diff --git a/Makefile b/Makefile index 3cbbc82e2ddf2..87828284236e3 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 5 PATCHLEVEL = 4 -SUBLEVEL = 231 +SUBLEVEL = 232 EXTRAVERSION = NAME = Kleptomaniac Octopus diff --git a/arch/arm64/boot/dts/amlogic/meson-axg.dtsi b/arch/arm64/boot/dts/amlogic/meson-axg.dtsi index 502c4ac45c29e..8732229f0588c 100644 --- a/arch/arm64/boot/dts/amlogic/meson-axg.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-axg.dtsi @@ -1705,7 +1705,7 @@ sd_emmc_b: sd@5000 { compatible = "amlogic,meson-axg-mmc"; reg = <0x0 0x5000 0x0 0x800>; - interrupts = ; + interrupts = ; status = "disabled"; clocks = <&clkc CLKID_SD_EMMC_B>, <&clkc CLKID_SD_EMMC_B_CLK0>, @@ -1717,7 +1717,7 @@ sd_emmc_c: mmc@7000 { compatible = "amlogic,meson-axg-mmc"; reg = <0x0 0x7000 0x0 0x800>; - interrupts = ; + interrupts = ; status = "disabled"; clocks = <&clkc CLKID_SD_EMMC_C>, <&clkc CLKID_SD_EMMC_C_CLK0>, diff --git a/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi b/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi index d2d255a988a81..6b495587eee2d 100644 --- a/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi @@ -2317,7 +2317,7 @@ sd_emmc_a: sd@ffe03000 { compatible = "amlogic,meson-axg-mmc"; reg = <0x0 0xffe03000 0x0 0x800>; - interrupts = ; + interrupts = ; status = "disabled"; clocks = <&clkc CLKID_SD_EMMC_A>, <&clkc CLKID_SD_EMMC_A_CLK0>, @@ -2329,7 +2329,7 @@ sd_emmc_b: sd@ffe05000 { compatible = "amlogic,meson-axg-mmc"; reg = <0x0 0xffe05000 0x0 0x800>; - interrupts = ; + interrupts = ; status = "disabled"; clocks = <&clkc CLKID_SD_EMMC_B>, <&clkc CLKID_SD_EMMC_B_CLK0>, @@ -2341,7 +2341,7 @@ sd_emmc_c: mmc@ffe07000 { compatible = "amlogic,meson-axg-mmc"; reg = <0x0 0xffe07000 0x0 0x800>; - interrupts = ; + interrupts = ; status = "disabled"; clocks = <&clkc CLKID_SD_EMMC_C>, <&clkc CLKID_SD_EMMC_C_CLK0>, diff --git a/arch/arm64/boot/dts/amlogic/meson-gx.dtsi b/arch/arm64/boot/dts/amlogic/meson-gx.dtsi index ad7bc0eec6682..0c667ec15f8cf 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gx.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gx.dtsi @@ -528,21 +528,21 @@ sd_emmc_a: mmc@70000 { compatible = "amlogic,meson-gx-mmc", "amlogic,meson-gxbb-mmc"; reg = <0x0 0x70000 0x0 0x800>; - interrupts = ; + interrupts = ; status = "disabled"; }; sd_emmc_b: mmc@72000 { compatible = "amlogic,meson-gx-mmc", "amlogic,meson-gxbb-mmc"; reg = <0x0 0x72000 0x0 0x800>; - interrupts = ; + interrupts = ; status = "disabled"; }; sd_emmc_c: mmc@74000 { compatible = "amlogic,meson-gx-mmc", "amlogic,meson-gxbb-mmc"; reg = <0x0 0x74000 0x0 0x800>; - interrupts = ; + interrupts = ; status = "disabled"; }; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-pinfunc.h b/arch/arm64/boot/dts/freescale/imx8mm-pinfunc.h index 93b44efdbc527..35a60b0d3a4f0 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-pinfunc.h +++ b/arch/arm64/boot/dts/freescale/imx8mm-pinfunc.h @@ -585,7 +585,7 @@ #define MX8MM_IOMUXC_UART1_RXD_GPIO5_IO22 0x234 0x49C 0x000 0x5 0x0 #define MX8MM_IOMUXC_UART1_RXD_TPSMP_HDATA24 0x234 0x49C 0x000 0x7 0x0 #define MX8MM_IOMUXC_UART1_TXD_UART1_DCE_TX 0x238 0x4A0 0x000 0x0 0x0 -#define MX8MM_IOMUXC_UART1_TXD_UART1_DTE_RX 0x238 0x4A0 0x4F4 0x0 0x0 +#define MX8MM_IOMUXC_UART1_TXD_UART1_DTE_RX 0x238 0x4A0 0x4F4 0x0 0x1 #define MX8MM_IOMUXC_UART1_TXD_ECSPI3_MOSI 0x238 0x4A0 0x000 0x1 0x0 #define MX8MM_IOMUXC_UART1_TXD_GPIO5_IO23 0x238 0x4A0 0x000 0x5 0x0 #define MX8MM_IOMUXC_UART1_TXD_TPSMP_HDATA25 0x238 0x4A0 0x000 0x7 0x0 diff --git a/arch/parisc/kernel/firmware.c b/arch/parisc/kernel/firmware.c index 1d976f2ebff0f..2496cb2c55511 100644 --- a/arch/parisc/kernel/firmware.c +++ b/arch/parisc/kernel/firmware.c @@ -1229,7 +1229,7 @@ static char __attribute__((aligned(64))) iodc_dbuf[4096]; */ int pdc_iodc_print(const unsigned char *str, unsigned count) { - unsigned int i; + unsigned int i, found = 0; unsigned long flags; for (i = 0; i < count;) { @@ -1238,6 +1238,7 @@ int pdc_iodc_print(const unsigned char *str, unsigned count) iodc_dbuf[i+0] = '\r'; iodc_dbuf[i+1] = '\n'; i += 2; + found = 1; goto print; default: iodc_dbuf[i] = str[i]; @@ -1254,7 +1255,7 @@ print: __pa(iodc_retbuf), 0, __pa(iodc_dbuf), i, 0); spin_unlock_irqrestore(&pdc_lock, flags); - return i; + return i - found; } #if !defined(BOOTLOADER) diff --git a/arch/parisc/kernel/ptrace.c b/arch/parisc/kernel/ptrace.c index 9f6ff7bc06f9a..7407fee7d8182 100644 --- a/arch/parisc/kernel/ptrace.c +++ b/arch/parisc/kernel/ptrace.c @@ -128,6 +128,12 @@ long arch_ptrace(struct task_struct *child, long request, unsigned long tmp; long ret = -EIO; + unsigned long user_regs_struct_size = sizeof(struct user_regs_struct); +#ifdef CONFIG_64BIT + if (is_compat_task()) + user_regs_struct_size /= 2; +#endif + switch (request) { /* Read the word at location addr in the USER area. For ptraced @@ -183,14 +189,14 @@ long arch_ptrace(struct task_struct *child, long request, return copy_regset_to_user(child, task_user_regset_view(current), REGSET_GENERAL, - 0, sizeof(struct user_regs_struct), + 0, user_regs_struct_size, datap); case PTRACE_SETREGS: /* Set all gp regs in the child. */ return copy_regset_from_user(child, task_user_regset_view(current), REGSET_GENERAL, - 0, sizeof(struct user_regs_struct), + 0, user_regs_struct_size, datap); case PTRACE_GETFPREGS: /* Get the child FPU state. */ @@ -304,6 +310,11 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request, } } break; + case PTRACE_GETREGS: + case PTRACE_SETREGS: + case PTRACE_GETFPREGS: + case PTRACE_SETFPREGS: + return arch_ptrace(child, request, addr, data); default: ret = compat_ptrace_request(child, request, addr, data); diff --git a/arch/powerpc/perf/imc-pmu.c b/arch/powerpc/perf/imc-pmu.c index b0e4241e7609d..d42f2e091201a 100644 --- a/arch/powerpc/perf/imc-pmu.c +++ b/arch/powerpc/perf/imc-pmu.c @@ -21,7 +21,7 @@ * Used to avoid races in counting the nest-pmu units during hotplug * register and unregister */ -static DEFINE_SPINLOCK(nest_init_lock); +static DEFINE_MUTEX(nest_init_lock); static DEFINE_PER_CPU(struct imc_pmu_ref *, local_nest_imc_refc); static struct imc_pmu **per_nest_pmu_arr; static cpumask_t nest_imc_cpumask; @@ -1605,7 +1605,7 @@ static void imc_common_mem_free(struct imc_pmu *pmu_ptr) static void imc_common_cpuhp_mem_free(struct imc_pmu *pmu_ptr) { if (pmu_ptr->domain == IMC_DOMAIN_NEST) { - spin_lock(&nest_init_lock); + mutex_lock(&nest_init_lock); if (nest_pmus == 1) { cpuhp_remove_state(CPUHP_AP_PERF_POWERPC_NEST_IMC_ONLINE); kfree(nest_imc_refc); @@ -1615,7 +1615,7 @@ static void imc_common_cpuhp_mem_free(struct imc_pmu *pmu_ptr) if (nest_pmus > 0) nest_pmus--; - spin_unlock(&nest_init_lock); + mutex_unlock(&nest_init_lock); } /* Free core_imc memory */ @@ -1772,11 +1772,11 @@ int init_imc_pmu(struct device_node *parent, struct imc_pmu *pmu_ptr, int pmu_id * rest. To handle the cpuhotplug callback unregister, we track * the number of nest pmus in "nest_pmus". */ - spin_lock(&nest_init_lock); + mutex_lock(&nest_init_lock); if (nest_pmus == 0) { ret = init_nest_pmu_ref(); if (ret) { - spin_unlock(&nest_init_lock); + mutex_unlock(&nest_init_lock); kfree(per_nest_pmu_arr); per_nest_pmu_arr = NULL; goto err_free_mem; @@ -1784,7 +1784,7 @@ int init_imc_pmu(struct device_node *parent, struct imc_pmu *pmu_ptr, int pmu_id /* Register for cpu hotplug notification. */ ret = nest_pmu_cpumask_init(); if (ret) { - spin_unlock(&nest_init_lock); + mutex_unlock(&nest_init_lock); kfree(nest_imc_refc); kfree(per_nest_pmu_arr); per_nest_pmu_arr = NULL; @@ -1792,7 +1792,7 @@ int init_imc_pmu(struct device_node *parent, struct imc_pmu *pmu_ptr, int pmu_id } } nest_pmus++; - spin_unlock(&nest_init_lock); + mutex_unlock(&nest_init_lock); break; case IMC_DOMAIN_CORE: ret = core_imc_pmu_cpumask_init(); diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile index aed3ba97575bf..1641d82014127 100644 --- a/arch/riscv/Makefile +++ b/arch/riscv/Makefile @@ -75,6 +75,9 @@ ifeq ($(CONFIG_PERF_EVENTS),y) KBUILD_CFLAGS += -fno-omit-frame-pointer endif +# Avoid generating .eh_frame sections. +KBUILD_CFLAGS += -fno-asynchronous-unwind-tables -fno-unwind-tables + KBUILD_CFLAGS_MODULE += $(call cc-option,-mno-relax) KBUILD_AFLAGS_MODULE += $(call as-option,-Wa$(comma)-mno-relax) diff --git a/arch/riscv/mm/cacheflush.c b/arch/riscv/mm/cacheflush.c index c54bd3c799552..9d1ec8c8b7183 100644 --- a/arch/riscv/mm/cacheflush.c +++ b/arch/riscv/mm/cacheflush.c @@ -71,6 +71,8 @@ void flush_icache_pte(pte_t pte) { struct page *page = pte_page(pte); - if (!test_and_set_bit(PG_dcache_clean, &page->flags)) + if (!test_bit(PG_dcache_clean, &page->flags)) { flush_icache_all(); + set_bit(PG_dcache_clean, &page->flags); + } } diff --git a/arch/s390/boot/compressed/decompressor.c b/arch/s390/boot/compressed/decompressor.c index 45046630c56ac..c42ab33bd4524 100644 --- a/arch/s390/boot/compressed/decompressor.c +++ b/arch/s390/boot/compressed/decompressor.c @@ -80,6 +80,6 @@ void *decompress_kernel(void) void *output = (void *)decompress_offset; __decompress(_compressed_start, _compressed_end - _compressed_start, - NULL, NULL, output, 0, NULL, error); + NULL, NULL, output, vmlinux.image_size, NULL, error); return output; } diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 93727f8092ee4..cf37a61729972 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -3948,12 +3948,11 @@ static void kvm_vcpu_ioctl_x86_get_debugregs(struct kvm_vcpu *vcpu, { unsigned long val; + memset(dbgregs, 0, sizeof(*dbgregs)); memcpy(dbgregs->db, vcpu->arch.db, sizeof(vcpu->arch.db)); kvm_get_dr(vcpu, 6, &val); dbgregs->dr6 = val; dbgregs->dr7 = vcpu->arch.dr7; - dbgregs->flags = 0; - memset(&dbgregs->reserved, 0, sizeof(dbgregs->reserved)); } static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu, diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index fbb1676aa33f1..c06f618b1aa3c 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -3096,7 +3096,7 @@ int sata_down_spd_limit(struct ata_link *link, u32 spd_limit) */ if (spd > 1) mask &= (1 << (spd - 1)) - 1; - else + else if (link->sata_spd) return -EINVAL; /* were we already at the bottom? */ diff --git a/drivers/bus/sunxi-rsb.c b/drivers/bus/sunxi-rsb.c index f8c29b888e6b4..98cbb18f17fa3 100644 --- a/drivers/bus/sunxi-rsb.c +++ b/drivers/bus/sunxi-rsb.c @@ -781,7 +781,13 @@ static int __init sunxi_rsb_init(void) return ret; } - return platform_driver_register(&sunxi_rsb_driver); + ret = platform_driver_register(&sunxi_rsb_driver); + if (ret) { + bus_unregister(&sunxi_rsb_bus); + return ret; + } + + return 0; } module_init(sunxi_rsb_init); diff --git a/drivers/firewire/core-cdev.c b/drivers/firewire/core-cdev.c index 3a43e5d6ed3b2..4fe36d549d615 100644 --- a/drivers/firewire/core-cdev.c +++ b/drivers/firewire/core-cdev.c @@ -818,8 +818,10 @@ static int ioctl_send_response(struct client *client, union ioctl_arg *arg) r = container_of(resource, struct inbound_transaction_resource, resource); - if (is_fcp_request(r->request)) + if (is_fcp_request(r->request)) { + kfree(r->data); goto out; + } if (a->length != fw_get_response_length(r->request)) { ret = -EINVAL; diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index eb98018ab420e..ed31b08855f94 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -1022,6 +1022,8 @@ int __ref efi_mem_reserve_persistent(phys_addr_t addr, u64 size) /* first try to find a slot in an existing linked list entry */ for (prsv = efi_memreserve_root->next; prsv; ) { rsv = memremap(prsv, sizeof(*rsv), MEMREMAP_WB); + if (!rsv) + return -ENOMEM; index = atomic_fetch_add_unless(&rsv->count, 1, rsv->size); if (index < rsv->size) { rsv->entry[index].base = addr; diff --git a/drivers/firmware/efi/memattr.c b/drivers/firmware/efi/memattr.c index 5d343dc8e5354..5f577357c3e7e 100644 --- a/drivers/firmware/efi/memattr.c +++ b/drivers/firmware/efi/memattr.c @@ -32,7 +32,7 @@ int __init efi_memattr_init(void) return -ENOMEM; } - if (tbl->version > 1) { + if (tbl->version > 2) { pr_warn("Unexpected EFI Memory Attributes table version %d\n", tbl->version); goto unmap; diff --git a/drivers/fpga/stratix10-soc.c b/drivers/fpga/stratix10-soc.c index 559839a960b60..04452520fd811 100644 --- a/drivers/fpga/stratix10-soc.c +++ b/drivers/fpga/stratix10-soc.c @@ -218,9 +218,9 @@ static int s10_ops_write_init(struct fpga_manager *mgr, /* Allocate buffers from the service layer's pool. */ for (i = 0; i < NUM_SVC_BUFS; i++) { kbuf = stratix10_svc_allocate_memory(priv->chan, SVC_BUF_SIZE); - if (!kbuf) { + if (IS_ERR(kbuf)) { s10_free_buffers(mgr); - ret = -ENOMEM; + ret = PTR_ERR(kbuf); goto init_done; } diff --git a/drivers/fsi/fsi-sbefifo.c b/drivers/fsi/fsi-sbefifo.c index c8ccc99e214fa..84a60d2d8e8ad 100644 --- a/drivers/fsi/fsi-sbefifo.c +++ b/drivers/fsi/fsi-sbefifo.c @@ -640,7 +640,7 @@ static void sbefifo_collect_async_ffdc(struct sbefifo *sbefifo) } ffdc_iov.iov_base = ffdc; ffdc_iov.iov_len = SBEFIFO_MAX_FFDC_SIZE; - iov_iter_kvec(&ffdc_iter, WRITE, &ffdc_iov, 1, SBEFIFO_MAX_FFDC_SIZE); + iov_iter_kvec(&ffdc_iter, READ, &ffdc_iov, 1, SBEFIFO_MAX_FFDC_SIZE); cmd[0] = cpu_to_be32(2); cmd[1] = cpu_to_be32(SBEFIFO_CMD_GET_SBE_FFDC); rc = sbefifo_do_command(sbefifo, cmd, 2, &ffdc_iter); @@ -737,7 +737,7 @@ int sbefifo_submit(struct device *dev, const __be32 *command, size_t cmd_len, rbytes = (*resp_len) * sizeof(__be32); resp_iov.iov_base = response; resp_iov.iov_len = rbytes; - iov_iter_kvec(&resp_iter, WRITE, &resp_iov, 1, rbytes); + iov_iter_kvec(&resp_iter, READ, &resp_iov, 1, rbytes); /* Perform the command */ mutex_lock(&sbefifo->lock); @@ -817,7 +817,7 @@ static ssize_t sbefifo_user_read(struct file *file, char __user *buf, /* Prepare iov iterator */ resp_iov.iov_base = buf; resp_iov.iov_len = len; - iov_iter_init(&resp_iter, WRITE, &resp_iov, 1, len); + iov_iter_init(&resp_iter, READ, &resp_iov, 1, len); /* Perform the command */ mutex_lock(&sbefifo->lock); diff --git a/drivers/i2c/busses/i2c-rk3x.c b/drivers/i2c/busses/i2c-rk3x.c index 1107a5e7229e4..ac3ae14a4c079 100644 --- a/drivers/i2c/busses/i2c-rk3x.c +++ b/drivers/i2c/busses/i2c-rk3x.c @@ -79,7 +79,7 @@ enum { #define DEFAULT_SCL_RATE (100 * 1000) /* Hz */ /** - * struct i2c_spec_values: + * struct i2c_spec_values - I2C specification values for various modes * @min_hold_start_ns: min hold time (repeated) START condition * @min_low_ns: min LOW period of the SCL clock * @min_high_ns: min HIGH period of the SCL cloc @@ -135,7 +135,7 @@ static const struct i2c_spec_values fast_mode_plus_spec = { }; /** - * struct rk3x_i2c_calced_timings: + * struct rk3x_i2c_calced_timings - calculated V1 timings * @div_low: Divider output for low * @div_high: Divider output for high * @tuning: Used to adjust setup/hold data time, @@ -158,7 +158,7 @@ enum rk3x_i2c_state { }; /** - * struct rk3x_i2c_soc_data: + * struct rk3x_i2c_soc_data - SOC-specific data * @grf_offset: offset inside the grf regmap for setting the i2c type * @calc_timings: Callback function for i2c timing information calculated */ @@ -238,7 +238,8 @@ static inline void rk3x_i2c_clean_ipd(struct rk3x_i2c *i2c) } /** - * Generate a START condition, which triggers a REG_INT_START interrupt. + * rk3x_i2c_start - Generate a START condition, which triggers a REG_INT_START interrupt. + * @i2c: target controller data */ static void rk3x_i2c_start(struct rk3x_i2c *i2c) { @@ -257,8 +258,8 @@ static void rk3x_i2c_start(struct rk3x_i2c *i2c) } /** - * Generate a STOP condition, which triggers a REG_INT_STOP interrupt. - * + * rk3x_i2c_stop - Generate a STOP condition, which triggers a REG_INT_STOP interrupt. + * @i2c: target controller data * @error: Error code to return in rk3x_i2c_xfer */ static void rk3x_i2c_stop(struct rk3x_i2c *i2c, int error) @@ -297,7 +298,8 @@ static void rk3x_i2c_stop(struct rk3x_i2c *i2c, int error) } /** - * Setup a read according to i2c->msg + * rk3x_i2c_prepare_read - Setup a read according to i2c->msg + * @i2c: target controller data */ static void rk3x_i2c_prepare_read(struct rk3x_i2c *i2c) { @@ -328,7 +330,8 @@ static void rk3x_i2c_prepare_read(struct rk3x_i2c *i2c) } /** - * Fill the transmit buffer with data from i2c->msg + * rk3x_i2c_fill_transmit_buf - Fill the transmit buffer with data from i2c->msg + * @i2c: target controller data */ static void rk3x_i2c_fill_transmit_buf(struct rk3x_i2c *i2c) { @@ -531,11 +534,10 @@ out: } /** - * Get timing values of I2C specification - * + * rk3x_i2c_get_spec - Get timing values of I2C specification * @speed: Desired SCL frequency * - * Returns: Matched i2c spec values. + * Return: Matched i2c_spec_values. */ static const struct i2c_spec_values *rk3x_i2c_get_spec(unsigned int speed) { @@ -548,13 +550,12 @@ static const struct i2c_spec_values *rk3x_i2c_get_spec(unsigned int speed) } /** - * Calculate divider values for desired SCL frequency - * + * rk3x_i2c_v0_calc_timings - Calculate divider values for desired SCL frequency * @clk_rate: I2C input clock rate * @t: Known I2C timing information * @t_calc: Caculated rk3x private timings that would be written into regs * - * Returns: 0 on success, -EINVAL if the goal SCL rate is too slow. In that case + * Return: %0 on success, -%EINVAL if the goal SCL rate is too slow. In that case * a best-effort divider value is returned in divs. If the target rate is * too high, we silently use the highest possible rate. */ @@ -709,13 +710,12 @@ static int rk3x_i2c_v0_calc_timings(unsigned long clk_rate, } /** - * Calculate timing values for desired SCL frequency - * + * rk3x_i2c_v1_calc_timings - Calculate timing values for desired SCL frequency * @clk_rate: I2C input clock rate * @t: Known I2C timing information * @t_calc: Caculated rk3x private timings that would be written into regs * - * Returns: 0 on success, -EINVAL if the goal SCL rate is too slow. In that case + * Return: %0 on success, -%EINVAL if the goal SCL rate is too slow. In that case * a best-effort divider value is returned in divs. If the target rate is * too high, we silently use the highest possible rate. * The following formulas are v1's method to calculate timings. @@ -959,14 +959,14 @@ static int rk3x_i2c_clk_notifier_cb(struct notifier_block *nb, unsigned long } /** - * Setup I2C registers for an I2C operation specified by msgs, num. - * - * Must be called with i2c->lock held. - * + * rk3x_i2c_setup - Setup I2C registers for an I2C operation specified by msgs, num. + * @i2c: target controller data * @msgs: I2C msgs to process * @num: Number of msgs * - * returns: Number of I2C msgs processed or negative in case of error + * Must be called with i2c->lock held. + * + * Return: Number of I2C msgs processed or negative in case of error */ static int rk3x_i2c_setup(struct rk3x_i2c *i2c, struct i2c_msg *msgs, int num) { diff --git a/drivers/iio/accel/hid-sensor-accel-3d.c b/drivers/iio/accel/hid-sensor-accel-3d.c index f908476fa095d..a4e0e2b129bcf 100644 --- a/drivers/iio/accel/hid-sensor-accel-3d.c +++ b/drivers/iio/accel/hid-sensor-accel-3d.c @@ -279,6 +279,7 @@ static int accel_3d_capture_sample(struct hid_sensor_hub_device *hsdev, hid_sensor_convert_timestamp( &accel_state->common_attributes, *(int64_t *)raw_data); + ret = 0; break; default: break; diff --git a/drivers/iio/adc/berlin2-adc.c b/drivers/iio/adc/berlin2-adc.c index 72d8fa94ab31c..86fdfea329799 100644 --- a/drivers/iio/adc/berlin2-adc.c +++ b/drivers/iio/adc/berlin2-adc.c @@ -289,8 +289,10 @@ static int berlin2_adc_probe(struct platform_device *pdev) int ret; indio_dev = devm_iio_device_alloc(&pdev->dev, sizeof(*priv)); - if (!indio_dev) + if (!indio_dev) { + of_node_put(parent_np); return -ENOMEM; + } priv = iio_priv(indio_dev); platform_set_drvdata(pdev, indio_dev); diff --git a/drivers/iio/adc/stm32-dfsdm-adc.c b/drivers/iio/adc/stm32-dfsdm-adc.c index c2948defa7853..0c92eb30f0d85 100644 --- a/drivers/iio/adc/stm32-dfsdm-adc.c +++ b/drivers/iio/adc/stm32-dfsdm-adc.c @@ -1544,6 +1544,7 @@ static const struct of_device_id stm32_dfsdm_adc_match[] = { }, {} }; +MODULE_DEVICE_TABLE(of, stm32_dfsdm_adc_match); static int stm32_dfsdm_adc_probe(struct platform_device *pdev) { diff --git a/drivers/iio/adc/twl6030-gpadc.c b/drivers/iio/adc/twl6030-gpadc.c index fb77c3ff5a3e4..0a76081747580 100644 --- a/drivers/iio/adc/twl6030-gpadc.c +++ b/drivers/iio/adc/twl6030-gpadc.c @@ -57,6 +57,18 @@ #define TWL6030_GPADCS BIT(1) #define TWL6030_GPADCR BIT(0) +#define USB_VBUS_CTRL_SET 0x04 +#define USB_ID_CTRL_SET 0x06 + +#define TWL6030_MISC1 0xE4 +#define VBUS_MEAS 0x01 +#define ID_MEAS 0x01 + +#define VAC_MEAS 0x04 +#define VBAT_MEAS 0x02 +#define BB_MEAS 0x01 + + /** * struct twl6030_chnl_calib - channel calibration * @gain: slope coefficient for ideal curve @@ -927,6 +939,26 @@ static int twl6030_gpadc_probe(struct platform_device *pdev) return ret; } + ret = twl_i2c_write_u8(TWL_MODULE_USB, VBUS_MEAS, USB_VBUS_CTRL_SET); + if (ret < 0) { + dev_err(dev, "failed to wire up inputs\n"); + return ret; + } + + ret = twl_i2c_write_u8(TWL_MODULE_USB, ID_MEAS, USB_ID_CTRL_SET); + if (ret < 0) { + dev_err(dev, "failed to wire up inputs\n"); + return ret; + } + + ret = twl_i2c_write_u8(TWL6030_MODULE_ID0, + VBAT_MEAS | BB_MEAS | VAC_MEAS, + TWL6030_MISC1); + if (ret < 0) { + dev_err(dev, "failed to wire up inputs\n"); + return ret; + } + indio_dev->name = DRIVER_NAME; indio_dev->dev.parent = dev; indio_dev->info = &twl6030_gpadc_iio_info; diff --git a/drivers/infiniband/hw/hfi1/file_ops.c b/drivers/infiniband/hw/hfi1/file_ops.c index efd977f70f9ea..607e2636a6d16 100644 --- a/drivers/infiniband/hw/hfi1/file_ops.c +++ b/drivers/infiniband/hw/hfi1/file_ops.c @@ -1363,12 +1363,15 @@ static int user_exp_rcv_setup(struct hfi1_filedata *fd, unsigned long arg, addr = arg + offsetof(struct hfi1_tid_info, tidcnt); if (copy_to_user((void __user *)addr, &tinfo.tidcnt, sizeof(tinfo.tidcnt))) - return -EFAULT; + ret = -EFAULT; addr = arg + offsetof(struct hfi1_tid_info, length); - if (copy_to_user((void __user *)addr, &tinfo.length, + if (!ret && copy_to_user((void __user *)addr, &tinfo.length, sizeof(tinfo.length))) ret = -EFAULT; + + if (ret) + hfi1_user_exp_rcv_invalid(fd, &tinfo); } return ret; diff --git a/drivers/infiniband/hw/usnic/usnic_uiom.c b/drivers/infiniband/hw/usnic/usnic_uiom.c index 62e6ffa9ad78e..1d060ae47933e 100644 --- a/drivers/infiniband/hw/usnic/usnic_uiom.c +++ b/drivers/infiniband/hw/usnic/usnic_uiom.c @@ -281,8 +281,8 @@ iter_chunk: size = pa_end - pa_start + PAGE_SIZE; usnic_dbg("va 0x%lx pa %pa size 0x%zx flags 0x%x", va_start, &pa_start, size, flags); - err = iommu_map(pd->domain, va_start, pa_start, - size, flags); + err = iommu_map_atomic(pd->domain, va_start, + pa_start, size, flags); if (err) { usnic_err("Failed to map va 0x%lx pa %pa size 0x%zx with err %d\n", va_start, &pa_start, size, err); @@ -298,8 +298,8 @@ iter_chunk: size = pa - pa_start + PAGE_SIZE; usnic_dbg("va 0x%lx pa %pa size 0x%zx flags 0x%x\n", va_start, &pa_start, size, flags); - err = iommu_map(pd->domain, va_start, pa_start, - size, flags); + err = iommu_map_atomic(pd->domain, va_start, + pa_start, size, flags); if (err) { usnic_err("Failed to map va 0x%lx pa %pa size 0x%zx with err %d\n", va_start, &pa_start, size, err); diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c index 69ecf37053a81..3c3cc6af0a1ef 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_main.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c @@ -2171,6 +2171,14 @@ int ipoib_intf_init(struct ib_device *hca, u8 port, const char *name, rn->attach_mcast = ipoib_mcast_attach; rn->detach_mcast = ipoib_mcast_detach; rn->hca = hca; + + rc = netif_set_real_num_tx_queues(dev, 1); + if (rc) + goto out; + + rc = netif_set_real_num_rx_queues(dev, 1); + if (rc) + goto out; } priv->rn_ops = dev->netdev_ops; diff --git a/drivers/input/serio/i8042-x86ia64io.h b/drivers/input/serio/i8042-x86ia64io.h index 0282c4c55e9da..6b2e88da30766 100644 --- a/drivers/input/serio/i8042-x86ia64io.h +++ b/drivers/input/serio/i8042-x86ia64io.h @@ -67,25 +67,84 @@ static inline void i8042_write_command(int val) #include -static const struct dmi_system_id __initconst i8042_dmi_noloop_table[] = { +#define SERIO_QUIRK_NOKBD BIT(0) +#define SERIO_QUIRK_NOAUX BIT(1) +#define SERIO_QUIRK_NOMUX BIT(2) +#define SERIO_QUIRK_FORCEMUX BIT(3) +#define SERIO_QUIRK_UNLOCK BIT(4) +#define SERIO_QUIRK_PROBE_DEFER BIT(5) +#define SERIO_QUIRK_RESET_ALWAYS BIT(6) +#define SERIO_QUIRK_RESET_NEVER BIT(7) +#define SERIO_QUIRK_DIECT BIT(8) +#define SERIO_QUIRK_DUMBKBD BIT(9) +#define SERIO_QUIRK_NOLOOP BIT(10) +#define SERIO_QUIRK_NOTIMEOUT BIT(11) +#define SERIO_QUIRK_KBDRESET BIT(12) +#define SERIO_QUIRK_DRITEK BIT(13) +#define SERIO_QUIRK_NOPNP BIT(14) + +/* Quirk table for different mainboards. Options similar or identical to i8042 + * module parameters. + * ORDERING IS IMPORTANT! The first match will be apllied and the rest ignored. + * This allows entries to overwrite vendor wide quirks on a per device basis. + * Where this is irrelevant, entries are sorted case sensitive by DMI_SYS_VENDOR + * and/or DMI_BOARD_VENDOR to make it easier to avoid dublicate entries. + */ +static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = { { - /* - * Arima-Rioworks HDAMB - - * AUX LOOP command does not raise AUX IRQ - */ .matches = { - DMI_MATCH(DMI_BOARD_VENDOR, "RIOWORKS"), - DMI_MATCH(DMI_BOARD_NAME, "HDAMB"), - DMI_MATCH(DMI_BOARD_VERSION, "Rev E"), + DMI_MATCH(DMI_SYS_VENDOR, "ALIENWARE"), + DMI_MATCH(DMI_PRODUCT_NAME, "Sentia"), }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) }, { - /* ASUS G1S */ .matches = { - DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK Computer Inc."), - DMI_MATCH(DMI_BOARD_NAME, "G1S"), - DMI_MATCH(DMI_BOARD_VERSION, "1.0"), + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_PRODUCT_NAME, "X750LN"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOLOOP) + }, + { + /* Asus X450LCP */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_PRODUCT_NAME, "X450LCP"), }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_NEVER) + }, + { + /* ASUS ZenBook UX425UA */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_PRODUCT_NAME, "ZenBook UX425UA"), + }, + .driver_data = (void *)(SERIO_QUIRK_PROBE_DEFER | SERIO_QUIRK_RESET_NEVER) + }, + { + /* ASUS ZenBook UM325UA */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_PRODUCT_NAME, "ZenBook UX325UA_UM325UA"), + }, + .driver_data = (void *)(SERIO_QUIRK_PROBE_DEFER | SERIO_QUIRK_RESET_NEVER) + }, + /* + * On some Asus laptops, just running self tests cause problems. + */ + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_CHASSIS_TYPE, "10"), /* Notebook */ + }, + .driver_data = (void *)(SERIO_QUIRK_RESET_NEVER) + }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_CHASSIS_TYPE, "31"), /* Convertible Notebook */ + }, + .driver_data = (void *)(SERIO_QUIRK_RESET_NEVER) }, { /* ASUS P65UP5 - AUX LOOP command does not raise AUX IRQ */ @@ -94,585 +153,681 @@ static const struct dmi_system_id __initconst i8042_dmi_noloop_table[] = { DMI_MATCH(DMI_BOARD_NAME, "P/I-P65UP5"), DMI_MATCH(DMI_BOARD_VERSION, "REV 2.X"), }, + .driver_data = (void *)(SERIO_QUIRK_NOLOOP) }, { + /* ASUS G1S */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), - DMI_MATCH(DMI_PRODUCT_NAME, "X750LN"), + DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK Computer Inc."), + DMI_MATCH(DMI_BOARD_NAME, "G1S"), + DMI_MATCH(DMI_BOARD_VERSION, "1.0"), }, + .driver_data = (void *)(SERIO_QUIRK_NOLOOP) }, { .