTROLLER_DUTY] == 0) { /* @@ -454,7 +496,7 @@ read_cooler_duty: * We're expecting a report, so parse it. */ goto read_controller_duty; - return 0; + goto unlock; } read_controller_duty: priv->duty_input[2] = data[RYUJIN_CONTROLLER_DUTY]; @@ -463,6 +505,8 @@ read_controller_duty: complete_all(&priv->controller_duty_received); } +unlock: + spin_unlock_irqrestore(&priv->status_report_request_lock, flags); return 0; } @@ -471,11 +515,15 @@ static int rog_ryujin_probe(struct hid_device *hdev, const struct hid_device_id struct rog_ryujin_data *priv; int ret; + if (!id->driver_data) + return -EINVAL; + priv = devm_kzalloc(&hdev->dev, sizeof(*priv), GFP_KERNEL); if (!priv) return -ENOMEM; priv->hdev = hdev; + priv->info = (const struct rog_ryujin_device_info *)id->driver_data; hid_set_drvdata(hdev, priv); /* @@ -546,7 +594,8 @@ static void rog_ryujin_remove(struct hid_device *hdev) } static const struct hid_device_id rog_ryujin_table[] = { - { HID_USB_DEVICE(USB_VENDOR_ID_ASUS_ROG, USB_PRODUCT_ID_RYUJIN_AIO) }, + { HID_USB_DEVICE(USB_VENDOR_ID_ASUS_ROG, USB_PRODUCT_ID_RYUJIN_AIO), + .driver_data = (kernel_ulong_t)&rog_ryujin_ii_360_info }, { } }; diff --git a/drivers/hwmon/chipcap2.c b/drivers/hwmon/chipcap2.c index 4aecf463180fd7..4b6244e13e9e26 100644 --- a/drivers/hwmon/chipcap2.c +++ b/drivers/hwmon/chipcap2.c @@ -89,11 +89,6 @@ struct cc2_data { bool process_irqs; }; -enum cc2_chan_addr { - CC2_CHAN_TEMP = 0, - CC2_CHAN_HUMIDITY, -}; - /* %RH as a per cent mille from a register value */ static long cc2_rh_convert(u16 data) { @@ -492,7 +487,7 @@ static irqreturn_t cc2_low_interrupt(int irq, void *data) if (cc2->process_irqs) { hwmon_notify_event(cc2->hwmon, hwmon_humidity, - hwmon_humidity_min_alarm, CC2_CHAN_HUMIDITY); + hwmon_humidity_min_alarm, 0); cc2->rh_alarm.low_alarm = true; } @@ -505,7 +500,7 @@ static irqreturn_t cc2_high_interrupt(int irq, void *data) if (cc2->process_irqs) { hwmon_notify_event(cc2->hwmon, hwmon_humidity, - hwmon_humidity_max_alarm, CC2_CHAN_HUMIDITY); + hwmon_humidity_max_alarm, 0); cc2->rh_alarm.high_alarm = true; } diff --git a/drivers/hwmon/corsair-cpro.c b/drivers/hwmon/corsair-cpro.c index 8354a002f4c5e1..c0964515261329 100644 --- a/drivers/hwmon/corsair-cpro.c +++ b/drivers/hwmon/corsair-cpro.c @@ -566,21 +566,18 @@ static int bootloader_show(struct seq_file *seqf, void *unused) } DEFINE_SHOW_ATTRIBUTE(bootloader); -static void ccp_debugfs_init(struct ccp_device *ccp) +static void ccp_debugfs_init(struct ccp_device *ccp, bool fw_valid, bool bl_valid) { char name[32]; - int ret; scnprintf(name, sizeof(name), "corsaircpro-%s", dev_name(&ccp->hdev->dev)); ccp->debugfs = debugfs_create_dir(name, NULL); - ret = get_fw_version(ccp); - if (!ret) + if (fw_valid) debugfs_create_file("firmware_version", 0444, ccp->debugfs, ccp, &firmware_fops); - ret = get_bl_version(ccp); - if (!ret) + if (bl_valid) debugfs_create_file("bootloader_version", 0444, ccp->debugfs, ccp, &bootloader_fops); } @@ -588,6 +585,7 @@ static void ccp_debugfs_init(struct ccp_device *ccp) static int ccp_probe(struct hid_device *hdev, const struct hid_device_id *id) { struct ccp_device *ccp; + bool fw_valid, bl_valid; int ret; ccp = devm_kzalloc(&hdev->dev, sizeof(*ccp), GFP_KERNEL); @@ -632,17 +630,27 @@ static int ccp_probe(struct hid_device *hdev, const struct hid_device_id *id) if (ret) goto out_hw_close; - ccp_debugfs_init(ccp); + /* + * Query the versions before registering the hwmon device: they send + * USB commands without holding ccp->mutex, which is only safe while + * nothing else can call send_usb_cmd(). + */ + fw_valid = !get_fw_version(ccp); + bl_valid = !get_bl_version(ccp); ccp->hwmon_dev = hwmon_device_register_with_info(&hdev->dev, "corsaircpro", ccp, &ccp_chip_info, NULL); if (IS_ERR(ccp->hwmon_dev)) { ret = PTR_ERR(ccp->hwmon_dev); - goto out_hw_close; + goto out_debugfs_remove; } + ccp_debugfs_init(ccp, fw_valid, bl_valid); + return 0; +out_debugfs_remove: + debugfs_remove_recursive(ccp->debugfs); out_hw_close: hid_hw_close(hdev); hid_device_io_stop(hdev); diff --git a/drivers/hwmon/gpio-fan.c b/drivers/hwmon/gpio-fan.c index 084828e1e2817b..df8bd970760505 100644 --- a/drivers/hwmon/gpio-fan.c +++ b/drivers/hwmon/gpio-fan.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include #include @@ -84,6 +85,7 @@ static DEVICE_ATTR_RO(fan1_alarm); static int fan_alarm_init(struct gpio_fan_data *fan_data) { int alarm_irq; + int err; struct device *dev = fan_data->dev; /* @@ -94,7 +96,11 @@ static int fan_alarm_init(struct gpio_fan_data *fan_data) if (alarm_irq <= 0) return 0; - INIT_WORK(&fan_data->alarm_work, fan_alarm_notify); + err = devm_work_autocancel(dev, &fan_data->alarm_work, + fan_alarm_notify); + if (err) + return err; + irq_set_irq_type(alarm_irq, IRQ_TYPE_EDGE_BOTH); return devm_request_irq(dev, alarm_irq, fan_alarm_irq_handler, IRQF_SHARED, "GPIO fan alarm", fan_data); @@ -606,8 +612,11 @@ static void gpio_fan_shutdown(struct platform_device *pdev) { struct gpio_fan_data *fan_data = platform_get_drvdata(pdev); - if (fan_data->gpios) + if (fan_data->gpios) { + mutex_lock(&fan_data->lock); set_fan_speed(fan_data, 0); + mutex_unlock(&fan_data->lock); + } } static int gpio_fan_runtime_suspend(struct device *dev) diff --git a/drivers/hwmon/hwmon.c b/drivers/hwmon/hwmon.c index 29dc90a2c3fe70..8cf717ae8b1dda 100644 --- a/drivers/hwmon/hwmon.c +++ b/drivers/hwmon/hwmon.c @@ -371,18 +371,17 @@ static ssize_t pec_store(struct device *dev, struct device_attribute *devattr, * handling is not required. */ hwdev = to_hwmon_device(hdev); - guard(mutex)(&hwdev->lock); - if (hwdev->chip->ops->write) { - err = hwdev->chip->ops->write(hdev, hwmon_chip, hwmon_chip_pec, 0, val); - if (err && err != -EOPNOTSUPP) - goto put; + scoped_guard(mutex, &hwdev->lock) { + if (hwdev->chip->ops->write) { + err = hwdev->chip->ops->write(hdev, hwmon_chip, hwmon_chip_pec, 0, val); + if (err && err != -EOPNOTSUPP) + goto put; + } + if (!val) + client->flags &= ~I2C_CLIENT_PEC; + else + client->flags |= I2C_CLIENT_PEC; } - - if (!val) - client->flags &= ~I2C_CLIENT_PEC; - else - client->flags |= I2C_CLIENT_PEC; - err = count; put: put_device(hdev); diff --git a/drivers/hwmon/ina2xx.c b/drivers/hwmon/ina2xx.c index 449a72c6b40bde..958a1e3ec728d3 100644 --- a/drivers/hwmon/ina2xx.c +++ b/drivers/hwmon/ina2xx.c @@ -8,6 +8,7 @@ */ #include +#include #include #include #include @@ -128,6 +129,17 @@ enum ina2xx_ids { sy24655 }; +enum ina2xx_alert_type { + INA2XX_ALERT_NONE, + INA2XX_ALERT_CURRENT_LOW, + INA2XX_ALERT_CURRENT_HIGH, + INA2XX_ALERT_POWER_HIGH, + INA2XX_ALERT_BUS_VOLTAGE_LOW, + INA2XX_ALERT_BUS_VOLTAGE_HIGH, + INA2XX_ALERT_SHUNT_VOLTAGE_LOW, + INA2XX_ALERT_SHUNT_VOLTAGE_HIGH, +}; + struct ina2xx_config { u16 config_default; bool has_alerts; /* chip supports alerts and limits */ @@ -147,6 +159,7 @@ struct ina2xx_data { const struct ina2xx_config *config; enum ina2xx_ids chip; + enum ina2xx_alert_type active_alert; long rshunt; long current_lsb_uA; long power_lsb_uW; @@ -413,16 +426,78 @@ static u16 ina226_alert_to_reg(struct ina2xx_data *data, int reg, long val) } } -static int ina226_alert_limit_read(struct ina2xx_data *data, u32 mask, int reg, long *val) +static u32 ina2xx_alert_type_to_mask(enum ina2xx_alert_type alert) +{ + switch (alert) { + case INA2XX_ALERT_CURRENT_LOW: + case INA2XX_ALERT_SHUNT_VOLTAGE_LOW: + return INA226_SHUNT_UNDER_VOLTAGE_MASK; + case INA2XX_ALERT_CURRENT_HIGH: + case INA2XX_ALERT_SHUNT_VOLTAGE_HIGH: + return INA226_SHUNT_OVER_VOLTAGE_MASK; + case INA2XX_ALERT_BUS_VOLTAGE_LOW: + return INA226_BUS_UNDER_VOLTAGE_MASK; + case INA2XX_ALERT_BUS_VOLTAGE_HIGH: + return INA226_BUS_OVER_VOLTAGE_MASK; + case INA2XX_ALERT_POWER_HIGH: + return INA226_POWER_OVER_LIMIT_MASK; + case INA2XX_ALERT_NONE: + return 0; + default: + /* programmer error */ + WARN_ON_ONCE(1); + return 0; + } +} + +static enum ina2xx_alert_type ina2xx_mask_to_alert_type(u32 mask) +{ + int top_bit = fls(mask & INA226_ALERT_CONFIG_MASK); + + if (!top_bit) + return INA2XX_ALERT_NONE; + + /* + * Multiple bits may be set, with the highest-set function taking + * precedence according to the datasheet. Shunt voltage masks are + * assumed to map to voltage monitoring rather than current monitoring, + * since the latter isn't directly implemented in the hardware. + */ + switch (BIT(top_bit - 1)) { + case INA226_SHUNT_OVER_VOLTAGE_MASK: + return INA2XX_ALERT_SHUNT_VOLTAGE_HIGH; + case INA226_SHUNT_UNDER_VOLTAGE_MASK: + return INA2XX_ALERT_SHUNT_VOLTAGE_LOW; + case INA226_BUS_OVER_VOLTAGE_MASK: + return INA2XX_ALERT_BUS_VOLTAGE_HIGH; + case INA226_BUS_UNDER_VOLTAGE_MASK: + return INA2XX_ALERT_BUS_VOLTAGE_LOW; + case INA226_POWER_OVER_LIMIT_MASK: + return INA2XX_ALERT_POWER_HIGH; + default: + return INA2XX_ALERT_NONE; + } +} + +static int ina226_alert_limit_read(struct ina2xx_data *data, enum ina2xx_alert_type alert, + int reg, long *val) { struct regmap *regmap = data->regmap; int regval; + u32 mask; int ret; + /* Avoid nonzero reads from inactive alerts caused by shared limit register */ + if (data->active_alert != alert) { + *val = 0; + return 0; + } + ret = regmap_read(regmap, INA226_MASK_ENABLE, ®val); if (ret) return ret; + mask = ina2xx_alert_type_to_mask(alert); if (regval & mask) { ret = regmap_read(regmap, INA226_ALERT_LIMIT, ®val); if (ret) @@ -434,9 +509,11 @@ static int ina226_alert_limit_read(struct ina2xx_data *data, u32 mask, int reg, return 0; } -static int ina226_alert_limit_write(struct ina2xx_data *data, u32 mask, int reg, long val) +static int ina226_alert_limit_write(struct ina2xx_data *data, enum ina2xx_alert_type alert, + int reg, long val) { struct regmap *regmap = data->regmap; + u32 mask; int ret; if (val < 0) @@ -451,15 +528,22 @@ static int ina226_alert_limit_write(struct ina2xx_data *data, u32 mask, int reg, INA226_ALERT_CONFIG_MASK, 0); if (ret < 0) return ret; + data->active_alert = INA2XX_ALERT_NONE; ret = regmap_write(regmap, INA226_ALERT_LIMIT, ina226_alert_to_reg(data, reg, val)); if (ret < 0) return ret; - if (val) - return regmap_update_bits(regmap, INA226_MASK_ENABLE, - INA226_ALERT_CONFIG_MASK, mask); + if (val) { + mask = ina2xx_alert_type_to_mask(alert); + ret = regmap_update_bits(regmap, INA226_MASK_ENABLE, + INA226_ALERT_CONFIG_MASK, mask); + if (ret < 0) + return ret; + data->active_alert = alert; + } + return 0; } @@ -483,15 +567,26 @@ static int ina2xx_chip_read(struct device *dev, u32 attr, long *val) return 0; } -static int ina226_alert_read(struct regmap *regmap, u32 mask, long *val) +static int ina226_alert_read(struct ina2xx_data *data, enum ina2xx_alert_type alert, long *val) { unsigned int regval; + u32 mask; int ret; - ret = regmap_read_bypassed(regmap, INA226_MASK_ENABLE, ®val); + /* + * With alert latching, reading alerts from hardware also clears the + * alert, so return early if the alert is inactive. + */ + if (data->active_alert != alert) { + *val = 0; + return 0; + } + + ret = regmap_read_bypassed(data->regmap, INA226_MASK_ENABLE, ®val); if (ret) return ret; + mask = ina2xx_alert_type_to_mask(alert); *val = (regval & mask) && (regval & INA226_ALERT_FUNCTION_FLAG); return 0; @@ -500,10 +595,10 @@ static int ina226_alert_read(struct regmap *regmap, u32 mask, long *val) static int ina2xx_in_read(struct device *dev, u32 attr, int channel, long *val) { int voltage_reg = channel ? INA2XX_BUS_VOLTAGE : INA2XX_SHUNT_VOLTAGE; - u32 under_voltage_mask = channel ? INA226_BUS_UNDER_VOLTAGE_MASK - : INA226_SHUNT_UNDER_VOLTAGE_MASK; - u32 over_voltage_mask = channel ? INA226_BUS_OVER_VOLTAGE_MASK - : INA226_SHUNT_OVER_VOLTAGE_MASK; + enum ina2xx_alert_type under_voltage_alert = channel ? INA2XX_ALERT_BUS_VOLTAGE_LOW + : INA2XX_ALERT_SHUNT_VOLTAGE_LOW; + enum ina2xx_alert_type over_voltage_alert = channel ? INA2XX_ALERT_BUS_VOLTAGE_HIGH + : INA2XX_ALERT_SHUNT_VOLTAGE_HIGH; struct ina2xx_data *data = dev_get_drvdata(dev); struct regmap *regmap = data->regmap; unsigned int regval; @@ -517,15 +612,15 @@ static int ina2xx_in_read(struct device *dev, u32 attr, int channel, long *val) *val = ina2xx_get_value(data, voltage_reg, regval); break; case hwmon_in_lcrit: - return ina226_alert_limit_read(data, under_voltage_mask, + return ina226_alert_limit_read(data, under_voltage_alert, voltage_reg, val); case hwmon_in_crit: - return ina226_alert_limit_read(data, over_voltage_mask, + return ina226_alert_limit_read(data, over_voltage_alert, voltage_reg, val); case hwmon_in_lcrit_alarm: - return ina226_alert_read(regmap, under_voltage_mask, val); + return ina226_alert_read(data, under_voltage_alert, val); case hwmon_in_crit_alarm: - return ina226_alert_read(regmap, over_voltage_mask, val); + return ina226_alert_read(data, over_voltage_alert, val); default: return -EOPNOTSUPP; } @@ -579,10 +674,10 @@ static int ina2xx_power_read(struct device *dev, u32 attr, long *val) case hwmon_power_average: return sy24655_average_power_read(data, SY24655_EIN, val); case hwmon_power_crit: - return ina226_alert_limit_read(data, INA226_POWER_OVER_LIMIT_MASK, + return ina226_alert_limit_read(data, INA2XX_ALERT_POWER_HIGH, INA2XX_POWER, val); case hwmon_power_crit_alarm: - return ina226_alert_read(data->regmap, INA226_POWER_OVER_LIMIT_MASK, val); + return ina226_alert_read(data, INA2XX_ALERT_POWER_HIGH, val); default: return -EOPNOTSUPP; } @@ -618,15 +713,15 @@ static int ina2xx_curr_read(struct device *dev, u32 attr, long *val) *val = ina2xx_get_value(data, INA2XX_CURRENT, regval); return 0; case hwmon_curr_lcrit: - return ina226_alert_limit_read(data, INA226_SHUNT_UNDER_VOLTAGE_MASK, + return ina226_alert_limit_read(data, INA2XX_ALERT_CURRENT_LOW, INA2XX_CURRENT, val); case hwmon_curr_crit: - return ina226_alert_limit_read(data, INA226_SHUNT_OVER_VOLTAGE_MASK, + return ina226_alert_limit_read(data, INA2XX_ALERT_CURRENT_HIGH, INA2XX_CURRENT, val); case hwmon_curr_lcrit_alarm: - return ina226_alert_read(regmap, INA226_SHUNT_UNDER_VOLTAGE_MASK, val); + return ina226_alert_read(data, INA2XX_ALERT_CURRENT_LOW, val); case hwmon_curr_crit_alarm: - return ina226_alert_read(regmap, INA226_SHUNT_OVER_VOLTAGE_MASK, val); + return ina226_alert_read(data, INA2XX_ALERT_CURRENT_HIGH, val); default: return -EOPNOTSUPP; } @@ -670,12 +765,12 @@ static int ina2xx_in_write(struct device *dev, u32 attr, int channel, long val) switch (attr) { case hwmon_in_lcrit: return ina226_alert_limit_write(data, - channel ? INA226_BUS_UNDER_VOLTAGE_MASK : INA226_SHUNT_UNDER_VOLTAGE_MASK, + channel ? INA2XX_ALERT_BUS_VOLTAGE_LOW : INA2XX_ALERT_SHUNT_VOLTAGE_LOW, channel ? INA2XX_BUS_VOLTAGE : INA2XX_SHUNT_VOLTAGE, val); case hwmon_in_crit: return ina226_alert_limit_write(data, - channel ? INA226_BUS_OVER_VOLTAGE_MASK : INA226_SHUNT_OVER_VOLTAGE_MASK, + channel ? INA2XX_ALERT_BUS_VOLTAGE_HIGH : INA2XX_ALERT_SHUNT_VOLTAGE_HIGH, channel ? INA2XX_BUS_VOLTAGE : INA2XX_SHUNT_VOLTAGE, val); default: @@ -690,7 +785,7 @@ static int ina2xx_power_write(struct device *dev, u32 attr, long val) switch (attr) { case hwmon_power_crit: - return ina226_alert_limit_write(data, INA226_POWER_OVER_LIMIT_MASK, + return ina226_alert_limit_write(data, INA2XX_ALERT_POWER_HIGH, INA2XX_POWER, val); default: return -EOPNOTSUPP; @@ -704,10 +799,10 @@ static int ina2xx_curr_write(struct device *dev, u32 attr, long val) switch (attr) { case hwmon_curr_lcrit: - return ina226_alert_limit_write(data, INA226_SHUNT_UNDER_VOLTAGE_MASK, + return ina226_alert_limit_write(data, INA2XX_ALERT_CURRENT_LOW, INA2XX_CURRENT, val); case hwmon_curr_crit: - return ina226_alert_limit_write(data, INA226_SHUNT_OVER_VOLTAGE_MASK, + return ina226_alert_limit_write(data, INA2XX_ALERT_CURRENT_HIGH, INA2XX_CURRENT, val); default: return -EOPNOTSUPP; @@ -868,8 +963,12 @@ static ssize_t shunt_resistor_show(struct device *dev, struct device_attribute *da, char *buf) { struct ina2xx_data *data = dev_get_drvdata(dev); + long rshunt; - return sysfs_emit(buf, "%li\n", data->rshunt); + scoped_guard(hwmon_lock, dev) { + rshunt = data->rshunt; + } + return sysfs_emit(buf, "%li\n", rshunt); } static ssize_t shunt_resistor_store(struct device *dev, @@ -925,6 +1024,16 @@ static int ina2xx_init(struct device *dev, struct ina2xx_data *data) if (data->config->has_alerts) { bool active_high = device_property_read_bool(dev, "ti,alert-polarity-active-high"); + unsigned int mask_enable; + + /* + * Infer active alert from MASK_ENABLE in case it's already + * configured (e.g., by a past probe or firmware) + */ + ret = regmap_read(regmap, INA226_MASK_ENABLE, &mask_enable); + if (ret < 0) + return ret; + data->active_alert = ina2xx_mask_to_alert_type(mask_enable); regmap_update_bits(regmap, INA226_MASK_ENABLE, INA226_ALERT_LATCH_ENABLE | INA226_ALERT_POLARITY, diff --git a/drivers/hwmon/ltc4282.c b/drivers/hwmon/ltc4282.c index b1675dc5b3c7fd..54ba4b8542e94b 100644 --- a/drivers/hwmon/ltc4282.c +++ b/drivers/hwmon/ltc4282.c @@ -1106,7 +1106,7 @@ static const struct clk_ops ltc4282_ops = { static int ltc428_clk_provider_setup(struct ltc4282_state *st, struct device *dev) { - struct clk_init_data init; + struct clk_init_data init = {}; int ret; if (!IS_ENABLED(CONFIG_COMMON_CLK)) diff --git a/drivers/hwmon/mcp9982.c b/drivers/hwmon/mcp9982.c index 9e19e2697e25ff..3918dc36c9463c 100644 --- a/drivers/hwmon/mcp9982.c +++ b/drivers/hwmon/mcp9982.c @@ -395,6 +395,8 @@ static int mcp9982_read(struct device *dev, enum hwmon_sensor_types type, u32 at reg_status, !(reg_status & MCP9982_STATUS_BUSY), MCP9982_WAKE_UP_TIME_US, MCP9982_WAKE_UP_TIME_US * 10); + if (ret) + return ret; break; } break; diff --git a/drivers/hwmon/nct6694-hwmon.c b/drivers/hwmon/nct6694-hwmon.c index 6dcf22ca5018a5..9a9a4db434c4f9 100644 --- a/drivers/hwmon/nct6694-hwmon.c +++ b/drivers/hwmon/nct6694-hwmon.c @@ -159,6 +159,9 @@ static inline s8 temp_to_reg(long val) #define NCT6694_HWMON_TEMP_CONFIG (HWMON_T_INPUT | HWMON_T_ENABLE | \ HWMON_T_MAX | HWMON_T_MAX_HYST | \ HWMON_T_MAX_ALARM) +#define NCT6694_HWMON_DTIN_CONFIG (HWMON_T_INPUT | \ + HWMON_T_MAX | HWMON_T_MAX_HYST | \ + HWMON_T_MAX_ALARM) #define NCT6694_HWMON_FAN_CONFIG (HWMON_F_INPUT | HWMON_F_ENABLE | \ HWMON_F_MIN | HWMON_F_MIN_ALARM) #define NCT6694_HWMON_PWM_CONFIG (HWMON_PWM_INPUT | HWMON_PWM_ENABLE | \ @@ -193,22 +196,22 @@ static const struct hwmon_channel_info *nct6694_info[] = { NCT6694_HWMON_TEMP_CONFIG, /* TDP2 */ NCT6694_HWMON_TEMP_CONFIG, /* TDP3 */ NCT6694_HWMON_TEMP_CONFIG, /* TDP4 */ - NCT6694_HWMON_TEMP_CONFIG, /* DTIN0 */ - NCT6694_HWMON_TEMP_CONFIG, /* DTIN1 */ - NCT6694_HWMON_TEMP_CONFIG, /* DTIN2 */ - NCT6694_HWMON_TEMP_CONFIG, /* DTIN3 */ - NCT6694_HWMON_TEMP_CONFIG, /* DTIN4 */ - NCT6694_HWMON_TEMP_CONFIG, /* DTIN5 */ - NCT6694_HWMON_TEMP_CONFIG, /* DTIN6 */ - NCT6694_HWMON_TEMP_CONFIG, /* DTIN7 */ - NCT6694_HWMON_TEMP_CONFIG, /* DTIN8 */ - NCT6694_HWMON_TEMP_CONFIG, /* DTIN9 */ - NCT6694_HWMON_TEMP_CONFIG, /* DTIN10 */ - NCT6694_HWMON_TEMP_CONFIG, /* DTIN11 */ - NCT6694_HWMON_TEMP_CONFIG, /* DTIN12 */ - NCT6694_HWMON_TEMP_CONFIG, /* DTIN13 */ - NCT6694_HWMON_TEMP_CONFIG, /* DTIN14 */ - NCT6694_HWMON_TEMP_CONFIG), /* DTIN15 */ + NCT6694_HWMON_DTIN_CONFIG, /* DTIN0 */ + NCT6694_HWMON_DTIN_CONFIG, /* DTIN1 */ + NCT6694_HWMON_DTIN_CONFIG, /* DTIN2 */ + NCT6694_HWMON_DTIN_CONFIG, /* DTIN3 */ + NCT6694_HWMON_DTIN_CONFIG, /* DTIN4 */ + NCT6694_HWMON_DTIN_CONFIG, /* DTIN5 */ + NCT6694_HWMON_DTIN_CONFIG, /* DTIN6 */ + NCT6694_HWMON_DTIN_CONFIG, /* DTIN7 */ + NCT6694_HWMON_DTIN_CONFIG, /* DTIN8 */ + NCT6694_HWMON_DTIN_CONFIG, /* DTIN9 */ + NCT6694_HWMON_DTIN_CONFIG, /* DTIN10 */ + NCT6694_HWMON_DTIN_CONFIG, /* DTIN11 */ + NCT6694_HWMON_DTIN_CONFIG, /* DTIN12 */ + NCT6694_HWMON_DTIN_CONFIG, /* DTIN13 */ + NCT6694_HWMON_DTIN_CONFIG, /* DTIN14 */ + NCT6694_HWMON_DTIN_CONFIG), /* DTIN15 */ HWMON_CHANNEL_INFO(fan, NCT6694_HWMON_FAN_CONFIG, /* FIN0 */ diff --git a/drivers/hwmon/pmbus/pmbus_core.c b/drivers/hwmon/pmbus/pmbus_core.c index 3b219ed5386fba..a73a118fca82c4 100644 --- a/drivers/hwmon/pmbus/pmbus_core.c +++ b/drivers/hwmon/pmbus/pmbus_core.c @@ -1192,7 +1192,9 @@ static int pmbus_get_boolean(struct i2c_client *client, struct pmbus_boolean *b, regval = status & mask; if (regval) { - if (data->revision >= PMBUS_REV_12) { + /* Generic STATUS_WORD alarms are not individually clearable. */ + if (data->revision >= PMBUS_REV_12 && + reg != PMBUS_STATUS_WORD) { ret = _pmbus_write_byte_data(client, page, reg, regval); if (ret) return ret; diff --git a/drivers/hwmon/sht4x.c b/drivers/hwmon/sht4x.c index 9cace0e8acdabc..a97dda9e92dc5d 100644 --- a/drivers/hwmon/sht4x.c +++ b/drivers/hwmon/sht4x.c @@ -277,6 +277,8 @@ static ssize_t heater_enable_store(struct device *dev, heating_time_bound = 1100; } + guard(hwmon_lock)(dev); + if (time_before(jiffies, data->heating_complete)) return -EBUSY; @@ -286,7 +288,7 @@ static ssize_t heater_enable_store(struct device *dev, data->heating_complete = jiffies + msecs_to_jiffies(heating_time_bound); data->data_pending = true; - return 0; + return count; } static ssize_t heater_power_show(struct device *dev, @@ -314,6 +316,8 @@ static ssize_t heater_power_store(struct device *dev, if (power != 20 && power != 110 && power != 200) return -EINVAL; + guard(hwmon_lock)(dev); + data->heater_power = power; return count; @@ -344,6 +348,8 @@ static ssize_t heater_time_store(struct device *dev, if (time != 100 && time != 1000) return -EINVAL; + guard(hwmon_lock)(dev); + data->heater_time = time; return count; diff --git a/drivers/hwmon/yogafan.c b/drivers/hwmon/yogafan.c index 605cc928f21f36..314ee61955dd8c 100644 --- a/drivers/hwmon/yogafan.c +++ b/drivers/hwmon/yogafan.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only -/** +/* * yoga_fan.c - Lenovo Yoga/Legion Fan Hardware Monitoring Driver * * Provides fan speed monitoring for Lenovo Yoga, Legion, and IdeaPad diff --git a/drivers/i2c/busses/i2c-designware-common.c b/drivers/i2c/busses/i2c-designware-common.c index e4dfa2ec58bb76..a1eca6cd4b75e9 100644 --- a/drivers/i2c/busses/i2c-designware-common.c +++ b/drivers/i2c/busses/i2c-designware-common.c @@ -33,6 +33,8 @@ #include #include +#include + #include "i2c-designware-core.h" #define DW_IC_DEFAULT_BUS_CAPACITANCE_pF 100 diff --git a/drivers/i2c/busses/i2c-designware-core.h b/drivers/i2c/busses/i2c-designware-core.h index c71aa2dd368d5f..2c929a6e8da2a3 100644 --- a/drivers/i2c/busses/i2c-designware-core.h +++ b/drivers/i2c/busses/i2c-designware-core.h @@ -18,6 +18,8 @@ #include #include +#include + #define DW_IC_DEFAULT_FUNCTIONALITY (I2C_FUNC_I2C | \ I2C_FUNC_SMBUS_BYTE | \ I2C_FUNC_SMBUS_BYTE_DATA | \ @@ -25,23 +27,6 @@ I2C_FUNC_SMBUS_BLOCK_DATA | \ I2C_FUNC_SMBUS_I2C_BLOCK) -#define DW_IC_CON_MASTER BIT(0) -#define DW_IC_CON_SPEED_STD (1 << 1) -#define DW_IC_CON_SPEED_FAST (2 << 1) -#define DW_IC_CON_SPEED_HIGH (3 << 1) -#define DW_IC_CON_SPEED_MASK GENMASK(2, 1) -#define DW_IC_CON_10BITADDR_SLAVE BIT(3) -#define DW_IC_CON_10BITADDR_MASTER BIT(4) -#define DW_IC_CON_RESTART_EN BIT(5) -#define DW_IC_CON_SLAVE_DISABLE BIT(6) -#define DW_IC_CON_STOP_DET_IFADDRESSED BIT(7) -#define DW_IC_CON_TX_EMPTY_CTRL BIT(8) -#define DW_IC_CON_RX_FIFO_FULL_HLD_CTRL BIT(9) -#define DW_IC_CON_BUS_CLEAR_CTRL BIT(11) - -#define DW_IC_DATA_CMD_DAT GENMASK(7, 0) -#define DW_IC_DATA_CMD_FIRST_DATA_BYTE BIT(11) - /* * Register access parameters */ @@ -55,65 +40,9 @@ #define DW_IC_FIFO_RX_FIELD GENMASK(15, 8) #define DW_IC_FIFO_MIN_DEPTH 2 -/* - * Registers offset - */ -#define DW_IC_CON 0x00 -#define DW_IC_TAR 0x04 -#define DW_IC_SAR 0x08 -#define DW_IC_DATA_CMD 0x10 -#define DW_IC_SS_SCL_HCNT 0x14 -#define DW_IC_SS_SCL_LCNT 0x18 -#define DW_IC_FS_SCL_HCNT 0x1c -#define DW_IC_FS_SCL_LCNT 0x20 -#define DW_IC_HS_SCL_HCNT 0x24 -#define DW_IC_HS_SCL_LCNT 0x28 -#define DW_IC_INTR_STAT 0x2c -#define DW_IC_INTR_MASK 0x30 -#define DW_IC_RAW_INTR_STAT 0x34 -#define DW_IC_RX_TL 0x38 -#define DW_IC_TX_TL 0x3c -#define DW_IC_CLR_INTR 0x40 -#define DW_IC_CLR_RX_UNDER 0x44 -#define DW_IC_CLR_RX_OVER 0x48 -#define DW_IC_CLR_TX_OVER 0x4c -#define DW_IC_CLR_RD_REQ 0x50 -#define DW_IC_CLR_TX_ABRT 0x54 -#define DW_IC_CLR_RX_DONE 0x58 -#define DW_IC_CLR_ACTIVITY 0x5c -#define DW_IC_CLR_STOP_DET 0x60 -#define DW_IC_CLR_START_DET 0x64 -#define DW_IC_CLR_GEN_CALL 0x68 -#define DW_IC_ENABLE 0x6c -#define DW_IC_STATUS 0x70 -#define DW_IC_TXFLR 0x74 -#define DW_IC_RXFLR 0x78 -#define DW_IC_SDA_HOLD 0x7c -#define DW_IC_TX_ABRT_SOURCE 0x80 -#define DW_IC_ENABLE_STATUS 0x9c -#define DW_IC_CLR_RESTART_DET 0xa8 -#define DW_IC_SMBUS_INTR_MASK 0xcc -#define DW_IC_COMP_PARAM_1 0xf4 -#define DW_IC_COMP_VERSION 0xf8 #define DW_IC_SDA_HOLD_MIN_VERS 0x3131312A /* "111*" == v1.11* */ -#define DW_IC_COMP_TYPE 0xfc #define DW_IC_COMP_TYPE_VALUE 0x44570140 /* "DW" + 0x0140 */ -#define DW_IC_INTR_RX_UNDER BIT(0) -#define DW_IC_INTR_RX_OVER BIT(1) -#define DW_IC_INTR_RX_FULL BIT(2) -#define DW_IC_INTR_TX_OVER BIT(3) -#define DW_IC_INTR_TX_EMPTY BIT(4) -#define DW_IC_INTR_RD_REQ BIT(5) -#define DW_IC_INTR_TX_ABRT BIT(6) -#define DW_IC_INTR_RX_DONE BIT(7) -#define DW_IC_INTR_ACTIVITY BIT(8) -#define DW_IC_INTR_STOP_DET BIT(9) -#define DW_IC_INTR_START_DET BIT(10) -#define DW_IC_INTR_GEN_CALL BIT(11) -#define DW_IC_INTR_RESTART_DET BIT(12) -#define DW_IC_INTR_MST_ON_HOLD BIT(13) - #define DW_IC_INTR_DEFAULT_MASK (DW_IC_INTR_RX_FULL | \ DW_IC_INTR_TX_ABRT | \ DW_IC_INTR_STOP_DET) @@ -123,16 +52,6 @@ DW_IC_INTR_RX_UNDER | \ DW_IC_INTR_RD_REQ) -#define DW_IC_ENABLE_ENABLE BIT(0) -#define DW_IC_ENABLE_ABORT BIT(1) - -#define DW_IC_STATUS_ACTIVITY BIT(0) -#define DW_IC_STATUS_TFE BIT(2) -#define DW_IC_STATUS_RFNE BIT(3) -#define DW_IC_STATUS_MASTER_ACTIVITY BIT(5) -#define DW_IC_STATUS_SLAVE_ACTIVITY BIT(6) -#define DW_IC_STATUS_MASTER_HOLD_TX_FIFO_EMPTY BIT(7) - #define DW_IC_SDA_HOLD_RX_SHIFT 16 #define DW_IC_SDA_HOLD_RX_MASK GENMASK(23, 16) diff --git a/drivers/i2c/busses/i2c-designware-master.c b/drivers/i2c/busses/i2c-designware-master.c index 7a301c8b604ef4..a1bcc3797e4ffe 100644 --- a/drivers/i2c/busses/i2c-designware-master.c +++ b/drivers/i2c/busses/i2c-designware-master.c @@ -25,6 +25,8 @@ #include #include +#include + #include "i2c-designware-core.h" #define AMD_TIMEOUT_MIN_US 25 diff --git a/drivers/i2c/busses/i2c-designware-slave.c b/drivers/i2c/busses/i2c-designware-slave.c index ad0d5fbfa6d5e7..0abcc7757b2312 100644 --- a/drivers/i2c/busses/i2c-designware-slave.c +++ b/drivers/i2c/busses/i2c-designware-slave.c @@ -19,6 +19,8 @@ #include #include +#include + #include "i2c-designware-core.h" int i2c_dw_reg_slave(struct i2c_client *slave) diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c index 2563ebe9f24611..3509be3fc744ee 100644 --- a/drivers/iommu/amd/init.c +++ b/drivers/iommu/amd/init.c @@ -906,7 +906,9 @@ static void free_ga_log(struct amd_iommu *iommu) { #ifdef CONFIG_IRQ_REMAP iommu_free_pages(iommu->ga_log); + iommu->ga_log = NULL; iommu_free_pages(iommu->ga_log_tail); + iommu->ga_log_tail = NULL; #endif } @@ -953,6 +955,9 @@ static int iommu_init_ga_log(struct amd_iommu *iommu) if (WARN_ON_ONCE(!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir))) return -EINVAL; + if (iommu->ga_log && iommu->ga_log_tail) + return 0; + iommu->ga_log = iommu_alloc_pages_node_sz(nid, GFP_KERNEL, GA_LOG_SIZE); if (!iommu->ga_log) goto err_out; @@ -1914,19 +1919,20 @@ static int __init init_iommu_one(struct amd_iommu *iommu, struct ivhd_header *h, else iommu->mmio_phys_end = MMIO_CNTR_CONF_OFFSET; + if (h->efr_attr & BIT(IOMMU_IVHD_ATTR_HATDIS_SHIFT)) { + pr_warn_once("Host Address Translation is not supported.\n"); + amd_iommu_hatdis = true; + } + /* XT and GAM require GA mode. */ if ((h->efr_reg & (0x1 << IOMMU_EFR_GASUP_SHIFT)) == 0) { amd_iommu_guest_ir = AMD_IOMMU_GUEST_IR_LEGACY; + break; } else { if (h->efr_reg & BIT(IOMMU_EFR_XTSUP_SHIFT)) amd_iommu_xt_mode = IRQ_REMAP_X2APIC_MODE; } - if (h->efr_attr & BIT(IOMMU_IVHD_ATTR_HATDIS_SHIFT)) { - pr_warn_once("Host Address Translation is not supported.\n"); - amd_iommu_hatdis = true; - } - early_iommu_features_init(iommu, h); break; diff --git a/drivers/iommu/amd/nested.c b/drivers/iommu/amd/nested.c index 63b53b29e02989..f1c7987fc58590 100644 --- a/drivers/iommu/amd/nested.c +++ b/drivers/iommu/amd/nested.c @@ -96,7 +96,7 @@ struct iommu_domain * amd_iommu_alloc_domain_nested(struct iommufd_viommu *viommu, u32 flags, const struct iommu_user_data *user_data) { - int ret; + int ret, hdom_id; unsigned long irqflags; struct nested_domain *ndom; struct guest_domain_mapping_info *gdom_info; @@ -161,8 +161,8 @@ amd_iommu_alloc_domain_nested(struct iommufd_viommu *viommu, u32 flags, } /* The gDomID does not exist. We allocate new hdom_id */ - gdom_info->hdom_id = amd_iommu_pdom_id_alloc(); - if (gdom_info->hdom_id <= 0) { + hdom_id = amd_iommu_pdom_id_alloc(); + if (hdom_id <= 0) { __xa_cmpxchg(&aviommu->gdomid_array, ndom->gdom_id, gdom_info, NULL, GFP_ATOMIC); xa_unlock_irqrestore(&aviommu->gdomid_array, irqflags); @@ -170,6 +170,7 @@ amd_iommu_alloc_domain_nested(struct iommufd_viommu *viommu, u32 flags, goto out_err_gdom_info; } + gdom_info->hdom_id = hdom_id; ndom->gdom_info = gdom_info; refcount_set(&gdom_info->users, 1); diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c index 35b7b2fd4a122f..b52dae11fbbef0 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c @@ -4741,6 +4741,8 @@ static void arm_smmu_disable_action(void *data) { struct arm_smmu_device *smmu = data; + if (smmu->impl_ops && smmu->impl_ops->device_disable) + smmu->impl_ops->device_disable(smmu); arm_smmu_device_disable(smmu); } @@ -5555,8 +5557,6 @@ static void arm_smmu_device_shutdown(struct platform_device *pdev) { struct arm_smmu_device *smmu = platform_get_drvdata(pdev); - if (smmu->impl_ops && smmu->impl_ops->device_disable) - smmu->impl_ops->device_disable(smmu); arm_smmu_device_disable(smmu); } diff --git a/drivers/iommu/riscv/iommu.c b/drivers/iommu/riscv/iommu.c index cec3ddd7ab1032..fe8e6d0f8a23b2 100644 --- a/drivers/iommu/riscv/iommu.c +++ b/drivers/iommu/riscv/iommu.c @@ -382,78 +382,97 @@ static int riscv_iommu_queue_wait(struct riscv_iommu_queue *queue, (int)(cons - index) > 0, 0, timeout_us); } -/* Enqueue an entry and wait to be processed if timeout_us > 0 - * - * Error handling for IOMMU hardware not responding in reasonable time - * will be added as separate patch series along with other RAS features. - * For now, only report hardware failure and continue. - */ -static unsigned int riscv_iommu_queue_send(struct riscv_iommu_queue *queue, - void *entry, size_t entry_size) +static int riscv_iommu_queue_wait_for_space(struct riscv_iommu_queue *queue, + unsigned int last) { - unsigned int prod; unsigned int head; unsigned int tail; + unsigned int hw_head; unsigned long flags; + int ret; - /* Do not preempt submission flow. */ - local_irq_save(flags); + ret = riscv_iommu_readl_timeout(queue->iommu, Q_HEAD(queue), hw_head, + !(hw_head & ~queue->mask) && hw_head != last, + 0, RISCV_IOMMU_QUEUE_TIMEOUT); + if (ret) + return ret; - /* 1. Allocate some space in the queue */ - prod = atomic_inc_return(&queue->prod) - 1; + raw_spin_lock_irqsave(&queue->lock, flags); head = atomic_read(&queue->head); + tail = atomic_read(&queue->tail); + if ((tail - head) >= queue->mask) { + last = Q_ITEM(queue, head); + /* + * Re-read hw_head under the lock so that it is consistent with + * the freshly computed 'last'. Using the pre-lock snapshot + * could produce a stale value that wraps around relative to the + * new 'last', advancing the shadow head past entries that have + * not yet been consumed by the hardware. + */ + hw_head = riscv_iommu_readl(queue->iommu, Q_HEAD(queue)); + if (!(hw_head & ~queue->mask) && hw_head != last) + atomic_add((hw_head - last) & queue->mask, &queue->head); + } + raw_spin_unlock_irqrestore(&queue->lock, flags); - /* 2. Wait for space availability. */ - if ((prod - head) > queue->mask) { - if (readx_poll_timeout(atomic_read, &queue->head, - head, (prod - head) < queue->mask, - 0, RISCV_IOMMU_QUEUE_TIMEOUT)) - goto err_busy; - } else if ((prod - head) == queue->mask) { - const unsigned int last = Q_ITEM(queue, head); + return 0; +} + +/* Enqueue an entry and publish it to the hardware queue. */ +static int riscv_iommu_queue_send(struct riscv_iommu_queue *queue, + void *entry, size_t entry_size, + unsigned int *out_prod) +{ + unsigned int prod; + unsigned int head; + unsigned long flags; + int ret; + + /* 1. Wait for space availability and reserve the next slot. */ + for (;;) { + raw_spin_lock_irqsave(&queue->lock, flags); + + prod = atomic_read(&queue->tail); + head = atomic_read(&queue->head); + + if ((prod - head) < queue->mask) + break; + + head = Q_ITEM(queue, head); + raw_spin_unlock_irqrestore(&queue->lock, flags); - if (riscv_iommu_readl_timeout(queue->iommu, Q_HEAD(queue), head, - !(head & ~queue->mask) && head != last, - 0, RISCV_IOMMU_QUEUE_TIMEOUT)) + ret = riscv_iommu_queue_wait_for_space(queue, head); + if (ret) goto err_busy; - atomic_add((head - last) & queue->mask, &queue->head); } - /* 3. Store entry in the ring buffer */ + /* 2. Store entry in the ring buffer. */ memcpy(queue->base + Q_ITEM(queue, prod) * entry_size, entry, entry_size); - /* 4. Wait for all previous entries to be ready */ - if (readx_poll_timeout(atomic_read, &queue->tail, tail, prod == tail, - 0, RISCV_IOMMU_QUEUE_TIMEOUT)) - goto err_busy; - - /* - * 5. Make sure the ring buffer update (whether in normal or I/O memory) is - * completed and visible before signaling the tail doorbell to fetch - * the next command. 'fence ow, ow' - */ + /* 3. Make sure the entry is visible before updating the queue tail. */ dma_wmb(); riscv_iommu_writel(queue->iommu, Q_TAIL(queue), Q_ITEM(queue, prod + 1)); /* - * 6. Make sure the doorbell write to the device has finished before updating - * the shadow tail index in normal memory. 'fence o, w' + * 4. Make sure the doorbell write to the device has finished before + * updating the shadow tail index in normal memory. 'fence o, w' */ #ifdef CONFIG_MMIOWB mmiowb(); #endif - atomic_inc(&queue->tail); + atomic_set(&queue->tail, prod + 1); + atomic_set(&queue->prod, prod + 1); - /* 7. Complete submission and restore local interrupts */ - local_irq_restore(flags); + if (out_prod) + *out_prod = prod; - return prod; + raw_spin_unlock_irqrestore(&queue->lock, flags); + return 0; err_busy: - local_irq_restore(flags); + /* Report the failure and continue; full RAS recovery is not implemented. */ dev_err_once(queue->iommu->dev, "Hardware error: command enqueue failed\n"); - - return prod; + return ret; } /* @@ -492,7 +511,7 @@ static irqreturn_t riscv_iommu_cmdq_process(int irq, void *data) static void riscv_iommu_cmd_send(struct riscv_iommu_device *iommu, struct riscv_iommu_command *cmd) { - riscv_iommu_queue_send(&iommu->cmdq, cmd, sizeof(*cmd)); + riscv_iommu_queue_send(&iommu->cmdq, cmd, sizeof(*cmd), NULL); } /* Send IOFENCE.C command and wait for all scheduled commands to complete. */ @@ -501,9 +520,12 @@ static void riscv_iommu_cmd_sync(struct riscv_iommu_device *iommu, { struct riscv_iommu_command cmd; unsigned int prod; + int ret; riscv_iommu_cmd_iofence(&cmd); - prod = riscv_iommu_queue_send(&iommu->cmdq, &cmd, sizeof(cmd)); + ret = riscv_iommu_queue_send(&iommu->cmdq, &cmd, sizeof(cmd), &prod); + if (ret) + return; if (!timeout_us) return; @@ -1560,6 +1582,7 @@ int riscv_iommu_init(struct riscv_iommu_device *iommu) int rc; RISCV_IOMMU_QUEUE_INIT(&iommu->cmdq, CQ); + raw_spin_lock_init(&iommu->cmdq.lock); RISCV_IOMMU_QUEUE_INIT(&iommu->fltq, FQ); rc = riscv_iommu_init_check(iommu); diff --git a/drivers/iommu/riscv/iommu.h b/drivers/iommu/riscv/iommu.h index 46df79dd549570..5676001548cc74 100644 --- a/drivers/iommu/riscv/iommu.h +++ b/drivers/iommu/riscv/iommu.h @@ -12,6 +12,7 @@ #define _RISCV_IOMMU_H_ #include +#include #include #include @@ -23,6 +24,7 @@ struct riscv_iommu_queue { atomic_t prod; /* unbounded producer allocation index */ atomic_t head; /* unbounded shadow ring buffer consumer index */ atomic_t tail; /* unbounded shadow ring buffer producer index */ + raw_spinlock_t lock; /* serialize queue publishing */ unsigned int mask; /* index mask, queue length - 1 */ unsigned int irq; /* allocated interrupt number */ struct riscv_iommu_device *iommu; /* iommu device handling the queue when active */ diff --git a/drivers/iommu/s390-iommu.c b/drivers/iommu/s390-iommu.c index f148f559ac5640..58ca7727b7f24e 100644 --- a/drivers/iommu/s390-iommu.c +++ b/drivers/iommu/s390-iommu.c @@ -974,6 +974,8 @@ static unsigned long *get_rto_from_iova(struct s390_domain *domain, case ZPCI_TABLE_TYPE_RFX: case ZPCI_TABLE_TYPE_RSX: rso = get_rso_from_iova(domain, iova); + if (!rso) + return NULL; rsx = calc_rsx(iova); rse = READ_ONCE(rso[rsx]); if (!reg_entry_isvalid(rse)) diff --git a/drivers/irqchip/irq-gic-v5.c b/drivers/irqchip/irq-gic-v5.c index d6f1c0c8b74732..21c34e75873237 100644 --- a/drivers/irqchip/irq-gic-v5.c +++ b/drivers/irqchip/irq-gic-v5.c @@ -974,7 +974,8 @@ static void gicv5_cpu_disable_interrupts(void) { u64 cr0; - cr0 = FIELD_PREP(ICC_CR0_EL1_EN, 0); + cr0 = read_sysreg_s(SYS_ICC_CR0_EL1); + cr0 &= ~ICC_CR0_EL1_EN_MASK; write_sysreg_s(cr0, SYS_ICC_CR0_EL1); isb(); } @@ -991,7 +992,8 @@ static void gicv5_cpu_enable_interrupts(void) pcr = FIELD_PREP(ICC_PCR_EL1_PRIORITY, GICV5_IRQ_PRI_MI); write_sysreg_s(pcr, SYS_ICC_PCR_EL1); - cr0 = FIELD_PREP(ICC_CR0_EL1_EN, 1); + cr0 = read_sysreg_s(SYS_ICC_CR0_EL1); + cr0 |= ICC_CR0_EL1_EN_MASK; write_sysreg_s(cr0, SYS_ICC_CR0_EL1); } diff --git a/drivers/leds/leds-st1202.c b/drivers/leds/leds-st1202.c index 2593ff39f22a6a..168df5ecf27b7c 100644 --- a/drivers/leds/leds-st1202.c +++ b/drivers/leds/leds-st1202.c @@ -237,6 +237,12 @@ static int st1202_led_pattern_set(struct led_classdev *ldev, if (len > ST1202_MAX_PATTERNS) return -EINVAL; + for (int patt = 0; patt < len; patt++) { + if (pattern[patt].delta_t < ST1202_MILLIS_PATTERN_DUR_MIN || + pattern[patt].delta_t > ST1202_MILLIS_PATTERN_DUR_MAX) + return -EINVAL; + } + guard(mutex)(&chip->lock); ret = st1202_write_reg(chip, ST1202_CONFIG_REG, ST1202_CONFIG_REG_SHFT); @@ -244,10 +250,6 @@ static int st1202_led_pattern_set(struct led_classdev *ldev, return ret; for (int patt = 0; patt < len; patt++) { - if (pattern[patt].delta_t < ST1202_MILLIS_PATTERN_DUR_MIN || - pattern[patt].delta_t > ST1202_MILLIS_PATTERN_DUR_MAX) - return -EINVAL; - ret = st1202_pwm_pattern_write(chip, led->led_num, patt, pattern[patt].brightness); if (ret != 0) return ret; diff --git a/drivers/media/i2c/mt9p031.c b/drivers/media/i2c/mt9p031.c index d21510caf45a83..2b09e8315c8ee1 100644 --- a/drivers/media/i2c/mt9p031.c +++ b/drivers/media/i2c/mt9p031.c @@ -452,11 +452,7 @@ static int mt9p031_set_params(struct mt9p031 *mt9p031) ret = mt9p031_write(client, MT9P031_HORIZONTAL_BLANK, hblank - 1); if (ret < 0) return ret; - ret = mt9p031_write(client, MT9P031_VERTICAL_BLANK, vblank - 1); - if (ret < 0) - return ret; - - return ret; + return mt9p031_write(client, MT9P031_VERTICAL_BLANK, vblank - 1); } static int mt9p031_s_stream(struct v4l2_subdev *subdev, int enable) diff --git a/drivers/media/pci/intel/ipu-bridge.c b/drivers/media/pci/intel/ipu-bridge.c index ad3ddfb9ccb1fb..510c0eca448419 100644 --- a/drivers/media/pci/intel/ipu-bridge.c +++ b/drivers/media/pci/intel/ipu-bridge.c @@ -173,6 +173,19 @@ static const struct acpi_device_id ivsc_acpi_ids[] = { { "INTC10E1" }, /* PTL */ }; +/* + * The subset of ivsc_acpi_ids[] which are IVSC, rather than CVS, devices. The + * CVS IDs are deliberately not listed here: new ones keep being added, whereas + * this list is complete. + */ +static const struct acpi_device_id ivsc_only_acpi_ids[] = { + { "INTC1059" }, + { "INTC1095" }, + { "INTC100A" }, + { "INTC10CF" }, + { } +}; + static struct acpi_device *ipu_bridge_get_ivsc_acpi_dev(struct acpi_device *adev) { unsigned int i; @@ -224,6 +237,17 @@ static struct device *ipu_bridge_get_ivsc_csi_dev(struct acpi_device *adev) return csi_dev; } + /* + * The lookups below match on the ACPI companion alone. That is fine for + * CVS, which binds a driver to that very device, but not for IVSC: there + * the ACPI device also has a driverless platform device, which would be + * returned instead of the mei-csi client. Return NULL for IVSC so that + * the caller fails and the probe is retried once the IVSC device shows + * up. + */ + if (!acpi_match_device_ids(adev, ivsc_only_acpi_ids)) + return NULL; + /* Try to locate CVS device on the I2C bus */ csi_dev = bus_find_device_by_acpi_dev(&i2c_bus_type, adev); if (csi_dev) diff --git a/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_av1_req_lat_if.c b/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_av1_req_lat_if.c index 2d622e85f82710..49d9b4a72387eb 100644 --- a/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_av1_req_lat_if.c +++ b/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_av1_req_lat_if.c @@ -1299,11 +1299,12 @@ static void vdec_av1_slice_setup_tile(struct vdec_av1_slice_frame *frame, tile->uniform_tile_spacing_flag = BIT_FLAG(ctrl_tile, V4L2_AV1_TILE_INFO_FLAG_UNIFORM_TILE_SPACING); - for (i = 0; i < tile->tile_cols + 1; i++) + /* Bound the copy to the mi_col_starts[]/mi_row_starts[] capacity. */ + for (i = 0; i < tile->tile_cols + 1 && i < V4L2_AV1_MAX_TILE_COLS + 1; i++) tile->mi_col_starts[i] = ALIGN(ctrl_tile->mi_col_starts[i], BIT(mib_size_log2)) >> mib_size_log2; - for (i = 0; i < tile->tile_rows + 1; i++) + for (i = 0; i < tile->tile_rows + 1 && i < V4L2_AV1_MAX_TILE_ROWS + 1; i++) tile->mi_row_starts[i] = ALIGN(ctrl_tile->mi_row_starts[i], BIT(mib_size_log2)) >> mib_size_log2; } diff --git a/drivers/media/platform/microchip/microchip-sama7g5-isc.c b/drivers/media/platform/microchip/microchip-sama7g5-isc.c index b0302dfc3278d7..7383341ec51d6e 100644 --- a/drivers/media/platform/microchip/microchip-sama7g5-isc.c +++ b/drivers/media/platform/microchip/microchip-sama7g5-isc.c @@ -598,13 +598,8 @@ static int __maybe_unused xisc_runtime_suspend(struct device *dev) static int __maybe_unused xisc_runtime_resume(struct device *dev) { struct isc_device *isc = dev_get_drvdata(dev); - int ret; - - ret = clk_prepare_enable(isc->hclock); - if (ret) - return ret; - return ret; + return clk_prepare_enable(isc->hclock); } static const struct dev_pm_ops microchip_xisc_dev_pm_ops = { diff --git a/drivers/media/platform/qcom/iris/iris_resources.c b/drivers/media/platform/qcom/iris/iris_resources.c index 773f6548370a25..6d3339423eec01 100644 --- a/drivers/media/platform/qcom/iris/iris_resources.c +++ b/drivers/media/platform/qcom/iris/iris_resources.c @@ -78,24 +78,21 @@ int iris_enable_power_domains(struct iris_core *core, struct device *pd_dev) if (ret) return ret; - ret = pm_runtime_get_sync(pd_dev); - if (ret < 0) - return ret; - - return ret; + return pm_runtime_resume_and_get(pd_dev); } int iris_disable_power_domains(struct iris_core *core, struct device *pd_dev) { int ret; + int pm_ret; ret = iris_opp_set_rate(core->dev, 0); - if (ret) - return ret; - pm_runtime_put_sync(pd_dev); + pm_ret = pm_runtime_put_sync(pd_dev); + if (!ret) + ret = pm_ret; - return 0; + return ret; } static struct clk *iris_get_clk_by_type(struct iris_core *core, enum platform_clk_type clk_type) diff --git a/drivers/media/platform/qcom/venus/pm_helpers.c b/drivers/media/platform/qcom/venus/pm_helpers.c index be1cbd5cfe8426..e88e66be4f6dfb 100644 --- a/drivers/media/platform/qcom/venus/pm_helpers.c +++ b/drivers/media/platform/qcom/venus/pm_helpers.c @@ -781,7 +781,6 @@ static int decide_core(struct venus_inst *inst) unsigned long max_freq = ULONG_MAX; struct device *dev = core->dev; struct dev_pm_opp *opp; - int ret = 0; if (legacy_binding) { if (inst->session_type == VIDC_SESSION_TYPE_DEC) @@ -829,11 +828,7 @@ static int decide_core(struct venus_inst *inst) } done: - ret = hfi_session_set_property(inst, ptype, &cu); - if (ret) - return ret; - - return ret; + return hfi_session_set_property(inst, ptype, &cu); } static int acquire_core(struct venus_inst *inst) diff --git a/drivers/media/platform/renesas/rcar-csi2.c b/drivers/media/platform/renesas/rcar-csi2.c index 7305cc4a04cb12..6635f578217553 100644 --- a/drivers/media/platform/renesas/rcar-csi2.c +++ b/drivers/media/platform/renesas/rcar-csi2.c @@ -2273,11 +2273,7 @@ static int rcsi2_init_phtw_v3u(struct rcar_csi2 *priv, return ret; } - ret = rcsi2_phtw_write_array(priv, step4, ARRAY_SIZE(step4)); - if (ret) - return ret; - - return ret; + return rcsi2_phtw_write_array(priv, step4, ARRAY_SIZE(step4)); } /* ----------------------------------------------------------------------------- diff --git a/drivers/media/platform/rockchip/rkvdec/rkvdec-hevc-common.c b/drivers/media/platform/rockchip/rkvdec/rkvdec-hevc-common.c index 9c4a6093af324c..2b8e04dd15727c 100644 --- a/drivers/media/platform/rockchip/rkvdec/rkvdec-hevc-common.c +++ b/drivers/media/platform/rockchip/rkvdec/rkvdec-hevc-common.c @@ -16,6 +16,7 @@ */ #include +#include #include #include "rkvdec.h" @@ -37,15 +38,17 @@ void compute_tiles_uniform(struct rkvdec_hevc_run *run, u16 log2_min_cb_size, s32 pic_in_cts_height, u16 *column_width, u16 *row_height) { const struct v4l2_ctrl_hevc_pps *pps = run->pps; + unsigned int num_cols = v4l2_hevc_pps_num_tile_columns(pps); + unsigned int num_rows = v4l2_hevc_pps_num_tile_rows(pps); int i; - for (i = 0; i < pps->num_tile_columns_minus1 + 1; i++) + for (i = 0; i < num_cols; i++) column_width[i] = ((i + 1) * pic_in_cts_width) / (pps->num_tile_columns_minus1 + 1) - (i * pic_in_cts_width) / (pps->num_tile_columns_minus1 + 1); - for (i = 0; i < pps->num_tile_rows_minus1 + 1; i++) + for (i = 0; i < num_rows; i++) row_height[i] = ((i + 1) * pic_in_cts_height) / (pps->num_tile_rows_minus1 + 1) - (i * pic_in_cts_height) / @@ -57,17 +60,20 @@ void compute_tiles_non_uniform(struct rkvdec_hevc_run *run, u16 log2_min_cb_size s32 pic_in_cts_height, u16 *column_width, u16 *row_height) { const struct v4l2_ctrl_hevc_pps *pps = run->pps; + unsigned int num_cols = v4l2_hevc_pps_num_tile_columns(pps); + unsigned int num_rows = v4l2_hevc_pps_num_tile_rows(pps); s32 sum = 0; int i; - for (i = 0; i < pps->num_tile_columns_minus1; i++) { + /* The last tile entry is written after the loop, so iterate one less. */ + for (i = 0; i < num_cols - 1; i++) { column_width[i] = pps->column_width_minus1[i] + 1; sum += column_width[i]; } column_width[i] = pic_in_cts_width - sum; sum = 0; - for (i = 0; i < pps->num_tile_rows_minus1; i++) { + for (i = 0; i < num_rows - 1; i++) { row_height[i] = pps->row_height_minus1[i] + 1; sum += row_height[i]; } diff --git a/drivers/media/platform/rockchip/rkvdec/rkvdec-hevc.c b/drivers/media/platform/rockchip/rkvdec/rkvdec-hevc.c index 87abf93dfd5e22..92373db50a4667 100644 --- a/drivers/media/platform/rockchip/rkvdec/rkvdec-hevc.c +++ b/drivers/media/platform/rockchip/rkvdec/rkvdec-hevc.c @@ -12,6 +12,7 @@ * Jeffy Chen */ +#include #include #include "rkvdec.h" @@ -135,6 +136,8 @@ static void assemble_hw_pps(struct rkvdec_ctx *ctx, * packet unit). so the driver copy SPS/PPS information to the exact PPS * packet unit for HW accessing. */ + if (pps->pic_parameter_set_id >= ARRAY_SIZE(priv_tbl->param_set)) + return; hw_ps = &priv_tbl->param_set[pps->pic_parameter_set_id]; memset(hw_ps, 0, sizeof(*hw_ps)); @@ -253,9 +256,9 @@ static void assemble_hw_pps(struct rkvdec_ctx *ctx, if (pps->flags & V4L2_HEVC_PPS_FLAG_TILES_ENABLED) { /* Userspace also provide column width and row height for uniform spacing */ - for (i = 0; i <= pps->num_tile_columns_minus1; i++) + for (i = 0; i < v4l2_hevc_pps_num_tile_columns(pps); i++) WRITE_PPS(pps->column_width_minus1[i], COLUMN_WIDTH(i)); - for (i = 0; i <= pps->num_tile_rows_minus1; i++) + for (i = 0; i < v4l2_hevc_pps_num_tile_rows(pps); i++) WRITE_PPS(pps->row_height_minus1[i], ROW_HEIGHT(i)); } else { WRITE_PPS(((sps->pic_width_in_luma_samples + ctb_size_y - 1) / ctb_size_y) - 1, diff --git a/drivers/media/platform/rockchip/rkvdec/rkvdec-vdpu381-hevc.c b/drivers/media/platform/rockchip/rkvdec/rkvdec-vdpu381-hevc.c index fe6414a175510c..6dafa1dd285075 100644 --- a/drivers/media/platform/rockchip/rkvdec/rkvdec-vdpu381-hevc.c +++ b/drivers/media/platform/rockchip/rkvdec/rkvdec-vdpu381-hevc.c @@ -145,6 +145,8 @@ static void assemble_hw_pps(struct rkvdec_ctx *ctx, * packet unit). so the driver copy SPS/PPS information to the exact PPS * packet unit for HW accessing. */ + if (pps->pic_parameter_set_id >= ARRAY_SIZE(priv_tbl->param_set)) + return; hw_ps = &priv_tbl->param_set[pps->pic_parameter_set_id]; memset(hw_ps, 0, sizeof(*hw_ps)); diff --git a/drivers/media/platform/samsung/s3c-camif/camif-core.c b/drivers/media/platform/samsung/s3c-camif/camif-core.c index 221e3c447f361d..a3c8b0a10eb3c5 100644 --- a/drivers/media/platform/samsung/s3c-camif/camif-core.c +++ b/drivers/media/platform/samsung/s3c-camif/camif-core.c @@ -302,7 +302,6 @@ static int camif_media_dev_init(struct camif_dev *camif) struct media_device *md = &camif->media_dev; struct v4l2_device *v4l2_dev = &camif->v4l2_dev; unsigned int ip_rev = camif->variant->ip_revision; - int ret; memset(md, 0, sizeof(*md)); snprintf(md->model, sizeof(md->model), "Samsung S3C%s CAMIF", @@ -317,11 +316,7 @@ static int camif_media_dev_init(struct camif_dev *camif) media_device_init(md); - ret = v4l2_device_register(camif->dev, v4l2_dev); - if (ret < 0) - return ret; - - return ret; + return v4l2_device_register(camif->dev, v4l2_dev); } static void camif_clk_put(struct camif_dev *camif) diff --git a/drivers/media/platform/verisilicon/hantro_g2_hevc_dec.c b/drivers/media/platform/verisilicon/hantro_g2_hevc_dec.c index e8c2e83379def5..e7a7c7a42467a2 100644 --- a/drivers/media/platform/verisilicon/hantro_g2_hevc_dec.c +++ b/drivers/media/platform/verisilicon/hantro_g2_hevc_dec.c @@ -5,6 +5,8 @@ * Copyright (C) 2020 Safran Passenger Innovations LLC */ +#include + #include "hantro_hw.h" #include "hantro_g2_regs.h" @@ -15,8 +17,8 @@ static void prepare_tile_info_buffer(struct hantro_ctx *ctx) const struct v4l2_ctrl_hevc_pps *pps = ctrls->pps; const struct v4l2_ctrl_hevc_sps *sps = ctrls->sps; u16 *p = (u16 *)((u8 *)ctx->hevc_dec.tile_sizes.cpu); - unsigned int num_tile_rows = pps->num_tile_rows_minus1 + 1; - unsigned int num_tile_cols = pps->num_tile_columns_minus1 + 1; + unsigned int num_tile_rows = v4l2_hevc_pps_num_tile_rows(pps); + unsigned int num_tile_cols = v4l2_hevc_pps_num_tile_columns(pps); unsigned int pic_width_in_ctbs, pic_height_in_ctbs; unsigned int max_log2_ctb_size, ctb_size; bool tiles_enabled, uniform_spacing; diff --git a/drivers/media/platform/verisilicon/rockchip_vpu981_hw_av1_dec.c b/drivers/media/platform/verisilicon/rockchip_vpu981_hw_av1_dec.c index e4e21ad373233e..00aa566a4ccdba 100644 --- a/drivers/media/platform/verisilicon/rockchip_vpu981_hw_av1_dec.c +++ b/drivers/media/platform/verisilicon/rockchip_vpu981_hw_av1_dec.c @@ -431,20 +431,39 @@ static int rockchip_vpu981_av1_dec_prepare_run(struct hantro_ctx *ctx) { struct hantro_av1_dec_hw_ctx *av1_dec = &ctx->av1_dec; struct hantro_av1_dec_ctrls *ctrls = &av1_dec->ctrls; + const struct v4l2_av1_tile_info *tile_info; + struct v4l2_ctrl *tge; + u32 num_tiles; ctrls->sequence = hantro_get_ctrl(ctx, V4L2_CID_STATELESS_AV1_SEQUENCE); if (WARN_ON(!ctrls->sequence)) return -EINVAL; - ctrls->tile_group_entry = - hantro_get_ctrl(ctx, V4L2_CID_STATELESS_AV1_TILE_GROUP_ENTRY); - if (WARN_ON(!ctrls->tile_group_entry)) + tge = v4l2_ctrl_find(&ctx->ctrl_handler, + V4L2_CID_STATELESS_AV1_TILE_GROUP_ENTRY); + if (WARN_ON(!tge)) return -EINVAL; + ctrls->tile_group_entry = tge->p_cur.p; ctrls->frame = hantro_get_ctrl(ctx, V4L2_CID_STATELESS_AV1_FRAME); if (WARN_ON(!ctrls->frame)) return -EINVAL; + /* + * rockchip_vpu981_av1_dec_set_tile_info() indexes the tile group + * entry array by tile1 * tile_cols + tile0, so it reads up to + * tile_cols * tile_rows entries, and lays out one descriptor per tile + * in the AV1_MAX_TILES tile_info buffer while programming the real + * tile geometry into the hardware. Reject a frame that claims more + * tiles than userspace submitted, or more than the hardware tile + * buffer holds, so the read stays in bounds and the programmed + * geometry matches the descriptors written. + */ + tile_info = &ctrls->frame->tile_info; + num_tiles = (u32)tile_info->tile_cols * tile_info->tile_rows; + if (num_tiles > tge->elems || num_tiles > AV1_MAX_TILES) + return -EINVAL; + ctrls->film_grain = hantro_get_ctrl(ctx, V4L2_CID_STATELESS_AV1_FILM_GRAIN); @@ -578,16 +597,30 @@ static void rockchip_vpu981_av1_dec_set_tile_info(struct hantro_ctx *ctx) const struct v4l2_av1_tile_info *tile_info = &ctrls->frame->tile_info; const struct v4l2_ctrl_av1_tile_group_entry *group_entry = ctrls->tile_group_entry; - int context_update_y = - tile_info->context_update_tile_id / tile_info->tile_cols; - int context_update_x = - tile_info->context_update_tile_id % tile_info->tile_cols; - int context_update_tile_id = - context_update_x * tile_info->tile_rows + context_update_y; + int context_update_y = 0; + int context_update_x = 0; + int context_update_tile_id = 0; u8 *dst = av1_dec->tile_info.cpu; + u8 *dst_end = dst + av1_dec->tile_info.size; struct hantro_dev *vpu = ctx->dev; int tile0, tile1; + /* + * tile_cols and tile_rows are bounded by the V4L2 control validation + * (V4L2_AV1_MAX_TILE_{COLS,ROWS} and V4L2_AV1_MAX_TILE_COUNT). Guard + * the divisor here, and keep the descriptor writes within the + * AV1_MAX_TILES tile_info buffer below; the register values use the + * unmodified tile geometry. + */ + if (tile_info->tile_cols) { + context_update_y = + tile_info->context_update_tile_id / tile_info->tile_cols; + context_update_x = + tile_info->context_update_tile_id % tile_info->tile_cols; + context_update_tile_id = + context_update_x * tile_info->tile_rows + context_update_y; + } + memset(dst, 0, av1_dec->tile_info.size); for (tile0 = 0; tile0 < tile_info->tile_cols; tile0++) { @@ -598,6 +631,10 @@ static void rockchip_vpu981_av1_dec_set_tile_info(struct hantro_ctx *ctx) tile_info->height_in_sbs_minus_1[tile1] + 1; u32 x0 = tile_info->width_in_sbs_minus_1[tile0] + 1; + /* Stop once the tile_info descriptor buffer is full. */ + if (dst + 16 > dst_end) + break; + /* tile size in SB units (width,height) */ *dst++ = x0; *dst++ = 0; @@ -622,6 +659,8 @@ static void rockchip_vpu981_av1_dec_set_tile_info(struct hantro_ctx *ctx) *dst++ = (end >> 16) & 255; *dst++ = (end >> 24) & 255; } + if (dst + 16 > dst_end) + break; } hantro_reg_write(vpu, &av1_multicore_expect_context_update, !!(context_update_x == 0)); diff --git a/drivers/media/usb/as102/as102_usb_drv.c b/drivers/media/usb/as102/as102_usb_drv.c index a11024451cebdc..be2f8be560fae2 100644 --- a/drivers/media/usb/as102/as102_usb_drv.c +++ b/drivers/media/usb/as102/as102_usb_drv.c @@ -24,35 +24,33 @@ static void as102_usb_stop_stream(struct as102_dev_t *dev); static int as102_open(struct inode *inode, struct file *file); static int as102_release(struct inode *inode, struct file *file); -static const struct usb_device_id as102_usb_id_table[] = { - { USB_DEVICE(AS102_USB_DEVICE_VENDOR_ID, AS102_USB_DEVICE_PID_0001) }, - { USB_DEVICE(PCTV_74E_USB_VID, PCTV_74E_USB_PID) }, - { USB_DEVICE(ELGATO_EYETV_DTT_USB_VID, ELGATO_EYETV_DTT_USB_PID) }, - { USB_DEVICE(NBOX_DVBT_DONGLE_USB_VID, NBOX_DVBT_DONGLE_USB_PID) }, - { USB_DEVICE(SKY_IT_DIGITAL_KEY_USB_VID, SKY_IT_DIGITAL_KEY_USB_PID) }, - { } /* Terminating entry */ +struct as102_dev_info { + const char *name; + /* + * eLNA configuration: devices built on the reference design work best + * with 0xA0, while custom designs seem to require 0xC0 + */ + uint8_t elna_cfg; }; -/* Note that this table must always have the same number of entries as the - as102_usb_id_table struct */ -static const char * const as102_device_names[] = { - AS102_REFERENCE_DESIGN, - AS102_PCTV_74E, - AS102_ELGATO_EYETV_DTT_NAME, - AS102_NBOX_DVBT_DONGLE_NAME, - AS102_SKY_IT_DIGITAL_KEY_NAME, - NULL /* Terminating entry */ -}; +#define DRIVER_INFO(dev_name, dev_elna_cfg) \ + .driver_info = (kernel_ulong_t)&(const struct as102_dev_info){ \ + .name = (dev_name), \ + .elna_cfg = (dev_elna_cfg), \ + } -/* eLNA configuration: devices built on the reference design work best - with 0xA0, while custom designs seem to require 0xC0 */ -static uint8_t const as102_elna_cfg[] = { - 0xA0, - 0xC0, - 0xC0, - 0xA0, - 0xA0, - 0x00 /* Terminating entry */ +static const struct usb_device_id as102_usb_id_table[] = { + { USB_DEVICE(AS102_USB_DEVICE_VENDOR_ID, AS102_USB_DEVICE_PID_0001), + DRIVER_INFO(AS102_REFERENCE_DESIGN, 0xA0) }, + { USB_DEVICE(PCTV_74E_USB_VID, PCTV_74E_USB_PID), + DRIVER_INFO(AS102_PCTV_74E, 0xC0) }, + { USB_DEVICE(ELGATO_EYETV_DTT_USB_VID, ELGATO_EYETV_DTT_USB_PID), + DRIVER_INFO(AS102_ELGATO_EYETV_DTT_NAME, 0xC0) }, + { USB_DEVICE(NBOX_DVBT_DONGLE_USB_VID, NBOX_DVBT_DONGLE_USB_PID), + DRIVER_INFO(AS102_NBOX_DVBT_DONGLE_NAME, 0xA0) }, + { USB_DEVICE(SKY_IT_DIGITAL_KEY_USB_VID, SKY_IT_DIGITAL_KEY_USB_PID), + DRIVER_INFO(AS102_SKY_IT_DIGITAL_KEY_NAME, 0xA0) }, + { } /* Terminating entry */ }; struct usb_driver as102_usb_driver = { @@ -336,29 +334,18 @@ static int as102_usb_probe(struct usb_interface *intf, { int ret; struct as102_dev_t *as102_dev; - int i; - - /* This should never actually happen */ - if (ARRAY_SIZE(as102_usb_id_table) != - (sizeof(as102_device_names) / sizeof(const char *))) { - pr_err("Device names table invalid size"); - return -EINVAL; - } + const struct as102_dev_info *info = (const struct as102_dev_info *)id->driver_info; as102_dev = kzalloc_obj(struct as102_dev_t); if (as102_dev == NULL) return -ENOMEM; - /* Assign the user-friendly device name */ - for (i = 0; i < ARRAY_SIZE(as102_usb_id_table); i++) { - if (id == &as102_usb_id_table[i]) { - as102_dev->name = as102_device_names[i]; - as102_dev->elna_cfg = as102_elna_cfg[i]; - } - } - - if (as102_dev->name == NULL) + if (info) { + as102_dev->name = info->name; + as102_dev->elna_cfg = info->elna_cfg; + } else { as102_dev->name = "Unknown AS102 device"; + } /* set private callback functions */ as102_dev->bus_adap.ops = &as102_priv_ops; diff --git a/drivers/media/usb/dvb-usb-v2/mxl111sf.c b/drivers/media/usb/dvb-usb-v2/mxl111sf.c index 870ac3c8b085d4..6404eb74db32fe 100644 --- a/drivers/media/usb/dvb-usb-v2/mxl111sf.c +++ b/drivers/media/usb/dvb-usb-v2/mxl111sf.c @@ -987,11 +987,7 @@ static int mxl111sf_frontend_attach_atsc_mh(struct dvb_usb_adapter *adap) if (ret < 0) return ret; - ret = mxl111sf_lg2160_frontend_attach(adap, 2); - if (ret < 0) - return ret; - - return ret; + return mxl111sf_lg2160_frontend_attach(adap, 2); } static int mxl111sf_frontend_attach_mercury(struct dvb_usb_adapter *adap) @@ -1007,11 +1003,7 @@ static int mxl111sf_frontend_attach_mercury(struct dvb_usb_adapter *adap) if (ret < 0) return ret; - ret = mxl111sf_lg2161_ep6_frontend_attach(adap, 2); - if (ret < 0) - return ret; - - return ret; + return mxl111sf_lg2161_ep6_frontend_attach(adap, 2); } static int mxl111sf_frontend_attach_mercury_mh(struct dvb_usb_adapter *adap) diff --git a/drivers/media/usb/gspca/jl2005bcd.c b/drivers/media/usb/gspca/jl2005bcd.c index a408fcc3a0608f..4988fbf5005e68 100644 --- a/drivers/media/usb/gspca/jl2005bcd.c +++ b/drivers/media/usb/gspca/jl2005bcd.c @@ -148,17 +148,12 @@ static int jl2005c_start_new_frame(struct gspca_dev *gspca_dev) static int jl2005c_write_reg(struct gspca_dev *gspca_dev, unsigned char reg, unsigned char value) { - int retval; u8 instruction[2]; instruction[0] = reg; instruction[1] = value; - retval = jl2005c_write2(gspca_dev, instruction); - if (retval < 0) - return retval; - - return retval; + return jl2005c_write2(gspca_dev, instruction); } static int jl2005c_get_firmware_id(struct gspca_dev *gspca_dev) diff --git a/drivers/media/v4l2-core/v4l2-ctrls-core.c b/drivers/media/v4l2-core/v4l2-ctrls-core.c index 5b8a594fb9e24e..648b88c868bc6d 100644 --- a/drivers/media/v4l2-core/v4l2-ctrls-core.c +++ b/drivers/media/v4l2-core/v4l2-ctrls-core.c @@ -793,10 +793,30 @@ static int validate_av1_film_grain(struct v4l2_ctrl_av1_film_grain *fg) return 0; } +static int validate_av1_tile_info(struct v4l2_av1_tile_info *t) +{ + /* + * tile_cols and tile_rows index the per-tile descriptor arrays and + * bound the tile loops in the stateless AV1 drivers; the product + * bounds the total tile descriptor count. + */ + if (t->tile_cols > V4L2_AV1_MAX_TILE_COLS || + t->tile_rows > V4L2_AV1_MAX_TILE_ROWS) + return -EINVAL; + + if ((u32)t->tile_cols * t->tile_rows > V4L2_AV1_MAX_TILE_COUNT) + return -EINVAL; + + return 0; +} + static int validate_av1_frame(struct v4l2_ctrl_av1_frame *f) { int ret = 0; + ret = validate_av1_tile_info(&f->tile_info); + if (ret) + return ret; ret = validate_av1_quantization(&f->quantization); if (ret) return ret; @@ -1253,6 +1273,18 @@ static int std_validate_compound(const struct v4l2_ctrl *ctrl, u32 idx, p_hevc_pps->flags &= ~V4L2_HEVC_PPS_FLAG_LOOP_FILTER_ACROSS_TILES_ENABLED; + } else { + /* + * These count the entries the stateless HEVC drivers + * read from column_width_minus1[] / row_height_minus1[] + * and use as tile-loop bounds. + */ + if (p_hevc_pps->num_tile_columns_minus1 >= + ARRAY_SIZE(p_hevc_pps->column_width_minus1)) + return -EINVAL; + if (p_hevc_pps->num_tile_rows_minus1 >= + ARRAY_SIZE(p_hevc_pps->row_height_minus1)) + return -EINVAL; } if (p_hevc_pps->flags & diff --git a/drivers/media/v4l2-core/v4l2-h264.c b/drivers/media/v4l2-core/v4l2-h264.c index c00197d095e75f..2323f559c6a3b1 100644 --- a/drivers/media/v4l2-core/v4l2-h264.c +++ b/drivers/media/v4l2-core/v4l2-h264.c @@ -440,7 +440,8 @@ v4l2_h264_build_b_ref_lists(const struct v4l2_h264_reflist_builder *builder, } if (builder->num_valid > 1 && - !memcmp(b1_reflist, b0_reflist, builder->num_valid)) + !memcmp(b1_reflist, b0_reflist, + sizeof(b1_reflist[0]) * builder->num_valid)) swap(b1_reflist[0], b1_reflist[1]); print_ref_list_b(builder, b0_reflist, 0); diff --git a/drivers/mfd/ab8500-core.c b/drivers/mfd/ab8500-core.c index f0bc0b5a6f4ade..86fa99022cb356 100644 --- a/drivers/mfd/ab8500-core.c +++ b/drivers/mfd/ab8500-core.c @@ -19,7 +19,7 @@ #include #include #include -#include +#include #include /* diff --git a/drivers/mfd/db8500-prcmu.c b/drivers/mfd/db8500-prcmu.c index 21e68a382b1145..6672c55f2ebcc3 100644 --- a/drivers/mfd/db8500-prcmu.c +++ b/drivers/mfd/db8500-prcmu.c @@ -32,7 +32,7 @@ #include #include #include -#include +#include #include #include #include @@ -2285,7 +2285,7 @@ void db8500_prcmu_system_reset(u16 reset_code) /** * db8500_prcmu_get_reset_code - Retrieve SW reset reason code * - * Retrieves the reset reason code stored by prcmu_system_reset() before + * Retrieves the reset reason code stored by db8500_prcmu_system_reset() before * last restart. */ u16 db8500_prcmu_get_reset_code(void) @@ -3041,7 +3041,7 @@ static int db8500_prcmu_probe(struct platform_device *pdev) db8500_irq_init(np); - prcmu_config_esram0_deep_sleep(ESRAM0_DEEP_SLEEP_STATE_RET); + db8500_prcmu_config_esram0_deep_sleep(ESRAM0_DEEP_SLEEP_STATE_RET); err = mfd_add_devices(&pdev->dev, 0, common_prcmu_devs, ARRAY_SIZE(common_prcmu_devs), NULL, 0, db8500_irq_domain); diff --git a/drivers/misc/amd-sbi/rmi-core.c b/drivers/misc/amd-sbi/rmi-core.c index d4238ebad3c6c8..95c9109101b536 100644 --- a/drivers/misc/amd-sbi/rmi-core.c +++ b/drivers/misc/amd-sbi/rmi-core.c @@ -581,6 +581,8 @@ int create_misc_rmi_device(struct sbrmi_data *data, GFP_KERNEL, "sbrmi-%x", data->dev_static_addr); + if (!data->sbrmi_misc_dev.name) + return -ENOMEM; data->sbrmi_misc_dev.minor = MISC_DYNAMIC_MINOR; data->sbrmi_misc_dev.fops = &sbrmi_fops; data->sbrmi_misc_dev.parent = dev; @@ -588,6 +590,8 @@ int create_misc_rmi_device(struct sbrmi_data *data, GFP_KERNEL, "sbrmi-%x", data->dev_static_addr); + if (!data->sbrmi_misc_dev.nodename) + return -ENOMEM; data->sbrmi_misc_dev.mode = 0600; return misc_register(&data->sbrmi_misc_dev); diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c index 839f7482dc1823..43ac8e28e41828 100644 --- a/drivers/net/bonding/bond_alb.c +++ b/drivers/net/bonding/bond_alb.c @@ -678,9 +678,15 @@ static struct slave *rlb_arp_xmit(struct sk_buff *skb, struct bonding *bond) if (arp->op_code == htons(ARPOP_REPLY)) { /* the arp must be sent on the selected rx channel */ tx_slave = rlb_choose_channel(skb, bond, arp); - if (tx_slave) + if (tx_slave && + !ether_addr_equal_64bits(arp->mac_src, + tx_slave->dev->dev_addr)) { + if (unlikely(skb_cow_head(skb, 0))) + return NULL; + arp = (struct arp_pkt *)skb_network_header(skb); bond_hw_addr_copy(arp->mac_src, tx_slave->dev->dev_addr, tx_slave->dev->addr_len); + } netdev_dbg(bond->dev, "(slave %s): Server sent ARP Reply packet\n", tx_slave ? tx_slave->dev->name : "NULL"); } else if (arp->op_code == htons(ARPOP_REQUEST)) { @@ -875,7 +881,7 @@ static int rlb_initialize(struct bonding *bond) spin_unlock_bh(&bond->mode_lock); /* register to receive ARPs */ - bond->recv_probe = rlb_arp_recv; + WRITE_ONCE(bond->recv_probe, rlb_arp_recv); return 0; } @@ -1281,10 +1287,10 @@ unwind: } /* determine if the packet is NA or NS */ -static bool alb_determine_nd(struct sk_buff *skb, struct bonding *bond) +static bool alb_determine_nd(struct sk_buff *skb) { - struct ipv6hdr *ip6hdr; - struct icmp6hdr *hdr; + const struct ipv6hdr *ip6hdr; + const struct icmp6hdr *hdr; if (!pskb_network_may_pull(skb, sizeof(*ip6hdr))) return true; @@ -1296,7 +1302,8 @@ static bool alb_determine_nd(struct sk_buff *skb, struct bonding *bond) if (!pskb_network_may_pull(skb, sizeof(*ip6hdr) + sizeof(*hdr))) return true; - hdr = icmp6_hdr(skb); + ip6hdr = ipv6_hdr(skb); + hdr = (const struct icmp6hdr *)(ip6hdr + 1); return hdr->icmp6_type == NDISC_NEIGHBOUR_ADVERTISEMENT || hdr->icmp6_type == NDISC_NEIGHBOUR_SOLICITATION; } @@ -1339,7 +1346,6 @@ static netdev_tx_t bond_do_alb_xmit(struct sk_buff *skb, struct bonding *bond, struct slave *tx_slave) { struct alb_bond_info *bond_info = &(BOND_ALB_INFO(bond)); - struct ethhdr *eth_data = eth_hdr(skb); if (!tx_slave) { /* unbalanced or unassigned, send through primary */ @@ -1350,7 +1356,9 @@ static netdev_tx_t bond_do_alb_xmit(struct sk_buff *skb, struct bonding *bond, if (tx_slave && bond_slave_can_tx(tx_slave)) { if (tx_slave != rcu_access_pointer(bond->curr_active_slave)) { - ether_addr_copy(eth_data->h_source, + if (unlikely(skb_cow_head(skb, 0))) + return bond_tx_drop(bond->dev, skb); + ether_addr_copy(skb_eth_hdr(skb)->h_source, tx_slave->dev->dev_addr); } @@ -1374,14 +1382,13 @@ struct slave *bond_xmit_tlb_slave_get(struct bonding *bond, struct ethhdr *eth_data; u32 hash_index; - skb_reset_mac_header(skb); - eth_data = eth_hdr(skb); + eth_data = skb_eth_hdr(skb); /* Do not TX balance any multicast or broadcast */ if (!is_multicast_ether_addr(eth_data->h_dest)) { switch (skb->protocol) { case htons(ETH_P_IPV6): - if (alb_determine_nd(skb, bond)) + if (alb_determine_nd(skb)) break; fallthrough; case htons(ETH_P_IP): @@ -1427,8 +1434,7 @@ struct slave *bond_xmit_alb_slave_get(struct bonding *bond, u32 hash_index = 0; int hash_size = 0; - skb_reset_mac_header(skb); - eth_data = eth_hdr(skb); + eth_data = skb_eth_hdr(skb); switch (ntohs(skb->protocol)) { case ETH_P_IP: { @@ -1467,7 +1473,7 @@ struct slave *bond_xmit_alb_slave_get(struct bonding *bond, break; } - if (alb_determine_nd(skb, bond)) { + if (alb_determine_nd(skb)) { do_tx_balance = false; break; } diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 522eab060f9edc..6ea46a617ee600 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1245,7 +1245,7 @@ static void bond_peer_notify_may_events(struct bonding *bond, bool force) } if (notified || force) - bond->send_peer_notif--; + WRITE_ONCE(bond->send_peer_notif, bond->send_peer_notif - 1); } /** @@ -2284,7 +2284,7 @@ skip_mac_set: } } - bond->slave_cnt++; + WRITE_ONCE(bond->slave_cnt, bond->slave_cnt + 1); netdev_compute_master_upper_features(bond->dev, true); bond_set_carrier(bond); @@ -2517,9 +2517,7 @@ static int __bond_release_one(struct net_device *bond_dev, bond_alb_deinit_slave(bond, slave); } - if (all) { - RCU_INIT_POINTER(bond->curr_active_slave, NULL); - } else if (oldcurrent == slave) { + if (!all && oldcurrent == slave) { /* Note that we hold RTNL over this sequence, so there * is no concern that another slave add/remove event * will interfere. @@ -2533,7 +2531,7 @@ static int __bond_release_one(struct net_device *bond_dev, unblock_netpoll_tx(); synchronize_rcu(); - bond->slave_cnt--; + WRITE_ONCE(bond->slave_cnt, bond->slave_cnt - 1); if (!bond_has_slaves(bond)) { call_netdevice_notifiers(NETDEV_CHANGEADDR, bond->dev); @@ -4385,13 +4383,13 @@ static int bond_open(struct net_device *bond_dev) if (bond->params.arp_interval) { /* arp interval, in milliseconds. */ queue_delayed_work(bond->wq, &bond->arp_work, 0); - bond->recv_probe = bond_rcv_validate; + WRITE_ONCE(bond->recv_probe, bond_rcv_validate); } if (BOND_MODE(bond) == BOND_MODE_8023AD) { queue_delayed_work(bond->wq, &bond->ad_work, 0); /* register to receive LACPDUs */ - bond->recv_probe = bond_3ad_lacpdu_recv; + WRITE_ONCE(bond->recv_probe, bond_3ad_lacpdu_recv); bond_3ad_initiate_agg_selection(bond, 1); bond_for_each_slave(bond, slave, iter) @@ -4413,7 +4411,7 @@ static int bond_close(struct net_device *bond_dev) struct slave *slave; bond_work_cancel_all(bond); - bond->send_peer_notif = 0; + WRITE_ONCE(bond->send_peer_notif, 0); WRITE_ONCE(bond->recv_probe, NULL); /* Wait for any in-flight RX handlers */ @@ -5124,7 +5122,7 @@ static void bond_skip_slave(struct bond_up_slave *slaves, if (skipslave == slaves->arr[idx]) { slaves->arr[idx] = slaves->arr[slaves->count - 1]; - slaves->count--; + WRITE_ONCE(slaves->count, slaves->count - 1); break; } } diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c index e590c8dee86e1e..d8cdbfca1bb160 100644 --- a/drivers/net/bonding/bond_options.c +++ b/drivers/net/bonding/bond_options.c @@ -1147,11 +1147,11 @@ static int bond_option_arp_interval_set(struct bonding *bond, */ if (!newval->value) { if (bond->params.arp_validate) - bond->recv_probe = NULL; + WRITE_ONCE(bond->recv_probe, NULL); cancel_delayed_work_sync(&bond->arp_work); } else { /* arp_validate can be set only in active-backup mode */ - bond->recv_probe = bond_rcv_validate; + WRITE_ONCE(bond->recv_probe, bond_rcv_validate); cancel_delayed_work_sync(&bond->mii_work); queue_delayed_work(bond->wq, &bond->arp_work, 0); } diff --git a/drivers/net/dsa/bcm_sf2_cfp.c b/drivers/net/dsa/bcm_sf2_cfp.c index 50d3a818eb1b74..84a086c3e99b4d 100644 --- a/drivers/net/dsa/bcm_sf2_cfp.c +++ b/drivers/net/dsa/bcm_sf2_cfp.c @@ -1088,6 +1088,8 @@ static int bcm_sf2_cfp_rule_get_all(struct bcm_sf2_priv *priv, unsigned int index = 1, rules_cnt = 0; for_each_set_bit_from(index, priv->cfp.unique, priv->num_cfp_rules) { + if (rules_cnt == nfc->rule_cnt) + return -EMSGSIZE; rule_locs[rules_cnt] = index; rules_cnt++; } diff --git a/drivers/net/dsa/lantiq/lantiq_gswip.h b/drivers/net/dsa/lantiq/lantiq_gswip.h index bc3686faad0d63..0b75be14dc109f 100644 --- a/drivers/net/dsa/lantiq/lantiq_gswip.h +++ b/drivers/net/dsa/lantiq/lantiq_gswip.h @@ -42,7 +42,7 @@ #define GSWIP_MDIO_PHY_FDUP_DIS 0x0600 #define GSWIP_MDIO_PHY_FCONTX_MASK 0x0180 #define GSWIP_MDIO_PHY_FCONTX_AUTO 0x0000 -#define GSWIP_MDIO_PHY_FCONTX_EN 0x0100 +#define GSWIP_MDIO_PHY_FCONTX_EN 0x0080 #define GSWIP_MDIO_PHY_FCONTX_DIS 0x0180 #define GSWIP_MDIO_PHY_FCONRX_MASK 0x0060 #define GSWIP_MDIO_PHY_FCONRX_AUTO 0x0000 diff --git a/drivers/net/dsa/mt7530-mmio.c b/drivers/net/dsa/mt7530-mmio.c index 119fdd863d9179..fd68b1cd063068 100644 --- a/drivers/net/dsa/mt7530-mmio.c +++ b/drivers/net/dsa/mt7530-mmio.c @@ -12,6 +12,7 @@ static const struct of_device_id mt7988_of_match[] = { { .compatible = "airoha,an7583-switch", .data = &mt753x_table[ID_AN7583], }, { .compatible = "airoha,en7581-switch", .data = &mt753x_table[ID_EN7581], }, + { .compatible = "econet,en7528-switch", .data = &mt753x_table[ID_EN7528], }, { .compatible = "mediatek,mt7988-switch", .data = &mt753x_table[ID_MT7988], }, { /* sentinel */ }, }; diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index aa33d94e11b5f9..56ee8dc34f5185 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -2902,6 +2902,30 @@ static void en7581_mac_port_get_caps(struct dsa_switch *ds, int port, } } +static void en7528_mac_port_get_caps(struct dsa_switch *ds, int port, + struct phylink_config *config) +{ + switch (port) { + /* Ports which are connected to switch PHYs. There is no MII pinout. */ + case 1 ... 4: + __set_bit(PHY_INTERFACE_MODE_INTERNAL, + config->supported_interfaces); + + config->mac_capabilities |= MAC_10 | MAC_100 | MAC_1000FD; + break; + + /* Port 6 is connected to SoC's GMAC at 1000 Mbps full duplex. There + * is no MII pinout. + */ + case 6: + __set_bit(PHY_INTERFACE_MODE_INTERNAL, + config->supported_interfaces); + + config->mac_capabilities |= MAC_1000FD; + break; + } +} + static void mt7530_mac_config(struct dsa_switch *ds, int port, unsigned int mode, phy_interface_t interface) @@ -3091,19 +3115,34 @@ static void mt753x_phylink_get_caps(struct dsa_switch *ds, int port, struct phylink_config *config) { struct mt7530_priv *priv = ds->priv; - u32 eeecr; config->mac_capabilities = MAC_ASYM_PAUSE | MAC_SYM_PAUSE; - config->lpi_capabilities = MAC_100FD | MAC_1000FD | MAC_2500FD; + priv->info->mac_port_get_caps(ds, port, config); - eeecr = mt7530_read(priv, MT753X_PMEEECR_P(port)); - /* tx_lpi_timer should be in microseconds. The time units for - * LPI threshold are unspecified. + /* The EN7528 GPHYs report EEE capability, but negotiating EEE with + * common link partners (e.g. Realtek GbE NICs) results in an unstable + * link with dropped frames. Leave the LPI capabilities empty so that + * phylink disables EEE on these PHYs and refuses to enable it from + * userspace. */ - config->lpi_timer_default = FIELD_GET(LPI_THRESH_MASK, eeecr); - - priv->info->mac_port_get_caps(ds, port, config); + if (priv->id != ID_EN7528 && + config->mac_capabilities & (MAC_100FD | MAC_1000FD)) { + u32 eeecr = mt7530_read(priv, MT753X_PMEEECR_P(port)); + + /* LPI above 1 Gbps is not supported */ + config->lpi_capabilities = config->mac_capabilities & + (MAC_100FD | MAC_1000FD); + phy_interface_copy(config->lpi_interfaces, + config->supported_interfaces); + __clear_bit(PHY_INTERFACE_MODE_2500BASEX, + config->lpi_interfaces); + + /* tx_lpi_timer should be in microseconds. The time units for + * LPI threshold are unspecified. + */ + config->lpi_timer_default = FIELD_GET(LPI_THRESH_MASK, eeecr); + } } static int mt753x_pcs_validate(struct phylink_pcs *pcs, @@ -3244,7 +3283,8 @@ mt753x_conduit_state_change(struct dsa_switch *ds, * forwarded to the numerically smallest CPU port whose conduit * interface is up. */ - if (priv->id != ID_MT7530 && priv->id != ID_MT7621) + if (priv->id != ID_MT7530 && priv->id != ID_MT7621 && + priv->id != ID_EN7528) return; mask = BIT(cpu_dp->index); @@ -3449,6 +3489,16 @@ const struct mt753x_info mt753x_table[] = { .phy_write_c45 = mt7531_ind_c45_phy_write, .mac_port_get_caps = en7581_mac_port_get_caps, }, + [ID_EN7528] = { + .id = ID_EN7528, + .pcs_ops = &mt7530_pcs_ops, + .sw_setup = mt7988_setup, + .phy_read_c22 = mt7531_ind_c22_phy_read, + .phy_write_c22 = mt7531_ind_c22_phy_write, + .phy_read_c45 = mt7531_ind_c45_phy_read, + .phy_write_c45 = mt7531_ind_c45_phy_write, + .mac_port_get_caps = en7528_mac_port_get_caps, + }, }; EXPORT_SYMBOL_GPL(mt753x_table); diff --git a/drivers/net/dsa/mt7530.h b/drivers/net/dsa/mt7530.h index dd33b0df3419e3..5f1e841f42c0ed 100644 --- a/drivers/net/dsa/mt7530.h +++ b/drivers/net/dsa/mt7530.h @@ -21,6 +21,7 @@ enum mt753x_id { ID_MT7988 = 3, ID_EN7581 = 4, ID_AN7583 = 5, + ID_EN7528 = 6, }; #define NUM_TRGMII_CTRL 5 diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 80b877c74513d6..7f68a0c5580265 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -2438,6 +2438,7 @@ static int mv88e6xxx_get_rxnfc(struct dsa_switch *ds, int port, struct ethtool_rx_flow_spec *fs = &rxnfc->fs; struct mv88e6xxx_chip *chip = ds->priv; struct mv88e6xxx_policy *policy; + u32 cnt = 0; int err; int id; @@ -2463,11 +2464,18 @@ static int mv88e6xxx_get_rxnfc(struct dsa_switch *ds, int port, break; case ETHTOOL_GRXCLSRLALL: rxnfc->data = 0; - rxnfc->rule_cnt = 0; - idr_for_each_entry(&chip->policies, policy, id) - if (policy->port == port) - rule_locs[rxnfc->rule_cnt++] = id; err = 0; + idr_for_each_entry(&chip->policies, policy, id) { + if (policy->port != port) + continue; + if (cnt == rxnfc->rule_cnt) { + err = -EMSGSIZE; + break; + } + rule_locs[cnt++] = id; + } + if (!err) + rxnfc->rule_cnt = cnt; break; default: err = -EOPNOTSUPP; diff --git a/drivers/net/ethernet/airoha/airoha_eth.h b/drivers/net/ethernet/airoha/airoha_eth.h index b894828b13752e..70f16189b25827 100644 --- a/drivers/net/ethernet/airoha/airoha_eth.h +++ b/drivers/net/ethernet/airoha/airoha_eth.h @@ -538,7 +538,7 @@ struct airoha_wdma_info { /* RX queue to IRQ mapping: BIT(q) in IRQ(n) */ #define RX_IRQ0_BANK_PIN_MASK 0x839f -#define RX_IRQ1_BANK_PIN_MASK 0x7fe00000 +#define RX_IRQ1_BANK_PIN_MASK 0xffe00000 #define RX_IRQ2_BANK_PIN_MASK 0x20 #define RX_IRQ3_BANK_PIN_MASK 0x40 #define RX_IRQ_BANK_PIN_MASK(_n) \ diff --git a/drivers/net/ethernet/allwinner/sun4i-emac.c b/drivers/net/ethernet/allwinner/sun4i-emac.c index a297874f4a819e..9382b4b329bdf3 100644 --- a/drivers/net/ethernet/allwinner/sun4i-emac.c +++ b/drivers/net/ethernet/allwinner/sun4i-emac.c @@ -1067,6 +1067,7 @@ static int emac_probe(struct platform_device *pdev) return 0; out_release_sram: + of_node_put(db->phy_node); sunxi_sram_release(&pdev->dev); out_clk_disable_unprepare: clk_disable_unprepare(db->clk); @@ -1094,6 +1095,7 @@ static void emac_remove(struct platform_device *pdev) } unregister_netdev(ndev); + of_node_put(db->phy_node); sunxi_sram_release(&pdev->dev); clk_disable_unprepare(db->clk); irq_dispose_mapping(ndev->irq); diff --git a/drivers/net/ethernet/amd/pds_core/fw.c b/drivers/net/ethernet/amd/pds_core/fw.c index fa626719e68d1b..59d262b0d29c58 100644 --- a/drivers/net/ethernet/amd/pds_core/fw.c +++ b/drivers/net/ethernet/amd/pds_core/fw.c @@ -107,8 +107,10 @@ int pdsc_firmware_update(struct pdsc *pdsc, const struct firmware *fw, dev_info(pdsc->dev, "Installing firmware\n"); - if (!pdsc->cmd_regs) + if (!pdsc->cmd_regs) { + NL_SET_ERR_MSG_MOD(extack, "BARs not mapped"); return -ENXIO; + } dl = priv_to_devlink(pdsc); devlink_flash_update_status_notify(dl, "Preparing to flash", @@ -134,6 +136,12 @@ int pdsc_firmware_update(struct pdsc *pdsc, const struct firmware *fw, copy_sz = min_t(unsigned int, buf_sz, fw->size - offset); mutex_lock(&pdsc->devcmd_lock); + if (!pdsc->cmd_regs) { + mutex_unlock(&pdsc->devcmd_lock); + err = -ENXIO; + NL_SET_ERR_MSG_MOD(extack, "Device reset during flash"); + goto err_out; + } memcpy_toio(&pdsc->cmd_regs->data, fw->data + offset, copy_sz); err = pdsc_devcmd_fw_download_locked(pdsc, data_addr, offset, copy_sz); diff --git a/drivers/net/ethernet/amd/pds_core/main.c b/drivers/net/ethernet/amd/pds_core/main.c index 9a2c64198d03bb..a19269f6b66c75 100644 --- a/drivers/net/ethernet/amd/pds_core/main.c +++ b/drivers/net/ethernet/amd/pds_core/main.c @@ -507,8 +507,12 @@ static void pdsc_reset_prepare(struct pci_dev *pdev) pdsc_auxbus_dev_del(pdsc, pdsc, &pdsc->padev); } - pdsc_unmap_bars(pdsc); - pci_release_regions(pdev); + if (!pdev->is_virtfn) { + mutex_lock(&pdsc->devcmd_lock); + pdsc_unmap_bars(pdsc); + mutex_unlock(&pdsc->devcmd_lock); + pci_release_regions(pdev); + } if (pci_is_enabled(pdev)) pci_disable_device(pdev); } @@ -536,7 +540,9 @@ static void pdsc_reset_done(struct pci_dev *pdev) return; } + mutex_lock(&pdsc->devcmd_lock); err = pdsc_map_bars(pdsc); + mutex_unlock(&pdsc->devcmd_lock); if (err) return; } diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c index 2de974213090cf..e2e850c1b90b1e 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c @@ -3400,7 +3400,7 @@ static void xgbe_enable_rx(struct xgbe_prv_data *pdata) XGMAC_IOWRITE(pdata, MAC_RQC0R, reg_val); /* Enable MAC Rx */ - XGMAC_IOWRITE_BITS(pdata, MAC_RCR, DCRCC, 1); + XGMAC_IOWRITE_BITS(pdata, MAC_RCR, DCRCC, 0); XGMAC_IOWRITE_BITS(pdata, MAC_RCR, CST, 1); XGMAC_IOWRITE_BITS(pdata, MAC_RCR, ACS, 1); XGMAC_IOWRITE_BITS(pdata, MAC_RCR, RE, 1); @@ -3411,7 +3411,6 @@ static void xgbe_disable_rx(struct xgbe_prv_data *pdata) unsigned int i; /* Disable MAC Rx */ - XGMAC_IOWRITE_BITS(pdata, MAC_RCR, DCRCC, 0); XGMAC_IOWRITE_BITS(pdata, MAC_RCR, CST, 0); XGMAC_IOWRITE_BITS(pdata, MAC_RCR, ACS, 0); XGMAC_IOWRITE_BITS(pdata, MAC_RCR, RE, 0); diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c b/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c index ed0977832ce4f5..f2176ef3a127b9 100644 --- a/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c +++ b/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c @@ -148,8 +148,9 @@ static int tx_spb_ring_full(struct bcmasp_intf *intf, int cnt) int next_index, i; /* Check if we have enough room for cnt descriptors */ + next_index = intf->tx_spb_index; for (i = 0; i < cnt; i++) { - next_index = incr_ring(intf->tx_spb_index, DESC_RING_COUNT); + next_index = incr_ring(next_index, DESC_RING_COUNT); if (next_index == intf->tx_spb_clean_index) return 1; } @@ -301,6 +302,7 @@ static netdev_tx_t bcmasp_xmit(struct sk_buff *skb, struct net_device *dev) txcb->bytes_sent = total_bytes; dma_unmap_addr_set(txcb, dma_addr, mapping); dma_unmap_len_set(txcb, dma_len, size); + txcb->last = false; if (!i) { desc->flags |= DESC_SOF; if (csum_hw) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index fd2ee24f3b0bcf..ced998399efc33 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -462,6 +462,16 @@ u16 bnxt_xmit_get_cfa_action(struct sk_buff *skb) static void bnxt_txr_db_kick(struct bnxt *bp, struct bnxt_tx_ring_info *txr, u16 prod) { + /* If the most recent BD has its completion suppressed, unset the bit + * so that a completion is generated, otherwise nothing is left to + * clean the ring and wake the queue. + */ + if (txr->kick_txbd0) { + txr->kick_txbd0->tx_bd_len_flags_type &= + cpu_to_le32(~TX_BD_FLAGS_NO_CMPL); + txr->kick_txbd0 = NULL; + } + /* Sync BD data before updating doorbell */ wmb(); bnxt_db_write(bp, &txr->tx_db, prod); @@ -485,7 +495,6 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev) struct bnxt_sw_tx_bd *tx_buf; __le32 lflags = 0; skb_frag_t *frag; - netdev_tx_t ret; i = skb_get_queue_mapping(skb); if (unlikely(i >= bp->tx_nr_rings)) { @@ -509,11 +518,22 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev) if (skb_is_gso(skb) && (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) && !(bp->flags & BNXT_FLAG_UDP_GSO_CAP)) { - ret = bnxt_sw_udp_gso_xmit(bp, txr, txq, skb); - if (txr->kick_pending) + int rc = bnxt_sw_udp_gso_xmit(bp, txr, txq, skb); + + /* if SW USO queued a packet, the doorbell will be written + * below and there is no reason to track the last BD with + * suppressed completions + */ + if (rc > 0) + txr->kick_txbd0 = NULL; + + /* if a packet was queued by SW USO or a doorbell was pending + * from a previous xmit that was deferred, write the doorbell. + */ + if (rc > 0 || txr->kick_pending) bnxt_txr_db_kick(bp, txr, txr->tx_prod); - return ret; + return rc < 0 ? NETDEV_TX_BUSY : NETDEV_TX_OK; } free_size = bnxt_tx_avail(bp, txr); @@ -751,23 +771,23 @@ normal_tx: prod = NEXT_TX(prod); WRITE_ONCE(txr->tx_prod, prod); + txr->kick_txbd0 = NULL; if (!netdev_xmit_more() || netif_xmit_stopped(txq)) { bnxt_txr_db_kick(bp, txr, prod); } else { - if (free_size >= bp->tx_wake_thresh) + if (free_size >= bp->tx_wake_thresh) { txbd0->tx_bd_len_flags_type |= cpu_to_le32(TX_BD_FLAGS_NO_CMPL); + txr->kick_txbd0 = txbd0; + } txr->kick_pending = 1; } tx_done: if (unlikely(bnxt_tx_avail(bp, txr) <= MAX_SKB_FRAGS + 1)) { - if (netdev_xmit_more() && !tx_buf->is_push) { - txbd0->tx_bd_len_flags_type &= - cpu_to_le32(~TX_BD_FLAGS_NO_CMPL); + if (txr->kick_pending) bnxt_txr_db_kick(bp, txr, prod); - } netif_txq_try_stop(txq, bnxt_tx_avail(bp, txr), bp->tx_wake_thresh); @@ -1514,14 +1534,16 @@ static int bnxt_discard_rx(struct bnxt *bp, struct bnxt_cp_ring_info *cpr, return 0; } -static u16 bnxt_alloc_agg_idx(struct bnxt_rx_ring_info *rxr, u16 agg_id) +static u16 bnxt_alloc_agg_idx(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, + u16 agg_id) { struct bnxt_tpa_idx_map *map = rxr->rx_tpa_idx_map; - u16 idx = agg_id & MAX_TPA_P5_MASK; + u16 idx = agg_id & (bp->max_tpa_roundup_size - 1); if (test_bit(idx, map->agg_idx_bmap)) { - idx = find_first_zero_bit(map->agg_idx_bmap, MAX_TPA_P5); - if (idx >= MAX_TPA_P5) + idx = find_first_zero_bit(map->agg_idx_bmap, + bp->max_tpa_roundup_size); + if (idx >= bp->max_tpa_roundup_size) return INVALID_HW_RING_ID; } __set_bit(idx, map->agg_idx_bmap); @@ -1586,7 +1608,7 @@ static void bnxt_tpa_start(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) { agg_id = TPA_START_AGG_ID_P5(tpa_start); - agg_id = bnxt_alloc_agg_idx(rxr, agg_id); + agg_id = bnxt_alloc_agg_idx(bp, rxr, agg_id); if (unlikely(agg_id == INVALID_HW_RING_ID)) { netdev_warn(bp->dev, "Unable to allocate agg ID for ring %d, agg 0x%x\n", rxr->bnapi->index, @@ -3584,7 +3606,7 @@ static void bnxt_free_one_tpa_info_data(struct bnxt *bp, { int i; - for (i = 0; i < bp->max_tpa; i++) { + for (i = 0; i < bp->max_tpa_roundup_size; i++) { struct bnxt_tpa_info *tpa_info = &rxr->rx_tpa[i]; u8 *data = tpa_info->data; @@ -3781,7 +3803,7 @@ static void bnxt_free_one_tpa_info(struct bnxt *bp, kfree(rxr->rx_tpa_idx_map); rxr->rx_tpa_idx_map = NULL; if (rxr->rx_tpa) { - for (i = 0; i < bp->max_tpa; i++) { + for (i = 0; i < bp->max_tpa_roundup_size; i++) { kfree(rxr->rx_tpa[i].agg_arr); rxr->rx_tpa[i].agg_arr = NULL; } @@ -3807,13 +3829,14 @@ static int bnxt_alloc_one_tpa_info(struct bnxt *bp, struct rx_agg_cmp *agg; int i; - rxr->rx_tpa = kzalloc_objs(struct bnxt_tpa_info, bp->max_tpa); + rxr->rx_tpa = kzalloc_objs(struct bnxt_tpa_info, + bp->max_tpa_roundup_size); if (!rxr->rx_tpa) return -ENOMEM; if (!(bp->flags & BNXT_FLAG_CHIP_P5_PLUS)) return 0; - for (i = 0; i < bp->max_tpa; i++) { + for (i = 0; i < bp->max_tpa_roundup_size; i++) { agg = kzalloc_objs(*agg, MAX_SKB_FRAGS); if (!agg) return -ENOMEM; @@ -3832,6 +3855,9 @@ static int bnxt_alloc_tpa_info(struct bnxt *bp) bp->max_tpa = MAX_TPA; if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) { + /* TPA is not supported at all, so there is nothing to + * allocate. + */ if (!bp->max_tpa_v2) return 0; bp->max_tpa = min_t(u16, bp->max_tpa_v2, MAX_TPA_P5); @@ -3839,6 +3865,7 @@ static int bnxt_alloc_tpa_info(struct bnxt *bp) if (bp->max_tpa <= 32 && BNXT_CHIP_P5(bp) && !BNXT_NPAR(bp)) bp->max_tpa = MAX_TPA_P5; } + bp->max_tpa_roundup_size = roundup_pow_of_two(bp->max_tpa); for (i = 0; i < bp->rx_nr_rings; i++) { struct bnxt_rx_ring_info *rxr = &bp->rx_ring[i]; @@ -4551,7 +4578,7 @@ static int bnxt_alloc_one_tpa_info_data(struct bnxt *bp, u8 *data; int i; - for (i = 0; i < bp->max_tpa; i++) { + for (i = 0; i < bp->max_tpa_roundup_size; i++) { data = __bnxt_alloc_rx_frag(bp, &mapping, rxr, GFP_KERNEL); if (!data) @@ -5006,7 +5033,8 @@ void bnxt_set_rx_skb_mode(struct bnxt *bp, bool page_mode) bnxt_get_max_rings(bp, &rx, &tx, true); if (rx > 1) { bp->flags &= ~BNXT_FLAG_NO_AGG_RINGS; - bp->dev->hw_features |= NETIF_F_LRO; + if (BNXT_SUPPORTS_TPA(bp)) + bp->dev->hw_features |= NETIF_F_LRO; } } @@ -5427,6 +5455,8 @@ static void bnxt_clear_ring_indices(struct bnxt *bp) txr->tx_prod = 0; txr->tx_cons = 0; txr->tx_hw_cons = 0; + txr->kick_pending = 0; + txr->kick_txbd0 = NULL; } rxr = bnapi->rx_ring; @@ -11340,8 +11370,13 @@ static int bnxt_shutdown_nic(struct bnxt *bp, bool irq_re_init) static int bnxt_init_nic(struct bnxt *bp, bool irq_re_init) { + int rc; + bnxt_init_cp_rings(bp); - bnxt_init_rx_rings(bp); + rc = bnxt_init_rx_rings(bp); + if (rc) + return rc; + bnxt_init_tx_rings(bp); bnxt_init_ring_grps(bp, irq_re_init); bnxt_init_vnics(bp); @@ -11772,6 +11807,8 @@ static int bnxt_tx_queue_start(struct bnxt *bp, int idx) txr->tx_prod = 0; txr->tx_cons = 0; txr->tx_hw_cons = 0; + txr->kick_pending = 0; + txr->kick_txbd0 = NULL; start_tx: WRITE_ONCE(txr->dev_state, 0); synchronize_net(); @@ -14563,7 +14600,14 @@ static void bnxt_rx_ring_reset(struct bnxt *bp) rxr->rx_sw_agg_prod = 0; rxr->rx_next_cons = 0; rxr->bnapi->in_reset = false; - bnxt_alloc_one_rx_ring(bp, i); + rc = bnxt_alloc_one_rx_ring(bp, i); + if (rc) { + netdev_warn(bp->dev, "RX ring reset failed to allocate buffers, rc = %d, falling back to global reset\n", + rc); + bnxt_reset_task(bp, true); + bnxt_rtnl_unlock_sp(bp); + return; + } cpr = &rxr->bnapi->cp_ring; cpr->sw_stats->rx.rx_resets++; if (bp->flags & BNXT_FLAG_AGG_RINGS) @@ -16289,6 +16333,8 @@ static int bnxt_queue_mem_alloc(struct net_device *dev, clone->need_head_pool = false; clone->rx_page_size = qcfg->rx_page_size; clone->rx_agg_bmap = NULL; + clone->rx_tpa = NULL; + clone->rx_tpa_idx_map = NULL; rc = bnxt_alloc_rx_page_pool(bp, clone, rxr->page_pool->p.nid); if (rc) @@ -16332,11 +16378,16 @@ static int bnxt_queue_mem_alloc(struct net_device *dev, bnxt_alloc_one_rx_ring_skb(bp, clone, idx); if (bp->flags & BNXT_FLAG_AGG_RINGS) bnxt_alloc_one_rx_ring_netmem(bp, clone, idx); - if (bp->flags & BNXT_FLAG_TPA) - bnxt_alloc_one_tpa_info_data(bp, clone); + if (bp->flags & BNXT_FLAG_TPA) { + rc = bnxt_alloc_one_tpa_info_data(bp, clone); + if (rc) + goto err_free_rx_ring_skbs; + } return 0; +err_free_rx_ring_skbs: + bnxt_free_one_rx_ring_skbs(bp, clone); err_free_tpa_info: bnxt_free_one_tpa_info(bp, clone); err_free_rx_agg_ring: diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index dc8ec5e5733e9e..4dbcd08ef7c32f 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -789,7 +789,6 @@ struct nqe_cn { #define MAX_TPA 64 #define MAX_TPA_P5 256 -#define MAX_TPA_P5_MASK (MAX_TPA_P5 - 1) #define MAX_TPA_SEGS_P5 0x3f #if (BNXT_PAGE_SHIFT == 16) @@ -993,6 +992,7 @@ struct bnxt_tx_ring_info { u16 txq_index; u8 tx_napi_idx; u8 kick_pending; + struct tx_bd *kick_txbd0; struct bnxt_db_info tx_db; struct tx_bd *tx_desc_ring[MAX_TX_PAGES]; @@ -2382,6 +2382,7 @@ struct bnxt { u16 max_tpa_v2; u16 max_tpa; + u16 max_tpa_roundup_size; u32 rx_buf_size; u32 rx_buf_use_size; /* useable size */ u16 rx_offset; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_gso.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_gso.c index f7e18bea0fb84f..6c1060fa2ea5ce 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_gso.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_gso.c @@ -31,10 +31,14 @@ static u32 bnxt_sw_gso_lhint(unsigned int len) return TX_BD_FLAGS_LHINT_2048_AND_LARGER; } -netdev_tx_t bnxt_sw_udp_gso_xmit(struct bnxt *bp, - struct bnxt_tx_ring_info *txr, - struct netdev_queue *txq, - struct sk_buff *skb) +/* Transmit an skb requiring software UDP segmentation. + * + * Returns 1 if the skb was queued and new BDs were produced, 0 if the skb + * was dropped, or -1 if the ring is full and the skb should be retried. + * The caller owns the doorbell for all three cases. + */ +int bnxt_sw_udp_gso_xmit(struct bnxt *bp, struct bnxt_tx_ring_info *txr, + struct netdev_queue *txq, struct sk_buff *skb) { unsigned int last_unmap_len __maybe_unused = 0; dma_addr_t last_unmap_addr __maybe_unused = 0; @@ -69,7 +73,7 @@ netdev_tx_t bnxt_sw_udp_gso_xmit(struct bnxt *bp, if (unlikely(bnxt_tx_avail(bp, txr) < bds_needed)) { netif_txq_try_stop(txq, bnxt_tx_avail(bp, txr), bp->tx_wake_thresh); - return NETDEV_TX_BUSY; + return -1; } /* BD backpressure alone cannot prevent overwriting in-flight @@ -77,7 +81,7 @@ netdev_tx_t bnxt_sw_udp_gso_xmit(struct bnxt *bp, */ if (!netif_txq_maybe_stop(txq, bnxt_inline_avail(txr), num_segs, num_segs)) - return NETDEV_TX_BUSY; + return -1; if (unlikely(tso_dma_map_init(&map, &pdev->dev, skb, hdr_len))) goto drop; @@ -223,16 +227,15 @@ netdev_tx_t bnxt_sw_udp_gso_xmit(struct bnxt *bp, netdev_tx_sent_queue(txq, skb->len); WRITE_ONCE(txr->tx_prod, prod); - txr->kick_pending = 1; if (unlikely(bnxt_tx_avail(bp, txr) <= bp->tx_wake_thresh)) netif_txq_try_stop(txq, bnxt_tx_avail(bp, txr), bp->tx_wake_thresh); - return NETDEV_TX_OK; + return 1; drop: dev_kfree_skb_any(skb); dev_core_stats_tx_dropped_inc(bp->dev); - return NETDEV_TX_OK; + return 0; } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_gso.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_gso.h index 47528c20f311b9..77d9af97cc22a8 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_gso.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_gso.h @@ -38,9 +38,7 @@ static inline int bnxt_min_tx_desc_cnt(struct bnxt *bp, return BNXT_MIN_TX_DESC_CNT; } -netdev_tx_t bnxt_sw_udp_gso_xmit(struct bnxt *bp, - struct bnxt_tx_ring_info *txr, - struct netdev_queue *txq, - struct sk_buff *skb); +int bnxt_sw_udp_gso_xmit(struct bnxt *bp, struct bnxt_tx_ring_info *txr, + struct netdev_queue *txq, struct sk_buff *skb); #endif diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h index 2de56017ee0d61..f8bff3e71b682f 100644 --- a/drivers/net/ethernet/cadence/macb.h +++ b/drivers/net/ethernet/cadence/macb.h @@ -974,6 +974,8 @@ struct macb_dma_desc_ptp { * of the frame * @mapping: DMA address of the skb's fragment buffer * @size: size of the DMA mapped buffer + * @fcs_len: FCS bytes appended in software, 0 or ETH_FCS_LEN, only + * set for the last buffer of the frame * @mapped_as_page: true when buffer was mapped with skb_frag_dma_map(), * false when buffer was mapped with dma_map_single() */ @@ -981,6 +983,7 @@ struct macb_tx_skb { struct sk_buff *skb; dma_addr_t mapping; size_t size; + u8 fcs_len; bool mapped_as_page; }; @@ -1207,11 +1210,11 @@ struct macb_or_gem_ops { /* MACB-PTP interface: adapt to platform needs. */ struct macb_ptp_info { - void (*ptp_init)(struct net_device *ndev); - void (*ptp_remove)(struct net_device *ndev); + void (*ptp_init)(struct net_device *netdev); + void (*ptp_remove)(struct net_device *netdev); s32 (*get_ptp_max_adj)(void); unsigned int (*get_tsu_rate)(struct macb *bp); - int (*get_ts_info)(struct net_device *dev, + int (*get_ts_info)(struct net_device *netdev, struct kernel_ethtool_ts_info *info); int (*get_hwtst)(struct net_device *netdev, struct kernel_hwtstamp_config *tstamp_config); @@ -1326,7 +1329,7 @@ struct macb { struct clk *tx_clk; struct clk *rx_clk; struct clk *tsu_clk; - struct net_device *dev; + struct net_device *netdev; /* Protects hw_stats and ethtool_stats */ spinlock_t stats_lock; union { @@ -1406,8 +1409,8 @@ enum macb_bd_control { TSTAMP_ALL_FRAMES, }; -void gem_ptp_init(struct net_device *ndev); -void gem_ptp_remove(struct net_device *ndev); +void gem_ptp_init(struct net_device *netdev); +void gem_ptp_remove(struct net_device *netdev); void gem_ptp_txstamp(struct macb *bp, struct sk_buff *skb, struct macb_dma_desc *desc); void gem_ptp_rxstamp(struct macb *bp, struct sk_buff *skb, struct macb_dma_desc *desc); static inline void gem_ptp_do_txstamp(struct macb *bp, struct sk_buff *skb, struct macb_dma_desc *desc) @@ -1426,14 +1429,14 @@ static inline void gem_ptp_do_rxstamp(struct macb *bp, struct sk_buff *skb, stru gem_ptp_rxstamp(bp, skb, desc); } -int gem_get_hwtst(struct net_device *dev, +int gem_get_hwtst(struct net_device *netdev, struct kernel_hwtstamp_config *tstamp_config); -int gem_set_hwtst(struct net_device *dev, +int gem_set_hwtst(struct net_device *netdev, struct kernel_hwtstamp_config *tstamp_config, struct netlink_ext_ack *extack); #else -static inline void gem_ptp_init(struct net_device *ndev) { } -static inline void gem_ptp_remove(struct net_device *ndev) { } +static inline void gem_ptp_init(struct net_device *netdev) { } +static inline void gem_ptp_remove(struct net_device *netdev) { } static inline void gem_ptp_do_txstamp(struct macb *bp, struct sk_buff *skb, struct macb_dma_desc *desc) { } static inline void gem_ptp_do_rxstamp(struct macb *bp, struct sk_buff *skb, struct macb_dma_desc *desc) { } diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index d394f1f43b685e..8085a3b3846db5 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -252,9 +252,9 @@ static void macb_set_hwaddr(struct macb *bp) u32 bottom; u16 top; - bottom = get_unaligned_le32(bp->dev->dev_addr); + bottom = get_unaligned_le32(bp->netdev->dev_addr); macb_or_gem_writel(bp, SA1B, bottom); - top = get_unaligned_le16(bp->dev->dev_addr + 4); + top = get_unaligned_le16(bp->netdev->dev_addr + 4); macb_or_gem_writel(bp, SA1T, top); if (gem_has_ptp(bp)) { @@ -291,13 +291,13 @@ static void macb_get_hwaddr(struct macb *bp) addr[5] = (top >> 8) & 0xff; if (is_valid_ether_addr(addr)) { - eth_hw_addr_set(bp->dev, addr); + eth_hw_addr_set(bp->netdev, addr); return; } } dev_info(&bp->pdev->dev, "invalid hw address, using random\n"); - eth_hw_addr_random(bp->dev); + eth_hw_addr_random(bp->netdev); } static int macb_mdio_wait_for_idle(struct macb *bp) @@ -509,12 +509,12 @@ static void macb_set_tx_clk(struct macb *bp, int speed) ferr = abs(rate_rounded - rate); ferr = DIV_ROUND_UP(ferr, rate / 100000); if (ferr > 5) - netdev_warn(bp->dev, + netdev_warn(bp->netdev, "unable to generate target frequency: %ld Hz\n", rate); if (clk_set_rate(bp->tx_clk, rate_rounded)) - netdev_err(bp->dev, "adjusting tx_clk failed.\n"); + netdev_err(bp->netdev, "adjusting tx_clk failed.\n"); } static void macb_usx_pcs_link_up(struct phylink_pcs *pcs, unsigned int neg_mode, @@ -697,8 +697,8 @@ static void macb_tx_lpi_wake(struct macb *bp) static void macb_mac_disable_tx_lpi(struct phylink_config *config) { - struct net_device *ndev = to_net_dev(config->dev); - struct macb *bp = netdev_priv(ndev); + struct net_device *netdev = to_net_dev(config->dev); + struct macb *bp = netdev_priv(netdev); unsigned long flags; cancel_delayed_work_sync(&bp->tx_lpi_work); @@ -712,8 +712,8 @@ static void macb_mac_disable_tx_lpi(struct phylink_config *config) static int macb_mac_enable_tx_lpi(struct phylink_config *config, u32 timer, bool tx_clk_stop) { - struct net_device *ndev = to_net_dev(config->dev); - struct macb *bp = netdev_priv(ndev); + struct net_device *netdev = to_net_dev(config->dev); + struct macb *bp = netdev_priv(netdev); unsigned long flags; spin_lock_irqsave(&bp->lock, flags); @@ -732,8 +732,8 @@ static int macb_mac_enable_tx_lpi(struct phylink_config *config, u32 timer, static void macb_mac_config(struct phylink_config *config, unsigned int mode, const struct phylink_link_state *state) { - struct net_device *ndev = to_net_dev(config->dev); - struct macb *bp = netdev_priv(ndev); + struct net_device *netdev = to_net_dev(config->dev); + struct macb *bp = netdev_priv(netdev); unsigned long flags; u32 old_ctrl, ctrl; u32 old_ncr, ncr; @@ -774,8 +774,8 @@ static void macb_mac_config(struct phylink_config *config, unsigned int mode, static void macb_mac_link_down(struct phylink_config *config, unsigned int mode, phy_interface_t interface) { - struct net_device *ndev = to_net_dev(config->dev); - struct macb *bp = netdev_priv(ndev); + struct net_device *netdev = to_net_dev(config->dev); + struct macb *bp = netdev_priv(netdev); struct macb_queue *queue; unsigned int q; u32 ctrl; @@ -789,7 +789,7 @@ static void macb_mac_link_down(struct phylink_config *config, unsigned int mode, ctrl = macb_readl(bp, NCR) & ~(MACB_BIT(RE) | MACB_BIT(TE)); macb_writel(bp, NCR, ctrl); - netif_tx_stop_all_queues(ndev); + netif_tx_stop_all_queues(netdev); } /* Use juggling algorithm to left rotate tx ring and tx skb array */ @@ -884,13 +884,13 @@ static void gem_shuffle_tx_rings(struct macb *bp) } static void macb_mac_link_up(struct phylink_config *config, - struct phy_device *phy, + struct phy_device *phydev, unsigned int mode, phy_interface_t interface, int speed, int duplex, bool tx_pause, bool rx_pause) { - struct net_device *ndev = to_net_dev(config->dev); - struct macb *bp = netdev_priv(ndev); + struct net_device *netdev = to_net_dev(config->dev); + struct macb *bp = netdev_priv(netdev); struct macb_queue *queue; unsigned long flags; unsigned int q; @@ -946,14 +946,14 @@ static void macb_mac_link_up(struct phylink_config *config, macb_writel(bp, NCR, ctrl | MACB_BIT(RE) | MACB_BIT(TE)); - netif_tx_wake_all_queues(ndev); + netif_tx_wake_all_queues(netdev); } static struct phylink_pcs *macb_mac_select_pcs(struct phylink_config *config, phy_interface_t interface) { - struct net_device *ndev = to_net_dev(config->dev); - struct macb *bp = netdev_priv(ndev); + struct net_device *netdev = to_net_dev(config->dev); + struct macb *bp = netdev_priv(netdev); if (interface == PHY_INTERFACE_MODE_10GBASER) return &bp->phylink_usx_pcs; @@ -982,7 +982,7 @@ static bool macb_phy_handle_exists(struct device_node *dn) static int macb_phylink_connect(struct macb *bp) { struct device_node *dn = bp->pdev->dev.of_node; - struct net_device *dev = bp->dev; + struct net_device *netdev = bp->netdev; struct phy_device *phydev; int ret; @@ -992,7 +992,7 @@ static int macb_phylink_connect(struct macb *bp) if (!dn || (ret && !macb_phy_handle_exists(dn))) { phydev = phy_find_first(bp->mii_bus); if (!phydev) { - netdev_err(dev, "no PHY found\n"); + netdev_err(netdev, "no PHY found\n"); return -ENXIO; } @@ -1001,7 +1001,7 @@ static int macb_phylink_connect(struct macb *bp) } if (ret) { - netdev_err(dev, "Could not attach PHY (%d)\n", ret); + netdev_err(netdev, "Could not attach PHY (%d)\n", ret); return ret; } @@ -1013,21 +1013,21 @@ static int macb_phylink_connect(struct macb *bp) static void macb_get_pcs_fixed_state(struct phylink_config *config, struct phylink_link_state *state) { - struct net_device *ndev = to_net_dev(config->dev); - struct macb *bp = netdev_priv(ndev); + struct net_device *netdev = to_net_dev(config->dev); + struct macb *bp = netdev_priv(netdev); state->link = (macb_readl(bp, NSR) & MACB_BIT(NSR_LINK)) != 0; } /* based on au1000_eth. c*/ -static int macb_mii_probe(struct net_device *dev) +static int macb_mii_probe(struct net_device *netdev) { - struct macb *bp = netdev_priv(dev); + struct macb *bp = netdev_priv(netdev); bp->phylink_sgmii_pcs.ops = &macb_phylink_pcs_ops; bp->phylink_usx_pcs.ops = &macb_phylink_usx_pcs_ops; - bp->phylink_config.dev = &dev->dev; + bp->phylink_config.dev = &netdev->dev; bp->phylink_config.type = PHYLINK_NETDEV; bp->phylink_config.mac_managed_pm = true; @@ -1086,7 +1086,7 @@ static int macb_mii_probe(struct net_device *dev) bp->phylink = phylink_create(&bp->phylink_config, bp->pdev->dev.fwnode, bp->phy_interface, &macb_phylink_ops); if (IS_ERR(bp->phylink)) { - netdev_err(dev, "Could not create a phylink instance (%ld)\n", + netdev_err(netdev, "Could not create a phylink instance (%ld)\n", PTR_ERR(bp->phylink)); return PTR_ERR(bp->phylink); } @@ -1133,7 +1133,7 @@ static int macb_mii_init(struct macb *bp) */ mdio_np = of_get_child_by_name(np, "mdio"); if (!mdio_np && of_phy_is_fixed_link(np)) - return macb_mii_probe(bp->dev); + return macb_mii_probe(bp->netdev); /* Enable management port */ macb_writel(bp, NCR, MACB_BIT(MPE)); @@ -1154,16 +1154,18 @@ static int macb_mii_init(struct macb *bp) bp->mii_bus->priv = bp; bp->mii_bus->parent = &bp->pdev->dev; - dev_set_drvdata(&bp->dev->dev, bp->mii_bus); + dev_set_drvdata(&bp->netdev->dev, bp->mii_bus); err = macb_mdiobus_register(bp, mdio_np); if (err) goto err_out_free_mdiobus; - err = macb_mii_probe(bp->dev); + err = macb_mii_probe(bp->netdev); if (err) goto err_out_unregister_bus; + of_node_put(mdio_np); + return 0; err_out_unregister_bus: @@ -1268,8 +1270,8 @@ static void macb_tx_error_task(struct work_struct *work) unsigned long flags; queue_index = queue - bp->queues; - netdev_vdbg(bp->dev, "macb_tx_error_task: q = %u, t = %u, h = %u\n", - queue_index, queue->tx_tail, queue->tx_head); + netdev_vdbg(bp->netdev, "%s: q = %u, t = %u, h = %u\n", + __func__, queue_index, queue->tx_tail, queue->tx_head); /* Prevent the queue NAPI TX poll from running, as it calls * macb_tx_complete(), which in turn may call netif_wake_subqueue(). @@ -1281,14 +1283,14 @@ static void macb_tx_error_task(struct work_struct *work) spin_lock_irqsave(&bp->lock, flags); /* Make sure nobody is trying to queue up new packets */ - netif_tx_stop_all_queues(bp->dev); + netif_tx_stop_all_queues(bp->netdev); /* Stop transmission now * (in case we have just queued new packets) * macb/gem must be halted to write TBQP register */ if (macb_halt_tx(bp)) { - netdev_err(bp->dev, "BUG: halt tx timed out\n"); + netdev_err(bp->netdev, "BUG: halt tx timed out\n"); macb_writel(bp, NCR, macb_readl(bp, NCR) & (~MACB_BIT(TE))); halt_timeout = true; } @@ -1317,14 +1319,14 @@ static void macb_tx_error_task(struct work_struct *work) * since it's the only one written back by the hardware */ if (!(ctrl & MACB_BIT(TX_BUF_EXHAUSTED))) { - netdev_vdbg(bp->dev, "txerr skb %u (data %p) TX complete\n", + netdev_vdbg(bp->netdev, "txerr skb %u (data %p) TX complete\n", macb_tx_ring_wrap(bp, tail), skb->data); - bp->dev->stats.tx_packets++; + bp->netdev->stats.tx_packets++; queue->stats.tx_packets++; packets++; - bp->dev->stats.tx_bytes += skb->len; - queue->stats.tx_bytes += skb->len; + bp->netdev->stats.tx_bytes += skb->len - tx_skb->fcs_len; + queue->stats.tx_bytes += skb->len - tx_skb->fcs_len; bytes += skb->len; } } else { @@ -1333,7 +1335,7 @@ static void macb_tx_error_task(struct work_struct *work) * those. Statistics are updated by hardware. */ if (ctrl & MACB_BIT(TX_BUF_EXHAUSTED)) - netdev_err(bp->dev, + netdev_err(bp->netdev, "BUG: TX buffers exhausted mid-frame\n"); desc->ctrl = ctrl | MACB_BIT(TX_USED); @@ -1342,7 +1344,7 @@ static void macb_tx_error_task(struct work_struct *work) macb_tx_unmap(bp, tx_skb, 0); } - netdev_tx_completed_queue(netdev_get_tx_queue(bp->dev, queue_index), + netdev_tx_completed_queue(netdev_get_tx_queue(bp->netdev, queue_index), packets, bytes); /* Set end of TX queue */ @@ -1367,7 +1369,7 @@ static void macb_tx_error_task(struct work_struct *work) macb_writel(bp, NCR, macb_readl(bp, NCR) | MACB_BIT(TE)); /* Now we are ready to start transmission again */ - netif_tx_start_all_queues(bp->dev); + netif_tx_start_all_queues(bp->netdev); macb_writel(bp, NCR, macb_readl(bp, NCR) | MACB_BIT(TSTART)); spin_unlock_irqrestore(&bp->lock, flags); @@ -1446,13 +1448,13 @@ static int macb_tx_complete(struct macb_queue *queue, int budget) !ptp_one_step_sync(skb)) gem_ptp_do_txstamp(bp, skb, desc); - netdev_vdbg(bp->dev, "skb %u (data %p) TX complete\n", + netdev_vdbg(bp->netdev, "skb %u (data %p) TX complete\n", macb_tx_ring_wrap(bp, tail), skb->data); - bp->dev->stats.tx_packets++; + bp->netdev->stats.tx_packets++; queue->stats.tx_packets++; - bp->dev->stats.tx_bytes += skb->len; - queue->stats.tx_bytes += skb->len; + bp->netdev->stats.tx_bytes += skb->len - tx_skb->fcs_len; + queue->stats.tx_bytes += skb->len - tx_skb->fcs_len; packets++; bytes += skb->len; } @@ -1469,14 +1471,14 @@ static int macb_tx_complete(struct macb_queue *queue, int budget) } } - netdev_tx_completed_queue(netdev_get_tx_queue(bp->dev, queue_index), + netdev_tx_completed_queue(netdev_get_tx_queue(bp->netdev, queue_index), packets, bytes); queue->tx_tail = tail; - if (__netif_subqueue_stopped(bp->dev, queue_index) && + if (__netif_subqueue_stopped(bp->netdev, queue_index) && CIRC_CNT(queue->tx_head, queue->tx_tail, bp->tx_ring_size) <= MACB_TX_WAKEUP_THRESH(bp)) - netif_wake_subqueue(bp->dev, queue_index); + netif_wake_subqueue(bp->netdev, queue_index); spin_unlock_irqrestore(&queue->tx_ptr_lock, flags); if (packets) @@ -1504,9 +1506,9 @@ static void gem_rx_refill(struct macb_queue *queue) if (!queue->rx_skbuff[entry]) { /* allocate sk_buff for this free entry in ring */ - skb = netdev_alloc_skb(bp->dev, bp->rx_buffer_size); + skb = netdev_alloc_skb(bp->netdev, bp->rx_buffer_size); if (unlikely(!skb)) { - netdev_err(bp->dev, + netdev_err(bp->netdev, "Unable to allocate sk_buff\n"); break; } @@ -1555,8 +1557,8 @@ static void gem_rx_refill(struct macb_queue *queue) /* Make descriptor updates visible to hardware */ wmb(); - netdev_vdbg(bp->dev, "rx ring: queue: %p, prepared head %d, tail %d\n", - queue, queue->rx_prepared_head, queue->rx_tail); + netdev_vdbg(bp->netdev, "rx ring: queue: %p, prepared head %d, tail %d\n", + queue, queue->rx_prepared_head, queue->rx_tail); } /* Mark DMA descriptors from begin up to and not including end as unused */ @@ -1616,17 +1618,17 @@ static int gem_rx(struct macb_queue *queue, struct napi_struct *napi, count++; if (!(ctrl & MACB_BIT(RX_SOF) && ctrl & MACB_BIT(RX_EOF))) { - netdev_err(bp->dev, + netdev_err(bp->netdev, "not whole frame pointed by descriptor\n"); - bp->dev->stats.rx_dropped++; + bp->netdev->stats.rx_dropped++; queue->stats.rx_dropped++; break; } skb = queue->rx_skbuff[entry]; if (unlikely(!skb)) { - netdev_err(bp->dev, + netdev_err(bp->netdev, "inconsistent Rx descriptor chain\n"); - bp->dev->stats.rx_dropped++; + bp->netdev->stats.rx_dropped++; queue->stats.rx_dropped++; break; } @@ -1634,28 +1636,29 @@ static int gem_rx(struct macb_queue *queue, struct napi_struct *napi, queue->rx_skbuff[entry] = NULL; len = ctrl & bp->rx_frm_len_mask; - netdev_vdbg(bp->dev, "gem_rx %u (len %u)\n", entry, len); + netdev_vdbg(bp->netdev, "%s %u (len %u)\n", + __func__, entry, len); skb_put(skb, len); dma_unmap_single(&bp->pdev->dev, addr, bp->rx_buffer_size, DMA_FROM_DEVICE); - skb->protocol = eth_type_trans(skb, bp->dev); + skb->protocol = eth_type_trans(skb, bp->netdev); skb_checksum_none_assert(skb); - if (bp->dev->features & NETIF_F_RXCSUM && - !(bp->dev->flags & IFF_PROMISC) && + if (bp->netdev->features & NETIF_F_RXCSUM && + !(bp->netdev->flags & IFF_PROMISC) && GEM_BFEXT(RX_CSUM, ctrl) & GEM_RX_CSUM_CHECKED_MASK) skb->ip_summed = CHECKSUM_UNNECESSARY; - bp->dev->stats.rx_packets++; + bp->netdev->stats.rx_packets++; queue->stats.rx_packets++; - bp->dev->stats.rx_bytes += skb->len; + bp->netdev->stats.rx_bytes += skb->len; queue->stats.rx_bytes += skb->len; gem_ptp_do_rxstamp(bp, skb, desc); #if defined(DEBUG) && defined(VERBOSE_DEBUG) - netdev_vdbg(bp->dev, "received skb of length %u, csum: %08x\n", + netdev_vdbg(bp->netdev, "received skb of length %u, csum: %08x\n", skb->len, skb->csum); print_hex_dump(KERN_DEBUG, " mac: ", DUMP_PREFIX_ADDRESS, 16, 1, skb_mac_header(skb), 16, true); @@ -1684,9 +1687,10 @@ static int macb_rx_frame(struct macb_queue *queue, struct napi_struct *napi, desc = macb_rx_desc(queue, last_frag); len = desc->ctrl & bp->rx_frm_len_mask; - netdev_vdbg(bp->dev, "macb_rx_frame frags %u - %u (len %u)\n", - macb_rx_ring_wrap(bp, first_frag), - macb_rx_ring_wrap(bp, last_frag), len); + netdev_vdbg(bp->netdev, "%s frags %u - %u (len %u)\n", + __func__, + macb_rx_ring_wrap(bp, first_frag), + macb_rx_ring_wrap(bp, last_frag), len); /* The ethernet header starts NET_IP_ALIGN bytes into the * first buffer. Since the header is 14 bytes, this makes the @@ -1696,9 +1700,9 @@ static int macb_rx_frame(struct macb_queue *queue, struct napi_struct *napi, * the two padding bytes into the skb so that we avoid hitting * the slowpath in memcpy(), and pull them off afterwards. */ - skb = netdev_alloc_skb(bp->dev, len + NET_IP_ALIGN); + skb = netdev_alloc_skb(bp->netdev, len + NET_IP_ALIGN); if (!skb) { - bp->dev->stats.rx_dropped++; + bp->netdev->stats.rx_dropped++; for (frag = first_frag; ; frag++) { desc = macb_rx_desc(queue, frag); desc->addr &= ~MACB_BIT(RX_USED); @@ -1742,11 +1746,11 @@ static int macb_rx_frame(struct macb_queue *queue, struct napi_struct *napi, wmb(); __skb_pull(skb, NET_IP_ALIGN); - skb->protocol = eth_type_trans(skb, bp->dev); + skb->protocol = eth_type_trans(skb, bp->netdev); - bp->dev->stats.rx_packets++; - bp->dev->stats.rx_bytes += skb->len; - netdev_vdbg(bp->dev, "received skb of length %u, csum: %08x\n", + bp->netdev->stats.rx_packets++; + bp->netdev->stats.rx_bytes += skb->len; + netdev_vdbg(bp->netdev, "received skb of length %u, csum: %08x\n", skb->len, skb->csum); napi_gro_receive(napi, skb); @@ -1826,7 +1830,7 @@ static int macb_rx(struct macb_queue *queue, struct napi_struct *napi, unsigned long flags; u32 ctrl; - netdev_err(bp->dev, "RX queue corruption: reset it\n"); + netdev_err(bp->netdev, "RX queue corruption: reset it\n"); spin_lock_irqsave(&bp->lock, flags); @@ -1873,7 +1877,7 @@ static int macb_rx_poll(struct napi_struct *napi, int budget) work_done = bp->macbgem_ops.mog_rx(queue, napi, budget); - netdev_vdbg(bp->dev, "RX poll: queue = %u, work_done = %d, budget = %d\n", + netdev_vdbg(bp->netdev, "RX poll: queue = %u, work_done = %d, budget = %d\n", (unsigned int)(queue - bp->queues), work_done, budget); if (work_done < budget && napi_complete_done(napi, work_done)) { @@ -1892,7 +1896,7 @@ static int macb_rx_poll(struct napi_struct *napi, int budget) if (macb_rx_pending(queue)) { queue_writel(queue, IDR, bp->rx_intr_mask); macb_queue_isr_clear(bp, queue, MACB_BIT(RCOMP)); - netdev_vdbg(bp->dev, "poll: packets pending, reschedule\n"); + netdev_vdbg(bp->netdev, "poll: packets pending, reschedule\n"); napi_schedule(napi); } } @@ -1956,11 +1960,11 @@ static int macb_tx_poll(struct napi_struct *napi, int budget) rmb(); // ensure txubr_pending is up to date if (queue->txubr_pending) { queue->txubr_pending = false; - netdev_vdbg(bp->dev, "poll: tx restart\n"); + netdev_vdbg(bp->netdev, "poll: tx restart\n"); macb_tx_restart(queue); } - netdev_vdbg(bp->dev, "TX poll: queue = %u, work_done = %d, budget = %d\n", + netdev_vdbg(bp->netdev, "TX poll: queue = %u, work_done = %d, budget = %d\n", (unsigned int)(queue - bp->queues), work_done, budget); if (work_done < budget && napi_complete_done(napi, work_done)) { @@ -1979,7 +1983,7 @@ static int macb_tx_poll(struct napi_struct *napi, int budget) if (macb_tx_complete_pending(queue)) { queue_writel(queue, IDR, MACB_BIT(TCOMP)); macb_queue_isr_clear(bp, queue, MACB_BIT(TCOMP)); - netdev_vdbg(bp->dev, "TX poll: packets pending, reschedule\n"); + netdev_vdbg(bp->netdev, "TX poll: packets pending, reschedule\n"); napi_schedule(napi); } } @@ -1990,7 +1994,7 @@ static int macb_tx_poll(struct napi_struct *napi, int budget) static void macb_hresp_error_task(struct work_struct *work) { struct macb *bp = from_work(bp, work, hresp_err_bh_work); - struct net_device *dev = bp->dev; + struct net_device *netdev = bp->netdev; struct macb_queue *queue; unsigned int q; u32 ctrl; @@ -2004,8 +2008,8 @@ static void macb_hresp_error_task(struct work_struct *work) ctrl &= ~(MACB_BIT(RE) | MACB_BIT(TE)); macb_writel(bp, NCR, ctrl); - netif_tx_stop_all_queues(dev); - netif_carrier_off(dev); + netif_tx_stop_all_queues(netdev); + netif_carrier_off(netdev); bp->macbgem_ops.mog_init_rings(bp); @@ -2022,8 +2026,8 @@ static void macb_hresp_error_task(struct work_struct *work) ctrl |= MACB_BIT(RE) | MACB_BIT(TE); macb_writel(bp, NCR, ctrl); - netif_carrier_on(dev); - netif_tx_start_all_queues(dev); + netif_carrier_on(netdev); + netif_tx_start_all_queues(netdev); } static void macb_wol_interrupt(struct macb_queue *queue, u32 status) @@ -2032,7 +2036,7 @@ static void macb_wol_interrupt(struct macb_queue *queue, u32 status) queue_writel(queue, IDR, MACB_BIT(WOL)); macb_writel(bp, WOL, 0); - netdev_vdbg(bp->dev, "MACB WoL: queue = %u, isr = 0x%08lx\n", + netdev_vdbg(bp->netdev, "MACB WoL: queue = %u, isr = 0x%08lx\n", (unsigned int)(queue - bp->queues), (unsigned long)status); macb_queue_isr_clear(bp, queue, MACB_BIT(WOL)); @@ -2045,7 +2049,7 @@ static void gem_wol_interrupt(struct macb_queue *queue, u32 status) queue_writel(queue, IDR, GEM_BIT(WOL)); gem_writel(bp, WOL, 0); - netdev_vdbg(bp->dev, "GEM WoL: queue = %u, isr = 0x%08lx\n", + netdev_vdbg(bp->netdev, "GEM WoL: queue = %u, isr = 0x%08lx\n", (unsigned int)(queue - bp->queues), (unsigned long)status); macb_queue_isr_clear(bp, queue, GEM_BIT(WOL)); @@ -2055,10 +2059,10 @@ static void gem_wol_interrupt(struct macb_queue *queue, u32 status) static int macb_interrupt_misc(struct macb_queue *queue, u32 status) { struct macb *bp = queue->bp; - struct net_device *dev; + struct net_device *netdev; u32 ctrl; - dev = bp->dev; + netdev = bp->netdev; if (unlikely(status & (MACB_TX_ERR_FLAGS))) { queue_writel(queue, IDR, MACB_TX_INT_FLAGS); @@ -2099,7 +2103,7 @@ static int macb_interrupt_misc(struct macb_queue *queue, u32 status) if (status & MACB_BIT(HRESP)) { queue_work(system_bh_wq, &bp->hresp_err_bh_work); - netdev_err(dev, "DMA bus error: HRESP not OK\n"); + netdev_err(netdev, "DMA bus error: HRESP not OK\n"); macb_queue_isr_clear(bp, queue, MACB_BIT(HRESP)); } @@ -2118,7 +2122,7 @@ static irqreturn_t macb_interrupt(int irq, void *dev_id) { struct macb_queue *queue = dev_id; struct macb *bp = queue->bp; - struct net_device *dev = bp->dev; + struct net_device *netdev = bp->netdev; u32 status; status = queue_readl(queue, ISR); @@ -2130,13 +2134,13 @@ static irqreturn_t macb_interrupt(int irq, void *dev_id) while (status) { /* close possible race with dev_close */ - if (unlikely(!netif_running(dev))) { + if (unlikely(!netif_running(netdev))) { queue_writel(queue, IDR, -1); macb_queue_isr_clear(bp, queue, -1); break; } - netdev_vdbg(bp->dev, "queue = %u, isr = 0x%08lx\n", + netdev_vdbg(netdev, "queue = %u, isr = 0x%08lx\n", (unsigned int)(queue - bp->queues), (unsigned long)status); @@ -2181,16 +2185,16 @@ static irqreturn_t macb_interrupt(int irq, void *dev_id) /* Polling receive - used by netconsole and other diagnostic tools * to allow network i/o with interrupts disabled. */ -static void macb_poll_controller(struct net_device *dev) +static void macb_poll_controller(struct net_device *netdev) { - struct macb *bp = netdev_priv(dev); + struct macb *bp = netdev_priv(netdev); struct macb_queue *queue; unsigned long flags; unsigned int q; local_irq_save(flags); for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) - macb_interrupt(dev->irq, queue); + macb_interrupt(netdev->irq, queue); local_irq_restore(flags); } #endif @@ -2198,7 +2202,8 @@ static void macb_poll_controller(struct net_device *dev) static unsigned int macb_tx_map(struct macb *bp, struct macb_queue *queue, struct sk_buff *skb, - unsigned int hdrlen) + unsigned int hdrlen, + u8 fcs_len) { unsigned int f, nr_frags = skb_shinfo(skb)->nr_frags; unsigned int len, i, tx_head = queue->tx_head; @@ -2277,12 +2282,13 @@ static unsigned int macb_tx_map(struct macb *bp, /* Should never happen */ if (unlikely(!tx_skb)) { - netdev_err(bp->dev, "BUG! empty skb!\n"); + netdev_err(bp->netdev, "BUG! empty skb!\n"); return 0; } /* This is the last buffer of the frame: save socket buffer */ tx_skb->skb = skb; + tx_skb->fcs_len = fcs_len; /* Update TX ring: update buffer descriptors in reverse order * to avoid race condition @@ -2328,7 +2334,7 @@ static unsigned int macb_tx_map(struct macb *bp, if (i == queue->tx_head) { ctrl |= MACB_BF(TX_LSO, lso_ctrl); ctrl |= MACB_BF(TX_TCP_SEQ_SRC, seq_ctrl); - if ((bp->dev->features & NETIF_F_HW_CSUM) && + if ((bp->netdev->features & NETIF_F_HW_CSUM) && skb->ip_summed != CHECKSUM_PARTIAL && !lso_ctrl && !ptp_one_step_sync(skb)) ctrl |= MACB_BIT(TX_NOCRC); @@ -2352,7 +2358,7 @@ static unsigned int macb_tx_map(struct macb *bp, return 0; dma_error: - netdev_err(bp->dev, "TX DMA map failed\n"); + netdev_err(bp->netdev, "TX DMA map failed\n"); for (i = queue->tx_head; i != tx_head; i++) { tx_skb = macb_tx_skb(queue, i); @@ -2364,7 +2370,7 @@ dma_error: } static netdev_features_t macb_features_check(struct sk_buff *skb, - struct net_device *dev, + struct net_device *netdev, netdev_features_t features) { unsigned int nr_frags, f; @@ -2416,7 +2422,8 @@ static inline int macb_clear_csum(struct sk_buff *skb) return 0; } -static int macb_pad_and_fcs(struct sk_buff **skb, struct net_device *ndev) +/* Returns a negative errno, or the FCS bytes appended (0 or ETH_FCS_LEN). */ +static int macb_pad_and_fcs(struct sk_buff **skb, struct net_device *netdev) { bool cloned = skb_cloned(*skb) || skb_header_cloned(*skb) || skb_is_nonlinear(*skb); @@ -2425,7 +2432,7 @@ static int macb_pad_and_fcs(struct sk_buff **skb, struct net_device *ndev) struct sk_buff *nskb; u32 fcs; - if (!(ndev->features & NETIF_F_HW_CSUM) || + if (!(netdev->features & NETIF_F_HW_CSUM) || !((*skb)->ip_summed != CHECKSUM_PARTIAL) || skb_shinfo(*skb)->gso_size || ptp_one_step_sync(*skb)) return 0; @@ -2464,17 +2471,19 @@ add_fcs: skb_put_u8(*skb, (fcs >> 16) & 0xff); skb_put_u8(*skb, (fcs >> 24) & 0xff); - return 0; + return ETH_FCS_LEN; } -static netdev_tx_t macb_start_xmit(struct sk_buff *skb, struct net_device *dev) +static netdev_tx_t macb_start_xmit(struct sk_buff *skb, + struct net_device *netdev) { u16 queue_index = skb_get_queue_mapping(skb); - struct macb *bp = netdev_priv(dev); + struct macb *bp = netdev_priv(netdev); struct macb_queue *queue = &bp->queues[queue_index]; unsigned int desc_cnt, nr_frags, frag_size, f; unsigned int hdrlen; unsigned long flags; + int fcs_len; bool is_lso; netdev_tx_t ret = NETDEV_TX_OK; @@ -2483,7 +2492,8 @@ static netdev_tx_t macb_start_xmit(struct sk_buff *skb, struct net_device *dev) return ret; } - if (macb_pad_and_fcs(&skb, dev)) { + fcs_len = macb_pad_and_fcs(&skb, netdev); + if (fcs_len < 0) { dev_kfree_skb_any(skb); return ret; } @@ -2502,7 +2512,7 @@ static netdev_tx_t macb_start_xmit(struct sk_buff *skb, struct net_device *dev) else hdrlen = skb_tcp_all_headers(skb); if (skb_headlen(skb) < hdrlen) { - netdev_err(bp->dev, "Error - LSO headers fragmented!!!\n"); + netdev_err(bp->netdev, "Error - LSO headers fragmented!!!\n"); /* if this is required, would need to copy to single buffer */ return NETDEV_TX_BUSY; } @@ -2510,7 +2520,7 @@ static netdev_tx_t macb_start_xmit(struct sk_buff *skb, struct net_device *dev) hdrlen = umin(skb_headlen(skb), bp->max_tx_length); #if defined(DEBUG) && defined(VERBOSE_DEBUG) - netdev_vdbg(bp->dev, + netdev_vdbg(bp->netdev, "start_xmit: queue %hu len %u head %p data %p tail %p end %p\n", queue_index, skb->len, skb->head, skb->data, skb_tail_pointer(skb), skb_end_pointer(skb)); @@ -2538,15 +2548,15 @@ static netdev_tx_t macb_start_xmit(struct sk_buff *skb, struct net_device *dev) /* This is a hard error, log it. */ if (CIRC_SPACE(queue->tx_head, queue->tx_tail, bp->tx_ring_size) < desc_cnt) { - netif_stop_subqueue(dev, queue_index); - netdev_dbg(bp->dev, "tx_head = %u, tx_tail = %u\n", + netif_stop_subqueue(netdev, queue_index); + netdev_dbg(netdev, "tx_head = %u, tx_tail = %u\n", queue->tx_head, queue->tx_tail); ret = NETDEV_TX_BUSY; goto unlock; } /* Map socket buffer for DMA transfer */ - if (macb_tx_map(bp, queue, skb, hdrlen)) { + if (macb_tx_map(bp, queue, skb, hdrlen, fcs_len)) { dev_kfree_skb_any(skb); goto unlock; } @@ -2554,7 +2564,7 @@ static netdev_tx_t macb_start_xmit(struct sk_buff *skb, struct net_device *dev) /* Make newly initialized descriptor visible to hardware */ wmb(); skb_tx_timestamp(skb); - netdev_tx_sent_queue(netdev_get_tx_queue(bp->dev, queue_index), + netdev_tx_sent_queue(netdev_get_tx_queue(bp->netdev, queue_index), skb->len); spin_lock(&bp->lock); @@ -2563,7 +2573,7 @@ static netdev_tx_t macb_start_xmit(struct sk_buff *skb, struct net_device *dev) spin_unlock(&bp->lock); if (CIRC_SPACE(queue->tx_head, queue->tx_tail, bp->tx_ring_size) < 1) - netif_stop_subqueue(dev, queue_index); + netif_stop_subqueue(netdev, queue_index); unlock: spin_unlock_irqrestore(&queue->tx_ptr_lock, flags); @@ -2579,7 +2589,7 @@ static void macb_init_rx_buffer_size(struct macb *bp, size_t size) bp->rx_buffer_size = MIN(size, RX_BUFFER_MAX); if (bp->rx_buffer_size % RX_BUFFER_MULTIPLE) { - netdev_dbg(bp->dev, + netdev_dbg(bp->netdev, "RX buffer must be multiple of %d bytes, expanding\n", RX_BUFFER_MULTIPLE); bp->rx_buffer_size = @@ -2587,8 +2597,8 @@ static void macb_init_rx_buffer_size(struct macb *bp, size_t size) } } - netdev_dbg(bp->dev, "mtu [%u] rx_buffer_size [%zu]\n", - bp->dev->mtu, bp->rx_buffer_size); + netdev_dbg(bp->netdev, "mtu [%u] rx_buffer_size [%zu]\n", + bp->netdev->mtu, bp->rx_buffer_size); } static void gem_free_rx_buffers(struct macb *bp) @@ -2679,7 +2689,7 @@ static void macb_free_consistent(struct macb *bp) } queue->stats.tx_dropped += dropped; - bp->dev->stats.tx_dropped += dropped; + bp->netdev->stats.tx_dropped += dropped; kfree(queue->tx_skb); queue->tx_skb = NULL; @@ -2704,7 +2714,7 @@ static int gem_alloc_rx_buffers(struct macb *bp) if (!queue->rx_skbuff) return -ENOMEM; else - netdev_dbg(bp->dev, + netdev_dbg(bp->netdev, "Allocated %d RX struct sk_buff entries at %p\n", bp->rx_ring_size, queue->rx_skbuff); } @@ -2722,7 +2732,7 @@ static int macb_alloc_rx_buffers(struct macb *bp) if (!queue->rx_buffers) return -ENOMEM; - netdev_dbg(bp->dev, + netdev_dbg(bp->netdev, "Allocated RX buffers of %d bytes at %08lx (mapped %p)\n", size, (unsigned long)queue->rx_buffers_dma, queue->rx_buffers); return 0; @@ -2748,14 +2758,14 @@ static int macb_alloc_consistent(struct macb *bp) tx = dma_alloc_coherent(dev, size, &tx_dma, GFP_KERNEL); if (!tx || upper_32_bits(tx_dma) != upper_32_bits(tx_dma + size - 1)) goto out_err; - netdev_dbg(bp->dev, "Allocated %zu bytes for %u TX rings at %08lx (mapped %p)\n", + netdev_dbg(bp->netdev, "Allocated %zu bytes for %u TX rings at %08lx (mapped %p)\n", size, bp->num_queues, (unsigned long)tx_dma, tx); size = bp->num_queues * macb_rx_ring_size_per_queue(bp); rx = dma_alloc_coherent(dev, size, &rx_dma, GFP_KERNEL); if (!rx || upper_32_bits(rx_dma) != upper_32_bits(rx_dma + size - 1)) goto out_err; - netdev_dbg(bp->dev, "Allocated %zu bytes for %u RX rings at %08lx (mapped %p)\n", + netdev_dbg(bp->netdev, "Allocated %zu bytes for %u RX rings at %08lx (mapped %p)\n", size, bp->num_queues, (unsigned long)rx_dma, rx); for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) { @@ -2983,7 +2993,7 @@ static void macb_configure_dma(struct macb *bp) else dmacfg |= GEM_BIT(ENDIA_DESC); /* CPU in big endian */ - if (bp->dev->features & NETIF_F_HW_CSUM) + if (bp->netdev->features & NETIF_F_HW_CSUM) dmacfg |= GEM_BIT(TXCOEN); else dmacfg &= ~GEM_BIT(TXCOEN); @@ -2993,7 +3003,7 @@ static void macb_configure_dma(struct macb *bp) dmacfg |= GEM_BIT(ADDR64); if (macb_dma_ptp(bp)) dmacfg |= GEM_BIT(RXEXT) | GEM_BIT(TXEXT); - netdev_dbg(bp->dev, "Cadence configure DMA with 0x%08x\n", + netdev_dbg(bp->netdev, "Cadence configure DMA with 0x%08x\n", dmacfg); gem_writel(bp, DMACFG, dmacfg); } @@ -3017,11 +3027,11 @@ static void macb_init_hw(struct macb *bp) config |= MACB_BIT(JFRAME); /* Enable jumbo frames */ else config |= MACB_BIT(BIG); /* Receive oversized frames */ - if (bp->dev->flags & IFF_PROMISC) + if (bp->netdev->flags & IFF_PROMISC) config |= MACB_BIT(CAF); /* Copy All Frames */ - else if (macb_is_gem(bp) && bp->dev->features & NETIF_F_RXCSUM) + else if (macb_is_gem(bp) && bp->netdev->features & NETIF_F_RXCSUM) config |= GEM_BIT(RXCOEN); - if (!(bp->dev->flags & IFF_BROADCAST)) + if (!(bp->netdev->flags & IFF_BROADCAST)) config |= MACB_BIT(NBC); /* No BroadCast */ config |= macb_dbw(bp); macb_writel(bp, NCFGR, config); @@ -3095,17 +3105,17 @@ static int hash_get_index(__u8 *addr) } /* Add multicast addresses to the internal multicast-hash table. */ -static void macb_sethashtable(struct net_device *dev) +static void macb_sethashtable(struct net_device *netdev) { struct netdev_hw_addr *ha; unsigned long mc_filter[2]; unsigned int bitnr; - struct macb *bp = netdev_priv(dev); + struct macb *bp = netdev_priv(netdev); mc_filter[0] = 0; mc_filter[1] = 0; - netdev_for_each_mc_addr(ha, dev) { + netdev_for_each_mc_addr(ha, netdev) { bitnr = hash_get_index(ha->addr); mc_filter[bitnr >> 5] |= 1 << (bitnr & 31); } @@ -3115,14 +3125,14 @@ static void macb_sethashtable(struct net_device *dev) } /* Enable/Disable promiscuous and multicast modes. */ -static void macb_set_rx_mode(struct net_device *dev) +static void macb_set_rx_mode(struct net_device *netdev) { unsigned long cfg; - struct macb *bp = netdev_priv(dev); + struct macb *bp = netdev_priv(netdev); cfg = macb_readl(bp, NCFGR); - if (dev->flags & IFF_PROMISC) { + if (netdev->flags & IFF_PROMISC) { /* Enable promiscuous mode */ cfg |= MACB_BIT(CAF); @@ -3134,20 +3144,20 @@ static void macb_set_rx_mode(struct net_device *dev) cfg &= ~MACB_BIT(CAF); /* Enable RX checksum offload only if requested */ - if (macb_is_gem(bp) && dev->features & NETIF_F_RXCSUM) + if (macb_is_gem(bp) && netdev->features & NETIF_F_RXCSUM) cfg |= GEM_BIT(RXCOEN); } - if (dev->flags & IFF_ALLMULTI) { + if (netdev->flags & IFF_ALLMULTI) { /* Enable all multicast mode */ macb_or_gem_writel(bp, HRB, -1); macb_or_gem_writel(bp, HRT, -1); cfg |= MACB_BIT(NCFGR_MTI); - } else if (!netdev_mc_empty(dev)) { + } else if (!netdev_mc_empty(netdev)) { /* Enable specific multicasts */ - macb_sethashtable(dev); + macb_sethashtable(netdev); cfg |= MACB_BIT(NCFGR_MTI); - } else if (dev->flags & (~IFF_ALLMULTI)) { + } else if (netdev->flags & (~IFF_ALLMULTI)) { /* Disable all multicast mode */ macb_or_gem_writel(bp, HRB, 0); macb_or_gem_writel(bp, HRT, 0); @@ -3157,15 +3167,15 @@ static void macb_set_rx_mode(struct net_device *dev) macb_writel(bp, NCFGR, cfg); } -static int macb_open(struct net_device *dev) +static int macb_open(struct net_device *netdev) { - size_t bufsz = dev->mtu + ETH_HLEN + ETH_FCS_LEN + NET_IP_ALIGN; - struct macb *bp = netdev_priv(dev); + size_t bufsz = netdev->mtu + ETH_HLEN + ETH_FCS_LEN + NET_IP_ALIGN; + struct macb *bp = netdev_priv(netdev); struct macb_queue *queue; unsigned int q; int err; - netdev_dbg(bp->dev, "open\n"); + netdev_dbg(bp->netdev, "open\n"); err = pm_runtime_resume_and_get(&bp->pdev->dev); if (err < 0) @@ -3176,7 +3186,7 @@ static int macb_open(struct net_device *dev) err = macb_alloc_consistent(bp); if (err) { - netdev_err(dev, "Unable to allocate DMA memory (error %d)\n", + netdev_err(netdev, "Unable to allocate DMA memory (error %d)\n", err); goto pm_exit; } @@ -3203,10 +3213,10 @@ static int macb_open(struct net_device *dev) if (err) goto phy_off; - netif_tx_start_all_queues(dev); + netif_tx_start_all_queues(netdev); if (bp->ptp_info) - bp->ptp_info->ptp_init(dev); + bp->ptp_info->ptp_init(netdev); return 0; @@ -3225,19 +3235,19 @@ pm_exit: return err; } -static int macb_close(struct net_device *dev) +static int macb_close(struct net_device *netdev) { - struct macb *bp = netdev_priv(dev); + struct macb *bp = netdev_priv(netdev); struct macb_queue *queue; unsigned long flags; unsigned int q; - netif_tx_stop_all_queues(dev); + netif_tx_stop_all_queues(netdev); for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) { napi_disable(&queue->napi_rx); napi_disable(&queue->napi_tx); - netdev_tx_reset_queue(netdev_get_tx_queue(dev, q)); + netdev_tx_reset_queue(netdev_get_tx_queue(netdev, q)); } cancel_delayed_work_sync(&bp->tx_lpi_work); @@ -3249,38 +3259,38 @@ static int macb_close(struct net_device *dev) spin_lock_irqsave(&bp->lock, flags); macb_reset_hw(bp); - netif_carrier_off(dev); + netif_carrier_off(netdev); spin_unlock_irqrestore(&bp->lock, flags); macb_free_consistent(bp); if (bp->ptp_info) - bp->ptp_info->ptp_remove(dev); + bp->ptp_info->ptp_remove(netdev); pm_runtime_put(&bp->pdev->dev); return 0; } -static int macb_change_mtu(struct net_device *dev, int new_mtu) +static int macb_change_mtu(struct net_device *netdev, int new_mtu) { - if (netif_running(dev)) + if (netif_running(netdev)) return -EBUSY; - WRITE_ONCE(dev->mtu, new_mtu); + WRITE_ONCE(netdev->mtu, new_mtu); return 0; } -static int macb_set_mac_addr(struct net_device *dev, void *addr) +static int macb_set_mac_addr(struct net_device *netdev, void *addr) { int err; - err = eth_mac_addr(dev, addr); + err = eth_mac_addr(netdev, addr); if (err < 0) return err; - macb_set_hwaddr(netdev_priv(dev)); + macb_set_hwaddr(netdev_priv(netdev)); return 0; } @@ -3318,7 +3328,7 @@ static void gem_get_stats(struct macb *bp, struct rtnl_link_stats64 *nstat) struct gem_stats *hwstat = &bp->hw_stats.gem; spin_lock_irq(&bp->stats_lock); - if (netif_running(bp->dev)) + if (netif_running(bp->netdev)) gem_update_stats(bp); nstat->rx_errors = (hwstat->rx_frame_check_sequence_errors + @@ -3351,10 +3361,10 @@ static void gem_get_stats(struct macb *bp, struct rtnl_link_stats64 *nstat) spin_unlock_irq(&bp->stats_lock); } -static void gem_get_ethtool_stats(struct net_device *dev, +static void gem_get_ethtool_stats(struct net_device *netdev, struct ethtool_stats *stats, u64 *data) { - struct macb *bp = netdev_priv(dev); + struct macb *bp = netdev_priv(netdev); spin_lock_irq(&bp->stats_lock); gem_update_stats(bp); @@ -3363,9 +3373,9 @@ static void gem_get_ethtool_stats(struct net_device *dev, spin_unlock_irq(&bp->stats_lock); } -static int gem_get_sset_count(struct net_device *dev, int sset) +static int gem_get_sset_count(struct net_device *netdev, int sset) { - struct macb *bp = netdev_priv(dev); + struct macb *bp = netdev_priv(netdev); switch (sset) { case ETH_SS_STATS: @@ -3375,9 +3385,9 @@ static int gem_get_sset_count(struct net_device *dev, int sset) } } -static void gem_get_ethtool_strings(struct net_device *dev, u32 sset, u8 *p) +static void gem_get_ethtool_strings(struct net_device *netdev, u32 sset, u8 *p) { - struct macb *bp = netdev_priv(dev); + struct macb *bp = netdev_priv(netdev); struct macb_queue *queue; unsigned int i; unsigned int q; @@ -3396,13 +3406,13 @@ static void gem_get_ethtool_strings(struct net_device *dev, u32 sset, u8 *p) } } -static void macb_get_stats(struct net_device *dev, +static void macb_get_stats(struct net_device *netdev, struct rtnl_link_stats64 *nstat) { - struct macb *bp = netdev_priv(dev); + struct macb *bp = netdev_priv(netdev); struct macb_stats *hwstat = &bp->hw_stats.macb; - netdev_stats_to_stats64(nstat, &bp->dev->stats); + netdev_stats_to_stats64(nstat, &bp->netdev->stats); if (macb_is_gem(bp)) { gem_get_stats(bp, nstat); return; @@ -3446,10 +3456,10 @@ static void macb_get_stats(struct net_device *dev, spin_unlock_irq(&bp->stats_lock); } -static void macb_get_pause_stats(struct net_device *dev, +static void macb_get_pause_stats(struct net_device *netdev, struct ethtool_pause_stats *pause_stats) { - struct macb *bp = netdev_priv(dev); + struct macb *bp = netdev_priv(netdev); struct macb_stats *hwstat = &bp->hw_stats.macb; spin_lock_irq(&bp->stats_lock); @@ -3459,10 +3469,10 @@ static void macb_get_pause_stats(struct net_device *dev, spin_unlock_irq(&bp->stats_lock); } -static void gem_get_pause_stats(struct net_device *dev, +static void gem_get_pause_stats(struct net_device *netdev, struct ethtool_pause_stats *pause_stats) { - struct macb *bp = netdev_priv(dev); + struct macb *bp = netdev_priv(netdev); struct gem_stats *hwstat = &bp->hw_stats.gem; spin_lock_irq(&bp->stats_lock); @@ -3472,10 +3482,10 @@ static void gem_get_pause_stats(struct net_device *dev, spin_unlock_irq(&bp->stats_lock); } -static void macb_get_eth_mac_stats(struct net_device *dev, +static void macb_get_eth_mac_stats(struct net_device *netdev, struct ethtool_eth_mac_stats *mac_stats) { - struct macb *bp = netdev_priv(dev); + struct macb *bp = netdev_priv(netdev); struct macb_stats *hwstat = &bp->hw_stats.macb; spin_lock_irq(&bp->stats_lock); @@ -3497,10 +3507,10 @@ static void macb_get_eth_mac_stats(struct net_device *dev, spin_unlock_irq(&bp->stats_lock); } -static void gem_get_eth_mac_stats(struct net_device *dev, +static void gem_get_eth_mac_stats(struct net_device *netdev, struct ethtool_eth_mac_stats *mac_stats) { - struct macb *bp = netdev_priv(dev); + struct macb *bp = netdev_priv(netdev); struct gem_stats *hwstat = &bp->hw_stats.gem; spin_lock_irq(&bp->stats_lock); @@ -3530,10 +3540,10 @@ static void gem_get_eth_mac_stats(struct net_device *dev, } /* TODO: Report SQE test errors when added to phy_stats */ -static void macb_get_eth_phy_stats(struct net_device *dev, +static void macb_get_eth_phy_stats(struct net_device *netdev, struct ethtool_eth_phy_stats *phy_stats) { - struct macb *bp = netdev_priv(dev); + struct macb *bp = netdev_priv(netdev); struct macb_stats *hwstat = &bp->hw_stats.macb; spin_lock_irq(&bp->stats_lock); @@ -3542,10 +3552,10 @@ static void macb_get_eth_phy_stats(struct net_device *dev, spin_unlock_irq(&bp->stats_lock); } -static void gem_get_eth_phy_stats(struct net_device *dev, +static void gem_get_eth_phy_stats(struct net_device *netdev, struct ethtool_eth_phy_stats *phy_stats) { - struct macb *bp = netdev_priv(dev); + struct macb *bp = netdev_priv(netdev); struct gem_stats *hwstat = &bp->hw_stats.gem; spin_lock_irq(&bp->stats_lock); @@ -3554,11 +3564,11 @@ static void gem_get_eth_phy_stats(struct net_device *dev, spin_unlock_irq(&bp->stats_lock); } -static void macb_get_rmon_stats(struct net_device *dev, +static void macb_get_rmon_stats(struct net_device *netdev, struct ethtool_rmon_stats *rmon_stats, const struct ethtool_rmon_hist_range **ranges) { - struct macb *bp = netdev_priv(dev); + struct macb *bp = netdev_priv(netdev); struct macb_stats *hwstat = &bp->hw_stats.macb; spin_lock_irq(&bp->stats_lock); @@ -3580,11 +3590,11 @@ static const struct ethtool_rmon_hist_range gem_rmon_ranges[] = { { }, }; -static void gem_get_rmon_stats(struct net_device *dev, +static void gem_get_rmon_stats(struct net_device *netdev, struct ethtool_rmon_stats *rmon_stats, const struct ethtool_rmon_hist_range **ranges) { - struct macb *bp = netdev_priv(dev); + struct macb *bp = netdev_priv(netdev); struct gem_stats *hwstat = &bp->hw_stats.gem; spin_lock_irq(&bp->stats_lock); @@ -3615,10 +3625,10 @@ static int macb_get_regs_len(struct net_device *netdev) return MACB_GREGS_NBR * sizeof(u32); } -static void macb_get_regs(struct net_device *dev, struct ethtool_regs *regs, +static void macb_get_regs(struct net_device *netdev, struct ethtool_regs *regs, void *p) { - struct macb *bp = netdev_priv(dev); + struct macb *bp = netdev_priv(netdev); unsigned int tail, head; u32 *regs_buff = p; @@ -3735,16 +3745,16 @@ static int macb_set_ringparam(struct net_device *netdev, return 0; } - if (netif_running(bp->dev)) { + if (netif_running(bp->netdev)) { reset = 1; - macb_close(bp->dev); + macb_close(bp->netdev); } bp->rx_ring_size = new_rx_size; bp->tx_ring_size = new_tx_size; if (reset) - macb_open(bp->dev); + macb_open(bp->netdev); return 0; } @@ -3771,13 +3781,13 @@ static s32 gem_get_ptp_max_adj(void) return 64000000; } -static int gem_get_ts_info(struct net_device *dev, +static int gem_get_ts_info(struct net_device *netdev, struct kernel_ethtool_ts_info *info) { - struct macb *bp = netdev_priv(dev); + struct macb *bp = netdev_priv(netdev); if (!macb_dma_ptp(bp)) { - ethtool_op_get_ts_info(dev, info); + ethtool_op_get_ts_info(netdev, info); return 0; } @@ -3824,7 +3834,7 @@ static int macb_get_ts_info(struct net_device *netdev, static void gem_enable_flow_filters(struct macb *bp, bool enable) { - struct net_device *netdev = bp->dev; + struct net_device *netdev = bp->netdev; struct ethtool_rx_fs_item *item; u32 t2_scr; int num_t2_scr; @@ -4154,16 +4164,16 @@ static const struct ethtool_ops macb_ethtool_ops = { .set_ringparam = macb_set_ringparam, }; -static int macb_get_eee(struct net_device *dev, struct ethtool_keee *eee) +static int macb_get_eee(struct net_device *netdev, struct ethtool_keee *eee) { - struct macb *bp = netdev_priv(dev); + struct macb *bp = netdev_priv(netdev); return phylink_ethtool_get_eee(bp->phylink, eee); } -static int macb_set_eee(struct net_device *dev, struct ethtool_keee *eee) +static int macb_set_eee(struct net_device *netdev, struct ethtool_keee *eee) { - struct macb *bp = netdev_priv(dev); + struct macb *bp = netdev_priv(netdev); return phylink_ethtool_set_eee(bp->phylink, eee); } @@ -4194,43 +4204,43 @@ static const struct ethtool_ops gem_ethtool_ops = { .set_eee = macb_set_eee, }; -static int macb_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) +static int macb_ioctl(struct net_device *netdev, struct ifreq *rq, int cmd) { - struct macb *bp = netdev_priv(dev); + struct macb *bp = netdev_priv(netdev); - if (!netif_running(dev)) + if (!netif_running(netdev)) return -EINVAL; return phylink_mii_ioctl(bp->phylink, rq, cmd); } -static int macb_hwtstamp_get(struct net_device *dev, +static int macb_hwtstamp_get(struct net_device *netdev, struct kernel_hwtstamp_config *cfg) { - struct macb *bp = netdev_priv(dev); + struct macb *bp = netdev_priv(netdev); - if (!netif_running(dev)) + if (!netif_running(netdev)) return -EINVAL; if (!bp->ptp_info) return -EOPNOTSUPP; - return bp->ptp_info->get_hwtst(dev, cfg); + return bp->ptp_info->get_hwtst(netdev, cfg); } -static int macb_hwtstamp_set(struct net_device *dev, +static int macb_hwtstamp_set(struct net_device *netdev, struct kernel_hwtstamp_config *cfg, struct netlink_ext_ack *extack) { - struct macb *bp = netdev_priv(dev); + struct macb *bp = netdev_priv(netdev); - if (!netif_running(dev)) + if (!netif_running(netdev)) return -EINVAL; if (!bp->ptp_info) return -EOPNOTSUPP; - return bp->ptp_info->set_hwtst(dev, cfg, extack); + return bp->ptp_info->set_hwtst(netdev, cfg, extack); } static inline void macb_set_txcsum_feature(struct macb *bp, @@ -4253,7 +4263,7 @@ static inline void macb_set_txcsum_feature(struct macb *bp, static inline void macb_set_rxcsum_feature(struct macb *bp, netdev_features_t features) { - struct net_device *netdev = bp->dev; + struct net_device *netdev = bp->netdev; u32 val; if (!macb_is_gem(bp)) @@ -4300,7 +4310,7 @@ static int macb_set_features(struct net_device *netdev, static void macb_restore_features(struct macb *bp) { - struct net_device *netdev = bp->dev; + struct net_device *netdev = bp->netdev; netdev_features_t features = netdev->features; struct ethtool_rx_fs_item *item; @@ -4317,15 +4327,15 @@ static void macb_restore_features(struct macb *bp) macb_set_rxflow_feature(bp, features); } -static int macb_taprio_setup_replace(struct net_device *ndev, +static int macb_taprio_setup_replace(struct net_device *netdev, struct tc_taprio_qopt_offload *conf) { u64 total_on_time = 0, start_time_sec = 0, start_time = conf->base_time; u32 configured_queues = 0, speed = 0, start_time_nsec; struct macb_queue_enst_config *enst_queue; + struct ethtool_link_ksettings kset = {}; + struct macb *bp = netdev_priv(netdev); struct tc_taprio_sched_entry *entry; - struct macb *bp = netdev_priv(ndev); - struct ethtool_link_ksettings kset; struct macb_queue *queue; u32 queue_mask; u8 queue_id; @@ -4333,13 +4343,13 @@ static int macb_taprio_setup_replace(struct net_device *ndev, int err; if (conf->num_entries > bp->num_queues) { - netdev_err(ndev, "Too many TAPRIO entries: %zu > %d queues\n", + netdev_err(netdev, "Too many TAPRIO entries: %zu > %d queues\n", conf->num_entries, bp->num_queues); return -EINVAL; } if (conf->base_time < 0) { - netdev_err(ndev, "Invalid base_time: must be 0 or positive, got %lld\n", + netdev_err(netdev, "Invalid base_time: must be 0 or positive, got %lld\n", conf->base_time); return -ERANGE; } @@ -4347,13 +4357,13 @@ static int macb_taprio_setup_replace(struct net_device *ndev, /* Get the current link speed */ err = phylink_ethtool_ksettings_get(bp->phylink, &kset); if (unlikely(err)) { - netdev_err(ndev, "Failed to get link settings: %d\n", err); + netdev_err(netdev, "Failed to get link settings: %d\n", err); return err; } speed = kset.base.speed; - if (unlikely(speed <= 0)) { - netdev_err(ndev, "Invalid speed: %d\n", speed); + if (unlikely(speed == SPEED_UNKNOWN || !speed)) { + netdev_err(netdev, "Invalid speed %d, link-down?\n", speed); return -EINVAL; } @@ -4366,7 +4376,7 @@ static int macb_taprio_setup_replace(struct net_device *ndev, entry = &conf->entries[i]; if (entry->command != TC_TAPRIO_CMD_SET_GATES) { - netdev_err(ndev, "Entry %zu: unsupported command %d\n", + netdev_err(netdev, "Entry %zu: unsupported command %d\n", i, entry->command); err = -EOPNOTSUPP; goto cleanup; @@ -4374,7 +4384,7 @@ static int macb_taprio_setup_replace(struct net_device *ndev, /* Validate gate_mask: must be nonzero, single queue, and within range */ if (!is_power_of_2(entry->gate_mask)) { - netdev_err(ndev, "Entry %zu: gate_mask 0x%x is not a power of 2 (only one queue per entry allowed)\n", + netdev_err(netdev, "Entry %zu: gate_mask 0x%x is not a power of 2 (only one queue per entry allowed)\n", i, entry->gate_mask); err = -EINVAL; goto cleanup; @@ -4383,7 +4393,7 @@ static int macb_taprio_setup_replace(struct net_device *ndev, /* gate_mask must not select queues outside the valid queues */ queue_id = order_base_2(entry->gate_mask); if (queue_id >= bp->num_queues) { - netdev_err(ndev, "Entry %zu: gate_mask 0x%x exceeds queue range (max_queues=%d)\n", + netdev_err(netdev, "Entry %zu: gate_mask 0x%x exceeds queue range (max_queues=%d)\n", i, entry->gate_mask, bp->num_queues); err = -EINVAL; goto cleanup; @@ -4393,7 +4403,7 @@ static int macb_taprio_setup_replace(struct net_device *ndev, start_time_sec = start_time; start_time_nsec = do_div(start_time_sec, NSEC_PER_SEC); if (start_time_sec > GENMASK(GEM_START_TIME_SEC_SIZE - 1, 0)) { - netdev_err(ndev, "Entry %zu: Start time %llu s exceeds hardware limit\n", + netdev_err(netdev, "Entry %zu: Start time %llu s exceeds hardware limit\n", i, start_time_sec); err = -ERANGE; goto cleanup; @@ -4401,7 +4411,7 @@ static int macb_taprio_setup_replace(struct net_device *ndev, /* Check for on time limit */ if (entry->interval > enst_max_hw_interval(speed)) { - netdev_err(ndev, "Entry %zu: interval %u ns exceeds hardware limit %llu ns\n", + netdev_err(netdev, "Entry %zu: interval %u ns exceeds hardware limit %llu ns\n", i, entry->interval, enst_max_hw_interval(speed)); err = -ERANGE; goto cleanup; @@ -4409,7 +4419,7 @@ static int macb_taprio_setup_replace(struct net_device *ndev, /* Check for off time limit*/ if ((conf->cycle_time - entry->interval) > enst_max_hw_interval(speed)) { - netdev_err(ndev, "Entry %zu: off_time %llu ns exceeds hardware limit %llu ns\n", + netdev_err(netdev, "Entry %zu: off_time %llu ns exceeds hardware limit %llu ns\n", i, conf->cycle_time - entry->interval, enst_max_hw_interval(speed)); err = -ERANGE; @@ -4432,13 +4442,13 @@ static int macb_taprio_setup_replace(struct net_device *ndev, /* Check total interval doesn't exceed cycle time */ if (total_on_time > conf->cycle_time) { - netdev_err(ndev, "Total ON %llu ns exceeds cycle time %llu ns\n", + netdev_err(netdev, "Total ON %llu ns exceeds cycle time %llu ns\n", total_on_time, conf->cycle_time); err = -EINVAL; goto cleanup; } - netdev_dbg(ndev, "TAPRIO setup: %zu entries, base_time=%lld ns, cycle_time=%llu ns\n", + netdev_dbg(netdev, "TAPRIO setup: %zu entries, base_time=%lld ns, cycle_time=%llu ns\n", conf->num_entries, conf->base_time, conf->cycle_time); /* All validations passed - proceed with hardware configuration */ @@ -4463,7 +4473,7 @@ static int macb_taprio_setup_replace(struct net_device *ndev, gem_writel(bp, ENST_CONTROL, configured_queues); } - netdev_info(ndev, "TAPRIO configuration completed successfully: %zu entries, %d queues configured\n", + netdev_info(netdev, "TAPRIO configuration completed successfully: %zu entries, %d queues configured\n", conf->num_entries, hweight32(configured_queues)); cleanup: @@ -4471,14 +4481,14 @@ cleanup: return err; } -static void macb_taprio_destroy(struct net_device *ndev) +static void macb_taprio_destroy(struct net_device *netdev) { - struct macb *bp = netdev_priv(ndev); + struct macb *bp = netdev_priv(netdev); struct macb_queue *queue; u32 queue_mask; unsigned int q; - netdev_reset_tc(ndev); + netdev_reset_tc(netdev); queue_mask = BIT_U32(bp->num_queues) - 1; scoped_guard(spinlock_irqsave, &bp->lock) { @@ -4493,30 +4503,30 @@ static void macb_taprio_destroy(struct net_device *ndev) queue_writel(queue, ENST_OFF_TIME, 0); } } - netdev_info(ndev, "TAPRIO destroy: All gates disabled\n"); + netdev_info(netdev, "TAPRIO destroy: All gates disabled\n"); } -static int macb_setup_taprio(struct net_device *ndev, +static int macb_setup_taprio(struct net_device *netdev, struct tc_taprio_qopt_offload *taprio) { - struct macb *bp = netdev_priv(ndev); + struct macb *bp = netdev_priv(netdev); int err = 0; - if (unlikely(!(ndev->hw_features & NETIF_F_HW_TC))) + if (unlikely(!(netdev->hw_features & NETIF_F_HW_TC))) return -EOPNOTSUPP; /* Check if Device is in runtime suspend */ if (unlikely(pm_runtime_suspended(&bp->pdev->dev))) { - netdev_err(ndev, "Device is in runtime suspend\n"); + netdev_err(netdev, "Device is in runtime suspend\n"); return -EOPNOTSUPP; } switch (taprio->cmd) { case TAPRIO_CMD_REPLACE: - err = macb_taprio_setup_replace(ndev, taprio); + err = macb_taprio_setup_replace(netdev, taprio); break; case TAPRIO_CMD_DESTROY: - macb_taprio_destroy(ndev); + macb_taprio_destroy(netdev); break; default: err = -EOPNOTSUPP; @@ -4525,23 +4535,23 @@ static int macb_setup_taprio(struct net_device *ndev, return err; } -static int macb_setup_tc(struct net_device *dev, enum tc_setup_type type, +static int macb_setup_tc(struct net_device *netdev, enum tc_setup_type type, void *type_data) { - if (!dev || !type_data) + if (!netdev || !type_data) return -EINVAL; switch (type) { case TC_SETUP_QDISC_TAPRIO: - return macb_setup_taprio(dev, type_data); + return macb_setup_taprio(netdev, type_data); default: return -EOPNOTSUPP; } } -static void macb_tx_timeout(struct net_device *dev, unsigned int q) +static void macb_tx_timeout(struct net_device *netdev, unsigned int q) { - struct macb *bp = netdev_priv(dev); + struct macb *bp = netdev_priv(netdev); macb_tx_restart(&bp->queues[q]); } @@ -4749,9 +4759,9 @@ static int macb_clk_init(struct platform_device *pdev, struct clk **pclk, static int macb_init_dflt(struct platform_device *pdev) { - struct net_device *dev = platform_get_drvdata(pdev); + struct net_device *netdev = platform_get_drvdata(pdev); unsigned int hw_q, q; - struct macb *bp = netdev_priv(dev); + struct macb *bp = netdev_priv(netdev); struct macb_queue *queue; int err; u32 val, reg; @@ -4767,8 +4777,8 @@ static int macb_init_dflt(struct platform_device *pdev) queue = &bp->queues[q]; queue->bp = bp; spin_lock_init(&queue->tx_ptr_lock); - netif_napi_add(dev, &queue->napi_rx, macb_rx_poll); - netif_napi_add_tx(dev, &queue->napi_tx, macb_tx_poll); + netif_napi_add(netdev, &queue->napi_rx, macb_rx_poll); + netif_napi_add_tx(netdev, &queue->napi_tx, macb_tx_poll); if (hw_q) { queue->ISR = GEM_ISR(hw_q - 1); queue->IER = GEM_IER(hw_q - 1); @@ -4798,7 +4808,7 @@ static int macb_init_dflt(struct platform_device *pdev) */ queue->irq = platform_get_irq(pdev, q); err = devm_request_irq(&pdev->dev, queue->irq, macb_interrupt, - IRQF_SHARED, dev->name, queue); + IRQF_SHARED, netdev->name, queue); if (err) { dev_err(&pdev->dev, "Unable to request IRQ %d (error %d)\n", @@ -4810,7 +4820,7 @@ static int macb_init_dflt(struct platform_device *pdev) q++; } - dev->netdev_ops = &macb_netdev_ops; + netdev->netdev_ops = &macb_netdev_ops; /* setup appropriated routines according to adapter type */ if (macb_is_gem(bp)) { @@ -4818,39 +4828,39 @@ static int macb_init_dflt(struct platform_device *pdev) bp->macbgem_ops.mog_free_rx_buffers = gem_free_rx_buffers; bp->macbgem_ops.mog_init_rings = gem_init_rings; bp->macbgem_ops.mog_rx = gem_rx; - dev->ethtool_ops = &gem_ethtool_ops; + netdev->ethtool_ops = &gem_ethtool_ops; } else { bp->macbgem_ops.mog_alloc_rx_buffers = macb_alloc_rx_buffers; bp->macbgem_ops.mog_free_rx_buffers = macb_free_rx_buffers; bp->macbgem_ops.mog_init_rings = macb_init_rings; bp->macbgem_ops.mog_rx = macb_rx; - dev->ethtool_ops = &macb_ethtool_ops; + netdev->ethtool_ops = &macb_ethtool_ops; } - netdev_sw_irq_coalesce_default_on(dev); + netdev_sw_irq_coalesce_default_on(netdev); - dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; + netdev->priv_flags |= IFF_LIVE_ADDR_CHANGE; /* Set features */ - dev->hw_features = NETIF_F_SG; + netdev->hw_features = NETIF_F_SG; /* Check LSO capability; runtime detection can be overridden by a cap * flag if the hardware is known to be buggy */ if (!(bp->caps & MACB_CAPS_NO_LSO) && GEM_BFEXT(PBUF_LSO, gem_readl(bp, DCFG6))) - dev->hw_features |= MACB_NETIF_LSO; + netdev->hw_features |= MACB_NETIF_LSO; /* Checksum offload is only available on gem with packet buffer */ if (macb_is_gem(bp) && !(bp->caps & MACB_CAPS_FIFO_MODE)) - dev->hw_features |= NETIF_F_HW_CSUM | NETIF_F_RXCSUM; + netdev->hw_features |= NETIF_F_HW_CSUM | NETIF_F_RXCSUM; if (bp->caps & MACB_CAPS_SG_DISABLED) - dev->hw_features &= ~NETIF_F_SG; + netdev->hw_features &= ~NETIF_F_SG; /* Enable HW_TC if hardware supports QBV */ if (bp->caps & MACB_CAPS_QBV) - dev->hw_features |= NETIF_F_HW_TC; + netdev->hw_features |= NETIF_F_HW_TC; - dev->features = dev->hw_features; + netdev->features = netdev->hw_features; /* Check RX Flow Filters support. * Max Rx flows set by availability of screeners & compare regs: @@ -4868,7 +4878,7 @@ static int macb_init_dflt(struct platform_device *pdev) reg = GEM_BFINS(ETHTCMP, (uint16_t)ETH_P_IP, reg); gem_writel_n(bp, ETHT, SCRT2_ETHT, reg); /* Filtering is supported in hw but don't enable it in kernel now */ - dev->hw_features |= NETIF_F_NTUPLE; + netdev->hw_features |= NETIF_F_NTUPLE; /* init Rx flow definitions */ bp->rx_fs_list.count = 0; spin_lock_init(&bp->rx_fs_lock); @@ -5078,9 +5088,9 @@ static void at91ether_stop(struct macb *lp) } /* Open the ethernet interface */ -static int at91ether_open(struct net_device *dev) +static int at91ether_open(struct net_device *netdev) { - struct macb *lp = netdev_priv(dev); + struct macb *lp = netdev_priv(netdev); u32 ctl; int ret; @@ -5102,7 +5112,7 @@ static int at91ether_open(struct net_device *dev) if (ret) goto stop; - netif_start_queue(dev); + netif_start_queue(netdev); return 0; @@ -5114,11 +5124,11 @@ pm_exit: } /* Close the interface */ -static int at91ether_close(struct net_device *dev) +static int at91ether_close(struct net_device *netdev) { - struct macb *lp = netdev_priv(dev); + struct macb *lp = netdev_priv(netdev); - netif_stop_queue(dev); + netif_stop_queue(netdev); phylink_stop(lp->phylink); phylink_disconnect_phy(lp->phylink); @@ -5132,14 +5142,14 @@ static int at91ether_close(struct net_device *dev) /* Transmit packet */ static netdev_tx_t at91ether_start_xmit(struct sk_buff *skb, - struct net_device *dev) + struct net_device *netdev) { - struct macb *lp = netdev_priv(dev); + struct macb *lp = netdev_priv(netdev); if (macb_readl(lp, TSR) & MACB_BIT(RM9200_BNQ)) { int desc = 0; - netif_stop_queue(dev); + netif_stop_queue(netdev); /* Store packet information (to free when Tx completed) */ lp->rm9200_txq[desc].skb = skb; @@ -5148,8 +5158,8 @@ static netdev_tx_t at91ether_start_xmit(struct sk_buff *skb, skb->len, DMA_TO_DEVICE); if (dma_mapping_error(&lp->pdev->dev, lp->rm9200_txq[desc].mapping)) { dev_kfree_skb_any(skb); - dev->stats.tx_dropped++; - netdev_err(dev, "%s: DMA mapping error\n", __func__); + netdev->stats.tx_dropped++; + netdev_err(netdev, "%s: DMA mapping error\n", __func__); return NETDEV_TX_OK; } @@ -5159,7 +5169,8 @@ static netdev_tx_t at91ether_start_xmit(struct sk_buff *skb, macb_writel(lp, TCR, skb->len); } else { - netdev_err(dev, "%s called, but device is busy!\n", __func__); + netdev_err(netdev, "%s called, but device is busy!\n", + __func__); return NETDEV_TX_BUSY; } @@ -5169,9 +5180,9 @@ static netdev_tx_t at91ether_start_xmit(struct sk_buff *skb, /* Extract received frame from buffer descriptors and sent to upper layers. * (Called from interrupt context) */ -static void at91ether_rx(struct net_device *dev) +static void at91ether_rx(struct net_device *netdev) { - struct macb *lp = netdev_priv(dev); + struct macb *lp = netdev_priv(netdev); struct macb_queue *q = &lp->queues[0]; struct macb_dma_desc *desc; unsigned char *p_recv; @@ -5182,21 +5193,21 @@ static void at91ether_rx(struct net_device *dev) while (desc->addr & MACB_BIT(RX_USED)) { p_recv = q->rx_buffers + q->rx_tail * AT91ETHER_MAX_RBUFF_SZ; pktlen = MACB_BF(RX_FRMLEN, desc->ctrl); - skb = netdev_alloc_skb(dev, pktlen + 2); + skb = netdev_alloc_skb(netdev, pktlen + 2); if (skb) { skb_reserve(skb, 2); skb_put_data(skb, p_recv, pktlen); - skb->protocol = eth_type_trans(skb, dev); - dev->stats.rx_packets++; - dev->stats.rx_bytes += pktlen; + skb->protocol = eth_type_trans(skb, netdev); + netdev->stats.rx_packets++; + netdev->stats.rx_bytes += pktlen; netif_rx(skb); } else { - dev->stats.rx_dropped++; + netdev->stats.rx_dropped++; } if (desc->ctrl & MACB_BIT(RX_MHASH_MATCH)) - dev->stats.multicast++; + netdev->stats.multicast++; /* reset ownership bit */ desc->addr &= ~MACB_BIT(RX_USED); @@ -5214,8 +5225,8 @@ static void at91ether_rx(struct net_device *dev) /* MAC interrupt handler */ static irqreturn_t at91ether_interrupt(int irq, void *dev_id) { - struct net_device *dev = dev_id; - struct macb *lp = netdev_priv(dev); + struct net_device *netdev = dev_id; + struct macb *lp = netdev_priv(netdev); u32 intstatus, ctl; unsigned int desc; @@ -5226,13 +5237,13 @@ static irqreturn_t at91ether_interrupt(int irq, void *dev_id) /* Receive complete */ if (intstatus & MACB_BIT(RCOMP)) - at91ether_rx(dev); + at91ether_rx(netdev); /* Transmit complete */ if (intstatus & MACB_BIT(TCOMP)) { /* The TCOM bit is set even if the transmission failed */ if (intstatus & (MACB_BIT(ISR_TUND) | MACB_BIT(ISR_RLE))) - dev->stats.tx_errors++; + netdev->stats.tx_errors++; desc = 0; if (lp->rm9200_txq[desc].skb) { @@ -5240,10 +5251,10 @@ static irqreturn_t at91ether_interrupt(int irq, void *dev_id) lp->rm9200_txq[desc].skb = NULL; dma_unmap_single(&lp->pdev->dev, lp->rm9200_txq[desc].mapping, lp->rm9200_txq[desc].size, DMA_TO_DEVICE); - dev->stats.tx_packets++; - dev->stats.tx_bytes += lp->rm9200_txq[desc].size; + netdev->stats.tx_packets++; + netdev->stats.tx_bytes += lp->rm9200_txq[desc].size; } - netif_wake_queue(dev); + netif_wake_queue(netdev); } /* Work-around for EMAC Errata section 41.3.1 */ @@ -5255,18 +5266,18 @@ static irqreturn_t at91ether_interrupt(int irq, void *dev_id) } if (intstatus & MACB_BIT(ISR_ROVR)) - netdev_err(dev, "ROVR error\n"); + netdev_err(netdev, "ROVR error\n"); return IRQ_HANDLED; } #ifdef CONFIG_NET_POLL_CONTROLLER -static void at91ether_poll_controller(struct net_device *dev) +static void at91ether_poll_controller(struct net_device *netdev) { unsigned long flags; local_irq_save(flags); - at91ether_interrupt(dev->irq, dev); + at91ether_interrupt(netdev->irq, netdev); local_irq_restore(flags); } #endif @@ -5313,17 +5324,17 @@ static int at91ether_clk_init(struct platform_device *pdev, struct clk **pclk, static int at91ether_init(struct platform_device *pdev) { - struct net_device *dev = platform_get_drvdata(pdev); - struct macb *bp = netdev_priv(dev); + struct net_device *netdev = platform_get_drvdata(pdev); + struct macb *bp = netdev_priv(netdev); int err; bp->queues[0].bp = bp; - dev->netdev_ops = &at91ether_netdev_ops; - dev->ethtool_ops = &macb_ethtool_ops; + netdev->netdev_ops = &at91ether_netdev_ops; + netdev->ethtool_ops = &macb_ethtool_ops; - err = devm_request_irq(&pdev->dev, dev->irq, at91ether_interrupt, - 0, dev->name, dev); + err = devm_request_irq(&pdev->dev, netdev->irq, at91ether_interrupt, + 0, netdev->name, netdev); if (err) return err; @@ -5452,8 +5463,8 @@ static int fu540_c000_init(struct platform_device *pdev) static int init_reset_optional(struct platform_device *pdev) { - struct net_device *dev = platform_get_drvdata(pdev); - struct macb *bp = netdev_priv(dev); + struct net_device *netdev = platform_get_drvdata(pdev); + struct macb *bp = netdev_priv(netdev); int ret; if (bp->phy_interface == PHY_INTERFACE_MODE_SGMII) { @@ -5761,7 +5772,7 @@ static int macb_probe(struct platform_device *pdev) const struct macb_config *macb_config; struct clk *tsu_clk = NULL; phy_interface_t interface; - struct net_device *dev; + struct net_device *netdev; struct resource *regs; u32 wtrmrk_rst_val; void __iomem *mem; @@ -5796,19 +5807,19 @@ static int macb_probe(struct platform_device *pdev) goto err_disable_clocks; } - dev = alloc_etherdev_mq(sizeof(*bp), num_queues); - if (!dev) { + netdev = alloc_etherdev_mq(sizeof(*bp), num_queues); + if (!netdev) { err = -ENOMEM; goto err_disable_clocks; } - dev->base_addr = regs->start; + netdev->base_addr = regs->start; - SET_NETDEV_DEV(dev, &pdev->dev); + SET_NETDEV_DEV(netdev, &pdev->dev); - bp = netdev_priv(dev); + bp = netdev_priv(netdev); bp->pdev = pdev; - bp->dev = dev; + bp->netdev = netdev; bp->regs = mem; bp->native_io = native_io; if (native_io) { @@ -5867,6 +5878,7 @@ static int macb_probe(struct platform_device *pdev) } spin_lock_init(&bp->lock); spin_lock_init(&bp->stats_lock); + spin_lock_init(&bp->tsu_clk_lock); /* setup capabilities */ macb_configure_caps(bp, macb_config); @@ -5881,21 +5893,21 @@ static int macb_probe(struct platform_device *pdev) bp->caps |= MACB_CAPS_DMA_64B; } #endif - platform_set_drvdata(pdev, dev); + platform_set_drvdata(pdev, netdev); - dev->irq = platform_get_irq(pdev, 0); - if (dev->irq < 0) { - err = dev->irq; + netdev->irq = platform_get_irq(pdev, 0); + if (netdev->irq < 0) { + err = netdev->irq; goto err_out_free_netdev; } /* MTU range: 68 - 1518 or 10240 */ - dev->min_mtu = GEM_MTU_MIN_SIZE; + netdev->min_mtu = GEM_MTU_MIN_SIZE; if ((bp->caps & MACB_CAPS_JUMBO) && bp->jumbo_max_len) - dev->max_mtu = MIN(bp->jumbo_max_len, RX_BUFFER_MAX) - + netdev->max_mtu = MIN(bp->jumbo_max_len, RX_BUFFER_MAX) - ETH_HLEN - ETH_FCS_LEN; else - dev->max_mtu = 1536 - ETH_HLEN - ETH_FCS_LEN; + netdev->max_mtu = 1536 - ETH_HLEN - ETH_FCS_LEN; if (bp->caps & MACB_CAPS_BD_RD_PREFETCH) { val = GEM_BFEXT(RXBD_RDBUFF, gem_readl(bp, DCFG10)); @@ -5913,7 +5925,7 @@ static int macb_probe(struct platform_device *pdev) if (bp->caps & MACB_CAPS_NEEDS_RSTONUBR) bp->rx_intr_mask |= MACB_BIT(RXUBR); - err = of_get_ethdev_address(np, bp->dev); + err = of_get_ethdev_address(np, bp->netdev); if (err == -EPROBE_DEFER) goto err_out_free_netdev; else if (err) @@ -5935,9 +5947,9 @@ static int macb_probe(struct platform_device *pdev) if (err) goto err_out_phy_exit; - netif_carrier_off(dev); + netif_carrier_off(netdev); - err = register_netdev(dev); + err = register_netdev(netdev); if (err) { dev_err(&pdev->dev, "Cannot register net device, aborting.\n"); goto err_out_unregister_mdio; @@ -5946,23 +5958,26 @@ static int macb_probe(struct platform_device *pdev) INIT_WORK(&bp->hresp_err_bh_work, macb_hresp_error_task); INIT_DELAYED_WORK(&bp->tx_lpi_work, macb_tx_lpi_work_fn); - netdev_info(dev, "Cadence %s rev 0x%08x at 0x%08lx irq %d (%pM)\n", + netdev_info(netdev, "Cadence %s rev 0x%08x at 0x%08lx irq %d (%pM)\n", macb_is_gem(bp) ? "GEM" : "MACB", macb_readl(bp, MID), - dev->base_addr, dev->irq, dev->dev_addr); + netdev->base_addr, netdev->irq, netdev->dev_addr); pm_runtime_put_autosuspend(&bp->pdev->dev); return 0; err_out_unregister_mdio: - mdiobus_unregister(bp->mii_bus); - mdiobus_free(bp->mii_bus); + if (bp->mii_bus) { + mdiobus_unregister(bp->mii_bus); + mdiobus_free(bp->mii_bus); + } + phylink_destroy(bp->phylink); err_out_phy_exit: phy_exit(bp->phy); err_out_free_netdev: - free_netdev(dev); + free_netdev(netdev); err_disable_clocks: macb_clks_disable(pclk, hclk, tx_clk, rx_clk, tsu_clk); @@ -5975,17 +5990,19 @@ err_disable_clocks: static void macb_remove(struct platform_device *pdev) { - struct net_device *dev; + struct net_device *netdev; struct macb *bp; - dev = platform_get_drvdata(pdev); + netdev = platform_get_drvdata(pdev); - if (dev) { - bp = netdev_priv(dev); - unregister_netdev(dev); + if (netdev) { + bp = netdev_priv(netdev); + unregister_netdev(netdev); phy_exit(bp->phy); - mdiobus_unregister(bp->mii_bus); - mdiobus_free(bp->mii_bus); + if (bp->mii_bus) { + mdiobus_unregister(bp->mii_bus); + mdiobus_free(bp->mii_bus); + } device_set_wakeup_enable(&bp->pdev->dev, 0); cancel_delayed_work_sync(&bp->tx_lpi_work); @@ -5994,7 +6011,7 @@ static void macb_remove(struct platform_device *pdev) pm_runtime_dont_use_autosuspend(&pdev->dev); pm_runtime_set_suspended(&pdev->dev); phylink_destroy(bp->phylink); - free_netdev(dev); + free_netdev(netdev); } } @@ -6009,7 +6026,7 @@ static int __maybe_unused macb_suspend(struct device *dev) u32 tmp, ifa_local; unsigned int q; - if (!device_may_wakeup(&bp->dev->dev)) + if (!device_may_wakeup(&bp->netdev->dev)) phy_exit(bp->phy); if (!netif_running(netdev)) @@ -6019,7 +6036,7 @@ static int __maybe_unused macb_suspend(struct device *dev) if (bp->wolopts & WAKE_ARP) { /* Check for IP address in WOL ARP mode */ rcu_read_lock(); - idev = __in_dev_get_rcu(bp->dev); + idev = __in_dev_get_rcu(bp->netdev); if (idev) ifa = rcu_dereference(idev->ifa_list); if (!ifa) { @@ -6121,7 +6138,7 @@ static int __maybe_unused macb_resume(struct device *dev) unsigned long flags; unsigned int q; - if (!device_may_wakeup(&bp->dev->dev)) + if (!device_may_wakeup(&bp->netdev->dev)) phy_init(bp->phy); if (!netif_running(netdev)) diff --git a/drivers/net/ethernet/cadence/macb_pci.c b/drivers/net/ethernet/cadence/macb_pci.c index b79dec17e6b099..ac009007118f31 100644 --- a/drivers/net/ethernet/cadence/macb_pci.c +++ b/drivers/net/ethernet/cadence/macb_pci.c @@ -24,48 +24,48 @@ #define GEM_PCLK_RATE 50000000 #define GEM_HCLK_RATE 50000000 -static int macb_probe(struct pci_dev *pdev, const struct pci_device_id *id) +static int macb_probe(struct pci_dev *pci, const struct pci_device_id *id) { int err; - struct platform_device *plat_dev; + struct platform_device *pdev; struct platform_device_info plat_info; struct macb_platform_data plat_data; struct resource res[2]; /* enable pci device */ - err = pcim_enable_device(pdev); + err = pcim_enable_device(pci); if (err < 0) { - dev_err(&pdev->dev, "Enabling PCI device has failed: %d", err); + dev_err(&pci->dev, "Enabling PCI device has failed: %d", err); return err; } - pci_set_master(pdev); + pci_set_master(pci); /* set up resources */ memset(res, 0x00, sizeof(struct resource) * ARRAY_SIZE(res)); - res[0].start = pci_resource_start(pdev, 0); - res[0].end = pci_resource_end(pdev, 0); + res[0].start = pci_resource_start(pci, 0); + res[0].end = pci_resource_end(pci, 0); res[0].name = PCI_DRIVER_NAME; res[0].flags = IORESOURCE_MEM; - res[1].start = pci_irq_vector(pdev, 0); + res[1].start = pci_irq_vector(pci, 0); res[1].name = PCI_DRIVER_NAME; res[1].flags = IORESOURCE_IRQ; - dev_info(&pdev->dev, "EMAC physical base addr: %pa\n", + dev_info(&pci->dev, "EMAC physical base addr: %pa\n", &res[0].start); /* set up macb platform data */ memset(&plat_data, 0, sizeof(plat_data)); /* initialize clocks */ - plat_data.pclk = clk_register_fixed_rate(&pdev->dev, "pclk", NULL, 0, + plat_data.pclk = clk_register_fixed_rate(&pci->dev, "pclk", NULL, 0, GEM_PCLK_RATE); if (IS_ERR(plat_data.pclk)) { err = PTR_ERR(plat_data.pclk); goto err_pclk_register; } - plat_data.hclk = clk_register_fixed_rate(&pdev->dev, "hclk", NULL, 0, + plat_data.hclk = clk_register_fixed_rate(&pci->dev, "hclk", NULL, 0, GEM_HCLK_RATE); if (IS_ERR(plat_data.hclk)) { err = PTR_ERR(plat_data.hclk); @@ -74,24 +74,24 @@ static int macb_probe(struct pci_dev *pdev, const struct pci_device_id *id) /* set up platform device info */ memset(&plat_info, 0, sizeof(plat_info)); - plat_info.parent = &pdev->dev; - plat_info.fwnode = pdev->dev.fwnode; + plat_info.parent = &pci->dev; + plat_info.fwnode = pci->dev.fwnode; plat_info.name = PLAT_DRIVER_NAME; - plat_info.id = pdev->devfn; + plat_info.id = pci->devfn; plat_info.res = res; plat_info.num_res = ARRAY_SIZE(res); plat_info.data = &plat_data; plat_info.size_data = sizeof(plat_data); - plat_info.dma_mask = pdev->dma_mask; + plat_info.dma_mask = pci->dma_mask; /* register platform device */ - plat_dev = platform_device_register_full(&plat_info); - if (IS_ERR(plat_dev)) { - err = PTR_ERR(plat_dev); + pdev = platform_device_register_full(&plat_info); + if (IS_ERR(pdev)) { + err = PTR_ERR(pdev); goto err_plat_dev_register; } - pci_set_drvdata(pdev, plat_dev); + pci_set_drvdata(pci, pdev); return 0; @@ -105,14 +105,14 @@ err_pclk_register: return err; } -static void macb_remove(struct pci_dev *pdev) +static void macb_remove(struct pci_dev *pci) { - struct platform_device *plat_dev = pci_get_drvdata(pdev); - struct macb_platform_data *plat_data = dev_get_platdata(&plat_dev->dev); + struct platform_device *pdev = pci_get_drvdata(pci); + struct macb_platform_data *plat_data = dev_get_platdata(&pdev->dev); struct clk *pclk = plat_data->pclk; struct clk *hclk = plat_data->hclk; - platform_device_unregister(plat_dev); + platform_device_unregister(pdev); clk_unregister_fixed_rate(pclk); clk_unregister_fixed_rate(hclk); } diff --git a/drivers/net/ethernet/cadence/macb_ptp.c b/drivers/net/ethernet/cadence/macb_ptp.c index d91f7b1aa39caa..6d916638998869 100644 --- a/drivers/net/ethernet/cadence/macb_ptp.c +++ b/drivers/net/ethernet/cadence/macb_ptp.c @@ -324,9 +324,9 @@ void gem_ptp_txstamp(struct macb *bp, struct sk_buff *skb, skb_tstamp_tx(skb, &shhwtstamps); } -void gem_ptp_init(struct net_device *dev) +void gem_ptp_init(struct net_device *netdev) { - struct macb *bp = netdev_priv(dev); + struct macb *bp = netdev_priv(netdev); bp->ptp_clock_info = gem_ptp_caps_template; @@ -334,7 +334,8 @@ void gem_ptp_init(struct net_device *dev) bp->tsu_rate = bp->ptp_info->get_tsu_rate(bp); bp->ptp_clock_info.max_adj = bp->ptp_info->get_ptp_max_adj(); gem_ptp_init_timer(bp); - bp->ptp_clock = ptp_clock_register(&bp->ptp_clock_info, &dev->dev); + gem_ptp_init_tsu(bp); + bp->ptp_clock = ptp_clock_register(&bp->ptp_clock_info, &netdev->dev); if (IS_ERR(bp->ptp_clock)) { pr_err("ptp clock register failed: %ld\n", PTR_ERR(bp->ptp_clock)); @@ -345,17 +346,13 @@ void gem_ptp_init(struct net_device *dev) return; } - spin_lock_init(&bp->tsu_clk_lock); - - gem_ptp_init_tsu(bp); - dev_info(&bp->pdev->dev, "%s ptp clock registered.\n", GEM_PTP_TIMER_NAME); } -void gem_ptp_remove(struct net_device *ndev) +void gem_ptp_remove(struct net_device *netdev) { - struct macb *bp = netdev_priv(ndev); + struct macb *bp = netdev_priv(netdev); if (bp->ptp_clock) { ptp_clock_unregister(bp->ptp_clock); @@ -378,10 +375,10 @@ static int gem_ptp_set_ts_mode(struct macb *bp, return 0; } -int gem_get_hwtst(struct net_device *dev, +int gem_get_hwtst(struct net_device *netdev, struct kernel_hwtstamp_config *tstamp_config) { - struct macb *bp = netdev_priv(dev); + struct macb *bp = netdev_priv(netdev); *tstamp_config = bp->tstamp_config; if (!macb_dma_ptp(bp)) @@ -402,13 +399,13 @@ static void gem_ptp_set_one_step_sync(struct macb *bp, u8 enable) macb_writel(bp, NCR, reg_val & ~MACB_BIT(OSSMODE)); } -int gem_set_hwtst(struct net_device *dev, +int gem_set_hwtst(struct net_device *netdev, struct kernel_hwtstamp_config *tstamp_config, struct netlink_ext_ack *extack) { enum macb_bd_control tx_bd_control = TSTAMP_DISABLED; enum macb_bd_control rx_bd_control = TSTAMP_DISABLED; - struct macb *bp = netdev_priv(dev); + struct macb *bp = netdev_priv(netdev); u32 regval; if (!macb_dma_ptp(bp)) diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c index 4c762229ce420f..f08de623e6f7c7 100644 --- a/drivers/net/ethernet/cortina/gemini.c +++ b/drivers/net/ethernet/cortina/gemini.c @@ -124,6 +124,7 @@ struct gemini_ethernet_port { unsigned int rx_coalesce_nsecs; struct sk_buff *rx_skb; unsigned int rx_frag_nr; + bool rx_dropping; unsigned int freeq_refill; struct gmac_txq txq[TX_QUEUE_NUM]; @@ -1439,7 +1440,8 @@ update_exit: return skb; } -static unsigned int gmac_rx(struct net_device *netdev, unsigned int budget) +static unsigned int gmac_rx(struct net_device *netdev, unsigned int budget, + unsigned int *freeq_consumed) { struct gemini_ethernet_port *port = netdev_priv(netdev); unsigned short m = (1 << port->rxq_order) - 1; @@ -1447,9 +1449,12 @@ static unsigned int gmac_rx(struct net_device *netdev, unsigned int budget) void __iomem *ptr_reg = port->rxq_rwptr; unsigned int frag_nr = port->rx_frag_nr; struct sk_buff *skb = port->rx_skb; + unsigned int consumed = 0; unsigned int frame_len, frag_len; struct gmac_rxdesc *rx = NULL; struct gmac_queue_page *gpage; + unsigned int received = 0; + bool dropping = port->rx_dropping; union gmac_rxdesc_0 word0; union gmac_rxdesc_1 word1; union gmac_rxdesc_3 word3; @@ -1471,6 +1476,7 @@ static unsigned int gmac_rx(struct net_device *netdev, unsigned int budget) w = rw.bits.wptr; while (budget && w != r) { + page = NULL; rx = port->rxq_ring + r; word0 = rx->word0; word1 = rx->word1; @@ -1479,11 +1485,22 @@ static unsigned int gmac_rx(struct net_device *netdev, unsigned int budget) r++; r &= m; + consumed++; frag_len = word0.bits.buffer_size; frame_len = word1.bits.byte_count; page_offs = mapping & ~PAGE_MASK; + if (word3.bits32 & SOF_BIT) { + if (skb) { + napi_free_frags(&port->napi); + port->stats.rx_dropped++; + skb = NULL; + frag_nr = 0; + } + dropping = false; + } + if (!mapping) { netdev_err(netdev, "rxq[%u]: HW BUG: zero DMA desc\n", r); @@ -1494,24 +1511,11 @@ static unsigned int gmac_rx(struct net_device *netdev, unsigned int budget) gpage = gmac_get_queue_page(geth, port, mapping + PAGE_SIZE); if (!gpage) { dev_err(geth->dev, "could not find mapping\n"); - port->stats.rx_dropped++; - if (skb) { - napi_free_frags(&port->napi); - skb = NULL; - frag_nr = 0; - } - continue; + goto err_drop; } page = gpage->page; if (word3.bits32 & SOF_BIT) { - if (skb) { - napi_free_frags(&port->napi); - port->stats.rx_dropped++; - skb = NULL; - frag_nr = 0; - } - skb = gmac_skb_if_good_frame(port, word0, frame_len); if (!skb) goto err_drop; @@ -1521,8 +1525,7 @@ static unsigned int gmac_rx(struct net_device *netdev, unsigned int budget) frag_nr = 0; } else if (!skb) { - put_page(page); - continue; + goto err_drop; } if (word3.bits32 & EOF_BIT) @@ -1545,9 +1548,8 @@ static unsigned int gmac_rx(struct net_device *netdev, unsigned int budget) napi_gro_frags(&port->napi); skb = NULL; frag_nr = 0; - --budget; } - continue; + goto next_desc; err_drop: if (skb) { @@ -1556,16 +1558,29 @@ err_drop: frag_nr = 0; } - if (mapping) + if (page) put_page(page); - port->stats.rx_dropped++; + if (!dropping) { + port->stats.rx_dropped++; + dropping = true; + } + +next_desc: + /* Final or single-descriptor fragment, advance things */ + if (word3.bits32 & EOF_BIT) { + budget--; + received++; + dropping = false; + } } port->rx_skb = skb; port->rx_frag_nr = frag_nr; + port->rx_dropping = dropping; + *freeq_consumed = consumed; writew(r, ptr_reg); - return budget; + return received; } static int gmac_napi_poll(struct napi_struct *napi, int budget) @@ -1573,26 +1588,27 @@ static int gmac_napi_poll(struct napi_struct *napi, int budget) struct gemini_ethernet_port *port = netdev_priv(napi->dev); struct gemini_ethernet *geth = port->geth; unsigned int freeq_threshold; + unsigned int freeq_consumed; unsigned int received; freeq_threshold = 1 << (geth->freeq_order - 1); u64_stats_update_begin(&port->rx_stats_syncp); - received = gmac_rx(napi->dev, budget); - if (received < budget) { - napi_gro_flush(napi, false); - napi_complete_done(napi, received); - gmac_enable_rx_irq(napi->dev, 1); + received = gmac_rx(napi->dev, budget, &freeq_consumed); + if (received < budget) ++port->rx_napi_exits; - } - port->freeq_refill += (budget - received); + u64_stats_update_end(&port->rx_stats_syncp); + + port->freeq_refill += freeq_consumed; if (port->freeq_refill > freeq_threshold) { port->freeq_refill -= freeq_threshold; geth_fill_freeq(geth, true); } - u64_stats_update_end(&port->rx_stats_syncp); + if (received < budget && napi_complete_done(napi, received)) + gmac_enable_rx_irq(napi->dev, 1); + return received; } @@ -1893,6 +1909,7 @@ static int gmac_stop(struct net_device *netdev) napi_disable(&port->napi); port->rx_skb = NULL; port->rx_frag_nr = 0; + port->rx_dropping = false; gmac_enable_irq(netdev, 0); gmac_cleanup_rxq(netdev); diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_mbox.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_mbox.c index 2784127327e644..6e67a6c9578e1f 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_mbox.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_mbox.c @@ -128,6 +128,7 @@ enum hinic_mbox_tx_status { #define SEQ_ID_START_VAL 0 #define SEQ_ID_MAX_VAL 42 +#define MBOX_LAST_SEG_MAX_LEN (MBOX_MAX_BUF_SZ - SEQ_ID_MAX_VAL * MBOX_SEG_LEN) #define NO_DMA_ATTRIBUTE_VAL 0 @@ -372,7 +373,8 @@ recv_pf_from_vf_mbox_handler(struct hinic_mbox_func_to_func *func_to_func, static bool check_mbox_seq_id_and_seg_len(struct hinic_recv_mbox *recv_mbox, u8 seq_id, u8 seg_len) { - if (seq_id > SEQ_ID_MAX_VAL || seg_len > MBOX_SEG_LEN) + if (seq_id > SEQ_ID_MAX_VAL || seg_len > MBOX_SEG_LEN || + (seq_id == SEQ_ID_MAX_VAL && seg_len > MBOX_LAST_SEG_MAX_LEN)) return false; if (seq_id == 0) { diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index ef1ce106f81b5e..04633103e3e610 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -1051,14 +1051,13 @@ int ice_init_hw(struct ice_hw *hw) hw->evb_veb = true; - /* init xarray for identifying scheduling nodes uniquely */ - xa_init_flags(&hw->port_info->sched_node_ids, XA_FLAGS_ALLOC); + xa_init_flags(&hw->sched_node_ids, XA_FLAGS_ALLOC); /* Query the allocated resources for Tx scheduler */ status = ice_sched_query_res_alloc(hw); if (status) { ice_debug(hw, ICE_DBG_SCHED, "Failed to get scheduler allocated resources\n"); - goto err_unroll_alloc; + goto err_unroll_xarray; } ice_sched_get_psm_clk_freq(hw); @@ -1146,6 +1145,8 @@ err_unroll_fltr_mgmt_struct: ice_cleanup_fltr_mgmt_struct(hw); err_unroll_sched: ice_sched_cleanup_all(hw); +err_unroll_xarray: + xa_destroy(&hw->sched_node_ids); err_unroll_alloc: devm_kfree(ice_hw_to_dev(hw), hw->port_info); err_unroll_cqinit: @@ -1186,6 +1187,8 @@ void ice_deinit_hw(struct ice_hw *hw) /* Clear VSI contexts if not already cleared */ ice_clear_all_vsi_ctx(hw); + + xa_destroy(&hw->sched_node_ids); } /** diff --git a/drivers/net/ethernet/intel/ice/ice_sched.c b/drivers/net/ethernet/intel/ice/ice_sched.c index fff0c1afdb4143..ffa18d86729a0d 100644 --- a/drivers/net/ethernet/intel/ice/ice_sched.c +++ b/drivers/net/ethernet/intel/ice/ice_sched.c @@ -371,7 +371,7 @@ void ice_free_sched_node(struct ice_port_info *pi, struct ice_sched_node *node) devm_kfree(ice_hw_to_dev(hw), node->children); kfree(node->name); - xa_erase(&pi->sched_node_ids, node->id); + xa_erase(&hw->sched_node_ids, node->id); devm_kfree(ice_hw_to_dev(hw), node); } @@ -977,7 +977,7 @@ ice_sched_add_elems(struct ice_port_info *pi, struct ice_sched_node *tc_node, if (!new_node->name) return -ENOMEM; - status = xa_alloc(&pi->sched_node_ids, &new_node->id, NULL, XA_LIMIT(0, UINT_MAX), + status = xa_alloc(&hw->sched_node_ids, &new_node->id, NULL, XA_LIMIT(0, UINT_MAX), GFP_KERNEL); if (status) { ice_debug(hw, ICE_DBG_SCHED, "xa_alloc failed for sched node status =%d\n", diff --git a/drivers/net/ethernet/intel/ice/ice_trace.h b/drivers/net/ethernet/intel/ice/ice_trace.h index 4f35ef8d6b299b..7568c917cdbe16 100644 --- a/drivers/net/ethernet/intel/ice/ice_trace.h +++ b/drivers/net/ethernet/intel/ice/ice_trace.h @@ -63,23 +63,33 @@ DECLARE_EVENT_CLASS(ice_rx_dim_template, TP_PROTO(struct ice_q_vector *q_vector, struct dim *dim), TP_ARGS(q_vector, dim), - TP_STRUCT__entry(__field(struct ice_q_vector *, q_vector) - __field(struct dim *, dim) + TP_STRUCT__entry(__field(u16, q_index) + __field(u8, state) + __field(u8, profile_ix) + __field(u8, tune_state) + __field(u8, steps_right) + __field(u8, steps_left) + __field(u8, tired) __string(devname, q_vector->rx.rx_ring->netdev->name)), - TP_fast_assign(__entry->q_vector = q_vector; - __entry->dim = dim; + TP_fast_assign(__entry->q_index = q_vector->rx.rx_ring->q_index; + __entry->state = dim->state; + __entry->profile_ix = dim->profile_ix; + __entry->tune_state = dim->tune_state; + __entry->steps_right = dim->steps_right; + __entry->steps_left = dim->steps_left; + __entry->tired = dim->tired; __assign_str(devname);), TP_printk("netdev: %s Rx-Q: %d dim-state: %d dim-profile: %d dim-tune: %d dim-st-right: %d dim-st-left: %d dim-tired: %d", __get_str(devname), - __entry->q_vector->rx.rx_ring->q_index, - __entry->dim->state, - __entry->dim->profile_ix, - __entry->dim->tune_state, - __entry->dim->steps_right, - __entry->dim->steps_left, - __entry->dim->tired) + __entry->q_index, + __entry->state, + __entry->profile_ix, + __entry->tune_state, + __entry->steps_right, + __entry->steps_left, + __entry->tired) ); DEFINE_EVENT(ice_rx_dim_template, ice_rx_dim_work, @@ -90,23 +100,33 @@ DEFINE_EVENT(ice_rx_dim_template, ice_rx_dim_work, DECLARE_EVENT_CLASS(ice_tx_dim_template, TP_PROTO(struct ice_q_vector *q_vector, struct dim *dim), TP_ARGS(q_vector, dim), - TP_STRUCT__entry(__field(struct ice_q_vector *, q_vector) - __field(struct dim *, dim) + TP_STRUCT__entry(__field(u16, q_index) + __field(u8, state) + __field(u8, profile_ix) + __field(u8, tune_state) + __field(u8, steps_right) + __field(u8, steps_left) + __field(u8, tired) __string(devname, q_vector->tx.tx_ring->netdev->name)), - TP_fast_assign(__entry->q_vector = q_vector; - __entry->dim = dim; + TP_fast_assign(__entry->q_index = q_vector->tx.tx_ring->q_index; + __entry->state = dim->state; + __entry->profile_ix = dim->profile_ix; + __entry->tune_state = dim->tune_state; + __entry->steps_right = dim->steps_right; + __entry->steps_left = dim->steps_left; + __entry->tired = dim->tired; __assign_str(devname);), TP_printk("netdev: %s Tx-Q: %d dim-state: %d dim-profile: %d dim-tune: %d dim-st-right: %d dim-st-left: %d dim-tired: %d", __get_str(devname), - __entry->q_vector->tx.tx_ring->q_index, - __entry->dim->state, - __entry->dim->profile_ix, - __entry->dim->tune_state, - __entry->dim->steps_right, - __entry->dim->steps_left, - __entry->dim->tired) + __entry->q_index, + __entry->state, + __entry->profile_ix, + __entry->tune_state, + __entry->steps_right, + __entry->steps_left, + __entry->tired) ); DEFINE_EVENT(ice_tx_dim_template, ice_tx_dim_work, diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h index d9a5c1aae7c232..cf147a21270712 100644 --- a/drivers/net/ethernet/intel/ice/ice_type.h +++ b/drivers/net/ethernet/intel/ice/ice_type.h @@ -765,7 +765,6 @@ struct ice_port_info { /* List contain profile ID(s) and other params per layer */ struct list_head rl_prof_list[ICE_AQC_TOPO_MAX_LEVEL_NUM]; struct ice_qos_cfg qos_cfg; - struct xarray sched_node_ids; u8 is_vf:1; u8 is_custom_tx_enabled:1; }; @@ -930,6 +929,7 @@ struct ice_hw { u8 sw_entry_point_layer; u16 max_children[ICE_AQC_TOPO_MAX_LEVEL_NUM]; struct list_head agg_list; /* lists all aggregator */ + struct xarray sched_node_ids; struct ice_vsi_ctx *vsi_ctx[ICE_MAX_VSI]; u8 evb_veb; /* true for VEB, false for VEPA */ diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c index 91ca75e454630f..81e83a98a8e2cf 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c +++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c @@ -3299,6 +3299,7 @@ static int idpf_rx_rsc(struct idpf_rx_queue *rxq, struct sk_buff *skb, struct libeth_rx_pt decoded) { u16 rsc_segments, rsc_seg_len; + u16 l3_start = 0; bool ipv4, ipv6; int len; @@ -3321,7 +3322,10 @@ static int idpf_rx_rsc(struct idpf_rx_queue *rxq, struct sk_buff *skb, NAPI_GRO_CB(skb)->count = rsc_segments; skb_shinfo(skb)->gso_size = rsc_seg_len; - skb_reset_network_header(skb); + if (unlikely(eth_type_vlan(skb->protocol))) + l3_start = VLAN_HLEN; + + skb_set_network_header(skb, l3_start); if (ipv4) { struct iphdr *ipv4h = ip_hdr(skb); @@ -3329,7 +3333,7 @@ static int idpf_rx_rsc(struct idpf_rx_queue *rxq, struct sk_buff *skb, skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4; /* Reset and set transport header offset in skb */ - skb_set_transport_header(skb, sizeof(struct iphdr)); + skb_set_transport_header(skb, l3_start + sizeof(struct iphdr)); len = skb->len - skb_transport_offset(skb); /* Compute the TCP pseudo header checksum*/ @@ -3339,7 +3343,7 @@ static int idpf_rx_rsc(struct idpf_rx_queue *rxq, struct sk_buff *skb, struct ipv6hdr *ipv6h = ipv6_hdr(skb); skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6; - skb_set_transport_header(skb, sizeof(struct ipv6hdr)); + skb_set_transport_header(skb, l3_start + sizeof(struct ipv6hdr)); len = skb->len - skb_transport_offset(skb); tcp_hdr(skb)->check = ~tcp_v6_check(len, &ipv6h->saddr, &ipv6h->daddr, 0); @@ -4145,6 +4149,26 @@ static void idpf_vport_intr_ena_irq_all(struct idpf_vport *vport, writel(rsrc->noirq_dyn_ctl_ena, rsrc->noirq_dyn_ctl); } +/** + * idpf_vport_intr_dis_dim_all - Disable DIM work for all q_vectors + * @rsrc: pointer to queue and vector resources + * + * The DIM works are embedded in the q_vector array that + * idpf_vport_intr_rel() frees, and the poll arms them after + * napi_complete_done() has already cleared NAPI_STATE_SCHED. Disable + * rather than just cancel, so that a poll tail still running past + * napi_disable() cannot queue them again behind the drain. + */ +static void idpf_vport_intr_dis_dim_all(struct idpf_q_vec_rsrc *rsrc) +{ + for (u16 v_idx = 0; v_idx < rsrc->num_q_vectors; v_idx++) { + struct idpf_q_vector *q_vector = &rsrc->q_vectors[v_idx]; + + disable_work_sync(&q_vector->tx_dim.work); + disable_work_sync(&q_vector->rx_dim.work); + } +} + /** * idpf_vport_intr_deinit - Release all vector associations for the vport * @vport: main vport structure @@ -4155,6 +4179,7 @@ void idpf_vport_intr_deinit(struct idpf_vport *vport, { idpf_vport_intr_dis_irq_all(rsrc); idpf_vport_intr_napi_dis_all(rsrc); + idpf_vport_intr_dis_dim_all(rsrc); idpf_vport_intr_napi_del_all(rsrc); idpf_vport_intr_rel_irq(vport, rsrc); } @@ -4235,7 +4260,6 @@ static void idpf_vport_intr_napi_ena_all(struct idpf_q_vec_rsrc *rsrc) for (u16 q_idx = 0; q_idx < rsrc->num_q_vectors; q_idx++) { struct idpf_q_vector *q_vector = &rsrc->q_vectors[q_idx]; - idpf_init_dim(q_vector); napi_enable(&q_vector->napi); } } @@ -4578,6 +4602,8 @@ int idpf_vport_intr_alloc(struct idpf_vport *vport, q_coal = &user_config->q_coalesce[v_idx]; q_vector->vport = vport; + idpf_init_dim(q_vector); + q_vector->tx_itr_value = q_coal->tx_coalesce_usecs; q_vector->tx_intr_mode = q_coal->tx_intr_mode; q_vector->tx_itr_idx = VIRTCHNL2_ITR_IDX_1; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mcs.c b/drivers/net/ethernet/marvell/octeontx2/af/mcs.c index a07e0b3d8d0006..211c10aa5880f2 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/mcs.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/mcs.c @@ -1417,6 +1417,16 @@ static int mcs_x2p_calibration(struct mcs *mcs) int i, err = 0; u64 val; + /* Clear any stale calibration state left by firmware/bootloader. + * Some firmware versions may leave MCSX_MIL_GLOBAL bit 5 set, + * preventing the hardware from detecting the rising edge needed to + * trigger X2P calibration. + */ + val = mcs_reg_read(mcs, MCSX_MIL_GLOBAL); + val &= ~BIT_ULL(5); + mcs_reg_write(mcs, MCSX_MIL_GLOBAL, val); + usleep_range(100, 200); + /* set X2P calibration */ val = mcs_reg_read(mcs, MCSX_MIL_GLOBAL); val |= BIT_ULL(5); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c index 74c041ab5280a3..937b085582b5f4 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c @@ -3468,6 +3468,8 @@ err: return ret; } +#define PCI_DEVID_OCTEONTX2_RVU_AFVF 0xA0F8 + static int rvu_enable_sriov(struct rvu *rvu) { struct pci_dev *pdev = rvu->pdev; @@ -3486,24 +3488,27 @@ static int rvu_enable_sriov(struct rvu *rvu) return 0; pci_read_config_word(pdev, pos + PCI_SRIOV_VF_DID, &rvu->vf_devid); - chans = rvu_get_num_lbk_chans(); - if (chans < 0) - return chans; - vfs = pci_sriov_get_totalvfs(pdev); - - /* Limit VFs in case we have more VFs than LBK channels available. */ - if (vfs > chans) - vfs = chans; - if (!vfs) return 0; - /* LBK channel number 63 is used for switching packets between - * CGX mapped VFs. Hence limit LBK pairs till 62 only. - */ - if (vfs > 62) - vfs = 62; + if (rvu->vf_devid == PCI_DEVID_OCTEONTX2_RVU_AFVF) { + chans = rvu_get_num_lbk_chans(); + if (chans < 0) + return chans; + + /* The last LBK channel is reserved for switching packets between + * CGX mapped VFs. Also, since LBK VFs work in pairs, limit VF + * count to available LBK channels minus 2. + */ + vfs = min(vfs, chans - 2); + + if (vfs <= 0) { + dev_warn(&pdev->dev, + "Skipping SRIOV enablement, not enough LBK channels available\n"); + return 0; + } + } /* Save VFs number for reference in VF interrupts handlers. * Since interrupts might start arriving during SRIOV enablement diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c index 22ee9967687963..904374baae6f32 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c @@ -829,19 +829,25 @@ static int rvu_dbg_rvu_pf_cgx_map_display(struct seq_file *filp, void *unused) int pf, domain, blkid; u8 cgx_id, lmac_id; u16 pcifunc; + u8 start; - domain = 2; + domain = pci_domain_nr(rvu->pdev->bus); mac_ops = get_mac_ops(rvu_first_cgx_pdata(rvu)); /* There can be no CGX devices at all */ if (!mac_ops) return 0; seq_printf(filp, "PCI dev\t\tRVU PF Func\tNIX block\t%s\tLMAC\tCHAN\n", mac_ops->name); + + /* All the PF devices are on contiguous PCI bus numbers, but the PF0(AF) + * may not start from 1 always. Hence get domain and bus from PCI device. + */ + start = rvu->pdev->bus->number; for (pf = 0; pf < rvu->hw->total_pfs; pf++) { if (!is_pf_cgxmapped(rvu, pf)) continue; - pdev = pci_get_domain_bus_and_slot(domain, pf + 1, 0); + pdev = pci_get_domain_bus_and_slot(domain, pf + start, 0); if (!pdev) continue; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c index 38554d51164e17..6f2e6bce164dec 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c @@ -2957,10 +2957,9 @@ static void npc_mcam_free_all_entries(struct rvu *rvu, struct npc_mcam *mcam, } } - /* Disable the entry */ - npc_enable_mcam_entry(rvu, mcam, blkaddr, index, false); - if (!cn20k_dft_rl) { + /* Disable the entry */ + npc_enable_mcam_entry(rvu, mcam, blkaddr, index, false); mcam->entry2pfvf_map[index] = NPC_MCAM_INVALID_MAP; /* Free the entry in bitmap */ npc_mcam_clear_bit(mcam, index); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/qos.c b/drivers/net/ethernet/marvell/octeontx2/nic/qos.c index 69c0911e28e915..f160b1618efa27 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/qos.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/qos.c @@ -235,13 +235,63 @@ static int otx2_qos_txschq_set_parent_topology(struct otx2_nic *pfvf, return rc; } +static int otx2_qos_reset_schq_topology(struct otx2_nic *pfvf, u16 lvl, + u16 schq) +{ + struct mbox *mbox = &pfvf->mbox; + struct nix_txschq_config *cfg; + int rc; + + if (lvl < NIX_TXSCH_LVL_TL4 || lvl >= NIX_TXSCH_LVL_TL1) + return 0; + + mutex_lock(&mbox->lock); + + cfg = otx2_mbox_alloc_msg_nix_txschq_cfg(mbox); + if (!cfg) { + mutex_unlock(&mbox->lock); + return -ENOMEM; + } + + cfg->lvl = lvl; + cfg->num_regs = 1; + + if (lvl == NIX_TXSCH_LVL_TL4) + cfg->reg[0] = NIX_AF_TL4X_TOPOLOGY(schq); + else if (lvl == NIX_TXSCH_LVL_TL3) + cfg->reg[0] = NIX_AF_TL3X_TOPOLOGY(schq); + else if (lvl == NIX_TXSCH_LVL_TL2) + cfg->reg[0] = NIX_AF_TL2X_TOPOLOGY(schq); + + cfg->regval[0] = 0; + + rc = otx2_sync_mbox_msg(mbox); + + mutex_unlock(&mbox->lock); + + return rc; +} + +static void otx2_qos_free_hw_schq(struct otx2_nic *pfvf, u16 lvl, u16 schq) +{ + int err; + + err = otx2_qos_reset_schq_topology(pfvf, lvl, schq); + if (err) + netdev_warn(pfvf->netdev, + "QoS: failed to reset topology for schq %u at level %u: %d\n", + schq, lvl, err); + + otx2_txschq_free_one(pfvf, lvl, schq); +} + static void otx2_qos_free_hw_node_schq(struct otx2_nic *pfvf, struct otx2_qos_node *parent) { struct otx2_qos_node *node; list_for_each_entry_reverse(node, &parent->child_schq_list, list) - otx2_txschq_free_one(pfvf, node->level, node->schq); + otx2_qos_free_hw_schq(pfvf, node->level, node->schq); } static void otx2_qos_free_hw_node(struct otx2_nic *pfvf, @@ -252,7 +302,7 @@ static void otx2_qos_free_hw_node(struct otx2_nic *pfvf, list_for_each_entry_safe(node, tmp, &parent->child_list, list) { otx2_qos_free_hw_node(pfvf, node); otx2_qos_free_hw_node_schq(pfvf, node); - otx2_txschq_free_one(pfvf, node->level, node->schq); + otx2_qos_free_hw_schq(pfvf, node->level, node->schq); } } @@ -266,7 +316,7 @@ static void otx2_qos_free_hw_cfg(struct otx2_nic *pfvf, otx2_qos_free_hw_node_schq(pfvf, node); /* free node hw mappings */ - otx2_txschq_free_one(pfvf, node->level, node->schq); + otx2_qos_free_hw_schq(pfvf, node->level, node->schq); mutex_unlock(&pfvf->qos.qos_lock); } @@ -913,7 +963,7 @@ static void otx2_qos_free_cfg(struct otx2_nic *pfvf, struct otx2_qos_cfg *cfg) for (lvl = 0; lvl < NIX_TXSCH_LVL_CNT; lvl++) { for (idx = 0; idx < cfg->schq[lvl]; idx++) { schq = cfg->schq_list[lvl][idx]; - otx2_txschq_free_one(pfvf, lvl, schq); + otx2_qos_free_hw_schq(pfvf, lvl, schq); } } @@ -921,7 +971,7 @@ static void otx2_qos_free_cfg(struct otx2_nic *pfvf, struct otx2_qos_cfg *cfg) for (idx = 0; idx < cfg->schq_contig[lvl]; idx++) { if (cfg->schq_index_used[lvl][idx]) { schq = cfg->schq_contig_list[lvl][idx]; - otx2_txschq_free_one(pfvf, lvl, schq); + otx2_qos_free_hw_schq(pfvf, lvl, schq); } } } diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index 351444fb487161..b2473df74dff06 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -4827,7 +4827,7 @@ static int mtk_add_mac(struct mtk_eth *eth, struct device_node *np) phy_interface_t phy_mode; struct phylink *phylink; struct mtk_mac *mac; - int id, err; + int id, err, i; int txqs = 1; u32 val; @@ -4906,8 +4906,8 @@ static int mtk_add_mac(struct mtk_eth *eth, struct device_node *np) mac->phylink_config.type = PHYLINK_NETDEV; mac->phylink_config.mac_capabilities = MAC_ASYM_PAUSE | MAC_SYM_PAUSE | MAC_10 | MAC_100 | MAC_1000 | MAC_2500FD; - mac->phylink_config.lpi_capabilities = MAC_100FD | MAC_1000FD | - MAC_2500FD; + /* LPI above 1 Gbps is not supported */ + mac->phylink_config.lpi_capabilities = MAC_100FD | MAC_1000FD; mac->phylink_config.lpi_timer_default = 1000; /* MT7623 gmac0 is now missing its speed-specific PLL configuration @@ -4965,6 +4965,18 @@ static int mtk_add_mac(struct mtk_eth *eth, struct device_node *np) __set_bit(PHY_INTERFACE_MODE_INTERNAL, mac->phylink_config.supported_interfaces); + /* LPI wake-up timing is only verified on MTK_GMAC_EEE SoCs */ + if (MTK_HAS_CAPS(eth->soc->caps, MTK_GMAC_EEE)) { + phy_interface_copy(mac->phylink_config.lpi_interfaces, + mac->phylink_config.supported_interfaces); + __clear_bit(PHY_INTERFACE_MODE_2500BASEX, + mac->phylink_config.lpi_interfaces); + for (i = 0; i < PHY_INTERFACE_MODE_MAX; i++) + if (mtk_interface_mode_is_xgmii(eth, i)) + __clear_bit(i, + mac->phylink_config.lpi_interfaces); + } + phylink = phylink_create(&mac->phylink_config, of_fwnode_handle(mac->of_node), phy_mode, mac_ops); diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h index 0168e2fbc6197a..88a9b3b23bea5e 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h @@ -994,6 +994,7 @@ enum mkt_eth_capabilities { MTK_U3_COPHY_V2_BIT, MTK_SRAM_BIT, MTK_36BIT_DMA_BIT, + MTK_GMAC_EEE_BIT, /* MUX BITS*/ MTK_ETH_MUX_GDM1_TO_GMAC1_ESW_BIT, @@ -1034,6 +1035,7 @@ enum mkt_eth_capabilities { #define MTK_U3_COPHY_V2 BIT_ULL(MTK_U3_COPHY_V2_BIT) #define MTK_SRAM BIT_ULL(MTK_SRAM_BIT) #define MTK_36BIT_DMA BIT_ULL(MTK_36BIT_DMA_BIT) +#define MTK_GMAC_EEE BIT_ULL(MTK_GMAC_EEE_BIT) #define MTK_ETH_MUX_GDM1_TO_GMAC1_ESW \ BIT_ULL(MTK_ETH_MUX_GDM1_TO_GMAC1_ESW_BIT) @@ -1117,7 +1119,7 @@ enum mkt_eth_capabilities { #define MT7981_CAPS (MTK_GMAC1_SGMII | MTK_GMAC2_SGMII | MTK_GMAC2_GEPHY | \ MTK_MUX_GMAC12_TO_GEPHY_SGMII | MTK_QDMA | \ MTK_MUX_U3_GMAC2_TO_QPHY | MTK_U3_COPHY_V2 | \ - MTK_RSTCTRL_PPE1 | MTK_SRAM) + MTK_RSTCTRL_PPE1 | MTK_SRAM | MTK_GMAC_EEE) #define MT7986_CAPS (MTK_GMAC1_SGMII | MTK_GMAC2_SGMII | \ MTK_MUX_GMAC12_TO_GEPHY_SGMII | MTK_QDMA | \ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c index 6049ccf475bc4d..a4c096a4fed258 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c @@ -557,6 +557,7 @@ int mlx5e_set_fec_mode(struct mlx5_core_dev *dev, u16 fec_policy) u32 in[MLX5_ST_SZ_DW(pplm_reg)] = {}; int sz = MLX5_ST_SZ_BYTES(pplm_reg); u16 fec_policy_auto = 0; + bool fec_set = false; int err; int i; @@ -569,9 +570,6 @@ int mlx5e_set_fec_mode(struct mlx5_core_dev *dev, u16 fec_policy) if (fec_policy >= (1 << MLX5E_FEC_LLRS_272_257_1) && !fec_50g_per_lane) return -EOPNOTSUPP; - if (fec_policy && !mlx5e_fec_in_caps(dev, fec_policy)) - return -EOPNOTSUPP; - MLX5_SET(pplm_reg, in, local_port, 1); err = mlx5_core_access_reg(dev, in, sz, out, sz, MLX5_REG_PPLM, 0, 0); if (err) @@ -591,12 +589,17 @@ int mlx5e_set_fec_mode(struct mlx5_core_dev *dev, u16 fec_policy) mlx5e_get_fec_cap_field(out, &fec_caps, i); /* policy supported for link speed */ - if (fec_caps & conf_fec) + if (fec_caps & conf_fec) { mlx5e_fec_admin_field(out, &conf_fec, 1, i); - else - /* set FEC to auto*/ + fec_set = true; + } else { + /* set FEC to auto */ mlx5e_fec_admin_field(out, &fec_policy_auto, 1, i); + } } + if (fec_policy && !fec_set) + return -EOPNOTSUPP; + return mlx5_core_access_reg(dev, out, sz, out, sz, MLX5_REG_PPLM, 0, 1); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port.h b/drivers/net/ethernet/mellanox/mlx5/core/en/port.h index fa2283dd383b02..53dbdf77bccea1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/port.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port.h @@ -66,4 +66,8 @@ enum { MLX5E_FEC_LLRS_272_257_1 = 9, }; +#define MLX5E_FEC_RS_MASK (BIT(MLX5E_FEC_RS_528_514) | \ + BIT(MLX5E_FEC_RS_544_514_INTERLEAVED_QUAD) | \ + BIT(MLX5E_FEC_RS_544_514)) + #endif diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.c index 89490f687a9c69..93c62d3f3e5bd3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.c @@ -311,12 +311,15 @@ err_alloc: static void sample_restore_put(struct mlx5e_tc_psample *tc_psample, struct mlx5e_sample_restore *restore) { + bool last; + mutex_lock(&tc_psample->restore_lock); - if (--restore->count == 0) + last = --restore->count == 0; + if (last) hash_del(&restore->hlist); mutex_unlock(&tc_psample->restore_lock); - if (!restore->count) { + if (last) { mlx5_del_flow_rules(restore->rule); mlx5_modify_header_dealloc(tc_psample->esw->dev, restore->modify_hdr); kfree(restore); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c index 00e706e1ede111..741f75b5bfec53 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c @@ -148,7 +148,7 @@ static int mlx5e_dcbnl_ieee_getets(struct net_device *netdev, if (err) return err; - if (ets->tc_tx_bw[i] < MLX5E_MAX_BW_ALLOC && + if (priv->dcbx.tc_tsa[i] == IEEE_8021QAZ_TSA_ETS && tc_group[i] == (MLX5E_LOWEST_PRIO_GROUP + 1)) is_zero_bw_ets_tc = true; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 112926d07634d7..3ed59ced0407aa 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -1002,9 +1002,9 @@ static u32 pplm2ethtool_fec(u_long fec_mode, unsigned long size) return 0; } -#define MLX5E_ADVERTISE_SUPPORTED_FEC(mlx5_fec, ethtool_fec) \ +#define MLX5E_ADVERTISE_SUPPORTED_FEC(fec_mask, ethtool_fec) \ do { \ - if (mlx5e_fec_in_caps(dev, 1 << (mlx5_fec))) \ + if (mlx5e_fec_in_caps(dev, fec_mask)) \ __set_bit(ethtool_fec, \ link_ksettings->link_modes.supported);\ } while (0) @@ -1013,6 +1013,7 @@ static const u32 pplm_fec_2_ethtool_linkmodes[] = { [MLX5E_FEC_NOFEC] = ETHTOOL_LINK_MODE_FEC_NONE_BIT, [MLX5E_FEC_FIRECODE] = ETHTOOL_LINK_MODE_FEC_BASER_BIT, [MLX5E_FEC_RS_528_514] = ETHTOOL_LINK_MODE_FEC_RS_BIT, + [MLX5E_FEC_RS_544_514_INTERLEAVED_QUAD] = ETHTOOL_LINK_MODE_FEC_RS_BIT, [MLX5E_FEC_RS_544_514] = ETHTOOL_LINK_MODE_FEC_RS_BIT, [MLX5E_FEC_LLRS_272_257_1] = ETHTOOL_LINK_MODE_FEC_LLRS_BIT, }; @@ -1029,13 +1030,13 @@ static int get_fec_supported_advertised(struct mlx5_core_dev *dev, if (err) return (err == -EOPNOTSUPP) ? 0 : err; - MLX5E_ADVERTISE_SUPPORTED_FEC(MLX5E_FEC_NOFEC, + MLX5E_ADVERTISE_SUPPORTED_FEC(BIT(MLX5E_FEC_NOFEC), ETHTOOL_LINK_MODE_FEC_NONE_BIT); - MLX5E_ADVERTISE_SUPPORTED_FEC(MLX5E_FEC_FIRECODE, + MLX5E_ADVERTISE_SUPPORTED_FEC(BIT(MLX5E_FEC_FIRECODE), ETHTOOL_LINK_MODE_FEC_BASER_BIT); - MLX5E_ADVERTISE_SUPPORTED_FEC(MLX5E_FEC_RS_528_514, + MLX5E_ADVERTISE_SUPPORTED_FEC(MLX5E_FEC_RS_MASK, ETHTOOL_LINK_MODE_FEC_RS_BIT); - MLX5E_ADVERTISE_SUPPORTED_FEC(MLX5E_FEC_LLRS_272_257_1, + MLX5E_ADVERTISE_SUPPORTED_FEC(BIT(MLX5E_FEC_LLRS_272_257_1), ETHTOOL_LINK_MODE_FEC_LLRS_BIT); active_fec_long = active_fec; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 3d544fe4e6f73b..eb3160bfbb29de 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -56,7 +56,6 @@ #include "lib/vxlan.h" #define CREATE_TRACE_POINTS #include "diag/en_rep_tracepoint.h" -#include "diag/reporter_vnic.h" #include "en_accel/ipsec.h" #include "en/tc/int_port.h" #include "en/ptp.h" @@ -1435,51 +1434,6 @@ static unsigned int mlx5e_ul_rep_stats_grps_num(struct mlx5e_priv *priv) return ARRAY_SIZE(mlx5e_ul_rep_stats_grps); } -static int -mlx5e_rep_vnic_reporter_diagnose(struct devlink_health_reporter *reporter, - struct devlink_fmsg *fmsg, - struct netlink_ext_ack *extack) -{ - struct mlx5e_rep_priv *rpriv = devlink_health_reporter_priv(reporter); - struct mlx5_eswitch_rep *rep = rpriv->rep; - - mlx5_reporter_vnic_diagnose_counters(rep->esw->dev, fmsg, rep->vport, - true); - return 0; -} - -static const struct devlink_health_reporter_ops mlx5_rep_vnic_reporter_ops = { - .name = "vnic", - .diagnose = mlx5e_rep_vnic_reporter_diagnose, -}; - -static void mlx5e_rep_vnic_reporter_create(struct mlx5e_priv *priv, - struct devlink_port *dl_port) -{ - struct mlx5e_rep_priv *rpriv = priv->ppriv; - struct devlink_health_reporter *reporter; - - reporter = devl_port_health_reporter_create(dl_port, - &mlx5_rep_vnic_reporter_ops, - rpriv); - if (IS_ERR(reporter)) { - mlx5_core_err(priv->mdev, - "Failed to create representor vnic reporter, err = %pe\n", - reporter); - return; - } - - rpriv->rep_vnic_reporter = reporter; -} - -static void mlx5e_rep_vnic_reporter_destroy(struct mlx5e_priv *priv) -{ - struct mlx5e_rep_priv *rpriv = priv->ppriv; - - if (!IS_ERR_OR_NULL(rpriv->rep_vnic_reporter)) - devl_health_reporter_destroy(rpriv->rep_vnic_reporter); -} - static const struct mlx5e_profile mlx5e_rep_profile = { .init = mlx5e_init_rep, .cleanup = mlx5e_cleanup_rep, @@ -1603,10 +1557,8 @@ mlx5e_vport_vf_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep) dl_port = mlx5_esw_offloads_devlink_port(dev->priv.eswitch, rpriv->rep->vport); - if (!IS_ERR(dl_port)) { + if (!IS_ERR(dl_port)) SET_NETDEV_DEVLINK_PORT(netdev, dl_port); - mlx5e_rep_vnic_reporter_create(priv, dl_port); - } err = register_netdev(netdev); if (err) { @@ -1619,7 +1571,6 @@ mlx5e_vport_vf_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep) return 0; err_detach_netdev: - mlx5e_rep_vnic_reporter_destroy(priv); mlx5e_detach_netdev(netdev_priv(netdev)); err_cleanup_profile: priv->profile->cleanup(priv); @@ -1677,7 +1628,6 @@ mlx5e_vport_rep_unload(struct mlx5_eswitch_rep *rep) } unregister_netdev(netdev); - mlx5e_rep_vnic_reporter_destroy(priv); mlx5e_detach_netdev(priv); priv->profile->cleanup(priv); mlx5e_destroy_netdev(netdev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h index 70640fa1ad7bc0..bcd7b4e814d061 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h @@ -118,7 +118,6 @@ struct mlx5e_rep_priv { struct rtnl_link_stats64 prev_vf_vport_stats; struct mlx5_flow_handle *send_to_vport_meta_rule; struct rhashtable tc_ht; - struct devlink_health_reporter *rep_vnic_reporter; }; static inline diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c index e7e6db7f6bf175..cd94bb44f6ab0f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c @@ -1199,50 +1199,39 @@ void mlx5e_stats_rmon_get(struct mlx5e_priv *priv, void mlx5e_stats_ts_get(struct mlx5e_priv *priv, struct ethtool_ts_stats *ts_stats) { - int i, j; + u16 nch = mlx5e_stats_nch_read(priv); + int i, tc; - mutex_lock(&priv->state_lock); + ts_stats->pkts = 0; - if (priv->tx_ptp_opened) { - struct mlx5e_ptp *ptp = priv->channels.ptp; + for (i = 0; i < nch; i++) { + struct mlx5e_channel_stats *channel_stats = + priv->channel_stats[i]; - ts_stats->pkts = 0; + for (tc = 0; tc < priv->max_opened_tc; tc++) + ts_stats->pkts += channel_stats->sq[tc].timestamps; + } + + /* Accumulate DMA and port timestamp counters so values stay monotonic + * across channel teardown and mode switches. + */ + if (priv->tx_ptp_opened) { + /* Err and Lost stats are only relevant for port timestamping, + * as the DMA layer will always successfully timestamp packets. + */ ts_stats->err = 0; ts_stats->lost = 0; - if (!ptp) - goto out; - - /* Aggregate stats across all TCs */ - for (i = 0; i < ptp->num_tc; i++) { + for (tc = 0; tc < priv->max_opened_tc; tc++) { struct mlx5e_ptp_cq_stats *stats = - ptp->ptpsq[i].cq_stats; + &priv->ptp_stats.cq[tc]; ts_stats->pkts += stats->cqe; ts_stats->err += stats->abort + stats->err_cqe + - stats->late_cqe; + stats->late_cqe; ts_stats->lost += stats->lost_cqe; } - } else { - /* DMA layer will always successfully timestamp packets. Other - * counters do not make sense for this layer. - */ - ts_stats->pkts = 0; - - /* Aggregate stats across all SQs */ - for (j = 0; j < priv->channels.num; j++) { - struct mlx5e_channel *c = priv->channels.c[j]; - - for (i = 0; i < c->num_tc; i++) { - struct mlx5e_sq_stats *stats = c->sq[i].stats; - - ts_stats->pkts += stats->timestamps; - } - } } - -out: - mutex_unlock(&priv->state_lock); } #define PPORT_PHY_LAYER_OFF(c) \ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c index 6e50311faa27f8..2e7eac4bca3ddd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c @@ -4,6 +4,26 @@ #include #include "eswitch.h" #include "devlink.h" +#include "diag/reporter_vnic.h" + +static int +mlx5_esw_rep_vnic_reporter_diagnose(struct devlink_health_reporter *reporter, + struct devlink_fmsg *fmsg, + struct netlink_ext_ack *extack) +{ + struct mlx5_vport *vport = devlink_health_reporter_priv(reporter); + + mlx5_reporter_vnic_diagnose_counters(vport->dev, fmsg, vport->vport, + true); + + return 0; +} + +static const +struct devlink_health_reporter_ops mlx5_esw_rep_vnic_reporter_ops = { + .name = "vnic", + .diagnose = mlx5_esw_rep_vnic_reporter_diagnose, +}; static void mlx5_esw_get_port_parent_id(struct mlx5_core_dev *dev, struct netdev_phys_item_id *ppid) @@ -217,6 +237,7 @@ static void mlx5_esw_devlink_port_res_unregister(struct devlink_port *dl_port) int mlx5_esw_offloads_devlink_port_register(struct mlx5_eswitch *esw, struct mlx5_vport *vport) { + struct devlink_health_reporter *reporter; struct mlx5_core_dev *dev = esw->dev; const struct devlink_port_ops *ops; struct mlx5_devlink_port *dl_port; @@ -252,6 +273,16 @@ int mlx5_esw_offloads_devlink_port_register(struct mlx5_eswitch *esw, struct mlx mlx5_core_dbg(dev, "Failed to register port resources: %d\n", err); + reporter = devl_port_health_reporter_create( + &dl_port->dl_port, &mlx5_esw_rep_vnic_reporter_ops, + vport); + if (IS_ERR(reporter)) + mlx5_core_err(dev, + "Failed to create vnic health reporter for vport %d: %pe\n", + vport_num, reporter); + else + dl_port->vnic_reporter = reporter; + return 0; rate_err: @@ -266,6 +297,12 @@ void mlx5_esw_offloads_devlink_port_unregister(struct mlx5_vport *vport) if (!vport->dl_port) return; dl_port = vport->dl_port; + + if (dl_port->vnic_reporter) { + devl_health_reporter_destroy(dl_port->vnic_reporter); + dl_port->vnic_reporter = NULL; + } + mlx5_esw_devlink_port_res_unregister(&dl_port->dl_port); mlx5_esw_qos_vport_update_parent(vport, NULL, NULL); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index a0e2ca87b8d8fd..eadc44119b1f46 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1040,13 +1040,19 @@ void mlx5_esw_vport_disable(struct mlx5_eswitch *esw, struct mlx5_vport *vport) (vport->info.ipsec_crypto_enabled || vport->info.ipsec_packet_enabled)) esw->enabled_ipsec_vf_count--; + /* Clear rx-mode before esw_vport_change_handle_locked(): on + * MLX5_VPORT_PROMISC_CHANGE it calls esw_update_vport_mc_promisc() + * when vport->allmulti_rule is set, repopulating mc_list with FDB + * rules that dangle once the FDB is destroyed. NULL allmulti_rule + * here skips that path. + */ + esw_apply_vport_rx_mode(esw, vport, false, false); /* We don't assume VFs will cleanup after themselves. * Calling vport change handler while vport is disabled will cleanup * the vport resources. */ esw_vport_change_handle_locked(vport); vport->enabled_events = 0; - esw_apply_vport_rx_mode(esw, vport, false, false); esw_vport_cleanup(esw, vport); esw->enabled_vports--; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index fea72b1dedab90..e8817d45763a6e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -189,6 +189,7 @@ struct mlx5_vport; struct mlx5_devlink_port { struct devlink_port dl_port; struct mlx5_vport *vport; + struct devlink_health_reporter *vnic_reporter; }; static inline void mlx5_devlink_port_init(struct mlx5_devlink_port *dl_port, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c index 19f65d4c4def98..d43f0736015963 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c @@ -163,12 +163,15 @@ void mlx5_eswitch_termtbl_put(struct mlx5_eswitch *esw, struct mlx5_termtbl_handle *tt) { + bool last; + mutex_lock(&esw->offloads.termtbl_mutex); - if (--tt->ref_count == 0) + last = (--tt->ref_count == 0); + if (last) hash_del(&tt->termtbl_hlist); mutex_unlock(&esw->offloads.termtbl_mutex); - if (!tt->ref_count) { + if (last) { mlx5_del_flow_rules(tt->rule); mlx5_destroy_flow_table(tt->termtbl); kfree(tt); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c index 2285c889c215e4..c655f6e32e9b07 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c @@ -63,14 +63,15 @@ static int get_port_sel_mode(enum mlx5_lag_mode mode, unsigned long flags) return MLX5_LAG_PORT_SELECT_MODE_QUEUE_AFFINITY; } -static u8 lag_active_port_bits(struct mlx5_lag *ldev) +static u8 lag_active_port_bits(struct mlx5_lag *ldev, + struct lag_tracker *tracker) { u8 enabled_ports[MLX5_MAX_PORTS] = {}; u8 active_port = 0; int num_enabled; int idx; - mlx5_infer_tx_enabled(&ldev->tracker, ldev, enabled_ports, + mlx5_infer_tx_enabled(tracker, ldev, enabled_ports, &num_enabled); for (idx = 0; idx < num_enabled; idx++) active_port |= BIT_MASK(enabled_ports[idx]); @@ -79,7 +80,8 @@ static u8 lag_active_port_bits(struct mlx5_lag *ldev) } static int mlx5_cmd_create_lag(struct mlx5_core_dev *dev, struct mlx5_lag *ldev, - int mode, unsigned long flags) + struct lag_tracker *tracker, int mode, + unsigned long flags) { bool fdb_sel_mode = test_bit(MLX5_LAG_MODE_FLAG_FDB_SEL_MODE_NATIVE, &flags); @@ -108,7 +110,7 @@ static int mlx5_cmd_create_lag(struct mlx5_core_dev *dev, struct mlx5_lag *ldev, break; MLX5_SET(lagc, lag_ctx, active_port, - lag_active_port_bits(mlx5_lag_dev(dev))); + lag_active_port_bits(ldev, tracker)); break; default: break; @@ -787,7 +789,8 @@ static int mlx5_cmd_modify_active_port(struct mlx5_core_dev *dev, u8 ports) return mlx5_cmd_exec_in(dev, modify_lag, in); } -static int _mlx5_modify_lag(struct mlx5_lag *ldev, u8 *ports) +static int _mlx5_modify_lag(struct mlx5_lag *ldev, + struct lag_tracker *tracker, u8 *ports) { int idx = mlx5_lag_get_dev_index_by_seq(ldev, MLX5_LAG_P1); struct mlx5_core_dev *dev0; @@ -804,7 +807,7 @@ static int _mlx5_modify_lag(struct mlx5_lag *ldev, u8 *ports) !MLX5_CAP_PORT_SELECTION(dev0, port_select_flow_table_bypass)) return ret; - active_ports = lag_active_port_bits(ldev); + active_ports = lag_active_port_bits(ldev, tracker); return mlx5_cmd_modify_active_port(dev0, active_ports); } @@ -868,7 +871,7 @@ void mlx5_modify_lag(struct mlx5_lag *ldev, idx = i * ldev->buckets + j; if (ports[idx] == ldev->v2p_map[idx]) continue; - err = _mlx5_modify_lag(ldev, ports); + err = _mlx5_modify_lag(ldev, tracker, ports); if (err) { mlx5_core_err(dev0, "Failed to modify LAG (%d)\n", @@ -976,7 +979,7 @@ static int mlx5_create_lag(struct mlx5_lag *ldev, mlx5_core_info(dev0, "shared_fdb:%d mode:%s\n", shared_fdb, mlx5_get_str_port_sel_mode(mode, flags)); - err = mlx5_cmd_create_lag(dev0, ldev, mode, flags); + err = mlx5_cmd_create_lag(dev0, ldev, tracker, mode, flags); if (err) { mlx5_core_err(dev0, "Failed to create LAG (%d)\n", diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c index 9939749c47bcc3..9c5862f4e16a35 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c @@ -572,6 +572,38 @@ mlxsw_sp1_ptp_unmatched_remove(struct mlxsw_sp *mlxsw_sp, mlxsw_sp1_ptp_unmatched_ht_params); } +/* mlxsw_sp1_ptp_packet_finish() is reached both from the NAPI poll context + * (mlxsw_sp1_ptp_got_packet(), mlxsw_sp1_ptp_got_piece() and + * mlxsw_sp1_packet_timestamp()) and from process context, by way of the GC + * workqueue (mlxsw_sp1_ptp_ht_gc_collect() -> + * mlxsw_sp1_ptp_unmatched_finish()). + * + * mlxsw_sp_rx_listener_no_mark_func() ends in napi_gro_receive(), using the + * NAPI pointer that was placed in the SKB control block when the trapped + * packet was received in the NAPI context. That pointer may only be used + * from its own poll context, which this call site cannot guarantee. + * + * netif_receive_skb(), unlike napi_gro_receive(), can be called from outside + * of the NAPI instance's poll context. RX stats accounting and the skb->dev + * assignment are still preserved; the only change is the delivery call. + */ +static void mlxsw_sp1_ptp_rx_finish(struct mlxsw_sp_port *mlxsw_sp_port, + struct sk_buff *skb) +{ + struct mlxsw_sp_port_pcpu_stats *pcpu_stats; + + skb->dev = mlxsw_sp_port->dev; + + pcpu_stats = this_cpu_ptr(mlxsw_sp_port->pcpu_stats); + u64_stats_update_begin(&pcpu_stats->syncp); + pcpu_stats->rx_packets++; + pcpu_stats->rx_bytes += skb->len; + u64_stats_update_end(&pcpu_stats->syncp); + + skb->protocol = eth_type_trans(skb, skb->dev); + netif_receive_skb(skb); +} + /* This function is called in the following scenarios: * * 1) When a packet is matched with its timestamp. @@ -600,7 +632,7 @@ static void mlxsw_sp1_ptp_packet_finish(struct mlxsw_sp *mlxsw_sp, if (ingress) { if (hwtstamps) *skb_hwtstamps(skb) = *hwtstamps; - mlxsw_sp_rx_listener_no_mark_func(skb, local_port, mlxsw_sp); + mlxsw_sp1_ptp_rx_finish(mlxsw_sp_port, skb); } else { /* skb_tstamp_tx() allows hwtstamps to be NULL. */ skb_tstamp_tx(skb, hwtstamps); diff --git a/drivers/net/ethernet/micrel/ks8851_common.c b/drivers/net/ethernet/micrel/ks8851_common.c index 4afbb40bc0e4a6..d49f281c786763 100644 --- a/drivers/net/ethernet/micrel/ks8851_common.c +++ b/drivers/net/ethernet/micrel/ks8851_common.c @@ -143,9 +143,6 @@ static int ks8851_write_mac_addr(struct net_device *dev) ks8851_wrreg16(ks, KS_MAR(i), val); } - if (!netif_running(dev)) - ks8851_set_powermode(ks, PMECR_PM_SOFTDOWN); - ks8851_unlock(ks); return 0; @@ -478,8 +475,7 @@ static int ks8851_net_open(struct net_device *dev) * @dev: The device being closed. * * Called to close down a network device which has been active. Cancel any - * work, shutdown the RX and TX process and then place the chip into a low - * power state whilst it is not being used. + * work and shutdown the RX and TX process. */ static int ks8851_net_stop(struct net_device *dev) { @@ -506,8 +502,6 @@ static int ks8851_net_stop(struct net_device *dev) /* shutdown TX process */ ks8851_wrreg16(ks, KS_TXCR, 0x0000); - /* set powermode to soft power down to save power */ - ks8851_set_powermode(ks, PMECR_PM_SOFTDOWN); ks8851_unlock(ks); /* ensure any queued tx buffers are dumped */ diff --git a/drivers/net/ethernet/microsoft/mana/mana_bpf.c b/drivers/net/ethernet/microsoft/mana/mana_bpf.c index 53308e139cbe91..5c9961ee9747ab 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_bpf.c +++ b/drivers/net/ethernet/microsoft/mana/mana_bpf.c @@ -208,6 +208,7 @@ static int mana_xdp_set(struct net_device *ndev, struct bpf_prog *prog, if (err) { NL_SET_ERR_MSG_MOD(extack, "XDP: Insufficient memory for tx/rx re-config"); + apc->bpf_prog = old_prog; return err; } diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index 92bb55935c1c4e..8fb29dcddf8e2e 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -2756,6 +2756,10 @@ static int mana_alloc_rx_wqe(struct mana_port_context *apc, *cq_size += COMP_ENTRY_SIZE; } + /* Reserve an extra slot for Fence completion + * event (CQE_RX_OBJECT_FENCE) in case RX CQ is full. + */ + *cq_size += COMP_ENTRY_SIZE; return 0; } @@ -2850,7 +2854,7 @@ static struct mana_rxq *mana_create_rxq(struct mana_port_context *apc, goto out; rq_size = MANA_PAGE_ALIGN(rq_size); - cq_size = MANA_PAGE_ALIGN(cq_size); + cq_size = MANA_PAGE_ALIGN(roundup_pow_of_two(cq_size)); /* Create RQ */ memset(&spec, 0, sizeof(spec)); @@ -3728,7 +3732,8 @@ static void mana_rdma_service_handle(struct work_struct *work) struct device *dev = gd->gdma_context->dev; int ret; - if (READ_ONCE(gd->rdma_teardown)) + /* Pairs with the smp_store_release() in mana_rdma_probe(). */ + if (smp_load_acquire(&gd->rdma_teardown)) goto out; switch (serv_work->event) { @@ -4024,6 +4029,21 @@ int mana_rdma_probe(struct gdma_dev *gd) if (err) return err; + /* Clear the state left by a previous mana_rdma_remove() so servicing + * events are handled again after a reset cycle. + */ + gd->is_suspended = false; + + /* Publish is_suspended before re-opening the gate, so the handler + * cannot observe an open gate with a stale is_suspended. Pairs + * with the smp_load_acquire() in mana_rdma_service_handle(). This + * matters on the reset path, where mana_rdma_remove() closed the + * gate and drained the workqueue; on the initial probe path the + * gate was never closed and both flags are already clear. It does + * not order gd->adev, which add_adev() publishes below. + */ + smp_store_release(&gd->rdma_teardown, false); + err = add_adev(gd, "rdma"); if (err) mana_gd_deregister_device(gd); diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c index a2a89d48e3cacc..4e83637715e031 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c @@ -1421,7 +1421,8 @@ static int nfp_net_get_fs_rule(struct nfp_net *nn, struct ethtool_rxnfc *cmd) return -ENOENT; } -static int nfp_net_get_fs_loc(struct nfp_net *nn, u32 *rule_locs) +static int nfp_net_get_fs_loc(struct nfp_net *nn, struct ethtool_rxnfc *cmd, + u32 *rule_locs) { struct nfp_fs_entry *entry; u32 count = 0; @@ -1429,8 +1430,12 @@ static int nfp_net_get_fs_loc(struct nfp_net *nn, u32 *rule_locs) if (!(nn->cap_w1 & NFP_NET_CFG_CTRL_FLOW_STEER)) return -EOPNOTSUPP; - list_for_each_entry(entry, &nn->fs.list, node) + list_for_each_entry(entry, &nn->fs.list, node) { + if (count == cmd->rule_cnt) + return -EMSGSIZE; rule_locs[count++] = entry->loc; + } + cmd->rule_cnt = count; return 0; } @@ -1455,7 +1460,7 @@ static int nfp_net_get_rxnfc(struct net_device *netdev, return nfp_net_get_fs_rule(nn, cmd); case ETHTOOL_GRXCLSRLALL: cmd->data = NFP_FS_MAX_ENTRY; - return nfp_net_get_fs_loc(nn, rule_locs); + return nfp_net_get_fs_loc(nn, cmd, rule_locs); default: return -EOPNOTSUPP; } @@ -1698,8 +1703,14 @@ static int nfp_net_fs_add(struct nfp_net *nn, struct ethtool_rxnfc *cmd) nn->fs.count--; err = nfp_net_fs_add_hw(nn, new); - if (err) + if (err) { + /* mbox broken, adding the old rule back will + * likely also fail. + */ + list_del(&entry->node); + kfree(entry); goto err; + } nn->fs.count++; list_replace(&entry->node, &new->node); diff --git a/drivers/net/ethernet/oa_tc6.c b/drivers/net/ethernet/oa_tc6.c index 0727d53345a33b..f552165e503e1a 100644 --- a/drivers/net/ethernet/oa_tc6.c +++ b/drivers/net/ethernet/oa_tc6.c @@ -12,46 +12,6 @@ #include #include -/* OPEN Alliance TC6 registers */ -/* Standard Capabilities Register */ -#define OA_TC6_REG_STDCAP 0x0002 -#define STDCAP_DIRECT_PHY_REG_ACCESS BIT(8) - -/* Reset Control and Status Register */ -#define OA_TC6_REG_RESET 0x0003 -#define RESET_SWRESET BIT(0) /* Software Reset */ - -/* Configuration Register #0 */ -#define OA_TC6_REG_CONFIG0 0x0004 -#define CONFIG0_SYNC BIT(15) -#define CONFIG0_ZARFE_ENABLE BIT(12) - -/* Status Register #0 */ -#define OA_TC6_REG_STATUS0 0x0008 -#define STATUS0_RESETC BIT(6) /* Reset Complete */ -#define STATUS0_HEADER_ERROR BIT(5) -#define STATUS0_LOSS_OF_FRAME_ERROR BIT(4) -#define STATUS0_RX_BUFFER_OVERFLOW_ERROR BIT(3) -#define STATUS0_TX_PROTOCOL_ERROR BIT(0) - -/* Buffer Status Register */ -#define OA_TC6_REG_BUFFER_STATUS 0x000B -#define BUFFER_STATUS_TX_CREDITS_AVAILABLE GENMASK(15, 8) -#define BUFFER_STATUS_RX_CHUNKS_AVAILABLE GENMASK(7, 0) - -/* Interrupt Mask Register #0 */ -#define OA_TC6_REG_INT_MASK0 0x000C -#define INT_MASK0_HEADER_ERR_MASK BIT(5) -#define INT_MASK0_LOSS_OF_FRAME_ERR_MASK BIT(4) -#define INT_MASK0_RX_BUFFER_OVERFLOW_ERR_MASK BIT(3) -#define INT_MASK0_TX_PROTOCOL_ERR_MASK BIT(0) -#define INT_MASK0_ALL_INTERRUPTS (GENMASK(5, 0) | \ - GENMASK(12, 7)) - -/* PHY Clause 22 registers base address and mask */ -#define OA_TC6_PHY_STD_REG_ADDR_BASE 0xFF00 -#define OA_TC6_PHY_STD_REG_ADDR_MASK 0x1F - /* Control command header */ #define OA_TC6_CTRL_HEADER_DATA_NOT_CTRL BIT(31) #define OA_TC6_CTRL_HEADER_WRITE_NOT_READ BIT(29) @@ -81,23 +41,17 @@ #define OA_TC6_DATA_FOOTER_END_BYTE_OFFSET GENMASK(13, 8) #define OA_TC6_DATA_FOOTER_TX_CREDITS GENMASK(5, 1) -/* PHY – Clause 45 registers memory map selector (MMS) as per table 6 in the - * OPEN Alliance specification. - */ -#define OA_TC6_PHY_C45_PCS_MMS2 2 /* MMD 3 */ -#define OA_TC6_PHY_C45_PMA_PMD_MMS3 3 /* MMD 1 */ -#define OA_TC6_PHY_C45_VS_PLCA_MMS4 4 /* MMD 31 */ -#define OA_TC6_PHY_C45_AUTO_NEG_MMS5 5 /* MMD 7 */ -#define OA_TC6_PHY_C45_POWER_UNIT_MMS6 6 /* MMD 13 */ - +#define OA_TC6_CTRL_PROT_REPLY_SIZE 4 #define OA_TC6_CTRL_HEADER_SIZE 4 #define OA_TC6_CTRL_REG_VALUE_SIZE 4 #define OA_TC6_CTRL_IGNORED_SIZE 4 #define OA_TC6_CTRL_MAX_REGISTERS 128 -#define OA_TC6_CTRL_SPI_BUF_SIZE (OA_TC6_CTRL_HEADER_SIZE +\ - (OA_TC6_CTRL_MAX_REGISTERS *\ - OA_TC6_CTRL_REG_VALUE_SIZE) +\ - OA_TC6_CTRL_IGNORED_SIZE) +#define OA_TC6_CTRL_SPI_BUF_SIZE (OA_TC6_CTRL_HEADER_SIZE +\ + (OA_TC6_CTRL_MAX_REGISTERS *\ + (OA_TC6_CTRL_REG_VALUE_SIZE +\ + OA_TC6_CTRL_PROT_REPLY_SIZE)) +\ + OA_TC6_CTRL_IGNORED_SIZE) + #define OA_TC6_CHUNK_PAYLOAD_SIZE 64 #define OA_TC6_DATA_HEADER_SIZE 4 #define OA_TC6_CHUNK_SIZE (OA_TC6_DATA_HEADER_SIZE +\ @@ -127,9 +81,10 @@ struct oa_tc6 { u16 spi_data_tx_buf_offset; u16 tx_credits; u8 rx_chunks_available; - bool rx_buf_overflow; + bool wait_until_start_valid; bool int_flag; bool disable_traffic; + bool prot_ctrl; }; enum oa_tc6_header_type { @@ -213,25 +168,36 @@ static void oa_tc6_update_ctrl_write_data(struct oa_tc6 *tc6, u32 value[], { __be32 *tx_buf = tc6->spi_ctrl_tx_buf + OA_TC6_CTRL_HEADER_SIZE; - for (int i = 0; i < length; i++) + for (int i = 0; i < length; i++) { *tx_buf++ = cpu_to_be32(value[i]); + if (tc6->prot_ctrl) + *tx_buf++ = cpu_to_be32(~value[i]); + } } -static u16 oa_tc6_calculate_ctrl_buf_size(u8 length) +static u16 oa_tc6_calculate_ctrl_buf_size(u8 length, bool ctrl_prot) { + u32 reply_size = OA_TC6_CTRL_REG_VALUE_SIZE; + + if (ctrl_prot) + reply_size += OA_TC6_CTRL_PROT_REPLY_SIZE; + /* Control command consists 4 bytes header + 4 bytes register value for - * each register + 4 bytes ignored value. + * each register (+ 4 bytes for the register value complement in case + * protected mode is used) + 4 bytes ignored value. */ - return OA_TC6_CTRL_HEADER_SIZE + OA_TC6_CTRL_REG_VALUE_SIZE * length + + return OA_TC6_CTRL_HEADER_SIZE + reply_size * length + OA_TC6_CTRL_IGNORED_SIZE; } static void oa_tc6_prepare_ctrl_spi_buf(struct oa_tc6 *tc6, u32 address, u32 value[], u8 length, - enum oa_tc6_register_op reg_op) + enum oa_tc6_register_op reg_op, + u16 buf_size) { __be32 *tx_buf = tc6->spi_ctrl_tx_buf; + memset(tx_buf, 0, buf_size); *tx_buf = oa_tc6_prepare_ctrl_header(address, length, reg_op); if (reg_op == OA_TC6_CTRL_REG_WRITE) @@ -254,10 +220,12 @@ static int oa_tc6_check_ctrl_write_reply(struct oa_tc6 *tc6, u8 size) return 0; } -static int oa_tc6_check_ctrl_read_reply(struct oa_tc6 *tc6, u8 size) +static int oa_tc6_check_ctrl_read_reply(struct oa_tc6 *tc6, u8 length) { - u32 *rx_buf = tc6->spi_ctrl_rx_buf + OA_TC6_CTRL_IGNORED_SIZE; - u32 *tx_buf = tc6->spi_ctrl_tx_buf; + __be32 *rx_buf = tc6->spi_ctrl_rx_buf + OA_TC6_CTRL_IGNORED_SIZE; + __be32 *tx_buf = tc6->spi_ctrl_tx_buf; + u32 complement; + u32 reply; /* The echoed control read header must match with the one that was * transmitted. @@ -265,6 +233,20 @@ static int oa_tc6_check_ctrl_read_reply(struct oa_tc6 *tc6, u8 size) if (*tx_buf != *rx_buf) return -EPROTO; + if (tc6->prot_ctrl) { + /* Skip past the echoed header to the value/complement pairs */ + rx_buf += 1; + for (int i = 0; i < length; i++) { + reply = be32_to_cpu(rx_buf[0]); + complement = be32_to_cpu(rx_buf[1]); + + if (complement != ~reply) + return -EPROTO; + + rx_buf += 2; + } + } + return 0; } @@ -274,8 +256,13 @@ static void oa_tc6_copy_ctrl_read_data(struct oa_tc6 *tc6, u32 value[], __be32 *rx_buf = tc6->spi_ctrl_rx_buf + OA_TC6_CTRL_IGNORED_SIZE + OA_TC6_CTRL_HEADER_SIZE; - for (int i = 0; i < length; i++) + for (int i = 0; i < length; i++) { value[i] = be32_to_cpu(*rx_buf++); + + /* skip complement word */ + if (tc6->prot_ctrl) + rx_buf++; + } } static int oa_tc6_perform_ctrl(struct oa_tc6 *tc6, u32 address, u32 value[], @@ -284,10 +271,10 @@ static int oa_tc6_perform_ctrl(struct oa_tc6 *tc6, u32 address, u32 value[], u16 size; int ret; - /* Prepare control command and copy to SPI control buffer */ - oa_tc6_prepare_ctrl_spi_buf(tc6, address, value, length, reg_op); + size = oa_tc6_calculate_ctrl_buf_size(length, tc6->prot_ctrl); - size = oa_tc6_calculate_ctrl_buf_size(length); + /* Prepare control command and copy to SPI control buffer */ + oa_tc6_prepare_ctrl_spi_buf(tc6, address, value, length, reg_op, size); /* Perform SPI transfer */ ret = oa_tc6_spi_transfer(tc6, OA_TC6_CTRL_HEADER, size); @@ -302,7 +289,7 @@ static int oa_tc6_perform_ctrl(struct oa_tc6 *tc6, u32 address, u32 value[], return oa_tc6_check_ctrl_write_reply(tc6, size); /* Check echoed/received control read command reply for errors */ - ret = oa_tc6_check_ctrl_read_reply(tc6, size); + ret = oa_tc6_check_ctrl_read_reply(tc6, length); if (ret) return ret; @@ -408,7 +395,7 @@ static int oa_tc6_check_phy_reg_direct_access_capability(struct oa_tc6 *tc6) if (ret) return ret; - if (!(regval & STDCAP_DIRECT_PHY_REG_ACCESS)) + if (!(regval & OA_TC6_STDCAP_DIRECT_PHY_REG_ACCESS)) return -ENODEV; return 0; @@ -423,7 +410,7 @@ static int oa_tc6_mdiobus_read(struct mii_bus *bus, int addr, int regnum) { struct oa_tc6 *tc6 = bus->priv; u32 regval; - bool ret; + int ret; ret = oa_tc6_read_register(tc6, OA_TC6_PHY_STD_REG_ADDR_BASE | (regnum & OA_TC6_PHY_STD_REG_ADDR_MASK), @@ -601,7 +588,7 @@ static int oa_tc6_read_status0(struct oa_tc6 *tc6) static int oa_tc6_sw_reset_macphy(struct oa_tc6 *tc6) { - u32 regval = RESET_SWRESET; + u32 regval = OA_TC6_RESET_SWRESET; int ret; ret = oa_tc6_write_register(tc6, OA_TC6_REG_RESET, regval); @@ -610,7 +597,7 @@ static int oa_tc6_sw_reset_macphy(struct oa_tc6 *tc6) /* Poll for soft reset complete for every 1ms until 1s timeout */ ret = readx_poll_timeout(oa_tc6_read_status0, tc6, regval, - regval & STATUS0_RESETC, + regval & OA_TC6_STATUS0_RESETC, STATUS0_RESETC_POLL_DELAY, STATUS0_RESETC_POLL_TIMEOUT); if (ret) @@ -629,10 +616,10 @@ static int oa_tc6_unmask_macphy_error_interrupts(struct oa_tc6 *tc6) if (ret) return ret; - regval &= ~(INT_MASK0_TX_PROTOCOL_ERR_MASK | - INT_MASK0_RX_BUFFER_OVERFLOW_ERR_MASK | - INT_MASK0_LOSS_OF_FRAME_ERR_MASK | - INT_MASK0_HEADER_ERR_MASK); + regval &= ~(OA_TC6_INT_MASK0_TX_PROTOCOL_ERR_MASK | + OA_TC6_INT_MASK0_RX_BUFFER_OVERFLOW_ERR_MASK | + OA_TC6_INT_MASK0_LOSS_OF_FRAME_ERR_MASK | + OA_TC6_INT_MASK0_HEADER_ERR_MASK); return oa_tc6_write_register(tc6, OA_TC6_REG_INT_MASK0, regval); } @@ -647,11 +634,31 @@ static int oa_tc6_enable_data_transfer(struct oa_tc6 *tc6) return ret; /* Enable configuration synchronization for data transfer */ - value |= CONFIG0_SYNC; + value |= OA_TC6_CONFIG0_SYNC; return oa_tc6_write_register(tc6, OA_TC6_REG_CONFIG0, value); } +/* Called when a frame that is meant to be transmitted, is dropped. */ +static void oa_tc6_drop_tx_skb(struct oa_tc6 *tc6, struct sk_buff *skb) +{ + if (skb) { + tc6->netdev->stats.tx_dropped++; + dev_kfree_skb_any(skb); + } +} + +static struct sk_buff *oa_tc6_detach_waiting_tx_skb(struct oa_tc6 *tc6) +{ + struct sk_buff *skb; + + lockdep_assert_held(&tc6->tx_skb_lock); + skb = tc6->waiting_tx_skb; + tc6->waiting_tx_skb = NULL; + + return skb; +} + static void oa_tc6_cleanup_ongoing_rx_skb(struct oa_tc6 *tc6) { if (tc6->rx_skb) { @@ -663,39 +670,59 @@ static void oa_tc6_cleanup_ongoing_rx_skb(struct oa_tc6 *tc6) static void oa_tc6_cleanup_ongoing_tx_skb(struct oa_tc6 *tc6) { - if (tc6->ongoing_tx_skb) { - tc6->netdev->stats.tx_dropped++; - kfree_skb(tc6->ongoing_tx_skb); - tc6->ongoing_tx_skb = NULL; - } + oa_tc6_drop_tx_skb(tc6, tc6->ongoing_tx_skb); + tc6->ongoing_tx_skb = NULL; } static void oa_tc6_cleanup_waiting_tx_skb(struct oa_tc6 *tc6) { - if (tc6->waiting_tx_skb) { - tc6->netdev->stats.tx_dropped++; - kfree_skb(tc6->waiting_tx_skb); - tc6->waiting_tx_skb = NULL; - } + struct sk_buff *skb; + + spin_lock_bh(&tc6->tx_skb_lock); + skb = oa_tc6_detach_waiting_tx_skb(tc6); + spin_unlock_bh(&tc6->tx_skb_lock); + + oa_tc6_drop_tx_skb(tc6, skb); } -static void oa_tc6_free_pending_skbs(struct oa_tc6 *tc6) +static void oa_tc6_free_ongoing_skbs(struct oa_tc6 *tc6) { oa_tc6_cleanup_ongoing_tx_skb(tc6); oa_tc6_cleanup_ongoing_rx_skb(tc6); +} + +static void oa_tc6_free_pending_skbs(struct oa_tc6 *tc6) +{ + oa_tc6_free_ongoing_skbs(tc6); oa_tc6_cleanup_waiting_tx_skb(tc6); } +static void oa_tc6_look_for_new_frame(struct oa_tc6 *tc6) +{ + tc6->wait_until_start_valid = true; + oa_tc6_cleanup_ongoing_rx_skb(tc6); +} + /* If the failure is at SPI interface level, masking and clearing * the interrupt of the device won't work. Since SPI interrupt is * disabled, it should stop the repeated interrupts. */ static void oa_tc6_disable_traffic(struct oa_tc6 *tc6) { - u32 regval = INT_MASK0_ALL_INTERRUPTS; + u32 regval = OA_TC6_INT_MASK0_ALL_INTERRUPTS; + struct sk_buff *skb; + spin_lock_bh(&tc6->tx_skb_lock); tc6->disable_traffic = true; - oa_tc6_free_pending_skbs(tc6); + skb = oa_tc6_detach_waiting_tx_skb(tc6); + spin_unlock_bh(&tc6->tx_skb_lock); + + /* disable_traffic, when set, is a point of no return to + * working state. Keeping the TX queues disabled. + */ + netif_tx_disable(tc6->netdev); + oa_tc6_drop_tx_skb(tc6, skb); + oa_tc6_free_ongoing_skbs(tc6); oa_tc6_write_register(tc6, OA_TC6_REG_INT_MASK0, regval); oa_tc6_read_register(tc6, OA_TC6_REG_STATUS0, ®val); oa_tc6_write_register(tc6, OA_TC6_REG_STATUS0, regval); @@ -714,6 +741,13 @@ static int oa_tc6_process_extended_status(struct oa_tc6 *tc6) return ret; } + /* This function is called for each chunk received in a given SPI + * transaction. In case, extended status bit is set in more than + * one chunk, skip the write, if status0 is already cleared. + */ + if (!value) + return 0; + /* Clear the error interrupts status */ ret = oa_tc6_write_register(tc6, OA_TC6_REG_STATUS0, value); if (ret) { @@ -722,25 +756,24 @@ static int oa_tc6_process_extended_status(struct oa_tc6 *tc6) return ret; } - if (FIELD_GET(STATUS0_RX_BUFFER_OVERFLOW_ERROR, value)) { - tc6->rx_buf_overflow = true; - oa_tc6_cleanup_ongoing_rx_skb(tc6); + if (FIELD_GET(OA_TC6_STATUS0_RX_BUFFER_OVERFLOW_ERROR, value)) { + oa_tc6_look_for_new_frame(tc6); net_err_ratelimited("%s: Receive buffer overflow error\n", tc6->netdev->name); return -EAGAIN; } - if (FIELD_GET(STATUS0_TX_PROTOCOL_ERROR, value)) { + if (FIELD_GET(OA_TC6_STATUS0_TX_PROTOCOL_ERROR, value)) { netdev_err(tc6->netdev, "Transmit protocol error\n"); return -ENODEV; } /* TODO: Currently loss of frame and header errors are treated as * non-recoverable errors. They will be handled in the next version. */ - if (FIELD_GET(STATUS0_LOSS_OF_FRAME_ERROR, value)) { + if (FIELD_GET(OA_TC6_STATUS0_LOSS_OF_FRAME_ERROR, value)) { netdev_err(tc6->netdev, "Loss of frame error\n"); return -ENODEV; } - if (FIELD_GET(STATUS0_HEADER_ERROR, value)) { + if (FIELD_GET(OA_TC6_STATUS0_HEADER_ERROR, value)) { netdev_err(tc6->netdev, "Header error\n"); return -ENODEV; } @@ -750,6 +783,8 @@ static int oa_tc6_process_extended_status(struct oa_tc6 *tc6) static int oa_tc6_process_rx_chunk_footer(struct oa_tc6 *tc6, u32 footer) { + int ret = 0; + /* Process rx chunk footer for the following, * 1. tx credits * 2. errors if any from MAC-PHY @@ -760,9 +795,11 @@ static int oa_tc6_process_rx_chunk_footer(struct oa_tc6 *tc6, u32 footer) footer); if (FIELD_GET(OA_TC6_DATA_FOOTER_EXTENDED_STS, footer)) { - int ret = oa_tc6_process_extended_status(tc6); - - if (ret) + ret = oa_tc6_process_extended_status(tc6); + /* EAGAIN error is recoverable. Move on to check + * HEADER and SYNC errors before returning. + */ + if (ret && ret != -EAGAIN) return ret; } @@ -780,7 +817,7 @@ static int oa_tc6_process_rx_chunk_footer(struct oa_tc6 *tc6, u32 footer) return -ENODEV; } - return 0; + return ret; } static void oa_tc6_submit_rx_skb(struct oa_tc6 *tc6) @@ -805,13 +842,35 @@ static void oa_tc6_submit_rx_skb(struct oa_tc6 *tc6) tc6->rx_skb = NULL; } -static void oa_tc6_update_rx_skb(struct oa_tc6 *tc6, u8 *payload, u8 length) +/* On oversubscribed traffic condition, particularly with overwhelming rx + * buffer overflow errors, there could be data chunk loss. If tail + length + * goes beyond end pointer, that is an indication that the data chunk with + * end_valid bit is lost. Time to look for a data chunk with start_valid bit. + * + * If rx_skb is NULL, it is time to start looking for data chunk with + * start_bit. + */ +static int oa_tc6_update_rx_skb(struct oa_tc6 *tc6, u8 *payload, u8 length) { + if (!tc6->rx_skb || + skb_tailroom(tc6->rx_skb) < length) { + oa_tc6_look_for_new_frame(tc6); + return -EAGAIN; + } + memcpy(skb_put(tc6->rx_skb, length), payload, length); + return 0; } +/* On overwhelming rx buffer overflow errors, due to data chunk loss, it is + * possible that we get two data chunks with start_valid bit set, without + * end_valid bit set in between. In this case, rx_skb would have a valid + * buffer pointer. We should release, if a valid pointer is found before + * allocating a new one. + */ static int oa_tc6_allocate_rx_skb(struct oa_tc6 *tc6) { + oa_tc6_cleanup_ongoing_rx_skb(tc6); tc6->rx_skb = netdev_alloc_skb_ip_align(tc6->netdev, tc6->netdev->mtu + ETH_HLEN + ETH_FCS_LEN); if (!tc6->rx_skb) { @@ -831,7 +890,9 @@ static int oa_tc6_prcs_complete_rx_frame(struct oa_tc6 *tc6, u8 *payload, if (ret) return ret; - oa_tc6_update_rx_skb(tc6, payload, size); + ret = oa_tc6_update_rx_skb(tc6, payload, size); + if (ret) + return ret; oa_tc6_submit_rx_skb(tc6); @@ -846,22 +907,24 @@ static int oa_tc6_prcs_rx_frame_start(struct oa_tc6 *tc6, u8 *payload, u16 size) if (ret) return ret; - oa_tc6_update_rx_skb(tc6, payload, size); - - return 0; + return oa_tc6_update_rx_skb(tc6, payload, size); } -static void oa_tc6_prcs_rx_frame_end(struct oa_tc6 *tc6, u8 *payload, u16 size) +static int oa_tc6_prcs_rx_frame_end(struct oa_tc6 *tc6, u8 *payload, u16 size) { - oa_tc6_update_rx_skb(tc6, payload, size); + int ret; - oa_tc6_submit_rx_skb(tc6); + ret = oa_tc6_update_rx_skb(tc6, payload, size); + if (!ret) + oa_tc6_submit_rx_skb(tc6); + return ret; } -static void oa_tc6_prcs_ongoing_rx_frame(struct oa_tc6 *tc6, u8 *payload, - u32 footer) +static int oa_tc6_prcs_ongoing_rx_frame(struct oa_tc6 *tc6, u8 *payload, + u32 footer) { - oa_tc6_update_rx_skb(tc6, payload, OA_TC6_CHUNK_PAYLOAD_SIZE); + return oa_tc6_update_rx_skb(tc6, payload, + OA_TC6_CHUNK_PAYLOAD_SIZE); } static int oa_tc6_prcs_rx_chunk_payload(struct oa_tc6 *tc6, u8 *data, @@ -876,10 +939,10 @@ static int oa_tc6_prcs_rx_chunk_payload(struct oa_tc6 *tc6, u8 *data, u16 size; /* Restart the new rx frame after receiving rx buffer overflow error */ - if (start_valid && tc6->rx_buf_overflow) - tc6->rx_buf_overflow = false; + if (start_valid && tc6->wait_until_start_valid) + tc6->wait_until_start_valid = false; - if (tc6->rx_buf_overflow) + if (tc6->wait_until_start_valid) return 0; /* Process the chunk with complete rx frame */ @@ -901,8 +964,7 @@ static int oa_tc6_prcs_rx_chunk_payload(struct oa_tc6 *tc6, u8 *data, /* Process the chunk with only rx frame end */ if (end_valid && !start_valid) { size = end_byte_offset + 1; - oa_tc6_prcs_rx_frame_end(tc6, data, size); - return 0; + return oa_tc6_prcs_rx_frame_end(tc6, data, size); } /* Process the chunk with previous rx frame end and next rx frame @@ -916,6 +978,15 @@ static int oa_tc6_prcs_rx_chunk_payload(struct oa_tc6 *tc6, u8 *data, if (tc6->rx_skb) { size = end_byte_offset + 1; oa_tc6_prcs_rx_frame_end(tc6, data, size); + + /* Return value from oa_tc6_prcs_rx_frame_end is not + * checked. If it returned an error, it is to make + * the code to look for new frame. At this stage, + * code below is going to process a new frame. So, + * error condition is set to false, in case it is + * set before proceeding. + */ + tc6->wait_until_start_valid = false; } size = OA_TC6_CHUNK_PAYLOAD_SIZE - start_byte_offset; return oa_tc6_prcs_rx_frame_start(tc6, @@ -924,9 +995,7 @@ static int oa_tc6_prcs_rx_chunk_payload(struct oa_tc6 *tc6, u8 *data, } /* Process the chunk with ongoing rx frame data */ - oa_tc6_prcs_ongoing_rx_frame(tc6, data, footer); - - return 0; + return oa_tc6_prcs_ongoing_rx_frame(tc6, data, footer); } static u32 oa_tc6_get_rx_chunk_footer(struct oa_tc6 *tc6, u16 footer_offset) @@ -942,8 +1011,9 @@ static u32 oa_tc6_get_rx_chunk_footer(struct oa_tc6 *tc6, u16 footer_offset) static int oa_tc6_process_spi_data_rx_buf(struct oa_tc6 *tc6, u16 length) { u16 no_of_rx_chunks = length / OA_TC6_CHUNK_SIZE; + bool retry = false; + int ret = 0; u32 footer; - int ret; /* All the rx chunks in the receive SPI data buffer are examined here */ for (int i = 0; i < no_of_rx_chunks; i++) { @@ -952,8 +1022,11 @@ static int oa_tc6_process_spi_data_rx_buf(struct oa_tc6 *tc6, u16 length) OA_TC6_CHUNK_PAYLOAD_SIZE); ret = oa_tc6_process_rx_chunk_footer(tc6, footer); - if (ret) - return ret; + if (ret) { + if (ret != -EAGAIN) + return ret; + retry = true; + } /* If there is a data valid chunks then process it for the * information needed to determine the validity and the location @@ -965,12 +1038,35 @@ static int oa_tc6_process_spi_data_rx_buf(struct oa_tc6 *tc6, u16 length) ret = oa_tc6_prcs_rx_chunk_payload(tc6, payload, footer); - if (ret) - return ret; + if (ret) { + if (ret != -ENOMEM && ret != -EAGAIN) + return ret; + retry = true; + } } } - return 0; + /* Not bailing out on recoverable error codes, -EAGAIN and + * -ENOMEM. If subsequent loop iterations, if any, succeeds, + * error code would be overwritten. retry flag helps to + * make the caller to continue and retry. Since recovery + * action for -ENOMEM and -EAGAIN are same, we are returning + * one of the error codes, that is -EAGAIN. + * + * Successful recovery depends on how small the frames are, + * how many chunks, among the received chunks triggered the + * error, whether data is intact even with error conditions. + * As a result, there is no single, best method to recover + * most data when error conditions hit. We do our best by + * processing all the chunks with good "footer header" and + * "data valid" bit set. + */ + if (retry) { + ret = -EAGAIN; + oa_tc6_look_for_new_frame(tc6); + } + + return ret; } static __be32 oa_tc6_prepare_data_header(bool data_valid, bool start_valid, @@ -1132,12 +1228,9 @@ static int oa_tc6_try_spi_transfer(struct oa_tc6 *tc6) } ret = oa_tc6_process_spi_data_rx_buf(tc6, spi_len); - if (ret) { - if (ret == -EAGAIN) - continue; - oa_tc6_cleanup_ongoing_tx_skb(tc6); - oa_tc6_cleanup_ongoing_rx_skb(tc6); + if (ret && ret != -EAGAIN) { + oa_tc6_free_ongoing_skbs(tc6); netdev_err(tc6->netdev, "Device error: %d\n", ret); return ret; } @@ -1159,15 +1252,20 @@ static irqreturn_t oa_tc6_macphy_threaded_irq(int irq, void *data) * no need to attempt spi transfer, once it fails. Pending skbs * are already freed. */ - if (!tc6->disable_traffic) { - while (tc6->int_flag || - (tc6->waiting_tx_skb && tc6->tx_credits)) { - ret = oa_tc6_try_spi_transfer(tc6); - if (ret) { - disable_irq_nosync(tc6->spi->irq); - oa_tc6_disable_traffic(tc6); - break; - } + spin_lock_bh(&tc6->tx_skb_lock); + if (tc6->disable_traffic) { + spin_unlock_bh(&tc6->tx_skb_lock); + return IRQ_HANDLED; + } + spin_unlock_bh(&tc6->tx_skb_lock); + + while (tc6->int_flag || + (tc6->waiting_tx_skb && tc6->tx_credits)) { + ret = oa_tc6_try_spi_transfer(tc6); + if (ret) { + disable_irq_nosync(tc6->spi->irq); + oa_tc6_disable_traffic(tc6); + break; } } @@ -1187,9 +1285,10 @@ static int oa_tc6_update_buffer_status_from_register(struct oa_tc6 *tc6) if (ret) return ret; - tc6->tx_credits = FIELD_GET(BUFFER_STATUS_TX_CREDITS_AVAILABLE, value); - tc6->rx_chunks_available = FIELD_GET(BUFFER_STATUS_RX_CHUNKS_AVAILABLE, - value); + tc6->tx_credits = FIELD_GET(OA_TC6_BUFFER_STATUS_TX_CREDITS_AVAILABLE, + value); + tc6->rx_chunks_available = + FIELD_GET(OA_TC6_BUFFER_STATUS_RX_CHUNKS_AVAILABLE, value); return 0; } @@ -1233,7 +1332,7 @@ int oa_tc6_zero_align_receive_frame_enable(struct oa_tc6 *tc6) return ret; /* Set Zero-Align Receive Frame Enable */ - regval |= CONFIG0_ZARFE_ENABLE; + regval |= OA_TC6_CONFIG0_ZARFE_ENABLE; return oa_tc6_write_register(tc6, OA_TC6_REG_CONFIG0, regval); } @@ -1245,23 +1344,30 @@ EXPORT_SYMBOL_GPL(oa_tc6_zero_align_receive_frame_enable); * @tc6: oa_tc6 struct. * @skb: socket buffer in which the ethernet frame is stored. * - * Return: NETDEV_TX_OK if the transmit ethernet frame skb added in the tx_skb_q - * otherwise returns NETDEV_TX_BUSY. + * Return: NETDEV_TX_OK either on successful queueing of the packet for + * transmission, or on packet getting dropped. Packet can be dropped due to + * failure in linearizing the buffer or disable_traffic is set due to + * earlier fatal error. Returns NETDEV_TX_BUSY when there is no room + * to queue the packet. */ netdev_tx_t oa_tc6_start_xmit(struct oa_tc6 *tc6, struct sk_buff *skb) { - if (tc6->disable_traffic || tc6->waiting_tx_skb) { - netif_stop_queue(tc6->netdev); - return NETDEV_TX_BUSY; - } - if (skb_linearize(skb)) { - dev_kfree_skb_any(skb); - tc6->netdev->stats.tx_dropped++; + oa_tc6_drop_tx_skb(tc6, skb); return NETDEV_TX_OK; } spin_lock_bh(&tc6->tx_skb_lock); + if (tc6->waiting_tx_skb) { + netif_stop_queue(tc6->netdev); + spin_unlock_bh(&tc6->tx_skb_lock); + return NETDEV_TX_BUSY; + } + if (tc6->disable_traffic) { + spin_unlock_bh(&tc6->tx_skb_lock); + oa_tc6_drop_tx_skb(tc6, skb); + return NETDEV_TX_OK; + } tc6->waiting_tx_skb = skb; spin_unlock_bh(&tc6->tx_skb_lock); @@ -1272,6 +1378,20 @@ netdev_tx_t oa_tc6_start_xmit(struct oa_tc6 *tc6, struct sk_buff *skb) } EXPORT_SYMBOL_GPL(oa_tc6_start_xmit); +static int oa_tc6_check_ctrl_protection(struct oa_tc6 *tc6) +{ + u32 regval; + int ret; + + ret = oa_tc6_read_register(tc6, OA_TC6_REG_CONFIG0, ®val); + if (ret) + return ret; + + tc6->prot_ctrl = FIELD_GET(OA_TC6_CONFIG0_PROTE, regval); + + return 0; +} + /** * oa_tc6_init - allocates and initializes oa_tc6 structure. * @spi: device with which data will be exchanged. @@ -1324,6 +1444,14 @@ struct oa_tc6 *oa_tc6_init(struct spi_device *spi, struct net_device *netdev) if (!tc6->spi_data_rx_buf) return NULL; + /* Check the PROTE bit status so that we can reset the device */ + ret = oa_tc6_check_ctrl_protection(tc6); + if (ret) { + dev_err(&tc6->spi->dev, + "Failed to check the protection mode: %d\n", ret); + return NULL; + } + ret = oa_tc6_sw_reset_macphy(tc6); if (ret) { dev_err(&tc6->spi->dev, @@ -1393,8 +1521,10 @@ EXPORT_SYMBOL_GPL(oa_tc6_init); */ void oa_tc6_exit(struct oa_tc6 *tc6) { - tc6->disable_traffic = true; disable_irq(tc6->spi->irq); + spin_lock_bh(&tc6->tx_skb_lock); + tc6->disable_traffic = true; + spin_unlock_bh(&tc6->tx_skb_lock); oa_tc6_phy_exit(tc6); oa_tc6_free_pending_skbs(tc6); } diff --git a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c index e436e3231e864b..2543a8ff854764 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c @@ -1672,15 +1672,22 @@ static int ionic_tx(struct net_device *netdev, struct ionic_queue *q, stats->pkts++; stats->bytes += skb->len; + ionic_txq_post(q, false); + if (likely(!ionic_txq_hwstamp_enabled(q))) { struct netdev_queue *ndq = q_to_ndq(netdev, q); - if (unlikely(!ionic_q_has_space(q, MAX_SKB_FRAGS + 1))) - netif_tx_stop_queue(ndq); + netif_txq_maybe_stop(ndq, ionic_q_space_avail(q), + MAX_SKB_FRAGS + 1, MAX_SKB_FRAGS + 1); ring_dbell = __netdev_tx_sent_queue(ndq, skb->len, netdev_xmit_more()); } - ionic_txq_post(q, ring_dbell); + + if (ring_dbell) { + ionic_dbell_ring(q->lif->kern_dbpage, q->hw_type, + q->dbval | q->head_idx); + q->dbell_jiffies = jiffies; + } return 0; } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 3a437409f78aef..f801caf65fff1f 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -3676,6 +3676,14 @@ static int stmmac_hw_setup(struct net_device *dev) /* Initialize MTL*/ stmmac_mtl_configuration(priv); + /* Apply the RX packet parser table */ + if (priv->tc_entries) { + ret = stmmac_rxp_config(priv, priv->hw->pcsr, priv->tc_entries, + priv->tc_entries_max); + if (ret) + return ret; + } + /* Initialize Safety Features */ stmmac_safety_feat_configuration(priv); @@ -4319,6 +4327,7 @@ static bool stmmac_vlan_insert(struct stmmac_priv *priv, struct sk_buff *skb, /** * stmmac_tso_allocator - close entry point of the driver * @priv: driver private structure + * @entry: TX queue buffer index * @des: buffer start address * @total_len: total length to fill in descriptors * @last_segment: condition for the last descriptor @@ -4327,8 +4336,9 @@ static bool stmmac_vlan_insert(struct stmmac_priv *priv, struct sk_buff *skb, * This function fills descriptor and request new descriptors according to * buffer length to fill */ -static void stmmac_tso_allocator(struct stmmac_priv *priv, dma_addr_t des, - int total_len, bool last_segment, u32 queue) +static void stmmac_tso_allocator(struct stmmac_priv *priv, u32 *entry, + dma_addr_t des, int total_len, + bool last_segment, u32 queue) { struct stmmac_tx_queue *tx_q = &priv->dma_conf.tx_queue[queue]; struct dma_desc *desc; @@ -4340,14 +4350,13 @@ static void stmmac_tso_allocator(struct stmmac_priv *priv, dma_addr_t des, while (tmp_len > 0) { dma_addr_t curr_addr; - tx_q->cur_tx = STMMAC_NEXT_ENTRY(tx_q->cur_tx, - priv->dma_conf.dma_tx_size); - WARN_ON(tx_q->tx_skbuff[tx_q->cur_tx]); + *entry = STMMAC_NEXT_ENTRY(*entry, priv->dma_conf.dma_tx_size); + WARN_ON(tx_q->tx_skbuff[*entry]); if (tx_q->tbs & STMMAC_TBS_AVAIL) - desc = &tx_q->dma_entx[tx_q->cur_tx].basic; + desc = &tx_q->dma_entx[*entry].basic; else - desc = &tx_q->dma_tx[tx_q->cur_tx]; + desc = &tx_q->dma_tx[*entry]; curr_addr = des + (total_len - tmp_len); stmmac_set_desc_addr(priv, desc, curr_addr); @@ -4445,6 +4454,26 @@ static bool stmmac_tso_valid_packet(struct sk_buff *skb) header_len + gso_size < 16383; } +static int stmmac_tso_get_num_desc(struct stmmac_tx_queue *tx_q, + struct sk_buff *skb, u32 pay_len) +{ + int i, ndesc = 1; + + /* head payload */ + ndesc += DIV_ROUND_UP(pay_len, TSO_MAX_BUFF_SIZE); + /* frag payload */ + for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { + const skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; + + ndesc += DIV_ROUND_UP(skb_frag_size(frag), + TSO_MAX_BUFF_SIZE); + } + /* MSS update requires a new descriptor */ + ndesc += !!