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Compaq"), - DMI_MATCH(DMI_PRODUCT_NAME , "ProLiant"), - DMI_MATCH(DMI_PRODUCT_VERSION, "8500"), + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 1360"), }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) }, { + /* Acer Aspire 5710 */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Compaq"), - DMI_MATCH(DMI_PRODUCT_NAME , "ProLiant"), - DMI_MATCH(DMI_PRODUCT_VERSION, "DL760"), + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 5710"), }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) }, { - /* Dell Embedded Box PC 3000 */ + /* Acer Aspire 7738 */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), - DMI_MATCH(DMI_PRODUCT_NAME, "Embedded Box PC 3000"), + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 7738"), }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) }, { - /* OQO Model 01 */ + /* Acer Aspire 5536 */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "OQO"), - DMI_MATCH(DMI_PRODUCT_NAME, "ZEPTO"), - DMI_MATCH(DMI_PRODUCT_VERSION, "00"), + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 5536"), + DMI_MATCH(DMI_PRODUCT_VERSION, "0100"), }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) }, { - /* ULI EV4873 - AUX LOOP does not work properly */ + /* + * Acer Aspire 5738z + * Touchpad stops working in mux mode when dis- + re-enabled + * with the touchpad enable/disable toggle hotkey + */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "ULI"), - DMI_MATCH(DMI_PRODUCT_NAME, "EV4873"), - DMI_MATCH(DMI_PRODUCT_VERSION, "5a"), + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 5738"), }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) }, { - /* Microsoft Virtual Machine */ + /* Acer Aspire One 150 */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Microsoft Corporation"), - DMI_MATCH(DMI_PRODUCT_NAME, "Virtual Machine"), - DMI_MATCH(DMI_PRODUCT_VERSION, "VS2005R2"), + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "AOA150"), }, + .driver_data = (void *)(SERIO_QUIRK_RESET_ALWAYS) }, { - /* Medion MAM 2070 */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Notebook"), - DMI_MATCH(DMI_PRODUCT_NAME, "MAM 2070"), - DMI_MATCH(DMI_PRODUCT_VERSION, "5a"), + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "Aspire A114-31"), }, + .driver_data = (void *)(SERIO_QUIRK_RESET_ALWAYS) }, { - /* Medion Akoya E7225 */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Medion"), - DMI_MATCH(DMI_PRODUCT_NAME, "Akoya E7225"), - DMI_MATCH(DMI_PRODUCT_VERSION, "1.0"), + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "Aspire A314-31"), }, + .driver_data = (void *)(SERIO_QUIRK_RESET_ALWAYS) }, { - /* Blue FB5601 */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "blue"), - DMI_MATCH(DMI_PRODUCT_NAME, "FB5601"), - DMI_MATCH(DMI_PRODUCT_VERSION, "M606"), + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "Aspire A315-31"), }, + .driver_data = (void *)(SERIO_QUIRK_RESET_ALWAYS) }, { - /* Gigabyte M912 */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "GIGABYTE"), - DMI_MATCH(DMI_PRODUCT_NAME, "M912"), - DMI_MATCH(DMI_PRODUCT_VERSION, "01"), + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "Aspire ES1-132"), }, + .driver_data = (void *)(SERIO_QUIRK_RESET_ALWAYS) }, { - /* Gigabyte M1022M netbook */ .matches = { - DMI_MATCH(DMI_BOARD_VENDOR, "Gigabyte Technology Co.,Ltd."), - DMI_MATCH(DMI_BOARD_NAME, "M1022E"), - DMI_MATCH(DMI_BOARD_VERSION, "1.02"), + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "Aspire ES1-332"), }, + .driver_data = (void *)(SERIO_QUIRK_RESET_ALWAYS) }, { - /* Gigabyte Spring Peak - defines wrong chassis type */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "GIGABYTE"), - DMI_MATCH(DMI_PRODUCT_NAME, "Spring Peak"), + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "Aspire ES1-432"), }, + .driver_data = (void *)(SERIO_QUIRK_RESET_ALWAYS) }, { - /* Gigabyte T1005 - defines wrong chassis type ("Other") */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "GIGABYTE"), - DMI_MATCH(DMI_PRODUCT_NAME, "T1005"), + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "TravelMate Spin B118-RN"), }, + .driver_data = (void *)(SERIO_QUIRK_RESET_ALWAYS) }, + /* + * Some Wistron based laptops need us to explicitly enable the 'Dritek + * keyboard extension' to make their extra keys start generating scancodes. + * Originally, this was just confined to older laptops, but a few Acer laptops + * have turned up in 2007 that also need this again. + */ { - /* Gigabyte T1005M/P - defines wrong chassis type ("Other") */ + /* Acer Aspire 5100 */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "GIGABYTE"), - DMI_MATCH(DMI_PRODUCT_NAME, "T1005M/P"), + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 5100"), }, + .driver_data = (void *)(SERIO_QUIRK_DRITEK) }, { + /* Acer Aspire 5610 */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), - DMI_MATCH(DMI_PRODUCT_NAME, "HP Pavilion dv9700"), - DMI_MATCH(DMI_PRODUCT_VERSION, "Rev 1"), + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 5610"), }, + .driver_data = (void *)(SERIO_QUIRK_DRITEK) }, { + /* Acer Aspire 5630 */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "PEGATRON CORPORATION"), - DMI_MATCH(DMI_PRODUCT_NAME, "C15B"), + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 5630"), }, + .driver_data = (void *)(SERIO_QUIRK_DRITEK) }, { + /* Acer Aspire 5650 */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "ByteSpeed LLC"), - DMI_MATCH(DMI_PRODUCT_NAME, "ByteSpeed Laptop C15B"), + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 5650"), }, + .driver_data = (void *)(SERIO_QUIRK_DRITEK) }, - { } -}; - -/* - * Some Fujitsu notebooks are having trouble with touchpads if - * active multiplexing mode is activated. Luckily they don't have - * external PS/2 ports so we can safely disable it. - * ... apparently some Toshibas don't like MUX mode either and - * die horrible death on reboot. - */ -static const struct dmi_system_id __initconst i8042_dmi_nomux_table[] = { { - /* Fujitsu Lifebook P7010/P7010D */ + /* Acer Aspire 5680 */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), - DMI_MATCH(DMI_PRODUCT_NAME, "P7010"), + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 5680"), }, + .driver_data = (void *)(SERIO_QUIRK_DRITEK) }, { - /* Fujitsu Lifebook P7010 */ + /* Acer Aspire 5720 */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU SIEMENS"), - DMI_MATCH(DMI_PRODUCT_NAME, "0000000000"), + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 5720"), }, + .driver_data = (void *)(SERIO_QUIRK_DRITEK) }, { - /* Fujitsu Lifebook P5020D */ + /* Acer Aspire 9110 */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), - DMI_MATCH(DMI_PRODUCT_NAME, "LifeBook P Series"), + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 9110"), }, + .driver_data = (void *)(SERIO_QUIRK_DRITEK) }, { - /* Fujitsu Lifebook S2000 */ + /* Acer TravelMate 660 */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), - DMI_MATCH(DMI_PRODUCT_NAME, "LifeBook S Series"), + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "TravelMate 660"), }, + .driver_data = (void *)(SERIO_QUIRK_DRITEK) }, { - /* Fujitsu Lifebook S6230 */ + /* Acer TravelMate 2490 */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), - DMI_MATCH(DMI_PRODUCT_NAME, "LifeBook S6230"), + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "TravelMate 2490"), }, + .driver_data = (void *)(SERIO_QUIRK_DRITEK) }, { - /* Fujitsu Lifebook T725 laptop */ + /* Acer TravelMate 4280 */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), - DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK T725"), + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "TravelMate 4280"), }, + .driver_data = (void *)(SERIO_QUIRK_DRITEK) }, { - /* Fujitsu Lifebook U745 */ + /* Amoi M636/A737 */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), - DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK U745"), + DMI_MATCH(DMI_SYS_VENDOR, "Amoi Electronics CO.,LTD."), + DMI_MATCH(DMI_PRODUCT_NAME, "M636/A737 platform"), }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) }, { - /* Fujitsu T70H */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), - DMI_MATCH(DMI_PRODUCT_NAME, "FMVLT70H"), + DMI_MATCH(DMI_SYS_VENDOR, "ByteSpeed LLC"), + DMI_MATCH(DMI_PRODUCT_NAME, "ByteSpeed Laptop C15B"), }, + .driver_data = (void *)(SERIO_QUIRK_NOLOOP) }, { - /* Fujitsu-Siemens Lifebook T3010 */ + /* Compal HEL80I */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU SIEMENS"), - DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK T3010"), + DMI_MATCH(DMI_SYS_VENDOR, "COMPAL"), + DMI_MATCH(DMI_PRODUCT_NAME, "HEL80I"), }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) }, { - /* Fujitsu-Siemens Lifebook E4010 */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU SIEMENS"), - DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK E4010"), + DMI_MATCH(DMI_SYS_VENDOR, "Compaq"), + DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant"), + DMI_MATCH(DMI_PRODUCT_VERSION, "8500"), }, + .driver_data = (void *)(SERIO_QUIRK_NOLOOP) }, { - /* Fujitsu-Siemens Amilo Pro 2010 */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU SIEMENS"), - DMI_MATCH(DMI_PRODUCT_NAME, "AMILO Pro V2010"), + DMI_MATCH(DMI_SYS_VENDOR, "Compaq"), + DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant"), + DMI_MATCH(DMI_PRODUCT_VERSION, "DL760"), }, + .driver_data = (void *)(SERIO_QUIRK_NOLOOP) }, { - /* Fujitsu-Siemens Amilo Pro 2030 */ + /* Advent 4211 */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU SIEMENS"), - DMI_MATCH(DMI_PRODUCT_NAME, "AMILO PRO V2030"), + DMI_MATCH(DMI_SYS_VENDOR, "DIXONSXP"), + DMI_MATCH(DMI_PRODUCT_NAME, "Advent 4211"), }, + .driver_data = (void *)(SERIO_QUIRK_RESET_ALWAYS) }, { - /* - * No data is coming from the touchscreen unless KBC - * is in legacy mode. - */ - /* Panasonic CF-29 */ + /* Dell Embedded Box PC 3000 */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Matsushita"), - DMI_MATCH(DMI_PRODUCT_NAME, "CF-29"), + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Embedded Box PC 3000"), }, + .driver_data = (void *)(SERIO_QUIRK_NOLOOP) }, { - /* - * HP Pavilion DV4017EA - - * errors on MUX ports are reported without raising AUXDATA - * causing "spurious NAK" messages. - */ + /* Dell XPS M1530 */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), - DMI_MATCH(DMI_PRODUCT_NAME, "Pavilion dv4000 (EA032EA#ABF)"), + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "XPS M1530"), }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) }, { - /* - * HP Pavilion ZT1000 - - * like DV4017EA does not raise AUXERR for errors on MUX ports. - */ + /* Dell Vostro 1510 */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), - DMI_MATCH(DMI_PRODUCT_NAME, "HP Pavilion Notebook PC"), - DMI_MATCH(DMI_PRODUCT_VERSION, "HP Pavilion Notebook ZT1000"), + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Vostro1510"), }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) }, { - /* - * HP Pavilion DV4270ca - - * like DV4017EA does not raise AUXERR for errors on MUX ports. - */ + /* Dell Vostro V13 */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), - DMI_MATCH(DMI_PRODUCT_NAME, "Pavilion dv4000 (EH476UA#ABL)"), + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Vostro V13"), }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_NOTIMEOUT) }, { + /* Dell Vostro 1320 */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "TOSHIBA"), - DMI_MATCH(DMI_PRODUCT_NAME, "Satellite P10"), + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Vostro 1320"), }, + .driver_data = (void *)(SERIO_QUIRK_RESET_ALWAYS) }, { + /* Dell Vostro 1520 */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "TOSHIBA"), - DMI_MATCH(DMI_PRODUCT_NAME, "EQUIUM A110"), + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Vostro 1520"), }, + .driver_data = (void *)(SERIO_QUIRK_RESET_ALWAYS) }, { + /* Dell Vostro 1720 */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "TOSHIBA"), - DMI_MATCH(DMI_PRODUCT_NAME, "SATELLITE C850D"), + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Vostro 1720"), + }, + .driver_data = (void *)(SERIO_QUIRK_RESET_ALWAYS) + }, + { + /* Entroware Proteus */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Entroware"), + DMI_MATCH(DMI_PRODUCT_NAME, "Proteus"), + DMI_MATCH(DMI_PRODUCT_VERSION, "EL07R4"), }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS) }, + /* + * Some Fujitsu notebooks are having trouble with touchpads if + * active multiplexing mode is activated. Luckily they don't have + * external PS/2 ports so we can safely disable it. + * ... apparently some Toshibas don't like MUX mode either and + * die horrible death on reboot. + */ { + /* Fujitsu Lifebook P7010/P7010D */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "ALIENWARE"), - DMI_MATCH(DMI_PRODUCT_NAME, "Sentia"), + DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), + DMI_MATCH(DMI_PRODUCT_NAME, "P7010"), }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) }, { - /* Sharp Actius MM20 */ + /* Fujitsu Lifebook P5020D */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "SHARP"), - DMI_MATCH(DMI_PRODUCT_NAME, "PC-MM20 Series"), + DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), + DMI_MATCH(DMI_PRODUCT_NAME, "LifeBook P Series"), }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) }, { - /* Sony Vaio FS-115b */ + /* Fujitsu Lifebook S2000 */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Sony Corporation"), - DMI_MATCH(DMI_PRODUCT_NAME, "VGN-FS115B"), + DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), + DMI_MATCH(DMI_PRODUCT_NAME, "LifeBook S Series"), }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) }, { - /* - * Sony Vaio FZ-240E - - * reset and GET ID commands issued via KBD port are - * sometimes being delivered to AUX3. - */ + /* Fujitsu Lifebook S6230 */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Sony Corporation"), - DMI_MATCH(DMI_PRODUCT_NAME, "VGN-FZ240E"), + DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), + DMI_MATCH(DMI_PRODUCT_NAME, "LifeBook S6230"), }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) }, { - /* - * Most (all?) VAIOs do not have external PS/2 ports nor - * they implement active multiplexing properly, and - * MUX discovery usually messes up keyboard/touchpad. - */ + /* Fujitsu Lifebook T725 laptop */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Sony Corporation"), - DMI_MATCH(DMI_BOARD_NAME, "VAIO"), + DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), + DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK T725"), }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_NOTIMEOUT) }, { - /* Amoi M636/A737 */ + /* Fujitsu Lifebook U745 */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Amoi Electronics CO.,LTD."), - DMI_MATCH(DMI_PRODUCT_NAME, "M636/A737 platform"), + DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), + DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK U745"), }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) }, { - /* Lenovo 3000 n100 */ + /* Fujitsu T70H */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), - DMI_MATCH(DMI_PRODUCT_NAME, "076804U"), + DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), + DMI_MATCH(DMI_PRODUCT_NAME, "FMVLT70H"), }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) }, { - /* Lenovo XiaoXin Air 12 */ + /* Fujitsu A544 laptop */ + /* https://bugzilla.redhat.com/show_bug.cgi?id=1111138 */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), - DMI_MATCH(DMI_PRODUCT_NAME, "80UN"), + DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), + DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK A544"), }, + .driver_data = (void *)(SERIO_QUIRK_NOTIMEOUT) }, { + /* Fujitsu AH544 laptop */ + /* https://bugzilla.kernel.org/show_bug.cgi?id=69731 */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Acer"), - DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 1360"), + DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), + DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK AH544"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOTIMEOUT) + }, + { + /* Fujitsu U574 laptop */ + /* https://bugzilla.kernel.org/show_bug.cgi?id=69731 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), + DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK U574"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOTIMEOUT) + }, + { + /* Fujitsu UH554 laptop */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), + DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK UH544"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOTIMEOUT) + }, + { + /* Fujitsu Lifebook P7010 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU SIEMENS"), + DMI_MATCH(DMI_PRODUCT_NAME, "0000000000"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) + }, + { + /* Fujitsu-Siemens Lifebook T3010 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU SIEMENS"), + DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK T3010"), }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) }, { - /* Acer Aspire 5710 */ + /* Fujitsu-Siemens Lifebook E4010 */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Acer"), - DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 5710"), + DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU SIEMENS"), + DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK E4010"), }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) }, { - /* Acer Aspire 7738 */ + /* Fujitsu-Siemens Amilo Pro 2010 */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Acer"), - DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 7738"), + DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU SIEMENS"), + DMI_MATCH(DMI_PRODUCT_NAME, "AMILO Pro V2010"), }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) }, { - /* Gericom Bellagio */ + /* Fujitsu-Siemens Amilo Pro 2030 */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Gericom"), - DMI_MATCH(DMI_PRODUCT_NAME, "N34AS6"), + DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU SIEMENS"), + DMI_MATCH(DMI_PRODUCT_NAME, "AMILO PRO V2030"), }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) }, { - /* IBM 2656 */ + /* Gigabyte M912 */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "IBM"), - DMI_MATCH(DMI_PRODUCT_NAME, "2656"), + DMI_MATCH(DMI_SYS_VENDOR, "GIGABYTE"), + DMI_MATCH(DMI_PRODUCT_NAME, "M912"), + DMI_MATCH(DMI_PRODUCT_VERSION, "01"), }, + .driver_data = (void *)(SERIO_QUIRK_NOLOOP) }, { - /* Dell XPS M1530 */ + /* Gigabyte Spring Peak - defines wrong chassis type */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), - DMI_MATCH(DMI_PRODUCT_NAME, "XPS M1530"), + DMI_MATCH(DMI_SYS_VENDOR, "GIGABYTE"), + DMI_MATCH(DMI_PRODUCT_NAME, "Spring Peak"), }, + .driver_data = (void *)(SERIO_QUIRK_NOLOOP) }, { - /* Compal HEL80I */ + /* Gigabyte T1005 - defines wrong chassis type ("Other") */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "COMPAL"), - DMI_MATCH(DMI_PRODUCT_NAME, "HEL80I"), + DMI_MATCH(DMI_SYS_VENDOR, "GIGABYTE"), + DMI_MATCH(DMI_PRODUCT_NAME, "T1005"), }, + .driver_data = (void *)(SERIO_QUIRK_NOLOOP) }, { - /* Dell Vostro 1510 */ + /* Gigabyte T1005M/P - defines wrong chassis type ("Other") */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), - DMI_MATCH(DMI_PRODUCT_NAME, "Vostro1510"), + DMI_MATCH(DMI_SYS_VENDOR, "GIGABYTE"), + DMI_MATCH(DMI_PRODUCT_NAME, "T1005M/P"), }, + .driver_data = (void *)(SERIO_QUIRK_NOLOOP) }, + /* + * Some laptops need keyboard reset before probing for the trackpad to get + * it detected, initialised & finally work. + */ { - /* Acer Aspire 5536 */ + /* Gigabyte P35 v2 - Elantech touchpad */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Acer"), - DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 5536"), - DMI_MATCH(DMI_PRODUCT_VERSION, "0100"), + DMI_MATCH(DMI_SYS_VENDOR, "GIGABYTE"), + DMI_MATCH(DMI_PRODUCT_NAME, "P35V2"), }, + .driver_data = (void *)(SERIO_QUIRK_KBDRESET) }, - { - /* Dell Vostro V13 */ + { + /* Aorus branded Gigabyte X3 Plus - Elantech touchpad */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), - DMI_MATCH(DMI_PRODUCT_NAME, "Vostro V13"), + DMI_MATCH(DMI_SYS_VENDOR, "GIGABYTE"), + DMI_MATCH(DMI_PRODUCT_NAME, "X3"), }, + .driver_data = (void *)(SERIO_QUIRK_KBDRESET) }, { - /* Newer HP Pavilion dv4 models */ + /* Gigabyte P34 - Elantech touchpad */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), - DMI_MATCH(DMI_PRODUCT_NAME, "HP Pavilion dv4 Notebook PC"), + DMI_MATCH(DMI_SYS_VENDOR, "GIGABYTE"), + DMI_MATCH(DMI_PRODUCT_NAME, "P34"), }, + .driver_data = (void *)(SERIO_QUIRK_KBDRESET) }, { - /* Asus X450LCP */ + /* Gigabyte P57 - Elantech touchpad */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), - DMI_MATCH(DMI_PRODUCT_NAME, "X450LCP"), + DMI_MATCH(DMI_SYS_VENDOR, "GIGABYTE"), + DMI_MATCH(DMI_PRODUCT_NAME, "P57"), }, + .driver_data = (void *)(SERIO_QUIRK_KBDRESET) }, { - /* Avatar AVIU-145A6 */ + /* Gericom Bellagio */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Intel"), - DMI_MATCH(DMI_PRODUCT_NAME, "IC4I"), + DMI_MATCH(DMI_SYS_VENDOR, "Gericom"), + DMI_MATCH(DMI_PRODUCT_NAME, "N34AS6"), }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) }, { - /* TUXEDO BU1406 */ + /* Gigabyte M1022M netbook */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Notebook"), - DMI_MATCH(DMI_PRODUCT_NAME, "N24_25BU"), + DMI_MATCH(DMI_BOARD_VENDOR, "Gigabyte Technology Co.,Ltd."), + DMI_MATCH(DMI_BOARD_NAME, "M1022E"), + DMI_MATCH(DMI_BOARD_VERSION, "1.02"), }, + .driver_data = (void *)(SERIO_QUIRK_NOLOOP) }, { - /* Lenovo LaVie Z */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), - DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo LaVie Z"), + DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), + DMI_MATCH(DMI_PRODUCT_NAME, "HP Pavilion dv9700"), + DMI_MATCH(DMI_PRODUCT_VERSION, "Rev 1"), }, + .driver_data = (void *)(SERIO_QUIRK_NOLOOP) }, { /* - * Acer Aspire 5738z - * Touchpad stops working in mux mode when dis- + re-enabled - * with the touchpad enable/disable toggle hotkey + * HP Pavilion DV4017EA - + * errors on MUX ports are reported without raising AUXDATA + * causing "spurious NAK" messages. */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Acer"), - DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 5738"), + DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), + DMI_MATCH(DMI_PRODUCT_NAME, "Pavilion dv4000 (EA032EA#ABF)"), }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) }, { - /* Entroware Proteus */ + /* + * HP Pavilion ZT1000 - + * like DV4017EA does not raise AUXERR for errors on MUX ports. + */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Entroware"), - DMI_MATCH(DMI_PRODUCT_NAME, "Proteus"), - DMI_MATCH(DMI_PRODUCT_VERSION, "EL07R4"), + DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), + DMI_MATCH(DMI_PRODUCT_NAME, "HP Pavilion Notebook PC"), + DMI_MATCH(DMI_PRODUCT_VERSION, "HP Pavilion Notebook ZT1000"), }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) }, - { } -}; - -static const struct dmi_system_id i8042_dmi_forcemux_table[] __initconst = { { /* - * Sony Vaio VGN-CS series require MUX or the touch sensor - * buttons will disturb touchpad operation + * HP Pavilion DV4270ca - + * like DV4017EA does not raise AUXERR for errors on MUX ports. */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Sony Corporation"), - DMI_MATCH(DMI_PRODUCT_NAME, "VGN-CS"), + DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), + DMI_MATCH(DMI_PRODUCT_NAME, "Pavilion dv4000 (EH476UA#ABL)"), }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) }, - { } -}; - -/* - * On some Asus laptops, just running self tests cause problems. - */ -static const struct dmi_system_id i8042_dmi_noselftest_table[] = { { + /* Newer HP Pavilion dv4 models */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), - DMI_MATCH(DMI_CHASSIS_TYPE, "10"), /* Notebook */ - }, - }, { - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), - DMI_MATCH(DMI_CHASSIS_TYPE, "31"), /* Convertible Notebook */ + DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), + DMI_MATCH(DMI_PRODUCT_NAME, "HP Pavilion dv4 Notebook PC"), }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_NOTIMEOUT) }, - { } -}; -static const struct dmi_system_id __initconst i8042_dmi_reset_table[] = { { - /* MSI Wind U-100 */ + /* IBM 2656 */ .matches = { - DMI_MATCH(DMI_BOARD_NAME, "U-100"), - DMI_MATCH(DMI_BOARD_VENDOR, "MICRO-STAR INTERNATIONAL CO., LTD"), + DMI_MATCH(DMI_SYS_VENDOR, "IBM"), + DMI_MATCH(DMI_PRODUCT_NAME, "2656"), }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) }, { - /* LG Electronics X110 */ + /* Avatar AVIU-145A6 */ .matches = { - DMI_MATCH(DMI_BOARD_NAME, "X110"), - DMI_MATCH(DMI_BOARD_VENDOR, "LG Electronics Inc."), + DMI_MATCH(DMI_SYS_VENDOR, "Intel"), + DMI_MATCH(DMI_PRODUCT_NAME, "IC4I"), }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) }, { - /* Acer Aspire One 150 */ + /* Intel MBO Desktop D845PESV */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Acer"), - DMI_MATCH(DMI_PRODUCT_NAME, "AOA150"), + DMI_MATCH(DMI_BOARD_VENDOR, "Intel Corporation"), + DMI_MATCH(DMI_BOARD_NAME, "D845PESV"), }, + .driver_data = (void *)(SERIO_QUIRK_NOPNP) }, { + /* + * Intel NUC D54250WYK - does not have i8042 controller but + * declares PS/2 devices in DSDT. + */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Acer"), - DMI_MATCH(DMI_PRODUCT_NAME, "Aspire A114-31"), + DMI_MATCH(DMI_BOARD_VENDOR, "Intel Corporation"), + DMI_MATCH(DMI_BOARD_NAME, "D54250WYK"), }, + .driver_data = (void *)(SERIO_QUIRK_NOPNP) }, { + /* Lenovo 3000 n100 */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Acer"), - DMI_MATCH(DMI_PRODUCT_NAME, "Aspire A314-31"), + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "076804U"), }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) }, { + /* Lenovo XiaoXin Air 12 */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Acer"), - DMI_MATCH(DMI_PRODUCT_NAME, "Aspire A315-31"), + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "80UN"), }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) }, { + /* Lenovo LaVie Z */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Acer"), - DMI_MATCH(DMI_PRODUCT_NAME, "Aspire ES1-132"), + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo LaVie Z"), }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) }, { + /* Lenovo Ideapad U455 */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Acer"), - DMI_MATCH(DMI_PRODUCT_NAME, "Aspire ES1-332"), + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "20046"), }, + .driver_data = (void *)(SERIO_QUIRK_RESET_ALWAYS) }, { + /* Lenovo ThinkPad L460 */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Acer"), - DMI_MATCH(DMI_PRODUCT_NAME, "Aspire ES1-432"), + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad L460"), }, + .driver_data = (void *)(SERIO_QUIRK_RESET_ALWAYS) }, { + /* Lenovo ThinkPad Twist S230u */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Acer"), - DMI_MATCH(DMI_PRODUCT_NAME, "TravelMate Spin B118-RN"), + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "33474HU"), }, + .driver_data = (void *)(SERIO_QUIRK_RESET_ALWAYS) }, { - /* Advent 4211 */ + /* LG Electronics X110 */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "DIXONSXP"), - DMI_MATCH(DMI_PRODUCT_NAME, "Advent 4211"), + DMI_MATCH(DMI_BOARD_VENDOR, "LG Electronics Inc."), + DMI_MATCH(DMI_BOARD_NAME, "X110"), }, + .driver_data = (void *)(SERIO_QUIRK_RESET_ALWAYS) }, { /* Medion Akoya Mini E1210 */ @@ -680,6 +835,7 @@ static const struct dmi_system_id __initconst i8042_dmi_reset_table[] = { DMI_MATCH(DMI_SYS_VENDOR, "MEDION"), DMI_MATCH(DMI_PRODUCT_NAME, "E1210"), }, + .driver_data = (void *)(SERIO_QUIRK_RESET_ALWAYS) }, { /* Medion Akoya E1222 */ @@ -687,48 +843,62 @@ static const struct dmi_system_id __initconst i8042_dmi_reset_table[] = { DMI_MATCH(DMI_SYS_VENDOR, "MEDION"), DMI_MATCH(DMI_PRODUCT_NAME, "E122X"), }, + .driver_data = (void *)(SERIO_QUIRK_RESET_ALWAYS) }, { - /* Mivvy M310 */ + /* MSI Wind U-100 */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "VIOOO"), - DMI_MATCH(DMI_PRODUCT_NAME, "N10"), + DMI_MATCH(DMI_BOARD_VENDOR, "MICRO-STAR INTERNATIONAL CO., LTD"), + DMI_MATCH(DMI_BOARD_NAME, "U-100"), }, + .driver_data = (void *)(SERIO_QUIRK_RESET_ALWAYS | SERIO_QUIRK_NOPNP) }, { - /* Dell Vostro 1320 */ + /* + * No data is coming from the touchscreen unless KBC + * is in legacy mode. + */ + /* Panasonic CF-29 */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), - DMI_MATCH(DMI_PRODUCT_NAME, "Vostro 