(skb_shinfo(skb)->gso_size != tx_q->mss); + + return ndesc; +} + /** * stmmac_tso_xmit - Tx entry point of the driver for oversized frames (TSO) * @skb : the socket buffer @@ -4486,12 +4515,12 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) { struct dma_desc *desc, *first, *mss_desc = NULL; struct stmmac_priv *priv = netdev_priv(dev); - unsigned int first_entry, tx_packets; + unsigned int first_entry, entry, tx_packets; struct stmmac_txq_stats *txq_stats; + int i, first_tx, nfrags, ndesc; struct stmmac_tx_queue *tx_q; bool set_ic, is_last_segment; u32 pay_len, mss, queue; - int i, first_tx, nfrags; u8 proto_hdr_len, hdr; dma_addr_t des; @@ -4504,14 +4533,15 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) /* Compute header lengths */ proto_hdr_len = stmmac_tso_header_size(skb); + pay_len = skb_headlen(skb) - proto_hdr_len; /* no frags */ + if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) hdr = sizeof(struct udphdr); else hdr = tcp_hdrlen(skb); - /* Desc availability based on threshold should be enough safe */ - if (unlikely(stmmac_tx_avail(priv, queue) < - (((skb->len - proto_hdr_len) / TSO_MAX_BUFF_SIZE + 1)))) { + ndesc = stmmac_tso_get_num_desc(tx_q, skb, pay_len); + if (unlikely(stmmac_tx_avail(priv, queue) < ndesc)) { if (!netif_tx_queue_stopped(netdev_get_tx_queue(dev, queue))) { netif_tx_stop_queue(netdev_get_tx_queue(priv->dev, queue)); @@ -4523,8 +4553,6 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) return NETDEV_TX_BUSY; } - pay_len = skb_headlen(skb) - proto_hdr_len; /* no frags */ - mss = skb_shinfo(skb)->gso_size; /* set new MSS value if needed */ @@ -4549,22 +4577,24 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) } first_entry = tx_q->cur_tx; - WARN_ON(tx_q->tx_skbuff[first_entry]); + entry = first_entry; + + WARN_ON(tx_q->tx_skbuff[entry]); if (tx_q->tbs & STMMAC_TBS_AVAIL) - desc = &tx_q->dma_entx[first_entry].basic; + desc = &tx_q->dma_entx[entry].basic; else - desc = &tx_q->dma_tx[first_entry]; + desc = &tx_q->dma_tx[entry]; first = desc; /* first descriptor: fill Headers on Buf1 */ des = dma_map_single(priv->device, skb->data, skb_headlen(skb), DMA_TO_DEVICE); if (dma_mapping_error(priv->device, des)) - goto dma_map_err; + goto error; stmmac_set_desc_addr(priv, first, des); - stmmac_tso_allocator(priv, des + proto_hdr_len, pay_len, + stmmac_tso_allocator(priv, &entry, des + proto_hdr_len, pay_len, (nfrags == 0), queue); /* In case two or more DMA transmit descriptors are allocated for this @@ -4579,8 +4609,7 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) * this DMA buffer right after the DMA engine completely finishes the * full buffer transmission. */ - stmmac_set_tx_skb_dma_entry(tx_q, tx_q->cur_tx, des, skb_headlen(skb), - false); + stmmac_set_tx_skb_dma_entry(tx_q, entry, des, skb_headlen(skb), false); /* Prepare fragments */ for (i = 0; i < nfrags; i++) { @@ -4590,14 +4619,15 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) skb_frag_size(frag), DMA_TO_DEVICE); if (dma_mapping_error(priv->device, des)) - goto dma_map_err; + goto error_dma_unmap; - stmmac_tso_allocator(priv, des, skb_frag_size(frag), + stmmac_tso_allocator(priv, &entry, des, skb_frag_size(frag), (i == nfrags - 1), queue); - stmmac_set_tx_skb_dma_entry(tx_q, tx_q->cur_tx, des, + stmmac_set_tx_skb_dma_entry(tx_q, entry, des, skb_frag_size(frag), true); } + tx_q->cur_tx = entry; stmmac_set_tx_dma_last_segment(tx_q, tx_q->cur_tx); @@ -4700,7 +4730,19 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) return NETDEV_TX_OK; -dma_map_err: +error_dma_unmap: + for (;;) { + desc = stmmac_get_tx_desc(priv, tx_q, first_entry); + stmmac_release_tx_desc(priv, desc, priv->descriptor_mode); + stmmac_free_tx_buffer(priv, &priv->dma_conf, queue, + first_entry); + if (first_entry == entry) + break; + + first_entry = STMMAC_NEXT_ENTRY(first_entry, + priv->dma_conf.dma_tx_size); + } +error: dev_err(priv->device, "Tx dma map failed\n"); dev_kfree_skb(skb); priv->xstats.tx_dropped++; @@ -8009,6 +8051,7 @@ static int __stmmac_dvr_probe(struct device *device, stmmac_napi_add(ndev); mutex_init(&priv->lock); + rwlock_init(&priv->ptp_lock); stmmac_fpe_init(priv); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c index 960249960004c5..3bfcc9760dce78 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c @@ -365,7 +365,6 @@ void stmmac_ptp_register(struct stmmac_priv *priv) if (priv->plat->crosststamp) priv->ptp_clock_ops.getcrosststamp = stmmac_getcrosststamp; - rwlock_init(&priv->ptp_lock); mutex_init(&priv->aux_ts_lock); priv->ptp_clock = ptp_clock_register(&priv->ptp_clock_ops, diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index 298efc76a56b0c..69fe5717846b5b 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -318,6 +318,11 @@ static int gtp_inner_proto(struct sk_buff *skb, unsigned int hdrlen, static int gtp_rx(struct pdp_ctx *pctx, struct sk_buff *skb, unsigned int hdrlen, unsigned int role, __u16 inner_proto) { + if (skb_is_gso(skb)) { + netdev_dbg(pctx->dev, "GSO is not supported in GTP\n"); + goto err; + } + if (!gtp_check_ms(skb, pctx, hdrlen, role, inner_proto)) { netdev_dbg(pctx->dev, "No PDP ctx for this MS\n"); return 1; diff --git a/drivers/net/ieee802154/cc2520.c b/drivers/net/ieee802154/cc2520.c index 2b7034193a00b8..abfcfe07246a7b 100644 --- a/drivers/net/ieee802154/cc2520.c +++ b/drivers/net/ieee802154/cc2520.c @@ -1156,11 +1156,10 @@ static void cc2520_remove(struct spi_device *spi) { struct cc2520_private *priv = spi_get_drvdata(spi); - mutex_destroy(&priv->buffer_mutex); - flush_work(&priv->fifop_irqwork); - + disable_work_sync(&priv->fifop_irqwork); ieee802154_unregister_hw(priv->hw); ieee802154_free_hw(priv->hw); + mutex_destroy(&priv->buffer_mutex); } static const struct spi_device_id cc2520_ids[] = { diff --git a/drivers/net/ieee802154/mac802154_hwsim.c b/drivers/net/ieee802154/mac802154_hwsim.c index 6daa0f198b9fa3..a9bd1555d2dc7c 100644 --- a/drivers/net/ieee802154/mac802154_hwsim.c +++ b/drivers/net/ieee802154/mac802154_hwsim.c @@ -72,6 +72,8 @@ struct hwsim_phy { struct ieee802154_hw *hw; u32 idx; + /* Serializes phy->pib_updates. */ + spinlock_t pib_lock; struct hwsim_pib __rcu *pib; bool suspended; @@ -102,8 +104,6 @@ static int hwsim_update_pib(struct ieee802154_hw *hw, u8 page, u8 channel, if (!pib) return -ENOMEM; - pib_old = rtnl_dereference(phy->pib); - pib->page = page; pib->channel = channel; pib->filt.short_addr = filt->short_addr; @@ -112,7 +112,10 @@ static int hwsim_update_pib(struct ieee802154_hw *hw, u8 page, u8 channel, pib->filt.pan_coord = filt->pan_coord; pib->filt_level = filt_level; - rcu_assign_pointer(phy->pib, pib); + spin_lock_bh(&phy->pib_lock); + pib_old = rcu_replace_pointer(phy->pib, pib, + lockdep_is_held(&phy->pib_lock)); + spin_unlock_bh(&phy->pib_lock); kfree_rcu(pib_old, rcu); return 0; } @@ -952,6 +955,7 @@ static int hwsim_add_one(struct genl_info *info, struct device *dev, goto err_pib; } + spin_lock_init(&phy->pib_lock); pib->channel = 13; pib->filt.short_addr = cpu_to_le16(IEEE802154_ADDR_BROADCAST); pib->filt.pan_id = cpu_to_le16(IEEE802154_PANID_BROADCAST); diff --git a/drivers/net/mctp/mctp-i3c.c b/drivers/net/mctp/mctp-i3c.c index 88d9e36cd4a2bc..4e857dd5df642c 100644 --- a/drivers/net/mctp/mctp-i3c.c +++ b/drivers/net/mctp/mctp-i3c.c @@ -288,6 +288,7 @@ err: static int mctp_i3c_probe(struct i3c_device *i3c) { struct mctp_i3c_bus *b = NULL, *mbus = NULL; + int rc; /* Look for a known bus */ mutex_lock(&busdevs_lock); @@ -296,14 +297,16 @@ static int mctp_i3c_probe(struct i3c_device *i3c) mbus = b; break; } - mutex_unlock(&busdevs_lock); if (!mbus) { /* probably no "mctp-controller" property on the i3c bus */ - return -ENODEV; + rc = -ENODEV; + } else { + rc = mctp_i3c_add_device(mbus, i3c); } + mutex_unlock(&busdevs_lock); - return mctp_i3c_add_device(mbus, i3c); + return rc; } static void mctp_i3c_remove_device(struct mctp_i3c_device *mi) diff --git a/drivers/net/net_failover.c b/drivers/net/net_failover.c index 3f7d31033bae8b..1b5213e8707034 100644 --- a/drivers/net/net_failover.c +++ b/drivers/net/net_failover.c @@ -675,7 +675,7 @@ static int net_failover_slave_name_change(struct net_device *slave_dev, /* We need to bring up the slave after the rename by udev in case * open failed with EBUSY when it was registered. */ - dev_open(slave_dev, NULL); + netif_open(slave_dev, NULL); return 0; } diff --git a/drivers/net/phy/dp83867.c b/drivers/net/phy/dp83867.c index 88255e92b4cdbd..61a941aa02d944 100644 --- a/drivers/net/phy/dp83867.c +++ b/drivers/net/phy/dp83867.c @@ -1150,6 +1150,9 @@ static int dp83867_led_polarity_set(struct phy_device *phydev, int index, case PHY_LED_ACTIVE_LOW: polarity = 0; break; + case PHY_LED_ACTIVE_HIGH: + polarity = DP83867_LED_POLARITY(index); + break; default: return -EINVAL; } diff --git a/drivers/net/phy/dp83td510.c b/drivers/net/phy/dp83td510.c index d75dae6071ad65..9e9a41bf64574b 100644 --- a/drivers/net/phy/dp83td510.c +++ b/drivers/net/phy/dp83td510.c @@ -439,6 +439,9 @@ static int dp83td510_led_polarity_set(struct phy_device *phydev, int index, case PHY_LED_ACTIVE_LOW: polarity = 0; break; + case PHY_LED_ACTIVE_HIGH: + polarity = DP83TD510E_LED_POLARITY(index); + break; default: return -EINVAL; } diff --git a/drivers/net/phy/mediatek/mtk-ge.c b/drivers/net/phy/mediatek/mtk-ge.c index 73d9b72f9d9e2c..96d8ac5154e5e7 100644 --- a/drivers/net/phy/mediatek/mtk-ge.c +++ b/drivers/net/phy/mediatek/mtk-ge.c @@ -62,10 +62,38 @@ static void mtk_gephy_config_init(struct phy_device *phydev) FIELD_PREP(MTK_MCC_NEARECHO_OFFSET_MASK, 0x3)); } +static int mt7530_phy_probe(struct phy_device *phydev) +{ + /* The MT7530 internal GE PHY has broken EEE: with EEE advertised, + * some link partners fail to establish a stable link (on a 2-pair + * cable, 1000BASE-T training fails and the port loops instead of + * falling back). MediaTek recommends disabling EEE on this PHY. + * Clear the advertisement as early as possible, before anything + * can negotiate EEE with the link partner. + */ + return phy_write_mmd(phydev, MDIO_MMD_AN, MDIO_AN_EEE_ADV, 0); +} + static int mt7530_phy_config_init(struct phy_device *phydev) { + int ret; + mtk_gephy_config_init(phydev); + /* The probe() clear alone is not durable: phy_init_hw() replays only + * ->config_init after a PHY reset, with the register back at its + * EEE-advertising hardware default, and phy_probe() zeroes + * eee_disabled_modes (of_set_phy_eee_broken()) after ->probe already + * ran. Clear the advertisement again and mark EEE disabled, so that + * neither phylib nor userspace can re-enable it; dp83867 disables + * broken EEE from config_init() the same way. + */ + ret = phy_write_mmd(phydev, MDIO_MMD_AN, MDIO_AN_EEE_ADV, 0); + if (ret) + return ret; + + phy_disable_eee(phydev); + /* Increase post_update_timer */ phy_write_paged(phydev, MTK_PHY_PAGE_EXTENDED_3, MTK_PHY_RG_LPI_PCS_DSP_CTRL_REG11, 0x4b); @@ -100,6 +128,7 @@ static struct phy_driver mtk_gephy_driver[] = { { PHY_ID_MATCH_EXACT(MTK_GPHY_ID_MT7530), .name = "MediaTek MT7530 PHY", + .probe = mt7530_phy_probe, .config_init = mt7530_phy_config_init, /* Interrupts are handled by the switch, not the PHY * itself. diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 7397169236fdfe..27fd9aa2027a41 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -1630,8 +1630,10 @@ static void phylink_resolve(struct work_struct *w) if (pl->phylink_disable_state) { pl->link_failed = false; + link_state = pl->link_config; link_state.link = false; } else if (pl->link_failed) { + link_state = pl->link_config; link_state.link = false; retrigger = true; } else if (pl->act_link_an_mode == MLO_AN_FIXED) { diff --git a/drivers/net/ppp/ppp_async.c b/drivers/net/ppp/ppp_async.c index 93a7b0f6c4e7e0..6664686b1e041d 100644 --- a/drivers/net/ppp/ppp_async.c +++ b/drivers/net/ppp/ppp_async.c @@ -65,8 +65,6 @@ struct asyncppp { struct tasklet_struct tsk; - refcount_t refcnt; - struct completion dead; struct ppp_channel chan; /* interface to generic ppp layer */ unsigned char obuf[OBUFSIZE]; }; @@ -116,38 +114,6 @@ static const struct ppp_channel_ops async_ops = { * Routines implementing the PPP line discipline. */ -/* - * We have a potential race on dereferencing tty->disc_data, - * because the tty layer provides no locking at all - thus one - * cpu could be running ppp_asynctty_receive while another - * calls ppp_asynctty_close, which zeroes tty->disc_data and - * frees the memory that ppp_asynctty_receive is using. The best - * way to fix this is to use a rwlock in the tty struct, but for now - * we use a single global rwlock for all ttys in ppp line discipline. - * - * FIXME: this is no longer true. The _close path for the ldisc is - * now guaranteed to be sane. - */ -static DEFINE_RWLOCK(disc_data_lock); - -static struct asyncppp *ap_get(struct tty_struct *tty) -{ - struct asyncppp *ap; - - read_lock(&disc_data_lock); - ap = tty->disc_data; - if (ap != NULL) - refcount_inc(&ap->refcnt); - read_unlock(&disc_data_lock); - return ap; -} - -static void ap_put(struct asyncppp *ap) -{ - if (refcount_dec_and_test(&ap->refcnt)) - complete(&ap->dead); -} - /* * Called when a tty is put into PPP line discipline. Called in process * context. @@ -182,9 +148,6 @@ ppp_asynctty_open(struct tty_struct *tty) skb_queue_head_init(&ap->rqueue); tasklet_setup(&ap->tsk, ppp_async_process); - refcount_set(&ap->refcnt, 1); - init_completion(&ap->dead); - ap->chan.private = ap; ap->chan.ops = &async_ops; ap->chan.mtu = PPP_MRU; @@ -205,34 +168,18 @@ ppp_asynctty_open(struct tty_struct *tty) } /* - * Called when the tty is put into another line discipline - * or it hangs up. We have to wait for any cpu currently - * executing in any of the other ppp_asynctty_* routines to - * finish before we can call ppp_unregister_channel and free - * the asyncppp struct. This routine must be called from - * process context, not interrupt or softirq context. + * Called when the tty is put into another line discipline or it hangs up. + * This call is serialized against other ldisc functions. */ static void ppp_asynctty_close(struct tty_struct *tty) { - struct asyncppp *ap; + struct asyncppp *ap = tty->disc_data; - write_lock_irq(&disc_data_lock); - ap = tty->disc_data; - tty->disc_data = NULL; - write_unlock_irq(&disc_data_lock); if (!ap) return; - /* - * We have now ensured that nobody can start using ap from now - * on, but we have to wait for all existing users to finish. - * Note that ppp_unregister_channel ensures that no calls to - * our channel ops (i.e. ppp_async_send/ioctl) are in progress - * by the time it returns. - */ - if (!refcount_dec_and_test(&ap->refcnt)) - wait_for_completion(&ap->dead); + tty->disc_data = NULL; tasklet_kill(&ap->tsk); ppp_unregister_channel(&ap->chan); @@ -242,17 +189,6 @@ ppp_asynctty_close(struct tty_struct *tty) kfree(ap); } -/* - * Called on tty hangup in process context. - * - * Wait for I/O to driver to complete and unregister PPP channel. - * This is already done by the close routine, so just call that. - */ -static void ppp_asynctty_hangup(struct tty_struct *tty) -{ - ppp_asynctty_close(tty); -} - /* * Read does nothing - no data is ever available this way. * Pppd reads and writes packets via /dev/ppp instead. @@ -283,7 +219,7 @@ ppp_asynctty_write(struct tty_struct *tty, struct file *file, const u8 *buf, static int ppp_asynctty_ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg) { - struct asyncppp *ap = ap_get(tty); + struct asyncppp *ap = tty->disc_data; int err, val; int __user *p = (int __user *)arg; @@ -324,7 +260,6 @@ ppp_asynctty_ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg) err = tty_mode_ioctl(tty, cmd, arg); } - ap_put(ap); return err; } @@ -333,7 +268,7 @@ static void ppp_asynctty_receive(struct tty_struct *tty, const u8 *buf, const u8 *cflags, size_t count) { - struct asyncppp *ap = ap_get(tty); + struct asyncppp *ap = tty->disc_data; unsigned long flags; if (!ap) @@ -343,21 +278,19 @@ ppp_asynctty_receive(struct tty_struct *tty, const u8 *buf, const u8 *cflags, spin_unlock_irqrestore(&ap->recv_lock, flags); if (!skb_queue_empty(&ap->rqueue)) tasklet_schedule(&ap->tsk); - ap_put(ap); tty_unthrottle(tty); } static void ppp_asynctty_wakeup(struct tty_struct *tty) { - struct asyncppp *ap = ap_get(tty); + struct asyncppp *ap = tty->disc_data; clear_bit(TTY_DO_WRITE_WAKEUP, &tty->flags); if (!ap) return; set_bit(XMIT_WAKEUP, &ap->xmit_flags); tasklet_schedule(&ap->tsk); - ap_put(ap); } @@ -367,7 +300,6 @@ static struct tty_ldisc_ops ppp_ldisc = { .name = "ppp", .open = ppp_asynctty_open, .close = ppp_asynctty_close, - .hangup = ppp_asynctty_hangup, .read = ppp_asynctty_read, .write = ppp_asynctty_write, .ioctl = ppp_asynctty_ioctl, @@ -812,11 +744,8 @@ process_input_packet(struct asyncppp *ap) err: /* frame had an error, remember that, reset SC_TOSS & SC_ESCAPE */ ap->state = SC_PREV_ERROR; - if (skb) { - /* make skb appear as freshly allocated */ - skb_trim(skb, 0); - skb_reserve(skb, - skb_headroom(skb)); - } + kfree_skb(skb); + ap->rpkt = NULL; } /* Called when the tty driver has data for us. Runs parallel with the diff --git a/drivers/net/ppp/ppp_synctty.c b/drivers/net/ppp/ppp_synctty.c index b7f243b416f824..1b64e610f96091 100644 --- a/drivers/net/ppp/ppp_synctty.c +++ b/drivers/net/ppp/ppp_synctty.c @@ -38,11 +38,9 @@ #include #include #include -#include #include #include #include -#include #include #include @@ -69,8 +67,6 @@ struct syncppp { struct tasklet_struct tsk; - refcount_t refcnt; - struct completion dead_cmp; struct ppp_channel chan; /* interface to generic ppp layer */ }; @@ -118,37 +114,6 @@ ppp_print_buffer (const char *name, const __u8 *buf, int count) * Routines implementing the synchronous PPP line discipline. */ -/* - * We have a potential race on dereferencing tty->disc_data, - * because the tty layer provides no locking at all - thus one - * cpu could be running ppp_synctty_receive while another - * calls ppp_synctty_close, which zeroes tty->disc_data and - * frees the memory that ppp_synctty_receive is using. The best - * way to fix this is to use a rwlock in the tty struct, but for now - * we use a single global rwlock for all ttys in ppp line discipline. - * - * FIXME: Fixed in tty_io nowadays. - */ -static DEFINE_RWLOCK(disc_data_lock); - -static struct syncppp *sp_get(struct tty_struct *tty) -{ - struct syncppp *ap; - - read_lock(&disc_data_lock); - ap = tty->disc_data; - if (ap != NULL) - refcount_inc(&ap->refcnt); - read_unlock(&disc_data_lock); - return ap; -} - -static void sp_put(struct syncppp *ap) -{ - if (refcount_dec_and_test(&ap->refcnt)) - complete(&ap->dead_cmp); -} - /* * Called when a tty is put into sync-PPP line discipline. */ @@ -179,9 +144,6 @@ ppp_sync_open(struct tty_struct *tty) skb_queue_head_init(&ap->rqueue); tasklet_setup(&ap->tsk, ppp_sync_process); - refcount_set(&ap->refcnt, 1); - init_completion(&ap->dead_cmp); - ap->chan.private = ap; ap->chan.ops = &sync_ops; ap->chan.mtu = PPP_MRU; @@ -203,34 +165,18 @@ ppp_sync_open(struct tty_struct *tty) } /* - * Called when the tty is put into another line discipline - * or it hangs up. We have to wait for any cpu currently - * executing in any of the other ppp_synctty_* routines to - * finish before we can call ppp_unregister_channel and free - * the syncppp struct. This routine must be called from - * process context, not interrupt or softirq context. + * Called when the tty is put into another line discipline or it hangs up. + * This call is serialized against other ldisc functions. */ static void ppp_sync_close(struct tty_struct *tty) { - struct syncppp *ap; + struct syncppp *ap = tty->disc_data; - write_lock_irq(&disc_data_lock); - ap = tty->disc_data; - tty->disc_data = NULL; - write_unlock_irq(&disc_data_lock); if (!ap) return; - /* - * We have now ensured that nobody can start using ap from now - * on, but we have to wait for all existing users to finish. - * Note that ppp_unregister_channel ensures that no calls to - * our channel ops (i.e. ppp_sync_send/ioctl) are in progress - * by the time it returns. - */ - if (!refcount_dec_and_test(&ap->refcnt)) - wait_for_completion(&ap->dead_cmp); + tty->disc_data = NULL; tasklet_kill(&ap->tsk); ppp_unregister_channel(&ap->chan); @@ -239,17 +185,6 @@ ppp_sync_close(struct tty_struct *tty) kfree(ap); } -/* - * Called on tty hangup in process context. - * - * Wait for I/O to driver to complete and unregister PPP channel. - * This is already done by the close routine, so just call that. - */ -static void ppp_sync_hangup(struct tty_struct *tty) -{ - ppp_sync_close(tty); -} - /* * Read does nothing - no data is ever available this way. * Pppd reads and writes packets via /dev/ppp instead. @@ -275,7 +210,7 @@ ppp_sync_write(struct tty_struct *tty, struct file *file, const u8 *buf, static int ppp_synctty_ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg) { - struct syncppp *ap = sp_get(tty); + struct syncppp *ap = tty->disc_data; int __user *p = (int __user *)arg; int err, val; @@ -316,7 +251,6 @@ ppp_synctty_ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg) break; } - sp_put(ap); return err; } @@ -325,7 +259,7 @@ static void ppp_sync_receive(struct tty_struct *tty, const u8 *buf, const u8 *cflags, size_t count) { - struct syncppp *ap = sp_get(tty); + struct syncppp *ap = tty->disc_data; unsigned long flags; if (!ap) @@ -335,21 +269,19 @@ ppp_sync_receive(struct tty_struct *tty, const u8 *buf, const u8 *cflags, spin_unlock_irqrestore(&ap->recv_lock, flags); if (!skb_queue_empty(&ap->rqueue)) tasklet_schedule(&ap->tsk); - sp_put(ap); tty_unthrottle(tty); } static void ppp_sync_wakeup(struct tty_struct *tty) { - struct syncppp *ap = sp_get(tty); + struct syncppp *ap = tty->disc_data; clear_bit(TTY_DO_WRITE_WAKEUP, &tty->flags); if (!ap) return; set_bit(XMIT_WAKEUP, &ap->xmit_flags); tasklet_schedule(&ap->tsk); - sp_put(ap); } @@ -359,7 +291,6 @@ static struct tty_ldisc_ops ppp_sync_ldisc = { .name = "pppsync", .open = ppp_sync_open, .close = ppp_sync_close, - .hangup = ppp_sync_hangup, .read = ppp_sync_read, .write = ppp_sync_write, .ioctl = ppp_synctty_ioctl, @@ -526,17 +457,9 @@ ppp_sync_txmunge(struct syncppp *ap, struct sk_buff *skb) /* prepend address/control fields if necessary */ if ((ap->flags & SC_COMP_AC) == 0 || islcp) { - if (skb_headroom(skb) < 2) { - struct sk_buff *npkt = dev_alloc_skb(skb->len + 2); - if (npkt == NULL) { - kfree_skb(skb); - return NULL; - } - skb_reserve(npkt,2); - skb_copy_from_linear_data(skb, - skb_put(npkt, skb->len), skb->len); - consume_skb(skb); - skb = npkt; + if (skb_cow_head(skb, 2)) { + kfree_skb(skb); + return NULL; } skb_push(skb,2); skb->data[0] = PPP_ALLSTATIONS; diff --git a/drivers/net/usb/cx82310_eth.c b/drivers/net/usb/cx82310_eth.c index 068acb052adb05..5df657acf3d557 100644 --- a/drivers/net/usb/cx82310_eth.c +++ b/drivers/net/usb/cx82310_eth.c @@ -282,6 +282,7 @@ static int cx82310_rx_fixup(struct usbnet *dev, struct sk_buff *skb) if (len == 0xffff) { netdev_info(dev->net, "router was rebooted, re-enabling ethernet mode"); schedule_work(&priv->reenable_work); + return 0; } else if (len > CX82310_MTU) { netdev_err(dev->net, "RX packet too long: %d B\n", len); return 0; diff --git a/drivers/net/usb/hso.c b/drivers/net/usb/hso.c index c1aec67688ae79..71caa3764b239a 100644 --- a/drivers/net/usb/hso.c +++ b/drivers/net/usb/hso.c @@ -1547,10 +1547,10 @@ hso_wait_modem_status(struct hso_serial *serial, unsigned long arg) spin_unlock_irq(&serial->serial_lock); add_wait_queue(&tiocmget->waitq, &wait); for (;;) { + set_current_state(TASK_INTERRUPTIBLE); spin_lock_irq(&serial->serial_lock); memcpy(&cnow, &tiocmget->icount, sizeof(struct uart_icount)); spin_unlock_irq(&serial->serial_lock); - set_current_state(TASK_INTERRUPTIBLE); if (((arg & TIOCM_RNG) && (cnow.rng != cprev.rng)) || ((arg & TIOCM_DSR) && (cnow.dsr != cprev.dsr)) || ((arg & TIOCM_CD) && (cnow.dcd != cprev.dcd))) { diff --git a/drivers/net/usb/pegasus.c b/drivers/net/usb/pegasus.c index 8700eeb8e22d07..aba1a640fc2688 100644 --- a/drivers/net/usb/pegasus.c +++ b/drivers/net/usb/pegasus.c @@ -43,21 +43,12 @@ static bool loopback; static bool mii_mode; static char *devid; -static struct usb_eth_dev usb_dev_id[] = { -#define PEGASUS_DEV(pn, vid, pid, flags) \ - {.name = pn, .vendor = vid, .device = pid, .private = flags}, -#define PEGASUS_DEV_CLASS(pn, vid, pid, dclass, flags) \ - PEGASUS_DEV(pn, vid, pid, flags) -#include "pegasus.h" -#undef PEGASUS_DEV -#undef PEGASUS_DEV_CLASS - {NULL, 0, 0, 0}, - {NULL, 0, 0, 0} -}; +static struct usb_eth_dev dynamic_id_info = {}; static struct usb_device_id pegasus_ids[] = { #define PEGASUS_DEV(pn, vid, pid, flags) \ - {.match_flags = USB_DEVICE_ID_MATCH_DEVICE, .idVendor = vid, .idProduct = pid}, + {.match_flags = USB_DEVICE_ID_MATCH_DEVICE, .idVendor = vid, .idProduct = pid, \ + .driver_info = (kernel_ulong_t)&(const struct usb_eth_dev) {.name = pn, .private = flags}}, /* * The Belkin F8T012xx1 bluetooth adaptor has the same vendor and product * IDs as the Belkin F5D5050, so we need to teach the pegasus driver to @@ -66,7 +57,8 @@ static struct usb_device_id pegasus_ids[] = { */ #define PEGASUS_DEV_CLASS(pn, vid, pid, dclass, flags) \ {.match_flags = (USB_DEVICE_ID_MATCH_DEVICE | USB_DEVICE_ID_MATCH_DEV_CLASS), \ - .idVendor = vid, .idProduct = pid, .bDeviceClass = dclass}, + .idVendor = vid, .idProduct = pid, .bDeviceClass = dclass, \ + .driver_info = (kernel_ulong_t)&(const struct usb_eth_dev) {.name = pn, .private = flags}}, #include "pegasus.h" #undef PEGASUS_DEV #undef PEGASUS_DEV_CLASS @@ -402,12 +394,12 @@ static inline int reset_mac(pegasus_t *pegasus) if (i == REG_TIMEOUT) return -ETIMEDOUT; - if (usb_dev_id[pegasus->dev_index].vendor == VENDOR_LINKSYS || - usb_dev_id[pegasus->dev_index].vendor == VENDOR_DLINK) { + if (le16_to_cpu(pegasus->usb->descriptor.idVendor) == VENDOR_LINKSYS || + le16_to_cpu(pegasus->usb->descriptor.idVendor) == VENDOR_DLINK) { set_register(pegasus, Gpio0, 0x24); set_register(pegasus, Gpio0, 0x26); } - if (usb_dev_id[pegasus->dev_index].vendor == VENDOR_ELCON) { + if (le16_to_cpu(pegasus->usb->descriptor.idVendor) == VENDOR_ELCON) { __u16 auxmode; ret = read_mii_word(pegasus, 3, 0x1b, &auxmode); if (ret < 0) @@ -445,9 +437,9 @@ static int enable_net_traffic(struct net_device *dev, struct usb_device *usb) memcpy(pegasus->eth_regs, data, sizeof(data)); ret = set_registers(pegasus, EthCtrl0, 3, data); - if (usb_dev_id[pegasus->dev_index].vendor == VENDOR_LINKSYS || - usb_dev_id[pegasus->dev_index].vendor == VENDOR_LINKSYS2 || - usb_dev_id[pegasus->dev_index].vendor == VENDOR_DLINK) { + if (le16_to_cpu(pegasus->usb->descriptor.idVendor) == VENDOR_LINKSYS || + le16_to_cpu(pegasus->usb->descriptor.idVendor) == VENDOR_LINKSYS2 || + le16_to_cpu(pegasus->usb->descriptor.idVendor) == VENDOR_DLINK) { u16 auxmode; ret = read_mii_word(pegasus, 0, 0x1b, &auxmode); if (ret < 0) @@ -1153,7 +1145,7 @@ static int pegasus_probe(struct usb_interface *intf, struct usb_device *dev = interface_to_usbdev(intf); struct net_device *net; pegasus_t *pegasus; - int dev_index = id - pegasus_ids; + const struct usb_eth_dev *info = (const struct usb_eth_dev *)id->driver_info; int res = -ENOMEM; static const u8 bulk_ep_addr[] = { PEGASUS_USB_EP_BULK_IN | USB_DIR_IN, @@ -1178,7 +1170,6 @@ static int pegasus_probe(struct usb_interface *intf, goto out; pegasus = netdev_priv(net); - pegasus->dev_index = dev_index; pegasus->intf = intf; res = alloc_urbs(pegasus); @@ -1206,7 +1197,7 @@ static int pegasus_probe(struct usb_interface *intf, pegasus->msg_enable = netif_msg_init(msg_level, NETIF_MSG_DRV | NETIF_MSG_PROBE | NETIF_MSG_LINK); - pegasus->features = usb_dev_id[dev_index].private; + pegasus->features = info ? info->private : DEFAULT_GPIO_RESET; res = get_interrupt_interval(pegasus); if (res) goto out2; @@ -1235,7 +1226,7 @@ static int pegasus_probe(struct usb_interface *intf, queue_delayed_work(system_long_wq, &pegasus->carrier_check, CARRIER_CHECK_DELAY); dev_info(&intf->dev, "%s, %s, %pM\n", net->name, - usb_dev_id[dev_index].name, net->dev_addr); + info ? info->name : "(unknown)", net->dev_addr); return 0; out3: @@ -1325,8 +1316,9 @@ static struct usb_driver pegasus_driver = { static void __init parse_id(char *id) { - unsigned int vendor_id = 0, device_id = 0, flags = 0, i = 0; + unsigned int vendor_id = 0, device_id = 0, flags = 0; char *token, *name = NULL; + int dyn_id_index = ARRAY_SIZE(pegasus_ids) - 2; token = strsep(&id, ":"); if (token) @@ -1348,14 +1340,12 @@ static void __init parse_id(char *id) if (device_id > 0x10000 || device_id == 0) return; - for (i = 0; usb_dev_id[i].name; i++); - usb_dev_id[i].name = name; - usb_dev_id[i].vendor = vendor_id; - usb_dev_id[i].device = device_id; - usb_dev_id[i].private = flags; - pegasus_ids[i].match_flags = USB_DEVICE_ID_MATCH_DEVICE; - pegasus_ids[i].idVendor = vendor_id; - pegasus_ids[i].idProduct = device_id; + dynamic_id_info.name = name; + dynamic_id_info.private = flags; + pegasus_ids[dyn_id_index].match_flags = USB_DEVICE_ID_MATCH_DEVICE; + pegasus_ids[dyn_id_index].idVendor = vendor_id; + pegasus_ids[dyn_id_index].idProduct = device_id; + pegasus_ids[dyn_id_index].driver_info = (kernel_ulong_t)&dynamic_id_info; } static int __init pegasus_init(void) diff --git a/drivers/net/usb/pegasus.h b/drivers/net/usb/pegasus.h index a05b143155ba86..ccdedcef52e76e 100644 --- a/drivers/net/usb/pegasus.h +++ b/drivers/net/usb/pegasus.h @@ -85,7 +85,6 @@ typedef struct pegasus { unsigned features; u32 msg_enable; u32 wolopts; - int dev_index; int intr_interval; struct tasklet_struct rx_tl; struct delayed_work carrier_check; @@ -102,8 +101,6 @@ typedef struct pegasus { struct usb_eth_dev { char *name; - __u16 vendor; - __u16 device; __u32 private; /* LSB is gpio reset value */ }; diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c index 44ea8499e78779..e045e1ee9e5947 100644 --- a/drivers/net/vxlan/vxlan_core.c +++ b/drivers/net/vxlan/vxlan_core.c @@ -996,6 +996,12 @@ static int vxlan_fdb_update_existing(struct vxlan_dev *vxlan, return -EOPNOTSUPP; } + if (rcu_access_pointer(f->nh) && + !(state & (NUD_PERMANENT | NUD_NOARP))) { + NL_SET_ERR_MSG(extack, "Cannot make a nexthop fdb dynamic"); + return -EOPNOTSUPP; + } + /* Do not allow an externally learned entry to take over an entry added * by the user. */ @@ -1257,6 +1263,11 @@ static int vxlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], if (err) return err; + if (nhid && !(ndm->ndm_state & (NUD_PERMANENT | NUD_NOARP))) { + NL_SET_ERR_MSG(extack, "A nexthop fdb cannot be dynamic"); + return -EINVAL; + } + if (vxlan->default_dst.remote_ip.sa.sa_family != ip.sa.sa_family) return -EAFNOSUPPORT; @@ -2362,7 +2373,7 @@ void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, struct ip_tunnel_key key; struct vxlan_dev *vxlan = netdev_priv(dev); const struct iphdr *old_iph; - struct vxlan_metadata _md; + struct vxlan_metadata _md = {}; struct vxlan_metadata *md = &_md; unsigned int pkt_len = skb->len; __be16 src_port = 0, dst_port; diff --git a/drivers/net/vxlan/vxlan_mdb.c b/drivers/net/vxlan/vxlan_mdb.c index d71e1925ecfdbd..841f42ffecb9aa 100644 --- a/drivers/net/vxlan/vxlan_mdb.c +++ b/drivers/net/vxlan/vxlan_mdb.c @@ -354,6 +354,10 @@ static bool vxlan_mdb_is_valid_source(const struct nlattr *attr, __be16 proto, NL_SET_ERR_MSG_MOD(extack, "IPv4 multicast source address is not allowed"); return false; } + if (ipv4_is_zeronet(nla_get_in_addr(attr))) { + NL_SET_ERR_MSG_MOD(extack, "IPv4 all-zeros source address is not allowed"); + return false; + } break; #if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): { @@ -368,6 +372,10 @@ static bool vxlan_mdb_is_valid_source(const struct nlattr *attr, __be16 proto, NL_SET_ERR_MSG_MOD(extack, "IPv6 multicast source address is not allowed"); return false; } + if (ipv6_addr_any(&src)) { + NL_SET_ERR_MSG_MOD(extack, "IPv6 all-zeros source address is not allowed"); + return false; + } break; } #endif diff --git a/drivers/net/wireless/ath/ath9k/hif_usb.c b/drivers/net/wireless/ath/ath9k/hif_usb.c index 47f904e7e65297..d3491ff08e6ef5 100644 --- a/drivers/net/wireless/ath/ath9k/hif_usb.c +++ b/drivers/net/wireless/ath/ath9k/hif_usb.c @@ -1087,7 +1087,7 @@ static int ath9k_hif_usb_download_fw(struct hif_device_usb *hif_dev) } kfree(buf); - if (IS_AR7010_DEVICE(hif_dev->usb_device_id->driver_info)) + if (IS_AR7010_DEVICE(hif_dev->id_info)) firm_offset = AR7010_FIRMWARE_TEXT; else firm_offset = AR9271_FIRMWARE_TEXT; @@ -1182,7 +1182,7 @@ static int ath9k_hif_request_firmware(struct hif_device_usb *hif_dev, if (MAJOR_VERSION_REQ == 1 && hif_dev->fw_minor_index == 3) { const char *filename; - if (IS_AR7010_DEVICE(hif_dev->usb_device_id->driver_info)) + if (IS_AR7010_DEVICE(hif_dev->id_info)) filename = FIRMWARE_AR7010_1_1; else filename = FIRMWARE_AR9271; @@ -1198,7 +1198,7 @@ static int ath9k_hif_request_firmware(struct hif_device_usb *hif_dev, return -ENOENT; } else { - if (IS_AR7010_DEVICE(hif_dev->usb_device_id->driver_info)) + if (IS_AR7010_DEVICE(hif_dev->id_info)) chip = "7010"; else chip = "9271"; @@ -1255,9 +1255,9 @@ static void ath9k_hif_usb_firmware_cb(const struct firmware *fw, void *context) ret = ath9k_htc_hw_init(hif_dev->htc_handle, &hif_dev->interface->dev, - hif_dev->usb_device_id->idProduct, + le16_to_cpu(hif_dev->udev->descriptor.idProduct), hif_dev->udev->product, - hif_dev->usb_device_id->driver_info); + hif_dev->id_info); if (ret) { ret = -EINVAL; goto err_htc_hw_init; @@ -1369,7 +1369,7 @@ static int ath9k_hif_usb_probe(struct usb_interface *interface, hif_dev->udev = udev; hif_dev->interface = interface; - hif_dev->usb_device_id = id; + hif_dev->id_info = id->driver_info; #ifdef CONFIG_PM udev->reset_resume = 1; #endif diff --git a/drivers/net/wireless/ath/ath9k/hif_usb.h b/drivers/net/wireless/ath/ath9k/hif_usb.h index dc0b0fa5c32574..b3e7b0fb54b841 100644 --- a/drivers/net/wireless/ath/ath9k/hif_usb.h +++ b/drivers/net/wireless/ath/ath9k/hif_usb.h @@ -115,7 +115,7 @@ struct cmd_buf { struct hif_device_usb { struct usb_device *udev; struct usb_interface *interface; - const struct usb_device_id *usb_device_id; + int id_info; const void *fw_data; size_t fw_size; struct completion fw_done; diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c index 25b9437250f7ba..45439652c847b6 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c @@ -415,7 +415,8 @@ static int mt7921_load_clc(struct mt792x_dev *dev, const char *fw_name) struct mt76_dev *mdev = &dev->mt76; struct mt792x_phy *phy = &dev->phy; const struct firmware *fw; - int ret, i, len, offset = 0; + size_t clc_len, fw_data_len, len, offset = 0; + int ret, i; u8 *clc_base = NULL, hw_encap = 0; dev->phy.clc_chan_conf = 0xff; @@ -441,13 +442,21 @@ static int mt7921_load_clc(struct mt792x_dev *dev, const char *fw_name) } hdr = (const void *)(fw->data + fw->size - sizeof(*hdr)); + if (hdr->n_region > (fw->size - sizeof(*hdr)) / sizeof(*region)) { + dev_err(mdev->dev, "Invalid firmware region table\n"); + ret = -EINVAL; + goto out; + } + fw_data_len = fw->size - sizeof(*hdr) - + hdr->n_region * sizeof(*region); + for (i = 0; i < hdr->n_region; i++) { region = (const void *)((const u8 *)hdr - (hdr->n_region - i) * sizeof(*region)); len = le32_to_cpu(region->len); /* check if we have valid buffer size */ - if (offset + len > fw->size) { + if (len > fw_data_len - offset) { dev_err(mdev->dev, "Invalid firmware region\n"); ret = -EINVAL; goto out; @@ -464,8 +473,24 @@ static int mt7921_load_clc(struct mt792x_dev *dev, const char *fw_name) if (!clc_base) goto out; - for (offset = 0; offset < len; offset += le32_to_cpu(clc->len)) { + for (offset = 0; offset < len; offset += clc_len) { + if (len - offset < sizeof(*clc)) { + dev_err(mdev->dev, "Invalid CLC record\n"); + ret = -EINVAL; + goto out; + } + clc = (const struct mt7921_clc *)(clc_base + offset); + clc_len = le32_to_cpu(clc->len); + if (clc_len < sizeof(*clc) || clc_len > len - offset) { + dev_err(mdev->dev, "Invalid CLC record\n"); + ret = -EINVAL; + goto out; + } + + /* Newer firmware may add records this driver does not use yet */ + if (clc->idx >= ARRAY_SIZE(phy->clc)) + continue; /* do not init buf again if chip reset triggered */ if (phy->clc[clc->idx]) @@ -477,7 +502,7 @@ static int mt7921_load_clc(struct mt792x_dev *dev, const char *fw_name) continue; phy->clc[clc->idx] = devm_kmemdup(mdev->dev, clc, - le32_to_cpu(clc->len), + clc_len, GFP_KERNEL); if (!phy->clc[clc->idx]) { diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 0b80db7a0599f0..a73cc6a43f5e6c 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -148,8 +148,6 @@ static const struct class nvme_ns_chr_class = { }; static void nvme_put_subsystem(struct nvme_subsystem *subsys); -static void nvme_remove_invalid_namespaces(struct nvme_ctrl *ctrl, - unsigned nsid); static void nvme_update_keep_alive(struct nvme_ctrl *ctrl, struct nvme_command *cmd); static int nvme_get_log_lsi(struct nvme_ctrl *ctrl, u32 nsid, u8 log_page, @@ -1594,7 +1592,7 @@ static int nvme_identify_ns_descs(struct nvme_ctrl *ctrl, } if (nvme_multi_css(ctrl) && !csi_seen) { - dev_warn(ctrl->device, "Command set not reported for nsid:%d\n", + dev_warn(ctrl->device, "Command set not reported for nsid:%u\n", info->nsid); status = -EINVAL; } @@ -2323,14 +2321,6 @@ static int nvme_query_fdp_info(struct nvme_ns *ns, struct nvme_ns_info *info) size_t size; int i, ret; - /* - * The FDP configuration is static for the lifetime of the namespace, - * so return immediately if we've already registered this namespace's - * streams. - */ - if (head->nr_plids) - return 0; - ret = nvme_get_features(ctrl, NVME_FEAT_FDP, info->endgid, NULL, 0, &fdp); if (ret) { @@ -2377,6 +2367,7 @@ static int nvme_query_fdp_info(struct nvme_ns *ns, struct nvme_ns_info *info) for (i = 0; i < head->nr_plids; i++) head->plids[i] = le16_to_cpu(ruhs->ruhsd[i].pid); + head->write_stream_granularity = min(info->runs, U32_MAX); free: kfree(ruhs); return ret; @@ -2424,12 +2415,6 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns, goto out; } - if (ns->ctrl->ctratt & NVME_CTRL_ATTR_FDPS) { - ret = nvme_query_fdp_info(ns, info); - if (ret < 0) - goto out; - } - if (nvme_invalid_lba_sz(le64_to_cpu(id->nsze), id->lbaf[lbaf].ds - SECTOR_SHIFT, &capacity)) { dev_warn_once(ns->ctrl->device, @@ -2489,10 +2474,7 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns, capacity = 0; lim.max_write_streams = ns->head->nr_plids; - if (lim.max_write_streams) - lim.write_stream_granularity = min(info->runs, U32_MAX); - else - lim.write_stream_granularity = 0; + lim.write_stream_granularity = ns->head->write_stream_granularity; /* * Only set the DEAC bit if the device guarantees that reads from @@ -3292,6 +3274,7 @@ static bool nvme_validate_cntlid(struct nvme_subsystem *subsys, } static int nvme_init_subsystem(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id) + __context_unsafe(/* initialize unpublished/lock-guarded variables */) { struct nvme_subsystem *subsys, *found; int ret; @@ -3863,6 +3846,7 @@ static const struct file_operations nvme_dev_fops = { static struct nvme_ns_head *nvme_find_ns_head(struct nvme_ctrl *ctrl, unsigned nsid) + __must_hold(&ctrl->subsys->lock) { struct nvme_ns_head *h; @@ -3885,6 +3869,7 @@ static struct nvme_ns_head *nvme_find_ns_head(struct nvme_ctrl *ctrl, static int nvme_subsys_check_duplicate_ids(struct nvme_subsystem *subsys, struct nvme_ns_ids *ids) + __must_hold(&subsys->lock) { bool has_uuid = !uuid_is_null(&ids->uuid); bool has_nguid = memchr_inv(ids->nguid, 0, sizeof(ids->nguid)); @@ -3984,9 +3969,11 @@ static void nvme_add_ns_cdev(struct nvme_ns *ns) set_bit(NVME_NS_CDEV_LIVE, &ns->flags); } -static struct nvme_ns_head *nvme_alloc_ns_head(struct nvme_ctrl *ctrl, +static struct nvme_ns_head *nvme_alloc_ns_head(struct nvme_ns *ns, struct nvme_ns_info *info) + __must_hold(&ns->ctrl->subsys->lock) { + struct nvme_ctrl *ctrl = ns->ctrl; struct nvme_ns_head *head; size_t size = sizeof(*head); int ret = -ENOMEM; @@ -4014,6 +4001,7 @@ static struct nvme_ns_head *nvme_alloc_ns_head(struct nvme_ctrl *ctrl, ratelimit_state_init(&head->rs_nuse, 5 * HZ, 1); ratelimit_set_flags(&head->rs_nuse, RATELIMIT_MSG_ON_RELEASE); kref_init(&head->ref); + ns->head = head; if (head->ids.csi) { ret = nvme_get_effects_log(ctrl, head->ids.csi, &head->effects); @@ -4022,21 +4010,30 @@ static struct nvme_ns_head *nvme_alloc_ns_head(struct nvme_ctrl *ctrl, } else head->effects = ctrl->effects; + if (ctrl->ctratt & NVME_CTRL_ATTR_FDPS) { + ret = nvme_query_fdp_info(ns, info); + if (ret < 0) + goto out_cleanup_srcu; + } + ret = nvme_mpath_alloc_disk(ctrl, head); if (ret) - goto out_cleanup_srcu; + goto out_cleanup_fdp; list_add_tail(&head->entry, &ctrl->subsys->nsheads); kref_get(&ctrl->subsys->ref); return head; +out_cleanup_fdp: + kfree(head->plids); out_cleanup_srcu: cleanup_srcu_struct(&head->srcu); out_ida_remove: ida_free(&ctrl->subsys->ns_ida, head->instance); out_free_head: kfree(head); + ns->head = NULL; out: if (ret > 0) ret = blk_status_to_errno(nvme_error_status(ret)); @@ -4098,13 +4095,13 @@ static int nvme_init_ns_head(struct nvme_ns *ns, struct nvme_ns_info *info) ((ns->ctrl->subsys->cmic & NVME_CTRL_CMIC_MULTI_CTRL) && info->is_shared)) { dev_err(ctrl->device, - "ignoring nsid %d because of duplicate IDs\n", + "ignoring nsid %u because of duplicate IDs\n", info->nsid); return ret; } dev_err(ctrl->device, - "clearing duplicate IDs for nsid %d\n", info->nsid); + "clearing duplicate IDs for nsid %u\n", info->nsid); dev_err(ctrl->device, "use of /dev/disk/by-id/ may cause data corruption\n"); memset(&info->ids.nguid, 0, sizeof(info->ids.nguid)); @@ -4119,11 +4116,11 @@ static int nvme_init_ns_head(struct nvme_ns *ns, struct nvme_ns_info *info) ret = nvme_subsys_check_duplicate_ids(ctrl->subsys, &info->ids); if (ret) { dev_err(ctrl->device, - "duplicate IDs in subsystem for nsid %d\n", + "duplicate IDs in subsystem for nsid %u\n", info->nsid); goto out_unlock; } - head = nvme_alloc_ns_head(ctrl, info); + head = nvme_alloc_ns_head(ns, info); if (IS_ERR(head)) { ret = PTR_ERR(head); goto out_unlock; @@ -4133,20 +4130,20 @@ static int nvme_init_ns_head(struct nvme_ns *ns, struct nvme_ns_info *info) if ((!info->is_shared || !head->shared) && !list_empty(&head->list)) { dev_err(ctrl->device, - "Duplicate unshared namespace %d\n", + "Duplicate unshared namespace %u\n", info->nsid); goto out_put_ns_head; } if (!nvme_ns_ids_equal(&head->ids, &info->ids)) { dev_err(ctrl->device, - "IDs don't match for shared namespace %d\n", + "IDs don't match for shared namespace %u\n", info->nsid); goto out_put_ns_head; } if (!multipath) { dev_warn(ctrl->device, - "Found shared namespace %d, but multipathing not supported.\n", + "Found shared namespace %u, but multipathing not supported.\n", info->nsid); dev_warn_once(ctrl->device, "Shared namespace support requires core_nvme.multipath=Y.\n"); @@ -4395,7 +4392,7 @@ static void nvme_validate_ns(struct nvme_ns *ns, struct nvme_ns_info *info) if (!nvme_ns_ids_equal(&ns->head->ids, &info->ids)) { dev_err(ns->ctrl->device, - "identifiers changed for nsid %d\n", ns->head->ns_id); + "identifiers changed for nsid %u\n", ns->head->ns_id); goto out; } @@ -4422,7 +4419,7 @@ static void nvme_scan_ns(struct nvme_ctrl *ctrl, unsigned nsid) if (info.ids.csi != NVME_CSI_NVM && !nvme_multi_css(ctrl)) { dev_warn(ctrl->device, - "command set not reported for nsid: %d\n", nsid); + "command set not reported for nsid: %u\n", nsid); return; } @@ -4486,15 +4483,16 @@ static void nvme_scan_ns_async(void *data, async_cookie_t cookie) nvme_scan_ns(scan_info->ctrl, nsid); } -static void nvme_remove_invalid_namespaces(struct nvme_ctrl *ctrl, - unsigned nsid) +static void nvme_remove_nsid_range(struct nvme_ctrl *ctrl, u32 start, u32 end) { struct nvme_ns *ns, *next; LIST_HEAD(rm_list); mutex_lock(&ctrl->namespaces_lock); list_for_each_entry_safe(ns, next, &ctrl->namespaces, list) { - if (ns->head->ns_id > nsid) { + if (ns->head->ns_id >= end) + break; + if (ns->head->ns_id > start) { list_del_rcu(&ns->list); synchronize_srcu(&ctrl->srcu); list_add_tail_rcu(&ns->list, &rm_list); @@ -4544,13 +4542,14 @@ static int nvme_scan_ns_list(struct nvme_ctrl *ctrl) goto out; async_schedule_domain(nvme_scan_ns_async, &scan_info, &domain); - while (++prev < nsid) - nvme_ns_remove_by_nsid(ctrl, prev); + if (prev + 1 < nsid) + nvme_remove_nsid_range(ctrl, prev, nsid); + prev = max(prev + 1, nsid); } async_synchronize_full_domain(&domain); } out: - nvme_remove_invalid_namespaces(ctrl, prev); + nvme_remove_nsid_range(ctrl, prev, UINT_MAX); free: async_synchronize_full_domain(&domain); kfree(ns_list); @@ -4570,7 +4569,7 @@ static void nvme_scan_ns_sequential(struct nvme_ctrl *ctrl) for (i = 1; i <= nn; i++) nvme_scan_ns(ctrl, i); - nvme_remove_invalid_namespaces(ctrl, nn); + nvme_remove_nsid_range(ctrl, nn, UINT_MAX); } static void nvme_clear_changed_ns_log(struct nvme_ctrl *ctrl) diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 957ded0c6f53b3..cfdcf53db5abd0 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -503,7 +503,8 @@ struct nvme_subsystem { struct list_head entry; struct mutex lock; struct list_head ctrls; - struct list_head nsheads; + struct list_head nsheads + __guarded_by(&lock); char subnqn[NVMF_NQN_SIZE]; char serial[20]; char model[40]; @@ -567,6 +568,7 @@ struct nvme_ns_head { u16 nr_plids; u16 *plids; + u32 write_stream_granularity; #ifdef CONFIG_NVME_MULTIPATH struct bio_list requeue_list; spinlock_t requeue_lock; @@ -575,7 +577,8 @@ struct nvme_ns_head { struct mutex lock; unsigned long flags; struct delayed_work remove_work; - unsigned int delayed_removal_secs; + unsigned int delayed_removal_secs + __guarded_by(&subsys->lock); atomic_long_t io_requeue_no_usable_path_count; atomic_long_t io_fail_no_available_path_count; #define NVME_NSHEAD_DISK_LIVE 0 @@ -1046,9 +1049,12 @@ static inline bool nvme_ctrl_use_ana(struct nvme_ctrl *ctrl) return ctrl->ana_log_buf != NULL; } -void nvme_mpath_unfreeze(struct nvme_subsystem *subsys); -void nvme_mpath_wait_freeze(struct nvme_subsystem *subsys); -void nvme_mpath_start_freeze(struct nvme_subsystem *subsys); +void nvme_mpath_unfreeze(struct nvme_subsystem *subsys) + __must_hold(&subsys->lock); +void nvme_mpath_wait_freeze(struct nvme_subsystem *subsys) + __must_hold(&subsys->lock); +void nvme_mpath_start_freeze(struct nvme_subsystem *subsys) + __must_hold(&subsys->lock); void nvme_mpath_default_iopolicy(struct nvme_subsystem *subsys); void nvme_failover_req(struct request *req); void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl); diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 6909e354279427..618ee954442635 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -2003,7 +2003,7 @@ static blk_status_t nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx, struct ib_device *dev; bool queue_ready = test_bit(NVME_RDMA_Q_LIVE, &queue->flags); blk_status_t ret; - int err; + int err = 0; WARN_ON_ONCE(rq->tag < 0); @@ -2059,16 +2059,18 @@ static blk_status_t nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx, err_unmap: nvme_rdma_unmap_data(queue, rq); err: - if (err == -EIO) - ret = nvme_host_path_error(rq); - else if (err == -ENOMEM || err == -EAGAIN) - ret = BLK_STS_RESOURCE; - else - ret = BLK_STS_IOERR; - nvme_cleanup_cmd(rq); + if (err != -EIO) { + nvme_cleanup_cmd(rq); + if (err == -ENOMEM || err == -EAGAIN) + ret = BLK_STS_RESOURCE; + else + ret = BLK_STS_IOERR; + } unmap_qe: ib_dma_unmap_single(dev, req->sqe.dma, sizeof(struct nvme_command), DMA_TO_DEVICE); + if (err == -EIO) + return nvme_host_path_error(rq); return ret; } diff --git a/drivers/nvme/host/sysfs.c b/drivers/nvme/host/sysfs.c index 75b2d69b59578e..be94739e17dcf9 100644 --- a/drivers/nvme/host/sysfs.c +++ b/drivers/nvme/host/sysfs.c @@ -166,7 +166,7 @@ static DEVICE_ATTR_RO(eui); static ssize_t nsid_show(struct device *dev, struct device_attribute *attr, char *buf) { - return sysfs_emit(buf, "%d\n", dev_to_ns_head(dev)->ns_id); + return sysfs_emit(buf, "%u\n", dev_to_ns_head(dev)->ns_id); } static DEVICE_ATTR_RO(nsid); diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index ddbb34a22f688b..52efc6e4f76239 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -411,8 +411,13 @@ static inline void nvme_tcp_queue_request(struct nvme_tcp_request *req, * if we're the first on the send_list and we can try to send * directly, otherwise queue io_work. Also, only do that if we * are on the same cpu, so we don't introduce contention. + * + * TLS kTLS send takes ctx->tx_lock while blk_mq holds set->srcu. + * lockdep reports circular locking via elevator_lock. Defer TLS + * sends to the io workqueue instead of inline from this path. */ if (queue->io_cpu == raw_smp_processor_id() && + !nvme_tcp_queue_tls(queue) && empty && mutex_trylock(&queue->send_mutex)) { nvme_tcp_send_all(queue); mutex_unlock(&queue->send_mutex); diff --git a/drivers/nvme/host/zns.c b/drivers/nvme/host/zns.c index 8ed1b6a33454e6..9477cfbd3a5130 100644 --- a/drivers/nvme/host/zns.c +++ b/drivers/nvme/host/zns.c @@ -48,12 +48,12 @@ int nvme_query_zone_info(struct nvme_ns *ns, unsigned lbaf, NVME_CMD_EFFECTS_CSUPP)) { if (test_and_clear_bit(NVME_NS_FORCE_RO, &ns->flags)) dev_warn(ns->ctrl->device, - "Zone Append supported for zoned namespace:%d. Remove read-only mode\n", + "Zone Append supported for zoned namespace:%u. Remove read-only mode\n", ns->head->ns_id); } else { set_bit(NVME_NS_FORCE_RO, &ns->flags); dev_warn(ns->ctrl->device, - "Zone Append not supported for zoned namespace:%d. Forcing to read-only mode\n", + "Zone Append not supported for zoned namespace:%u. Forcing to read-only mode\n", ns->head->ns_id); } diff --git a/drivers/nvme/target/configfs.c b/drivers/nvme/target/configfs.c index 413ee2d16d29ca..6286e38436ddf8 100644 --- a/drivers/nvme/target/configfs.c +++ b/drivers/nvme/target/configfs.c @@ -814,7 +814,7 @@ static ssize_t nvmet_ns_resv_enable_store(struct config_item *item, mutex_lock(&ns->subsys->lock); if (ns->enabled) { - pr_err("the ns:%d is already enabled.\n", ns->nsid); + pr_err("the ns:%u is already enabled.\n", ns->nsid); mutex_unlock(&ns->subsys->lock); return -EINVAL; } @@ -880,7 +880,7 @@ static struct config_group *nvmet_ns_make(struct config_group *group, goto out; config_group_init_type_name(&ns->group, name, &nvmet_ns_type); - pr_info("adding nsid %d to subsystem %s\n", nsid, subsys->subsysnqn); + pr_info("adding nsid %u to subsystem %s\n", nsid, subsys->subsysnqn); return &ns->group; out: diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index 23fa90ec3c00e0..269daefb888541 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -558,7 +558,7 @@ static void nvmet_p2pmem_ns_add_p2p(struct nvmet_ctrl *ctrl, if (ret < 0) pci_dev_put(p2p_dev); - pr_info("using p2pmem on %s for nsid %d\n", pci_name(p2p_dev), + pr_info("using p2pmem on %s for nsid %u\n", pci_name(p2p_dev), ns->nsid); } diff --git a/drivers/nvme/target/pr.c b/drivers/nvme/target/pr.c index 7d937093b22626..ad07f55e7f173f 100644 --- a/drivers/nvme/target/pr.c +++ b/drivers/nvme/target/pr.c @@ -145,7 +145,7 @@ static void nvmet_pr_add_resv_log(struct nvmet_ctrl *ctrl, u8 log_type, log.nsid = cpu_to_le32(nsid); if (!kfifo_put(&log_mgr->log_queue, log)) { - pr_info("a reservation log lost, cntlid:%d, log_type:%d, nsid:%d\n", + pr_info("a reservation log lost, cntlid:%d, log_type:%d, nsid:%u\n", ctrl->cntlid, log_type, nsid); log_mgr->lost_count++; } diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c index de5a88fbb2337b..542138fd669f47 100644 --- a/drivers/nvme/target/rdma.c +++ b/drivers/nvme/target/rdma.c @@ -1627,19 +1627,13 @@ static int nvmet_rdma_queue_connect(struct rdma_cm_id *cm_id, mutex_unlock(&nvmet_rdma_queue_mutex); if (pending > NVMET_RDMA_BACKLOG) { ret = NVME_SC_CONNECT_CTRL_BUSY; - goto put_device; + goto free_queue; } } ret = nvmet_rdma_cm_accept(cm_id, queue, &event->param.conn); - if (ret) { - /* - * Don't destroy the cm_id in free path, as we implicitly - * destroy the cm_id here with non-zero ret code. - */ - queue->cm_id = NULL; + if (ret) goto free_queue; - } mutex_lock(&nvmet_rdma_queue_mutex); list_add_tail(&queue->queue_list, &nvmet_rdma_queue_list); @@ -1648,6 +1642,11 @@ static int nvmet_rdma_queue_connect(struct rdma_cm_id *cm_id, return 0; free_queue: + /* + * Don't destroy the cm_id in free path, as we implicitly + * destroy the cm_id here with non-zero ret code. + */ + queue->cm_id = NULL; nvmet_rdma_free_queue(queue); put_device: kref_put(&ndev->ref, nvmet_rdma_free_dev); diff --git a/drivers/opp/of.c b/drivers/opp/of.c index c02e20632fa645..9c4fd1f0e944ae 100644 --- a/drivers/opp/of.c +++ b/drivers/opp/of.c @@ -1039,7 +1039,7 @@ static int _of_add_opp_table_v1(struct device *dev, struct opp_table *opp_table) val = prop->value; while (nr) { - unsigned long freq = be32_to_cpup(val++) * 1000; + unsigned long freq = (unsigned long)be32_to_cpup(val++) * 1000; unsigned long volt = be32_to_cpup(val++); struct dev_pm_opp_data data = { .freq = freq, diff --git a/drivers/perf/riscv_pmu_legacy.c b/drivers/perf/riscv_pmu_legacy.c index 4d6461d6a74f57..1b8e4789cb3c14 100644 --- a/drivers/perf/riscv_pmu_legacy.c +++ b/drivers/perf/riscv_pmu_legacy.c @@ -110,8 +110,9 @@ static void pmu_legacy_init(struct riscv_pmu *pmu) { pr_info("Legacy PMU implementation is available\n"); - pmu->cmask = BIT(RISCV_PMU_LEGACY_CYCLE) | - BIT(RISCV_PMU_LEGACY_INSTRET); + bitmap_zero(pmu->cmask, RISCV_MAX_COUNTERS); + set_bit(RISCV_PMU_LEGACY_CYCLE, pmu->cmask); + set_bit(RISCV_PMU_LEGACY_INSTRET, pmu->cmask); pmu->ctr_start = pmu_legacy_ctr_start; pmu->ctr_stop = NULL; pmu->event_map = pmu_legacy_event_map; diff --git a/drivers/perf/riscv_pmu_sbi.c b/drivers/perf/riscv_pmu_sbi.c index dfc886dee5ad03..2e89d2fee53a0c 100644 --- a/drivers/perf/riscv_pmu_sbi.c +++ b/drivers/perf/riscv_pmu_sbi.c @@ -97,7 +97,7 @@ static unsigned int riscv_pmu_irq_mask; static unsigned int riscv_pmu_irq; /* Cache the available counters in a bitmask */ -static unsigned long cmask; +static DECLARE_BITMAP(cmask, RISCV_MAX_COUNTERS); static int pmu_event_find_cache(u64 config); struct sbi_pmu_event_data { @@ -359,16 +359,38 @@ free_mem: return result; } +static struct sbiret pmu_sbi_ctr_cfg_match(unsigned long cbase, + unsigned long ctr_mask, + unsigned long cflags, + unsigned long event_idx, + u64 config) +{ +#if defined(CONFIG_32BIT) + return sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_CFG_MATCH, cbase, + ctr_mask, cflags, event_idx, config, config >> 32); +#else + return sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_CFG_MATCH, cbase, + ctr_mask, cflags, event_idx, config, 0); +#endif +} + static void pmu_sbi_check_event(struct sbi_pmu_event_data *edata) { - struct sbiret ret; + struct sbiret ret = { .error = SBI_ERR_NOT_SUPPORTED }; + int i; - ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_CFG_MATCH, - 0, cmask, 0, edata->event_idx, 0, 0); - if (!ret.error) { - sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_STOP, - ret.value, 0x1, SBI_PMU_STOP_FLAG_RESET, 0, 0, 0); - } else if (ret.error == SBI_ERR_NOT_SUPPORTED) { + for (i = 0; i < BITS_TO_LONGS(RISCV_MAX_COUNTERS); i++) { + if (!cmask[i]) + continue; + ret = pmu_sbi_ctr_cfg_match(i * BITS_PER_LONG, cmask[i], 0, + edata->event_idx, 0); + if (!ret.error) { + sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_STOP, + ret.value, 0x1, SBI_PMU_STOP_FLAG_RESET, 0, 0, 0); + return; + } + } + if (ret.error == SBI_ERR_NOT_SUPPORTED) { /* This event cannot be monitored by any counter */ edata->event_idx = -ENOENT; } @@ -488,10 +510,10 @@ int riscv_pmu_get_hpm_info(u32 *hw_ctr_width, u32 *num_hw_ctr) union sbi_pmu_ctr_info *info; u32 hpm_width = 0, hpm_count = 0; - if (!cmask) + if (bitmap_empty(cmask, RISCV_MAX_COUNTERS)) return -EINVAL; - for_each_set_bit(i, &cmask, RISCV_MAX_COUNTERS) { + for_each_set_bit(i, cmask, RISCV_MAX_COUNTERS) { info = &pmu_ctr_list[i]; if (!info) continue; @@ -540,8 +562,8 @@ static int pmu_sbi_ctr_get_idx(struct perf_event *event) struct riscv_pmu *rvpmu = to_riscv_pmu(event->pmu); struct cpu_hw_events *cpuc = this_cpu_ptr(rvpmu->hw_events); struct sbiret ret; - int idx; - uint64_t cbase = 0, cmask = rvpmu->cmask; + int idx, i; + u64 cbase = 0, cmask = 0; unsigned long cflags = 0; cflags = pmu_sbi_get_filter_flags(event); @@ -562,14 +584,21 @@ static int pmu_sbi_ctr_get_idx(struct perf_event *event) } /* retrieve the available counter index */ -#if defined(CONFIG_32BIT) - ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_CFG_MATCH, cbase, - cmask, cflags, hwc->event_base, hwc->config, - hwc->config >> 32); -#else - ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_CFG_MATCH, cbase, - cmask, cflags, hwc->event_base, hwc->config, 0); -#endif + if (cmask) { + ret = pmu_sbi_ctr_cfg_match(cbase, cmask, cflags, hwc->event_base, + hwc->config); + } else { + ret.error = SBI_ERR_NOT_SUPPORTED; + for (i = 0; i < BITS_TO_LONGS(RISCV_MAX_COUNTERS); i++) { + if (!rvpmu->cmask[i]) + continue; + cbase = i * BITS_PER_LONG; + ret = pmu_sbi_ctr_cfg_match(cbase, rvpmu->cmask[i], cflags, + hwc->event_base, hwc->config); + if (!ret.error) + break; + } + } if (ret.error) { pr_debug("Not able to find a counter for event %lx config %llx\n", hwc->event_base, hwc->config); @@ -577,7 +606,7 @@ static int pmu_sbi_ctr_get_idx(struct perf_event *event) } idx = ret.value; - if (!test_bit(idx, &rvpmu->cmask) || !pmu_ctr_list[idx].value) + if (!test_bit(idx, rvpmu->cmask) || !pmu_ctr_list[idx].value) return -ENOENT; /* Additional sanity check for the counter id */ @@ -881,7 +910,7 @@ static int pmu_sbi_get_ctrinfo(int nctr, unsigned long *mask) /* The logical counter ids are not expected to be contiguous */ continue; - *mask |= BIT(i); + set_bit(i, mask); cinfo.value = ret.value; if (cinfo.type == SBI_PMU_CTR_TYPE_FW) @@ -898,12 +927,19 @@ static int pmu_sbi_get_ctrinfo(int nctr, unsigned long *mask) static inline void pmu_sbi_stop_all(struct riscv_pmu *pmu) { + int i; + /* * No need to check the error because we are disabling all the counters * which may include counters that are not enabled yet. */ - sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_STOP, - 0, pmu->cmask, SBI_PMU_STOP_FLAG_RESET, 0, 0, 0); + for (i = 0; i < BITS_TO_LONGS(RISCV_MAX_COUNTERS); i++) { + if (!pmu->cmask[i]) + continue; + sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_STOP, + i * BITS_PER_LONG, pmu->cmask[i], + SBI_PMU_STOP_FLAG_RESET, 0, 0, 0); + } } static inline void pmu_sbi_stop_hw_ctrs(struct riscv_pmu *pmu) @@ -1002,7 +1038,7 @@ static inline void pmu_sbi_start_ovf_ctrs_snapshot(struct cpu_hw_events *cpu_hw_ struct riscv_pmu_snapshot_data *sdata = cpu_hw_evt->snapshot_addr; for_each_set_bit(idx, cpu_hw_evt->used_hw_ctrs, RISCV_MAX_COUNTERS) { - if (ctr_ovf_mask & BIT(idx)) { + if (ctr_ovf_mask & BIT_ULL(idx)) { event = cpu_hw_evt->events[idx]; hwc = &event->hw; max_period = riscv_pmu_ctr_get_width_mask(event); @@ -1050,11 +1086,13 @@ static irqreturn_t pmu_sbi_ovf_handler(int irq, void *dev) u64 overflowed_ctrs = 0; struct cpu_hw_events *cpu_hw_evt = dev; u64 start_clock = sched_clock(); - struct riscv_pmu_snapshot_data *sdata = cpu_hw_evt->snapshot_addr; + struct riscv_pmu_snapshot_data *sdata; if (WARN_ON_ONCE(!cpu_hw_evt)) return IRQ_NONE; + sdata = cpu_hw_evt->snapshot_addr; + /* Firmware counter don't support overflow yet */ fidx = find_first_bit(cpu_hw_evt->used_hw_ctrs, RISCV_MAX_COUNTERS); if (fidx == RISCV_MAX_COUNTERS) { @@ -1109,14 +1147,14 @@ static irqreturn_t pmu_sbi_ovf_handler(int irq, void *dev) hidx = info->csr - CSR_CYCLE; /* check if the corresponding bit is set in scountovf or overflow mask in shmem */ - if (!(overflow & BIT(hidx))) + if (!(overflow & BIT_ULL(hidx))) continue; /* * Keep a track of overflowed counters so that they can be started * with updated initial value. */ - overflowed_ctrs |= BIT(lidx); + overflowed_ctrs |= BIT_ULL(lidx); hw_evt = &event->hw; /* Update the event states here so that we know the state while reading */ hw_evt->state |= PERF_HES_STOPPED; @@ -1442,7 +1480,7 @@ static int pmu_sbi_device_probe(struct platform_device *pdev) } /* cache all the information about counters now */ - if (pmu_sbi_get_ctrinfo(num_counters, &cmask)) + if (pmu_sbi_get_ctrinfo(num_counters, cmask)) goto out_free; ret = pmu_sbi_setup_irqs(pmu, pdev); @@ -1454,7 +1492,7 @@ static int pmu_sbi_device_probe(struct platform_device *pdev) pmu->pmu.attr_groups = riscv_pmu_attr_groups; pmu->pmu.parent = &pdev->dev; - pmu->cmask = cmask; + bitmap_copy(pmu->cmask, cmask, RISCV_MAX_COUNTERS); pmu->ctr_start = pmu_sbi_ctr_start; pmu->ctr_stop = pmu_sbi_ctr_stop; pmu->event_map = pmu_sbi_event_map; diff --git a/drivers/platform/x86/asus-laptop.c b/drivers/platform/x86/asus-laptop.c index 140ac8a1053729..19024fa3796e62 100644 --- a/drivers/platform/x86/asus-laptop.c +++ b/drivers/platform/x86/asus-laptop.c @@ -1887,7 +1887,7 @@ static int asus_acpi_probe(struct platform_device *pdev) if (result && result != -ENODEV) goto fail_pega_rfkill; - result = acpi_dev_install_notify_handler(device, ACPI_DEVICE_NOTIFY, + result = acpi_dev_install_notify_handler(device, ACPI_ALL_NOTIFY, asus_acpi_notify, asus); if (result) goto fail_pega_rfkill; @@ -1917,7 +1917,7 @@ static void asus_acpi_remove(struct platform_device *pdev) { struct asus_laptop *asus = platform_get_drvdata(pdev); - acpi_dev_remove_notify_handler(asus->device, ACPI_DEVICE_NOTIFY, + acpi_dev_remove_notify_handler(asus->device, ACPI_ALL_NOTIFY, asus_acpi_notify); asus_backlight_exit(asus); asus_rfkill_exit(asus); diff --git a/drivers/platform/x86/hp/hp-wmi.c b/drivers/platform/x86/hp/hp-wmi.c index 94147102cca43a..051676c7ec1ade 100644 --- a/drivers/platform/x86/hp/hp-wmi.c +++ b/drivers/platform/x86/hp/hp-wmi.c @@ -133,11 +133,35 @@ static const struct thermal_profile_params omen_v1_no_ec_thermal_params = { .ec_tp_offset = HP_NO_THERMAL_PROFILE_OFFSET, }; -/* - * A generic pointer for the currently-active board's thermal profile - * parameters. - */ -static struct thermal_profile_params *active_thermal_profile_params; +struct hp_wmi_board_params { + const struct thermal_profile_params *thermal_profile; +}; + +static const struct hp_wmi_board_params victus_s_board_params = { + .thermal_profile = &victus_s_thermal_params, +}; + +static const struct hp_wmi_board_params omen_v1_board_params = { + .thermal_profile = &omen_v1_thermal_params, +}; + +static const struct hp_wmi_board_params omen_v1_legacy_board_params = { + .thermal_profile = &omen_v1_legacy_thermal_params, +}; + +static const struct hp_wmi_board_params omen_v1_no_ec_board_params = { + .thermal_profile = &omen_v1_no_ec_thermal_params, +}; + +static const struct hp_wmi_board_params *active_board_params; + +static const struct thermal_profile_params *hp_wmi_thermal_profile(void) +{ + if (!active_board_params) + return NULL; + + return active_board_params->thermal_profile; +} /* DMI board names of devices that should use the omen specific path for * thermal profiles. @@ -187,91 +211,91 @@ static const char * const victus_thermal_profile_boards[] = { "8A25", }; -/* DMI Board names of Victus 16-r and Victus 16-s laptops */ -static const struct dmi_system_id victus_s_thermal_profile_boards[] __initconst = { +/* DMI board-specific feature data for Omen and Victus laptops. */ +static const struct dmi_system_id hp_wmi_feature_boards[] __initconst = { { .matches = { DMI_MATCH(DMI_BOARD_NAME, "8902") }, - .driver_data = (void *)&omen_v1_legacy_thermal_params, + .driver_data = (void *)&omen_v1_legacy_board_params, }, { .matches = { DMI_MATCH(DMI_BOARD_NAME, "8A44") }, - .driver_data = (void *)&omen_v1_legacy_thermal_params, + .driver_data = (void *)&omen_v1_legacy_board_params, }, { .matches = { DMI_MATCH(DMI_BOARD_NAME, "8A4D") }, - .driver_data = (void *)&omen_v1_legacy_thermal_params, + .driver_data = (void *)&omen_v1_legacy_board_params, }, { .matches = { DMI_MATCH(DMI_BOARD_NAME, "8BAB") }, - .driver_data = (void *)&omen_v1_thermal_params, + .driver_data = (void *)&omen_v1_board_params, }, { .matches = { DMI_MATCH(DMI_BOARD_NAME, "8B2F") }, - .driver_data = (void *)&victus_s_thermal_params, + .driver_data = (void *)&victus_s_board_params, }, { .matches = { DMI_MATCH(DMI_BOARD_NAME, "8BBE") }, - .driver_data = (void *)&victus_s_thermal_params, + .driver_data = (void *)&victus_s_board_params, }, { .matches = { DMI_MATCH(DMI_BOARD_NAME, "8BC2") }, - .driver_data = (void *)&omen_v1_thermal_params, + .driver_data = (void *)&omen_v1_board_params, }, { .matches = { DMI_MATCH(DMI_BOARD_NAME, "8BCA") }, - .driver_data = (void *)&omen_v1_thermal_params, + .driver_data = (void *)&omen_v1_board_params, }, { .matches = { DMI_MATCH(DMI_BOARD_NAME, "8BCD") }, - .driver_data = (void *)&omen_v1_thermal_params, + .driver_data = (void *)&omen_v1_board_params, }, { .matches = { DMI_MATCH(DMI_BOARD_NAME, "8BD4") }, - .driver_data = (void *)&victus_s_thermal_params, + .driver_data = (void *)&victus_s_board_params, }, { .matches = { DMI_MATCH(DMI_BOARD_NAME, "8BD5") }, - .driver_data = (void *)&victus_s_thermal_params, + .driver_data = (void *)&victus_s_board_params, }, { .matches = { DMI_MATCH(DMI_BOARD_NAME, "8C76") }, - .driver_data = (void *)&omen_v1_thermal_params, + .driver_data = (void *)&omen_v1_board_params, }, { .matches = { DMI_MATCH(DMI_BOARD_NAME, "8C77") }, - .driver_data = (void *)&omen_v1_thermal_params, + .driver_data = (void *)&omen_v1_board_params, }, { .matches = { DMI_MATCH(DMI_BOARD_NAME, "8C78") }, - .driver_data = (void *)&omen_v1_thermal_params, + .driver_data = (void *)&omen_v1_board_params, }, { .matches = { DMI_MATCH(DMI_BOARD_NAME, "8C99") }, - .driver_data = (void *)&victus_s_thermal_params, + .driver_data = (void *)&victus_s_board_params, }, { .matches = { DMI_MATCH(DMI_BOARD_NAME, "8C9C") }, - .driver_data = (void *)&victus_s_thermal_params, + .driver_data = (void *)&victus_s_board_params, }, { .matches = { DMI_MATCH(DMI_BOARD_NAME, "8D26") }, - .driver_data = (void *)&omen_v1_legacy_thermal_params, + .driver_data = (void *)&omen_v1_legacy_board_params, }, { .matches = { DMI_MATCH(DMI_BOARD_NAME, "8D41") }, - .driver_data = (void *)&omen_v1_no_ec_thermal_params, + .driver_data = (void *)&omen_v1_no_ec_board_params, }, { .matches = { DMI_MATCH(DMI_BOARD_NAME, "8D87") }, - .driver_data = (void *)&omen_v1_no_ec_thermal_params, + .driver_data = (void *)&omen_v1_no_ec_board_params, }, { .matches = { DMI_MATCH(DMI_BOARD_NAME, "8DD6") }, - .driver_data = (void *)&omen_v1_no_ec_thermal_params, + .driver_data = (void *)&omen_v1_no_ec_board_params, }, { .matches = { DMI_MATCH(DMI_BOARD_NAME, "8E35") }, - .driver_data = (void *)&omen_v1_legacy_thermal_params, + .driver_data = (void *)&omen_v1_legacy_board_params, }, {}, }; @@ -1878,7 +1902,10 @@ static int platform_profile_victus_s_get_ec(enum platform_profile_option *profil u8 current_dstate, current_gpu_slowdown_temp, tp; const struct thermal_profile_params *params; - params = active_thermal_profile_params; + params = hp_wmi_thermal_profile(); + if (!params) + return -ENODEV; + if (params->ec_tp_offset == HP_EC_OFFSET_UNKNOWN || params->ec_tp_offset == HP_NO_THERMAL_PROFILE_OFFSET) { *profile = active_platform_profile; @@ -1890,10 +1917,10 @@ static int platform_profile_victus_s_get_ec(enum platform_profile_option *profil return ret; /* - * We cannot use active_thermal_profile_params here, because boards - * like 8C78 have tp == 0x0 || tp == 0x1 after cold boot, but logically - * it should have tp == 0x30 || tp == 0x31, as corrected by the Omen - * Gaming Hub on windows. Hence accept both of these values. + * Boards like 8C78 have tp == 0x0 || tp == 0x1 after cold boot, + * but logically it should have tp == 0x30 || tp == 0x31, as + * corrected by the Omen Gaming Hub on windows. Hence accept both + * of these values. */ if (tp == victus_s_thermal_params.performance || tp == omen_v1_thermal_params.performance) { @@ -1928,12 +1955,12 @@ static int platform_profile_victus_s_get_ec(enum platform_profile_option *profil static int platform_profile_victus_s_set_ec(enum platform_profile_option profile) { - struct thermal_profile_params *params; + const struct thermal_profile_params *params; bool gpu_ctgp_enable, gpu_ppab_enable; u8 gpu_dstate; /* Test shows 1 = 100%, 2 = 50%, 3 = 25%, 4 = 12.5% */ int err, tp; - params = active_thermal_profile_params; + params = hp_wmi_thermal_profile(); if (!params) return -ENODEV; @@ -2199,6 +2226,7 @@ static const struct platform_profile_ops hp_wmi_platform_profile_ops = { static int thermal_profile_setup(struct platform_device *device) { const struct platform_profile_ops *ops; + const struct thermal_profile_params *params; int err, tp; if (is_omen_thermal_profile()) { @@ -2230,13 +2258,17 @@ static int thermal_profile_setup(struct platform_device *device) ops = &platform_profile_victus_ops; } else if (is_victus_s_thermal_profile()) { + params = hp_wmi_thermal_profile(); + if (!params) + return -ENODEV; + /* * For an unknown EC layout board, platform_profile_victus_s_get_ec(), * behaves like a wrapper around active_platform_profile, to avoid using * uninitialized data, we default to PLATFORM_PROFILE_BALANCED. */ - if (active_thermal_profile_params->ec_tp_offset == HP_EC_OFFSET_UNKNOWN || - active_thermal_profile_params->ec_tp_offset == HP_NO_THERMAL_PROFILE_OFFSET) { + if (params->ec_tp_offset == HP_EC_OFFSET_UNKNOWN || + params->ec_tp_offset == HP_NO_THERMAL_PROFILE_OFFSET) { active_platform_profile = PLATFORM_PROFILE_BALANCED; } else { err = platform_profile_victus_s_get_ec(&active_platform_profile); @@ -2697,24 +2729,25 @@ static int hp_wmi_hwmon_init(void) return 0; } -static void __init setup_active_thermal_profile_params(void) +static void __init setup_active_board_params(void) { const struct dmi_system_id *id; + const struct thermal_profile_params *params; - /* - * Currently only victus_s devices use the - * active_thermal_profile_params - */ - id = dmi_first_match(victus_s_thermal_profile_boards); + id = dmi_first_match(hp_wmi_feature_boards); if (id) { + active_board_params = id->driver_data; + params = hp_wmi_thermal_profile(); + if (!params) + return; + /* * Marking this boolean is required to ensure that * is_victus_s_thermal_profile() behaves like a valid * wrapper. */ is_victus_s_board = true; - active_thermal_profile_params = id->driver_data; - if (active_thermal_profile_params->ec_tp_offset == HP_EC_OFFSET_UNKNOWN) { + if (params->ec_tp_offset == HP_EC_OFFSET_UNKNOWN) { pr_warn("Unknown EC layout for board %s. Thermal profile readback will be disabled. Please report this to platform-driver-x86@vger.kernel.org\n", dmi_get_system_info(DMI_BOARD_NAME)); } @@ -2749,10 +2782,10 @@ static int __init hp_wmi_init(void) } /* - * Setup active board's thermal profile parameters before - * starting platform driver probe. + * Setup active board feature data before starting platform + * driver probe. */ - setup_active_thermal_profile_params(); + setup_active_board_params(); err = platform_driver_probe(&hp_wmi_driver, hp_wmi_bios_setup); if (err) goto err_unregister_device; diff --git a/drivers/platform/x86/x86-android-tablets/core.c b/drivers/platform/x86/x86-android-tablets/core.c index 5db794d65eb5f7..7751261f4b7cf4 100644 --- a/drivers/platform/x86/x86-android-tablets/core.c +++ b/drivers/platform/x86/x86-android-tablets/core.c @@ -367,6 +367,7 @@ static void gpio_secondary_unset(void *data) struct device *dev = data; set_secondary_fwnode(dev, NULL); + put_device(dev); } static void gpio_secondary_unregister_node_group(void *data) @@ -380,6 +381,7 @@ static int gpio_secondary_fwnode_init(struct device *parent) { const struct software_node *const *swnode; struct fwnode_handle *fwnode; + struct device *phys_dev; int ret; if (!gpiochip_node_group) @@ -407,9 +409,15 @@ static int gpio_secondary_fwnode_init(struct device *parent) if (WARN_ON(!fwnode)) return -ENOENT; - set_secondary_fwnode(dev, fwnode); + phys_dev = acpi_get_first_physical_node(to_acpi_device(dev)); + if (!phys_dev) + return dev_err_probe(parent, -ENODEV, + "No physical device for ACPI GPIO dev: %pfwP\n", + fwnode); - ret = devm_add_action_or_reset(parent, gpio_secondary_unset, dev); + set_secondary_fwnode(phys_dev, fwnode); + + ret = devm_add_action_or_reset(parent, gpio_secondary_unset, get_device(phys_dev)); if (ret) return ret; } diff --git a/drivers/ras/amd/atl/core.c b/drivers/ras/amd/atl/core.c index 0f7cd6dab0b0e0..d77dacdd4f5693 100644 --- a/drivers/ras/amd/atl/core.c +++ b/drivers/ras/amd/atl/core.c @@ -190,7 +190,6 @@ static const struct x86_cpu_id amd_atl_cpuids[] = { X86_MATCH_FEATURE(X86_FEATURE_ZEN, NULL), { } }; -MODULE_DEVICE_TABLE(x86cpu, amd_atl_cpuids); static int __init amd_atl_init(void) { diff --git a/drivers/regulator/db8500-prcmu.c b/drivers/regulator/db8500-prcmu.c index 1ec2e1348891df..751fe36580fafd 100644 --- a/drivers/regulator/db8500-prcmu.c +++ b/drivers/regulator/db8500-prcmu.c @@ -13,7 +13,7 @@ #include #include #include -#include +#include #include #include #include @@ -93,13 +93,13 @@ static int enable_epod(u16 epod_id, bool ramret) if (ramret) { if (!epod_on[epod_id]) { - ret = prcmu_set_epod(epod_id, EPOD_STATE_RAMRET); + ret = db8500_prcmu_set_epod(epod_id, EPOD_STATE_RAMRET); if (ret < 0) return ret; } epod_ramret[epod_id] = true; } else { - ret = prcmu_set_epod(epod_id, EPOD_STATE_ON); + ret = db8500_prcmu_set_epod(epod_id, EPOD_STATE_ON); if (ret < 0) return ret; epod_on[epod_id] = true; @@ -114,18 +114,18 @@ static int disable_epod(u16 epod_id, bool ramret) if (ramret) { if (!epod_on[epod_id]) { - ret = prcmu_set_epod(epod_id, EPOD_STATE_OFF); + ret = db8500_prcmu_set_epod(epod_id, EPOD_STATE_OFF); if (ret < 0) return ret; } epod_ramret[epod_id] = false; } else { if (epod_ramret[epod_id]) { - ret = prcmu_set_epod(epod_id, EPOD_STATE_RAMRET); + ret = db8500_prcmu_set_epod(epod_id, EPOD_STATE_RAMRET); if (ret < 0) return ret; } else { - ret = prcmu_set_epod(epod_id, EPOD_STATE_OFF); + ret = db8500_prcmu_set_epod(epod_id, EPOD_STATE_OFF); if (ret < 0) return ret; } diff --git a/drivers/regulator/pf1550-regulator.c b/drivers/regulator/pf1550-regulator.c index 610eac9bb9cb2c..ceee553a84b237 100644 --- a/drivers/regulator/pf1550-regulator.c +++ b/drivers/regulator/pf1550-regulator.c @@ -283,63 +283,61 @@ static struct pf1550_desc pf1550_regulators[] = { PF_LDO1(PF1550, "ldo3", LDO3, 0x1f, pf1550_ldo13_volts), }; +/* + * The _LS interrupts indicate an over-current event. The _HS + * interrupts, which are more accurate and can detect catastrophic + * faults, issue an error event. The current limit FAULT interrupt is + * similar to the _HS. + */ +static const struct pf1550_regulator_irq { + unsigned int event; + u8 id; +} pf1550_regulator_irqs[] = { + [PF1550_PMIC_IRQ_SW1_LS] = { REGULATOR_EVENT_OVER_CURRENT_WARN, PF1550_SW1 }, + [PF1550_PMIC_IRQ_SW2_LS] = { REGULATOR_EVENT_OVER_CURRENT_WARN, PF1550_SW2 }, + [PF1550_PMIC_IRQ_SW3_LS] = { REGULATOR_EVENT_OVER_CURRENT_WARN, PF1550_SW3 }, + [PF1550_PMIC_IRQ_SW1_HS] = { REGULATOR_EVENT_OVER_CURRENT, PF1550_SW1 }, + [PF1550_PMIC_IRQ_SW2_HS] = { REGULATOR_EVENT_OVER_CURRENT, PF1550_SW2 }, + [PF1550_PMIC_IRQ_SW3_HS] = { REGULATOR_EVENT_OVER_CURRENT, PF1550_SW3 }, + [PF1550_PMIC_IRQ_LDO1_FAULT] = { REGULATOR_EVENT_OVER_CURRENT, PF1550_LDO1 }, + [PF1550_PMIC_IRQ_LDO2_FAULT] = { REGULATOR_EVENT_OVER_CURRENT, PF1550_LDO2 }, + [PF1550_PMIC_IRQ_LDO3_FAULT] = { REGULATOR_EVENT_OVER_CURRENT, PF1550_LDO3 }, +}; + static irqreturn_t pf1550_regulator_irq_handler(int irq, void *data) { + const struct pf1550_regulator_irq *map; struct pf1550_regulator_info *info = data; struct device *dev = info->dev; struct platform_device *pdev = to_platform_device(dev); int i, irq_type = -1; - unsigned int event; for (i = 0; i < PF1550_REGULATOR_IRQ_NR; i++) if (irq == platform_get_irq(pdev, i)) irq_type = i; - switch (irq_type) { - /* The _LS interrupts indicate over-current event. The _HS interrupts - * which are more accurate and can detect catastrophic faults, issue - * an error event. The current limit FAULT interrupt is similar to the - * _HS' - */ - case PF1550_PMIC_IRQ_SW1_LS: - case PF1550_PMIC_IRQ_SW2_LS: - case PF1550_PMIC_IRQ_SW3_LS: - event = REGULATOR_EVENT_OVER_CURRENT_WARN; - for (i = 0; i < PF1550_MAX_REGULATOR; i++) - if (!strcmp(rdev_get_name(info->rdevs[i]), "SW3")) - regulator_notifier_call_chain(info->rdevs[i], - event, NULL); - break; - case PF1550_PMIC_IRQ_SW1_HS: - case PF1550_PMIC_IRQ_SW2_HS: - case PF1550_PMIC_IRQ_SW3_HS: - event = REGULATOR_EVENT_OVER_CURRENT; - for (i = 0; i < PF1550_MAX_REGULATOR; i++) - if (!strcmp(rdev_get_name(info->rdevs[i]), "SW3")) - regulator_notifier_call_chain(info->rdevs[i], - event, NULL); - break; - case PF1550_PMIC_IRQ_LDO1_FAULT: - case PF1550_PMIC_IRQ_LDO2_FAULT: - case PF1550_PMIC_IRQ_LDO3_FAULT: - event = REGULATOR_EVENT_OVER_CURRENT; - for (i = 0; i < PF1550_MAX_REGULATOR; i++) - if (!strcmp(rdev_get_name(info->rdevs[i]), "LDO3")) - regulator_notifier_call_chain(info->rdevs[i], - event, NULL); - break; - case PF1550_PMIC_IRQ_TEMP_110: - case PF1550_PMIC_IRQ_TEMP_125: - event = REGULATOR_EVENT_OVER_TEMP; + /* The die temperature concerns every rail. */ + if (irq_type == PF1550_PMIC_IRQ_TEMP_110 || + irq_type == PF1550_PMIC_IRQ_TEMP_125) { for (i = 0; i < PF1550_MAX_REGULATOR; i++) regulator_notifier_call_chain(info->rdevs[i], - event, NULL); - break; - default: - dev_err(dev, "regulator interrupt: irq %d occurred\n", - irq_type); + REGULATOR_EVENT_OVER_TEMP, + NULL); + return IRQ_HANDLED; + } + + if (irq_type < 0 || irq_type >= (int)ARRAY_SIZE(pf1550_regulator_irqs)) { + dev_err(dev, "regulator interrupt: irq %d occurred\n", irq_type); + return IRQ_HANDLED; } + map = &pf1550_regulator_irqs[irq_type]; + + for (i = 0; i < PF1550_MAX_REGULATOR; i++) + if (rdev_get_id(info->rdevs[i]) == map->id) + regulator_notifier_call_chain(info->rdevs[i], + map->event, NULL); + return IRQ_HANDLED; } diff --git a/drivers/s390/net/ism_drv.c b/drivers/s390/net/ism_drv.c index 242da20f27e0ed..035b233abb4e94 100644 --- a/drivers/s390/net/ism_drv.c +++ b/drivers/s390/net/ism_drv.c @@ -231,6 +231,7 @@ static void ism_free_dmb(struct ism_dev *ism, struct dibs_dmb *dmb) dma_unmap_page(&ism->pdev->dev, dmb->dma_addr, dmb->dmb_len, DMA_FROM_DEVICE); folio_put(virt_to_folio(dmb->cpu_addr)); + dmb->cpu_addr = NULL; } static int ism_alloc_dmb(struct ism_dev *ism, struct dibs_dmb *dmb) @@ -274,7 +275,8 @@ static int ism_alloc_dmb(struct ism_dev *ism, struct dibs_dmb *dmb) return 0; out_free: - kfree(dmb->cpu_addr); + folio_put(folio); + dmb->cpu_addr = NULL; out_bit: clear_bit(dmb->idx, ism->sba_bitmap); return rc; diff --git a/drivers/s390/net/qeth_l2.h b/drivers/s390/net/qeth_l2.h index 7c646e2fed7e53..f94975e970cadd 100644 --- a/drivers/s390/net/qeth_l2.h +++ b/drivers/s390/net/qeth_l2.h @@ -13,7 +13,8 @@ extern const struct attribute_group *qeth_l2_attr_groups[]; int qeth_bridgeport_query_ports(struct qeth_card *card, enum qeth_sbp_roles *role, - enum qeth_sbp_states *state); + enum qeth_sbp_states *state, + bool *os_mismatch); int qeth_bridgeport_setrole(struct qeth_card *card, enum qeth_sbp_roles role); int qeth_bridgeport_an_set(struct qeth_card *card, int enable); diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c index a9e7d1d637a208..2935c2ecc314b3 100644 --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@ -1158,7 +1158,7 @@ static void qeth_l2_setup_bridgeport_attrs(struct qeth_card *card) qeth_bridgeport_setrole(card, card->options.sbp.role); /* Let the callback function refresh the stored role value. */ qeth_bridgeport_query_ports(card, &card->options.sbp.role, - NULL); + NULL, NULL); } if (card->options.sbp.hostnotification) { if (qeth_bridgeport_an_set(card, 1)) @@ -1545,6 +1545,7 @@ struct _qeth_sbp_cbctl { struct { enum qeth_sbp_roles *role; enum qeth_sbp_states *state; + bool *os_mismatch; } qports; } data; }; @@ -1721,10 +1722,19 @@ static int qeth_bridgeport_query_ports_cb(struct qeth_card *card, struct qeth_ipa_cmd *cmd = (struct qeth_ipa_cmd *) data; struct _qeth_sbp_cbctl *cbctl = (struct _qeth_sbp_cbctl *)reply->param; struct qeth_sbp_port_data *qports; + u16 sbp_rc; int rc; QETH_CARD_TEXT(card, 2, "brqprtcb"); - rc = qeth_bridgeport_makerc(card, cmd); + sbp_rc = cmd->data.sbp.hdr.return_code; + + /* on OS family mismatch, query still returns valid port data; + * treat as success + */ + if (sbp_rc == IPA_RC_SBP_IQD_OS_MISMATCH && !cmd->hdr.return_code) + rc = 0; + else + rc = qeth_bridgeport_makerc(card, cmd); if (rc) return rc; @@ -1740,6 +1750,9 @@ static int qeth_bridgeport_query_ports_cb(struct qeth_card *card, if (cbctl->data.qports.state) *cbctl->data.qports.state = qports->entry[0].state; } + if (cbctl->data.qports.os_mismatch) + *cbctl->data.qports.os_mismatch = + (sbp_rc == IPA_RC_SBP_IQD_OS_MISMATCH); return 0; } @@ -1748,13 +1761,17 @@ static int qeth_bridgeport_query_ports_cb(struct qeth_card *card, * @card: qeth_card structure pointer. * @role: Role of the port: 0-none, 1-primary, 2-secondary. * @state: State of the port: 0-inactive, 1-standby, 2-active. + * @os_mismatch: if non-NULL, set to true when firmware reports + * OS family mismatch. * * Returns negative errno-compatible error indication or 0 on success. * - * 'role' and 'state' are not updated in case of hardware operation failure. + * 'role', 'state' and 'os_mismatch' are not updated in case of + * hardware operation failure. */ int qeth_bridgeport_query_ports(struct qeth_card *card, - enum qeth_sbp_roles *role, enum qeth_sbp_states *state) + enum qeth_sbp_roles *role, enum qeth_sbp_states *state, + bool *os_mismatch) { struct qeth_cmd_buffer *iob; struct _qeth_sbp_cbctl cbctl = { @@ -1762,6 +1779,7 @@ int qeth_bridgeport_query_ports(struct qeth_card *card, .qports = { .role = role, .state = state, + .os_mismatch = os_mismatch, }, }, }; diff --git a/drivers/s390/net/qeth_l2_sys.c b/drivers/s390/net/qeth_l2_sys.c index 7f592f9125172e..7101be62eb1d5a 100644 --- a/drivers/s390/net/qeth_l2_sys.c +++ b/drivers/s390/net/qeth_l2_sys.c @@ -15,6 +15,7 @@ static ssize_t qeth_bridge_port_role_state_show(struct device *dev, { struct qeth_card *card = dev_get_drvdata(dev); enum qeth_sbp_states state = QETH_SBP_STATE_INACTIVE; + bool os_mismatch = false; int rc = 0; char *word; @@ -25,7 +26,7 @@ static ssize_t qeth_bridge_port_role_state_show(struct device *dev, if (qeth_card_hw_is_reachable(card) && card->options.sbp.supported_funcs) rc = qeth_bridgeport_query_ports(card, - &card->options.sbp.role, &state); + &card->options.sbp.role, &state, &os_mismatch); if (!rc) { if (show_state) switch (state) { @@ -52,6 +53,10 @@ static ssize_t qeth_bridge_port_role_state_show(struct device *dev, if (rc) QETH_CARD_TEXT_(card, 2, "SBP%02x:%02x", card->options.sbp.role, state); + else if (!show_state && + card->options.sbp.role == QETH_SBP_ROLE_NONE && + os_mismatch) + rc = sysfs_emit(buf, "%s (OS family mismatch)\n", word); else rc = sysfs_emit(buf, "%s\n", word); } diff --git a/drivers/scsi/mpi3mr/mpi3mr_transport.c b/drivers/scsi/mpi3mr/mpi3mr_transport.c index 240f67a8e2e3b6..232af978d73729 100644 --- a/drivers/scsi/mpi3mr/mpi3mr_transport.c +++ b/drivers/scsi/mpi3mr/mpi3mr_transport.c @@ -1428,9 +1428,15 @@ static struct mpi3mr_sas_port *mpi3mr_sas_port_add(struct mpi3mr_ioc *mrioc, } port = sas_port_alloc_num(mr_sas_node->parent_dev); + if (!port) { + ioc_err(mrioc, "failure at %s:%d/%s()!\n", + __FILE__, __LINE__, __func__); + goto out_fail; + } if ((sas_port_add(port))) { ioc_err(mrioc, "failure at %s:%d/%s()!\n", __FILE__, __LINE__, __func__); + sas_port_free(port); goto out_fail; } @@ -1501,6 +1507,8 @@ static struct mpi3mr_sas_port *mpi3mr_sas_port_add(struct mpi3mr_ioc *mrioc, list_for_each_entry_safe(mr_sas_phy, next, &mr_sas_port->phy_list, port_siblings) list_del(&mr_sas_phy->port_siblings); + if (tgtdev) + mpi3mr_tgtdev_put(tgtdev); kfree(mr_sas_port); return NULL; } diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c index 11bcb8440e1c87..ae2f7d9c281f92 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.c +++ b/drivers/scsi/mpt3sas/mpt3sas_base.c @@ -3238,7 +3238,10 @@ _base_assign_reply_queues(struct MPT3SAS_ADAPTER *ioc) * corresponding to high iops queues. */ if (ioc->high_iops_queues) { - mask = cpumask_of_node(dev_to_node(&ioc->pdev->dev)); + int node = dev_to_node(&ioc->pdev->dev); + + mask = (node == NUMA_NO_NODE) ? + cpu_online_mask : cpumask_of_node(node); for (index = 0; index < ioc->high_iops_queues; index++) { irq = pci_irq_vector(ioc->pdev, index); diff --git a/drivers/scsi/qla2xxx/qla_bsg.c b/drivers/scsi/qla2xxx/qla_bsg.c index 5b15fc28ddd7b6..79144530fa24db 100644 --- a/drivers/scsi/qla2xxx/qla_bsg.c +++ b/drivers/scsi/qla2xxx/qla_bsg.c @@ -160,6 +160,12 @@ qla24xx_proc_fcp_prio_cfg_cmd(struct bsg_job *bsg_job) goto exit_fcp_prio_cfg; } + if (bsg_job->request_len < + sizeof(struct fc_bsg_request) + 2 * sizeof(uint32_t)) { + ret = -EINVAL; + goto exit_fcp_prio_cfg; + } + /* Get the sub command */ oper = bsg_request->rqst_data.h_vendor.vendor_cmd[1]; @@ -758,6 +764,10 @@ qla2x00_process_loopback(struct bsg_job *bsg_job) return -EIO; } + if (bsg_job->request_len < + sizeof(struct fc_bsg_request) + 3 * sizeof(uint32_t)) + return -EINVAL; + memset(&elreq, 0, sizeof(elreq)); elreq.req_sg_cnt = dma_map_sg(&ha->pdev->dev, @@ -990,6 +1000,10 @@ qla84xx_reset(struct bsg_job *bsg_job) return -EINVAL; } + if (bsg_job->request_len < + sizeof(struct fc_bsg_request) + 2 * sizeof(uint32_t)) + return -EINVAL; + flag = bsg_request->rqst_data.h_vendor.vendor_cmd[1]; rval = qla84xx_reset_chip(vha, flag == A84_ISSUE_RESET_DIAG_FW); @@ -1034,6 +1048,10 @@ qla84xx_updatefw(struct bsg_job *bsg_job) return -EINVAL; } + if (bsg_job->request_len < + sizeof(struct fc_bsg_request) + 2 * sizeof(uint32_t)) + return -EINVAL; + sg_cnt = dma_map_sg(&ha->pdev->dev, bsg_job->request_payload.sg_list, bsg_job->request_payload.sg_cnt, DMA_TO_DEVICE); if (!sg_cnt) { @@ -1484,6 +1502,10 @@ qla2x00_read_optrom(struct bsg_job *bsg_job) struct qla_hw_data *ha = vha->hw; int rval = 0; + if (bsg_job->request_len < + sizeof(struct fc_bsg_request) + 2 * sizeof(uint32_t)) + return -EINVAL; + if (ha->flags.nic_core_reset_hdlr_active) return -EBUSY; @@ -1521,6 +1543,10 @@ qla2x00_update_optrom(struct bsg_job *bsg_job) struct qla_hw_data *ha = vha->hw; int rval = 0; + if (bsg_job->request_len < + sizeof(struct fc_bsg_request) + 2 * sizeof(uint32_t)) + return -EINVAL; + mutex_lock(&ha->optrom_mutex); rval = qla2x00_optrom_setup(bsg_job, vha, 1); if (rval) { @@ -2012,6 +2038,11 @@ qlafx00_mgmt_cmd(struct bsg_job *bsg_job) struct fc_port *fcport; char *type = "FC_BSG_HST_FX_MGMT"; + if (bsg_job->request_len < + sizeof(struct fc_bsg_request) + sizeof(uint32_t) + + sizeof(struct qla_mt_iocb_rqst_fx00)) + return -EINVAL; + /* Copy the IOCB specific information */ piocb_rqst = (struct qla_mt_iocb_rqst_fx00 *) &bsg_request->rqst_data.h_vendor.vendor_cmd[1]; @@ -2925,6 +2956,13 @@ qla2x00_process_vendor_specific(struct scsi_qla_host *vha, struct bsg_job *bsg_j { struct fc_bsg_request *bsg_request = bsg_job->request; + if (bsg_job->request_len < + sizeof(struct fc_bsg_request) + sizeof(uint32_t)) { + ql_log(ql_log_warn, vha, 0x7000, + "BSG request too small for vendor cmd.\n"); + return -EINVAL; + } + ql_dbg(ql_dbg_edif, vha, 0x911b, "%s FC_BSG_HST_VENDOR cmd[0]=0x%x\n", __func__, bsg_request->rqst_data.h_vendor.vendor_cmd[0]); @@ -3056,8 +3094,11 @@ qla24xx_bsg_request(struct bsg_job *bsg_job) } /* Disable port will bring down the chip, allow enable command */ - if (bsg_request->rqst_data.h_vendor.vendor_cmd[0] == QL_VND_MANAGE_HOST_PORT || - bsg_request->rqst_data.h_vendor.vendor_cmd[0] == QL_VND_GET_HOST_STATS) + if (bsg_request->msgcode == FC_BSG_HST_VENDOR && + bsg_job->request_len >= + sizeof(struct fc_bsg_request) + sizeof(uint32_t) && + (bsg_request->rqst_data.h_vendor.vendor_cmd[0] == QL_VND_MANAGE_HOST_PORT || + bsg_request->rqst_data.h_vendor.vendor_cmd[0] == QL_VND_GET_HOST_STATS)) goto skip_chip_chk; if (vha->hw->flags.port_isolated) { @@ -3366,6 +3407,10 @@ static int qla28xx_validate_flash_image(struct bsg_job *bsg_job) if (!IS_QLA28XX(ha) || vha->vp_idx != 0) return -EPERM; + if (bsg_job->request_len < + sizeof(struct fc_bsg_request) + 2 * sizeof(uint32_t)) + return -EINVAL; + mutex_lock(&ha->optrom_mutex); rval = qla28xx_do_validate_flash_image(bsg_job, &state); if (rval) diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h index 5593ad7fad274b..8be3dd40f6d771 100644 --- a/drivers/scsi/qla2xxx/qla_def.h +++ b/drivers/scsi/qla2xxx/qla_def.h @@ -2591,6 +2591,8 @@ typedef struct fc_port { struct list_head list; struct scsi_qla_host *vha; struct list_head unsol_ctx_head; + /* Serializes unsol_ctx_head against ISR, DPC and NVMe transport. */ + spinlock_t unsol_ctx_lock; unsigned int conf_compl_supported:1; unsigned int deleted:2; diff --git a/drivers/scsi/qla2xxx/qla_fw.h b/drivers/scsi/qla2xxx/qla_fw.h index f307beed9d29d9..e7ded95afb9a82 100644 --- a/drivers/scsi/qla2xxx/qla_fw.h +++ b/drivers/scsi/qla2xxx/qla_fw.h @@ -1442,6 +1442,10 @@ struct vp_ctrl_entry_24xx { uint8_t reserved_5[24]; }; +/* vp_idx_map is a 128-bit (16-byte) bitmap selecting target VPs. */ +#define VP_CTRL_IDX_MAP_BITS \ + (sizeof_field(struct vp_ctrl_entry_24xx, vp_idx_map) * 8) + /* * Modify Virtual Port Configuration IOCB */ diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index d38bf74ea7a543..22374f844e0814 100644 --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -4421,6 +4421,19 @@ enable_82xx_npiv: MIN_MULTI_ID_FABRIC)) ha->max_npiv_vports = MIN_MULTI_ID_FABRIC - 1; + + /* + * The VP_CTRL IOCB selects target VPs + * through the fixed vp_idx_map bitmap, + * so a vp_index beyond it can be enabled + * via VP_CONFIG but never disabled via + * VP_CTRL, leaking the VP. Cap the count + * to the bitmap capacity. + */ + if (ha->max_npiv_vports >= + VP_CTRL_IDX_MAP_BITS) + ha->max_npiv_vports = + VP_CTRL_IDX_MAP_BITS - 1; } qlt_config_nvram_with_fw_version(vha); qla2x00_get_resource_cnts(vha); @@ -5650,6 +5663,7 @@ qla2x00_alloc_fcport(scsi_qla_host_t *vha, gfp_t flags) INIT_LIST_HEAD(&fcport->gnl_entry); INIT_LIST_HEAD(&fcport->list); INIT_LIST_HEAD(&fcport->unsol_ctx_head); + spin_lock_init(&fcport->unsol_ctx_lock); INIT_LIST_HEAD(&fcport->sess_cmd_list); spin_lock_init(&fcport->sess_cmd_lock); diff --git a/drivers/scsi/qla2xxx/qla_iocb.c b/drivers/scsi/qla2xxx/qla_iocb.c index dbe3cd4e274c83..1a58dd4e8ec2fa 100644 --- a/drivers/scsi/qla2xxx/qla_iocb.c +++ b/drivers/scsi/qla2xxx/qla_iocb.c @@ -11,6 +11,10 @@ #include +/* All adapters supported by this tree use the 64-byte request ring. */ +#define qla_req_ring_slot(ha, req) ((req)->ring_ptr) +#define qla_req_entry_size(ha) REQUEST_ENTRY_SIZE + static int qla_start_scsi_type6(srb_t *sp); /** * qla2x00_get_cmd_direction() - Determine control_flag data direction. @@ -2286,10 +2290,9 @@ __qla2x00_alloc_iocbs(struct qla_qpair *qpair, srb_t *sp) struct req_que *req = qpair->req; device_reg_t *reg = ISP_QUE_REG(ha, req->id); uint32_t handle; - request_t *pkt; uint16_t cnt, req_cnt; + request_t *pkt = NULL; - pkt = NULL; req_cnt = 1; handle = 0; @@ -2343,14 +2346,18 @@ __qla2x00_alloc_iocbs(struct qla_qpair *qpair, srb_t *sp) sp->handle = handle; } - /* Prep packet */ + /* + * Prep the current request-ring slot. + */ req->cnt -= req_cnt; - pkt = req->ring_ptr; - memset(pkt, 0, REQUEST_ENTRY_SIZE); + pkt = qla_req_ring_slot(ha, req); if (IS_QLAFX00(ha)) { + memset_io((void __iomem __force *)pkt, 0, + qla_req_entry_size(ha)); wrt_reg_byte((u8 __force __iomem *)&pkt->entry_count, req_cnt); wrt_reg_dword((__le32 __force __iomem *)&pkt->handle, handle); } else { + memset(pkt, 0, qla_req_entry_size(ha)); pkt->entry_count = req_cnt; pkt->handle = handle; } @@ -3826,6 +3833,12 @@ qla25xx_ctrlvp_iocb(srb_t *sp, struct vp_ctrl_entry_24xx *vce) */ map = (sp->u.iocb_cmd.u.ctrlvp.vp_index - 1) / 8; pos = (sp->u.iocb_cmd.u.ctrlvp.vp_index - 1) & 7; + if (map >= ARRAY_SIZE(vce->vp_idx_map)) { + ql_log(ql_log_warn, sp->vha, 0x307c, + "ctrlvp: vp_index %u exceeds vp_idx_map capacity\n", + sp->u.iocb_cmd.u.ctrlvp.vp_index); + return; + } vce->vp_idx_map[map] |= 1 << pos; } diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c index 612e00ca1ada05..81997119fd07d8 100644 --- a/drivers/scsi/qla2xxx/qla_isr.c +++ b/drivers/scsi/qla2xxx/qla_isr.c @@ -921,14 +921,6 @@ qla27xx_copy_multiple_pkt(struct scsi_qla_host *vha, void **pkt, do { while ((total_bytes > 0) && (entry_count_remaining > 0)) { - if (rsp_q->ring_ptr->signature == RESPONSE_PROCESSED) { - ql_dbg(ql_dbg_async, vha, 0x5084, - "Ran out of IOCBs, partial data 0x%x\n", - buffer_copy_offset); - cpu_relax(); - continue; - } - new_pkt = (sts_cont_entry_t *)rsp_q->ring_ptr; *pkt = new_pkt; @@ -1205,14 +1197,6 @@ qla27xx_copy_fpin_pkt(struct scsi_qla_host *vha, void **pkt, do { while ((total_bytes > 0) && (entry_count_remaining > 0)) { - if (rsp_q->ring_ptr->signature == RESPONSE_PROCESSED) { - ql_dbg(ql_dbg_async, vha, 0x5084, - "Ran out of IOCBs, partial data 0x%x\n", - buffer_copy_offset); - cpu_relax(); - continue; - } - new_pkt = (sts_cont_entry_t *)rsp_q->ring_ptr; *pkt = new_pkt; @@ -4142,9 +4126,24 @@ process_err: "SCM not active for this port\n"); break; } + if (qla_chk_cont_iocb_avail(vha, rsp, + (response_t *)pkt, rsp_in)) { + /* + * ring_ptr and ring_index were + * pre-incremented above. Reset them + * back to current. Wait for next + * interrupt with all IOCBs to arrive + * and re-process. + */ + rsp->ring_ptr = (response_t *)pkt; + rsp->ring_index = cur_ring_index; + + ql_dbg(ql_dbg_init, vha, 0x5095, + "Defer processing FPIN...\n"); + return; + } pure_item = qla27xx_copy_fpin_pkt(vha, (void **)&pkt, &rsp); - __update_rsp_in(is_shadow_hba, rsp, rsp_in); if (!pure_item) break; qla24xx_queue_purex_item(vha, pure_item, diff --git a/drivers/scsi/qla2xxx/qla_mbx.c b/drivers/scsi/qla2xxx/qla_mbx.c index f604aab8b161ec..aec8e9ff3f3e7a 100644 --- a/drivers/scsi/qla2xxx/qla_mbx.c +++ b/drivers/scsi/qla2xxx/qla_mbx.c @@ -4204,6 +4204,8 @@ qla24xx_report_id_acquisition(scsi_qla_host_t *vha, spin_lock_irqsave(&ha->vport_slock, flags); list_for_each_entry(vp, &ha->vp_list, list) { if (rptid_entry->vp_idx == vp->vp_idx) { + if (test_bit(VPORT_DELETE, &vp->dpc_flags)) + break; found = 1; atomic_inc(&vp->vref_count); break; @@ -5715,7 +5717,7 @@ qla2x00_get_data_rate(scsi_qla_host_t *vha) ql_dbg(ql_dbg_mbx, vha, 0x1107, "Failed=%x mb[0]=%x.\n", rval, mcp->mb[0]); } else { - if (mcp->mb[1] != 0x7) + if (mcp->mb[1] != 0x7 || IS_QLA28XX(ha)) ha->link_data_rate = mcp->mb[1]; if (IS_QLA83XX(ha) || IS_QLA27XX(ha) || IS_QLA28XX(ha)) { @@ -5726,8 +5728,6 @@ qla2x00_get_data_rate(scsi_qla_host_t *vha) ql_dbg(ql_dbg_mbx + ql_dbg_verbose, vha, 0x1108, "Done %s.\n", __func__); - if (mcp->mb[1] != 0x7) - ha->link_data_rate = mcp->mb[1]; } return rval; diff --git a/drivers/scsi/qla2xxx/qla_mid.c b/drivers/scsi/qla2xxx/qla_mid.c index c563133f751e8f..21e2f9dbe0a9ca 100644 --- a/drivers/scsi/qla2xxx/qla_mid.c +++ b/drivers/scsi/qla2xxx/qla_mid.c @@ -574,16 +574,19 @@ qla25xx_free_req_que(struct scsi_qla_host *vha, struct req_que *req) { struct qla_hw_data *ha = vha->hw; uint16_t que_id = req->id; + size_t req_entry_size = sizeof(request_t); - dma_free_coherent(&ha->pdev->dev, (req->length + 1) * - sizeof(request_t), req->ring, req->dma); + if (req->ring) + dma_free_coherent(&ha->pdev->dev, + (req->length + 1) * req_entry_size, + req->ring, req->dma); req->ring = NULL; req->dma = 0; if (que_id) { + mutex_lock(&ha->mq_lock); ha->req_q_map[que_id] = NULL; - mutex_lock(&ha->vport_lock); clear_bit(que_id, ha->req_qid_map); - mutex_unlock(&ha->vport_lock); + mutex_unlock(&ha->mq_lock); } kfree(req->outstanding_cmds); kfree(req); @@ -594,6 +597,7 @@ qla25xx_free_rsp_que(struct scsi_qla_host *vha, struct rsp_que *rsp) { struct qla_hw_data *ha = vha->hw; uint16_t que_id = rsp->id; + size_t rsp_entry_size = sizeof(response_t); if (rsp->msix && rsp->msix->have_irq) { free_irq(rsp->msix->vector, rsp->msix->handle); @@ -601,15 +605,22 @@ qla25xx_free_rsp_que(struct scsi_qla_host *vha, struct rsp_que *rsp) rsp->msix->in_use = 0; rsp->msix->handle = NULL; } - dma_free_coherent(&ha->pdev->dev, (rsp->length + 1) * - sizeof(response_t), rsp->ring, rsp->dma); + + /* Flush any queued response work before freeing the queue/qpair. */ + if (rsp->qpair && ha->wq) + cancel_work_sync(&rsp->qpair->q_work); + + if (rsp->ring) + dma_free_coherent(&ha->pdev->dev, + (rsp->length + 1) * rsp_entry_size, + rsp->ring, rsp->dma); rsp->ring = NULL; rsp->dma = 0; if (que_id) { + mutex_lock(&ha->mq_lock); ha->rsp_q_map[que_id] = NULL; - mutex_lock(&ha->vport_lock); clear_bit(que_id, ha->rsp_qid_map); - mutex_unlock(&ha->vport_lock); + mutex_unlock(&ha->mq_lock); } kfree(rsp); } @@ -794,9 +805,6 @@ qla25xx_create_req_que(struct qla_hw_data *ha, uint16_t options, if (ret != QLA_SUCCESS) { ql_log(ql_log_fatal, base_vha, 0x00df, "%s failed.\n", __func__); - mutex_lock(&ha->mq_lock); - clear_bit(que_id, ha->req_qid_map); - mutex_unlock(&ha->mq_lock); goto que_failed; } vha->flags.qpairs_req_created = 1; @@ -908,9 +916,6 @@ qla25xx_create_rsp_que(struct qla_hw_data *ha, uint16_t options, if (ret != QLA_SUCCESS) { ql_log(ql_log_fatal, base_vha, 0x00e7, "%s failed.\n", __func__); - mutex_lock(&ha->mq_lock); - clear_bit(que_id, ha->rsp_qid_map); - mutex_unlock(&ha->mq_lock); goto que_failed; } vha->flags.qpairs_rsp_created = 1; @@ -957,6 +962,22 @@ int qla24xx_control_vp(scsi_qla_host_t *vha, int cmd) if (vp_index == 0 || vp_index >= ha->max_npiv_vports) return QLA_PARAMETER_ERROR; + /* + * The VP_CTRL IOCB selects the target VP through a fixed 128-bit + * (16-byte) vp_idx_map bitmap, so vp_index must fit within it even + * if firmware advertises more NPIV vports. + */ + if (vp_index > sizeof_field(struct vp_ctrl_entry_24xx, vp_idx_map) * 8) + return QLA_PARAMETER_ERROR; + + /* + * The VP_CTRL IOCB selects the target VP through a fixed 128-bit + * (16-byte) vp_idx_map bitmap, so vp_index must fit within it even + * if firmware advertises more NPIV vports. + */ + if (vp_index > VP_CTRL_IDX_MAP_BITS) + return QLA_PARAMETER_ERROR; + /* ref: INIT */ sp = qla2x00_get_sp(base_vha, NULL, GFP_KERNEL); if (!sp) diff --git a/drivers/scsi/qla2xxx/qla_nvme.c b/drivers/scsi/qla2xxx/qla_nvme.c index b84fe71ea340da..71772226819625 100644 --- a/drivers/scsi/qla2xxx/qla_nvme.c +++ b/drivers/scsi/qla2xxx/qla_nvme.c @@ -257,7 +257,9 @@ static void qla_nvme_release_lsrsp_cmd_kref(struct kref *kref) fd_rsp = uctx->fd_rsp; + spin_lock_irqsave(&uctx->fcport->unsol_ctx_lock, flags); list_del(&uctx->elem); + spin_unlock_irqrestore(&uctx->fcport->unsol_ctx_lock, flags); fd_rsp->done(fd_rsp); kfree(uctx); @@ -446,6 +448,9 @@ out: qla_nvme_ls_reject_iocb(vha, ha->base_qpair, &a, true); spin_unlock_irqrestore(ha->base_qpair->qp_lock_ptr, flags); } + spin_lock_irqsave(&uctx->fcport->unsol_ctx_lock, flags); + list_del(&uctx->elem); + spin_unlock_irqrestore(&uctx->fcport->unsol_ctx_lock, flags); kfree(uctx); return rval; } @@ -1215,7 +1220,9 @@ qla2xxx_process_purls_pkt(struct scsi_qla_host *vha, struct purex_item *item) spin_unlock_irqrestore(vha->hw->base_qpair->qp_lock_ptr, flags); } + spin_lock_irqsave(&uctx->fcport->unsol_ctx_lock, flags); list_del(&uctx->elem); + spin_unlock_irqrestore(&uctx->fcport->unsol_ctx_lock, flags); kfree(uctx); } } @@ -1257,6 +1264,7 @@ void qla2xxx_process_purls_iocb(void **pkt, struct rsp_que **rsp) struct purex_item *item; port_id_t d_id = {0}; port_id_t id = {0}; + unsigned long flags; u8 *opcode; bool xmt_reject = false; @@ -1322,7 +1330,9 @@ void qla2xxx_process_purls_iocb(void **pkt, struct rsp_que **rsp) uctx->ox_id = p->ox_id; qla_rport->uctx = uctx; INIT_LIST_HEAD(&uctx->elem); + spin_lock_irqsave(&fcport->unsol_ctx_lock, flags); list_add_tail(&uctx->elem, &fcport->unsol_ctx_head); + spin_unlock_irqrestore(&fcport->unsol_ctx_lock, flags); item->purls_context = (void *)uctx; ql_dbg(ql_dbg_unsol, vha, 0x2121, diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index d853b4006f4e79..e0c5732037adfb 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -4484,25 +4484,40 @@ qla2x00_mem_alloc(struct qla_hw_data *ha, uint16_t req_len, uint16_t rsp_len, fail_lsrjt: dma_free_coherent(&ha->pdev->dev, ha->elsrej.size, ha->elsrej.c, ha->elsrej.cdma); + ha->elsrej.c = NULL; + ha->elsrej.cdma = 0; fail_elsrej: dma_pool_destroy(ha->purex_dma_pool); + ha->purex_dma_pool = NULL; fail_flt: dma_free_coherent(&ha->pdev->dev, sizeof(struct qla_flt_header) + FLT_REGIONS_SIZE, ha->flt, ha->flt_dma); + ha->flt = NULL; + ha->flt_dma = 0; fail_flt_buffer: dma_free_coherent(&ha->pdev->dev, SFP_DEV_SIZE, ha->sfp_data, ha->sfp_data_dma); + ha->sfp_data = NULL; + ha->sfp_data_dma = 0; fail_sfp_data: kfree(ha->loop_id_map); + ha->loop_id_map = NULL; fail_loop_id_map: dma_pool_free(ha->s_dma_pool, ha->async_pd, ha->async_pd_dma); + ha->async_pd = NULL; + ha->async_pd_dma = 0; fail_async_pd: dma_pool_free(ha->s_dma_pool, ha->sf_init_cb, ha->sf_init_cb_dma); + ha->sf_init_cb = NULL; + ha->sf_init_cb_dma = 0; fail_sf_init_cb: dma_pool_free(ha->s_dma_pool, ha->ex_init_cb, ha->ex_init_cb_dma); + ha->ex_init_cb = NULL; + ha->ex_init_cb_dma = 0; fail_ex_init_cb: kfree(ha->npiv_info); + ha->npiv_info = NULL; fail_npiv_info: dma_free_coherent(&ha->pdev->dev, ((*rsp)->length + 1) * sizeof(response_t), (*rsp)->ring, (*rsp)->dma); diff --git a/drivers/staging/fbtft/fbtft-core.c b/drivers/staging/fbtft/fbtft-core.c index ca0c38221c16bb..7925d974de8017 100644 --- a/drivers/staging/fbtft/fbtft-core.c +++ b/drivers/staging/fbtft/fbtft-core.c @@ -298,14 +298,15 @@ static void fbtft_mkdirty(struct fb_info *info, int y, int height) { struct fbtft_par *par = info->par; struct fb_deferred_io *fbdefio = info->fbdefio; + unsigned long flags; /* Mark display lines/area as dirty */ - spin_lock(&par->dirty_lock); + spin_lock_irqsave(&par->dirty_lock, flags); if (y < par->dirty_lines_start) par->dirty_lines_start = y; if (y + height - 1 > par->dirty_lines_end) par->dirty_lines_end = y + height - 1; - spin_unlock(&par->dirty_lock); + spin_unlock_irqrestore(&par->dirty_lock, flags); /* Schedule deferred_io to update display (no-op if already on queue)*/ schedule_delayed_work(&info->deferred_work, fbdefio->delay); @@ -318,13 +319,13 @@ static void fbtft_deferred_io(struct fb_info *info, struct list_head *pagereflis struct fb_deferred_io_pageref *pageref; unsigned int y_low = 0, y_high = 0; - spin_lock(&par->dirty_lock); + spin_lock_irq(&par->dirty_lock); dirty_lines_start = par->dirty_lines_start; dirty_lines_end = par->dirty_lines_end; /* set display line markers as clean */ par->dirty_lines_start = par->info->var.yres - 1; par->dirty_lines_end = 0; - spin_unlock(&par->dirty_lock); + spin_unlock_irq(&par->dirty_lock); /* Mark display lines as dirty */ list_for_each_entry(pageref, pagereflist, list) { diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c index 62ada3a52210ea..124ff269b8e759 100644 --- a/drivers/target/iscsi/iscsi_target.c +++ b/drivers/target/iscsi/iscsi_target.c @@ -1533,8 +1533,10 @@ __iscsit_check_dataout_hdr(struct iscsit_conn *conn, void *buf, */ if (se_cmd->transport_state & CMD_T_ABORTED) { if (hdr->flags & ISCSI_FLAG_CMD_FINAL && - --cmd->outstanding_r2ts < 1) + --cmd->outstanding_r2ts < 1) { iscsit_stop_dataout_timer(cmd); + target_complete_cmd(se_cmd, SAM_STAT_TASK_ABORTED); + } return iscsit_dump_data_payload(conn, payload_length, 1); } diff --git a/drivers/thermal/db8500_thermal.c b/drivers/thermal/db8500_thermal.c index 576f88b6a1b352..cf1706569e6d7b 100644 --- a/drivers/thermal/db8500_thermal.c +++ b/drivers/thermal/db8500_thermal.c @@ -10,7 +10,7 @@ #include #include -#include +#include #include #include #include @@ -82,7 +82,7 @@ static void db8500_thermal_update_config(struct db8500_thermal_zone *th, unsigned long next_low, unsigned long next_high) { - prcmu_stop_temp_sense(); + db8500_prcmu_stop_temp_sense(); th->cur_index = idx; th->interpolated_temp = (next_low + next_high)/2; @@ -91,8 +91,8 @@ static void db8500_thermal_update_config(struct db8500_thermal_zone *th, * The PRCMU accept absolute temperatures in celsius so divide * down the millicelsius with 1000 */ - prcmu_config_hotmon((u8)(next_low/1000), (u8)(next_high/1000)); - prcmu_start_temp_sense(PRCMU_DEFAULT_MEASURE_TIME); + db8500_prcmu_config_hotmon((u8)(next_low / 1000), (u8)(next_high / 1000)); + db8500_prcmu_start_temp_sense(PRCMU_DEFAULT_MEASURE_TIME); } static irqreturn_t prcmu_low_irq_handler(int irq, void *irq_data) @@ -204,7 +204,7 @@ static int db8500_thermal_probe(struct platform_device *pdev) static int db8500_thermal_suspend(struct platform_device *pdev, pm_message_t state) { - prcmu_stop_temp_sense(); + db8500_prcmu_stop_temp_sense(); return 0; } diff --git a/drivers/thermal/thermal_sysfs.c b/drivers/thermal/thermal_sysfs.c index b44abfc997edf3..44bd7c50e4ac2a 100644 --- a/drivers/thermal/thermal_sysfs.c +++ b/drivers/thermal/thermal_sysfs.c @@ -400,8 +400,8 @@ static int create_trip_attrs(struct thermal_zone_device *tz) struct thermal_trip_attrs *trip_attrs = &td->trip_attrs; /* create trip type attribute */ - snprintf(trip_attrs->type.name, THERMAL_NAME_LENGTH, - "trip_point_%d_type", i); + scnprintf(trip_attrs->type.name, sizeof(trip_attrs->type.name), + "trip_point_%d_type", i); sysfs_attr_init(&trip_attrs->type.attr.attr); trip_attrs->type.attr.attr.name = trip_attrs->type.name; @@ -410,8 +410,8 @@ static int create_trip_attrs(struct thermal_zone_device *tz) attrs[i] = &trip_attrs->type.attr.attr; /* create trip temp attribute */ - snprintf(trip_attrs->temp.name, THERMAL_NAME_LENGTH, - "trip_point_%d_temp", i); + scnprintf(trip_attrs->temp.name, sizeof(trip_attrs->temp.name), + "trip_point_%d_temp", i); sysfs_attr_init(&trip_attrs->temp.attr.attr); trip_attrs->temp.attr.attr.name = trip_attrs->temp.name; @@ -423,8 +423,8 @@ static int create_trip_attrs(struct thermal_zone_device *tz) } attrs[i + tz->num_trips] = &trip_attrs->temp.attr.attr; - snprintf(trip_attrs->hyst.name, THERMAL_NAME_LENGTH, - "trip_point_%d_hyst", i); + scnprintf(trip_attrs->hyst.name, sizeof(trip_attrs->hyst.name), + "trip_point_%d_hyst", i); sysfs_attr_init(&trip_attrs->hyst.attr.attr); trip_attrs->hyst.attr.attr.name = trip_attrs->hyst.name; diff --git a/drivers/ufs/host/ufshcd-pci.c b/drivers/ufs/host/ufshcd-pci.c index f2433879b0ebaa..21bb11c724bea5 100644 --- a/drivers/ufs/host/ufshcd-pci.c +++ b/drivers/ufs/host/ufshcd-pci.c @@ -181,6 +181,25 @@ static int ufs_intel_lkf_pwr_change_notify(struct ufs_hba *hba, return err; } +static int ufs_intel_nvl_pwr_change_notify(struct ufs_hba *hba, + enum ufs_notify_change_status stage, + struct ufs_pa_layer_attr *dev_req_params) +{ + int adapt_val; + + if (stage != PRE_CHANGE || hba->ufs_version < ufshci_version(4, 0)) + return 0; + + if (dev_req_params->pwr_tx == FAST_MODE || dev_req_params->pwr_tx == FASTAUTO_MODE) + adapt_val = PA_INITIAL_ADAPT; + else + adapt_val = PA_NO_ADAPT; + + ufshcd_dme_configure_adapt(hba, dev_req_params->gear_tx, adapt_val); + + return 0; +} + static int ufs_intel_lkf_apply_dev_quirks(struct ufs_hba *hba) { u32 granularity, peer_granularity; @@ -441,6 +460,43 @@ static int ufs_intel_mtl_init(struct ufs_hba *hba) return ufs_intel_common_init(hba); } +static int ufs_intel_mcq_config_resource(struct ufs_hba *hba) +{ + hba->mcq_base = hba->mmio_base + ufshcd_mcq_queue_cfg_addr(hba); + + return 0; +} + +/* + * This Intel UFS4.0 controller maps MCQ doorbell and interrupt-status + * registers into the same PCI BAR as the legacy HCI space, at this + * fixed offset/stride. + */ +#define UFS_INTEL_SQDAO0 0x2800 +#define UFS_INTEL_SQISAO0 0x2814 +#define UFS_INTEL_CQDAO0 0x281C +#define UFS_INTEL_CQISAO0 0x2824 +#define UFS_INTEL_MCQ_STRIDE 0x30 + +static int ufs_intel_op_runtime_config(struct ufs_hba *hba) +{ + struct ufshcd_mcq_opr_info_t *opr; + int i; + + hba->mcq_opr[OPR_SQD].offset = UFS_INTEL_SQDAO0; + hba->mcq_opr[OPR_SQIS].offset = UFS_INTEL_SQISAO0; + hba->mcq_opr[OPR_CQD].offset = UFS_INTEL_CQDAO0; + hba->mcq_opr[OPR_CQIS].offset = UFS_INTEL_CQISAO0; + + for (i = 0; i < OPR_MAX; i++) { + opr = &hba->mcq_opr[i]; + opr->stride = UFS_INTEL_MCQ_STRIDE; + opr->base = hba->mmio_base + opr->offset; + } + + return 0; +} + static int ufs_qemu_get_hba_mac(struct ufs_hba *hba) { return MAX_SUPP_MAC; @@ -527,6 +583,9 @@ static struct ufs_hba_variant_ops ufs_intel_mtl_hba_vops = { .exit = ufs_intel_common_exit, .hce_enable_notify = ufs_intel_hce_enable_notify, .link_startup_notify = ufs_intel_link_startup_notify, + .pwr_change_notify = ufs_intel_nvl_pwr_change_notify, + .mcq_config_resource = ufs_intel_mcq_config_resource, + .op_runtime_config = ufs_intel_op_runtime_config, .resume = ufs_intel_resume, .device_reset = ufs_intel_device_reset, }; diff --git a/drivers/usb/atm/xusbatm.c b/drivers/usb/atm/xusbatm.c index 0befbf63d1cc83..5c1e1f52155558 100644 --- a/drivers/usb/atm/xusbatm.c +++ b/drivers/usb/atm/xusbatm.c @@ -79,7 +79,7 @@ static int xusbatm_bind(struct usbatm_data *usbatm, struct usb_interface *intf, const struct usb_device_id *id) { struct usb_device *usb_dev = interface_to_usbdev(intf); - int drv_ix = id - xusbatm_usb_ids; + int drv_ix = id->driver_info; int rx_alt = rx_altsetting[drv_ix]; int tx_alt = tx_altsetting[drv_ix]; struct usb_interface *rx_intf = xusbatm_find_intf(usb_dev, rx_alt, rx_endpoint[drv_ix]); @@ -168,7 +168,8 @@ static struct usb_driver xusbatm_usb_driver = { .name = xusbatm_driver_name, .probe = xusbatm_usb_probe, .disconnect = usbatm_usb_disconnect, - .id_table = xusbatm_usb_ids + .id_table = xusbatm_usb_ids, + .no_dynamic_id = 1, }; static int __init xusbatm_init(void) @@ -190,6 +191,7 @@ static int __init xusbatm_init(void) xusbatm_usb_ids[i].match_flags = USB_DEVICE_ID_MATCH_DEVICE; xusbatm_usb_ids[i].idVendor = vendor[i]; xusbatm_usb_ids[i].idProduct = product[i]; + xusbatm_usb_ids[i].driver_info = i; xusbatm_drivers[i].driver_name = xusbatm_driver_name; xusbatm_drivers[i].bind = xusbatm_bind; diff --git a/drivers/usb/class/usbtmc.c b/drivers/usb/class/usbtmc.c index af9ae55dae14e0..51cd9320a7366a 100644 --- a/drivers/usb/class/usbtmc.c +++ b/drivers/usb/class/usbtmc.c @@ -71,7 +71,6 @@ struct usbtmc_dev_capabilities { * allocated for each USBTMC device in the driver's probe function. */ struct usbtmc_device_data { - const struct usb_device_id *id; struct usb_device *usb_dev; struct usb_interface *intf; struct list_head file_list; @@ -2394,7 +2393,6 @@ static int usbtmc_probe(struct usb_interface *intf, return -ENOMEM; data->intf = intf; - data->id = id; data->usb_dev = usb_get_dev(interface_to_usbdev(intf)); usb_set_intfdata(intf, data); kref_init(&data->kref); diff --git a/drivers/usb/serial/spcp8x5.c b/drivers/usb/serial/spcp8x5.c index f610aef6bf59b1..3ef7ca2c0cf44c 100644 --- a/drivers/usb/serial/spcp8x5.c +++ b/drivers/usb/serial/spcp8x5.c @@ -133,14 +133,14 @@ struct spcp8x5_private { static int spcp8x5_probe(struct usb_serial *serial, const struct usb_device_id *id) { - usb_set_serial_data(serial, (void *)id); + usb_set_serial_data(serial, (void *)id->driver_info); return 0; } static int spcp8x5_port_probe(struct usb_serial_port *port) { - const struct usb_device_id *id = usb_get_serial_data(port->serial); + unsigned int quirks = (unsigned int)(unsigned long)usb_get_serial_data(port->serial); struct spcp8x5_private *priv; priv = kzalloc_obj(*priv); @@ -148,7 +148,7 @@ static int spcp8x5_port_probe(struct usb_serial_port *port) return -ENOMEM; spin_lock_init(&priv->lock); - priv->quirks = id->driver_info; + priv->quirks = quirks; usb_set_serial_port_data(port, priv); diff --git a/drivers/vdpa/ifcvf/ifcvf_main.c b/drivers/vdpa/ifcvf/ifcvf_main.c index ab6d6ab3b3d8d9..2af1cec9588481 100644 --- a/drivers/vdpa/ifcvf/ifcvf_main.c +++ b/drivers/vdpa/ifcvf/ifcvf_main.c @@ -724,7 +724,8 @@ static int ifcvf_vdpa_dev_add(struct vdpa_mgmt_dev *mdev, const char *name, if (config->device_features & ~device_features) { IFCVF_ERR(pdev, "The provisioned features 0x%llx are not supported by this device with features 0x%llx\n", config->device_features, device_features); - return -EINVAL; + ret = -EINVAL; + goto err; } device_features &= config->device_features; } diff --git a/drivers/vdpa/solidrun/snet_main.c b/drivers/vdpa/solidrun/snet_main.c index 28d55315df2a8e..3e2cea1e45f3ed 100644 --- a/drivers/vdpa/solidrun/snet_main.c +++ b/drivers/vdpa/solidrun/snet_main.c @@ -418,11 +418,15 @@ static int snet_request_irqs(struct pci_dev *pdev, struct snet *snet) snet->vqs[i]->irq_name, snet->vqs[i]); if (ret) { SNET_ERR(pdev, "Failed to request IRQ\n"); - return ret; + goto err_free_irqs; } snet->vqs[i]->irq = irq; } return 0; + +err_free_irqs: + snet_free_irqs(snet); + return ret; } static void snet_set_status(struct vdpa_device *vdev, u8 status) diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c b/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c index f70f454dde8eb7..76dd5b0828d7a3 100644 --- a/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c +++ b/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c @@ -79,10 +79,11 @@ static void vdpasim_blk_buffer_unlock(struct vdpasim_blk *blk) static bool vdpasim_blk_check_range(struct vdpasim *vdpasim, u64 start_sector, u64 num_sectors, u64 max_sectors) { - if (start_sector > VDPASIM_BLK_CAPACITY) { + if (start_sector >= VDPASIM_BLK_CAPACITY) { dev_dbg(&vdpasim->vdpa.dev, "starting sector exceeds the capacity - start: 0x%llx capacity: 0x%x\n", start_sector, VDPASIM_BLK_CAPACITY); + return false; } if (num_sectors > max_sectors) { diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim_net.c b/drivers/vdpa/vdpa_sim/vdpa_sim_net.c index 29fd14ce5860b6..a6514b5ccd8654 100644 --- a/drivers/vdpa/vdpa_sim/vdpa_sim_net.c +++ b/drivers/vdpa/vdpa_sim/vdpa_sim_net.c @@ -225,10 +225,15 @@ static void vdpasim_net_work(struct vdpasim *vdpasim) break; } - ++tx_pkts; read = vringh_iov_pull_iotlb(&txq->vring, &txq->out_iov, net->buffer, PAGE_SIZE); + if (read <= 0) { + ++tx_errors; + vdpasim_net_complete(txq, 0); + continue; + } + ++tx_pkts; tx_bytes += read; if (!receive_filter(vdpasim, read)) { diff --git a/drivers/vdpa/vdpa_user/vduse_dev.c b/drivers/vdpa/vdpa_user/vduse_dev.c index 10dcf016bfb061..ed71e5835e60c7 100644 --- a/drivers/vdpa/vdpa_user/vduse_dev.c +++ b/drivers/vdpa/vdpa_user/vduse_dev.c @@ -1751,11 +1751,11 @@ static long vduse_dev_compat_ioctl(struct file *file, unsigned int cmd, break; } default: - ret = -ENOIOCTLCMD; - break; + return vduse_dev_ioctl(file, cmd, + (unsigned long)compat_ptr(arg)); } - return vduse_dev_ioctl(file, cmd, (unsigned long)compat_ptr(arg)); + return ret; } #else #define vduse_dev_compat_ioctl compat_ptr_ioctl @@ -2094,7 +2094,9 @@ static bool vduse_validate_config(struct vduse_dev_config *config, return false; } - if (config->vq_align > PAGE_SIZE) + if (config->vq_align < VRING_USED_ALIGN_SIZE || + !is_power_of_2(config->vq_align) || + config->vq_align > PAGE_SIZE) return false; if (config->config_size > PAGE_SIZE) diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index 38d9c184082d0f..4d9d7c2216ed59 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -1696,6 +1696,8 @@ static int vhost_net_set_features(struct vhost_net *n, const u64 *features) if (virtio_features_test_bit(features, VIRTIO_F_ACCESS_PLATFORM)) { if (vhost_init_device_iotlb(&n->dev)) goto out_unlock; + } else { + vhost_clear_device_iotlb(&n->dev); } for (i = 0; i < VHOST_NET_VQ_MAX; ++i) { diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index c3d913bd7cac7c..a31786796d4cef 100644 --- a/drivers/vhost/vdpa.c +++ b/drivers/vhost/vdpa.c @@ -58,9 +58,12 @@ struct vhost_vdpa { struct cdev cdev; atomic_t opened; u32 nvqs; + u16 vq_num_max; int virtio_id; int minor; struct eventfd_ctx *config_ctx; + /* Serialises vhost_vdpa_config_cb() against config_ctx being replaced. */ + spinlock_t config_lock; int in_batch; struct vdpa_iova_range range; u32 batch_asid; @@ -194,10 +197,12 @@ static irqreturn_t vhost_vdpa_virtqueue_cb(void *private) static irqreturn_t vhost_vdpa_config_cb(void *private) { struct vhost_vdpa *v = private; - struct eventfd_ctx *config_ctx = v->config_ctx; + unsigned long flags; - if (config_ctx) - eventfd_signal(config_ctx); + spin_lock_irqsave(&v->config_lock, flags); + if (v->config_ctx) + eventfd_signal(v->config_ctx); + spin_unlock_irqrestore(&v->config_lock, flags); return IRQ_HANDLED; } @@ -236,7 +241,9 @@ static void vhost_vdpa_unsetup_vq_irq(struct vhost_vdpa *v, u16 qid) static int _compat_vdpa_reset(struct vhost_vdpa *v) { struct vdpa_device *vdpa = v->vdpa; + const struct vdpa_config_ops *ops = vdpa->config; u32 flags = 0; + int ret; v->suspended = false; @@ -246,7 +253,14 @@ static int _compat_vdpa_reset(struct vhost_vdpa *v) VDPA_RESET_F_CLEAN_MAP : 0; } - return vdpa_reset(vdpa, flags); + v->vq_num_max = 0; + ret = vdpa_reset(vdpa, flags); + if (!ret) { + /* Some backends derive the max from mutable queue state. */ + v->vq_num_max = ops->get_vq_num_max(vdpa); + } + + return ret; } static int vhost_vdpa_reset(struct vhost_vdpa *v) @@ -518,15 +532,22 @@ static long vhost_vdpa_get_vring_num(struct vhost_vdpa *v, u16 __user *argp) static void vhost_vdpa_config_put(struct vhost_vdpa *v) { - if (v->config_ctx) { - eventfd_ctx_put(v->config_ctx); - v->config_ctx = NULL; - } + struct eventfd_ctx *ctx; + unsigned long flags; + + spin_lock_irqsave(&v->config_lock, flags); + ctx = v->config_ctx; + v->config_ctx = NULL; + spin_unlock_irqrestore(&v->config_lock, flags); + + if (ctx) + eventfd_ctx_put(ctx); } static long vhost_vdpa_set_config_call(struct vhost_vdpa *v, u32 __user *argp) { struct vdpa_callback cb; + unsigned long flags; int fd; struct eventfd_ctx *ctx; @@ -536,18 +557,20 @@ static long vhost_vdpa_set_config_call(struct vhost_vdpa *v, u32 __user *argp) return -EFAULT; ctx = fd == VHOST_FILE_UNBIND ? NULL : eventfd_ctx_fdget(fd); + if (IS_ERR(ctx)) + return PTR_ERR(ctx); + + spin_lock_irqsave(&v->config_lock, flags); swap(ctx, v->config_ctx); + spin_unlock_irqrestore(&v->config_lock, flags); - if (!IS_ERR_OR_NULL(ctx)) + /* + * The callback can no longer reach the old context, so this is the + * last reference to it. + */ + if (ctx) eventfd_ctx_put(ctx); - if (IS_ERR(v->config_ctx)) { - long ret = PTR_ERR(v->config_ctx); - - v->config_ctx = NULL; - return ret; - } - v->vdpa->config->set_config_cb(v->vdpa, &cb); return 0; @@ -648,9 +671,15 @@ static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd, u32 idx; long r; - r = get_user(idx, (u32 __user *)argp); - if (r < 0) - return r; + if (cmd == VHOST_SET_VRING_NUM) { + if (copy_from_user(&s, argp, sizeof(s))) + return -EFAULT; + idx = s.index; + } else { + r = get_user(idx, (u32 __user *)argp); + if (r < 0) + return r; + } if (idx >= v->nvqs) return -ENOBUFS; @@ -659,6 +688,23 @@ static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd, vq = &v->vqs[idx]; switch (cmd) { + case VHOST_SET_VRING_NUM: + mutex_lock(&vq->mutex); + if (vq->private_data) { + r = -EBUSY; + } else if (!s.num || s.num > 0xffff || + s.num > v->vq_num_max || + (s.num & (s.num - 1))) { + r = -EINVAL; + } else { + vq->num = s.num; + r = 0; + } + mutex_unlock(&vq->mutex); + if (r) + return r; + ops->set_vq_num(vdpa, idx, s.num); + return 0; case VHOST_VDPA_SET_VRING_ENABLE: if (copy_from_user(&s, argp, sizeof(s))) return -EFAULT; @@ -772,9 +818,6 @@ static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd, ops->set_vq_cb(vdpa, idx, &cb); break; - case VHOST_SET_VRING_NUM: - ops->set_vq_num(vdpa, idx, vq->num); - break; } return r; @@ -1613,6 +1656,7 @@ static int vhost_vdpa_probe(struct vdpa_device *vdpa) } atomic_set(&v->opened, 0); + spin_lock_init(&v->config_lock); v->minor = minor; v->vdpa = vdpa; v->nvqs = vdpa->nvqs; diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index 269efad90369e5..f9511be1fa43f9 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -344,6 +344,17 @@ static void __vhost_vq_meta_reset(struct vhost_virtqueue *vq) vq->meta_iotlb[j] = NULL; } +/* Caller must hold the virtqueue mutex. */ +static void vhost_vq_invalidate_access(struct vhost_virtqueue *vq) +{ + vq->desc = NULL; + vq->avail = NULL; + vq->used = NULL; + vq->log_used = false; + vq->log_addr = -1ull; + __vhost_vq_meta_reset(vq); +} + static void vhost_vq_meta_reset(struct vhost_dev *d) { int i; @@ -1914,6 +1925,13 @@ int vq_meta_prefetch(struct vhost_virtqueue *vq) { unsigned int num = vq->num; + /* + * vhost_vq_invalidate_access() clears all three addresses together. + * A single zero address may be a valid GIOVA in IOTLB mode. + */ + if (!vq->desc && !vq->avail && !vq->used) + return 0; + if (!vq->iotlb) return 1; @@ -2283,6 +2301,40 @@ long vhost_vring_ioctl(struct vhost_dev *d, unsigned int ioctl, void __user *arg } EXPORT_SYMBOL_GPL(vhost_vring_ioctl); +/* Caller must hold the device mutex. */ +void vhost_clear_device_iotlb(struct vhost_dev *d) +{ + struct vhost_iotlb *iotlb; + int i; + + iotlb = d->iotlb; + if (!iotlb) + return; + + vhost_dev_lock_vqs(d); + + /* + * vhost_dev_lock_vqs() takes all VQ mutexes in index order. Drop the + * device-wide view while they are held, then clear each per-VQ view + * and its cached ring access before releasing the locks. Workers + * cannot observe a mixed address-space state during this handoff. + */ + d->iotlb = NULL; + + for (i = 0; i < d->nvqs; ++i) { + struct vhost_virtqueue *vq = d->vqs[i]; + + vq->iotlb = NULL; + vhost_vq_invalidate_access(vq); + } + + vhost_dev_unlock_vqs(d); + vhost_clear_msg(d); + vhost_iotlb_free(iotlb); + wake_up_interruptible_poll(&d->wait, EPOLLIN | EPOLLRDNORM); +} +EXPORT_SYMBOL_GPL(vhost_clear_device_iotlb); + int vhost_init_device_iotlb(struct vhost_dev *d) { struct vhost_iotlb *niotlb, *oiotlb; @@ -2303,7 +2355,10 @@ int vhost_init_device_iotlb(struct vhost_dev *d) mutex_lock(&vq->mutex); vq->iotlb = niotlb; - __vhost_vq_meta_reset(vq); + if (oiotlb) + __vhost_vq_meta_reset(vq); + else + vhost_vq_invalidate_access(vq); mutex_unlock(&vq->mutex); } diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h index 0192ade6e74910..3c75e80893730e 100644 --- a/drivers/vhost/vhost.h +++ b/drivers/vhost/vhost.h @@ -277,6 +277,7 @@ ssize_t vhost_chr_read_iter(struct vhost_dev *dev, struct iov_iter *to, int noblock); ssize_t vhost_chr_write_iter(struct vhost_dev *dev, struct iov_iter *from); +void vhost_clear_device_iotlb(struct vhost_dev *d); int vhost_init_device_iotlb(struct vhost_dev *d); void vhost_iotlb_map_free(struct vhost_iotlb *iotlb, diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c index 9aaab6bb8061c1..abed1fbcf66cc5 100644 --- a/drivers/vhost/vsock.c +++ b/drivers/vhost/vsock.c @@ -868,6 +868,8 @@ static int vhost_vsock_set_features(struct vhost_vsock *vsock, u64 features) if ((features & (1ULL << VIRTIO_F_ACCESS_PLATFORM))) { if (vhost_init_device_iotlb(&vsock->dev)) goto err; + } else { + vhost_clear_device_iotlb(&vsock->dev); } vsock->seqpacket_allow = features & (1ULL << VIRTIO_VSOCK_F_SEQPACKET); diff --git a/drivers/video/fbdev/vfb.c b/drivers/video/fbdev/vfb.c index 5b7965f36c5eda..de137b2bdaedc6 100644 --- a/drivers/video/fbdev/vfb.c +++ b/drivers/video/fbdev/vfb.c @@ -78,6 +78,13 @@ static int vfb_pan_display(struct fb_var_screeninfo *var, static int vfb_mmap(struct fb_info *info, struct vm_area_struct *vma); +static void vfb_destroy(struct fb_info *info) +{ + vfree(info->screen_buffer); + fb_dealloc_cmap(&info->cmap); + framebuffer_release(info); +} + static const struct fb_ops vfb_ops = { .owner = THIS_MODULE, __FB_DEFAULT_SYSMEM_OPS_RDWR, @@ -87,6 +94,7 @@ static const struct fb_ops vfb_ops = { .fb_pan_display = vfb_pan_display, __FB_DEFAULT_SYSMEM_OPS_DRAW, .fb_mmap = vfb_mmap, + .fb_destroy = vfb_destroy, }; /* @@ -485,9 +493,6 @@ static void vfb_remove(struct platform_device *dev) if (info) { unregister_framebuffer(info); - vfree(videomemory); - fb_dealloc_cmap(&info->cmap); - framebuffer_release(info); } } diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c index 75bb4ffe3b8774..b6c9e927bef570 100644 --- a/drivers/virtio/virtio.c +++ b/drivers/virtio/virtio.c @@ -604,8 +604,8 @@ void unregister_virtio_device(struct virtio_device *dev) { int index = dev->index; /* save for after device release */ - device_unregister(&dev->dev); virtio_debug_device_exit(dev); + device_unregister(&dev->dev); ida_free(&virtio_index_ida, index); } EXPORT_SYMBOL_GPL(unregister_virtio_device); diff --git a/drivers/virtio/virtio_input.c b/drivers/virtio/virtio_input.c index deec24e8e68283..e3bd0b9616f94b 100644 --- a/drivers/virtio/virtio_input.c +++ b/drivers/virtio/virtio_input.c @@ -49,9 +49,12 @@ static void virtinput_recv_events(struct virtqueue *vq) le16_to_cpu(event->code), le32_to_cpu(event->value)); spin_lock_irqsave(&vi->lock, flags); + if (!vi->ready) + continue; virtinput_queue_evtbuf(vi, event); } - virtqueue_kick(vq); + if (vi->ready) + virtqueue_kick(vq); } spin_unlock_irqrestore(&vi->lock, flags); } @@ -331,6 +334,7 @@ err_input_register: spin_lock_irqsave(&vi->lock, flags); vi->ready = false; spin_unlock_irqrestore(&vi->lock, flags); + virtio_reset_device(vdev); err_mt_init_slots: input_free_device(vi->idev); err_input_alloc: @@ -350,8 +354,9 @@ static void virtinput_remove(struct virtio_device *vdev) vi->ready = false; spin_unlock_irqrestore(&vi->lock, flags); - input_unregister_device(vi->idev); + /* Callbacks use vi->idev. */ virtio_reset_device(vdev); + input_unregister_device(vi->idev); while ((buf = virtqueue_detach_unused_buf(vi->sts)) != NULL) kfree(buf); vdev->config->del_vqs(vdev); diff --git a/drivers/virtio/virtio_mmio.c b/drivers/virtio/virtio_mmio.c index 510b7c4efdff8b..d5b148bde180ab 100644 --- a/drivers/virtio/virtio_mmio.c +++ b/drivers/virtio/virtio_mmio.c @@ -87,6 +87,9 @@ struct virtio_mmio_device { void __iomem *base; unsigned long version; + + /* True if enable_irq_wake() succeeded for the shared IRQ. */ + bool wake_irq_enabled; }; /* Configuration interface */ @@ -329,11 +332,17 @@ static void vm_del_vqs(struct virtio_device *vdev) { struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev); struct virtqueue *vq, *n; + int irq = platform_get_irq(vm_dev->pdev, 0); list_for_each_entry_safe(vq, n, &vdev->vqs, list) vm_del_vq(vq); - free_irq(platform_get_irq(vm_dev->pdev, 0), vm_dev); + if (vm_dev->wake_irq_enabled) { + disable_irq_wake(irq); + vm_dev->wake_irq_enabled = false; + } + + free_irq(irq, vm_dev); } static void vm_synchronize_cbs(struct virtio_device *vdev) @@ -460,8 +469,9 @@ static int vm_find_vqs(struct virtio_device *vdev, unsigned int nvqs, if (err) return err; - if (of_property_read_bool(vm_dev->pdev->dev.of_node, "wakeup-source")) - enable_irq_wake(irq); + if (of_property_read_bool(vm_dev->pdev->dev.of_node, "wakeup-source") && + !enable_irq_wake(irq)) + vm_dev->wake_irq_enabled = true; for (i = 0; i < nvqs; ++i) { struct virtqueue_info *vqi = &vqs_info[i]; diff --git a/drivers/virtio/virtio_pci_common.c b/drivers/virtio/virtio_pci_common.c index 10371ecbc054cb..b90c174450b20a 100644 --- a/drivers/virtio/virtio_pci_common.c +++ b/drivers/virtio/virtio_pci_common.c @@ -120,7 +120,9 @@ static irqreturn_t vp_interrupt(int irq, void *opaque) if (isr & VIRTIO_PCI_ISR_CONFIG) vp_config_changed(irq, opaque); - return vp_vring_interrupt(irq, opaque); + vp_vring_interrupt(irq, opaque); + + return IRQ_HANDLED; } static int vp_request_msix_vectors(struct virtio_device *vdev, int nvectors, diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index b438dc2ce1b80a..a9e1ee9536b5be 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -1670,7 +1670,7 @@ static inline int virtqueue_add_packed(struct vring_virtqueue *vq, struct scatterlist *sg; unsigned int i, n, c, descs_used, err_idx, len; __le16 head_flags, flags; - u16 head, id, prev, curr, avail_used_flags; + u16 head, id, prev, curr, avail_used_flags, unpub_flags; int err; START_USE(vq); @@ -1798,15 +1798,30 @@ unmap_release: curr = vq->free_head; vq->packed.avail_used_flags = avail_used_flags; + unpub_flags = avail_used_flags ^ (1 << VRING_PACKED_DESC_F_AVAIL | + 1 << VRING_PACKED_DESC_F_USED); for (n = 0; n < total_sg; n++) { if (i == err_idx) break; + /* + * The mapping loop made every descriptor but the head + * available. Stamp the previous wrap counter's AVAIL and USED + * bits on those, so that a later and shorter chain at this head + * does not leave one of them available beyond its own last + * descriptor. Marking them used instead would hand + * is_used_desc_packed() a completion we never made. + */ + if (i != head) + desc[i].flags = cpu_to_le16(unpub_flags); vring_unmap_extra_packed(vq, &vq->packed.desc_extra[curr]); curr = vq->packed.desc_extra[curr].next; i++; - if (i >= vq->packed.vring.num) + if (i >= vq->packed.vring.num) { i = 0; + unpub_flags ^= 1 << VRING_PACKED_DESC_F_AVAIL | + 1 << VRING_PACKED_DESC_F_USED; + } } END_USE(vq); @@ -1828,7 +1843,7 @@ static inline int virtqueue_add_packed_in_order(struct vring_virtqueue *vq, struct scatterlist *sg; unsigned int i, n, sg_count, err_idx, total_in_len = 0; __le16 head_flags, flags; - u16 head, avail_used_flags; + u16 head, avail_used_flags, unpub_flags; bool avail_wrap_counter; int err; @@ -1955,14 +1970,29 @@ unmap_release: i = head; vq->packed.avail_used_flags = avail_used_flags; vq->packed.avail_wrap_counter = avail_wrap_counter; + unpub_flags = avail_used_flags ^ (1 << VRING_PACKED_DESC_F_AVAIL | + 1 << VRING_PACKED_DESC_F_USED); for (n = 0; n < total_sg; n++) { if (i == err_idx) break; + /* + * The mapping loop made every descriptor but the head + * available. Stamp the previous wrap counter's AVAIL and USED + * bits on those, so that a later and shorter chain at this head + * does not leave one of them available beyond its own last + * descriptor. Marking them used instead would hand + * is_used_desc_packed() a completion we never made. + */ + if (i != head) + desc[i].flags = cpu_to_le16(unpub_flags); vring_unmap_extra_packed(vq, &vq->packed.desc_extra[i]); i++; - if (i >= vq->packed.vring.num) + if (i >= vq->packed.vring.num) { i = 0; + unpub_flags ^= 1 << VRING_PACKED_DESC_F_AVAIL | + 1 << VRING_PACKED_DESC_F_USED; + } } END_USE(vq); diff --git a/drivers/watchdog/db8500_wdt.c b/drivers/watchdog/db8500_wdt.c index 97148ac0aa54a8..70ccea13288d87 100644 --- a/drivers/watchdog/db8500_wdt.c +++ b/drivers/watchdog/db8500_wdt.c @@ -16,7 +16,7 @@ #include #include -#include +#include #define WATCHDOG_TIMEOUT 600 /* 10 minutes */ @@ -37,24 +37,24 @@ MODULE_PARM_DESC(nowayout, static int db8500_wdt_start(struct watchdog_device *wdd) { - return prcmu_enable_a9wdog(PRCMU_WDOG_ALL); + return db8500_prcmu_enable_a9wdog(PRCMU_WDOG_ALL); } static int db8500_wdt_stop(struct watchdog_device *wdd) { - return prcmu_disable_a9wdog(PRCMU_WDOG_ALL); + return db8500_prcmu_disable_a9wdog(PRCMU_WDOG_ALL); } static int db8500_wdt_keepalive(struct watchdog_device *wdd) { - return prcmu_kick_a9wdog(PRCMU_WDOG_ALL); + return db8500_prcmu_kick_a9wdog(PRCMU_WDOG_ALL); } static int db8500_wdt_set_timeout(struct watchdog_device *wdd, unsigned int timeout) { db8500_wdt_stop(wdd); - prcmu_load_a9wdog(PRCMU_WDOG_ALL, timeout * 1000); + db8500_prcmu_load_a9wdog(PRCMU_WDOG_ALL, timeout * 1000); db8500_wdt_start(wdd); return 0; @@ -91,10 +91,10 @@ static int db8500_wdt_probe(struct platform_device *pdev) watchdog_set_nowayout(&db8500_wdt, nowayout); /* disable auto off on sleep */ - prcmu_config_a9wdog(PRCMU_WDOG_CPU1, false); + db8500_prcmu_config_a9wdog(PRCMU_WDOG_CPU1, false); /* set HW initial value */ - prcmu_load_a9wdog(PRCMU_WDOG_ALL, timeout * 1000); + db8500_prcmu_load_a9wdog(PRCMU_WDOG_ALL, timeout * 1000); ret = devm_watchdog_register_device(dev, &db8500_wdt); if (ret) @@ -110,9 +110,9 @@ static int db8500_wdt_suspend(struct platform_device *pdev, { if (watchdog_active(&db8500_wdt)) { db8500_wdt_stop(&db8500_wdt); - prcmu_config_a9wdog(PRCMU_WDOG_CPU1, true); + db8500_prcmu_config_a9wdog(PRCMU_WDOG_CPU1, true); - prcmu_load_a9wdog(PRCMU_WDOG_ALL, timeout * 1000); + db8500_prcmu_load_a9wdog(PRCMU_WDOG_ALL, timeout * 1000); db8500_wdt_start(&db8500_wdt); } return 0; @@ -122,9 +122,9 @@ static int db8500_wdt_resume(struct platform_device *pdev) { if (watchdog_active(&db8500_wdt)) { db8500_wdt_stop(&db8500_wdt); - prcmu_config_a9wdog(PRCMU_WDOG_CPU1, false); + db8500_prcmu_config_a9wdog(PRCMU_WDOG_CPU1, false); - prcmu_load_a9wdog(PRCMU_WDOG_ALL, timeout * 1000); + db8500_prcmu_load_a9wdog(PRCMU_WDOG_ALL, timeout * 1000); db8500_wdt_start(&db8500_wdt); } return 0; diff --git a/drivers/watchdog/msc313e_wdt.c b/drivers/watchdog/msc313e_wdt.c index d962589e2c55a8..4a5cce2a16b185 100644 --- a/drivers/watchdog/msc313e_wdt.c +++ b/drivers/watchdog/msc313e_wdt.c @@ -31,20 +31,36 @@ struct msc313e_wdt_priv { struct clk *clk; }; +static u32 msc313e_wdt_get_hw_timeout(struct msc313e_wdt_priv *priv) +{ + u16 low, high; + + low = readw(priv->base + REG_WDT_MAX_PRD_L); + high = readw(priv->base + REG_WDT_MAX_PRD_H); + + return ((u32)high << 16) | low; +} + +static void msc313e_wdt_set_hw_timeout(struct msc313e_wdt_priv *priv, + unsigned int timeout) +{ + u32 t = timeout * clk_get_rate(priv->clk); + + writew(t & 0xffff, priv->base + REG_WDT_MAX_PRD_L); + writew((t >> 16) & 0xffff, priv->base + REG_WDT_MAX_PRD_H); + writew(1, priv->base + REG_WDT_CLR); +} + static int msc313e_wdt_start(struct watchdog_device *wdev) { struct msc313e_wdt_priv *priv = watchdog_get_drvdata(wdev); - u32 timeout; int err; err = clk_prepare_enable(priv->clk); if (err) return err; - timeout = wdev->timeout * clk_get_rate(priv->clk); - writew(timeout & 0xffff, priv->base + REG_WDT_MAX_PRD_L); - writew((timeout >> 16) & 0xffff, priv->base + REG_WDT_MAX_PRD_H); - writew(1, priv->base + REG_WDT_CLR); + msc313e_wdt_set_hw_timeout(priv, wdev->timeout); return 0; } @@ -69,9 +85,13 @@ static int msc313e_wdt_stop(struct watchdog_device *wdev) static int msc313e_wdt_settimeout(struct watchdog_device *wdev, unsigned int new_time) { + struct msc313e_wdt_priv *priv = watchdog_get_drvdata(wdev); + wdev->timeout = new_time; - return msc313e_wdt_start(wdev); + if (watchdog_hw_running(wdev) || watchdog_active(wdev)) + msc313e_wdt_set_hw_timeout(priv, wdev->timeout); + return 0; } static const struct watchdog_info msc313e_wdt_ident = { @@ -97,6 +117,8 @@ static int msc313e_wdt_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; struct msc313e_wdt_priv *priv; + unsigned long rate; + int ret; priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL); if (!priv) @@ -116,27 +138,51 @@ static int msc313e_wdt_probe(struct platform_device *pdev) priv->wdev.ops = &msc313e_wdt_ops, priv->wdev.parent = dev; priv->wdev.min_timeout = MSC313E_WDT_MIN_TIMEOUT; - priv->wdev.max_timeout = U32_MAX / clk_get_rate(priv->clk); + rate = clk_get_rate(priv->clk); + if (!rate) + return -EINVAL; + priv->wdev.max_timeout = U32_MAX / rate; priv->wdev.timeout = MSC313E_WDT_DEFAULT_TIMEOUT; - /* If the period is non-zero the WDT is running */ - if (readw(priv->base + REG_WDT_MAX_PRD_L) | (readw(priv->base + REG_WDT_MAX_PRD_H) << 16)) - set_bit(WDOG_HW_RUNNING, &priv->wdev.status); - watchdog_set_drvdata(&priv->wdev, priv); + platform_set_drvdata(pdev, priv); watchdog_init_timeout(&priv->wdev, timeout, dev); watchdog_stop_on_reboot(&priv->wdev); watchdog_stop_on_unregister(&priv->wdev); + watchdog_stop_ping_on_suspend(&priv->wdev); + + ret = clk_prepare_enable(priv->clk); + if (ret) + return ret; + + /* If the period is non-zero the WDT is running */ + if (msc313e_wdt_get_hw_timeout(priv)) { + msc313e_wdt_set_hw_timeout(priv, priv->wdev.timeout); + set_bit(WDOG_HW_RUNNING, &priv->wdev.status); + /* + * Keep the clock enabled. The watchdog core will skip the next + * start() and a future stop() will balance the CCF reference + * count. + */ + } else { + clk_disable_unprepare(priv->clk); + } + + ret = devm_watchdog_register_device(dev, &priv->wdev); + + /* If the WDT is running and anything goes wrong, disable the clock. */ + if (ret && test_bit(WDOG_HW_RUNNING, &priv->wdev.status)) + clk_disable_unprepare(priv->clk); - return devm_watchdog_register_device(dev, &priv->wdev); + return ret; } static int __maybe_unused msc313e_wdt_suspend(struct device *dev) { struct msc313e_wdt_priv *priv = dev_get_drvdata(dev); - if (watchdog_active(&priv->wdev)) + if (watchdog_active(&priv->wdev) || watchdog_hw_running(&priv->wdev)) msc313e_wdt_stop(&priv->wdev); return 0; @@ -146,7 +192,7 @@ static int __maybe_unused msc313e_wdt_resume(struct device *dev) { struct msc313e_wdt_priv *priv = dev_get_drvdata(dev); - if (watchdog_active(&priv->wdev)) + if (watchdog_active(&priv->wdev) || watchdog_hw_running(&priv->wdev)) msc313e_wdt_start(&priv->wdev); return 0; diff --git a/drivers/watchdog/sunxi_wdt.c b/drivers/watchdog/sunxi_wdt.c index b6c761acc3de67..3db34524ed13bf 100644 --- a/drivers/watchdog/sunxi_wdt.c +++ b/drivers/watchdog/sunxi_wdt.c @@ -128,6 +128,38 @@ static int sunxi_wdt_ping(struct watchdog_device *wdt_dev) return 0; } +static bool sunxi_wdt_is_running(struct watchdog_device *wdt_dev) +{ + struct sunxi_wdt_dev *sunxi_wdt = watchdog_get_drvdata(wdt_dev); + const struct sunxi_wdt_reg *regs = sunxi_wdt->wdt_regs; + + return readl(sunxi_wdt->wdt_base + regs->wdt_mode) & WDT_MODE_EN; +} + +static unsigned int sunxi_wdt_get_timeout(struct watchdog_device *wdt_dev) +{ + struct sunxi_wdt_dev *sunxi_wdt = watchdog_get_drvdata(wdt_dev); + const struct sunxi_wdt_reg *regs = sunxi_wdt->wdt_regs; + unsigned int timeout; + u32 interval; + + interval = readl(sunxi_wdt->wdt_base + regs->wdt_mode); + interval >>= regs->wdt_timeout_shift; + interval &= WDT_TIMEOUT_MASK; + /* Round the 0.5-second interval up to the minimum representable timeout. */ + if (!interval) + return WDT_MIN_TIMEOUT; + + for (timeout = WDT_MIN_TIMEOUT; + timeout < ARRAY_SIZE(wdt_timeout_map); timeout++) { + if (wdt_timeout_map[timeout] == interval) + return timeout; + } + + /* Reserved interval encoding. */ + return 0; +} + static int sunxi_wdt_set_timeout(struct watchdog_device *wdt_dev, unsigned int timeout) { @@ -259,6 +291,7 @@ static int sunxi_wdt_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; struct sunxi_wdt_dev *sunxi_wdt; + unsigned int running_timeout; int err; sunxi_wdt = devm_kzalloc(dev, sizeof(*sunxi_wdt), GFP_KERNEL); @@ -286,7 +319,17 @@ static int sunxi_wdt_probe(struct platform_device *pdev) watchdog_set_drvdata(&sunxi_wdt->wdt_dev, sunxi_wdt); - sunxi_wdt_stop(&sunxi_wdt->wdt_dev); + if (sunxi_wdt_is_running(&sunxi_wdt->wdt_dev)) { + running_timeout = sunxi_wdt_get_timeout(&sunxi_wdt->wdt_dev); + if (running_timeout) + sunxi_wdt->wdt_dev.timeout = running_timeout; + + err = sunxi_wdt_start(&sunxi_wdt->wdt_dev); + if (err) + return err; + + set_bit(WDOG_HW_RUNNING, &sunxi_wdt->wdt_dev.status); + } watchdog_stop_on_reboot(&sunxi_wdt->wdt_dev); err = devm_watchdog_register_device(dev, &sunxi_wdt->wdt_dev); diff --git a/drivers/watchdog/watchdog_hrtimer_pretimeout.c b/drivers/watchdog/watchdog_hrtimer_pretimeout.c index fbc7eecd8b203f..49a05ea60c9792 100644 --- a/drivers/watchdog/watchdog_hrtimer_pretimeout.c +++ b/drivers/watchdog/watchdog_hrtimer_pretimeout.c @@ -30,6 +30,7 @@ void watchdog_hrtimer_pretimeout_init(struct watchdog_device *wdd) void watchdog_hrtimer_pretimeout_start(struct watchdog_device *wdd) { if (!(wdd->info->options & WDIOF_PRETIMEOUT) && + wdd->pretimeout && !watchdog_pretimeout_invalid(wdd, wdd->pretimeout)) hrtimer_start(&wdd->wd_data->pretimeout_timer, ktime_set(wdd->timeout - wdd->pretimeout, 0), diff --git a/fs/afs/addr_list.c b/fs/afs/addr_list.c index 63bf096b721aa5..73195d76b481a2 100644 --- a/fs/afs/addr_list.c +++ b/fs/afs/addr_list.c @@ -394,8 +394,11 @@ void afs_set_peer_appdata(struct afs_server *server, struct rxrpc_peer *pn = new_alist->addrs[n].peer; struct rxrpc_peer *po = old_alist->addrs[o].peer; - if (pn == po) + if (pn == po) { + n++; + o++; continue; + } if (pn < po) { rxrpc_kernel_set_peer_data(pn, data); n++; diff --git a/fs/afs/dir_edit.c b/fs/afs/dir_edit.c index 3ead36a070487a..c31303059444ad 100644 --- a/fs/afs/dir_edit.c +++ b/fs/afs/dir_edit.c @@ -442,7 +442,7 @@ void afs_edit_dir_remove(struct afs_vnode *vnode, /* Check and clear the entry. */ de = &block->dirents[slot]; if (de->u.valid != 1) - goto error_unmap; + goto error; trace_afs_edit_dir(vnode, why, afs_edit_dir_delete, b, slot, ntohl(de->u.vnode), ntohl(de->u.unique), @@ -458,7 +458,6 @@ void afs_edit_dir_remove(struct afs_vnode *vnode, /* Clear the constituent entries. */ next = de->u.hash_next; memset(de, 0, sizeof(*de) * iter.nr_slots); - kunmap_local(block); /* Adjust the hash chain: if iter->prev_entry is 0, the hashtable head * index is previous; otherwise it's slot number of the previous entry. @@ -485,7 +484,6 @@ void afs_edit_dir_remove(struct afs_vnode *vnode, pde = &pblock->dirents[ps]; prev_next = pde->u.hash_next; if (prev_next != htons(entry)) { - kunmap_local(pblock); pr_warn("%llx:%llx:%x: not prev in chain b=%x p=%x,%x e=%x %*s", vnode->fid.vid, vnode->fid.vnode, vnode->fid.unique, iter.bucket, iter.prev_entry, prev_next, entry, @@ -493,7 +491,6 @@ void afs_edit_dir_remove(struct afs_vnode *vnode, goto error; } pde->u.hash_next = next; - kunmap_local(pblock); } netfs_single_mark_inode_dirty(&vnode->netfs.inode); @@ -503,18 +500,16 @@ void afs_edit_dir_remove(struct afs_vnode *vnode, _debug("Remove %s from %u[%u]", name->name, b, slot); out_unmap: + afs_dir_end_iter(&iter); kunmap_local(meta); _leave(""); return; already_invalidated: - kunmap_local(block); trace_afs_edit_dir(vnode, why, afs_edit_dir_delete_inval, 0, 0, 0, 0, name->name); goto out_unmap; -error_unmap: - kunmap_local(block); error: trace_afs_edit_dir(vnode, why, afs_edit_dir_delete_error, 0, 0, 0, 0, name->name); diff --git a/fs/afs/dir_search.c b/fs/afs/dir_search.c index 104411c0692f57..11ebdfffcb1d38 100644 --- a/fs/afs/dir_search.c +++ b/fs/afs/dir_search.c @@ -75,10 +75,7 @@ union afs_xdr_dir_block *afs_dir_find_block(struct afs_dir_iter *iter, size_t bl _enter("%zx,%d", block, slot); - if (iter->block) { - kunmap_local(iter->block); - iter->block = NULL; - } + afs_dir_end_iter(iter); if (dvnode->directory_size < blend) goto fail; @@ -173,12 +170,8 @@ int afs_dir_search_bucket(struct afs_dir_iter *iter, const struct qstr *name, ret = -ENOENT; found: - if (iter->block) { - kunmap_local(iter->block); - iter->block = NULL; - } - bad: + afs_dir_end_iter(iter); if (ret == -ESTALE) afs_invalidate_dir(iter->dvnode, afs_dir_invalid_iter_stale); _leave(" = %d", ret); diff --git a/fs/afs/fs_probe.c b/fs/afs/fs_probe.c index a91ad1938d0788..8c62334dbfe72d 100644 --- a/fs/afs/fs_probe.c +++ b/fs/afs/fs_probe.c @@ -258,6 +258,7 @@ int afs_fs_probe_fileserver(struct afs_net *net, struct afs_server *server, lockdep_is_held(&server->fs_lock)); if (old) { estate->responsive_set = old->responsive_set; + old_alist = old->addresses; if (!new_alist) new_alist = old->addresses; } diff --git a/fs/afs/internal.h b/fs/afs/internal.h index 290873bac89b3f..330654ed16ecea 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -1133,6 +1133,14 @@ int afs_dir_search_bucket(struct afs_dir_iter *iter, const struct qstr *name, int afs_dir_search(struct afs_vnode *dvnode, const struct qstr *name, struct afs_fid *_fid, afs_dataversion_t *_dir_version); +static inline void afs_dir_end_iter(struct afs_dir_iter *iter) +{ + if (iter->block) { + kunmap_local(iter->block); + iter->block = NULL; + } +} + /* * dir_silly.c */ diff --git a/fs/afs/server.c b/fs/afs/server.c index 0fe162ea2a36db..189138bd6d712c 100644 --- a/fs/afs/server.c +++ b/fs/afs/server.c @@ -242,7 +242,6 @@ struct afs_server *afs_lookup_server(struct afs_cell *cell, struct key *key, out: afs_put_addrlist(alist, afs_alist_trace_put_server_create); if (candidate) { - kfree(rcu_access_pointer(server->endpoint_state)); kfree(candidate); afs_dec_servers_outstanding(cell->net); } diff --git a/fs/autofs/inode.c b/fs/autofs/inode.c index c1e210cec43692..6b15a3717ba7e4 100644 --- a/fs/autofs/inode.c +++ b/fs/autofs/inode.c @@ -323,8 +323,10 @@ static int autofs_fill_super(struct super_block *s, struct fs_context *fc) return -ENOMEM; root_inode = autofs_get_inode(s, S_IFDIR | 0755); - if (!root_inode) + if (!root_inode) { + autofs_free_ino(ino); return -ENOMEM; + } root_inode->i_uid = ctx->uid; root_inode->i_gid = ctx->gid; diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 39a01f9cf6b515..188b4ac9889fcb 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -3435,6 +3435,9 @@ out: */ btrfs_remove_ordered_extent(ordered_extent); + /* Cleanup any remaining biocs attached to the OE. */ + btrfs_cleanup_ordered_bioc_list(ordered_extent); + /* once for us */ btrfs_put_ordered_extent(ordered_extent); /* once for the tree */ diff --git a/fs/btrfs/raid-stripe-tree.c b/fs/btrfs/raid-stripe-tree.c index b210371ce91e38..d9e660447205f2 100644 --- a/fs/btrfs/raid-stripe-tree.c +++ b/fs/btrfs/raid-stripe-tree.c @@ -310,8 +310,10 @@ static int update_raid_extent_item(struct btrfs_trans_handle *trans, ret = btrfs_search_slot(trans, trans->fs_info->stripe_root, key, path, 0, 1); - if (ret) - return (ret == 1 ? ret : -EINVAL); + if (ret > 0) + ret = -ENOENT; + if (ret < 0) + return ret; leaf = path->nodes[0]; slot = path->slots[0]; @@ -337,7 +339,6 @@ int btrfs_insert_one_raid_extent(struct btrfs_trans_handle *trans, stripe_extent = kzalloc(item_size, GFP_NOFS); if (unlikely(!stripe_extent)) { btrfs_abort_transaction(trans, -ENOMEM); - btrfs_end_transaction(trans); return -ENOMEM; } @@ -374,7 +375,7 @@ int btrfs_insert_raid_extent(struct btrfs_trans_handle *trans, struct btrfs_ordered_extent *ordered_extent) { struct btrfs_io_context *bioc; - int ret; + int ret = 0; if (!btrfs_fs_incompat(trans->fs_info, RAID_STRIPE_TREE)) return 0; @@ -382,17 +383,23 @@ int btrfs_insert_raid_extent(struct btrfs_trans_handle *trans, list_for_each_entry(bioc, &ordered_extent->bioc_list, rst_ordered_entry) { ret = btrfs_insert_one_raid_extent(trans, bioc); if (ret) - return ret; + break; } - while (!list_empty(&ordered_extent->bioc_list)) { - bioc = list_first_entry(&ordered_extent->bioc_list, + btrfs_cleanup_ordered_bioc_list(ordered_extent); + return ret; +} + +void btrfs_cleanup_ordered_bioc_list(struct btrfs_ordered_extent *ordered) +{ + while (!list_empty(&ordered->bioc_list)) { + struct btrfs_io_context *bioc; + + bioc = list_first_entry(&ordered->bioc_list, typeof(*bioc), rst_ordered_entry); list_del(&bioc->rst_ordered_entry); btrfs_put_bioc(bioc); } - - return 0; } int btrfs_get_raid_extent_offset(struct btrfs_fs_info *fs_info, diff --git a/fs/btrfs/raid-stripe-tree.h b/fs/btrfs/raid-stripe-tree.h index 69942ad431408c..eb02cf48511bc9 100644 --- a/fs/btrfs/raid-stripe-tree.h +++ b/fs/btrfs/raid-stripe-tree.h @@ -28,6 +28,7 @@ int btrfs_get_raid_extent_offset(struct btrfs_fs_info *fs_info, u32 stripe_index, struct btrfs_io_stripe *stripe); int btrfs_insert_raid_extent(struct btrfs_trans_handle *trans, struct btrfs_ordered_extent *ordered_extent); +void btrfs_cleanup_ordered_bioc_list(struct btrfs_ordered_extent *ordered); #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS int btrfs_insert_one_raid_extent(struct btrfs_trans_handle *trans, diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index d2f7ac5b6e9617..3b3f04521369d7 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -1041,6 +1041,10 @@ static void scrub_stripe_report_errors(struct scrub_ctx *sctx, skip: for_each_set_bit(sector_nr, &extent_bitmap, stripe->nr_sectors) { + const u64 sector_logical = stripe->logical + + ((u64)sector_nr << fs_info->sectorsize_bits); + const u64 sector_physical = physical + + ((u64)sector_nr << fs_info->sectorsize_bits); bool repaired = false; if (scrub_bitmap_test_bit_is_metadata(stripe, sector_nr)) { @@ -1069,12 +1073,12 @@ skip: if (dev) { btrfs_err_rl(fs_info, "scrub: fixed up error at logical %llu on dev %s physical %llu", - stripe->logical, btrfs_dev_name(dev), - physical); + sector_logical, btrfs_dev_name(dev), + sector_physical); } else { btrfs_err_rl(fs_info, "scrub: fixed up error at logical %llu on mirror %u", - stripe->logical, stripe->mirror_num); + sector_logical, stripe->mirror_num); } continue; } @@ -1083,30 +1087,30 @@ skip: if (dev) { btrfs_err_rl(fs_info, "scrub: unable to fixup (regular) error at logical %llu on dev %s physical %llu", - stripe->logical, btrfs_dev_name(dev), - physical); + sector_logical, btrfs_dev_name(dev), + sector_physical); } else { btrfs_err_rl(fs_info, "scrub: unable to fixup (regular) error at logical %llu on mirror %u", - stripe->logical, stripe->mirror_num); + sector_logical, stripe->mirror_num); } if (scrub_bitmap_test_bit_io_error(stripe, sector_nr)) if (__ratelimit(&rs) && dev) scrub_print_common_warning("i/o error", dev, false, - stripe->logical, physical); + sector_logical, sector_physical); if (scrub_bitmap_test_bit_csum_error(stripe, sector_nr)) if (__ratelimit(&rs) && dev) scrub_print_common_warning("checksum error", dev, false, - stripe->logical, physical); + sector_logical, sector_physical); if (scrub_bitmap_test_bit_meta_error(stripe, sector_nr)) if (__ratelimit(&rs) && dev) scrub_print_common_warning("header error", dev, false, - stripe->logical, physical); + sector_logical, sector_physical); if (scrub_bitmap_test_bit_meta_gen_error(stripe, sector_nr)) if (__ratelimit(&rs) && dev) scrub_print_common_warning("generation error", dev, false, - stripe->logical, physical); + sector_logical, sector_physical); } /* Update the device stats. */ diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 3ae480c7474b0e..a888202397edb3 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -2066,7 +2066,7 @@ static int will_overwrite_ref(struct send_ctx *sctx, u64 dir, u64 dir_gen, ret = is_inode_existent(sctx, dir, dir_gen, NULL, &parent_root_dir_gen); if (ret <= 0) - return 0; + return ret; /* * If we have a parent root we need to verify that the parent dir was diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 80919590175fcd..b64c6d2855c9af 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -458,8 +458,19 @@ static int record_root_in_trans(struct btrfs_trans_handle *trans, * through btrfs_record_root_in_trans without having to take the * lock. smp_wmb() makes sure that all the writes above are * done before we pop in the zero below + * + * If @force is true, it means the call is from + * qgroup_account_snapshot(), which only requires radix tree + * tracking. + * We should not force reloc root creation here, as the root + * may have already been modified, and in that case + * root->commit_root has already been dropped. + * + * Using that commit root will cause the reloc root to refer + * to a deleted extent, causing extent tree corruption. */ - ret = btrfs_init_reloc_root(trans, root); + if (!force) + ret = btrfs_init_reloc_root(trans, root); smp_mb__before_atomic(); clear_bit(BTRFS_ROOT_IN_TRANS_SETUP, &root->state); } diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 875e4ddc68eaea..c87f6a7e8d612a 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -7307,6 +7307,22 @@ static int btrfs_log_all_parents(struct btrfs_trans_handle *trans, ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); if (ret < 0) goto out; + /* + * There can't be an inode ref key with offset 0 because inode numbers + * start at BTRFS_FIRST_FREE_OBJECTID. + */ + if (WARN_ON_ONCE(ret == 0)) { + btrfs_err(trans->fs_info, + "found inode ref key with offset 0 for root %llu inode %llu", + btrfs_root_id(root), ino); + ret = BTRFS_LOG_FORCE_COMMIT; + goto out; + } + /* + * Set to 0 so that in case we don't do any work below, we won't return + * 1 and trigger an unnecessary transaction commit. + */ + ret = 0; while (true) { struct extent_buffer *leaf = path->nodes[0]; diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 6eab4cc73ce44c..b90cbd1e3ebe3f 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -3070,7 +3070,11 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path error_sysfs: btrfs_sysfs_remove_device(device); mutex_lock(&fs_info->fs_devices->device_list_mutex); + if (seeding_dev) + btrfs_assign_next_active_device(device, seed_devices->latest_dev); mutex_lock(&fs_info->chunk_mutex); + if (!list_empty(&device->post_commit_list)) + list_del_init(&device->post_commit_list); list_del_rcu(&device->dev_list); list_del(&device->dev_alloc_list); fs_info->fs_devices->num_devices--; diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index a016cb471beb47..7f0dde6398d4d3 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -2626,16 +2626,13 @@ static int do_zone_finish(struct btrfs_block_group *block_group, bool fully_writ down_read(&dev_replace->rwsem); map = block_group->physical_map; for (i = 0; i < map->num_stripes; i++) { - ret = call_zone_finish(block_group, &map->stripes[i]); - if (ret) { - up_read(&dev_replace->rwsem); - return ret; - } + if (ret) + break; } up_read(&dev_replace->rwsem); - if (!fully_written) + if (!ret && !fully_written) btrfs_dec_block_group_ro(block_group); spin_lock(&fs_info->zone_active_bgs_lock); @@ -2648,7 +2645,7 @@ static int do_zone_finish(struct btrfs_block_group *block_group, bool fully_writ clear_and_wake_up_bit(BTRFS_FS_NEED_ZONE_FINISH, &fs_info->flags); - return 0; + return ret; } int btrfs_zone_finish(struct btrfs_block_group *block_group) diff --git a/fs/btrfs/zstd.c b/fs/btrfs/zstd.c index 86919293fd546b..58d9ff76fe07bb 100644 --- a/fs/btrfs/zstd.c +++ b/fs/btrfs/zstd.c @@ -307,8 +307,17 @@ again: DEFINE_WAIT(wait); prepare_to_wait(&zwsm->wait, &wait, TASK_UNINTERRUPTIBLE); - schedule(); + /* + * Re-check after being queued: zstd_put_workspace() only wakes + * a queue that already has a sleeper, so a workspace returned + * since the failed allocation woke nobody. + */ + ws = zstd_find_workspace(fs_info, level); + if (!ws) + schedule(); finish_wait(&zwsm->wait, &wait); + if (ws) + return ws; goto again; } diff --git a/fs/cachefiles/xattr.c b/fs/cachefiles/xattr.c index f8ae78b3f7b6d3..c70bf67e52b01a 100644 --- a/fs/cachefiles/xattr.c +++ b/fs/cachefiles/xattr.c @@ -13,6 +13,7 @@ #include #include #include +#include #include "internal.h" #define CACHEFILES_COOKIE_TYPE_DATA 1 @@ -50,7 +51,7 @@ int cachefiles_set_object_xattr(struct cachefiles_object *object) _enter("%x,#%d", object->debug_id, len); - buf = kmalloc(sizeof(struct cachefiles_xattr) + len, GFP_KERNEL); + buf = kmalloc(sizeof(struct cachefiles_xattr) + max(len, sizeof(__be64)), GFP_KERNEL); if (!buf) return -ENOMEM; @@ -60,6 +61,7 @@ int cachefiles_set_object_xattr(struct cachefiles_object *object) buf->content = object->content_info; if (test_bit(FSCACHE_COOKIE_LOCAL_WRITE, &object->cookie->flags)) buf->content = CACHEFILES_CONTENT_DIRTY; + put_unaligned_be64(0, (__be64 *)buf->data); if (len > 0) memcpy(buf->data, fscache_get_aux(object->cookie), len); @@ -77,8 +79,7 @@ int cachefiles_set_object_xattr(struct cachefiles_object *object) trace_cachefiles_vfs_error(object, file_inode(file), ret, cachefiles_trace_setxattr_error); trace_cachefiles_coherency(object, file_inode(file)->i_ino, - be64_to_cpup((__be64 *)buf->data), - buf->content, + buf->data, buf->content, cachefiles_coherency_set_fail); if (ret != -ENOMEM) cachefiles_io_error_obj( @@ -86,8 +87,7 @@ int cachefiles_set_object_xattr(struct cachefiles_object *object) "Failed to set xattr with error %d", ret); } else { trace_cachefiles_coherency(object, file_inode(file)->i_ino, - be64_to_cpup((__be64 *)buf->data), - buf->content, + buf->data, buf->content, cachefiles_coherency_set_ok); } @@ -110,9 +110,10 @@ int cachefiles_check_auxdata(struct cachefiles_object *object, struct file *file int ret = -ESTALE; tlen = sizeof(struct cachefiles_xattr) + len; - buf = kmalloc(tlen, GFP_KERNEL); + buf = kmalloc(sizeof(struct cachefiles_xattr) + max(len, sizeof(__be64)), GFP_KERNEL); if (!buf) return -ENOMEM; + put_unaligned_be64(0, (__be64 *)buf->data); xlen = cachefiles_inject_read_error(); if (xlen == 0) @@ -148,8 +149,7 @@ int cachefiles_check_auxdata(struct cachefiles_object *object, struct file *file out: trace_cachefiles_coherency(object, file_inode(file)->i_ino, - be64_to_cpup((__be64 *)buf->data), - buf->content, why); + buf->data, buf->content, why); kfree(buf); return ret; } diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c index 3c88f13f1ca2e9..eda80c2a2d3888 100644 --- a/fs/configfs/dir.c +++ b/fs/configfs/dir.c @@ -416,6 +416,15 @@ static void configfs_remove_dir(struct dentry *d) if (d_really_is_positive(d)) { if (unlikely(simple_rmdir(d_inode(parent), d))) pr_warn("remove_dir (%pd): attributes remain", d); + else + /* + * configfs_get_config_item() takes a hashed dentry as + * proof that ->s_element is still alive. Our caller + * is about to drop the last reference to the item and + * the VFS will not unhash until after we return, so + * unhash it here. + */ + d_drop(d); } pr_debug(" o %pd removing done (%d)\n", d, d_count(d)); diff --git a/fs/configfs/symlink.c b/fs/configfs/symlink.c index 31eb28b2730913..3b31c714400f99 100644 --- a/fs/configfs/symlink.c +++ b/fs/configfs/symlink.c @@ -76,9 +76,9 @@ static int configfs_get_target_path(struct config_item *item, static int create_link(struct config_item *parent_item, struct config_item *item, + struct configfs_dirent *target_sd, struct dentry *dentry) { - struct configfs_dirent *target_sd = item->ci_dentry->d_fsdata; char *body; int ret; @@ -115,6 +115,7 @@ static int create_link(struct config_item *parent_item, static int get_target(const char *symname, struct config_item **target, + struct configfs_dirent **target_sd, struct super_block *sb) { struct path path __free(path_put) = {}; @@ -125,7 +126,20 @@ static int get_target(const char *symname, struct config_item **target, return ret; if (path.dentry->d_sb != sb) return -EPERM; - *target = configfs_get_config_item(path.dentry); + /* + * A hashed dentry guarantees that neither the item nor the dirent + * have been released yet, as removals unhash before dropping. + * Grab both references here. An item reference alone would not keep + * ->ci_dentry alive. + */ + spin_lock(&path.dentry->d_lock); + if (!d_unhashed(path.dentry)) { + struct configfs_dirent *sd = path.dentry->d_fsdata; + + *target = config_item_get(sd->s_element); + *target_sd = configfs_get(sd); + } + spin_unlock(&path.dentry->d_lock); if (!*target) return -ENOENT; return 0; @@ -139,6 +153,7 @@ int configfs_symlink(struct mnt_idmap *idmap, struct inode *dir, struct configfs_dirent *sd; struct config_item *parent_item; struct config_item *target_item = NULL; + struct configfs_dirent *target_sd = NULL; const struct config_item_type *type; sd = dentry->d_parent->d_fsdata; @@ -182,7 +197,7 @@ int configfs_symlink(struct mnt_idmap *idmap, struct inode *dir, * AV, a thoroughly annoyed bastard. */ inode_unlock(dir); - ret = get_target(symname, &target_item, dentry->d_sb); + ret = get_target(symname, &target_item, &target_sd, dentry->d_sb); inode_lock(dir); if (ret) goto out_put; @@ -196,13 +211,14 @@ int configfs_symlink(struct mnt_idmap *idmap, struct inode *dir, ret = type->ct_item_ops->allow_link(parent_item, target_item); if (!ret) { mutex_lock(&configfs_symlink_mutex); - ret = create_link(parent_item, target_item, dentry); + ret = create_link(parent_item, target_item, target_sd, dentry); mutex_unlock(&configfs_symlink_mutex); if (ret && type->ct_item_ops->drop_link) type->ct_item_ops->drop_link(parent_item, target_item); } + configfs_put(target_sd); config_item_put(target_item); out_put: diff --git a/fs/erofs/data.c b/fs/erofs/data.c index 9aa48c8d67d128..b6cdffd0d8936e 100644 --- a/fs/erofs/data.c +++ b/fs/erofs/data.c @@ -61,7 +61,7 @@ void *erofs_bread(struct erofs_buf *buf, erofs_off_t offset, bool need_kmap) return NULL; if (!buf->base) buf->base = kmap_local_page(buf->page); - return buf->base + (offset & ~PAGE_MASK); + return buf->base + ((buf->off + offset) & ~PAGE_MASK); } int erofs_init_metabuf(struct erofs_buf *buf, struct super_block *sb, diff --git a/fs/erofs/decompressor.c b/fs/erofs/decompressor.c index 27caf4bebddc37..d387b27c4ee215 100644 --- a/fs/erofs/decompressor.c +++ b/fs/erofs/decompressor.c @@ -7,8 +7,6 @@ #include "compress.h" #include -#define LZ4_MAX_DISTANCE_PAGES (DIV_ROUND_UP(LZ4_DISTANCE_MAX, PAGE_SIZE) + 1) - static int z_erofs_load_lz4_config(struct super_block *sb, struct erofs_super_block *dsb, void *data, int size) { @@ -21,8 +19,6 @@ static int z_erofs_load_lz4_config(struct super_block *sb, erofs_err(sb, "invalid lz4 cfgs, size=%u", size); return -EINVAL; } - distance = le16_to_cpu(lz4->max_distance); - sbi->lz4.max_pclusterblks = le16_to_cpu(lz4->max_pclusterblks); if (!sbi->lz4.max_pclusterblks) { sbi->lz4.max_pclusterblks = 1; /* reserved case */ @@ -39,45 +35,25 @@ static int z_erofs_load_lz4_config(struct super_block *sb, sbi->lz4.max_pclusterblks = 1; sbi->available_compr_algs = 1 << Z_EROFS_COMPRESSION_LZ4; } - - sbi->lz4.max_distance_pages = distance ? - DIV_ROUND_UP(distance, PAGE_SIZE) + 1 : - LZ4_MAX_DISTANCE_PAGES; return z_erofs_gbuf_growsize(sbi->lz4.max_pclusterblks); } /* - * Fill all gaps with bounce pages if it's a sparse page list. Also check if - * all physical pages are consecutive, which can be seen for moderate CR. + * Fill all gaps with bounce pages if it's a sparse page list (for example some + * folios are already uptodate and thus can be mapped into userspace). Also + * check if pages are physically consecutive, which can be seen for moderate CR. */ -static int z_erofs_lz4_prepare_dstpages(struct z_erofs_decompress_req *rq, - struct page **pagepool) +static int z_erofs_oneshot_prepare_dstpages(struct z_erofs_decompress_req *rq, + struct page **pagepool) { - struct page *availables[LZ4_MAX_DISTANCE_PAGES] = { NULL }; - unsigned long bounced[DIV_ROUND_UP(LZ4_MAX_DISTANCE_PAGES, - BITS_PER_LONG)] = { 0 }; - unsigned int lz4_max_distance_pages = - EROFS_SB(rq->sb)->lz4.max_distance_pages; void *kaddr = NULL; - unsigned int i, j, top; + unsigned int i; - top = 0; - for (i = j = 0; i < rq->outpages; ++i, ++j) { - struct page *const page = rq->out[i]; - struct page *victim; - - if (j >= lz4_max_distance_pages) - j = 0; - - /* 'valid' bounced can only be tested after a complete round */ - if (!rq->fillgaps && test_bit(j, bounced)) { - DBG_BUGON(i < lz4_max_distance_pages); - DBG_BUGON(top >= lz4_max_distance_pages); - availables[top++] = rq->out[i - lz4_max_distance_pages]; - } + for (i = 0; i < rq->outpages; ++i) { + struct page *page, *victim; + page = rq->out[i]; if (page) { - __clear_bit(j, bounced); if (!PageHighMem(page)) { if (!i) { kaddr = page_address(page); @@ -89,21 +65,14 @@ static int z_erofs_lz4_prepare_dstpages(struct z_erofs_decompress_req *rq, continue; } } - kaddr = NULL; - continue; - } - kaddr = NULL; - __set_bit(j, bounced); - - if (top) { - victim = availables[--top]; } else { victim = __erofs_allocpage(pagepool, rq->gfp, true); if (!victim) return -ENOMEM; set_page_private(victim, Z_EROFS_SHORTLIVED_PAGE); + rq->out[i] = victim; } - rq->out[i] = victim; + kaddr = NULL; } return kaddr ? 1 : 0; } @@ -266,7 +235,7 @@ static const char *z_erofs_lz4_decompress(struct z_erofs_decompress_req *rq, dst_maptype = 0; } else { /* general decoding path which can be used for all cases */ - ret = z_erofs_lz4_prepare_dstpages(rq, pagepool); + ret = z_erofs_oneshot_prepare_dstpages(rq, pagepool); if (ret < 0) return ERR_PTR(ret); if (ret > 0) { diff --git a/fs/erofs/decompressor_lzma.c b/fs/erofs/decompressor_lzma.c index 6b0cdb446c6ad2..9d15f94cbee172 100644 --- a/fs/erofs/decompressor_lzma.c +++ b/fs/erofs/decompressor_lzma.c @@ -5,6 +5,7 @@ struct z_erofs_lzma { struct z_erofs_lzma *next; struct xz_dec_microlzma *state; + unsigned int dict_size; u8 bounce[PAGE_SIZE]; }; @@ -128,11 +129,19 @@ again: err = 0; /* 2. walk each isolated stream and grow max dict_size if needed */ for (strm = head; strm; strm = strm->next) { + struct xz_dec_microlzma *state; + + if (strm->dict_size >= dict_size) + continue; + state = xz_dec_microlzma_alloc(XZ_PREALLOC, dict_size); + if (!state) { + err = -ENOMEM; + break; + } if (strm->state) xz_dec_microlzma_end(strm->state); - strm->state = xz_dec_microlzma_alloc(XZ_PREALLOC, dict_size); - if (!strm->state) - err = -ENOMEM; + strm->state = state; + strm->dict_size = dict_size; } /* 3. push back all to the global list and update max dict_size */ @@ -142,7 +151,8 @@ again: spin_unlock(&z_erofs_lzma_lock); wake_up_all(&z_erofs_lzma_wq); - z_erofs_lzma_max_dictsize = dict_size; + if (!err) + z_erofs_lzma_max_dictsize = dict_size; mutex_unlock(&lzma_resize_mutex); return err; } diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h index bee2f50c8488fa..be98c9222bf79d 100644 --- a/fs/erofs/internal.h +++ b/fs/erofs/internal.h @@ -71,12 +71,8 @@ struct erofs_dev_context { bool flatdev; }; -/* all filesystem-wide lz4 configurations */ struct erofs_sb_lz4_info { - /* # of pages needed for EROFS lz4 rolling decompression */ - u16 max_distance_pages; - /* maximum possible blocks for pclusters in the filesystem */ - u16 max_pclusterblks; + u16 max_pclusterblks; /* maximum physical blocks for LZ4 pclusters */ }; struct erofs_xattr_prefix_item { diff --git a/fs/erofs/sysfs.c b/fs/erofs/sysfs.c index 6734483a440fbb..dfcec9376cd54d 100644 --- a/fs/erofs/sysfs.c +++ b/fs/erofs/sysfs.c @@ -95,6 +95,7 @@ EROFS_ATTR_FEATURE(sb_chksum); EROFS_ATTR_FEATURE(ztailpacking); EROFS_ATTR_FEATURE(fragments); EROFS_ATTR_FEATURE(dedupe); +EROFS_ATTR_FEATURE(xattr_prefixes); EROFS_ATTR_FEATURE(48bit); EROFS_ATTR_FEATURE(metabox); @@ -108,6 +109,7 @@ static struct attribute *erofs_feat_attrs[] = { ATTR_LIST(ztailpacking), ATTR_LIST(fragments), ATTR_LIST(dedupe), + ATTR_LIST(xattr_prefixes), ATTR_LIST(48bit), ATTR_LIST(metabox), NULL, diff --git a/fs/erofs/xattr.c b/fs/erofs/xattr.c index df7ea019526d72..57cfb75207824c 100644 --- a/fs/erofs/xattr.c +++ b/fs/erofs/xattr.c @@ -620,8 +620,8 @@ int erofs_xattr_fill_inode_fingerprint(struct erofs_inode_fingerprint *fp, { struct erofs_sb_info *sbi = EROFS_SB(inode->i_sb); struct erofs_xattr_prefix_item *prefix; + int domainlen, valuelen, base_index; const char *infix; - int valuelen, base_index; if (!test_opt(&sbi->opt, INODE_SHARE)) return -EOPNOTSUPP; @@ -633,17 +633,18 @@ int erofs_xattr_fill_inode_fingerprint(struct erofs_inode_fingerprint *fp, valuelen = erofs_getxattr(inode, base_index, infix, NULL, 0); if (valuelen <= 0 || valuelen > (1 << sbi->blkszbits)) return -EFSCORRUPTED; - fp->size = valuelen + (domain_id ? strlen(domain_id) : 0); + domainlen = strlen(domain_id); + fp->size = domainlen + 1 + valuelen; fp->opaque = kmalloc(fp->size, GFP_KERNEL); if (!fp->opaque) return -ENOMEM; + memcpy(fp->opaque, domain_id, domainlen + 1); if (valuelen != erofs_getxattr(inode, base_index, infix, - fp->opaque, valuelen)) { + fp->opaque + domainlen + 1, valuelen)) { kfree(fp->opaque); fp->opaque = NULL; return -EFSCORRUPTED; } - memcpy(fp->opaque + valuelen, domain_id, fp->size - valuelen); return 0; } #endif diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c index 0e9cac8ee12d35..f0759211b72349 100644 --- a/fs/erofs/zdata.c +++ b/fs/erofs/zdata.c @@ -1264,7 +1264,7 @@ static int z_erofs_decompress_pcluster(struct z_erofs_backend *be, bool eio) const struct z_erofs_decompressor *alg = z_erofs_decomp[pcl->algorithmformat]; bool try_free = true; - int i, j, jtop, err2, err = eio ? -EIO : 0; + int i, err2, err = eio ? -EIO : 0; struct page *page; bool overlapped; const char *reason; @@ -1353,7 +1353,6 @@ static int z_erofs_decompress_pcluster(struct z_erofs_backend *be, bool eio) be->compressed_pages >= be->onstack_pages + Z_EROFS_ONSTACK_PAGES) kvfree(be->compressed_pages); - jtop = 0; z_erofs_fill_other_copies(be, err); for (i = 0; i < be->nr_pages; ++i) { page = be->decompressed_pages[i]; @@ -1361,22 +1360,11 @@ static int z_erofs_decompress_pcluster(struct z_erofs_backend *be, bool eio) continue; DBG_BUGON(z_erofs_page_is_invalidated(page)); - if (!z_erofs_is_shortlived_page(page)) { + if (!z_erofs_is_shortlived_page(page)) erofs_onlinefolio_end(page_folio(page), err, true); - continue; - } - if (pcl->algorithmformat != Z_EROFS_COMPRESSION_LZ4) { + else erofs_pagepool_add(be->pagepool, page); - continue; - } - for (j = 0; j < jtop && be->decompressed_pages[j] != page; ++j) - ; - if (j >= jtop) /* this bounce page is newly detected */ - be->decompressed_pages[jtop++] = page; } - while (jtop) - erofs_pagepool_add(be->pagepool, - be->decompressed_pages[--jtop]); if (be->decompressed_pages != be->onstack_pages) kvfree(be->decompressed_pages); diff --git a/fs/exec.c b/fs/exec.c index d01523d0d8b47f..7ae972f3c88697 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1149,6 +1149,20 @@ int begin_new_exec(struct linux_binprm * bprm) if (retval) goto out; + /* + * We have to apply CLOEXEC before we change whether the process is + * dumpable (in setup_new_exec) to avoid a race with a process in userspace + * trying to access the should-be-closed file descriptors of a process + * undergoing exec(2). + * + * This can block on filesystem ->flush() handlers, including waiting + * for FUSE daemons, so do it before exec_mmap takes the + * exec_update_lock. + * This must happen after the point of no return, and after unsharing + * the FD table. + */ + do_close_on_exec(me->files); + /* * Must be called _before_ exec_mmap() as bprm->mm is * not visible until then. Doing it here also ensures @@ -1199,14 +1213,6 @@ int begin_new_exec(struct linux_binprm * bprm) clear_syscall_work_syscall_user_dispatch(me); - /* - * We have to apply CLOEXEC before we change whether the process is - * dumpable (in setup_new_exec) to avoid a race with a process in userspace - * trying to access the should-be-closed file descriptors of a process - * undergoing exec(2). - */ - do_close_on_exec(me->files); - if (bprm->secureexec) { /* Make sure parent cannot signal privileged process. */ me->pdeath_signal = 0; diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index bc2246abd421b4..b3c763a98cb8d4 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -4271,7 +4271,7 @@ int f2fs_gc(struct f2fs_sb_info *sbi, struct f2fs_gc_control *gc_control); void f2fs_build_gc_manager(struct f2fs_sb_info *sbi); int f2fs_gc_range(struct f2fs_sb_info *sbi, unsigned int start_seg, unsigned int end_seg, - bool dry_run, unsigned int dry_run_sections); + bool dry_run, unsigned int dry_run_sections, bool lock); int f2fs_resize_fs(struct file *filp, __u64 block_count); int __init f2fs_create_garbage_collection_cache(void); void f2fs_destroy_garbage_collection_cache(void); diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index c771adedff39c9..57ef3876d7afd5 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -2150,8 +2150,9 @@ void f2fs_build_gc_manager(struct f2fs_sb_info *sbi) int f2fs_gc_range(struct f2fs_sb_info *sbi, unsigned int start_seg, unsigned int end_seg, - bool dry_run, unsigned int dry_run_sections) + bool dry_run, unsigned int dry_run_sections, bool lock) { + struct f2fs_lock_context lc; unsigned int segno; unsigned int gc_secs = dry_run_sections; @@ -2164,28 +2165,46 @@ int f2fs_gc_range(struct f2fs_sb_info *sbi, .ilist = LIST_HEAD_INIT(gc_list.ilist), .iroot = RADIX_TREE_INIT(gc_list.iroot, GFP_NOFS), }; + int err = 0; + + if (lock) + f2fs_down_write_trace(&sbi->gc_lock, &lc); /* * avoid migrating empty section, as it can be allocated by * log in parallel. */ if (!get_valid_blocks(sbi, segno, true)) - continue; + goto next; if (is_cursec(sbi, GET_SEC_FROM_SEG(sbi, segno))) - continue; + goto next; do_garbage_collect(sbi, segno, &gc_list, FG_GC, true, false); put_gc_inode(&gc_list); - if (!dry_run && get_valid_blocks(sbi, segno, true)) - return -EAGAIN; + /* reset all pinned status during fggc */ + f2fs_unpin_all_sections(sbi, true); + + if (!dry_run && get_valid_blocks(sbi, segno, true)) { + err = -EAGAIN; + goto next; + } if (dry_run && dry_run_sections && - !get_valid_blocks(sbi, segno, true) && --gc_secs == 0) - break; + !get_valid_blocks(sbi, segno, true)) { + --gc_secs; + goto next; + } if (fatal_signal_pending(current)) - return -ERESTARTSYS; + err = -ERESTARTSYS; +next: + if (lock) + f2fs_up_write_trace(&sbi->gc_lock, &lc); + if (err) + return err; + if (dry_run && dry_run_sections && !gc_secs) + return 0; } return 0; @@ -2194,8 +2213,9 @@ int f2fs_gc_range(struct f2fs_sb_info *sbi, static int free_segment_range(struct f2fs_sb_info *sbi, unsigned int secs, bool dry_run) { - unsigned int next_inuse, start, end; + unsigned int secno, next_inuse, start, end, end_secno; struct cp_control cpc = { CP_RESIZE, 0, 0, 0 }; + unsigned int freed_secs = 0; int gc_mode, gc_type; int err = 0; int type; @@ -2204,6 +2224,7 @@ static int free_segment_range(struct f2fs_sb_info *sbi, MAIN_SECS(sbi) -= secs; start = MAIN_SECS(sbi) * SEGS_PER_SEC(sbi); end = MAIN_SEGS(sbi) - 1; + end_secno = GET_SEC_FROM_SEG(sbi, end); mutex_lock(&DIRTY_I(sbi)->seglist_lock); for (gc_mode = 0; gc_mode < MAX_GC_POLICY; gc_mode++) @@ -2215,6 +2236,14 @@ static int free_segment_range(struct f2fs_sb_info *sbi, sbi->next_victim_seg[gc_type] = NULL_SEGNO; mutex_unlock(&DIRTY_I(sbi)->seglist_lock); + spin_lock(&FREE_I(sbi)->segmap_lock); + for (secno = MAIN_SECS(sbi); secno <= end_secno; secno++) { + if (!test_bit(secno, FREE_I(sbi)->free_secmap)) + freed_secs++; + } + FREE_I(sbi)->free_sections -= freed_secs; + spin_unlock(&FREE_I(sbi)->segmap_lock); + /* Move out cursegs from the target range */ for (type = CURSEG_HOT_DATA; type < NR_CURSEG_TYPE; type++) { err = f2fs_allocate_segment_for_resize(sbi, type, start, end); @@ -2223,7 +2252,7 @@ static int free_segment_range(struct f2fs_sb_info *sbi, } /* do GC to move out valid blocks in the range */ - err = f2fs_gc_range(sbi, start, end, dry_run, 0); + err = f2fs_gc_range(sbi, start, end, dry_run, 0, false); if (err || dry_run) goto out; @@ -2239,6 +2268,9 @@ static int free_segment_range(struct f2fs_sb_info *sbi, f2fs_bug_on(sbi, 1); } out: + spin_lock(&FREE_I(sbi)->segmap_lock); + FREE_I(sbi)->free_sections += freed_secs; + spin_unlock(&FREE_I(sbi)->segmap_lock); MAIN_SECS(sbi) += secs; return err; } diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index 8830e1892b4353..011f8172e92346 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -3357,10 +3357,8 @@ retry: f2fs_unlock_op(sbi, &lc); if (f2fs_sb_has_blkzoned(sbi) && err == -EAGAIN && gc_required) { - f2fs_down_write_trace(&sbi->gc_lock, &lc); err = f2fs_gc_range(sbi, 0, sbi->first_seq_zone_segno - 1, - true, ZONED_PIN_SEC_REQUIRED_COUNT); - f2fs_up_write_trace(&sbi->gc_lock, &lc); + true, ZONED_PIN_SEC_REQUIRED_COUNT, true); if (err) return err; err = f2fs_sync_fs(sbi->sb, 1); diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c index 7fdfa4f27e3492..424df70a5c30f1 100644 --- a/fs/netfs/buffered_read.c +++ b/fs/netfs/buffered_read.c @@ -54,6 +54,42 @@ static void netfs_rreq_expand(struct netfs_io_request *rreq, } } +/* + * Drop the folio refs acquired from the readahead API. + */ +static void netfs_bulk_drop_ra_refs(struct netfs_io_request *rreq) +{ + struct folio_batch fbatch; + struct folio *folio; + pgoff_t nr_pages = DIV_ROUND_UP(rreq->len, PAGE_SIZE); + pgoff_t first = rreq->start / PAGE_SIZE; + XA_STATE(xas, &rreq->mapping->i_pages, first); + + folio_batch_init(&fbatch); + + rcu_read_lock(); + + xas_for_each(&xas, folio, first + nr_pages - 1) { + if (xas_retry(&xas, folio)) + continue; + + if (!folio_batch_add(&fbatch, folio)) + folio_batch_release(&fbatch); + } + + rcu_read_unlock(); + folio_batch_release(&fbatch); + trace_netfs_rreq(rreq, netfs_rreq_trace_ra_put_ref); + clear_bit_unlock(NETFS_RREQ_NEED_PUT_RA_REFS, &rreq->flags); + wake_up(&rreq->waitq); +} + +static void netfs_maybe_bulk_drop_ra_refs(struct netfs_io_request *rreq) +{ + if (test_bit(NETFS_RREQ_NEED_PUT_RA_REFS, &rreq->flags)) + netfs_bulk_drop_ra_refs(rreq); +} + /* * Begin an operation, and fetch the stored zero point value from the cookie if * available. @@ -74,12 +110,8 @@ static int netfs_begin_cache_read(struct netfs_io_request *rreq, struct netfs_in * * Returns the limited size if successful and -ENOMEM if insufficient memory * available. - * - * [!] NOTE: This must be run in the same thread as ->issue_read() was called - * in as we access the readahead_control struct. */ -static ssize_t netfs_prepare_read_iterator(struct netfs_io_subrequest *subreq, - struct readahead_control *ractl) +static ssize_t netfs_prepare_read_iterator(struct netfs_io_subrequest *subreq) { struct netfs_io_request *rreq = subreq->rreq; size_t rsize = subreq->len; @@ -87,30 +119,6 @@ static ssize_t netfs_prepare_read_iterator(struct netfs_io_subrequest *subreq, if (subreq->source == NETFS_DOWNLOAD_FROM_SERVER) rsize = umin(rsize, rreq->io_streams[0].sreq_max_len); - if (ractl) { - /* If we don't have sufficient folios in the rolling buffer, - * extract a folioq's worth from the readahead region at a time - * into the buffer. Note that this acquires a ref on each page - * that we will need to release later - but we don't want to do - * that until after we've started the I/O. - */ - struct folio_batch put_batch; - - folio_batch_init(&put_batch); - while (rreq->submitted < subreq->start + rsize) { - ssize_t added; - - added = rolling_buffer_load_from_ra(&rreq->buffer, ractl, - &put_batch); - if (added < 0) { - folio_batch_release(&put_batch); - return added; - } - rreq->submitted += added; - } - folio_batch_release(&put_batch); - } - subreq->len = rsize; if (unlikely(rreq->io_streams[0].sreq_max_segs)) { size_t limit = netfs_limit_iter(&rreq->buffer.iter, 0, rsize, @@ -203,17 +211,68 @@ static void netfs_issue_read(struct netfs_io_request *rreq, } } +/* + * Mark folios that we want to copy to the cache. For filesystems that use + * netfslib fully, we set folio->private to NETFS_FOLIO_COPY_TO_CACHE; + * otherwise we set the deprecated PG_private_2. + */ +static void netfs_mark_copy_to_cache(struct netfs_io_request *rreq, + struct folio_queue **fq, + unsigned int *offset, + int *slot, + size_t len, + bool copy) +{ + while (len > 0) { + struct folio *folio; + size_t fsize, overlap; + + if (!*fq) + break; + if (*slot >= folioq_count(*fq)) { + *fq = (*fq)->next; + *slot = 0; + *offset = 0; + continue; + } + + /* Determine how much the subreq overlaps the folio, if at all. */ + fsize = folioq_folio_size(*fq, *slot); + overlap = min(len, fsize - *offset); + + if (overlap > 0 && copy) { + folio = folioq_folio(*fq, *slot); + if (unlikely(test_bit(NETFS_RREQ_USE_PGPRIV2, &rreq->flags))) { + if (!folio_test_private_2(folio)) + folio_start_private_2(folio); + } else { + if (!folio_get_private(folio)) + folio_attach_private(folio, NETFS_FOLIO_COPY_TO_CACHE); + } + trace_netfs_folio(folio, netfs_folio_trace_mark_copy); + } + + len -= overlap; + *offset += overlap; + if (*offset >= fsize) { + *slot += 1; + *offset = 0; + } + } +} + /* * Perform a read to the pagecache from a series of sources of different types, * slicing up the region to be read according to available cache blocks and * network rsize. */ -static void netfs_read_to_pagecache(struct netfs_io_request *rreq, - struct readahead_control *ractl) +static void netfs_read_to_pagecache(struct netfs_io_request *rreq) { + struct folio_queue *fq = rreq->buffer.tail; unsigned long long start = rreq->start; + unsigned int offset = 0; ssize_t size = rreq->len; - int ret = 0; + int ret = 0, slot = 0; do { struct netfs_io_subrequest *subreq; @@ -288,7 +347,7 @@ static void netfs_read_to_pagecache(struct netfs_io_request *rreq, break; issue: - slice = netfs_prepare_read_iterator(subreq, ractl); + slice = netfs_prepare_read_iterator(subreq); if (slice < 0) { ret = slice; netfs_cancel_read(subreq, ret); @@ -301,7 +360,15 @@ static void netfs_read_to_pagecache(struct netfs_io_request *rreq, set_bit(NETFS_RREQ_ALL_QUEUED, &rreq->flags); } + if (fq) { + /* See if the cache indicated this should be cached. */ + bool copy = test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags); + + netfs_mark_copy_to_cache(rreq, &fq, &slot, &offset, slice, copy); + } + netfs_issue_read(rreq, subreq); + netfs_maybe_bulk_drop_ra_refs(rreq); if (test_bit(NETFS_RREQ_PAUSE, &rreq->flags)) netfs_wait_for_paused_read(rreq); @@ -339,7 +406,8 @@ void netfs_readahead(struct readahead_control *ractl) { struct netfs_io_request *rreq; struct netfs_inode *ictx = netfs_inode(ractl->mapping->host); - unsigned long long start = readahead_pos(ractl); + ssize_t added; + uoff_t start = readahead_pos(ractl); size_t size = readahead_length(ractl); int ret; @@ -360,11 +428,24 @@ void netfs_readahead(struct readahead_control *ractl) netfs_rreq_expand(rreq, ractl); - rreq->submitted = rreq->start; - if (rolling_buffer_init(&rreq->buffer, rreq->debug_id, ITER_DEST, rreq->gfp) < 0) + /* Load the folios to be read into a bvecq chain. Note that this + * acquires a ref on each folio that we will need to release later - + * but we don't want to do that until after we've started the I/O. + */ + added = rolling_buffer_bulk_load_from_ra(&rreq->buffer, ractl, + rreq->debug_id, rreq->gfp); + if (added < 0) { + ret = added; goto cleanup_free; - netfs_read_to_pagecache(rreq, ractl); + } + __set_bit(NETFS_RREQ_NEED_PUT_RA_REFS, &rreq->flags); + + rreq->submitted = rreq->start + added; + rreq->cleaned_to = rreq->start; + netfs_read_set_unlock_at(rreq); + netfs_read_to_pagecache(rreq); + netfs_maybe_bulk_drop_ra_refs(rreq); return netfs_put_request(rreq, netfs_rreq_trace_put_return); cleanup_free: @@ -387,6 +468,7 @@ static int netfs_create_singular_buffer(struct netfs_io_request *rreq, struct fo if (added < 0) return added; rreq->submitted = rreq->start + added; + rreq->progress_at = added; return 0; } @@ -457,7 +539,7 @@ static int netfs_read_gaps(struct file *file, struct folio *folio) iov_iter_bvec(&rreq->buffer.iter, ITER_DEST, bvec, i, rreq->len); rreq->submitted = rreq->start + flen; - netfs_read_to_pagecache(rreq, NULL); + netfs_read_to_pagecache(rreq); ret = netfs_wait_for_read(rreq); if (ret >= 0) { @@ -532,7 +614,7 @@ int netfs_read_folio(struct file *file, struct folio *folio) if (ret < 0) goto discard; - netfs_read_to_pagecache(rreq, NULL); + netfs_read_to_pagecache(rreq); ret = netfs_wait_for_read(rreq); netfs_put_request(rreq, netfs_rreq_trace_put_return); return ret < 0 ? ret : 0; @@ -689,7 +771,7 @@ retry: if (ret < 0) goto error_put; - netfs_read_to_pagecache(rreq, NULL); + netfs_read_to_pagecache(rreq); ret = netfs_wait_for_read(rreq); netfs_put_request(rreq, netfs_rreq_trace_put_return); if (ret < 0) @@ -754,7 +836,7 @@ int netfs_prefetch_for_write(struct file *file, struct folio *folio, if (ret < 0) goto error_put; - netfs_read_to_pagecache(rreq, NULL); + netfs_read_to_pagecache(rreq); ret = netfs_wait_for_read(rreq); netfs_put_request(rreq, netfs_rreq_trace_put_return); return ret < 0 ? ret : 0; diff --git a/fs/netfs/direct_write.c b/fs/netfs/direct_write.c index c16fbad286a177..2361277416c730 100644 --- a/fs/netfs/direct_write.c +++ b/fs/netfs/direct_write.c @@ -21,7 +21,7 @@ static void netfs_unbuffered_write_done(struct netfs_io_request *wreq) /* Okay, declare that all I/O is complete. */ trace_netfs_rreq(wreq, netfs_rreq_trace_write_done); - if (!wreq->error) + if (wreq->transferred) netfs_update_i_size(ictx, &ictx->inode, wreq->start, wreq->transferred); if (wreq->origin == NETFS_DIO_WRITE && @@ -51,7 +51,7 @@ static void netfs_unbuffered_write_done(struct netfs_io_request *wreq) wreq->iocb->ki_pos += written; if (wreq->iocb->ki_complete) { trace_netfs_rreq(wreq, netfs_rreq_trace_ki_complete); - wreq->iocb->ki_complete(wreq->iocb, wreq->error ?: written); + wreq->iocb->ki_complete(wreq->iocb, written ?: wreq->error); } wreq->iocb = VFS_PTR_POISON; } @@ -95,7 +95,7 @@ static int netfs_unbuffered_write(struct netfs_io_request *wreq) { struct netfs_io_subrequest *subreq = NULL; struct netfs_io_stream *stream = &wreq->io_streams[0]; - int ret; + int ret = 0; _enter("%llx", wreq->len); @@ -110,6 +110,11 @@ static int netfs_unbuffered_write(struct netfs_io_request *wreq) if (!subreq) { netfs_prepare_write(wreq, stream, wreq->start + wreq->transferred); subreq = stream->construct; + if (!subreq) { + wreq->error = -ENOMEM; + ret = -ENOMEM; + break; + } stream->construct = NULL; } @@ -121,8 +126,14 @@ static int netfs_unbuffered_write(struct netfs_io_request *wreq) } iov_iter_truncate(&subreq->io_iter, wreq->len - wreq->transferred); - if (!iov_iter_count(&subreq->io_iter)) + if (!iov_iter_count(&subreq->io_iter)) { + pr_warn("netfs: Unexpected zero-length iterator R=%08x\n", + wreq->debug_id); + __set_bit(NETFS_SREQ_FAILED, &subreq->flags); + netfs_write_subrequest_terminated(subreq, -EIO); + wreq->error = -EIO; break; + } subreq->len = netfs_limit_iter(&subreq->io_iter, 0, stream->sreq_max_len, @@ -139,13 +150,11 @@ static int netfs_unbuffered_write(struct netfs_io_request *wreq) if (test_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags)) { retry = true; } else if (test_bit(NETFS_SREQ_FAILED, &subreq->flags)) { - ret = subreq->error; - wreq->error = ret; + wreq->error = subreq->error; netfs_see_subrequest(subreq, netfs_sreq_trace_see_failed); subreq = NULL; break; } - ret = 0; if (!retry) { netfs_unbuffered_write_collect(wreq, stream, subreq); @@ -288,11 +297,11 @@ ssize_t netfs_unbuffered_write_iter_locked(struct kiocb *iocb, struct iov_iter * ret = -EIOCBQUEUED; } else { ret = netfs_unbuffered_write(wreq); - if (ret < 0) { - _debug("begin = %zd", ret); - } else { + if (wreq->transferred) { iocb->ki_pos += wreq->transferred; - ret = wreq->transferred ?: wreq->error; + ret = wreq->transferred; + } else if (wreq->error) { + ret = wreq->error; } netfs_put_request(wreq, netfs_rreq_trace_put_complete); diff --git a/fs/netfs/internal.h b/fs/netfs/internal.h index 420ee7b26580f0..c79c8e69d60ca7 100644 --- a/fs/netfs/internal.h +++ b/fs/netfs/internal.h @@ -79,6 +79,7 @@ ssize_t netfs_wait_for_read(struct netfs_io_request *rreq); ssize_t netfs_wait_for_write(struct netfs_io_request *rreq); void netfs_wait_for_paused_read(struct netfs_io_request *rreq); void netfs_wait_for_paused_write(struct netfs_io_request *rreq); +void netfs_wait_for_put_ra_refs(struct netfs_io_request *rreq); /* * objects.c @@ -109,6 +110,8 @@ static inline void netfs_see_subrequest(struct netfs_io_subrequest *subreq, /* * read_collect.c */ +void netfs_cancel_copy_to_cache(struct netfs_io_request *rreq, struct folio *folio); +void netfs_read_set_unlock_at(struct netfs_io_request *rreq); bool netfs_read_collection(struct netfs_io_request *rreq); void netfs_read_collection_worker(struct work_struct *work); void netfs_cancel_read(struct netfs_io_subrequest *subreq, int error); diff --git a/fs/netfs/misc.c b/fs/netfs/misc.c index 5d554512ed23a2..f5c1c463f4ff7a 100644 --- a/fs/netfs/misc.c +++ b/fs/netfs/misc.c @@ -563,3 +563,22 @@ void netfs_wait_for_paused_write(struct netfs_io_request *rreq) { return netfs_wait_for_pause(rreq, netfs_write_collection); } + +/* + * Wait for the readahead-acquired refs to be put. + */ +void netfs_wait_for_put_ra_refs(struct netfs_io_request *rreq) +{ + DEFINE_WAIT(myself); + + for (;;) { + trace_netfs_rreq(rreq, netfs_rreq_trace_wait_put_ra_refs); + prepare_to_wait(&rreq->waitq, &myself, TASK_UNINTERRUPTIBLE); + if (!test_bit(NETFS_RREQ_NEED_PUT_RA_REFS, &rreq->flags)) + break; + schedule(); + } + + trace_netfs_rreq(rreq, netfs_rreq_trace_waited_put_ra_refs); + finish_wait(&rreq->waitq, &myself); +} diff --git a/fs/netfs/objects.c b/fs/netfs/objects.c index 01461a74642d64..7f6a3e912602ee 100644 --- a/fs/netfs/objects.c +++ b/fs/netfs/objects.c @@ -41,24 +41,32 @@ struct netfs_io_request *netfs_alloc_request(struct address_space *mapping, memset(rreq, 0, kmem_cache_size(cache)); INIT_WORK(&rreq->cleanup_work, netfs_free_request); - rreq->gfp = gfp; - rreq->start = start; - rreq->len = len; - rreq->origin = origin; - rreq->netfs_ops = ctx->ops; - rreq->mapping = mapping; - rreq->inode = inode; - rreq->i_size = i_size_read(inode); - rreq->debug_id = atomic_inc_return(&debug_ids); - rreq->wsize = INT_MAX; + rreq->gfp = gfp; + rreq->start = start; + rreq->collected_to = start; + rreq->cleaned_to = start; + rreq->len = len; + rreq->progress_at = 0; + rreq->origin = origin; + rreq->netfs_ops = ctx->ops; + rreq->mapping = mapping; + rreq->inode = inode; + rreq->i_size = i_size_read(inode); + rreq->debug_id = atomic_inc_return(&debug_ids); + rreq->wsize = INT_MAX; rreq->io_streams[0].sreq_max_len = ULONG_MAX; rreq->io_streams[0].sreq_max_segs = 0; spin_lock_init(&rreq->lock); - INIT_LIST_HEAD(&rreq->io_streams[0].subrequests); - INIT_LIST_HEAD(&rreq->io_streams[1].subrequests); init_waitqueue_head(&rreq->waitq); refcount_set(&rreq->ref, 2); + for (int s = 0; s < NR_IO_STREAMS; s++) { + struct netfs_io_stream *stream = &rreq->io_streams[s]; + + INIT_LIST_HEAD(&stream->subrequests); + stream->collected_to = rreq->start; + } + if (origin == NETFS_READAHEAD || origin == NETFS_READPAGE || origin == NETFS_READ_GAPS || diff --git a/fs/netfs/read_collect.c b/fs/netfs/read_collect.c index 23660a59012464..5cf22087d2439d 100644 --- a/fs/netfs/read_collect.c +++ b/fs/netfs/read_collect.c @@ -19,7 +19,6 @@ #define MADE_PROGRESS 0x04 /* Made progress cleaning up a stream or the folio set */ #define BUFFERED 0x08 /* The pagecache needs cleaning up */ #define NEED_RETRY 0x10 /* A front op requests retrying */ -#define COPY_TO_CACHE 0x40 /* Need to copy subrequest to cache */ #define ABANDON_SREQ 0x80 /* Need to abandon untransferred part of subrequest */ /* @@ -34,6 +33,30 @@ static void netfs_clear_unread(struct netfs_io_subrequest *subreq) __set_bit(NETFS_SREQ_HIT_EOF, &subreq->flags); } +/* + * Cancel the copy-to-cache mark on a folio. + */ +void netfs_cancel_copy_to_cache(struct netfs_io_request *rreq, struct folio *folio) +{ + if (!test_bit(NETFS_RREQ_USE_PGPRIV2, &rreq->flags)) { + if (folio_get_private(folio) == NETFS_FOLIO_COPY_TO_CACHE) { + folio_detach_private(folio); + trace_netfs_folio(folio, netfs_folio_trace_cancel_copy); + } else if (netfs_folio_group(folio) == NETFS_FOLIO_COPY_TO_CACHE) { + struct netfs_folio *finfo = netfs_folio_info(folio); + + finfo->netfs_group = NULL; + trace_netfs_folio(folio, netfs_folio_trace_cancel_copy); + } + } else { + // TODO: Use of PG_private_2 is deprecated. + if (folio_test_private_2(folio)) { + folio_end_private_2(folio); + trace_netfs_folio(folio, netfs_folio_trace_cancel_copy); + } + } +} + /* * Flush, mark and unlock a folio that's now completely read. If we want to * cache the folio, we set the group to NETFS_FOLIO_COPY_TO_CACHE, mark it @@ -48,37 +71,37 @@ static void netfs_unlock_read_folio(struct netfs_io_request *rreq, if (unlikely(folio_pos(folio) < rreq->abandon_to)) { trace_netfs_folio(folio, netfs_folio_trace_abandon); + netfs_cancel_copy_to_cache(rreq, folio); goto just_unlock; } flush_dcache_folio(folio); folio_mark_uptodate(folio); - if (!test_bit(NETFS_RREQ_USE_PGPRIV2, &rreq->flags)) { - finfo = netfs_folio_info(folio); - if (finfo) { - trace_netfs_folio(folio, netfs_folio_trace_filled_gaps); - if (finfo->netfs_group) - folio_change_private(folio, finfo->netfs_group); - else - folio_detach_private(folio); - kfree(finfo); - } + if (unlikely(test_bit(NETFS_RREQ_CANCEL_CACHING, &rreq->flags))) + netfs_cancel_copy_to_cache(rreq, folio); - if (test_bit(NETFS_RREQ_FOLIO_COPY_TO_CACHE, &rreq->flags)) { - if (!WARN_ON_ONCE(folio_get_private(folio) != NULL)) { - trace_netfs_folio(folio, netfs_folio_trace_copy_to_cache); - folio_attach_private(folio, NETFS_FOLIO_COPY_TO_CACHE); - folio_mark_dirty(folio); - } + if (!test_bit(NETFS_RREQ_USE_PGPRIV2, &rreq->flags)) { + if (netfs_folio_group(folio) == NETFS_FOLIO_COPY_TO_CACHE) { + trace_netfs_folio(folio, netfs_folio_trace_sched_copy); + folio_mark_dirty(folio); } else { + finfo = netfs_folio_info(folio); + if (finfo) { + trace_netfs_folio(folio, netfs_folio_trace_filled_gaps); + if (finfo->netfs_group) + folio_change_private(folio, finfo->netfs_group); + else + folio_detach_private(folio); + kfree(finfo); + } trace_netfs_folio(folio, netfs_folio_trace_read_done); } folioq_clear(folioq, slot); } else { // TODO: Use of PG_private_2 is deprecated. - if (test_bit(NETFS_RREQ_FOLIO_COPY_TO_CACHE, &rreq->flags)) + if (folio_test_private_2(folio)) netfs_pgpriv2_copy_to_cache(rreq, folio); } @@ -94,6 +117,35 @@ just_unlock: folioq_clear(folioq, slot); } +/* + * Determine how much to gather before unlocking more folios. + */ +void netfs_read_set_unlock_at(struct netfs_io_request *rreq) +{ + struct folio_queue *folioq = rreq->buffer.tail; + unsigned int slot = rreq->buffer.first_tail_slot; + size_t cleaned_to = rreq->cleaned_to - rreq->start; + size_t progress_at = cleaned_to; + size_t minimum = 256 * 1024; + + while (progress_at < rreq->len) { + if (slot >= folioq_count(folioq)) { + folioq = folioq->next; + if (!folioq) + break; + slot = 0; + } + + progress_at += folioq_folio_size(folioq, slot); + if (progress_at - cleaned_to >= minimum) + break; + slot++; + } + + WRITE_ONCE(rreq->progress_at, progress_at); + trace_netfs_read_progress_at(rreq); +} + /* * Unlock any folios we've finished with. */ @@ -112,30 +164,31 @@ static void netfs_read_unlock_folios(struct netfs_io_request *rreq, if (slot >= folioq_nr_slots(folioq)) { folioq = rolling_buffer_delete_spent(&rreq->buffer); if (!folioq) { - rreq->front_folio_order = 0; + WRITE_ONCE(rreq->progress_at, rreq->len); return; } slot = 0; } + /* We have to wait for readahead refs to have been released before we + * can unlock any folios as the ref-dropper walks i_pages and the only + * thing preventing these folios from being removed is the folio lock. + */ + if (test_bit(NETFS_RREQ_NEED_PUT_RA_REFS, &rreq->flags)) + netfs_wait_for_put_ra_refs(rreq); + for (;;) { struct folio *folio; unsigned long long fpos, fend; - unsigned int order; size_t fsize; - if (*notes & COPY_TO_CACHE) - set_bit(NETFS_RREQ_FOLIO_COPY_TO_CACHE, &rreq->flags); - folio = folioq_folio(folioq, slot); if (WARN_ONCE(!folio_test_locked(folio), "R=%08x: folio %lx is not locked\n", rreq->debug_id, folio->index)) trace_netfs_folio(folio, netfs_folio_trace_not_locked); - order = folioq_folio_order(folioq, slot); - rreq->front_folio_order = order; - fsize = PAGE_SIZE << order; + fsize = folioq_folio_size(folioq, slot); fpos = folio_pos(folio); fend = fpos + fsize; @@ -149,8 +202,6 @@ static void netfs_read_unlock_folios(struct netfs_io_request *rreq, WRITE_ONCE(rreq->cleaned_to, fpos + fsize); *notes |= MADE_PROGRESS; - clear_bit(NETFS_RREQ_FOLIO_COPY_TO_CACHE, &rreq->flags); - /* Clean up the head folioq. If we clear an entire folioq, then * we can get rid of it provided it's not also the tail folioq * being filled by the issuer. @@ -172,6 +223,8 @@ static void netfs_read_unlock_folios(struct netfs_io_request *rreq, rreq->buffer.tail = folioq; done: rreq->buffer.first_tail_slot = slot; + + netfs_read_set_unlock_at(rreq); } /* @@ -232,7 +285,7 @@ reassess: * subreqs. */ if (notes & BUFFERED) { - size_t fsize = PAGE_SIZE << rreq->front_folio_order; + uoff_t unlock_at = rreq->start + rreq->progress_at; /* Clear the tail of a short read. */ if (!(notes & HIT_PENDING) && @@ -248,16 +301,13 @@ reassess: stream->collected_to = front->start + transferred; rreq->collected_to = stream->collected_to; - if (test_bit(NETFS_SREQ_COPY_TO_CACHE, &front->flags)) - notes |= COPY_TO_CACHE; - if (test_bit(NETFS_SREQ_FAILED, &front->flags)) { rreq->abandon_to = front->start + front->len; front->transferred = front->len; transferred = front->len; trace_netfs_rreq(rreq, netfs_rreq_trace_set_abandon); } - if (front->start + transferred >= rreq->cleaned_to + fsize || + if (front->start + transferred >= unlock_at || test_bit(NETFS_SREQ_HIT_EOF, &front->flags)) netfs_read_unlock_folios(rreq, ¬es); } else { @@ -477,20 +527,22 @@ void netfs_read_collection_worker(struct work_struct *work) void netfs_read_subreq_progress(struct netfs_io_subrequest *subreq) { struct netfs_io_request *rreq = subreq->rreq; - struct netfs_io_stream *stream = &rreq->io_streams[0]; - size_t fsize = PAGE_SIZE << rreq->front_folio_order; - - trace_netfs_sreq(subreq, netfs_sreq_trace_progress); + struct netfs_io_stream *stream = &rreq->io_streams[subreq->stream_nr]; + size_t progress_at = READ_ONCE(rreq->progress_at); + uoff_t update_at = rreq->start + progress_at; + uoff_t transferred_to = subreq->start + subreq->transferred; /* If we are at the head of the queue, wake up the collector, * getting a ref to it if we were the ones to do so. */ - if (subreq->start + subreq->transferred > rreq->cleaned_to + fsize && + if (progress_at < rreq->len && + transferred_to >= update_at && (rreq->origin == NETFS_READAHEAD || rreq->origin == NETFS_READPAGE || rreq->origin == NETFS_READ_FOR_WRITE) && list_is_first(&subreq->rreq_link, &stream->subrequests) ) { + trace_netfs_sreq(subreq, netfs_sreq_trace_progress); __set_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags); netfs_wake_collector(rreq); } diff --git a/fs/netfs/read_pgpriv2.c b/fs/netfs/read_pgpriv2.c index c31190993b7626..a4b7bb88cbdb60 100644 --- a/fs/netfs/read_pgpriv2.c +++ b/fs/netfs/read_pgpriv2.c @@ -54,8 +54,8 @@ static void netfs_pgpriv2_copy_folio(struct netfs_io_request *creq, struct folio /* Attach the folio to the rolling buffer. */ if (rolling_buffer_append(&creq->buffer, folio, 0, creq->gfp) < 0) { + set_bit(NETFS_RREQ_CANCEL_CACHING, &creq->flags); folio_end_private_2(folio); - clear_bit(NETFS_RREQ_FOLIO_COPY_TO_CACHE, &creq->flags); return; } @@ -122,13 +122,14 @@ cancel_put: netfs_put_failed_request(creq); cancel: rreq->copy_to_cache = ERR_PTR(-ENOBUFS); - clear_bit(NETFS_RREQ_FOLIO_COPY_TO_CACHE, &rreq->flags); + set_bit(NETFS_RREQ_CANCEL_CACHING, &rreq->flags); return ERR_PTR(-ENOBUFS); } /* * [DEPRECATED] Mark page as requiring copy-to-cache using PG_private_2 and add - * it to the copy write request. + * it to the copy write request. PG_private_2 should already be set on the + * folio. */ void netfs_pgpriv2_copy_to_cache(struct netfs_io_request *rreq, struct folio *folio) { @@ -136,11 +137,13 @@ void netfs_pgpriv2_copy_to_cache(struct netfs_io_request *rreq, struct folio *fo if (!creq) creq = netfs_pgpriv2_begin_copy_to_cache(rreq, folio); - if (IS_ERR(creq)) + if (IS_ERR(creq)) { + set_bit(NETFS_RREQ_CANCEL_CACHING, &rreq->flags); + netfs_cancel_copy_to_cache(rreq, folio); return; + } - trace_netfs_folio(folio, netfs_folio_trace_copy_to_cache); - folio_start_private_2(folio); + trace_netfs_folio(folio, netfs_folio_trace_pgpriv2_copy); netfs_pgpriv2_copy_folio(creq, folio); } diff --git a/fs/netfs/read_retry.c b/fs/netfs/read_retry.c index 2b42758e01ec94..4f6a36c6e214f7 100644 --- a/fs/netfs/read_retry.c +++ b/fs/netfs/read_retry.c @@ -292,11 +292,22 @@ void netfs_unlock_abandoned_read_pages(struct netfs_io_request *rreq) { struct folio_queue *p; + /* We have to wait for readahead refs to have been released before we + * can unlock any folios as the ref-dropper walks i_pages and the only + * thing preventing these folios from being removed is the folio lock. + */ + if (test_bit(NETFS_RREQ_NEED_PUT_RA_REFS, &rreq->flags)) + netfs_wait_for_put_ra_refs(rreq); + for (p = rreq->buffer.tail; p; p = p->next) { for (int slot = 0; slot < folioq_count(p); slot++) { struct folio *folio = folioq_folio(p, slot); - if (folio && !folioq_is_marked2(p, slot)) { + if (!folio) + continue; + netfs_cancel_copy_to_cache(rreq, folio); + + if (!folioq_is_marked2(p, slot)) { if (folio == rreq->no_unlock_folio && test_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags)) { diff --git a/fs/netfs/read_single.c b/fs/netfs/read_single.c index 8833550d2eb608..de67ac41548d1a 100644 --- a/fs/netfs/read_single.c +++ b/fs/netfs/read_single.c @@ -170,6 +170,8 @@ ssize_t netfs_read_single(struct inode *inode, struct file *file, struct iov_ite if (IS_ERR(rreq)) return PTR_ERR(rreq); + rreq->progress_at = rreq->len; + ret = netfs_single_begin_cache_read(rreq, ictx); if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS) goto cleanup_free; diff --git a/fs/netfs/rolling_buffer.c b/fs/netfs/rolling_buffer.c index 8c0026836f9c1c..424e77a9a1098e 100644 --- a/fs/netfs/rolling_buffer.c +++ b/fs/netfs/rolling_buffer.c @@ -115,42 +115,65 @@ int rolling_buffer_make_space(struct rolling_buffer *roll, gfp_t gfp) } /* - * Decant the list of folios to read into a rolling buffer. + * Decant the entire list of folios to read into a rolling buffer. */ -ssize_t rolling_buffer_load_from_ra(struct rolling_buffer *roll, - struct readahead_control *ractl, - struct folio_batch *put_batch) +ssize_t rolling_buffer_bulk_load_from_ra(struct rolling_buffer *roll, + struct readahead_control *ractl, + unsigned int rreq_id, gfp_t gfp) { struct folio_queue *fq; - struct page **vec; - int nr, ix, to; - ssize_t size = 0; + ssize_t loaded = 0; - if (rolling_buffer_make_space(roll, GFP_KERNEL) < 0) - return -ENOMEM; + while (ractl->_nr_pages - ractl->_batch_count > 0) { + unsigned int nr; - fq = roll->head; - vec = (struct page **)fq->vec.folios; - nr = __readahead_batch(ractl, vec + folio_batch_count(&fq->vec), - folio_batch_space(&fq->vec)); - ix = fq->vec.nr; - to = ix + nr; - fq->vec.nr = to; - for (; ix < to; ix++) { - struct folio *folio = folioq_folio(fq, ix); - unsigned int order = folio_order(folio); - - fq->orders[ix] = order; - size += PAGE_SIZE << order; - trace_netfs_folio(folio, netfs_folio_trace_read); - if (!folio_batch_add(put_batch, folio)) - folio_batch_release(put_batch); + /* Allocate a folioq to put some folios into and attach it to + * the rolling buffer. + */ + fq = netfs_folioq_alloc(rreq_id, gfp, + netfs_trace_folioq_make_space); + if (!fq) + goto nomem_unlock; + fq->prev = roll->head; + if (!roll->tail) + roll->tail = fq; + else + roll->head->next = fq; + roll->head = fq; + + /* Get a batch of folios and note their orders. */ + nr = __readahead_batch(ractl, (struct page **)fq->vec.folios, + folioq_nr_slots(fq)); + if (WARN_ON_ONCE(!nr)) + break; + fq->vec.nr = nr; + + for (int slot = 0; slot < nr; slot++) { + struct folio *folio = folioq_folio(fq, slot); + unsigned int order; + + order = folio_order(folio); + fq->orders[slot] = order; + loaded += PAGE_SIZE << order; + trace_netfs_folio(folio, netfs_folio_trace_read); + } } - WRITE_ONCE(roll->iter.count, roll->iter.count + size); - /* Store the counter after setting the slot. */ - smp_store_release(&roll->next_head_slot, to); - return size; + WRITE_ONCE(roll->iter.count, loaded); + iov_iter_folio_queue(&roll->iter, ITER_DEST, roll->tail, 0, 0, loaded); + return loaded; + +nomem_unlock: + for (fq = roll->tail; fq; fq = fq->next) { + for (int slot = 0; slot < folioq_count(fq); slot++) { + folio_unlock(fq->vec.folios[slot]); + folioq_mark(fq, slot); + } + } + rolling_buffer_clear(roll); + roll->head = NULL; + roll->tail = NULL; + return -ENOMEM; } /* diff --git a/fs/netfs/write_issue.c b/fs/netfs/write_issue.c index 2d9cfcd43658f7..851f6f93ad45ab 100644 --- a/fs/netfs/write_issue.c +++ b/fs/netfs/write_issue.c @@ -170,6 +170,8 @@ void netfs_prepare_write(struct netfs_io_request *wreq, rolling_buffer_make_space(&wreq->buffer, wreq->gfp); subreq = netfs_alloc_subrequest(wreq); + if (!subreq) + return; subreq->source = stream->source; subreq->start = start; subreq->stream_nr = stream->stream_nr; diff --git a/fs/ntfs/attrib.c b/fs/ntfs/attrib.c index b4c6137c037b6e..918ff4db75f73e 100644 --- a/fs/ntfs/attrib.c +++ b/fs/ntfs/attrib.c @@ -1732,8 +1732,8 @@ static struct attr_def *ntfs_attr_find_in_attrdef(const struct ntfs_volume *vol, struct attr_def *ad; WARN_ON(!type); - for (ad = vol->attrdef; (u8 *)ad - (u8 *)vol->attrdef < - vol->attrdef_size && ad->type; ++ad) { + for (ad = vol->attrdef; (u8 *)ad - (u8 *)vol->attrdef <= + vol->attrdef_size - (s32)sizeof(*ad) && ad->type; ++ad) { /* We have not found it yet, carry on searching. */ if (likely(le32_to_cpu(ad->type) < le32_to_cpu(type))) continue; @@ -2495,7 +2495,7 @@ int ntfs_resident_attr_record_add(struct ntfs_inode *ni, __le32 type, return offset; put_err_out: ntfs_attr_put_search_ctx(ctx); - return -EIO; + return err; } /* @@ -2634,7 +2634,7 @@ static int ntfs_non_resident_attr_record_add(struct ntfs_inode *ni, __le32 type, return offset; put_err_out: ntfs_attr_put_search_ctx(ctx); - return -1; + return err; } /* @@ -5693,7 +5693,7 @@ int ntfs_attr_fallocate(struct ntfs_inode *ni, loff_t start, loff_t byte_len, bo lcn << vol->cluster_size_bits, alloc_cnt << vol->cluster_size_bits); - if (err > 0) + if (err) goto out; } diff --git a/fs/ntfs/ea.c b/fs/ntfs/ea.c index 25ff159dbfd38b..75a251ec4ebcbf 100644 --- a/fs/ntfs/ea.c +++ b/fs/ntfs/ea.c @@ -390,10 +390,12 @@ alloc_new_ea: *packed_ea_size = p_ea_info->ea_length; mark_mft_record_dirty(ni); out: - if (ea_info_qsize > 0) - NInoSetHasEA(ni); - else - NInoClearHasEA(ni); + if (!err) { + if (ea_info_qsize > 0) + NInoSetHasEA(ni); + else + NInoClearHasEA(ni); + } kvfree(ea_buf); kvfree(old_ea_buf); @@ -591,7 +593,7 @@ static int ntfs_getxattr(const struct xattr_handler *handler, if (!buffer) { err = sizeof(u8); } else if (size < sizeof(u8)) { - err = -ENODATA; + err = -ERANGE; } else { err = sizeof(u8); *(u8 *)buffer = (u8)(le32_to_cpu(ni->flags) & 0x3F); @@ -604,7 +606,7 @@ static int ntfs_getxattr(const struct xattr_handler *handler, if (!buffer) { err = sizeof(u32); } else if (size < sizeof(u32)) { - err = -ENODATA; + err = -ERANGE; } else { err = sizeof(u32); *(u32 *)buffer = le32_to_cpu(ni->flags); diff --git a/fs/ntfs/lcnalloc.c b/fs/ntfs/lcnalloc.c index aa2e017a43844b..0d6cd08ee2e76d 100644 --- a/fs/ntfs/lcnalloc.c +++ b/fs/ntfs/lcnalloc.c @@ -53,10 +53,10 @@ int ntfs_cluster_free_from_rl_nolock(struct ntfs_volume *vol, if (rl->lcn < 0) continue; err = ntfs_bitmap_clear_run(lcnbmp_vi, rl->lcn, rl->length); - if (unlikely(err && (!ret || ret == -ENOMEM) && ret != err)) - ret = err; - else + if (likely(!err)) nr_freed += rl->length; + else if (!ret || ret == -ENOMEM) + ret = err; } ntfs_inc_free_clusters(vol, nr_freed); ntfs_debug("Done."); @@ -1045,8 +1045,9 @@ err_out: "Failed to rollback (error %i). Leaving inconsistent metadata! Unmount and run chkdsk.", (int)delta); NVolSetErrors(vol); + } else { + ntfs_dec_free_clusters(vol, delta); } - ntfs_dec_free_clusters(vol, delta); up_write(&vol->lcnbmp_lock); memalloc_nofs_restore(memalloc_flags); ntfs_error(vol->sb, "Aborting (error %i).", err); diff --git a/fs/ntfs/mft.c b/fs/ntfs/mft.c index 271a265491280e..3ad739179c7a16 100644 --- a/fs/ntfs/mft.c +++ b/fs/ntfs/mft.c @@ -580,7 +580,7 @@ int write_mft_record_nolock(struct ntfs_inode *ni, struct mft_record *m, int syn err = pre_write_mst_fixup((struct ntfs_record *)fixup_m, vol->mft_record_size); if (err) { ntfs_error(vol->sb, "Failed to apply mst fixups!"); - goto err_out; + goto unmap_err_out; } folio_size = vol->mft_record_size / ni->mft_lcn_count; @@ -645,6 +645,8 @@ done: return 0; put_bio_out: bio_put(bio); +unmap_err_out: + kunmap_local(kaddr); err_out: /* * The caller should mark the base inode as bad so no more I/O diff --git a/fs/ntfs/reparse.c b/fs/ntfs/reparse.c index fa523dc3691ea1..f8b88a110cb672 100644 --- a/fs/ntfs/reparse.c +++ b/fs/ntfs/reparse.c @@ -332,7 +332,7 @@ unsigned int ntfs_reparse_tag_dt_types(struct ntfs_volume *vol, unsigned long mr vi = ntfs_iget(vol->sb, mref); if (IS_ERR(vi)) - return PTR_ERR(vi); + return DT_UNKNOWN; reparse_attr = (struct reparse_point *)ntfs_attr_readall(NTFS_I(vi), AT_REPARSE_POINT, NULL, 0, &attr_size); @@ -620,8 +620,9 @@ static int update_reparse_data(struct ntfs_inode *ni, struct ntfs_index_context goto put_rp_inode; } - if (set_reparse_index(ni, xr, ((const struct reparse_point *)value)->reparse_tag) && - oldsize > 0) { + err = set_reparse_index(ni, xr, + ((const struct reparse_point *)value)->reparse_tag); + if (err && oldsize > 0) { /* * If cannot index, try to remove the reparse * data and log the error. There will be an diff --git a/fs/ntfs/super.c b/fs/ntfs/super.c index cd8fa2c133700c..63aa83ff77f5d7 100644 --- a/fs/ntfs/super.c +++ b/fs/ntfs/super.c @@ -557,8 +557,8 @@ static bool is_boot_sector_ntfs(const struct super_block *sb, * Check sectors per cluster value is valid and the cluster size * is not above the maximum (2MB). */ - if (b->bpb.sectors_per_cluster > 0x80 && - b->bpb.sectors_per_cluster < 0xf4) + if (b->bpb.sectors_per_cluster < 0xf4 && + !is_power_of_2(b->bpb.sectors_per_cluster)) goto not_ntfs; /* Check reserved/unused fields are really zero. */ @@ -1241,9 +1241,9 @@ static bool load_and_init_attrdef(struct ntfs_volume *vol) goto failed; } NInoSetSparseDisabled(NTFS_I(ino)); - /* The size of FILE_AttrDef must be above 0 and fit inside 31 bits. */ + /* FILE_AttrDef must hold at least one entry and fit inside 31 bits. */ i_size = i_size_read(ino); - if (i_size <= 0 || i_size > 0x7fffffff) + if (i_size < (s64)sizeof(struct attr_def) || i_size > 0x7fffffff) goto iput_failed; vol->attrdef = kvzalloc(i_size, GFP_NOFS); if (!vol->attrdef) @@ -1862,7 +1862,8 @@ static int ntfs_sync_fs(struct super_block *sb, int wait) return 0; /* If there are some dirty buffers in the bdev inode */ - if (ntfs_clear_volume_flags(vol, VOLUME_IS_DIRTY)) { + if (!NVolErrors(vol) && + ntfs_clear_volume_flags(vol, VOLUME_IS_DIRTY)) { ntfs_warning(sb, "Failed to clear dirty bit in volume information flags. Run chkdsk."); err = -EIO; } diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index 60b808b85fc439..43eb0c053dacd9 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -1543,7 +1543,7 @@ int ovl_fill_super(struct super_block *sb, struct fs_context *fc) struct ovl_fs *ofs = sb->s_fs_info; int err; - err = -EIO; + err = -EINVAL; /* The fscontext fd may have been passed to another user namespace. */ if (fc->user_ns != current_user_ns()) goto out_err; diff --git a/fs/smb/client/cifsacl.c b/fs/smb/client/cifsacl.c index 12005f46307dea..c5e47a835f99db 100644 --- a/fs/smb/client/cifsacl.c +++ b/fs/smb/client/cifsacl.c @@ -100,8 +100,23 @@ cifs_idmap_key_destroy(struct key *key) kfree(key->payload.data[0]); } +static int +cifs_idmap_key_vet_description(const char *description) +{ + /* + * cifs.idmap descriptions are authority-bearing inputs to the + * cifs.idmap upcall helper. Only allow the kernel to create this + * type of key using the private root_cred installed in + * init_cifs_idmap; reject userspace request_key(2)/add_key(2). + */ + if (current_cred() != root_cred) + return -EPERM; + return 0; +} + static struct key_type cifs_idmap_key_type = { .name = "cifs.idmap", + .vet_description = cifs_idmap_key_vet_description, .instantiate = cifs_idmap_key_instantiate, .destroy = cifs_idmap_key_destroy, .describe = user_describe, @@ -1081,13 +1096,13 @@ unsigned int setup_special_user_owner_ACE(struct smb_ace *pntace) static void populate_new_aces(char *nacl_base, struct smb_sid *pownersid, struct smb_sid *pgrpsid, - __u64 *pnmode, u16 *pnum_aces, u16 *pnsize, + __u64 *pnmode, u16 *pnum_aces, u32 *pnsize, bool modefromsid, bool posix) { __u64 nmode; u16 num_aces = 0; - u16 nsize = 0; + u32 nsize = 0; __u64 user_mode; __u64 group_mode; __u64 other_mode; @@ -1186,17 +1201,17 @@ set_size: *pnsize = nsize; } -static __u16 replace_sids_and_copy_aces(struct smb_acl *pdacl, struct smb_acl *pndacl, - struct smb_sid *pownersid, struct smb_sid *pgrpsid, - struct smb_sid *pnownersid, struct smb_sid *pngrpsid, - int *aclflag) +static int replace_sids_and_copy_aces(struct smb_acl *pdacl, struct smb_acl *pndacl, + struct smb_sid *pownersid, struct smb_sid *pgrpsid, + struct smb_sid *pnownersid, struct smb_sid *pngrpsid, + int *aclflag, u16 *pnsize) { int i; u16 size = 0; struct smb_ace *pntace = NULL; char *acl_base = NULL; u16 src_num_aces = 0; - u16 nsize = 0; + u32 nsize = 0; struct smb_ace *pnntace = NULL; char *nacl_base = NULL; u16 ace_size = 0; @@ -1225,9 +1240,12 @@ static __u16 replace_sids_and_copy_aces(struct smb_acl *pdacl, struct smb_acl *p size += le16_to_cpu(pntace->size); nsize += ace_size; + if (nsize > U16_MAX) + return -EOVERFLOW; } - return nsize; + *pnsize = nsize; + return 0; } static int set_chmod_dacl(struct smb_acl *pdacl, struct smb_acl *pndacl, @@ -1239,7 +1257,7 @@ static int set_chmod_dacl(struct smb_acl *pdacl, struct smb_acl *pndacl, struct smb_ace *pntace = NULL; char *acl_base = NULL; u16 src_num_aces = 0; - u16 nsize = 0; + u32 nsize = 0; struct smb_ace *pnntace = NULL; char *nacl_base = NULL; u16 num_aces = 0; @@ -1290,6 +1308,8 @@ static int set_chmod_dacl(struct smb_acl *pdacl, struct smb_acl *pndacl, nsize += cifs_copy_ace(pnntace, pntace, NULL); num_aces++; + if (nsize > U16_MAX) + return -EOVERFLOW; next_ace: size += le16_to_cpu(pntace->size); @@ -1306,6 +1326,10 @@ next_ace: } finalize_dacl: + /* The DACL size field is 16-bit on the wire, see MS-DTYP 2.4.5 */ + if (nsize > U16_MAX) + return -EOVERFLOW; + pndacl->num_aces = cpu_to_le16(num_aces); pndacl->size = cpu_to_le16(nsize); @@ -1331,6 +1355,7 @@ static int parse_sec_desc(struct cifs_sb_info *cifs_sb, { int rc = 0; struct smb_sid *owner_sid_ptr, *group_sid_ptr; + unsigned int sbflags = cifs_sb_flags(cifs_sb); struct smb_acl *dacl_ptr; /* no need for SACL ptr */ char *end_of_acl; __u32 dacloffset, osidoffset, gsidoffset; @@ -1349,17 +1374,21 @@ static int parse_sec_desc(struct cifs_sb_info *cifs_sb, cifs_dbg(NOISY, "revision %d type 0x%x ooffset 0x%x goffset 0x%x sacloffset 0x%x dacloffset 0x%x\n", pntsd->revision, pntsd->type, osidoffset, gsidoffset, le32_to_cpu(pntsd->sacloffset), dacloffset); -/* cifs_dump_mem("owner_sid: ", owner_sid_ptr, 64); */ + fattr->cf_uid = cifs_sb->ctx->linux_uid; + fattr->cf_gid = cifs_sb->ctx->linux_gid; + rc = sid_from_sd(pntsd, acl_len, osidoffset, &owner_sid_ptr); if (rc) { cifs_dbg(FYI, "%s: Error %d parsing Owner SID\n", __func__, rc); return rc; } - rc = sid_to_id(cifs_sb, owner_sid_ptr, fattr, SIDOWNER); - if (rc) { - cifs_dbg(FYI, "%s: Error %d mapping Owner SID to uid\n", - __func__, rc); - return rc; + if (!(sbflags & CIFS_MOUNT_OVERR_UID)) { + rc = sid_to_id(cifs_sb, owner_sid_ptr, fattr, SIDOWNER); + if (rc) { + cifs_dbg(FYI, "%s: Error %d mapping Owner SID to uid\n", + __func__, rc); + return rc; + } } rc = sid_from_sd(pntsd, acl_len, gsidoffset, &group_sid_ptr); @@ -1368,11 +1397,13 @@ static int parse_sec_desc(struct cifs_sb_info *cifs_sb, __func__, rc); return rc; } - rc = sid_to_id(cifs_sb, group_sid_ptr, fattr, SIDGROUP); - if (rc) { - cifs_dbg(FYI, "%s: Error %d mapping Group SID to gid\n", - __func__, rc); - return rc; + if (!(sbflags & CIFS_MOUNT_OVERR_GID)) { + rc = sid_to_id(cifs_sb, group_sid_ptr, fattr, SIDGROUP); + if (rc) { + cifs_dbg(FYI, "%s: Error %d mapping Group SID to gid\n", + __func__, rc); + return rc; + } } if (dacloffset) { @@ -1451,6 +1482,8 @@ static int build_sec_desc(struct smb_ntsd *pntsd, struct smb_ntsd *pnntsd, rc = set_chmod_dacl(dacl_ptr, ndacl_ptr, owner_sid_ptr, group_sid_ptr, pnmode, mode_from_sid, posix); + if (rc) + return rc; sidsoffset = ndacloffset + le16_to_cpu(ndacl_ptr->size); /* copy the non-dacl portion of secdesc */ @@ -1526,10 +1559,12 @@ static int build_sec_desc(struct smb_ntsd *pntsd, struct smb_ntsd *pnntsd, if (dacloffset) { /* Replace ACEs for old owner with new one */ - size = replace_sids_and_copy_aces(dacl_ptr, ndacl_ptr, - owner_sid_ptr, group_sid_ptr, - nowner_sid_ptr, ngroup_sid_ptr, - aclflag); + rc = replace_sids_and_copy_aces(dacl_ptr, ndacl_ptr, + owner_sid_ptr, group_sid_ptr, + nowner_sid_ptr, ngroup_sid_ptr, + aclflag, &size); + if (rc) + goto chown_chgrp_exit; ndacl_ptr->size = cpu_to_le16(size); } @@ -1815,11 +1850,13 @@ id_mode_to_cifs_acl(struct inode *inode, const char *path, __u64 *pnmode, cifs_put_tlink(tlink); return rc; } - if (mode_from_sid) - nsecdesclen += - le16_to_cpu(dacl_ptr->num_aces) * sizeof(struct smb_ace); - else /* cifsacl */ - nsecdesclen += le16_to_cpu(dacl_ptr->size); + /* + * Worst case: every ACE is rewritten with a new SID of + * SID_MAX_SUB_AUTHORITIES sub-auths -> sizeof(smb_ace) each, + * plus the smb_acl header replace_sids_and_copy_aces() emits. + */ + nsecdesclen += sizeof(struct smb_acl) + + le16_to_cpu(dacl_ptr->num_aces) * sizeof(struct smb_ace); } } diff --git a/fs/smb/client/cifssmb.c b/fs/smb/client/cifssmb.c index f5aad5f61dce10..a1da1ade8c1016 100644 --- a/fs/smb/client/cifssmb.c +++ b/fs/smb/client/cifssmb.c @@ -1719,8 +1719,17 @@ CIFSSMBRead(const unsigned int xid, struct cifs_io_parms *io_parms, pSMBr = (READ_RSP *)rsp_iov.iov_base; if (rc) { cifs_dbg(VFS, "Send error in read = %d\n", rc); + } else if (rsp_iov.iov_len < tcon->ses->server->vals->read_rsp_size) { + /* check that the received response can hold a whole READ_RSP */ + cifs_dbg(FYI, "%s: server returned short header. got=%zu expected=%zu\n", + __func__, rsp_iov.iov_len, + tcon->ses->server->vals->read_rsp_size); + rc = smb_EIO2(smb_eio_trace_read_rsp_short, + rsp_iov.iov_len, tcon->ses->server->vals->read_rsp_size); + *nbytes = 0; } else { - int data_length = le16_to_cpu(pSMBr->DataLengthHigh); + unsigned int data_length = le16_to_cpu(pSMBr->DataLengthHigh); + __u16 data_offset = le16_to_cpu(pSMBr->DataOffset); data_length = data_length << 16; data_length += le16_to_cpu(pSMBr->DataLength); *nbytes = data_length; @@ -1728,14 +1737,21 @@ CIFSSMBRead(const unsigned int xid, struct cifs_io_parms *io_parms, /*check that DataLength would not go beyond end of SMB */ if ((data_length > CIFSMaxBufSize) || (data_length > count)) { - cifs_dbg(FYI, "bad length %d for count %d\n", - data_length, count); + cifs_dbg(FYI, "%s: bad length %u for count %u\n", + __func__, data_length, count); rc = smb_EIO2(smb_eio_trace_read_overlarge, data_length, count); *nbytes = 0; + } else if (data_offset < sizeof(*pSMBr) || + (size_t)data_offset + data_length > rsp_iov.iov_len) { + /* check that the data lies within the received response */ + cifs_dbg(FYI, "%s: bad data offset %u length %u for response of %zu\n", + __func__, data_offset, data_length, rsp_iov.iov_len); + rc = smb_EIO2(smb_eio_trace_read_bad_offset, + data_offset, data_length); + *nbytes = 0; } else { - pReadData = (char *) (&pSMBr->hdr.Protocol) + - le16_to_cpu(pSMBr->DataOffset); + pReadData = (char *) (&pSMBr->hdr.Protocol) + data_offset; /* if (rc = copy_to_user(buf, pReadData, data_length)) { cifs_dbg(VFS, "Faulting on read rc = %d\n",rc); rc = -EFAULT; diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c index 389083f9ce003f..8886e9483c91ed 100644 --- a/fs/smb/client/file.c +++ b/fs/smb/client/file.c @@ -1491,11 +1491,18 @@ int cifs_close(struct inode *inode, struct file *file) trace_smb3_close_cached(tcon->tid, tcon->ses->Suid, cfile->fid.persistent_fid, cifs_sb->ctx->closetimeo); - queue_delayed_work(deferredclose_wq, - &cfile->deferred, cifs_sb->ctx->closetimeo); - cfile->deferred_close_scheduled = true; - spin_unlock(&cinode->deferred_lock); - return 0; + /* + * Each queued execution owns one reference. + * If nothing was queued, the reference of + * the closing file is dropped below. + */ + if (queue_delayed_work(deferredclose_wq, + &cfile->deferred, + cifs_sb->ctx->closetimeo)) { + cfile->deferred_close_scheduled = true; + spin_unlock(&cinode->deferred_lock); + return 0; + } } spin_unlock(&cinode->deferred_lock); _cifsFileInfo_put(cfile, true, false); @@ -3324,8 +3331,11 @@ void cifs_oplock_break(struct work_struct *work) TASK_UNINTERRUPTIBLE); tlink = cifs_sb_tlink(cifs_sb); - if (IS_ERR(tlink)) + if (IS_ERR(tlink)) { + /* drop the reference taken when the break was queued */ + _cifsFileInfo_put(cfile, false /* do not wait for ourself */, false); goto out; + } tcon = tlink_tcon(tlink); server = tcon->ses->server; diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c index 85ef8fff0e8422..db797a56215666 100644 --- a/fs/smb/client/inode.c +++ b/fs/smb/client/inode.c @@ -851,6 +851,7 @@ static void smb311_posix_info_to_fattr(struct cifs_fattr *fattr, struct smb311_posix_qinfo *info = &data->posix_fi; struct cifs_sb_info *cifs_sb = CIFS_SB(sb); struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb); + unsigned int sbflags = cifs_sb_flags(cifs_sb); memset(fattr, 0, sizeof(*fattr)); @@ -895,8 +896,12 @@ out_reparse: fattr->cf_symlink_target = data->symlink_target; data->symlink_target = NULL; } - sid_to_id(cifs_sb, &data->posix_owner, fattr, SIDOWNER); - sid_to_id(cifs_sb, &data->posix_group, fattr, SIDGROUP); + fattr->cf_uid = cifs_sb->ctx->linux_uid; + fattr->cf_gid = cifs_sb->ctx->linux_gid; + if (!(sbflags & CIFS_MOUNT_OVERR_UID)) + sid_to_id(cifs_sb, &data->posix_owner, fattr, SIDOWNER); + if (!(sbflags & CIFS_MOUNT_OVERR_GID)) + sid_to_id(cifs_sb, &data->posix_group, fattr, SIDGROUP); cifs_dbg(FYI, "POSIX query info: mode 0x%x uniqueid 0x%llx nlink %d\n", fattr->cf_mode, fattr->cf_uniqueid, fattr->cf_nlink); @@ -2983,14 +2988,14 @@ int cifs_getattr(struct mnt_idmap *idmap, const struct path *path, stat->attributes |= STATX_ATTR_ENCRYPTED; /* - * If on a multiuser mount without unix extensions or cifsacl being - * enabled, and the admin hasn't overridden them, set the ownership - * to the fsuid/fsgid of the current process. + * If on a multiuser mount without unix extensions, posix extensions + * or cifsacl being enabled, and the admin hasn't overridden them, + * set the ownership to the fsuid/fsgid of the current process. */ sbflags = cifs_sb_flags(cifs_sb); if ((sbflags & CIFS_MOUNT_MULTIUSER) && !(sbflags & CIFS_MOUNT_CIFS_ACL) && - !tcon->unix_ext) { + !tcon->unix_ext && !tcon->posix_extensions) { if (!(sbflags & CIFS_MOUNT_OVERR_UID)) stat->uid = current_fsuid(); if (!(sbflags & CIFS_MOUNT_OVERR_GID)) diff --git a/fs/smb/client/misc.c b/fs/smb/client/misc.c index 46e1382e8e04b2..945194fe7a9754 100644 --- a/fs/smb/client/misc.c +++ b/fs/smb/client/misc.c @@ -378,10 +378,11 @@ void cifs_queue_oplock_break(struct cifsFileInfo *cfile) * open_file_lock to enforce the validity of it for the oplock * break handler. The matching put is done at the end of the * handler. + * + * Only take a reference if the work is actually queued. */ - cifsFileInfo_get(cfile); - - queue_work(cifsoplockd_wq, &cfile->oplock_break); + if (queue_work(cifsoplockd_wq, &cfile->oplock_break)) + cifsFileInfo_get(cfile); } void cifs_done_oplock_break(struct cifsInodeInfo *cinode) @@ -891,8 +892,14 @@ static void tcon_super_cb(struct super_block *sb, void *arg) t1->ses->dfs_root_ses == t2->ses->dfs_root_ses) && t1->ses->server == t2->ses->server && t2->origin_fullpath && - dfs_src_pathname_equal(t2->origin_fullpath, t1->origin_fullpath)) + dfs_src_pathname_equal(t2->origin_fullpath, t1->origin_fullpath)) { + /* + * Take the active reference while iterate_supers_type() still + * holds s_umount shared. + */ + cifs_sb_active(sb); sd->sb = sb; + } spin_unlock(&t2->tc_lock); } @@ -909,15 +916,8 @@ static struct super_block *__cifs_get_super(void (*f)(struct super_block *, void for (; *fs_type; fs_type++) { iterate_supers_type(*fs_type, f, &sd); - if (sd.sb) { - /* - * Grab an active reference in order to prevent automounts (DFS links) - * of expiring and then freeing up our cifs superblock pointer while - * we're doing failover. - */ - cifs_sb_active(sd.sb); + if (sd.sb) return sd.sb; - } } pr_warn_once("%s: could not find dfs superblock\n", __func__); return ERR_PTR(-EINVAL); diff --git a/fs/smb/client/readdir.c b/fs/smb/client/readdir.c index 32a75afca8f52c..9530e5b0156429 100644 --- a/fs/smb/client/readdir.c +++ b/fs/smb/client/readdir.c @@ -242,9 +242,11 @@ static void cifs_posix_to_fattr(struct cifs_fattr *fattr, struct smb2_posix_info *info, struct cifs_sb_info *cifs_sb) { + unsigned int sbflags = cifs_sb_flags(cifs_sb); struct smb2_posix_info_parsed parsed; + int rc; - posix_info_parse(info, NULL, &parsed); + rc = posix_info_parse(info, NULL, &parsed); memset(fattr, 0, sizeof(*fattr)); fattr->cf_uniqueid = le64_to_cpu(info->Inode); @@ -281,8 +283,17 @@ cifs_posix_to_fattr(struct cifs_fattr *fattr, struct smb2_posix_info *info, le32_to_cpu(info->ReparseTag), le32_to_cpu(info->Mode)); - sid_to_id(cifs_sb, &parsed.owner, fattr, SIDOWNER); - sid_to_id(cifs_sb, &parsed.group, fattr, SIDGROUP); + fattr->cf_uid = cifs_sb->ctx->linux_uid; + fattr->cf_gid = cifs_sb->ctx->linux_gid; + if (rc < 0) { + cifs_dbg(VFS, "%s: failed to parse SIDs: %d\n", + __func__, rc); + } else { + if (!(sbflags & CIFS_MOUNT_OVERR_UID)) + sid_to_id(cifs_sb, &parsed.owner, fattr, SIDOWNER); + if (!(sbflags & CIFS_MOUNT_OVERR_GID)) + sid_to_id(cifs_sb, &parsed.group, fattr, SIDGROUP); + } } static void __dir_info_to_fattr(struct cifs_fattr *fattr, const void *info) diff --git a/fs/smb/client/reparse.c b/fs/smb/client/reparse.c index 5cc5b0410d4894..8a1b9e8be5ba71 100644 --- a/fs/smb/client/reparse.c +++ b/fs/smb/client/reparse.c @@ -971,7 +971,8 @@ globalroot: linux_target[i*3 + 1] = '.'; linux_target[i*3 + 2] = sep; } - memcpy(linux_target + levels*3, smb_target+1, smb_target_len); /* +1 to skip leading sep */ + /* +1 to skip leading sep */ + memcpy(linux_target + levels*3, smb_target+1, smb_target_len-1); } else { /* * This is either an absolute symlink in POSIX-style format @@ -1137,10 +1138,15 @@ static bool wsl_to_fattr(struct cifs_open_info_data *data, struct cifs_sb_info *cifs_sb, u32 tag, struct cifs_fattr *fattr) { + unsigned int sbflags = cifs_sb_flags(cifs_sb); struct smb2_file_full_ea_info *ea; bool have_xattr_dev = false; u32 next = 0; + fattr->cf_uid = cifs_sb->ctx->linux_uid; + fattr->cf_gid = cifs_sb->ctx->linux_gid; + + fattr->cf_mode &= ~S_IFMT; switch (tag) { case IO_REPARSE_TAG_LX_SYMLINK: fattr->cf_mode |= S_IFLNK; @@ -1177,11 +1183,13 @@ static bool wsl_to_fattr(struct cifs_open_info_data *data, nlen = ea->ea_name_length; v = (void *)((u8 *)ea->ea_data + ea->ea_name_length + 1); - if (!strncmp(name, SMB2_WSL_XATTR_UID, nlen)) - fattr->cf_uid = wsl_make_kuid(cifs_sb, v); - else if (!strncmp(name, SMB2_WSL_XATTR_GID, nlen)) - fattr->cf_gid = wsl_make_kgid(cifs_sb, v); - else if (!strncmp(name, SMB2_WSL_XATTR_MODE, nlen)) { + if (!strncmp(name, SMB2_WSL_XATTR_UID, nlen)) { + if (!(sbflags & CIFS_MOUNT_OVERR_UID)) + fattr->cf_uid = wsl_make_kuid(cifs_sb, v); + } else if (!strncmp(name, SMB2_WSL_XATTR_GID, nlen)) { + if (!