1320"), + DMI_MATCH(DMI_SYS_VENDOR, "Matsushita"), + DMI_MATCH(DMI_PRODUCT_NAME, "CF-29"), }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) }, { - /* Dell Vostro 1520 */ + /* Medion Akoya E7225 */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), - DMI_MATCH(DMI_PRODUCT_NAME, "Vostro 1520"), + DMI_MATCH(DMI_SYS_VENDOR, "Medion"), + DMI_MATCH(DMI_PRODUCT_NAME, "Akoya E7225"), + DMI_MATCH(DMI_PRODUCT_VERSION, "1.0"), }, + .driver_data = (void *)(SERIO_QUIRK_NOLOOP) }, { - /* Dell Vostro 1720 */ + /* Microsoft Virtual Machine */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), - DMI_MATCH(DMI_PRODUCT_NAME, "Vostro 1720"), + DMI_MATCH(DMI_SYS_VENDOR, "Microsoft Corporation"), + DMI_MATCH(DMI_PRODUCT_NAME, "Virtual Machine"), + DMI_MATCH(DMI_PRODUCT_VERSION, "VS2005R2"), }, + .driver_data = (void *)(SERIO_QUIRK_NOLOOP) }, { - /* Lenovo Ideapad U455 */ + /* Medion MAM 2070 */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), - DMI_MATCH(DMI_PRODUCT_NAME, "20046"), + DMI_MATCH(DMI_SYS_VENDOR, "Notebook"), + DMI_MATCH(DMI_PRODUCT_NAME, "MAM 2070"), + DMI_MATCH(DMI_PRODUCT_VERSION, "5a"), }, + .driver_data = (void *)(SERIO_QUIRK_NOLOOP) }, { - /* Lenovo ThinkPad L460 */ + /* TUXEDO BU1406 */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), - DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad L460"), + DMI_MATCH(DMI_SYS_VENDOR, "Notebook"), + DMI_MATCH(DMI_PRODUCT_NAME, "N24_25BU"), }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) }, { /* Clevo P650RS, 650RP6, Sager NP8152-S, and others */ @@ -736,282 +906,318 @@ static const struct dmi_system_id __initconst i8042_dmi_reset_table[] = { DMI_MATCH(DMI_SYS_VENDOR, "Notebook"), DMI_MATCH(DMI_PRODUCT_NAME, "P65xRP"), }, + .driver_data = (void *)(SERIO_QUIRK_RESET_ALWAYS) + }, + { + /* OQO Model 01 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "OQO"), + DMI_MATCH(DMI_PRODUCT_NAME, "ZEPTO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "00"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOLOOP) }, { - /* Lenovo ThinkPad Twist S230u */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), - DMI_MATCH(DMI_PRODUCT_NAME, "33474HU"), + DMI_MATCH(DMI_SYS_VENDOR, "PEGATRON CORPORATION"), + DMI_MATCH(DMI_PRODUCT_NAME, "C15B"), }, + .driver_data = (void *)(SERIO_QUIRK_NOLOOP) }, { - /* Entroware Proteus */ + /* Acer Aspire 5 A515 */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Entroware"), - DMI_MATCH(DMI_PRODUCT_NAME, "Proteus"), - DMI_MATCH(DMI_PRODUCT_VERSION, "EL07R4"), + DMI_MATCH(DMI_BOARD_VENDOR, "PK"), + DMI_MATCH(DMI_BOARD_NAME, "Grumpy_PK"), }, + .driver_data = (void *)(SERIO_QUIRK_NOPNP) }, - { } -}; - -#ifdef CONFIG_PNP -static const struct dmi_system_id __initconst i8042_dmi_nopnp_table[] = { { - /* Intel MBO Desktop D845PESV */ + /* ULI EV4873 - AUX LOOP does not work properly */ .matches = { - DMI_MATCH(DMI_BOARD_NAME, "D845PESV"), - DMI_MATCH(DMI_BOARD_VENDOR, "Intel Corporation"), + DMI_MATCH(DMI_SYS_VENDOR, "ULI"), + DMI_MATCH(DMI_PRODUCT_NAME, "EV4873"), + DMI_MATCH(DMI_PRODUCT_VERSION, "5a"), }, + .driver_data = (void *)(SERIO_QUIRK_NOLOOP) }, { /* - * Intel NUC D54250WYK - does not have i8042 controller but - * declares PS/2 devices in DSDT. + * Arima-Rioworks HDAMB - + * AUX LOOP command does not raise AUX IRQ */ .matches = { - DMI_MATCH(DMI_BOARD_NAME, "D54250WYK"), - DMI_MATCH(DMI_BOARD_VENDOR, "Intel Corporation"), + DMI_MATCH(DMI_BOARD_VENDOR, "RIOWORKS"), + DMI_MATCH(DMI_BOARD_NAME, "HDAMB"), + DMI_MATCH(DMI_BOARD_VERSION, "Rev E"), }, + .driver_data = (void *)(SERIO_QUIRK_NOLOOP) }, { - /* MSI Wind U-100 */ + /* Sharp Actius MM20 */ .matches = { - DMI_MATCH(DMI_BOARD_NAME, "U-100"), - DMI_MATCH(DMI_BOARD_VENDOR, "MICRO-STAR INTERNATIONAL CO., LTD"), + DMI_MATCH(DMI_SYS_VENDOR, "SHARP"), + DMI_MATCH(DMI_PRODUCT_NAME, "PC-MM20 Series"), }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) }, { - /* Acer Aspire 5 A515 */ + /* + * Sony Vaio FZ-240E - + * reset and GET ID commands issued via KBD port are + * sometimes being delivered to AUX3. + */ .matches = { - DMI_MATCH(DMI_BOARD_NAME, "Grumpy_PK"), - DMI_MATCH(DMI_BOARD_VENDOR, "PK"), + DMI_MATCH(DMI_SYS_VENDOR, "Sony Corporation"), + DMI_MATCH(DMI_PRODUCT_NAME, "VGN-FZ240E"), }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) }, - { } -}; - -static const struct dmi_system_id __initconst i8042_dmi_laptop_table[] = { { + /* + * Most (all?) VAIOs do not have external PS/2 ports nor + * they implement active multiplexing properly, and + * MUX discovery usually messes up keyboard/touchpad. + */ .matches = { - DMI_MATCH(DMI_CHASSIS_TYPE, "8"), /* Portable */ + DMI_MATCH(DMI_SYS_VENDOR, "Sony Corporation"), + DMI_MATCH(DMI_BOARD_NAME, "VAIO"), }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) }, { + /* Sony Vaio FS-115b */ .matches = { - DMI_MATCH(DMI_CHASSIS_TYPE, "9"), /* Laptop */ + DMI_MATCH(DMI_SYS_VENDOR, "Sony Corporation"), + DMI_MATCH(DMI_PRODUCT_NAME, "VGN-FS115B"), }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) }, { + /* + * Sony Vaio VGN-CS series require MUX or the touch sensor + * buttons will disturb touchpad operation + */ .matches = { - DMI_MATCH(DMI_CHASSIS_TYPE, "10"), /* Notebook */ + DMI_MATCH(DMI_SYS_VENDOR, "Sony Corporation"), + DMI_MATCH(DMI_PRODUCT_NAME, "VGN-CS"), }, + .driver_data = (void *)(SERIO_QUIRK_FORCEMUX) }, { .matches = { - DMI_MATCH(DMI_CHASSIS_TYPE, "14"), /* Sub-Notebook */ + DMI_MATCH(DMI_SYS_VENDOR, "TOSHIBA"), + DMI_MATCH(DMI_PRODUCT_NAME, "Satellite P10"), }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) }, - { } -}; -#endif - -static const struct dmi_system_id __initconst i8042_dmi_notimeout_table[] = { { - /* Dell Vostro V13 */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), - DMI_MATCH(DMI_PRODUCT_NAME, "Vostro V13"), + DMI_MATCH(DMI_SYS_VENDOR, "TOSHIBA"), + DMI_MATCH(DMI_PRODUCT_NAME, "EQUIUM A110"), }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) }, { - /* Newer HP Pavilion dv4 models */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), - DMI_MATCH(DMI_PRODUCT_NAME, "HP Pavilion dv4 Notebook PC"), + DMI_MATCH(DMI_SYS_VENDOR, "TOSHIBA"), + DMI_MATCH(DMI_PRODUCT_NAME, "SATELLITE C850D"), }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) }, + /* + * A lot of modern Clevo barebones have touchpad and/or keyboard issues + * after suspend fixable with nomux + reset + noloop + nopnp. Luckily, + * none of them have an external PS/2 port so this can safely be set for + * all of them. These two are based on a Clevo design, but have the + * board_name changed. + */ { - /* Fujitsu A544 laptop */ - /* https://bugzilla.redhat.com/show_bug.cgi?id=1111138 */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), - DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK A544"), + DMI_MATCH(DMI_BOARD_VENDOR, "TUXEDO"), + DMI_MATCH(DMI_BOARD_NAME, "AURA1501"), }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS | + SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP) }, { - /* Fujitsu AH544 laptop */ - /* https://bugzilla.kernel.org/show_bug.cgi?id=69731 */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), - DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK AH544"), + DMI_MATCH(DMI_BOARD_VENDOR, "TUXEDO"), + DMI_MATCH(DMI_BOARD_NAME, "EDUBOOK1502"), }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS | + SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP) }, { - /* Fujitsu Lifebook T725 laptop */ + /* Mivvy M310 */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), - DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK T725"), + DMI_MATCH(DMI_SYS_VENDOR, "VIOOO"), + DMI_MATCH(DMI_PRODUCT_NAME, "N10"), }, + .driver_data = (void *)(SERIO_QUIRK_RESET_ALWAYS) }, + /* + * Some laptops need keyboard reset before probing for the trackpad to get + * it detected, initialised & finally work. + */ { - /* Fujitsu U574 laptop */ - /* https://bugzilla.kernel.org/show_bug.cgi?id=69731 */ + /* Schenker XMG C504 - Elantech touchpad */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), - DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK U574"), + DMI_MATCH(DMI_SYS_VENDOR, "XMG"), + DMI_MATCH(DMI_PRODUCT_NAME, "C504"), }, + .driver_data = (void *)(SERIO_QUIRK_KBDRESET) }, { - /* Fujitsu UH554 laptop */ + /* Blue FB5601 */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), - DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK UH544"), + DMI_MATCH(DMI_SYS_VENDOR, "blue"), + DMI_MATCH(DMI_PRODUCT_NAME, "FB5601"), + DMI_MATCH(DMI_PRODUCT_VERSION, "M606"), }, + .driver_data = (void *)(SERIO_QUIRK_NOLOOP) }, - { } -}; - -/* - * Some Wistron based laptops need us to explicitly enable the 'Dritek - * keyboard extension' to make their extra keys start generating scancodes. - * Originally, this was just confined to older laptops, but a few Acer laptops - * have turned up in 2007 that also need this again. - */ -static const struct dmi_system_id __initconst i8042_dmi_dritek_table[] = { + /* + * A lot of modern Clevo barebones have touchpad and/or keyboard issues + * after suspend fixable with nomux + reset + noloop + nopnp. Luckily, + * none of them have an external PS/2 port so this can safely be set for + * all of them. + * Clevo barebones come with board_vendor and/or system_vendor set to + * either the very generic string "Notebook" and/or a different value + * for each individual reseller. The only somewhat universal way to + * identify them is by board_name. + */ { - /* Acer Aspire 5100 */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Acer"), - DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 5100"), + DMI_MATCH(DMI_BOARD_NAME, "LAPQC71A"), }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS | + SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP) }, { - /* Acer Aspire 5610 */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Acer"), - DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 5610"), + DMI_MATCH(DMI_BOARD_NAME, "LAPQC71B"), }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS | + SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP) }, { - /* Acer Aspire 5630 */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Acer"), - DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 5630"), + DMI_MATCH(DMI_BOARD_NAME, "N140CU"), }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS | + SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP) }, { - /* Acer Aspire 5650 */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Acer"), - DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 5650"), + DMI_MATCH(DMI_BOARD_NAME, "N141CU"), }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS | + SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP) }, { - /* Acer Aspire 5680 */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Acer"), - DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 5680"), + DMI_MATCH(DMI_BOARD_NAME, "NH5xAx"), }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS | + SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP) }, { - /* Acer Aspire 5720 */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Acer"), - DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 5720"), + DMI_MATCH(DMI_BOARD_NAME, "NL5xRU"), }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS | + SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP) }, + /* + * At least one modern Clevo barebone has the touchpad connected both + * via PS/2 and i2c interface. This causes a race condition between the + * psmouse and i2c-hid driver. Since the full capability of the touchpad + * is available via the i2c interface and the device has no external + * PS/2 port, it is safe to just ignore all ps2 mouses here to avoid + * this issue. The known affected device is the + * TUXEDO InfinityBook S17 Gen6 / Clevo NS70MU which comes with one of + * the two different dmi strings below. NS50MU is not a typo! + */ { - /* Acer Aspire 9110 */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Acer"), - DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 9110"), + DMI_MATCH(DMI_BOARD_NAME, "NS50MU"), }, + .driver_data = (void *)(SERIO_QUIRK_NOAUX | SERIO_QUIRK_NOMUX | + SERIO_QUIRK_RESET_ALWAYS | SERIO_QUIRK_NOLOOP | + SERIO_QUIRK_NOPNP) }, { - /* Acer TravelMate 660 */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Acer"), - DMI_MATCH(DMI_PRODUCT_NAME, "TravelMate 660"), + DMI_MATCH(DMI_BOARD_NAME, "NS50_70MU"), }, + .driver_data = (void *)(SERIO_QUIRK_NOAUX | SERIO_QUIRK_NOMUX | + SERIO_QUIRK_RESET_ALWAYS | SERIO_QUIRK_NOLOOP | + SERIO_QUIRK_NOPNP) }, { - /* Acer TravelMate 2490 */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Acer"), - DMI_MATCH(DMI_PRODUCT_NAME, "TravelMate 2490"), + DMI_MATCH(DMI_BOARD_NAME, "NJ50_70CU"), }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS | + SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP) }, { - /* Acer TravelMate 4280 */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Acer"), - DMI_MATCH(DMI_PRODUCT_NAME, "TravelMate 4280"), + DMI_MATCH(DMI_BOARD_NAME, "PB50_70DFx,DDx"), }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS | + SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP) }, - { } -}; - -/* - * Some laptops need keyboard reset before probing for the trackpad to get - * it detected, initialised & finally work. - */ -static const struct dmi_system_id __initconst i8042_dmi_kbdreset_table[] = { { - /* Gigabyte P35 v2 - Elantech touchpad */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "GIGABYTE"), - DMI_MATCH(DMI_PRODUCT_NAME, "P35V2"), + DMI_MATCH(DMI_BOARD_NAME, "PCX0DX"), }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS | + SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP) }, - { - /* Aorus branded Gigabyte X3 Plus - Elantech touchpad */ + { .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "GIGABYTE"), - DMI_MATCH(DMI_PRODUCT_NAME, "X3"), + DMI_MATCH(DMI_BOARD_NAME, "X170SM"), }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS | + SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP) }, { - /* Gigabyte P34 - Elantech touchpad */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "GIGABYTE"), - DMI_MATCH(DMI_PRODUCT_NAME, "P34"), + DMI_MATCH(DMI_BOARD_NAME, "X170KM-G"), }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS | + SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP) }, + { } +}; + +#ifdef CONFIG_PNP +static const struct dmi_system_id i8042_dmi_laptop_table[] __initconst = { { - /* Gigabyte P57 - Elantech touchpad */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "GIGABYTE"), - DMI_MATCH(DMI_PRODUCT_NAME, "P57"), + DMI_MATCH(DMI_CHASSIS_TYPE, "8"), /* Portable */ }, }, { - /* Schenker XMG C504 - Elantech touchpad */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "XMG"), - DMI_MATCH(DMI_PRODUCT_NAME, "C504"), + DMI_MATCH(DMI_CHASSIS_TYPE, "9"), /* Laptop */ }, }, - { } -}; - -static const struct dmi_system_id i8042_dmi_probe_defer_table[] __initconst = { { - /* ASUS ZenBook UX425UA */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), - DMI_MATCH(DMI_PRODUCT_NAME, "ZenBook UX425UA"), + DMI_MATCH(DMI_CHASSIS_TYPE, "10"), /* Notebook */ }, }, { - /* ASUS ZenBook UM325UA */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), - DMI_MATCH(DMI_PRODUCT_NAME, "ZenBook UX325UA_UM325UA"), + DMI_MATCH(DMI_CHASSIS_TYPE, "14"), /* Sub-Notebook */ }, }, { } }; +#endif #endif /* CONFIG_X86 */ @@ -1166,11 +1372,6 @@ static int __init i8042_pnp_init(void) bool pnp_data_busted = false; int err; -#ifdef CONFIG_X86 - if (dmi_check_system(i8042_dmi_nopnp_table)) - i8042_nopnp = true; -#endif - if (i8042_nopnp) { pr_info("PNP detection disabled\n"); return 0; @@ -1274,6 +1475,59 @@ static inline int i8042_pnp_init(void) { return 0; } static inline void i8042_pnp_exit(void) { } #endif /* CONFIG_PNP */ + +#ifdef CONFIG_X86 +static void __init i8042_check_quirks(void) +{ + const struct dmi_system_id *device_quirk_info; + uintptr_t quirks; + + device_quirk_info = dmi_first_match(i8042_dmi_quirk_table); + if (!device_quirk_info) + return; + + quirks = (uintptr_t)device_quirk_info->driver_data; + + if (quirks & SERIO_QUIRK_NOKBD) + i8042_nokbd = true; + if (quirks & SERIO_QUIRK_NOAUX) + i8042_noaux = true; + if (quirks & SERIO_QUIRK_NOMUX) + i8042_nomux = true; + if (quirks & SERIO_QUIRK_FORCEMUX) + i8042_nomux = false; + if (quirks & SERIO_QUIRK_UNLOCK) + i8042_unlock = true; + if (quirks & SERIO_QUIRK_PROBE_DEFER) + i8042_probe_defer = true; + /* Honor module parameter when value is not default */ + if (i8042_reset == I8042_RESET_DEFAULT) { + if (quirks & SERIO_QUIRK_RESET_ALWAYS) + i8042_reset = I8042_RESET_ALWAYS; + if (quirks & SERIO_QUIRK_RESET_NEVER) + i8042_reset = I8042_RESET_NEVER; + } + if (quirks & SERIO_QUIRK_DIECT) + i8042_direct = true; + if (quirks & SERIO_QUIRK_DUMBKBD) + i8042_dumbkbd = true; + if (quirks & SERIO_QUIRK_NOLOOP) + i8042_noloop = true; + if (quirks & SERIO_QUIRK_NOTIMEOUT) + i8042_notimeout = true; + if (quirks & SERIO_QUIRK_KBDRESET) + i8042_kbdreset = true; + if (quirks & SERIO_QUIRK_DRITEK) + i8042_dritek = true; +#ifdef CONFIG_PNP + if (quirks & SERIO_QUIRK_NOPNP) + i8042_nopnp = true; +#endif +} +#else +static inline void i8042_check_quirks(void) {} +#endif + static int __init i8042_platform_init(void) { int retval; @@ -1296,45 +1550,17 @@ static int __init i8042_platform_init(void) i8042_kbd_irq = I8042_MAP_IRQ(1); i8042_aux_irq = I8042_MAP_IRQ(12); - retval = i8042_pnp_init(); - if (retval) - return retval; - #if defined(__ia64__) - i8042_reset = I8042_RESET_ALWAYS; + i8042_reset = I8042_RESET_ALWAYS; #endif -#ifdef CONFIG_X86 - /* Honor module parameter when value is not default */ - if (i8042_reset == I8042_RESET_DEFAULT) { - if (dmi_check_system(i8042_dmi_reset_table)) - i8042_reset = I8042_RESET_ALWAYS; - - if (dmi_check_system(i8042_dmi_noselftest_table)) - i8042_reset = I8042_RESET_NEVER; - } - - if (dmi_check_system(i8042_dmi_noloop_table)) - i8042_noloop = true; - - if (dmi_check_system(i8042_dmi_nomux_table)) - i8042_nomux = true; - - if (dmi_check_system(i8042_dmi_forcemux_table)) - i8042_nomux = false; - - if (dmi_check_system(i8042_dmi_notimeout_table)) - i8042_notimeout = true; - - if (dmi_check_system(i8042_dmi_dritek_table)) - i8042_dritek = true; - - if (dmi_check_system(i8042_dmi_kbdreset_table)) - i8042_kbdreset = true; + i8042_check_quirks(); - if (dmi_check_system(i8042_dmi_probe_defer_table)) - i8042_probe_defer = true; + retval = i8042_pnp_init(); + if (retval) + return retval; +#ifdef CONFIG_X86 /* * A20 was already enabled during early kernel init. But some buggy * BIOSes (in MSI Laptops) require A20 to be enabled using 8042 to diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index c392930253a30..b79309928d786 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -3098,7 +3098,8 @@ static int amd_iommu_attach_device(struct iommu_domain *dom, } static int amd_iommu_map(struct iommu_domain *dom, unsigned long iova, - phys_addr_t paddr, size_t page_size, int iommu_prot) + phys_addr_t paddr, size_t page_size, int iommu_prot, + gfp_t gfp) { struct protection_domain *domain = to_pdomain(dom); int prot = 0; @@ -3113,7 +3114,7 @@ static int amd_iommu_map(struct iommu_domain *dom, unsigned long iova, prot |= IOMMU_PROT_IW; mutex_lock(&domain->api_lock); - ret = iommu_map_page(domain, iova, paddr, page_size, prot, GFP_KERNEL); + ret = iommu_map_page(domain, iova, paddr, page_size, prot, gfp); mutex_unlock(&domain->api_lock); domain_flush_np_cache(domain, iova, page_size); diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c index 02c2fb551f381..4f64c3a9ee88d 100644 --- a/drivers/iommu/arm-smmu-v3.c +++ b/drivers/iommu/arm-smmu-v3.c @@ -2451,7 +2451,7 @@ out_unlock: } static int arm_smmu_map(struct iommu_domain *domain, unsigned long iova, - phys_addr_t paddr, size_t size, int prot) + phys_addr_t paddr, size_t size, int prot, gfp_t gfp) { struct io_pgtable_ops *ops = to_smmu_domain(domain)->pgtbl_ops; diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c index 2185ea5191c15..775acae84d7d2 100644 --- a/drivers/iommu/arm-smmu.c +++ b/drivers/iommu/arm-smmu.c @@ -1160,7 +1160,7 @@ rpm_put: } static int arm_smmu_map(struct iommu_domain *domain, unsigned long iova, - phys_addr_t paddr, size_t size, int prot) + phys_addr_t paddr, size_t size, int prot, gfp_t gfp) { struct io_pgtable_ops *ops = to_smmu_domain(domain)->pgtbl_ops; struct arm_smmu_device *smmu = to_smmu_domain(domain)->smmu; diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index 9c3e630c6c4c8..4fc8fb92d45ef 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -477,7 +477,7 @@ static dma_addr_t __iommu_dma_map(struct device *dev, phys_addr_t phys, if (!iova) return DMA_MAPPING_ERROR; - if (iommu_map(domain, iova, phys - iova_off, size, prot)) { + if (iommu_map_atomic(domain, iova, phys - iova_off, size, prot)) { iommu_dma_free_iova(cookie, iova, size); return DMA_MAPPING_ERROR; } @@ -612,7 +612,7 @@ static void *iommu_dma_alloc_remap(struct device *dev, size_t size, arch_dma_prep_coherent(sg_page(sg), sg->length); } - if (iommu_map_sg(domain, iova, sgt.sgl, sgt.orig_nents, ioprot) + if (iommu_map_sg_atomic(domain, iova, sgt.sgl, sgt.orig_nents, ioprot) < size) goto out_free_sg; @@ -872,7 +872,7 @@ static int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg, * We'll leave any physical concatenation to the IOMMU driver's * implementation - it knows better than we do. */ - if (iommu_map_sg(domain, iova, sg, nents, prot) < iova_len) + if (iommu_map_sg_atomic(domain, iova, sg, nents, prot) < iova_len) goto out_free_iova; return __finalise_sg(dev, sg, nents, iova); diff --git a/drivers/iommu/exynos-iommu.c b/drivers/iommu/exynos-iommu.c index 31a9b9885653f..acf21e4237949 100644 --- a/drivers/iommu/exynos-iommu.c +++ b/drivers/iommu/exynos-iommu.c @@ -1077,7 +1077,7 @@ static int lv2set_page(sysmmu_pte_t *pent, phys_addr_t paddr, size_t size, */ static int exynos_iommu_map(struct iommu_domain *iommu_domain, unsigned long l_iova, phys_addr_t paddr, size_t size, - int prot) + int prot, gfp_t gfp) { struct exynos_iommu_domain *domain = to_exynos_domain(iommu_domain); sysmmu_pte_t *entry; diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index ff120d7ed3424..2a53fa7d2b47d 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -5458,7 +5458,7 @@ static void intel_iommu_aux_detach_device(struct iommu_domain *domain, static int intel_iommu_map(struct iommu_domain *domain, unsigned long iova, phys_addr_t hpa, - size_t size, int iommu_prot) + size_t size, int iommu_prot, gfp_t gfp) { struct dmar_domain *dmar_domain = to_dmar_domain(domain); u64 max_addr; diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index c5758fb696cc8..ef8f0d1ac5ab1 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -1858,8 +1858,8 @@ static size_t iommu_pgsize(struct iommu_domain *domain, return pgsize; } -int iommu_map(struct iommu_domain *domain, unsigned long iova, - phys_addr_t paddr, size_t size, int prot) +int __iommu_map(struct iommu_domain *domain, unsigned long iova, + phys_addr_t paddr, size_t size, int prot, gfp_t gfp) { const struct iommu_ops *ops = domain->ops; unsigned long orig_iova = iova; @@ -1896,8 +1896,8 @@ int iommu_map(struct iommu_domain *domain, unsigned long iova, pr_debug("mapping: iova 0x%lx pa %pa pgsize 0x%zx\n", iova, &paddr, pgsize); + ret = ops->map(domain, iova, paddr, pgsize, prot, gfp); - ret = ops->map(domain, iova, paddr, pgsize, prot); if (ret) break; @@ -1917,8 +1917,22 @@ int iommu_map(struct iommu_domain *domain, unsigned long iova, return ret; } + +int iommu_map(struct iommu_domain *domain, unsigned long iova, + phys_addr_t paddr, size_t size, int prot) +{ + might_sleep(); + return __iommu_map(domain, iova, paddr, size, prot, GFP_KERNEL); +} EXPORT_SYMBOL_GPL(iommu_map); +int iommu_map_atomic(struct iommu_domain *domain, unsigned long iova, + phys_addr_t paddr, size_t size, int prot) +{ + return __iommu_map(domain, iova, paddr, size, prot, GFP_ATOMIC); +} +EXPORT_SYMBOL_GPL(iommu_map_atomic); + static size_t __iommu_unmap(struct iommu_domain *domain, unsigned long iova, size_t size, struct iommu_iotlb_gather *iotlb_gather) @@ -1995,8 +2009,9 @@ size_t iommu_unmap_fast(struct iommu_domain *domain, } EXPORT_SYMBOL_GPL(iommu_unmap_fast); -size_t iommu_map_sg(struct iommu_domain *domain, unsigned long iova, - struct scatterlist *sg, unsigned int nents, int prot) +size_t __iommu_map_sg(struct iommu_domain *domain, unsigned long iova, + struct scatterlist *sg, unsigned int nents, int prot, + gfp_t gfp) { size_t len = 0, mapped = 0; phys_addr_t start; @@ -2007,7 +2022,9 @@ size_t iommu_map_sg(struct iommu_domain *domain, unsigned long iova, phys_addr_t s_phys = sg_phys(sg); if (len && s_phys != start + len) { - ret = iommu_map(domain, iova + mapped, start, len, prot); + ret = __iommu_map(domain, iova + mapped, start, + len, prot, gfp); + if (ret) goto out_err; @@ -2035,8 +2052,22 @@ out_err: return 0; } + +size_t iommu_map_sg(struct iommu_domain *domain, unsigned long iova, + struct scatterlist *sg, unsigned int nents, int prot) +{ + might_sleep(); + return __iommu_map_sg(domain, iova, sg, nents, prot, GFP_KERNEL); +} EXPORT_SYMBOL_GPL(iommu_map_sg); +size_t iommu_map_sg_atomic(struct iommu_domain *domain, unsigned long iova, + struct scatterlist *sg, unsigned int nents, int prot) +{ + return __iommu_map_sg(domain, iova, sg, nents, prot, GFP_ATOMIC); +} +EXPORT_SYMBOL_GPL(iommu_map_sg_atomic); + int iommu_domain_window_enable(struct iommu_domain *domain, u32 wnd_nr, phys_addr_t paddr, u64 size, int prot) { diff --git a/drivers/iommu/ipmmu-vmsa.c b/drivers/iommu/ipmmu-vmsa.c index 584eefab1dbcd..33874c7aea42c 100644 --- a/drivers/iommu/ipmmu-vmsa.c +++ b/drivers/iommu/ipmmu-vmsa.c @@ -724,7 +724,7 @@ static void ipmmu_detach_device(struct iommu_domain *io_domain, } static int ipmmu_map(struct iommu_domain *io_domain, unsigned long iova, - phys_addr_t paddr, size_t size, int prot) + phys_addr_t paddr, size_t size, int prot, gfp_t gfp) { struct ipmmu_vmsa_domain *domain = to_vmsa_domain(io_domain); diff --git a/drivers/iommu/msm_iommu.c b/drivers/iommu/msm_iommu.c index cba0097eba39c..696a6c53a69fd 100644 --- a/drivers/iommu/msm_iommu.c +++ b/drivers/iommu/msm_iommu.c @@ -504,7 +504,7 @@ fail: } static int msm_iommu_map(struct iommu_domain *domain, unsigned long iova, - phys_addr_t pa, size_t len, int prot) + phys_addr_t pa, size_t len, int prot, gfp_t gfp) { struct msm_priv *priv = to_msm_priv(domain); unsigned long flags; diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c index 18d7c818a174c..dad44e10b3314 100644 --- a/drivers/iommu/mtk_iommu.c +++ b/drivers/iommu/mtk_iommu.c @@ -427,7 +427,7 @@ static void mtk_iommu_detach_device(struct iommu_domain *domain, } static int mtk_iommu_map(struct iommu_domain *domain, unsigned long iova, - phys_addr_t paddr, size_t size, int prot) + phys_addr_t paddr, size_t size, int prot, gfp_t gfp) { struct mtk_iommu_domain *dom = to_mtk_domain(domain); struct mtk_iommu_data *data = mtk_iommu_get_m4u_data(); diff --git a/drivers/iommu/mtk_iommu_v1.c b/drivers/iommu/mtk_iommu_v1.c index e31bd281e59d6..fa602bfe69512 100644 --- a/drivers/iommu/mtk_iommu_v1.c +++ b/drivers/iommu/mtk_iommu_v1.c @@ -295,7 +295,7 @@ static void mtk_iommu_detach_device(struct iommu_domain *domain, } static int mtk_iommu_map(struct iommu_domain *domain, unsigned long iova, - phys_addr_t paddr, size_t size, int prot) + phys_addr_t paddr, size_t size, int prot, gfp_t gfp) { struct mtk_iommu_domain *dom = to_mtk_domain(domain); unsigned int page_num = size >> MT2701_IOMMU_PAGE_SHIFT; diff --git a/drivers/iommu/omap-iommu.c b/drivers/iommu/omap-iommu.c index 09c6e1c680db9..be551cc34be45 100644 --- a/drivers/iommu/omap-iommu.c +++ b/drivers/iommu/omap-iommu.c @@ -1339,7 +1339,7 @@ static u32 iotlb_init_entry(struct iotlb_entry *e, u32 da, u32 pa, int pgsz) } static int omap_iommu_map(struct iommu_domain *domain, unsigned long da, - phys_addr_t pa, size_t bytes, int prot) + phys_addr_t pa, size_t bytes, int prot, gfp_t gfp) { struct omap_iommu_domain *omap_domain = to_omap_domain(domain); struct device *dev = omap_domain->dev; diff --git a/drivers/iommu/qcom_iommu.c b/drivers/iommu/qcom_iommu.c index b6e546b62a7cb..e377f7771e30b 100644 --- a/drivers/iommu/qcom_iommu.c +++ b/drivers/iommu/qcom_iommu.c @@ -419,7 +419,7 @@ static void qcom_iommu_detach_dev(struct iommu_domain *domain, struct device *de } static int qcom_iommu_map(struct iommu_domain *domain, unsigned long iova, - phys_addr_t paddr, size_t size, int prot) + phys_addr_t paddr, size_t size, int prot, gfp_t gfp) { int ret; unsigned long flags; diff --git a/drivers/iommu/rockchip-iommu.c b/drivers/iommu/rockchip-iommu.c index 0df091934361b..96f37d9d4d93c 100644 --- a/drivers/iommu/rockchip-iommu.c +++ b/drivers/iommu/rockchip-iommu.c @@ -758,7 +758,7 @@ unwind: } static int rk_iommu_map(struct iommu_domain *domain, unsigned long _iova, - phys_addr_t paddr, size_t size, int prot) + phys_addr_t paddr, size_t size, int prot, gfp_t gfp) { struct rk_iommu_domain *rk_domain = to_rk_domain(domain); unsigned long flags; diff --git a/drivers/iommu/s390-iommu.c b/drivers/iommu/s390-iommu.c index 3b0b18e23187c..1137f3ddcb851 100644 --- a/drivers/iommu/s390-iommu.c +++ b/drivers/iommu/s390-iommu.c @@ -265,7 +265,7 @@ undo_cpu_trans: } static int s390_iommu_map(struct iommu_domain *domain, unsigned long iova, - phys_addr_t paddr, size_t size, int prot) + phys_addr_t paddr, size_t size, int prot, gfp_t gfp) { struct s390_domain *s390_domain = to_s390_domain(domain); int flags = ZPCI_PTE_VALID, rc = 0; diff --git a/drivers/iommu/tegra-gart.c b/drivers/iommu/tegra-gart.c index 3924f7c055440..3fb7ba72507de 100644 --- a/drivers/iommu/tegra-gart.c +++ b/drivers/iommu/tegra-gart.c @@ -178,7 +178,7 @@ static inline int __gart_iommu_map(struct gart_device *gart, unsigned long iova, } static int gart_iommu_map(struct iommu_domain *domain, unsigned long iova, - phys_addr_t pa, size_t bytes, int prot) + phys_addr_t pa, size_t bytes, int prot, gfp_t gfp) { struct gart_device *gart = gart_handle; int ret; diff --git a/drivers/iommu/tegra-smmu.c b/drivers/iommu/tegra-smmu.c index dd486233e2828..576be3f245daa 100644 --- a/drivers/iommu/tegra-smmu.c +++ b/drivers/iommu/tegra-smmu.c @@ -651,7 +651,7 @@ static void tegra_smmu_set_pte(struct tegra_smmu_as *as, unsigned long iova, } static int tegra_smmu_map(struct iommu_domain *domain, unsigned long iova, - phys_addr_t paddr, size_t size, int prot) + phys_addr_t paddr, size_t size, int prot, gfp_t gfp) { struct tegra_smmu_as *as = to_smmu_as(domain); dma_addr_t pte_dma; diff --git a/drivers/iommu/virtio-iommu.c b/drivers/iommu/virtio-iommu.c index 60e659a24f90b..37e2267acf295 100644 --- a/drivers/iommu/virtio-iommu.c +++ b/drivers/iommu/virtio-iommu.c @@ -715,7 +715,7 @@ static int viommu_attach_dev(struct iommu_domain *domain, struct device *dev) } static int viommu_map(struct iommu_domain *domain, unsigned long iova, - phys_addr_t paddr, size_t size, int prot) + phys_addr_t paddr, size_t size, int prot, gfp_t gfp) { int ret; u32 flags; diff --git a/drivers/mmc/core/sdio_bus.c b/drivers/mmc/core/sdio_bus.c index aef235203d571..69eeff7a7d165 100644 --- a/drivers/mmc/core/sdio_bus.c +++ b/drivers/mmc/core/sdio_bus.c @@ -269,6 +269,12 @@ static void sdio_release_func(struct device *dev) if (!(func->card->quirks & MMC_QUIRK_NONSTD_SDIO)) sdio_free_func_cis(func); + /* + * We have now removed the link to the tuples in the + * card structure, so remove the reference. + */ + put_device(&func->card->dev); + kfree(func->info); kfree(func->tmpbuf); kfree(func); @@ -299,6 +305,12 @@ struct sdio_func *sdio_alloc_func(struct mmc_card *card) device_initialize(&func->dev); + /* + * We may link to tuples in the card structure, + * we need make sure we have a reference to it. + */ + get_device(&func->card->dev); + func->dev.parent = &card->dev; func->dev.bus = &sdio_bus_type; func->dev.release = sdio_release_func; @@ -352,10 +364,9 @@ int sdio_add_func(struct sdio_func *func) */ void sdio_remove_func(struct sdio_func *func) { - if (!sdio_func_present(func)) - return; + if (sdio_func_present(func)) + device_del(&func->dev); - device_del(&func->dev); of_node_put(func->dev.of_node); put_device(&func->dev); } diff --git a/drivers/mmc/core/sdio_cis.c b/drivers/mmc/core/sdio_cis.c index 9a5aaac29099b..e45053284fdc9 100644 --- a/drivers/mmc/core/sdio_cis.c +++ b/drivers/mmc/core/sdio_cis.c @@ -383,12 +383,6 @@ int sdio_read_func_cis(struct sdio_func *func) if (ret) return ret; - /* - * Since we've linked to tuples in the card structure, - * we must make sure we have a reference to it. - */ - get_device(&func->card->dev); - /* * Vendor/device id is optional for function CIS, so * copy it from the card structure as needed. @@ -414,11 +408,5 @@ void sdio_free_func_cis(struct sdio_func *func) } func->tuples = NULL; - - /* - * We have now removed the link to the tuples in the - * card structure, so remove the reference. - */ - put_device(&func->card->dev); } diff --git a/drivers/mmc/host/mmc_spi.c b/drivers/mmc/host/mmc_spi.c index 7083d8ddd4951..7874b266a4448 100644 --- a/drivers/mmc/host/mmc_spi.c +++ b/drivers/mmc/host/mmc_spi.c @@ -1420,7 +1420,7 @@ static int mmc_spi_probe(struct spi_device *spi) status = mmc_add_host(mmc); if (status != 0) - goto fail_add_host; + goto fail_glue_init; /* * Index 0 is card detect @@ -1428,7 +1428,7 @@ static int mmc_spi_probe(struct spi_device *spi) */ status = mmc_gpiod_request_cd(mmc, NULL, 0, false, 1, NULL); if (status == -EPROBE_DEFER) - goto fail_add_host; + goto fail_gpiod_request; if (!status) { /* * The platform has a CD GPIO signal that may support @@ -1443,7 +1443,7 @@ static int mmc_spi_probe(struct spi_device *spi) /* Index 1 is write protect/read only */ status = mmc_gpiod_request_ro(mmc, NULL, 1, 0, NULL); if (status == -EPROBE_DEFER) - goto fail_add_host; + goto fail_gpiod_request; if (!status) has_ro = true; @@ -1457,7 +1457,7 @@ static int mmc_spi_probe(struct spi_device *spi) ? ", cd polling" : ""); return 0; -fail_add_host: +fail_gpiod_request: mmc_remove_host(mmc); fail_glue_init: if (host->dma_dev) diff --git a/drivers/net/bonding/bond_debugfs.c b/drivers/net/bonding/bond_debugfs.c index f3f86ef68ae0c..8b6cf2bf9025a 100644 --- a/drivers/net/bonding/bond_debugfs.c +++ b/drivers/net/bonding/bond_debugfs.c @@ -76,7 +76,7 @@ void bond_debug_reregister(struct bonding *bond) d = debugfs_rename(bonding_debug_root, bond->debug_dir, bonding_debug_root, bond->dev->name); - if (d) { + if (!IS_ERR(d)) { bond->debug_dir = d; } else { netdev_warn(bond->dev, "failed to reregister, so just unregister old one\n"); diff --git a/drivers/net/ethernet/broadcom/bgmac-bcma.c b/drivers/net/ethernet/broadcom/bgmac-bcma.c index 2d52754afc33a..7d844b0ea0da0 100644 --- a/drivers/net/ethernet/broadcom/bgmac-bcma.c +++ b/drivers/net/ethernet/broadcom/bgmac-bcma.c @@ -228,12 +228,12 @@ static int bgmac_probe(struct bcma_device *core) bgmac->feature_flags |= BGMAC_FEAT_CLKCTLST; bgmac->feature_flags |= BGMAC_FEAT_FLW_CTRL1; bgmac->feature_flags |= BGMAC_FEAT_SW_TYPE_PHY; - if (ci->pkg == BCMA_PKG_ID_BCM47188 || - ci->pkg == BCMA_PKG_ID_BCM47186) { + if ((ci->id == BCMA_CHIP_ID_BCM5357 && ci->pkg == BCMA_PKG_ID_BCM47186) || + (ci->id == BCMA_CHIP_ID_BCM53572 && ci->pkg == BCMA_PKG_ID_BCM47188)) { bgmac->feature_flags |= BGMAC_FEAT_SW_TYPE_RGMII; bgmac->feature_flags |= BGMAC_FEAT_IOST_ATTACHED; } - if (ci->pkg == BCMA_PKG_ID_BCM5358) + if (ci->id == BCMA_CHIP_ID_BCM5357 && ci->pkg == BCMA_PKG_ID_BCM5358) bgmac->feature_flags |= BGMAC_FEAT_SW_TYPE_EPHYRMII; break; case BCMA_CHIP_ID_BCM53573: diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 3636849f63656..ef8225b7445d3 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -8205,10 +8205,14 @@ int bnxt_reserve_rings(struct bnxt *bp, bool irq_re_init) netdev_err(bp->dev, "ring reservation/IRQ init failure rc: %d\n", rc); return rc; } - if (tcs && (bp->tx_nr_rings_per_tc * tcs != bp->tx_nr_rings)) { + if (tcs && (bp->tx_nr_rings_per_tc * tcs != + bp->tx_nr_rings - bp->tx_nr_rings_xdp)) { netdev_err(bp->dev, "tx ring reservation failure\n"); netdev_reset_tc(bp->dev); - bp->tx_nr_rings_per_tc = bp->tx_nr_rings; + if (bp->tx_nr_rings_xdp) + bp->tx_nr_rings_per_tc = bp->tx_nr_rings_xdp; + else + bp->tx_nr_rings_per_tc = bp->tx_nr_rings; return -ENOMEM; } return 0; diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index d612b23c2e3f9..3f983d69f10eb 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -2702,7 +2702,7 @@ static int i40e_change_mtu(struct net_device *netdev, int new_mtu) struct i40e_pf *pf = vsi->back; if (i40e_enabled_xdp_vsi(vsi)) { - int frame_size = new_mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN; + int frame_size = new_mtu + I40E_PACKET_HDR_PAD; if (frame_size > i40e_max_xdp_frame_size(vsi)) return -EINVAL; @@ -12535,6 +12535,8 @@ static int i40e_ndo_bridge_setlink(struct net_device *dev, } br_spec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC); + if (!br_spec) + return -EINVAL; nla_for_each_nested(attr, br_spec, rem) { __u16 mode; diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 7d28563ab7946..ae1d305672259 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -3211,7 +3211,7 @@ static int __init ice_module_init(void) pr_info("%s - version %s\n", ice_driver_string, ice_drv_ver); pr_info("%s\n", ice_copyright); - ice_wq = alloc_workqueue("%s", WQ_MEM_RECLAIM, 0, KBUILD_MODNAME); + ice_wq = alloc_workqueue("%s", 0, 0, KBUILD_MODNAME); if (!ice_wq) { pr_err("Failed to create workqueue\n"); return -ENOMEM; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h index fa49ef2afde5f..0142ca226bf50 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h @@ -67,6 +67,8 @@ #define IXGBE_RXBUFFER_4K 4096 #define IXGBE_MAX_RXBUFFER 16384 /* largest size for a single descriptor */ +#define IXGBE_PKT_HDR_PAD (ETH_HLEN + ETH_FCS_LEN + (VLAN_HLEN * 2)) + /* Attempt to maximize the headroom available for incoming frames. We * use a 2K buffer for receives and need 1536/1534 to store the data for * the frame. This leaves us with 512 bytes of room. From that we need diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index f8aa1a0b89c5d..a864b91065e33 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -6721,6 +6721,18 @@ static void ixgbe_free_all_rx_resources(struct ixgbe_adapter *adapter) ixgbe_free_rx_resources(adapter->rx_ring[i]); } +/** + * ixgbe_max_xdp_frame_size - returns the maximum allowed frame size for XDP + * @adapter: device handle, pointer to adapter + */ +static int ixgbe_max_xdp_frame_size(struct ixgbe_adapter *adapter) +{ + if (PAGE_SIZE >= 8192 || adapter->flags2 & IXGBE_FLAG2_RX_LEGACY) + return IXGBE_RXBUFFER_2K; + else + return IXGBE_RXBUFFER_3K; +} + /** * ixgbe_change_mtu - Change the Maximum Transfer Unit * @netdev: network interface device structure @@ -6732,18 +6744,12 @@ static int ixgbe_change_mtu(struct net_device *netdev, int new_mtu) { struct ixgbe_adapter *adapter = netdev_priv(netdev); - if (adapter->xdp_prog) { - int new_frame_size = new_mtu + ETH_HLEN + ETH_FCS_LEN + - VLAN_HLEN; - int i; - - for (i = 0; i < adapter->num_rx_queues; i++) { - struct ixgbe_ring *ring = adapter->rx_ring[i]; + if (ixgbe_enabled_xdp_adapter(adapter)) { + int new_frame_size = new_mtu + IXGBE_PKT_HDR_PAD; - if (new_frame_size > ixgbe_rx_bufsz(ring)) { - e_warn(probe, "Requested MTU size is not supported with XDP\n"); - return -EINVAL; - } + if (new_frame_size > ixgbe_max_xdp_frame_size(adapter)) { + e_warn(probe, "Requested MTU size is not supported with XDP\n"); + return -EINVAL; } } diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c index f9c303d76658a..d0841836cf705 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c @@ -190,6 +190,7 @@ static int ionic_qcq_enable(struct ionic_qcq *qcq) .oper = IONIC_Q_ENABLE, }, }; + int ret; idev = &lif->ionic->idev; dev = lif->ionic->dev; @@ -197,16 +198,24 @@ static int ionic_qcq_enable(struct ionic_qcq *qcq) dev_dbg(dev, "q_enable.index %d q_enable.qtype %d\n", ctx.cmd.q_control.index, ctx.cmd.q_control.type); + if (qcq->flags & IONIC_QCQ_F_INTR) + ionic_intr_clean(idev->intr_ctrl, qcq->intr.index); + + ret = ionic_adminq_post_wait(lif, &ctx); + if (ret) + return ret; + + if (qcq->napi.poll) + napi_enable(&qcq->napi); + if (qcq->flags & IONIC_QCQ_F_INTR) { irq_set_affinity_hint(qcq->intr.vector, &qcq->intr.affinity_mask); - napi_enable(&qcq->napi); - ionic_intr_clean(idev->intr_ctrl, qcq->intr.index); ionic_intr_mask(idev->intr_ctrl, qcq->intr.index, IONIC_INTR_MASK_CLEAR); } - return ionic_adminq_post_wait(lif, &ctx); + return 0; } static int ionic_qcq_disable(struct ionic_qcq *qcq) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c index bfc4a92f1d92b..78be62ecc9a9a 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c @@ -505,6 +505,8 @@ static int qcom_ethqos_probe(struct platform_device *pdev) plat_dat->has_gmac4 = 1; plat_dat->pmt = 1; plat_dat->tso_en = of_property_read_bool(np, "snps,tso"); + if (of_device_is_compatible(np, "qcom,qcs404-ethqos")) + plat_dat->rx_clk_runs_in_lpi = 1; ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); if (ret) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac5.c b/drivers/net/ethernet/stmicro/stmmac/dwmac5.c index e436fa160c7d6..59165c0560d74 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac5.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac5.c @@ -520,9 +520,9 @@ int dwmac5_flex_pps_config(void __iomem *ioaddr, int index, return 0; } - val |= PPSCMDx(index, 0x2); val |= TRGTMODSELx(index, 0x2); val |= PPSEN0; + writel(val, ioaddr + MAC_PPS_CONTROL); writel(cfg->start.tv_sec, ioaddr + MAC_PPSx_TARGET_TIME_SEC(index)); @@ -547,6 +547,7 @@ int dwmac5_flex_pps_config(void __iomem *ioaddr, int index, writel(period - 1, ioaddr + MAC_PPSx_WIDTH(index)); /* Finally, activate it */ + val |= PPSCMDx(index, 0x2); writel(val, ioaddr + MAC_PPS_CONTROL); return 0; } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 3079e52546663..6a3b0f76d9729 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -932,7 +932,8 @@ static void stmmac_mac_link_up(struct phylink_config *config, stmmac_mac_set(priv, priv->ioaddr, true); if (phy && priv->dma_cap.eee) { - priv->eee_active = phy_init_eee(phy, 1) >= 0; + priv->eee_active = + phy_init_eee(phy, !priv->plat->rx_clk_runs_in_lpi) >= 0; priv->eee_enabled = stmmac_eee_init(priv); stmmac_set_eee_pls(priv, priv->hw, true); } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index a2ff9b4727ecd..6388bae68b659 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -554,7 +554,7 @@ stmmac_probe_config_dt(struct platform_device *pdev, const char **mac) dma_cfg->mixed_burst = of_property_read_bool(np, "snps,mixed-burst"); plat->force_thresh_dma_mode = of_property_read_bool(np, "snps,force_thresh_dma_mode"); - if (plat->force_thresh_dma_mode) { + if (plat->force_thresh_dma_mode && plat->force_sf_dma_mode) { plat->force_sf_dma_mode = 0; dev_warn(&pdev->dev, "force_sf_dma_mode is ignored if force_thresh_dma_mode is set.\n"); diff --git a/drivers/net/phy/meson-gxl.c b/drivers/net/phy/meson-gxl.c index e8f2ca625837f..39151ec6f65e2 100644 --- a/drivers/net/phy/meson-gxl.c +++ b/drivers/net/phy/meson-gxl.c @@ -235,6 +235,8 @@ static struct phy_driver meson_gxl_phy[] = { .config_intr = meson_gxl_config_intr, .suspend = genphy_suspend, .resume = genphy_resume, + .read_mmd = genphy_read_mmd_unsupported, + .write_mmd = genphy_write_mmd_unsupported, }, { PHY_ID_MATCH_EXACT(0x01803301), .name = "Meson G12A Internal PHY", @@ -245,6 +247,8 @@ static struct phy_driver meson_gxl_phy[] = { .config_intr = meson_gxl_config_intr, .suspend = genphy_suspend, .resume = genphy_resume, + .read_mmd = genphy_read_mmd_unsupported, + .write_mmd = genphy_write_mmd_unsupported, }, }; diff --git a/drivers/net/usb/kalmia.c b/drivers/net/usb/kalmia.c index fc5895f85cee2..a552bb1665b8a 100644 --- a/drivers/net/usb/kalmia.c +++ b/drivers/net/usb/kalmia.c @@ -65,8 +65,8 @@ kalmia_send_init_packet(struct usbnet *dev, u8 *init_msg, u8 init_msg_len, init_msg, init_msg_len, &act_len, KALMIA_USB_TIMEOUT); if (status != 0) { netdev_err(dev->net, - "Error sending init packet. Status %i, length %i\n", - status, act_len); + "Error sending init packet. Status %i\n", + status); return status; } else if (act_len != init_msg_len) { @@ -83,8 +83,8 @@ kalmia_send_init_packet(struct usbnet *dev, u8 *init_msg, u8 init_msg_len, if (status != 0) netdev_err(dev->net, - "Error receiving init result. Status %i, length %i\n", - status, act_len); + "Error receiving init result. Status %i\n", + status); else if (act_len != expected_len) netdev_err(dev->net, "Unexpected init result length: %i\n", act_len); diff --git a/drivers/net/usb/plusb.c b/drivers/net/usb/plusb.c index 17c9c63b8eebb..ce7862dac2b75 100644 --- a/drivers/net/usb/plusb.c +++ b/drivers/net/usb/plusb.c @@ -57,9 +57,7 @@ static inline int pl_vendor_req(struct usbnet *dev, u8 req, u8 val, u8 index) { - return usbnet_read_cmd(dev, req, - USB_DIR_IN | USB_TYPE_VENDOR | - USB_RECIP_DEVICE, + return usbnet_write_cmd(dev, req, USB_TYPE_VENDOR | USB_RECIP_DEVICE, val, index, NULL, 0); } diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 579df7c5411d3..5212d9cb03728 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -1910,8 +1910,8 @@ static int virtnet_close(struct net_device *dev) cancel_delayed_work_sync(&vi->refill); for (i = 0; i < vi->max_queue_pairs; i++) { - xdp_rxq_info_unreg(&vi->rq[i].xdp_rxq); napi_disable(&vi->rq[i].napi); + xdp_rxq_info_unreg(&vi->rq[i].xdp_rxq); virtnet_napi_tx_disable(&vi->sq[i].napi); } diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c index 6439adcd2f995..cd146bbca670b 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c @@ -87,6 +87,9 @@ #define BRCMF_ASSOC_PARAMS_FIXED_SIZE \ (sizeof(struct brcmf_assoc_params_le) - sizeof(u16)) +#define BRCMF_MAX_CHANSPEC_LIST \ + (BRCMF_DCMD_MEDLEN / sizeof(__le32) - 1) + static bool check_vif_up(struct brcmf_cfg80211_vif *vif) { if (!test_bit(BRCMF_VIF_STATUS_READY, &vif->sme_state)) { @@ -6067,6 +6070,13 @@ static int brcmf_construct_chaninfo(struct brcmf_cfg80211_info *cfg, band->channels[i].flags = IEEE80211_CHAN_DISABLED; total = le32_to_cpu(list->count); + if (total > BRCMF_MAX_CHANSPEC_LIST) { + bphy_err(drvr, "Invalid count of channel Spec. (%u)\n", + total); + err = -EINVAL; + goto fail_pbuf; + } + for (i = 0; i < total; i++) { ch.chspec = (u16)le32_to_cpu(list->element[i]); cfg->d11inf.decchspec(&ch); @@ -6212,6 +6222,13 @@ static int brcmf_enable_bw40_2g(struct brcmf_cfg80211_info *cfg) band = cfg_to_wiphy(cfg)->bands[NL80211_BAND_2GHZ]; list = (struct brcmf_chanspec_list *)pbuf; num_chan = le32_to_cpu(list->count); + if (num_chan > BRCMF_MAX_CHANSPEC_LIST) { + bphy_err(drvr, "Invalid count of channel Spec. (%u)\n", + num_chan); + kfree(pbuf); + return -EINVAL; + } + for (i = 0; i < num_chan; i++) { ch.chspec = (u16)le32_to_cpu(list->element[i]); cfg->d11inf.decchspec(&ch); diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 5d62d1042c0e6..a58711c488509 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -3199,7 +3199,6 @@ static const struct pci_device_id nvme_id_table[] = { NVME_QUIRK_IGNORE_DEV_SUBNQN, }, { PCI_DEVICE(0x1c5c, 0x1504), /* SK Hynix PC400 */ .driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, }, - { PCI_DEVICE_CLASS(PCI_CLASS_STORAGE_EXPRESS, 0xffffff) }, { PCI_DEVICE(0x2646, 0x2263), /* KINGSTON A2000 NVMe SSD */ .driver_data = NVME_QUIRK_NO_DEEPEST_PS, }, { PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2001), @@ -3209,6 +3208,8 @@ static const struct pci_device_id nvme_id_table[] = { .driver_data = NVME_QUIRK_SINGLE_VECTOR | NVME_QUIRK_128_BYTES_SQES | NVME_QUIRK_SHARED_TAGS }, + + { PCI_DEVICE_CLASS(PCI_CLASS_STORAGE_EXPRESS, 0xffffff) }, { 0, } }; MODULE_DEVICE_TABLE(pci, nvme_id_table); diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c index 9b07e8c7689ab..f74fc6481731d 100644 --- a/drivers/nvme/target/fc.c +++ b/drivers/nvme/target/fc.c @@ -1362,8 +1362,10 @@ nvmet_fc_ls_create_association(struct nvmet_fc_tgtport *tgtport, else { queue = nvmet_fc_alloc_target_queue(iod->assoc, 0, be16_to_cpu(rqst->assoc_cmd.sqsize)); - if (!queue) + if (!queue) { ret = VERR_QUEUE_ALLOC_FAIL; + nvmet_fc_tgt_a_put(iod->assoc); + } } } diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c index c0f4324d8f7c8..cde1d77845fee 100644 --- a/drivers/nvmem/core.c +++ b/drivers/nvmem/core.c @@ -439,7 +439,7 @@ struct nvmem_device *nvmem_register(const struct nvmem_config *config) if (config->cells) { rval = nvmem_add_cells(nvmem, config->cells, config->ncells); if (rval) - goto err_teardown_compat; + goto err_remove_cells; } rval = nvmem_add_cells_from_table(nvmem); @@ -456,7 +456,6 @@ struct nvmem_device *nvmem_register(const struct nvmem_config *config) err_remove_cells: nvmem_device_remove_all_cells(nvmem); -err_teardown_compat: if (config->compat) nvmem_sysfs_remove_compat(nvmem, config); err_device_del: diff --git a/drivers/pinctrl/aspeed/pinctrl-aspeed.c b/drivers/pinctrl/aspeed/pinctrl-aspeed.c index 22aca6d182c0c..2c1e799b029e7 100644 --- a/drivers/pinctrl/aspeed/pinctrl-aspeed.c +++ b/drivers/pinctrl/aspeed/pinctrl-aspeed.c @@ -115,7 +115,7 @@ static int aspeed_disable_sig(struct aspeed_pinmux_data *ctx, int ret = 0; if (!exprs) - return true; + return -EINVAL; while (*exprs && !ret) { ret = aspeed_sig_expr_disable(ctx, *exprs); diff --git a/drivers/pinctrl/intel/pinctrl-intel.c b/drivers/pinctrl/intel/pinctrl-intel.c index e0cb76f7e5407..32c6326337f73 100644 --- a/drivers/pinctrl/intel/pinctrl-intel.c +++ b/drivers/pinctrl/intel/pinctrl-intel.c @@ -1510,6 +1510,12 @@ int intel_pinctrl_probe_by_uid(struct platform_device *pdev) EXPORT_SYMBOL_GPL(intel_pinctrl_probe_by_uid); #ifdef CONFIG_PM_SLEEP +static bool __intel_gpio_is_direct_irq(u32 value) +{ + return (value & PADCFG0_GPIROUTIOXAPIC) && (value & PADCFG0_GPIOTXDIS) && + (__intel_gpio_get_gpio_mode(value) == PADCFG0_PMODE_GPIO); +} + static bool intel_pinctrl_should_save(struct intel_pinctrl *pctrl, unsigned int pin) { const struct pin_desc *pd = pin_desc_get(pctrl->pctldev, pin); @@ -1543,8 +1549,7 @@ static bool intel_pinctrl_should_save(struct intel_pinctrl *pctrl, unsigned int * See https://bugzilla.kernel.org/show_bug.cgi?id=214749. */ value = readl(intel_get_padcfg(pctrl, pin, PADCFG0)); - if ((value & PADCFG0_GPIROUTIOXAPIC) && (value & PADCFG0_GPIOTXDIS) && - (__intel_gpio_get_gpio_mode(value) == PADCFG0_PMODE_GPIO)) + if (__intel_gpio_is_direct_irq(value)) return true; return false; @@ -1656,7 +1661,12 @@ int intel_pinctrl_resume_noirq(struct device *dev) void __iomem *padcfg; u32 val; - if (!intel_pinctrl_should_save(pctrl, desc->number)) + if (!(intel_pinctrl_should_save(pctrl, desc->number) || + /* + * If the firmware mangled the register contents too much, + * check the saved value for the Direct IRQ mode. + */ + __intel_gpio_is_direct_irq(pads[i].padcfg0))) continue; padcfg = intel_get_padcfg(pctrl, desc->number, PADCFG0); diff --git a/drivers/pinctrl/pinctrl-single.c b/drivers/pinctrl/pinctrl-single.c index 20c89023d312e..ce5be6f0b7aac 100644 --- a/drivers/pinctrl/pinctrl-single.c +++ b/drivers/pinctrl/pinctrl-single.c @@ -345,6 +345,8 @@ static int pcs_set_mux(struct pinctrl_dev *pctldev, unsigned fselector, if (!pcs->fmask) return 0; function = pinmux_generic_get_function(pctldev, fselector); + if (!function) + return -EINVAL; func = function->data; if (!func) return -EINVAL; diff --git a/drivers/scsi/iscsi_tcp.c b/drivers/scsi/iscsi_tcp.c index b5dd1caae5e92..9320a0a92bb2f 100644 --- a/drivers/scsi/iscsi_tcp.c +++ b/drivers/scsi/iscsi_tcp.c @@ -770,7 +770,7 @@ static int iscsi_sw_tcp_host_get_param(struct Scsi_Host *shost, enum iscsi_host_param param, char *buf) { struct iscsi_sw_tcp_host *tcp_sw_host = iscsi_host_priv(shost); - struct iscsi_session *session = tcp_sw_host->session; + struct iscsi_session *session; struct iscsi_conn *conn; struct iscsi_tcp_conn *tcp_conn; struct iscsi_sw_tcp_conn *tcp_sw_conn; @@ -779,6 +779,7 @@ static int iscsi_sw_tcp_host_get_param(struct Scsi_Host *shost, switch (param) { case ISCSI_HOST_PARAM_IPADDRESS: + session = tcp_sw_host->session; if (!session) return -ENOTCONN; @@ -867,12 +868,14 @@ iscsi_sw_tcp_session_create(struct iscsi_endpoint *ep, uint16_t cmds_max, if (!cls_session) goto remove_host; session = cls_session->dd_data; - tcp_sw_host = iscsi_host_priv(shost); - tcp_sw_host->session = session; shost->can_queue = session->scsi_cmds_max; if (iscsi_tcp_r2tpool_alloc(session)) goto remove_session; + + /* We are now fully setup so expose the session to sysfs. */ + tcp_sw_host = iscsi_host_priv(shost); + tcp_sw_host->session = session; return cls_session; remove_session: diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c index 3fd109fd9335d..d236322ced30e 100644 --- a/drivers/scsi/scsi_scan.c +++ b/drivers/scsi/scsi_scan.c @@ -1130,8 +1130,7 @@ static int scsi_probe_and_add_lun(struct scsi_target *starget, * that no LUN is present, so don't add sdev in these cases. * Two specific examples are: * 1) NetApp targets: return PQ=1, PDT=0x1f - * 2) IBM/2145 targets: return PQ=1, PDT=0 - * 3) USB UFI: returns PDT=0x1f, with the PQ bits being "reserved" + * 2) USB UFI: returns PDT=0x1f, with the PQ bits being "reserved" * in the UFI 1.0 spec (we cannot rely on reserved bits). * * References: @@ -1145,8 +1144,8 @@ static int scsi_probe_and_add_lun(struct scsi_target *starget, * PDT=00h Direct-access device (floppy) * PDT=1Fh none (no FDD connected to the requested logical unit) */ - if (((result[0] >> 5) == 1 || - (starget->pdt_1f_for_no_lun && (result[0] & 0x1f) == 0x1f)) && + if (((result[0] >> 5) == 1 || starget->pdt_1f_for_no_lun) && + (result[0] & 0x1f) == 0x1f && !scsi_is_wlun(lun)) { SCSI_LOG_SCAN_BUS(3, sdev_printk(KERN_INFO, sdev, "scsi scan: peripheral device type" diff --git a/drivers/target/target_core_file.c b/drivers/target/target_core_file.c index 7143d03f0e027..18fbbe510d018 100644 --- a/drivers/target/target_core_file.c +++ b/drivers/target/target_core_file.c @@ -340,7 +340,7 @@ static int fd_do_rw(struct se_cmd *cmd, struct file *fd, len += sg->length; } - iov_iter_bvec(&iter, READ, bvec, sgl_nents, len); + iov_iter_bvec(&iter, is_write, bvec, sgl_nents, len); if (is_write) ret = vfs_iter_write(fd, &iter, &pos, 0); else @@ -477,7 +477,7 @@ fd_execute_write_same(struct se_cmd *cmd) len += se_dev->dev_attrib.block_size; } - iov_iter_bvec(&iter, READ, bvec, nolb, len); + iov_iter_bvec(&iter, WRITE, bvec, nolb, len); ret = vfs_iter_write(fd_dev->fd_file, &iter, &pos, 0); kfree(bvec); diff --git a/drivers/target/target_core_tmr.c b/drivers/target/target_core_tmr.c index feeba3966617b..6928ebf0be9c7 100644 --- a/drivers/target/target_core_tmr.c +++ b/drivers/target/target_core_tmr.c @@ -82,8 +82,8 @@ static bool __target_check_io_state(struct se_cmd *se_cmd, { struct se_session *sess = se_cmd->se_sess; - assert_spin_locked(&sess->sess_cmd_lock); - WARN_ON_ONCE(!irqs_disabled()); + lockdep_assert_held(&sess->sess_cmd_lock); + /* * If command already reached CMD_T_COMPLETE state within * target_complete_cmd() or CMD_T_FABRIC_STOP due to shutdown, diff --git a/drivers/tty/serial/8250/8250_dma.c b/drivers/tty/serial/8250/8250_dma.c index 890fa7ddaa7f3..bdc7bb7a1b929 100644 --- a/drivers/tty/serial/8250/8250_dma.c +++ b/drivers/tty/serial/8250/8250_dma.c @@ -46,19 +46,39 @@ static void __dma_rx_complete(void *param) struct uart_8250_dma *dma = p->dma; struct tty_port *tty_port = &p->port.state->port; struct dma_tx_state state; + enum dma_status dma_status; int count; - dma->rx_running = 0; - dmaengine_tx_status(dma->rxchan, dma->rx_cookie, &state); + /* + * New DMA Rx can be started during the completion handler before it + * could acquire port's lock and it might still be ongoing. Don't to + * anything in such case. + */ + dma_status = dmaengine_tx_status(dma->rxchan, dma->rx_cookie, &state); + if (dma_status == DMA_IN_PROGRESS) + return; count = dma->rx_size - state.residue; tty_insert_flip_string(tty_port, dma->rx_buf, count); p->port.icount.rx += count; + dma->rx_running = 