(sbflags & CIFS_MOUNT_OVERR_GID)) + fattr->cf_gid = wsl_make_kgid(cifs_sb, v); + } else if (!strncmp(name, SMB2_WSL_XATTR_MODE, nlen)) { /* File type in reparse point tag and in xattr mode must match. */ if (S_DT(fattr->cf_mode) != S_DT(le32_to_cpu(*(__le32 *)v))) return false; @@ -1205,6 +1213,7 @@ static bool posix_reparse_to_fattr(struct cifs_sb_info *cifs_sb, struct cifs_open_info_data *data) { struct reparse_nfs_data_buffer *buf = (struct reparse_nfs_data_buffer *)data->reparse.buf; + umode_t ftype; if (buf == NULL) return true; @@ -1220,7 +1229,7 @@ static bool posix_reparse_to_fattr(struct cifs_sb_info *cifs_sb, WARN_ON_ONCE(1); return false; } - fattr->cf_mode |= S_IFCHR; + ftype = S_IFCHR; fattr->cf_rdev = reparse_mkdev(buf->DataBuffer); break; case NFS_SPECFILE_BLK: @@ -1228,22 +1237,23 @@ static bool posix_reparse_to_fattr(struct cifs_sb_info *cifs_sb, WARN_ON_ONCE(1); return false; } - fattr->cf_mode |= S_IFBLK; + ftype = S_IFBLK; fattr->cf_rdev = reparse_mkdev(buf->DataBuffer); break; case NFS_SPECFILE_FIFO: - fattr->cf_mode |= S_IFIFO; + ftype = S_IFIFO; break; case NFS_SPECFILE_SOCK: - fattr->cf_mode |= S_IFSOCK; + ftype = S_IFSOCK; break; case NFS_SPECFILE_LNK: - fattr->cf_mode |= S_IFLNK; + ftype = S_IFLNK; break; default: WARN_ON_ONCE(1); return false; } + fattr->cf_mode = (fattr->cf_mode & ~S_IFMT) | ftype; return true; } @@ -1271,6 +1281,7 @@ bool cifs_reparse_point_to_fattr(struct cifs_sb_info *cifs_sb, break; case 0: /* SMB1 symlink */ case IO_REPARSE_TAG_SYMLINK: + fattr->cf_mode &= ~S_IFMT; fattr->cf_mode |= S_IFLNK; break; default: diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index 0e872d58fae7ca..5f616384c75c01 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -1839,31 +1839,31 @@ free_vars: * * @tcon: destination file tcon * @bytes_left: how many bytes are left to copy + * @chunk_size: maximum size of a single chunk * * Return: maximum number of chunks with which Chunks[] can be filled. */ static inline u32 -calc_chunk_count(struct cifs_tcon *tcon, u64 bytes_left) +calc_chunk_count(struct cifs_tcon *tcon, u64 bytes_left, u32 chunk_size) { u32 max_chunks = READ_ONCE(tcon->max_chunks); u32 max_bytes_copy = READ_ONCE(tcon->max_bytes_copy); - u32 max_bytes_chunk = READ_ONCE(tcon->max_bytes_chunk); u64 need; u32 allowed; - if (!max_bytes_chunk || !max_bytes_copy || !max_chunks) + if (!chunk_size || !max_bytes_copy || !max_chunks) return 0; /* chunks needed for the remaining bytes */ - need = DIV_ROUND_UP_ULL(bytes_left, max_bytes_chunk); + need = DIV_ROUND_UP_ULL(bytes_left, chunk_size); /* chunks allowed per cc request */ - allowed = DIV_ROUND_UP(max_bytes_copy, max_bytes_chunk); + allowed = DIV_ROUND_UP(max_bytes_copy, chunk_size); return (u32)umin(need, umin(max_chunks, allowed)); } /** - * smb2_copychunk_range - server-side copy of data range + * __smb2_copychunk_range - server-side copy of data range * * @xid: transaction id * @src_file: source file @@ -1875,15 +1875,15 @@ calc_chunk_count(struct cifs_tcon *tcon, u64 bytes_left) * Obtains a resume key for @src_file and issues FSCTL_SRV_COPYCHUNK_WRITE * IOCTLs, splitting the request into chunks limited by tcon->max_*. * - * Return: @len on success; negative errno on failure. + * Return: 0 on success; negative errno on failure. */ -static ssize_t -smb2_copychunk_range(const unsigned int xid, - struct cifsFileInfo *src_file, - struct cifsFileInfo *dst_file, - u64 src_off, - u64 len, - u64 dst_off) +static int +__smb2_copychunk_range(const unsigned int xid, + struct cifsFileInfo *src_file, + struct cifsFileInfo *dst_file, + u64 src_off, + u64 len, + u64 dst_off) { int rc = 0; unsigned int ret_data_len = 0; @@ -1891,12 +1891,14 @@ smb2_copychunk_range(const unsigned int xid, struct copychunk_ioctl_rsp *cc_rsp = NULL; struct cifs_tcon *tcon; struct srv_copychunk *chunk; - u32 chunks, chunk_count, chunk_bytes; + u32 chunks, chunk_count, chunk_bytes, chunk_size; u32 copy_bytes, copy_bytes_left; u32 chunks_written, bytes_written; u64 total_bytes_left = len; u64 src_off_prev, dst_off_prev; + u64 max_chunk = 0; u32 retries = 0; + bool reverse = false; tcon = tlink_tcon(dst_file->tlink); @@ -1904,8 +1906,50 @@ smb2_copychunk_range(const unsigned int xid, dst_file->fid.volatile_fid, tcon->tid, tcon->ses->Suid, src_off, dst_off, len); + /* + * Same-file left shifts are safe in forward order. For a right shift, + * let L be the copy length, delta the distance between the source and + * destination, and C the normal chunk size: + * + * delta >= L: copy forwards using C + * delta < L: + * delta >= C: copy backwards using C + * delta < C: copy backwards with chunks limited to delta + * + * Copying backwards prevents one chunk from overwriting data needed by + * a later chunk. Limiting the chunk size to delta prevents an individual + * chunk from overlapping itself. + * This limit can be removed once all supported servers handle overlapping + * descriptors safely. + * + * A small right shift over a large range may therefore require many + * chunks. + */ + if (src_file == dst_file && dst_off > src_off) { + u64 delta = dst_off - src_off; + + if (delta < len) { + reverse = true; + max_chunk = delta; + } + } + + /* + * A backward copy walks the offsets down from the end of the range. + * Do this once, outside the retry loop, so a retry does not move the + * offsets again. + */ + if (reverse) { + src_off += len; + dst_off += len; + } + retry: - chunk_count = calc_chunk_count(tcon, total_bytes_left); + chunk_size = READ_ONCE(tcon->max_bytes_chunk); + if (max_chunk && max_chunk < chunk_size) + chunk_size = (u32)max_chunk; + + chunk_count = calc_chunk_count(tcon, total_bytes_left, chunk_size); if (!chunk_count) { rc = -EOPNOTSUPP; goto out; @@ -1946,16 +1990,21 @@ retry: while (copy_bytes_left > 0 && chunks < chunk_count) { chunk = &cc_req->Chunks[chunks++]; + chunk_bytes = umin(copy_bytes_left, chunk_size); + if (reverse) { + src_off -= chunk_bytes; + dst_off -= chunk_bytes; + } + chunk->SourceOffset = cpu_to_le64(src_off); chunk->TargetOffset = cpu_to_le64(dst_off); - - chunk_bytes = umin(copy_bytes_left, tcon->max_bytes_chunk); - chunk->Length = cpu_to_le32(chunk_bytes); /* Buffer is zeroed, no need to set chunk->Reserved = 0 */ - src_off += chunk_bytes; - dst_off += chunk_bytes; + if (!reverse) { + src_off += chunk_bytes; + dst_off += chunk_bytes; + } copy_bytes_left -= chunk_bytes; copy_bytes += chunk_bytes; @@ -2003,6 +2052,18 @@ retry: goto out; } + /* + * A successful COPYCHUNK should copy every descriptor (MS-SMB2 + * 3.3.5.15.6). Reject a short backward copy because the rewind + * below only supports forward copying. + */ + if (unlikely(reverse && bytes_written < copy_bytes)) { + cifs_tcon_dbg(VFS, "Copychunk short write %u/%u (reverse)\n", + bytes_written, copy_bytes); + rc = -EIO; + goto out; + } + /* Partial write: rewind */ if (bytes_written < copy_bytes) { u32 delta = copy_bytes - bytes_written; @@ -2064,10 +2125,27 @@ out: trace_smb3_copychunk_done(xid, src_file->fid.volatile_fid, dst_file->fid.volatile_fid, tcon->tid, tcon->ses->Suid, src_off, dst_off, len); - return len; + return 0; } } +static ssize_t +smb2_copychunk_range(const unsigned int xid, + struct cifsFileInfo *src_file, + struct cifsFileInfo *dst_file, + u64 src_off, + u64 len, + u64 dst_off) +{ + int rc; + + rc = __smb2_copychunk_range(xid, src_file, dst_file, src_off, len, + dst_off); + if (rc) + return rc; + return len; +} + static int smb2_flush_file(const unsigned int xid, struct cifs_tcon *tcon, struct cifs_fid *fid) @@ -3441,6 +3519,13 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon, trace_smb3_zero_enter(xid, cfile->fid.persistent_fid, tcon->tid, ses->Suid, offset, len); + new_size = offset + len; + if (!keep_size && i_size_read(inode) < new_size) { + rc = inode_newsize_ok(inode, new_size); + if (rc) + goto out; + } + filemap_invalidate_lock(inode->i_mapping); netfs_read_sizes(inode, &i_size, &remote_i_size, &zero_point); @@ -3464,6 +3549,9 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon, if (keep_size == false && !CIFS_CACHE_READ(cifsi)) goto zero_range_exit; + fscache_invalidate(cifs_inode_cookie(inode), NULL, + i_size_read(inode), 0); + rc = smb3_zero_data(file, tcon, offset, len, xid); if (rc < 0) goto zero_range_exit; @@ -3471,7 +3559,6 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon, /* * do we also need to change the size of the file? */ - new_size = offset + len; if (keep_size == false && (unsigned long long)i_size_read(inode) < new_size) { rc = SMB2_set_eof(xid, tcon, cfile->fid.persistent_fid, cfile->fid.volatile_fid, cfile->pid, new_size); @@ -3488,6 +3575,7 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon, zero_range_exit: filemap_invalidate_unlock(inode->i_mapping); + out: free_xid(xid); if (rc) trace_smb3_zero_err(xid, cfile->fid.persistent_fid, tcon->tid, @@ -3533,6 +3621,8 @@ static long smb3_punch_hole(struct file *file, struct cifs_tcon *tcon, */ truncate_pagecache_range(inode, offset, offset + len - 1); netfs_wait_for_outstanding_io(inode); + fscache_invalidate(cifs_inode_cookie(inode), NULL, + i_size_read(inode), 0); cifs_dbg(FYI, "Offset %lld len %lld\n", offset, len); @@ -3938,18 +4028,26 @@ static long smb3_collapse_range(struct file *file, struct cifs_tcon *tcon, } filemap_invalidate_lock(inode->i_mapping); - rc = filemap_write_and_wait_range(inode->i_mapping, off, old_eof - 1); + rc = filemap_write_and_wait_range(inode->i_mapping, + round_down(off, PAGE_SIZE), + old_eof - 1); if (rc < 0) goto out_2; - truncate_pagecache_range(inode, off, old_eof); + netfs_wait_for_outstanding_io(inode); + /* + * Invalidate cached folios from the page containing off to EOF before + * moving data on the server, so subsequent reads do not see stale data. + */ + truncate_pagecache_range(inode, round_down(off, PAGE_SIZE), -1); + fscache_invalidate(cifs_inode_cookie(inode), NULL, old_eof, 0); + spin_lock(&inode->i_lock); netfs_write_zero_point(inode, old_eof); spin_unlock(&inode->i_lock); - netfs_wait_for_outstanding_io(inode); - rc = smb2_copychunk_range(xid, cfile, cfile, off + len, - old_eof - off - len, off); + rc = __smb2_copychunk_range(xid, cfile, cfile, off + len, + old_eof - off - len, off); if (rc < 0) goto out_2; @@ -3982,7 +4080,7 @@ static long smb3_insert_range(struct file *file, struct cifs_tcon *tcon, struct cifsFileInfo *cfile = file->private_data; struct inode *inode = file_inode(file); struct cifsInodeInfo *cifsi = CIFS_I(inode); - __u64 count, old_eof, new_eof; + loff_t old_eof, new_eof; xid = get_xid(); @@ -3992,15 +4090,32 @@ static long smb3_insert_range(struct file *file, struct cifs_tcon *tcon, goto out; } - count = old_eof - off; - new_eof = old_eof + len; + if (check_add_overflow(old_eof, len, &new_eof)) { + rc = -EFBIG; + goto out; + } + rc = inode_newsize_ok(inode, new_eof); + if (rc) + goto out; + + /* SET_ZERO_DATA creates a hole only in a sparse file. */ + rc = smb2_set_sparse(xid, tcon, cfile, inode, true); + if (rc) + goto out; filemap_invalidate_lock(inode->i_mapping); - rc = filemap_write_and_wait_range(inode->i_mapping, off, new_eof - 1); + rc = filemap_write_and_wait_range(inode->i_mapping, + round_down(off, PAGE_SIZE), + old_eof - 1); if (rc < 0) goto out_2; - truncate_pagecache_range(inode, off, old_eof); netfs_wait_for_outstanding_io(inode); + /* + * Invalidate cached folios from the page containing off to EOF before + * moving data on the server, so subsequent reads do not see stale data. + */ + truncate_pagecache_range(inode, round_down(off, PAGE_SIZE), -1); + fscache_invalidate(cifs_inode_cookie(inode), NULL, old_eof, 0); rc = SMB2_set_eof(xid, tcon, cfile->fid.persistent_fid, cfile->fid.volatile_fid, cfile->pid, new_eof); @@ -4013,7 +4128,12 @@ static long smb3_insert_range(struct file *file, struct cifs_tcon *tcon, spin_unlock(&inode->i_lock); fscache_resize_cookie(cifs_inode_cookie(inode), i_size_read(inode)); - rc = smb2_copychunk_range(xid, cfile, cfile, off, count, off + len); + /* + * Move [off, old_eof) right by len. The helper copies backwards if the + * source and destination ranges overlap. + */ + rc = __smb2_copychunk_range(xid, cfile, cfile, off, old_eof - off, + off + len); if (rc < 0) goto out_2; spin_lock(&inode->i_lock); diff --git a/fs/smb/client/trace.h b/fs/smb/client/trace.h index 12241abb8e2ebc..b442cccd153085 100644 --- a/fs/smb/client/trace.h +++ b/fs/smb/client/trace.h @@ -79,6 +79,7 @@ EM(smb_eio_trace_qreparse_setup_count, "qreparse_setup_count") \ EM(smb_eio_trace_qreparse_sizes_wrong, "qreparse_sizes_wrong") \ EM(smb_eio_trace_qsym_bcc_too_small, "qsym_bcc_too_small") \ + EM(smb_eio_trace_read_bad_offset, "read_bad_offset") \ EM(smb_eio_trace_read_mid_state_unknown, "read_mid_state_unknown") \ EM(smb_eio_trace_read_overlarge, "read_overlarge") \ EM(smb_eio_trace_read_rsp_malformed, "read_rsp_malformed") \ diff --git a/fs/smb/client/transport.c b/fs/smb/client/transport.c index fdf4e50c27ceb4..e266859818a441 100644 --- a/fs/smb/client/transport.c +++ b/fs/smb/client/transport.c @@ -101,12 +101,11 @@ void __release_mid(struct TCP_Server_Info *server, struct mid_q_entry *midEntry) trace_smb3_slow_rsp(smb_cmd, midEntry->mid, midEntry->pid, midEntry->when_sent, midEntry->when_received); if (cifsFYI & CIFS_TIMER) { - pr_debug("slow rsp: cmd %d mid %llu", - midEntry->command, midEntry->mid); - cifs_info("A: 0x%lx S: 0x%lx R: 0x%lx\n", - now - midEntry->when_alloc, - now - midEntry->when_sent, - now - midEntry->when_received); + pr_debug("slow rsp: cmd %d mid %llu A: 0x%lx S: 0x%lx R: 0x%lx\n", + midEntry->command, midEntry->mid, + now - midEntry->when_alloc, + now - midEntry->when_sent, + now - midEntry->when_received); } } #endif diff --git a/fs/smb/server/connection.c b/fs/smb/server/connection.c index af73c2ed5d249f..39ac777fd45270 100644 --- a/fs/smb/server/connection.c +++ b/fs/smb/server/connection.c @@ -13,6 +13,7 @@ #include "mgmt/ksmbd_ida.h" #include "mgmt/user_session.h" #include "connection.h" +#include "vfs_cache.h" #include "compress.h" #include "transport_tcp.h" #include "transport_rdma.h" @@ -294,6 +295,26 @@ void ksmbd_conn_try_dequeue_request(struct ksmbd_work *work) wake_up_all(&conn->req_running_q); } +static void ksmbd_conn_cancel_async_requests(struct ksmbd_conn *conn) +{ + struct ksmbd_work *work, *tmp; + + ksmbd_debug(CONN, "Cancel pending async requests on releasing connection\n"); + spin_lock(&conn->request_lock); + list_for_each_entry_safe(work, tmp, &conn->async_requests, + async_request_entry) { + if (cmpxchg(&work->state, KSMBD_WORK_ACTIVE, + KSMBD_WORK_CANCELLED) != KSMBD_WORK_ACTIVE) + continue; + + ksmbd_debug(CONN, "Cancel async request id %d\n", + work->async_id); + if (work->cancel_fn) + work->cancel_fn(work->cancel_argv); + } + spin_unlock(&conn->request_lock); +} + void ksmbd_conn_lock(struct ksmbd_conn *conn) { mutex_lock(&conn->srv_mutex); @@ -371,6 +392,9 @@ retry_idle: if (retry_count >= max_timeout) return -EIO; + /* A blocked byte-range lock cannot drain until teardown wakes it. */ + ksmbd_wake_session_blocked_works(sess); + down_read(&conn_list_lock); hash_for_each(conn_list, bkt, conn, hlist) { if (ksmbd_session_is_bound_to_conn(sess, conn)) { @@ -608,6 +632,7 @@ recheck: } ksmbd_conn_set_releasing(conn); + ksmbd_conn_cancel_async_requests(conn); /* Wait till all reference dropped to the Server object*/ ksmbd_debug(CONN, "Wait for all pending requests(%d)\n", atomic_read(&conn->r_count)); wait_event(conn->r_count_q, atomic_read(&conn->r_count) == 0); diff --git a/fs/smb/server/ksmbd_work.h b/fs/smb/server/ksmbd_work.h index 5f1d3ebab4fb5a..0844aa929f55da 100644 --- a/fs/smb/server/ksmbd_work.h +++ b/fs/smb/server/ksmbd_work.h @@ -82,7 +82,7 @@ struct ksmbd_work { /* Contiguous SMB2 compression transform owned by this work item. */ void *compress_buf; - unsigned char state; + unsigned int state; /* No response for cancelled request */ bool send_no_response:1; /* Request is encrypted */ diff --git a/fs/smb/server/mgmt/user_session.c b/fs/smb/server/mgmt/user_session.c index d91dde3f9e6197..10b31df185a601 100644 --- a/fs/smb/server/mgmt/user_session.c +++ b/fs/smb/server/mgmt/user_session.c @@ -650,10 +650,21 @@ void destroy_previous_session(struct ksmbd_conn *conn, memcmp(user->passkey, prev_user->passkey, user->passkey_sz)) goto out; + down_write(&prev_sess->chann_lock); + if (prev_sess->tearing_down) { + up_write(&prev_sess->chann_lock); + goto out; + } + prev_sess->tearing_down = true; + up_write(&prev_sess->chann_lock); + ksmbd_all_conn_set_status(prev_sess, KSMBD_SESS_NEED_RECONNECT); err = ksmbd_conn_wait_idle_sess(conn, prev_sess); if (err) { - ksmbd_all_conn_set_status(prev_sess, KSMBD_SESS_NEED_SETUP); + down_write(&prev_sess->chann_lock); + prev_sess->tearing_down = false; + up_write(&prev_sess->chann_lock); + ksmbd_all_conn_set_status(prev_sess, KSMBD_SESS_GOOD); goto out; } diff --git a/fs/smb/server/mgmt/user_session.h b/fs/smb/server/mgmt/user_session.h index f8a24c33f7fe43..3e52d4cc132472 100644 --- a/fs/smb/server/mgmt/user_session.h +++ b/fs/smb/server/mgmt/user_session.h @@ -42,6 +42,7 @@ struct ksmbd_session { bool sign; bool enc; + bool tearing_down; int state; __u8 *Preauth_HashValue; diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 4cf7083f35ccdf..184b28072a6f04 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -95,6 +95,11 @@ static int register_session_channel(struct ksmbd_session *sess, int rc = 0; down_write(&sess->chann_lock); + if (sess->tearing_down) { + rc = -ESHUTDOWN; + goto out; + } + if (xa_load(&sess->ksmbd_chann_list, (long)conn)) goto out; @@ -2812,17 +2817,41 @@ int smb2_session_logoff(struct ksmbd_work *work) smb2_set_err_rsp(work); return -ENOENT; } + + down_write(&sess->chann_lock); + if (sess->tearing_down) { + up_write(&sess->chann_lock); + ksmbd_conn_unlock(conn); + rsp->hdr.Status = STATUS_USER_SESSION_DELETED; + smb2_set_err_rsp(work); + return -ENOENT; + } + sess->tearing_down = true; + up_write(&sess->chann_lock); + ksmbd_all_conn_set_status(sess, KSMBD_SESS_NEED_RECONNECT); ksmbd_conn_unlock(conn); + err = ksmbd_conn_wait_idle_sess(conn, sess); + if (err) { + down_write(&sess->chann_lock); + sess->tearing_down = false; + up_write(&sess->chann_lock); + ksmbd_all_conn_set_status(sess, KSMBD_SESS_GOOD); + rsp->hdr.Status = STATUS_UNEXPECTED_IO_ERROR; + smb2_set_err_rsp(work); + return err; + } + ksmbd_close_session_fds(work); - ksmbd_conn_wait_idle(conn); if (ksmbd_tree_conn_session_logoff(sess)) { ksmbd_debug(SMB, "Invalid tid %d\n", req->hdr.Id.SyncId.TreeId); rsp->hdr.Status = STATUS_NETWORK_NAME_DELETED; smb2_set_err_rsp(work); - return -ENOENT; + err = -ENOENT; + } else { + err = 0; } down_write(&conn->session_lock); @@ -2832,6 +2861,9 @@ int smb2_session_logoff(struct ksmbd_work *work) ksmbd_all_conn_set_status(sess, KSMBD_SESS_NEED_SETUP); + if (err) + return err; + rsp->StructureSize = cpu_to_le16(4); err = ksmbd_iov_pin_rsp(work, rsp, sizeof(struct smb2_logoff_rsp)); if (err) { @@ -8488,14 +8520,14 @@ int smb2_cancel(struct ksmbd_work *work) * still on conn->async_requests with a live cancel_fn * pointing at the freed file_lock. */ - if (iter->state != KSMBD_WORK_ACTIVE) + if (cmpxchg(&iter->state, KSMBD_WORK_ACTIVE, + KSMBD_WORK_CANCELLED) != KSMBD_WORK_ACTIVE) break; ksmbd_debug(SMB, "smb2 with AsyncId %llu cancelled command = 0x%x\n", le64_to_cpu(hdr->Id.AsyncId), le16_to_cpu(chdr->Command)); - iter->state = KSMBD_WORK_CANCELLED; if (iter->cancel_fn == smb2_notify_cancel_fn) cancelled_notify = smb2_notify_cancel_claim(iter->cancel_argv); @@ -8524,11 +8556,16 @@ int smb2_cancel(struct ksmbd_work *work) iter == work) continue; + if (cmpxchg(&iter->state, KSMBD_WORK_ACTIVE, + KSMBD_WORK_CANCELLED) != KSMBD_WORK_ACTIVE) + break; + ksmbd_debug(SMB, "smb2 with mid %llu cancelled command = 0x%x\n", le64_to_cpu(hdr->MessageId), le16_to_cpu(chdr->Command)); - iter->state = KSMBD_WORK_CANCELLED; + if (iter->cancel_fn) + iter->cancel_fn(iter->cancel_argv); break; } spin_unlock(&conn->request_lock); diff --git a/fs/smb/server/smbacl.c b/fs/smb/server/smbacl.c index 33825c1356b477..ae1527aa626974 100644 --- a/fs/smb/server/smbacl.c +++ b/fs/smb/server/smbacl.c @@ -380,10 +380,10 @@ void free_acl_state(struct posix_acl_state *state) kfree(state->groups); } -static void parse_dacl(struct mnt_idmap *idmap, - struct smb_acl *pdacl, char *end_of_acl, - struct smb_sid *pownersid, struct smb_sid *pgrpsid, - struct smb_fattr *fattr) +static int parse_dacl(struct mnt_idmap *idmap, + struct smb_acl *pdacl, char *end_of_acl, + struct smb_sid *pownersid, struct smb_sid *pgrpsid, + struct smb_fattr *fattr) { int i, ret; u16 num_aces = 0; @@ -397,13 +397,13 @@ static void parse_dacl(struct mnt_idmap *idmap, bool owner_found = false, group_found = false, others_found = false; if (!pdacl) - return; + return 0; /* validate that we do not go past end of acl */ if (end_of_acl < (char *)pdacl + sizeof(struct smb_acl) || end_of_acl < (char *)pdacl + le16_to_cpu(pdacl->size)) { pr_err("ACL too small to parse DACL\n"); - return; + return -EINVAL; } ksmbd_debug(SMB, "DACL revision %d size %d num aces %d\n", @@ -415,31 +415,31 @@ static void parse_dacl(struct mnt_idmap *idmap, num_aces = le16_to_cpu(pdacl->num_aces); if (num_aces <= 0) - return; + return 0; dacl_size = le16_to_cpu(pdacl->size); if (dacl_size < sizeof(struct smb_acl)) - return; + return -EINVAL; if (num_aces > (dacl_size - sizeof(struct smb_acl)) / (offsetof(struct smb_ace, sid) + offsetof(struct smb_sid, sub_auth) + sizeof(__le16))) - return; + return -EINVAL; ret = init_acl_state(&acl_state, num_aces); if (ret) - return; + return ret; ret = init_acl_state(&default_acl_state, num_aces); if (ret) { free_acl_state(&acl_state); - return; + return ret; } ppace = kmalloc_objs(struct smb_ace *, num_aces, KSMBD_DEFAULT_GFP); if (!ppace) { free_acl_state(&default_acl_state); free_acl_state(&acl_state); - return; + return -ENOMEM; } /* @@ -448,8 +448,10 @@ static void parse_dacl(struct mnt_idmap *idmap, * user/group/other have no permissions */ for (i = 0; i < num_aces; ++i) { - if (end_of_acl - acl_base < acl_size) - break; + if (end_of_acl - acl_base < acl_size) { + ret = -EINVAL; + goto out; + } ppace[i] = (struct smb_ace *)(acl_base + acl_size); acl_base = (char *)ppace[i]; @@ -462,8 +464,10 @@ static void parse_dacl(struct mnt_idmap *idmap, (end_of_acl - acl_base < acl_size + sizeof(__le32) * ppace[i]->sid.num_subauth) || (le16_to_cpu(ppace[i]->size) < - acl_size + sizeof(__le32) * ppace[i]->sid.num_subauth)) - break; + acl_size + sizeof(__le32) * ppace[i]->sid.num_subauth)) { + ret = -EINVAL; + goto out; + } acl_size = le16_to_cpu(ppace[i]->size); ppace[i]->access_req = @@ -521,8 +525,8 @@ static void parse_dacl(struct mnt_idmap *idmap, temp_fattr.cf_uid = INVALID_UID; ret = sid_to_id(idmap, &ppace[i]->sid, SIDOWNER, &temp_fattr); if (ret || uid_eq(temp_fattr.cf_uid, INVALID_UID)) { - pr_err("%s: Error %d mapping Owner SID to uid\n", - __func__, ret); + pr_err_ratelimited("%s: Error %d mapping Owner SID to uid\n", + __func__, ret); continue; } @@ -538,7 +542,6 @@ static void parse_dacl(struct mnt_idmap *idmap, ((acl_mode & 0700) >> 6) | 0004; } } - kfree(ppace); if (owner_found) { /* The owner must be set to at least read-only. */ @@ -581,10 +584,12 @@ static void parse_dacl(struct mnt_idmap *idmap, fattr->cf_acls = posix_acl_alloc(acl_state.users->n + acl_state.groups->n + 4, KSMBD_DEFAULT_GFP); - if (fattr->cf_acls) { - cf_pace = fattr->cf_acls->a_entries; - posix_state_to_acl(&acl_state, cf_pace); + if (!fattr->cf_acls) { + ret = -ENOMEM; + goto out; } + cf_pace = fattr->cf_acls->a_entries; + posix_state_to_acl(&acl_state, cf_pace); } } @@ -595,14 +600,20 @@ static void parse_dacl(struct mnt_idmap *idmap, fattr->cf_dacls = posix_acl_alloc(default_acl_state.users->n + default_acl_state.groups->n + 4, KSMBD_DEFAULT_GFP); - if (fattr->cf_dacls) { - cf_pdace = fattr->cf_dacls->a_entries; - posix_state_to_acl(&default_acl_state, cf_pdace); + if (!fattr->cf_dacls) { + ret = -ENOMEM; + goto out; } + cf_pdace = fattr->cf_dacls->a_entries; + posix_state_to_acl(&default_acl_state, cf_pdace); } } + ret = 0; +out: + kfree(ppace); free_acl_state(&acl_state); free_acl_state(&default_acl_state); + return ret; } static void set_posix_acl_entries_dacl(struct mnt_idmap *idmap, @@ -963,8 +974,10 @@ int parse_sec_desc(struct mnt_idmap *idmap, struct smb_ntsd *pntsd, if (dacloffset < sizeof(struct smb_ntsd)) return -EINVAL; - parse_dacl(idmap, dacl_ptr, end_of_acl, - owner_sid_ptr, group_sid_ptr, fattr); + rc = parse_dacl(idmap, dacl_ptr, end_of_acl, + owner_sid_ptr, group_sid_ptr, fattr); + if (rc) + return rc; } return 0; diff --git a/fs/smb/server/transport_tcp.c b/fs/smb/server/transport_tcp.c index 990b14e5d3ea23..668fc333c5be3e 100644 --- a/fs/smb/server/transport_tcp.c +++ b/fs/smb/server/transport_tcp.c @@ -39,6 +39,7 @@ struct tcp_transport { static const struct ksmbd_transport_ops ksmbd_tcp_transport_ops; static void tcp_stop_kthread(struct task_struct *kthread); +static void ksmbd_tcp_stop_listener(struct interface *iface); static struct interface *alloc_iface(char *ifname); static void ksmbd_tcp_disconnect(struct ksmbd_transport *t); @@ -315,13 +316,20 @@ static int ksmbd_tcp_run_kthread(struct interface *iface) int rc; struct task_struct *kthread; - kthread = kthread_run(ksmbd_kthread_fn, (void *)iface, "ksmbd-%s", - iface->name); + kthread = kthread_create(ksmbd_kthread_fn, (void *)iface, "ksmbd-%s", + iface->name); if (IS_ERR(kthread)) { rc = PTR_ERR(kthread); return rc; } + + /* + * The listener can exit after its socket is shutdown, so keep the + * task_struct alive until the caller has stopped it. + */ + get_task_struct(kthread); iface->ksmbd_kthread = kthread; + wake_up_process(kthread); return 0; } @@ -585,12 +593,7 @@ static int ksmbd_netdev_event(struct notifier_block *nb, unsigned long event, if (iface && iface->state == IFACE_STATE_CONFIGURED) { ksmbd_debug(CONN, "netdev-down event: netdev(%s) is going down\n", iface->name); - kernel_sock_shutdown(iface->ksmbd_socket, SHUT_RDWR); - tcp_stop_kthread(iface->ksmbd_kthread); - iface->ksmbd_kthread = NULL; - sock_release(iface->ksmbd_socket); - iface->ksmbd_socket = NULL; - + ksmbd_tcp_stop_listener(iface); iface->state = IFACE_STATE_DOWN; break; } @@ -618,11 +621,25 @@ static void tcp_stop_kthread(struct task_struct *kthread) if (!kthread) return; - ret = kthread_stop(kthread); + ret = kthread_stop_put(kthread); if (ret) pr_err("failed to stop forker thread\n"); } +static void ksmbd_tcp_stop_listener(struct interface *iface) +{ + if (iface->ksmbd_socket) + kernel_sock_shutdown(iface->ksmbd_socket, SHUT_RDWR); + + tcp_stop_kthread(iface->ksmbd_kthread); + iface->ksmbd_kthread = NULL; + + if (iface->ksmbd_socket) { + sock_release(iface->ksmbd_socket); + iface->ksmbd_socket = NULL; + } +} + void ksmbd_tcp_destroy(void) { struct interface *iface, *tmp; @@ -630,6 +647,7 @@ void ksmbd_tcp_destroy(void) unregister_netdevice_notifier(&ksmbd_netdev_notifier); list_for_each_entry_safe(iface, tmp, &iface_list, entry) { + ksmbd_tcp_stop_listener(iface); list_del(&iface->entry); kfree(iface->name); kfree(iface); diff --git a/fs/smb/server/vfs_cache.c b/fs/smb/server/vfs_cache.c index 293dab9b43be17..a23bd9b1a68bc3 100644 --- a/fs/smb/server/vfs_cache.c +++ b/fs/smb/server/vfs_cache.c @@ -727,12 +727,25 @@ static void set_close_state_blocked_works(struct ksmbd_file *fp) spin_lock(&fp->f_lock); list_for_each_entry(cancel_work, &fp->blocked_works, fp_entry) { - cancel_work->state = KSMBD_WORK_CLOSED; - cancel_work->cancel_fn(cancel_work->cancel_argv); + if (xchg(&cancel_work->state, KSMBD_WORK_CLOSED) == + KSMBD_WORK_ACTIVE) + cancel_work->cancel_fn(cancel_work->cancel_argv); } spin_unlock(&fp->f_lock); } +void ksmbd_wake_session_blocked_works(struct ksmbd_session *sess) +{ + struct ksmbd_file_table *ft = &sess->file_table; + struct ksmbd_file *fp; + unsigned int id; + + read_lock(&ft->lock); + idr_for_each_entry(ft->idr, fp, id) + set_close_state_blocked_works(fp); + read_unlock(&ft->lock); +} + int ksmbd_close_fd(struct ksmbd_work *work, u64 id) { struct ksmbd_file *fp; diff --git a/fs/smb/server/vfs_cache.h b/fs/smb/server/vfs_cache.h index 8bb4396f952386..d6a9cd4b6d5634 100644 --- a/fs/smb/server/vfs_cache.h +++ b/fs/smb/server/vfs_cache.h @@ -211,6 +211,7 @@ void ksmbd_launch_ksmbd_durable_scavenger(void); void ksmbd_stop_durable_scavenger(void); void ksmbd_close_tree_conn_fds(struct ksmbd_work *work); void ksmbd_close_session_fds(struct ksmbd_work *work); +void ksmbd_wake_session_blocked_works(struct ksmbd_session *sess); int ksmbd_close_inode_fds(struct ksmbd_work *work, struct inode *inode); int ksmbd_init_global_file_table(void); void ksmbd_free_global_file_table(void); diff --git a/fs/super.c b/fs/super.c index d94f3a3e988df7..1159a73856db61 100644 --- a/fs/super.c +++ b/fs/super.c @@ -2122,11 +2122,14 @@ static int thaw_super_locked(struct super_block *sb, enum freeze_holder who, goto out_unlock; /* - * All freezers share a single active reference. - * So just unlock in case there are any left. + * All freezers share a single active reference. If other freezers + * remain, drop our hold and report success; the superblock stays + * frozen until the last holder thaws it. */ - if (freeze_dec(sb, who)) + if (freeze_dec(sb, who)) { + error = 0; goto out_unlock; + } if (sb_rdonly(sb)) { sb->s_writers.frozen = SB_UNFROZEN; diff --git a/fs/ufs/cylinder.c b/fs/ufs/cylinder.c index a2813270c303ed..b930ee1cf85307 100644 --- a/fs/ufs/cylinder.c +++ b/fs/ufs/cylinder.c @@ -68,6 +68,16 @@ static bool ufs_read_cylinder(struct super_block *sb, ucpi->c_clustersumoff = fs32_to_cpu(sb, ucg->cg_u.cg_44.cg_clustersumoff); ucpi->c_clusteroff = fs32_to_cpu(sb, ucg->cg_u.cg_44.cg_clusteroff); ucpi->c_nclusterblks = fs32_to_cpu(sb, ucg->cg_u.cg_44.cg_nclusterblks); + + /* these on-disk values become array and bitmap indices */ + if (ucpi->c_cgx != cgno || + ucpi->c_rotor >= uspi->s_fpg || + ucpi->c_frotor >= uspi->s_fpg || + ucpi->c_irotor >= uspi->s_ipg) { + ufs_error(sb, __func__, + "inconsistent metadata in cylinder group %u\n", cgno); + goto failed; + } UFSD("EXIT\n"); return true; diff --git a/fs/ufs/dir.c b/fs/ufs/dir.c index e62fe566767107..ce43cf20b07c98 100644 --- a/fs/ufs/dir.c +++ b/fs/ufs/dir.c @@ -590,7 +590,7 @@ int ufs_empty_dir(struct inode * inode) kaddr = ufs_get_folio(inode, i, &folio); if (IS_ERR(kaddr)) - continue; + return 0; de = (struct ufs_dir_entry *)kaddr; kaddr += ufs_last_byte(inode, i) - UFS_DIR_REC_LEN(1); diff --git a/fs/ufs/super.c b/fs/ufs/super.c index c4831a8b9b3fb1..7deecb3954e234 100644 --- a/fs/ufs/super.c +++ b/fs/ufs/super.c @@ -1199,6 +1199,15 @@ magic_found: sb->s_maxbytes = ufs_max_bytes(sb); sb->s_max_links = UFS_LINK_MAX; + ufs_setup_cstotal(sb); + /* + * Read cylinder group structures + */ + if (!sb_rdonly(sb)) + if (!ufs_read_cylinder_structures(sb)) + goto failed; + + /* create the root dentry last, once UFS_SB(sb) is fully set up */ inode = ufs_iget(sb, UFS_ROOTINO); if (IS_ERR(inode)) { ret = PTR_ERR(inode); @@ -1210,14 +1219,6 @@ magic_found: goto failed; } - ufs_setup_cstotal(sb); - /* - * Read cylinder group structures - */ - if (!sb_rdonly(sb)) - if (!ufs_read_cylinder_structures(sb)) - goto failed; - UFSD("EXIT\n"); return 0; diff --git a/fs/xfs/libxfs/xfs_btree_mem.c b/fs/xfs/libxfs/xfs_btree_mem.c index 37136a70e56d66..1d83a4251ceeb6 100644 --- a/fs/xfs/libxfs/xfs_btree_mem.c +++ b/fs/xfs/libxfs/xfs_btree_mem.c @@ -117,6 +117,7 @@ xfbtree_init( struct xfs_buftarg *btp, const struct xfs_btree_ops *ops) { + unsigned long long owner = xfbt->owner; unsigned int blocklen = xfbtree_rec_bytes(mp, ops); unsigned int keyptr_len; int error; @@ -133,6 +134,7 @@ xfbtree_init( memset(xfbt, 0, sizeof(*xfbt)); xfbt->target = btp; + xfbt->owner = owner; /* Set up min/maxrecs for this btree. */ keyptr_len = ops->key_len + sizeof(__be64); diff --git a/fs/xfs/libxfs/xfs_btree_staging.c b/fs/xfs/libxfs/xfs_btree_staging.c index c3c7ea54895a60..c5b7613e5216ab 100644 --- a/fs/xfs/libxfs/xfs_btree_staging.c +++ b/fs/xfs/libxfs/xfs_btree_staging.c @@ -337,8 +337,10 @@ xfs_btree_bload_prep_block( xfs_btree_set_sibling(cur, *blockp, &new_ptr, XFS_BB_RIGHTSIB); ret = xfs_btree_bload_drop_buf(bbl, buffers_list, bpp); - if (ret) + if (ret) { + xfs_buf_relse(new_bp); return ret; + } /* Initialize the new btree block. */ xfs_btree_init_block_cur(cur, new_bp, level, nr_this_block); diff --git a/fs/xfs/libxfs/xfs_da_btree.c b/fs/xfs/libxfs/xfs_da_btree.c index 9debb95d86fa07..98f02d68e938f9 100644 --- a/fs/xfs/libxfs/xfs_da_btree.c +++ b/fs/xfs/libxfs/xfs_da_btree.c @@ -130,7 +130,7 @@ xfs_da_state_reset( state->mp = state->args->dp->i_mount; } -static inline int xfs_dabuf_nfsb(struct xfs_mount *mp, int whichfork) +inline int xfs_dabuf_nfsb(struct xfs_mount *mp, int whichfork) { if (whichfork == XFS_DATA_FORK) return mp->m_dir_geo->fsbcount; diff --git a/fs/xfs/libxfs/xfs_da_btree.h b/fs/xfs/libxfs/xfs_da_btree.h index afcf2d3c7a21c0..a718b1ceb0aab7 100644 --- a/fs/xfs/libxfs/xfs_da_btree.h +++ b/fs/xfs/libxfs/xfs_da_btree.h @@ -244,4 +244,6 @@ xfs_failaddr_t xfs_da3_node_header_check(struct xfs_buf *bp, xfs_ino_t owner); extern struct kmem_cache *xfs_da_state_cache; +int xfs_dabuf_nfsb(struct xfs_mount *mp, int whichfork); + #endif /* __XFS_DA_BTREE_H__ */ diff --git a/fs/xfs/libxfs/xfs_defer.c b/fs/xfs/libxfs/xfs_defer.c index 89501e8bd2f845..843c3330444150 100644 --- a/fs/xfs/libxfs/xfs_defer.c +++ b/fs/xfs/libxfs/xfs_defer.c @@ -583,7 +583,7 @@ xfs_defer_finish_one( const struct xfs_defer_op_type *ops = dfp->dfp_ops; struct xfs_btree_cur *state = NULL; struct list_head *li, *n; - int error; + int error = 0; trace_xfs_defer_pending_finish(tp->t_mountp, dfp); diff --git a/fs/xfs/libxfs/xfs_exchmaps.c b/fs/xfs/libxfs/xfs_exchmaps.c index 3efed37cb98a8f..49eda8d0994dee 100644 --- a/fs/xfs/libxfs/xfs_exchmaps.c +++ b/fs/xfs/libxfs/xfs_exchmaps.c @@ -959,6 +959,16 @@ xmi_can_exchange_reflink_flags( { struct xfs_mount *mp = req->ip1->i_mount; + /* + * The INO1_WRITTEN optimization can skip exchanging hole and + * unwritten mappings, which means we cannot guarantee that all + * shared extents actually moved to the other file. Clearing the + * reflink flag of an inode that still holds shared extents breaks + * the CoW write path, so refuse to exchange the flags in that case. + */ + if (req->flags & XFS_EXCHMAPS_INO1_WRITTEN) + return false; + /* * The INO1_WRITTEN optimization can skip exchanging hole and * unwritten mappings, which means we cannot guarantee that all diff --git a/fs/xfs/libxfs/xfs_parent.c b/fs/xfs/libxfs/xfs_parent.c index 8d111c9b6527ee..a2f2f5fa640e41 100644 --- a/fs/xfs/libxfs/xfs_parent.c +++ b/fs/xfs/libxfs/xfs_parent.c @@ -193,7 +193,7 @@ xfs_parent_addname( const struct xfs_name *parent_name, struct xfs_inode *child) { - int error; + int error, local; error = xfs_parent_iread_extents(tp, child); if (error) @@ -203,6 +203,10 @@ xfs_parent_addname( xfs_parent_da_args_init(&ppargs->args, tp, &ppargs->rec, child, I_INO(child), parent_name); + /* Growing the attr fork needs a real reservation in args->total. */ + ppargs->args.total = xfs_attr_calc_size(&ppargs->args, &local); + ASSERT(local); + return xfs_attr_setname(&ppargs->args, 0); } @@ -239,7 +243,7 @@ xfs_parent_replacename( const struct xfs_name *new_name, struct xfs_inode *child) { - int error; + int error, local; error = xfs_parent_iread_extents(tp, child); if (error) @@ -249,6 +253,10 @@ xfs_parent_replacename( xfs_parent_da_args_init(&ppargs->args, tp, &ppargs->rec, child, I_INO(child), old_name); + /* Growing the attr fork needs a real reservation in args->total. */ + ppargs->args.total = xfs_attr_calc_size(&ppargs->args, &local); + ASSERT(local); + xfs_inode_to_parent_rec(&ppargs->new_rec, new_dp); ppargs->args.new_name = new_name->name; diff --git a/fs/xfs/libxfs/xfs_rtrefcount_btree.c b/fs/xfs/libxfs/xfs_rtrefcount_btree.c index 22acc1411aacd8..e2950dbe20681b 100644 --- a/fs/xfs/libxfs/xfs_rtrefcount_btree.c +++ b/fs/xfs/libxfs/xfs_rtrefcount_btree.c @@ -489,8 +489,11 @@ xfs_rtrefcountbt_maxlevels_ondisk(void) minrecs[0] = xfs_rtrefcountbt_block_maxrecs(blocklen, true) / 2; minrecs[1] = xfs_rtrefcountbt_block_maxrecs(blocklen, false) / 2; - /* We need at most one record for every block in an rt group. */ - return xfs_btree_compute_maxlevels(minrecs, XFS_MAX_RGBLOCKS); + /* + * We need at most one record for every block in an rt group, and + * one extra level for the inode root. + */ + return xfs_btree_compute_maxlevels(minrecs, XFS_MAX_RGBLOCKS) + 1; } int __init diff --git a/fs/xfs/libxfs/xfs_rtrmap_btree.c b/fs/xfs/libxfs/xfs_rtrmap_btree.c index c264bc5651c0a6..a15e460a1ec7f4 100644 --- a/fs/xfs/libxfs/xfs_rtrmap_btree.c +++ b/fs/xfs/libxfs/xfs_rtrmap_btree.c @@ -618,7 +618,7 @@ xfs_rtrmapbt_mem_cursor( struct xfs_btree_cur *cur; cur = xfs_btree_alloc_cursor(mp, tp, &xfs_rtrmapbt_mem_ops, - mp->m_rtrmap_maxlevels, xfs_rtrmapbt_cur_cache); + xfs_rtrmapbt_maxlevels_ondisk(), xfs_rtrmapbt_cur_cache); cur->bc_mem.xfbtree = xfbt; cur->bc_nlevels = xfbt->nlevels; cur->bc_group = xfs_group_hold(rtg_group(rtg)); @@ -716,10 +716,12 @@ xfs_rtrmapbt_maxlevels_ondisk(void) * happens, which means that we must compute the max height based on * what the btree will look like if it consumes almost all the blocks * in the data device due to maximal sharing factor. + * + * Add one extra level for the inode root. */ max_dblocks = -1U; /* max ag count */ max_dblocks *= XFS_MAX_CRC_AG_BLOCKS; - return xfs_btree_space_to_height(minrecs, max_dblocks); + return xfs_btree_space_to_height(minrecs, max_dblocks) + 1; } int __init diff --git a/fs/xfs/scrub/agheader.c b/fs/xfs/scrub/agheader.c index 1fa66aa68e169f..fa5d32ec020aec 100644 --- a/fs/xfs/scrub/agheader.c +++ b/fs/xfs/scrub/agheader.c @@ -418,6 +418,13 @@ xchk_superblock( xchk_block_set_corrupt(sc, bp); } + if (xfs_has_zoned(mp)) { + if (sb->sb_rtstart != cpu_to_be64(mp->m_sb.sb_rtstart)) + xchk_block_set_corrupt(sc, bp); + if (sb->sb_rtreserved != cpu_to_be64(mp->m_sb.sb_rtreserved)) + xchk_block_set_corrupt(sc, bp); + } + /* Everything else must be zero. */ sblen = xchk_superblock_ondisk_size(mp); if (memchr_inv((char *)sb + sblen, 0, BBTOB(bp->b_length) - sblen)) diff --git a/fs/xfs/scrub/agheader_repair.c b/fs/xfs/scrub/agheader_repair.c index 2104512f1ee19a..a66b611588c47f 100644 --- a/fs/xfs/scrub/agheader_repair.c +++ b/fs/xfs/scrub/agheader_repair.c @@ -668,14 +668,16 @@ xrep_agfl_init_header( struct xfs_scrub *sc, struct xfs_buf *agfl_bp, struct xagb_bitmap *agfl_extents, - xfs_agblock_t flcount) + xfs_agblock_t flcount, + struct xfs_agfl *old_agfl) { struct xrep_agfl_fill af = { .sc = sc, .flcount = flcount, }; struct xfs_mount *mp = sc->mp; - struct xfs_agfl *agfl; + struct xfs_agfl *agfl = XFS_BUF_TO_AGFL(agfl_bp); + const size_t agfl_sz = BBTOB(agfl_bp->b_length); int error; ASSERT(flcount <= xfs_agfl_size(mp)); @@ -684,8 +686,8 @@ xrep_agfl_init_header( * Start rewriting the header by setting the bno[] array to * NULLAGBLOCK, then setting AGFL header fields. */ - agfl = XFS_BUF_TO_AGFL(agfl_bp); - memset(agfl, 0xFF, BBTOB(agfl_bp->b_length)); + memcpy(old_agfl, agfl, agfl_sz); + memset(agfl, 0xFF, agfl_sz); agfl->agfl_magicnum = cpu_to_be32(XFS_AGFL_MAGIC); agfl->agfl_seqno = cpu_to_be32(pag_agno(sc->sa.pag)); uuid_copy(&agfl->agfl_uuid, &mp->m_sb.sb_meta_uuid); @@ -697,16 +699,23 @@ xrep_agfl_init_header( */ xagb_bitmap_init(&af.used_extents); af.agfl_bno = xfs_buf_to_agfl_bno(agfl_bp); - xagb_bitmap_walk(agfl_extents, xrep_agfl_fill, &af); + error = xagb_bitmap_walk(agfl_extents, xrep_agfl_fill, &af); + if (error && error != -ECANCELED) + goto err_undo; error = xagb_bitmap_disunion(agfl_extents, &af.used_extents); if (error) - return error; + goto err_undo; /* Write new AGFL to disk. */ xfs_trans_buf_set_type(sc->tp, agfl_bp, XFS_BLFT_AGFL_BUF); - xfs_trans_log_buf(sc->tp, agfl_bp, 0, BBTOB(agfl_bp->b_length) - 1); + xfs_trans_log_buf(sc->tp, agfl_bp, 0, agfl_sz - 1); xagb_bitmap_destroy(&af.used_extents); return 0; + +err_undo: + xagb_bitmap_destroy(&af.used_extents); + memcpy(agfl, old_agfl, agfl_sz); + return error; } /* Repair the AGFL. */ @@ -718,6 +727,7 @@ xrep_agfl( struct xfs_mount *mp = sc->mp; struct xfs_buf *agf_bp; struct xfs_buf *agfl_bp; + struct xfs_agfl *old_agfl; xfs_agblock_t flcount; int error; @@ -725,6 +735,10 @@ xrep_agfl( if (!xfs_has_rmapbt(mp)) return -EOPNOTSUPP; + old_agfl = kzalloc(BBTOB(XFS_FSS_TO_BB(mp, 1)), XCHK_GFP_FLAGS); + if (!old_agfl) + return -ENOMEM; + xagb_bitmap_init(&agfl_extents); /* @@ -734,7 +748,7 @@ xrep_agfl( */ error = xfs_alloc_read_agf(sc->sa.pag, sc->tp, 0, &agf_bp); if (error) - return error; + goto err_old_agfl; /* * Make sure we have the AGFL buffer, as scrub might have decided it @@ -745,7 +759,7 @@ xrep_agfl( XFS_AGFL_DADDR(mp)), XFS_FSS_TO_BB(mp, 1), 0, &agfl_bp, NULL); if (error) - return error; + goto err_old_agfl; agfl_bp->b_ops = &xfs_agfl_buf_ops; /* Gather all the extents we're going to put on the new AGFL. */ @@ -762,10 +776,11 @@ xrep_agfl( * we adjust the AGF flcount (which can fail) so avoid updating any * buffers until we know that part works. */ - xrep_agfl_update_agf(sc, agf_bp, flcount); - error = xrep_agfl_init_header(sc, agfl_bp, &agfl_extents, flcount); + error = xrep_agfl_init_header(sc, agfl_bp, &agfl_extents, flcount, + old_agfl); if (error) goto err; + xrep_agfl_update_agf(sc, agf_bp, flcount); /* * Ok, the AGFL should be ready to go now. Roll the transaction to @@ -785,6 +800,8 @@ xrep_agfl( err: xagb_bitmap_destroy(&agfl_extents); +err_old_agfl: + kfree(old_agfl); return error; } diff --git a/fs/xfs/scrub/alloc_repair.c b/fs/xfs/scrub/alloc_repair.c index dce6ab0429dcfe..95e318e4f3a6c7 100644 --- a/fs/xfs/scrub/alloc_repair.c +++ b/fs/xfs/scrub/alloc_repair.c @@ -571,7 +571,7 @@ xrep_abt_dispose_one( * allocation, and blocks that didn't get used can be freed via the usual * (deferred) means. */ -STATIC void +STATIC int xrep_abt_dispose_reservations( struct xrep_abt *ra, int error) @@ -582,9 +582,13 @@ xrep_abt_dispose_reservations( goto junkit; list_for_each_entry_safe(resv, n, &ra->new_bnobt.resv_list, list) { - error = xrep_abt_dispose_one(ra, resv); - if (error) + int error2 = xrep_abt_dispose_one(ra, resv); + + if (error2) { + if (!error) + error = error2; goto junkit; + } } junkit: @@ -596,6 +600,7 @@ junkit: xrep_newbt_cancel(&ra->new_bnobt); xrep_newbt_cancel(&ra->new_cntbt); + return error; } /* Retrieve free space data for bulk load. */ @@ -801,7 +806,9 @@ xrep_abt_build_new_trees( goto err_newbt; /* Dispose of any unused blocks and the accounting information. */ - xrep_abt_dispose_reservations(ra, error); + error = xrep_abt_dispose_reservations(ra, error); + if (error) + return error; return xrep_roll_ag_trans(sc); @@ -812,8 +819,7 @@ err_cur: xfs_btree_del_cursor(cnt_cur, error); xfs_btree_del_cursor(bno_cur, error); err_newbt: - xrep_abt_dispose_reservations(ra, error); - return error; + return xrep_abt_dispose_reservations(ra, error); } /* diff --git a/fs/xfs/scrub/attr_repair.c b/fs/xfs/scrub/attr_repair.c index 6e6af142f1fb8e..28f92e9ba72b24 100644 --- a/fs/xfs/scrub/attr_repair.c +++ b/fs/xfs/scrub/attr_repair.c @@ -1294,7 +1294,7 @@ xrep_xattr_swap_prep( .geo = sc->mp->m_attr_geo, .whichfork = XFS_ATTR_FORK, .trans = sc->tp, - .total = 1, + .total = xfs_dabuf_nfsb(sc->mp, XFS_ATTR_FORK), .owner = I_INO(sc->ip), }; diff --git a/fs/xfs/scrub/bmap.c b/fs/xfs/scrub/bmap.c index 401c278725d216..3b0f1dbd9147ac 100644 --- a/fs/xfs/scrub/bmap.c +++ b/fs/xfs/scrub/bmap.c @@ -274,7 +274,7 @@ xchk_bmap_xref_rmap_cow( unsigned long long rmap_end; uint64_t owner = XFS_RMAP_OWN_COW; - if (!info->sc->sa.rmap_cur || xchk_skip_xref(info->sc->sm)) + if (xchk_skip_xref(info->sc->sm)) return; /* Find the rmap record for this irec. */ diff --git a/fs/xfs/scrub/dir_repair.c b/fs/xfs/scrub/dir_repair.c index 1c088cfba10ea9..2cfcf1c35679ea 100644 --- a/fs/xfs/scrub/dir_repair.c +++ b/fs/xfs/scrub/dir_repair.c @@ -484,18 +484,24 @@ xrep_dir_recover_data( while (offset < end) { struct xfs_dir2_data_unused *dup = bp->b_addr + offset; struct xfs_dir2_data_entry *dep = bp->b_addr + offset; + unsigned int advance; if (xchk_should_terminate(rd->sc, &error)) return error; /* Skip unused entries. */ if (be16_to_cpu(dup->freetag) == XFS_DIR2_DATA_FREE_TAG) { + if (!dup->length) + break; offset += be16_to_cpu(dup->length); continue; } /* Don't walk off the end of the block. */ - offset += xfs_dir2_data_entsize(rd->sc->mp, dep->namelen); + advance = xfs_dir2_data_entsize(rd->sc->mp, dep->namelen); + if (!advance) + break; + offset += advance; if (offset > end) break; @@ -721,7 +727,7 @@ xrep_dir_replay_removename( const struct xfs_name *name, xfs_extlen_t total) { - struct xfs_inode *dp = rd->args.dp; + struct xfs_inode *dp = rd->sc->tempip; ASSERT(S_ISDIR(VFS_I(dp)->i_mode)); @@ -1375,9 +1381,24 @@ xrep_dir_live_update( if (p->delta > 0) error = xrep_dir_stash_createname(rd, p->name, I_INO(p->ip)); - else - error = xrep_dir_stash_removename(rd, p->name, + else { + /* + * xfs_dentry_to_name in unlink or rename-exchange can + * pass us names with ftype FT_UNKNOWN, but we really + * must know the ftype of the child that is being + * removed so that we can do nlink updates correctly + * without holding inode references. + */ + struct xfs_name name = { + .name = p->name->name, + .len = p->name->len, + .type = xfs_mode_to_ftype( + VFS_IC(p->ip)->i_mode), + }; + + error = xrep_dir_stash_removename(rd, &name, I_INO(p->ip)); + } mutex_unlock(&rd->pscan.lock); if (error) goto out_abort; @@ -1467,7 +1488,7 @@ xrep_dir_swap_prep( .geo = sc->mp->m_dir_geo, .whichfork = XFS_DATA_FORK, .trans = sc->tp, - .total = 1, + .total = xfs_dabuf_nfsb(sc->mp, XFS_DATA_FORK), .owner = I_INO(sc->ip), }; diff --git a/fs/xfs/scrub/dirtree.c b/fs/xfs/scrub/dirtree.c index b2cf6e5439d915..9b0ab23166124e 100644 --- a/fs/xfs/scrub/dirtree.c +++ b/fs/xfs/scrub/dirtree.c @@ -259,6 +259,7 @@ xchk_dirtree_create_path( dl->nr_paths++; return 0; out_path: + xino_bitmap_destroy(&path->seen_inodes); kfree(path); return error; } @@ -368,12 +369,38 @@ xchk_dirpath_step_up( struct xfs_inode *dp; xfs_ino_t parent_ino = be64_to_cpu(dl->pptr_rec.p_ino); unsigned int lock_mode; - int error; + int error = 0; + + if (xchk_should_terminate(sc, &error)) + return error; /* Grab and lock the parent directory. */ error = xchk_iget(sc, parent_ino, &dp); - if (error) + switch (error) { + case -EINVAL: + case -ENOENT: + mutex_lock(&dl->lock); + + if (dl->stale) { + /* live update detected a change in this path */ + error = -ESTALE; + } else { + /* inode doesn't exist, path invalid */ + error = -EFSCORRUPTED; + + trace_xchk_dirpath_badino(dl->sc, path->path_nr, + path->nr_steps, &dl->xname, + &dl->pptr_rec); + } + + mutex_unlock(&dl->lock); + return error; + case 0: + /* keep going */ + break; + default: return error; + } lock_mode = xfs_ilock_attr_map_shared(dp); mutex_lock(&dl->lock); diff --git a/fs/xfs/scrub/dirtree_repair.c b/fs/xfs/scrub/dirtree_repair.c index bbf6acf6fd400c..1d1eafcf6eb598 100644 --- a/fs/xfs/scrub/dirtree_repair.c +++ b/fs/xfs/scrub/dirtree_repair.c @@ -479,6 +479,7 @@ again: } if (xfs_has_parent(sc->mp)) { + memset(&dl->ppargs, 0, sizeof(dl->ppargs)); error = xfs_parent_removename(sc->tp, &dl->ppargs, dp, &dl->xname, sc->ip); if (error) @@ -618,6 +619,7 @@ xrep_dirtree_create_adoption_path( return 0; out_path: + xino_bitmap_destroy(&path->seen_inodes); kfree(path); return error; } diff --git a/fs/xfs/scrub/findparent.c b/fs/xfs/scrub/findparent.c index 04b6b96b0a30ed..eab3ac2704befe 100644 --- a/fs/xfs/scrub/findparent.c +++ b/fs/xfs/scrub/findparent.c @@ -139,32 +139,52 @@ xrep_findparent_dirent( return 0; } -/* - * If this is a directory, walk the dirents looking for any that point to the - * scrub target inode. - */ -STATIC int -xrep_findparent_walk_directory( - struct xrep_findparent_info *fpi) +static inline bool +xrep_findparent_want_scan_file( + const struct xrep_findparent_info *fpi) { - struct xfs_scrub *sc = fpi->sc; - struct xfs_inode *dp = fpi->dp; - unsigned int lock_mode; - int error = 0; + const struct xfs_scrub *sc = fpi->sc; + const struct xfs_inode *dp = fpi->dp; + + /* Only directories can be parents */ + if (!S_ISDIR(VFS_IC(dp)->i_mode)) + return false; /* * The inode being scanned cannot be its own parent, nor can any * temporary directory we created to stage this repair. */ if (dp == sc->ip || dp == sc->tempip) - return 0; + return false; /* * Similarly, temporary files created to stage a repair cannot be the * parent of this inode. */ if (xrep_is_tempfile(dp)) + return false; + + return true; +} + +/* + * If this is a directory, walk the dirents looking for any that point to the + * scrub target inode. + */ +STATIC int +xrep_findparent_walk_file( + struct xrep_findparent_info *fpi) +{ + struct xfs_scrub *sc = fpi->sc; + struct xfs_inode *dp = fpi->dp; + unsigned int lock_mode; + int error = 0; + + if (!xrep_findparent_want_scan_file(fpi)) { + if (fpi->parent_scan) + xchk_iscan_mark_visited(&fpi->parent_scan->iscan, dp); return 0; + } /* * Scan the directory to see if there it contains an entry pointing to @@ -201,6 +221,8 @@ xrep_findparent_walk_directory( goto out_unlock; out_unlock: + if (fpi->parent_scan) + xchk_iscan_mark_visited(&fpi->parent_scan->iscan, dp); xfs_iunlock(dp, lock_mode); return error; } @@ -308,11 +330,7 @@ xrep_findparent_scan( ASSERT(S_ISDIR(VFS_IC(sc->ip)->i_mode)); while ((ret = xchk_iscan_iter(&pscan->iscan, &fpi.dp)) == 1) { - if (S_ISDIR(VFS_I(fpi.dp)->i_mode)) - ret = xrep_findparent_walk_directory(&fpi); - else - ret = 0; - xchk_iscan_mark_visited(&pscan->iscan, fpi.dp); + ret = xrep_findparent_walk_file(&fpi); xchk_irele(sc, fpi.dp); if (ret) break; @@ -401,7 +419,7 @@ xrep_findparent_confirm( goto out_rele; } - error = xrep_findparent_walk_directory(&fpi); + error = xrep_findparent_walk_file(&fpi); if (error) goto out_rele; diff --git a/fs/xfs/scrub/ialloc.c b/fs/xfs/scrub/ialloc.c index 19c0b1b2a787bb..9270ad075fe0a2 100644 --- a/fs/xfs/scrub/ialloc.c +++ b/fs/xfs/scrub/ialloc.c @@ -85,6 +85,8 @@ xchk_inobt_xref_finobt( goto no_record; error = xfs_inobt_get_rec(cur, &frec, &has_record); + if (error) + return error; if (!has_record) return -EFSCORRUPTED; @@ -188,6 +190,8 @@ xchk_finobt_xref_inobt( goto no_record; error = xfs_inobt_get_rec(cur, &irec, &has_record); + if (error) + return error; if (!has_record) return -EFSCORRUPTED; diff --git a/fs/xfs/scrub/metapath.c b/fs/xfs/scrub/metapath.c index ff1ff762b3003c..c1fa0e17965311 100644 --- a/fs/xfs/scrub/metapath.c +++ b/fs/xfs/scrub/metapath.c @@ -397,7 +397,7 @@ xrep_metapath_unlink( /* Figure out if we're removing a parent pointer too. */ if (xfs_has_parent(mp)) { - xfs_inode_to_parent_rec(&rec, ip); + xfs_inode_to_parent_rec(&rec, mpath->dp); error = xfs_parent_lookup(sc->tp, ip, &mpath->xname, &rec, &mpath->pptr_args); switch (error) { @@ -556,6 +556,8 @@ xrep_metapath_try_unlink( error = xchk_metapath_ilock_parent_and_child(mpath, ip); if (error) { xchk_trans_cancel(sc); + if (ip) + xchk_irele(sc, ip); return error; } xfs_trans_ijoin(sc->tp, mpath->dp, 0); diff --git a/fs/xfs/scrub/quota_repair.c b/fs/xfs/scrub/quota_repair.c index 487bd4f68ebb2a..59302e8afc7ef0 100644 --- a/fs/xfs/scrub/quota_repair.c +++ b/fs/xfs/scrub/quota_repair.c @@ -325,7 +325,7 @@ xrep_quota_block( * If there's nothing that would impede a dqiterate, we're * done. */ - if ((ddq->d_type & XFS_DQTYPE_REC_MASK) != dqtype || + if ((ddq->d_type & XFS_DQTYPE_REC_MASK) == dqtype && id == be32_to_cpu(ddq->d_id)) { xfs_trans_brelse(sc->tp, bp); return 0; @@ -363,11 +363,18 @@ xrep_quota_block( ddq->d_rtbcount, &ddq->d_rtbtimer, defq->rtb.time); + /* + * This transaction operates on raw disk buffers, so we don't + * have a dquot log item to assign the LSN for us. Instead, + * set it to zero so that log recovery will always replay any + * logged dquot item atop this buffer. + */ + dqblk->dd_lsn = 0; + /* We only support v5 filesystems so always set these. */ uuid_copy(&dqblk->dd_uuid, &sc->mp->m_sb.sb_meta_uuid); xfs_update_cksum((char *)dqblk, sizeof(struct xfs_dqblk), XFS_DQUOT_CRC_OFF); - dqblk->dd_lsn = 0; } switch (dqtype) { case XFS_DQTYPE_USER: @@ -455,8 +462,7 @@ xrep_quota_data_fork( if (truncate) { /* Erase everything after the block containing the max dquot */ - error = xfs_bunmapi_range(&sc->tp, sc->ip, 0, - max_dqid_off * sc->mp->m_sb.sb_blocksize, + error = xfs_bunmapi_range(&sc->tp, sc->ip, 0, max_dqid_off + 1, XFS_MAX_FILEOFF); if (error) goto out; diff --git a/fs/xfs/scrub/quotacheck.c b/fs/xfs/scrub/quotacheck.c index c199d128538e55..c32030a0544065 100644 --- a/fs/xfs/scrub/quotacheck.c +++ b/fs/xfs/scrub/quotacheck.c @@ -263,8 +263,10 @@ xqcheck_mod_live_ino_dqtrx( dqa->tx_id = p->tx_id; error = rhashtable_insert_fast(&xqc->shadow_dquot_acct, &dqa->hash, xqcheck_dqacct_hash_params); - if (error) + if (error) { + kfree(dqa); goto out_abort; + } } /* Find the shadow dqtrx (or an empty slot) here. */ diff --git a/fs/xfs/scrub/reap.c b/fs/xfs/scrub/reap.c index fcd14c1703ea04..f698b9be3dd1df 100644 --- a/fs/xfs/scrub/reap.c +++ b/fs/xfs/scrub/reap.c @@ -601,7 +601,7 @@ xreap_configure_agextent_limits( /* Maximum overhead of invalidating one buffer. */ const unsigned int per_binval = - xfs_buf_inval_log_space(1, XFS_B_TO_FSBT(mp, max_binval)); + xfs_buf_inval_log_space(1, XFS_FSB_TO_B(mp, max_binval)); /* * For each transaction in a reap chain, we can delete some number of @@ -680,7 +680,7 @@ xreap_configure_agcow_limits( /* Overhead of invalidating one buffer */ const unsigned int per_binval = - xfs_buf_inval_log_space(1, XFS_B_TO_FSBT(mp, max_binval)); + xfs_buf_inval_log_space(1, XFS_FSB_TO_B(mp, max_binval)); /* * For each transaction in a reap chain, we can delete some number of @@ -1399,7 +1399,7 @@ xreap_bmapi_binval( * far we've gotten. */ if (!xreap_inc_binval(rs)) { - imap->br_blockcount = agbno_next - bno; + imap->br_blockcount = bno - agbno; goto out; } } diff --git a/fs/xfs/scrub/refcount.c b/fs/xfs/scrub/refcount.c index 4e1bf23e5b8972..f8c51d8fbb3da5 100644 --- a/fs/xfs/scrub/refcount.c +++ b/fs/xfs/scrub/refcount.c @@ -410,7 +410,7 @@ xchk_refcount_mergeable( const struct xfs_refcount_irec *r1 = &rrc->prev_rec; /* Ignore if prev_rec is not yet initialized. */ - if (r1->rc_blockcount > 0) + if (r1->rc_blockcount == 0) return false; if (r1->rc_domain != r2->rc_domain) @@ -581,8 +581,12 @@ xchk_xref_is_cow_staging( if (rc.rc_domain != XFS_REFC_DOMAIN_COW) xchk_btree_xref_set_corrupt(sc, sc->sa.refc_cur, 0); + /* Can't start after bno */ + if (rc.rc_startblock > agbno) + xchk_btree_xref_set_corrupt(sc, sc->sa.refc_cur, 0); + /* Must be at least as long as what was passed in */ - if (rc.rc_blockcount < len) + if (rc.rc_startblock + rc.rc_blockcount < agbno + len) xchk_btree_xref_set_corrupt(sc, sc->sa.refc_cur, 0); } diff --git a/fs/xfs/scrub/rgsuper.c b/fs/xfs/scrub/rgsuper.c index 2bd2c0351b35f7..6e2abe5dc27cd5 100644 --- a/fs/xfs/scrub/rgsuper.c +++ b/fs/xfs/scrub/rgsuper.c @@ -36,8 +36,10 @@ xchk_rgsuperblock_xref( if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT) return; - xchk_xref_is_used_rt_space(sc, xfs_rgbno_to_rtb(sc->sr.rtg, 0), 1); - xchk_xref_is_only_rt_owned_by(sc, 0, 1, &XFS_RMAP_OINFO_FS); + xchk_xref_is_used_rt_space(sc, xfs_rgbno_to_rtb(sc->sr.rtg, 0), + sc->mp->m_sb.sb_rextsize); + xchk_xref_is_only_rt_owned_by(sc, 0, sc->mp->m_sb.sb_rextsize, + &XFS_RMAP_OINFO_FS); } int diff --git a/fs/xfs/scrub/rtrefcount.c b/fs/xfs/scrub/rtrefcount.c index 4e7c540c8d2307..3d916d71a135dc 100644 --- a/fs/xfs/scrub/rtrefcount.c +++ b/fs/xfs/scrub/rtrefcount.c @@ -20,6 +20,7 @@ #include "xfs_metafile.h" #include "xfs_rtrefcount_btree.h" #include "xfs_rtalloc.h" +#include "xfs_ag.h" #include "scrub/scrub.h" #include "scrub/common.h" #include "scrub/btree.h" @@ -375,7 +376,7 @@ xchk_rtrefcount_mergeable( const struct xfs_refcount_irec *r1 = &rrc->prev_rec; /* Ignore if prev_rec is not yet initialized. */ - if (r1->rc_blockcount > 0) + if (r1->rc_blockcount == 0) return false; if (r1->rc_startblock + r1->rc_blockcount != r2->rc_startblock) @@ -428,7 +429,7 @@ static inline void xchk_rtrefcountbt_xref_gaps( struct xfs_scrub *sc, struct xchk_rtrefcbt_records *rrc, - xfs_rtblock_t bno) + xfs_rgblock_t bno) { struct xfs_rmap_irec low; struct xfs_rmap_irec high; @@ -504,30 +505,75 @@ xchk_rtrefcountbt_rec( return 0; } +/* Count the number of blocks used by the rtrefcount btree file in this AG. */ +static int +xchk_rtrefcount_count_agblocks( + struct xfs_scrub *sc, + xfs_agnumber_t agno, + const struct xfs_owner_info *btree_oinfo, + xfs_filblks_t *blocks) +{ + xfs_filblks_t agblocks = 0; + int error; + + error = xchk_ag_init_existing(sc, agno, &sc->sa); + if (error) + goto out_free; + + /* + * If we don't have an rmap cursor, we can't complete the cross + * referencing, so return EFSCORRUPTED to end the loop and trigger the + * XFAIL flag. + */ + if (!sc->sa.rmap_cur) { + error = -EFSCORRUPTED; + goto out_free; + } + + error = xchk_count_rmap_ownedby_ag(sc, sc->sa.rmap_cur, btree_oinfo, + &agblocks); + if (error) + goto out_free; + + *blocks += agblocks; +out_free: + xchk_ag_free(sc, &sc->sa); + return error; +} + /* Make sure we have as many refc blocks as the rmap says. */ STATIC void -xchk_refcount_xref_rmap( +xchk_rtrefcount_xref_rmap( struct xfs_scrub *sc, const struct xfs_owner_info *btree_oinfo, xfs_extlen_t cow_blocks) { xfs_filblks_t refcbt_blocks = 0; - xfs_filblks_t blocks; - int error; + xfs_filblks_t blocks = 1; /* one for the iroot */ + xfs_agnumber_t agno; + int error = 0; - if (!sc->sr.rmap_cur || !sc->sa.rmap_cur || xchk_skip_xref(sc->sm)) + if (!xfs_has_rmapbt(sc->mp) || xchk_skip_xref(sc->sm)) return; /* Check that we saw as many refcbt blocks as the rmap knows about. */ error = xfs_btree_count_blocks(sc->sr.refc_cur, &refcbt_blocks); if (!xchk_btree_process_error(sc, sc->sr.refc_cur, 0, &error)) return; - error = xchk_count_rmap_ownedby_ag(sc, sc->sa.rmap_cur, btree_oinfo, - &blocks); - if (!xchk_should_check_xref(sc, &error, &sc->sa.rmap_cur)) + + for (agno = 0; agno < sc->mp->m_sb.sb_agcount; agno++) { + error = xchk_rtrefcount_count_agblocks(sc, agno, btree_oinfo, + &blocks); + if (error) + break; + } + if (!xchk_fblock_xref_process_error(sc, XFS_DATA_FORK, 0, &error)) return; if (blocks != refcbt_blocks) - xchk_btree_xref_set_corrupt(sc, sc->sa.rmap_cur, 0); + xchk_fblock_xref_set_corrupt(sc, XFS_DATA_FORK, 0); + + if (!sc->sr.rmap_cur || xchk_skip_xref(sc->sm)) + return; /* Check that we saw as many cow blocks as the rmap knows about. */ error = xchk_count_rmap_ownedby_ag(sc, sc->sr.rmap_cur, @@ -538,7 +584,7 @@ xchk_refcount_xref_rmap( xchk_btree_xref_set_corrupt(sc, sc->sr.rmap_cur, 0); } -/* Scrub the refcount btree for some AG. */ +/* Scrub the refcount btree for some rtgroup. */ int xchk_rtrefcountbt( struct xfs_scrub *sc) @@ -564,11 +610,11 @@ xchk_rtrefcountbt( /* * Check that all blocks between the last refcount > 1 record and the - * end of the rt volume have at most one reverse mapping. + * end of the rtgroup have at most one reverse mapping. */ - xchk_rtrefcountbt_xref_gaps(sc, &rrc, sc->mp->m_sb.sb_rblocks); - - xchk_refcount_xref_rmap(sc, &btree_oinfo, rrc.cow_blocks); + xchk_rtrefcountbt_xref_gaps(sc, &rrc, + xfs_rtx_to_rgbno(sc->sr.rtg, sc->mp->m_sb.sb_rgextents)); + xchk_rtrefcount_xref_rmap(sc, &btree_oinfo, rrc.cow_blocks); return 0; } @@ -609,8 +655,12 @@ xchk_xref_is_rt_cow_staging( if (rc.rc_domain != XFS_REFC_DOMAIN_COW) xchk_btree_xref_set_corrupt(sc, sc->sr.refc_cur, 0); + /* Can't start after bno */ + if (rc.rc_startblock > bno) + xchk_btree_xref_set_corrupt(sc, sc->sr.refc_cur, 0); + /* Must be at least as long as what was passed in */ - if (rc.rc_blockcount < len) + if (rc.rc_startblock + rc.rc_blockcount < bno + len) xchk_btree_xref_set_corrupt(sc, sc->sr.refc_cur, 0); } diff --git a/fs/xfs/scrub/rtsummary_repair.c b/fs/xfs/scrub/rtsummary_repair.c index f065c3e51ce2e4..ed763290aec1e5 100644 --- a/fs/xfs/scrub/rtsummary_repair.c +++ b/fs/xfs/scrub/rtsummary_repair.c @@ -164,9 +164,10 @@ xrep_rtsummary( /* * Now exchange the contents. Nothing in repair uses the temporary * buffer, so we can reuse it for the tempfile exchrange information. + * Use XFS_MAX_FILEOFF here so that we correct the rtsummary file size. */ error = xrep_tempexch_trans_reserve(sc, XFS_DATA_FORK, 0, - rts->rsumblocks, &rts->tempexch); + XFS_MAX_FILEOFF, &rts->tempexch); if (error) return error; diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c index 8742445c86f45e..12c228b7f4770d 100644 --- a/fs/xfs/scrub/scrub.c +++ b/fs/xfs/scrub/scrub.c @@ -765,8 +765,7 @@ out_nofix: out_teardown: error = xchk_teardown(sc, error); out_sc: - if (error != -ENOENT) - xchk_stats_merge(mp, sm, &run); + xchk_stats_merge(mp, sm, error, &run); kfree(sc); out: trace_xchk_done(XFS_I(file_inode(file)), sm, error); diff --git a/fs/xfs/scrub/stats.c b/fs/xfs/scrub/stats.c index ef3f6abdb7061a..da0c05ffe5cd0b 100644 --- a/fs/xfs/scrub/stats.c +++ b/fs/xfs/scrub/stats.c @@ -84,6 +84,7 @@ static const char *name_map[XFS_SCRUB_TYPE_NR] = { [XFS_SCRUB_TYPE_RGSUPER] = "rgsuper", [XFS_SCRUB_TYPE_RTRMAPBT] = "rtrmapbt", [XFS_SCRUB_TYPE_RTREFCBT] = "rtrefcountbt", + [XFS_SCRUB_TYPE_HEALTHY] = "healthy", }; /* Format the scrub stats into a text buffer, similar to pcp style. */ @@ -99,25 +100,31 @@ xchk_stats_format( int ret = 0; for (i = 0; i < XFS_SCRUB_TYPE_NR; i++, css++) { + struct xchk_scrub_stats fss; + if (!name_map[i]) continue; + spin_lock(&css->css_lock); + memcpy(&fss, css, offsetof(struct xchk_scrub_stats, css_lock)); + spin_unlock(&css->css_lock); + ret = scnprintf(buf, remaining, "%s %u %u %u %u %u %u %u %u %u %llu %u %u %llu\n", name_map[i], - (unsigned int)css->invocations, - (unsigned int)css->clean, - (unsigned int)css->corrupt, - (unsigned int)css->preen, - (unsigned int)css->xfail, - (unsigned int)css->xcorrupt, - (unsigned int)css->incomplete, - (unsigned int)css->warning, - (unsigned int)css->retries, - (unsigned long long)css->checktime_us, - (unsigned int)css->repair_invocations, - (unsigned int)css->repair_success, - (unsigned long long)css->repairtime_us); + (unsigned int)fss.invocations, + (unsigned int)fss.clean, + (unsigned int)fss.corrupt, + (unsigned int)fss.preen, + (unsigned int)fss.xfail, + (unsigned int)fss.xcorrupt, + (unsigned int)fss.incomplete, + (unsigned int)fss.warning, + (unsigned int)fss.retries, + (unsigned long long)fss.checktime_us, + (unsigned int)fss.repair_invocations, + (unsigned int)fss.repair_success, + (unsigned long long)fss.repairtime_us); if (ret <= 0) break; @@ -188,31 +195,37 @@ STATIC void xchk_stats_merge_one( struct xchk_stats *cs, const struct xfs_scrub_metadata *sm, + int error, const struct xchk_stats_run *run) { struct xchk_scrub_stats *css; + unsigned int sm_flags = sm->sm_flags; if (sm->sm_type >= XFS_SCRUB_TYPE_NR) { ASSERT(sm->sm_type < XFS_SCRUB_TYPE_NR); return; } + /* caller applies this same transformation after we return */ + if (error == -EFSCORRUPTED || error == -EFSBADCRC) + sm_flags |= XFS_SCRUB_OFLAG_CORRUPT; + css = &cs->cs_stats[sm->sm_type]; spin_lock(&css->css_lock); css->invocations++; - if (!(sm->sm_flags & XFS_SCRUB_OFLAG_UNCLEAN)) + if (!(sm_flags & XFS_SCRUB_OFLAG_UNCLEAN)) css->clean++; - if (sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT) + if (sm_flags & XFS_SCRUB_OFLAG_CORRUPT) css->corrupt++; - if (sm->sm_flags & XFS_SCRUB_OFLAG_PREEN) + if (sm_flags & XFS_SCRUB_OFLAG_PREEN) css->preen++; - if (sm->sm_flags & XFS_SCRUB_OFLAG_XFAIL) + if (sm_flags & XFS_SCRUB_OFLAG_XFAIL) css->xfail++; - if (sm->sm_flags & XFS_SCRUB_OFLAG_XCORRUPT) + if (sm_flags & XFS_SCRUB_OFLAG_XCORRUPT) css->xcorrupt++; - if (sm->sm_flags & XFS_SCRUB_OFLAG_INCOMPLETE) + if (sm_flags & XFS_SCRUB_OFLAG_INCOMPLETE) css->incomplete++; - if (sm->sm_flags & XFS_SCRUB_OFLAG_WARNING) + if (sm_flags & XFS_SCRUB_OFLAG_WARNING) css->warning++; css->retries += run->retries; css->checktime_us += howmany_64(run->scrub_ns, NSEC_PER_USEC); @@ -230,10 +243,14 @@ void xchk_stats_merge( struct xfs_mount *mp, const struct xfs_scrub_metadata *sm, + int error, const struct xchk_stats_run *run) { - xchk_stats_merge_one(&global_stats, sm, run); - xchk_stats_merge_one(mp->m_scrub_stats, sm, run); + if (error == -ENOENT) + return; + + xchk_stats_merge_one(&global_stats, sm, error, run); + xchk_stats_merge_one(mp->m_scrub_stats, sm, error, run); } /* debugfs boilerplate */ diff --git a/fs/xfs/scrub/stats.h b/fs/xfs/scrub/stats.h index b358ad8d8b90ac..221052b95dd077 100644 --- a/fs/xfs/scrub/stats.h +++ b/fs/xfs/scrub/stats.h @@ -27,7 +27,7 @@ void xchk_stats_register(struct xchk_stats *cs, struct dentry *parent); void xchk_stats_unregister(struct xchk_stats *cs); void xchk_stats_merge(struct xfs_mount *mp, const struct xfs_scrub_metadata *sm, - const struct xchk_stats_run *run); + int error, const struct xchk_stats_run *run); static inline u64 xchk_stats_now(void) { return ktime_get_ns(); } static inline u64 xchk_stats_elapsed_ns(u64 since) @@ -53,7 +53,7 @@ static inline u64 xchk_stats_elapsed_ns(u64 since) # define xchk_stats_unregister(cs) ((void)0) # define xchk_stats_now() (0) # define xchk_stats_elapsed_ns(x) (0 * (x)) -# define xchk_stats_merge(mp, sm, run) ((void)0) +# define xchk_stats_merge(mp, sm, error, run) ((void)0) #endif /* CONFIG_XFS_ONLINE_SCRUB_STATS */ #endif /* __XFS_SCRUB_STATS_H__ */ diff --git a/fs/xfs/scrub/symlink_repair.c b/fs/xfs/scrub/symlink_repair.c index 91c86ea0e0f155..18196136423336 100644 --- a/fs/xfs/scrub/symlink_repair.c +++ b/fs/xfs/scrub/symlink_repair.c @@ -291,7 +291,7 @@ xrep_symlink_swap_prep( if (error) return error; - xfs_trans_log_inode(sc->tp, sc->ip, 0); + xfs_trans_log_inode(sc->tp, sc->tempip, logflags); error = xfs_defer_finish(&sc->tp); if (error) diff --git a/fs/xfs/scrub/tempfile.c b/fs/xfs/scrub/tempfile.c index 98820003b9298f..59a9213a3c7ddf 100644 --- a/fs/xfs/scrub/tempfile.c +++ b/fs/xfs/scrub/tempfile.c @@ -649,6 +649,19 @@ xrep_tempexch_prep_request( return 0; } +static inline unsigned int +xrep_tempexch_estimate_sf_resblks( + struct xfs_scrub *sc, + int whichfork) +{ + /* repairing a symlink target */ + if (S_ISLNK(VFS_I(sc->ip)->i_mode) && whichfork == XFS_DATA_FORK) + return 1; + + /* everything else is a directory or an xattr structure */ + return xfs_dabuf_nfsb(sc->mp, whichfork); +} + /* * Fill out the mapping exchange resource estimation structures in preparation * for exchanging the contents of a metadata file that we've rebuilt in the @@ -663,6 +676,8 @@ xrep_tempexch_estimate( struct xfs_ifork *ifp; struct xfs_ifork *tifp; int whichfork = xfs_exchmaps_reqfork(req); + unsigned int sf_resblks = + xrep_tempexch_estimate_sf_resblks(sc, whichfork); int state = 0; /* @@ -693,9 +708,9 @@ xrep_tempexch_estimate( * plus the block we converted. */ req->ip1_bcount = sc->tempip->i_nblocks; - req->ip2_bcount = 1; + req->ip2_bcount = sf_resblks; req->nr_exchanges = 1 + tifp->if_nextents; - req->resblks = 1; + req->resblks = sf_resblks; break; case 2: /* @@ -707,10 +722,10 @@ xrep_tempexch_estimate( * is (worst case) the extent count of the file being repaired * plus the block we converted. */ - req->ip1_bcount = 1; + req->ip1_bcount = sf_resblks; req->ip2_bcount = sc->ip->i_nblocks; req->nr_exchanges = 1 + ifp->if_nextents; - req->resblks = 1; + req->resblks = sf_resblks; break; case 3: /* @@ -722,10 +737,10 @@ xrep_tempexch_estimate( * fileoff 0. Presumably, the caller could not exchange the * two inode fork areas directly. */ - req->ip1_bcount = 1; - req->ip2_bcount = 1; + req->ip1_bcount = sf_resblks; + req->ip2_bcount = sf_resblks; req->nr_exchanges = 1; - req->resblks = 2; + req->resblks = 2 * sf_resblks; break; } diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h index 14aa0ec1f09e4a..0f5adc293962fa 100644 --- a/fs/xfs/scrub/trace.h +++ b/fs/xfs/scrub/trace.h @@ -1640,7 +1640,7 @@ DECLARE_EVENT_CLASS(xchk_pptr_class, __entry->dev = ip->i_mount->m_super->s_dev; __entry->ino = I_INO(ip); __entry->namelen = name->len; - memcpy(__get_str(name), name, name->len); + memcpy(__get_str(name), name->name, name->len); __entry->far_ino = far_ino; ), TP_printk("dev %d:%d ino 0x%llx name '%.*s' far_ino 0x%llx", @@ -1706,6 +1706,39 @@ DEFINE_EVENT(xchk_dirtree_class, name, \ DEFINE_XCHK_DIRTREE_EVENT(xchk_dirtree_create_path); DEFINE_XCHK_DIRTREE_EVENT(xchk_dirpath_walk_upwards); +TRACE_EVENT(xchk_dirpath_badino, + TP_PROTO(struct xfs_scrub *sc, unsigned int path_nr, + unsigned int step_nr, const struct xfs_name *name, + const struct xfs_parent_rec *pptr), + TP_ARGS(sc, path_nr, step_nr, name, pptr), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(unsigned int, path_nr) + __field(unsigned int, step_nr) + __field(xfs_ino_t, parent_ino) + __field(unsigned int, parent_gen) + __field(unsigned int, namelen) + __dynamic_array(char, name, name->len) + ), + TP_fast_assign( + __entry->dev = sc->mp->m_super->s_dev; + __entry->path_nr = path_nr; + __entry->step_nr = step_nr; + __entry->parent_ino = be64_to_cpu(pptr->p_ino); + __entry->parent_gen = be32_to_cpu(pptr->p_gen); + __entry->namelen = name->len; + memcpy(__get_str(name), name->name, name->len); + ), + TP_printk("dev %d:%d path %u step %u parent_ino 0x%llx parent_gen 0x%x name '%.*s'", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->path_nr, + __entry->step_nr, + __entry->parent_ino, + __entry->parent_gen, + __entry->namelen, + __get_str(name)) +); + DECLARE_EVENT_CLASS(xchk_dirpath_class, TP_PROTO(struct xfs_scrub *sc, struct xfs_inode *ip, unsigned int path_nr, unsigned int step_nr, diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index 48d7dfd3e15f04..44e344fc51e912 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -108,7 +108,7 @@ xfs_buf_free( ASSERT(list_empty(&bp->b_lru)); if (!xfs_buftarg_is_mem(bp->b_target) && size >= PAGE_SIZE) - mm_account_reclaimed_pages(howmany(size, PAGE_SHIFT)); + mm_account_reclaimed_pages(howmany(size, PAGE_SIZE)); if (is_vmalloc_addr(bp->b_addr)) vfree(bp->b_addr); diff --git a/fs/xfs/xfs_exchmaps_item.c b/fs/xfs/xfs_exchmaps_item.c index c3745d33e54ea2..dd5d92ca1010fe 100644 --- a/fs/xfs/xfs_exchmaps_item.c +++ b/fs/xfs/xfs_exchmaps_item.c @@ -344,7 +344,17 @@ xfs_xmi_validate( if (!xfs_verify_fileext(mp, xlf->xmi_startoff1, xlf->xmi_blockcount)) return false; - return xfs_verify_fileext(mp, xlf->xmi_startoff2, xlf->xmi_blockcount); + if (!xfs_verify_fileext(mp, xlf->xmi_startoff2, xlf->xmi_blockcount)) + return false; + + if (xlf->xmi_flags & XFS_EXCHMAPS_SET_SIZES) { + if ((int64_t)xlf->xmi_isize1 < 0) + return false; + if ((int64_t)xlf->xmi_isize2 < 0) + return false; + } + + return true; } /* @@ -403,6 +413,13 @@ xfs_xmi_item_recover_intent( *ipp1 = ip1; *ipp2 = ip2; xmi = xfs_exchmaps_init_intent(req); + + /* Restore intended file sizes from recovered logged item */ + if (req->flags & XFS_EXCHMAPS_SET_SIZES) { + xmi->xmi_isize1 = xlf->xmi_isize1; + xmi->xmi_isize2 = xlf->xmi_isize2; + } + xfs_defer_add_item(dfp, &xmi->xmi_list); return xmi; diff --git a/fs/xfs/xfs_exchrange.c b/fs/xfs/xfs_exchrange.c index 94965a6c2187ff..c69ecd6a19de4f 100644 --- a/fs/xfs/xfs_exchrange.c +++ b/fs/xfs/xfs_exchrange.c @@ -504,6 +504,9 @@ xfs_exchange_range_finish( { int error; + if (fxr->flags & XFS_EXCHANGE_RANGE_DRY_RUN) + return 0; + error = file_remove_privs(fxr->file1); if (error) return error; @@ -783,9 +786,12 @@ xfs_exchange_range( if (ret) return ret; - fsnotify_modify(fxr->file1); - if (fxr->file2 != fxr->file1) - fsnotify_modify(fxr->file2); + if (!(fxr->flags & XFS_EXCHANGE_RANGE_DRY_RUN)) { + fsnotify_modify(fxr->file1); + if (fxr->file2 != fxr->file1) + fsnotify_modify(fxr->file2); + } + return 0; } diff --git a/fs/xfs/xfs_healthmon.c b/fs/xfs/xfs_healthmon.c index 4521ffdab9f1ae..acb85a1249a848 100644 --- a/fs/xfs/xfs_healthmon.c +++ b/fs/xfs/xfs_healthmon.c @@ -272,12 +272,13 @@ __xfs_healthmon_insert( { struct timespec64 now; + lockdep_assert_held(&hm->lock); + ktime_get_coarse_real_ts64(&now); event->time_ns = (now.tv_sec * NSEC_PER_SEC) + now.tv_nsec; event->next = hm->first_event; - if (!hm->first_event) - hm->first_event = event; + hm->first_event = event; if (!hm->last_event) hm->last_event = event; xfs_healthmon_bump_events(hm); @@ -294,6 +295,8 @@ __xfs_healthmon_push( { struct timespec64 now; + lockdep_assert_held(&hm->lock); + ktime_get_coarse_real_ts64(&now); event->time_ns = (now.tv_sec * NSEC_PER_SEC) + now.tv_nsec; @@ -330,8 +333,10 @@ xfs_healthmon_clear_lost_prev( if (hm->events < XFS_HEALTHMON_MAX_EVENTS) event = kmemdup(&lost_event, sizeof(struct xfs_healthmon_event), GFP_NOFS); - if (!event) + if (!event) { + xfs_healthmon_bump_lost(hm); return -ENOMEM; + } __xfs_healthmon_push(hm, event); cleared: @@ -415,8 +420,10 @@ xfs_healthmon_unmount( * There's nothing actionable for userspace after an unmount. Once * we've inserted the unmount event, hm no longer owns that event. */ + mutex_lock(&hm->lock); __xfs_healthmon_insert(hm, hm->unmount_event); hm->unmount_event = NULL; + mutex_unlock(&hm->lock); xfs_healthmon_detach(hm); xfs_healthmon_put(hm); @@ -738,6 +745,13 @@ static const unsigned int type_map[] = { [XFS_HEALTHMON_DATALOST] = XFS_HEALTH_MONITOR_TYPE_DATALOST, }; +static inline bool +xfs_healthmon_check_outbuffer_space(const struct xfs_healthmon *hm) +{ + return hm->bufhead + sizeof(struct xfs_health_monitor_event) <= + hm->bufsize; +} + /* Render event as a V0 structure */ STATIC int xfs_healthmon_format_v0( @@ -804,10 +818,10 @@ xfs_healthmon_format_v0( break; } - ASSERT(hm->bufhead + sizeof(hme) <= hm->bufsize); + ASSERT(xfs_healthmon_check_outbuffer_space(hm)); /* copy formatted object to the outbuf */ - if (hm->bufhead + sizeof(hme) <= hm->bufsize) { + if (xfs_healthmon_check_outbuffer_space(hm)) { memcpy(hm->buffer + hm->bufhead, &hme, sizeof(hme)); hm->bufhead += sizeof(hme); } @@ -890,7 +904,11 @@ xfs_healthmon_format_pop( { struct xfs_healthmon_event *event; - if (hm->bufhead + sizeof(*event) > hm->bufsize) + /* + * Don't bother if there's not enough space to format even one event in + * the outbuffer. + */ + if (!xfs_healthmon_check_outbuffer_space(hm)) return NULL; mutex_lock(&hm->lock); diff --git a/fs/xfs/xfs_verify_media.c b/fs/xfs/xfs_verify_media.c index 5ead3976d51151..b75c81f8fcc037 100644 --- a/fs/xfs/xfs_verify_media.c +++ b/fs/xfs/xfs_verify_media.c @@ -268,6 +268,8 @@ xfs_verify_media( struct xfs_buftarg *btp = NULL; struct bio *bio; struct folio *folio; + xfs_daddr_t dev_start = 0; + xfs_daddr_t dev_end = 0; xfs_daddr_t daddr; uint64_t bbcount; int error = 0; @@ -277,24 +279,33 @@ xfs_verify_media( switch (me->me_dev) { case XFS_DEV_DATA: btp = mp->m_ddev_targp; + dev_end = XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks); break; case XFS_DEV_LOG: - if (mp->m_logdev_targp != mp->m_ddev_targp) + if (mp->m_logdev_targp != mp->m_ddev_targp) { btp = mp->m_logdev_targp; + dev_end = XFS_FSB_TO_BB(mp, mp->m_sb.sb_logblocks); + } break; case XFS_DEV_RT: btp = mp->m_rtdev_targp; + dev_start = XFS_FSB_TO_BB(mp, mp->m_sb.sb_rtstart); + dev_end = XFS_FSB_TO_BB(mp, mp->m_sb.sb_rtstart + + mp->m_sb.sb_rblocks); break; } if (!btp) return -ENODEV; /* - * If the caller told us to verify beyond the end of the disk, tell the - * user exactly where that was. + * If the caller told us to verify before the start or beyond the end + * of the disk volume, tell the user exactly where the volume starts + * and ends. */ - if (me->me_end_daddr > btp->bt_nr_sectors) - me->me_end_daddr = btp->bt_nr_sectors; + if (me->me_end_daddr > dev_end) + me->me_end_daddr = dev_end; + if (me->me_start_daddr < dev_start) + me->me_start_daddr = dev_start; /* start and end have to be aligned to the lba size */ if (!IS_ALIGNED(BBTOB(me->me_start_daddr | me->me_end_daddr), @@ -323,8 +334,7 @@ xfs_verify_media( * verifying. */ daddr = me->me_start_daddr; - bbcount = min_t(sector_t, me->me_end_daddr, btp->bt_nr_sectors) - - me->me_start_daddr; + bbcount = me->me_end_daddr - me->me_start_daddr; folio = xfs_verify_alloc_folio(xfs_verify_iosize(me, btp, bbcount)); if (!folio) diff --git a/include/drm/drm_pagemap.h b/include/drm/drm_pagemap.h index 95eb4b66b0577f..ebbd3b0ddf3676 100644 --- a/include/drm/drm_pagemap.h +++ b/include/drm/drm_pagemap.h @@ -2,6 +2,7 @@ #ifndef _DRM_PAGEMAP_H_ #define _DRM_PAGEMAP_H_ +#include #include #include #include @@ -339,6 +340,9 @@ struct drm_pagemap_migrate_details { #if IS_ENABLED(CONFIG_ZONE_DEVICE) +#define DRM_PAGEMAP_ZDD_FLAG_MIGRATED BIT(0) +#define DRM_PAGEMAP_ZDD_FLAG_MASK DRM_PAGEMAP_ZDD_FLAG_MIGRATED + int drm_pagemap_migrate_to_devmem(struct drm_pagemap_devmem *devmem_allocation, struct mm_struct *mm, unsigned long start, unsigned long end, @@ -373,7 +377,9 @@ static inline struct drm_pagemap_zdd *drm_pagemap_page_zone_device_data(struct p { struct folio *folio = page_folio(page); - return folio_zone_device_data(folio); + return (struct drm_pagemap_zdd *) + ((unsigned long)folio_zone_device_data(folio) & + ~DRM_PAGEMAP_ZDD_FLAG_MASK); } #else diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 77e2075f77c737..c2c327dc0a72f2 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -894,6 +894,7 @@ enum bpf_arg_type { ARG_PTR_TO_CTX, /* pointer to context */ ARG_ANYTHING, /* any (initialized) argument is ok */ + ARG_SCALAR, /* scalar argument */ ARG_PTR_TO_SPIN_LOCK, /* pointer to bpf_spin_lock */ ARG_PTR_TO_SOCK_COMMON, /* pointer to sock_common */ ARG_PTR_TO_SOCKET, /* pointer to bpf_sock (fullsock) */ @@ -4184,7 +4185,7 @@ static inline int bpf_map_check_op_flags(struct bpf_map *map, u64 flags, u64 all return -EINVAL; cpu = flags >> 32; - if ((flags & BPF_F_CPU) && cpu >= num_possible_cpus()) + if ((flags & BPF_F_CPU) && (cpu >= nr_cpu_ids || !cpu_possible(cpu))) return -ERANGE; } diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 39a851e690ec41..7ad03ffb9300f8 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -385,6 +385,8 @@ struct bpf_func_state { * | number of simulations is tracked in frame N */ u32 callback_depth; + /* Instructions processed in this frame and callees on the current path. */ + u32 insns_subtotal; /* The following fields should be last. See copy_func_state() */ /* The state of the stack. Each element of the array describes BPF_REG_SIZE @@ -704,6 +706,8 @@ struct bpf_insn_aux_data { */ u32 calls_callback:1; u32 indirect_target:1; /* if it is an indirect jump target */ + /* true if some jump or call instruction targets this instruction */ + u32 jump_target:1; /* * CFG strongly connected component this instruction belongs to, * zero if it is a singleton SCC. @@ -803,7 +807,8 @@ struct bpf_subprog_info { u32 exit_idx; /* Index of one of the BPF_EXIT instructions in this subprogram */ u16 stack_depth; /* max. stack depth used by this function */ u16 stack_extra; - u32 insn_processed; + u32 insns_total; + u32 insns_self; /* offsets in range [stack_depth .. fastcall_stack_off) * are used for bpf_fastcall spills and fills. */ @@ -1115,6 +1120,16 @@ static inline void mark_jmp_point(struct bpf_verifier_env *env, int idx) env->insn_aux_data[idx].jmp_point = true; } +static inline void mark_jump_target(struct bpf_verifier_env *env, int idx) +{ + env->insn_aux_data[idx].jump_target = true; +} + +static inline bool bpf_is_jump_target(struct bpf_verifier_env *env, int insn_idx) +{ + return env->insn_aux_data[insn_idx].jump_target; +} + static inline struct bpf_func_state *cur_func(struct bpf_verifier_env *env) { struct bpf_verifier_state *cur = env->cur_state; @@ -1307,7 +1322,9 @@ static inline bool bpf_type_has_unsafe_modifiers(u32 type) static inline bool type_is_ptr_alloc_obj(u32 type) { - return base_type(type) == PTR_TO_BTF_ID && type_flag(type) & MEM_ALLOC; + return base_type(type) == PTR_TO_BTF_ID && + type_flag(type) & MEM_ALLOC && + !(type_flag(type) & PTR_UNTRUSTED); } static inline bool type_is_non_owning_ref(u32 type) diff --git a/include/linux/designware_i2c.h b/include/linux/designware_i2c.h new file mode 100644 index 00000000000000..53f37f18a7229d --- /dev/null +++ b/include/linux/designware_i2c.h @@ -0,0 +1,107 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Synopsys DesignWare I2C register definitions + * + * Copyright (C) 2026, Intel Corporation + */ + +#ifndef __LINUX_DESIGNWARE_I2C_H +#define __LINUX_DESIGNWARE_I2C_H + +#include + +/* + * Registers offset + */ +#define DW_IC_CON 0x00 +#define DW_IC_TAR 0x04 +#define DW_IC_SAR 0x08 +#define DW_IC_DATA_CMD 0x10 +#define DW_IC_SS_SCL_HCNT 0x14 +#define DW_IC_SS_SCL_LCNT 0x18 +#define DW_IC_FS_SCL_HCNT 0x1c +#define DW_IC_FS_SCL_LCNT 0x20 +#define DW_IC_HS_SCL_HCNT 0x24 +#define DW_IC_HS_SCL_LCNT 0x28 +#define DW_IC_INTR_STAT 0x2c +#define DW_IC_INTR_MASK 0x30 +#define DW_IC_RAW_INTR_STAT 0x34 +#define DW_IC_RX_TL 0x38 +#define DW_IC_TX_TL 0x3c +#define DW_IC_CLR_INTR 0x40 +#define DW_IC_CLR_RX_UNDER 0x44 +#define DW_IC_CLR_RX_OVER 0x48 +#define DW_IC_CLR_TX_OVER 0x4c +#define DW_IC_CLR_RD_REQ 0x50 +#define DW_IC_CLR_TX_ABRT 0x54 +#define DW_IC_CLR_RX_DONE 0x58 +#define DW_IC_CLR_ACTIVITY 0x5c +#define DW_IC_CLR_STOP_DET 0x60 +#define DW_IC_CLR_START_DET 0x64 +#define DW_IC_CLR_GEN_CALL 0x68 +#define DW_IC_ENABLE 0x6c +#define DW_IC_STATUS 0x70 +#define DW_IC_TXFLR 0x74 +#define DW_IC_RXFLR 0x78 +#define DW_IC_SDA_HOLD 0x7c +#define DW_IC_TX_ABRT_SOURCE 0x80 +#define DW_IC_ENABLE_STATUS 0x9c +#define DW_IC_CLR_RESTART_DET 0xa8 +#define DW_IC_SMBUS_INTR_STAT 0xc8 +#define DW_IC_SMBUS_INTR_MASK 0xcc +#define DW_IC_CLR_SMBUS_INTR 0xd4 +#define DW_IC_COMP_PARAM_1 0xf4 +#define DW_IC_COMP_VERSION 0xf8 +#define DW_IC_COMP_TYPE 0xfc + +/* DW_IC_CON bits */ +#define DW_IC_CON_MASTER BIT(0) +#define DW_IC_CON_SPEED_STD (1 << 1) +#define DW_IC_CON_SPEED_FAST (2 << 1) +#define DW_IC_CON_SPEED_HIGH (3 << 1) +#define DW_IC_CON_SPEED_MASK GENMASK(2, 1) +#define DW_IC_CON_10BITADDR_SLAVE BIT(3) +#define DW_IC_CON_10BITADDR_MASTER BIT(4) +#define DW_IC_CON_RESTART_EN BIT(5) +#define DW_IC_CON_SLAVE_DISABLE BIT(6) +#define DW_IC_CON_STOP_DET_IFADDRESSED BIT(7) +#define DW_IC_CON_TX_EMPTY_CTRL BIT(8) +#define DW_IC_CON_RX_FIFO_FULL_HLD_CTRL BIT(9) +#define DW_IC_CON_BUS_CLEAR_CTRL BIT(11) + +/* DW_IC_DATA_CMD bits */ +#define DW_IC_DATA_CMD_DAT GENMASK(7, 0) +#define DW_IC_DATA_CMD_FIRST_DATA_BYTE BIT(11) + +/* DW_IC_INTR_* bits */ +#define DW_IC_INTR_RX_UNDER BIT(0) +#define DW_IC_INTR_RX_OVER BIT(1) +#define DW_IC_INTR_RX_FULL BIT(2) +#define DW_IC_INTR_TX_OVER BIT(3) +#define DW_IC_INTR_TX_EMPTY BIT(4) +#define DW_IC_INTR_RD_REQ BIT(5) +#define DW_IC_INTR_TX_ABRT BIT(6) +#define DW_IC_INTR_RX_DONE BIT(7) +#define DW_IC_INTR_ACTIVITY BIT(8) +#define DW_IC_INTR_STOP_DET BIT(9) +#define DW_IC_INTR_START_DET BIT(10) +#define DW_IC_INTR_GEN_CALL BIT(11) +#define DW_IC_INTR_RESTART_DET BIT(12) +#define DW_IC_INTR_MST_ON_HOLD BIT(13) + +/* DW_IC_ENABLE bits */ +#define DW_IC_ENABLE_ENABLE BIT(0) +#define DW_IC_ENABLE_ABORT BIT(1) + +/* DW_IC_STATUS bits */ +#define DW_IC_STATUS_ACTIVITY BIT(0) +#define DW_IC_STATUS_TFE BIT(2) +#define DW_IC_STATUS_RFNE BIT(3) +#define DW_IC_STATUS_MASTER_ACTIVITY BIT(5) +#define DW_IC_STATUS_SLAVE_ACTIVITY BIT(6) +#define DW_IC_STATUS_MASTER_HOLD_TX_FIFO_EMPTY BIT(7) + +/* DW_IC_SMBUS_INTR_* bits */ +#define DW_IC_SMBUS_INTR_ALERT BIT(10) + +#endif /* __LINUX_DESIGNWARE_I2C_H */ diff --git a/include/linux/dma-fence-array.h b/include/linux/dma-fence-array.h index 1b1d87579c382d..0c49d7ccefb649 100644 --- a/include/linux/dma-fence-array.h +++ b/include/linux/dma-fence-array.h @@ -28,7 +28,6 @@ struct dma_fence_array_cb { /** * struct dma_fence_array - fence to represent an array of fences * @base: fence base class - * @lock: spinlock for fence handling * @num_fences: number of fences in the array * @num_pending: fences in the array still pending * @fences: array of the fences diff --git a/include/linux/dma-fence-chain.h b/include/linux/dma-fence-chain.h index df3beadf151573..705c4394ac0d0d 100644 --- a/include/linux/dma-fence-chain.h +++ b/include/linux/dma-fence-chain.h @@ -20,7 +20,6 @@ * @prev: previous fence of the chain * @prev_seqno: original previous seqno before garbage collection * @fence: encapsulated fence - * @lock: spinlock for fence handling */ struct dma_fence_chain { struct dma_fence base; @@ -81,9 +80,8 @@ dma_fence_chain_contained(struct dma_fence *fence) } /** - * dma_fence_chain_alloc - * - * Returns a new struct dma_fence_chain object or NULL on failure. + * dma_fence_chain_alloc - Returns a new &struct dma_fence_chain object or + * %NULL on failure. * * This specialized allocator has to be a macro for its allocations to be * accounted separately (to have a separate alloc_tag). The typecast is @@ -93,7 +91,8 @@ dma_fence_chain_contained(struct dma_fence *fence) kmalloc_obj(struct dma_fence_chain) /** - * dma_fence_chain_free + * dma_fence_chain_free - Frees an allocated but not used + * &struct dma_fence_chain object. * @chain: chain node to free * * Frees up an allocated but not used struct dma_fence_chain object. This diff --git a/include/linux/igmp.h b/include/linux/igmp.h index 3a2d35a9f3078f..a0cf0398519fd7 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -57,20 +57,21 @@ struct ip_mc_socklist { }; struct ip_sf_list { - struct ip_sf_list *sf_next; + struct ip_sf_list __rcu *sf_next; unsigned long sf_count[2]; /* include/exclude counts */ __be32 sf_inaddr; unsigned char sf_gsresp; /* include in g & s response? */ unsigned char sf_oldin; /* change state */ unsigned char sf_crcount; /* retrans. left to send */ + struct rcu_head rcu; }; struct ip_mc_list { struct in_device *interface; __be32 multiaddr; unsigned int sfmode; - struct ip_sf_list *sources; - struct ip_sf_list *tomb; + struct ip_sf_list __rcu *sources; + struct ip_sf_list __rcu *tomb; unsigned long sfcount[2]; union { struct ip_mc_list *next; diff --git a/include/linux/mfd/db8500-prcmu.h b/include/linux/mfd/db8500-prcmu.h index a62de3d155edc8..c939c9a1170a08 100644 --- a/include/linux/mfd/db8500-prcmu.h +++ b/include/linux/mfd/db8500-prcmu.h @@ -12,6 +12,9 @@ #include #include +#include + +#include /* For clock identifiers */ /* * Registers @@ -24,6 +27,38 @@ #define DB8500_PRCM_DSI_SW_RESET_DSI1_SW_RESETN BIT(1) #define DB8500_PRCM_DSI_SW_RESET_DSI2_SW_RESETN BIT(2) +/* Offset for the firmware version within the TCPM */ +#define DB8500_PRCMU_FW_VERSION_OFFSET 0xA4 + +#define DB8500_PRCMU_LEGACY_OFFSET 0xDD4 + +/* + * CLKOUT sources + */ +#define PRCMU_CLKSRC_CLK38M 0x00 +#define PRCMU_CLKSRC_ACLK 0x01 +#define PRCMU_CLKSRC_SYSCLK 0x02 +#define PRCMU_CLKSRC_LCDCLK 0x03 +#define PRCMU_CLKSRC_SDMMCCLK 0x04 +#define PRCMU_CLKSRC_TVCLK 0x05 +#define PRCMU_CLKSRC_TIMCLK 0x06 +#define PRCMU_CLKSRC_CLK009 0x07 +/* These are only valid for CLKOUT1: */ +#define PRCMU_CLKSRC_SIAMMDSPCLK 0x40 +#define PRCMU_CLKSRC_I2CCLK 0x41 +#define PRCMU_CLKSRC_MSP02CLK 0x42 +#define PRCMU_CLKSRC_ARMPLL_OBSCLK 0x43 +#define PRCMU_CLKSRC_HSIRXCLK 0x44 +#define PRCMU_CLKSRC_HSITXCLK 0x45 +#define PRCMU_CLKSRC_ARMCLKFIX 0x46 +#define PRCMU_CLKSRC_HDMICLK 0x47 + +/* + * Definitions for controlling ESRAM0 in deep sleep. + */ +#define ESRAM0_DEEP_SLEEP_STATE_OFF 1 +#define ESRAM0_DEEP_SLEEP_STATE_RET 2 + /* This portion previously known as */ /** @@ -451,10 +486,173 @@ enum prcmu_power_status { PRCMU_ARMPENDINGIT_ER = 0x93, }; +/* PRCMU Wakeup defines */ +enum prcmu_wakeup_index { + PRCMU_WAKEUP_INDEX_RTC, + PRCMU_WAKEUP_INDEX_RTT0, + PRCMU_WAKEUP_INDEX_RTT1, + PRCMU_WAKEUP_INDEX_HSI0, + PRCMU_WAKEUP_INDEX_HSI1, + PRCMU_WAKEUP_INDEX_USB, + PRCMU_WAKEUP_INDEX_ABB, + PRCMU_WAKEUP_INDEX_ABB_FIFO, + PRCMU_WAKEUP_INDEX_ARM, + PRCMU_WAKEUP_INDEX_CD_IRQ, + NUM_PRCMU_WAKEUP_INDICES +}; + +#define PRCMU_WAKEUP(_name) (BIT(PRCMU_WAKEUP_INDEX_##_name)) + +/** + * enum prcmu_wdog_id - PRCMU watchdog IDs + * @PRCMU_WDOG_ALL: use all timers + * @PRCMU_WDOG_CPU1: use first CPU timer only + * @PRCMU_WDOG_CPU2: use second CPU timer conly + */ +enum prcmu_wdog_id { + PRCMU_WDOG_ALL = 0x00, + PRCMU_WDOG_CPU1 = 0x01, + PRCMU_WDOG_CPU2 = 0x02, +}; + +/** + * enum ape_opp - APE OPP states definition + * @APE_OPP_INIT: + * @APE_NO_CHANGE: The APE operating point is unchanged + * @APE_100_OPP: The new APE operating point is ape100opp + * @APE_50_OPP: 50% + * @APE_50_PARTLY_25_OPP: 50%, except some clocks at 25%. + */ +enum ape_opp { + APE_OPP_INIT = 0x00, + APE_NO_CHANGE = 0x01, + APE_100_OPP = 0x02, + APE_50_OPP = 0x03, + APE_50_PARTLY_25_OPP = 0xFF, +}; + +/** + * enum arm_opp - ARM OPP states definition + * @ARM_OPP_INIT: + * @ARM_NO_CHANGE: The ARM operating point is unchanged + * @ARM_100_OPP: The new ARM operating point is arm100opp + * @ARM_50_OPP: The new ARM operating point is arm50opp + * @ARM_MAX_OPP: Operating point is "max" (more than 100) + * @ARM_MAX_FREQ100OPP: Set max opp if available, else 100 + * @ARM_EXTCLK: The new ARM operating point is armExtClk + */ +enum arm_opp { + ARM_OPP_INIT = 0x00, + ARM_NO_CHANGE = 0x01, + ARM_100_OPP = 0x02, + ARM_50_OPP = 0x03, + ARM_MAX_OPP = 0x04, + ARM_MAX_FREQ100OPP = 0x05, + ARM_EXTCLK = 0x07 +}; + +/** + * enum ddr_opp - DDR OPP states definition + * @DDR_100_OPP: The new DDR operating point is ddr100opp + * @DDR_50_OPP: The new DDR operating point is ddr50opp + * @DDR_25_OPP: The new DDR operating point is ddr25opp + */ +enum ddr_opp { + DDR_100_OPP = 0x00, + DDR_50_OPP = 0x01, + DDR_25_OPP = 0x02, +}; + +/** + * enum ddr_pwrst - DDR power states definition + * @DDR_PWR_STATE_UNCHANGED: SDRAM and DDR controller state is unchanged + * @DDR_PWR_STATE_ON: + * @DDR_PWR_STATE_OFFLOWLAT: + * @DDR_PWR_STATE_OFFHIGHLAT: + */ +enum ddr_pwrst { + DDR_PWR_STATE_UNCHANGED = 0x00, + DDR_PWR_STATE_ON = 0x01, + DDR_PWR_STATE_OFFLOWLAT = 0x02, + DDR_PWR_STATE_OFFHIGHLAT = 0x03 +}; + /* * Definitions for autonomous power management configuration. */ +/* EPOD (power domain) IDs */ + +/* + * DB8500 EPODs + * - EPOD_ID_SVAMMDSP: power domain for SVA MMDSP + * - EPOD_ID_SVAPIPE: power domain for SVA pipe + * - EPOD_ID_SIAMMDSP: power domain for SIA MMDSP + * - EPOD_ID_SIAPIPE: power domain for SIA pipe + * - EPOD_ID_SGA: power domain for SGA + * - EPOD_ID_B2R2_MCDE: power domain for B2R2 and MCDE + * - EPOD_ID_ESRAM12: power domain for ESRAM 1 and 2 + * - EPOD_ID_ESRAM34: power domain for ESRAM 3 and 4 + * - NUM_EPOD_ID: number of power domains + * + * TODO: These should be prefixed. + */ +#define EPOD_ID_SVAMMDSP 0 +#define EPOD_ID_SVAPIPE 1 +#define EPOD_ID_SIAMMDSP 2 +#define EPOD_ID_SIAPIPE 3 +#define EPOD_ID_SGA 4 +#define EPOD_ID_B2R2_MCDE 5 +#define EPOD_ID_ESRAM12 6 +#define EPOD_ID_ESRAM34 7 +#define NUM_EPOD_ID 8 + +/* + * state definition for EPOD (power domain) + * - EPOD_STATE_NO_CHANGE: The EPOD should remain unchanged + * - EPOD_STATE_OFF: The EPOD is switched off + * - EPOD_STATE_RAMRET: The EPOD is switched off with its internal RAM in + * retention + * - EPOD_STATE_ON_CLK_OFF: The EPOD is switched on, clock is still off + * - EPOD_STATE_ON: Same as above, but with clock enabled + */ +#define EPOD_STATE_NO_CHANGE 0x00 +#define EPOD_STATE_OFF 0x01 +#define EPOD_STATE_RAMRET 0x02 +#define EPOD_STATE_ON_CLK_OFF 0x03 +#define EPOD_STATE_ON 0x04 + +#define PRCMU_FW_PROJECT_U8500 2 +#define PRCMU_FW_PROJECT_U8400 3 +#define PRCMU_FW_PROJECT_U9500 4 /* Customer specific */ +#define PRCMU_FW_PROJECT_U8500_MBB 5 +#define PRCMU_FW_PROJECT_U8500_C1 6 +#define PRCMU_FW_PROJECT_U8500_C2 7 +#define PRCMU_FW_PROJECT_U8500_C3 8 +#define PRCMU_FW_PROJECT_U8500_C4 9 +#define PRCMU_FW_PROJECT_U9500_MBL 10 +#define PRCMU_FW_PROJECT_U8500_SSG1 11 /* Samsung specific */ +#define PRCMU_FW_PROJECT_U8500_MBL2 12 /* Customer specific */ +#define PRCMU_FW_PROJECT_U8520 13 +#define PRCMU_FW_PROJECT_U8420 14 +#define PRCMU_FW_PROJECT_U8500_SSG2 15 /* Samsung specific */ +#define PRCMU_FW_PROJECT_U8420_SYSCLK 17 +#define PRCMU_FW_PROJECT_A9420 20 +/* [32..63] 9540 and derivatives */ +#define PRCMU_FW_PROJECT_U9540 32 +/* [64..95] 8540 and derivatives */ +#define PRCMU_FW_PROJECT_L8540 64 +/* [96..126] 8580 and derivatives */ +#define PRCMU_FW_PROJECT_L8580 96 + +#define PRCMU_FW_PROJECT_NAME_LEN 20 + +/* PRCMU QoS APE OPP class */ +#define PRCMU_QOS_APE_OPP 1 +#define PRCMU_QOS_DDR_OPP 2 +#define PRCMU_QOS_ARM_OPP 3 +#define PRCMU_QOS_DEFAULT_VALUE -1 + #define PRCMU_AUTO_PM_OFF 0 #define PRCMU_AUTO_PM_ON 1 @@ -469,6 +667,14 @@ enum prcmu_auto_pm_policy { PRCMU_AUTO_PM_POLICY_DSP_CLK_OFF_HWP_CLK_OFF, }; +struct prcmu_fw_version { + u32 project; /* Notice, project shifted with 8 on ux540 */ + u8 api_version; + u8 func_version; + u8 errata; + char project_name[PRCMU_FW_PROJECT_NAME_LEN]; +}; + /** * struct prcmu_auto_pm_config - Autonomous power management configuration. * @sia_auto_pm_enable: SIA autonomous pm enable. (PRCMU_AUTO_PM_{OFF,ON}) @@ -501,6 +707,9 @@ void prcmu_configure_auto_pm(struct prcmu_auto_pm_config *sleep, bool prcmu_is_auto_pm_enabled(void); int prcmu_config_clkout(u8 clkout, u8 source, u8 div); +unsigned long prcmu_clock_rate(u8 clock); +long prcmu_round_clock_rate(u8 clock, unsigned long rate); +int prcmu_set_clock_rate(u8 clock, unsigned long rate); int prcmu_set_clock_divider(u8 clock, u8 divider); int db8500_prcmu_config_hotdog(u8 threshold); int db8500_prcmu_config_hotmon(u8 low, u8 high); @@ -508,6 +717,8 @@ int db8500_prcmu_start_temp_sense(u16 cycles32k); int db8500_prcmu_stop_temp_sense(void); int prcmu_abb_read(u8 slave, u8 reg, u8 *value, u8 size); int prcmu_abb_write(u8 slave, u8 reg, u8 *value, u8 size); +int prcmu_abb_write_masked(u8 slave, u8 reg, u8 *value, + u8 *mask, u8 size); int prcmu_ac_wake_req(void); void prcmu_ac_sleep_req(void); @@ -610,6 +821,21 @@ static inline int prcmu_config_clkout(u8 clkout, u8 source, u8 div) return 0; } +static inline unsigned long prcmu_clock_rate(u8 clock) +{ + return 0; +} + +static inline long prcmu_round_clock_rate(u8 clock, unsigned long rate) +{ + return 0; +} + +static inline int prcmu_set_clock_rate(u8 clock, unsigned long rate) +{ + return 0; +} + static inline int prcmu_set_clock_divider(u8 clock, u8 divider) { return 0; @@ -637,12 +863,18 @@ static inline int db8500_prcmu_stop_temp_sense(void) static inline int prcmu_abb_read(u8 slave, u8 reg, u8 *value, u8 size) { - return -ENOSYS; + return -EINVAL; } static inline int prcmu_abb_write(u8 slave, u8 reg, u8 *value, u8 size) { - return -ENOSYS; + return -EINVAL; +} + +static inline int prcmu_abb_write_masked(u8 slave, u8 reg, + u8 *value, u8 *mask, u8 size) +{ + return -EINVAL; } static inline int prcmu_ac_wake_req(void) @@ -745,4 +977,20 @@ static inline void db8500_prcmu_write_masked(unsigned int reg, u32 mask, #endif /* !CONFIG_MFD_DB8500_PRCMU */ +static inline int prcmu_qos_add_requirement(int prcmu_qos_class, + char *name, s32 value) +{ + return 0; +} + +static inline int prcmu_qos_update_requirement(int prcmu_qos_class, + char *name, s32 new_value) +{ + return 0; +} + +static inline void prcmu_qos_remove_requirement(int prcmu_qos_class, char *name) +{ +} + #endif /* __MFD_DB8500_PRCMU_H */ diff --git a/include/linux/mfd/dbx500-prcmu.h b/include/linux/mfd/dbx500-prcmu.h deleted file mode 100644 index 828362b7860c6c..00000000000000 --- a/include/linux/mfd/dbx500-prcmu.h +++ /dev/null @@ -1,575 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) ST Ericsson SA 2011 - * - * STE Ux500 PRCMU API - */ -#ifndef __MACH_PRCMU_H -#define __MACH_PRCMU_H - -#include -#include -#include - -#include /* For clock identifiers */ - -/* Offset for the firmware version within the TCPM */ -#define DB8500_PRCMU_FW_VERSION_OFFSET 0xA4 -#define DBX540_PRCMU_FW_VERSION_OFFSET 0xA8 - -/* PRCMU Wakeup defines */ -enum prcmu_wakeup_index { - PRCMU_WAKEUP_INDEX_RTC, - PRCMU_WAKEUP_INDEX_RTT0, - PRCMU_WAKEUP_INDEX_RTT1, - PRCMU_WAKEUP_INDEX_HSI0, - PRCMU_WAKEUP_INDEX_HSI1, - PRCMU_WAKEUP_INDEX_USB, - PRCMU_WAKEUP_INDEX_ABB, - PRCMU_WAKEUP_INDEX_ABB_FIFO, - PRCMU_WAKEUP_INDEX_ARM, - PRCMU_WAKEUP_INDEX_CD_IRQ, - NUM_PRCMU_WAKEUP_INDICES -}; -#define PRCMU_WAKEUP(_name) (BIT(PRCMU_WAKEUP_INDEX_##_name)) - -/* EPOD (power domain) IDs */ - -/* - * DB8500 EPODs - * - EPOD_ID_SVAMMDSP: power domain for SVA MMDSP - * - EPOD_ID_SVAPIPE: power domain for SVA pipe - * - EPOD_ID_SIAMMDSP: power domain for SIA MMDSP - * - EPOD_ID_SIAPIPE: power domain for SIA pipe - * - EPOD_ID_SGA: power domain for SGA - * - EPOD_ID_B2R2_MCDE: power domain for B2R2 and MCDE - * - EPOD_ID_ESRAM12: power domain for ESRAM 1 and 2 - * - EPOD_ID_ESRAM34: power domain for ESRAM 3 and 4 - * - NUM_EPOD_ID: number of power domains - * - * TODO: These should be prefixed. - */ -#define EPOD_ID_SVAMMDSP 0 -#define EPOD_ID_SVAPIPE 1 -#define EPOD_ID_SIAMMDSP 2 -#define EPOD_ID_SIAPIPE 3 -#define EPOD_ID_SGA 4 -#define EPOD_ID_B2R2_MCDE 5 -#define EPOD_ID_ESRAM12 6 -#define EPOD_ID_ESRAM34 7 -#define NUM_EPOD_ID 8 - -/* - * state definition for EPOD (power domain) - * - EPOD_STATE_NO_CHANGE: The EPOD should remain unchanged - * - EPOD_STATE_OFF: The EPOD is switched off - * - EPOD_STATE_RAMRET: The EPOD is switched off with its internal RAM in - * retention - * - EPOD_STATE_ON_CLK_OFF: The EPOD is switched on, clock is still off - * - EPOD_STATE_ON: Same as above, but with clock enabled - */ -#define EPOD_STATE_NO_CHANGE 0x00 -#define EPOD_STATE_OFF 0x01 -#define EPOD_STATE_RAMRET 0x02 -#define EPOD_STATE_ON_CLK_OFF 0x03 -#define EPOD_STATE_ON 0x04 - -/* - * CLKOUT sources - */ -#define PRCMU_CLKSRC_CLK38M 0x00 -#define PRCMU_CLKSRC_ACLK 0x01 -#define PRCMU_CLKSRC_SYSCLK 0x02 -#define PRCMU_CLKSRC_LCDCLK 0x03 -#define PRCMU_CLKSRC_SDMMCCLK 0x04 -#define PRCMU_CLKSRC_TVCLK 0x05 -#define PRCMU_CLKSRC_TIMCLK 0x06 -#define PRCMU_CLKSRC_CLK009 0x07 -/* These are only valid for CLKOUT1: */ -#define PRCMU_CLKSRC_SIAMMDSPCLK 0x40 -#define PRCMU_CLKSRC_I2CCLK 0x41 -#define PRCMU_CLKSRC_MSP02CLK 0x42 -#define PRCMU_CLKSRC_ARMPLL_OBSCLK 0x43 -#define PRCMU_CLKSRC_HSIRXCLK 0x44 -#define PRCMU_CLKSRC_HSITXCLK 0x45 -#define PRCMU_CLKSRC_ARMCLKFIX 0x46 -#define PRCMU_CLKSRC_HDMICLK 0x47 - -/** - * enum prcmu_wdog_id - PRCMU watchdog IDs - * @PRCMU_WDOG_ALL: use all timers - * @PRCMU_WDOG_CPU1: use first CPU timer only - * @PRCMU_WDOG_CPU2: use second CPU timer conly - */ -enum prcmu_wdog_id { - PRCMU_WDOG_ALL = 0x00, - PRCMU_WDOG_CPU1 = 0x01, - PRCMU_WDOG_CPU2 = 0x02, -}; - -/** - * enum ape_opp - APE OPP states definition - * @APE_OPP_INIT: - * @APE_NO_CHANGE: The APE operating point is unchanged - * @APE_100_OPP: The new APE operating point is ape100opp - * @APE_50_OPP: 50% - * @APE_50_PARTLY_25_OPP: 50%, except some clocks at 25%. - */ -enum ape_opp { - APE_OPP_INIT = 0x00, - APE_NO_CHANGE = 0x01, - APE_100_OPP = 0x02, - APE_50_OPP = 0x03, - APE_50_PARTLY_25_OPP = 0xFF, -}; - -/** - * enum arm_opp - ARM OPP states definition - * @ARM_OPP_INIT: - * @ARM_NO_CHANGE: The ARM operating point is unchanged - * @ARM_100_OPP: The new ARM operating point is arm100opp - * @ARM_50_OPP: The new ARM operating point is arm50opp - * @ARM_MAX_OPP: Operating point is "max" (more than 100) - * @ARM_MAX_FREQ100OPP: Set max opp if available, else 100 - * @ARM_EXTCLK: The new ARM operating point is armExtClk - */ -enum arm_opp { - ARM_OPP_INIT = 0x00, - ARM_NO_CHANGE = 0x01, - ARM_100_OPP = 0x02, - ARM_50_OPP = 0x03, - ARM_MAX_OPP = 0x04, - ARM_MAX_FREQ100OPP = 0x05, - ARM_EXTCLK = 0x07 -}; - -/** - * enum ddr_opp - DDR OPP states definition - * @DDR_100_OPP: The new DDR operating point is ddr100opp - * @DDR_50_OPP: The new DDR operating point is ddr50opp - * @DDR_25_OPP: The new DDR operating point is ddr25opp - */ -enum ddr_opp { - DDR_100_OPP = 0x00, - DDR_50_OPP = 0x01, - DDR_25_OPP = 0x02, -}; - -/* - * Definitions for controlling ESRAM0 in deep sleep. - */ -#define ESRAM0_DEEP_SLEEP_STATE_OFF 1 -#define ESRAM0_DEEP_SLEEP_STATE_RET 2 - -/** - * enum ddr_pwrst - DDR power states definition - * @DDR_PWR_STATE_UNCHANGED: SDRAM and DDR controller state is unchanged - * @DDR_PWR_STATE_ON: - * @DDR_PWR_STATE_OFFLOWLAT: - * @DDR_PWR_STATE_OFFHIGHLAT: - */ -enum ddr_pwrst { - DDR_PWR_STATE_UNCHANGED = 0x00, - DDR_PWR_STATE_ON = 0x01, - DDR_PWR_STATE_OFFLOWLAT = 0x02, - DDR_PWR_STATE_OFFHIGHLAT = 0x03 -}; - -#define DB8500_PRCMU_LEGACY_OFFSET 0xDD4 - -#define PRCMU_FW_PROJECT_U8500 2 -#define PRCMU_FW_PROJECT_U8400 3 -#define PRCMU_FW_PROJECT_U9500 4 /* Customer specific */ -#define PRCMU_FW_PROJECT_U8500_MBB 5 -#define PRCMU_FW_PROJECT_U8500_C1 6 -#define PRCMU_FW_PROJECT_U8500_C2 7 -#define PRCMU_FW_PROJECT_U8500_C3 8 -#define PRCMU_FW_PROJECT_U8500_C4 9 -#define PRCMU_FW_PROJECT_U9500_MBL 10 -#define PRCMU_FW_PROJECT_U8500_SSG1 11 /* Samsung specific */ -#define PRCMU_FW_PROJECT_U8500_MBL2 12 /* Customer specific */ -#define PRCMU_FW_PROJECT_U8520 13 -#define PRCMU_FW_PROJECT_U8420 14 -#define PRCMU_FW_PROJECT_U8500_SSG2 15 /* Samsung specific */ -#define PRCMU_FW_PROJECT_U8420_SYSCLK 17 -#define PRCMU_FW_PROJECT_A9420 20 -/* [32..63] 9540 and derivatives */ -#define PRCMU_FW_PROJECT_U9540 32 -/* [64..95] 8540 and derivatives */ -#define PRCMU_FW_PROJECT_L8540 64 -/* [96..126] 8580 and derivatives */ -#define PRCMU_FW_PROJECT_L8580 96 - -#define PRCMU_FW_PROJECT_NAME_LEN 20 -struct prcmu_fw_version { - u32 project; /* Notice, project shifted with 8 on ux540 */ - u8 api_version; - u8 func_version; - u8 errata; - char project_name[PRCMU_FW_PROJECT_NAME_LEN]; -}; - -#include - -#if defined(CONFIG_UX500_SOC_DB8500) - -static inline void __init prcmu_early_init(void) -{ - db8500_prcmu_early_init(); -} - -static inline int prcmu_set_power_state(u8 state, bool keep_ulp_clk, - bool keep_ap_pll) -{ - return db8500_prcmu_set_power_state(state, keep_ulp_clk, - keep_ap_pll); -} - -static inline u8 prcmu_get_power_state_result(void) -{ - return db8500_prcmu_get_power_state_result(); -} - -static inline int prcmu_set_epod(u16 epod_id, u8 epod_state) -{ - return db8500_prcmu_set_epod(epod_id, epod_state); -} - -static inline void prcmu_enable_wakeups(u32 wakeups) -{ - db8500_prcmu_enable_wakeups(wakeups); -} - -static inline void prcmu_disable_wakeups(void) -{ - prcmu_enable_wakeups(0); -} - -static inline void prcmu_config_abb_event_readout(u32 abb_events) -{ - db8500_prcmu_config_abb_event_readout(abb_events); -} - -static inline void prcmu_get_abb_event_buffer(void __iomem **buf) -{ - db8500_prcmu_get_abb_event_buffer(buf); -} - -int prcmu_abb_read(u8 slave, u8 reg, u8 *value, u8 size); -int prcmu_abb_write(u8 slave, u8 reg, u8 *value, u8 size); -int prcmu_abb_write_masked(u8 slave, u8 reg, u8 *value, u8 *mask, u8 size); - -int prcmu_config_clkout(u8 clkout, u8 source, u8 div); - -static inline int prcmu_request_clock(u8 clock, bool enable) -{ - return db8500_prcmu_request_clock(clock, enable); -} - -unsigned long prcmu_clock_rate(u8 clock); -long prcmu_round_clock_rate(u8 clock, unsigned long rate); -int prcmu_set_clock_rate(u8 clock, unsigned long rate); - -static inline int prcmu_get_ddr_opp(void) -{ - return db8500_prcmu_get_ddr_opp(); -} - -static inline int prcmu_set_arm_opp(u8 opp) -{ - return db8500_prcmu_set_arm_opp(opp); -} - -static inline int prcmu_get_arm_opp(void) -{ - return db8500_prcmu_get_arm_opp(); -} - -static inline int prcmu_set_ape_opp(u8 opp) -{ - return db8500_prcmu_set_ape_opp(opp); -} - -static inline int prcmu_get_ape_opp(void) -{ - return db8500_prcmu_get_ape_opp(); -} - -static inline int prcmu_request_ape_opp_100_voltage(bool enable) -{ - return db8500_prcmu_request_ape_opp_100_voltage(enable); -} - -static inline void prcmu_system_reset(u16 reset_code) -{ - db8500_prcmu_system_reset(reset_code); -} - -static inline u16 prcmu_get_reset_code(void) -{ - return db8500_prcmu_get_reset_code(); -} - -int prcmu_ac_wake_req(void); -void prcmu_ac_sleep_req(void); -static inline void prcmu_modem_reset(void) -{ - db8500_prcmu_modem_reset(); -} - -static inline bool prcmu_is_ac_wake_requested(void) -{ - return db8500_prcmu_is_ac_wake_requested(); -} - -static inline int prcmu_config_esram0_deep_sleep(u8 state) -{ - return db8500_prcmu_config_esram0_deep_sleep(state); -} - -static inline int prcmu_config_hotdog(u8 threshold) -{ - return db8500_prcmu_config_hotdog(threshold); -} - -static inline int prcmu_config_hotmon(u8 low, u8 high) -{ - return db8500_prcmu_config_hotmon(low, high); -} - -static inline int prcmu_start_temp_sense(u16 cycles32k) -{ - return db8500_prcmu_start_temp_sense(cycles32k); -} - -static inline int prcmu_stop_temp_sense(void) -{ - return db8500_prcmu_stop_temp_sense(); -} - -static inline u32 prcmu_read(unsigned int reg) -{ - return db8500_prcmu_read(reg); -} - -static inline void prcmu_write(unsigned int reg, u32 value) -{ - db8500_prcmu_write(reg, value); -} - -static inline void prcmu_write_masked(unsigned int reg, u32 mask, u32 value) -{ - db8500_prcmu_write_masked(reg, mask, value); -} - -static inline int prcmu_enable_a9wdog(u8 id) -{ - return db8500_prcmu_enable_a9wdog(id); -} - -static inline int prcmu_disable_a9wdog(u8 id) -{ - return db8500_prcmu_disable_a9wdog(id); -} - -static inline int prcmu_kick_a9wdog(u8 id) -{ - return db8500_prcmu_kick_a9wdog(id); -} - -static inline int prcmu_load_a9wdog(u8 id, u32 timeout) -{ - return db8500_prcmu_load_a9wdog(id, timeout); -} - -static inline int prcmu_config_a9wdog(u8 num, bool sleep_auto_off) -{ - return db8500_prcmu_config_a9wdog(num, sleep_auto_off); -} -#else - -static inline void prcmu_early_init(void) {} - -static inline int prcmu_set_power_state(u8 state, bool keep_ulp_clk, - bool keep_ap_pll) -{ - return 0; -} - -static inline int prcmu_set_epod(u16 epod_id, u8 epod_state) -{ - return 0; -} - -static inline void prcmu_enable_wakeups(u32 wakeups) {} - -static inline void prcmu_disable_wakeups(void) {} - -static inline int prcmu_abb_read(u8 slave, u8 reg, u8 *value, u8 size) -{ - return -ENOSYS; -} - -static inline int prcmu_abb_write(u8 slave, u8 reg, u8 *value, u8 size) -{ - return -ENOSYS; -} - -static inline int prcmu_abb_write_masked(u8 slave, u8 reg, u8 *value, u8 *mask, - u8 size) -{ - return -ENOSYS; -} - -static inline int prcmu_config_clkout(u8 clkout, u8 source, u8 div) -{ - return 0; -} - -static inline int prcmu_request_clock(u8 clock, bool enable) -{ - return 0; -} - -static inline long prcmu_round_clock_rate(u8 clock, unsigned long rate) -{ - return 0; -} - -static inline int prcmu_set_clock_rate(u8 clock, unsigned long rate) -{ - return 0; -} - -static inline unsigned long prcmu_clock_rate(u8 clock) -{ - return 0; -} - -static inline int prcmu_set_ape_opp(u8 opp) -{ - return 0; -} - -static inline int prcmu_get_ape_opp(void) -{ - return APE_100_OPP; -} - -static inline int prcmu_request_ape_opp_100_voltage(bool enable) -{ - return 0; -} - -static inline int prcmu_set_arm_opp(u8 opp) -{ - return 0; -} - -static inline int prcmu_get_arm_opp(void) -{ - return ARM_100_OPP; -} - -static inline int prcmu_get_ddr_opp(void) -{ - return DDR_100_OPP; -} - -static inline void prcmu_system_reset(u16 reset_code) {} - -static inline u16 prcmu_get_reset_code(void) -{ - return 0; -} - -static inline int prcmu_ac_wake_req(void) -{ - return 0; -} - -static inline void prcmu_ac_sleep_req(void) {} - -static inline void prcmu_modem_reset(void) {} - -static inline bool prcmu_is_ac_wake_requested(void) -{ - return false; -} - -static inline int prcmu_config_esram0_deep_sleep(u8 state) -{ - return 0; -} - -static inline void prcmu_config_abb_event_readout(u32 abb_events) {} - -static inline void prcmu_get_abb_event_buffer(void __iomem **buf) -{ - *buf = NULL; -} - -static inline int prcmu_config_hotdog(u8 threshold) -{ - return 0; -} - -static inline int prcmu_config_hotmon(u8 low, u8 high) -{ - return 0; -} - -static inline int prcmu_start_temp_sense(u16 cycles32k) -{ - return 0; -} - -static inline int prcmu_stop_temp_sense(void) -{ - return 0; -} - -static inline u32 prcmu_read(unsigned int reg) -{ - return 0; -} - -static inline void prcmu_write(unsigned int reg, u32 value) {} - -static inline void prcmu_write_masked(unsigned int reg, u32 mask, u32 value) {} - -#endif - -static inline void prcmu_set(unsigned int reg, u32 bits) -{ - prcmu_write_masked(reg, bits, bits); -} - -static inline void prcmu_clear(unsigned int reg, u32 bits) -{ - prcmu_write_masked(reg, bits, 0); -} - -/* PRCMU QoS APE OPP class */ -#define PRCMU_QOS_APE_OPP 1 -#define PRCMU_QOS_DDR_OPP 2 -#define PRCMU_QOS_ARM_OPP 3 -#define PRCMU_QOS_DEFAULT_VALUE -1 - -static inline int prcmu_qos_add_requirement(int prcmu_qos_class, - char *name, s32 value) -{ - return 0; -} - -static inline int prcmu_qos_update_requirement(int prcmu_qos_class, - char *name, s32 new_value) -{ - return 0; -} - -static inline void prcmu_qos_remove_requirement(int prcmu_qos_class, char *name) -{ -} - -#endif /* __MACH_PRCMU_H */ diff --git a/include/linux/mmap_lock.h b/include/linux/mmap_lock.h index 6b5c2390cc301f..e1d348d430c1a9 100644 --- a/include/linux/mmap_lock.h +++ b/include/linux/mmap_lock.h @@ -622,6 +622,8 @@ static inline void mmap_read_unlock(struct mm_struct *mm) DEFINE_GUARD(mmap_read_lock, struct mm_struct *, mmap_read_lock(_T), mmap_read_unlock(_T)) DEFINE_GUARD_COND(mmap_read_lock, _try, mmap_read_trylock(_T)) +DEFINE_GUARD(mmap_write_lock, struct mm_struct *, + mmap_write_lock(_T), mmap_write_unlock(_T)) static inline void mmap_read_unlock_non_owner(struct mm_struct *mm) { diff --git a/include/linux/netfs.h b/include/linux/netfs.h index d0b62d53eea992..67c2d9ef7c6232 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -247,6 +247,7 @@ struct netfs_io_request { unsigned long long submitted; /* Amount submitted for I/O so far */ unsigned long long len; /* Length of the request */ size_t transferred; /* Amount to be indicated as transferred */ + size_t progress_at; /* Report read progress when hit this much read */ long error; /* 0 or error that occurred */ unsigned long long i_size; /* Size of the file */ unsigned long long start; /* Start position */ @@ -263,7 +264,6 @@ struct netfs_io_request { atomic_t subreq_counter; /* Next subreq->debug_index */ unsigned int nr_group_rel; /* Number of refs to release on ->group */ spinlock_t lock; /* Lock for queuing subreqs */ - unsigned char front_folio_order; /* Order (size) of front folio */ enum netfs_io_origin origin; /* Origin of the request */ bool direct_bv_unpin; /* T if direct_bv[] must be unpinned */ refcount_t ref; @@ -276,9 +276,10 @@ struct netfs_io_request { #define NETFS_RREQ_SHORT_TRANSFER 5 /* Set if we have a short transfer */ #define NETFS_RREQ_OFFLOAD_COLLECTION 8 /* Offload collection to workqueue */ #define NETFS_RREQ_NO_UNLOCK_FOLIO 9 /* Don't unlock no_unlock_folio on completion */ -#define NETFS_RREQ_FOLIO_COPY_TO_CACHE 10 /* Copy current folio to cache from read */ +#define NETFS_RREQ_CANCEL_CACHING 10 /* Set to cancel caching */ #define NETFS_RREQ_UPLOAD_TO_SERVER 11 /* Need to write to the server */ #define NETFS_RREQ_USE_IO_ITER 12 /* Use ->io_iter rather than ->i_pages */ +#define NETFS_RREQ_NEED_PUT_RA_REFS 17 /* Need to put the folio refs RA gave us */ #define NETFS_RREQ_USE_PGPRIV2 31 /* [DEPRECATED] Use PG_private_2 to mark * write to cache on read */ const struct netfs_request_ops *netfs_ops; diff --git a/include/linux/oa_tc6.h b/include/linux/oa_tc6.h index 15f58e3c56c740..71cffcb041b1c9 100644 --- a/include/linux/oa_tc6.h +++ b/include/linux/oa_tc6.h @@ -10,6 +10,56 @@ #include #include +/* OPEN Alliance TC6 registers */ +/* Standard Capabilities Register */ +#define OA_TC6_REG_STDCAP 0x0002 +#define OA_TC6_STDCAP_DIRECT_PHY_REG_ACCESS BIT(8) + +/* Reset Control and Status Register */ +#define OA_TC6_REG_RESET 0x0003 +#define OA_TC6_RESET_SWRESET BIT(0) /* Software Reset */ + +/* Configuration Register #0 */ +#define OA_TC6_REG_CONFIG0 0x0004 +#define OA_TC6_CONFIG0_SYNC BIT(15) +#define OA_TC6_CONFIG0_ZARFE_ENABLE BIT(12) +#define OA_TC6_CONFIG0_PROTE BIT(5) + +/* Status Register #0 */ +#define OA_TC6_REG_STATUS0 0x0008 +#define OA_TC6_STATUS0_RESETC BIT(6) /* Reset Complete */ +#define OA_TC6_STATUS0_HEADER_ERROR BIT(5) +#define OA_TC6_STATUS0_LOSS_OF_FRAME_ERROR BIT(4) +#define OA_TC6_STATUS0_RX_BUFFER_OVERFLOW_ERROR BIT(3) +#define OA_TC6_STATUS0_TX_PROTOCOL_ERROR BIT(0) + +/* Buffer Status Register */ +#define OA_TC6_REG_BUFFER_STATUS 0x000B +#define OA_TC6_BUFFER_STATUS_TX_CREDITS_AVAILABLE GENMASK(15, 8) +#define OA_TC6_BUFFER_STATUS_RX_CHUNKS_AVAILABLE GENMASK(7, 0) + +/* Interrupt Mask Register #0 */ +#define OA_TC6_REG_INT_MASK0 0x000C +#define OA_TC6_INT_MASK0_HEADER_ERR_MASK BIT(5) +#define OA_TC6_INT_MASK0_LOSS_OF_FRAME_ERR_MASK BIT(4) +#define OA_TC6_INT_MASK0_RX_BUFFER_OVERFLOW_ERR_MASK BIT(3) +#define OA_TC6_INT_MASK0_TX_PROTOCOL_ERR_MASK BIT(0) +#define OA_TC6_INT_MASK0_ALL_INTERRUPTS (GENMASK(5, 0) | \ + GENMASK(12, 7)) + +/* PHY Clause 22 registers base address and mask */ +#define OA_TC6_PHY_STD_REG_ADDR_BASE 0xFF00 +#define OA_TC6_PHY_STD_REG_ADDR_MASK 0x1F + +/* PHY – Clause 45 registers memory map selector (MMS) as per table 6 in the + * OPEN Alliance specification. + */ +#define OA_TC6_PHY_C45_PCS_MMS2 2 /* MMD 3 */ +#define OA_TC6_PHY_C45_PMA_PMD_MMS3 3 /* MMD 1 */ +#define OA_TC6_PHY_C45_VS_PLCA_MMS4 4 /* MMD 31 */ +#define OA_TC6_PHY_C45_AUTO_NEG_MMS5 5 /* MMD 7 */ +#define OA_TC6_PHY_C45_POWER_UNIT_MMS6 6 /* MMD 13 */ + struct oa_tc6; struct oa_tc6 *oa_tc6_init(struct spi_device *spi, struct net_device *netdev); diff --git a/include/linux/perf/riscv_pmu.h b/include/linux/perf/riscv_pmu.h index f82a28040594bd..ecaa40370830a6 100644 --- a/include/linux/perf/riscv_pmu.h +++ b/include/linux/perf/riscv_pmu.h @@ -55,7 +55,7 @@ struct riscv_pmu { irqreturn_t (*handle_irq)(int irq_num, void *dev); - unsigned long cmask; + DECLARE_BITMAP(cmask, RISCV_MAX_COUNTERS); u64 (*ctr_read)(struct perf_event *event); int (*ctr_get_idx)(struct perf_event *event); int (*ctr_get_width)(int idx); diff --git a/include/linux/rbtree_augmented.h b/include/linux/rbtree_augmented.h index 6dbc5a1bf6a8ce..d2fa1c41bfd2b2 100644 --- a/include/linux/rbtree_augmented.h +++ b/include/linux/rbtree_augmented.h @@ -87,18 +87,18 @@ rb_add_augmented_cached(struct rb_node *node, struct rb_root_cached *tree, } /* - * Template for declaring augmented rbtree callbacks (generic case) + * Template for declaring augmented rbtree callbacks (generic multi fields) * * RBSTATIC: 'static' or empty * RBNAME: name of the rb_augment_callbacks structure * RBSTRUCT: struct type of the tree nodes * RBFIELD: name of struct rb_node field within RBSTRUCT - * RBAUGMENTED: name of field within RBSTRUCT holding data for subtree - * RBCOMPUTE: name of function that recomputes the RBAUGMENTED data + * RBCOPY: name of function that copies the RBAUGMENTED datas + * RBCOMPUTE: name of function that recomputes the RBAUGMENTED datas */ -#define RB_DECLARE_CALLBACKS(RBSTATIC, RBNAME, \ - RBSTRUCT, RBFIELD, RBAUGMENTED, RBCOMPUTE) \ +#define RB_DECLARE_CALLBACKS_MULTI(RBSTATIC, RBNAME, \ + RBSTRUCT, RBFIELD, RBCOPY, RBCOMPUTE) \ static inline void \ RBNAME ## _propagate(struct rb_node *rb, struct rb_node *stop) \ { \ @@ -114,14 +114,14 @@ RBNAME ## _copy(struct rb_node *rb_old, struct rb_node *rb_new) \ { \ RBSTRUCT *old = rb_entry(rb_old, RBSTRUCT, RBFIELD); \ RBSTRUCT *new = rb_entry(rb_new, RBSTRUCT, RBFIELD); \ - new->RBAUGMENTED = old->RBAUGMENTED; \ + RBCOPY(new, old); \ } \ static void \ RBNAME ## _rotate(struct rb_node *rb_old, struct rb_node *rb_new) \ { \ RBSTRUCT *old = rb_entry(rb_old, RBSTRUCT, RBFIELD); \ RBSTRUCT *new = rb_entry(rb_new, RBSTRUCT, RBFIELD); \ - new->RBAUGMENTED = old->RBAUGMENTED; \ + RBCOPY(new, old); \ RBCOMPUTE(old, false); \ } \ RBSTATIC const struct rb_augment_callbacks RBNAME = { \ @@ -130,6 +130,27 @@ RBSTATIC const struct rb_augment_callbacks RBNAME = { \ .rotate = RBNAME ## _rotate \ }; +/* + * Template for declaring augmented rbtree callbacks (generic single field) + * + * RBSTATIC: 'static' or empty + * RBNAME: name of the rb_augment_callbacks structure + * RBSTRUCT: struct type of the tree nodes + * RBFIELD: name of struct rb_node field within RBSTRUCT + * RBAUGMENTED: name of field within RBSTRUCT holding data for subtree + * RBCOMPUTE: name of function that recomputes the RBAUGMENTED data + */ + +#define RB_DECLARE_CALLBACKS(RBSTATIC, RBNAME, \ + RBSTRUCT, RBFIELD, RBAUGMENTED, RBCOMPUTE) \ +static inline void \ +RBNAME ## _copy_single(RBSTRUCT *new, RBSTRUCT *old) \ +{ \ + new->RBAUGMENTED = old->RBAUGMENTED; \ +} \ +RB_DECLARE_CALLBACKS_MULTI(RBSTATIC, RBNAME, \ + RBSTRUCT, RBFIELD, RBNAME ## _copy_single, RBCOMPUTE) + /* * Template for declaring augmented rbtree callbacks, * computing RBAUGMENTED scalar as max(RBCOMPUTE(node)) for all subtree nodes. diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index 0670742b2d6013..eac3e9080c3c03 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -3,8 +3,9 @@ #define _LINUX_RING_BUFFER_H #include -#include #include +#include +#include #include @@ -218,14 +219,15 @@ bool ring_buffer_time_stamp_abs(struct trace_buffer *buffer); size_t ring_buffer_nr_dirty_pages(struct trace_buffer *buffer, int cpu); struct buffer_data_read_page; -struct buffer_data_read_page * -ring_buffer_alloc_read_page(struct trace_buffer *buffer, int cpu); +int ring_buffer_alloc_read_page(struct trace_buffer *buffer, int cpu, + struct buffer_data_read_page **rpage); void ring_buffer_free_read_page(struct trace_buffer *buffer, int cpu, struct buffer_data_read_page *page); int ring_buffer_read_page(struct trace_buffer *buffer, struct buffer_data_read_page *data_page, size_t len, int cpu, int full); void *ring_buffer_read_page_data(struct buffer_data_read_page *page); +unsigned int ring_buffer_read_page_size(struct buffer_data_read_page *rpage); struct trace_seq; @@ -278,11 +280,25 @@ static inline struct ring_buffer_desc *__first_ring_buffer_desc(struct trace_buf return (struct ring_buffer_desc *)(&desc->__data[0]); } +/* + * Returns the number of pages for a ring_buffer_desc. The caller must ensure it + * does not overflow ring_buffer_desc::nr_page_va. + */ +static inline unsigned long __calc_nr_pages_ring_buffer_desc(size_t size) +{ + /* Takes into account the reader page */ + return max(DIV_ROUND_UP(size, PAGE_SIZE - BUF_PAGE_HDR_SIZE), 2UL) + 1; +} + static inline size_t trace_buffer_desc_size(size_t buffer_size, unsigned int nr_cpus) { - unsigned int nr_pages = max(DIV_ROUND_UP(buffer_size, PAGE_SIZE), 2UL) + 1; + unsigned long nr_pages = __calc_nr_pages_ring_buffer_desc(buffer_size); struct ring_buffer_desc *rbdesc; + /* Capped by ring_buffer_desc::nr_page_va */ + if (nr_pages > UINT_MAX) + return SIZE_MAX; + return size_add(offsetof(struct trace_buffer_desc, __data), size_mul(nr_cpus, struct_size(rbdesc, page_va, nr_pages))); } diff --git a/include/linux/rolling_buffer.h b/include/linux/rolling_buffer.h index 9e5dad29669cf0..a97f7cfaacaad7 100644 --- a/include/linux/rolling_buffer.h +++ b/include/linux/rolling_buffer.h @@ -45,9 +45,9 @@ struct rolling_buffer_snapshot { int rolling_buffer_init(struct rolling_buffer *roll, unsigned int rreq_id, unsigned int direction, gfp_t gfp); int rolling_buffer_make_space(struct rolling_buffer *roll, gfp_t gfp); -ssize_t rolling_buffer_load_from_ra(struct rolling_buffer *roll, - struct readahead_control *ractl, - struct folio_batch *put_batch); +ssize_t rolling_buffer_bulk_load_from_ra(struct rolling_buffer *roll, + struct readahead_control *ractl, + unsigned int rreq_id, gfp_t gfp); ssize_t rolling_buffer_append(struct rolling_buffer *roll, struct folio *folio, unsigned int flags, gfp_t gfp); struct folio_queue *rolling_buffer_delete_spent(struct rolling_buffer *roll); diff --git a/include/linux/sched.h b/include/linux/sched.h index 7a53c15cecb52d..9341d647bbd157 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1775,7 +1775,7 @@ static inline bool is_lazy_mmu_mode_active(void) } #endif -extern struct pid *cad_pid; +extern struct pid __rcu *cad_pid; /* * Per process flags diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index 584ae88b435e9e..d45a5476b97dec 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -562,10 +562,7 @@ static inline sigset_t *sigmask_to_save(void) return res; } -static inline int kill_cad_pid(int sig, int priv) -{ - return kill_pid(cad_pid, sig, priv); -} +int kill_cad_pid(int sig, int priv); /* These can be the second arg to send_sig_info/send_group_sig_info. */ #define SEND_SIG_NOINFO ((struct kernel_siginfo *) 0) diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index ed6a2bc23db51c..f7dd3db9459c65 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3082,6 +3082,11 @@ static inline bool skb_transport_header_was_set(const struct sk_buff *skb) return skb->transport_header != (typeof(skb->transport_header))~0U; } +static inline void skb_unset_transport_header(struct sk_buff *skb) +{ + skb->transport_header = (typeof(skb->transport_header))~0U; +} + static inline unsigned char *skb_transport_header(const struct sk_buff *skb) { DEBUG_NET_WARN_ON_ONCE(!skb_transport_header_was_set(skb)); diff --git a/include/media/v4l2-hevc.h b/include/media/v4l2-hevc.h new file mode 100644 index 00000000000000..973c96be16be43 --- /dev/null +++ b/include/media/v4l2-hevc.h @@ -0,0 +1,41 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Helper functions for HEVC stateless codecs. + */ + +#ifndef _MEDIA_V4L2_HEVC_H +#define _MEDIA_V4L2_HEVC_H + +#include +#include + +/** + * v4l2_hevc_pps_num_tile_columns - number of HEVC tile columns, bounded + * @pps: the V4L2 HEVC PPS control + * + * Return the number of tile columns (num_tile_columns_minus1 + 1) clamped to + * the capacity of column_width_minus1[]. The control validation already + * rejects out-of-range counts; this keeps the consuming drivers bounded too. + */ +static inline unsigned int +v4l2_hevc_pps_num_tile_columns(const struct v4l2_ctrl_hevc_pps *pps) +{ + return min_t(unsigned int, pps->num_tile_columns_minus1 + 1, + ARRAY_SIZE(pps->column_width_minus1)); +} + +/** + * v4l2_hevc_pps_num_tile_rows - number of HEVC tile rows, bounded + * @pps: the V4L2 HEVC PPS control + * + * Return the number of tile rows (num_tile_rows_minus1 + 1) clamped to the + * capacity of row_height_minus1[]. + */ +static inline unsigned int +v4l2_hevc_pps_num_tile_rows(const struct v4l2_ctrl_hevc_pps *pps) +{ + return min_t(unsigned int, pps->num_tile_rows_minus1 + 1, + ARRAY_SIZE(pps->row_height_minus1)); +} + +#endif /* _MEDIA_V4L2_HEVC_H */ diff --git a/include/net/cfg802154.h b/include/net/cfg802154.h index 76d2cd2e2b3099..2e960441ea49e3 100644 --- a/include/net/cfg802154.h +++ b/include/net/cfg802154.h @@ -376,6 +376,7 @@ struct cfg802154_mac_pkt { struct list_head node; struct sk_buff *skb; struct ieee802154_sub_if_data *sdata; + netdevice_tracker dev_tracker; u8 page; u8 channel; }; diff --git a/include/net/if_inet6.h b/include/net/if_inet6.h index 238ad3349456a3..795fb41b45f5d1 100644 --- a/include/net/if_inet6.h +++ b/include/net/if_inet6.h @@ -88,8 +88,6 @@ struct ip6_sf_socklist { struct in6_addr sl_addr[] __counted_by(sl_max); }; -#define IP6_SFBLOCK 10 /* allocate this many at once */ - struct ipv6_mc_socklist { struct in6_addr addr; int ifindex; diff --git a/include/net/ip.h b/include/net/ip.h index a8f57b4f4aa23f..6f602df72ee621 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -704,7 +704,8 @@ static inline void ip_ipgre_mc_map(__be32 naddr, const unsigned char *broadcast, static __inline__ void inet_reset_saddr(struct sock *sk) { - inet_sk(sk)->inet_rcv_saddr = inet_sk(sk)->inet_saddr = 0; + inet_sk(sk)->inet_saddr = 0; + WRITE_ONCE(inet_sk(sk)->inet_rcv_saddr, 0); #if IS_ENABLED(CONFIG_IPV6) if (sk->sk_family == PF_INET6) { struct ipv6_pinfo *np = inet6_sk(sk); diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index ac1acc0b74368c..745ab62154ace4 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -382,6 +382,8 @@ static inline unsigned int ip6_dst_mtu_maybe_forward(const struct dst_entry *dst rcu_read_unlock(); out: + mtu = min_t(unsigned int, mtu, IP6_MAX_MTU); + return mtu - lwtunnel_headroom(dst->lwtstate, mtu); } diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index cbc24877651187..f35bd06a6bad68 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -793,7 +793,7 @@ void qdisc_offload_query_caps(struct net_device *dev, struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, const struct Qdisc_ops *ops, struct netlink_ext_ack *extack); -void qdisc_free(struct Qdisc *qdisc); +void qdisc_free_rcu(struct Qdisc *qdisc); struct Qdisc *qdisc_create_dflt(struct netdev_queue *dev_queue, const struct Qdisc_ops *ops, u32 parentid, struct netlink_ext_ack *extack); diff --git a/include/net/tcp.h b/include/net/tcp.h index 670c20876f265c..436495ff2271de 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -765,8 +765,7 @@ int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue, void tcp_send_probe0(struct sock *); int tcp_write_wakeup(struct sock *, int mib); void tcp_send_fin(struct sock *sk); -void tcp_send_active_reset(struct sock *sk, gfp_t priority, - enum sk_rst_reason reason); +void tcp_send_active_reset(struct sock *sk, enum sk_rst_reason reason); int tcp_send_synack(struct sock *); void tcp_push_one(struct sock *, unsigned int mss_now); void __tcp_send_ack(struct sock *sk, u32 rcv_nxt, u16 flags); diff --git a/include/trace/events/cachefiles.h b/include/trace/events/cachefiles.h index 6e3b1424eea4dc..d002ed508a4353 100644 --- a/include/trace/events/cachefiles.h +++ b/include/trace/events/cachefiles.h @@ -380,7 +380,7 @@ TRACE_EVENT(cachefiles_rename, TRACE_EVENT(cachefiles_coherency, TP_PROTO(struct cachefiles_object *obj, ino_t ino, - u64 disk_aux, + const void *disk_aux, enum cachefiles_content content, enum cachefiles_coherency_trace why), @@ -397,12 +397,27 @@ TRACE_EVENT(cachefiles_coherency, ), TP_fast_assign( + union { + __be16 s[4]; + __be64 ll; + } x; + __entry->obj = obj->debug_id; __entry->why = why; __entry->content = content; __entry->ino = ino; __entry->aux = be64_to_cpup((__be64 *)obj->cookie->inline_aux); - __entry->disk_aux = disk_aux; + + /* cachefiles_xattr::data is 2-byte aligned but not 8-byte aligned. */ + if (disk_aux) { + x.s[0] = ((__be16 *)disk_aux)[0]; + x.s[1] = ((__be16 *)disk_aux)[1]; + x.s[2] = ((__be16 *)disk_aux)[2]; + x.s[3] = ((__be16 *)disk_aux)[3]; + __entry->disk_aux = be64_to_cpu(x.ll); + } else { + __entry->disk_aux = 0; + } ), TP_printk("o=%08x %s B=%llx c=%u aux=%llx dsk=%llx", diff --git a/include/trace/events/icmp.h b/include/trace/events/icmp.h index 31559796949a78..acfcf2b132d600 100644 --- a/include/trace/events/icmp.h +++ b/include/trace/events/icmp.h @@ -27,17 +27,20 @@ TRACE_EVENT(icmp_send, TP_fast_assign( struct iphdr *iph = ip_hdr(skb); - struct udphdr *uh = udp_hdr(skb); - int proto_4 = iph->protocol; + struct udphdr _uh, *uh = NULL; __be32 *p32; __entry->skbaddr = skb; __entry->type = type; __entry->code = code; - if (proto_4 != IPPROTO_UDP || (u8 *)uh < skb->head || - (u8 *)uh + sizeof(struct udphdr) - > skb_tail_pointer(skb)) { + if (iph->protocol == IPPROTO_UDP) + uh = skb_header_pointer(skb, + skb_network_offset(skb) + + (iph->ihl << 2), + sizeof(_uh), &_uh); + + if (!uh) { __entry->sport = 0; __entry->dport = 0; __entry->ulen = 0; diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h index 082cb03c613160..3fec3e8f91c859 100644 --- a/include/trace/events/netfs.h +++ b/include/trace/events/netfs.h @@ -59,6 +59,7 @@ EM(netfs_rreq_trace_free, "FREE ") \ EM(netfs_rreq_trace_intr, "INTR ") \ EM(netfs_rreq_trace_ki_complete, "KI-CMPL") \ + EM(netfs_rreq_trace_ra_put_ref, "RA-PUT ") \ EM(netfs_rreq_trace_recollect, "RECLLCT") \ EM(netfs_rreq_trace_redirty, "REDIRTY") \ EM(netfs_rreq_trace_resubmit, "RESUBMT") \ @@ -70,9 +71,11 @@ EM(netfs_rreq_trace_unpause, "UNPAUSE") \ EM(netfs_rreq_trace_wait_ip, "WAIT-IP") \ EM(netfs_rreq_trace_wait_pause, "--PAUSED--") \ + EM(netfs_rreq_trace_wait_put_ra_refs, "WAIT-P-RA") \ EM(netfs_rreq_trace_wait_quiesce, "WAIT-QUIESCE") \ EM(netfs_rreq_trace_waited_ip, "DONE-IP") \ EM(netfs_rreq_trace_waited_pause, "--UNPAUSED--") \ + EM(netfs_rreq_trace_waited_put_ra_refs, "DONE-P-RA") \ EM(netfs_rreq_trace_waited_quiesce, "DONE-QUIESCE") \ EM(netfs_rreq_trace_wake_ip, "WAKE-IP") \ EM(netfs_rreq_trace_wake_queue, "WAKE-Q ") \ @@ -195,7 +198,6 @@ EM(netfs_folio_trace_clear_cc, "clear-cc") \ EM(netfs_folio_trace_clear_g, "clear-g") \ EM(netfs_folio_trace_clear_s, "clear-s") \ - EM(netfs_folio_trace_copy_to_cache, "mark-copy") \ EM(netfs_folio_trace_end_copy, "end-copy") \ EM(netfs_folio_trace_filled_gaps, "filled-gaps") \ EM(netfs_folio_trace_invalidate_all, "inval-all") \ @@ -206,16 +208,19 @@ EM(netfs_folio_trace_kill_cc, "kill-cc") \ EM(netfs_folio_trace_kill_g, "kill-g") \ EM(netfs_folio_trace_kill_s, "kill-s") \ + EM(netfs_folio_trace_mark_copy, "mark-copy") \ EM(netfs_folio_trace_mkwrite, "mkwrite") \ EM(netfs_folio_trace_mkwrite_plus, "mkwrite+") \ - EM(netfs_folio_trace_not_under_wback, "!wback") \ EM(netfs_folio_trace_not_locked, "!locked") \ + EM(netfs_folio_trace_not_under_wback, "!wback") \ + EM(netfs_folio_trace_pgpriv2_copy, "pgpriv2-copy") \ EM(netfs_folio_trace_put, "put") \ EM(netfs_folio_trace_read, "read") \ EM(netfs_folio_trace_read_done, "read-done") \ EM(netfs_folio_trace_read_gaps, "read-gaps") \ EM(netfs_folio_trace_read_unlock, "read-unlock") \ EM(netfs_folio_trace_redirtied, "redirtied") \ + EM(netfs_folio_trace_sched_copy, "sched-copy") \ EM(netfs_folio_trace_store, "store") \ EM(netfs_folio_trace_store_copy, "store-copy") \ EM(netfs_folio_trace_store_plus, "store+") \ @@ -786,6 +791,27 @@ TRACE_EVENT(netfs_folioq, __print_symbolic(__entry->trace, netfs_folioq_traces)) ); +TRACE_EVENT(netfs_read_progress_at, + TP_PROTO(const struct netfs_io_request *rreq), + + TP_ARGS(rreq), + + TP_STRUCT__entry( + __field(unsigned int, rreq) + __field(size_t, progress_at) + __field(size_t, cleaned_to) + ), + + TP_fast_assign( + __entry->rreq = rreq->debug_id; + __entry->cleaned_to = rreq->cleaned_to - rreq->start; + __entry->progress_at = rreq->progress_at; + ), + + TP_printk("R=%08x cln=%zx prg=%zx", + __entry->rreq, __entry->cleaned_to, __entry->progress_at) + ); + #undef EM #undef E_ #endif /* _TRACE_NETFS_H */ diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h index 9f3090db2f1637..322aef9b54bbe2 100644 --- a/include/uapi/drm/amdgpu_drm.h +++ b/include/uapi/drm/amdgpu_drm.h @@ -1510,6 +1510,7 @@ struct drm_amdgpu_info_device { __u64 high_va_max; /* gfx10 pa_sc_tile_steering_override */ __u32 pa_sc_tile_steering_override; + __u32 pad; /* disabled TCCs */ __u64 tcc_disabled_mask; __u64 min_engine_clock; @@ -1534,7 +1535,6 @@ struct drm_amdgpu_info_device { __u32 csa_alignment; /* Userq IP mask (1 << AMDGPU_HW_IP_*) */ __u32 userq_ip_mask; - __u32 pad; }; struct drm_amdgpu_info_hw_ip { diff --git a/init/main.c b/init/main.c index e363232b428b47..dd7b2a6599fca7 100644 --- a/init/main.c +++ b/init/main.c @@ -276,7 +276,8 @@ static void * __init get_boot_config_from_initrd(size_t *_size) u8 *hdr; int i; - if (!initrd_end) + if (!initrd_end || initrd_end < initrd_start || + initrd_end - initrd_start < BOOTCONFIG_MAGIC_LEN + 8) return NULL; data = (char *)initrd_end - BOOTCONFIG_MAGIC_LEN; @@ -293,16 +294,26 @@ static void * __init get_boot_config_from_initrd(size_t *_size) found: hdr = (u8 *)(data - 8); + if ((unsigned long)hdr < initrd_start) + return NULL; + size = get_unaligned_le32(hdr); csum = get_unaligned_le32(hdr + 4); - data = ((void *)hdr) - size; - if ((unsigned long)data < initrd_start) { - pr_err("bootconfig size %d is greater than initrd size %ld\n", + if (size > XBC_DATA_MAX) { + pr_err("bootconfig size %u is greater than max size %d\n", + size, XBC_DATA_MAX); + return NULL; + } + + if (size > ((unsigned long)hdr - initrd_start)) { + pr_err("bootconfig size %u is greater than initrd size %lu\n", size, initrd_end - initrd_start); return NULL; } + data = ((void *)hdr) - size; + if (xbc_calc_checksum(data, size) != csum) { pr_err("bootconfig checksum failed\n"); return NULL; @@ -405,12 +416,6 @@ static void __init setup_boot_config(void) return; } - if (size >= XBC_DATA_MAX) { - pr_err("bootconfig size %ld greater than max size %d\n", - (long)size, XBC_DATA_MAX); - return; - } - ret = xbc_init(data, size, &msg, &pos); if (ret < 0) { if (pos < 0) @@ -1636,7 +1641,7 @@ static noinline void __init kernel_init_freeable(void) */ set_mems_allowed(node_states[N_MEMORY]); - cad_pid = get_pid(task_pid(current)); + rcu_assign_pointer(cad_pid, get_pid(task_pid(current))); smp_prepare_cpus(setup_max_cpus); diff --git a/io_uring/net.c b/io_uring/net.c index a74d15f7b7d2b6..e6847fb084abcb 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -884,7 +884,7 @@ int io_recvmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) static inline bool io_recv_finish(struct io_kiocb *req, struct io_async_msghdr *kmsg, struct io_br_sel *sel, bool mshot_finished, - unsigned issue_flags) + unsigned issue_flags, int consumed) { struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg); unsigned int cflags = 0; @@ -908,7 +908,7 @@ static inline bool io_recv_finish(struct io_kiocb *req, if (sr->flags & IORING_RECVSEND_BUNDLE) { size_t this_ret = sel->val - sr->done_io; - cflags |= io_put_kbufs(req, this_ret, sel->buf_list, io_bundle_nbufs(kmsg, this_ret)); + cflags |= io_put_kbufs(req, consumed, sel->buf_list, io_bundle_nbufs(kmsg, consumed)); if (sr->flags & IORING_RECV_RETRY) cflags = req->cqe.flags | (cflags & CQE_F_MASK); if (sr->mshot_len && sel->val >= sr->mshot_len) @@ -930,7 +930,7 @@ static inline bool io_recv_finish(struct io_kiocb *req, return false; } } else { - cflags |= io_put_kbuf(req, sel->val, sel->buf_list); + cflags |= io_put_kbuf(req, consumed, sel->buf_list); } /* @@ -1058,6 +1058,8 @@ int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags) int ret, min_ret = 0; bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; bool mshot_finished = true; + int consumed = 0; + size_t len; sock = sock_from_file(req->file); if (unlikely(!sock)) @@ -1073,9 +1075,8 @@ int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags) retry_multishot: sel.buf_list = NULL; + len = sr->len; if (io_do_buffer_select(req)) { - size_t len = sr->len; - sel = io_buffer_select(req, &len, sr->buf_group, issue_flags); if (!sel.addr) return -ENOBUFS; @@ -1096,6 +1097,7 @@ retry_multishot: if (req->flags & REQ_F_APOLL_MULTISHOT) { ret = io_recvmsg_multishot(sock, sr, kmsg, flags, &mshot_finished); + consumed = ret; } else { /* disable partial retry for recvmsg with cmsg attached */ if (flags & MSG_WAITALL && !kmsg->msg.msg_controllen) @@ -1103,6 +1105,15 @@ retry_multishot: ret = __sys_recvmsg_sock(sock, &kmsg->msg, sr->umsg, kmsg->uaddr, flags); + /* + * With MSG_TRUNC, the net layer will return the full size of + * the packet, even if we only filled part of it in the buffers. + * Adjust the returned size to consume only the real part of the + * buffer. + */ + consumed = ret; + if (ret > 0) + consumed = min_t(size_t, ret, len); } if (ret < min_ret) { @@ -1129,7 +1140,7 @@ retry_multishot: io_kbuf_recycle(req, sel.buf_list, issue_flags); sel.val = ret; - if (!io_recv_finish(req, kmsg, &sel, mshot_finished, issue_flags)) + if (!io_recv_finish(req, kmsg, &sel, mshot_finished, issue_flags, consumed)) goto retry_multishot; return sel.val; @@ -1139,6 +1150,7 @@ static int io_recv_buf_select(struct io_kiocb *req, struct io_async_msghdr *kmsg struct io_br_sel *sel, unsigned int issue_flags) { struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg); + size_t len; int ret; /* @@ -1184,13 +1196,14 @@ static int io_recv_buf_select(struct io_kiocb *req, struct io_async_msghdr *kmsg /* special case 1 vec, can be a fast path */ if (ret == 1) { sr->buf = arg.iovs[0].iov_base; - sr->len = arg.iovs[0].iov_len; + len = sr->len = arg.iovs[0].iov_len; goto map_ubuf; } iov_iter_init(&kmsg->msg.msg_iter, ITER_DEST, arg.iovs, ret, - arg.out_len); + arg.out_len); + len = arg.out_len; } else { - size_t len = sel->val; + len = sel->val; *sel = io_buffer_select(req, &len, sr->buf_group, issue_flags); if (!sel->addr) @@ -1204,7 +1217,7 @@ map_ubuf: return ret; } - return 0; + return len; } int io_recv(struct io_kiocb *req, unsigned int issue_flags) @@ -1214,9 +1227,10 @@ int io_recv(struct io_kiocb *req, unsigned int issue_flags) struct io_br_sel sel; struct socket *sock; unsigned flags; - int ret, min_ret = 0; + int ret, min_ret = 0, consumed = 0; bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; bool mshot_finished; + size_t len = 0; sock = sock_from_file(req->file); if (unlikely(!sock)) @@ -1244,6 +1258,7 @@ int io_recv(struct io_kiocb *req, unsigned int issue_flags) retry_multishot: sel.buf_list = NULL; + len = sr->len; if (io_do_buffer_select(req)) { sel.val = sr->len; ret = io_recv_buf_select(req, kmsg, &sel, issue_flags); @@ -1251,6 +1266,7 @@ retry_multishot: kmsg->msg.msg_inq = -1; goto out_free; } + len = ret; sr->buf = NULL; } @@ -1281,6 +1297,17 @@ out_free: } mshot_finished = ret <= 0; + + /* + * With MSG_TRUNC, the net layer will return the full size of + * the packet, even if we only filled part of it in the buffers. + * Adjust the returned size to consume only the real part of the + * buffer. + */ + consumed = ret; + if (ret > 0) + consumed = min_t(size_t, ret, len); + if (ret > 0) ret += sr->done_io; else if (sr->done_io) @@ -1289,7 +1316,7 @@ out_free: io_kbuf_recycle(req, sel.buf_list, issue_flags); sel.val = ret; - if (!io_recv_finish(req, kmsg, &sel, mshot_finished, issue_flags)) + if (!io_recv_finish(req, kmsg, &sel, mshot_finished, issue_flags, consumed)) goto retry_multishot; return sel.val; diff --git a/io_uring/rw.c b/io_uring/rw.c index 95038cfda61538..45a96e6546fcc2 100644 --- a/io_uring/rw.c +++ b/io_uring/rw.c @@ -531,20 +531,25 @@ static void io_req_end_write(struct io_kiocb *req) } } -/* - * Trigger the notifications after having done some IO, and finish the write - * accounting, if any. - */ -static void io_req_io_end(struct io_kiocb *req) +/* Trigger the notifications after having done some IO. */ +static void io_req_io_notify(struct io_kiocb *req) { struct io_rw *rw = io_kiocb_to_cmd(req, struct io_rw); - if (rw->kiocb.ki_flags & IOCB_WRITE) { - io_req_end_write(req); + if (rw->kiocb.ki_flags & IOCB_WRITE) fsnotify_modify(req->file); - } else { + else fsnotify_access(req->file); - } +} + +/* Finish write accounting and notify, for inline completions only. */ +static void io_req_io_end(struct io_kiocb *req) +{ + struct io_rw *rw = io_kiocb_to_cmd(req, struct io_rw); + + if (rw->kiocb.ki_flags & IOCB_WRITE) + io_req_end_write(req); + io_req_io_notify(req); } static void __io_complete_rw_common(struct io_kiocb *req, long res) @@ -577,7 +582,7 @@ void io_req_rw_complete(struct io_tw_req tw_req, io_tw_token_t tw) { struct io_kiocb *req = tw_req.req; - io_req_io_end(req); + io_req_io_notify(req); if (req->flags & (REQ_F_BUFFER_SELECTED|REQ_F_BUFFER_RING)) req->cqe.flags |= io_put_kbuf(req, max(req->cqe.res, 0), NULL); @@ -591,6 +596,10 @@ static void io_complete_rw(struct kiocb *kiocb, long res) struct io_rw *rw = container_of(kiocb, struct io_rw, kiocb); struct io_kiocb *req = cmd_to_io_kiocb(rw); + /* ring owner may block in freeze_super() before task_work runs */ + if (kiocb->ki_flags & IOCB_WRITE) + io_req_end_write(req); + __io_complete_rw_common(req, res); io_req_set_res(req, io_fixup_rw_res(req, res), 0); req->io_task_work.func = io_req_rw_complete; diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 248b4818178cd1..cc3f8c25a28b5b 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -405,7 +405,7 @@ int bpf_percpu_array_update(struct bpf_map *map, void *key, void *value, void __percpu *pptr; void *ptr, *val; u32 size; - int cpu; + int cpu, off = 0; if (unlikely((map_flags & BPF_F_LOCK) || (u32)map_flags > BPF_F_ALL_CPUS)) /* unknown flags */ @@ -437,9 +437,10 @@ int bpf_percpu_array_update(struct bpf_map *map, void *key, void *value, } for_each_possible_cpu(cpu) { ptr = per_cpu_ptr(pptr, cpu); - val = (map_flags & BPF_F_ALL_CPUS) ? value : value + size * cpu; + val = (map_flags & BPF_F_ALL_CPUS) ? value : value + off; copy_map_value(map, ptr, val); bpf_obj_cancel_fields(map, ptr); + off += size; } unlock: rcu_read_unlock(); diff --git a/kernel/bpf/backtrack.c b/kernel/bpf/backtrack.c index 2e4ae0ef08609d..53a1e52d73c5a4 100644 --- a/kernel/bpf/backtrack.c +++ b/kernel/bpf/backtrack.c @@ -521,37 +521,34 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx, return -EFAULT; } } else if (opcode == BPF_EXIT) { - bool r0_precise; + bool from_subprog_call, r0_precise; + + /* BPF_EXIT in subprog or callback always returns + * right after the call instruction, so by checking + * whether the instruction at subseq_idx-1 is subprog + * call or not we can distinguish actual exit from + * *subprog* from exit from *callback*. In the former + * case, we need to propagate r0 precision, if + * necessary. In the former we never do that. + */ + from_subprog_call = subseq_idx - 1 >= 0 && + bpf_pseudo_call(&env->prog->insnsi[subseq_idx - 1]); + + r0_precise = from_subprog_call && bt_is_reg_set(bt, BPF_REG_0); /* Backtracking to a nested function call, 'idx' is a part of * the inner frame 'subseq_idx' is a part of the outer frame. * In case of a regular function call, instructions giving * precision to registers R1-R5 should have been found already. - * In case of a callback, it is ok to have R1-R5 marked for - * backtracking, as these registers are set by the function - * invoking callback. + * In case of a callback from bpf_loop(), R{1,4} in the calling + * frame would be set as precise and that is correct. */ - if (subseq_idx >= 0 && bpf_calls_callback(env, subseq_idx)) - for (i = BPF_REG_1; i <= BPF_REG_5; i++) - bt_clear_reg(bt, i); - if (bt_reg_mask(bt) & BPF_REGMASK_ARGS) { + if (from_subprog_call && (bt_reg_mask(bt) & BPF_REGMASK_ARGS)) { verifier_bug(env, "backtracking exit unexpected regs %x", bt_reg_mask(bt)); return -EFAULT; } - /* BPF_EXIT in subprog or callback always returns - * right after the call instruction, so by checking - * whether the instruction at subseq_idx-1 is subprog - * call or not we can distinguish actual exit from - * *subprog* from exit from *callback*. In the former - * case, we need to propagate r0 precision, if - * necessary. In the former we never do that. - */ - r0_precise = subseq_idx - 1 >= 0 && - bpf_pseudo_call(&env->prog->insnsi[subseq_idx - 1]) && - bt_is_reg_set(bt, BPF_REG_0); - bt_clear_reg(bt, BPF_REG_0); if (bt_subprog_enter(bt)) return -EFAULT; @@ -583,16 +580,29 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx, */ } } else if (class == BPF_LD) { - if (!bt_is_reg_set(bt, dreg)) - return 0; - bt_clear_reg(bt, dreg); /* It's ld_imm64 or ld_abs or ld_ind. * For ld_imm64 no further tracking of precision * into parent is necessary */ - if (mode == BPF_IND || mode == BPF_ABS) - /* to be analyzed */ - return -ENOTSUPP; + if (mode == BPF_IMM) { + bt_clear_reg(bt, dreg); + return 0; + } + /* + * BPF_{IND,ABS} are modelled as two branches: + * - fallthrough; + * - implicit subprogram exit. + * It is necessary to switch current frame if + * implicit subprogram exit branch is backtracked. + */ + if (mode == BPF_IND || mode == BPF_ABS) { + if (bt_is_reg_set(bt, dreg)) + return -ENOTSUPP; + if (subseq_idx != idx + 1) + if (bt_subprog_enter(bt)) + return -EFAULT; + return 0; + } } /* Propagate precision marks to linked registers, to account for * registers marked as precise in this function. diff --git a/kernel/bpf/bpf_iter.c b/kernel/bpf/bpf_iter.c index f5eaeb2493d4a1..9b4f5236c5ea31 100644 --- a/kernel/bpf/bpf_iter.c +++ b/kernel/bpf/bpf_iter.c @@ -754,7 +754,7 @@ const struct bpf_func_proto bpf_loop_proto = { .func = bpf_loop, .gpl_only = false, .ret_type = RET_INTEGER, - .arg1_type = ARG_ANYTHING, + .arg1_type = ARG_SCALAR, .arg2_type = ARG_PTR_TO_FUNC, .arg3_type = ARG_PTR_TO_STACK_OR_NULL, .arg4_type = ARG_ANYTHING, diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 608be952717d41..022d5a594dc95e 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -2912,14 +2912,29 @@ static void btf_modifier_show(const struct btf *btf, else t = btf_type_skip_modifiers(btf, type_id, NULL); - btf_type_ops(t)->show(btf, t, type_id, data, bits_offset, show); + /* + * A modifier can resolve to void, which has no show op; print a + * placeholder rather than dereferencing NULL. + */ + if (!btf_type_ops(t)) + btf_df_show(btf, t, type_id, data, bits_offset, show); + else + btf_type_ops(t)->show(btf, t, type_id, data, bits_offset, show); } static void btf_var_show(const struct btf *btf, const struct btf_type *t, u32 type_id, void *data, u8 bits_offset, struct btf_show *show) { - t = btf_type_id_resolve(btf, &type_id); + /* + * btf_type_id_resolve() dereferences btf->resolved_ids, which is NULL + * for a base BTF (e.g. the vmlinux BTF that bpf_snprintf_btf() uses). + * Resolve the var's type directly in that case. + */ + if (btf->resolved_ids) + t = btf_type_id_resolve(btf, &type_id); + else + t = btf_type_skip_modifiers(btf, t->type, &type_id); btf_type_ops(t)->show(btf, t, type_id, data, bits_offset, show); } @@ -6658,6 +6673,10 @@ struct bpf_raw_tp_null_args { static const struct bpf_raw_tp_null_args raw_tp_null_args[] = { /* sched */ { "sched_pi_setprio", 0x10 }, + /* + * do_wait() passes NULL for wait4(-1) and waitid(P_ALL). + */ + { "sched_process_wait", 0x1 }, /* ... from sched_numa_pair_template event class */ { "sched_stick_numa", 0x100 }, { "sched_swap_numa", 0x100 }, @@ -6725,6 +6744,9 @@ static const struct bpf_raw_tp_null_args raw_tp_null_args[] = { { "rxrpc_resend", 0x10 }, { "rxrpc_tq", 0x10 }, { "rxrpc_client", 0x1 }, + /* signal */ + { "signal_generate", 0x20 }, + { "signal_deliver", 0x20 }, /* skb */ {"kfree_skb", 0x1000}, /* sunrpc */ @@ -8707,6 +8729,7 @@ BPF_CALL_4(bpf_btf_find_by_name_kind, char *, name, int, name_sz, u32, kind, int const struct bpf_func_proto bpf_btf_find_by_name_kind_proto = { .func = bpf_btf_find_by_name_kind, .gpl_only = false, + .might_sleep = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg2_type = ARG_CONST_SIZE, diff --git a/kernel/bpf/cfg.c b/kernel/bpf/cfg.c index 26d37066465f38..d5fc03f12969bd 100644 --- a/kernel/bpf/cfg.c +++ b/kernel/bpf/cfg.c @@ -120,6 +120,7 @@ static int push_insn(int t, int w, int e, struct bpf_verifier_env *env) /* mark branch target for state pruning */ mark_prune_point(env, w); mark_jmp_point(env, w); + mark_jump_target(env, w); } if (insn_state[w] == 0) { @@ -378,6 +379,7 @@ static int visit_gotox_insn(int t, struct bpf_verifier_env *env) } mark_jmp_point(env, w); + mark_jump_target(env, w); /* EXPLORED || DISCOVERED */ if (insn_state[w]) @@ -539,6 +541,7 @@ static int visit_insn(int t, struct bpf_verifier_env *env) mark_prune_point(env, t + off + 1); mark_jmp_point(env, t + off + 1); + mark_jump_target(env, t + off + 1); return ret; diff --git a/kernel/bpf/fixups.c b/kernel/bpf/fixups.c index cd42eb838d6c20..48acb61854ed4f 100644 --- a/kernel/bpf/fixups.c +++ b/kernel/bpf/fixups.c @@ -13,10 +13,15 @@ #define verbose(env, fmt, args...) bpf_verifier_log_write(env, fmt, ##args) +/* + * Matches BPF_PROBE_ATOMIC too: bpf_convert_ctx_accesses() rewrites arena + * atomics before bpf_opt_subreg_zext_lo32_rnd_hi32() runs. + */ static bool is_cmpxchg_insn(const struct bpf_insn *insn) { return BPF_CLASS(insn->code) == BPF_STX && - BPF_MODE(insn->code) == BPF_ATOMIC && + (BPF_MODE(insn->code) == BPF_ATOMIC || + BPF_MODE(insn->code) == BPF_PROBE_ATOMIC) && insn->imm == BPF_CMPXCHG; } diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 9f394e1aa2e85b..59406da06424df 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -530,6 +530,9 @@ static int htab_map_check_btf(struct bpf_map *map, const struct btf *btf, { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); + if (btf_type_is_void(key_type)) + return -EINVAL; + if (htab_is_prealloc(htab)) return 0; /* @@ -1026,7 +1029,7 @@ static void pcpu_copy_value(struct bpf_htab *htab, void __percpu *pptr, } else { u32 size = round_up(htab->map.value_size, 8); void *val; - int cpu; + int cpu, off = 0; if (map_flags & BPF_F_CPU) { cpu = map_flags >> 32; @@ -1038,9 +1041,10 @@ static void pcpu_copy_value(struct bpf_htab *htab, void __percpu *pptr, for_each_possible_cpu(cpu) { ptr = per_cpu_ptr(pptr, cpu); - val = (map_flags & BPF_F_ALL_CPUS) ? value : value + size * cpu; + val = (map_flags & BPF_F_ALL_CPUS) ? value : value + off; copy_map_value(&htab->map, ptr, val); bpf_obj_cancel_fields(&htab->map, ptr); + off += size; } } } @@ -2865,16 +2869,6 @@ static int rhtab_map_alloc_check(union bpf_attr *attr) return htab_map_alloc_check(attr); } -static void rhtab_check_and_free_fields(struct bpf_rhtab *rhtab, - struct rhtab_elem *elem) -{ - if (IS_ERR_OR_NULL(rhtab->map.record)) - return; - - bpf_obj_free_fields(rhtab->map.record, - rhtab_elem_value(elem, rhtab->map.key_size)); -} - static void rhtab_mem_dtor(void *obj, void *ctx) { struct htab_btf_record *hrec = ctx; @@ -2964,8 +2958,8 @@ static int rhtab_delete_elem(struct bpf_rhtab *rhtab, struct rhtab_elem *elem, v rhtab_read_elem_value(&rhtab->map, copy, elem, flags); check_and_init_map_value(&rhtab->map, copy); } - /* Release internal structs: kptr, bpf_timer, task_work, wq */ - rhtab_check_and_free_fields(rhtab, elem); + bpf_obj_cancel_fields(&rhtab->map, + rhtab_elem_value(elem, rhtab->map.key_size)); bpf_mem_cache_free_rcu(&rhtab->ma, elem); return 0; } @@ -3007,7 +3001,6 @@ static int rhtab_map_lookup_and_delete_elem(struct bpf_map *map, void *key, void static long rhtab_map_update_existing(struct bpf_map *map, struct rhtab_elem *elem, void *value, u64 map_flags) { - struct bpf_rhtab *rhtab = container_of(map, struct bpf_rhtab, map); void *old_val = rhtab_elem_value(elem, map->key_size); if (map_flags & BPF_NOEXIST) @@ -3027,7 +3020,7 @@ static long rhtab_map_update_existing(struct bpf_map *map, struct rhtab_elem *el * kptrs/etc. still sit in the slot. Cancel them after the copy * to match arraymap's update semantics. */ - rhtab_check_and_free_fields(rhtab, elem); + bpf_obj_cancel_fields(map, old_val); return 0; } @@ -3068,7 +3061,6 @@ static long rhtab_map_update_elem(struct bpf_map *map, void *key, void *value, u memcpy(elem->data, key, map->key_size); copy_map_value(map, rhtab_elem_value(elem, map->key_size), value); - check_and_init_map_value(map, rhtab_elem_value(elem, map->key_size)); /* Prevent deadlock for NMI programs attempting to take bucket lock */ bpf_disable_instrumentation(); @@ -3112,6 +3104,9 @@ static int rhtab_map_check_btf(struct bpf_map *map, const struct btf *btf, { struct bpf_rhtab *rhtab = container_of(map, struct bpf_rhtab, map); + if (btf_type_is_void(key_type)) + return -EINVAL; + return bpf_ma_set_dtor(map, &rhtab->ma, rhtab_mem_dtor); } diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c index 23267213a17fb7..83cd527a2542bd 100644 --- a/kernel/bpf/local_storage.c +++ b/kernel/bpf/local_storage.c @@ -220,7 +220,7 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *_map, void *key, struct bpf_cgroup_storage *storage; void *val; u32 size; - int cpu; + int cpu, off = 0; if ((u32)map_flags & ~(BPF_ANY | BPF_EXIST | BPF_F_CPU | BPF_F_ALL_CPUS)) return -EINVAL; @@ -245,8 +245,9 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *_map, void *key, } size = round_up(_map->value_size, 8); for_each_possible_cpu(cpu) { - val = (map_flags & BPF_F_ALL_CPUS) ? value : value + size * cpu; + val = (map_flags & BPF_F_ALL_CPUS) ? value : value + off; copy_map_value(_map, per_cpu_ptr(storage->percpu_buf, cpu), val); + off += size; } unlock: rcu_read_unlock(); diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index 142a65672c6f97..e41fb1c567cd79 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -880,6 +880,7 @@ BPF_CALL_4(bpf_get_stack_sleepable, struct pt_regs *, regs, void *, buf, u32, si const struct bpf_func_proto bpf_get_stack_sleepable_proto = { .func = bpf_get_stack_sleepable, .gpl_only = true, + .might_sleep = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_UNINIT_MEM, @@ -933,6 +934,7 @@ BPF_CALL_4(bpf_get_task_stack_sleepable, struct task_struct *, task, void *, buf const struct bpf_func_proto bpf_get_task_stack_sleepable_proto = { .func = bpf_get_task_stack_sleepable, .gpl_only = false, + .might_sleep = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID, .arg1_btf_id = &btf_tracing_ids[BTF_TRACING_TYPE_TASK], diff --git a/kernel/bpf/states.c b/kernel/bpf/states.c index 4e6aafad33bd2f..66fb11b6c6a765 100644 --- a/kernel/bpf/states.c +++ b/kernel/bpf/states.c @@ -445,22 +445,19 @@ static void __clean_func_state(struct bpf_verifier_env *env, struct bpf_reg_state *spill = &st->stack[i].spilled_ptr; if (lo_live && stype == STACK_SPILL) { - u8 val = STACK_MISC; - if (spill->type != SCALAR_VALUE) continue; - /* - * 8 byte spill of scalar 0 where half slot is dead - * should become STACK_ZERO in lo 4 bytes. + * Can't replace with STACK_ZERO, because + * that requires bpf_mark_chain_precision(). */ if (bpf_register_is_null(spill)) - val = STACK_ZERO; + continue; for (j = 0; j < 4; j++) { u8 *t = &st->stack[i].slot_type[j]; if (*t == STACK_SPILL) - *t = val; + *t = STACK_MISC; } } bpf_mark_reg_not_init(env, spill); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index fb678b9dcd3e62..c7cb336fb0648c 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -6633,6 +6633,7 @@ EXPORT_SYMBOL_NS(kern_sys_bpf, "BPF_INTERNAL"); static const struct bpf_func_proto bpf_sys_bpf_proto = { .func = bpf_sys_bpf, .gpl_only = false, + .might_sleep = true, .ret_type = RET_INTEGER, .arg1_type = ARG_ANYTHING, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, @@ -6658,6 +6659,7 @@ BPF_CALL_1(bpf_sys_close, u32, fd) static const struct bpf_func_proto bpf_sys_close_proto = { .func = bpf_sys_close, .gpl_only = false, + .might_sleep = true, .ret_type = RET_INTEGER, .arg1_type = ARG_ANYTHING, }; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 14a9fd2d547200..1a0cd37b03cdef 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -367,9 +367,18 @@ static bool reg_not_null(struct bpf_verifier_env *env, const struct bpf_reg_stat if (type_may_be_null(type)) return false; + /* + * The types below guarantee a non-NULL base, an unbounded offset can + * still wrap base + offset to zero. + */ + if (reg_smin(reg) <= -BPF_MAX_VAR_OFF || reg_smax(reg) >= BPF_MAX_VAR_OFF) + return false; + type = base_type(type); return type == PTR_TO_SOCKET || type == PTR_TO_TCP_SOCK || + type == PTR_TO_XDP_SOCK || + type == PTR_TO_BUF || type == PTR_TO_MAP_VALUE || type == PTR_TO_MAP_KEY || type == PTR_TO_SOCK_COMMON || @@ -1611,6 +1620,8 @@ static int copy_func_state(struct bpf_func_state *dst, const struct bpf_func_state *src) { memcpy(dst, src, offsetof(struct bpf_func_state, stack)); + /* Instruction accounting is path-local, not part of verifier state. */ + dst->insns_subtotal = 0; return copy_stack_state(dst, src); } @@ -4309,6 +4320,13 @@ static int map_kptr_match_type(struct bpf_verifier_env *env, if (type_flag(reg->type) & ~perm_flags) goto bad_type; + /* + * A BPF_KPTR_PERCPU field is read back as MEM_PERCPU, so the value + * stored in it must carry the same flag. + */ + if ((kptr_field->type == BPF_KPTR_PERCPU) != !!