0; tty_flip_buffer_push(tty_port); } +static void dma_rx_complete(void *param) +{ + struct uart_8250_port *p = param; + struct uart_8250_dma *dma = p->dma; + unsigned long flags; + + spin_lock_irqsave(&p->port.lock, flags); + if (dma->rx_running) + __dma_rx_complete(p); + spin_unlock_irqrestore(&p->port.lock, flags); +} + int serial8250_tx_dma(struct uart_8250_port *p) { struct uart_8250_dma *dma = p->dma; @@ -121,7 +141,7 @@ int serial8250_rx_dma(struct uart_8250_port *p) return -EBUSY; dma->rx_running = 1; - desc->callback = __dma_rx_complete; + desc->callback = dma_rx_complete; desc->callback_param = p; dma->rx_cookie = dmaengine_submit(desc); diff --git a/drivers/tty/vt/vc_screen.c b/drivers/tty/vt/vc_screen.c index 778f83ea22493..e61fd04a0d8d0 100644 --- a/drivers/tty/vt/vc_screen.c +++ b/drivers/tty/vt/vc_screen.c @@ -265,10 +265,6 @@ vcs_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) uni_mode = use_unicode(inode); attr = use_attributes(inode); - ret = -ENXIO; - vc = vcs_vc(inode, &viewed); - if (!vc) - goto unlock_out; ret = -EINVAL; if (pos < 0) @@ -288,6 +284,11 @@ vcs_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) ssize_t orig_count; long p = pos; + ret = -ENXIO; + vc = vcs_vc(inode, &viewed); + if (!vc) + goto unlock_out; + /* Check whether we are above size each round, * as copy_to_user at the end of this loop * could sleep. diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c index 35a11f7bcb658..1346c600ebedf 100644 --- a/drivers/usb/core/quirks.c +++ b/drivers/usb/core/quirks.c @@ -527,6 +527,9 @@ static const struct usb_device_id usb_quirk_list[] = { /* DJI CineSSD */ { USB_DEVICE(0x2ca3, 0x0031), .driver_info = USB_QUIRK_NO_LPM }, + /* Alcor Link AK9563 SC Reader used in 2022 Lenovo ThinkPads */ + { USB_DEVICE(0x2ce3, 0x9563), .driver_info = USB_QUIRK_NO_LPM }, + /* DELL USB GEN2 */ { USB_DEVICE(0x413c, 0xb062), .driver_info = USB_QUIRK_NO_LPM | USB_QUIRK_RESET_RESUME }, diff --git a/drivers/usb/dwc3/dwc3-qcom.c b/drivers/usb/dwc3/dwc3-qcom.c index aed35276e0e0c..2dcdeb52fc293 100644 --- a/drivers/usb/dwc3/dwc3-qcom.c +++ b/drivers/usb/dwc3/dwc3-qcom.c @@ -102,7 +102,7 @@ static inline void dwc3_qcom_clrbits(void __iomem *base, u32 offset, u32 val) readl(base + offset); } -static void dwc3_qcom_vbus_overrride_enable(struct dwc3_qcom *qcom, bool enable) +static void dwc3_qcom_vbus_override_enable(struct dwc3_qcom *qcom, bool enable) { if (enable) { dwc3_qcom_setbits(qcom->qscratch_base, QSCRATCH_SS_PHY_CTRL, @@ -123,7 +123,7 @@ static int dwc3_qcom_vbus_notifier(struct notifier_block *nb, struct dwc3_qcom *qcom = container_of(nb, struct dwc3_qcom, vbus_nb); /* enable vbus override for device mode */ - dwc3_qcom_vbus_overrride_enable(qcom, event); + dwc3_qcom_vbus_override_enable(qcom, event); qcom->mode = event ? USB_DR_MODE_PERIPHERAL : USB_DR_MODE_HOST; return NOTIFY_DONE; @@ -135,7 +135,7 @@ static int dwc3_qcom_host_notifier(struct notifier_block *nb, struct dwc3_qcom *qcom = container_of(nb, struct dwc3_qcom, host_nb); /* disable vbus override in host mode */ - dwc3_qcom_vbus_overrride_enable(qcom, !event); + dwc3_qcom_vbus_override_enable(qcom, !event); qcom->mode = event ? USB_DR_MODE_HOST : USB_DR_MODE_PERIPHERAL; return NOTIFY_DONE; @@ -669,8 +669,8 @@ static int dwc3_qcom_probe(struct platform_device *pdev) qcom->mode = usb_get_dr_mode(&qcom->dwc3->dev); /* enable vbus override for device mode */ - if (qcom->mode == USB_DR_MODE_PERIPHERAL) - dwc3_qcom_vbus_overrride_enable(qcom, true); + if (qcom->mode != USB_DR_MODE_HOST) + dwc3_qcom_vbus_override_enable(qcom, true); /* register extcon to override sw_vbus on Vbus change later */ ret = dwc3_qcom_register_extcon(qcom); diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index 431ab6d07497f..5fe7490367734 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -278,8 +278,10 @@ static int __ffs_ep0_queue_wait(struct ffs_data *ffs, char *data, size_t len) struct usb_request *req = ffs->ep0req; int ret; - if (!req) + if (!req) { + spin_unlock_irq(&ffs->ev.waitq.lock); return -EINVAL; + } req->zero = len < le16_to_cpu(ffs->ev.setup.wLength); diff --git a/drivers/usb/typec/altmodes/displayport.c b/drivers/usb/typec/altmodes/displayport.c index 1aa1bd991ef43..c840f03996fb6 100644 --- a/drivers/usb/typec/altmodes/displayport.c +++ b/drivers/usb/typec/altmodes/displayport.c @@ -522,10 +522,10 @@ int dp_altmode_probe(struct typec_altmode *alt) /* FIXME: Port can only be DFP_U. */ /* Make sure we have compatiple pin configurations */ - if (!(DP_CAP_DFP_D_PIN_ASSIGN(port->vdo) & - DP_CAP_UFP_D_PIN_ASSIGN(alt->vdo)) && - !(DP_CAP_UFP_D_PIN_ASSIGN(port->vdo) & - DP_CAP_DFP_D_PIN_ASSIGN(alt->vdo))) + if (!(DP_CAP_PIN_ASSIGN_DFP_D(port->vdo) & + DP_CAP_PIN_ASSIGN_UFP_D(alt->vdo)) && + !(DP_CAP_PIN_ASSIGN_UFP_D(port->vdo) & + DP_CAP_PIN_ASSIGN_DFP_D(alt->vdo))) return -ENODEV; ret = sysfs_create_group(&alt->dev.kobj, &dp_altmode_group); diff --git a/drivers/video/fbdev/core/fbcon.c b/drivers/video/fbdev/core/fbcon.c index 673af5937489f..e487928289392 100644 --- a/drivers/video/fbdev/core/fbcon.c +++ b/drivers/video/fbdev/core/fbcon.c @@ -2497,9 +2497,12 @@ static int fbcon_set_font(struct vc_data *vc, struct console_font *font, h > FBCON_SWAP(info->var.rotate, info->var.yres, info->var.xres)) return -EINVAL; + if (font->width > 32 || font->height > 32) + return -EINVAL; + /* Make sure drawing engine can handle the font */ - if (!(info->pixmap.blit_x & (1 << (font->width - 1))) || - !(info->pixmap.blit_y & (1 << (font->height - 1)))) + if (!(info->pixmap.blit_x & BIT(font->width - 1)) || + !(info->pixmap.blit_y & BIT(font->height - 1))) return -EINVAL; /* Make sure driver can handle the font length */ diff --git a/drivers/video/fbdev/smscufx.c b/drivers/video/fbdev/smscufx.c index a5abdec58fe26..53fb34f074c74 100644 --- a/drivers/video/fbdev/smscufx.c +++ b/drivers/video/fbdev/smscufx.c @@ -1622,7 +1622,7 @@ static int ufx_usb_probe(struct usb_interface *interface, struct usb_device *usbdev; struct ufx_data *dev; struct fb_info *info; - int retval; + int retval = -ENOMEM; u32 id_rev, fpga_rev; /* usb initialization */ @@ -1654,15 +1654,17 @@ static int ufx_usb_probe(struct usb_interface *interface, if (!ufx_alloc_urb_list(dev, WRITES_IN_FLIGHT, MAX_TRANSFER)) { dev_err(dev->gdev, "ufx_alloc_urb_list failed\n"); - goto e_nomem; + goto put_ref; } /* We don't register a new USB class. Our client interface is fbdev */ /* allocates framebuffer driver structure, not framebuffer memory */ info = framebuffer_alloc(0, &usbdev->dev); - if (!info) - goto e_nomem; + if (!info) { + dev_err(dev->gdev, "framebuffer_alloc failed\n"); + goto free_urb_list; + } dev->info = info; info->par = dev; @@ -1705,22 +1707,34 @@ static int ufx_usb_probe(struct usb_interface *interface, check_warn_goto_error(retval, "unable to find common mode for display and adapter"); retval = ufx_reg_set_bits(dev, 0x4000, 0x00000001); - check_warn_goto_error(retval, "error %d enabling graphics engine", retval); + if (retval < 0) { + dev_err(dev->gdev, "error %d enabling graphics engine", retval); + goto setup_modes; + } /* ready to begin using device */ atomic_set(&dev->usb_active, 1); dev_dbg(dev->gdev, "checking var"); retval = ufx_ops_check_var(&info->var, info); - check_warn_goto_error(retval, "error %d ufx_ops_check_var", retval); + if (retval < 0) { + dev_err(dev->gdev, "error %d ufx_ops_check_var", retval); + goto reset_active; + } dev_dbg(dev->gdev, "setting par"); retval = ufx_ops_set_par(info); - check_warn_goto_error(retval, "error %d ufx_ops_set_par", retval); + if (retval < 0) { + dev_err(dev->gdev, "error %d ufx_ops_set_par", retval); + goto reset_active; + } dev_dbg(dev->gdev, "registering framebuffer"); retval = register_framebuffer(info); - check_warn_goto_error(retval, "error %d register_framebuffer", retval); + if (retval < 0) { + dev_err(dev->gdev, "error %d register_framebuffer", retval); + goto reset_active; + } dev_info(dev->gdev, "SMSC UDX USB device /dev/fb%d attached. %dx%d resolution." " Using %dK framebuffer memory\n", info->node, @@ -1728,21 +1742,23 @@ static int ufx_usb_probe(struct usb_interface *interface, return 0; -error: - fb_dealloc_cmap(&info->cmap); -destroy_modedb: +reset_active: + atomic_set(&dev->usb_active, 0); +setup_modes: fb_destroy_modedb(info->monspecs.modedb); vfree(info->screen_base); fb_destroy_modelist(&info->modelist); +error: + fb_dealloc_cmap(&info->cmap); +destroy_modedb: framebuffer_release(info); +free_urb_list: + if (dev->urbs.count > 0) + ufx_free_urb_list(dev); put_ref: kref_put(&dev->kref, ufx_free); /* ref for framebuffer */ kref_put(&dev->kref, ufx_free); /* last ref from kref_init */ return retval; - -e_nomem: - retval = -ENOMEM; - goto put_ref; } static void ufx_usb_disconnect(struct usb_interface *interface) diff --git a/drivers/watchdog/diag288_wdt.c b/drivers/watchdog/diag288_wdt.c index aafc8d98bf9fd..370f648cb4b1a 100644 --- a/drivers/watchdog/diag288_wdt.c +++ b/drivers/watchdog/diag288_wdt.c @@ -86,7 +86,7 @@ static int __diag288(unsigned int func, unsigned int timeout, "1:\n" EX_TABLE(0b, 1b) : "+d" (err) : "d"(__func), "d"(__timeout), - "d"(__action), "d"(__len) : "1", "cc"); + "d"(__action), "d"(__len) : "1", "cc", "memory"); return err; } @@ -272,12 +272,21 @@ static int __init diag288_init(void) char ebc_begin[] = { 194, 197, 199, 201, 213 }; + char *ebc_cmd; watchdog_set_nowayout(&wdt_dev, nowayout_info); if (MACHINE_IS_VM) { - if (__diag288_vm(WDT_FUNC_INIT, 15, - ebc_begin, sizeof(ebc_begin)) != 0) { + ebc_cmd = kmalloc(sizeof(ebc_begin), GFP_KERNEL); + if (!ebc_cmd) { + pr_err("The watchdog cannot be initialized\n"); + return -ENOMEM; + } + memcpy(ebc_cmd, ebc_begin, sizeof(ebc_begin)); + ret = __diag288_vm(WDT_FUNC_INIT, 15, + ebc_cmd, sizeof(ebc_begin)); + kfree(ebc_cmd); + if (ret != 0) { pr_err("The watchdog cannot be initialized\n"); return -EINVAL; } diff --git a/drivers/xen/pvcalls-back.c b/drivers/xen/pvcalls-back.c index 9439de2ca0e45..9c267e27d9d95 100644 --- a/drivers/xen/pvcalls-back.c +++ b/drivers/xen/pvcalls-back.c @@ -129,13 +129,13 @@ static bool pvcalls_conn_back_read(void *opaque) if (masked_prod < masked_cons) { vec[0].iov_base = data->in + masked_prod; vec[0].iov_len = wanted; - iov_iter_kvec(&msg.msg_iter, WRITE, vec, 1, wanted); + iov_iter_kvec(&msg.msg_iter, READ, vec, 1, wanted); } else { vec[0].iov_base = data->in + masked_prod; vec[0].iov_len = array_size - masked_prod; vec[1].iov_base = data->in; vec[1].iov_len = wanted - vec[0].iov_len; - iov_iter_kvec(&msg.msg_iter, WRITE, vec, 2, wanted); + iov_iter_kvec(&msg.msg_iter, READ, vec, 2, wanted); } atomic_set(&map->read, 0); @@ -188,13 +188,13 @@ static bool pvcalls_conn_back_write(struct sock_mapping *map) if (pvcalls_mask(prod, array_size) > pvcalls_mask(cons, array_size)) { vec[0].iov_base = data->out + pvcalls_mask(cons, array_size); vec[0].iov_len = size; - iov_iter_kvec(&msg.msg_iter, READ, vec, 1, size); + iov_iter_kvec(&msg.msg_iter, WRITE, vec, 1, size); } else { vec[0].iov_base = data->out + pvcalls_mask(cons, array_size); vec[0].iov_len = array_size - pvcalls_mask(cons, array_size); vec[1].iov_base = data->out; vec[1].iov_len = size - vec[0].iov_len; - iov_iter_kvec(&msg.msg_iter, READ, vec, 2, size); + iov_iter_kvec(&msg.msg_iter, WRITE, vec, 2, size); } atomic_set(&map->write, 0); diff --git a/fs/aio.c b/fs/aio.c index fb92c32a6f1e9..1ec5a773d09c5 100644 --- a/fs/aio.c +++ b/fs/aio.c @@ -336,6 +336,9 @@ static int aio_ring_mremap(struct vm_area_struct *vma) spin_lock(&mm->ioctx_lock); rcu_read_lock(); table = rcu_dereference(mm->ioctx_table); + if (!table) + goto out_unlock; + for (i = 0; i < table->nr; i++) { struct kioctx *ctx; @@ -349,6 +352,7 @@ static int aio_ring_mremap(struct vm_area_struct *vma) } } +out_unlock: rcu_read_unlock(); spin_unlock(&mm->ioctx_lock); return res; diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 548de841cee53..3fa972a43b5e1 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -354,6 +354,7 @@ void btrfs_free_device(struct btrfs_device *device) static void free_fs_devices(struct btrfs_fs_devices *fs_devices) { struct btrfs_device *device; + WARN_ON(fs_devices->opened); while (!list_empty(&fs_devices->devices)) { device = list_entry(fs_devices->devices.next, @@ -1401,6 +1402,17 @@ int btrfs_close_devices(struct btrfs_fs_devices *fs_devices) if (!fs_devices->opened) { seed_devices = fs_devices->seed; fs_devices->seed = NULL; + + /* + * If the struct btrfs_fs_devices is not assembled with any + * other device, it can be re-initialized during the next mount + * without the needing device-scan step. Therefore, it can be + * fully freed. + */ + if (fs_devices->num_devices == 1) { + list_del(&fs_devices->fs_list); + free_fs_devices(fs_devices); + } } mutex_unlock(&uuid_mutex); @@ -1701,7 +1713,7 @@ again: goto out; } - while (1) { + while (search_start < search_end) { l = path->nodes[0]; slot = path->slots[0]; if (slot >= btrfs_header_nritems(l)) { @@ -1724,6 +1736,9 @@ again: if (key.type != BTRFS_DEV_EXTENT_KEY) goto next; + if (key.offset > search_end) + break; + if (key.offset > search_start) { hole_size = key.offset - search_start; @@ -1794,6 +1809,7 @@ next: else ret = 0; + ASSERT(max_hole_start + max_hole_size <= search_end); out: btrfs_free_path(path); *start = max_hole_start; diff --git a/fs/btrfs/zlib.c b/fs/btrfs/zlib.c index df1aace5df501..9385d0bb276dd 100644 --- a/fs/btrfs/zlib.c +++ b/fs/btrfs/zlib.c @@ -74,7 +74,7 @@ static struct list_head *zlib_alloc_workspace(unsigned int level) workspacesize = max(zlib_deflate_workspacesize(MAX_WBITS, MAX_MEM_LEVEL), zlib_inflate_workspacesize()); - workspace->strm.workspace = kvmalloc(workspacesize, GFP_KERNEL); + workspace->strm.workspace = kvzalloc(workspacesize, GFP_KERNEL); workspace->level = level; workspace->buf = kmalloc(PAGE_SIZE, GFP_KERNEL); if (!workspace->strm.workspace || !workspace->buf) diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 37fb71797b341..3bf81fe5f10a3 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -3151,6 +3151,12 @@ static void handle_session(struct ceph_mds_session *session, break; case CEPH_SESSION_FLUSHMSG: + /* flush cap releases */ + spin_lock(&session->s_cap_lock); + if (session->s_num_cap_releases) + ceph_flush_cap_releases(mdsc, session); + spin_unlock(&session->s_cap_lock); + send_flushmsg_ack(mdsc, session, seq); break; diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index ef71d9cda5851..939be9df0207e 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -612,7 +612,7 @@ static bool is_alive(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, { struct page *node_page; nid_t nid; - unsigned int ofs_in_node, max_addrs; + unsigned int ofs_in_node, max_addrs, base; block_t source_blkaddr; nid = le32_to_cpu(sum->nid); @@ -638,11 +638,17 @@ static bool is_alive(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, return false; } - max_addrs = IS_INODE(node_page) ? DEF_ADDRS_PER_INODE : - DEF_ADDRS_PER_BLOCK; - if (ofs_in_node >= max_addrs) { - f2fs_err(sbi, "Inconsistent ofs_in_node:%u in summary, ino:%u, nid:%u, max:%u", - ofs_in_node, dni->ino, dni->nid, max_addrs); + if (IS_INODE(node_page)) { + base = offset_in_addr(F2FS_INODE(node_page)); + max_addrs = DEF_ADDRS_PER_INODE; + } else { + base = 0; + max_addrs = DEF_ADDRS_PER_BLOCK; + } + + if (base + ofs_in_node >= max_addrs) { + f2fs_err(sbi, "Inconsistent blkaddr offset: base:%u, ofs_in_node:%u, max:%u, ino:%u, nid:%u", + base, ofs_in_node, max_addrs, dni->ino, dni->nid); f2fs_put_page(node_page, 1); return false; } diff --git a/fs/nilfs2/ioctl.c b/fs/nilfs2/ioctl.c index 91b9dac6b2cc0..262783cd79cc3 100644 --- a/fs/nilfs2/ioctl.c +++ b/fs/nilfs2/ioctl.c @@ -1130,7 +1130,14 @@ static int nilfs_ioctl_set_alloc_range(struct inode *inode, void __user *argp) minseg = range[0] + segbytes - 1; do_div(minseg, segbytes); + + if (range[1] < 4096) + goto out; + maxseg = NILFS_SB2_OFFSET_BYTES(range[1]); + if (maxseg < segbytes) + goto out; + do_div(maxseg, segbytes); maxseg--; diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c index 049768a22388e..b1015e97f37b7 100644 --- a/fs/nilfs2/super.c +++ b/fs/nilfs2/super.c @@ -403,6 +403,15 @@ int nilfs_resize_fs(struct super_block *sb, __u64 newsize) if (newsize > devsize) goto out; + /* + * Prevent underflow in second superblock position calculation. + * The exact minimum size check is done in nilfs_sufile_resize(). + */ + if (newsize < 4096) { + ret = -ENOSPC; + goto out; + } + /* * Write lock is required to protect some functions depending * on the number of segments, the number of reserved segments, diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c index 74ef3d313686f..6541e29a8b200 100644 --- a/fs/nilfs2/the_nilfs.c +++ b/fs/nilfs2/the_nilfs.c @@ -517,9 +517,15 @@ static int nilfs_load_super_block(struct the_nilfs *nilfs, { struct nilfs_super_block **sbp = nilfs->ns_sbp; struct buffer_head **sbh = nilfs->ns_sbh; - u64 sb2off = NILFS_SB2_OFFSET_BYTES(nilfs->ns_bdev->bd_inode->i_size); + u64 sb2off, devsize = nilfs->ns_bdev->bd_inode->i_size; int valid[2], swp = 0; + if (devsize < NILFS_SEG_MIN_BLOCKS * NILFS_MIN_BLOCK_SIZE + 4096) { + nilfs_msg(sb, KERN_ERR, "device size too small"); + return -EINVAL; + } + sb2off = NILFS_SB2_OFFSET_BYTES(devsize); + sbp[0] = nilfs_read_super_block(sb, NILFS_SB_OFFSET_BYTES, blocksize, &sbh[0]); sbp[1] = nilfs_read_super_block(sb, sb2off, blocksize, &sbh[1]); diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index d9633e5a5ddd2..0bdfef023d345 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -723,9 +723,7 @@ static int smaps_hugetlb_range(pte_t *pte, unsigned long hmask, page = device_private_entry_to_page(swpent); } if (page) { - int mapcount = page_mapcount(page); - - if (mapcount >= 2) + if (page_mapcount(page) >= 2 || hugetlb_pmd_shared(pte)) mss->shared_hugetlb += huge_page_size(hstate_vma(vma)); else mss->private_hugetlb += huge_page_size(hstate_vma(vma)); diff --git a/fs/squashfs/squashfs_fs.h b/fs/squashfs/squashfs_fs.h index 236664d691419..ccfaf8c81958d 100644 --- a/fs/squashfs/squashfs_fs.h +++ b/fs/squashfs/squashfs_fs.h @@ -183,7 +183,7 @@ static inline int squashfs_block_size(__le32 raw) #define SQUASHFS_ID_BLOCK_BYTES(A) (SQUASHFS_ID_BLOCKS(A) *\ sizeof(u64)) /* xattr id lookup table defines */ -#define SQUASHFS_XATTR_BYTES(A) ((A) * sizeof(struct squashfs_xattr_id)) +#define SQUASHFS_XATTR_BYTES(A) (((u64) (A)) * sizeof(struct squashfs_xattr_id)) #define SQUASHFS_XATTR_BLOCK(A) (SQUASHFS_XATTR_BYTES(A) / \ SQUASHFS_METADATA_SIZE) diff --git a/fs/squashfs/squashfs_fs_sb.h b/fs/squashfs/squashfs_fs_sb.h index 166e98806265b..8f9445e290e72 100644 --- a/fs/squashfs/squashfs_fs_sb.h +++ b/fs/squashfs/squashfs_fs_sb.h @@ -63,7 +63,7 @@ struct squashfs_sb_info { long long bytes_used; unsigned int inodes; unsigned int fragments; - int xattr_ids; + unsigned int xattr_ids; unsigned int ids; }; #endif diff --git a/fs/squashfs/xattr.h b/fs/squashfs/xattr.h index d8a270d3ac4cb..f1a463d8bfa02 100644 --- a/fs/squashfs/xattr.h +++ b/fs/squashfs/xattr.h @@ -10,12 +10,12 @@ #ifdef CONFIG_SQUASHFS_XATTR extern __le64 *squashfs_read_xattr_id_table(struct super_block *, u64, - u64 *, int *); + u64 *, unsigned int *); extern int squashfs_xattr_lookup(struct super_block *, unsigned int, int *, unsigned int *, unsigned long long *); #else static inline __le64 *squashfs_read_xattr_id_table(struct super_block *sb, - u64 start, u64 *xattr_table_start, int *xattr_ids) + u64 start, u64 *xattr_table_start, unsigned int *xattr_ids) { struct squashfs_xattr_id_table *id_table; diff --git a/fs/squashfs/xattr_id.c b/fs/squashfs/xattr_id.c index 087cab8c78f4e..c8469c656e0dc 100644 --- a/fs/squashfs/xattr_id.c +++ b/fs/squashfs/xattr_id.c @@ -56,7 +56,7 @@ int squashfs_xattr_lookup(struct super_block *sb, unsigned int index, * Read uncompressed xattr id lookup table indexes from disk into memory */ __le64 *squashfs_read_xattr_id_table(struct super_block *sb, u64 table_start, - u64 *xattr_table_start, int *xattr_ids) + u64 *xattr_table_start, unsigned int *xattr_ids) { struct squashfs_sb_info *msblk = sb->s_fs_info; unsigned int len, indexes; diff --git a/fs/xfs/libxfs/xfs_defer.c b/fs/xfs/libxfs/xfs_defer.c index 8cc3faa624049..3a78a189ea018 100644 --- a/fs/xfs/libxfs/xfs_defer.c +++ b/fs/xfs/libxfs/xfs_defer.c @@ -16,6 +16,8 @@ #include "xfs_inode.h" #include "xfs_inode_item.h" #include "xfs_trace.h" +#include "xfs_icache.h" +#include "xfs_log.h" /* * Deferred Operations in XFS @@ -178,6 +180,19 @@ static const struct xfs_defer_op_type *defer_op_types[] = { [XFS_DEFER_OPS_TYPE_AGFL_FREE] = &xfs_agfl_free_defer_type, }; +static void +xfs_defer_create_intent( + struct xfs_trans *tp, + struct xfs_defer_pending *dfp, + bool sort) +{ + const struct xfs_defer_op_type *ops = defer_op_types[dfp->dfp_type]; + + if (!dfp->dfp_intent) + dfp->dfp_intent = ops->create_intent(tp, &dfp->dfp_work, + dfp->dfp_count, sort); +} + /* * For each pending item in the intake list, log its intent item and the * associated extents, then add the entire intake list to the end of @@ -187,17 +202,11 @@ STATIC void xfs_defer_create_intents( struct xfs_trans *tp) { - struct list_head *li; struct xfs_defer_pending *dfp; - const struct xfs_defer_op_type *ops; list_for_each_entry(dfp, &tp->t_dfops, dfp_list) { - ops = defer_op_types[dfp->dfp_type]; - dfp->dfp_intent = ops->create_intent(tp, dfp->dfp_count); trace_xfs_defer_create_intent(tp->t_mountp, dfp); - list_sort(tp->t_mountp, &dfp->dfp_work, ops->diff_items); - list_for_each(li, &dfp->dfp_work) - ops->log_item(tp, dfp->dfp_intent, li); + xfs_defer_create_intent(tp, dfp, true); } } @@ -353,6 +362,106 @@ xfs_defer_cancel_list( } } +/* + * Prevent a log intent item from pinning the tail of the log by logging a + * done item to release the intent item; and then log a new intent item. + * The caller should provide a fresh transaction and roll it after we're done. + */ +static int +xfs_defer_relog( + struct xfs_trans **tpp, + struct list_head *dfops) +{ + struct xlog *log = (*tpp)->t_mountp->m_log; + struct xfs_defer_pending *dfp; + xfs_lsn_t threshold_lsn = NULLCOMMITLSN; + + + ASSERT((*tpp)->t_flags & XFS_TRANS_PERM_LOG_RES); + + list_for_each_entry(dfp, dfops, dfp_list) { + /* + * If the log intent item for this deferred op is not a part of + * the current log checkpoint, relog the intent item to keep + * the log tail moving forward. We're ok with this being racy + * because an incorrect decision means we'll be a little slower + * at pushing the tail. + */ + if (dfp->dfp_intent == NULL || + xfs_log_item_in_current_chkpt(dfp->dfp_intent)) + continue; + + /* + * Figure out where we need the tail to be in order to maintain + * the minimum required free space in the log. Only sample + * the log threshold once per call. + */ + if (threshold_lsn == NULLCOMMITLSN) { + threshold_lsn = xlog_grant_push_threshold(log, 0); + if (threshold_lsn == NULLCOMMITLSN) + break; + } + if (XFS_LSN_CMP(dfp->dfp_intent->li_lsn, threshold_lsn) >= 0) + continue; + + trace_xfs_defer_relog_intent((*tpp)->t_mountp, dfp); + XFS_STATS_INC((*tpp)->t_mountp, defer_relog); + dfp->dfp_intent = xfs_trans_item_relog(dfp->dfp_intent, *tpp); + } + + if ((*tpp)->t_flags & XFS_TRANS_DIRTY) + return xfs_defer_trans_roll(tpp); + return 0; +} + +/* + * Log an intent-done item for the first pending intent, and finish the work + * items. + */ +static int +xfs_defer_finish_one( + struct xfs_trans *tp, + struct xfs_defer_pending *dfp) +{ + const struct xfs_defer_op_type *ops = defer_op_types[dfp->dfp_type]; + void *state = NULL; + struct list_head *li, *n; + int error; + + trace_xfs_defer_pending_finish(tp->t_mountp, dfp); + + dfp->dfp_done = ops->create_done(tp, dfp->dfp_intent, dfp->dfp_count); + list_for_each_safe(li, n, &dfp->dfp_work) { + list_del(li); + dfp->dfp_count--; + error = ops->finish_item(tp, li, dfp->dfp_done, &state); + if (error == -EAGAIN) { + /* + * Caller wants a fresh transaction; put the work item + * back on the list and log a new log intent item to + * replace the old one. See "Requesting a Fresh + * Transaction while Finishing Deferred Work" above. + */ + list_add(li, &dfp->dfp_work); + dfp->dfp_count++; + dfp->dfp_done = NULL; + dfp->dfp_intent = NULL; + xfs_defer_create_intent(tp, dfp, false); + } + + if (error) + goto out; + } + + /* Done with the dfp, free it. */ + list_del(&dfp->dfp_list); + kmem_free(dfp); +out: + if (ops->finish_cleanup) + ops->finish_cleanup(tp, state, error); + return error; +} + /* * Finish all the pending work. This involves logging intent items for * any work items that wandered in since the last transaction roll (if @@ -366,11 +475,7 @@ xfs_defer_finish_noroll( struct xfs_trans **tp) { struct xfs_defer_pending *dfp; - struct list_head *li; - struct list_head *n; - void *state; int error = 0; - const struct xfs_defer_op_type *ops; LIST_HEAD(dop_pending); ASSERT((*tp)->t_flags & XFS_TRANS_PERM_LOG_RES); @@ -379,87 +484,44 @@ xfs_defer_finish_noroll( /* Until we run out of pending work to finish... */ while (!list_empty(&dop_pending) || !list_empty(&(*tp)->t_dfops)) { - /* log intents and pull in intake items */ - xfs_defer_create_intents(*tp); - list_splice_tail_init(&(*tp)->t_dfops, &dop_pending); - /* - * Roll the transaction. + * Deferred items that are created in the process of finishing + * other deferred work items should be queued at the head of + * the pending list, which puts them ahead of the deferred work + * that was created by the caller. This keeps the number of + * pending work items to a minimum, which decreases the amount + * of time that any one intent item can stick around in memory, + * pinning the log tail. */ + xfs_defer_create_intents(*tp); + list_splice_init(&(*tp)->t_dfops, &dop_pending); + error = xfs_defer_trans_roll(tp); if (error) - goto out; + goto out_shutdown; + + /* Possibly relog intent items to keep the log moving. */ + error = xfs_defer_relog(tp, &dop_pending); + if (error) + goto out_shutdown; - /* Log an intent-done item for the first pending item. */ dfp = list_first_entry(&dop_pending, struct xfs_defer_pending, dfp_list); - ops = defer_op_types[dfp->dfp_type]; - trace_xfs_defer_pending_finish((*tp)->t_mountp, dfp); - dfp->dfp_done = ops->create_done(*tp, dfp->dfp_intent, - dfp->dfp_count); - - /* Finish the work items. */ - state = NULL; - list_for_each_safe(li, n, &dfp->dfp_work) { - list_del(li); - dfp->dfp_count--; - error = ops->finish_item(*tp, li, dfp->dfp_done, - &state); - if (error == -EAGAIN) { - /* - * Caller wants a fresh transaction; - * put the work item back on the list - * and jump out. - */ - list_add(li, &dfp->dfp_work); - dfp->dfp_count++; - break; - } else if (error) { - /* - * Clean up after ourselves and jump out. - * xfs_defer_cancel will take care of freeing - * all these lists and stuff. - */ - if (ops->finish_cleanup) - ops->finish_cleanup(*tp, state, error); - goto out; - } - } - if (error == -EAGAIN) { - /* - * Caller wants a fresh transaction, so log a - * new log intent item to replace the old one - * and roll the transaction. See "Requesting - * a Fresh Transaction while Finishing - * Deferred Work" above. - */ - dfp->dfp_intent = ops->create_intent(*tp, - dfp->dfp_count); - dfp->dfp_done = NULL; - list_for_each(li, &dfp->dfp_work) - ops->log_item(*tp, dfp->dfp_intent, li); - } else { - /* Done with the dfp, free it. */ - list_del(&dfp->dfp_list); - kmem_free(dfp); - } - - if (ops->finish_cleanup) - ops->finish_cleanup(*tp, state, error); - } - -out: - if (error) { - xfs_defer_trans_abort(*tp, &dop_pending); - xfs_force_shutdown((*tp)->t_mountp, SHUTDOWN_CORRUPT_INCORE); - trace_xfs_defer_finish_error(*tp, error); - xfs_defer_cancel_list((*tp)->t_mountp, &dop_pending); - xfs_defer_cancel(*tp); - return error; + error = xfs_defer_finish_one(*tp, dfp); + if (error && error != -EAGAIN) + goto out_shutdown; } trace_xfs_defer_finish_done(*tp, _RET_IP_); return 0; + +out_shutdown: + xfs_defer_trans_abort(*tp, &dop_pending); + xfs_force_shutdown((*tp)->t_mountp, SHUTDOWN_CORRUPT_INCORE); + trace_xfs_defer_finish_error(*tp, error); + xfs_defer_cancel_list((*tp)->t_mountp, &dop_pending); + xfs_defer_cancel(*tp); + return error; } int @@ -560,3 +622,137 @@ xfs_defer_move( xfs_defer_reset(stp); } + +/* + * Prepare a chain of fresh deferred ops work items to be completed later. Log + * recovery requires the ability to put off until later the actual finishing + * work so that it can process unfinished items recovered from the log in + * correct order. + * + * Create and log intent items for all the work that we're capturing so that we + * can be assured that the items will get replayed if the system goes down + * before log recovery gets a chance to finish the work it put off. The entire + * deferred ops state is transferred to the capture structure and the + * transaction is then ready for the caller to commit it. If there are no + * intent items to capture, this function returns NULL. + * + * If capture_ip is not NULL, the capture structure will obtain an extra + * reference to the inode. + */ +static struct xfs_defer_capture * +xfs_defer_ops_capture( + struct xfs_trans *tp, + struct xfs_inode *capture_ip) +{ + struct xfs_defer_capture *dfc; + + if (list_empty(&tp->t_dfops)) + return NULL; + + /* Create an object to capture the defer ops. */ + dfc = kmem_zalloc(sizeof(*dfc), KM_NOFS); + INIT_LIST_HEAD(&dfc->dfc_list); + INIT_LIST_HEAD(&dfc->dfc_dfops); + + xfs_defer_create_intents(tp); + + /* Move the dfops chain and transaction state to the capture struct. */ + list_splice_init(&tp->t_dfops, &dfc->dfc_dfops); + dfc->dfc_tpflags = tp->t_flags & XFS_TRANS_LOWMODE; + tp->t_flags &= ~XFS_TRANS_LOWMODE; + + /* Capture the remaining block reservations along with the dfops. */ + dfc->dfc_blkres = tp->t_blk_res - tp->t_blk_res_used; + dfc->dfc_rtxres = tp->t_rtx_res - tp->t_rtx_res_used; + + /* Preserve the log reservation size. */ + dfc->dfc_logres = tp->t_log_res; + + /* + * Grab an extra reference to this inode and attach it to the capture + * structure. + */ + if (capture_ip) { + ihold(VFS_I(capture_ip)); + dfc->dfc_capture_ip = capture_ip; + } + + return dfc; +} + +/* Release all resources that we used to capture deferred ops. */ +void +xfs_defer_ops_release( + struct xfs_mount *mp, + struct xfs_defer_capture *dfc) +{ + xfs_defer_cancel_list(mp, &dfc->dfc_dfops); + if (dfc->dfc_capture_ip) + xfs_irele(dfc->dfc_capture_ip); + kmem_free(dfc); +} + +/* + * Capture any deferred ops and commit the transaction. This is the last step + * needed to finish a log intent item that we recovered from the log. If any + * of the deferred ops operate on an inode, the caller must pass in that inode + * so that the reference can be transferred to the capture structure. The + * caller must hold ILOCK_EXCL on the inode, and must unlock it before calling + * xfs_defer_ops_continue. + */ +int +xfs_defer_ops_capture_and_commit( + struct xfs_trans *tp, + struct xfs_inode *capture_ip, + struct list_head *capture_list) +{ + struct xfs_mount *mp = tp->t_mountp; + struct xfs_defer_capture *dfc; + int error; + + ASSERT(!capture_ip || xfs_isilocked(capture_ip, XFS_ILOCK_EXCL)); + + /* If we don't capture anything, commit transaction and exit. */ + dfc = xfs_defer_ops_capture(tp, capture_ip); + if (!dfc) + return xfs_trans_commit(tp); + + /* Commit the transaction and add the capture structure to the list. */ + error = xfs_trans_commit(tp); + if (error) { + xfs_defer_ops_release(mp, dfc); + return error; + } + + list_add_tail(&dfc->dfc_list, capture_list); + return 0; +} + +/* + * Attach a chain of captured deferred ops to a new transaction and free the + * capture structure. If an inode was captured, it will be passed back to the + * caller with ILOCK_EXCL held and joined to the transaction with lockflags==0. + * The caller now owns the inode reference. + */ +void +xfs_defer_ops_continue( + struct xfs_defer_capture *dfc, + struct xfs_trans *tp, + struct xfs_inode **captured_ipp) +{ + ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES); + ASSERT(!