(reg->type & MEM_PERCPU)) + goto bad_type; + /* We need to verify reg->type and reg->btf, before accessing reg->btf */ reg_name = btf_type_name(reg->btf, reg->btf_id); @@ -4510,8 +4528,15 @@ static int check_map_kptr_access(struct bpf_verifier_env *env, return ret; } else if (class == BPF_STX) { val_reg = reg_state(env, value_regno); - if (!bpf_register_is_null(val_reg) && - map_kptr_match_type(env, kptr_field, val_reg, value_regno)) + if (bpf_register_is_null(val_reg)) { + /* + * This store is valid only because the scalar is known to be + * zero. Mark it precise so another scalar cannot be pruned + * against this state. + */ + return mark_chain_precision(env, value_regno); + } + if (map_kptr_match_type(env, kptr_field, val_reg, value_regno)) return -EACCES; } else if (class == BPF_ST) { if (insn->imm) { @@ -5115,6 +5140,15 @@ static int check_max_stack_depth_subprog(struct bpf_verifier_env *env, int idx, if (!priv_stack_supported) subprog[idx].priv_stack_mode = NO_PRIV_STACK; process_func: + if (subprog[idx].has_ld_abs) { + for (tmp = idx; tmp >= 0; tmp = dinfo[tmp].caller) { + if (subprog[tmp].is_cb) { + verbose(env, "cannot use BPF_LD_[ABS|IND] within callback\n"); + return -EINVAL; + } + } + } + /* protect against potential stack overflow that might happen when * bpf2bpf calls get combined with tailcalls. Limit the caller's stack * depth for such case down to 256 so that the worst case scenario @@ -7843,6 +7877,7 @@ static const struct bpf_reg_types *compatible_reg_types[__BPF_ARG_TYPE_MAX] = { [ARG_CONST_SIZE] = &scalar_types, [ARG_CONST_SIZE_OR_ZERO] = &scalar_types, [ARG_CONST_ALLOC_SIZE_OR_ZERO] = &scalar_types, + [ARG_SCALAR] = &scalar_types, [ARG_CONST_MAP_PTR] = &const_map_ptr_types, [ARG_PTR_TO_CTX] = &context_types, [ARG_PTR_TO_SOCK_COMMON] = &sock_types, @@ -8283,11 +8318,15 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 arg, return err; } - if (bpf_register_is_null(reg) && type_may_be_null(arg_type)) + if (bpf_register_is_null(reg) && type_may_be_null(arg_type)) { /* A NULL register has a SCALAR_VALUE type, so skip * type checking. */ + err = mark_chain_precision(env, regno); + if (err) + return err; goto skip_type_check; + } /* arg_btf_id and arg_size are in a union. */ if (base_type(arg_type) == ARG_PTR_TO_BTF_ID || @@ -9495,10 +9534,12 @@ int map_set_for_each_callback_args(struct bpf_verifier_env *env, callee->regs[BPF_REG_2].type = PTR_TO_MAP_KEY; __mark_reg_known_zero(&callee->regs[BPF_REG_2]); callee->regs[BPF_REG_2].map_ptr = caller->regs[BPF_REG_1].map_ptr; + callee->regs[BPF_REG_2].map_uid = caller->regs[BPF_REG_1].map_uid; callee->regs[BPF_REG_3].type = PTR_TO_MAP_VALUE; __mark_reg_known_zero(&callee->regs[BPF_REG_3]); callee->regs[BPF_REG_3].map_ptr = caller->regs[BPF_REG_1].map_ptr; + callee->regs[BPF_REG_3].map_uid = caller->regs[BPF_REG_1].map_uid; /* pointer to stack or null */ callee->regs[BPF_REG_4] = caller->regs[BPF_REG_3]; @@ -9576,6 +9617,7 @@ static int set_timer_callback_state(struct bpf_verifier_env *env, int insn_idx) { struct bpf_map *map_ptr = caller->regs[BPF_REG_1].map_ptr; + u32 map_uid = caller->regs[BPF_REG_1].map_uid; /* bpf_timer_set_callback(struct bpf_timer *timer, void *callback_fn); * callback_fn(struct bpf_map *map, void *key, void *value); @@ -9583,14 +9625,17 @@ static int set_timer_callback_state(struct bpf_verifier_env *env, callee->regs[BPF_REG_1].type = CONST_PTR_TO_MAP; __mark_reg_known_zero(&callee->regs[BPF_REG_1]); callee->regs[BPF_REG_1].map_ptr = map_ptr; + callee->regs[BPF_REG_1].map_uid = map_uid; callee->regs[BPF_REG_2].type = PTR_TO_MAP_KEY; __mark_reg_known_zero(&callee->regs[BPF_REG_2]); callee->regs[BPF_REG_2].map_ptr = map_ptr; + callee->regs[BPF_REG_2].map_uid = map_uid; callee->regs[BPF_REG_3].type = PTR_TO_MAP_VALUE; __mark_reg_known_zero(&callee->regs[BPF_REG_3]); callee->regs[BPF_REG_3].map_ptr = map_ptr; + callee->regs[BPF_REG_3].map_uid = map_uid; /* unused */ bpf_mark_reg_not_init(env, &callee->regs[BPF_REG_4]); @@ -9690,6 +9735,7 @@ static int set_task_work_schedule_callback_state(struct bpf_verifier_env *env, int insn_idx) { struct bpf_map *map_ptr = caller->regs[BPF_REG_3].map_ptr; + u32 map_uid = caller->regs[BPF_REG_3].map_uid; /* * callback_fn(struct bpf_map *map, void *key, void *value); @@ -9697,14 +9743,17 @@ static int set_task_work_schedule_callback_state(struct bpf_verifier_env *env, callee->regs[BPF_REG_1].type = CONST_PTR_TO_MAP; __mark_reg_known_zero(&callee->regs[BPF_REG_1]); callee->regs[BPF_REG_1].map_ptr = map_ptr; + callee->regs[BPF_REG_1].map_uid = map_uid; callee->regs[BPF_REG_2].type = PTR_TO_MAP_KEY; __mark_reg_known_zero(&callee->regs[BPF_REG_2]); callee->regs[BPF_REG_2].map_ptr = map_ptr; + callee->regs[BPF_REG_2].map_uid = map_uid; callee->regs[BPF_REG_3].type = PTR_TO_MAP_VALUE; __mark_reg_known_zero(&callee->regs[BPF_REG_3]); callee->regs[BPF_REG_3].map_ptr = map_ptr; + callee->regs[BPF_REG_3].map_uid = map_uid; /* unused */ bpf_mark_reg_not_init(env, &callee->regs[BPF_REG_4]); @@ -9716,9 +9765,46 @@ static int set_task_work_schedule_callback_state(struct bpf_verifier_env *env, static bool is_rbtree_lock_required_kfunc(u32 btf_id); -/* Are we currently verifying the callback for a rbtree helper that must - * be called with lock held? If so, no need to complain about unreleased - * lock +static void account_processed_insn(struct bpf_verifier_env *env) +{ + struct bpf_func_state *frame = cur_func(env); + + env->insn_processed++; + frame->insns_subtotal++; + env->subprog_info[frame->subprogno].insns_self++; +} + +static void account_processed_insns(struct bpf_verifier_env *env, + struct bpf_func_state *callee, + struct bpf_func_state *caller) +{ + u32 insns; + + if (!callee) + return; + + insns = callee->insns_subtotal; + + env->subprog_info[callee->subprogno].insns_total += insns; + if (caller) + caller->insns_subtotal += insns; + callee->insns_subtotal = 0; +} + +static void account_current_path(struct bpf_verifier_env *env) +{ + struct bpf_verifier_state *state = env->cur_state; + int frame; + + for (frame = state->curframe; frame >= 0; frame--) + account_processed_insns(env, state->frame[frame], + frame ? state->frame[frame - 1] : NULL); +} + +/* + * Are we currently verifying the callback for an rbtree kfunc that must + * be called with a lock held, or one of that callback's subprogs? If so, + * no need to complain about an unreleased lock. */ static bool in_rbtree_lock_required_cb(struct bpf_verifier_env *env) { @@ -9726,17 +9812,19 @@ static bool in_rbtree_lock_required_cb(struct bpf_verifier_env *env) struct bpf_insn *insn = env->prog->insnsi; struct bpf_func_state *callee; int kfunc_btf_id; + u32 frame; - if (!state->curframe) - return false; - - callee = state->frame[state->curframe]; + for (frame = state->curframe; frame; frame--) { + callee = state->frame[frame]; + if (!callee->in_callback_fn) + continue; - if (!callee->in_callback_fn) - return false; + kfunc_btf_id = insn[callee->callsite].imm; + if (is_rbtree_lock_required_kfunc(kfunc_btf_id)) + return true; + } - kfunc_btf_id = insn[callee->callsite].imm; - return is_rbtree_lock_required_kfunc(kfunc_btf_id); + return false; } static bool retval_range_within(struct bpf_retval_range range, const struct bpf_reg_state *reg) @@ -9812,6 +9900,7 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx) verbose(env, "to caller at %d:\n", *insn_idx); print_verifier_state(env, state, caller->frameno, true); } + account_processed_insns(env, callee, caller); /* clear everything in the callee. In case of exceptional exits using * bpf_throw, this will be done by copy_verifier_state for extra frames. */ free_func_state(callee); @@ -10100,33 +10189,45 @@ static struct bpf_insn_aux_data *cur_aux(const struct bpf_verifier_env *env) return &env->insn_aux_data[env->insn_idx]; } -static bool loop_flag_is_zero(struct bpf_verifier_env *env) +/* Returns 1 if R4 is a known zero, 0 if it is not, a negative errno on error. */ +static int loop_flag_is_zero(struct bpf_verifier_env *env) { struct bpf_reg_state *reg = reg_state(env, BPF_REG_4); - bool reg_is_null = bpf_register_is_null(reg); + int err; - if (reg_is_null) - mark_chain_precision(env, BPF_REG_4); + if (!bpf_register_is_null(reg)) + return 0; - return reg_is_null; + err = mark_chain_precision(env, BPF_REG_4); + if (err) + return err; + return 1; } -static void update_loop_inline_state(struct bpf_verifier_env *env, u32 subprogno) +static int update_loop_inline_state(struct bpf_verifier_env *env, u32 subprogno) { struct bpf_loop_inline_state *state = &cur_aux(env)->loop_inline_state; + int flag_is_zero; if (!state->initialized) { + flag_is_zero = loop_flag_is_zero(env); + if (flag_is_zero < 0) + return flag_is_zero; state->initialized = 1; - state->fit_for_inline = loop_flag_is_zero(env); + state->fit_for_inline = flag_is_zero; state->callback_subprogno = subprogno; - return; + return 0; } if (!state->fit_for_inline) - return; + return 0; - state->fit_for_inline = (loop_flag_is_zero(env) && + flag_is_zero = loop_flag_is_zero(env); + if (flag_is_zero < 0) + return flag_is_zero; + state->fit_for_inline = (flag_is_zero && state->callback_subprogno == subprogno); + return 0; } /* Returns whether or not the given map can potentially elide @@ -10318,6 +10419,9 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn verbose(env, "get_local_storage() doesn't support non-zero flags\n"); return -EINVAL; } + err = mark_chain_precision(env, BPF_REG_2); + if (err) + return err; break; case BPF_FUNC_for_each_map_elem: err = push_callback_call(env, insn, insn_idx, meta.subprogno, @@ -10335,7 +10439,9 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn err = check_bpf_snprintf_call(env, regs); break; case BPF_FUNC_loop: - update_loop_inline_state(env, meta.subprogno); + err = update_loop_inline_state(env, meta.subprogno); + if (err) + return err; /* Verifier relies on R1 value to determine if bpf_loop() iteration * is finished, thus mark it precise. */ @@ -10670,6 +10776,17 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn if (env->cur_state->curframe) { struct bpf_verifier_state *branch; + /* + * A taken tail call is modeled as a return from the current + * frame. A callback frame cannot be left that way because + * prepare_func_exit() would apply its return contract to the + * unknown R0 synthesized below. Stack-depth validation rejects + * this construct anyway. + */ + if (cur_func(env)->in_callback_fn) { + verbose(env, "cannot tail call within callback\n"); + return -EINVAL; + } mark_reg_scratched(env, BPF_REG_0); branch = push_stack(env, env->insn_idx + 1, env->insn_idx, false); if (IS_ERR(branch)) @@ -12459,7 +12576,7 @@ check_ok: reg_arg_name(env, argno)); return -EINVAL; } - if (!type_is_non_owning_ref(reg->type)) + if (!type_is_non_owning_ref(reg->type) && reg_is_referenced(env, reg)) meta->arg_owning_ref = true; rec = reg_btf_record(reg); @@ -12531,6 +12648,11 @@ check_ok: { int flags = PROCESS_RES_LOCK; + if (in_rbtree_lock_required_cb(env)) { + verbose(env, "can't res_spin_{lock,unlock} in rbtree cb\n"); + return -EACCES; + } + if (reg->type != PTR_TO_MAP_VALUE && reg->type != (PTR_TO_BTF_ID | MEM_ALLOC)) { verbose(env, "%s doesn't point to map value or allocated object\n", reg_arg_name(env, argno)); @@ -13794,9 +13916,6 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, !check_reg_sane_offset_ptr(env, ptr_reg, ptr_reg->type)) return -EINVAL; - /* pointer types do not carry 32-bit bounds at the moment. */ - __mark_reg32_unbounded(dst_reg); - if (sanitize_needed(opcode)) { ret = sanitize_ptr_alu(env, insn, ptr_reg, off_reg, dst_reg, &info, false); @@ -13804,6 +13923,14 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, return sanitize_err(env, insn, ret); } + /* + * Pointer types do not carry 32-bit bounds at the moment. Blank r32 + * only after sanitize_ptr_alu() may have snapshotted dst_reg into a + * speculative path: otherwise reg_bounds_sanity_check() might hit some + * constraints violations. + */ + __mark_reg32_unbounded(dst_reg); + switch (opcode) { case BPF_ADD: /* @@ -15495,6 +15622,13 @@ static int is_branch_taken(struct bpf_verifier_env *env, struct bpf_reg_state *r if (__is_pointer_value(false, reg1) || __is_pointer_value(false, reg2)) { u64 val; + /* + * The low 32 bits of a valid pointer may well be zero, hence + * nothing below applies to a 32-bit comparison. + */ + if (is_jmp32) + return -1; + /* arrange that reg2 is a scalar, and reg1 is a pointer */ if (!is_reg_const(reg2, is_jmp32)) { opcode = flip_opcode(opcode); @@ -16061,6 +16195,16 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, return err; } + /* + * Collect the linked registers before env->{true,false}_reg{1,2} setup, + * otherwise ids dropped by collect_linked_regs() would be resurrected + * when env->{true,false}_reg{1,2} are copied back. + */ + if (BPF_SRC(insn->code) == BPF_X && src_reg->type == SCALAR_VALUE && src_reg->id) + collect_linked_regs(env, this_branch, src_reg->id, &linked_regs); + if (dst_reg->type == SCALAR_VALUE && dst_reg->id) + collect_linked_regs(env, this_branch, dst_reg->id, &linked_regs); + is_jmp32 = BPF_CLASS(insn->code) == BPF_JMP32; env->false_reg1 = *dst_reg; env->false_reg2 = *src_reg; @@ -16115,10 +16259,6 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, * 'this_branch' and 'other_branch' share this history * if parent state is created. */ - if (BPF_SRC(insn->code) == BPF_X && src_reg->type == SCALAR_VALUE && src_reg->id) - collect_linked_regs(env, this_branch, src_reg->id, &linked_regs); - if (dst_reg->type == SCALAR_VALUE && dst_reg->id) - collect_linked_regs(env, this_branch, dst_reg->id, &linked_regs); if (linked_regs.cnt > 1) { err = bpf_push_jmp_history(env, this_branch, 0, 0, 0, linked_regs_pack(&linked_regs)); if (err) @@ -16168,7 +16308,6 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, */ if (!is_jmp32 && BPF_SRC(insn->code) == BPF_X && __is_pointer_value(false, src_reg) && __is_pointer_value(false, dst_reg) && - type_may_be_null(src_reg->type) != type_may_be_null(dst_reg->type) && base_type(src_reg->type) != PTR_TO_BTF_ID && base_type(dst_reg->type) != PTR_TO_BTF_ID) { eq_branch_regs = NULL; @@ -16184,9 +16323,11 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, break; } if (eq_branch_regs) { - if (type_may_be_null(src_reg->type)) + /* src == dst && dst != NULL => src != NULL */ + if (reg_not_null(env, dst_reg) && type_may_be_null(src_reg->type)) mark_ptr_not_null_reg(&eq_branch_regs[insn->src_reg]); - else + /* src == dst && src != NULL => dst != NULL */ + if (reg_not_null(env, src_reg) && type_may_be_null(dst_reg->type)) mark_ptr_not_null_reg(&eq_branch_regs[insn->dst_reg]); } } @@ -16201,6 +16342,15 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, type_may_be_null(dst_reg->type) && ((BPF_SRC(insn->code) == BPF_K && insn->imm == 0) || (BPF_SRC(insn->code) == BPF_X && bpf_register_is_null(src_reg)))) { + /* + * For BPF_X the zero is a property of this execution path, + * hence src_reg has to be precise. + */ + if (BPF_SRC(insn->code) == BPF_X) { + err = mark_chain_precision(env, insn->src_reg); + if (err) + return err; + } /* Mark all identical registers in each branch as either * safe or unknown depending R == 0 or R != 0 conditional. */ @@ -16283,6 +16433,15 @@ static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn) verbose(env, "callback function not static\n"); return -EINVAL; } + /* + * When env->subprog_cnt == 1 this instruction won't be rewritten + * to hold a real function address. Assume that no usable program + * combines e.g. main and timer callback and just reject here. + */ + if (subprogno == 0) { + verbose(env, "callback function cannot be the main program\n"); + return -EINVAL; + } dst_reg->type = PTR_TO_FUNC; dst_reg->subprogno = subprogno; @@ -16345,6 +16504,7 @@ static bool may_access_skb(enum bpf_prog_type type) */ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) { + struct bpf_verifier_state *state = env->cur_state; struct bpf_reg_state *regs = cur_regs(env); static const int ctx_reg = BPF_REG_6; u8 mode = BPF_MODE(insn->code); @@ -16355,6 +16515,13 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) return -EINVAL; } + for (i = state->curframe; i; i--) { + if (state->frame[i]->in_callback_fn) { + verbose(env, "cannot use BPF_LD_[ABS|IND] within callback\n"); + return -EINVAL; + } + } + if (!env->ops->gen_ld_abs) { verifier_bug(env, "gen_ld_abs is null"); return -EFAULT; @@ -16823,6 +16990,10 @@ bool bpf_get_call_summary(struct bpf_verifier_env *env, struct bpf_insn *call, * r0 = *(u64 *)(r10 - 8); r0 += r1; * r0 += r1; exit; * exit; + * + * Both uses of the marks assume that a pattern is entered at its first + * spill and thus executes as a unit, hence a pattern is not grown past + * an instruction targeted by a jump. */ static void mark_fastcall_pattern_for_call(struct bpf_verifier_env *env, struct bpf_subprog_info *subprog, @@ -16861,6 +17032,10 @@ static void mark_fastcall_pattern_for_call(struct bpf_verifier_env *env, for (i = 1, off = lowest_off; i <= ARRAY_SIZE(caller_saved); ++i, off += BPF_REG_SIZE) { if (insn_idx - i < 0 || insn_idx + i >= env->prog->len) break; + /* stx/ldx/call must not be a jump targets, a jump to the first stx is fine */ + if (bpf_is_jump_target(env, insn_idx - i + 1) || + bpf_is_jump_target(env, insn_idx + i)) + break; stx = &insns[insn_idx - i]; ldx = &insns[insn_idx + i]; /* must be a stack spill/fill pair */ @@ -17404,7 +17579,9 @@ static int do_check(struct bpf_verifier_env *env) insn = &insns[env->insn_idx]; insn_aux = &env->insn_aux_data[env->insn_idx]; - if (++env->insn_processed > BPF_COMPLEXITY_LIMIT_INSNS) { + account_processed_insn(env); + + if (env->insn_processed > BPF_COMPLEXITY_LIMIT_INSNS) { verbose(env, "BPF program is too large. Processed %d insn\n", env->insn_processed); @@ -17544,6 +17721,7 @@ static int do_check(struct bpf_verifier_env *env) "speculation barrier after jump instruction may not have the desired effect")) return -EFAULT; process_bpf_exit: + account_current_path(env); mark_verifier_state_scratched(env); err = bpf_update_branch_counts(env, env->cur_state); if (err) @@ -18538,6 +18716,7 @@ static int do_check_common(struct bpf_verifier_env *env, int subprog) ret = do_check(env); out: + account_current_path(env); if (!ret && pop_log) bpf_vlog_reset(&env->log, 0); free_states(env); @@ -18569,7 +18748,6 @@ static int do_check_subprogs(struct bpf_verifier_env *env) struct bpf_prog_aux *aux = env->prog->aux; struct bpf_func_info_aux *sub_aux; int i, ret, new_cnt; - u32 insn_processed; if (!aux->func_info) return 0; @@ -18584,8 +18762,6 @@ again: if (!bpf_subprog_is_global(env, i)) continue; - insn_processed = env->insn_processed; - sub_aux = subprog_aux(env, i); if (!sub_aux->called || sub_aux->verified) continue; @@ -18593,7 +18769,6 @@ again: env->insn_idx = env->subprog_info[i].start; WARN_ON_ONCE(env->insn_idx == 0); ret = do_check_common(env, i); - env->subprog_info[i].insn_processed = env->insn_processed - insn_processed; if (ret) { return ret; } else if (env->log.level & BPF_LOG_LEVEL) { @@ -18620,12 +18795,10 @@ again: static int do_check_main(struct bpf_verifier_env *env) { - u32 insn_processed = env->insn_processed; int ret; env->insn_idx = 0; ret = do_check_common(env, 0); - env->subprog_info[0].insn_processed = env->insn_processed - insn_processed; if (!ret) env->prog->aux->stack_depth = env->subprog_info[0].stack_depth; return ret; @@ -18644,10 +18817,10 @@ static void print_verification_stats(struct bpf_verifier_env *env) for (i = 1; i < subprog_cnt; i++) verbose(env, "+%d", env->subprog_info[i].stack_depth); verbose(env, " max %d\n", env->max_stack_depth); - verbose(env, "insns processed %d", env->subprog_info[0].insn_processed); + verbose(env, "insns processed %d", env->subprog_info[0].insns_total); for (i = 1; i < subprog_cnt; i++) if (bpf_subprog_is_global(env, i)) - verbose(env, "+%d", env->subprog_info[i].insn_processed); + verbose(env, "+%d", env->subprog_info[i].insns_total); verbose(env, "\n"); } verbose(env, "processed %d insns (limit %d) max_states_per_insn %d " diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 1c6d568006688b..69ff86e03c630e 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -1220,6 +1220,28 @@ static void reset_partition_data(struct cpuset *cs) cpumask_copy(cs->effective_cpus, parent->effective_cpus); } +/* Return true if isolated_cpus changes. */ +static bool isolated_cpu_update(int new_prs, int cpu) +{ + lockdep_assert_held(&callback_lock); + lockdep_assert_held(&cpuset_mutex); + + if (new_prs == PRS_ISOLATED) { + if (cpumask_test_cpu(cpu, isolated_cpus)) + return false; + cpumask_set_cpu(cpu, isolated_cpus); + return true; + } + + /* CPUs isolated at boot must remain isolated. */ + if (!cpumask_test_cpu(cpu, + housekeeping_cpumask(HK_TYPE_DOMAIN_BOOT)) || + !cpumask_test_cpu(cpu, isolated_cpus)) + return false; + cpumask_clear_cpu(cpu, isolated_cpus); + return true; +} + /* * isolated_cpus_update - Update the isolated_cpus mask * @old_prs: old partition_root_state @@ -1228,19 +1250,16 @@ static void reset_partition_data(struct cpuset *cs) */ static void isolated_cpus_update(int old_prs, int new_prs, struct cpumask *xcpus) { + bool updated = false; + int cpu; + WARN_ON_ONCE(old_prs == new_prs); lockdep_assert_held(&callback_lock); lockdep_assert_held(&cpuset_mutex); - if (new_prs == PRS_ISOLATED) { - if (cpumask_subset(xcpus, isolated_cpus)) - return; - cpumask_or(isolated_cpus, isolated_cpus, xcpus); - } else { - if (!cpumask_intersects(xcpus, isolated_cpus)) - return; - cpumask_andnot(isolated_cpus, isolated_cpus, xcpus); - } - update_housekeeping = true; + for_each_cpu(cpu, xcpus) + updated |= isolated_cpu_update(new_prs, cpu); + if (updated) + update_housekeeping = true; } /* diff --git a/kernel/events/core.c b/kernel/events/core.c index ed3b62b0f948fb..bd8c1acf59e2e6 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -3925,13 +3925,13 @@ static void perf_pmu_sched_task(struct task_struct *prev, bool sched_in) { struct perf_cpu_context *cpuctx = this_cpu_ptr(&perf_cpu_context); - struct perf_cpu_pmu_context *cpc; + struct perf_cpu_pmu_context *cpc, *cpc2; /* cpuctx->task_ctx will be handled in perf_event_context_sched_in/out */ if (prev == next || cpuctx->task_ctx) return; - list_for_each_entry(cpc, this_cpu_ptr(&sched_cb_list), sched_cb_entry) + list_for_each_entry_safe(cpc, cpc2, this_cpu_ptr(&sched_cb_list), sched_cb_entry) __perf_pmu_sched_task(cpc, sched_in ? next : prev, sched_in); } diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index 9fe92161715e09..1b1ffe0533e58a 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -509,7 +509,10 @@ void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size) /* * Only send RECORD_AUX if we have something useful to communicate * - * Note: the OVERWRITE records by themselves are not considered + * PMU_FORMAT bits identify the PMU type rather than an AUX event + * has occurred, so ignore them for zero-sized records. + * + * The OVERWRITE records by themselves are not considered * useful, as they don't communicate any *new* information, * aside from the short-lived offset, that becomes history at * the next event sched-in and therefore isn't useful. @@ -518,7 +521,9 @@ void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size) * offset. So, from now on we don't output AUX records that * have *only* OVERWRITE flag set. */ - if (size || (handle->aux_flags & ~(u64)PERF_AUX_FLAG_OVERWRITE)) + if (size || + (handle->aux_flags & ~(u64)(PERF_AUX_FLAG_PMU_FORMAT_TYPE_MASK | + PERF_AUX_FLAG_OVERWRITE))) perf_event_aux_event(handle->event, aux_head, size, handle->aux_flags); diff --git a/kernel/exit.c b/kernel/exit.c index 2c0b1c02920f46..e4cd7232015df1 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -262,8 +262,11 @@ repeat: pidfs_exit(p); cgroup_task_release(p); - /* Retrieve @thread_pid before __unhash_process() may set it to NULL. */ - thread_pid = task_pid(p); + /* + * Pin @thread_pid before __unhash_process() clears it. The last + * PIDTYPE detach can otherwise free it before proc_flush_pid(). + */ + thread_pid = get_pid(task_pid(p)); write_lock_irq(&tasklist_lock); ptrace_release_task(p); @@ -292,8 +295,8 @@ repeat: } write_unlock_irq(&tasklist_lock); - /* @thread_pid can't go away until free_pids() below */ proc_flush_pid(thread_pid); + put_pid(thread_pid); exit_cred_namespaces(p); add_device_randomness(&p->se.sum_exec_runtime, sizeof(p->se.sum_exec_runtime)); diff --git a/kernel/fork.c b/kernel/fork.c index abc2f01ac35731..3340dbaf2bb4a8 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -2114,6 +2114,11 @@ __latent_entropy struct task_struct *copy_process( p = dup_task_struct(current, node); if (!p) goto fork_out; + /* + * Must run before the first fallible op, so error paths never + * free the parent's ret_stack. + */ + ftrace_graph_init_task(p); retval = copy_exec_state(clone_flags, p); if (retval) goto bad_fork_free; @@ -2140,8 +2145,6 @@ __latent_entropy struct task_struct *copy_process( */ p->clear_child_tid = (clone_flags & CLONE_CHILD_CLEARTID) ? args->child_tid : NULL; - ftrace_graph_init_task(p); - rt_mutex_init_task(p); raw_spin_lock_init(&p->blocked_lock); diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index e0de811148242a..06f025abe88757 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -947,6 +947,34 @@ look_up_lock_class(const struct lockdep_map *lock, unsigned int subclass) return NULL; } +static __always_inline bool lock_class_cache_is_valid(const struct lockdep_map *lock, + const struct lock_class *class, + unsigned int subclass) +{ + unsigned int class_subclass; + + if (!class) + return false; + + if (unlikely(class < lock_classes || class >= lock_classes + MAX_LOCKDEP_KEYS)) + return false; + + if (unlikely(!arch_test_bit(class - lock_classes, lock_classes_in_use))) + return false; + + if (unlikely(!lock->key)) + return false; + + class_subclass = subclass ? subclass : class->subclass; + if (unlikely(class_subclass >= MAX_LOCKDEP_SUBCLASSES)) + return false; + + if (unlikely(READ_ONCE(class->key) != lock->key->subkeys + class_subclass)) + return false; + + return true; +} + /* * Static locks do not have their class-keys yet - for them the key is * the lock object itself. If the lock is in the per cpu area, the @@ -1379,9 +1407,9 @@ out_unlock_set: out_set_class_cache: if (!subclass || force) - lock->class_cache[0] = class; + WRITE_ONCE(lock->class_cache[0], class); else if (subclass < NR_LOCKDEP_CACHING_CLASSES) - lock->class_cache[subclass] = class; + WRITE_ONCE(lock->class_cache[subclass], class); /* * Hash collision, did we smoke some? We found a class with a matching @@ -4941,7 +4969,7 @@ void lockdep_init_map_type(struct lockdep_map *lock, const char *name, int i; for (i = 0; i < NR_LOCKDEP_CACHING_CLASSES; i++) - lock->class_cache[i] = NULL; + WRITE_ONCE(lock->class_cache[i], NULL); #ifdef CONFIG_LOCK_STAT lock->cpu = raw_smp_processor_id(); @@ -5006,12 +5034,15 @@ EXPORT_SYMBOL_GPL(__lockdep_no_track__); void lockdep_set_lock_cmp_fn(struct lockdep_map *lock, lock_cmp_fn cmp_fn, lock_print_fn print_fn) { - struct lock_class *class = lock->class_cache[0]; + struct lock_class *class = READ_ONCE(lock->class_cache[0]); unsigned long flags; raw_local_irq_save(flags); lockdep_recursion_inc(); + if (!lock_class_cache_is_valid(lock, class, 0)) + class = NULL; + if (!class) class = register_lock_class(lock, 0, 0); @@ -5103,8 +5134,11 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass, if (DEBUG_LOCKS_WARN_ON(subclass >= MAX_LOCKDEP_SUBCLASSES)) return 0; - if (subclass < NR_LOCKDEP_CACHING_CLASSES) - class = lock->class_cache[subclass]; + if (subclass < NR_LOCKDEP_CACHING_CLASSES) { + class = READ_ONCE(lock->class_cache[subclass]); + if (!lock_class_cache_is_valid(lock, class, subclass)) + class = NULL; + } /* * Not cached? */ @@ -5307,9 +5341,9 @@ static noinstr int match_held_lock(const struct held_lock *hlock, return 1; if (hlock->references) { - const struct lock_class *class = lock->class_cache[0]; + const struct lock_class *class = READ_ONCE(lock->class_cache[0]); - if (!class) + if (!lock_class_cache_is_valid(lock, class, 0)) class = look_up_lock_class(lock, 0); /* diff --git a/kernel/nstree.c b/kernel/nstree.c index 6d12e5900ac015..831f279d174a32 100644 --- a/kernel/nstree.c +++ b/kernel/nstree.c @@ -533,19 +533,13 @@ DEFINE_FREE(ns_put, struct ns_common *, if (!IS_ERR_OR_NULL(_T)) ns_put(_T)) static inline struct ns_common *__must_check legitimize_ns(const struct klistns *kls, struct ns_common *candidate) { - struct ns_common *ns __free(ns_put) = NULL; - if (!ns_requested(kls, candidate)) return NULL; - ns = ns_get_unless_inactive(candidate); - if (!ns) - return NULL; - - if (!may_list_ns(kls, ns)) + if (!may_list_ns(kls, candidate)) return NULL; - return no_free_ptr(ns); + return ns_get_unless_inactive(candidate); } static ssize_t do_listns_userns(struct klistns *kls) diff --git a/kernel/printk/nbcon.c b/kernel/printk/nbcon.c index 4b03b019cd5ee2..ad79e30afd647b 100644 --- a/kernel/printk/nbcon.c +++ b/kernel/printk/nbcon.c @@ -1382,7 +1382,7 @@ bool nbcon_kthread_create(struct console *con) return true; kt = kthread_run(nbcon_kthread_func, con, "pr/%s%d", con->name, con->index); - if (WARN_ON(IS_ERR(kt))) { + if (IS_ERR(kt)) { con_printk(KERN_ERR, con, "failed to start printing thread\n"); return false; } @@ -1782,7 +1782,7 @@ bool nbcon_alloc(struct console *con) } rcuwait_init(&con->rcuwait); - init_irq_work(&con->irq_work, nbcon_irq_work); + con->irq_work = IRQ_WORK_INIT_LAZY(nbcon_irq_work); atomic_long_set(&ACCESS_PRIVATE(con, nbcon_prev_seq), -1UL); nbcon_state_set(con, &state); diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 6d363e42e2a057..96ff9547e888b7 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -3732,7 +3732,7 @@ static bool legacy_kthread_create(void) lockdep_assert_console_list_lock_held(); kt = kthread_run(legacy_kthread_func, NULL, "pr/legacy"); - if (WARN_ON(IS_ERR(kt))) { + if (IS_ERR(kt)) { pr_err("failed to start legacy printing thread\n"); return false; } diff --git a/kernel/reboot.c b/kernel/reboot.c index f070c5c1103a9c..d177d89fcc33e2 100644 --- a/kernel/reboot.c +++ b/kernel/reboot.c @@ -13,7 +13,9 @@ #include #include #include +#include #include +#include #include #include #include @@ -24,8 +26,7 @@ */ static int C_A_D = 1; -struct pid *cad_pid; -EXPORT_SYMBOL(cad_pid); +struct pid __rcu *cad_pid; #if defined(CONFIG_ARM) #define DEFAULT_REBOOT_MODE = REBOOT_HARD @@ -1371,10 +1372,14 @@ static int proc_do_cad_pid(const struct ctl_table *table, int write, void *buffe { struct ctl_table tmp_table = *table; struct pid *new_pid; + struct pid *old_pid; pid_t tmp_pid; int r; - tmp_pid = pid_vnr(cad_pid); + rcu_read_lock(); + tmp_pid = pid_vnr(rcu_dereference(cad_pid)); + rcu_read_unlock(); + tmp_table.data = &tmp_pid; r = proc_dointvec(&tmp_table, write, buffer, lenp, ppos); @@ -1385,7 +1390,13 @@ static int proc_do_cad_pid(const struct ctl_table *table, int write, void *buffe if (!new_pid) return -ESRCH; - put_pid(xchg(&cad_pid, new_pid)); + old_pid = unrcu_pointer(xchg(&cad_pid, RCU_INITIALIZER(new_pid))); + /* + * Wait for cad_pid readers before put_pid(). We cannot use + * call_rcu() here because free_pid() already owns pid->rcu. + */ + synchronize_rcu(); + put_pid(old_pid); return 0; } diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 87caa1290fad69..35d647c8c36831 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -3743,11 +3743,17 @@ static inline void ttwu_do_wakeup(struct task_struct *p) void update_rq_avg_idle(struct rq *rq) { - u64 delta = rq_clock(rq) - rq->idle_stamp; - u64 max = 2*rq->max_idle_balance_cost; + u64 idle_stamp = rq->idle_stamp; + u64 delta, max; + + if (!idle_stamp) + return; + + delta = rq_clock(rq) - idle_stamp; update_avg(&rq->avg_idle, delta); + max = 2 * rq->max_idle_balance_cost; if (rq->avg_idle > max) rq->avg_idle = max; rq->idle_stamp = 0; @@ -5774,8 +5780,8 @@ void sched_tick(void) { int cpu = smp_processor_id(); struct rq *rq = cpu_rq(cpu); - /* accounting goes to the donor task */ - struct task_struct *donor; + /* scheduler accounting goes to the donor task */ + struct task_struct *curr, *donor; struct rq_flags rf; unsigned long hw_pressure; u64 resched_latency; @@ -5786,6 +5792,7 @@ void sched_tick(void) sched_clock_tick(); rq_lock(rq, &rf); + curr = rq->curr; donor = rq->donor; psi_account_irqtime(rq, donor, NULL); @@ -5811,8 +5818,8 @@ void sched_tick(void) perf_event_task_tick(); - if (donor->flags & PF_WQ_WORKER) - wq_worker_tick(donor); + if (curr->flags & PF_WQ_WORKER) + wq_worker_tick(curr); if (!scx_switched_all()) { rq->idle_balance = idle_cpu(cpu); diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 857dbe3519a868..0663c00c41c042 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -3028,8 +3028,8 @@ static struct task_struct *pick_next_pushable_dl_task(struct rq *rq) next_node = rb_first_cached(&rq->dl.pushable_dl_tasks_root); while (next_node) { i = __node_2_pdl(next_node); - /* make sure task isn't on_cpu (possible with proxy-exec) */ - if (!task_on_cpu(rq, i)) { + /* skip tasks that cannot be migrated */ + if (!task_on_cpu(rq, i) && !is_migration_disabled(i)) { p = i; break; } diff --git a/kernel/sched/ext/ext.c b/kernel/sched/ext/ext.c index 558be0cdebef8b..548f46a4278834 100644 --- a/kernel/sched/ext/ext.c +++ b/kernel/sched/ext/ext.c @@ -7435,7 +7435,7 @@ static void scx_root_enable_workfn(struct kthread_work *work) /* * Enable ops for every task. Fork is excluded by scx_fork_rwsem * preventing new tasks from being added. No need to exclude tasks - * leaving as sched_ext_free() can handle both prepped and enabled + * leaving as sched_ext_dead() can handle both prepped and enabled * tasks. Prep all tasks first and then enable them with preemption * disabled. * @@ -7524,7 +7524,7 @@ static void scx_root_enable_workfn(struct kthread_work *work) /* * We're fully committed and can't fail. The task READY -> ENABLED - * transitions here are synchronized against sched_ext_free() through + * transitions here are synchronized against sched_ext_dead() through * scx_tasks_lock. */ percpu_down_write(&scx_fork_rwsem); @@ -9019,12 +9019,6 @@ static bool scx_dsq_move(struct bpf_iter_scx_dsq_kern *kit, if (unlikely(READ_ONCE(sch->aborting))) return false; - if (unlikely(!scx_task_on_sched(sch, p))) { - scx_error(sch, "scx_bpf_dsq_move[_vtime]() on %s[%d] but the task belongs to a different scheduler", - p->comm, p->pid); - return false; - } - /* * Can be called from either ops.dispatch() holding the dispatched rq's * lock or any context where no rq lock is held. If latter, lock @p's @@ -9056,6 +9050,17 @@ static bool scx_dsq_move(struct bpf_iter_scx_dsq_kern *kit, goto out; } + /* + * @p has been on $src_dsq and can't move anymore. If @p is not on @sch, + * the caller didn't have authority over @p at the time of the call. + */ + if (unlikely(!scx_task_on_sched(sch, p))) { + scx_error(sch, "scx_bpf_dsq_move[_vtime]() on %s[%d] but the task belongs to a different scheduler", + p->comm, p->pid); + raw_spin_unlock(&src_dsq->lock); + goto out; + } + /* @p is still on $src_dsq and stable, determine the destination */ dst_dsq = find_dsq_for_dispatch(sch, locked_rq ?: this_rq(), dsq_id, task_cpu(p)); diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 4c7bb4b7018e28..bb8a5f358ee194 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -1004,6 +1004,13 @@ static inline void __max_slice_update(struct sched_entity *se, struct rb_node *n } } +static inline void min_vruntime_copy(struct sched_entity *new, struct sched_entity *old) +{ + new->min_vruntime = old->min_vruntime; + new->min_slice = old->min_slice; + new->max_slice = old->max_slice; +} + /* * se->min_vruntime = min(se->vruntime, {left,right}->min_vruntime) */ @@ -1031,8 +1038,9 @@ static inline bool min_vruntime_update(struct sched_entity *se, bool exit) se->max_slice == old_max_slice; } -RB_DECLARE_CALLBACKS(static, min_vruntime_cb, struct sched_entity, - run_node, min_vruntime, min_vruntime_update); + +RB_DECLARE_CALLBACKS_MULTI(static, min_vruntime_cb, struct sched_entity, + run_node, min_vruntime_copy, min_vruntime_update); /* * Enqueue an entity into the rb-tree: @@ -1042,6 +1050,8 @@ static void __enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se) sum_w_vruntime_add(cfs_rq, se); se->min_vruntime = se->vruntime; se->min_slice = se->slice; + se->max_slice = se->slice; + rb_add_augmented_cached(&se->run_node, &cfs_rq->tasks_timeline, __entity_less, &min_vruntime_cb); } @@ -1363,7 +1373,6 @@ static s64 update_se(struct rq *rq, struct sched_entity *se) se->exec_start = now; if (entity_is_task(se)) { - struct task_struct *donor = task_of(se); struct task_struct *running = rq->curr; /* * If se is a task, we account the time against the running @@ -1376,8 +1385,7 @@ static s64 update_se(struct rq *rq, struct sched_entity *se) account_group_exec_runtime(running, delta_exec); account_mm_sched(rq, running, delta_exec); - /* cgroup time is always accounted against the donor */ - cgroup_account_cputime(donor, delta_exec); + cgroup_account_cputime(running, delta_exec); } else { /* If not task, account the time against donor se */ se->sum_exec_runtime += delta_exec; diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index e6e5f8a2caafbd..85303add726df4 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -1872,8 +1872,8 @@ static struct task_struct *pick_next_pushable_task(struct rq *rq) return NULL; plist_for_each_entry(i, head, pushable_tasks) { - /* make sure task isn't on_cpu (possible with proxy-exec) */ - if (!task_on_cpu(rq, i)) { + /* skip tasks that cannot be migrated */ + if (!task_on_cpu(rq, i) && !is_migration_disabled(i)) { p = i; break; } diff --git a/kernel/signal.c b/kernel/signal.c index c53f202da9daaa..5f34ee7b504ef4 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1903,6 +1903,18 @@ int kill_pid(struct pid *pid, int sig, int priv) } EXPORT_SYMBOL(kill_pid); +int kill_cad_pid(int sig, int priv) +{ + int ret; + + rcu_read_lock(); + ret = kill_pid(rcu_dereference(cad_pid), sig, priv); + rcu_read_unlock(); + + return ret; +} +EXPORT_SYMBOL(kill_cad_pid); + #ifdef CONFIG_POSIX_TIMERS /* * These functions handle POSIX timer signals. POSIX timers use diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c index 0014d163f989bb..62ad7c000386ec 100644 --- a/kernel/time/clockevents.c +++ b/kernel/time/clockevents.c @@ -615,33 +615,40 @@ void clockevents_handle_noop(struct clock_event_device *dev) { } -/** - * clockevents_exchange_device - release and request clock devices - * @old: device to release (can be NULL) - * @new: device to request (can be NULL) - * - * Called from various tick functions with clockevents_lock held and - * interrupts disabled. - */ -void clockevents_exchange_device(struct clock_event_device *old, - struct clock_event_device *new) +void __clockevents_exchange_device(struct clock_event_device *old, + struct clock_event_device *new) { /* * Caller releases a clock event device. We queue it into the * released list and do a notify add later. */ if (old) { - module_put(old->owner); clockevents_switch_state(old, CLOCK_EVT_STATE_DETACHED); list_move(&old->list, &clockevents_released); } if (new) { - BUG_ON(!clockevent_state_detached(new)); + WARN_ON(!clockevent_state_detached(new)); clockevents_shutdown(new); } } +/** + * clockevents_exchange_device - release and request clock devices + * @old: device to release (can be NULL) + * @new: device to request (can be NULL) + * + * Called from various tick functions with clockevents_lock held and + * interrupts disabled. + */ +void clockevents_exchange_device(struct clock_event_device *old, + struct clock_event_device *new) +{ + __clockevents_exchange_device(old, new); + if (old) + module_put(old->owner); +} + /** * clockevents_suspend - suspend clock devices */ @@ -699,7 +706,7 @@ void tick_offline_cpu(unsigned int cpu) if (cpumask_test_cpu(cpu, dev->cpumask) && cpumask_weight(dev->cpumask) == 1 && !tick_is_broadcast_device(dev)) { - BUG_ON(!clockevent_state_detached(dev)); + WARN_ON(!clockevent_state_detached(dev)); list_del(&dev->list); } } diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index 96eef3026fbaeb..71015e59f5de63 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -1236,13 +1236,23 @@ remove_and_enqueue_same_base(struct hrtimer *timer, struct hrtimer_clock_base *b { bool was_first = false; + /* + * Updating the sort key while @timer is queued can temporarily + * make the tree inconsistent. This is safe under cpu_base->lock: + * no other queue operation can observe that state. + * hrtimer_can_update_in_place() either confirms that the new expiry + * fits between the neighbours or timerqueue_linked_del() removes the + * timer without consulting the expiry. + */ + hrtimer_set_expires_range_ns(timer, expires, delta_ns); + expires = hrtimer_get_expires(timer); + /* Remove it from the timer queue if active */ if (timer->is_queued) { was_first = !timerqueue_linked_prev(&timer->node); /* Try to update in place to avoid the de/enqueue dance */ if (hrtimer_can_update_in_place(timer, base, expires)) { - hrtimer_set_expires_range_ns(timer, expires, delta_ns); trace_hrtimer_start(timer, mode, true); if (was_first) base->expires_next = expires; @@ -1253,9 +1263,6 @@ remove_and_enqueue_same_base(struct hrtimer *timer, struct hrtimer_clock_base *b timerqueue_linked_del(&base->active, &timer->node); } - /* Set the new expiry time */ - hrtimer_set_expires_range_ns(timer, expires, delta_ns); - debug_activate(timer, mode, timer->is_queued); base->cpu_base->active_bases |= 1 << base->index; diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c index 115e0bf012764e..bda3d2391a60b6 100644 --- a/kernel/time/tick-broadcast.c +++ b/kernel/time/tick-broadcast.c @@ -165,23 +165,31 @@ static bool tick_set_oneshot_wakeup_device(struct clock_event_device *newdev, */ void tick_install_broadcast_device(struct clock_event_device *dev, int cpu) { - struct clock_event_device *cur = tick_broadcast_device.evtdev; + struct clock_event_device *cur; - if (tick_set_oneshot_wakeup_device(dev, cpu)) - return; + scoped_guard(raw_spinlock_irqsave, &tick_broadcast_lock) { - if (!tick_check_broadcast_device(cur, dev)) - return; + if (tick_set_oneshot_wakeup_device(dev, cpu)) + return; - if (!try_module_get(dev->owner)) - return; + cur = tick_broadcast_device.evtdev; + if (!tick_check_broadcast_device(cur, dev)) + return; - clockevents_exchange_device(cur, dev); + if (!try_module_get(dev->owner)) + return; + + __clockevents_exchange_device(cur, dev); + if (cur) + cur->event_handler = clockevents_handle_noop; + WRITE_ONCE(tick_broadcast_device.evtdev, dev); + if (!cpumask_empty(tick_broadcast_mask)) + tick_broadcast_start_periodic(dev); + } + + /* Module release must be outside of the lock */ if (cur) - cur->event_handler = clockevents_handle_noop; - tick_broadcast_device.evtdev = dev; - if (!cpumask_empty(tick_broadcast_mask)) - tick_broadcast_start_periodic(dev); + module_put(cur->owner); if (!(dev->features & CLOCK_EVT_FEAT_ONESHOT)) return; @@ -1218,7 +1226,7 @@ int tick_broadcast_oneshot_active(void) */ bool tick_broadcast_oneshot_available(void) { - struct clock_event_device *bc = tick_broadcast_device.evtdev; + struct clock_event_device *bc = READ_ONCE(tick_broadcast_device.evtdev); return bc ? bc->features & CLOCK_EVT_FEAT_ONESHOT : false; } @@ -1226,7 +1234,7 @@ bool tick_broadcast_oneshot_available(void) #else int __tick_broadcast_oneshot_control(enum tick_broadcast_state state) { - struct clock_event_device *bc = tick_broadcast_device.evtdev; + struct clock_event_device *bc = READ_ONCE(tick_broadcast_device.evtdev); if (!bc || (bc->features & CLOCK_EVT_FEAT_HRTIMER)) return -EBUSY; diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h index 597d816d22e883..ce1c9d1f6b96f6 100644 --- a/kernel/time/tick-internal.h +++ b/kernel/time/tick-internal.h @@ -54,6 +54,8 @@ static inline void clockevent_set_state(struct clock_event_device *dev, } extern void clockevents_shutdown(struct clock_event_device *dev); +extern void __clockevents_exchange_device(struct clock_event_device *old, + struct clock_event_device *new); extern void clockevents_exchange_device(struct clock_event_device *old, struct clock_event_device *new); extern void clockevents_switch_state(struct clock_event_device *dev, diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index a4ecba1518ded3..db8eeaefeb00b9 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -6675,7 +6675,7 @@ int update_ftrace_direct_mod(struct ftrace_ops *ops, struct ftrace_hash *hash, b /* Enable the tmp_ops to have the same functions as the hash object. */ ftrace_ops_init(&tmp_ops); - tmp_ops.func_hash->filter_hash = hash; + rcu_assign_pointer(tmp_ops.func_hash->filter_hash, hash); err = register_ftrace_function_nolock(&tmp_ops); if (err) diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 1925ee9cc36da5..7c59e8e5861963 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -330,6 +330,11 @@ struct buffer_data_read_page { struct buffer_data_page *data; /* actual data, stored in this page */ }; +static __always_inline unsigned int rb_read_page_capacity(struct buffer_data_read_page *rpage) +{ + return (PAGE_SIZE << rpage->order) - BUF_PAGE_HDR_SIZE; +} + /* * Note, the buffer_page list must be first. The buffer pages * are allocated in cache lines, which means that each buffer @@ -514,7 +519,7 @@ struct ring_buffer_per_cpu { int cpu; atomic_t record_disabled; atomic_t resize_disabled; - struct trace_buffer *buffer; + struct trace_buffer *buffer; raw_spinlock_t reader_lock; /* serialize readers */ arch_spinlock_t lock; struct lock_class_key lock_key; @@ -552,7 +557,6 @@ struct ring_buffer_per_cpu { /* pages removed since last reset */ unsigned long pages_removed; - unsigned int mapped; unsigned int user_mapped; /* user space mapping */ struct mutex mapping_lock; struct buffer_page **subbuf_ids; /* ID to subbuf VA */ @@ -632,6 +636,20 @@ unsigned long rb_subbuf_start(struct trace_buffer *buffer, unsigned long addr) return addr & ~((unsigned long)(rb_subbuf_size(buffer) - 1)); } +static bool rb_is_static(struct ring_buffer_per_cpu *cpu_buffer) +{ + return cpu_buffer->user_mapped || cpu_buffer->remote || cpu_buffer->ring_meta; +} + +static unsigned long rb_static_max_pages(void) +{ + /* + * Static ring buffers are using bpage::id and must account for the + * reader page. + */ + return (1UL << 30) - 1; +} + struct ring_buffer_iter { struct ring_buffer_per_cpu *cpu_buffer; unsigned long head; @@ -867,14 +885,13 @@ static void rb_wake_up_waiters(struct irq_work *work) struct ring_buffer_per_cpu *cpu_buffer = container_of(rbwork, struct ring_buffer_per_cpu, irq_work); - /* Called from interrupt context */ - raw_spin_lock(&cpu_buffer->reader_lock); - rbwork->wakeup_full = false; - rbwork->full_waiters_pending = false; + scoped_guard(raw_spinlock_irqsave, &cpu_buffer->reader_lock) { + rbwork->wakeup_full = false; + rbwork->full_waiters_pending = false; - /* Waking up all waiters, they will reset the shortest full */ - cpu_buffer->shortest_full = 0; - raw_spin_unlock(&cpu_buffer->reader_lock); + /* Waking up all waiters, they will reset the shortest full */ + cpu_buffer->shortest_full = 0; + } wake_up_all(&rbwork->full_waiters); } @@ -1836,6 +1853,11 @@ static bool rb_cpu_meta_valid(struct ring_buffer_cpu_meta *meta, int cpu, return false; } + if (meta->nr_subbufs != nr_pages + 1) { + pr_info("Ring buffer boot meta [%d] invalid nr_subbufs\n", cpu); + return false; + } + buffers_start = meta->first_buffer; buffers_end = meta->first_buffer + (subbuf_size * meta->nr_subbufs); @@ -2562,7 +2584,6 @@ rb_allocate_cpu_buffer(struct trace_buffer *buffer, long nr_pages, int cpu) * Range mapped buffers have the same restrictions as memory * mapped ones do. */ - cpu_buffer->mapped = 1; cpu_buffer->ring_meta = rb_range_meta(buffer, nr_pages, cpu); bpage->page = rb_range_buffer(cpu_buffer, 0); if (!bpage->page) @@ -2812,6 +2833,8 @@ static struct trace_buffer *alloc_buffer(unsigned long size, unsigned flags, size = end - buffers_start; size = size / nr_cpu_ids; + if (size < sizeof(struct ring_buffer_cpu_meta)) + goto fail_free_buffers; /* * The number of sub-buffers (nr_pages) is determined by the * total size allocated minus the meta data size. @@ -2821,6 +2844,10 @@ static struct trace_buffer *alloc_buffer(unsigned long size, unsigned flags, */ nr_pages = (size - sizeof(struct ring_buffer_cpu_meta)) / (subbuf_size + sizeof(int)); + + if (nr_pages > rb_static_max_pages()) + goto fail_free_buffers; + /* Need at least two pages plus the reader page */ if (nr_pages < 3) goto fail_free_buffers; @@ -2853,6 +2880,10 @@ static struct trace_buffer *alloc_buffer(unsigned long size, unsigned flags, /* The writer is remote. This ring-buffer is read-only */ atomic_inc(&buffer->record_disabled); nr_pages = desc->nr_page_va - 1; + + if (nr_pages > rb_static_max_pages()) + goto fail_free_buffers; + if (nr_pages < 2) goto fail_free_buffers; } else { @@ -6656,12 +6687,11 @@ rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer) rb_head_page_activate(cpu_buffer); cpu_buffer->pages_removed = 0; - if (cpu_buffer->mapped) { - rb_update_meta_page(cpu_buffer); - if (cpu_buffer->ring_meta) { - struct ring_buffer_cpu_meta *meta = cpu_buffer->ring_meta; - meta->commit_buffer = meta->head_buffer; - } + rb_update_meta_page(cpu_buffer); + if (cpu_buffer->ring_meta) { + struct ring_buffer_cpu_meta *meta = cpu_buffer->ring_meta; + + meta->commit_buffer = meta->head_buffer; } } @@ -6910,8 +6940,8 @@ int ring_buffer_swap_cpu(struct trace_buffer *buffer_a, cpu_buffer_a = buffer_a->buffers[cpu]; cpu_buffer_b = buffer_b->buffers[cpu]; - /* It's up to the callers to not try to swap mapped buffers */ - if (WARN_ON_ONCE(cpu_buffer_a->mapped || cpu_buffer_b->mapped)) + /* It's up to the callers to not try to swap static buffers */ + if (WARN_ON_ONCE(rb_is_static(cpu_buffer_a) || rb_is_static(cpu_buffer_b))) return -EBUSY; /* At least make sure the two buffers are somewhat the same */ @@ -6977,56 +7007,78 @@ EXPORT_SYMBOL_GPL(ring_buffer_swap_cpu); * ring_buffer_alloc_read_page - allocate a page to read from buffer * @buffer: the buffer to allocate for. * @cpu: the cpu buffer to allocate. + * @rpage: pointer to pass in an already allocated page (can be NULL) + * and returns the allocated page. * - * This function is used in conjunction with ring_buffer_read_page. + * This function is used in conjunction with ring_buffer_read_page(). * When reading a full page from the ring buffer, these functions * can be used to speed up the process. The calling function should * allocate a few pages first with this function. Then when it * needs to get pages from the ring buffer, it passes the result - * of this function into ring_buffer_read_page, which will swap + * of this function into ring_buffer_read_page(), which will swap * the page that was allocated, with the read page of the buffer. * + * If @rpage is provided, and it has a different order than the current + * subbuffer order, its payload will be freed and re-allocated. If it + * already matches the order, it is simply returned. + * * Returns: - * The page allocated, or ERR_PTR + * 0 on success, < 0 on error */ -struct buffer_data_read_page * -ring_buffer_alloc_read_page(struct trace_buffer *buffer, int cpu) +int ring_buffer_alloc_read_page(struct trace_buffer *buffer, int cpu, + struct buffer_data_read_page **rpage) { struct ring_buffer_per_cpu *cpu_buffer; - struct buffer_data_read_page *bpage = NULL; unsigned long flags; + unsigned int order; if (!cpumask_test_cpu(cpu, buffer->cpumask)) - return ERR_PTR(-ENODEV); + return -ENODEV; - bpage = kzalloc_obj(*bpage); - if (!bpage) - return ERR_PTR(-ENOMEM); + if (!rpage) + return -EINVAL; + + order = READ_ONCE(buffer->subbuf_order); - bpage->order = buffer->subbuf_order; + if (*rpage) { + if ((*rpage)->order == order) + return 0; + + /* We can reuse rpage, but we discard the payload */ + free_pages((unsigned long)(*rpage)->data, (*rpage)->order); + (*rpage)->data = NULL; + } else { + *rpage = kzalloc_obj(**rpage); + if (!*rpage) + return -ENOMEM; + } + + (*rpage)->order = order; cpu_buffer = buffer->buffers[cpu]; + local_irq_save(flags); arch_spin_lock(&cpu_buffer->lock); if (cpu_buffer->free_page.data) { - *bpage = cpu_buffer->free_page; + **rpage = cpu_buffer->free_page; cpu_buffer->free_page.data = NULL; } arch_spin_unlock(&cpu_buffer->lock); local_irq_restore(flags); - if (bpage->data) { - rb_init_data_page(bpage->data); + if ((*rpage)->data) { + rb_init_data_page((*rpage)->data); } else { - bpage->data = alloc_cpu_data(cpu, bpage->order); - if (!bpage->data) { - kfree(bpage); - return ERR_PTR(-ENOMEM); + (*rpage)->data = alloc_cpu_data(cpu, (*rpage)->order); + if (!(*rpage)->data) { + kfree(*rpage); + *rpage = NULL; + return -ENOMEM; } } - return bpage; + return 0; } EXPORT_SYMBOL_GPL(ring_buffer_alloc_read_page); @@ -7034,21 +7086,30 @@ EXPORT_SYMBOL_GPL(ring_buffer_alloc_read_page); * ring_buffer_free_read_page - free an allocated read page * @buffer: the buffer the page was allocate for * @cpu: the cpu buffer the page came from - * @data_page: the page to free + * @rpage: the buffer_data_read_page to free * * Free a page allocated from ring_buffer_alloc_read_page. */ void ring_buffer_free_read_page(struct trace_buffer *buffer, int cpu, - struct buffer_data_read_page *data_page) + struct buffer_data_read_page *rpage) { struct ring_buffer_per_cpu *cpu_buffer; - struct buffer_data_page *dpage = data_page->data; - struct page *page = virt_to_page(dpage); + struct buffer_data_page *dpage; unsigned long flags; + struct page *page; if (!buffer || !buffer->buffers || !buffer->buffers[cpu]) return; + if (!rpage) + return; + + dpage = rpage->data; + if (!dpage) + goto out; + + page = virt_to_page(dpage); + cpu_buffer = buffer->buffers[cpu]; /* @@ -7056,14 +7117,14 @@ void ring_buffer_free_read_page(struct trace_buffer *buffer, int cpu, * is different from the subbuffer order of the buffer - * we can't reuse it */ - if (page_ref_count(page) > 1 || data_page->order != buffer->subbuf_order) + if (page_ref_count(page) > 1 || rpage->order != READ_ONCE(buffer->subbuf_order)) goto out; local_irq_save(flags); arch_spin_lock(&cpu_buffer->lock); if (!cpu_buffer->free_page.data) { - cpu_buffer->free_page = *data_page; + cpu_buffer->free_page = *rpage; dpage = NULL; } @@ -7071,8 +7132,8 @@ void ring_buffer_free_read_page(struct trace_buffer *buffer, int cpu, local_irq_restore(flags); out: - free_pages((unsigned long)dpage, data_page->order); - kfree(data_page); + free_pages((unsigned long)dpage, rpage->order); + kfree(rpage); } EXPORT_SYMBOL_GPL(ring_buffer_free_read_page); @@ -7123,7 +7184,6 @@ int ring_buffer_read_page(struct trace_buffer *buffer, unsigned int size; unsigned int read; u64 save_timestamp; - bool force_memcpy; if (!cpumask_test_cpu(cpu, buffer->cpumask)) return -1; @@ -7144,10 +7204,9 @@ int ring_buffer_read_page(struct trace_buffer *buffer, if (!dpage) return -1; - guard(raw_spinlock_irqsave)(&cpu_buffer->reader_lock); + len = min_t(size_t, len, rb_read_page_capacity(data_page)); - if (data_page->order != cpu_buffer->reader_page->order) - return -1; + guard(raw_spinlock_irqsave)(&cpu_buffer->reader_lock); reader = rb_get_reader_page(cpu_buffer); if (!reader) @@ -7162,18 +7221,18 @@ int ring_buffer_read_page(struct trace_buffer *buffer, /* Check if any events were dropped */ missed_events = cpu_buffer->lost_events; - force_memcpy = cpu_buffer->mapped || cpu_buffer->remote; - - /* - * If this page has been partially read or - * if len is not big enough to read the rest of the page or - * a writer is still on the page, then - * we must copy the data from the page to the buffer. - * Otherwise, we can simply swap the page with the one passed in. - */ + /* + * It is not possible to swap the reader page if: + * - It has been partially read + * - len is not big enough to read it entirely + * - A writer is still on it + * - The ring buffer is static + * - The order doesn't match + */ if (read || (len < (size - read)) || cpu_buffer->reader_page == cpu_buffer->commit_page || - force_memcpy) { + rb_is_static(cpu_buffer) || + data_page->order != reader->order) { struct buffer_data_page *rpage = cpu_buffer->reader_page->page; unsigned int rpos = read; unsigned int pos = 0; @@ -7267,7 +7326,7 @@ int ring_buffer_read_page(struct trace_buffer *buffer, * missed events, then record it there. */ if (missed_events > 0 && - rb_page_capacity(reader) - size >= sizeof(missed_events)) { + rb_read_page_capacity(data_page) - size >= sizeof(missed_events)) { memcpy(&dpage->data[size], &missed_events, sizeof(missed_events)); local_add(RB_MISSED_STORED, &dpage->commit); @@ -7287,8 +7346,8 @@ int ring_buffer_read_page(struct trace_buffer *buffer, /* * This page may be off to user land. Zero it out here. */ - if (size < rb_page_capacity(reader)) - memset(&dpage->data[size], 0, rb_page_capacity(reader) - size); + if (size < rb_read_page_capacity(data_page)) + memset(&dpage->data[size], 0, rb_read_page_capacity(data_page) - size); return read; } @@ -7306,6 +7365,18 @@ void *ring_buffer_read_page_data(struct buffer_data_read_page *page) } EXPORT_SYMBOL_GPL(ring_buffer_read_page_data); +/** + * ring_buffer_read_page_size - get size of the read page. + * @rpage: the page to get the size from + * + * Returns size of the page in bytes. + */ +unsigned int ring_buffer_read_page_size(struct buffer_data_read_page *rpage) +{ + return rpage ? PAGE_SIZE << rpage->order : 0; +} +EXPORT_SYMBOL_GPL(ring_buffer_read_page_size); + /** * ring_buffer_subbuf_size_get - get size of the sub buffer. * @buffer: the buffer to get the sub buffer size from @@ -7386,12 +7457,20 @@ int ring_buffer_subbuf_order_set(struct trace_buffer *buffer, int order) old_capacity = rb_subbuf_capacity(buffer); + /* The mmap fast path reads subbuf_order without buffer->mutex. */ + for_each_buffer_cpu(buffer, cpu) { + if (!cpumask_test_cpu(cpu, buffer->cpumask)) + continue; + if (atomic_read(&buffer->buffers[cpu]->resize_disabled)) + return -EBUSY; + } + atomic_inc(&buffer->record_disabled); /* Make sure all commits have finished */ synchronize_rcu(); - buffer->subbuf_order = order; + WRITE_ONCE(buffer->subbuf_order, order); /* Make sure all new buffers are allocated, before deleting the old ones */ for_each_buffer_cpu(buffer, cpu) { @@ -7495,7 +7574,7 @@ int ring_buffer_subbuf_order_set(struct trace_buffer *buffer, int order) return 0; error: - buffer->subbuf_order = old_order; + WRITE_ONCE(buffer->subbuf_order, old_order); atomic_dec(&buffer->record_disabled); @@ -7615,11 +7694,7 @@ static int __rb_inc_dec_mapped(struct ring_buffer_per_cpu *cpu_buffer, lockdep_assert_held(&cpu_buffer->mapping_lock); - /* mapped is always greater or equal to user_mapped */ - if (WARN_ON(cpu_buffer->mapped < cpu_buffer->user_mapped)) - return -EINVAL; - - if (inc && cpu_buffer->mapped == UINT_MAX) + if (inc && cpu_buffer->user_mapped == UINT_MAX) return -EBUSY; if (WARN_ON(!inc && cpu_buffer->user_mapped == 0)) @@ -7628,13 +7703,10 @@ static int __rb_inc_dec_mapped(struct ring_buffer_per_cpu *cpu_buffer, mutex_lock(&cpu_buffer->buffer->mutex); raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); - if (inc) { + if (inc) cpu_buffer->user_mapped++; - cpu_buffer->mapped++; - } else { + else cpu_buffer->user_mapped--; - cpu_buffer->mapped--; - } raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); mutex_unlock(&cpu_buffer->buffer->mutex); @@ -7780,6 +7852,9 @@ int ring_buffer_map(struct trace_buffer *buffer, int cpu, /* prevent another thread from changing buffer/sub-buffer sizes */ guard(mutex)(&buffer->mutex); + if (cpu_buffer->nr_pages > rb_static_max_pages()) + return -E2BIG; + err = rb_alloc_meta_page(cpu_buffer); if (err) return err; @@ -7806,7 +7881,6 @@ int ring_buffer_map(struct trace_buffer *buffer, int cpu, if (!err) { raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); /* This is the first time it is mapped by user */ - cpu_buffer->mapped++; cpu_buffer->user_mapped = 1; raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); } else { @@ -7863,8 +7937,6 @@ int ring_buffer_unmap(struct trace_buffer *buffer, int cpu) raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); /* This is the last user space mapping */ - if (!WARN_ON_ONCE(cpu_buffer->mapped < cpu_buffer->user_mapped)) - cpu_buffer->mapped--; cpu_buffer->user_mapped = 0; raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); diff --git a/kernel/trace/ring_buffer_benchmark.c b/kernel/trace/ring_buffer_benchmark.c index 593e3b59e42e94..c3d34c0e64e289 100644 --- a/kernel/trace/ring_buffer_benchmark.c +++ b/kernel/trace/ring_buffer_benchmark.c @@ -104,7 +104,7 @@ static enum event_status read_event(int cpu) static enum event_status read_page(int cpu) { - struct buffer_data_read_page *bpage; + struct buffer_data_read_page *bpage = NULL; struct ring_buffer_event *event; struct rb_page *rpage; unsigned long commit; @@ -114,8 +114,8 @@ static enum event_status read_page(int cpu) int inc; int i; - bpage = ring_buffer_alloc_read_page(buffer, cpu); - if (IS_ERR(bpage)) + ret = ring_buffer_alloc_read_page(buffer, cpu, &bpage); + if (ret < 0) return EVENT_DROPPED; page_size = ring_buffer_subbuf_size_get(buffer); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index fc964001783f3c..c4fa38a1f167cd 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -7080,8 +7080,8 @@ ssize_t tracing_buffers_read(struct file *filp, char __user *ubuf, { struct ftrace_buffer_info *info = filp->private_data; struct trace_iterator *iter = &info->iter; + unsigned int spare_size; void *trace_data; - int page_size; ssize_t ret = 0; ssize_t size; @@ -7091,36 +7091,22 @@ ssize_t tracing_buffers_read(struct file *filp, char __user *ubuf, if (iter->snapshot && tracer_uses_snapshot(iter->tr->current_trace)) return -EBUSY; - page_size = ring_buffer_subbuf_size_get(iter->array_buffer->buffer); + spare_size = ring_buffer_read_page_size(info->spare); - /* Make sure the spare matches the current sub buffer size */ - if (info->spare) { - if (page_size != info->spare_size) { - ring_buffer_free_read_page(iter->array_buffer->buffer, - info->spare_cpu, info->spare); - info->spare = NULL; - } - } +again: + /* Do we have previous read data to read? */ + if (info->read < spare_size) + goto read; - if (!info->spare) { - info->spare = ring_buffer_alloc_read_page(iter->array_buffer->buffer, - iter->cpu_file); - if (IS_ERR(info->spare)) { - ret = PTR_ERR(info->spare); - info->spare = NULL; - } else { - info->spare_cpu = iter->cpu_file; - info->spare_size = page_size; - } - } - if (!info->spare) + ret = ring_buffer_alloc_read_page(iter->array_buffer->buffer, iter->cpu_file, + &info->spare); + if (ret) return ret; - /* Do we have previous read data to read? */ - if (info->read < page_size) - goto read; + spare_size = ring_buffer_read_page_size(info->spare); + info->read = spare_size; + info->spare_cpu = iter->cpu_file; - again: trace_access_lock(iter->cpu_file); ret = ring_buffer_read_page(iter->array_buffer->buffer, info->spare, @@ -7146,8 +7132,9 @@ ssize_t tracing_buffers_read(struct file *filp, char __user *ubuf, } info->read = 0; + read: - size = page_size - info->read; + size = spare_size - info->read; if (size > count) size = count; trace_data = ring_buffer_read_page_data(info->spare); @@ -7188,26 +7175,24 @@ int tracing_buffers_release(struct inode *inode, struct file *file) __trace_array_put(iter->tr); - if (info->spare) - ring_buffer_free_read_page(iter->array_buffer->buffer, - info->spare_cpu, info->spare); + ring_buffer_free_read_page(iter->array_buffer->buffer, info->spare_cpu, info->spare); kvfree(info); return 0; } struct buffer_ref { - struct trace_buffer *buffer; - void *page; - int cpu; - refcount_t refcount; + struct trace_buffer *buffer; + struct buffer_data_read_page *rpage; + int cpu; + refcount_t refcount; }; static void buffer_ref_release(struct buffer_ref *ref) { if (!refcount_dec_and_test(&ref->refcount)) return; - ring_buffer_free_read_page(ref->buffer, ref->cpu, ref->page); + ring_buffer_free_read_page(ref->buffer, ref->cpu, ref->rpage); kfree(ref); } @@ -7266,25 +7251,15 @@ ssize_t tracing_buffers_splice_read(struct file *file, loff_t *ppos, .ops = &buffer_pipe_buf_ops, .spd_release = buffer_spd_release, }; + unsigned int page_size = 0; struct buffer_ref *ref; bool woken = false; - int page_size; int entries, i; ssize_t ret = 0; if (iter->snapshot && tracer_uses_snapshot(iter->tr->current_trace)) return -EBUSY; - page_size = ring_buffer_subbuf_size_get(iter->array_buffer->buffer); - if (*ppos & (page_size - 1)) - return -EINVAL; - - if (len & (page_size - 1)) { - if (len < page_size) - return -EINVAL; - len &= (~(page_size - 1)); - } - if (splice_grow_spd(pipe, &spd)) return -ENOMEM; @@ -7304,25 +7279,39 @@ ssize_t tracing_buffers_splice_read(struct file *file, loff_t *ppos, refcount_set(&ref->refcount, 1); ref->buffer = iter->array_buffer->buffer; - ref->page = ring_buffer_alloc_read_page(ref->buffer, iter->cpu_file); - if (IS_ERR(ref->page)) { - ret = PTR_ERR(ref->page); - ref->page = NULL; + + ret = ring_buffer_alloc_read_page(ref->buffer, iter->cpu_file, &ref->rpage); + if (ret) { kfree(ref); break; } ref->cpu = iter->cpu_file; - r = ring_buffer_read_page(ref->buffer, ref->page, - len, iter->cpu_file, 1); + page_size = ring_buffer_read_page_size(ref->rpage); + + r = -EINVAL; + if (IS_ALIGNED(*ppos, page_size) && len >= page_size) { + r = ring_buffer_read_page(ref->buffer, ref->rpage, len, iter->cpu_file, 1); + } else if (!i) { + /* + * If this fails to read on the first iteration, it + * means the length was too small and an error should + * be returned to user space. Otherwise, at least + * one sub-buffer was successfully read but this failed + * due to either the length was unaligned or the + * subbuf order changed. Either case, do not report + * an error. + */ + ret = -EINVAL; + } + if (r < 0) { - ring_buffer_free_read_page(ref->buffer, ref->cpu, - ref->page); + ring_buffer_free_read_page(ref->buffer, ref->cpu, ref->rpage); kfree(ref); break; } - page = virt_to_page(ring_buffer_read_page_data(ref->page)); + page = virt_to_page(ring_buffer_read_page_data(ref->rpage)); spd.pages[i] = page; spd.partial[i].len = page_size; @@ -7726,12 +7715,55 @@ trace_options_write(struct file *filp, const char __user *ubuf, size_t cnt, return cnt; } +static bool tr_option_match(struct trace_array *tr, void *topt) +{ + for (int i = 0; i < tr->nr_topts; i++) { + struct trace_options *tr_topts = &tr->topts[i]; + + if (topt >= (void *)&tr_topts->topts[0] && + topt < (void *)&tr_topts->topts[tr_topts->nr_topts]) + return true; + } + return false; +} + +/* + * The topt is the address of a trace_array->topts[] element that holds the + * the tracer options descriptor. But since the trace_array reference has not + * been taken yet, it cannot be dereferenced as it could have been freed by + * a rmdir of the instance the trace_array represents. + * + * Search the list of trace_arrays and compare the topt to the address of + * the entire trace_array topts array for each trace_array in the list. + * If one is matched, then take the reference and return it. If not, the + * trace_array no longer exits. + */ +static int trace_array_tracer_options_get(void *topt) +{ + struct trace_array *tr; + int ret; + + ret = security_locked_down(LOCKDOWN_TRACEFS); + if (ret) + return ret; + + if (tracing_disabled) + return -ENODEV; + + guard(mutex)(&trace_types_lock); + list_for_each_entry(tr, &ftrace_trace_arrays, list) { + if (tr_option_match(tr, topt)) + return __trace_array_get(tr); + } + return -ENODEV; +} + static int tracing_open_options(struct inode *inode, struct file *filp) { struct trace_option_dentry *topt = inode->i_private; int ret; - ret = tracing_check_open_get_tr(topt->tr); + ret = trace_array_tracer_options_get(topt); if (ret) return ret; @@ -7993,6 +8025,7 @@ create_trace_option_files(struct trace_array *tr, struct tracer *tracer, tr->topts = tr_topts; tr->topts[tr->nr_topts].tracer = tracer; tr->topts[tr->nr_topts].topts = topts; + tr->topts[tr->nr_topts].nr_topts = cnt; tr->nr_topts++; for (cnt = 0; opts[cnt].name; cnt++) { @@ -9708,6 +9741,11 @@ __init static void enable_instances(void) if (flag_delim) *flag_delim++ = '\0'; + if (trace_array_find(name)) { + pr_warn("Tracing: Instance %s already exists\n", name); + continue; + } + if (backup) { if (backup_instance_area(backup, &addr, &size) < 0) continue; diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 3c111ca88e32dd..3749485a7d85fd 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -227,6 +227,7 @@ struct array_buffer { struct trace_options { struct tracer *tracer; struct trace_option_dentry *topts; + int nr_topts; }; struct trace_pid_list *trace_pid_list_alloc(void); @@ -745,11 +746,10 @@ static inline int tracing_get_cpu(struct inode *inode) void tracing_reset_cpu(struct array_buffer *buf, int cpu); struct ftrace_buffer_info { - struct trace_iterator iter; - void *spare; - unsigned int spare_cpu; - unsigned int spare_size; - unsigned int read; + struct trace_iterator iter; + struct buffer_data_read_page *spare; + unsigned int spare_cpu; + unsigned int read; }; /** @@ -1953,6 +1953,7 @@ struct event_trigger_data { struct enable_trigger_data { struct trace_event_file *file; + struct trace_event_call *call; bool enable; bool hist; }; diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index e03471109e4874..9c62202b0c97bc 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -1462,6 +1462,8 @@ int ftrace_set_clr_event(struct trace_array *tr, char *buf, int set) /* Put back the colon to allow this to be called again */ if (buf) *(buf - 1) = ':'; + if (mod) + *(mod - 5) = ':'; return ret; } diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 6bf00710fd100b..539b5f583af92d 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -170,7 +170,6 @@ struct hist_field { struct hist_field *operands[HIST_FIELD_OPERANDS_MAX]; struct hist_trigger_data *hist_data; enum hist_field_fn fn_num; - unsigned int ref; unsigned int size; unsigned int offset; unsigned int is_signed; @@ -1906,16 +1905,8 @@ out: return field_op; } -static void get_hist_field(struct hist_field *hist_field) -{ - hist_field->ref++; -} - static void __destroy_hist_field(struct hist_field *hist_field) { - if (--hist_field->ref > 1) - return; - kfree(hist_field->var.name); kfree(hist_field->name); @@ -1962,8 +1953,6 @@ static struct hist_field *create_hist_field(struct hist_trigger_data *hist_data, if (!hist_field) return NULL; - hist_field->ref = 1; - hist_field->hist_data = hist_data; if (flags & HIST_FIELD_FL_EXPR || flags & HIST_FIELD_FL_ALIAS) @@ -2218,10 +2207,8 @@ static struct hist_field *create_var_ref(struct hist_trigger_data *hist_data, for (i = 0; i < hist_data->n_var_refs; i++) { ref_field = hist_data->var_refs[i]; if (ref_field->var.idx == var_field->var.idx && - ref_field->var.hist_data == var_field->hist_data) { - get_hist_field(ref_field); + ref_field->var.hist_data == var_field->hist_data) return ref_field; - } } /* Sanity check to avoid out-of-bound write on 'hist_data->var_refs' */ if (hist_data->n_var_refs >= TRACING_MAP_VARS_MAX) @@ -2229,7 +2216,7 @@ static struct hist_field *create_var_ref(struct hist_trigger_data *hist_data, ref_field = create_hist_field(var_field->hist_data, NULL, flags, NULL); if (ref_field) { if (init_var_ref(ref_field, var_field, system, event_name)) { - destroy_hist_field(ref_field, 0); + __destroy_hist_field(ref_field); return NULL; } @@ -2325,6 +2312,7 @@ parse_field(struct hist_trigger_data *hist_data, struct trace_event_file *file, struct ftrace_event_field *field = NULL; char *field_name, *modifier, *str; struct trace_array *tr = file->tr; + bool stack_modifier = false; modifier = str = kstrdup(field_str, GFP_KERNEL); if (!modifier) @@ -2347,9 +2335,10 @@ parse_field(struct hist_trigger_data *hist_data, struct trace_event_file *file, *flags |= HIST_FIELD_FL_EXECNAME; else if (strcmp(modifier, "syscall") == 0) *flags |= HIST_FIELD_FL_SYSCALL; - else if (strcmp(modifier, "stacktrace") == 0) + else if (strcmp(modifier, "stacktrace") == 0) { *flags |= HIST_FIELD_FL_STACKTRACE; - else if (strcmp(modifier, "log2") == 0) + stack_modifier = true; + } else if (strcmp(modifier, "log2") == 0) *flags |= HIST_FIELD_FL_LOG2; else if (strcmp(modifier, "usecs") == 0) *flags |= HIST_FIELD_FL_TIMESTAMP_USECS; @@ -2410,6 +2399,7 @@ parse_field(struct hist_trigger_data *hist_data, struct trace_event_file *file, *flags |= HIST_FIELD_FL_CPU; } else if (field && field->filter_type == FILTER_STACKTRACE) { *flags |= HIST_FIELD_FL_STACKTRACE; + field = NULL; } else if (field && field->filter_type == FILTER_COMM) { *flags |= HIST_FIELD_FL_COMM | HIST_FIELD_FL_STRING; } else { @@ -2420,6 +2410,12 @@ parse_field(struct hist_trigger_data *hist_data, struct trace_event_file *file, } } } + + if (stack_modifier && + (!field || field->filter_type != FILTER_STACKTRACE)) { + hist_err(tr, HIST_ERR_BAD_FIELD_MODIFIER, errpos(field_str)); + field = ERR_PTR(-EINVAL); + } out: kfree(str); @@ -3256,7 +3252,6 @@ static struct hist_field *create_var(struct hist_trigger_data *hist_data, goto out; } - var->ref = 1; var->flags = HIST_FIELD_FL_VAR; var->var.idx = idx; var->var.hist_data = var->hist_data = hist_data; @@ -4293,8 +4288,7 @@ static int __create_val_field(struct hist_trigger_data *hist_data, goto err; } else { /* Value */ - if (hist_field->flags & (HIST_FIELD_FL_GRAPH | HIST_FIELD_FL_PERCENT | - HIST_FIELD_FL_BUCKET | HIST_FIELD_FL_LOG2 | + if (hist_field->flags & (HIST_FIELD_FL_BUCKET | HIST_FIELD_FL_LOG2 | HIST_FIELD_FL_SYM | HIST_FIELD_FL_SYM_OFFSET | HIST_FIELD_FL_SYSCALL | HIST_FIELD_FL_STACKTRACE)) goto err; @@ -4311,6 +4305,7 @@ static int __create_val_field(struct hist_trigger_data *hist_data, return ret; err: hist_err(file->tr, HIST_ERR_BAD_FIELD_MODIFIER, errpos(field_str)); + destroy_hist_field(hist_field, 0); return -EINVAL; } @@ -5670,7 +5665,7 @@ static int print_entries(struct seq_file *m, { struct tracing_map_sort_entry **sort_entries = NULL; struct tracing_map *map = hist_data->map; - int i, j, n_entries; + int i, j, n_entries, ret; struct hist_val_stat *stats = NULL; u64 val; @@ -5680,6 +5675,8 @@ static int print_entries(struct seq_file *m, if (n_entries < 0) return n_entries; + ret = n_entries; + /* Calculate the max and the total for each field if needed. */ for (j = 0; j < hist_data->n_vals; j++) { if (!(hist_data->fields[j]->flags & @@ -5688,7 +5685,7 @@ static int print_entries(struct seq_file *m, if (!stats) { stats = kzalloc_objs(*stats, hist_data->n_vals); if (!stats) { - n_entries = -ENOMEM; + ret = -ENOMEM; goto out; } } @@ -5709,7 +5706,7 @@ static int print_entries(struct seq_file *m, out: tracing_map_destroy_sort_entries(sort_entries, n_entries); - return n_entries; + return ret; } static void hist_trigger_show(struct seq_file *m, @@ -6363,17 +6360,18 @@ static int event_hist_trigger_named_init(struct event_trigger_data *data) { int ret; - data->ref++; - - save_named_trigger(data->named_data->name, data); - ret = event_hist_trigger_init(data->named_data); if (ret < 0) { kfree(data->cmd_ops); data->cmd_ops = &trigger_hist_cmd; + return ret; } - return ret; + data->ref++; + + save_named_trigger(data->named_data->name, data); + + return 0; } static void event_hist_trigger_named_free(struct event_trigger_data *data) @@ -6623,12 +6621,6 @@ static int hist_register_trigger(char *glob, data->cmd_ops = cmd_ops; } - if (data->cmd_ops->init) { - ret = data->cmd_ops->init(data); - if (ret < 0) - goto out; - } - if (hist_data->enable_timestamps) { char *clock = hist_data->attrs->clock; @@ -6641,6 +6633,15 @@ static int hist_register_trigger(char *glob, tracing_set_filter_buffering(file->tr, true); } + if (data->cmd_ops->init) { + ret = data->cmd_ops->init(data); + if (ret < 0) { + if (hist_data->enable_timestamps) + tracing_set_filter_buffering(file->tr, false); + goto out; + } + } + if (named_data) { remove_hist_vars(hist_data); destroy_hist_data(hist_data); @@ -6658,11 +6659,12 @@ static int hist_trigger_enable(struct event_trigger_data *data, update_cond_flag(file); - if (trace_event_trigger_enable_disable(file, 1) < 0) { - list_del_rcu(&data->list); - update_cond_flag(file); + /* + * On failure the caller undoes the registration, and + * hist_unregister_trigger() can only find the trigger here. + */ + if (trace_event_trigger_enable_disable(file, 1) < 0) ret--; - } return ret; } @@ -6740,13 +6742,13 @@ static void hist_unregister_trigger(char *glob, } } - if (test && test->cmd_ops->free) - test->cmd_ops->free(test); - if (hist_data->enable_timestamps) { if (!hist_data->remove || test) tracing_set_filter_buffering(file->tr, false); } + + if (test && test->cmd_ops->free) + test->cmd_ops->free(test); } static bool hist_file_check_refs(struct trace_event_file *file) @@ -6951,6 +6953,8 @@ static int event_hist_trigger_parse(struct event_command *cmd_ops, return ret; out_unreg: event_trigger_unregister(cmd_ops, file, glob+1, trigger_data); + /* The unregister frees trigger_data, skip out_free */ + goto out; out_free: remove_hist_vars(hist_data); diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c index ad83419cb42019..1954184ab2b9dd 100644 --- a/kernel/trace/trace_events_trigger.c +++ b/kernel/trace/trace_events_trigger.c @@ -1728,7 +1728,8 @@ static void enable_trigger_private_data_free(struct event_trigger_data *data) { struct enable_trigger_data *enable_data = data->private_data; - trace_event_put_ref(enable_data->file->event_call); + /* The file may already be freed here, only the call is kept alive */ + trace_event_put_ref(enable_data->call); kfree(enable_data); } @@ -1801,6 +1802,7 @@ int event_enable_trigger_parse(struct event_command *cmd_ops, enable_data->hist = hist; enable_data->enable = enable; enable_data->file = event_enable_file; + enable_data->call = event_enable_file->event_call; trigger_data = trigger_data_alloc(cmd_ops, cmd, param, enable_data); if (!trigger_data) { diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c index 6b89d225b189e4..e190dad1eb9145 100644 --- a/kernel/trace/trace_events_user.c +++ b/kernel/trace/trace_events_user.c @@ -1122,10 +1122,9 @@ static void user_event_destroy_validators(struct user_event *user) } } -static void user_event_destroy_fields(struct user_event *user) +static void user_event_destroy_fields(struct list_head *head) { struct ftrace_event_field *field, *next; - struct list_head *head = &user->fields; list_for_each_entry_safe(field, next, head, link) { list_del(&field->link); @@ -1502,17 +1501,32 @@ static int user_event_set_call_visible(struct user_event *user, bool visible) static int destroy_user_event(struct user_event *user) { + LIST_HEAD(fields); int ret = 0; lockdep_assert_held(&event_mutex); - /* Must destroy fields before call removal */ - user_event_destroy_fields(user); + /* + * Detach the fields before removing the call. Removing the event + * frees the field list memory (trace_destroy_fields() is run on + * successful removal and kmem_cache_free()s the fields), but the + * fields here are allocated and owned by user_events. Destroy + * them separately once removal has succeeded. + */ + list_splice_init(&user->fields, &fields); ret = user_event_set_call_visible(user, false); - if (ret) + if (ret) { + /* + * Removal failed and the event stays registered, recover + * the fields so it is left in a consistent state. + */ + list_splice(&fields, &user->fields); return ret; + } + + user_event_destroy_fields(&fields); dyn_event_remove(&user->devent); hash_del(&user->node); @@ -2212,7 +2226,7 @@ static int user_event_parse(struct user_event_group *group, char *name, put_user_lock: mutex_unlock(&event_mutex); put_user: - user_event_destroy_fields(user); + user_event_destroy_fields(&user->fields); user_event_destroy_validators(user); kfree(user->call.print_fmt); diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index 0d2d3a2ea7dda0..9ce68d207ef933 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -52,6 +52,7 @@ struct fgraph_data { }; struct ftrace_graph_ret_entry ret; int failed; + int ent_size; int cpu; }; @@ -1274,6 +1275,7 @@ print_graph_entry(struct ftrace_graph_ent_entry *field, struct trace_seq *s, if (s->full) { data->failed = 1; data->cpu = cpu; + data->ent_size = iter->ent_size; } else data->failed = 0; } @@ -1457,6 +1459,7 @@ print_graph_function_flags(struct trace_iterator *iter, u32 flags) if (data && data->failed) { field = &data->ent.ent; iter->cpu = data->cpu; + iter->ent_size = data->ent_size; ret = print_graph_entry(field, s, iter, flags); if (ret == TRACE_TYPE_HANDLED && iter->cpu != cpu) { per_cpu_ptr(data->cpu_data, iter->cpu)->ignore = 1; diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c index aae60fbebeafbb..f3c20a093f5dd8 100644 --- a/kernel/trace/trace_probe.c +++ b/kernel/trace/trace_probe.c @@ -2108,19 +2108,60 @@ int traceprobe_set_print_fmt(struct trace_probe *tp, enum probe_print_type ptype int traceprobe_define_arg_fields(struct trace_event_call *event_call, size_t offset, struct trace_probe *tp) { + struct trace_probe_event *tpe = trace_probe_event_from_call(event_call); int ret, i; + /* + * A field created by trace_define_field() only stores the name and + * type pointers, it does not copy the strings. Here they point into + * the probe_arg of @tp, which is freed when @tp is removed. For an + * event with multiple probes attached, the field list is defined + * once by the first probe but kept alive by the surviving siblings, + * so removing that first probe would leave the fields referencing + * freed memory. Duplicate the strings and anchor the copies on the + * trace_probe_event, which lives as long as the field list itself. + * + * event_define_fields() ignores the return value of this hook, so + * if a previous attempt failed before creating any field, it may + * call here again. Release duplicates left behind by such an + * attempt before starting over. + */ + for (i = 0; i < tpe->nr_field_strings; i++) + kfree(tpe->field_strings[i]); + kfree(tpe->field_strings); + tpe->field_strings = NULL; + tpe->nr_field_strings = 0; + + if (tp->nr_args) { + tpe->field_strings = kcalloc(tp->nr_args * 2, sizeof(char *), + GFP_KERNEL); + if (!tpe->field_strings) + return -ENOMEM; + } + /* Set argument names as fields */ for (i = 0; i < tp->nr_args; i++) { struct probe_arg *parg = &tp->args[i]; const char *fmt = parg->type->fmttype; int size = parg->type->size; + char *name, *type; if (parg->fmt) fmt = parg->fmt; if (parg->count) size *= parg->count; - ret = trace_define_field(event_call, fmt, parg->name, + + name = kstrdup(parg->name, GFP_KERNEL); + type = kstrdup(fmt, GFP_KERNEL); + if (!name || !type) { + kfree(name); + kfree(type); + return -ENOMEM; + } + tpe->field_strings[tpe->nr_field_strings++] = name; + tpe->field_strings[tpe->nr_field_strings++] = type; + + ret = trace_define_field(event_call, type, name, offset + parg->offset, size, parg->type->is_signed, FILTER_OTHER); @@ -2132,6 +2173,11 @@ int traceprobe_define_arg_fields(struct trace_event_call *event_call, static void trace_probe_event_free(struct trace_probe_event *tpe) { + int i; + + for (i = 0; i < tpe->nr_field_strings; i++) + kfree(tpe->field_strings[i]); + kfree(tpe->field_strings); kfree(tpe->class.system); kfree(tpe->call.name); kfree(tpe->call.print_fmt); diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h index 0f09f7aaf93fbb..480eb6acd883f2 100644 --- a/kernel/trace/trace_probe.h +++ b/kernel/trace/trace_probe.h @@ -255,6 +255,8 @@ struct trace_probe_event { struct trace_event_call call; struct list_head files; struct list_head probes; + char **field_strings; + int nr_field_strings; struct trace_uprobe_filter filter[]; }; diff --git a/kernel/trace/trace_remote.c b/kernel/trace/trace_remote.c index e6724f947170d9..c79cd21347a03b 100644 --- a/kernel/trace/trace_remote.c +++ b/kernel/trace/trace_remote.c @@ -980,9 +980,12 @@ int trace_remote_alloc_buffer(struct trace_buffer_desc *desc, size_t desc_size, const struct cpumask *cpumask) { size_t min_desc_size = trace_buffer_desc_size(buffer_size, cpumask_weight(cpumask)); - unsigned int nr_pages = max(DIV_ROUND_UP(buffer_size, PAGE_SIZE), 2UL) + 1; struct ring_buffer_desc *rb_desc; int cpu, ret = -ENOMEM; + unsigned int nr_pages; + + if (min_desc_size == SIZE_MAX) + return -E2BIG; if (desc_size < min_desc_size) return -EINVAL; @@ -991,6 +994,7 @@ int trace_remote_alloc_buffer(struct trace_buffer_desc *desc, size_t desc_size, desc->struct_len = min_desc_size; rb_desc = __first_ring_buffer_desc(desc); + nr_pages = __calc_nr_pages_ring_buffer_desc(buffer_size); for_each_cpu(cpu, cpumask) { unsigned int id; diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 929c04a9581bd0..36aaeb38e21747 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -7923,6 +7923,9 @@ static int wq_watchdog_param_set_thresh(const char *val, if (ret) return ret; + if (thresh > MAX_JIFFY_OFFSET / HZ) + return -ERANGE; + if (system_percpu_wq) wq_watchdog_set_thresh(thresh); else diff --git a/lib/iov_iter.c b/lib/iov_iter.c index 34a52e9ba9e1b5..52387319109178 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -1920,15 +1920,29 @@ ssize_t iov_iter_extract_bvecs(struct iov_iter *iter, struct bio_vec *bv, unsigned short max_vecs, unsigned mem_align_mask, iov_iter_extraction_t extraction_flags) { - unsigned long start = (unsigned long)iter_iov_addr(iter); unsigned short entries_left = max_vecs - *nr_vecs; unsigned short nr_pages, i = 0; size_t left, offset, len; struct page **pages; ssize_t size; - if ((start | iter_iov_len(iter)) & mem_align_mask) + /* + * DMA engines typically have both memory address and length alignment + * requirements, so check these against the alignment mask. For UBUF, + * IOVEC and KVEC, only the current segment will be extracted from; for + * everything else we might extract from multiple segments, so we need + * to check those too. + */ + if (likely(iter_is_ubuf(iter) || + iter_is_iovec(iter) || + iov_iter_is_kvec(iter))) { + unsigned long start = (unsigned long)iter_iov_addr(iter); + + if ((start | iter_iov_len(iter)) & mem_align_mask) + return -EINVAL; + } else if (iov_iter_alignment(iter) & mem_align_mask) { return -EINVAL; + } /* * Move page array up in the allocated memory for the bio vecs as far as diff --git a/mm/slub.c b/mm/slub.c index 5e88c520522b0b..3791d69ba6f90f 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -5612,10 +5612,12 @@ static noinline void free_to_partial_list( * * Fail if the slab isn't full anymore due to a concurrent free. */ -static bool __slab_try_return_freelist(struct kmem_cache *s, struct slab *slab, - void *head, int cnt) +static bool __slab_try_return_freelist(struct kmem_cache *s, + struct kmem_cache_node *n, + struct slab *slab, void *head, int cnt) { struct freelist_counters old, new; + unsigned long flags; old.freelist = slab->freelist; old.counters = slab->counters; @@ -5627,9 +5629,15 @@ static bool __slab_try_return_freelist(struct kmem_cache *s, struct slab *slab, new.counters = old.counters; new.inuse -= cnt; - if (!slab_update_freelist(s, slab, &old, &new, "__slab_try_return_freelist")) + spin_lock_irqsave(&n->list_lock, flags); + + if (!slab_update_freelist(s, slab, &old, &new, "__slab_try_return_freelist")) { + spin_unlock_irqrestore(&n->list_lock, flags); return false; + } + add_partial(n, slab, ADD_TO_TAIL); + spin_unlock_irqrestore(&n->list_lock, flags); return true; } @@ -7202,10 +7210,8 @@ __refill_objects_node(struct kmem_cache *s, void **p, gfp_t gfp, unsigned int mi void *head = object; void *tail; - if (__slab_try_return_freelist(s, slab, head, count)) { - list_add(&slab->slab_list, &pc.slabs); + if (__slab_try_return_freelist(s, n, slab, head, count)) break; - } do { tail = object; @@ -7218,7 +7224,7 @@ __refill_objects_node(struct kmem_cache *s, void **p, gfp_t gfp, unsigned int mi break; } - if (!list_empty(&pc.slabs)) { + if (unlikely(!list_empty(&pc.slabs))) { spin_lock_irqsave(&n->list_lock, flags); list_for_each_entry(slab, &pc.slabs, slab_list) diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index f346505c3f88cb..f747492da5f661 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -2629,11 +2629,11 @@ int hci_register_dev(struct hci_dev *hdev) if (error) BT_WARN("register suspend notifier failed error:%d\n", error); - queue_work(hdev->req_workqueue, &hdev->power_on); - idr_init(&hdev->adv_monitors_idr); msft_register(hdev); + queue_work(hdev->req_workqueue, &hdev->power_on); + return id; err_wqueue: diff --git a/net/bluetooth/hci_sysfs.c b/net/bluetooth/hci_sysfs.c index 8957ce7c21b76c..c2065abf753e08 100644 --- a/net/bluetooth/hci_sysfs.c +++ b/net/bluetooth/hci_sysfs.c @@ -13,7 +13,10 @@ static const struct class bt_class = { static void bt_link_release(struct device *dev) { struct hci_conn *conn = to_hci_conn(dev); + struct device *parent = dev->parent; + kfree(conn); + put_device(parent); } static const struct device_type bt_link = { @@ -21,6 +24,16 @@ static const struct device_type bt_link = { .release = bt_link_release, }; +/* + * The rfcomm tty device will possibly retain even when conn + * is down, and sysfs doesn't support move zombie device, + * so we should move the device before conn device is destroyed. + */ +static int __match_tty(struct device *dev, const void *data) +{ + return !strncmp(dev_name(dev), "rfcomm", 6); +} + void hci_conn_init_sysfs(struct hci_conn *conn) { struct hci_dev *hdev = conn->hdev; @@ -29,7 +42,7 @@ void hci_conn_init_sysfs(struct hci_conn *conn) conn->dev.type = &bt_link; conn->dev.class = &bt_class; - conn->dev.parent = &hdev->dev; + conn->dev.parent = get_device(&hdev->dev); device_initialize(&conn->dev); } @@ -69,7 +82,7 @@ void hci_conn_del_sysfs(struct hci_conn *conn) while (1) { struct device *dev; - dev = device_find_any_child(&conn->dev); + dev = device_find_child(&conn->dev, NULL, __match_tty); if (!dev) break; device_move(dev, NULL, DPM_ORDER_DEV_LAST); diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 30d7120d3a150c..800f7517bfeb06 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -1337,7 +1337,7 @@ static void l2cap_le_connect(struct l2cap_chan *chan) struct l2cap_ecred_conn_data { struct { struct l2cap_ecred_conn_req_hdr req; - __le16 scid[5]; + __le16 scid[L2CAP_ECRED_CONN_SCID_MAX]; } __packed pdu; struct l2cap_chan *chan; struct pid *pid; @@ -1352,7 +1352,7 @@ static void l2cap_ecred_defer_connect(struct l2cap_chan *chan, void *data) if (chan == conn->chan) return; - if (!test_and_clear_bit(FLAG_DEFER_SETUP, &chan->flags)) + if (!test_bit(FLAG_DEFER_SETUP, &chan->flags)) return; pid = chan->ops->get_peer_pid(chan); @@ -1362,9 +1362,16 @@ static void l2cap_ecred_defer_connect(struct l2cap_chan *chan, void *data) chan->mode != L2CAP_MODE_EXT_FLOWCTL || chan->state != BT_CONNECT) return; + if (!test_and_clear_bit(FLAG_DEFER_SETUP, &chan->flags)) + return; + if (test_and_set_bit(FLAG_ECRED_CONN_REQ_SENT, &chan->flags)) return; + /* Unreachable, checked in l2cap_connect (+timer drops it if reached) */ + if (WARN_ON_ONCE(conn->count >= ARRAY_SIZE(conn->pdu.scid))) + return; + l2cap_ecred_init(chan, 0); /* Set the same ident so we can match on the rsp */ @@ -3893,6 +3900,9 @@ static void l2cap_ecred_rsp_defer(struct l2cap_chan *chan, void *data) struct l2cap_ecred_conn_rsp *rsp_flex = container_of(&rsp->pdu.rsp, struct l2cap_ecred_conn_rsp, hdr); + if (chan->mode != L2CAP_MODE_EXT_FLOWCTL) + return; + /* Check if channel for outgoing connection or if it wasn't deferred * since in those cases it must be skipped. */ @@ -3903,6 +3913,10 @@ static void l2cap_ecred_rsp_defer(struct l2cap_chan *chan, void *data) /* Reset ident so only one response is sent */ chan->ident = 0; + /* Unreachable, check in l2cap_ecred_conn_req. If reached, drop rest */ + if (WARN_ON_ONCE(rsp->count >= ARRAY_SIZE(rsp->pdu.scid))) + rsp->pdu.rsp.result = cpu_to_le16(L2CAP_CR_LE_NO_MEM); + /* Include all channels pending with the same ident */ if (!rsp->pdu.rsp.result) rsp_flex->dcid[rsp->count++] = cpu_to_le16(chan->scid); @@ -5062,6 +5076,7 @@ static int l2cap_le_connect_req(struct l2cap_conn *conn, __set_chan_timer(chan, chan->ops->get_sndtimeo(chan)); chan->ident = cmd->ident; + chan->mode = L2CAP_MODE_LE_FLOWCTL; if (test_bit(FLAG_DEFER_SETUP, &chan->flags)) { l2cap_state_change(chan, BT_CONNECT2); @@ -7365,6 +7380,9 @@ int l2cap_chan_connect(struct l2cap_chan *chan, __le16 psm, u16 cid, goto done; } + mutex_lock(&conn->lock); + l2cap_chan_lock(chan); + if (chan->mode == L2CAP_MODE_EXT_FLOWCTL) { struct l2cap_chan_data data; @@ -7372,19 +7390,20 @@ int l2cap_chan_connect(struct l2cap_chan *chan, __le16 psm, u16 cid, data.pid = chan->ops->get_peer_pid(chan); data.count = 1; - l2cap_chan_list(conn, l2cap_chan_by_pid, &data); + __l2cap_chan_list(conn, l2cap_chan_by_pid, &data); + + /* Leave room for non-deferred channel that ends the group. */ + if (test_bit(FLAG_DEFER_SETUP, &chan->flags)) + data.count += 1; /* Check if there isn't too many channels being connected */ if (data.count > L2CAP_ECRED_CONN_SCID_MAX) { hci_conn_drop(hcon); err = -EPROTO; - goto done; + goto chan_unlock; } } - mutex_lock(&conn->lock); - l2cap_chan_lock(chan); - if (cid && __l2cap_get_chan_by_dcid(conn, cid)) { hci_conn_drop(hcon); err = -EBUSY; diff --git a/net/bluetooth/msft.c b/net/bluetooth/msft.c index ded68568e6c9b5..d9dd722db3ebd5 100644 --- a/net/bluetooth/msft.c +++ b/net/bluetooth/msft.c @@ -769,8 +769,8 @@ void msft_register(struct hci_dev *hdev) INIT_LIST_HEAD(&msft->handle_map); INIT_LIST_HEAD(&msft->address_filters); - hdev->msft_data = msft; mutex_init(&msft->filter_lock); + hdev->msft_data = msft; } void msft_release(struct hci_dev *hdev) diff --git a/net/bridge/br_cfm.c b/net/bridge/br_cfm.c index dea56fffa1c19f..9dcc97d63a6fc4 100644 --- a/net/bridge/br_cfm.c +++ b/net/bridge/br_cfm.c @@ -367,7 +367,7 @@ static u32 ccm_tlv_extract(struct sk_buff *skb, u32 index, } /* note: already called with rcu_read_lock */ -static int br_cfm_frame_rx(struct net_bridge_port *port, struct sk_buff *skb) +int br_cfm_frame_rx(struct net_bridge_port *port, struct sk_buff *skb) { u32 mdlevel, interval, size, index, max; const struct br_cfm_common_hdr *hdr; @@ -489,11 +489,6 @@ static int br_cfm_frame_rx(struct net_bridge_port *port, struct sk_buff *skb) return 1; } -static struct br_frame_type cfm_frame_type __read_mostly = { - .type = cpu_to_be16(ETH_P_CFM), - .frame_handler = br_cfm_frame_rx, -}; - int br_cfm_mep_create(struct net_bridge *br, const u32 instance, struct br_cfm_mep_create *const create, @@ -559,7 +554,7 @@ int br_cfm_mep_create(struct net_bridge *br, INIT_DELAYED_WORK(&mep->ccm_tx_dwork, ccm_tx_work_expired); if (hlist_empty(&br->mep_list)) - br_add_frame(br, &cfm_frame_type); + br_opt_toggle(br, BROPT_CFM_ENABLED, true); hlist_add_tail_rcu(&mep->head, &br->mep_list); @@ -588,7 +583,7 @@ static void mep_delete_implementation(struct net_bridge *br, kfree_rcu(mep, rcu); if (hlist_empty(&br->mep_list)) - br_del_frame(br, &cfm_frame_type); + br_opt_toggle(br, BROPT_CFM_ENABLED, false); } int br_cfm_mep_delete(struct net_bridge *br, diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index e7f343ab22d379..7b163d2b4e01df 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -503,7 +503,6 @@ void br_dev_setup(struct net_device *dev) spin_lock_init(&br->lock); INIT_LIST_HEAD(&br->port_list); INIT_HLIST_HEAD(&br->fdb_list); - INIT_HLIST_HEAD(&br->frame_type_list); #if IS_ENABLED(CONFIG_BRIDGE_MRP) INIT_HLIST_HEAD(&br->mrp_list); #endif diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index ddb8f002a40e82..1322543bc91718 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -317,17 +317,25 @@ frame_finish: return RX_HANDLER_CONSUMED; } +#define BR_CFM_MRP_OPTS \ + ((IS_ENABLED(CONFIG_BRIDGE_CFM) ? BIT(BROPT_CFM_ENABLED) : 0UL) | \ + (IS_ENABLED(CONFIG_BRIDGE_MRP) ? BIT(BROPT_MRP_ENABLED) : 0UL)) + /* Return 0 if the frame was not processed otherwise 1 * note: already called with rcu_read_lock */ static int br_process_frame_type(struct net_bridge_port *p, struct sk_buff *skb) { - struct br_frame_type *tmp; + struct net_bridge *br = p->br; + + if (skb->protocol == htons(ETH_P_CFM) && + br_opt_get(br, BROPT_CFM_ENABLED)) + return br_cfm_frame_rx(p, skb); - hlist_for_each_entry_rcu(tmp, &p->br->frame_type_list, list) - if (unlikely(tmp->type == skb->protocol)) - return tmp->frame_handler(p, skb); + if (skb->protocol == htons(ETH_P_MRP) && + br_opt_get(br, BROPT_MRP_ENABLED)) + return br_mrp_process(p, skb); return 0; } @@ -425,7 +433,8 @@ static rx_handler_result_t br_handle_frame(struct sk_buff **pskb) } } - if (unlikely(br_process_frame_type(p, skb))) + if (unlikely((READ_ONCE(p->br->options) & BR_CFM_MRP_OPTS) && + br_process_frame_type(p, skb))) return RX_HANDLER_PASS; forward: @@ -467,19 +476,3 @@ rx_handler_func_t *br_get_rx_handler(const struct net_device *dev) return br_handle_frame; } - -void br_add_frame(struct net_bridge *br, struct br_frame_type *ft) -{ - hlist_add_head_rcu(&ft->list, &br->frame_type_list); -} - -void br_del_frame(struct net_bridge *br, struct br_frame_type *ft) -{ - struct br_frame_type *tmp; - - hlist_for_each_entry(tmp, &br->frame_type_list, list) - if (ft == tmp) { - hlist_del_rcu(&ft->list); - return; - } -} diff --git a/net/bridge/br_mrp.c b/net/bridge/br_mrp.c index ef16d07039241a..dce6efa96c4c61 100644 --- a/net/bridge/br_mrp.c +++ b/net/bridge/br_mrp.c @@ -6,13 +6,6 @@ static const u8 mrp_test_dmac[ETH_ALEN] = { 0x1, 0x15, 0x4e, 0x0, 0x0, 0x1 }; static const u8 mrp_in_test_dmac[ETH_ALEN] = { 0x1, 0x15, 0x4e, 0x0, 0x0, 0x3 }; -static int br_mrp_process(struct net_bridge_port *p, struct sk_buff *skb); - -static struct br_frame_type mrp_frame_type __read_mostly = { - .type = cpu_to_be16(ETH_P_MRP), - .frame_handler = br_mrp_process, -}; - static bool br_mrp_is_ring_port(struct net_bridge_port *p_port, struct net_bridge_port *s_port, struct net_bridge_port *port) @@ -486,7 +479,7 @@ static void br_mrp_del_impl(struct net_bridge *br, struct br_mrp *mrp) kfree_rcu(mrp, rcu); if (hlist_empty(&br->mrp_list)) - br_del_frame(br, &mrp_frame_type); + br_opt_toggle(br, BROPT_MRP_ENABLED, false); } /* Adds a new MRP instance. @@ -536,7 +529,7 @@ int br_mrp_add(struct net_bridge *br, struct br_mrp_instance *instance) rcu_assign_pointer(mrp->s_port, p); if (hlist_empty(&br->mrp_list)) - br_add_frame(br, &mrp_frame_type); + br_opt_toggle(br, BROPT_MRP_ENABLED, true); INIT_DELAYED_WORK(&mrp->test_work, br_mrp_test_work_expired); INIT_DELAYED_WORK(&mrp->in_test_work, br_mrp_in_test_work_expired); @@ -1241,7 +1234,7 @@ no_forward: * normal forwarding. * note: already called with rcu_read_lock */ -static int br_mrp_process(struct net_bridge_port *p, struct sk_buff *skb) +int br_mrp_process(struct net_bridge_port *p, struct sk_buff *skb) { /* If there is no MRP instance do normal forwarding */ if (likely(!test_bit(BR_MRP_AWARE_BIT, &p->flags))) diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index ec0339e204bda4..2191d35d9fa07a 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -1435,16 +1435,17 @@ struct net_bridge_port_group *br_multicast_new_port_group( goto free_out; } - rcu_assign_pointer(p->next, next); timer_setup(&p->timer, br_multicast_port_group_expired, 0); timer_setup(&p->rexmit_timer, br_multicast_port_group_rexmit, 0); - hlist_add_head(&p->mglist, &port->mglist); if (src) memcpy(p->eth_addr, src, ETH_ALEN); else eth_broadcast_addr(p->eth_addr); + RCU_INIT_POINTER(p->next, next); + hlist_add_head_rcu(&p->mglist, &port->mglist); + return p; free_out: @@ -1459,11 +1460,11 @@ void br_multicast_del_port_group(struct net_bridge_port_group *p) struct net_bridge_port *port = p->key.port; __u16 vid = p->key.addr.vid; - hlist_del_init(&p->mglist); + hlist_del_init_rcu(&p->mglist); if (!br_multicast_is_star_g(&p->key.addr)) rhashtable_remove_fast(&port->br->sg_port_tbl, &p->rhnode, br_sg_port_rht_params); - kfree(p); + kfree_rcu(p, rcu); br_multicast_port_ngroups_dec(port, vid); } diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index d3880f31edc4e1..d08e318f045552 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -491,12 +491,13 @@ enum net_bridge_opts { BROPT_MST_ENABLED, BROPT_MDB_OFFLOAD_FAIL_NOTIFICATION, BROPT_FDB_LOCAL_VLAN_0, + BROPT_CFM_ENABLED, + BROPT_MRP_ENABLED, }; struct net_bridge { spinlock_t lock; spinlock_t hash_lock; - struct hlist_head frame_type_list; struct net_device *dev; unsigned long options; /* These fields are accessed on each packet */ @@ -928,16 +929,6 @@ int nbp_backup_change(struct net_bridge_port *p, struct net_device *backup_dev); int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb); rx_handler_func_t *br_get_rx_handler(const struct net_device *dev); -struct br_frame_type { - __be16 type; - int (*frame_handler)(struct net_bridge_port *port, - struct sk_buff *skb); - struct hlist_node list; -}; - -void br_add_frame(struct net_bridge *br, struct br_frame_type *ft); -void br_del_frame(struct net_bridge *br, struct br_frame_type *ft); - static inline bool br_rx_handler_check_rcu(const struct net_device *dev) { return rcu_dereference(dev->rx_handler) == br_get_rx_handler(dev); @@ -2076,6 +2067,7 @@ int br_mrp_parse(struct net_bridge *br, struct net_bridge_port *p, bool br_mrp_enabled(struct net_bridge *br); void br_mrp_port_del(struct net_bridge *br, struct net_bridge_port *p); int br_mrp_fill_info(struct sk_buff *skb, struct net_bridge *br); +int br_mrp_process(struct net_bridge_port *p, struct sk_buff *skb); #else static inline int br_mrp_parse(struct net_bridge *br, struct net_bridge_port *p, struct nlattr *attr, int cmd, @@ -2099,6 +2091,11 @@ static inline int br_mrp_fill_info(struct sk_buff *skb, struct net_bridge *br) return 0; } +static inline int br_mrp_process(struct net_bridge_port *p, struct sk_buff *skb) +{ + return 0; +} + #endif /* br_cfm.c */ @@ -2107,6 +2104,7 @@ int br_cfm_parse(struct net_bridge *br, struct net_bridge_port *p, struct nlattr *attr, int cmd, struct netlink_ext_ack *extack); bool br_cfm_created(struct net_bridge *br); void br_cfm_port_del(struct net_bridge *br, struct net_bridge_port *p); +int br_cfm_frame_rx(struct net_bridge_port *port, struct sk_buff *skb); int br_cfm_config_fill_info(struct sk_buff *skb, struct net_bridge *br); int br_cfm_status_fill_info(struct sk_buff *skb, struct net_bridge *br, @@ -2131,6 +2129,12 @@ static inline void br_cfm_port_del(struct net_bridge *br, { } +static inline int br_cfm_frame_rx(struct net_bridge_port *port, + struct sk_buff *skb) +{ + return 0; +} + static inline int br_cfm_config_fill_info(struct sk_buff *skb, struct net_bridge *br) { return -EOPNOTSUPP; diff --git a/net/core/dev.c b/net/core/dev.c index 39807b68ff2609..74dd9e25f4ff7a 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -9932,7 +9932,7 @@ int netif_change_tx_queue_len(struct net_device *dev, unsigned long new_len) unsigned int orig_len = dev->tx_queue_len; int res; - if (new_len != (unsigned int)new_len) + if (new_len > S16_MAX) return -ERANGE; if (new_len != orig_len) { @@ -12541,7 +12541,7 @@ int __dev_change_net_namespace(struct net_device *dev, struct net *net, const char *pat, int new_ifindex, struct netlink_ext_ack *extack) { - struct netdev_name_node *name_node; + struct netdev_name_node *name_node, *tmp; struct net *net_old = dev_net(dev); char new_name[IFNAMSIZ] = {}; int err, new_nsid; @@ -12587,13 +12587,19 @@ int __dev_change_net_namespace(struct net_device *dev, struct net *net, } /* Check that none of the altnames conflicts. */ err = -EEXIST; - netdev_for_each_altname(dev, name_node) { - if (netdev_name_in_use(net, name_node->name)) { - NL_SET_ERR_MSG_FMT(extack, - "An interface with the altname %s exists in the target netns", - name_node->name); - goto out; + netdev_for_each_altname_safe(dev, name_node, tmp) { + if (!netdev_name_in_use(net, name_node->name)) + continue; + + if (!check_net(net_old)) { + __netdev_name_node_alt_destroy(name_node); + continue; } + + NL_SET_ERR_MSG_FMT(extack, + "An interface with the altname %s exists in the target netns", + name_node->name); + goto out; } /* Check that new_ifindex isn't used yet. */ @@ -13044,7 +13050,6 @@ static struct pernet_operations __net_initdata netdev_net_ops = { static void __net_exit default_device_exit_net(struct net *net) { - struct netdev_name_node *name_node, *tmp; struct net_device *dev, *aux; /* * Push all migratable network devices back to the @@ -13068,10 +13073,6 @@ static void __net_exit default_device_exit_net(struct net *net) if (netdev_name_in_use(&init_net, fb_name)) snprintf(fb_name, IFNAMSIZ, "dev%%d"); - netdev_for_each_altname_safe(dev, name_node, tmp) - if (netdev_name_in_use(&init_net, name_node->name)) - __netdev_name_node_alt_destroy(name_node); - err = dev_change_net_namespace(dev, &init_net, fb_name); if (err) { pr_emerg("%s: failed to move %s to init_net: %d\n", diff --git a/net/core/gro_cells.c b/net/core/gro_cells.c index 1b84385c04bd9c..d8c0a286712019 100644 --- a/net/core/gro_cells.c +++ b/net/core/gro_cells.c @@ -22,6 +22,8 @@ int gro_cells_receive(struct gro_cells *gcells, struct sk_buff *skb) if (unlikely(!(dev->flags & IFF_UP))) goto drop; + skb_unset_transport_header(skb); + if (!gcells->cells || skb_cloned(skb) || netif_elide_gro(dev)) { res = netif_rx(skb); goto unlock; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 12aa3aa1688b13..73101ec65c9af0 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2236,6 +2236,11 @@ nla_put_failure: return -EMSGSIZE; } +static const struct netlink_range_validation txqlen_range = { + .min = 0, + .max = S16_MAX, +}; + static const struct nla_policy ifla_policy[IFLA_MAX+1] = { [IFLA_UNSPEC] = { .strict_start_type = IFLA_DPLL_PIN }, [IFLA_IFNAME] = { .type = NLA_STRING, .len = IFNAMSIZ-1 }, @@ -2246,7 +2251,7 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = { [IFLA_LINK] = { .type = NLA_U32 }, [IFLA_MASTER] = { .type = NLA_U32 }, [IFLA_CARRIER] = { .type = NLA_U8 }, - [IFLA_TXQLEN] = { .type = NLA_U32 }, + [IFLA_TXQLEN] = NLA_POLICY_FULL_RANGE(NLA_U32, &txqlen_range), [IFLA_WEIGHT] = { .type = NLA_U32 }, [IFLA_OPERSTATE] = { .type = NLA_U8 }, [IFLA_LINKMODE] = { .type = NLA_U8 }, diff --git a/net/core/skbuff.c b/net/core/skbuff.c index b3edb90a21d625..0e964c67a7213e 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -6678,6 +6678,13 @@ int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto, int mac_len, } skb->protocol = next_proto; + /* The last label is gone, so the inner header recorded by + * skb_mpls_push() no longer describes this packet. Drop it, or a + * later push keeps the stale offset. + */ + if (!eth_p_mpls(next_proto)) + skb->inner_protocol = 0; + return 0; } EXPORT_SYMBOL_GPL(skb_mpls_pop); diff --git a/net/dsa/tag_brcm.c b/net/dsa/tag_brcm.c index 411e3b57d16af5..b7c49822ca8880 100644 --- a/net/dsa/tag_brcm.c +++ b/net/dsa/tag_brcm.c @@ -373,6 +373,7 @@ static const struct dsa_device_ops brcm_legacy_fcs_netdev_ops = { .xmit = brcm_leg_fcs_tag_xmit, .rcv = brcm_leg_tag_rcv, .needed_headroom = BRCM_LEG_TAG_LEN, + .needed_tailroom = ETH_FCS_LEN, }; DSA_TAG_DRIVER(brcm_legacy_fcs_netdev_ops); diff --git a/net/hsr/hsr_slave.c b/net/hsr/hsr_slave.c index 01c73b4b50ddd8..a546f70f9cc8b4 100644 --- a/net/hsr/hsr_slave.c +++ b/net/hsr/hsr_slave.c @@ -149,9 +149,12 @@ static int hsr_portdev_setup(struct hsr_priv *hsr, struct net_device *dev, int res; /* Don't use promiscuous mode for offload since L2 frame forward - * happens at the offloaded hardware. + * happens at the offloaded hardware. The interlink port never + * gets forwarding offload (RedBox forwarding to/from it is done + * by this driver), so it still needs promiscuous mode to receive + * frames addressed to hsr_dev's MAC rather than its own. */ - if (!port->hsr->fwd_offloaded) { + if (!port->hsr->fwd_offloaded || port->type == HSR_PT_INTERLINK) { res = dev_set_promiscuity(dev, 1); if (res) return res; @@ -176,7 +179,7 @@ static int hsr_portdev_setup(struct hsr_priv *hsr, struct net_device *dev, fail_rx_handler: netdev_upper_dev_unlink(dev, hsr_dev); fail_upper_dev_link: - if (!port->hsr->fwd_offloaded) + if (!port->hsr->fwd_offloaded || port->type == HSR_PT_INTERLINK) dev_set_promiscuity(dev, -1); return res; @@ -240,7 +243,7 @@ void hsr_del_port(struct hsr_port *port) netdev_update_features(master->dev); dev_set_mtu(master->dev, hsr_get_max_mtu(hsr)); netdev_rx_handler_unregister(port->dev); - if (!port->hsr->fwd_offloaded) + if (!port->hsr->fwd_offloaded || port->type == HSR_PT_INTERLINK) dev_set_promiscuity(port->dev, -1); if (port->type == HSR_PT_SLAVE_A || port->type == HSR_PT_SLAVE_B) vlan_vids_del_by_dev(port->dev, master->dev); diff --git a/net/ieee802154/6lowpan/core.c b/net/ieee802154/6lowpan/core.c index 018929563c6bc3..6a8d6852cb9305 100644 --- a/net/ieee802154/6lowpan/core.c +++ b/net/ieee802154/6lowpan/core.c @@ -150,7 +150,7 @@ static int lowpan_newlink(struct net_device *ldev, wdev = dev_get_by_index(dev_net(ldev), nla_get_u32(tb[IFLA_LINK])); if (!wdev) return -ENODEV; - if (wdev->type != ARPHRD_IEEE802154) { + if (wdev->type != ARPHRD_IEEE802154 || !wdev->ieee802154_ptr) { dev_put(wdev); return -EINVAL; } diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index e068a5bace73f2..dcbbfdb291ed3f 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -214,6 +214,8 @@ INDIRECT_CALLABLE_SCOPE int fib4_rule_match(struct fib_rule *rule, return 1; } +#define FIB_MAX_AUTO_TABLE_ID 4096 + static struct fib_table *fib_empty_table(struct net *net) { u32 id = 1; @@ -222,7 +224,7 @@ static struct fib_table *fib_empty_table(struct net *net) if (!fib_get_table(net, id)) return fib_new_table(net, id); - if (id++ == RT_TABLE_MAX) + if (id++ == FIB_MAX_AUTO_TABLE_ID) break; } return NULL; diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index bb2d4441a49294..0a5b7ded23be2c 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -188,6 +188,10 @@ static void ip_ma_put(struct ip_mc_list *im) } } +#define pmc_dereference(e, pmc) \ + rcu_dereference_protected(e, lockdep_is_held(&(pmc)->lock) || \ + lockdep_is_held(&(pmc)->interface->mc_tomb_lock)) + #define for_each_pmc_rcu(in_dev, pmc) \ for (pmc = rcu_dereference(in_dev->mc_list); \ pmc != NULL; \ @@ -198,13 +202,28 @@ static void ip_ma_put(struct ip_mc_list *im) pmc != NULL; \ pmc = rtnl_dereference(pmc->next_rcu)) +#define for_each_psf_mclock(pmc, psf) \ + for (psf = pmc_dereference((pmc)->sources, pmc); \ + psf; \ + psf = pmc_dereference(psf->sf_next, pmc)) + +#define for_each_psf_rcu(im, psf) \ + for (psf = rcu_dereference((im)->sources); \ + psf; \ + psf = rcu_dereference(psf->sf_next)) + +#define for_each_psf_tomb(pmc, psf) \ + for (psf = pmc_dereference((pmc)->tomb, pmc); \ + psf; \ + psf = pmc_dereference(psf->sf_next, pmc)) + static void ip_sf_list_clear_all(struct ip_sf_list *psf) { struct ip_sf_list *next; while (psf) { - next = psf->sf_next; - kfree(psf); + next = rcu_dereference_protected(psf->sf_next, 1); + kfree_rcu(psf, rcu); psf = next; } } @@ -349,7 +368,7 @@ igmp_scount(struct ip_mc_list *pmc, int type, int gdeleted, int sdeleted) struct ip_sf_list *psf; int scount = 0; - for (psf = pmc->sources; psf; psf = psf->sf_next) { + for_each_psf_mclock(pmc, psf) { if (!is_in(pmc, psf, type, gdeleted, sdeleted)) continue; scount++; @@ -494,7 +513,8 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc, struct net *net = dev_net(dev); struct igmpv3_report *pih; struct igmpv3_grec *pgr = NULL; - struct ip_sf_list *psf, *psf_next, *psf_prev, **psf_list; + struct ip_sf_list *psf, *psf_next, *psf_prev; + struct ip_sf_list __rcu **psf_list; int scount, stotal, first, isquery, truncate; unsigned int mtu; @@ -517,7 +537,7 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc, psf_list = sdeleted ? &pmc->tomb : &pmc->sources; - if (!*psf_list) + if (!rcu_access_pointer(*psf_list)) goto empty_source; pih = skb ? igmpv3_report_hdr(skb) : NULL; @@ -533,10 +553,12 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc, } first = 1; psf_prev = NULL; - for (psf = *psf_list; psf; psf = psf_next) { + for (psf = pmc_dereference(*psf_list, pmc); + psf; + psf = psf_next) { __be32 *psrc; - psf_next = psf->sf_next; + psf_next = pmc_dereference(psf->sf_next, pmc); if (!is_in(pmc, psf, type, gdeleted, sdeleted)) { psf_prev = psf; @@ -583,10 +605,12 @@ decrease_sf_crcount: psf->sf_crcount--; if ((sdeleted || gdeleted) && psf->sf_crcount == 0) { if (psf_prev) - psf_prev->sf_next = psf->sf_next; + rcu_assign_pointer(psf_prev->sf_next, + psf_next); else - *psf_list = psf->sf_next; - kfree(psf); + rcu_assign_pointer(*psf_list, + psf_next); + kfree_rcu(psf, rcu); continue; } } @@ -655,28 +679,29 @@ static int igmpv3_send_report(struct in_device *in_dev, struct ip_mc_list *pmc) /* * remove zero-count source records from a source filter list */ -static void igmpv3_clear_zeros(struct ip_sf_list **ppsf) +static void igmpv3_clear_zeros(struct ip_sf_list __rcu **ppsf) { struct ip_sf_list *psf_prev, *psf_next, *psf; psf_prev = NULL; - for (psf = *ppsf; psf; psf = psf_next) { - psf_next = psf->sf_next; + for (psf = rcu_dereference_protected(*ppsf, 1); psf; psf = psf_next) { + psf_next = rcu_dereference_protected(psf->sf_next, 1); if (psf->sf_crcount == 0) { if (psf_prev) - psf_prev->sf_next = psf->sf_next; + rcu_assign_pointer(psf_prev->sf_next, psf_next); else - *ppsf = psf->sf_next; - kfree(psf); - } else + rcu_assign_pointer(*ppsf, psf_next); + kfree_rcu(psf, rcu); + } else { psf_prev = psf; + } } } static void kfree_pmc(struct ip_mc_list *pmc) { - ip_sf_list_clear_all(pmc->sources); - ip_sf_list_clear_all(pmc->tomb); + ip_sf_list_clear_all(rcu_dereference_protected(pmc->sources, 1)); + ip_sf_list_clear_all(rcu_dereference_protected(pmc->tomb, 1)); kfree(pmc); } @@ -710,7 +735,8 @@ static void igmpv3_send_cr(struct in_device *in_dev) igmpv3_clear_zeros(&pmc->sources); } } - if (pmc->crcount == 0 && !pmc->tomb && !pmc->sources) { + if (pmc->crcount == 0 && !rcu_access_pointer(pmc->tomb) && + !rcu_access_pointer(pmc->sources)) { if (pmc_prev) pmc_prev->next = pmc_next; else @@ -896,7 +922,7 @@ static int igmp_xmarksources(struct ip_mc_list *pmc, int nsrcs, __be32 *srcs) int i, scount; scount = 0; - for (psf = pmc->sources; psf; psf = psf->sf_next) { + for_each_psf_mclock(pmc, psf) { if (scount == nsrcs) break; for (i = 0; i < nsrcs; i++) { @@ -927,7 +953,7 @@ static int igmp_marksources(struct ip_mc_list *pmc, int nsrcs, __be32 *srcs) /* mark INCLUDE-mode sources */ scount = 0; - for (psf = pmc->sources; psf; psf = psf->sf_next) { + for_each_psf_mclock(pmc, psf) { if (scount == nsrcs) break; for (i = 0; i < nsrcs; i++) @@ -1228,11 +1254,12 @@ static void igmpv3_add_delrec(struct in_device *in_dev, struct ip_mc_list *im, if (pmc->sfmode == MCAST_INCLUDE) { struct ip_sf_list *psf; + for_each_psf_mclock(im, psf) + psf->sf_crcount = pmc->crcount; pmc->tomb = im->tomb; pmc->sources = im->sources; - im->tomb = im->sources = NULL; - for (psf = pmc->sources; psf; psf = psf->sf_next) - psf->sf_crcount = pmc->crcount; + RCU_INIT_POINTER(im->tomb, NULL); + RCU_INIT_POINTER(im->sources, NULL); } spin_unlock_bh(&im->lock); @@ -1271,9 +1298,18 @@ static void igmpv3_del_delrec(struct in_device *in_dev, struct ip_mc_list *im) if (pmc) { im->interface = pmc->interface; if (im->sfmode == MCAST_INCLUDE) { - swap(im->tomb, pmc->tomb); - swap(im->sources, pmc->sources); - for (psf = im->sources; psf; psf = psf->sf_next) + struct ip_sf_list *sources, *tomb; + + tomb = rcu_replace_pointer(im->tomb, + rcu_dereference_protected(pmc->tomb, 1), + lockdep_is_held(&im->lock)); + rcu_assign_pointer(pmc->tomb, tomb); + + sources = rcu_replace_pointer(im->sources, + rcu_dereference_protected(pmc->sources, 1), + lockdep_is_held(&im->lock)); + rcu_assign_pointer(pmc->sources, sources); + for_each_psf_mclock(im, psf) psf->sf_crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); } else { @@ -1310,8 +1346,8 @@ static void igmpv3_clear_delrec(struct in_device *in_dev) struct ip_sf_list *psf; spin_lock_bh(&pmc->lock); - psf = pmc->tomb; - pmc->tomb = NULL; + psf = pmc_dereference(pmc->tomb, pmc); + RCU_INIT_POINTER(pmc->tomb, NULL); spin_unlock_bh(&pmc->lock); ip_sf_list_clear_all(psf); } @@ -1988,7 +2024,7 @@ static int ip_mc_del1_src(struct ip_mc_list *pmc, int sfmode, int rv = 0; psf_prev = NULL; - for (psf = pmc->sources; psf; psf = psf->sf_next) { + for_each_psf_mclock(pmc, psf) { if (psf->sf_inaddr == *psfsrc) break; psf_prev = psf; @@ -1997,7 +2033,7 @@ static int ip_mc_del1_src(struct ip_mc_list *pmc, int sfmode, /* source filter not found, or count wrong => bug */ return -ESRCH; } - psf->sf_count[sfmode]--; + WRITE_ONCE(psf->sf_count[sfmode], psf->sf_count[sfmode] - 1); if (psf->sf_count[sfmode] == 0) { ip_rt_multicast_event(pmc->interface); } @@ -2009,19 +2045,28 @@ static int ip_mc_del1_src(struct ip_mc_list *pmc, int sfmode, /* no more filters for this source */ if (psf_prev) - psf_prev->sf_next = psf->sf_next; + rcu_assign_pointer(psf_prev->sf_next, + pmc_dereference(psf->sf_next, pmc)); else - pmc->sources = psf->sf_next; + rcu_assign_pointer(pmc->sources, + pmc_dereference(psf->sf_next, pmc)); #ifdef CONFIG_IP_MULTICAST if (psf->sf_oldin && !IGMP_V1_SEEN(in_dev) && !IGMP_V2_SEEN(in_dev)) { - psf->sf_crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); - psf->sf_next = pmc->tomb; - pmc->tomb = psf; - rv = 1; - } else + struct ip_sf_list *dpsf = kmalloc_obj(*dpsf, GFP_ATOMIC); + + if (dpsf) { + *dpsf = *psf; + dpsf->sf_crcount = in_dev->mr_qrv ?: + READ_ONCE(net->ipv4.sysctl_igmp_qrv); + rcu_assign_pointer(dpsf->sf_next, + pmc_dereference(pmc->tomb, pmc)); + rcu_assign_pointer(pmc->tomb, dpsf); + rv = 1; + } + } #endif - kfree(psf); + kfree_rcu(psf, rcu); } return rv; } @@ -2058,7 +2103,7 @@ static int ip_mc_del_src(struct in_device *in_dev, __be32 *pmca, int sfmode, err = -EINVAL; if (!pmc->sfcount[sfmode]) goto out_unlock; - pmc->sfcount[sfmode]--; + WRITE_ONCE(pmc->sfcount[sfmode], pmc->sfcount[sfmode] - 1); } err = 0; for (i = 0; i < sfcount; i++) { @@ -2081,7 +2126,7 @@ static int ip_mc_del_src(struct in_device *in_dev, __be32 *pmca, int sfmode, #ifdef CONFIG_IP_MULTICAST pmc->crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); WRITE_ONCE(in_dev->mr_ifc_count, pmc->crcount); - for (psf = pmc->sources; psf; psf = psf->sf_next) + for_each_psf_mclock(pmc, psf) psf->sf_crcount = 0; igmp_ifc_event(pmc->interface); } else if (sf_setstate(pmc) || changerec) { @@ -2102,7 +2147,7 @@ static int ip_mc_add1_src(struct ip_mc_list *pmc, int sfmode, struct ip_sf_list *psf, *psf_prev; psf_prev = NULL; - for (psf = pmc->sources; psf; psf = psf->sf_next) { + for_each_psf_mclock(pmc, psf) { if (psf->sf_inaddr == *psfsrc) break; psf_prev = psf; @@ -2112,12 +2157,12 @@ static int ip_mc_add1_src(struct ip_mc_list *pmc, int sfmode, if (!psf) return -ENOBUFS; psf->sf_inaddr = *psfsrc; - if (psf_prev) { - psf_prev->sf_next = psf; - } else - pmc->sources = psf; + if (psf_prev) + rcu_assign_pointer(psf_prev->sf_next, psf); + else + rcu_assign_pointer(pmc->sources, psf); } - psf->sf_count[sfmode]++; + WRITE_ONCE(psf->sf_count[sfmode], psf->sf_count[sfmode] + 1); if (psf->sf_count[sfmode] == 1) { ip_rt_multicast_event(pmc->interface); } @@ -2130,13 +2175,15 @@ static void sf_markstate(struct ip_mc_list *pmc) struct ip_sf_list *psf; int mca_xcount = pmc->sfcount[MCAST_EXCLUDE]; - for (psf = pmc->sources; psf; psf = psf->sf_next) + for_each_psf_mclock(pmc, psf) { if (pmc->sfcount[MCAST_EXCLUDE]) { psf->sf_oldin = mca_xcount == psf->sf_count[MCAST_EXCLUDE] && !psf->sf_count[MCAST_INCLUDE]; - } else + } else { psf->sf_oldin = psf->sf_count[MCAST_INCLUDE] != 0; + } + } } static int sf_setstate(struct ip_mc_list *pmc) @@ -2147,27 +2194,31 @@ static int sf_setstate(struct ip_mc_list *pmc) int new_in, rv; rv = 0; - for (psf = pmc->sources; psf; psf = psf->sf_next) { + for_each_psf_mclock(pmc, psf) { if (pmc->sfcount[MCAST_EXCLUDE]) { new_in = mca_xcount == psf->sf_count[MCAST_EXCLUDE] && !psf->sf_count[MCAST_INCLUDE]; - } else + } else { new_in = psf->sf_count[MCAST_INCLUDE] != 0; + } if (new_in) { if (!psf->sf_oldin) { struct ip_sf_list *prev = NULL; - for (dpsf = pmc->tomb; dpsf; dpsf = dpsf->sf_next) { + for_each_psf_tomb(pmc, dpsf) { if (dpsf->sf_inaddr == psf->sf_inaddr) break; prev = dpsf; } if (dpsf) { + struct ip_sf_list *dpsf_next; + + dpsf_next = pmc_dereference(dpsf->sf_next, pmc); if (prev) - prev->sf_next = dpsf->sf_next; + rcu_assign_pointer(prev->sf_next, dpsf_next); else - pmc->tomb = dpsf->sf_next; - kfree(dpsf); + rcu_assign_pointer(pmc->tomb, dpsf_next); + kfree_rcu(dpsf, rcu); } psf->sf_crcount = qrv; rv++; @@ -2179,17 +2230,19 @@ static int sf_setstate(struct ip_mc_list *pmc) * add or update "delete" records if an active filter * is now inactive */ - for (dpsf = pmc->tomb; dpsf; dpsf = dpsf->sf_next) + for_each_psf_tomb(pmc, dpsf) { if (dpsf->sf_inaddr == psf->sf_inaddr) break; + } if (!dpsf) { dpsf = kmalloc_obj(*dpsf, GFP_ATOMIC); if (!dpsf) continue; *dpsf = *psf; /* pmc->lock held by callers */ - dpsf->sf_next = pmc->tomb; - pmc->tomb = dpsf; + rcu_assign_pointer(dpsf->sf_next, + pmc_dereference(pmc->tomb, pmc)); + rcu_assign_pointer(pmc->tomb, dpsf); } dpsf->sf_crcount = qrv; rv++; @@ -2229,7 +2282,7 @@ static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode, #endif isexclude = pmc->sfmode == MCAST_EXCLUDE; if (!delta) - pmc->sfcount[sfmode]++; + WRITE_ONCE(pmc->sfcount[sfmode], pmc->sfcount[sfmode] + 1); err = 0; for (i = 0; i < sfcount; i++) { err = ip_mc_add1_src(pmc, sfmode, &psfsrc[i]); @@ -2240,7 +2293,7 @@ static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode, int j; if (!delta) - pmc->sfcount[sfmode]--; + WRITE_ONCE(pmc->sfcount[sfmode], pmc->sfcount[sfmode] - 1); for (j = 0; j < i; j++) (void) ip_mc_del1_src(pmc, sfmode, &psfsrc[j]); } else if (isexclude != (pmc->sfcount[MCAST_EXCLUDE] != 0)) { @@ -2260,7 +2313,7 @@ static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode, pmc->crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); WRITE_ONCE(in_dev->mr_ifc_count, pmc->crcount); - for (psf = pmc->sources; psf; psf = psf->sf_next) + for_each_psf_mclock(pmc, psf) psf->sf_crcount = 0; igmp_ifc_event(in_dev); } else if (sf_setstate(pmc)) { @@ -2276,13 +2329,13 @@ static void ip_mc_clear_src(struct ip_mc_list *pmc) struct ip_sf_list *tomb, *sources; spin_lock_bh(&pmc->lock); - tomb = pmc->tomb; - pmc->tomb = NULL; - sources = pmc->sources; - pmc->sources = NULL; + tomb = pmc_dereference(pmc->tomb, pmc); + RCU_INIT_POINTER(pmc->tomb, NULL); + sources = pmc_dereference(pmc->sources, pmc); + RCU_INIT_POINTER(pmc->sources, NULL); pmc->sfmode = MCAST_EXCLUDE; - pmc->sfcount[MCAST_INCLUDE] = 0; - pmc->sfcount[MCAST_EXCLUDE] = 1; + WRITE_ONCE(pmc->sfcount[MCAST_INCLUDE], 0); + WRITE_ONCE(pmc->sfcount[MCAST_EXCLUDE], 1); spin_unlock_bh(&pmc->lock); ip_sf_list_clear_all(tomb); @@ -2864,20 +2917,19 @@ int ip_check_mc_rcu(struct in_device *in_dev, __be32 mc_addr, __be32 src_addr, u rv = 1; } else if (im) { if (src_addr) { - spin_lock_bh(&im->lock); - for (psf = im->sources; psf; psf = psf->sf_next) { + for_each_psf_rcu(im, psf) { if (psf->sf_inaddr == src_addr) break; } if (psf) - rv = psf->sf_count[MCAST_INCLUDE] || - psf->sf_count[MCAST_EXCLUDE] != - im->sfcount[MCAST_EXCLUDE]; + rv = READ_ONCE(psf->sf_count[MCAST_INCLUDE]) || + READ_ONCE(psf->sf_count[MCAST_EXCLUDE]) != + READ_ONCE(im->sfcount[MCAST_EXCLUDE]); else - rv = im->sfcount[MCAST_EXCLUDE] != 0; - spin_unlock_bh(&im->lock); - } else + rv = READ_ONCE(im->sfcount[MCAST_EXCLUDE]) != 0; + } else { rv = 1; /* unspecified source; tentatively allow */ + } } return rv; } @@ -3041,7 +3093,7 @@ static inline struct ip_sf_list *igmp_mcf_get_first(struct seq_file *seq) im = rcu_dereference(idev->mc_list); if (likely(im)) { spin_lock_bh(&im->lock); - psf = im->sources; + psf = pmc_dereference(im->sources, im); if (likely(psf)) { state->im = im; state->idev = idev; @@ -3057,7 +3109,7 @@ static struct ip_sf_list *igmp_mcf_get_next(struct seq_file *seq, struct ip_sf_l { struct igmp_mcf_iter_state *state = igmp_mcf_seq_private(seq); - psf = psf->sf_next; + psf = pmc_dereference(psf->sf_next, state->im); while (!psf) { spin_unlock_bh(&state->im->lock); state->im = state->im->next; @@ -3073,7 +3125,7 @@ static struct ip_sf_list *igmp_mcf_get_next(struct seq_file *seq, struct ip_sf_l state->im = rcu_dereference(state->idev->mc_list); } spin_lock_bh(&state->im->lock); - psf = state->im->sources; + psf = pmc_dereference(state->im->sources, state->im); } out: return psf; diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index c17e57ec7d5cdb..b286ee429da8fa 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -235,6 +235,8 @@ void fqdir_pre_exit(struct fqdir *fqdir) rhashtable_walk_start(&hti); while ((fq = rhashtable_walk_next(&hti))) { + int refs = 0; + if (IS_ERR(fq)) { if (PTR_ERR(fq) != -EAGAIN) break; @@ -242,8 +244,12 @@ void fqdir_pre_exit(struct fqdir *fqdir) } spin_lock_bh(&fq->lock); if (!(fq->flags & INET_FRAG_COMPLETE)) + inet_frag_kill(fq, &refs); + + if (fq->flags & INET_FRAG_HASH_DEAD) inet_frag_queue_flush(fq, 0); spin_unlock_bh(&fq->lock); + inet_frag_putn(fq, refs); } rhashtable_walk_stop(&hti); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 74e095b6b7ca07..a24cc8ee11d3ea 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -1303,6 +1303,7 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork, cork->fragsize = ip_sk_use_pmtu(sk) ? dst4_mtu(&rt->dst) : READ_ONCE(rt->dst.dev->mtu); + cork->fragsize = min(cork->fragsize, IP_MAX_MTU); if (!inetdev_valid_mtu(cork->fragsize)) return -ENETUNREACH; diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index d3c677e9bff208..5168d546ea2fda 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -268,6 +268,9 @@ static int iptunnel_pmtud_build_icmp(struct sk_buff *skb, int mtu) eth_header(skb, skb->dev, ntohs(eh.h_proto), eh.h_source, eh.h_dest, 0); skb_reset_mac_header(skb); + if (skb_valid_dst(skb)) + skb_dst_drop(skb); + return skb->len; } @@ -371,6 +374,9 @@ static int iptunnel_pmtud_build_icmpv6(struct sk_buff *skb, int mtu) eth_header(skb, skb->dev, ntohs(eh.h_proto), eh.h_source, eh.h_dest, 0); skb_reset_mac_header(skb); + if (skb_valid_dst(skb)) + skb_dst_drop(skb); + return skb->len; } diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index e5f2b1c6150d2f..b9c544d48c4521 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -3376,7 +3376,8 @@ int __init ip_mr_init(void) { int err; - mrt_cachep = KMEM_CACHE(mfc_cache, SLAB_HWCACHE_ALIGN | SLAB_PANIC); + mrt_cachep = KMEM_CACHE(mfc_cache, + SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT); err = register_pernet_subsys(&ipmr_net_ops); if (err) diff --git a/net/ipv4/ipmr_base.c b/net/ipv4/ipmr_base.c index 867b24beded112..a0ec6d19a237ff 100644 --- a/net/ipv4/ipmr_base.c +++ b/net/ipv4/ipmr_base.c @@ -52,7 +52,7 @@ mr_table_alloc(struct net *net, u32 id, struct mr_table *mrt; int err; - mrt = kzalloc_obj(*mrt); + mrt = kzalloc_obj(*mrt, GFP_KERNEL_ACCOUNT); if (!mrt) return ERR_PTR(-ENOMEM); mrt->id = id; diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index 0f1e21a5c812e2..901c3531968282 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -2029,7 +2029,7 @@ remove_nh_grp_entry(struct net *net, struct nh_grp_entry *nhge, { struct nh_grp_entry *nhges, *new_nhges; struct nexthop *nhp = nhge->nh_parent; - struct netlink_ext_ack extack; + struct netlink_ext_ack extack = {}; struct nexthop *nh = nhge->nh; struct nh_group *nhg, *newg; int i, j, err; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 10f58281be17be..47a34a993972af 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3181,8 +3181,7 @@ void __tcp_close(struct sock *sk, long timeout) /* Unread data was tossed, zap the connection. */ NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONCLOSE); tcp_set_state(sk, TCP_CLOSE); - tcp_send_active_reset(sk, sk->sk_allocation, - SK_RST_REASON_TCP_ABORT_ON_CLOSE); + tcp_send_active_reset(sk, SK_RST_REASON_TCP_ABORT_ON_CLOSE); } else if (sock_flag(sk, SOCK_LINGER) && !sk->sk_lingertime) { /* Check zero linger _after_ checking for unread data. */ sk->sk_prot->disconnect(sk, 0); @@ -3256,7 +3255,7 @@ adjudge_to_death: struct tcp_sock *tp = tcp_sk(sk); if (READ_ONCE(tp->linger2) < 0) { tcp_set_state(sk, TCP_CLOSE); - tcp_send_active_reset(sk, GFP_ATOMIC, + tcp_send_active_reset(sk, SK_RST_REASON_TCP_ABORT_ON_LINGER); __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONLINGER); @@ -3275,7 +3274,7 @@ adjudge_to_death: if (sk->sk_state != TCP_CLOSE) { if (tcp_check_oom(sk, 0)) { tcp_set_state(sk, TCP_CLOSE); - tcp_send_active_reset(sk, GFP_ATOMIC, + tcp_send_active_reset(sk, SK_RST_REASON_TCP_ABORT_ON_MEMORY); __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONMEMORY); @@ -3376,14 +3375,14 @@ int tcp_disconnect(struct sock *sk, int flags) } else if (unlikely(tp->repair)) { WRITE_ONCE(sk->sk_err, ECONNABORTED); } else if (tcp_need_reset(old_state)) { - tcp_send_active_reset(sk, gfp_any(), SK_RST_REASON_TCP_STATE); + tcp_send_active_reset(sk, SK_RST_REASON_TCP_STATE); WRITE_ONCE(sk->sk_err, ECONNRESET); } else if (tp->snd_nxt != tp->write_seq && (1 << old_state) & (TCPF_CLOSING | TCPF_LAST_ACK)) { /* The last check adjusts for discrepancy of Linux wrt. RFC * states */ - tcp_send_active_reset(sk, gfp_any(), + tcp_send_active_reset(sk, SK_RST_REASON_TCP_DISCONNECT_WITH_DATA); WRITE_ONCE(sk->sk_err, ECONNRESET); } else if (old_state == TCP_SYN_SENT) @@ -5146,8 +5145,7 @@ int tcp_abort(struct sock *sk, int err) bh_lock_sock(sk); if (tcp_need_reset(sk->sk_state)) - tcp_send_active_reset(sk, GFP_ATOMIC, - SK_RST_REASON_TCP_STATE); + tcp_send_active_reset(sk, SK_RST_REASON_TCP_STATE); tcp_done_with_error(sk, err); bh_unlock_sock(sk); diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c index 3b1fdcd3cb29b3..e74d99ca9face6 100644 --- a/net/ipv4/tcp_offload.c +++ b/net/ipv4/tcp_offload.c @@ -332,6 +332,7 @@ struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb, flush |= skb->ip_summed != p->ip_summed; flush |= skb->csum_level != p->csum_level; flush |= NAPI_GRO_CB(p)->count >= 64; + flush |= NAPI_GRO_CB(p)->is_flist != NAPI_GRO_CB(skb)->is_flist; skb_set_network_header(skb, skb_gro_receive_network_offset(skb)); if (flush || skb_gro_receive_list(p, skb)) @@ -395,12 +396,20 @@ static void tcp4_check_fraglist_gro(struct list_head *head, struct sk_buff *skb, struct net *net; int iif, sdif; - if (likely(!(skb->dev->features & NETIF_F_GRO_FRAGLIST))) - return; - p = tcp_gro_lookup(head, th); if (p) { - NAPI_GRO_CB(skb)->is_flist = NAPI_GRO_CB(p)->is_flist; + /* flist GRO applies to consecutive non-GSO skbs */ + if (!skb_is_gso(skb) || !NAPI_GRO_CB(p)->is_flist) { + NAPI_GRO_CB(skb)->is_flist = NAPI_GRO_CB(p)->is_flist; + return; + } + + /* Fall back to the regular GRO path */ + if (NAPI_GRO_CB(p)->count == 1) + NAPI_GRO_CB(p)->is_flist = 0; + + NAPI_GRO_CB(skb)->is_flist = 0; + return; } @@ -410,7 +419,7 @@ static void tcp4_check_fraglist_gro(struct list_head *head, struct sk_buff *skb, sk = __inet_lookup_established(net, iph->saddr, th->source, iph->daddr, ntohs(th->dest), iif, sdif); - NAPI_GRO_CB(skb)->is_flist = !sk; + NAPI_GRO_CB(skb)->is_flist = !sk && !skb_is_gso(skb); if (sk) sock_gen_put(sk); } @@ -430,7 +439,8 @@ struct sk_buff *tcp4_gro_receive(struct list_head *head, struct sk_buff *skb) if (!th) goto flush; - tcp4_check_fraglist_gro(head, skb, th); + if (unlikely(skb->dev->features & NETIF_F_GRO_FRAGLIST)) + tcp4_check_fraglist_gro(head, skb, th); return tcp_gro_receive(head, skb, th); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 8d243e91761a92..f72a6b1fe749b1 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -3849,9 +3849,9 @@ void tcp_send_fin(struct sock *sk) * was unread data in the receive queue. This behavior is recommended * by RFC 2525, section 2.17. -DaveM */ -void tcp_send_active_reset(struct sock *sk, gfp_t priority, - enum sk_rst_reason reason) +void tcp_send_active_reset(struct sock *sk, enum sk_rst_reason reason) { + gfp_t priority = sk_gfp_mask(sk, GFP_ATOMIC | __GFP_NOWARN); struct sk_buff *skb; TCP_INC_STATS(sock_net(sk), TCP_MIB_OUTRSTS); diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 4df1c9745c5d57..95296b1cf0ca21 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -126,7 +126,7 @@ static int tcp_out_of_resources(struct sock *sk, bool do_reset) (!tp->snd_wnd && !tp->packets_out)) do_reset = true; if (do_reset) - tcp_send_active_reset(sk, GFP_ATOMIC, + tcp_send_active_reset(sk, SK_RST_REASON_TCP_ABORT_ON_MEMORY); tcp_done(sk); __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONMEMORY); @@ -809,7 +809,7 @@ static void tcp_keepalive_timer(struct timer_list *t) goto out; } } - tcp_send_active_reset(sk, GFP_ATOMIC, SK_RST_REASON_TCP_STATE); + tcp_send_active_reset(sk, SK_RST_REASON_TCP_STATE); goto death; } @@ -836,7 +836,7 @@ static void tcp_keepalive_timer(struct timer_list *t) icsk->icsk_probes_out > 0) || (user_timeout == 0 && icsk->icsk_probes_out >= keepalive_probes(tp))) { - tcp_send_active_reset(sk, GFP_ATOMIC, + tcp_send_active_reset(sk, SK_RST_REASON_TCP_KEEPALIVE_TIMEOUT); tcp_write_err(sk); goto out; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 70f6cbd4ef73bf..45e96b72198960 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -2164,10 +2164,10 @@ int __udp_disconnect(struct sock *sk, int flags) */ sk->sk_state = TCP_CLOSE; - inet->inet_daddr = 0; + WRITE_ONCE(inet->inet_daddr, 0); inet->inet_dport = 0; sock_rps_reset_rxhash(sk); - sk->sk_bound_dev_if = 0; + WRITE_ONCE(sk->sk_bound_dev_if, 0); if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) { inet_reset_saddr(sk); if (sk->sk_prot->rehash && diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index 51941ad656a36e..09a4552f7f08aa 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -445,7 +445,7 @@ looped_back: hdr->segments_left--; addr = hdr->segments + hdr->segments_left; - skb_push(skb, sizeof(struct ipv6hdr)); + skb_push(skb, -skb_network_offset(skb)); if (skb->ip_summed == CHECKSUM_COMPLETE) seg6_update_csum(skb); @@ -469,7 +469,7 @@ looped_back: } ipv6_hdr(skb)->hop_limit--; - skb_pull(skb, sizeof(struct ipv6hdr)); + skb_pull(skb, skb_transport_offset(skb)); goto looped_back; } diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index e9fc692d4f3b22..7c5daea3f0963f 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -85,7 +85,7 @@ static void fib6_walker_link(struct net *net, struct fib6_walker *w) static void fib6_walker_unlink(struct net *net, struct fib6_walker *w) { write_lock_bh(&net->ipv6.fib6_walker_lock); - list_del(&w->lh); + list_del_init(&w->lh); write_unlock_bh(&net->ipv6.fib6_walker_lock); } @@ -2758,7 +2758,7 @@ static void *ipv6_route_seq_start(struct seq_file *seq, loff_t *pos) static bool ipv6_route_iter_active(struct ipv6_route_iter *iter) { struct fib6_walker *w = &iter->w; - return w->node && !(w->state == FWS_U && w->node == w->root); + return w->node && !list_empty(&w->lh); } static void ipv6_route_native_seq_stop(struct seq_file *seq, void *v) diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index 1ab5ad0dcf24fd..006585dc8b5c61 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -461,6 +461,21 @@ done: return NULL; } +static bool fl_sock_at_lease_limit(const struct sock *sk) +{ + const struct ipv6_fl_socklist *sfl; + int count = 0; + + rcu_read_lock(); + for_each_sk_fl_rcu(sk, sfl) { + if (++count >= FL_MAX_PER_SOCK) + break; + } + rcu_read_unlock(); + + return count >= FL_MAX_PER_SOCK; +} + static int mem_check(struct sock *sk) { const int unpriv_total_limit = FL_MAX_SIZE - (FL_MAX_SIZE / 4); @@ -679,6 +694,10 @@ recheck: err = -ENOMEM; if (!sfl1) goto release; + err = -ENOBUFS; + if (fl_sock_at_lease_limit(sk) && + !capable(CAP_NET_ADMIN)) + goto release; if (fl->linger > fl1->linger) fl1->linger = fl->linger; if ((long)(fl->expires - fl1->expires) > 0) diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 200d0ba1a40e71..678678fcb5da39 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -878,6 +878,7 @@ static int ip6gre_xmit_other(struct sk_buff *skb, struct net_device *dev) static netdev_tx_t ip6gre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) { + struct ip_tunnel_info *tun_info = NULL; struct ip6_tnl *t = netdev_priv(dev); __be16 payload_protocol; int ret; @@ -888,6 +889,9 @@ static netdev_tx_t ip6gre_tunnel_xmit(struct sk_buff *skb, if (!ip6_tnl_xmit_ctl(t, &t->parms.laddr, &t->parms.raddr)) goto tx_err; + if (t->parms.collect_md) + tun_info = skb_tunnel_info_txcheck(skb); + payload_protocol = skb_protocol(skb, true); switch (payload_protocol) { case htons(ETH_P_IP): @@ -907,7 +911,7 @@ static netdev_tx_t ip6gre_tunnel_xmit(struct sk_buff *skb, return NETDEV_TX_OK; tx_err: - if (!t->parms.collect_md || !IS_ERR(skb_tunnel_info_txcheck(skb))) + if (!IS_ERR(tun_info)) DEV_STATS_INC(dev, tx_errors); DEV_STATS_INC(dev, tx_dropped); kfree_skb(skb); diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 8fc4766c8da906..5509650589915c 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1432,6 +1432,8 @@ static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork, if (frag_size && frag_size < mtu) mtu = frag_size; + if (sk_is_udp(sk)) + mtu = min(mtu, IP6_MAX_MTU); cork->base.fragsize = mtu; cork->base.gso_size = ipc6->gso_size; cork->base.tx_flags = 0; diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 3f2ed9b77deb51..9d8116b5edb173 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -1427,7 +1427,7 @@ int __init ip6_mr_init(void) { int err; - mrt_cachep = KMEM_CACHE(mfc6_cache, SLAB_HWCACHE_ALIGN); + mrt_cachep = KMEM_CACHE(mfc6_cache, SLAB_HWCACHE_ALIGN | SLAB_ACCOUNT); if (!mrt_cachep) return -ENOMEM; diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 4d2b9377ba2de5..fad53a5cdfffba 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -240,7 +240,8 @@ static int __ipv6_sock_mc_join(struct sock *sk, int ifindex, return err; } - mc_lst->next = np->ipv6_mc_list; + rcu_assign_pointer(mc_lst->next, + sock_dereference(np->ipv6_mc_list, sk)); rcu_assign_pointer(np->ipv6_mc_list, mc_lst); return 0; @@ -300,7 +301,8 @@ int ipv6_sock_mc_drop(struct sock *sk, int ifindex, const struct in6_addr *addr) lnk = &mc_lst->next) { if ((ifindex == 0 || mc_lst->ifindex == ifindex) && ipv6_addr_equal(&mc_lst->addr, addr)) { - *lnk = mc_lst->next; + rcu_assign_pointer(*lnk, + sock_dereference(mc_lst->next, sk)); __ipv6_sock_mc_drop(sk, mc_lst); return 0; } @@ -333,7 +335,8 @@ void __ipv6_sock_mc_close(struct sock *sk) struct ipv6_mc_socklist *mc_lst; while ((mc_lst = sock_dereference(np->ipv6_mc_list, sk)) != NULL) { - np->ipv6_mc_list = mc_lst->next; + rcu_assign_pointer(np->ipv6_mc_list, + sock_dereference(mc_lst->next, sk)); __ipv6_sock_mc_drop(sk, mc_lst); } } @@ -355,12 +358,12 @@ int ip6_mc_source(int add, int omode, struct sock *sk, { struct ipv6_pinfo *inet6 = inet6_sk(sk); struct in6_addr *source, *group; + struct ip6_sf_socklist *newpsl, *psl; struct net *net = sock_net(sk); struct ipv6_mc_socklist *pmc; - struct ip6_sf_socklist *psl; struct inet6_dev *idev; int leavegroup = 0; - int i, j, rv; + int i, j; int err; source = &((struct sockaddr_in6 *)&pgsr->gsr_source)->sin6_addr; @@ -409,13 +412,11 @@ int ip6_mc_source(int add, int omode, struct sock *sk, if (!add) { if (!psl) goto done; /* err = -EADDRNOTAVAIL */ - rv = !0; for (i = 0; i < psl->sl_count; i++) { - rv = !ipv6_addr_equal(&psl->sl_addr[i], source); - if (rv == 0) + if (ipv6_addr_equal(&psl->sl_addr[i], source)) break; } - if (rv) /* source not found */ + if (i == psl->sl_count) /* source not found */ goto done; /* err = -EADDRNOTAVAIL */ /* special case - (INCLUDE, empty) == LEAVE_GROUP */ @@ -424,58 +425,74 @@ int ip6_mc_source(int add, int omode, struct sock *sk, goto done; } + atomic_sub(struct_size(psl, sl_addr, psl->sl_max), + &sk->sk_omem_alloc); + + if (psl->sl_count == 1) { + newpsl = NULL; + } else { + newpsl = sock_kmalloc(sk, struct_size(newpsl, sl_addr, + psl->sl_count - 1), + GFP_KERNEL); + if (!newpsl) { + atomic_add(struct_size(psl, sl_addr, psl->sl_max), + &sk->sk_omem_alloc); + err = -ENOBUFS; + goto done; + } + newpsl->sl_max = psl->sl_count - 1; + newpsl->sl_count = psl->sl_count - 1; + for (j = 0; j < i; j++) + newpsl->sl_addr[j] = psl->sl_addr[j]; + for (j = i + 1; j < psl->sl_count; j++) + newpsl->sl_addr[j - 1] = psl->sl_addr[j]; + } + /* update the interface filter */ ip6_mc_del_src(idev, group, omode, 1, source, 1); - for (j = i+1; j < psl->sl_count; j++) - psl->sl_addr[j-1] = psl->sl_addr[j]; - psl->sl_count--; + rcu_assign_pointer(pmc->sflist, newpsl); + kfree_rcu(psl, rcu); err = 0; goto done; } /* else, add a new source to the filter */ - if (psl && psl->sl_count >= sysctl_mld_max_msf) { + if (psl && psl->sl_count >= READ_ONCE(sysctl_mld_max_msf)) { err = -ENOBUFS; goto done; } - if (!psl || psl->sl_count == psl->sl_max) { - struct ip6_sf_socklist *newpsl; - int count = IP6_SFBLOCK; - - if (psl) - count += psl->sl_max; - newpsl = sock_kmalloc(sk, struct_size(newpsl, sl_addr, count), - GFP_KERNEL); - if (!newpsl) { - err = -ENOBUFS; - goto done; - } - newpsl->sl_max = count; - newpsl->sl_count = count - IP6_SFBLOCK; - if (psl) { - for (i = 0; i < psl->sl_count; i++) - newpsl->sl_addr[i] = psl->sl_addr[i]; - atomic_sub(struct_size(psl, sl_addr, psl->sl_max), - &sk->sk_omem_alloc); + if (psl) { + for (i = 0; i < psl->sl_count; i++) { + if (ipv6_addr_equal(&psl->sl_addr[i], source)) + goto done; /* err = -EADDRNOTAVAIL */ } - rcu_assign_pointer(pmc->sflist, newpsl); - kfree_rcu(psl, rcu); - psl = newpsl; } - rv = 1; /* > 0 for insert logic below if sl_count is 0 */ - for (i = 0; i < psl->sl_count; i++) { - rv = !ipv6_addr_equal(&psl->sl_addr[i], source); - if (rv == 0) /* There is an error in the address. */ - goto done; + + i = psl ? psl->sl_count + 1 : 1; + newpsl = sock_kmalloc(sk, struct_size(newpsl, sl_addr, i), + GFP_KERNEL); + if (!newpsl) { + err = -ENOBUFS; + goto done; } - for (j = psl->sl_count-1; j >= i; j--) - psl->sl_addr[j+1] = psl->sl_addr[j]; - psl->sl_addr[i] = *source; - psl->sl_count++; - err = 0; + newpsl->sl_max = i; + newpsl->sl_count = i; + if (psl) { + for (j = 0; j < psl->sl_count; j++) + newpsl->sl_addr[j] = psl->sl_addr[j]; + } + newpsl->sl_addr[i - 1] = *source; + /* update the interface list */ ip6_mc_add_src(idev, group, omode, 1, source, 1); + + if (psl) + atomic_sub(struct_size(psl, sl_addr, psl->sl_max), + &sk->sk_omem_alloc); + rcu_assign_pointer(pmc->sflist, newpsl); + kfree_rcu(psl, rcu); + err = 0; done: mutex_unlock(&idev->mc_lock); in6_dev_put(idev); @@ -784,9 +801,11 @@ static void mld_del_delrec(struct inet6_dev *idev, struct ifmcaddr6 *im) if (!pmc) return; if (pmc_prev) - rcu_assign_pointer(pmc_prev->next, pmc->next); + rcu_assign_pointer(pmc_prev->next, + mc_dereference(pmc->next, idev)); else - rcu_assign_pointer(idev->mc_tomb, pmc->next); + rcu_assign_pointer(idev->mc_tomb, + mc_dereference(pmc->next, idev)); im->idev = pmc->idev; if (im->mca_sfmode == MCAST_INCLUDE) { @@ -965,7 +984,7 @@ static int __ipv6_dev_mc_inc(struct net_device *dev, return -ENOMEM; } - rcu_assign_pointer(mc->next, idev->mc_list); + rcu_assign_pointer(mc->next, mc_dereference(idev->mc_list, idev)); rcu_assign_pointer(idev->mc_list, mc); mld_del_delrec(idev, mc); @@ -999,7 +1018,8 @@ int __ipv6_dev_mc_dec(struct inet6_dev *idev, const struct in6_addr *addr) WRITE_ONCE(ma->mca_users, new_users); if (new_users == 0) { - *map = ma->next; + rcu_assign_pointer(*map, + mc_dereference(ma->next, idev)); igmp6_group_dropped(ma); inet6_ifmcaddr_notify(idev->dev, ma, @@ -2350,14 +2370,18 @@ static int ip6_mc_del1_src(struct ifmcaddr6 *pmc, int sfmode, if (psf->sf_oldin && !(pmc->mca_flags & MAF_NOREPORT) && !mld_in_v1_mode(idev)) { - psf->sf_crcount = idev->mc_qrv; - rcu_assign_pointer(psf->sf_next, - mc_dereference(pmc->mca_tomb, idev)); - rcu_assign_pointer(pmc->mca_tomb, psf); - rv = 1; - } else { - kfree_rcu(psf, rcu); + struct ip6_sf_list *dpsf = kmalloc_obj(*dpsf); + + if (dpsf) { + *dpsf = *psf; + dpsf->sf_crcount = idev->mc_qrv; + rcu_assign_pointer(dpsf->sf_next, + mc_dereference(pmc->mca_tomb, idev)); + rcu_assign_pointer(pmc->mca_tomb, dpsf); + rv = 1; + } } + kfree_rcu(psf, rcu); } return rv; } @@ -2620,7 +2644,7 @@ static void ip6_mc_clear_src(struct ifmcaddr6 *pmc) static void igmp6_join_group(struct ifmcaddr6 *ma) { - unsigned long delay; + unsigned long delay, interval; mc_assert_locked(ma->idev); @@ -2629,13 +2653,17 @@ static void igmp6_join_group(struct ifmcaddr6 *ma) igmp6_send(&ma->mca_addr, ma->idev->dev, ICMPV6_MGM_REPORT); - delay = get_random_u32_below(unsolicited_report_interval(ma->idev)); + interval = unsolicited_report_interval(ma->idev); + delay = interval; if (cancel_delayed_work(&ma->mca_work)) { refcount_dec(&ma->mca_refcnt); delay = ma->mca_work.timer.expires - jiffies; } + if (delay >= interval) + delay = get_random_u32_below(interval); + if (!mod_delayed_work(mld_wq, &ma->mca_work, delay)) refcount_inc(&ma->mca_refcnt); WRITE_ONCE(ma->mca_flags, ma->mca_flags | @@ -3000,7 +3028,7 @@ static int igmp6_mc_seq_show(struct seq_file *seq, void *v) struct ifmcaddr6 *im = (struct ifmcaddr6 *)v; struct igmp6_mc_iter_state *state = igmp6_mc_seq_private(seq); unsigned int mca_flags = READ_ONCE(im->mca_flags); - unsigned long expires = READ_ONCE(im->mca_work.timer.expires); + long delta = READ_ONCE(im->mca_work.timer.expires) - jiffies; seq_printf(seq, "%-4d %-15s %pi6 %5d %08X %ld\n", @@ -3008,7 +3036,7 @@ static int igmp6_mc_seq_show(struct seq_file *seq, void *v) &im->mca_addr, READ_ONCE(im->mca_users), mca_flags, (mca_flags & MAF_TIMER_RUNNING) ? - jiffies_to_clock_t(expires - jiffies) : 0); + jiffies_delta_to_clock_t(delta) : 0); return 0; } diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index f42fb96ef64b68..313c4aac377aa2 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -647,6 +647,11 @@ check_entry_size_and_hooks(struct ip6t_entry *e, /* Clear counters and comefrom */ e->counters = ((struct xt_counters) { 0, 0 }); e->comefrom = 0; + + /* set F_PROTO, else ip6_packet_match won't do the right thing. */ + if (e->ipv6.proto) + e->ipv6.flags |= IP6T_F_PROTO; + return 0; } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index dc9060af5bb1e8..ee707e48f4efae 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -4010,6 +4010,7 @@ static int __ip6_del_rt_siblings(struct fib6_info *rt, struct fib6_config *cfg) struct net *net = info->nl_net; struct sk_buff *skb = NULL; struct fib6_table *table; + struct fib6_node *fn; int err = -ENOENT; if (rt == net->ipv6.fib6_null_entry) @@ -4017,9 +4018,13 @@ static int __ip6_del_rt_siblings(struct fib6_info *rt, struct fib6_config *cfg) table = rt->fib6_table; spin_lock_bh(&table->tb6_lock); + fn = rcu_dereference_protected(rt->fib6_node, + lockdep_is_held(&table->tb6_lock)); + if (!fn) + goto out_unlock; + if (rt->fib6_nsiblings && cfg->fc_delete_all_nh) { struct fib6_info *sibling, *next_sibling; - struct fib6_node *fn; /* prefer to send a single notification with all hops */ skb = nlmsg_new(rt6_nlmsg_size(rt), GFP_ATOMIC); @@ -4041,8 +4046,6 @@ static int __ip6_del_rt_siblings(struct fib6_info *rt, struct fib6_config *cfg) * and emit a replace or delete notification, respectively. */ info->skip_notify_kernel = 1; - fn = rcu_dereference_protected(rt->fib6_node, - lockdep_is_held(&table->tb6_lock)); if (rcu_access_pointer(fn->leaf) == rt) { struct fib6_info *last_sibling, *replace_rt; diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c index f2a659cd6183c7..eec3778855eb89 100644 --- a/net/ipv6/tcpv6_offload.c +++ b/net/ipv6/tcpv6_offload.c @@ -26,7 +26,18 @@ static void tcp6_check_fraglist_gro(struct list_head *head, struct sk_buff *skb, p = tcp_gro_lookup(head, th); if (p) { - NAPI_GRO_CB(skb)->is_flist = NAPI_GRO_CB(p)->is_flist; + /* flist GRO applies to consecutive non-GSO skbs */ + if (!skb_is_gso(skb) || !NAPI_GRO_CB(p)->is_flist) { + NAPI_GRO_CB(skb)->is_flist = NAPI_GRO_CB(p)->is_flist; + return; + } + + /* Fall back to the regular GRO path */ + if (NAPI_GRO_CB(p)->count == 1) + NAPI_GRO_CB(p)->is_flist = 0; + + NAPI_GRO_CB(skb)->is_flist = 0; + return; } @@ -36,7 +47,7 @@ static void tcp6_check_fraglist_gro(struct list_head *head, struct sk_buff *skb, sk = __inet6_lookup_established(net, &hdr->saddr, th->source, &hdr->daddr, ntohs(th->dest), iif, sdif); - NAPI_GRO_CB(skb)->is_flist = !sk; + NAPI_GRO_CB(skb)->is_flist = !sk && !skb_is_gso(skb); if (sk) sock_gen_put(sk); #endif /* IS_ENABLED(CONFIG_IPV6) */ diff --git a/net/mac802154/ieee802154_i.h b/net/mac802154/ieee802154_i.h index 8f2bff268392b0..279ff4e9b11eac 100644 --- a/net/mac802154/ieee802154_i.h +++ b/net/mac802154/ieee802154_i.h @@ -74,6 +74,10 @@ struct ieee802154_local { struct work_struct rx_beacon_work; struct list_head rx_mac_cmd_list; struct work_struct rx_mac_cmd_work; + /* Serializes rx_beacon_list and rx_mac_cmd_list against the RX + * softirq producer, the mac_wq workers and the teardown flush. + */ + spinlock_t rx_lock; /* Association */ struct ieee802154_pan_device *assoc_dev; @@ -300,6 +304,10 @@ static inline bool mac802154_is_beaconing(struct ieee802154_local *local) } void mac802154_rx_mac_cmd_worker(struct work_struct *work); +void mac802154_flush_list(struct list_head *list, + struct ieee802154_sub_if_data *sdata); +void mac802154_flush_queued_pkts(struct ieee802154_local *local, + struct ieee802154_sub_if_data *sdata); int mac802154_perform_association(struct ieee802154_sub_if_data *sdata, struct ieee802154_pan_device *coord, diff --git a/net/mac802154/iface.c b/net/mac802154/iface.c index b823720630e726..31353795fa240a 100644 --- a/net/mac802154/iface.c +++ b/net/mac802154/iface.c @@ -694,6 +694,7 @@ void ieee802154_if_remove(struct ieee802154_sub_if_data *sdata) mutex_unlock(&sdata->local->iflist_mtx); synchronize_rcu(); + mac802154_flush_queued_pkts(sdata->local, sdata); unregister_netdevice(sdata->dev); } @@ -705,6 +706,11 @@ void ieee802154_remove_interfaces(struct ieee802154_local *local) list_for_each_entry_safe(sdata, tmp, &local->interfaces, list) { list_del_rcu(&sdata->list); + /* Best-effort: a frame the RX softirq queues for this sdata + * after the flush still pins the netdev, so the + * unregister_netdevice() below waits it out. + */ + mac802154_flush_queued_pkts(local, sdata); unregister_netdevice(sdata->dev); } mutex_unlock(&local->iflist_mtx); diff --git a/net/mac802154/main.c b/net/mac802154/main.c index ea1efef3572ae7..386c086c79d173 100644 --- a/net/mac802154/main.c +++ b/net/mac802154/main.c @@ -91,6 +91,7 @@ ieee802154_alloc_hw(size_t priv_data_len, const struct ieee802154_ops *ops) INIT_LIST_HEAD(&local->interfaces); INIT_LIST_HEAD(&local->rx_beacon_list); INIT_LIST_HEAD(&local->rx_mac_cmd_list); + spin_lock_init(&local->rx_lock); mutex_init(&local->iflist_mtx); tasklet_setup(&local->tasklet, ieee802154_tasklet_handler); diff --git a/net/mac802154/rx.c b/net/mac802154/rx.c index cd8f2a11920d0a..19b5382e85a84f 100644 --- a/net/mac802154/rx.c +++ b/net/mac802154/rx.c @@ -35,16 +35,23 @@ void mac802154_rx_beacon_worker(struct work_struct *work) container_of(work, struct ieee802154_local, rx_beacon_work); struct cfg802154_mac_pkt *mac_pkt; - mac_pkt = list_first_entry_or_null(&local->rx_beacon_list, - struct cfg802154_mac_pkt, node); - if (!mac_pkt) - return; + for (;;) { + spin_lock_bh(&local->rx_lock); + mac_pkt = list_first_entry_or_null(&local->rx_beacon_list, + struct cfg802154_mac_pkt, node); + if (mac_pkt) + list_del(&mac_pkt->node); + spin_unlock_bh(&local->rx_lock); + if (!mac_pkt) + break; - mac802154_process_beacon(local, mac_pkt->skb, mac_pkt->page, mac_pkt->channel); + mac802154_process_beacon(local, mac_pkt->skb, + mac_pkt->page, mac_pkt->channel); - list_del(&mac_pkt->node); - kfree_skb(mac_pkt->skb); - kfree(mac_pkt); + netdev_put(mac_pkt->sdata->dev, &mac_pkt->dev_tracker); + kfree_skb(mac_pkt->skb); + kfree(mac_pkt); + } } static bool mac802154_should_answer_beacon_req(struct ieee802154_local *local) @@ -68,22 +75,15 @@ static bool mac802154_should_answer_beacon_req(struct ieee802154_local *local) return interval == IEEE802154_ACTIVE_SCAN_DURATION; } -void mac802154_rx_mac_cmd_worker(struct work_struct *work) +static void mac802154_rx_mac_cmd(struct ieee802154_local *local, + struct cfg802154_mac_pkt *mac_pkt) { - struct ieee802154_local *local = - container_of(work, struct ieee802154_local, rx_mac_cmd_work); - struct cfg802154_mac_pkt *mac_pkt; u8 mac_cmd; int rc; - mac_pkt = list_first_entry_or_null(&local->rx_mac_cmd_list, - struct cfg802154_mac_pkt, node); - if (!mac_pkt) - return; - rc = ieee802154_get_mac_cmd(mac_pkt->skb, &mac_cmd); if (rc) - goto out; + return; switch (mac_cmd) { case IEEE802154_CMD_BEACON_REQ: @@ -121,11 +121,81 @@ void mac802154_rx_mac_cmd_worker(struct work_struct *work) default: break; } +} -out: - list_del(&mac_pkt->node); - kfree_skb(mac_pkt->skb); - kfree(mac_pkt); +void mac802154_rx_mac_cmd_worker(struct work_struct *work) +{ + struct ieee802154_local *local = + container_of(work, struct ieee802154_local, rx_mac_cmd_work); + struct cfg802154_mac_pkt *mac_pkt; + + for (;;) { + spin_lock_bh(&local->rx_lock); + mac_pkt = list_first_entry_or_null(&local->rx_mac_cmd_list, + struct cfg802154_mac_pkt, node); + if (mac_pkt) + list_del(&mac_pkt->node); + spin_unlock_bh(&local->rx_lock); + if (!mac_pkt) + break; + + /* A stopped interface cannot transmit; skipping avoids a + * needless association response (and the !netif_running() + * warning it would trip) during teardown. The beacon worker + * needs no such check as it never transmits. + */ + if (ieee802154_sdata_running(mac_pkt->sdata)) + mac802154_rx_mac_cmd(local, mac_pkt); + + netdev_put(mac_pkt->sdata->dev, &mac_pkt->dev_tracker); + kfree_skb(mac_pkt->skb); + kfree(mac_pkt); + } +} + +/** + * mac802154_flush_list - free queued RX frames on @list + * @list: rx_beacon_list or rx_mac_cmd_list + * @sdata: only free frames received on this interface, or %NULL for all + * + * Each frame pins the net_device it was received on (via netdev_hold()), + * so release that reference as the frame is dropped. Caller must hold + * local->rx_lock. + */ +void mac802154_flush_list(struct list_head *list, + struct ieee802154_sub_if_data *sdata) +{ + struct cfg802154_mac_pkt *mac_pkt, *tmp; + + list_for_each_entry_safe(mac_pkt, tmp, list, node) { + if (sdata && mac_pkt->sdata != sdata) + continue; + list_del(&mac_pkt->node); + netdev_put(mac_pkt->sdata->dev, &mac_pkt->dev_tracker); + kfree_skb(mac_pkt->skb); + kfree(mac_pkt); + } +} + +/** + * mac802154_flush_queued_pkts - drop queued RX work referencing @sdata + * @local: the mac802154 device + * @sdata: interface being removed + * + * The workers dereference the queued frame's interface directly + * (mac_pkt->sdata) or through skb->dev in mac802154_process_beacon(). Drop + * the not-yet-started entries belonging to @sdata before it is unregistered + * so their netdev reference is released; an entry already dequeued by a + * running worker keeps its own reference until the worker completes, which + * unregister_netdevice() then waits out. + */ +void mac802154_flush_queued_pkts(struct ieee802154_local *local, + struct ieee802154_sub_if_data *sdata) +{ + spin_lock_bh(&local->rx_lock); + mac802154_flush_list(&local->rx_beacon_list, sdata); + mac802154_flush_list(&local->rx_mac_cmd_list, sdata); + spin_unlock_bh(&local->rx_lock); } static int @@ -221,7 +291,10 @@ ieee802154_subif_frame(struct ieee802154_sub_if_data *sdata, mac_pkt->sdata = sdata; mac_pkt->page = sdata->local->scan_page; mac_pkt->channel = sdata->local->scan_channel; + netdev_hold(sdata->dev, &mac_pkt->dev_tracker, GFP_ATOMIC); + spin_lock(&sdata->local->rx_lock); list_add_tail(&mac_pkt->node, &sdata->local->rx_beacon_list); + spin_unlock(&sdata->local->rx_lock); queue_work(sdata->local->mac_wq, &sdata->local->rx_beacon_work); return NET_RX_SUCCESS; @@ -233,7 +306,10 @@ ieee802154_subif_frame(struct ieee802154_sub_if_data *sdata, mac_pkt->skb = skb_get(skb); mac_pkt->sdata = sdata; + netdev_hold(sdata->dev, &mac_pkt->dev_tracker, GFP_ATOMIC); + spin_lock(&sdata->local->rx_lock); list_add_tail(&mac_pkt->node, &sdata->local->rx_mac_cmd_list); + spin_unlock(&sdata->local->rx_lock); queue_work(sdata->local->mac_wq, &sdata->local->rx_mac_cmd_work); return NET_RX_SUCCESS; diff --git a/net/mac802154/scan.c b/net/mac802154/scan.c index 005338f89b75e1..ec36eb5716f594 100644 --- a/net/mac802154/scan.c +++ b/net/mac802154/scan.c @@ -104,13 +104,9 @@ static unsigned int mac802154_scan_get_channel_time(u8 duration_order, static void mac802154_flush_queued_beacons(struct ieee802154_local *local) { - struct cfg802154_mac_pkt *mac_pkt, *tmp; - - list_for_each_entry_safe(mac_pkt, tmp, &local->rx_beacon_list, node) { - list_del(&mac_pkt->node); - kfree_skb(mac_pkt->skb); - kfree(mac_pkt); - } + spin_lock_bh(&local->rx_lock); + mac802154_flush_list(&local->rx_beacon_list, NULL); + spin_unlock_bh(&local->rx_lock); } static void diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 1057d500577b04..bf8ea4cccb2f07 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -93,7 +93,8 @@ static void mptcp_parse_option(const struct sk_buff *skb, * In other words, the only way for checksums not to be used * is if both hosts in their SYNs set A=0." */ - if (flags & MPTCP_CAP_CHECKSUM_REQD) + if ((flags & MPTCP_CAP_CHECKSUM_REQD) && + opsize < TCPOLEN_MPTCP_MPC_ACK_DATA) mp_opt->suboptions |= OPTION_MPTCP_CSUMREQD; mp_opt->deny_join_id0 = !!(flags & MPTCP_CAP_DENY_JOIN_ID0); @@ -529,7 +530,7 @@ static bool mptcp_established_options_mp(struct sock *sk, struct sk_buff *skb, return false; /* MPC/MPJ needed only on 3rd ack packet, DATA_FIN and TCP shutdown take precedence */ - if (READ_ONCE(subflow->fully_established) || snd_data_fin_enable || + if (subflow->fully_established || snd_data_fin_enable || subflow->snd_isn != TCP_SKB_CB(skb)->seq || sk->sk_state != TCP_ESTABLISHED) return false; @@ -611,6 +612,7 @@ static void mptcp_write_data_fin(struct mptcp_subflow_context *subflow, ext->data_seq = data_fin_tx_seq; ext->subflow_seq = 0; ext->data_len = 1; + ext->csum = 0; } else if (ext->data_seq + ext->data_len == data_fin_tx_seq) { /* If there's an existing DSS mapping and it is the * final mapping, DATA_FIN consumes 1 additional byte of @@ -980,7 +982,7 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk, /* here we can process OoO, in-window pkts, only in-sequence 4th ack * will make the subflow fully established */ - if (likely(READ_ONCE(subflow->fully_established))) { + if (likely(subflow->fully_established)) { /* on passive sockets, check for 3rd ack retransmission * note that msk is always set by subflow_syn_recv_sock() * for mp_join subflows diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c index 64a1236aabee96..79bf88ca033b44 100644 --- a/net/mptcp/pm.c +++ b/net/mptcp/pm.c @@ -462,10 +462,10 @@ bool mptcp_pm_announced_alloc(struct mptcp_sock *msk, add_entry->addr = *addr; add_entry->sock = msk; - add_entry->retrans_times = 0; timer_setup(&add_entry->timer, mptcp_pm_add_addr_timer, 0); reset_timer: + add_entry->retrans_times = 0; add_entry->timer_done = false; timeout = mptcp_adjust_add_addr_timeout(msk); if (timeout) @@ -1065,7 +1065,8 @@ bool mptcp_pm_is_backup(struct mptcp_sock *msk, struct sock_common *skc) return mptcp_pm_nl_is_backup(msk, &skc_local); } -static void mptcp_pm_subflows_chk_stale(const struct mptcp_sock *msk, struct sock *ssk) +static void +mptcp_pm_subflow_chk_stale(const struct mptcp_sock *msk, struct sock *ssk) { struct mptcp_subflow_context *iter, *subflow = mptcp_subflow_ctx(ssk); struct sock *sk = (struct sock *)msk; @@ -1102,22 +1103,34 @@ static void mptcp_pm_subflows_chk_stale(const struct mptcp_sock *msk, struct soc } } -void mptcp_pm_subflow_chk_stale(const struct mptcp_sock *msk, struct sock *ssk) +void mptcp_pm_chk_stale(const struct mptcp_sock *msk) { - struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); - u32 rcv_tstamp = READ_ONCE(tcp_sk(ssk)->rcv_tstamp); - - /* keep track of rtx periods with no progress */ - if (!subflow->stale_count) { - subflow->stale_rcv_tstamp = rcv_tstamp; - subflow->stale_count++; - } else if (subflow->stale_rcv_tstamp == rcv_tstamp) { - if (subflow->stale_count < U8_MAX) + struct mptcp_subflow_context *subflow; + + mptcp_for_each_subflow(msk, subflow) { + struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + u32 rcv_tstamp; + + if (!__mptcp_subflow_active(subflow)) + continue; + + /* No data outstanding at TCP level? not stale */ + if (tcp_rtx_and_write_queues_empty(ssk)) + continue; + + /* keep track of rtx periods with no progress */ + rcv_tstamp = READ_ONCE(tcp_sk(ssk)->rcv_tstamp); + if (!subflow->stale_count) { + subflow->stale_rcv_tstamp = rcv_tstamp; subflow->stale_count++; - mptcp_pm_subflows_chk_stale(msk, ssk); - } else { - subflow->stale_count = 0; - mptcp_subflow_set_active(subflow); + } else if (subflow->stale_rcv_tstamp == rcv_tstamp) { + if (subflow->stale_count < U8_MAX) + subflow->stale_count++; + mptcp_pm_subflow_chk_stale(msk, ssk); + } else { + subflow->stale_count = 0; + mptcp_subflow_set_active(subflow); + } } } diff --git a/net/mptcp/pm_kernel.c b/net/mptcp/pm_kernel.c index 424f1a7f924827..1a775081323549 100644 --- a/net/mptcp/pm_kernel.c +++ b/net/mptcp/pm_kernel.c @@ -1137,6 +1137,8 @@ static int mptcp_nl_remove_id_zero_address(struct net *net, while ((msk = mptcp_token_iter_next(net, &s_slot, &s_num)) != NULL) { struct sock *sk = (struct sock *)msk; struct mptcp_addr_info msk_local; + struct mptcp_addr_info anno_addr; + bool announced; if (list_empty(&msk->conn_list) || mptcp_pm_is_userspace(msk)) goto next; @@ -1146,7 +1148,13 @@ static int mptcp_nl_remove_id_zero_address(struct net *net, goto next; lock_sock(sk); + /* Drop a possibly pending ADD_ADDR for this address. */ + anno_addr = msk_local; + anno_addr.port = 0; + announced = mptcp_pm_announced_remove(msk, &anno_addr); spin_lock_bh(&msk->pm.lock); + if (announced) + msk->pm.add_addr_signaled--; mptcp_pm_remove_addr(msk, &list); mptcp_pm_rm_subflow(msk, &list); __mark_subflow_endp_available(msk, 0); diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c index 2203cc2d27485f..57c13293a5f892 100644 --- a/net/mptcp/pm_userspace.c +++ b/net/mptcp/pm_userspace.c @@ -69,6 +69,19 @@ static int mptcp_userspace_pm_append_new_local_addr(struct mptcp_sock *msk, } if (!addr_match && !id_match) { + unsigned int id; + + if (!entry->addr.id && needs_id) { + id = find_next_zero_bit(id_bitmap, + MPTCP_PM_MAX_ADDR_ID + 1, 1); + if (id > MPTCP_PM_MAX_ADDR_ID) { + ret = -ENOSPC; + goto append_err; + } + } else { + id = entry->addr.id; + } + /* Memory for the entry is allocated from the * sock option buffer. */ @@ -78,10 +91,7 @@ static int mptcp_userspace_pm_append_new_local_addr(struct mptcp_sock *msk, goto append_err; } - if (!e->addr.id && needs_id) - e->addr.id = find_next_zero_bit(id_bitmap, - MPTCP_PM_MAX_ADDR_ID + 1, - 1); + e->addr.id = id; list_add_tail_rcu(&e->list, &msk->pm.userspace_pm_local_addr_list); msk->pm.local_addr_used++; ret = e->addr.id; diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 7c8180d8d5eff6..49c46498af9606 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -95,6 +95,7 @@ bool __mptcp_try_fallback(struct mptcp_sock *msk, int fb_mib) msk->allow_subflows = false; set_bit(MPTCP_FALLBACK_DONE, &msk->flags); + clear_bit(MPTCP_RTX_ENABLED, &msk->flags); __MPTCP_INC_STATS(net, fb_mib); spin_unlock_bh(&msk->fallback_lock); return true; @@ -772,12 +773,12 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk, mptcp_dss_corruption(msk, ssk); } } else { + sk_eat_skb(ssk, skb); + if (unlikely(!fin)) { DEBUG_NET_WARN_ON_ONCE(1); mptcp_dss_corruption(msk, ssk); } - - sk_eat_skb(ssk, skb); } WRITE_ONCE(tp->copied_seq, seq); @@ -1001,13 +1002,14 @@ static bool mptcp_rtx_timer_pending(struct sock *sk) static void mptcp_reset_rtx_timer(struct sock *sk) { + struct mptcp_sock *msk = mptcp_sk(sk); unsigned long tout; - /* prevent rescheduling on close */ - if (unlikely(inet_sk_state_load(sk) == TCP_CLOSE)) + /* Prevent rescheduling on close and in case of fallback. */ + if (!test_bit(MPTCP_RTX_ENABLED, &msk->flags)) return; - tout = mptcp_sk(sk)->timer_ival; + tout = msk->timer_ival; sk_reset_timer(sk, &sk->mptcp_retransmit_timer, jiffies + tout); } @@ -1586,7 +1588,9 @@ struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk) static void mptcp_push_release(struct sock *ssk, struct mptcp_sendmsg_info *info) { - tcp_push(ssk, 0, info->mss_now, tcp_sk(ssk)->nonagle, info->size_goal); + if (info->mss_now) + tcp_push(ssk, 0, info->mss_now, tcp_sk(ssk)->nonagle, + info->size_goal); release_sock(ssk); } @@ -1774,7 +1778,8 @@ static void __mptcp_subflow_push_pending(struct sock *sk, struct sock *ssk, bool ret = __subflow_push_pending(sk, ssk, &info); if (ret <= 0) keep_pushing = false; - copied += ret; + else + copied += ret; } mptcp_for_each_subflow(msk, subflow) { @@ -2469,7 +2474,6 @@ struct sock *mptcp_subflow_get_retrans(struct mptcp_sock *msk) /* still data outstanding at TCP level? skip this */ if (!tcp_rtx_and_write_queues_empty(ssk)) { - mptcp_pm_subflow_chk_stale(msk, ssk); min_stale_count = min_t(int, min_stale_count, subflow->stale_count); continue; } @@ -2801,9 +2805,10 @@ static void __mptcp_retrans(struct sock *sk) int ret, err; u16 len = 0; + mptcp_pm_chk_stale(msk); + mptcp_clean_una_wakeup(sk); - /* first check ssk: need to kick "stale" logic */ err = mptcp_sched_get_retrans(msk); dfrag = mptcp_rtx_head(sk); if (!dfrag) { @@ -2985,8 +2990,7 @@ static void mptcp_do_fastclose(struct sock *sk) */ inet_csk(ssk)->icsk_ack.rcv_mss = TCP_MIN_MSS; - tcp_send_active_reset(ssk, ssk->sk_allocation, - SK_RST_REASON_TCP_ABORT_ON_CLOSE); + tcp_send_active_reset(ssk, SK_RST_REASON_TCP_ABORT_ON_CLOSE); unlock: release_sock(ssk); } @@ -3192,6 +3196,9 @@ void mptcp_set_state(struct sock *sk, int state) * transition from TCP_SYN_RECV to TCP_CLOSE_WAIT. */ break; + case TCP_CLOSE: + clear_bit(MPTCP_RTX_ENABLED, &mptcp_sk(sk)->flags); + fallthrough; default: if (oldstate == TCP_ESTABLISHED || oldstate == TCP_CLOSE_WAIT) MPTCP_DEC_STATS(sock_net(sk), MPTCP_MIB_CURRESTAB); @@ -3452,6 +3459,7 @@ static void mptcp_destroy_common(struct mptcp_sock *msk) static int mptcp_disconnect(struct sock *sk, int flags) { + struct inet_connection_sock *icsk = inet_csk(sk); struct mptcp_sock *msk = mptcp_sk(sk); /* We are on the fastopen error path. We can't call straight into the @@ -3464,8 +3472,13 @@ static int mptcp_disconnect(struct sock *sk, int flags) mptcp_check_listen_stop(sk); mptcp_set_state(sk, TCP_CLOSE); - mptcp_stop_rtx_timer(sk); - mptcp_stop_tout_timer(sk); + /* The later subflow close can not kick again the tout timer, + * as the msk is already in closed status. + */ + msk->timer_ival = icsk->icsk_rto_min; + sk_stop_timer_sync(sk, &sk->mptcp_retransmit_timer); + icsk->icsk_mtup.probe_timestamp = 0; + sk_stop_timer_sync(sk, &icsk->mptcp_tout_timer); mptcp_pm_connection_closed(msk); @@ -3744,7 +3757,7 @@ static void schedule_3rdack_retransmission(struct sock *ssk) struct tcp_sock *tp = tcp_sk(ssk); unsigned long timeout; - if (READ_ONCE(mptcp_subflow_ctx(ssk)->fully_established)) + if (mptcp_subflow_ctx(ssk)->fully_established) return; /* reschedule with a timeout above RTT, as we must look only for drop */ @@ -4009,6 +4022,7 @@ static int mptcp_connect(struct sock *sk, struct sockaddr_unsized *uaddr, if (IS_ERR(ssk)) return PTR_ERR(ssk); + set_bit(MPTCP_RTX_ENABLED, &msk->flags); mptcp_set_state(sk, TCP_SYN_SENT); subflow = mptcp_subflow_ctx(ssk); #ifdef CONFIG_TCP_MD5SIG @@ -4156,6 +4170,7 @@ static int mptcp_listen(struct socket *sock, int backlog) goto unlock; } + set_bit(MPTCP_RTX_ENABLED, &msk->flags); mptcp_set_state(sk, TCP_LISTEN); sock_set_flag(sk, SOCK_RCU_FREE); diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 1b80f2d6ec5a23..d44aaa783c22be 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -116,6 +116,7 @@ #define MPTCP_WORK_RTX 1 #define MPTCP_FALLBACK_DONE 2 #define MPTCP_WORK_CLOSE_SUBFLOW 3 +#define MPTCP_RTX_ENABLED 4 /* MPTCP socket release cb flags */ #define MPTCP_PUSH_PENDING 1 @@ -580,11 +581,11 @@ struct mptcp_subflow_context { remote_key_valid : 1, /* received the peer key from */ disposable : 1, /* ctx can be free at ulp release time */ closing : 1, /* must not pass rx data to msk anymore */ - stale : 1, /* unable to snd/rcv data, do not use for xmit */ valid_csum_seen : 1, /* at least one csum validated */ is_mptfo : 1, /* subflow is doing TFO */ close_event_done : 1, /* has done the post-closed part */ mpc_drop : 1, /* the MPC option has been dropped in a rtx */ + resetting : 1, /* subflow is resetting */ __unused : 8; bool data_avail; bool scheduled; @@ -604,7 +605,11 @@ struct mptcp_subflow_context { u8 reset_seen:1; u8 reset_transient:1; u8 reset_reason:4; - u8 stale_count; + u8 stale_count; /* Protected by the msk socket lock */ + u8 stale; /* Protected by the msk socket lock, + * if set the subflow is unable to snd/rcv + * data, the schedule should skip it + */ u32 subflow_id; @@ -687,7 +692,7 @@ mptcp_send_active_reset_reason(struct sock *sk) enum sk_rst_reason reason; reason = sk_rst_convert_mptcp_reason(subflow->reset_reason); - tcp_send_active_reset(sk, GFP_ATOMIC, reason); + tcp_send_active_reset(sk, reason); } /* Made the fwd mem carried by the given skb available to the msk, @@ -1103,7 +1108,7 @@ int mptcp_pm_parse_entry(struct nlattr *attr, struct genl_info *info, bool mptcp_pm_addr_families_match(const struct sock *sk, const struct mptcp_addr_info *loc, const struct mptcp_addr_info *rem); -void mptcp_pm_subflow_chk_stale(const struct mptcp_sock *msk, struct sock *ssk); +void mptcp_pm_chk_stale(const struct mptcp_sock *msk); void mptcp_pm_new_connection(struct mptcp_sock *msk, const struct sock *ssk, int server_side); void mptcp_pm_fully_established(struct mptcp_sock *msk, const struct sock *ssk); bool mptcp_pm_allow_new_subflow(struct mptcp_sock *msk); diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index e1f20ff8fdb424..edd33dc9367f93 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -436,6 +436,10 @@ void mptcp_subflow_reset(struct sock *ssk) /* must hold: tcp_done() could drop last reference on parent */ sock_hold(sk); + subflow->resetting = 1; + + /* No need to delay the actual close for to-be discarded data. */ + __skb_queue_purge(&ssk->sk_receive_queue); mptcp_send_active_reset_reason(ssk); tcp_done(ssk); if (!test_and_set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &mptcp_sk(sk)->flags)) @@ -1873,6 +1877,13 @@ static void subflow_state_change(struct sock *sk) __subflow_state_change(sk); + /* Rx queue processing is unneeded, error reporting will take place at + * __mptcp_close_ssk() time and subflow reset can't happen in case of + * fallback: subflow_sched_work_if_closed() would be a no-op. + */ + if (subflow->resetting) + return; + /* as recvmsg() does not acquire the subflow socket for ssk selection * a fin packet carrying a DSS can be unnoticed if we don't trigger * the data available machinery here. @@ -2074,7 +2085,6 @@ static void subflow_ulp_clone(const struct request_sock *req, new_ctx->request_bkup = subflow_req->request_bkup; WRITE_ONCE(new_ctx->remote_id, subflow_req->remote_id); new_ctx->token = subflow_req->token; - new_ctx->thmac = subflow_req->thmac; /* the subflow req id is valid, fetched via subflow_check_req() * and subflow_token_join_request() diff --git a/net/mptcp/syncookies.c b/net/mptcp/syncookies.c index b5cac570112219..9474706641c119 100644 --- a/net/mptcp/syncookies.c +++ b/net/mptcp/syncookies.c @@ -26,7 +26,8 @@ struct join_entry { u32 local_nonce; u8 join_id; u8 local_id; - u8 backup; + u8 backup:1, + request_bkup:1; u8 valid; }; @@ -63,6 +64,7 @@ static void mptcp_join_store_state(struct join_entry *entry, entry->remote_nonce = subflow_req->remote_nonce; entry->local_nonce = subflow_req->local_nonce; entry->backup = subflow_req->backup; + entry->request_bkup = subflow_req->request_bkup; entry->join_id = subflow_req->remote_id; entry->local_id = subflow_req->local_id; entry->valid = 1; @@ -117,6 +119,7 @@ bool mptcp_token_join_cookie_init_state(struct mptcp_subflow_request_sock *subfl subflow_req->remote_nonce = e->remote_nonce; subflow_req->local_nonce = e->local_nonce; subflow_req->backup = e->backup; + subflow_req->request_bkup = e->request_bkup; subflow_req->remote_id = e->join_id; subflow_req->local_id = e->local_id; subflow_req->token = e->token; diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index ea5fdd4f4ce762..5383aeafb0aed4 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -747,9 +747,9 @@ sloop: if (cp->flags & IP_VS_CONN_F_SEQ_MASK) { *(p++) = IPVS_OPT_SEQ_DATA; *(p++) = sizeof(struct ip_vs_sync_conn_options); - hton_seq((struct ip_vs_seq *)p, &cp->in_seq); + hton_seq(&cp->in_seq, (struct ip_vs_seq *)p); p += sizeof(struct ip_vs_seq); - hton_seq((struct ip_vs_seq *)p, &cp->out_seq); + hton_seq(&cp->out_seq, (struct ip_vs_seq *)p); p += sizeof(struct ip_vs_seq); } /* Handle pe data */ @@ -999,10 +999,10 @@ static void ip_vs_process_message_v0(struct netns_ipvs *ipvs, const char *buffer pp->name, state); continue; } - } else { - if (state >= IP_VS_CTPL_S_LAST) - IP_VS_DBG(7, "BACKUP v0, Invalid tpl state %u\n", - state); + } else if (state >= IP_VS_CTPL_S_LAST) { + IP_VS_DBG(7, "BACKUP v0, Invalid tpl state %u\n", + state); + continue; } ip_vs_conn_fill_param(ipvs, AF_INET, s->protocol, @@ -1159,10 +1159,10 @@ static inline int ip_vs_proc_sync_conn(struct netns_ipvs *ipvs, __u8 *p, __u8 *m retc = 40; goto out; } - } else { - if (state >= IP_VS_CTPL_S_LAST) - IP_VS_DBG(7, "BACKUP, Invalid tpl state %u\n", - state); + } else if (state >= IP_VS_CTPL_S_LAST) { + IP_VS_DBG(7, "BACKUP, Invalid tpl state %u\n", state); + retc = 40; + goto out; } if (ip_vs_conn_fill_param_sync(ipvs, af, s, ¶m, pe_data, pe_data_len, pe_name, pe_name_len)) { diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 11e873a0bd1490..92c3bb77d27e89 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -1077,6 +1077,8 @@ static int ctnetlink_start(struct netlink_callback *cb) } cb->data = filter; + if (filter) + cb->answer_flags = NLM_F_DUMP_FILTERED; return 0; } diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c index e4a70d1d77b0b9..4fb33b5e9a85a2 100644 --- a/net/netfilter/nf_conntrack_sip.c +++ b/net/netfilter/nf_conntrack_sip.c @@ -429,7 +429,7 @@ static const char *sip_skip_whitespace(const char *dptr, const char *limit) dptr = sip_follow_continuation(dptr, limit); break; } - return dptr; + return dptr < limit ? dptr : NULL; } /* Search within a SIP header value, dealing with continuation lines */ diff --git a/net/netfilter/nf_log_syslog.c b/net/netfilter/nf_log_syslog.c index 5ffde27d450a75..ae0f9a47556c5c 100644 --- a/net/netfilter/nf_log_syslog.c +++ b/net/netfilter/nf_log_syslog.c @@ -1073,12 +1073,12 @@ err1: static void __exit nf_log_syslog_exit(void) { - unregister_pernet_subsys(&nf_log_syslog_net_ops); nf_log_unregister(&nf_ip_logger); nf_log_unregister(&nf_arp_logger); nf_log_unregister(&nf_ip6_logger); nf_log_unregister(&nf_netdev_logger); nf_log_unregister(&nf_bridge_logger); + unregister_pernet_subsys(&nf_log_syslog_net_ops); } module_init(nf_log_syslog_init); diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c index 170d3db860c564..659bafcacc856a 100644 --- a/net/netfilter/nfnetlink_cttimeout.c +++ b/net/netfilter/nfnetlink_cttimeout.c @@ -652,9 +652,9 @@ static void __exit cttimeout_exit(void) { nfnetlink_subsys_unregister(&cttimeout_subsys); - unregister_pernet_subsys(&cttimeout_ops); RCU_INIT_POINTER(nf_ct_timeout_hook, NULL); synchronize_net(); + unregister_pernet_subsys(&cttimeout_ops); } module_init(cttimeout_init); diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index 6c7fa2ed34f5c0..d923f2cb139800 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -228,13 +228,18 @@ static void __nfulnl_flush(struct nfulnl_instance *inst); static void __instance_destroy(struct nfulnl_instance *inst) { + spin_lock(&inst->lock); + if (inst->copy_mode == NFULNL_COPY_DISABLED) { + /* attempt to UNBIND a queue already pending + * destruction via netlink close event. Ignore. + */ + spin_unlock(&inst->lock); + return; + } + /* first pull it out of the global list */ hlist_del_rcu(&inst->hlist); - /* then flush all pending packets from skb */ - - spin_lock(&inst->lock); - /* lockless readers wont be able to use us */ inst->copy_mode = NFULNL_COPY_DISABLED; @@ -1233,8 +1238,8 @@ static void __exit nfnetlink_log_fini(void) { nfnetlink_subsys_unregister(&nfulnl_subsys); netlink_unregister_notifier(&nfulnl_rtnl_notifier); - unregister_pernet_subsys(&nfnl_log_net_ops); nf_log_unregister(&nfulnl_logger); + unregister_pernet_subsys(&nfnl_log_net_ops); } MODULE_DESCRIPTION("netfilter userspace logging"); diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 0da39eaed255f4..41d37442f18681 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -1513,6 +1513,7 @@ struct ctrl_dump_policy_ctx { struct netlink_policy_dump_state *state; const struct genl_family *rt; struct genl_op_iter *op_iter; + struct module *owner; u32 op; u16 fam_id; u8 dump_map:1, @@ -1555,6 +1556,9 @@ static int ctrl_dumppolicy_start(struct netlink_callback *cb) return -ENOENT; ctx->rt = rt; + ctx->owner = rt->module; + if (!try_module_get(ctx->owner)) + return -ENOENT; if (tb[CTRL_ATTR_OP]) { struct genl_split_ops doit, dump; @@ -1565,7 +1569,7 @@ static int ctrl_dumppolicy_start(struct netlink_callback *cb) err = genl_get_cmd_both(ctx->op, rt, &doit, &dump); if (err) { NL_SET_BAD_ATTR(cb->extack, tb[CTRL_ATTR_OP]); - return err; + goto err_put_owner; } if (doit.policy) { @@ -1583,16 +1587,20 @@ static int ctrl_dumppolicy_start(struct netlink_callback *cb) goto err_free_state; } - if (!ctx->state) - return -ENODATA; + if (!ctx->state) { + err = -ENODATA; + goto err_put_owner; + } ctx->dump_map = 1; return 0; } ctx->op_iter = kmalloc_obj(*ctx->op_iter); - if (!ctx->op_iter) - return -ENOMEM; + if (!ctx->op_iter) { + err = -ENOMEM; + goto err_put_owner; + } genl_op_iter_init(rt, ctx->op_iter); ctx->dump_map = genl_op_iter_next(ctx->op_iter); @@ -1624,6 +1632,8 @@ err_free_state: netlink_policy_dump_free(ctx->state); err_free_op_iter: kfree(ctx->op_iter); +err_put_owner: + module_put(ctx->owner); return err; } @@ -1760,6 +1770,7 @@ static int ctrl_dumppolicy_done(struct netlink_callback *cb) kfree(ctx->op_iter); netlink_policy_dump_free(ctx->state); + module_put(ctx->owner); return 0; } diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c index 46c1d66aad8c3d..868d9fdf3afdfa 100644 --- a/net/openvswitch/flow.c +++ b/net/openvswitch/flow.c @@ -288,7 +288,7 @@ static void get_ipv6_ext_hdrs(struct sk_buff *skb, struct ipv6hdr *nh, if (*ext_hdrs & OFPIEH12_ESP) *ext_hdrs |= OFPIEH12_UNREP; if ((*ext_hdrs & ~(OFPIEH12_HOP | OFPIEH12_DEST | - OFPIEH12_ROUTER | IPPROTO_FRAGMENT | + OFPIEH12_ROUTER | OFPIEH12_FRAG | OFPIEH12_AUTH | OFPIEH12_UNREP)) || dest_options_header_count >= 2) { *ext_hdrs |= OFPIEH12_UNSEQ; @@ -301,7 +301,7 @@ static void get_ipv6_ext_hdrs(struct sk_buff *skb, struct ipv6hdr *nh, *ext_hdrs |= OFPIEH12_UNREP; if ((*ext_hdrs & ~(OFPIEH12_HOP | OFPIEH12_DEST | OFPIEH12_ROUTER | - IPPROTO_FRAGMENT | OFPIEH12_UNREP)) || + OFPIEH12_FRAG | OFPIEH12_UNREP)) || dest_options_header_count >= 2) { *ext_hdrs |= OFPIEH12_UNSEQ; } diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c index 67d5b8c0fe792b..1e0f9d193eb062 100644 --- a/net/openvswitch/flow_table.c +++ b/net/openvswitch/flow_table.c @@ -257,11 +257,13 @@ static int tbl_mask_array_realloc(struct flow_table *tbl, int size) if (ovsl_dereference(old->masks[i])) new->masks[new->count++] = old->masks[i]; } - call_rcu(&old->rcu, mask_array_rcu_cb); } rcu_assign_pointer(tbl->mask_array, new); + if (old) + call_rcu(&old->rcu, mask_array_rcu_cb); + return 0; } diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index b22cda32213636..76bde7906d4946 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2675,7 +2675,8 @@ static int tpacket_parse_header(struct packet_sock *po, void *frame, int size_max, void **data) { union tpacket_uhdr ph; - int tp_len, off; + u32 tp_len; + int off; ph.raw = frame; @@ -2695,7 +2696,7 @@ static int tpacket_parse_header(struct packet_sock *po, void *frame, break; } if (unlikely(tp_len > size_max)) { - pr_err("packet size is too long (%d > %d)\n", tp_len, size_max); + pr_err("packet size is too long (%u > %d)\n", tp_len, size_max); return -EMSGSIZE; } diff --git a/net/rds/connection.c b/net/rds/connection.c index 7c8ab8e973e1bc..b6c4beb50eaf0e 100644 --- a/net/rds/connection.c +++ b/net/rds/connection.c @@ -106,10 +106,12 @@ static struct rds_connection *rds_conn_lookup(struct net *net, } /* - * This is called by transports as they're bringing down a connection. - * It clears partial message state so that the transport can start sending - * and receiving over this connection again in the future. It is up to - * the transport to have serialized this call with its send and recv. + * This is called by rds_conn_shutdown() once the transport has brought + * a path down. It clears partial message state so that the transport + * can start sending and receiving over this path again in the future. + * The caller owns RDS_IN_XMIT and RDS_RECV_REFILL across this call, + * which is what serializes it against the send and receive-refill + * paths. */ static void rds_conn_path_reset(struct rds_conn_path *cp) { @@ -120,7 +122,16 @@ static void rds_conn_path_reset(struct rds_conn_path *cp) rds_stats_inc(s_conn_reset); rds_send_path_reset(cp); - cp->cp_flags = 0; + + /* Clear the bits the reset is responsible for individually: a + * blanket cp_flags = 0 is a plain store that can clobber a + * concurrent atomic read-modify-write on the same word. + * RDS_IN_XMIT and RDS_RECV_REFILL are held as locks by the + * caller, rds_conn_shutdown(), which releases them once the + * teardown is complete. + */ + clear_bit(RDS_LL_SEND_FULL, &cp->cp_flags); + clear_bit(RDS_RECONNECT_PENDING, &cp->cp_flags); /* Do not clear next_rx_seq here, else we cannot distinguish * retransmitted packets from new packets, and will hand all @@ -406,28 +417,70 @@ void rds_conn_shutdown(struct rds_conn_path *cp) } mutex_unlock(&cp->cp_cm_lock); + /* Quiesce the transmit and receive-refill paths by + * acquiring their bit locks, not merely waiting for + * them to be released: with a plain wait, either path + * can re-take its lock the instant after we sample it + * clear and then run concurrently with the transport + * shutdown and the path reset below. Holding both + * locks across the teardown makes that structurally + * impossible. + */ wait_event(cp->cp_waitq, - !test_bit(RDS_IN_XMIT, &cp->cp_flags)); + !test_and_set_bit_lock(RDS_IN_XMIT, &cp->cp_flags)); wait_event(cp->cp_waitq, - !test_bit(RDS_RECV_REFILL, &cp->cp_flags)); + !test_and_set_bit(RDS_RECV_REFILL, &cp->cp_flags)); conn->c_trans->conn_path_shutdown(cp); rds_conn_path_reset(cp); + /* Release the two locks and wake any waiter (e.g. + * rds_tcp_reset_callbacks()) that blocked on them while + * we held them. The unlock orders the transport's ring + * re-initialization and the path reset above before + * either bit is seen clear. rds_conn_path_reset() leaves + * both bits alone: ownership ends here, not inside the + * reset. + */ + clear_bit_unlock(RDS_IN_XMIT, &cp->cp_flags); + clear_bit_unlock(RDS_RECV_REFILL, &cp->cp_flags); + wake_up_all(&cp->cp_waitq); + if (!rds_conn_path_transition(cp, RDS_CONN_DISCONNECTING, - RDS_CONN_DOWN) && - !rds_conn_path_transition(cp, RDS_CONN_ERROR, RDS_CONN_DOWN)) { - /* This can happen - eg when we're in the middle of tearing - * down the connection, and someone unloads the rds module. - * Quite reproducible with loopback connections. - * Mostly harmless. + /* The path was dropped again while we tore it + * down: by a socket state-change callback in + * irq context on receipt of a FIN, or by an + * accept that claimed the path just before a + * drop put it back to RDS_CONN_ERROR and then + * installed a fresh socket on it. Unless a + * pending destroy suppressed it, the drop also + * queued another shutdown pass, and that pass + * must run, because it is what tears down + * whatever attached to the path after the + * transport shutdown above sampled its state. + * Consuming the RDS_CONN_ERROR here would turn + * that pass into a no-op: leave the state + * alone, and let the pass finish the job. * - * Note that this also happens with rds-tcp because - * we could have triggered rds_conn_path_drop in irq - * mode from rds_tcp_state change on the receipt of - * a FIN, thus we need to recheck for RDS_CONN_ERROR - * here. + * Quiesce the reconnect timer before bailing + * out, though. When a pending destroy did + * suppress the queue, no later pass runs, and + * rds_conn_path_destroy() is about to flush + * cp_down_w and free the path: it must not + * find cp_conn_w still armed. A successor + * pass, when there is one, re-arms the + * reconnect from its own tail. + */ + cancel_delayed_work_sync(&cp->cp_conn_w); + clear_bit(RDS_RECONNECT_PENDING, &cp->cp_flags); + + if (rds_conn_path_state(cp) == RDS_CONN_ERROR) + return; + /* No current cp_state writer leaves a + * DISCONNECTING path in any state but + * RDS_CONN_ERROR; report loudly if one ever + * does. */ rds_conn_path_error(cp, "%s: failed to transition " "to state DOWN, current state " diff --git a/net/rds/ib_recv.c b/net/rds/ib_recv.c index 357128d34a546c..bd6cb3ffaa5711 100644 --- a/net/rds/ib_recv.c +++ b/net/rds/ib_recv.c @@ -363,15 +363,14 @@ static int acquire_refill(struct rds_connection *conn) static void release_refill(struct rds_connection *conn) { - clear_bit(RDS_RECV_REFILL, &conn->c_flags); - smp_mb__after_atomic(); + clear_bit_unlock(RDS_RECV_REFILL, &conn->c_flags); /* We don't use wait_on_bit()/wake_up_bit() because our waking is in a * hot path and finding waiters is very rare. We don't want to walk * the system-wide hashed waitqueue buckets in the fast path only to * almost never find waiters. */ - if (waitqueue_active(&conn->c_waitq)) + if (wq_has_sleeper(&conn->c_waitq)) wake_up_all(&conn->c_waitq); } @@ -392,7 +391,9 @@ void rds_ib_recv_refill(struct rds_connection *conn, int prefill, gfp_t gfp) /* the goal here is to just make sure that someone, somewhere * is posting buffers. If we can't get the refill lock, - * let them do their thing + * let them do their thing. The holder may also be + * rds_conn_shutdown() tearing the path down, in which case + * there is nothing to post. */ if (!acquire_refill(conn)) return; diff --git a/net/rds/message.c b/net/rds/message.c index 7feb0eb6537db8..9cbf045fe00314 100644 --- a/net/rds/message.c +++ b/net/rds/message.c @@ -405,7 +405,9 @@ struct rds_message *rds_message_map_pages(unsigned long *page_addrs, unsigned in for (i = 0; i < rm->data.op_nents; ++i) { sg_set_page(&rm->data.op_sg[i], virt_to_page((void *)page_addrs[i]), - PAGE_SIZE, 0); + i == rm->data.op_nents - 1 + ? total_len - (i * PAGE_SIZE) + : PAGE_SIZE, 0); } return rm; diff --git a/net/rds/send.c b/net/rds/send.c index 68be1bf0e0adf9..ffb3dd99983806 100644 --- a/net/rds/send.c +++ b/net/rds/send.c @@ -114,8 +114,13 @@ static void release_in_xmit(struct rds_conn_path *cp) * hot path and finding waiters is very rare. We don't want to walk * the system-wide hashed waitqueue buckets in the fast path only to * almost never find waiters. + * + * wq_has_sleeper() supplies the full barrier that orders the wait + * queue read after the bit clear; clear_bit_unlock() alone is only + * a release and would let this check read a stale empty queue, + * losing the wake-up. */ - if (waitqueue_active(&cp->cp_waitq)) + if (wq_has_sleeper(&cp->cp_waitq)) wake_up_all(&cp->cp_waitq); } @@ -231,8 +236,11 @@ restart: WRITE_ONCE(cp->cp_send_gen, send_gen); /* - * rds_conn_shutdown() sets the conn state and then tests RDS_IN_XMIT, - * we do the opposite to avoid races. + * rds_conn_shutdown() sets the conn state and then acquires + * RDS_IN_XMIT; we take the lock first and then check the state. + * Ownership is decided by the atomic RMW on the cp_flags word: + * if the teardown won the bit we back off here, and if we won + * it the teardown waits until we release it. */ if (!rds_conn_path_up(cp)) { release_in_xmit(cp); diff --git a/net/rds/tcp.c b/net/rds/tcp.c index b263634ac750d2..774a71f88d3752 100644 --- a/net/rds/tcp.c +++ b/net/rds/tcp.c @@ -115,46 +115,90 @@ void rds_tcp_restore_callbacks(struct socket *sock, } /* - * rds_tcp_reset_callbacks() switches the to the new sock and - * returns the existing tc->t_sock. + * rds_tcp_reset_callbacks() switches a path to a new socket and + * releases the old one it finds in tc->t_sock, resolving a duelling + * SYN. * - * The only functions that set tc->t_sock are rds_tcp_set_callbacks - * and rds_tcp_reset_callbacks. Send and receive trust that - * it is set. The absence of RDS_CONN_UP bit protects those paths - * from being called while it isn't set. + * tc->t_sock is set by rds_tcp_set_callbacks() and cleared by + * rds_tcp_restore_callbacks(). Four paths write it: the active + * connect in rds_tcp_conn_path_connect(), which sets it and clears it + * again on failure; the accept path in rds_tcp_accept_one(), which + * sets it for a path with no socket yet; the teardown in + * rds_tcp_conn_path_shutdown(), which clears it; and the swap done + * here, which does both. The connect and accept paths are serialized + * against each other by t_conn_path_lock. Send and receive trust + * that it is set: the absence of RDS_CONN_UP protects those paths + * from being called while it isn't, and the swap done here runs under + * RDS_IN_XMIT so that it cannot interleave with a sender already + * inside rds_send_xmit(). */ void rds_tcp_reset_callbacks(struct socket *sock, struct rds_conn_path *cp) { struct rds_tcp_connection *tc = cp->cp_transport_data; - struct socket *osock = tc->t_sock; - - if (!osock) - goto newsock; + struct socket *osock; /* Need to resolve a duelling SYN between peers. * We have an outstanding SYN to this peer, which may * potentially have transitioned to the RDS_CONN_UP state, * so we must quiesce any send threads before resetting - * cp_transport_data. We quiesce these threads by setting - * cp_state to something other than RDS_CONN_UP, and then - * waiting for any existing threads in rds_send_xmit to - * complete release_in_xmit(). (Subsequent threads entering - * rds_send_xmit() will bail on !rds_conn_up(). + * cp_transport_data. Setting cp_state to something other + * than RDS_CONN_UP stops new senders, and owning RDS_IN_XMIT + * excludes any thread already inside rds_send_xmit() - or a + * teardown in rds_conn_shutdown(), which holds the same lock + * for the duration of the transport shutdown - for the whole + * socket swap and the rds_send_path_reset() below. * - * However an incoming syn-ack at this point would end up - * marking the conn as RDS_CONN_UP, and would again permit - * rds_send_xmi() threads through, so ideally we would - * synchronize on RDS_CONN_UP after lock_sock(), but cannot - * do that: waiting on !RDS_IN_XMIT after lock_sock() may - * end up deadlocking with tcp_sendmsg(), and the RDS_IN_XMIT - * would not get set. As a result, we set c_state to - * RDS_CONN_RESETTTING, to ensure that rds_tcp_state_change - * cannot mark rds_conn_path_up() in the window before lock_sock() + * An incoming syn-ack at this point would end up marking the + * conn as RDS_CONN_UP, and would again permit rds_send_xmit() + * threads through, so ideally we would synchronize on + * RDS_CONN_UP after lock_sock(), but cannot do that: acquiring + * RDS_IN_XMIT after lock_sock() may end up deadlocking with + * tcp_sendmsg(), which takes the socket lock while holding + * RDS_IN_XMIT. As a result, we set c_state to + * RDS_CONN_RESETTING, to ensure that rds_tcp_state_change + * cannot mark rds_conn_path_up() in the window before + * lock_sock(). + * + * Only make that transition if the path is still connecting + * (or already resetting from an earlier duel). A path in any + * other state - typically RDS_CONN_DISCONNECTING or + * RDS_CONN_ERROR with a shutdown in flight - is dropped + * instead. That still replaces its state, with RDS_CONN_ERROR, + * and, unless a pending destroy is about to reap the whole + * connection anyway, queues one more shutdown pass. A shutdown + * already in flight leaves that RDS_CONN_ERROR alone when it + * finishes; the queued pass then completes the transition to + * RDS_CONN_DOWN and tears down anything that attached to the + * path in the meantime. + */ + if (!rds_conn_path_transition(cp, RDS_CONN_CONNECTING, + RDS_CONN_RESETTING) && + !rds_conn_path_transition(cp, RDS_CONN_RESETTING, + RDS_CONN_RESETTING)) + rds_conn_path_drop(cp, 0); + wait_event(cp->cp_waitq, + !test_and_set_bit_lock(RDS_IN_XMIT, &cp->cp_flags)); + + /* Read t_sock only while owning RDS_IN_XMIT, never before the + * wait: the teardown in rds_conn_shutdown() releases the old + * socket and clears t_sock, so a pointer sampled earlier can + * be stale by the time we wake up. The teardown holds the + * same lock while it does so, so what we read here cannot + * change under us until we release it. + */ + osock = tc->t_sock; + if (!osock) + goto newsock; + + /* reset receive side state for rds_tcp_data_recv() for osock. + * + * The sync cancels while owning RDS_IN_XMIT rely on cp_wq + * being ordered: a teardown blocked on the bit occupies + * cp_wq's only execution slot, so cp_send_w and cp_recv_w are + * pending at most and the cancels never flush. Nothing here + * may flush or wait on cp_wq itself. */ - atomic_set(&cp->cp_state, RDS_CONN_RESETTING); - wait_event(cp->cp_waitq, !test_bit(RDS_IN_XMIT, &cp->cp_flags)); - /* reset receive side state for rds_tcp_data_recv() for osock */ cancel_delayed_work_sync(&cp->cp_send_w); cancel_delayed_work_sync(&cp->cp_recv_w); lock_sock(osock->sk); @@ -172,6 +216,9 @@ newsock: lock_sock(sock->sk); rds_tcp_set_callbacks(sock, cp); release_sock(sock->sk); + + clear_bit_unlock(RDS_IN_XMIT, &cp->cp_flags); + wake_up_all(&cp->cp_waitq); } /* Add tc to rds_tcp_tc_list and set tc->t_sock. See comments diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c index a3db9b057084d3..13fa60c1985bb7 100644 --- a/net/rds/tcp_listen.c +++ b/net/rds/tcp_listen.c @@ -295,7 +295,11 @@ int rds_tcp_accept_one(struct rds_tcp_net *rtn) if (rs_tcp->t_sock) { /* Duelling SYN has been handled in rds_tcp_accept_one() */ rds_tcp_reset_callbacks(new_sock, cp); - /* rds_connect_path_complete() marks RDS_CONN_UP */ + /* rds_connect_path_complete() marks RDS_CONN_UP, or, + * if a concurrent shutdown won the duel, drops the + * path again and the pass that drop queues reaps the + * socket installed above. + */ rds_connect_path_complete(cp, RDS_CONN_RESETTING); } else { rds_tcp_set_callbacks(new_sock, cp); diff --git a/net/sched/act_api.c b/net/sched/act_api.c index b4415d358c9114..19501dc994641c 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -443,12 +443,21 @@ static size_t tcf_action_shared_attrs_size(const struct tc_action *act) + nla_total_size(IFNAMSIZ) /* TCA_ACT_KIND */ + cookie_len /* TCA_ACT_COOKIE */ + nla_total_size(sizeof(struct nla_bitfield32)) /* TCA_ACT_HW_STATS */ + /* TCA_ACT_USED_HW_STATS */ + + nla_total_size(sizeof(struct nla_bitfield32)) + + nla_total_size(sizeof(u32)) /* TCA_ACT_IN_HW_COUNT */ + nla_total_size(0) /* TCA_ACT_STATS nested */ + nla_total_size(sizeof(struct nla_bitfield32)) /* TCA_ACT_FLAGS */ /* TCA_STATS_BASIC */ + nla_total_size_64bit(sizeof(struct gnet_stats_basic)) - /* TCA_STATS_PKT64 */ - + nla_total_size_64bit(sizeof(u64)) + /* TCA_STATS_BASIC_HW */ + + nla_total_size_64bit(sizeof(struct gnet_stats_basic)) + /* TCA_STATS_PKT64, emitted by both of the basic copies above */ + + 2 * nla_total_size_64bit(sizeof(u64)) + /* TCA_STATS_RATE_EST */ + + nla_total_size_64bit(sizeof(struct gnet_stats_rate_est)) + /* TCA_STATS_RATE_EST64 */ + + nla_total_size_64bit(sizeof(struct gnet_stats_rate_est64)) /* TCA_STATS_QUEUE */ + nla_total_size_64bit(sizeof(struct gnet_stats_queue)) + nla_total_size(0) /* TCA_ACT_OPTIONS nested */ @@ -1191,18 +1200,13 @@ EXPORT_SYMBOL(tcf_action_exec); int tcf_action_destroy(struct tc_action *actions[], int bind) { - const struct tc_action_ops *ops; struct tc_action *a; int ret = 0, i; tcf_act_for_each_action(i, a, actions) { actions[i] = NULL; - ops = a->ops; - ret = __tcf_idr_release(a, bind, true); - if (ret == ACT_P_DELETED) - module_put(ops->owner); - else if (ret < 0) - return ret; + /* Drop our reference even if the action is still bound to a filter. */ + ret = tcf_idr_release(a, bind); } return ret; } @@ -1688,12 +1692,12 @@ out_nlmsg_trim: static int tcf_get_notify(struct net *net, u32 portid, struct nlmsghdr *n, - struct tc_action *actions[], int event, + struct tc_action *actions[], size_t attr_size, int event, struct netlink_ext_ack *extack) { struct sk_buff *skb; - skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); + skb = alloc_skb(max(attr_size, NLMSG_GOODSIZE), GFP_KERNEL); if (!skb) return -ENOBUFS; if (tca_get_fill(skb, actions, portid, n->nlmsg_seq, 0, event, @@ -1858,11 +1862,13 @@ static int tcf_action_delete(struct net *net, struct tc_action *actions[]) static struct sk_buff *tcf_reoffload_del_notify_msg(struct net *net, struct tc_action *action) { - size_t attr_size = tcf_action_fill_size(action); struct tc_action *actions[TCA_ACT_MAX_PRIO] = { [0] = action, }; struct sk_buff *skb; + size_t attr_size; + + attr_size = tcf_action_full_attrs_size(tcf_action_fill_size(action)); skb = alloc_skb(max(attr_size, NLMSG_GOODSIZE), GFP_KERNEL); if (!skb) @@ -1879,15 +1885,18 @@ static struct sk_buff *tcf_reoffload_del_notify_msg(struct net *net, static int tcf_reoffload_del_notify(struct net *net, struct tc_action *action) { const struct tc_action_ops *ops = action->ops; - struct sk_buff *skb; + struct sk_buff *skb = NULL; int ret; - if (!rtnl_notify_needed(net, 0, RTNLGRP_TC)) { - skb = NULL; - } else { + if (rtnl_notify_needed(net, 0, RTNLGRP_TC)) { skb = tcf_reoffload_del_notify_msg(net, action); + /* The action has already lost its hardware instance and is + * skip_sw, so it must be released whether or not the + * notification can be built. Drop the notification rather + * than leave an action behind that processes no packets. + */ if (IS_ERR(skb)) - return PTR_ERR(skb); + skb = NULL; } ret = tcf_idr_release_unsafe(action); @@ -2044,7 +2053,8 @@ tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n, attr_size = tcf_action_full_attrs_size(attr_size); if (event == RTM_GETACTION) - ret = tcf_get_notify(net, portid, n, actions, event, extack); + ret = tcf_get_notify(net, portid, n, actions, attr_size, event, + extack); else { /* delete */ ret = tcf_del_notify(net, n, actions, portid, attr_size, extack); if (ret) diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 9966766661d50d..c47d2ee13641d4 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -3254,7 +3254,7 @@ errout: tcf_chain_put(chain); errout_block: tcf_block_release(q, block, true); - if (err == -EAGAIN) + if (err == -EAGAIN && n->nlmsg_type == RTM_NEWCHAIN) /* Replay the request. */ goto replay; return err; diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c index 0d1324c9058373..0f211f030fd9a7 100644 --- a/net/sched/cls_route.c +++ b/net/sched/cls_route.c @@ -11,6 +11,7 @@ #include #include #include +#include #include #include #include @@ -41,6 +42,7 @@ struct route4_head { struct route4_bucket { /* 16 FROM buckets + 16 IIF buckets + 1 wildcard bucket */ struct route4_filter __rcu *ht[16 + 16 + 1]; + refcount_t filters_ref; struct rcu_head rcu; }; @@ -336,7 +338,7 @@ static int route4_delete(struct tcf_proto *tp, void *arg, bool *last, struct route4_filter *nf; struct route4_bucket *b; unsigned int h = 0; - int i, h1; + int h1; if (!head || !f) return -EINVAL; @@ -362,23 +364,14 @@ static int route4_delete(struct tcf_proto *tp, void *arg, bool *last, tcf_exts_get_net(&f->exts); tcf_queue_work(&f->rwork, route4_delete_filter_work); - /* Strip RTNL protected tree */ - for (i = 0; i <= 32; i++) { - struct route4_filter *rt; - - rt = rtnl_dereference(b->ht[i]); - if (rt) - goto out; + if (refcount_dec_and_test(&b->filters_ref)) { + RCU_INIT_POINTER(head->table[to_hash(h)], NULL); + kfree_rcu(b, rcu); } - - /* OK, session has no flows */ - RCU_INIT_POINTER(head->table[to_hash(h)], NULL); - kfree_rcu(b, rcu); break; } } -out: *last = true; for (h1 = 0; h1 <= 256; h1++) { if (rcu_access_pointer(head->table[h1])) { @@ -400,8 +393,9 @@ static const struct nla_policy route4_policy[TCA_ROUTE4_MAX + 1] = { static int route4_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, struct route4_filter *f, u32 handle, struct route4_head *head, - struct nlattr **tb, struct nlattr *est, int new, - u32 flags, struct netlink_ext_ack *extack) + struct nlattr **tb, struct nlattr *est, + struct route4_filter *fold, u32 flags, + struct netlink_ext_ack *extack) { u32 id = 0, to = 0, nhandle = 0x8000; struct route4_filter *fp; @@ -414,7 +408,7 @@ static int route4_set_parms(struct net *net, struct tcf_proto *tp, return err; if (tb[TCA_ROUTE4_TO]) { - if (new && handle & 0x8000) { + if (!fold && handle & 0x8000) { NL_SET_ERR_MSG(extack, "Invalid handle"); return -EINVAL; } @@ -437,14 +431,14 @@ static int route4_set_parms(struct net *net, struct tcf_proto *tp, } else nhandle |= 0xFFFF << 16; - if (handle && new) { + if (handle && (!fold || nhandle == (handle & ~0x7F00))) nhandle |= handle & 0x7F00; - if (nhandle != handle) { - NL_SET_ERR_MSG_FMT(extack, - "Handle mismatch constructed: %x (expected: %x)", - handle, nhandle); - return -EINVAL; - } + + if (handle && !fold && nhandle != handle) { + NL_SET_ERR_MSG_FMT(extack, + "Handle mismatch constructed: %x (expected: %x)", + handle, nhandle); + return -EINVAL; } if (!nhandle) { @@ -459,6 +453,7 @@ static int route4_set_parms(struct net *net, struct tcf_proto *tp, if (b == NULL) return -ENOBUFS; + refcount_set(&b->filters_ref, 1); rcu_assign_pointer(head->table[h1], b); } else { unsigned int h2 = from_hash(nhandle >> 16); @@ -466,8 +461,14 @@ static int route4_set_parms(struct net *net, struct tcf_proto *tp, for (fp = rtnl_dereference(b->ht[h2]); fp; fp = rtnl_dereference(fp->next)) - if (fp->handle == f->handle) + if (fp != fold && fp->handle == nhandle) { + NL_SET_ERR_MSG_FMT(extack, + "Handle %x is already in use", + nhandle); return -EEXIST; + } + + refcount_inc(&b->filters_ref); } if (tb[TCA_ROUTE4_TO]) @@ -500,9 +501,8 @@ static int route4_change(struct net *net, struct sk_buff *in_skb, struct route4_filter *fold, *f1, *pfp, *f = NULL; struct route4_bucket *b; struct nlattr *tb[TCA_ROUTE4_MAX + 1]; - unsigned int h, th; + unsigned int h; int err; - bool new = true; if (!handle) { NL_SET_ERR_MSG(extack, "Creating with handle of 0 is invalid"); @@ -539,11 +539,10 @@ static int route4_change(struct net *net, struct sk_buff *in_skb, f->tp = fold->tp; f->bkt = fold->bkt; - new = false; } err = route4_set_parms(net, tp, base, f, handle, head, tb, - tca[TCA_RATE], new, flags, extack); + tca[TCA_RATE], fold, flags, extack); if (err < 0) goto errout; @@ -560,17 +559,20 @@ static int route4_change(struct net *net, struct sk_buff *in_skb, rcu_assign_pointer(*fp, f); if (fold) { - th = to_hash(fold->handle); + b = fold->bkt; h = from_hash(fold->handle >> 16); - b = rtnl_dereference(head->table[th]); - if (b) { - fp = &b->ht[h]; - for (pfp = rtnl_dereference(*fp); pfp; - fp = &pfp->next, pfp = rtnl_dereference(*fp)) { - if (pfp == fold) { - rcu_assign_pointer(*fp, fold->next); - break; + fp = &b->ht[h]; + for (pfp = rtnl_dereference(*fp); pfp; + fp = &pfp->next, pfp = rtnl_dereference(*fp)) { + if (pfp == fold) { + rcu_assign_pointer(*fp, fold->next); + if (refcount_dec_and_test(&b->filters_ref)) { + unsigned int th = to_hash(fold->handle); + + RCU_INIT_POINTER(head->table[th], NULL); + kfree_rcu(b, rcu); } + break; } } } diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index ac6d0fa5a40e3f..a3e65c8cf29ef3 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -370,6 +370,10 @@ static int u32_init(struct tcf_proto *tp) refcount_set(&root_ht->refcnt, 1); root_ht->handle = tp_c ? gen_new_htid(tp_c, root_ht) : id2handle(0); + if (root_ht->handle == 0) { + kfree(root_ht); + return -ENOMEM; + } root_ht->prio = tp->prio; root_ht->is_root = true; idr_init(&root_ht->handle_idr); @@ -695,21 +699,33 @@ out: return ret; } -static u32 gen_new_kid(struct tc_u_hnode *ht, u32 htid) +static u32 gen_new_kid(struct tc_u_hnode *ht, u32 htid, int *err) { u32 index = htid | 0x800; u32 max = htid | 0xFFF; + *err = 0; + if (idr_alloc_u32(&ht->handle_idr, NULL, &index, max, GFP_KERNEL)) { index = htid + 1; - if (idr_alloc_u32(&ht->handle_idr, NULL, &index, max, - GFP_KERNEL)) - index = max; + *err = idr_alloc_u32(&ht->handle_idr, NULL, &index, max, + GFP_KERNEL); + if (*err) + return 0; } return index; } +static int u32_kid_extack(int err, struct netlink_ext_ack *extack) +{ + if (err == -ENOSPC) + NL_SET_ERR_MSG_MOD(extack, "Hash table node ID pool exhausted"); + else + NL_SET_ERR_MSG_MOD(extack, "Failed to allocate node ID"); + return err; +} + static const struct nla_policy u32_policy[TCA_U32_MAX + 1] = { [TCA_U32_CLASSID] = { .type = NLA_U32 }, [TCA_U32_HASH] = { .type = NLA_U32 }, @@ -1079,7 +1095,9 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, * handle which is used to uniquely identify the match entry. */ if (!TC_U32_NODE(handle)) { - handle = gen_new_kid(ht, htid); + handle = gen_new_kid(ht, htid, &err); + if (err) + return u32_kid_extack(err, extack); } else { handle = htid | TC_U32_NODE(handle); err = idr_alloc_u32(&ht->handle_idr, NULL, &handle, @@ -1091,7 +1109,9 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, /* The user did not give us a handle; lets just generate one * from the table's pool of nodeids. */ - handle = gen_new_kid(ht, htid); + handle = gen_new_kid(ht, htid, &err); + if (err) + return u32_kid_extack(err, extack); } if (tb[TCA_U32_SEL] == NULL) { diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 90503e59e6e3ba..463ededcdcfe0c 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1385,7 +1385,7 @@ err_out4: err_out3: qdisc_lock_uninit(sch, ops); netdev_put(dev, &sch->dev_tracker); - qdisc_free(sch); + qdisc_free_rcu(sch); err_out2: bpf_module_put(ops, ops->owner); err_out: diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c index 91b1ef824afaf2..8621d057edd9f9 100644 --- a/net/sched/sch_drr.c +++ b/net/sched/sch_drr.c @@ -82,8 +82,9 @@ static int drr_change_class(struct Qdisc *sch, u32 classid, u32 parentid, NL_SET_ERR_MSG(extack, "Specified DRR quantum cannot be zero"); return -EINVAL; } + quantum = clamp_t(u32, quantum, 256, 1 << 20); } else - quantum = psched_mtu(qdisc_dev(sch)); + quantum = clamp_t(u32, (u32)psched_mtu(qdisc_dev(sch)), 256, 1 << 20); if (cl != NULL) { if (tca[TCA_RATE]) { diff --git a/net/sched/sch_dualpi2.c b/net/sched/sch_dualpi2.c index 4f678d4ff10ec7..4947def7c49efa 100644 --- a/net/sched/sch_dualpi2.c +++ b/net/sched/sch_dualpi2.c @@ -208,9 +208,11 @@ static void dualpi2_reset_c_protection(struct dualpi2_sched_data *q) static void dualpi2_calculate_c_protection(struct Qdisc *sch, struct dualpi2_sched_data *q, u32 wc) { + u32 mtu = clamp_t(u32, psched_mtu(qdisc_dev(sch)), 1, 1 << 20); + q->c_protection_wc = wc; q->c_protection_wl = MAX_WC - wc; - q->c_protection_init = (s32)psched_mtu(qdisc_dev(sch)) * + q->c_protection_init = (s32)mtu * ((int)q->c_protection_wc - (int)q->c_protection_wl); dualpi2_reset_c_protection(q); } @@ -285,8 +287,9 @@ static bool must_drop(struct Qdisc *sch, struct dualpi2_sched_data *q, u64 local_l_prob; bool overload; u32 prob; + u32 mtu = clamp_t(u32, psched_mtu(qdisc_dev(sch)), 1, 1 << 20); - if (sch->qstats.backlog < 2 * psched_mtu(qdisc_dev(sch))) + if (sch->qstats.backlog < 2 * mtu) return false; prob = READ_ONCE(q->pi2_prob); @@ -712,7 +715,8 @@ static u32 get_memory_limit(struct Qdisc *sch, u32 limit) /* Apply rule of thumb, i.e., doubling the packet length, * to further include per packet overhead in memory_limit. */ - u64 memlim = mul_u32_u32(limit, 2 * psched_mtu(qdisc_dev(sch))); + u64 memlim = mul_u32_u32(limit, 2 * clamp_t(u32, psched_mtu(qdisc_dev(sch)), + 1, 1 << 20)); if (upper_32_bits(memlim)) return U32_MAX; diff --git a/net/sched/sch_ets.c b/net/sched/sch_ets.c index 25fcf4079fece1..6cc902a0383876 100644 --- a/net/sched/sch_ets.c +++ b/net/sched/sch_ets.c @@ -83,11 +83,7 @@ static int ets_quantum_parse(struct Qdisc *sch, const struct nlattr *attr, unsigned int *quantum, struct netlink_ext_ack *extack) { - *quantum = nla_get_u32(attr); - if (!*quantum) { - NL_SET_ERR_MSG(extack, "ETS quantum cannot be zero"); - return -EINVAL; - } + *quantum = clamp_t(u32, nla_get_u32(attr), 256, 1 << 20); return 0; } @@ -632,11 +628,13 @@ static int ets_qdisc_change(struct Qdisc *sch, struct nlattr *opt, return err; } /* If there are more bands than strict + quanta provided, the remaining - * ones are ETS with quantum of MTU. Initialize the missing values here. + * ones are ETS with quantum of max(MTU, 256). Initialize the missing + * values here. */ for (i = nstrict; i < nbands; i++) { if (!quanta[i]) - quanta[i] = psched_mtu(qdisc_dev(sch)); + quanta[i] = clamp_t(u32, (u32)psched_mtu(qdisc_dev(sch)), + 256, 1 << 20); } /* Before commit, make sure we can allocate all new qdiscs */ diff --git a/net/sched/sch_fq_pie.c b/net/sched/sch_fq_pie.c index b27d95418707a5..5982847df8f858 100644 --- a/net/sched/sch_fq_pie.c +++ b/net/sched/sch_fq_pie.c @@ -341,7 +341,8 @@ static int fq_pie_change(struct Qdisc *sch, struct nlattr *opt, nla_get_u32(tb[TCA_FQ_PIE_BETA])); if (tb[TCA_FQ_PIE_QUANTUM]) - WRITE_ONCE(q->quantum, nla_get_u32(tb[TCA_FQ_PIE_QUANTUM])); + WRITE_ONCE(q->quantum, + max(256U, nla_get_u32(tb[TCA_FQ_PIE_QUANTUM]))); if (tb[TCA_FQ_PIE_MEMORY_LIMIT]) WRITE_ONCE(q->memory_limit, diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 4539dc2c6d3805..6f6a6f0d5eb0d7 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -1086,21 +1086,21 @@ void qdisc_reset(struct Qdisc *qdisc) } EXPORT_SYMBOL(qdisc_reset); -void qdisc_free(struct Qdisc *qdisc) +static void qdisc_free_cb(struct rcu_head *head) { - if (qdisc_is_percpu_stats(qdisc)) { - free_percpu(qdisc->cpu_bstats); - free_percpu(qdisc->cpu_qstats); + struct Qdisc *q = container_of(head, struct Qdisc, rcu); + + if (qdisc_is_percpu_stats(q)) { + free_percpu(q->cpu_bstats); + free_percpu(q->cpu_qstats); } - kfree(qdisc); + kfree(q); } -static void qdisc_free_cb(struct rcu_head *head) +void qdisc_free_rcu(struct Qdisc *qdisc) { - struct Qdisc *q = container_of(head, struct Qdisc, rcu); - - qdisc_free(q); + call_rcu(&qdisc->rcu, qdisc_free_cb); } static void __qdisc_destroy(struct Qdisc *qdisc) @@ -1127,7 +1127,7 @@ static void __qdisc_destroy(struct Qdisc *qdisc) trace_qdisc_destroy(qdisc); - call_rcu(&qdisc->rcu, qdisc_free_cb); + qdisc_free_rcu(qdisc); } void qdisc_destroy(struct Qdisc *qdisc) diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c index 96acab6a8da035..fc72f825fbd92a 100644 --- a/net/sched/sch_hhf.c +++ b/net/sched/sch_hhf.c @@ -551,7 +551,7 @@ static int hhf_change(struct Qdisc *sch, struct nlattr *opt, return err; if (tb[TCA_HHF_QUANTUM]) - new_quantum = nla_get_u32(tb[TCA_HHF_QUANTUM]); + new_quantum = max(256U, nla_get_u32(tb[TCA_HHF_QUANTUM])); if (tb[TCA_HHF_NON_HH_WEIGHT]) new_hhf_non_hh_weight = nla_get_u32(tb[TCA_HHF_NON_HH_WEIGHT]); @@ -613,7 +613,7 @@ static int hhf_init(struct Qdisc *sch, struct nlattr *opt, int i; sch->limit = 1000; - q->quantum = psched_mtu(qdisc_dev(sch)); + q->quantum = clamp_t(u32, psched_mtu(qdisc_dev(sch)), 256, 1 << 20); get_random_bytes(&q->perturbation, sizeof(q->perturbation)); INIT_LIST_HEAD(&q->new_buckets); INIT_LIST_HEAD(&q->old_buckets); @@ -624,10 +624,6 @@ static int hhf_init(struct Qdisc *sch, struct nlattr *opt, q->hhf_evict_timeout = HZ; /* 1 sec */ q->hhf_non_hh_weight = 2; - if ((int)q->quantum <= 0 || - (u64)q->quantum * q->hhf_non_hh_weight > INT_MAX) - q->quantum = 256; - if (opt) { int err = hhf_change(sch, opt, extack); diff --git a/net/sched/sch_pie.c b/net/sched/sch_pie.c index b41f2def2e2cc5..3b7863ffd284c9 100644 --- a/net/sched/sch_pie.c +++ b/net/sched/sch_pie.c @@ -35,7 +35,7 @@ bool pie_drop_early(struct Qdisc *sch, struct pie_params *params, { u64 rnd; u64 local_prob = vars->prob; - u32 mtu = psched_mtu(qdisc_dev(sch)); + u32 mtu = clamp_t(u32, psched_mtu(qdisc_dev(sch)), 1, 1 << 20); /* If there is still burst allowance left skip random early drop */ if (vars->burst_time > 0) diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index 187d3ed578f268..8bbcfc9e85d94b 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -660,6 +660,11 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt, return -EINVAL; } + if (ctl->quantum > 1 << 20) { + NL_SET_ERR_MSG_MOD(extack, "quantum too large"); + return -EINVAL; + } + if (ctl->perturb_period < 0 || ctl->perturb_period > INT_MAX / HZ) { NL_SET_ERR_MSG_MOD(extack, "invalid perturb period"); @@ -688,7 +693,7 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt, /* update and validate configuration */ if (ctl->quantum) - quantum = ctl->quantum; + quantum = max(256U, ctl->quantum); if (ctl->flows) maxflows = min_t(u32, ctl->flows, SFQ_MAX_FLOWS); if (ctl->divisor) { diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 236e25abc7a428..84a4c97d0f7558 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -3215,6 +3215,9 @@ bool sctp_verify_asconf(const struct sctp_association *asoc, *errp = param.p; switch (param.p->type) { case SCTP_PARAM_ERR_CAUSE: + if (length < sizeof(struct sctp_addip_param) + + sizeof(struct sctp_errhdr)) + return false; break; case SCTP_PARAM_IPV4_ADDRESS: if (length != sizeof(struct sctp_ipv4addr_param)) @@ -3448,20 +3451,15 @@ static __be16 sctp_get_asconf_response(struct sctp_chunk *asconf_ack, case SCTP_PARAM_ERR_CAUSE: length = sizeof(*asconf_ack_param); err_param = (void *)asconf_ack_param + length; - asconf_ack_len -= length; - if (asconf_ack_len > 0) - return err_param->cause; - else - return SCTP_ERROR_INV_PARAM; - break; + return err_param->cause; default: return SCTP_ERROR_INV_PARAM; } } length = ntohs(asconf_ack_param->param_hdr.length); - asconf_ack_param = (void *)asconf_ack_param + length; - asconf_ack_len -= length; + asconf_ack_param = (void *)asconf_ack_param + SCTP_PAD4(length); + asconf_ack_len -= SCTP_PAD4(length); } return err_code; diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index 94716406d602ce..0d99b7e8c082f0 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -1545,17 +1545,8 @@ static int sctp_cmd_interpreter(enum sctp_event_type event_type, timeout = asoc->timeouts[cmd->obj.to]; BUG_ON(!timeout); - /* - * SCTP has a hard time with timer starts. Because we process - * timer starts as side effects, it can be hard to tell if we - * have already started a timer or not, which leads to BUG - * halts when we call add_timer. So here, instead of just starting - * a timer, if the timer is already started, and just mod - * the timer with the shorter of the two expiration times - */ - if (!timer_pending(timer)) + if (!timer_reduce(timer, jiffies + timeout)) sctp_association_hold(asoc); - timer_reduce(timer, jiffies + timeout); break; case SCTP_CMD_TIMER_RESTART: diff --git a/net/tipc/link.c b/net/tipc/link.c index 49dfc098d89b2c..6427c69f892942 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -504,7 +504,7 @@ bool tipc_link_create(struct net *net, char *if_name, int bearer_id, snprintf(l->name, sizeof(l->name), "%s:%s-%s:unknown", self_str, if_name, peer_str); - strcpy(l->if_name, if_name); + strscpy(l->if_name, if_name); l->addr = peer; l->peer_caps = peer_caps; l->net = net; @@ -574,7 +574,7 @@ bool tipc_link_bc_create(struct net *net, u32 ownnode, u32 peer, u8 *peer_id, snprintf(l->name, sizeof(l->name), "%s:%s", tipc_bclink_name, peer_str); } else { - strcpy(l->name, tipc_bclink_name); + strscpy(l->name, tipc_bclink_name); } trace_tipc_link_reset(l, TIPC_DUMP_ALL, "bclink created!"); tipc_link_reset(l); @@ -1898,7 +1898,7 @@ static void tipc_link_build_proto_msg(struct tipc_link *l, int mtyp, bool probe, msg_set_dest_session(hdr, l->peer_session); } msg_set_max_pkt(hdr, l->advertised_mtu); - strcpy(data, l->if_name); + memcpy(data, l->if_name, TIPC_MAX_IF_NAME); msg_set_size(hdr, INT_H_SIZE + TIPC_MAX_IF_NAME); skb_trim(skb, INT_H_SIZE + TIPC_MAX_IF_NAME); } diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c index 253c72d1366eb9..6fda36ab176695 100644 --- a/net/tipc/name_table.c +++ b/net/tipc/name_table.c @@ -763,21 +763,40 @@ struct publication *tipc_nametbl_publish(struct net *net, struct tipc_uaddr *ua, struct tipc_socket_addr *sk, u32 key) { struct name_table *nt = tipc_name_table(net); + u32 max_user_pub = TIPC_MAX_PUBL - 1; struct tipc_net *tn = tipc_net(net); struct publication *p = NULL; struct sk_buff *skb = NULL; + bool protocol_type = false; u32 rc_dests; + if (ua->sr.type == TIPC_NODE_STATE || ua->sr.type == TIPC_LINK_STATE || + ua->sr.type == TIPC_TOP_SRV) + protocol_type = true; + spin_lock_bh(&tn->nametbl_lock); + if (protocol_type) + goto insert; - if (nt->local_publ_count >= TIPC_MAX_PUBL) { - pr_warn("Bind failed, max limit %u reached\n", TIPC_MAX_PUBL); + /* Reserve one entry for node state service type because it has cluster + * scope and it is distributed in bulk. So, the maximum number of user's + * publications is (TIPC_MAX_PUBL - 1). + */ + if (nt->local_publ_count >= max_user_pub) { + pr_warn("Bind failed, max limit %u reached\n", max_user_pub); goto exit; } +insert: p = tipc_nametbl_insert_publ(net, ua, sk, key); if (p) { - nt->local_publ_count++; + /* Not count node state, link state and topology server types + * so that maximum nt->local_publ_count does not prevent + * protocol service types from being inserted into the name + * table. + */ + if (!protocol_type) + nt->local_publ_count++; skb = tipc_named_publish(net, p); } rc_dests = nt->rc_dests; @@ -810,7 +829,10 @@ void tipc_nametbl_withdraw(struct net *net, struct tipc_uaddr *ua, p = tipc_nametbl_remove_publ(net, ua, sk, key); if (p) { - nt->local_publ_count--; + if (p->sr.type != TIPC_NODE_STATE && + p->sr.type != TIPC_LINK_STATE && + p->sr.type != TIPC_TOP_SRV) + nt->local_publ_count--; skb = tipc_named_withdraw(net, p); list_del_init(&p->binding_sock); kfree_rcu(p, rcu); diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 10ed9421e43aa5..c7a03b01119d74 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2805,8 +2805,8 @@ static int unix_stream_recv_urg(struct unix_stream_read_state *state) return 1; } -static struct sk_buff *manage_oob(struct sk_buff *skb, struct sock *sk, - int flags, int copied) +static struct sk_buff *manage_oob(struct sk_buff *skb, struct sk_buff **last, + struct sock *sk, int flags, int copied) { struct sk_buff *read_skb = NULL, *unread_skb = NULL; struct unix_sock *u = unix_sk(sk); @@ -2820,11 +2820,13 @@ static struct sk_buff *manage_oob(struct sk_buff *skb, struct sock *sk, if (copied && (!u->oob_skb || skb == u->oob_skb)) { skb = NULL; } else if (flags & MSG_PEEK) { + *last = skb; skb = skb_peek_next(skb, &sk->sk_receive_queue); } else { read_skb = skb; skb = skb_peek_next(skb, &sk->sk_receive_queue); __skb_unlink(read_skb, &sk->sk_receive_queue); + *last = skb; } if (!skb) @@ -2843,8 +2845,10 @@ static struct sk_buff *manage_oob(struct sk_buff *skb, struct sock *sk, __skb_unlink(skb, &sk->sk_receive_queue); unread_skb = skb; skb = skb_peek(&sk->sk_receive_queue); + *last = skb; } } else if (!sock_flag(sk, SOCK_URGINLINE)) { + *last = skb; skb = skb_peek_next(skb, &sk->sk_receive_queue); } @@ -2964,8 +2968,8 @@ redo: again: #if IS_ENABLED(CONFIG_AF_UNIX_OOB) if (skb) { - skb = manage_oob(skb, sk, flags, copied); - if (!skb && copied) { + skb = manage_oob(skb, &last, sk, flags, copied); + if (!skb && (copied || !state->size)) { unix_state_unlock(sk); break; } diff --git a/rust/bindings/lib.rs b/rust/bindings/lib.rs index 812f8e5a08d536..439ab88a5da13f 100644 --- a/rust/bindings/lib.rs +++ b/rust/bindings/lib.rs @@ -22,11 +22,13 @@ #![feature(cfi_encoding)] #[allow(dead_code)] +#[allow(clippy::as_underscore)] #[allow(clippy::cast_lossless)] #[allow(clippy::ptr_as_ptr)] #[allow(clippy::ref_as_ptr)] #[allow(clippy::undocumented_unsafe_blocks)] -#[cfg_attr(CONFIG_RUSTC_HAS_UNNECESSARY_TRANSMUTES, allow(unnecessary_transmutes))] +#[cfg_attr(not(CONFIG_RUSTC_HAS_UNNECESSARY_TRANSMUTES), allow(unknown_lints))] +#[allow(unnecessary_transmutes)] #[cfg_attr( CONFIG_RUSTC_HAS_SUSPICIOUS_RUNTIME_SYMBOL_DEFINITIONS, allow(suspicious_runtime_symbol_definitions) diff --git a/rust/kernel/num.rs b/rust/kernel/num.rs index 8532b511384cc0..ba1eb58aee02f1 100644 --- a/rust/kernel/num.rs +++ b/rust/kernel/num.rs @@ -13,9 +13,14 @@ pub enum Unsigned {} /// Designates signed primitive types. pub enum Signed {} +mod private { + pub trait Sealed {} +} + /// Describes core properties of integer types. pub trait Integer: - Sized + private::Sealed + + Sized + Copy + Clone + PartialEq @@ -54,6 +59,8 @@ pub trait Integer: macro_rules! impl_integer { ($($type:ty: $signedness:ty), *) => { $( + impl private::Sealed for $type {} + impl Integer for $type { type Signedness = $signedness; diff --git a/rust/pin-init/src/lib.rs b/rust/pin-init/src/lib.rs index fd40c8f244a1ee..27a6969fa29b8e 100644 --- a/rust/pin-init/src/lib.rs +++ b/rust/pin-init/src/lib.rs @@ -493,13 +493,7 @@ macro_rules! stack_pin_init { (let $var:ident $(: $t:ty)? = $val:expr) => { let val = $val; let mut $var = ::core::pin::pin!($crate::__internal::StackInit$(::<$t>)?::uninit()); - let mut $var = match $crate::__internal::StackInit::init($var, val) { - Ok(res) => res, - Err(x) => { - let x: ::core::convert::Infallible = x; - match x {} - } - }; + let Ok(mut $var) = $crate::__internal::StackInit::init($var, val); }; } diff --git a/rust/uapi/lib.rs b/rust/uapi/lib.rs index 797ead5b5626ce..003e6d4f7c4b7f 100644 --- a/rust/uapi/lib.rs +++ b/rust/uapi/lib.rs @@ -10,6 +10,7 @@ #![no_std] #![allow( clippy::all, + clippy::as_underscore, clippy::cast_lossless, clippy::ptr_as_ptr, clippy::ref_as_ptr, @@ -23,7 +24,8 @@ unreachable_pub, unsafe_op_in_unsafe_fn )] -#![cfg_attr(CONFIG_RUSTC_HAS_UNNECESSARY_TRANSMUTES, allow(unnecessary_transmutes))] +#![cfg_attr(not(CONFIG_RUSTC_HAS_UNNECESSARY_TRANSMUTES), allow(unknown_lints))] +#![allow(unnecessary_transmutes)] #![cfg_attr( CONFIG_RUSTC_HAS_SUSPICIOUS_RUNTIME_SYMBOL_DEFINITIONS, allow(suspicious_runtime_symbol_definitions) diff --git a/samples/rust/rust_print_main.rs b/samples/rust/rust_print_main.rs index 682207c81fc2b3..01729e87d6b5a4 100644 --- a/samples/rust/rust_print_main.rs +++ b/samples/rust/rust_print_main.rs @@ -23,10 +23,10 @@ fn arc_print() -> Result { let b = UniqueArc::new("hello, world", GFP_KERNEL)?; // Prints the value of data in `a`. - pr_info!("{}", a); + pr_info!("{}\n", a); // Uses ":?" to print debug fmt of `b`. - pr_info!("{:?}", b); + pr_info!("{:?}\n", b); let a: Arc<&str> = b.into(); let c = a.clone(); @@ -42,7 +42,7 @@ fn arc_print() -> Result { use kernel::fmt::Display; fn arc_dyn_print(arc: &Arc) { - pr_info!("Arc says {arc}"); + pr_info!("Arc says {arc}\n"); } let a_i32_display: Arc = Arc::new(42i32, GFP_KERNEL)?; @@ -53,7 +53,7 @@ fn arc_print() -> Result { } // Pretty-prints the debug formatting with lower-case hexadecimal integers. - pr_info!("{:#x?}", a); + pr_info!("{:#x?}\n", a); Ok(()) } diff --git a/scripts/livepatch/init.c b/scripts/livepatch/init.c index f14d8c8fb35fa3..16aff8f736eb69 100644 --- a/scripts/livepatch/init.c +++ b/scripts/livepatch/init.c @@ -51,7 +51,7 @@ static int __init livepatch_mod_init(void) if (!funcs) { ret = -ENOMEM; for (int j = 0; j < i; j++) - kfree(objs[i].funcs); + kfree(objs[j].funcs); goto err_free_objs; } diff --git a/scripts/mksysmap b/scripts/mksysmap index c4531eacde2020..856b26ba2ac024 100755 --- a/scripts/mksysmap +++ b/scripts/mksysmap @@ -35,7 +35,7 @@ / __efistub_/d # arm64 local symbols in PIE namespace -/ __pi_\\$/d +/ __pi_\$/d / __pi_\.L/d # arm64 local symbols in non-VHE KVM namespace @@ -83,7 +83,7 @@ / _SDA2_BASE_$/d # MODULE_INFO() -/ __UNIQUE_ID_modinfo[0-9]*$/d +/ __UNIQUE_ID_modinfo_[0-9]*$/d # --------------------------------------------------------------------------- # Ignored patterns diff --git a/scripts/sorttable.c b/scripts/sorttable.c index d8dc2a1b7c3126..d7b50581c7329f 100644 --- a/scripts/sorttable.c +++ b/scripts/sorttable.c @@ -116,7 +116,7 @@ static inline void *get_index(void *start, int entsize, int index) } static int extable_ent_size; -static int long_size; +static int long_size __maybe_unused; #define ERRSTR_MAXSZ 256 diff --git a/security/landlock/fs.c b/security/landlock/fs.c index 8fc7f82a374aca..f1c9effc93fe4a 100644 --- a/security/landlock/fs.c +++ b/security/landlock/fs.c @@ -1222,11 +1222,12 @@ static int current_check_refer_path(struct dentry *const old_dentry, /* * old_dentry may be the root of the common mount point and * !IS_ROOT(old_dentry) at the same time (e.g. with open_tree() and - * OPEN_TREE_CLONE). We do not need to call dget(old_parent) because - * we keep a reference to old_dentry. + * OPEN_TREE_CLONE). Pin the dentry used as old_parent in either case. + * Otherwise, dget_parent() safely fetches and pins the current parent + * against a concurrent rename(2). */ - old_parent = (old_dentry == mnt_dir.dentry) ? old_dentry : - old_dentry->d_parent; + old_parent = (old_dentry == mnt_dir.dentry) ? dget(old_dentry) : + dget_parent(old_dentry); /* new_dir->dentry is equal to new_dentry->d_parent */ allow_parent1 = collect_domain_accesses(subject->domain, mnt_dir.dentry, @@ -1235,8 +1236,10 @@ static int current_check_refer_path(struct dentry *const old_dentry, allow_parent2 = collect_domain_accesses(subject->domain, mnt_dir.dentry, new_dir->dentry, &layer_masks_parent2); - if (allow_parent1 && allow_parent2) + if (allow_parent1 && allow_parent2) { + dput(old_parent); return 0; + } /* * To be able to compare source and destination domain access rights, @@ -1248,8 +1251,10 @@ static int current_check_refer_path(struct dentry *const old_dentry, subject->domain, &mnt_dir, access_request_parent1, &layer_masks_parent1, &request1, old_dentry, access_request_parent2, &layer_masks_parent2, &request2, - exchange ? new_dentry : NULL)) + exchange ? new_dentry : NULL)) { + dput(old_parent); return 0; + } if (request1.access) { request1.audit.u.path.dentry = old_parent; @@ -1259,6 +1264,7 @@ static int current_check_refer_path(struct dentry *const old_dentry, request2.audit.u.path.dentry = new_dir->dentry; landlock_log_denial(subject, &request2); } + dput(old_parent); /* * This prioritizes EACCES over EXDEV for all actions, including diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c index fa6723a6e82711..2fcdde09a03059 100644 --- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -4019,20 +4019,33 @@ int snd_pcm_mmap_data(struct snd_pcm_substream *substream, struct file *file, return -EINVAL; } runtime = substream->runtime; - if (runtime->state == SNDRV_PCM_STATE_OPEN) - return -EBADFD; - if (!