(tp->t_flags & XFS_TRANS_DIRTY)); + + /* Lock and join the captured inode to the new transaction. */ + if (dfc->dfc_capture_ip) { + xfs_ilock(dfc->dfc_capture_ip, XFS_ILOCK_EXCL); + xfs_trans_ijoin(tp, dfc->dfc_capture_ip, 0); + } + *captured_ipp = dfc->dfc_capture_ip; + + /* Move captured dfops chain and state to the transaction. */ + list_splice_init(&dfc->dfc_dfops, &tp->t_dfops); + tp->t_flags |= dfc->dfc_tpflags; + + kmem_free(dfc); +} diff --git a/fs/xfs/libxfs/xfs_defer.h b/fs/xfs/libxfs/xfs_defer.h index 7c28d7608ac62..4c3248d47a350 100644 --- a/fs/xfs/libxfs/xfs_defer.h +++ b/fs/xfs/libxfs/xfs_defer.h @@ -7,6 +7,7 @@ #define __XFS_DEFER_H__ struct xfs_defer_op_type; +struct xfs_defer_capture; /* * Header for deferred operation list. @@ -28,7 +29,7 @@ enum xfs_defer_ops_type { struct xfs_defer_pending { struct list_head dfp_list; /* pending items */ struct list_head dfp_work; /* work items */ - void *dfp_intent; /* log intent item */ + struct xfs_log_item *dfp_intent; /* log intent item */ void *dfp_done; /* log done item */ unsigned int dfp_count; /* # extent items */ enum xfs_defer_ops_type dfp_type; @@ -43,15 +44,15 @@ void xfs_defer_move(struct xfs_trans *dtp, struct xfs_trans *stp); /* Description of a deferred type. */ struct xfs_defer_op_type { - void (*abort_intent)(void *); - void *(*create_done)(struct xfs_trans *, void *, unsigned int); + struct xfs_log_item *(*create_intent)(struct xfs_trans *tp, + struct list_head *items, unsigned int count, bool sort); + void (*abort_intent)(struct xfs_log_item *intent); + void *(*create_done)(struct xfs_trans *tp, struct xfs_log_item *intent, + unsigned int count); int (*finish_item)(struct xfs_trans *, struct list_head *, void *, void **); void (*finish_cleanup)(struct xfs_trans *, void *, int); void (*cancel_item)(struct list_head *); - int (*diff_items)(void *, struct list_head *, struct list_head *); - void *(*create_intent)(struct xfs_trans *, uint); - void (*log_item)(struct xfs_trans *, void *, struct list_head *); unsigned int max_items; }; @@ -61,4 +62,40 @@ extern const struct xfs_defer_op_type xfs_rmap_update_defer_type; extern const struct xfs_defer_op_type xfs_extent_free_defer_type; extern const struct xfs_defer_op_type xfs_agfl_free_defer_type; +/* + * This structure enables a dfops user to detach the chain of deferred + * operations from a transaction so that they can be continued later. + */ +struct xfs_defer_capture { + /* List of other capture structures. */ + struct list_head dfc_list; + + /* Deferred ops state saved from the transaction. */ + struct list_head dfc_dfops; + unsigned int dfc_tpflags; + + /* Block reservations for the data and rt devices. */ + unsigned int dfc_blkres; + unsigned int dfc_rtxres; + + /* Log reservation saved from the transaction. */ + unsigned int dfc_logres; + + /* + * An inode reference that must be maintained to complete the deferred + * work. + */ + struct xfs_inode *dfc_capture_ip; +}; + +/* + * Functions to capture a chain of deferred operations and continue them later. + * This doesn't normally happen except log recovery. + */ +int xfs_defer_ops_capture_and_commit(struct xfs_trans *tp, + struct xfs_inode *capture_ip, struct list_head *capture_list); +void xfs_defer_ops_continue(struct xfs_defer_capture *d, struct xfs_trans *tp, + struct xfs_inode **captured_ipp); +void xfs_defer_ops_release(struct xfs_mount *mp, struct xfs_defer_capture *d); + #endif /* __XFS_DEFER_H__ */ diff --git a/fs/xfs/libxfs/xfs_inode_fork.c b/fs/xfs/libxfs/xfs_inode_fork.c index 15d6f947620ff..93357072b19da 100644 --- a/fs/xfs/libxfs/xfs_inode_fork.c +++ b/fs/xfs/libxfs/xfs_inode_fork.c @@ -592,7 +592,7 @@ void xfs_iflush_fork( xfs_inode_t *ip, xfs_dinode_t *dip, - xfs_inode_log_item_t *iip, + struct xfs_inode_log_item *iip, int whichfork) { char *cp; diff --git a/fs/xfs/libxfs/xfs_trans_inode.c b/fs/xfs/libxfs/xfs_trans_inode.c index 0ba7368b9a5f0..1d0e78e0099d9 100644 --- a/fs/xfs/libxfs/xfs_trans_inode.c +++ b/fs/xfs/libxfs/xfs_trans_inode.c @@ -27,7 +27,7 @@ xfs_trans_ijoin( struct xfs_inode *ip, uint lock_flags) { - xfs_inode_log_item_t *iip; + struct xfs_inode_log_item *iip; ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL)); if (ip->i_itemp == NULL) diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index f16d5f196c6b1..5d9f8e4c4cdee 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -495,7 +495,7 @@ xfs_map_blocks( ssize_t count = i_blocksize(inode); xfs_fileoff_t offset_fsb = XFS_B_TO_FSBT(mp, offset); xfs_fileoff_t end_fsb = XFS_B_TO_FSB(mp, offset + count); - xfs_fileoff_t cow_fsb = NULLFILEOFF; + xfs_fileoff_t cow_fsb; struct xfs_bmbt_irec imap; struct xfs_iext_cursor icur; int retries = 0; @@ -529,6 +529,8 @@ xfs_map_blocks( * landed in a hole and we skip the block. */ retry: + cow_fsb = NULLFILEOFF; + wpc->fork = XFS_DATA_FORK; xfs_ilock(ip, XFS_ILOCK_SHARED); ASSERT(ip->i_d.di_format != XFS_DINODE_FMT_BTREE || (ip->i_df.if_flags & XFS_IFEXTENTS)); diff --git a/fs/xfs/xfs_bmap_item.c b/fs/xfs/xfs_bmap_item.c index 243e5e0f82a30..7b0c4d9679d96 100644 --- a/fs/xfs/xfs_bmap_item.c +++ b/fs/xfs/xfs_bmap_item.c @@ -22,6 +22,7 @@ #include "xfs_bmap_btree.h" #include "xfs_trans_space.h" #include "xfs_error.h" +#include "xfs_quota.h" kmem_zone_t *xfs_bui_zone; kmem_zone_t *xfs_bud_zone; @@ -124,34 +125,6 @@ xfs_bui_item_release( xfs_bui_release(BUI_ITEM(lip)); } -static const struct xfs_item_ops xfs_bui_item_ops = { - .iop_size = xfs_bui_item_size, - .iop_format = xfs_bui_item_format, - .iop_unpin = xfs_bui_item_unpin, - .iop_release = xfs_bui_item_release, -}; - -/* - * Allocate and initialize an bui item with the given number of extents. - */ -struct xfs_bui_log_item * -xfs_bui_init( - struct xfs_mount *mp) - -{ - struct xfs_bui_log_item *buip; - - buip = kmem_zone_zalloc(xfs_bui_zone, 0); - - xfs_log_item_init(mp, &buip->bui_item, XFS_LI_BUI, &xfs_bui_item_ops); - buip->bui_format.bui_nextents = XFS_BUI_MAX_FAST_EXTENTS; - buip->bui_format.bui_id = (uintptr_t)(void *)buip; - atomic_set(&buip->bui_next_extent, 0); - atomic_set(&buip->bui_refcount, 2); - - return buip; -} - static inline struct xfs_bud_log_item *BUD_ITEM(struct xfs_log_item *lip) { return container_of(lip, struct xfs_bud_log_item, bud_item); @@ -278,27 +251,6 @@ xfs_bmap_update_diff_items( return ba->bi_owner->i_ino - bb->bi_owner->i_ino; } -/* Get an BUI. */ -STATIC void * -xfs_bmap_update_create_intent( - struct xfs_trans *tp, - unsigned int count) -{ - struct xfs_bui_log_item *buip; - - ASSERT(count == XFS_BUI_MAX_FAST_EXTENTS); - ASSERT(tp != NULL); - - buip = xfs_bui_init(tp->t_mountp); - ASSERT(buip != NULL); - - /* - * Get a log_item_desc to point at the new item. - */ - xfs_trans_add_item(tp, &buip->bui_item); - return buip; -} - /* Set the map extent flags for this mapping. */ static void xfs_trans_set_bmap_flags( @@ -326,16 +278,12 @@ xfs_trans_set_bmap_flags( STATIC void xfs_bmap_update_log_item( struct xfs_trans *tp, - void *intent, - struct list_head *item) + struct xfs_bui_log_item *buip, + struct xfs_bmap_intent *bmap) { - struct xfs_bui_log_item *buip = intent; - struct xfs_bmap_intent *bmap; uint next_extent; struct xfs_map_extent *map; - bmap = container_of(item, struct xfs_bmap_intent, bi_list); - tp->t_flags |= XFS_TRANS_DIRTY; set_bit(XFS_LI_DIRTY, &buip->bui_item.li_flags); @@ -355,14 +303,35 @@ xfs_bmap_update_log_item( bmap->bi_bmap.br_state); } +static struct xfs_log_item * +xfs_bmap_update_create_intent( + struct xfs_trans *tp, + struct list_head *items, + unsigned int count, + bool sort) +{ + struct xfs_mount *mp = tp->t_mountp; + struct xfs_bui_log_item *buip = xfs_bui_init(mp); + struct xfs_bmap_intent *bmap; + + ASSERT(count == XFS_BUI_MAX_FAST_EXTENTS); + + xfs_trans_add_item(tp, &buip->bui_item); + if (sort) + list_sort(mp, items, xfs_bmap_update_diff_items); + list_for_each_entry(bmap, items, bi_list) + xfs_bmap_update_log_item(tp, buip, bmap); + return &buip->bui_item; +} + /* Get an BUD so we can process all the deferred rmap updates. */ STATIC void * xfs_bmap_update_create_done( struct xfs_trans *tp, - void *intent, + struct xfs_log_item *intent, unsigned int count) { - return xfs_trans_get_bud(tp, intent); + return xfs_trans_get_bud(tp, BUI_ITEM(intent)); } /* Process a deferred rmap update. */ @@ -398,9 +367,9 @@ xfs_bmap_update_finish_item( /* Abort all pending BUIs. */ STATIC void xfs_bmap_update_abort_intent( - void *intent) + struct xfs_log_item *intent) { - xfs_bui_release(intent); + xfs_bui_release(BUI_ITEM(intent)); } /* Cancel a deferred rmap update. */ @@ -416,10 +385,8 @@ xfs_bmap_update_cancel_item( const struct xfs_defer_op_type xfs_bmap_update_defer_type = { .max_items = XFS_BUI_MAX_FAST_EXTENTS, - .diff_items = xfs_bmap_update_diff_items, .create_intent = xfs_bmap_update_create_intent, .abort_intent = xfs_bmap_update_abort_intent, - .log_item = xfs_bmap_update_log_item, .create_done = xfs_bmap_update_create_done, .finish_item = xfs_bmap_update_finish_item, .cancel_item = xfs_bmap_update_cancel_item, @@ -431,8 +398,8 @@ const struct xfs_defer_op_type xfs_bmap_update_defer_type = { */ int xfs_bui_recover( - struct xfs_trans *parent_tp, - struct xfs_bui_log_item *buip) + struct xfs_bui_log_item *buip, + struct list_head *capture_list) { int error = 0; unsigned int bui_type; @@ -440,15 +407,13 @@ xfs_bui_recover( xfs_fsblock_t startblock_fsb; xfs_fsblock_t inode_fsb; xfs_filblks_t count; - bool op_ok; struct xfs_bud_log_item *budp; - enum xfs_bmap_intent_type type; int whichfork; xfs_exntst_t state; struct xfs_trans *tp; struct xfs_inode *ip = NULL; struct xfs_bmbt_irec irec; - struct xfs_mount *mp = parent_tp->t_mountp; + struct xfs_mount *mp = buip->bui_item.li_mountp; ASSERT(!test_bit(XFS_BUI_RECOVERED, &buip->bui_flags)); @@ -468,16 +433,19 @@ xfs_bui_recover( XFS_FSB_TO_DADDR(mp, bmap->me_startblock)); inode_fsb = XFS_BB_TO_FSB(mp, XFS_FSB_TO_DADDR(mp, XFS_INO_TO_FSB(mp, bmap->me_owner))); - switch (bmap->me_flags & XFS_BMAP_EXTENT_TYPE_MASK) { + state = (bmap->me_flags & XFS_BMAP_EXTENT_UNWRITTEN) ? + XFS_EXT_UNWRITTEN : XFS_EXT_NORM; + whichfork = (bmap->me_flags & XFS_BMAP_EXTENT_ATTR_FORK) ? + XFS_ATTR_FORK : XFS_DATA_FORK; + bui_type = bmap->me_flags & XFS_BMAP_EXTENT_TYPE_MASK; + switch (bui_type) { case XFS_BMAP_MAP: case XFS_BMAP_UNMAP: - op_ok = true; break; default: - op_ok = false; - break; + return -EFSCORRUPTED; } - if (!op_ok || startblock_fsb == 0 || + if (startblock_fsb == 0 || bmap->me_len == 0 || inode_fsb == 0 || startblock_fsb >= mp->m_sb.sb_dblocks || @@ -493,52 +461,37 @@ xfs_bui_recover( return -EFSCORRUPTED; } - error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, - XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK), 0, 0, &tp); + /* Grab the inode. */ + error = xfs_iget(mp, NULL, bmap->me_owner, 0, 0, &ip); if (error) return error; - /* - * Recovery stashes all deferred ops during intent processing and - * finishes them on completion. Transfer current dfops state to this - * transaction and transfer the result back before we return. - */ - xfs_defer_move(tp, parent_tp); - budp = xfs_trans_get_bud(tp, buip); - /* Grab the inode. */ - error = xfs_iget(mp, tp, bmap->me_owner, 0, XFS_ILOCK_EXCL, &ip); + error = xfs_qm_dqattach(ip); if (error) - goto err_inode; + goto err_rele; if (VFS_I(ip)->i_nlink == 0) xfs_iflags_set(ip, XFS_IRECOVERY); - /* Process deferred bmap item. */ - state = (bmap->me_flags & XFS_BMAP_EXTENT_UNWRITTEN) ? - XFS_EXT_UNWRITTEN : XFS_EXT_NORM; - whichfork = (bmap->me_flags & XFS_BMAP_EXTENT_ATTR_FORK) ? - XFS_ATTR_FORK : XFS_DATA_FORK; - bui_type = bmap->me_flags & XFS_BMAP_EXTENT_TYPE_MASK; - switch (bui_type) { - case XFS_BMAP_MAP: - case XFS_BMAP_UNMAP: - type = bui_type; - break; - default: - XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, mp); - error = -EFSCORRUPTED; - goto err_inode; - } + /* Allocate transaction and do the work. */ + error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, + XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK), 0, 0, &tp); + if (error) + goto err_rele; + + budp = xfs_trans_get_bud(tp, buip); + xfs_ilock(ip, XFS_ILOCK_EXCL); xfs_trans_ijoin(tp, ip, 0); count = bmap->me_len; - error = xfs_trans_log_finish_bmap_update(tp, budp, type, ip, whichfork, - bmap->me_startoff, bmap->me_startblock, &count, state); + error = xfs_trans_log_finish_bmap_update(tp, budp, bui_type, ip, + whichfork, bmap->me_startoff, bmap->me_startblock, + &count, state); if (error) - goto err_inode; + goto err_cancel; if (count > 0) { - ASSERT(type == XFS_BMAP_UNMAP); + ASSERT(bui_type == XFS_BMAP_UNMAP); irec.br_startblock = bmap->me_startblock; irec.br_blockcount = count; irec.br_startoff = bmap->me_startoff; @@ -547,19 +500,78 @@ xfs_bui_recover( } set_bit(XFS_BUI_RECOVERED, &buip->bui_flags); - xfs_defer_move(parent_tp, tp); - error = xfs_trans_commit(tp); + /* + * Commit transaction, which frees the transaction and saves the inode + * for later replay activities. + */ + error = xfs_defer_ops_capture_and_commit(tp, ip, capture_list); + if (error) + goto err_unlock; + xfs_iunlock(ip, XFS_ILOCK_EXCL); xfs_irele(ip); + return 0; - return error; - -err_inode: - xfs_defer_move(parent_tp, tp); +err_cancel: xfs_trans_cancel(tp); - if (ip) { - xfs_iunlock(ip, XFS_ILOCK_EXCL); - xfs_irele(ip); - } +err_unlock: + xfs_iunlock(ip, XFS_ILOCK_EXCL); +err_rele: + xfs_irele(ip); return error; } + +/* Relog an intent item to push the log tail forward. */ +static struct xfs_log_item * +xfs_bui_item_relog( + struct xfs_log_item *intent, + struct xfs_trans *tp) +{ + struct xfs_bud_log_item *budp; + struct xfs_bui_log_item *buip; + struct xfs_map_extent *extp; + unsigned int count; + + count = BUI_ITEM(intent)->bui_format.bui_nextents; + extp = BUI_ITEM(intent)->bui_format.bui_extents; + + tp->t_flags |= XFS_TRANS_DIRTY; + budp = xfs_trans_get_bud(tp, BUI_ITEM(intent)); + set_bit(XFS_LI_DIRTY, &budp->bud_item.li_flags); + + buip = xfs_bui_init(tp->t_mountp); + memcpy(buip->bui_format.bui_extents, extp, count * sizeof(*extp)); + atomic_set(&buip->bui_next_extent, count); + xfs_trans_add_item(tp, &buip->bui_item); + set_bit(XFS_LI_DIRTY, &buip->bui_item.li_flags); + return &buip->bui_item; +} + +static const struct xfs_item_ops xfs_bui_item_ops = { + .iop_size = xfs_bui_item_size, + .iop_format = xfs_bui_item_format, + .iop_unpin = xfs_bui_item_unpin, + .iop_release = xfs_bui_item_release, + .iop_relog = xfs_bui_item_relog, +}; + +/* + * Allocate and initialize an bui item with the given number of extents. + */ +struct xfs_bui_log_item * +xfs_bui_init( + struct xfs_mount *mp) + +{ + struct xfs_bui_log_item *buip; + + buip = kmem_zone_zalloc(xfs_bui_zone, 0); + + xfs_log_item_init(mp, &buip->bui_item, XFS_LI_BUI, &xfs_bui_item_ops); + buip->bui_format.bui_nextents = XFS_BUI_MAX_FAST_EXTENTS; + buip->bui_format.bui_id = (uintptr_t)(void *)buip; + atomic_set(&buip->bui_next_extent, 0); + atomic_set(&buip->bui_refcount, 2); + + return buip; +} diff --git a/fs/xfs/xfs_bmap_item.h b/fs/xfs/xfs_bmap_item.h index ad479cc73de84..a95e99c269790 100644 --- a/fs/xfs/xfs_bmap_item.h +++ b/fs/xfs/xfs_bmap_item.h @@ -77,6 +77,7 @@ extern struct kmem_zone *xfs_bud_zone; struct xfs_bui_log_item *xfs_bui_init(struct xfs_mount *); void xfs_bui_item_free(struct xfs_bui_log_item *); void xfs_bui_release(struct xfs_bui_log_item *); -int xfs_bui_recover(struct xfs_trans *parent_tp, struct xfs_bui_log_item *buip); +int xfs_bui_recover(struct xfs_bui_log_item *buip, + struct list_head *capture_list); #endif /* __XFS_BMAP_ITEM_H__ */ diff --git a/fs/xfs/xfs_extfree_item.c b/fs/xfs/xfs_extfree_item.c index a05a1074e8f81..de3cdce892fda 100644 --- a/fs/xfs/xfs_extfree_item.c +++ b/fs/xfs/xfs_extfree_item.c @@ -139,44 +139,6 @@ xfs_efi_item_release( xfs_efi_release(EFI_ITEM(lip)); } -static const struct xfs_item_ops xfs_efi_item_ops = { - .iop_size = xfs_efi_item_size, - .iop_format = xfs_efi_item_format, - .iop_unpin = xfs_efi_item_unpin, - .iop_release = xfs_efi_item_release, -}; - - -/* - * Allocate and initialize an efi item with the given number of extents. - */ -struct xfs_efi_log_item * -xfs_efi_init( - struct xfs_mount *mp, - uint nextents) - -{ - struct xfs_efi_log_item *efip; - uint size; - - ASSERT(nextents > 0); - if (nextents > XFS_EFI_MAX_FAST_EXTENTS) { - size = (uint)(sizeof(xfs_efi_log_item_t) + - ((nextents - 1) * sizeof(xfs_extent_t))); - efip = kmem_zalloc(size, 0); - } else { - efip = kmem_zone_zalloc(xfs_efi_zone, 0); - } - - xfs_log_item_init(mp, &efip->efi_item, XFS_LI_EFI, &xfs_efi_item_ops); - efip->efi_format.efi_nextents = nextents; - efip->efi_format.efi_id = (uintptr_t)(void *)efip; - atomic_set(&efip->efi_next_extent, 0); - atomic_set(&efip->efi_refcount, 2); - - return efip; -} - /* * Copy an EFI format buffer from the given buf, and into the destination * EFI format structure. @@ -412,41 +374,16 @@ xfs_extent_free_diff_items( XFS_FSB_TO_AGNO(mp, rb->xefi_startblock); } -/* Get an EFI. */ -STATIC void * -xfs_extent_free_create_intent( - struct xfs_trans *tp, - unsigned int count) -{ - struct xfs_efi_log_item *efip; - - ASSERT(tp != NULL); - ASSERT(count > 0); - - efip = xfs_efi_init(tp->t_mountp, count); - ASSERT(efip != NULL); - - /* - * Get a log_item_desc to point at the new item. - */ - xfs_trans_add_item(tp, &efip->efi_item); - return efip; -} - /* Log a free extent to the intent item. */ STATIC void xfs_extent_free_log_item( struct xfs_trans *tp, - void *intent, - struct list_head *item) + struct xfs_efi_log_item *efip, + struct xfs_extent_free_item *free) { - struct xfs_efi_log_item *efip = intent; - struct xfs_extent_free_item *free; uint next_extent; struct xfs_extent *extp; - free = container_of(item, struct xfs_extent_free_item, xefi_list); - tp->t_flags |= XFS_TRANS_DIRTY; set_bit(XFS_LI_DIRTY, &efip->efi_item.li_flags); @@ -462,14 +399,35 @@ xfs_extent_free_log_item( extp->ext_len = free->xefi_blockcount; } +static struct xfs_log_item * +xfs_extent_free_create_intent( + struct xfs_trans *tp, + struct list_head *items, + unsigned int count, + bool sort) +{ + struct xfs_mount *mp = tp->t_mountp; + struct xfs_efi_log_item *efip = xfs_efi_init(mp, count); + struct xfs_extent_free_item *free; + + ASSERT(count > 0); + + xfs_trans_add_item(tp, &efip->efi_item); + if (sort) + list_sort(mp, items, xfs_extent_free_diff_items); + list_for_each_entry(free, items, xefi_list) + xfs_extent_free_log_item(tp, efip, free); + return &efip->efi_item; +} + /* Get an EFD so we can process all the free extents. */ STATIC void * xfs_extent_free_create_done( struct xfs_trans *tp, - void *intent, + struct xfs_log_item *intent, unsigned int count) { - return xfs_trans_get_efd(tp, intent, count); + return xfs_trans_get_efd(tp, EFI_ITEM(intent), count); } /* Process a free extent. */ @@ -495,9 +453,9 @@ xfs_extent_free_finish_item( /* Abort all pending EFIs. */ STATIC void xfs_extent_free_abort_intent( - void *intent) + struct xfs_log_item *intent) { - xfs_efi_release(intent); + xfs_efi_release(EFI_ITEM(intent)); } /* Cancel a free extent. */ @@ -513,10 +471,8 @@ xfs_extent_free_cancel_item( const struct xfs_defer_op_type xfs_extent_free_defer_type = { .max_items = XFS_EFI_MAX_FAST_EXTENTS, - .diff_items = xfs_extent_free_diff_items, .create_intent = xfs_extent_free_create_intent, .abort_intent = xfs_extent_free_abort_intent, - .log_item = xfs_extent_free_log_item, .create_done = xfs_extent_free_create_done, .finish_item = xfs_extent_free_finish_item, .cancel_item = xfs_extent_free_cancel_item, @@ -579,10 +535,8 @@ xfs_agfl_free_finish_item( /* sub-type with special handling for AGFL deferred frees */ const struct xfs_defer_op_type xfs_agfl_free_defer_type = { .max_items = XFS_EFI_MAX_FAST_EXTENTS, - .diff_items = xfs_extent_free_diff_items, .create_intent = xfs_extent_free_create_intent, .abort_intent = xfs_extent_free_abort_intent, - .log_item = xfs_extent_free_log_item, .create_done = xfs_extent_free_create_done, .finish_item = xfs_agfl_free_finish_item, .cancel_item = xfs_extent_free_cancel_item, @@ -594,9 +548,10 @@ const struct xfs_defer_op_type xfs_agfl_free_defer_type = { */ int xfs_efi_recover( - struct xfs_mount *mp, - struct xfs_efi_log_item *efip) + struct xfs_efi_log_item *efip, + struct list_head *capture_list) { + struct xfs_mount *mp = efip->efi_item.li_mountp; struct xfs_efd_log_item *efdp; struct xfs_trans *tp; int i; @@ -645,10 +600,76 @@ xfs_efi_recover( } set_bit(XFS_EFI_RECOVERED, &efip->efi_flags); - error = xfs_trans_commit(tp); - return error; + + return xfs_defer_ops_capture_and_commit(tp, NULL, capture_list); abort_error: xfs_trans_cancel(tp); return error; } + +/* Relog an intent item to push the log tail forward. */ +static struct xfs_log_item * +xfs_efi_item_relog( + struct xfs_log_item *intent, + struct xfs_trans *tp) +{ + struct xfs_efd_log_item *efdp; + struct xfs_efi_log_item *efip; + struct xfs_extent *extp; + unsigned int count; + + count = EFI_ITEM(intent)->efi_format.efi_nextents; + extp = EFI_ITEM(intent)->efi_format.efi_extents; + + tp->t_flags |= XFS_TRANS_DIRTY; + efdp = xfs_trans_get_efd(tp, EFI_ITEM(intent), count); + efdp->efd_next_extent = count; + memcpy(efdp->efd_format.efd_extents, extp, count * sizeof(*extp)); + set_bit(XFS_LI_DIRTY, &efdp->efd_item.li_flags); + + efip = xfs_efi_init(tp->t_mountp, count); + memcpy(efip->efi_format.efi_extents, extp, count * sizeof(*extp)); + atomic_set(&efip->efi_next_extent, count); + xfs_trans_add_item(tp, &efip->efi_item); + set_bit(XFS_LI_DIRTY, &efip->efi_item.li_flags); + return &efip->efi_item; +} + +static const struct xfs_item_ops xfs_efi_item_ops = { + .iop_size = xfs_efi_item_size, + .iop_format = xfs_efi_item_format, + .iop_unpin = xfs_efi_item_unpin, + .iop_release = xfs_efi_item_release, + .iop_relog = xfs_efi_item_relog, +}; + +/* + * Allocate and initialize an efi item with the given number of extents. + */ +struct xfs_efi_log_item * +xfs_efi_init( + struct xfs_mount *mp, + uint nextents) + +{ + struct xfs_efi_log_item *efip; + uint size; + + ASSERT(nextents > 0); + if (nextents > XFS_EFI_MAX_FAST_EXTENTS) { + size = (uint)(sizeof(struct xfs_efi_log_item) + + ((nextents - 1) * sizeof(xfs_extent_t))); + efip = kmem_zalloc(size, 0); + } else { + efip = kmem_zone_zalloc(xfs_efi_zone, 0); + } + + xfs_log_item_init(mp, &efip->efi_item, XFS_LI_EFI, &xfs_efi_item_ops); + efip->efi_format.efi_nextents = nextents; + efip->efi_format.efi_id = (uintptr_t)(void *)efip; + atomic_set(&efip->efi_next_extent, 0); + atomic_set(&efip->efi_refcount, 2); + + return efip; +} diff --git a/fs/xfs/xfs_extfree_item.h b/fs/xfs/xfs_extfree_item.h index 16aaab06d4ecc..883f0f1d8989d 100644 --- a/fs/xfs/xfs_extfree_item.h +++ b/fs/xfs/xfs_extfree_item.h @@ -50,25 +50,25 @@ struct kmem_zone; * of commit failure or log I/O errors. Note that the EFD is not inserted in the * AIL, so at this point both the EFI and EFD are freed. */ -typedef struct xfs_efi_log_item { +struct xfs_efi_log_item { struct xfs_log_item efi_item; atomic_t efi_refcount; atomic_t efi_next_extent; unsigned long efi_flags; /* misc flags */ xfs_efi_log_format_t efi_format; -} xfs_efi_log_item_t; +}; /* * This is the "extent free done" log item. It is used to log * the fact that some extents earlier mentioned in an efi item * have been freed. */ -typedef struct xfs_efd_log_item { +struct xfs_efd_log_item { struct xfs_log_item efd_item; - xfs_efi_log_item_t *efd_efip; + struct xfs_efi_log_item *efd_efip; uint efd_next_extent; xfs_efd_log_format_t efd_format; -} xfs_efd_log_item_t; +}; /* * Max number of extents in fast allocation path. @@ -78,13 +78,13 @@ typedef struct xfs_efd_log_item { extern struct kmem_zone *xfs_efi_zone; extern struct kmem_zone *xfs_efd_zone; -xfs_efi_log_item_t *xfs_efi_init(struct xfs_mount *, uint); +struct xfs_efi_log_item *xfs_efi_init(struct xfs_mount *, uint); int xfs_efi_copy_format(xfs_log_iovec_t *buf, xfs_efi_log_format_t *dst_efi_fmt); -void xfs_efi_item_free(xfs_efi_log_item_t *); +void xfs_efi_item_free(struct xfs_efi_log_item *); void xfs_efi_release(struct xfs_efi_log_item *); -int xfs_efi_recover(struct xfs_mount *mp, - struct xfs_efi_log_item *efip); +int xfs_efi_recover(struct xfs_efi_log_item *efip, + struct list_head *capture_list); #endif /* __XFS_EXTFREE_ITEM_H__ */ diff --git a/fs/xfs/xfs_icreate_item.c b/fs/xfs/xfs_icreate_item.c index 3ebd1b7f49d82..7d940b289db54 100644 --- a/fs/xfs/xfs_icreate_item.c +++ b/fs/xfs/xfs_icreate_item.c @@ -10,6 +10,7 @@ #include "xfs_trans.h" #include "xfs_trans_priv.h" #include "xfs_icreate_item.h" +#include "xfs_log_priv.h" #include "xfs_log.h" kmem_zone_t *xfs_icreate_zone; /* inode create item zone */ diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index e5a90a0b8f8a2..02f77a359972e 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -2555,7 +2555,7 @@ xfs_ifree_cluster( xfs_daddr_t blkno; xfs_buf_t *bp; xfs_inode_t *ip; - xfs_inode_log_item_t *iip; + struct xfs_inode_log_item *iip; struct xfs_log_item *lip; struct xfs_perag *pag; struct xfs_ino_geometry *igeo = M_IGEO(mp); @@ -2617,7 +2617,7 @@ xfs_ifree_cluster( */ list_for_each_entry(lip, &bp->b_li_list, li_bio_list) { if (lip->li_type == XFS_LI_INODE) { - iip = (xfs_inode_log_item_t *)lip; + iip = (struct xfs_inode_log_item *)lip; ASSERT(iip->ili_logged == 1); lip->li_cb = xfs_istale_done; xfs_trans_ail_copy_lsn(mp->m_ail, diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c index 76a60526af94f..83b8f5655636e 100644 --- a/fs/xfs/xfs_inode_item.c +++ b/fs/xfs/xfs_inode_item.c @@ -781,7 +781,7 @@ xfs_iflush_abort( xfs_inode_t *ip, bool stale) { - xfs_inode_log_item_t *iip = ip->i_itemp; + struct xfs_inode_log_item *iip = ip->i_itemp; if (iip) { if (test_bit(XFS_LI_IN_AIL, &iip->ili_item.li_flags)) { diff --git a/fs/xfs/xfs_inode_item.h b/fs/xfs/xfs_inode_item.h index 07a60e74c39c8..ad667fd4ae622 100644 --- a/fs/xfs/xfs_inode_item.h +++ b/fs/xfs/xfs_inode_item.h @@ -13,7 +13,7 @@ struct xfs_bmbt_rec; struct xfs_inode; struct xfs_mount; -typedef struct xfs_inode_log_item { +struct xfs_inode_log_item { struct xfs_log_item ili_item; /* common portion */ struct xfs_inode *ili_inode; /* inode ptr */ xfs_lsn_t ili_flush_lsn; /* lsn at last flush */ @@ -23,7 +23,7 @@ typedef struct xfs_inode_log_item { unsigned int ili_last_fields; /* fields when flushed */ unsigned int ili_fields; /* fields to be logged */ unsigned int ili_fsync_fields; /* logged since last fsync */ -} xfs_inode_log_item_t; +}; static inline int xfs_inode_clean(xfs_inode_t *ip) { diff --git a/fs/xfs/xfs_iwalk.c b/fs/xfs/xfs_iwalk.c index aa375cf53021a..cc5c0c835884e 100644 --- a/fs/xfs/xfs_iwalk.c +++ b/fs/xfs/xfs_iwalk.c @@ -55,6 +55,9 @@ struct xfs_iwalk_ag { /* Where do we start the traversal? */ xfs_ino_t startino; + /* What was the last inode number we saw when iterating the inobt? */ + xfs_ino_t lastino; + /* Array of inobt records we cache. */ struct xfs_inobt_rec_incore *recs; @@ -300,6 +303,9 @@ xfs_iwalk_ag_start( return error; XFS_WANT_CORRUPTED_RETURN(mp, *has_more == 1); + iwag->lastino = XFS_AGINO_TO_INO(mp, agno, + irec->ir_startino + XFS_INODES_PER_CHUNK - 1); + /* * If the LE lookup yielded an inobt record before the cursor position, * skip it and see if there's another one after it. @@ -346,15 +352,17 @@ xfs_iwalk_run_callbacks( struct xfs_mount *mp = iwag->mp; struct xfs_trans *tp = iwag->tp; struct xfs_inobt_rec_incore *irec; - xfs_agino_t restart; + xfs_agino_t next_agino; int error; + next_agino = XFS_INO_TO_AGINO(mp, iwag->lastino) + 1; + ASSERT(iwag->nr_recs > 0); /* Delete cursor but remember the last record we cached... */ xfs_iwalk_del_inobt(tp, curpp, agi_bpp, 0); irec = &iwag->recs[iwag->nr_recs - 1]; - restart = irec->ir_startino + XFS_INODES_PER_CHUNK - 1; + ASSERT(next_agino >= irec->ir_startino + XFS_INODES_PER_CHUNK); error = xfs_iwalk_ag_recs(iwag); if (error) @@ -371,7 +379,7 @@ xfs_iwalk_run_callbacks( if (error) return error; - return xfs_inobt_lookup(*curpp, restart, XFS_LOOKUP_GE, has_more); + return xfs_inobt_lookup(*curpp, next_agino, XFS_LOOKUP_GE, has_more); } /* Walk all inodes in a single AG, from @iwag->startino to the end of the AG. */ @@ -395,6 +403,7 @@ xfs_iwalk_ag( while (!error && has_more) { struct xfs_inobt_rec_incore *irec; + xfs_ino_t rec_fsino; cond_resched(); if (xfs_pwork_want_abort(&iwag->pwork)) @@ -406,6 +415,15 @@ xfs_iwalk_ag( if (error || !has_more) break; + /* Make sure that we always move forward. */ + rec_fsino = XFS_AGINO_TO_INO(mp, agno, irec->ir_startino); + if (iwag->lastino != NULLFSINO && iwag->lastino >= rec_fsino) { + ASSERT(iwag->lastino < rec_fsino); + error = -EFSCORRUPTED; + goto out; + } + iwag->lastino = rec_fsino + XFS_INODES_PER_CHUNK - 1; + /* No allocated inodes in this chunk; skip it. */ if (iwag->skip_empty && irec->ir_freecount == irec->ir_count) { error = xfs_btree_increment(cur, 0, &has_more); @@ -534,6 +552,7 @@ xfs_iwalk( .trim_start = 1, .skip_empty = 1, .pwork = XFS_PWORK_SINGLE_THREADED, + .lastino = NULLFSINO, }; xfs_agnumber_t agno = XFS_INO_TO_AGNO(mp, startino); int error; @@ -622,6 +641,7 @@ xfs_iwalk_threaded( iwag->data = data; iwag->startino = startino; iwag->sz_recs = xfs_iwalk_prefetch(inode_records); + iwag->lastino = NULLFSINO; xfs_pwork_queue(&pctl, &iwag->pwork); startino = XFS_AGINO_TO_INO(mp, agno + 1, 0); if (flags & XFS_INOBT_WALK_SAME_AG) @@ -695,6 +715,7 @@ xfs_inobt_walk( .startino = startino, .sz_recs = xfs_inobt_walk_prefetch(inobt_records), .pwork = XFS_PWORK_SINGLE_THREADED, + .lastino = NULLFSINO, }; xfs_agnumber_t agno = XFS_INO_TO_AGNO(mp, startino); int error; diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index 63c0f1e9d1018..03a52b3919b82 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -369,6 +369,25 @@ xlog_tic_add_region(xlog_ticket_t *tic, uint len, uint type) tic->t_res_num++; } +bool +xfs_log_writable( + struct xfs_mount *mp) +{ + /* + * Never write to the log on norecovery mounts, if the block device is + * read-only, or if the filesystem is shutdown. Read-only mounts still + * allow internal writes for log recovery and unmount purposes, so don't + * restrict that case here. + */ + if (mp->m_flags & XFS_MOUNT_NORECOVERY) + return false; + if (xfs_readonly_buftarg(mp->m_log->l_targ)) + return false; + if (XFS_FORCED_SHUTDOWN(mp)) + return false; + return true; +} + /* * Replenish the byte reservation required by moving the grant write head. */ @@ -895,15 +914,8 @@ xfs_log_unmount_write(xfs_mount_t *mp) #endif int error; - /* - * Don't write out unmount record on norecovery mounts or ro devices. - * Or, if we are doing a forced umount (typically because of IO errors). - */ - if (mp->m_flags & XFS_MOUNT_NORECOVERY || - xfs_readonly_buftarg(log->l_targ)) { - ASSERT(mp->m_flags & XFS_MOUNT_RDONLY); + if (!xfs_log_writable(mp)) return 0; - } error = xfs_log_force(mp, XFS_LOG_SYNC); ASSERT(error || !(XLOG_FORCED_SHUTDOWN(log))); @@ -1537,14 +1549,14 @@ xlog_commit_record( } /* - * Push on the buffer cache code if we ever use more than 75% of the on-disk - * log space. This code pushes on the lsn which would supposedly free up - * the 25% which we want to leave free. We may need to adopt a policy which - * pushes on an lsn which is further along in the log once we reach the high - * water mark. In this manner, we would be creating a low water mark. + * Compute the LSN that we'd need to push the log tail towards in order to have + * (a) enough on-disk log space to log the number of bytes specified, (b) at + * least 25% of the log space free, and (c) at least 256 blocks free. If the + * log free space already meets all three thresholds, this function returns + * NULLCOMMITLSN. */ -STATIC void -xlog_grant_push_ail( +xfs_lsn_t +xlog_grant_push_threshold( struct xlog *log, int need_bytes) { @@ -1570,7 +1582,7 @@ xlog_grant_push_ail( free_threshold = max(free_threshold, (log->l_logBBsize >> 2)); free_threshold = max(free_threshold, 256); if (free_blocks >= free_threshold) - return; + return NULLCOMMITLSN; xlog_crack_atomic_lsn(&log->l_tail_lsn, &threshold_cycle, &threshold_block); @@ -1590,13 +1602,33 @@ xlog_grant_push_ail( if (XFS_LSN_CMP(threshold_lsn, last_sync_lsn) > 0) threshold_lsn = last_sync_lsn; + return threshold_lsn; +} + +/* + * Push the tail of the log if we need to do so to maintain the free log space + * thresholds set out by xlog_grant_push_threshold. We may need to adopt a + * policy which pushes on an lsn which is further along in the log once we + * reach the high water mark. In this manner, we would be creating a low water + * mark. + */ +STATIC void +xlog_grant_push_ail( + struct xlog *log, + int need_bytes) +{ + xfs_lsn_t threshold_lsn; + + threshold_lsn = xlog_grant_push_threshold(log, need_bytes); + if (threshold_lsn == NULLCOMMITLSN || XLOG_FORCED_SHUTDOWN(log)) + return; + /* * Get the transaction layer to kick the dirty buffers out to * disk asynchronously. No point in trying to do this if * the filesystem is shutting down. */ - if (!XLOG_FORCED_SHUTDOWN(log)) - xfs_ail_push(log->l_ailp, threshold_lsn); + xfs_ail_push(log->l_ailp, threshold_lsn); } /* diff --git a/fs/xfs/xfs_log.h b/fs/xfs/xfs_log.h index 84e06805160f8..dc9229e7ddaaa 100644 --- a/fs/xfs/xfs_log.h +++ b/fs/xfs/xfs_log.h @@ -132,6 +132,7 @@ int xfs_log_reserve(struct xfs_mount *mp, int xfs_log_regrant(struct xfs_mount *mp, struct xlog_ticket *tic); void xfs_log_unmount(struct xfs_mount *mp); int xfs_log_force_umount(struct xfs_mount *mp, int logerror); +bool xfs_log_writable(struct xfs_mount *mp); struct xlog_ticket *xfs_log_ticket_get(struct xlog_ticket *ticket); void xfs_log_ticket_put(struct xlog_ticket *ticket); @@ -146,4 +147,6 @@ void xfs_log_quiesce(struct xfs_mount *mp); bool xfs_log_check_lsn(struct xfs_mount *, xfs_lsn_t); bool xfs_log_in_recovery(struct xfs_mount *); +xfs_lsn_t xlog_grant_push_threshold(struct xlog *log, int need_bytes); + #endif /* __XFS_LOG_H__ */ diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c index 550fd5de2404a..ae9b8efcfa545 100644 --- a/fs/xfs/xfs_log_cil.c +++ b/fs/xfs/xfs_log_cil.c @@ -1178,21 +1178,19 @@ out_shutdown: */ bool xfs_log_item_in_current_chkpt( - struct xfs_log_item *lip) + struct xfs_log_item *lip) { - struct xfs_cil_ctx *ctx; + struct xfs_cil *cil = lip->li_mountp->m_log->l_cilp; if (list_empty(&lip->li_cil)) return false; - ctx = lip->li_mountp->m_log->l_cilp->xc_ctx; - /* * li_seq is written on the first commit of a log item to record the * first checkpoint it is written to. Hence if it is different to the * current sequence, we're in a new checkpoint. */ - if (XFS_LSN_CMP(lip->li_seq, ctx->sequence) != 0) + if (XFS_LSN_CMP(lip->li_seq, READ_ONCE(cil->xc_current_sequence)) != 0) return false; return true; } diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c index 46b1e255f55fc..6c60cdd10d330 100644 --- a/fs/xfs/xfs_log_recover.c +++ b/fs/xfs/xfs_log_recover.c @@ -2206,6 +2206,8 @@ xlog_recover_get_buf_lsn( case XFS_ABTC_MAGIC: case XFS_RMAP_CRC_MAGIC: case XFS_REFC_CRC_MAGIC: + case XFS_FIBT_CRC_MAGIC: + case XFS_FIBT_MAGIC: case XFS_IBT_CRC_MAGIC: case XFS_IBT_MAGIC: { struct xfs_btree_block *btb = blk; @@ -3384,7 +3386,7 @@ xlog_recover_efd_pass2( struct xlog_recover_item *item) { xfs_efd_log_format_t *efd_formatp; - xfs_efi_log_item_t *efip = NULL; + struct xfs_efi_log_item *efip = NULL; struct xfs_log_item *lip; uint64_t efi_id; struct xfs_ail_cursor cur; @@ -3405,7 +3407,7 @@ xlog_recover_efd_pass2( lip = xfs_trans_ail_cursor_first(ailp, &cur, 0); while (lip != NULL) { if (lip->li_type == XFS_LI_EFI) { - efip = (xfs_efi_log_item_t *)lip; + efip = (struct xfs_efi_log_item *)lip; if (efip->efi_format.efi_id == efi_id) { /* * Drop the EFD reference to the EFI. This @@ -4585,9 +4587,9 @@ xlog_recover_process_data( /* Recover the EFI if necessary. */ STATIC int xlog_recover_process_efi( - struct xfs_mount *mp, struct xfs_ail *ailp, - struct xfs_log_item *lip) + struct xfs_log_item *lip, + struct list_head *capture_list) { struct xfs_efi_log_item *efip; int error; @@ -4600,7 +4602,7 @@ xlog_recover_process_efi( return 0; spin_unlock(&ailp->ail_lock); - error = xfs_efi_recover(mp, efip); + error = xfs_efi_recover(efip, capture_list); spin_lock(&ailp->ail_lock); return error; @@ -4625,9 +4627,9 @@ xlog_recover_cancel_efi( /* Recover the RUI if necessary. */ STATIC int xlog_recover_process_rui( - struct xfs_mount *mp, struct xfs_ail *ailp, - struct xfs_log_item *lip) + struct xfs_log_item *lip, + struct list_head *capture_list) { struct xfs_rui_log_item *ruip; int error; @@ -4640,7 +4642,7 @@ xlog_recover_process_rui( return 0; spin_unlock(&ailp->ail_lock); - error = xfs_rui_recover(mp, ruip); + error = xfs_rui_recover(ruip, capture_list); spin_lock(&ailp->ail_lock); return error; @@ -4665,9 +4667,9 @@ xlog_recover_cancel_rui( /* Recover the CUI if necessary. */ STATIC int xlog_recover_process_cui( - struct xfs_trans *parent_tp, struct xfs_ail *ailp, - struct xfs_log_item *lip) + struct xfs_log_item *lip, + struct list_head *capture_list) { struct xfs_cui_log_item *cuip; int error; @@ -4680,7 +4682,7 @@ xlog_recover_process_cui( return 0; spin_unlock(&ailp->ail_lock); - error = xfs_cui_recover(parent_tp, cuip); + error = xfs_cui_recover(cuip, capture_list); spin_lock(&ailp->ail_lock); return error; @@ -4705,9 +4707,9 @@ xlog_recover_cancel_cui( /* Recover the BUI if necessary. */ STATIC int xlog_recover_process_bui( - struct xfs_trans *parent_tp, struct xfs_ail *ailp, - struct xfs_log_item *lip) + struct xfs_log_item *lip, + struct list_head *capture_list) { struct xfs_bui_log_item *buip; int error; @@ -4720,7 +4722,7 @@ xlog_recover_process_bui( return 0; spin_unlock(&ailp->ail_lock); - error = xfs_bui_recover(parent_tp, buip); + error = xfs_bui_recover(buip, capture_list); spin_lock(&ailp->ail_lock); return error; @@ -4759,37 +4761,66 @@ static inline bool xlog_item_is_intent(struct xfs_log_item *lip) /* Take all the collected deferred ops and finish them in order. */ static int xlog_finish_defer_ops( - struct xfs_trans *parent_tp) + struct xfs_mount *mp, + struct list_head *capture_list) { - struct xfs_mount *mp = parent_tp->t_mountp; + struct xfs_defer_capture *dfc, *next; struct xfs_trans *tp; - int64_t freeblks; - uint resblks; - int error; + struct xfs_inode *ip; + int error = 0; - /* - * We're finishing the defer_ops that accumulated as a result of - * recovering unfinished intent items during log recovery. We - * reserve an itruncate transaction because it is the largest - * permanent transaction type. Since we're the only user of the fs - * right now, take 93% (15/16) of the available free blocks. Use - * weird math to avoid a 64-bit division. - */ - freeblks = percpu_counter_sum(&mp->m_fdblocks); - if (freeblks <= 0) - return -ENOSPC; - resblks = min_t(int64_t, UINT_MAX, freeblks); - resblks = (resblks * 15) >> 4; - error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, resblks, - 0, XFS_TRANS_RESERVE, &tp); - if (error) - return error; - /* transfer all collected dfops to this transaction */ - xfs_defer_move(tp, parent_tp); + list_for_each_entry_safe(dfc, next, capture_list, dfc_list) { + struct xfs_trans_res resv; + + /* + * Create a new transaction reservation from the captured + * information. Set logcount to 1 to force the new transaction + * to regrant every roll so that we can make forward progress + * in recovery no matter how full the log might be. + */ + resv.tr_logres = dfc->dfc_logres; + resv.tr_logcount = 1; + resv.tr_logflags = XFS_TRANS_PERM_LOG_RES; + + error = xfs_trans_alloc(mp, &resv, dfc->dfc_blkres, + dfc->dfc_rtxres, XFS_TRANS_RESERVE, &tp); + if (error) + return error; + + /* + * Transfer to this new transaction all the dfops we captured + * from recovering a single intent item. + */ + list_del_init(&dfc->dfc_list); + xfs_defer_ops_continue(dfc, tp, &ip); + + error = xfs_trans_commit(tp); + if (ip) { + xfs_iunlock(ip, XFS_ILOCK_EXCL); + xfs_irele(ip); + } + if (error) + return error; + } - return xfs_trans_commit(tp); + ASSERT(list_empty(capture_list)); + return 0; } +/* Release all the captured defer ops and capture structures in this list. */ +static void +xlog_abort_defer_ops( + struct xfs_mount *mp, + struct list_head *capture_list) +{ + struct xfs_defer_capture *dfc; + struct xfs_defer_capture *next; + + list_for_each_entry_safe(dfc, next, capture_list, dfc_list) { + list_del_init(&dfc->dfc_list); + xfs_defer_ops_release(mp, dfc); + } +} /* * When this is called, all of the log intent items which did not have * corresponding log done items should be in the AIL. What we do now @@ -4810,35 +4841,23 @@ STATIC int xlog_recover_process_intents( struct xlog *log) { - struct xfs_trans *parent_tp; + LIST_HEAD(capture_list); struct xfs_ail_cursor cur; struct xfs_log_item *lip; struct xfs_ail *ailp; - int error; + int error = 0; #if defined(DEBUG) || defined(XFS_WARN) xfs_lsn_t last_lsn; #endif - /* - * The intent recovery handlers commit transactions to complete recovery - * for individual intents, but any new deferred operations that are - * queued during that process are held off until the very end. The - * purpose of this transaction is to serve as a container for deferred - * operations. Each intent recovery handler must transfer dfops here - * before its local transaction commits, and we'll finish the entire - * list below. - */ - error = xfs_trans_alloc_empty(log->l_mp, &parent_tp); - if (error) - return error; - ailp = log->l_ailp; spin_lock(&ailp->ail_lock); - lip = xfs_trans_ail_cursor_first(ailp, &cur, 0); #if defined(DEBUG) || defined(XFS_WARN) last_lsn = xlog_assign_lsn(log->l_curr_cycle, log->l_curr_block); #endif - while (lip != NULL) { + for (lip = xfs_trans_ail_cursor_first(ailp, &cur, 0); + lip != NULL; + lip = xfs_trans_ail_cursor_next(ailp, &cur)) { /* * We're done when we see something other than an intent. * There should be no intents left in the AIL now. @@ -4860,35 +4879,40 @@ xlog_recover_process_intents( /* * NOTE: If your intent processing routine can create more - * deferred ops, you /must/ attach them to the dfops in this - * routine or else those subsequent intents will get + * deferred ops, you /must/ attach them to the capture list in + * the recover routine or else those subsequent intents will be * replayed in the wrong order! */ switch (lip->li_type) { case XFS_LI_EFI: - error = xlog_recover_process_efi(log->l_mp, ailp, lip); + error = xlog_recover_process_efi(ailp, lip, &capture_list); break; case XFS_LI_RUI: - error = xlog_recover_process_rui(log->l_mp, ailp, lip); + error = xlog_recover_process_rui(ailp, lip, &capture_list); break; case XFS_LI_CUI: - error = xlog_recover_process_cui(parent_tp, ailp, lip); + error = xlog_recover_process_cui(ailp, lip, &capture_list); break; case XFS_LI_BUI: - error = xlog_recover_process_bui(parent_tp, ailp, lip); + error = xlog_recover_process_bui(ailp, lip, &capture_list); break; } if (error) - goto out; - lip = xfs_trans_ail_cursor_next(ailp, &cur); + break; } -out: + xfs_trans_ail_cursor_done(&cur); spin_unlock(&ailp->ail_lock); - if (!error) - error = xlog_finish_defer_ops(parent_tp); - xfs_trans_cancel(parent_tp); + if (error) + goto err; + error = xlog_finish_defer_ops(log->l_mp, &capture_list); + if (error) + goto err; + + return 0; +err: + xlog_abort_defer_ops(log->l_mp, &capture_list); return error; } diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index bbcf48a625b2a..2860966af6c20 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -1218,8 +1218,7 @@ xfs_fs_writable( int xfs_log_sbcount(xfs_mount_t *mp) { - /* allow this to proceed during the freeze sequence... */ - if (!xfs_fs_writable(mp, SB_FREEZE_COMPLETE)) + if (!xfs_log_writable(mp)) return 0; /* diff --git a/fs/xfs/xfs_refcount_item.c b/fs/xfs/xfs_refcount_item.c index d5708d40ad877..fa1018a6e6777 100644 --- a/fs/xfs/xfs_refcount_item.c +++ b/fs/xfs/xfs_refcount_item.c @@ -123,40 +123,6 @@ xfs_cui_item_release( xfs_cui_release(CUI_ITEM(lip)); } -static const struct xfs_item_ops xfs_cui_item_ops = { - .iop_size = xfs_cui_item_size, - .iop_format = xfs_cui_item_format, - .iop_unpin = xfs_cui_item_unpin, - .iop_release = xfs_cui_item_release, -}; - -/* - * Allocate and initialize an cui item with the given number of extents. - */ -struct xfs_cui_log_item * -xfs_cui_init( - struct xfs_mount *mp, - uint nextents) - -{ - struct xfs_cui_log_item *cuip; - - ASSERT(nextents > 0); - if (nextents > XFS_CUI_MAX_FAST_EXTENTS) - cuip = kmem_zalloc(xfs_cui_log_item_sizeof(nextents), - 0); - else - cuip = kmem_zone_zalloc(xfs_cui_zone, 0); - - xfs_log_item_init(mp, &cuip->cui_item, XFS_LI_CUI, &xfs_cui_item_ops); - cuip->cui_format.cui_nextents = nextents; - cuip->cui_format.cui_id = (uintptr_t)(void *)cuip; - atomic_set(&cuip->cui_next_extent, 0); - atomic_set(&cuip->cui_refcount, 2); - - return cuip; -} - static inline struct xfs_cud_log_item *CUD_ITEM(struct xfs_log_item *lip) { return container_of(lip, struct xfs_cud_log_item, cud_item); @@ -284,27 +250,6 @@ xfs_refcount_update_diff_items( XFS_FSB_TO_AGNO(mp, rb->ri_startblock); } -/* Get an CUI. */ -STATIC void * -xfs_refcount_update_create_intent( - struct xfs_trans *tp, - unsigned int count) -{ - struct xfs_cui_log_item *cuip; - - ASSERT(tp != NULL); - ASSERT(count > 0); - - cuip = xfs_cui_init(tp->t_mountp, count); - ASSERT(cuip != NULL); - - /* - * Get a log_item_desc to point at the new item. - */ - xfs_trans_add_item(tp, &cuip->cui_item); - return cuip; -} - /* Set the phys extent flags for this reverse mapping. */ static void xfs_trans_set_refcount_flags( @@ -328,16 +273,12 @@ xfs_trans_set_refcount_flags( STATIC void xfs_refcount_update_log_item( struct xfs_trans *tp, - void *intent, - struct list_head *item) + struct xfs_cui_log_item *cuip, + struct xfs_refcount_intent *refc) { - struct xfs_cui_log_item *cuip = intent; - struct xfs_refcount_intent *refc; uint next_extent; struct xfs_phys_extent *ext; - refc = container_of(item, struct xfs_refcount_intent, ri_list); - tp->t_flags |= XFS_TRANS_DIRTY; set_bit(XFS_LI_DIRTY, &cuip->cui_item.li_flags); @@ -354,14 +295,35 @@ xfs_refcount_update_log_item( xfs_trans_set_refcount_flags(ext, refc->ri_type); } +static struct xfs_log_item * +xfs_refcount_update_create_intent( + struct xfs_trans *tp, + struct list_head *items, + unsigned int count, + bool sort) +{ + struct xfs_mount *mp = tp->t_mountp; + struct xfs_cui_log_item *cuip = xfs_cui_init(mp, count); + struct xfs_refcount_intent *refc; + + ASSERT(count > 0); + + xfs_trans_add_item(tp, &cuip->cui_item); + if (sort) + list_sort(mp, items, xfs_refcount_update_diff_items); + list_for_each_entry(refc, items, ri_list) + xfs_refcount_update_log_item(tp, cuip, refc); + return &cuip->cui_item; +} + /* Get an CUD so we can process all the deferred refcount updates. */ STATIC void * xfs_refcount_update_create_done( struct xfs_trans *tp, - void *intent, + struct xfs_log_item *intent, unsigned int count) { - return xfs_trans_get_cud(tp, intent); + return xfs_trans_get_cud(tp, CUI_ITEM(intent)); } /* Process a deferred refcount update. */ @@ -411,9 +373,9 @@ xfs_refcount_update_finish_cleanup( /* Abort all pending CUIs. */ STATIC void xfs_refcount_update_abort_intent( - void *intent) + struct xfs_log_item *intent) { - xfs_cui_release(intent); + xfs_cui_release(CUI_ITEM(intent)); } /* Cancel a deferred refcount update. */ @@ -429,10 +391,8 @@ xfs_refcount_update_cancel_item( const struct xfs_defer_op_type xfs_refcount_update_defer_type = { .max_items = XFS_CUI_MAX_FAST_EXTENTS, - .diff_items = xfs_refcount_update_diff_items, .create_intent = xfs_refcount_update_create_intent, .abort_intent = xfs_refcount_update_abort_intent, - .log_item = xfs_refcount_update_log_item, .create_done = xfs_refcount_update_create_done, .finish_item = xfs_refcount_update_finish_item, .finish_cleanup = xfs_refcount_update_finish_cleanup, @@ -445,8 +405,8 @@ const struct xfs_defer_op_type xfs_refcount_update_defer_type = { */ int xfs_cui_recover( - struct xfs_trans *parent_tp, - struct xfs_cui_log_item *cuip) + struct xfs_cui_log_item *cuip, + struct list_head *capture_list) { int i; int error = 0; @@ -462,7 +422,7 @@ xfs_cui_recover( xfs_extlen_t new_len; struct xfs_bmbt_irec irec; bool requeue_only = false; - struct xfs_mount *mp = parent_tp->t_mountp; + struct xfs_mount *mp = cuip->cui_item.li_mountp; ASSERT(!test_bit(XFS_CUI_RECOVERED, &cuip->cui_flags)); @@ -517,12 +477,7 @@ xfs_cui_recover( mp->m_refc_maxlevels * 2, 0, XFS_TRANS_RESERVE, &tp); if (error) return error; - /* - * Recovery stashes all deferred ops during intent processing and - * finishes them on completion. Transfer current dfops state to this - * transaction and transfer the result back before we return. - */ - xfs_defer_move(tp, parent_tp); + cudp = xfs_trans_get_cud(tp, cuip); for (i = 0; i < cuip->cui_format.cui_nextents; i++) { @@ -580,13 +535,71 @@ xfs_cui_recover( xfs_refcount_finish_one_cleanup(tp, rcur, error); set_bit(XFS_CUI_RECOVERED, &cuip->cui_flags); - xfs_defer_move(parent_tp, tp); - error = xfs_trans_commit(tp); - return error; + return xfs_defer_ops_capture_and_commit(tp, NULL, capture_list); abort_error: xfs_refcount_finish_one_cleanup(tp, rcur, error); - xfs_defer_move(parent_tp, tp); xfs_trans_cancel(tp); return error; } + +/* Relog an intent item to push the log tail forward. */ +static struct xfs_log_item * +xfs_cui_item_relog( + struct xfs_log_item *intent, + struct xfs_trans *tp) +{ + struct xfs_cud_log_item *cudp; + struct xfs_cui_log_item *cuip; + struct xfs_phys_extent *extp; + unsigned int count; + + count = CUI_ITEM(intent)->cui_format.cui_nextents; + extp = CUI_ITEM(intent)->cui_format.cui_extents; + + tp->t_flags |= XFS_TRANS_DIRTY; + cudp = xfs_trans_get_cud(tp, CUI_ITEM(intent)); + set_bit(XFS_LI_DIRTY, &cudp->cud_item.li_flags); + + cuip = xfs_cui_init(tp->t_mountp, count); + memcpy(cuip->cui_format.cui_extents, extp, count * sizeof(*extp)); + atomic_set(&cuip->cui_next_extent, count); + xfs_trans_add_item(tp, &cuip->cui_item); + set_bit(XFS_LI_DIRTY, &cuip->cui_item.li_flags); + return &cuip->cui_item; +} + +static const struct xfs_item_ops xfs_cui_item_ops = { + .iop_size = xfs_cui_item_size, + .iop_format = xfs_cui_item_format, + .iop_unpin = xfs_cui_item_unpin, + .iop_release = xfs_cui_item_release, + .iop_relog = xfs_cui_item_relog, +}; + +/* + * Allocate and initialize an cui item with the given number of extents. + */ +struct xfs_cui_log_item * +xfs_cui_init( + struct xfs_mount *mp, + uint nextents) + +{ + struct xfs_cui_log_item *cuip; + + ASSERT(nextents > 0); + if (nextents > XFS_CUI_MAX_FAST_EXTENTS) + cuip = kmem_zalloc(xfs_cui_log_item_sizeof(nextents), + 0); + else + cuip = kmem_zone_zalloc(xfs_cui_zone, 0); + + xfs_log_item_init(mp, &cuip->cui_item, XFS_LI_CUI, &xfs_cui_item_ops); + cuip->cui_format.cui_nextents = nextents; + cuip->cui_format.cui_id = (uintptr_t)(void *)cuip; + atomic_set(&cuip->cui_next_extent, 0); + atomic_set(&cuip->cui_refcount, 2); + + return cuip; +} diff --git a/fs/xfs/xfs_refcount_item.h b/fs/xfs/xfs_refcount_item.h index e47530f30489d..de5f48ff4f74e 100644 --- a/fs/xfs/xfs_refcount_item.h +++ b/fs/xfs/xfs_refcount_item.h @@ -80,6 +80,7 @@ extern struct kmem_zone *xfs_cud_zone; struct xfs_cui_log_item *xfs_cui_init(struct xfs_mount *, uint); void xfs_cui_item_free(struct xfs_cui_log_item *); void xfs_cui_release(struct xfs_cui_log_item *); -int xfs_cui_recover(struct xfs_trans *parent_tp, struct xfs_cui_log_item *cuip); +int xfs_cui_recover(struct xfs_cui_log_item *cuip, + struct list_head *capture_list); #endif /* __XFS_REFCOUNT_ITEM_H__ */ diff --git a/fs/xfs/xfs_rmap_item.c b/fs/xfs/xfs_rmap_item.c index 02f84d9a511c3..ba1dbb6c40632 100644 --- a/fs/xfs/xfs_rmap_item.c +++ b/fs/xfs/xfs_rmap_item.c @@ -122,39 +122,6 @@ xfs_rui_item_release( xfs_rui_release(RUI_ITEM(lip)); } -static const struct xfs_item_ops xfs_rui_item_ops = { - .iop_size = xfs_rui_item_size, - .iop_format = xfs_rui_item_format, - .iop_unpin = xfs_rui_item_unpin, - .iop_release = xfs_rui_item_release, -}; - -/* - * Allocate and initialize an rui item with the given number