(runtime->info & SNDRV_PCM_INFO_MMAP)) - return -ENXIO; + /* don't race with buffer reallocation in hw_params/hw_free */ + if (!atomic_inc_unless_negative(&runtime->buffer_accessing)) + return -EBUSY; + if (runtime->state == SNDRV_PCM_STATE_OPEN) { + err = -EBADFD; + goto out; + } + if (!(runtime->info & SNDRV_PCM_INFO_MMAP)) { + err = -ENXIO; + goto out; + } if (runtime->access == SNDRV_PCM_ACCESS_RW_INTERLEAVED || - runtime->access == SNDRV_PCM_ACCESS_RW_NONINTERLEAVED) - return -EINVAL; + runtime->access == SNDRV_PCM_ACCESS_RW_NONINTERLEAVED) { + err = -EINVAL; + goto out; + } size = area->vm_end - area->vm_start; offset = area->vm_pgoff << PAGE_SHIFT; dma_bytes = PAGE_ALIGN(runtime->dma_bytes); - if ((size_t)size > dma_bytes) - return -EINVAL; - if (offset > dma_bytes - size) - return -EINVAL; + if ((size_t)size > dma_bytes) { + err = -EINVAL; + goto out; + } + if (offset > dma_bytes - size) { + err = -EINVAL; + goto out; + } area->vm_ops = &snd_pcm_vm_ops_data; area->vm_private_data = substream; @@ -4042,6 +4055,8 @@ int snd_pcm_mmap_data(struct snd_pcm_substream *substream, struct file *file, err = snd_pcm_lib_default_mmap(substream, area); if (!err) atomic_inc(&substream->mmap_count); +out: + atomic_dec(&runtime->buffer_accessing); return err; } EXPORT_SYMBOL(snd_pcm_mmap_data); diff --git a/sound/core/ump.c b/sound/core/ump.c index 632c13baf21e10..a85d1006e7a510 100644 --- a/sound/core/ump.c +++ b/sound/core/ump.c @@ -1333,6 +1333,8 @@ static void update_legacy_names(struct snd_ump_endpoint *ump) { struct snd_rawmidi *rmidi = ump->legacy_rmidi; + if (!rmidi) + return; update_legacy_substreams(ump, rmidi, SNDRV_RAWMIDI_STREAM_INPUT); update_legacy_substreams(ump, rmidi, SNDRV_RAWMIDI_STREAM_OUTPUT); } @@ -1341,6 +1343,8 @@ static void ump_legacy_set_rawmidi_name(struct snd_ump_endpoint *ump) { struct snd_rawmidi *rmidi = ump->legacy_rmidi; + if (!rmidi) + return; snprintf(rmidi->name, sizeof(rmidi->name), "%.68s (MIDI 1.0)", ump->core.name); } diff --git a/sound/drivers/dummy.c b/sound/drivers/dummy.c index 41ceeafce824e0..21eb0d76d6f8da 100644 --- a/sound/drivers/dummy.c +++ b/sound/drivers/dummy.c @@ -782,7 +782,7 @@ static int snd_dummy_capsrc_put(struct snd_kcontrol *kcontrol, struct snd_ctl_el left = ucontrol->value.integer.value[0] & 1; right = ucontrol->value.integer.value[1] & 1; guard(spinlock_irq)(&dummy->mixer_lock); - change = dummy->capture_source[addr][0] != left && + change = dummy->capture_source[addr][0] != left || dummy->capture_source[addr][1] != right; dummy->capture_source[addr][0] = left; dummy->capture_source[addr][1] = right; diff --git a/sound/hda/common/codec.c b/sound/hda/common/codec.c index ef533770179b49..33dbe21fa165c9 100644 --- a/sound/hda/common/codec.c +++ b/sound/hda/common/codec.c @@ -2271,6 +2271,7 @@ static int snd_hda_spdif_default_put(struct snd_kcontrol *kcontrol, int idx = kcontrol->private_value; struct hda_spdif_out *spdif; hda_nid_t nid; + unsigned int old_status; unsigned short val; int change; @@ -2279,6 +2280,7 @@ static int snd_hda_spdif_default_put(struct snd_kcontrol *kcontrol, guard(mutex)(&codec->spdif_mutex); spdif = snd_array_elem(&codec->spdif_out, idx); nid = spdif->nid; + old_status = spdif->status; spdif->status = ucontrol->value.iec958.status[0] | ((unsigned int)ucontrol->value.iec958.status[1] << 8) | ((unsigned int)ucontrol->value.iec958.status[2] << 16) | @@ -2289,7 +2291,7 @@ static int snd_hda_spdif_default_put(struct snd_kcontrol *kcontrol, spdif->ctls = val; if (change && nid != (u16)-1) set_dig_out_convert(codec, nid, val & 0xff, (val >> 8) & 0xff); - return change; + return change || spdif->status != old_status; } #define snd_hda_spdif_out_switch_info snd_ctl_boolean_mono_info diff --git a/sound/hda/core/device.c b/sound/hda/core/device.c index 160c8d0453b0e4..ebaa106d0f0185 100644 --- a/sound/hda/core/device.c +++ b/sound/hda/core/device.c @@ -404,6 +404,7 @@ static void setup_fg_nodes(struct hdac_device *codec) */ int snd_hdac_refresh_widgets(struct hdac_device *codec) { + hda_nid_t fg = codec->afg ? codec->afg : codec->mfg; hda_nid_t start_nid; int nums, err = 0; @@ -412,10 +413,10 @@ int snd_hdac_refresh_widgets(struct hdac_device *codec) * widgets array. */ guard(mutex)(&codec->widget_lock); - nums = snd_hdac_get_sub_nodes(codec, codec->afg, &start_nid); + nums = snd_hdac_get_sub_nodes(codec, fg, &start_nid); if (!start_nid || nums <= 0 || nums >= 0xff) { dev_err(&codec->dev, "cannot read sub nodes for FG 0x%02x\n", - codec->afg); + fg); return -EINVAL; } diff --git a/sound/pci/ctxfi/cthw20k2.c b/sound/pci/ctxfi/cthw20k2.c index 07e1490a6d174a..36066ffe8784c9 100644 --- a/sound/pci/ctxfi/cthw20k2.c +++ b/sound/pci/ctxfi/cthw20k2.c @@ -994,6 +994,7 @@ static int daio_mgr_dao_init(struct hw *hw, void *blk, unsigned int idx, unsigne /* S/PDIF output */ switch ((conf & 0xf)) { case 1: + case 9: set_field(&ctl->txctl[idx], ATXCTL_NUC, 0); break; case 2: diff --git a/sound/soc/amd/acp-da7219-max98357a.c b/sound/soc/amd/acp-da7219-max98357a.c index af559653e62554..1ac729a58bb45c 100644 --- a/sound/soc/amd/acp-da7219-max98357a.c +++ b/sound/soc/amd/acp-da7219-max98357a.c @@ -17,6 +17,7 @@ #include #include #include +#include #include "acp.h" #include "../codecs/da7219.h" @@ -742,6 +743,18 @@ static const struct regulator_desc acp_da7219_desc = { .n_voltages = 1, }; +/* + * The ACP3.x+ (Raven/Picasso and later) audio coprocessor is a dedicated PCI + * function. Carrizo/Stoney - the only platforms handled by this driver - reach + * the ACP through the GPU driver and have no such device. + */ +#define ACP3X_PCI_DEV_ID 0x15e2 + +static const struct pci_device_id acp3x_pci_ids[] = { + { PCI_DEVICE(PCI_VENDOR_ID_AMD, ACP3X_PCI_DEV_ID) }, + { 0, }, +}; + static int cz_probe(struct platform_device *pdev) { int ret; @@ -750,6 +763,16 @@ static int cz_probe(struct platform_device *pdev) struct regulator_dev *rdev; struct device *dev = &pdev->dev; + /* + * AMDI5682 is also matched by acp3x-alc5682-max98357 (Raven/Picasso). + * If the ACP3.x PCI function is present this is such a board; return + * -ENODEV so that driver binds instead. + */ + if (pci_dev_present(acp3x_pci_ids)) { + dev_info(dev, "ACP3.x PCI device present, deferring to acp3x-alc5682-max98357\n"); + return -ENODEV; + } + card = (struct snd_soc_card *)acp_soc_is_rltk_max(dev); if (!card) return -ENODEV; diff --git a/sound/soc/amd/renoir/acp3x-pdm-dma.c b/sound/soc/amd/renoir/acp3x-pdm-dma.c index e60e3821703ccb..3f59b753243d56 100644 --- a/sound/soc/amd/renoir/acp3x-pdm-dma.c +++ b/sound/soc/amd/renoir/acp3x-pdm-dma.c @@ -104,7 +104,7 @@ static void disable_pdm_interrupts(void __iomem *acp_base) u32 ext_int_ctrl; ext_int_ctrl = rn_readl(acp_base + ACP_EXTERNAL_INTR_CNTL); - ext_int_ctrl |= ~PDM_DMA_INTR_MASK; + ext_int_ctrl &= ~PDM_DMA_INTR_MASK; rn_writel(ext_int_ctrl, acp_base + ACP_EXTERNAL_INTR_CNTL); } diff --git a/sound/soc/amd/yc/acp6x-pdm-dma.c b/sound/soc/amd/yc/acp6x-pdm-dma.c index 710db721ffa480..40c4d833f4ed30 100644 --- a/sound/soc/amd/yc/acp6x-pdm-dma.c +++ b/sound/soc/amd/yc/acp6x-pdm-dma.c @@ -275,9 +275,11 @@ static int acp6x_pdm_dma_close(struct snd_soc_component *component, struct snd_pcm_substream *substream) { struct pdm_dev_data *adata = dev_get_drvdata(component->dev); + struct snd_pcm_runtime *runtime = substream->runtime; acp6x_disable_pdm_interrupts(adata->acp6x_base); adata->capture_stream = NULL; + kfree(runtime->private_data); return 0; } diff --git a/sound/soc/bcm/bcm63xx-i2s-whistler.c b/sound/soc/bcm/bcm63xx-i2s-whistler.c index c47ed1e6ea2b6d..14d111fe29d83c 100644 --- a/sound/soc/bcm/bcm63xx-i2s-whistler.c +++ b/sound/soc/bcm/bcm63xx-i2s-whistler.c @@ -285,6 +285,7 @@ static const struct of_device_id snd_soc_bcm_audio_match[] = { {.compatible = "brcm,bcm63xx-i2s"}, { } }; +MODULE_DEVICE_TABLE(of, snd_soc_bcm_audio_match); #endif static struct platform_driver bcm63xx_i2s_driver = { diff --git a/sound/soc/codecs/ab8500-codec.c b/sound/soc/codecs/ab8500-codec.c index 6e8ef9cd1b31a7..e1a0e35836e6c8 100644 --- a/sound/soc/codecs/ab8500-codec.c +++ b/sound/soc/codecs/ab8500-codec.c @@ -20,10 +20,8 @@ #include #include #include -#include #include #include -#include #include #include #include @@ -53,32 +51,9 @@ /* Macrocell register definitions */ #define AB8500_GPIO_DIR4_REG 0x13 /* Bank AB8500_MISC */ -/* Nr of FIR/IIR-coeff banks in ANC-block */ -#define AB8500_NR_OF_ANC_COEFF_BANKS 2 - -/* Minimum duration to keep ANC IIR Init bit high or -low before proceeding with the configuration sequence */ -#define AB8500_ANC_SM_DELAY 2000 - -/* Sidetone states */ -static const char * const enum_sid_state[] = { - "Unconfigured", - "Apply FIR", - "FIR is configured", -}; -enum sid_state { - SID_UNCONFIGURED = 0, - SID_APPLY_FIR = 1, - SID_FIR_CONFIGURED = 2, -}; - /* Private data for AB8500 device-driver */ struct ab8500_codec_drvdata { struct regmap *regmap; - struct mutex ctrl_lock; - - /* Sidetone */ - enum sid_state sid_status; }; static inline const char *amic_micbias_str(enum amic_micbias micbias) @@ -258,7 +233,7 @@ static const struct snd_kcontrol_new dapm_anc_in_select[] = { /* ANC - Enable/Disable */ static const struct snd_kcontrol_new dapm_anc_enable[] = { SOC_DAPM_SINGLE("Switch", AB8500_ANCCONF1, - AB8500_ANCCONF1_ENANC, 0, 0), + AB8500_ANCCONF1_ENANC, 1, 0), }; /* ANC to Earpiece - Mute */ @@ -340,12 +315,6 @@ static const struct snd_soc_dapm_widget ab8500_dapm_widgets[] = { /* DA/AD */ - SND_SOC_DAPM_INPUT("ADC Input"), - SND_SOC_DAPM_ADC("ADC", "ab8500_0c", SND_SOC_NOPM, 0, 0), - - SND_SOC_DAPM_DAC("DAC", NULL, SND_SOC_NOPM, 0, 0), - SND_SOC_DAPM_OUTPUT("DAC Output"), - SND_SOC_DAPM_AIF_IN("DA_IN1", NULL, 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("DA_IN2", NULL, 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("DA_IN3", NULL, 0, SND_SOC_NOPM, 0, 0), @@ -537,9 +506,8 @@ static const struct snd_soc_dapm_widget ab8500_dapm_widgets[] = { SND_SOC_DAPM_MIXER("AD3 Channel Volume", SND_SOC_NOPM, 0, 0, NULL, 0), - SND_SOC_DAPM_MIXER("AD3 Enable", - AB8500_ADPATHENA, AB8500_ADPATHENA_ENAD34, 0, - NULL, 0), + SND_SOC_DAPM_SUPPLY("AD34 Enable", AB8500_ADPATHENA, + AB8500_ADPATHENA_ENAD34, 0, NULL, 0), /* Mic 2 */ @@ -598,9 +566,8 @@ static const struct snd_soc_dapm_widget ab8500_dapm_widgets[] = { SND_SOC_NOPM, 0, 0, NULL, 0), - SND_SOC_DAPM_MIXER("AD12 Enable", - AB8500_ADPATHENA, AB8500_ADPATHENA_ENAD12, 0, - NULL, 0), + SND_SOC_DAPM_SUPPLY("AD12 Enable", AB8500_ADPATHENA, + AB8500_ADPATHENA_ENAD12, 0, NULL, 0), /* HD Capture path */ @@ -614,12 +581,8 @@ static const struct snd_soc_dapm_widget ab8500_dapm_widgets[] = { SND_SOC_DAPM_MIXER("AD6 Channel Volume", SND_SOC_NOPM, 0, 0, NULL, 0), - SND_SOC_DAPM_MIXER("AD57 Enable", - AB8500_ADPATHENA, AB8500_ADPATHENA_ENAD5768, 0, - NULL, 0), - SND_SOC_DAPM_MIXER("AD68 Enable", - AB8500_ADPATHENA, AB8500_ADPATHENA_ENAD5768, 0, - NULL, 0), + SND_SOC_DAPM_SUPPLY("AD5768 Enable", AB8500_ADPATHENA, + AB8500_ADPATHENA_ENAD5768, 0, NULL, 0), /* Digital Microphone path */ @@ -651,15 +614,8 @@ static const struct snd_soc_dapm_widget ab8500_dapm_widgets[] = { SND_SOC_DAPM_MIXER("AD4 Channel Volume", SND_SOC_NOPM, 0, 0, NULL, 0), - SND_SOC_DAPM_MIXER("AD4 Enable", - AB8500_ADPATHENA, AB8500_ADPATHENA_ENAD34, - 0, NULL, 0), - /* Acoustical Noise Cancellation path */ - SND_SOC_DAPM_INPUT("ANC Configure Input"), - SND_SOC_DAPM_OUTPUT("ANC Configure Output"), - SND_SOC_DAPM_MUX("ANC Source", SND_SOC_NOPM, 0, 0, dapm_anc_in_select), @@ -702,24 +658,13 @@ static const struct snd_soc_dapm_route ab8500_dapm_routes[] = { {"Main Supply", NULL, "Audio Power"}, {"Main Supply", NULL, "Audio Analog Power"}, - {"DAC", NULL, "ab8500_0p"}, - {"DAC", NULL, "Main Supply"}, - {"ADC", NULL, "ab8500_0c"}, - {"ADC", NULL, "Main Supply"}, - - /* ANC Configure */ - {"ANC Configure Input", NULL, "Main Supply"}, - {"ANC Configure Output", NULL, "ANC Configure Input"}, - - /* AD/DA */ - {"ADC", NULL, "ADC Input"}, - {"DAC Output", NULL, "DAC"}, - /* Powerup charge pump if DA1/2 is in use */ {"DA_IN1", NULL, "ab8500_0p"}, + {"DA_IN1", NULL, "Main Supply"}, {"DA_IN1", NULL, "Charge Pump"}, {"DA_IN2", NULL, "ab8500_0p"}, + {"DA_IN2", NULL, "Main Supply"}, {"DA_IN2", NULL, "Charge Pump"}, /* Headset path */ @@ -754,8 +699,10 @@ static const struct snd_soc_dapm_route ab8500_dapm_routes[] = { /* HF or LineOut path */ {"DA_IN3", NULL, "ab8500_0p"}, + {"DA_IN3", NULL, "Main Supply"}, {"DA3 Channel Volume", NULL, "DA_IN3"}, {"DA_IN4", NULL, "ab8500_0p"}, + {"DA_IN4", NULL, "Main Supply"}, {"DA4 Channel Volume", NULL, "DA_IN4"}, {"Speaker Left Source", "Audio Path", "DA3 Channel Volume"}, @@ -813,8 +760,10 @@ static const struct snd_soc_dapm_route ab8500_dapm_routes[] = { /* Vibrator path */ {"DA_IN5", NULL, "ab8500_0p"}, + {"DA_IN5", NULL, "Main Supply"}, {"DA5 Channel Volume", NULL, "DA_IN5"}, {"DA_IN6", NULL, "ab8500_0p"}, + {"DA_IN6", NULL, "Main Supply"}, {"DA6 Channel Volume", NULL, "DA_IN6"}, {"VIB1 DAC", NULL, "DA5 Channel Volume"}, @@ -856,13 +805,15 @@ static const struct snd_soc_dapm_route ab8500_dapm_routes[] = { {"AD1 Channel Volume", NULL, "AD1 Source Select"}, {"AD2 Channel Volume", NULL, "AD2 Source Select"}, - {"AD12 Enable", NULL, "AD1 Channel Volume"}, - {"AD12 Enable", NULL, "AD2 Channel Volume"}, + {"AD1 Channel Volume", NULL, "AD12 Enable"}, + {"AD2 Channel Volume", NULL, "AD12 Enable"}, - {"AD_OUT1", NULL, "ab8500_0c"}, - {"AD_OUT1", NULL, "AD12 Enable"}, - {"AD_OUT2", NULL, "ab8500_0c"}, - {"AD_OUT2", NULL, "AD12 Enable"}, + {"ab8500_0c", NULL, "AD_OUT1"}, + {"AD_OUT1", NULL, "Main Supply"}, + {"AD_OUT1", NULL, "AD1 Channel Volume"}, + {"ab8500_0c", NULL, "AD_OUT2"}, + {"AD_OUT2", NULL, "Main Supply"}, + {"AD_OUT2", NULL, "AD2 Channel Volume"}, /* Mic 1 */ @@ -879,11 +830,11 @@ static const struct snd_soc_dapm_route ab8500_dapm_routes[] = { {"AD3 Source Select", "Mic 1", "MIC1 ADC"}, {"AD3 Channel Volume", NULL, "AD3 Source Select"}, + {"AD3 Channel Volume", NULL, "AD34 Enable"}, - {"AD3 Enable", NULL, "AD3 Channel Volume"}, - - {"AD_OUT3", NULL, "ab8500_0c"}, - {"AD_OUT3", NULL, "AD3 Enable"}, + {"ab8500_0c", NULL, "AD_OUT3"}, + {"AD_OUT3", NULL, "Main Supply"}, + {"AD_OUT3", NULL, "AD3 Channel Volume"}, /* HD Capture path */ @@ -892,14 +843,15 @@ static const struct snd_soc_dapm_route ab8500_dapm_routes[] = { {"AD5 Channel Volume", NULL, "AD5 Source Select"}, {"AD6 Channel Volume", NULL, "AD6 Source Select"}, + {"AD5 Channel Volume", NULL, "AD5768 Enable"}, + {"AD6 Channel Volume", NULL, "AD5768 Enable"}, - {"AD57 Enable", NULL, "AD5 Channel Volume"}, - {"AD68 Enable", NULL, "AD6 Channel Volume"}, - - {"AD_OUT57", NULL, "ab8500_0c"}, - {"AD_OUT57", NULL, "AD57 Enable"}, - {"AD_OUT68", NULL, "ab8500_0c"}, - {"AD_OUT68", NULL, "AD68 Enable"}, + {"ab8500_0c", NULL, "AD_OUT57"}, + {"AD_OUT57", NULL, "Main Supply"}, + {"AD_OUT57", NULL, "AD5 Channel Volume"}, + {"ab8500_0c", NULL, "AD_OUT68"}, + {"AD_OUT68", NULL, "Main Supply"}, + {"AD_OUT68", NULL, "AD6 Channel Volume"}, /* Digital Microphone path */ @@ -910,17 +862,25 @@ static const struct snd_soc_dapm_route ab8500_dapm_routes[] = { {"DMic 5", NULL, "V-DMIC"}, {"DMic 6", NULL, "V-DMIC"}, - {"AD1 Source Select", NULL, "DMic 1"}, - {"AD2 Source Select", NULL, "DMic 2"}, - {"AD3 Source Select", NULL, "DMic 3"}, - {"AD5 Source Select", NULL, "DMic 5"}, - {"AD6 Source Select", NULL, "DMic 6"}, + {"DMIC1", NULL, "DMic 1"}, + {"DMIC2", NULL, "DMic 2"}, + {"DMIC3", NULL, "DMic 3"}, + {"DMIC4", NULL, "DMic 4"}, + {"DMIC5", NULL, "DMic 5"}, + {"DMIC6", NULL, "DMic 6"}, - {"AD4 Channel Volume", NULL, "DMic 4"}, - {"AD4 Enable", NULL, "AD4 Channel Volume"}, + {"AD1 Source Select", "DMic 1", "DMIC1"}, + {"AD2 Source Select", "DMic 2", "DMIC2"}, + {"AD3 Source Select", "DMic 3", "DMIC3"}, + {"AD5 Source Select", "DMic 5", "DMIC5"}, + {"AD6 Source Select", "DMic 6", "DMIC6"}, - {"AD_OUT4", NULL, "ab8500_0c"}, - {"AD_OUT4", NULL, "AD4 Enable"}, + {"AD4 Channel Volume", NULL, "DMIC4"}, + {"AD4 Channel Volume", NULL, "AD34 Enable"}, + + {"ab8500_0c", NULL, "AD_OUT4"}, + {"AD_OUT4", NULL, "Main Supply"}, + {"AD_OUT4", NULL, "AD4 Channel Volume"}, /* LineIn Bypass path */ @@ -945,13 +905,13 @@ static const struct snd_soc_dapm_route ab8500_dapm_routes[] = { /* Sidetone Filter path */ - {"Sidetone Left Source", "LineIn Left", "AD12 Enable"}, - {"Sidetone Left Source", "LineIn Right", "AD12 Enable"}, - {"Sidetone Left Source", "Mic 1", "AD3 Enable"}, + {"Sidetone Left Source", "LineIn Left", "AD1 Channel Volume"}, + {"Sidetone Left Source", "LineIn Right", "AD2 Channel Volume"}, + {"Sidetone Left Source", "Mic 1", "AD3 Channel Volume"}, {"Sidetone Left Source", "Headset Left", "DA_IN1"}, - {"Sidetone Right Source", "LineIn Right", "AD12 Enable"}, - {"Sidetone Right Source", "Mic 1", "AD3 Enable"}, - {"Sidetone Right Source", "DMic 4", "AD4 Enable"}, + {"Sidetone Right Source", "LineIn Right", "AD2 Channel Volume"}, + {"Sidetone Right Source", "Mic 1", "AD3 Channel Volume"}, + {"Sidetone Right Source", "DMic 4", "AD4 Channel Volume"}, {"Sidetone Right Source", "Headset Right", "DA_IN2"}, {"STFIR1 Control", NULL, "Sidetone Left Source"}, @@ -979,78 +939,6 @@ static const struct snd_soc_dapm_route ab8500_dapm_routes_mic2_vamicx[] = { {"MIC2 V-AMICx Enable", NULL, "V-AMIC2"}, }; -/* - * Control-events - */ - -static int sid_status_control_get(struct snd_kcontrol *kcontrol, - struct snd_ctl_elem_value *ucontrol) -{ - struct snd_soc_component *component = snd_kcontrol_chip(kcontrol); - struct ab8500_codec_drvdata *drvdata = dev_get_drvdata(component->dev); - - mutex_lock(&drvdata->ctrl_lock); - ucontrol->value.enumerated.item[0] = drvdata->sid_status; - mutex_unlock(&drvdata->ctrl_lock); - - return 0; -} - -/* Write sidetone FIR-coefficients configuration sequence */ -static int sid_status_control_put(struct snd_kcontrol *kcontrol, - struct snd_ctl_elem_value *ucontrol) -{ - struct snd_soc_component *component = snd_kcontrol_chip(kcontrol); - struct ab8500_codec_drvdata *drvdata = dev_get_drvdata(component->dev); - unsigned int param, sidconf; - int status = 1; - - dev_dbg(component->dev, "%s: Enter\n", __func__); - - if (ucontrol->value.enumerated.item[0] != SID_APPLY_FIR) { - dev_err(component->dev, - "%s: ERROR: This control supports '%s' only!\n", - __func__, enum_sid_state[SID_APPLY_FIR]); - return -EIO; - } - - mutex_lock(&drvdata->ctrl_lock); - - sidconf = snd_soc_component_read(component, AB8500_SIDFIRCONF); - if (((sidconf & BIT(AB8500_SIDFIRCONF_FIRSIDBUSY)) != 0)) { - if ((sidconf & BIT(AB8500_SIDFIRCONF_ENFIRSIDS)) == 0) { - dev_err(component->dev, "%s: Sidetone busy while off!\n", - __func__); - status = -EPERM; - } else { - status = -EBUSY; - } - goto out; - } - - snd_soc_component_write(component, AB8500_SIDFIRADR, 0); - - for (param = 0; param < AB8500_SID_FIR_COEFFS; param++) { - snd_soc_component_write(component, AB8500_SIDFIRCOEF1, 0); - snd_soc_component_write(component, AB8500_SIDFIRCOEF2, 0); - } - - snd_soc_component_update_bits(component, AB8500_SIDFIRADR, - BIT(AB8500_SIDFIRADR_FIRSIDSET), - BIT(AB8500_SIDFIRADR_FIRSIDSET)); - snd_soc_component_update_bits(component, AB8500_SIDFIRADR, - BIT(AB8500_SIDFIRADR_FIRSIDSET), 0); - - drvdata->sid_status = SID_FIR_CONFIGURED; - -out: - mutex_unlock(&drvdata->ctrl_lock); - - dev_dbg(component->dev, "%s: Exit\n", __func__); - - return status; -} - /* * Controls - Non-DAPM ASoC */ @@ -1334,9 +1222,6 @@ static SOC_ENUM_SINGLE_DECL(soc_enum_bfifomast, AB8500_FIFOCONF3, AB8500_FIFOCONF3_BFIFOMAST_SHIFT, enum_slavemaster); -/* Sidetone */ -static SOC_ENUM_SINGLE_EXT_DECL(soc_enum_sidstate, enum_sid_state); - /* ANC */ static struct snd_kcontrol_new ab8500_ctrls[] = { @@ -1627,8 +1512,6 @@ static struct snd_kcontrol_new ab8500_ctrls[] = { AB8500_ANC_WARP_DELAY_MIN, AB8500_ANC_WARP_DELAY_MAX, 0), /* Sidetone */ - SOC_ENUM_EXT("Sidetone Status", soc_enum_sidstate, - sid_status_control_get, sid_status_control_put), SOC_SINGLE_STROBE("Sidetone Reset", AB8500_SIDFIRADR, AB8500_SIDFIRADR_FIRSIDSET, 0), }; @@ -1640,23 +1523,25 @@ static struct snd_kcontrol_new ab8500_ctrls[] = { static int ab8500_audio_init_audioblock(struct snd_soc_component *component) { int status; + u8 mask = AB8500_STW4500CTRL3_CLK32KOUT2DIS | + AB8500_STW4500CTRL3_RESETAUDN; dev_dbg(component->dev, "%s: Enter.\n", __func__); - /* Reset audio-registers and disable 32kHz-clock output 2 */ - status = ab8500_sysctrl_write(AB8500_STW4500CTRL3, - AB8500_STW4500CTRL3_CLK32KOUT2DIS | - AB8500_STW4500CTRL3_RESETAUDN, - AB8500_STW4500CTRL3_RESETAUDN); + /* Reset the audio registers and disable the unused 32 kHz output. */ + status = ab8500_sysctrl_write(AB8500_STW4500CTRL3, mask, + AB8500_STW4500CTRL3_CLK32KOUT2DIS); if (status < 0) return status; - return 0; + return ab8500_sysctrl_write(AB8500_STW4500CTRL3, mask, mask); } static int ab8500_audio_setup_mics(struct snd_soc_component *component, struct amic_settings *amics) { + struct device *dev = component->dev; + struct ab8500 *ab8500 = dev_get_drvdata(dev->parent); struct snd_soc_dapm_context *dapm = snd_soc_component_to_dapm(component); u8 value8; unsigned int value; @@ -1665,20 +1550,21 @@ static int ab8500_audio_setup_mics(struct snd_soc_component *component, dev_dbg(component->dev, "%s: Enter.\n", __func__); - /* Set DMic-clocks to outputs */ - status = abx500_get_register_interruptible(component->dev, AB8500_MISC, - AB8500_GPIO_DIR4_REG, - &value8); - if (status < 0) - return status; - value = value8 | GPIO27_DIR_OUTPUT | GPIO29_DIR_OUTPUT | - GPIO31_DIR_OUTPUT; - status = abx500_set_register_interruptible(component->dev, - AB8500_MISC, - AB8500_GPIO_DIR4_REG, - value); - if (status < 0) - return status; + /* Set DMic-clocks to outputs; these GPIOs do not exist on AB8505. */ + if (!is_ab8505(ab8500)) { + status = abx500_get_register_interruptible(dev, AB8500_MISC, + AB8500_GPIO_DIR4_REG, + &value8); + if (status < 0) + return status; + value = value8 | GPIO27_DIR_OUTPUT | GPIO29_DIR_OUTPUT | + GPIO31_DIR_OUTPUT; + status = abx500_set_register_interruptible(dev, AB8500_MISC, + AB8500_GPIO_DIR4_REG, + value); + if (status < 0) + return status; + } /* Attach regulators to AMic DAPM-paths */ dev_dbg(component->dev, "%s: Mic 1a regulator: %s\n", __func__, @@ -1747,149 +1633,91 @@ static int ab8500_audio_set_ear_cmv(struct snd_soc_component *component, return 0; } -static int ab8500_audio_set_bit_delay(struct snd_soc_dai *dai, - unsigned int delay) -{ - unsigned int mask, val; - struct snd_soc_component *component = dai->component; - - mask = BIT(AB8500_DIGIFCONF2_IF0DEL); - val = 0; - - switch (delay) { - case 0: - break; - case 1: - val |= BIT(AB8500_DIGIFCONF2_IF0DEL); - break; - default: - dev_err(dai->component->dev, - "%s: ERROR: Unsupported bit-delay (0x%x)!\n", - __func__, delay); - return -EINVAL; - } - - dev_dbg(dai->component->dev, "%s: IF0 Bit-delay: %d bits.\n", - __func__, delay); - snd_soc_component_update_bits(component, AB8500_DIGIFCONF2, mask, val); - - return 0; -} - -/* Gates clocking according format mask */ -static int ab8500_codec_set_dai_clock_gate(struct snd_soc_component *component, - unsigned int fmt) -{ - unsigned int mask; - unsigned int val; - - mask = BIT(AB8500_DIGIFCONF1_ENMASTGEN) | - BIT(AB8500_DIGIFCONF1_ENFSBITCLK0); - - val = BIT(AB8500_DIGIFCONF1_ENMASTGEN); - - switch (fmt & SND_SOC_DAIFMT_CLOCK_MASK) { - case SND_SOC_DAIFMT_CONT: /* continuous clock */ - dev_dbg(component->dev, "%s: IF0 Clock is continuous.\n", - __func__); - val |= BIT(AB8500_DIGIFCONF1_ENFSBITCLK0); - break; - case SND_SOC_DAIFMT_GATED: /* clock is gated */ - dev_dbg(component->dev, "%s: IF0 Clock is gated.\n", - __func__); - break; - default: - dev_err(component->dev, - "%s: ERROR: Unsupported clock mask (0x%x)!\n", - __func__, fmt & SND_SOC_DAIFMT_CLOCK_MASK); - return -EINVAL; - } - - snd_soc_component_update_bits(component, AB8500_DIGIFCONF1, mask, val); - - return 0; -} - static int ab8500_codec_set_dai_fmt(struct snd_soc_dai *dai, unsigned int fmt) { - unsigned int mask; - unsigned int val; struct snd_soc_component *component = dai->component; - int status; + unsigned int conf1_mask, conf1_val = 0; + unsigned int conf2_mask, conf2_val = 0; + unsigned int conf3_mask, conf3_val = 0; + bool provider = false; + int ret; dev_dbg(component->dev, "%s: Enter (fmt = 0x%x)\n", __func__, fmt); - mask = BIT(AB8500_DIGIFCONF3_IF1DATOIF0AD) | + conf3_mask = BIT(AB8500_DIGIFCONF3_IF1DATOIF0AD) | BIT(AB8500_DIGIFCONF3_IF1CLKTOIF0CLK) | BIT(AB8500_DIGIFCONF3_IF0BFIFOEN) | BIT(AB8500_DIGIFCONF3_IF0MASTER); - val = 0; switch (fmt & SND_SOC_DAIFMT_CLOCK_PROVIDER_MASK) { case SND_SOC_DAIFMT_CBP_CFP: - dev_dbg(dai->component->dev, + dev_dbg(component->dev, "%s: IF0 Master-mode: AB8500 provider.\n", __func__); - val |= BIT(AB8500_DIGIFCONF3_IF0MASTER); + conf3_val |= BIT(AB8500_DIGIFCONF3_IF0MASTER); + provider = true; break; case SND_SOC_DAIFMT_CBC_CFC: - dev_dbg(dai->component->dev, + dev_dbg(component->dev, "%s: IF0 Master-mode: AB8500 consumer.\n", __func__); break; case SND_SOC_DAIFMT_CBC_CFP: case SND_SOC_DAIFMT_CBP_CFC: - dev_err(dai->component->dev, + dev_err(component->dev, "%s: ERROR: The device is either a provider or a consumer.\n", __func__); fallthrough; default: - dev_err(dai->component->dev, - "%s: ERROR: Unsupporter clocking mask 0x%x\n", + dev_err(component->dev, + "%s: ERROR: Unsupported clocking mask 0x%x\n", __func__, fmt & SND_SOC_DAIFMT_CLOCK_PROVIDER_MASK); return -EINVAL; } - snd_soc_component_update_bits(component, AB8500_DIGIFCONF3, mask, val); - - /* Set clock gating */ - status = ab8500_codec_set_dai_clock_gate(component, fmt); - if (status) { - dev_err(dai->component->dev, - "%s: ERROR: Failed to set clock gate (%d).\n", - __func__, status); - return status; + conf1_mask = BIT(AB8500_DIGIFCONF1_ENMASTGEN) | + BIT(AB8500_DIGIFCONF1_ENFSBITCLK0); + switch (fmt & SND_SOC_DAIFMT_CLOCK_MASK) { + case SND_SOC_DAIFMT_CONT: + if (provider) + conf1_val = conf1_mask; + break; + case SND_SOC_DAIFMT_GATED: + if (provider) + conf1_val = BIT(AB8500_DIGIFCONF1_ENMASTGEN); + break; + default: + dev_err(component->dev, "%s: Unsupported clock mask 0x%x\n", + __func__, fmt & SND_SOC_DAIFMT_CLOCK_MASK); + return -EINVAL; } - /* Setting data transfer format */ - - mask = BIT(AB8500_DIGIFCONF2_IF0FORMAT0) | - BIT(AB8500_DIGIFCONF2_IF0FORMAT1) | - BIT(AB8500_DIGIFCONF2_FSYNC0P) | - BIT(AB8500_DIGIFCONF2_BITCLK0P); - val = 0; + conf2_mask = BIT(AB8500_DIGIFCONF2_IF0FORMAT0) | + BIT(AB8500_DIGIFCONF2_IF0FORMAT1) | + BIT(AB8500_DIGIFCONF2_IF0DEL) | + BIT(AB8500_DIGIFCONF2_FSYNC0P) | + BIT(AB8500_DIGIFCONF2_BITCLK0P); switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) { case SND_SOC_DAIFMT_I2S: /* I2S mode */ - dev_dbg(dai->component->dev, "%s: IF0 Protocol: I2S\n", __func__); - val |= BIT(AB8500_DIGIFCONF2_IF0FORMAT1); - ab8500_audio_set_bit_delay(dai, 0); + dev_dbg(component->dev, "%s: IF0 Protocol: I2S\n", __func__); + conf2_val |= BIT(AB8500_DIGIFCONF2_IF0FORMAT1) | + BIT(AB8500_DIGIFCONF2_IF0DEL); break; case SND_SOC_DAIFMT_DSP_A: /* L data MSB after FRM LRC */ - dev_dbg(dai->component->dev, + dev_dbg(component->dev, "%s: IF0 Protocol: DSP A (TDM)\n", __func__); - val |= BIT(AB8500_DIGIFCONF2_IF0FORMAT0); - ab8500_audio_set_bit_delay(dai, 1); + conf2_val |= BIT(AB8500_DIGIFCONF2_IF0FORMAT0) | + BIT(AB8500_DIGIFCONF2_IF0DEL); break; case SND_SOC_DAIFMT_DSP_B: /* L data MSB during FRM LRC */ - dev_dbg(dai->component->dev, + dev_dbg(component->dev, "%s: IF0 Protocol: DSP B (TDM)\n", __func__); - val |= BIT(AB8500_DIGIFCONF2_IF0FORMAT0); - ab8500_audio_set_bit_delay(dai, 0); + conf2_val |= BIT(AB8500_DIGIFCONF2_IF0FORMAT0); break; default: - dev_err(dai->component->dev, + dev_err(component->dev, "%s: ERROR: Unsupported format (0x%x)!\n", __func__, fmt & SND_SOC_DAIFMT_FORMAT_MASK); return -EINVAL; @@ -1897,39 +1725,50 @@ static int ab8500_codec_set_dai_fmt(struct snd_soc_dai *dai, unsigned int fmt) switch (fmt & SND_SOC_DAIFMT_INV_MASK) { case SND_SOC_DAIFMT_NB_NF: /* normal bit clock + frame */ - dev_dbg(dai->component->dev, + dev_dbg(component->dev, "%s: IF0: Normal bit clock, normal frame\n", __func__); break; case SND_SOC_DAIFMT_NB_IF: /* normal BCLK + inv FRM */ - dev_dbg(dai->component->dev, + dev_dbg(component->dev, "%s: IF0: Normal bit clock, inverted frame\n", __func__); - val |= BIT(AB8500_DIGIFCONF2_FSYNC0P); + conf2_val |= BIT(AB8500_DIGIFCONF2_FSYNC0P); break; case SND_SOC_DAIFMT_IB_NF: /* invert BCLK + nor FRM */ - dev_dbg(dai->component->dev, + dev_dbg(component->dev, "%s: IF0: Inverted bit clock, normal frame\n", __func__); - val |= BIT(AB8500_DIGIFCONF2_BITCLK0P); + conf2_val |= BIT(AB8500_DIGIFCONF2_BITCLK0P); break; case SND_SOC_DAIFMT_IB_IF: /* invert BCLK + FRM */ - dev_dbg(dai->component->dev, + dev_dbg(component->dev, "%s: IF0: Inverted bit clock, inverted frame\n", __func__); - val |= BIT(AB8500_DIGIFCONF2_FSYNC0P); - val |= BIT(AB8500_DIGIFCONF2_BITCLK0P); + conf2_val |= BIT(AB8500_DIGIFCONF2_FSYNC0P) | + BIT(AB8500_DIGIFCONF2_BITCLK0P); break; default: - dev_err(dai->component->dev, + dev_err(component->dev, "%s: ERROR: Unsupported INV mask 0x%x\n", __func__, fmt & SND_SOC_DAIFMT_INV_MASK); return -EINVAL; } - snd_soc_component_update_bits(component, AB8500_DIGIFCONF2, mask, val); + ret = snd_soc_component_update_bits(component, AB8500_DIGIFCONF3, + conf3_mask, conf3_val); + if (ret < 0) + return ret; - return 0; + ret = snd_soc_component_update_bits(component, AB8500_DIGIFCONF1, + conf1_mask, conf1_val); + if (ret < 0) + return ret; + + ret = snd_soc_component_update_bits(component, AB8500_DIGIFCONF2, + conf2_mask, conf2_val); + + return ret < 0 ? ret : 0; } static int ab8500_codec_set_dai_tdm_slot(struct snd_soc_dai *dai, @@ -1937,23 +1776,27 @@ static int ab8500_codec_set_dai_tdm_slot(struct snd_soc_dai *dai, int slots, int slot_width) { struct snd_soc_component *component = dai->component; - unsigned int val, mask, slot, slots_active; + unsigned int active_mask, clock_ratio, slot, value, ad_out, reg; + unsigned int tx_active, rx_active; + unsigned int conf1_val, conf2_val; + unsigned int mask; + int channel, ret; mask = BIT(AB8500_DIGIFCONF2_IF0WL0) | BIT(AB8500_DIGIFCONF2_IF0WL1); - val = 0; + conf2_val = 0; switch (slot_width) { case 16: break; case 20: - val |= BIT(AB8500_DIGIFCONF2_IF0WL0); + conf2_val |= BIT(AB8500_DIGIFCONF2_IF0WL0); break; case 24: - val |= BIT(AB8500_DIGIFCONF2_IF0WL1); + conf2_val |= BIT(AB8500_DIGIFCONF2_IF0WL1); break; case 32: - val |= BIT(AB8500_DIGIFCONF2_IF0WL1) | + conf2_val |= BIT(AB8500_DIGIFCONF2_IF0WL1) | BIT(AB8500_DIGIFCONF2_IF0WL0); break; default: @@ -1962,27 +1805,11 @@ static int ab8500_codec_set_dai_tdm_slot(struct snd_soc_dai *dai, return -EINVAL; } - dev_dbg(dai->component->dev, "%s: IF0 slot-width: %d bits.\n", - __func__, slot_width); - snd_soc_component_update_bits(component, AB8500_DIGIFCONF2, mask, val); - - /* Setup TDM clocking according to slot count */ - dev_dbg(dai->component->dev, "%s: Slots, total: %d\n", __func__, slots); - mask = BIT(AB8500_DIGIFCONF1_IF0BITCLKOS0) | - BIT(AB8500_DIGIFCONF1_IF0BITCLKOS1); switch (slots) { case 2: - val = AB8500_MASK_NONE; - break; case 4: - val = BIT(AB8500_DIGIFCONF1_IF0BITCLKOS0); - break; case 8: - val = BIT(AB8500_DIGIFCONF1_IF0BITCLKOS1); - break; case 16: - val = BIT(AB8500_DIGIFCONF1_IF0BITCLKOS0) | - BIT(AB8500_DIGIFCONF1_IF0BITCLKOS1); break; default: dev_err(dai->component->dev, @@ -1990,92 +1817,134 @@ static int ab8500_codec_set_dai_tdm_slot(struct snd_soc_dai *dai, __func__, slots); return -EINVAL; } - snd_soc_component_update_bits(component, AB8500_DIGIFCONF1, mask, val); - - /* Setup TDM DA according to active tx slots */ - if (tx_mask & ~0xff) - return -EINVAL; - - mask = AB8500_DASLOTCONFX_SLTODAX_MASK; - tx_mask = tx_mask << AB8500_DA_DATA0_OFFSET; - slots_active = hweight32(tx_mask); - - dev_dbg(dai->component->dev, "%s: Slots, active, TX: %d\n", __func__, - slots_active); - - switch (slots_active) { - case 0: + clock_ratio = slots * slot_width; + switch (clock_ratio) { + case 32: + conf1_val = 0; break; - case 1: - slot = ffs(tx_mask); - snd_soc_component_update_bits(component, AB8500_DASLOTCONF1, mask, slot); - snd_soc_component_update_bits(component, AB8500_DASLOTCONF3, mask, slot); - snd_soc_component_update_bits(component, AB8500_DASLOTCONF2, mask, slot); - snd_soc_component_update_bits(component, AB8500_DASLOTCONF4, mask, slot); + case 64: + conf1_val = BIT(AB8500_DIGIFCONF1_IF0BITCLKOS0); break; - case 2: - slot = ffs(tx_mask); - snd_soc_component_update_bits(component, AB8500_DASLOTCONF1, mask, slot); - snd_soc_component_update_bits(component, AB8500_DASLOTCONF3, mask, slot); - slot = fls(tx_mask); - snd_soc_component_update_bits(component, AB8500_DASLOTCONF2, mask, slot); - snd_soc_component_update_bits(component, AB8500_DASLOTCONF4, mask, slot); + case 128: + conf1_val = BIT(AB8500_DIGIFCONF1_IF0BITCLKOS1); break; - case 8: - dev_dbg(dai->component->dev, - "%s: In 8-channel mode DA-from-slot mapping is set manually.", - __func__); + case 256: + conf1_val = BIT(AB8500_DIGIFCONF1_IF0BITCLKOS0) | + BIT(AB8500_DIGIFCONF1_IF0BITCLKOS1); break; default: - dev_err(dai->component->dev, - "%s: Unsupported number of active TX-slots (%d)!\n", - __func__, slots_active); + dev_err(component->dev, "%s: Unsupported BCLK ratio (%u)!\n", + __func__, clock_ratio); return -EINVAL; } - /* Setup TDM AD according to active RX-slots */ + active_mask = GENMASK(min(slots, 8) - 1, 0); + if ((tx_mask | rx_mask) & ~active_mask) { + dev_err(component->dev, "%s: Slot mask exceeds slot count\n", + __func__); + return -EINVAL; + } - if (rx_mask & ~0xff) + tx_active = hweight32(tx_mask); + rx_active = hweight32(rx_mask); + if (tx_active != 0 && tx_active != 1 && tx_active != 2 && + tx_active != 8) { + dev_err(component->dev, "%s: Unsupported active TX slots (%u)!\n", + __func__, tx_active); return -EINVAL; + } + if (rx_active != 0 && rx_active != 1 && rx_active != 2 && + rx_active != 8) { + dev_err(component->dev, "%s: Unsupported active RX slots (%u)!\n", + __func__, rx_active); + return -EINVAL; + } - rx_mask = rx_mask << AB8500_AD_DATA0_OFFSET; - slots_active = hweight32(rx_mask); + dev_dbg(component->dev, + "%s: %d slots of %d bits, TX active: %u, RX active: %u\n", + __func__, slots, slot_width, tx_active, rx_active); - dev_dbg(dai->component->dev, "%s: Slots, active, RX: %d\n", __func__, - slots_active); + ret = snd_soc_component_update_bits(component, AB8500_DIGIFCONF2, + mask, conf2_val); + if (ret < 0) + return ret; - switch (slots_active) { - case 0: - break; - case 1: - slot = ffs(rx_mask); - snd_soc_component_update_bits(component, AB8500_ADSLOTSEL(slot), - AB8500_MASK_SLOT(slot), - AB8500_ADSLOTSELX_AD_OUT_TO_SLOT(AB8500_AD_OUT3, slot)); - break; - case 2: - slot = ffs(rx_mask); - snd_soc_component_update_bits(component, - AB8500_ADSLOTSEL(slot), - AB8500_MASK_SLOT(slot), - AB8500_ADSLOTSELX_AD_OUT_TO_SLOT(AB8500_AD_OUT3, slot)); - slot = fls(rx_mask); - snd_soc_component_update_bits(component, - AB8500_ADSLOTSEL(slot), - AB8500_MASK_SLOT(slot), - AB8500_ADSLOTSELX_AD_OUT_TO_SLOT(AB8500_AD_OUT2, slot)); - break; - case 8: - dev_dbg(dai->component->dev, - "%s: In 8-channel mode AD-to-slot mapping is set manually.", - __func__); - break; - default: - dev_err(dai->component->dev, - "%s: Unsupported number of active RX-slots (%d)!\n", - __func__, slots_active); - return -EINVAL; + mask = BIT(AB8500_DIGIFCONF1_IF0BITCLKOS0) | + BIT(AB8500_DIGIFCONF1_IF0BITCLKOS1); + ret = snd_soc_component_update_bits(component, AB8500_DIGIFCONF1, + mask, conf1_val); + if (ret < 0) + return ret; + + mask = AB8500_DASLOTCONFX_SLTODAX_MASK; + if (tx_active == 1 || tx_active == 2) { + slot = __ffs(tx_mask) + AB8500_DA_DATA0_OFFSET; + reg = AB8500_DASLOTCONF1; + ret = snd_soc_component_update_bits(component, reg, mask, slot); + if (ret < 0) + return ret; + reg = AB8500_DASLOTCONF3; + ret = snd_soc_component_update_bits(component, reg, mask, slot); + if (ret < 0) + return ret; + + if (tx_active == 2) + slot = __fls(tx_mask) + AB8500_DA_DATA0_OFFSET; + reg = AB8500_DASLOTCONF2; + ret = snd_soc_component_update_bits(component, reg, mask, slot); + if (ret < 0) + return ret; + reg = AB8500_DASLOTCONF4; + ret = snd_soc_component_update_bits(component, reg, mask, slot); + if (ret < 0) + return ret; + } else if (tx_active == 8) { + channel = 0; + for (slot = 0; slot < 8; slot++) { + if (!(tx_mask & BIT(slot))) + continue; + reg = AB8500_DASLOTCONF1 + channel++; + value = slot + AB8500_DA_DATA0_OFFSET; + ret = snd_soc_component_update_bits(component, reg, mask, value); + if (ret < 0) + return ret; + } + } + + if (rx_active == 1 || rx_active == 2) { + slot = __ffs(rx_mask) + AB8500_AD_DATA0_OFFSET; + value = AB8500_ADSLOTSELX_AD_OUT_TO_SLOT(AB8500_AD_OUT3, + slot); + reg = AB8500_ADSLOTSEL(slot); + mask = AB8500_MASK_SLOT(slot); + ret = snd_soc_component_update_bits(component, reg, mask, value); + if (ret < 0) + return ret; + + if (rx_active == 2) { + slot = __fls(rx_mask) + AB8500_AD_DATA0_OFFSET; + value = AB8500_ADSLOTSELX_AD_OUT_TO_SLOT(AB8500_AD_OUT2, + slot); + reg = AB8500_ADSLOTSEL(slot); + mask = AB8500_MASK_SLOT(slot); + ret = snd_soc_component_update_bits(component, reg, mask, value); + if (ret < 0) + return ret; + } + } else if (rx_active == 8) { + channel = 0; + for (slot = 0; slot < 8; slot++) { + if (!(rx_mask & BIT(slot))) + continue; + ad_out = AB8500_AD_OUT1 + channel++; + value = AB8500_ADSLOTSELX_AD_OUT_TO_SLOT(ad_out, slot); + reg = AB8500_ADSLOTSEL(slot); + mask = AB8500_MASK_SLOT(slot); + ret = snd_soc_component_update_bits(component, reg, mask, value); + if (ret < 0) + return ret; + } } return 0; @@ -2172,10 +2041,8 @@ static void ab8500_codec_of_probe(struct device *dev, struct device_node *np, static int ab8500_codec_probe(struct snd_soc_component *component) { - struct snd_soc_dapm_context *dapm = snd_soc_component_to_dapm(component); struct device *dev = component->dev; struct device_node *np = dev->of_node; - struct ab8500_codec_drvdata *drvdata = dev_get_drvdata(dev); struct ab8500_codec_platform_data codec_pdata; int status; @@ -2183,6 +2050,13 @@ static int ab8500_codec_probe(struct snd_soc_component *component) ab8500_codec_of_probe(dev, np, &codec_pdata); + status = ab8500_audio_init_audioblock(component); + if (status < 0) { + dev_err(dev, "%s: failed to init audio-block (%d)!\n", + __func__, status); + return status; + } + status = ab8500_audio_setup_mics(component, &codec_pdata.amics); if (status < 0) { pr_err("%s: Failed to setup mics (%d)!\n", __func__, status); @@ -2195,23 +2069,12 @@ static int ab8500_codec_probe(struct snd_soc_component *component) return status; } - status = ab8500_audio_init_audioblock(component); - if (status < 0) { - dev_err(dev, "%s: failed to init audio-block (%d)!\n", - __func__, status); - return status; - } - /* Override HW-defaults */ snd_soc_component_write(component, AB8500_ANACONF5, BIT(AB8500_ANACONF5_HSAUTOEN)); snd_soc_component_write(component, AB8500_SHORTCIRCONF, BIT(AB8500_SHORTCIRCONF_HSZCDDIS)); - snd_soc_dapm_disable_pin(dapm, "ANC Configure Input"); - - mutex_init(&drvdata->ctrl_lock); - return status; } @@ -2240,7 +2103,6 @@ static int ab8500_codec_driver_probe(struct platform_device *pdev) GFP_KERNEL); if (!drvdata) return -ENOMEM; - drvdata->sid_status = SID_UNCONFIGURED; dev_set_drvdata(&pdev->dev, drvdata); drvdata->regmap = devm_regmap_init(&pdev->dev, NULL, &pdev->dev, diff --git a/sound/soc/codecs/cs35l56-i2c.c b/sound/soc/codecs/cs35l56-i2c.c index 4f6ddf1c5a3f6a..5e69ddbe342a1d 100644 --- a/sound/soc/codecs/cs35l56-i2c.c +++ b/sound/soc/codecs/cs35l56-i2c.c @@ -51,15 +51,7 @@ static int cs35l56_i2c_probe(struct i2c_client *client) return dev_err_probe(cs35l56->base.dev, ret, "Failed to allocate register map\n"); } - ret = cs35l56_common_probe(cs35l56); - if (ret != 0) - return ret; - - ret = cs35l56_irq_request(&cs35l56->base, client->irq); - if (ret < 0) - cs35l56_remove(cs35l56); - - return ret; + return cs35l56_common_probe(cs35l56, client->irq); } static void cs35l56_i2c_remove(struct i2c_client *client) diff --git a/sound/soc/codecs/cs35l56-sdw.c b/sound/soc/codecs/cs35l56-sdw.c index 0a55b93b96f966..a3812ab4c02271 100644 --- a/sound/soc/codecs/cs35l56-sdw.c +++ b/sound/soc/codecs/cs35l56-sdw.c @@ -483,11 +483,7 @@ static int cs35l56_sdw_probe(struct sdw_slave *peripheral, const struct sdw_devi /* Start in cache-only until device is enumerated */ regcache_cache_only(cs35l56->base.regmap, true); - ret = cs35l56_common_probe(cs35l56); - if (ret != 0) - return ret; - - return 0; + return cs35l56_common_probe(cs35l56, -EINVAL); } static void cs35l56_sdw_remove(struct sdw_slave *peripheral) diff --git a/sound/soc/codecs/cs35l56-spi.c b/sound/soc/codecs/cs35l56-spi.c index b1eb924a5b6ccf..21b18da9e73d1d 100644 --- a/sound/soc/codecs/cs35l56-spi.c +++ b/sound/soc/codecs/cs35l56-spi.c @@ -40,15 +40,7 @@ static int cs35l56_spi_probe(struct spi_device *spi) if (ret) return ret; - ret = cs35l56_common_probe(cs35l56); - if (ret != 0) - return ret; - - ret = cs35l56_irq_request(&cs35l56->base, spi->irq); - if (ret < 0) - cs35l56_remove(cs35l56); - - return ret; + return cs35l56_common_probe(cs35l56, spi->irq); } static void cs35l56_spi_remove(struct spi_device *spi) diff --git a/sound/soc/codecs/cs35l56.c b/sound/soc/codecs/cs35l56.c index 063ef7a70de03d..8beef93ac4676b 100644 --- a/sound/soc/codecs/cs35l56.c +++ b/sound/soc/codecs/cs35l56.c @@ -18,9 +18,11 @@ #include #include #include +#include #include #include #include +#include #include #include #include @@ -37,6 +39,13 @@ #include "wm_adsp.h" #include "cs35l56.h" +/* + * snd_soc_register_component() can call component_probe() on all instances + * in a card, so deferred registration must be protected across all instances. + */ +static DEFINE_MUTEX(cs35l56_component_register_lock); +static bool cs35l56_shutting_down; + void cs35l56_mask_soundwire_interrupts(struct sdw_slave *peripheral) { /* @@ -1368,12 +1377,6 @@ static int _cs35l56_component_probe(struct snd_soc_component *component) BUILD_BUG_ON(ARRAY_SIZE(cs35l56_tx_input_texts) != ARRAY_SIZE(cs35l56_tx_input_values)); - if (!wait_for_completion_timeout(&cs35l56->init_completion, - msecs_to_jiffies(5000))) { - dev_err(cs35l56->base.dev, "%s: init_completion timed out\n", __func__); - return -ENODEV; - } - cs35l56->dsp.part = kasprintf(GFP_KERNEL, "cs35l%02x", cs35l56->base.type); if (!cs35l56->dsp.part) return -ENOMEM; @@ -1941,7 +1944,46 @@ static int cs35l56_try_get_broken_sdca_spkid_gpio(struct cs35l56_private *cs35l5 return ret; } -int cs35l56_common_probe(struct cs35l56_private *cs35l56) +static int cs35l56_component_register(struct cs35l56_private *cs35l56) +{ + int ret; + + ret = snd_soc_register_component(cs35l56->base.dev, + &soc_component_dev_cs35l56, + cs35l56_dai, ARRAY_SIZE(cs35l56_dai)); + if (ret < 0) { + dev_err(cs35l56->base.dev, "Register codec failed: %d\n", ret); + return ret; + } + + cs35l56->component_registered = true; + + return 0; +} + +static void cs35l56_component_register_work(struct work_struct *work) +{ + struct cs35l56_private *cs35l56 = container_of(work, + struct cs35l56_private, + component_register_work); + int ret; + + guard(mutex)(&cs35l56_component_register_lock); + + if (cs35l56_shutting_down) + return; + + PM_RUNTIME_ACQUIRE_AUTOSUSPEND(cs35l56->base.dev, pm_err); + ret = PM_RUNTIME_ACQUIRE_ERR(&pm_err); + if (ret) { + dev_err(cs35l56->base.dev, "register_work failed to get pm_runtime: %d\n", ret); + return; + } + + cs35l56_component_register(cs35l56); +} + +int cs35l56_common_probe(struct cs35l56_private *cs35l56, int irq) { int ret; @@ -1949,6 +1991,7 @@ int cs35l56_common_probe(struct cs35l56_private *cs35l56) mutex_init(&cs35l56->base.irq_lock); cs35l56->base.cal_index = -1; cs35l56->speaker_id = -ENOENT; + INIT_WORK(&cs35l56->component_register_work, cs35l56_component_register_work); dev_set_drvdata(cs35l56->base.dev, cs35l56); @@ -2018,16 +2061,29 @@ int cs35l56_common_probe(struct cs35l56_private *cs35l56) goto err_remove_wm_adsp; } - ret = snd_soc_register_component(cs35l56->base.dev, - &soc_component_dev_cs35l56, - cs35l56_dai, ARRAY_SIZE(cs35l56_dai)); - if (ret < 0) { - dev_err_probe(cs35l56->base.dev, ret, "Register codec failed\n"); + ret = cs35l56_irq_request(&cs35l56->base, irq); + if (ret) goto err_remove_wm_adsp; + + /* + * Defer calling snd_soc_register_component() on SoundWire to prevent + * a deadlock where it calls our component_probe(), which requires the + * SoundWire enumeration to complete, but because we are still in probe() + * the SoundWire core will not call the update_status() callback. At time + * of writing snd_soc_register_component() never returns EPROBE_DEFER. + */ + if (!cs35l56->sdw_peripheral) { + ret = cs35l56_component_register(cs35l56); + if (ret < 0) + goto err_free_irq; } return 0; +err_free_irq: + if (cs35l56->base.irq) + devm_free_irq(cs35l56->base.dev, cs35l56->base.irq, &cs35l56->base); + err_remove_wm_adsp: wm_adsp2_remove(&cs35l56->dsp); @@ -2049,6 +2105,7 @@ EXPORT_SYMBOL_NS_GPL(cs35l56_common_probe, "SND_SOC_CS35L56_CORE"); int cs35l56_init(struct cs35l56_private *cs35l56) { + bool first_time_init = !cs35l56->base.init_done; int ret; /* @@ -2125,13 +2182,23 @@ post_soft_reset: cs35l56->base.init_done = true; complete_all(&cs35l56->init_completion); + if (cs35l56->sdw_peripheral && first_time_init) { + /* + * Hardware now accessible, queue work to call + * snd_soc_register_component(). + */ + queue_work(system_freezable_wq, &cs35l56->component_register_work); + } + return 0; } EXPORT_SYMBOL_NS_GPL(cs35l56_init, "SND_SOC_CS35L56_CORE"); void cs35l56_remove(struct cs35l56_private *cs35l56) { - snd_soc_unregister_component(cs35l56->base.dev); + cancel_work_sync(&cs35l56->component_register_work); + if (cs35l56->component_registered) + snd_soc_unregister_component(cs35l56->base.dev); cs35l56->base.init_done = false; @@ -2166,6 +2233,37 @@ EXPORT_NS_GPL_DEV_PM_OPS(cs35l56_pm_ops_i2c_spi, SND_SOC_CS35L56_CORE) = { }; #endif +static int cs35l56_reboot_notify(struct notifier_block *nb, + unsigned long action, void *data) +{ + guard(mutex)(&cs35l56_component_register_lock); + cs35l56_shutting_down = true; + + return NOTIFY_DONE; +} + +static struct notifier_block cs35l56_reboot_notifier = { + .notifier_call = cs35l56_reboot_notify, +}; + +static int __init cs35l56_modinit(void) +{ + /* + * Use reboot notifier to prevent race between shutdown and + * snd_soc_register_component(). Driver shutdown() callback would + * run too late, after device_shutdown() is already walking the + * device list that component registration can modify. + */ + return register_reboot_notifier(&cs35l56_reboot_notifier); +} +module_init(cs35l56_modinit); + +static void __exit cs35l56_modexit(void) +{ + unregister_reboot_notifier(&cs35l56_reboot_notifier); +} +module_exit(cs35l56_modexit); + MODULE_DESCRIPTION("ASoC CS35L56 driver"); MODULE_IMPORT_NS("SND_SOC_CS35L56_SHARED"); MODULE_IMPORT_NS("SND_SOC_CS_AMP_LIB"); diff --git a/sound/soc/codecs/cs35l56.h b/sound/soc/codecs/cs35l56.h index 9acd2e7e17c93a..6adba4d2da1f82 100644 --- a/sound/soc/codecs/cs35l56.h +++ b/sound/soc/codecs/cs35l56.h @@ -32,6 +32,7 @@ struct sdw_slave; struct cs35l56_private { struct wm_adsp dsp; /* must be first member */ struct cs35l56_base base; + struct work_struct component_register_work; struct work_struct dsp_work; struct workqueue_struct *dsp_wq; struct snd_soc_component *component; @@ -43,6 +44,7 @@ struct cs35l56_private { bool sdw_irq_no_unmask; bool soft_resetting; bool sdw_attached; + bool component_registered; struct completion init_completion; int speaker_id; @@ -78,7 +80,7 @@ int cs35l56_system_resume_early(struct device *dev); int cs35l56_system_resume(struct device *dev); irqreturn_t cs35l56_irq(int irq, void *data); int cs35l56_irq_request(struct cs35l56_base *cs35l56_base, int irq); -int cs35l56_common_probe(struct cs35l56_private *cs35l56); +int cs35l56_common_probe(struct cs35l56_private *cs35l56, int irq); int cs35l56_init(struct cs35l56_private *cs35l56); void cs35l56_remove(struct cs35l56_private *cs35l56); diff --git a/sound/soc/codecs/mt6351.c b/sound/soc/codecs/mt6351.c index 1768c249650d8e..3be0491a2588c0 100644 --- a/sound/soc/codecs/mt6351.c +++ b/sound/soc/codecs/mt6351.c @@ -1478,6 +1478,7 @@ static const struct of_device_id mt6351_of_match[] = { {.compatible = "mediatek,mt6351-sound",}, {} }; +MODULE_DEVICE_TABLE(of, mt6351_of_match); static struct platform_driver mt6351_codec_driver = { .driver = { diff --git a/sound/soc/fsl/fsl_micfil.c b/sound/soc/fsl/fsl_micfil.c index 60ac8eabab9dab..5d8f0f76ab46fa 100644 --- a/sound/soc/fsl/fsl_micfil.c +++ b/sound/soc/fsl/fsl_micfil.c @@ -953,12 +953,17 @@ static int fsl_micfil_reparent_rootclk(struct fsl_micfil *micfil, unsigned int s /* Get root clock */ clk = micfil->mclk; - /* Disable clock first, for it was enabled by pm_runtime */ + /* Reparent root clock to the PLL matching this sample rate */ fsl_asoc_reparent_pll_clocks(dev, clk, micfil->pll8k_clk, micfil->pll11k_clk, ratio); - ret = clk_prepare_enable(clk); - if (ret) - return ret; + + /* Enable only once; hw_params can be called multiple times */ + if (!micfil->mclk_flag) { + ret = clk_prepare_enable(clk); + if (ret) + return ret; + micfil->mclk_flag = true; + } return 0; } @@ -991,8 +996,6 @@ static int fsl_micfil_hw_params(struct snd_pcm_substream *substream, if (ret) return ret; - micfil->mclk_flag = true; - /* floor(K * CLKDIV) */ switch (micfil->quality) { case QUALITY_HIGH: @@ -1068,8 +1071,10 @@ static int fsl_micfil_hw_free(struct snd_pcm_substream *substream, { struct fsl_micfil *micfil = snd_soc_dai_get_drvdata(dai); - clk_disable_unprepare(micfil->mclk); - micfil->mclk_flag = false; + if (micfil->mclk_flag) { + clk_disable_unprepare(micfil->mclk); + micfil->mclk_flag = false; + } return 0; } diff --git a/sound/soc/intel/atom/sst/sst_pci.c b/sound/soc/intel/atom/sst/sst_pci.c index 44bb11c694905f..1a53c993b57fcc 100644 --- a/sound/soc/intel/atom/sst/sst_pci.c +++ b/sound/soc/intel/atom/sst/sst_pci.c @@ -167,6 +167,7 @@ static const struct pci_device_id intel_sst_ids[] = { { PCI_DEVICE_DATA(INTEL, SST_TNG, 0) }, { 0, } }; +MODULE_DEVICE_TABLE(pci, intel_sst_ids); static struct pci_driver sst_driver = { .name = SST_DRV_NAME, diff --git a/sound/soc/intel/avs/core.c b/sound/soc/intel/avs/core.c index 1a53856c2ffbef..a6b877f41e8b25 100644 --- a/sound/soc/intel/avs/core.c +++ b/sound/soc/intel/avs/core.c @@ -473,8 +473,13 @@ static int avs_pci_probe(struct pci_dev *pci, const struct pci_device_id *id) } snd_hdac_bus_parse_capabilities(bus); - if (bus->mlcap) - snd_hdac_ext_bus_get_ml_capabilities(bus); + if (bus->mlcap) { + ret = snd_hdac_ext_bus_get_ml_capabilities(bus); + if (ret < 0) { + dev_err(dev, "failed to get ml capabilities: %d\n", ret); + goto err_ml_cap; + } + } if (dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64))) dma_set_mask_and_coherent(dev, DMA_BIT_MASK(32)); @@ -516,6 +521,8 @@ err_acquire_irq: snd_hdac_bus_free_stream_pages(bus); snd_hdac_ext_stream_free_all(bus); err_init_streams: + snd_hdac_ext_link_free_all(bus); +err_ml_cap: iounmap(adev->dsp_ba); err_remap_bar4: iounmap(bus->remap_addr); diff --git a/sound/soc/intel/avs/debugfs.c b/sound/soc/intel/avs/debugfs.c index 701c247227bf95..fc321f61fc9294 100644 --- a/sound/soc/intel/avs/debugfs.c +++ b/sound/soc/intel/avs/debugfs.c @@ -8,6 +8,7 @@ #include #include +#include #include #include #include @@ -235,15 +236,20 @@ static int strace_open(struct inode *inode, struct file *file) if (!try_module_get(adev->dev->driver->owner)) return -ENODEV; - if (kfifo_initialized(&adev->trace_fifo)) - return -EBUSY; + if (kfifo_initialized(&adev->trace_fifo)) { + ret = -EBUSY; + goto err; + } ret = kfifo_alloc(&adev->trace_fifo, PAGE_SIZE, GFP_KERNEL); if (ret < 0) - return ret; + goto err; file->private_data = adev; return 0; +err: + module_put(adev->dev->driver->owner); + return ret; } static int strace_release(struct inode *inode, struct file *file) diff --git a/sound/soc/intel/avs/path.c b/sound/soc/intel/avs/path.c index 2291f9728a54f3..de699e23c9e22d 100644 --- a/sound/soc/intel/avs/path.c +++ b/sound/soc/intel/avs/path.c @@ -838,15 +838,10 @@ static int avs_path_module_type_create(struct avs_dev *adev, struct avs_path_mod static int avs_path_module_send_init_configs(struct avs_dev *adev, struct avs_path_module *mod) { - struct avs_soc_component *acomp; - - acomp = to_avs_soc_component(mod->template->owner->owner->owner->owner->comp); - - u32 num_ids = mod->template->num_config_ids; - u32 *ids = mod->template->config_ids; + struct avs_tplg_module *template = mod->template; - for (int i = 0; i < num_ids; i++) { - struct avs_tplg_init_config *config = &acomp->tplg->init_configs[ids[i]]; + for (int i = 0; i < template->num_init_configs; i++) { + struct avs_tplg_init_config *config = template->init_configs[i]; size_t len = config->length; void *data = config->data; u32 param = config->param; diff --git a/sound/soc/intel/avs/pcm.c b/sound/soc/intel/avs/pcm.c index 797b9c9163b492..094ea1366ea8fc 100644 --- a/sound/soc/intel/avs/pcm.c +++ b/sound/soc/intel/avs/pcm.c @@ -6,6 +6,7 @@ // Amadeusz Slawinski // +#include #include #include #include @@ -987,13 +988,25 @@ static int avs_component_load_libraries(struct avs_soc_component *acomp) return ret; } +static int avs_request_topology(struct snd_soc_component *component, const char *name, + const struct firmware **fw) +{ + char *fullname __free(kfree) = NULL; + + fullname = kasprintf(GFP_KERNEL, "%s/%s", component->driver->topology_name_prefix, name); + if (!fullname) + return -ENOMEM; + + return request_firmware(fw, fullname, component->dev); +} + static int avs_component_probe(struct snd_soc_component *component) { struct snd_soc_card *card = component->card; struct snd_soc_acpi_mach *mach; struct avs_soc_component *acomp; + const struct firmware *fw; struct avs_dev *adev; - char *filename; int ret; dev_dbg(card->dev, "probing %s card %s\n", component->name, card->name); @@ -1009,13 +1022,7 @@ static int avs_component_probe(struct snd_soc_component *component) goto finalize; /* Load specified topology and create debugfs for it. */ - filename = kasprintf(GFP_KERNEL, "%s/%s", component->driver->topology_name_prefix, - mach->tplg_filename); - if (!filename) - return -ENOMEM; - - ret = avs_load_topology(component, filename); - kfree(filename); + ret = avs_request_topology(component, mach->tplg_filename, &fw); if (ret == -ENOENT && !strncmp(mach->tplg_filename, "hda-", 4)) { unsigned int vendor_id; @@ -1030,18 +1037,17 @@ static int avs_component_probe(struct snd_soc_component *component) "hda-generic-tplg.bin"); if (!mach->tplg_filename) return -ENOMEM; - filename = kasprintf(GFP_KERNEL, "%s/%s", component->driver->topology_name_prefix, - mach->tplg_filename); - if (!filename) - return -ENOMEM; dev_info(card->dev, "trying to load fallback topology %s\n", mach->tplg_filename); - ret = avs_load_topology(component, filename); - kfree(filename); + ret = avs_request_topology(component, mach->tplg_filename, &fw); } if (ret < 0) return ret; + ret = snd_soc_tplg_component_load(component, &avs_tplg_ops, fw); + if (ret) + return ret; + ret = avs_component_load_libraries(acomp); if (ret < 0) { dev_err(card->dev, "libraries loading failed: %d\n", ret); diff --git a/sound/soc/intel/avs/topology.c b/sound/soc/intel/avs/topology.c index 9033f683393c43..c9837d78e6234b 100644 --- a/sound/soc/intel/avs/topology.c +++ b/sound/soc/intel/avs/topology.c @@ -350,6 +350,7 @@ AVS_DEFINE_PTR_PARSER(modcfg_base, struct avs_tplg_modcfg_base, modcfgs_base); AVS_DEFINE_PTR_PARSER(modcfg_ext, struct avs_tplg_modcfg_ext, modcfgs_ext); AVS_DEFINE_PTR_PARSER(pplcfg, struct avs_tplg_pplcfg, pplcfgs); AVS_DEFINE_PTR_PARSER(binding, struct avs_tplg_binding, bindings); +AVS_DEFINE_PTR_PARSER(init_config, struct avs_tplg_init_config, init_configs); AVS_DEFINE_PTR_PARSER(nhlt_config, struct avs_tplg_nhlt_config, nhlt_configs); static int @@ -1198,7 +1199,7 @@ static const struct avs_tplg_token_parser module_parsers[] = { { .token = AVS_TKN_MOD_INIT_CONFIG_NUM_IDS_U32, .type = SND_SOC_TPLG_TUPLE_TYPE_WORD, - .offset = offsetof(struct avs_tplg_module, num_config_ids), + .offset = offsetof(struct avs_tplg_module, num_init_configs), .parse = avs_parse_byte_token, }, { @@ -1214,10 +1215,32 @@ static const struct avs_tplg_token_parser init_config_parsers[] = { .token = AVS_TKN_MOD_INIT_CONFIG_ID_U32, .type = SND_SOC_TPLG_TUPLE_TYPE_WORD, .offset = 0, - .parse = avs_parse_word_token, + .parse = avs_parse_init_config_ptr, }, }; +static int avs_tplg_module_init_configs(struct snd_soc_component *comp, + struct avs_tplg_module *module, + struct snd_soc_tplg_vendor_array *tuples, u32 block_size) +{ + struct avs_tplg_init_config **cfgs; + int ret; + + if (!module->num_init_configs) + return -EINVAL; + + cfgs = devm_kcalloc(comp->card->dev, module->num_init_configs, sizeof(*cfgs), GFP_KERNEL); + if (!cfgs) + return -ENOMEM; + + ret = parse_dictionary_entries(comp, tuples, block_size, cfgs, module->num_init_configs, + sizeof(*cfgs), AVS_TKN_MOD_INIT_CONFIG_ID_U32, + init_config_parsers, ARRAY_SIZE(init_config_parsers)); + if (!ret) + module->init_configs = cfgs; + return ret; +} + static struct avs_tplg_module * avs_tplg_module_create(struct snd_soc_component *comp, struct avs_tplg_pipeline *owner, struct snd_soc_tplg_vendor_array *tuples, u32 block_size) @@ -1244,27 +1267,11 @@ avs_tplg_module_create(struct snd_soc_component *comp, struct avs_tplg_pipeline block_size -= esize; /* Parse trailing config ids if any. */ if (block_size) { - u32 num_config_ids = module->num_config_ids; - u32 *config_ids; - - if (!num_config_ids) - return ERR_PTR(-EINVAL); - - config_ids = devm_kcalloc(comp->card->dev, num_config_ids, sizeof(*config_ids), - GFP_KERNEL); - if (!config_ids) - return ERR_PTR(-ENOMEM); - tuples = avs_tplg_vendor_array_at(tuples, esize); - ret = parse_dictionary_entries(comp, tuples, block_size, - config_ids, num_config_ids, sizeof(*config_ids), - AVS_TKN_MOD_INIT_CONFIG_ID_U32, - init_config_parsers, - ARRAY_SIZE(init_config_parsers)); + + ret = avs_tplg_module_init_configs(comp, module, tuples, block_size); if (ret) return ERR_PTR(ret); - - module->config_ids = config_ids; } module->owner = owner; @@ -2194,7 +2201,7 @@ avs_control_load(struct snd_soc_component *comp, int index, struct snd_kcontrol_ return 0; } -static const struct snd_soc_tplg_ops avs_tplg_ops = { +const struct snd_soc_tplg_ops avs_tplg_ops = { .io_ops = avs_control_ops, .io_ops_count = ARRAY_SIZE(avs_control_ops), .control_load = avs_control_load, diff --git a/sound/soc/intel/avs/topology.h b/sound/soc/intel/avs/topology.h index 1cf7455b6c0107..189984ce7b51e5 100644 --- a/sound/soc/intel/avs/topology.h +++ b/sound/soc/intel/avs/topology.h @@ -221,8 +221,8 @@ struct avs_tplg_module { u8 domain; struct avs_tplg_modcfg_ext *cfg_ext; u32 ctl_id; - u32 num_config_ids; - u32 *config_ids; + u32 num_init_configs; + struct avs_tplg_init_config **init_configs; struct avs_tplg_nhlt_config *nhlt_config; struct avs_tplg_pipeline *owner; @@ -230,6 +230,7 @@ struct avs_tplg_module { struct list_head node; }; +extern const struct snd_soc_tplg_ops avs_tplg_ops; struct avs_tplg *avs_tplg_new(struct snd_soc_component *comp); int avs_load_topology(struct snd_soc_component *comp, const char *filename); diff --git a/sound/soc/sprd/sprd-pcm-compress.c b/sound/soc/sprd/sprd-pcm-compress.c index a7d437b49fbf54..e5249924b54d91 100644 --- a/sound/soc/sprd/sprd-pcm-compress.c +++ b/sound/soc/sprd/sprd-pcm-compress.c @@ -17,7 +17,7 @@ /* Default values if userspace does not set */ #define SPRD_COMPR_MIN_FRAGMENT_SIZE SZ_8K -#define SPRD_COMPR_MAX_FRAGMENT_SIZE SZ_128K +#define SPRD_COMPR_MAX_FRAGMENT_SIZE SZ_32K #define SPRD_COMPR_MIN_NUM_FRAGMENTS 4 #define SPRD_COMPR_MAX_NUM_FRAGMENTS 64 @@ -271,6 +271,19 @@ static int sprd_platform_compr_set_params(struct snd_soc_component *component, struct sprd_compr_params compr_params = { }; int ret; + /* + * The stage 0 IRAM buffer and the stage 1 DDR buffer are allocated + * with fixed sizes at open time, so the requested fragment size and + * fragments must fit into them, otherwise sprd_platform_compr_copy() + * would overflow the buffers. Note the compress core only checks the + * fragment size and fragments against an u32 overflow, not against + * the buffer sizes advertised by get_caps. + */ + if (params->buffer.fragment_size > SPRD_COMPR_IRAM_BUF_SIZE || + (u64)params->buffer.fragment_size * params->buffer.fragments > + SPRD_COMPR_AREA_BUF_SIZE) + return -EINVAL; + /* * Configure the DMA engine 2-stage transfer mode. Channel 1 set as the * destination channel, and channel 0 set as the source channel, that diff --git a/sound/soc/sti/uniperif_reader.c b/sound/soc/sti/uniperif_reader.c index 45d7613f595cce..5347f9620f2559 100644 --- a/sound/soc/sti/uniperif_reader.c +++ b/sound/soc/sti/uniperif_reader.c @@ -416,6 +416,8 @@ int uni_reader_init(struct platform_device *pdev, else reader->hw = &uni_reader_pcm_hw; + spin_lock_init(&reader->irq_lock); + ret = devm_request_irq(&pdev->dev, reader->irq, uni_reader_irq_handler, IRQF_SHARED, dev_name(&pdev->dev), reader); @@ -424,8 +426,6 @@ int uni_reader_init(struct platform_device *pdev, return -EBUSY; } - spin_lock_init(&reader->irq_lock); - return 0; } EXPORT_SYMBOL_GPL(uni_reader_init); diff --git a/sound/soc/ux500/ux500_msp_dai.c b/sound/soc/ux500/ux500_msp_dai.c index 7798957c6504d5..37c48cc70394ea 100644 --- a/sound/soc/ux500/ux500_msp_dai.c +++ b/sound/soc/ux500/ux500_msp_dai.c @@ -14,7 +14,7 @@ #include #include #include -#include +#include #include #include @@ -34,8 +34,10 @@ static int setup_pcm_multichan(struct snd_soc_dai *dai, if (drvdata->slots > 1) { msp_config->multichannel_configured = 1; - multi->tx_multichannel_enable = true; - multi->rx_multichannel_enable = true; + multi->tx_multichannel_enable = + msp_config->direction & MSP_DIR_TX; + multi->rx_multichannel_enable = + msp_config->direction & MSP_DIR_RX; multi->rx_comparison_enable_mode = MSP_COMPARISON_DISABLED; multi->tx_channel_0_enable = drvdata->tx_mask; @@ -57,72 +59,21 @@ static int setup_pcm_multichan(struct snd_soc_dai *dai, return 0; } -static int setup_frameper(struct snd_soc_dai *dai, unsigned int rate, - struct msp_protdesc *prot_desc) +static void setup_frameper(struct snd_soc_dai *dai, + struct msp_protdesc *prot_desc) { struct ux500_msp_i2s_drvdata *drvdata = dev_get_drvdata(dai->dev); - switch (drvdata->slots) { - case 1: - switch (rate) { - case 8000: - prot_desc->frame_period = - FRAME_PER_SINGLE_SLOT_8_KHZ; - break; - - case 16000: - prot_desc->frame_period = - FRAME_PER_SINGLE_SLOT_16_KHZ; - break; - - case 44100: - prot_desc->frame_period = - FRAME_PER_SINGLE_SLOT_44_1_KHZ; - break; - - case 48000: - prot_desc->frame_period = - FRAME_PER_SINGLE_SLOT_48_KHZ; - break; - - default: - dev_err(dai->dev, - "%s: Error: Unsupported sample-rate (freq = %d)!\n", - __func__, rate); - return -EINVAL; - } - break; - - case 2: - prot_desc->frame_period = FRAME_PER_2_SLOTS; - break; - - case 8: - prot_desc->frame_period = FRAME_PER_8_SLOTS; - break; - - case 16: - prot_desc->frame_period = FRAME_PER_16_SLOTS; - break; - default: - dev_err(dai->dev, - "%s: Error: Unsupported slot-count (slots = %d)!\n", - __func__, drvdata->slots); - return -EINVAL; - } - - prot_desc->clocks_per_frame = - prot_desc->frame_period+1; + prot_desc->clocks_per_frame = drvdata->slots * drvdata->slot_width; + prot_desc->frame_period = prot_desc->clocks_per_frame - 1; dev_dbg(dai->dev, "%s: Clocks per frame: %u\n", __func__, prot_desc->clocks_per_frame); - - return 0; } -static int setup_pcm_framing(struct snd_soc_dai *dai, unsigned int rate, - struct msp_protdesc *prot_desc) +static int setup_pcm_framing(struct snd_soc_dai *dai, + struct msp_protdesc *prot_desc) { struct ux500_msp_i2s_drvdata *drvdata = dev_get_drvdata(dai->dev); @@ -163,7 +114,9 @@ static int setup_pcm_framing(struct snd_soc_dai *dai, unsigned int rate, prot_desc->tx_elem_len_2 = MSP_ELEM_LEN_16; prot_desc->rx_elem_len_2 = MSP_ELEM_LEN_16; - return setup_frameper(dai, rate, prot_desc); + setup_frameper(dai, prot_desc); + + return 0; } static int setup_clocking(struct snd_soc_dai *dai, @@ -177,7 +130,16 @@ static int setup_clocking(struct snd_soc_dai *dai, case SND_SOC_DAIFMT_NB_IF: msp_config->tx_fsync_pol ^= 1 << TFSPOL_SHIFT; msp_config->rx_fsync_pol ^= 1 << RFSPOL_SHIFT; + break; + + case SND_SOC_DAIFMT_IB_NF: + msp_config->bclk_inverted = true; + break; + case SND_SOC_DAIFMT_IB_IF: + msp_config->bclk_inverted = true; + msp_config->tx_fsync_pol ^= 1 << TFSPOL_SHIFT; + msp_config->rx_fsync_pol ^= 1 << RFSPOL_SHIFT; break; default: @@ -192,6 +154,7 @@ static int setup_clocking(struct snd_soc_dai *dai, case SND_SOC_DAIFMT_BC_FC: dev_dbg(dai->dev, "%s: Codec is master.\n", __func__); + msp_config->clock_provider = false; msp_config->iodelay = 0x20; msp_config->rx_fsync_sel = 0; msp_config->tx_fsync_sel = 1 << TFSSEL_SHIFT; @@ -204,6 +167,7 @@ static int setup_clocking(struct snd_soc_dai *dai, case SND_SOC_DAIFMT_BP_FP: dev_dbg(dai->dev, "%s: Codec is slave.\n", __func__); + msp_config->clock_provider = true; msp_config->tx_clk_sel = TX_CLK_SEL_SRG; msp_config->tx_fsync_sel = TX_SYNC_SRG_PROG; msp_config->rx_clk_sel = RX_CLK_SEL_SRG; @@ -362,7 +326,7 @@ static int setup_msp_config(struct snd_pcm_substream *substream, if (ret < 0) return ret; - ret = setup_pcm_framing(dai, runtime->rate, prot_desc); + ret = setup_pcm_framing(dai, prot_desc); if (ret < 0) return ret; @@ -424,21 +388,21 @@ static void ux500_msp_dai_shutdown(struct snd_pcm_substream *substream, int ret; struct ux500_msp_i2s_drvdata *drvdata = dev_get_drvdata(dai->dev); bool is_playback = (substream->stream == SNDRV_PCM_STREAM_PLAYBACK); + unsigned int configured = is_playback ? PLAYBACK_CONFIGURED : + CAPTURE_CONFIGURED; + unsigned int dir = is_playback ? MSP_DIR_TX : MSP_DIR_RX; dev_dbg(dai->dev, "%s: MSP %d (%s): Enter.\n", __func__, dai->id, snd_pcm_stream_str(substream)); - if (drvdata->vape_opp_constraint == 1) { - prcmu_qos_update_requirement(PRCMU_QOS_APE_OPP, - "ux500_msp_i2s", 50); - drvdata->vape_opp_constraint = 0; - } - - if (ux500_msp_i2s_close(drvdata->msp, - is_playback ? MSP_DIR_TX : MSP_DIR_RX)) { - dev_err(dai->dev, - "%s: Error: MSP %d (%s): Unable to close i2s.\n", - __func__, dai->id, snd_pcm_stream_str(substream)); + if (drvdata->configured & configured) { + if (ux500_msp_i2s_close(drvdata->msp, dir)) { + dev_err(dai->dev, + "%s: Error: MSP %d (%s): Unable to close i2s.\n", + __func__, dai->id, + snd_pcm_stream_str(substream)); + } + drvdata->configured &= ~configured; } /* Disable and unprepare clocks */ @@ -456,15 +420,23 @@ static void ux500_msp_dai_shutdown(struct snd_pcm_substream *substream, static int ux500_msp_dai_prepare(struct snd_pcm_substream *substream, struct snd_soc_dai *dai) { - int ret = 0; struct ux500_msp_i2s_drvdata *drvdata = dev_get_drvdata(dai->dev); struct snd_pcm_runtime *runtime = substream->runtime; struct ux500_msp_config msp_config; + bool is_playback = substream->stream == SNDRV_PCM_STREAM_PLAYBACK; + unsigned int configured = is_playback ? PLAYBACK_CONFIGURED : + CAPTURE_CONFIGURED; + int ret; dev_dbg(dai->dev, "%s: MSP %d (%s): Enter (rate = %d).\n", __func__, dai->id, snd_pcm_stream_str(substream), runtime->rate); - setup_msp_config(substream, dai, &msp_config); + if (drvdata->configured & configured) + return 0; + + ret = setup_msp_config(substream, dai, &msp_config); + if (ret) + return ret; ret = ux500_msp_i2s_open(drvdata->msp, &msp_config); if (ret < 0) { @@ -473,22 +445,9 @@ static int ux500_msp_dai_prepare(struct snd_pcm_substream *substream, return ret; } - /* Set OPP-level */ - if ((drvdata->fmt & SND_SOC_DAIFMT_CLOCK_PROVIDER_MASK) && - (drvdata->msp->f_bitclk > 19200000)) { - /* If the bit-clock is higher than 19.2MHz, Vape should be - * run in 100% OPP. Only when bit-clock is used (MSP master) - */ - prcmu_qos_update_requirement(PRCMU_QOS_APE_OPP, - "ux500-msp-i2s", 100); - drvdata->vape_opp_constraint = 1; - } else { - prcmu_qos_update_requirement(PRCMU_QOS_APE_OPP, - "ux500-msp-i2s", 50); - drvdata->vape_opp_constraint = 0; - } + drvdata->configured |= configured; - return ret; + return 0; } static int ux500_msp_dai_hw_params(struct snd_pcm_substream *substream, @@ -496,7 +455,6 @@ static int ux500_msp_dai_hw_params(struct snd_pcm_substream *substream, struct snd_soc_dai *dai) { unsigned int mask, slots_active; - struct snd_pcm_runtime *runtime = substream->runtime; struct ux500_msp_i2s_drvdata *drvdata = dev_get_drvdata(dai->dev); dev_dbg(dai->dev, "%s: MSP %d (%s): Enter.\n", @@ -504,9 +462,8 @@ static int ux500_msp_dai_hw_params(struct snd_pcm_substream *substream, switch (drvdata->fmt & SND_SOC_DAIFMT_FORMAT_MASK) { case SND_SOC_DAIFMT_I2S: - snd_pcm_hw_constraint_minmax(runtime, - SNDRV_PCM_HW_PARAM_CHANNELS, - 1, 2); + if (params_channels(params) < 1 || params_channels(params) > 2) + return -EINVAL; break; case SND_SOC_DAIFMT_DSP_B: @@ -518,9 +475,8 @@ static int ux500_msp_dai_hw_params(struct snd_pcm_substream *substream, slots_active = hweight32(mask); dev_dbg(dai->dev, "TDM-slots active: %d", slots_active); - snd_pcm_hw_constraint_single(runtime, - SNDRV_PCM_HW_PARAM_CHANNELS, - slots_active); + if (!slots_active || params_channels(params) != slots_active) + return -EINVAL; break; default: @@ -553,20 +509,21 @@ static int ux500_msp_dai_set_dai_fmt(struct snd_soc_dai *dai, default: dev_err(dai->dev, "%s: Error: Unsupported protocol/master (fmt = 0x%x)!\n", - __func__, drvdata->fmt); + __func__, fmt); return -EINVAL; } switch (fmt & SND_SOC_DAIFMT_INV_MASK) { case SND_SOC_DAIFMT_NB_NF: case SND_SOC_DAIFMT_NB_IF: + case SND_SOC_DAIFMT_IB_NF: case SND_SOC_DAIFMT_IB_IF: break; default: dev_err(dai->dev, "%s: Error: Unsupported inversion (fmt = 0x%x)!\n", - __func__, drvdata->fmt); + __func__, fmt); return -EINVAL; } @@ -600,17 +557,23 @@ static int ux500_msp_dai_set_tdm_slot(struct snd_soc_dai *dai, __func__, slots); return -EINVAL; } - drvdata->slots = slots; - if (!(slot_width == 16)) { + if (slot_width != 16) { dev_err(dai->dev, "%s: Error: Unsupported slot-width (%d)!\n", __func__, slot_width); return -EINVAL; } - drvdata->slot_width = slot_width; - drvdata->tx_mask = tx_mask & cap; - drvdata->rx_mask = rx_mask & cap; + if ((tx_mask | rx_mask) & ~cap) { + dev_err(dai->dev, "%s: Slot mask exceeds %d slots\n", + __func__, slots); + return -EINVAL; + } + + drvdata->slots = slots; + drvdata->slot_width = slot_width; + drvdata->tx_mask = tx_mask; + drvdata->rx_mask = rx_mask; return 0; } @@ -716,6 +679,7 @@ static const struct snd_soc_component_driver ux500_msp_component = { static int ux500_msp_drv_probe(struct platform_device *pdev) { struct ux500_msp_i2s_drvdata *drvdata; + struct reset_control *reset; int ret = 0; drvdata = devm_kzalloc(&pdev->dev, @@ -729,7 +693,6 @@ static int ux500_msp_drv_probe(struct platform_device *pdev) drvdata->tx_mask = 0x01; drvdata->rx_mask = 0x01; drvdata->slot_width = 16; - drvdata->master_clk = MSP_INPUT_FREQ_APB; drvdata->reg_vape = devm_regulator_get(&pdev->dev, "v-ape"); if (IS_ERR(drvdata->reg_vape)) { @@ -739,8 +702,6 @@ static int ux500_msp_drv_probe(struct platform_device *pdev) __func__, ret); return ret; } - prcmu_qos_add_requirement(PRCMU_QOS_APE_OPP, (char *)pdev->name, 50); - drvdata->pclk = devm_clk_get(&pdev->dev, "apb_pclk"); if (IS_ERR(drvdata->pclk)) { ret = PTR_ERR(drvdata->pclk); @@ -758,9 +719,19 @@ static int ux500_msp_drv_probe(struct platform_device *pdev) __func__, ret); return ret; } + drvdata->master_clk = clk_get_rate(drvdata->clk); + if (!drvdata->master_clk) { + dev_err(&pdev->dev, "MSP clock has no rate\n"); + return -EINVAL; + } + + reset = devm_reset_control_get_exclusive_deasserted(&pdev->dev, NULL); + if (IS_ERR(reset)) + return dev_err_probe(&pdev->dev, PTR_ERR(reset), + "Failed to deassert MSP reset\n"); ret = ux500_msp_i2s_init_msp(pdev, &drvdata->msp); - if (!drvdata->msp) { + if (ret) { dev_err(&pdev->dev, "%s: ERROR: Failed to init MSP-struct (%d)!", __func__, ret); @@ -799,8 +770,6 @@ static void ux500_msp_drv_remove(struct platform_device *pdev) snd_soc_unregister_component(&pdev->dev); - prcmu_qos_remove_requirement(PRCMU_QOS_APE_OPP, "ux500_msp_i2s"); - ux500_msp_i2s_cleanup_msp(pdev, drvdata->msp); } diff --git a/sound/soc/ux500/ux500_msp_dai.h b/sound/soc/ux500/ux500_msp_dai.h index 30bf7083819615..aae582030d9594 100644 --- a/sound/soc/ux500/ux500_msp_dai.h +++ b/sound/soc/ux500/ux500_msp_dai.h @@ -22,17 +22,6 @@ #define UX500_I2S_FORMATS (SNDRV_PCM_FMTBIT_S16_LE) -#define FRAME_PER_SINGLE_SLOT_8_KHZ 31 -#define FRAME_PER_SINGLE_SLOT_16_KHZ 124 -#define FRAME_PER_SINGLE_SLOT_44_1_KHZ 63 -#define FRAME_PER_SINGLE_SLOT_48_KHZ 49 -#define FRAME_PER_2_SLOTS 31 -#define FRAME_PER_8_SLOTS 138 -#define FRAME_PER_16_SLOTS 277 - -#define UX500_MSP_INTERNAL_CLOCK_FREQ 40000000 -#define UX500_MSP1_INTERNAL_CLOCK_FREQ UX500_MSP_INTERNAL_CLOCK_FREQ - #define UX500_MSP_MIN_CHANNELS 1 #define UX500_MSP_MAX_CHANNELS 8 @@ -47,6 +36,7 @@ struct ux500_msp_i2s_drvdata { struct ux500_msp *msp; struct regulator *reg_vape; unsigned int fmt; + unsigned int configured; unsigned int tx_mask; unsigned int rx_mask; int slots; @@ -57,8 +47,6 @@ struct ux500_msp_i2s_drvdata { struct clk *clk; struct clk *pclk; - /* Regulators */ - int vape_opp_constraint; }; int ux500_msp_dai_set_data_delay(struct snd_soc_dai *dai, int delay); diff --git a/sound/soc/ux500/ux500_msp_i2s.c b/sound/soc/ux500/ux500_msp_i2s.c index fbfeefa418ca70..683b485fb57085 100644 --- a/sound/soc/ux500/ux500_msp_i2s.c +++ b/sound/soc/ux500/ux500_msp_i2s.c @@ -201,10 +201,12 @@ static int configure_protocol(struct ux500_msp *msp, /* The code below should not be separated. */ temp_reg = readl(msp->registers + MSP_GCR) & ~TX_CLK_POL_RISING; - temp_reg |= MSP_TX_CLKPOL_BIT(~protdesc->tx_clk_pol); + temp_reg |= MSP_TX_CLKPOL_BIT(!protdesc->tx_clk_pol ^ + config->bclk_inverted); writel(temp_reg, msp->registers + MSP_GCR); temp_reg = readl(msp->registers + MSP_GCR) & ~RX_CLK_POL_RISING; - temp_reg |= MSP_RX_CLKPOL_BIT(protdesc->rx_clk_pol); + temp_reg |= MSP_RX_CLKPOL_BIT(protdesc->rx_clk_pol ^ + config->bclk_inverted); writel(temp_reg, msp->registers + MSP_GCR); return 0; @@ -212,35 +214,20 @@ static int configure_protocol(struct ux500_msp *msp, static int setup_bitclk(struct ux500_msp *msp, struct ux500_msp_config *config) { + struct msp_protdesc *protdesc; + u64 desired_bitclk; + unsigned int bitclk; u32 reg_val_GCR; - u32 frame_per = 0; - u32 sck_div = 0; - u32 frame_width = 0; - u32 temp_reg = 0; - struct msp_protdesc *protdesc = NULL; + u32 sck_div; + u32 temp_reg; reg_val_GCR = readl(msp->registers + MSP_GCR); writel(reg_val_GCR & ~SRG_ENABLE, msp->registers + MSP_GCR); - if (config->default_protdesc) - protdesc = - (struct msp_protdesc *)&prot_descs[config->protocol]; - else - protdesc = (struct msp_protdesc *)&config->protdesc; - switch (config->protocol) { case MSP_PCM_PROTOCOL: case MSP_PCM_COMPAND_PROTOCOL: - frame_width = protdesc->frame_width; - sck_div = config->f_inputclk / (config->frame_freq * - (protdesc->clocks_per_frame)); - frame_per = protdesc->frame_period; - break; case MSP_I2S_PROTOCOL: - frame_width = protdesc->frame_width; - sck_div = config->f_inputclk / (config->frame_freq * - (protdesc->clocks_per_frame)); - frame_per = protdesc->frame_period; break; default: dev_err(msp->dev, "%s: ERROR: Unknown protocol (%d)!\n", @@ -249,12 +236,35 @@ static int setup_bitclk(struct ux500_msp *msp, struct ux500_msp_config *config) return -EINVAL; } + if (config->default_protdesc) + protdesc = (struct msp_protdesc *)&prot_descs[config->protocol]; + else + protdesc = &config->protdesc; + + if (!config->frame_freq || !protdesc->clocks_per_frame) + return -EINVAL; + + desired_bitclk = (u64)config->frame_freq * protdesc->clocks_per_frame; + if (desired_bitclk > config->f_inputclk) + return -EINVAL; + bitclk = desired_bitclk; + if (config->f_inputclk % bitclk) { + dev_err(msp->dev, + "Input clock %u cannot generate bit clock %u\n", + config->f_inputclk, bitclk); + return -EINVAL; + } + + sck_div = config->f_inputclk / bitclk; + if (!sck_div || sck_div > SCK_DIV_MASK + 1) + return -EINVAL; + temp_reg = (sck_div - 1) & SCK_DIV_MASK; - temp_reg |= FRAME_WIDTH_BITS(frame_width); - temp_reg |= FRAME_PERIOD_BITS(frame_per); + temp_reg |= FRAME_WIDTH_BITS(protdesc->frame_width); + temp_reg |= FRAME_PERIOD_BITS(protdesc->frame_period); writel(temp_reg, msp->registers + MSP_SRG); - msp->f_bitclk = (config->f_inputclk)/(sck_div + 1); + msp->f_bitclk = config->f_inputclk / sck_div; /* Enable bit-clock */ udelay(100); @@ -344,20 +354,27 @@ static int configure_multichannel(struct ux500_msp *msp, return 0; } -static int enable_msp(struct ux500_msp *msp, struct ux500_msp_config *config) +static int enable_msp(struct ux500_msp *msp, struct ux500_msp_config *config, + bool first) { - int status = 0; - u32 reg_val_DMACR, reg_val_GCR; + int status; + u32 reg_val_DMACR; /* Configure msp with protocol dependent settings */ - configure_protocol(msp, config); - setup_bitclk(msp, config); + status = configure_protocol(msp, config); + if (status) + return status; + + if (first && config->clock_provider) { + status = setup_bitclk(msp, config); + if (status) + return status; + } + if (config->multichannel_configured == 1) { status = configure_multichannel(msp, config); if (status) - dev_warn(msp->dev, - "%s: WARN: configure_multichannel failed (%d)!\n", - __func__, status); + return status; } reg_val_DMACR = readl(msp->registers + MSP_DMACR); @@ -369,11 +386,7 @@ static int enable_msp(struct ux500_msp *msp, struct ux500_msp_config *config) writel(config->iodelay, msp->registers + MSP_IODLY); - /* Enable frame generation logic */ - reg_val_GCR = readl(msp->registers + MSP_GCR); - writel(reg_val_GCR | FRAME_GEN_ENABLE, msp->registers + MSP_GCR); - - return status; + return 0; } static void flush_fifo_rx(struct ux500_msp *msp) @@ -411,12 +424,37 @@ static void flush_fifo_tx(struct ux500_msp *msp) writel(reg_val_GCR, msp->registers + MSP_GCR); } +static bool ux500_msp_config_compatible(struct ux500_msp *msp, + struct ux500_msp_config *config) +{ + struct ux500_msp_config *active = &msp->config; + + return active->f_inputclk == config->f_inputclk && + active->tx_clk_sel == config->tx_clk_sel && + active->rx_clk_sel == config->rx_clk_sel && + active->srg_clk_sel == config->srg_clk_sel && + active->rx_fsync_pol == config->rx_fsync_pol && + active->tx_fsync_pol == config->tx_fsync_pol && + active->rx_fsync_sel == config->rx_fsync_sel && + active->tx_fsync_sel == config->tx_fsync_sel && + active->default_protdesc == config->default_protdesc && + active->protocol == config->protocol && + active->frame_freq == config->frame_freq && + active->data_size == config->data_size && + active->def_elem_len == config->def_elem_len && + active->clock_provider == config->clock_provider && + active->bclk_inverted == config->bclk_inverted && + !memcmp(&active->protdesc, &config->protdesc, + sizeof(active->protdesc)); +} + int ux500_msp_i2s_open(struct ux500_msp *msp, struct ux500_msp_config *config) { u32 old_reg, new_reg, mask; int res; unsigned int tx_sel, rx_sel, tx_busy, rx_busy; + bool first; if (in_interrupt()) { dev_err(msp->dev, @@ -444,40 +482,68 @@ int ux500_msp_i2s_open(struct ux500_msp *msp, return -EBUSY; } - msp->dir_busy |= (tx_sel ? MSP_DIR_TX : 0) | (rx_sel ? MSP_DIR_RX : 0); - - /* First do the global config register */ - mask = RX_CLK_SEL_MASK | TX_CLK_SEL_MASK | RX_FSYNC_MASK | - TX_FSYNC_MASK | RX_SYNC_SEL_MASK | TX_SYNC_SEL_MASK | - RX_FIFO_ENABLE_MASK | TX_FIFO_ENABLE_MASK | SRG_CLK_SEL_MASK | - LOOPBACK_MASK | TX_EXTRA_DELAY_MASK; - - new_reg = (config->tx_clk_sel | config->rx_clk_sel | - config->rx_fsync_pol | config->tx_fsync_pol | - config->rx_fsync_sel | config->tx_fsync_sel | - config->rx_fifo_config | config->tx_fifo_config | - config->srg_clk_sel | config->loopback_enable | - config->tx_data_enable); + first = !msp->dir_busy; + if (!first && !ux500_msp_config_compatible(msp, config)) { + dev_err(msp->dev, "%s: Incompatible duplex configuration\n", + __func__); + return -EBUSY; + } - old_reg = readl(msp->registers + MSP_GCR); - old_reg &= ~mask; - new_reg |= old_reg; - writel(new_reg, msp->registers + MSP_GCR); + if (first) { + /* First do the global config register */ + mask = RX_CLK_SEL_MASK | TX_CLK_SEL_MASK | RX_FSYNC_MASK | + TX_FSYNC_MASK | RX_SYNC_SEL_MASK | TX_SYNC_SEL_MASK | + RX_FIFO_ENABLE_MASK | TX_FIFO_ENABLE_MASK | + SRG_CLK_SEL_MASK | LOOPBACK_MASK | TX_EXTRA_DELAY_MASK; + + new_reg = config->tx_clk_sel | config->rx_clk_sel | + config->rx_fsync_pol | config->tx_fsync_pol | + config->rx_fsync_sel | config->tx_fsync_sel | + config->rx_fifo_config | config->tx_fifo_config | + config->srg_clk_sel | config->loopback_enable | + config->tx_data_enable; + + old_reg = readl(msp->registers + MSP_GCR); + old_reg &= ~mask; + new_reg |= old_reg; + writel(new_reg, msp->registers + MSP_GCR); + writel(MSP_WMRK_TX_4_ELEMENTS | MSP_WMRK_RX_4_ELEMENTS, + msp->registers + MSP_WMRK); + } - res = enable_msp(msp, config); + res = enable_msp(msp, config, first); if (res < 0) { dev_err(msp->dev, "%s: ERROR: enable_msp failed (%d)!\n", __func__, res); - return -EBUSY; + if (tx_sel) + writel(0, msp->registers + MSP_TCF); + if (rx_sel) + writel(0, msp->registers + MSP_RCF); + if (first) { + writel(0, msp->registers + MSP_GCR); + writel(0, msp->registers + MSP_DMACR); + writel(0, msp->registers + MSP_SRG); + writel(0, msp->registers + MSP_MCR); + } + return res; + } + + msp->dir_busy |= config->direction; + if (first) { + msp->config = *config; + msp->clock_provider = config->clock_provider; } if (config->loopback_enable & 0x80) msp->loopback_enable = 1; /* Flush FIFOs */ - flush_fifo_tx(msp); - flush_fifo_rx(msp); + if (tx_sel) + flush_fifo_tx(msp); + if (rx_sel) + flush_fifo_rx(msp); - msp->msp_state = MSP_STATE_CONFIGURED; + if (!msp->dir_running) + msp->msp_state = MSP_STATE_CONFIGURED; return 0; } @@ -494,7 +560,6 @@ static void disable_msp_rx(struct ux500_msp *msp) ~(RX_SERVICE_INT | RX_OVERRUN_ERROR_INT), msp->registers + MSP_IMSC); - msp->dir_busy &= ~MSP_DIR_RX; } static void disable_msp_tx(struct ux500_msp *msp) @@ -510,7 +575,6 @@ static void disable_msp_tx(struct ux500_msp *msp) ~(TX_SERVICE_INT | TX_UNDERRUN_ERR_INT), msp->registers + MSP_IMSC); - msp->dir_busy &= ~MSP_DIR_TX; } static int disable_msp(struct ux500_msp *msp, unsigned int dir) @@ -520,7 +584,7 @@ static int disable_msp(struct ux500_msp *msp, unsigned int dir) reg_val_GCR = readl(msp->registers + MSP_GCR); disable_tx = dir & MSP_DIR_TX; - disable_rx = dir & MSP_DIR_TX; + disable_rx = dir & MSP_DIR_RX; if (disable_tx && disable_rx) { reg_val_GCR = readl(msp->registers + MSP_GCR); writel(reg_val_GCR | LOOPBACK_MASK, @@ -553,7 +617,15 @@ static int disable_msp(struct ux500_msp *msp, unsigned int dir) int ux500_msp_i2s_trigger(struct ux500_msp *msp, int cmd, int direction) { - u32 reg_val_GCR, enable_bit; + u32 reg_val_DMACR, reg_val_GCR, dma_enable_bit, enable_bit; + unsigned int dir; + + if (direction == SNDRV_PCM_STREAM_PLAYBACK) + dir = MSP_DIR_TX; + else if (direction == SNDRV_PCM_STREAM_CAPTURE) + dir = MSP_DIR_RX; + else + return -EINVAL; if (msp->msp_state == MSP_STATE_IDLE) { dev_err(msp->dev, "%s: ERROR: MSP is not configured!\n", @@ -565,21 +637,44 @@ int ux500_msp_i2s_trigger(struct ux500_msp *msp, int cmd, int direction) case SNDRV_PCM_TRIGGER_START: case SNDRV_PCM_TRIGGER_RESUME: case SNDRV_PCM_TRIGGER_PAUSE_RELEASE: - if (direction == SNDRV_PCM_STREAM_PLAYBACK) + if (direction == SNDRV_PCM_STREAM_PLAYBACK) { enable_bit = TX_ENABLE; - else + dma_enable_bit = TX_DMA_ENABLE; + } else { enable_bit = RX_ENABLE; + dma_enable_bit = RX_DMA_ENABLE; + } + if (!(msp->dir_busy & dir)) + return -EINVAL; + reg_val_DMACR = readl(msp->registers + MSP_DMACR); + writel(reg_val_DMACR | dma_enable_bit, + msp->registers + MSP_DMACR); reg_val_GCR = readl(msp->registers + MSP_GCR); + if (msp->clock_provider) + enable_bit |= FRAME_GEN_ENABLE; writel(reg_val_GCR | enable_bit, msp->registers + MSP_GCR); + msp->dir_running |= dir; + msp->msp_state = MSP_STATE_RUNNING; break; case SNDRV_PCM_TRIGGER_STOP: case SNDRV_PCM_TRIGGER_SUSPEND: case SNDRV_PCM_TRIGGER_PAUSE_PUSH: - if (direction == SNDRV_PCM_STREAM_PLAYBACK) + if (!(msp->dir_busy & dir)) + return -EINVAL; + if (direction == SNDRV_PCM_STREAM_PLAYBACK) { disable_msp_tx(msp); - else + msp->dir_running &= ~MSP_DIR_TX; + } else { disable_msp_rx(msp); + msp->dir_running &= ~MSP_DIR_RX; + } + if (!msp->dir_running) { + reg_val_GCR = readl(msp->registers + MSP_GCR); + writel(reg_val_GCR & ~FRAME_GEN_ENABLE, + msp->registers + MSP_GCR); + msp->msp_state = MSP_STATE_CONFIGURED; + } break; default: return -EINVAL; @@ -594,7 +689,18 @@ int ux500_msp_i2s_close(struct ux500_msp *msp, unsigned int dir) dev_dbg(msp->dev, "%s: Enter (dir = 0x%01x).\n", __func__, dir); + if (!dir || dir & ~(MSP_DIR_TX | MSP_DIR_RX) || + (msp->dir_busy & dir) != dir) + return -EINVAL; + status = disable_msp(msp, dir); + msp->dir_busy &= ~dir; + msp->dir_running &= ~dir; + if (msp->dir_busy && !msp->dir_running) { + writel(readl(msp->registers + MSP_GCR) & ~FRAME_GEN_ENABLE, + msp->registers + MSP_GCR); + msp->msp_state = MSP_STATE_CONFIGURED; + } if (msp->dir_busy == 0) { /* disable sample rate and frame generators */ msp->msp_state = MSP_STATE_IDLE; @@ -618,6 +724,8 @@ int ux500_msp_i2s_close(struct ux500_msp *msp, unsigned int dir) writel(0, msp->registers + MSP_RCE1); writel(0, msp->registers + MSP_RCE2); writel(0, msp->registers + MSP_RCE3); + memset(&msp->config, 0, sizeof(msp->config)); + msp->clock_provider = false; } return status; @@ -627,7 +735,7 @@ int ux500_msp_i2s_close(struct ux500_msp *msp, unsigned int dir) int ux500_msp_i2s_init_msp(struct platform_device *pdev, struct ux500_msp **msp_p) { - struct resource *res = NULL; + struct resource *res; struct ux500_msp *msp; *msp_p = devm_kzalloc(&pdev->dev, sizeof(struct ux500_msp), GFP_KERNEL); @@ -637,20 +745,10 @@ int ux500_msp_i2s_init_msp(struct platform_device *pdev, msp->dev = &pdev->dev; - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - if (res == NULL) { - dev_err(&pdev->dev, "%s: ERROR: Unable to get resource!\n", - __func__); - return -ENOMEM; - } - + msp->registers = devm_platform_get_and_ioremap_resource(pdev, 0, &res); + if (IS_ERR(msp->registers)) + return PTR_ERR(msp->registers); msp->tx_rx_addr = res->start + MSP_DR; - msp->registers = devm_ioremap(&pdev->dev, res->start, - resource_size(res)); - if (msp->registers == NULL) { - dev_err(&pdev->dev, "%s: ERROR: ioremap failed!\n", __func__); - return -ENOMEM; - } msp->msp_state = MSP_STATE_IDLE; msp->loopback_enable = 0; diff --git a/sound/soc/ux500/ux500_msp_i2s.h b/sound/soc/ux500/ux500_msp_i2s.h index 69d4ebc409fc12..2bf2699bdc49f8 100644 --- a/sound/soc/ux500/ux500_msp_i2s.h +++ b/sound/soc/ux500/ux500_msp_i2s.h @@ -12,8 +12,6 @@ #include -#define MSP_INPUT_FREQ_APB 48000000 - /*** Stereo mode. Used for APB data accesses as 16 bits accesses (mono), * 32 bits accesses (stereo). ***/ @@ -64,6 +62,7 @@ enum msp_direction { #define MSP_SRG 0x10 #define MSP_FLR 0x14 #define MSP_DMACR 0x18 +#define MSP_WMRK 0x1c #define MSP_IMSC 0x20 #define MSP_RIS 0x24 @@ -230,6 +229,10 @@ enum msp_direction { #define RDMAE_SHIFT 0 #define TDMAE_SHIFT 1 +/* FIFO watermark register */ +#define MSP_WMRK_RX_4_ELEMENTS BIT(0) +#define MSP_WMRK_TX_4_ELEMENTS BIT(3) + /* Interrupt Register */ #define RX_SERVICE_INT BIT(0) #define RX_OVERRUN_ERROR_INT BIT(1) @@ -460,6 +463,8 @@ struct ux500_msp_config { enum msp_data_size data_size; unsigned int def_elem_len; unsigned int iodelay; + bool clock_provider; + bool bclk_inverted; }; struct ux500_msp { @@ -470,8 +475,11 @@ struct ux500_msp { enum msp_state msp_state; int def_elem_len; unsigned int dir_busy; + unsigned int dir_running; int loopback_enable; unsigned int f_bitclk; + bool clock_provider; + struct ux500_msp_config config; }; int ux500_msp_i2s_init_msp(struct platform_device *pdev, diff --git a/sound/usb/caiaq/audio.c b/sound/usb/caiaq/audio.c index ba3f73455ebeea..bb6280aa353347 100644 --- a/sound/usb/caiaq/audio.c +++ b/sound/usb/caiaq/audio.c @@ -828,16 +828,13 @@ int snd_usb_caiaq_audio_init(struct snd_usb_caiaqdev *cdev) cdev->data_urbs_in = alloc_urbs(cdev, SNDRV_PCM_STREAM_CAPTURE, &ret); if (ret < 0) { - kfree(cdev->data_cb_info); - free_urbs(cdev->data_urbs_in); + snd_usb_caiaq_audio_free(cdev); return ret; } cdev->data_urbs_out = alloc_urbs(cdev, SNDRV_PCM_STREAM_PLAYBACK, &ret); if (ret < 0) { - kfree(cdev->data_cb_info); - free_urbs(cdev->data_urbs_in); - free_urbs(cdev->data_urbs_out); + snd_usb_caiaq_audio_free(cdev); return ret; } @@ -858,6 +855,9 @@ void snd_usb_caiaq_audio_free(struct snd_usb_caiaqdev *cdev) dev_dbg(dev, "%s(%p)\n", __func__, cdev); free_urbs(cdev->data_urbs_in); + cdev->data_urbs_in = NULL; free_urbs(cdev->data_urbs_out); + cdev->data_urbs_out = NULL; kfree(cdev->data_cb_info); + cdev->data_cb_info = NULL; } diff --git a/sound/usb/caiaq/device.c b/sound/usb/caiaq/device.c index a16e5924848033..3d821fde458206 100644 --- a/sound/usb/caiaq/device.c +++ b/sound/usb/caiaq/device.c @@ -192,8 +192,8 @@ static void usb_ep1_command_reply_dispatch (struct urb* urb) break; } - cdev->ep1_in_urb.actual_length = 0; - ret = usb_submit_urb(&cdev->ep1_in_urb, GFP_ATOMIC); + cdev->ep1_in_urb->actual_length = 0; + ret = usb_submit_urb(cdev->ep1_in_urb, GFP_ATOMIC); if (ret < 0) dev_err(dev, "unable to submit urb. OOM!?\n"); } @@ -408,6 +408,10 @@ static void card_free(struct snd_card *card) #endif snd_usb_caiaq_audio_free(cdev); usb_put_dev(cdev->chip.dev); + usb_free_urb(cdev->ep1_in_urb); + cdev->ep1_in_urb = NULL; + usb_free_urb(cdev->midi_out_urb); + cdev->midi_out_urb = NULL; } static int create_card(struct usb_device *usb_dev, @@ -457,22 +461,30 @@ static int init_card(struct snd_usb_caiaqdev *cdev) return -EIO; } - usb_init_urb(&cdev->ep1_in_urb); - usb_init_urb(&cdev->midi_out_urb); + cdev->ep1_in_urb = usb_alloc_urb(0, GFP_KERNEL); + if (!cdev->ep1_in_urb) + return -ENOMEM; - usb_fill_bulk_urb(&cdev->ep1_in_urb, usb_dev, + cdev->midi_out_urb = usb_alloc_urb(0, GFP_KERNEL); + if (!cdev->midi_out_urb) { + usb_free_urb(cdev->ep1_in_urb); + cdev->ep1_in_urb = NULL; + return -ENOMEM; + } + + usb_fill_bulk_urb(cdev->ep1_in_urb, usb_dev, usb_rcvbulkpipe(usb_dev, 0x1), cdev->ep1_in_buf, EP1_BUFSIZE, usb_ep1_command_reply_dispatch, cdev); - usb_fill_bulk_urb(&cdev->midi_out_urb, usb_dev, + usb_fill_bulk_urb(cdev->midi_out_urb, usb_dev, usb_sndbulkpipe(usb_dev, 0x1), cdev->midi_out_buf, EP1_BUFSIZE, snd_usb_caiaq_midi_output_done, cdev); /* sanity checks of EPs before actually submitting */ - if (usb_urb_ep_type_check(&cdev->ep1_in_urb) || - usb_urb_ep_type_check(&cdev->midi_out_urb)) { + if (usb_urb_ep_type_check(cdev->ep1_in_urb) || + usb_urb_ep_type_check(cdev->midi_out_urb)) { dev_err(dev, "invalid EPs\n"); return -EINVAL; } @@ -480,7 +492,7 @@ static int init_card(struct snd_usb_caiaqdev *cdev) init_waitqueue_head(&cdev->ep1_wait_queue); init_waitqueue_head(&cdev->prepare_wait_queue); - if (usb_submit_urb(&cdev->ep1_in_urb, GFP_KERNEL) != 0) + if (usb_submit_urb(cdev->ep1_in_urb, GFP_KERNEL) != 0) return -EIO; err = snd_usb_caiaq_send_command(cdev, EP1_CMD_GET_DEVICE_INFO, NULL, 0); @@ -530,7 +542,7 @@ static int init_card(struct snd_usb_caiaqdev *cdev) return 0; err_kill_urb: - usb_kill_urb(&cdev->ep1_in_urb); + usb_kill_urb(cdev->ep1_in_urb); return err; } @@ -576,8 +588,8 @@ static void snd_disconnect(struct usb_interface *intf) #endif snd_usb_caiaq_audio_disconnect(cdev); - usb_kill_urb(&cdev->ep1_in_urb); - usb_kill_urb(&cdev->midi_out_urb); + usb_kill_urb(cdev->ep1_in_urb); + usb_kill_urb(cdev->midi_out_urb); snd_card_free_when_closed(card); } diff --git a/sound/usb/caiaq/device.h b/sound/usb/caiaq/device.h index 743eb0387b5fbb..1c6f34693fa819 100644 --- a/sound/usb/caiaq/device.h +++ b/sound/usb/caiaq/device.h @@ -60,8 +60,8 @@ struct snd_usb_caiaq_cb_info; struct snd_usb_caiaqdev { struct snd_usb_audio chip; - struct urb ep1_in_urb; - struct urb midi_out_urb; + struct urb *ep1_in_urb; + struct urb *midi_out_urb; struct urb **data_urbs_in; struct urb **data_urbs_out; struct snd_usb_caiaq_cb_info *data_cb_info; diff --git a/sound/usb/caiaq/midi.c b/sound/usb/caiaq/midi.c index c656d016243214..18529484c8dcca 100644 --- a/sound/usb/caiaq/midi.c +++ b/sound/usb/caiaq/midi.c @@ -43,7 +43,7 @@ static int snd_usb_caiaq_midi_output_close(struct snd_rawmidi_substream *substre { struct snd_usb_caiaqdev *cdev = substream->rmidi->private_data; if (cdev->midi_out_active) { - usb_kill_urb(&cdev->midi_out_urb); + usb_kill_urb(cdev->midi_out_urb); cdev->midi_out_active = 0; } return 0; @@ -64,9 +64,9 @@ static void snd_usb_caiaq_midi_send(struct snd_usb_caiaqdev *cdev, return; cdev->midi_out_buf[2] = len; - cdev->midi_out_urb.transfer_buffer_length = len+3; + cdev->midi_out_urb->transfer_buffer_length = len+3; - ret = usb_submit_urb(&cdev->midi_out_urb, GFP_ATOMIC); + ret = usb_submit_urb(cdev->midi_out_urb, GFP_ATOMIC); if (ret < 0) dev_err(dev, "snd_usb_caiaq_midi_send(%p): usb_submit_urb() failed," diff --git a/sound/usb/usx2y/us122l.c b/sound/usb/usx2y/us122l.c index f00b53346abd34..a5db0d044ef96c 100644 --- a/sound/usb/usx2y/us122l.c +++ b/sound/usb/usx2y/us122l.c @@ -180,8 +180,11 @@ static int usb_stream_hwdep_mmap(struct snd_hwdep *hw, guard(mutex)(&us122l->mutex); s = us122l->sk.s; read = offset < s->read_size; - if (read && area->vm_flags & VM_WRITE) - return -EPERM; + if (read) { + if (area->vm_flags & VM_WRITE) + return -EPERM; + vm_flags_clear(area, VM_MAYWRITE); + } /* if userspace tries to mmap beyond end of our buffer, fail */ if (size > PAGE_ALIGN(read ? s->read_size : s->write_size)) { dev_warn(hw->card->dev, "%s: size %lu > %u\n", __func__, diff --git a/sound/usb/usx2y/usbusx2y.c b/sound/usb/usx2y/usbusx2y.c index 4190227c5a2a58..108f9bddf9aa35 100644 --- a/sound/usb/usx2y/usbusx2y.c +++ b/sound/usb/usx2y/usbusx2y.c @@ -189,6 +189,9 @@ static void i_usx2y_in04_int(struct urb *urb) return; } + if (urb->actual_length < USX2Y_IN04_SIZE) + goto resubmit; + if (us428ctls) { diff = -1; if (us428ctls->ctl_snapshot_last == -2) { @@ -196,7 +199,7 @@ static void i_usx2y_in04_int(struct urb *urb) memcpy(usx2y->in04_last, usx2y->in04_buf, sizeof(usx2y->in04_last)); us428ctls->ctl_snapshot_last = -1; } else { - for (i = 0; i < 21; i++) { + for (i = 0; i < USX2Y_IN04_SIZE; i++) { if (usx2y->in04_last[i] != ((char *)usx2y->in04_buf)[i]) { if (diff < 0) diff = i; @@ -253,6 +256,7 @@ static void i_usx2y_in04_int(struct urb *urb) if (err) dev_err(&urb->dev->dev, "in04_int() usb_submit_urb err=%i\n", err); +resubmit: urb->dev = usx2y->dev; usb_submit_urb(urb, GFP_ATOMIC); } @@ -305,7 +309,7 @@ int usx2y_in04_init(struct usx2ydev *usx2y) goto error; } - usx2y->in04_buf = kmalloc(21, GFP_KERNEL); + usx2y->in04_buf = kzalloc(USX2Y_IN04_SIZE, GFP_KERNEL); if (!usx2y->in04_buf) { err = -ENOMEM; goto error; @@ -313,7 +317,7 @@ int usx2y_in04_init(struct usx2ydev *usx2y) init_waitqueue_head(&usx2y->in04_wait_queue); usb_fill_int_urb(usx2y->in04_urb, usx2y->dev, usb_rcvintpipe(usx2y->dev, 0x4), - usx2y->in04_buf, 21, + usx2y->in04_buf, USX2Y_IN04_SIZE, i_usx2y_in04_int, usx2y, 10); if (usb_urb_ep_type_check(usx2y->in04_urb)) { diff --git a/sound/usb/usx2y/usbusx2y.h b/sound/usb/usx2y/usbusx2y.h index 6a76d04bf1c7df..7b6deed17d4b1d 100644 --- a/sound/usb/usx2y/usbusx2y.h +++ b/sound/usb/usx2y/usbusx2y.h @@ -5,6 +5,8 @@ #include "../midi.h" #include "usbus428ctldefs.h" +#define USX2Y_IN04_SIZE sizeof(struct us428_ctls) + #define NRURBS 2 /* Default value used for nr of packs per urb. @@ -55,7 +57,7 @@ struct usx2ydev { int stride; struct urb *in04_urb; void *in04_buf; - char in04_last[24]; + char in04_last[USX2Y_IN04_SIZE]; unsigned int in04_int_calls; struct snd_usx2y_urb_seq *us04; wait_queue_head_t in04_wait_queue; diff --git a/tools/bootconfig/main.c b/tools/bootconfig/main.c index 7dc9fff9b6370e..17d971d47f8791 100644 --- a/tools/bootconfig/main.c +++ b/tools/bootconfig/main.c @@ -140,6 +140,9 @@ static int load_xbc_fd(int fd, char **buf, int size) { int ret; + if (size < 0 || size > XBC_DATA_MAX) + return -EINVAL; + *buf = malloc(size + 1); if (!*buf) return -ENOMEM; @@ -168,6 +171,13 @@ static int load_xbc_file(const char *path, char **buf) return ret; } + if (stat.st_size > XBC_DATA_MAX) { + pr_err("%s size is too big\n", path); + ret = -E2BIG; + close(fd); + return ret; + } + ret = load_xbc_fd(fd, buf, stat.st_size); close(fd); @@ -218,7 +228,8 @@ static int load_xbc_from_initrd(int fd, char **buf) csum = le32toh(csum); /* Wrong size error */ - if (stat.st_size < size + BOOTCONFIG_FOOTER_SIZE) { + if (size > XBC_DATA_MAX || + size > stat.st_size - BOOTCONFIG_FOOTER_SIZE) { pr_err("bootconfig size is too big\n"); return -E2BIG; } diff --git a/tools/objtool/klp-checksum.c b/tools/objtool/klp-checksum.c index b8e47f28997e92..ebe25f9c5260ad 100644 --- a/tools/objtool/klp-checksum.c +++ b/tools/objtool/klp-checksum.c @@ -54,6 +54,19 @@ static int checksum_debug_init(struct objtool_file *file) return 0; } +/* + * Detect a reference to anonymous constant pool data which the compiler places + * in .rodata.cst and which either has an .LC symbol associated with + * it or (with Clang) no symbol at all. These are typically initializers for + * local function stack data, so they're considered part of the function rather + * than data per se. + */ +static bool is_anonymous_const_data(struct symbol *sym) +{ + return strstarts(sym->sec->name, ".rodata.cst") && + (is_sec_sym(sym) || strstarts(sym->name, ".LC")); +} + static void checksum_update_insn(struct objtool_file *file, struct symbol *func, struct instruction *insn) { @@ -129,6 +142,14 @@ static void checksum_update_insn(struct objtool_file *file, struct symbol *func, goto alts; } + if (is_anonymous_const_data(sym)) { + void *cst; + + cst = sym->sec->data->d_buf + sym->offset + offset; + __checksum_update_insn(func, insn, cst, sym->sec->sh.sh_entsize); + goto alts; + } + if (is_sec_sym(sym)) { sym = find_symbol_containing(reloc->sym->sec, offset); if (!sym) diff --git a/tools/perf/util/powerpc-vpadtl.c b/tools/perf/util/powerpc-vpadtl.c index 710f3093f3f909..af6783cfdb53d7 100644 --- a/tools/perf/util/powerpc-vpadtl.c +++ b/tools/perf/util/powerpc-vpadtl.c @@ -196,7 +196,7 @@ static int powerpc_vpadtl_sample(struct powerpc_vpadtl_entry *record, sample.cpumode = PERF_RECORD_MISC_KERNEL; sample.time = save; sample.raw_data = record; - sample.raw_size = sizeof(record); + sample.raw_size = sizeof(*record); event.sample.header.type = PERF_RECORD_SAMPLE; event.sample.header.misc = sample.cpumode; event.sample.header.size = sizeof(struct perf_event_header); diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 35104a56d8e385..1de5796fc4ff66 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -1947,7 +1947,16 @@ int dso__load(struct dso *dso, struct map *map) if (next_slot) { ss_pos++; - if (dso__binary_type(dso) == DSO_BINARY_TYPE__NOT_FOUND) + /* + * The binary type is used to find the file containing + * the executed instructions, so prefer the types that + * refer to the actual object over debug-only files such + * as DSO_BINARY_TYPE__DEBUGLINK. + */ + if (dso__binary_type(dso) == DSO_BINARY_TYPE__NOT_FOUND || + symtab_type == DSO_BINARY_TYPE__BUILD_ID_CACHE || + (symtab_type == DSO_BINARY_TYPE__SYSTEM_PATH_DSO && + dso__binary_type(dso) != DSO_BINARY_TYPE__BUILD_ID_CACHE)) dso__set_binary_type(dso, symtab_type); if (syms_ss && runtime_ss) diff --git a/tools/sched_ext/scx_central.bpf.c b/tools/sched_ext/scx_central.bpf.c index 64dd60b3e92239..65dae9e454009e 100644 --- a/tools/sched_ext/scx_central.bpf.c +++ b/tools/sched_ext/scx_central.bpf.c @@ -299,6 +299,7 @@ static int central_timerfn(void *map, int *key, struct bpf_timer *timer) u64 now = scx_bpf_now(); u64 nr_to_kick = nr_queued; s32 i, curr_cpu; + int ret; curr_cpu = bpf_get_smp_processor_id(); if (timer_pinned && (curr_cpu != central_cpu)) { @@ -332,7 +333,10 @@ static int central_timerfn(void *map, int *key, struct bpf_timer *timer) scx_bpf_kick_cpu(cpu, SCX_KICK_PREEMPT); } - bpf_timer_start(timer, TIMER_INTERVAL_NS, BPF_F_TIMER_CPU_PIN); + ret = bpf_timer_start(timer, TIMER_INTERVAL_NS, + timer_pinned ? BPF_F_TIMER_CPU_PIN : 0); + if (ret) + scx_bpf_error("bpf_timer_start failed (%d)", ret); __sync_fetch_and_add(&nr_timers, 1); return 0; } diff --git a/tools/sched_ext/scx_flatcg.bpf.c b/tools/sched_ext/scx_flatcg.bpf.c index ddcf6bc03b11c8..98fdd4b0403316 100644 --- a/tools/sched_ext/scx_flatcg.bpf.c +++ b/tools/sched_ext/scx_flatcg.bpf.c @@ -934,7 +934,7 @@ void BPF_STRUCT_OPS(fcg_cgroup_move, struct task_struct *p, if (!(from_cgc = find_cgrp_ctx(from)) || !(to_cgc = find_cgrp_ctx(to))) return; - delta = time_delta(p->scx.dsq_vtime, from_cgc->tvtime_now); + delta = (s64)(p->scx.dsq_vtime - from_cgc->tvtime_now); scx_bpf_task_set_dsq_vtime(p, to_cgc->tvtime_now + delta); } diff --git a/tools/testing/selftests/alsa/mixer-test.c b/tools/testing/selftests/alsa/mixer-test.c index a329f901c5edf4..0857d64c322a01 100644 --- a/tools/testing/selftests/alsa/mixer-test.c +++ b/tools/testing/selftests/alsa/mixer-test.c @@ -319,8 +319,8 @@ static bool ctl_value_index_valid(struct ctl_data *ctl, /* Only check step size if there is one and we're in bounds */ if (snd_ctl_elem_info_get_step(ctl->info) && - (int_val - snd_ctl_elem_info_get_min(ctl->info) % - snd_ctl_elem_info_get_step(ctl->info))) { + (int_val - snd_ctl_elem_info_get_min(ctl->info)) % + snd_ctl_elem_info_get_step(ctl->info)) { ksft_print_msg("%s.%d value %ld invalid for step %ld minimum %ld\n", ctl->name, index, int_val, snd_ctl_elem_info_get_step(ctl->info), diff --git a/tools/testing/selftests/bpf/progs/test_bpf_nf.c b/tools/testing/selftests/bpf/progs/test_bpf_nf.c index df43649ecb7854..eda9b7bbab7580 100644 --- a/tools/testing/selftests/bpf/progs/test_bpf_nf.c +++ b/tools/testing/selftests/bpf/progs/test_bpf_nf.c @@ -190,8 +190,8 @@ nf_ct_test(struct nf_conn *(*lookup_fn)(void *, struct bpf_sock_tuple *, u32, ct = alloc_fn(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4), &opts_def, sizeof(opts_def)); if (ct) { - __u16 sport = bpf_get_prandom_u32(); - __u16 dport = bpf_get_prandom_u32(); + __u16 sport = bpf_get_prandom_u32() % 65535 + 1; + __u16 dport = bpf_get_prandom_u32() % 65535 + 1; union nf_inet_addr saddr = {}; union nf_inet_addr daddr = {}; struct nf_conn *ct_ins; @@ -293,8 +293,8 @@ nf_ct_opts_new_test(struct nf_conn *(*lookup_fn)(void *, struct bpf_sock_tuple * ct = alloc_fn(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4), &opts_def, sizeof(opts_def)); if (ct) { - __u16 sport = bpf_get_prandom_u32(); - __u16 dport = bpf_get_prandom_u32(); + __u16 sport = bpf_get_prandom_u32() % 65535 + 1; + __u16 dport = bpf_get_prandom_u32() % 65535 + 1; union nf_inet_addr saddr = {}; union nf_inet_addr daddr = {}; struct nf_conn *ct_ins; diff --git a/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c b/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c index d21d32f6a67602..d990532e88b6d7 100644 --- a/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c +++ b/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c @@ -287,9 +287,9 @@ __msg("17: (b7) r0 = 0") __msg("18: (95) exit") __msg("returning from callee:") __msg("to caller at 9:") -__msg("frame 0: propagating r1,r4") +__msg("frame 0: propagating r1,r3,r4") __msg("mark_precise: frame0: last_idx 9 first_idx 9 subseq_idx -1") -__msg("mark_precise: frame0: regs=r1,r4 stack= before 18: (95) exit") +__msg("mark_precise: frame0: regs=r1,r3,r4 stack= before 18: (95) exit") __msg("from 18 to 9: safe") __naked int callback_result_precise(void) { @@ -419,9 +419,9 @@ __msg("to caller at 9:") /* r1, r4 are always precise for bpf_loop(), * r6 was marked before backtracking to callback body. */ -__msg("frame 0: propagating r1,r4,r6") +__msg("frame 0: propagating r1,r3,r4,r6") __msg("mark_precise: frame0: last_idx 9 first_idx 9 subseq_idx -1") -__msg("mark_precise: frame0: regs=r1,r4,r6 stack= before 16: (95) exit") +__msg("mark_precise: frame0: regs=r1,r3,r4,r6 stack= before 16: (95) exit") __msg("mark_precise: frame1: regs= stack= before 15: (b7) r0 = 0") __msg("mark_precise: frame1: regs= stack= before 9: (85) call bpf_loop") __msg("mark_precise: frame0: parent state regs= stack=:") @@ -575,9 +575,9 @@ __msg("to caller at 10:") /* r1, r4 are always precise for bpf_loop(), * fp-8 was marked before backtracking to callback body. */ -__msg("frame 0: propagating r1,r4,fp-8") +__msg("frame 0: propagating r1,r3,r4,fp-8") __msg("mark_precise: frame0: last_idx 10 first_idx 10 subseq_idx -1") -__msg("mark_precise: frame0: regs=r1,r4 stack=-8 before 18: (95) exit") +__msg("mark_precise: frame0: regs=r1,r3,r4 stack=-8 before 18: (95) exit") __msg("mark_precise: frame1: regs= stack= before 17: (b7) r0 = 0") __msg("mark_precise: frame1: regs= stack= before 10: (85) call bpf_loop#181") __msg("mark_precise: frame0: parent state regs= stack=:") diff --git a/tools/testing/selftests/cgroup/test_core.c b/tools/testing/selftests/cgroup/test_core.c index 88ca832d4fc130..64f4962a4659df 100644 --- a/tools/testing/selftests/cgroup/test_core.c +++ b/tools/testing/selftests/cgroup/test_core.c @@ -927,7 +927,6 @@ int main(int argc, char *argv[]) int i; ksft_print_header(); - ksft_set_plan(ARRAY_SIZE(tests)); if (cg_find_unified_root(root, sizeof(root), &nsdelegate)) { if (setup_named_v1_root(root, sizeof(root), CG_NAMED_NAME)) ksft_exit_skip("cgroup v2 isn't mounted and could not setup named v1 hierarchy\n"); @@ -940,6 +939,7 @@ int main(int argc, char *argv[]) ksft_exit_skip("Failed to set memory controller\n"); post_v2_setup: + ksft_set_plan(ARRAY_SIZE(tests)); for (i = 0; i < ARRAY_SIZE(tests); i++) { switch (tests[i].fn(root)) { case KSFT_PASS: diff --git a/tools/testing/selftests/cgroup/test_cpu.c b/tools/testing/selftests/cgroup/test_cpu.c index 7a40d76b95487c..8f96bfd19ab9fd 100644 --- a/tools/testing/selftests/cgroup/test_cpu.c +++ b/tools/testing/selftests/cgroup/test_cpu.c @@ -799,7 +799,6 @@ int main(int argc, char *argv[]) int i; ksft_print_header(); - ksft_set_plan(ARRAY_SIZE(tests)); if (cg_find_unified_root(root, sizeof(root), NULL)) ksft_exit_skip("cgroup v2 isn't mounted\n"); @@ -807,6 +806,7 @@ int main(int argc, char *argv[]) if (cg_write(root, "cgroup.subtree_control", "+cpu")) ksft_exit_skip("Failed to set cpu controller\n"); + ksft_set_plan(ARRAY_SIZE(tests)); for (i = 0; i < ARRAY_SIZE(tests); i++) { switch (tests[i].fn(root)) { case KSFT_PASS: diff --git a/tools/testing/selftests/cgroup/test_cpuset.c b/tools/testing/selftests/cgroup/test_cpuset.c index c5cf8b56ceb8f7..52ed8fba685aef 100644 --- a/tools/testing/selftests/cgroup/test_cpuset.c +++ b/tools/testing/selftests/cgroup/test_cpuset.c @@ -250,7 +250,6 @@ int main(int argc, char *argv[]) int i; ksft_print_header(); - ksft_set_plan(ARRAY_SIZE(tests)); if (cg_find_unified_root(root, sizeof(root), NULL)) ksft_exit_skip("cgroup v2 isn't mounted\n"); @@ -258,6 +257,7 @@ int main(int argc, char *argv[]) if (cg_write(root, "cgroup.subtree_control", "+cpuset")) ksft_exit_skip("Failed to set cpuset controller\n"); + ksft_set_plan(ARRAY_SIZE(tests)); for (i = 0; i < ARRAY_SIZE(tests); i++) { switch (tests[i].fn(root)) { case KSFT_PASS: diff --git a/tools/testing/selftests/cgroup/test_cpuset_prs.sh b/tools/testing/selftests/cgroup/test_cpuset_prs.sh index b2e60671273ec1..ebbc5b4def2438 100755 --- a/tools/testing/selftests/cgroup/test_cpuset_prs.sh +++ b/tools/testing/selftests/cgroup/test_cpuset_prs.sh @@ -791,7 +791,6 @@ check_isolcpus() EXPECTED_ISOLCPUS=$1 ISCPUS=${CGROUP2}/cpuset.cpus.isolated ISOLCPUS=$(cat $ISCPUS) - HKICPUS=$(cat /sys/devices/system/cpu/isolated) LASTISOLCPU= SCHED_DOMAINS=/sys/kernel/debug/sched/domains if [[ $EXPECTED_ISOLCPUS = . ]] @@ -829,11 +828,6 @@ check_isolcpus() ISOLCPUS= EXPECTED_ISOLCPUS=$EXPECTED_SDOMAIN - # - # The inverse of HK_TYPE_DOMAIN cpumask in $HKICPUS should match $ISOLCPUS - # - [[ "$ISOLCPUS" != "$HKICPUS" ]] && return 1 - # # Use the sched domain in debugfs to check isolated CPUs, if available # diff --git a/tools/testing/selftests/cgroup/test_freezer.c b/tools/testing/selftests/cgroup/test_freezer.c index 0569e93fa6b005..f28bb02e9783b0 100644 --- a/tools/testing/selftests/cgroup/test_freezer.c +++ b/tools/testing/selftests/cgroup/test_freezer.c @@ -1491,9 +1491,9 @@ int main(int argc, char *argv[]) int i; ksft_print_header(); - ksft_set_plan(ARRAY_SIZE(tests)); if (cg_find_unified_root(root, sizeof(root), NULL)) ksft_exit_skip("cgroup v2 isn't mounted\n"); + ksft_set_plan(ARRAY_SIZE(tests)); for (i = 0; i < ARRAY_SIZE(tests); i++) { switch (tests[i].fn(root)) { case KSFT_PASS: diff --git a/tools/testing/selftests/cgroup/test_kill.c b/tools/testing/selftests/cgroup/test_kill.c index f6cd23a8ecc71c..99cafd9dc0136e 100644 --- a/tools/testing/selftests/cgroup/test_kill.c +++ b/tools/testing/selftests/cgroup/test_kill.c @@ -278,9 +278,9 @@ int main(int argc, char *argv[]) int i; ksft_print_header(); - ksft_set_plan(ARRAY_SIZE(tests)); if (cg_find_unified_root(root, sizeof(root), NULL)) ksft_exit_skip("cgroup v2 isn't mounted\n"); + ksft_set_plan(ARRAY_SIZE(tests)); for (i = 0; i < ARRAY_SIZE(tests); i++) { switch (tests[i].fn(root)) { case KSFT_PASS: diff --git a/tools/testing/selftests/cgroup/test_kmem.c b/tools/testing/selftests/cgroup/test_kmem.c index 1db0ba1226b9bf..437f2d35f205ef 100644 --- a/tools/testing/selftests/cgroup/test_kmem.c +++ b/tools/testing/selftests/cgroup/test_kmem.c @@ -145,7 +145,7 @@ static int cg_run_in_subcgroups(const char *parent, return -1; } - if (cg_run(child, fn, NULL)) { + if (cg_run(child, fn, arg)) { cg_destroy(child); free(child); return -1; @@ -426,7 +426,6 @@ int main(int argc, char **argv) int i; ksft_print_header(); - ksft_set_plan(ARRAY_SIZE(tests)); if (cg_find_unified_root(root, sizeof(root), NULL)) ksft_exit_skip("cgroup v2 isn't mounted\n"); @@ -441,6 +440,7 @@ int main(int argc, char **argv) if (cg_write(root, "cgroup.subtree_control", "+memory")) ksft_exit_skip("Failed to set memory controller\n"); + ksft_set_plan(ARRAY_SIZE(tests)); for (i = 0; i < ARRAY_SIZE(tests); i++) { switch (tests[i].fn(root)) { case KSFT_PASS: diff --git a/tools/testing/selftests/cgroup/test_memcontrol.c b/tools/testing/selftests/cgroup/test_memcontrol.c index 0ebf796f3cffe2..3a84d068fbf368 100644 --- a/tools/testing/selftests/cgroup/test_memcontrol.c +++ b/tools/testing/selftests/cgroup/test_memcontrol.c @@ -1798,7 +1798,6 @@ int main(int argc, char **argv) page_size = BUF_SIZE; ksft_print_header(); - ksft_set_plan(ARRAY_SIZE(tests)); if (cg_find_unified_root(root, sizeof(root), NULL)) ksft_exit_skip("cgroup v2 isn't mounted\n"); @@ -1823,6 +1822,7 @@ int main(int argc, char **argv) ksft_exit_skip("Failed to query cgroup mount option\n"); has_localevents = proc_status; + ksft_set_plan(ARRAY_SIZE(tests)); for (i = 0; i < ARRAY_SIZE(tests); i++) { switch (tests[i].fn(root)) { case KSFT_PASS: diff --git a/tools/testing/selftests/cgroup/test_pids.c b/tools/testing/selftests/cgroup/test_pids.c index 9a387c815d2cd5..710109b53dfe96 100644 --- a/tools/testing/selftests/cgroup/test_pids.c +++ b/tools/testing/selftests/cgroup/test_pids.c @@ -148,7 +148,6 @@ int main(int argc, char **argv) char root[PATH_MAX]; ksft_print_header(); - ksft_set_plan(ARRAY_SIZE(tests)); if (cg_find_unified_root(root, sizeof(root), NULL)) ksft_exit_skip("cgroup v2 isn't mounted\n"); @@ -163,6 +162,7 @@ int main(int argc, char **argv) if (cg_write(root, "cgroup.subtree_control", "+pids")) ksft_exit_skip("Failed to set pids controller\n"); + ksft_set_plan(ARRAY_SIZE(tests)); for (int i = 0; i < ARRAY_SIZE(tests); i++) { switch (tests[i].fn(root)) { case KSFT_PASS: diff --git a/tools/testing/selftests/cgroup/test_zswap.c b/tools/testing/selftests/cgroup/test_zswap.c index 49b36ee791606f..6e7b89315bbf3e 100644 --- a/tools/testing/selftests/cgroup/test_zswap.c +++ b/tools/testing/selftests/cgroup/test_zswap.c @@ -810,7 +810,6 @@ int main(int argc, char **argv) page_size = BUF_SIZE; ksft_print_header(); - ksft_set_plan(ARRAY_SIZE(tests)); if (cg_find_unified_root(root, sizeof(root), NULL)) ksft_exit_skip("cgroup v2 isn't mounted\n"); @@ -827,6 +826,7 @@ int main(int argc, char **argv) if (cg_write(root, "cgroup.subtree_control", "+memory")) ksft_exit_skip("Failed to set memory controller\n"); + ksft_set_plan(ARRAY_SIZE(tests)); for (i = 0; i < ARRAY_SIZE(tests); i++) { switch (tests[i].fn(root)) { case KSFT_PASS: diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh index ac868a7316946a..daceb1ec592ab4 100755 --- a/tools/testing/selftests/net/fib_nexthops.sh +++ b/tools/testing/selftests/net/fib_nexthops.sh @@ -522,6 +522,20 @@ ipv6_fdb_grp_fcnal() run_cmd "$BRIDGE fdb add 02:02:00:00:00:14 dev vx10 nhid 61 self" log_test $? 255 "Fdb mac add with nexthop" + # fdb entries with a nexthop group cannot be aged out + run_cmd "$BRIDGE fdb add 02:02:00:00:00:15 dev vx10 nhid 102 self static" + log_test $? 0 "Fdb mac add with nexthop group and static state" + + run_cmd "$BRIDGE fdb add 02:02:00:00:00:16 dev vx10 nhid 102 self dynamic" + log_test $? 255 "Fdb mac add with nexthop group and dynamic state" + + run_cmd "$BRIDGE fdb add 02:02:00:00:00:17 dev vx10 nhid 102 self" + run_cmd "$BRIDGE fdb replace 02:02:00:00:00:17 dev vx10 dst 2001:db8:91::11 self dynamic" + log_test $? 255 "Fdb mac replace with nexthop group and dynamic state" + + run_cmd "$BRIDGE fdb append 02:02:00:00:00:17 dev vx10 dst 2001:db8:91::11 self dynamic" + log_test $? 255 "Fdb mac append with nexthop group and dynamic state" + run_cmd "$IP -6 ro add 2001:db8:101::1/128 nhid 66" log_test $? 2 "Route add with fdb nexthop" @@ -622,6 +636,20 @@ ipv4_fdb_grp_fcnal() run_cmd "$BRIDGE fdb add 02:02:00:00:00:14 dev vx10 nhid 12 self" log_test $? 255 "Fdb mac add with nexthop" + # fdb entries with a nexthop group cannot be aged out + run_cmd "$BRIDGE fdb add 02:02:00:00:00:15 dev vx10 nhid 102 self static" + log_test $? 0 "Fdb mac add with nexthop group and static state" + + run_cmd "$BRIDGE fdb add 02:02:00:00:00:16 dev vx10 nhid 102 self dynamic" + log_test $? 255 "Fdb mac add with nexthop group and dynamic state" + + run_cmd "$BRIDGE fdb add 02:02:00:00:00:17 dev vx10 nhid 102 self" + run_cmd "$BRIDGE fdb replace 02:02:00:00:00:17 dev vx10 dst 10.0.0.3 self dynamic" + log_test $? 255 "Fdb mac replace with nexthop group and dynamic state" + + run_cmd "$BRIDGE fdb append 02:02:00:00:00:17 dev vx10 dst 10.0.0.3 self dynamic" + log_test $? 255 "Fdb mac append with nexthop group and dynamic state" + run_cmd "$IP ro add 172.16.0.0/22 nhid 16" log_test $? 2 "Route add with fdb nexthop" diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/testing/selftests/net/mptcp/mptcp_connect.c index cbe573c4ab3ad2..4c339ad449a7af 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.c +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c @@ -381,6 +381,9 @@ static int sock_connect_mptcp(const char * const remoteaddr, hints.ai_family = pf; + /* Keep the resolved address alive for the whole execution: it is + * used again when reconnecting, and will be released at exit time. + */ xgetaddrinfo(remoteaddr, port, &hints, &addr); for (a = addr; a; a = a->ai_next) { sock = socket(a->ai_family, a->ai_socktype, proto); @@ -421,7 +424,6 @@ static int sock_connect_mptcp(const char * const remoteaddr, sock = -1; } - freeaddrinfo(addr); if (sock != -1) SOCK_TEST_TCPULP(sock, proto); return sock; diff --git a/tools/testing/selftests/net/mptcp/mptcp_lib.sh b/tools/testing/selftests/net/mptcp/mptcp_lib.sh index 5ef6033775c86d..b9d14647f40190 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_lib.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_lib.sh @@ -108,12 +108,14 @@ mptcp_lib_pr_info() { mptcp_lib_pr_nstat() { local ns="${1}" - local hist="/tmp/${ns}.out" + local cache="/tmp/${ns}.out" + local hist="/tmp/${ns}.nstat" - if [ -f "${hist}" ]; then - awk '$2 != 0 { print " "$0 }' "${hist}" + if [ -f "${cache}" ]; then + awk '$2 != 0 { print " "$0 }' "${cache}" else - ip netns exec "${ns}" nstat -as | grep Tcp + NSTAT_HISTORY="${hist}" ip netns exec "${ns}" nstat -s | + grep Tcp fi } @@ -414,19 +416,21 @@ mptcp_lib_nstat_get() { } # $1: ns, $2: MIB counter -# Get the counter from the history (mptcp_lib_nstat_{init,get}()) if available. -# If not, get the counter from nstat ignoring any history. +# Get the counter from the cache (mptcp_lib_nstat_{init,get}()) if available. +# If not, get the counter from nstat ignoring any cache, but using the history. mptcp_lib_get_counter() { local ns="${1}" local counter="${2}" - local hist="/tmp/${ns}.out" + local cache="/tmp/${ns}.out" + local hist="/tmp/${ns}.nstat" local count - if [[ -s "${hist}" && "${counter}" == *"Tcp"* ]]; then - count=$(awk "/^${counter} / {print \$2; exit}" "${hist}") + if [[ -s "${cache}" && "${counter}" == *"Tcp"* ]]; then + count=$(awk "/^${counter} / {print \$2; exit}" "${cache}") else - count=$(ip netns exec "${ns}" nstat -asz "${counter}" | - awk 'NR==1 {next} {print $2}') + count=$(NSTAT_HISTORY="${hist}" ip netns exec "${ns}" \ + nstat -sz "${counter}" | + awk 'NR==1 {next} {print $2}') fi if [ -z "${count}" ]; then mptcp_lib_fail_if_expected_feature "${counter} counter" diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh index a3323c21f00149..c7cd271714ef7c 100755 --- a/tools/testing/selftests/net/pmtu.sh +++ b/tools/testing/selftests/net/pmtu.sh @@ -1457,7 +1457,7 @@ test_pmtu_ipvX_over_bridged_vxlanY_or_geneveY_exception() { mtu "${ns_b}" ${type}_b $((${ll_mtu} + 1000)) run_cmd ${ns_c} ${ping} -q -M want -i 0.1 -c 10 -s $((${ll_mtu} + 500)) ${dst} || return 1 - run_cmd ${ns_a} ${ping} -q -M want -i 0.1 -w 1 -s $((${ll_mtu} + 500)) ${dst} || return 1 + run_cmd ${ns_a} ${ping} -q -M want -i 0.1 -c 10 -s $((${ll_mtu} + 500)) ${dst} || return 1 # Check that exceptions were created pmtu="$(route_get_dst_pmtu_from_exception "${ns_c}" ${dst})" diff --git a/tools/testing/selftests/net/test_vxlan_mdb.sh b/tools/testing/selftests/net/test_vxlan_mdb.sh index 58da5de99ac451..f9600aabd4a29a 100755 --- a/tools/testing/selftests/net/test_vxlan_mdb.sh +++ b/tools/testing/selftests/net/test_vxlan_mdb.sh @@ -685,6 +685,9 @@ star_g_common() run_cmd "bridge -n $ns1 mdb add dev vx0 port vx0 grp $grp permanent filter_mode exclude source_list $grp dst $vtep_ip src_vni 10010" log_test $? 255 "Invalid source in source list" + run_cmd "bridge -n $ns1 mdb add dev vx0 port vx0 grp $grp permanent filter_mode exclude source_list $all_zeros_grp dst $vtep_ip src_vni 10010" + log_test $? 255 "All-zeros source in source list" + run_cmd "bridge -n $ns1 mdb add dev vx0 port vx0 grp $grp permanent source_list $src1 dst $vtep_ip src_vni 10010" log_test $? 255 "Source list without filter mode" } @@ -784,6 +787,9 @@ sg_common() run_cmd "bridge -n $ns1 mdb add dev vx0 port vx0 grp $grp src $grp permanent dst $vtep_ip src_vni 10010" log_test $? 255 "(S, G) with an invalid source list" + run_cmd "bridge -n $ns1 mdb add dev vx0 port vx0 grp $grp src $all_zeros_grp permanent dst $vtep_ip src_vni 10010" + log_test $? 255 "(S, G) with an all-zeros source" + run_cmd "bridge -n $ns1 mdb add dev vx0 port vx0 grp $all_zeros_grp src $src permanent dst $vtep_ip src_vni 10010" log_test $? 255 "All-zeros group with source" } diff --git a/tools/testing/selftests/powerpc/tm/tm.h b/tools/testing/selftests/powerpc/tm/tm.h index c03c6e77887679..6024ce4ba6ffd7 100644 --- a/tools/testing/selftests/powerpc/tm/tm.h +++ b/tools/testing/selftests/powerpc/tm/tm.h @@ -105,8 +105,12 @@ static inline bool failure_is_nesting(void) static inline int tcheck(void) { long cr; - asm volatile ("tcheck 0" : "=r"(cr) : : "cr0"); - return (cr >> 28) & 4; + asm volatile("tcheck 0;" + "mfcr %0;" + : "=r"(cr) + : + : "cr0"); + return (cr >> 28) & 0xf; } static inline bool tcheck_doomed(void) diff --git a/tools/testing/selftests/ublk/Makefile b/tools/testing/selftests/ublk/Makefile index 6e4fe8d1fed1d0..6dbae1391a0647 100644 --- a/tools/testing/selftests/ublk/Makefile +++ b/tools/testing/selftests/ublk/Makefile @@ -69,6 +69,8 @@ TEST_PROGS += test_stress_08.sh TEST_PROGS += test_stress_09.sh TEST_FILES := settings +TEST_FILES += test_common.sh +TEST_FILES += trace TEST_GEN_PROGS_EXTENDED = kublk metadata_size STANDALONE_UTILS := metadata_size.c