of extents. - */ -struct xfs_rui_log_item * -xfs_rui_init( - struct xfs_mount *mp, - uint nextents) - -{ - struct xfs_rui_log_item *ruip; - - ASSERT(nextents > 0); - if (nextents > XFS_RUI_MAX_FAST_EXTENTS) - ruip = kmem_zalloc(xfs_rui_log_item_sizeof(nextents), 0); - else - ruip = kmem_zone_zalloc(xfs_rui_zone, 0); - - xfs_log_item_init(mp, &ruip->rui_item, XFS_LI_RUI, &xfs_rui_item_ops); - ruip->rui_format.rui_nextents = nextents; - ruip->rui_format.rui_id = (uintptr_t)(void *)ruip; - atomic_set(&ruip->rui_next_extent, 0); - atomic_set(&ruip->rui_refcount, 2); - - return ruip; -} - /* * Copy an RUI format buffer from the given buf, and into the destination * RUI format structure. The RUI/RUD items were designed not to need any @@ -352,41 +319,16 @@ xfs_rmap_update_diff_items( XFS_FSB_TO_AGNO(mp, rb->ri_bmap.br_startblock); } -/* Get an RUI. */ -STATIC void * -xfs_rmap_update_create_intent( - struct xfs_trans *tp, - unsigned int count) -{ - struct xfs_rui_log_item *ruip; - - ASSERT(tp != NULL); - ASSERT(count > 0); - - ruip = xfs_rui_init(tp->t_mountp, count); - ASSERT(ruip != NULL); - - /* - * Get a log_item_desc to point at the new item. - */ - xfs_trans_add_item(tp, &ruip->rui_item); - return ruip; -} - /* Log rmap updates in the intent item. */ STATIC void xfs_rmap_update_log_item( struct xfs_trans *tp, - void *intent, - struct list_head *item) + struct xfs_rui_log_item *ruip, + struct xfs_rmap_intent *rmap) { - struct xfs_rui_log_item *ruip = intent; - struct xfs_rmap_intent *rmap; uint next_extent; struct xfs_map_extent *map; - rmap = container_of(item, struct xfs_rmap_intent, ri_list); - tp->t_flags |= XFS_TRANS_DIRTY; set_bit(XFS_LI_DIRTY, &ruip->rui_item.li_flags); @@ -406,14 +348,35 @@ xfs_rmap_update_log_item( rmap->ri_bmap.br_state); } +static struct xfs_log_item * +xfs_rmap_update_create_intent( + struct xfs_trans *tp, + struct list_head *items, + unsigned int count, + bool sort) +{ + struct xfs_mount *mp = tp->t_mountp; + struct xfs_rui_log_item *ruip = xfs_rui_init(mp, count); + struct xfs_rmap_intent *rmap; + + ASSERT(count > 0); + + xfs_trans_add_item(tp, &ruip->rui_item); + if (sort) + list_sort(mp, items, xfs_rmap_update_diff_items); + list_for_each_entry(rmap, items, ri_list) + xfs_rmap_update_log_item(tp, ruip, rmap); + return &ruip->rui_item; +} + /* Get an RUD so we can process all the deferred rmap updates. */ STATIC void * xfs_rmap_update_create_done( struct xfs_trans *tp, - void *intent, + struct xfs_log_item *intent, unsigned int count) { - return xfs_trans_get_rud(tp, intent); + return xfs_trans_get_rud(tp, RUI_ITEM(intent)); } /* Process a deferred rmap update. */ @@ -455,9 +418,9 @@ xfs_rmap_update_finish_cleanup( /* Abort all pending RUIs. */ STATIC void xfs_rmap_update_abort_intent( - void *intent) + struct xfs_log_item *intent) { - xfs_rui_release(intent); + xfs_rui_release(RUI_ITEM(intent)); } /* Cancel a deferred rmap update. */ @@ -473,10 +436,8 @@ xfs_rmap_update_cancel_item( const struct xfs_defer_op_type xfs_rmap_update_defer_type = { .max_items = XFS_RUI_MAX_FAST_EXTENTS, - .diff_items = xfs_rmap_update_diff_items, .create_intent = xfs_rmap_update_create_intent, .abort_intent = xfs_rmap_update_abort_intent, - .log_item = xfs_rmap_update_log_item, .create_done = xfs_rmap_update_create_done, .finish_item = xfs_rmap_update_finish_item, .finish_cleanup = xfs_rmap_update_finish_cleanup, @@ -489,9 +450,10 @@ const struct xfs_defer_op_type xfs_rmap_update_defer_type = { */ int xfs_rui_recover( - struct xfs_mount *mp, - struct xfs_rui_log_item *ruip) + struct xfs_rui_log_item *ruip, + struct list_head *capture_list) { + struct xfs_mount *mp = ruip->rui_item.li_mountp; int i; int error = 0; struct xfs_map_extent *rmap; @@ -598,11 +560,70 @@ xfs_rui_recover( xfs_rmap_finish_one_cleanup(tp, rcur, error); set_bit(XFS_RUI_RECOVERED, &ruip->rui_flags); - error = xfs_trans_commit(tp); - return error; + return xfs_defer_ops_capture_and_commit(tp, NULL, capture_list); abort_error: xfs_rmap_finish_one_cleanup(tp, rcur, error); xfs_trans_cancel(tp); return error; } + +/* Relog an intent item to push the log tail forward. */ +static struct xfs_log_item * +xfs_rui_item_relog( + struct xfs_log_item *intent, + struct xfs_trans *tp) +{ + struct xfs_rud_log_item *rudp; + struct xfs_rui_log_item *ruip; + struct xfs_map_extent *extp; + unsigned int count; + + count = RUI_ITEM(intent)->rui_format.rui_nextents; + extp = RUI_ITEM(intent)->rui_format.rui_extents; + + tp->t_flags |= XFS_TRANS_DIRTY; + rudp = xfs_trans_get_rud(tp, RUI_ITEM(intent)); + set_bit(XFS_LI_DIRTY, &rudp->rud_item.li_flags); + + ruip = xfs_rui_init(tp->t_mountp, count); + memcpy(ruip->rui_format.rui_extents, extp, count * sizeof(*extp)); + atomic_set(&ruip->rui_next_extent, count); + xfs_trans_add_item(tp, &ruip->rui_item); + set_bit(XFS_LI_DIRTY, &ruip->rui_item.li_flags); + return &ruip->rui_item; +} + +static const struct xfs_item_ops xfs_rui_item_ops = { + .iop_size = xfs_rui_item_size, + .iop_format = xfs_rui_item_format, + .iop_unpin = xfs_rui_item_unpin, + .iop_release = xfs_rui_item_release, + .iop_relog = xfs_rui_item_relog, +}; + +/* + * Allocate and initialize an rui item with the given number of extents. + */ +struct xfs_rui_log_item * +xfs_rui_init( + struct xfs_mount *mp, + uint nextents) + +{ + struct xfs_rui_log_item *ruip; + + ASSERT(nextents > 0); + if (nextents > XFS_RUI_MAX_FAST_EXTENTS) + ruip = kmem_zalloc(xfs_rui_log_item_sizeof(nextents), 0); + else + ruip = kmem_zone_zalloc(xfs_rui_zone, 0); + + xfs_log_item_init(mp, &ruip->rui_item, XFS_LI_RUI, &xfs_rui_item_ops); + ruip->rui_format.rui_nextents = nextents; + ruip->rui_format.rui_id = (uintptr_t)(void *)ruip; + atomic_set(&ruip->rui_next_extent, 0); + atomic_set(&ruip->rui_refcount, 2); + + return ruip; +} diff --git a/fs/xfs/xfs_rmap_item.h b/fs/xfs/xfs_rmap_item.h index 8708e4a5aa5c3..5cf4acb0e915e 100644 --- a/fs/xfs/xfs_rmap_item.h +++ b/fs/xfs/xfs_rmap_item.h @@ -82,6 +82,7 @@ int xfs_rui_copy_format(struct xfs_log_iovec *buf, struct xfs_rui_log_format *dst_rui_fmt); void xfs_rui_item_free(struct xfs_rui_log_item *); void xfs_rui_release(struct xfs_rui_log_item *); -int xfs_rui_recover(struct xfs_mount *mp, struct xfs_rui_log_item *ruip); +int xfs_rui_recover(struct xfs_rui_log_item *ruip, + struct list_head *capture_list); #endif /* __XFS_RMAP_ITEM_H__ */ diff --git a/fs/xfs/xfs_stats.c b/fs/xfs/xfs_stats.c index f70f1255220b3..20e0534a772c9 100644 --- a/fs/xfs/xfs_stats.c +++ b/fs/xfs/xfs_stats.c @@ -23,6 +23,7 @@ int xfs_stats_format(struct xfsstats __percpu *stats, char *buf) uint64_t xs_xstrat_bytes = 0; uint64_t xs_write_bytes = 0; uint64_t xs_read_bytes = 0; + uint64_t defer_relog = 0; static const struct xstats_entry { char *desc; @@ -70,10 +71,13 @@ int xfs_stats_format(struct xfsstats __percpu *stats, char *buf) xs_xstrat_bytes += per_cpu_ptr(stats, i)->s.xs_xstrat_bytes; xs_write_bytes += per_cpu_ptr(stats, i)->s.xs_write_bytes; xs_read_bytes += per_cpu_ptr(stats, i)->s.xs_read_bytes; + defer_relog += per_cpu_ptr(stats, i)->s.defer_relog; } len += scnprintf(buf + len, PATH_MAX-len, "xpc %Lu %Lu %Lu\n", xs_xstrat_bytes, xs_write_bytes, xs_read_bytes); + len += scnprintf(buf + len, PATH_MAX-len, "defer_relog %llu\n", + defer_relog); len += scnprintf(buf + len, PATH_MAX-len, "debug %u\n", #if defined(DEBUG) 1); diff --git a/fs/xfs/xfs_stats.h b/fs/xfs/xfs_stats.h index 34d704f703d25..43ffba74f045e 100644 --- a/fs/xfs/xfs_stats.h +++ b/fs/xfs/xfs_stats.h @@ -137,6 +137,7 @@ struct __xfsstats { uint64_t xs_xstrat_bytes; uint64_t xs_write_bytes; uint64_t xs_read_bytes; + uint64_t defer_relog; }; #define xfsstats_offset(f) (offsetof(struct __xfsstats, f)/sizeof(uint32_t)) diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index f1407900aeef9..9e73d2b29911d 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -1914,13 +1914,13 @@ xfs_init_zones(void) if (!xfs_buf_item_zone) goto out_destroy_trans_zone; - xfs_efd_zone = kmem_zone_init((sizeof(xfs_efd_log_item_t) + + xfs_efd_zone = kmem_zone_init((sizeof(struct xfs_efd_log_item) + ((XFS_EFD_MAX_FAST_EXTENTS - 1) * sizeof(xfs_extent_t))), "xfs_efd_item"); if (!xfs_efd_zone) goto out_destroy_buf_item_zone; - xfs_efi_zone = kmem_zone_init((sizeof(xfs_efi_log_item_t) + + xfs_efi_zone = kmem_zone_init((sizeof(struct xfs_efi_log_item) + ((XFS_EFI_MAX_FAST_EXTENTS - 1) * sizeof(xfs_extent_t))), "xfs_efi_item"); if (!xfs_efi_zone) @@ -1934,8 +1934,8 @@ xfs_init_zones(void) goto out_destroy_efi_zone; xfs_ili_zone = - kmem_zone_init_flags(sizeof(xfs_inode_log_item_t), "xfs_ili", - KM_ZONE_SPREAD, NULL); + kmem_zone_init_flags(sizeof(struct xfs_inode_log_item), + "xfs_ili", KM_ZONE_SPREAD, NULL); if (!xfs_ili_zone) goto out_destroy_inode_zone; xfs_icreate_zone = kmem_zone_init(sizeof(struct xfs_icreate_item), diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h index f94908125e8f9..4b58183954064 100644 --- a/fs/xfs/xfs_trace.h +++ b/fs/xfs/xfs_trace.h @@ -2418,6 +2418,7 @@ DEFINE_DEFER_PENDING_EVENT(xfs_defer_create_intent); DEFINE_DEFER_PENDING_EVENT(xfs_defer_cancel_list); DEFINE_DEFER_PENDING_EVENT(xfs_defer_pending_finish); DEFINE_DEFER_PENDING_EVENT(xfs_defer_pending_abort); +DEFINE_DEFER_PENDING_EVENT(xfs_defer_relog_intent); #define DEFINE_BMAP_FREE_DEFERRED_EVENT DEFINE_PHYS_EXTENT_DEFERRED_EVENT DEFINE_BMAP_FREE_DEFERRED_EVENT(xfs_bmap_free_defer); diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h index 64d7f171ebd32..941647027f00f 100644 --- a/fs/xfs/xfs_trans.h +++ b/fs/xfs/xfs_trans.h @@ -77,6 +77,8 @@ struct xfs_item_ops { void (*iop_release)(struct xfs_log_item *); xfs_lsn_t (*iop_committed)(struct xfs_log_item *, xfs_lsn_t); void (*iop_error)(struct xfs_log_item *, xfs_buf_t *); + struct xfs_log_item *(*iop_relog)(struct xfs_log_item *intent, + struct xfs_trans *tp); }; /* @@ -244,4 +246,12 @@ void xfs_trans_buf_copy_type(struct xfs_buf *dst_bp, extern kmem_zone_t *xfs_trans_zone; +static inline struct xfs_log_item * +xfs_trans_item_relog( + struct xfs_log_item *lip, + struct xfs_trans *tp) +{ + return lip->li_ops->iop_relog(lip, tp); +} + #endif /* __XFS_TRANS_H__ */ diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index c7507135c2a05..311dd8e921826 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -7,6 +7,7 @@ #include #include #include +#include #include #include #include @@ -396,7 +397,10 @@ static inline struct hstate *hstate_sizelog(int page_size_log) if (!page_size_log) return &default_hstate; - return size_to_hstate(1UL << page_size_log); + if (page_size_log < BITS_PER_LONG) + return size_to_hstate(1UL << page_size_log); + + return NULL; } static inline struct hstate *hstate_vma(struct vm_area_struct *vma) @@ -744,4 +748,16 @@ static inline spinlock_t *huge_pte_lock(struct hstate *h, return ptl; } +#ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE +static inline bool hugetlb_pmd_shared(pte_t *pte) +{ + return page_count(virt_to_page(pte)) > 1; +} +#else +static inline bool hugetlb_pmd_shared(pte_t *pte) +{ + return false; +} +#endif + #endif /* _LINUX_HUGETLB_H */ diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 29bac5345563a..6ca3fb2873d7d 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -256,7 +256,7 @@ struct iommu_ops { int (*attach_dev)(struct iommu_domain *domain, struct device *dev); void (*detach_dev)(struct iommu_domain *domain, struct device *dev); int (*map)(struct iommu_domain *domain, unsigned long iova, - phys_addr_t paddr, size_t size, int prot); + phys_addr_t paddr, size_t size, int prot, gfp_t gfp); size_t (*unmap)(struct iommu_domain *domain, unsigned long iova, size_t size, struct iommu_iotlb_gather *iotlb_gather); void (*flush_iotlb_all)(struct iommu_domain *domain); @@ -421,6 +421,8 @@ extern struct iommu_domain *iommu_get_domain_for_dev(struct device *dev); extern struct iommu_domain *iommu_get_dma_domain(struct device *dev); extern int iommu_map(struct iommu_domain *domain, unsigned long iova, phys_addr_t paddr, size_t size, int prot); +extern int iommu_map_atomic(struct iommu_domain *domain, unsigned long iova, + phys_addr_t paddr, size_t size, int prot); extern size_t iommu_unmap(struct iommu_domain *domain, unsigned long iova, size_t size); extern size_t iommu_unmap_fast(struct iommu_domain *domain, @@ -428,6 +430,9 @@ extern size_t iommu_unmap_fast(struct iommu_domain *domain, struct iommu_iotlb_gather *iotlb_gather); extern size_t iommu_map_sg(struct iommu_domain *domain, unsigned long iova, struct scatterlist *sg,unsigned int nents, int prot); +extern size_t iommu_map_sg_atomic(struct iommu_domain *domain, + unsigned long iova, struct scatterlist *sg, + unsigned int nents, int prot); extern phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain, dma_addr_t iova); extern void iommu_set_fault_handler(struct iommu_domain *domain, iommu_fault_handler_t handler, void *token); @@ -662,6 +667,13 @@ static inline int iommu_map(struct iommu_domain *domain, unsigned long iova, return -ENODEV; } +static inline int iommu_map_atomic(struct iommu_domain *domain, + unsigned long iova, phys_addr_t paddr, + size_t size, int prot) +{ + return -ENODEV; +} + static inline size_t iommu_unmap(struct iommu_domain *domain, unsigned long iova, size_t size) { @@ -682,6 +694,13 @@ static inline size_t iommu_map_sg(struct iommu_domain *domain, return 0; } +static inline size_t iommu_map_sg_atomic(struct iommu_domain *domain, + unsigned long iova, struct scatterlist *sg, + unsigned int nents, int prot) +{ + return 0; +} + static inline void iommu_flush_tlb_all(struct iommu_domain *domain) { } diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 0b35747c9837a..88b107e20fc7c 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -178,6 +178,7 @@ struct plat_stmmacenet_data { int rss_en; int mac_port_sel_speed; bool en_tx_lpi_clockgating; + bool rx_clk_runs_in_lpi; int has_xgmac; bool sph_disable; }; diff --git a/include/net/sock.h b/include/net/sock.h index 5fa255b1e0a65..976433438c6f2 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2167,6 +2167,19 @@ static inline __must_check bool skb_set_owner_sk_safe(struct sk_buff *skb, struc return false; } +static inline struct sk_buff *skb_clone_and_charge_r(struct sk_buff *skb, struct sock *sk) +{ + skb = skb_clone(skb, sk_gfp_mask(sk, GFP_ATOMIC)); + if (skb) { + if (sk_rmem_schedule(sk, skb, skb->truesize)) { + skb_set_owner_r(skb, sk); + return skb; + } + __kfree_skb(skb); + } + return NULL; +} + void sk_reset_timer(struct sock *sk, struct timer_list *timer, unsigned long expires); diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index 9dd83eb74a9da..8c19a5438d0ee 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -1092,10 +1092,11 @@ void psi_trigger_destroy(struct psi_trigger *t) group = t->group; /* - * Wakeup waiters to stop polling. Can happen if cgroup is deleted - * from under a polling process. + * Wakeup waiters to stop polling and clear the queue to prevent it from + * being accessed later. Can happen if cgroup is deleted from under a + * polling process. */ - wake_up_interruptible(&t->event_wait); + wake_up_pollfree(&t->event_wait); mutex_lock(&group->trigger_lock); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 8b87f1f74e325..306fbe14747bf 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -8298,9 +8298,6 @@ buffer_percent_write(struct file *filp, const char __user *ubuf, if (val > 100) return -EINVAL; - if (!val) - val = 1; - tr->buffer_percent = val; (*ppos)++; diff --git a/mm/memblock.c b/mm/memblock.c index 84a14b63e9129..a75cc65f03307 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -1546,13 +1546,7 @@ void __init __memblock_free_late(phys_addr_t base, phys_addr_t size) end = PFN_DOWN(base + size); for (; cursor < end; cursor++) { - /* - * Reserved pages are always initialized by the end of - * memblock_free_all() (by memmap_init() and, if deferred - * initialization is enabled, memmap_init_reserved_pages()), so - * these pages can be released directly to the buddy allocator. - */ - __free_pages_core(pfn_to_page(cursor), 0); + memblock_free_pages(pfn_to_page(cursor), cursor, 0); totalram_pages_inc(); } } diff --git a/mm/mempolicy.c b/mm/mempolicy.c index f7b231f67156b..36c2a9619ba56 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -571,7 +571,8 @@ static int queue_pages_hugetlb(pte_t *pte, unsigned long hmask, goto unlock; /* With MPOL_MF_MOVE, we migrate only unshared hugepage. */ if (flags & (MPOL_MF_MOVE_ALL) || - (flags & MPOL_MF_MOVE && page_mapcount(page) == 1)) + (flags & MPOL_MF_MOVE && page_mapcount(page) == 1 && + !hugetlb_pmd_shared(pte))) isolate_huge_page(page, qp->pagelist); unlock: spin_unlock(ptl); diff --git a/mm/swapfile.c b/mm/swapfile.c index f6964212c6c8f..d6bdacaedc95c 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -1061,6 +1061,7 @@ start_over: goto check_out; pr_debug("scan_swap_map of si %d failed to find offset\n", si->type); + cond_resched(); spin_lock(&swap_avail_lock); nextsi: @@ -1950,10 +1951,14 @@ static int unuse_pte_range(struct vm_area_struct *vma, pmd_t *pmd, pte_unmap(pte); swap_map = &si->swap_map[offset]; - vmf.vma = vma; - vmf.address = addr; - vmf.pmd = pmd; - page = swapin_readahead(entry, GFP_HIGHUSER_MOVABLE, &vmf); + page = lookup_swap_cache(entry, vma, addr); + if (!page) { + vmf.vma = vma; + vmf.address = addr; + vmf.pmd = pmd; + page = swapin_readahead(entry, GFP_HIGHUSER_MOVABLE, + &vmf); + } if (!page) { if (*swap_map == 0 || *swap_map == SWAP_MAP_BAD) goto try_next; diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index 01e33724d10c3..43cb7aab4eed6 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -871,6 +871,7 @@ static unsigned int ip_sabotage_in(void *priv, if (nf_bridge && !nf_bridge->in_prerouting && !netif_is_l3_master(skb->dev) && !netif_is_l3_slave(skb->dev)) { + nf_bridge_info_free(skb); state->okfn(state->net, state->sk, skb); return NF_STOLEN; } diff --git a/net/can/j1939/address-claim.c b/net/can/j1939/address-claim.c index f33c473279278..ca4ad6cdd5cbf 100644 --- a/net/can/j1939/address-claim.c +++ b/net/can/j1939/address-claim.c @@ -165,6 +165,46 @@ static void j1939_ac_process(struct j1939_priv *priv, struct sk_buff *skb) * leaving this function. */ ecu = j1939_ecu_get_by_name_locked(priv, name); + + if (ecu && ecu->addr == skcb->addr.sa) { + /* The ISO 11783-5 standard, in "4.5.2 - Address claim + * requirements", states: + * d) No CF shall begin, or resume, transmission on the + * network until 250 ms after it has successfully claimed + * an address except when responding to a request for + * address-claimed. + * + * But "Figure 6" and "Figure 7" in "4.5.4.2 - Address-claim + * prioritization" show that the CF begins the transmission + * after 250 ms from the first AC (address-claimed) message + * even if it sends another AC message during that time window + * to resolve the address contention with another CF. + * + * As stated in "4.4.2.3 - Address-claimed message": + * In order to successfully claim an address, the CF sending + * an address claimed message shall not receive a contending + * claim from another CF for at least 250 ms. + * + * As stated in "4.4.3.2 - NAME management (NM) message": + * 1) A commanding CF can + * d) request that a CF with a specified NAME transmit + * the address-claimed message with its current NAME. + * 2) A target CF shall + * d) send an address-claimed message in response to a + * request for a matching NAME + * + * Taking the above arguments into account, the 250 ms wait is + * requested only during network initialization. + * + * Do not restart the timer on AC message if both the NAME and + * the address match and so if the address has already been + * claimed (timer has expired) or the AC message has been sent + * to resolve the contention with another CF (timer is still + * running). + */ + goto out_ecu_put; + } + if (!ecu && j1939_address_is_unicast(skcb->addr.sa)) ecu = j1939_ecu_create_locked(priv, name); diff --git a/net/can/j1939/transport.c b/net/can/j1939/transport.c index 9ca19dfe3e839..9c8c7c5dc9c36 100644 --- a/net/can/j1939/transport.c +++ b/net/can/j1939/transport.c @@ -1087,10 +1087,6 @@ static bool j1939_session_deactivate(struct j1939_session *session) bool active; j1939_session_list_lock(priv); - /* This function should be called with a session ref-count of at - * least 2. - */ - WARN_ON_ONCE(kref_read(&session->kref) < 2); active = j1939_session_deactivate_locked(session); j1939_session_list_unlock(priv); diff --git a/net/core/dev.c b/net/core/dev.c index 296bed9431f3b..615cdaac3e729 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -9467,7 +9467,7 @@ void netdev_stats_to_stats64(struct rtnl_link_stats64 *stats64, BUILD_BUG_ON(n > sizeof(*stats64) / sizeof(u64)); for (i = 0; i < n; i++) - dst[i] = atomic_long_read(&src[i]); + dst[i] = (unsigned long)atomic_long_read(&src[i]); /* zero out counters that only exist in rtnl_link_stats64 */ memset((char *)stats64 + n * sizeof(u64), 0, sizeof(*stats64) - n * sizeof(u64)); diff --git a/net/core/filter.c b/net/core/filter.c index 71fcb4e7edae4..051b9710d7b5e 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -4617,7 +4617,6 @@ static int bpf_fib_set_fwd_params(struct bpf_fib_lookup *params, memcpy(params->smac, dev->dev_addr, ETH_ALEN); params->h_vlan_TCI = 0; params->h_vlan_proto = 0; - params->ifindex = dev->ifindex; return 0; } @@ -4714,6 +4713,7 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params, dev = nhc->nhc_dev; params->rt_metric = res.fi->fib_priority; + params->ifindex = dev->ifindex; /* xdp and cls_bpf programs are run in RCU-bh so * rcu_read_lock_bh is not needed here @@ -4839,6 +4839,7 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params, dev = res.nh->fib_nh_dev; params->rt_metric = res.f6i->fib6_metric; + params->ifindex = dev->ifindex; /* xdp and cls_bpf programs are run in RCU-bh so rcu_read_lock_bh is * not needed here. diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 1bf267d36a9c8..c2844fb442c4f 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -541,11 +541,9 @@ static struct sock *dccp_v6_request_recv_sock(const struct sock *sk, *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash), NULL); /* Clone pktoptions received with SYN, if we own the req */ if (*own_req && ireq->pktopts) { - newnp->pktoptions = skb_clone(ireq->pktopts, GFP_ATOMIC); + newnp->pktoptions = skb_clone_and_charge_r(ireq->pktopts, newsk); consume_skb(ireq->pktopts); ireq->pktopts = NULL; - if (newnp->pktoptions) - skb_set_owner_r(newnp->pktoptions, newsk); } return newsk; @@ -605,7 +603,7 @@ static int dccp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) --ANK (980728) */ if (np->rxopt.all) - opt_skb = skb_clone(skb, GFP_ATOMIC); + opt_skb = skb_clone_and_charge_r(skb, sk); if (sk->sk_state == DCCP_OPEN) { /* Fast path */ if (dccp_rcv_established(sk, skb, dccp_hdr(skb), skb->len)) @@ -669,7 +667,6 @@ ipv6_pktoptions: np->flow_label = ip6_flowlabel(ipv6_hdr(opt_skb)); if (ipv6_opt_accepted(sk, opt_skb, &DCCP_SKB_CB(opt_skb)->header.h6)) { - skb_set_owner_r(opt_skb, sk); memmove(IP6CB(opt_skb), &DCCP_SKB_CB(opt_skb)->header.h6, sizeof(struct inet6_skb_parm)); diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 390bedde21a56..06261603e083b 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -50,7 +50,7 @@ static void ip6_datagram_flow_key_init(struct flowi6 *fl6, struct sock *sk) fl6->flowi6_mark = sk->sk_mark; fl6->fl6_dport = inet->inet_dport; fl6->fl6_sport = inet->inet_sport; - fl6->flowlabel = np->flow_label; + fl6->flowlabel = ip6_make_flowinfo(np->tclass, np->flow_label); fl6->flowi6_uid = sk->sk_uid; if (!fl6->flowi6_oif) diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index e84b79357b2ff..da8611a75d2aa 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -264,6 +264,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, fl6.flowi6_proto = IPPROTO_TCP; fl6.daddr = sk->sk_v6_daddr; fl6.saddr = saddr ? *saddr : np->saddr; + fl6.flowlabel = ip6_make_flowinfo(np->tclass, np->flow_label); fl6.flowi6_oif = sk->sk_bound_dev_if; fl6.flowi6_mark = sk->sk_mark; fl6.fl6_dport = usin->sin6_port; @@ -1318,14 +1319,11 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff * /* Clone pktoptions received with SYN, if we own the req */ if (ireq->pktopts) { - newnp->pktoptions = skb_clone(ireq->pktopts, - sk_gfp_mask(sk, GFP_ATOMIC)); + newnp->pktoptions = skb_clone_and_charge_r(ireq->pktopts, newsk); consume_skb(ireq->pktopts); ireq->pktopts = NULL; - if (newnp->pktoptions) { + if (newnp->pktoptions) tcp_v6_restore_cb(newnp->pktoptions); - skb_set_owner_r(newnp->pktoptions, newsk); - } } } else { if (!req_unhash && found_dup_sk) { @@ -1393,7 +1391,7 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) --ANK (980728) */ if (np->rxopt.all) - opt_skb = skb_clone(skb, sk_gfp_mask(sk, GFP_ATOMIC)); + opt_skb = skb_clone_and_charge_r(skb, sk); if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */ struct dst_entry *dst; @@ -1475,7 +1473,6 @@ ipv6_pktoptions: if (np->repflow) np->flow_label = ip6_flowlabel(ipv6_hdr(opt_skb)); if (ipv6_opt_accepted(sk, opt_skb, &TCP_SKB_CB(opt_skb)->header.h6)) { - skb_set_owner_r(opt_skb, sk); tcp_v6_restore_cb(opt_skb); opt_skb = xchg(&np->pktoptions, opt_skb); } else { diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index d5e3656fc67ca..3a55a392e0218 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -1428,6 +1428,7 @@ static int mpls_dev_sysctl_register(struct net_device *dev, free: kfree(table); out: + mdev->sysctl = NULL; return -ENOBUFS; } @@ -1437,6 +1438,9 @@ static void mpls_dev_sysctl_unregister(struct net_device *dev, struct net *net = dev_net(dev); struct ctl_table *table; + if (!mdev->sysctl) + return; + table = mdev->sysctl->ctl_table_arg; unregister_net_sysctl_table(mdev->sysctl); kfree(table); diff --git a/net/netfilter/nft_tproxy.c b/net/netfilter/nft_tproxy.c index b97ab1198b03f..a0e30bf4a845c 100644 --- a/net/netfilter/nft_tproxy.c +++ b/net/netfilter/nft_tproxy.c @@ -289,6 +289,13 @@ static int nft_tproxy_dump(struct sk_buff *skb, return 0; } +static int nft_tproxy_validate(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nft_data **data) +{ + return nft_chain_validate_hooks(ctx->chain, 1 << NF_INET_PRE_ROUTING); +} + static struct nft_expr_type nft_tproxy_type; static const struct nft_expr_ops nft_tproxy_ops = { .type = &nft_tproxy_type, @@ -296,6 +303,7 @@ static const struct nft_expr_ops nft_tproxy_ops = { .eval = nft_tproxy_eval, .init = nft_tproxy_init, .dump = nft_tproxy_dump, + .validate = nft_tproxy_validate, }; static struct nft_expr_type nft_tproxy_type __read_mostly = { diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index 58d5373c513c7..7da77ddba5f4d 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -378,6 +378,11 @@ static int nr_listen(struct socket *sock, int backlog) struct sock *sk = sock->sk; lock_sock(sk); + if (sock->state != SS_UNCONNECTED) { + release_sock(sk); + return -EINVAL; + } + if (sk->sk_state != TCP_LISTEN) { memset(&nr_sk(sk)->user_addr, 0, AX25_ADDR_LEN); sk->sk_max_ack_backlog = backlog; diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index a8a8396dd9838..4c537e74b18c7 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -941,14 +941,14 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info) key = kzalloc(sizeof(*key), GFP_KERNEL); if (!key) { error = -ENOMEM; - goto err_kfree_key; + goto err_kfree_flow; } ovs_match_init(&match, key, false, &mask); error = ovs_nla_get_match(net, &match, a[OVS_FLOW_ATTR_KEY], a[OVS_FLOW_ATTR_MASK], log); if (error) - goto err_kfree_flow; + goto err_kfree_key; ovs_flow_mask_key(&new_flow->key, key, true, &mask); @@ -956,14 +956,14 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info) error = ovs_nla_get_identifier(&new_flow->id, a[OVS_FLOW_ATTR_UFID], key, log); if (error) - goto err_kfree_flow; + goto err_kfree_key; /* Validate actions. */ error = ovs_nla_copy_actions(net, a[OVS_FLOW_ATTR_ACTIONS], &new_flow->key, &acts, log); if (error) { OVS_NLERR(log, "Flow actions may not be safe on all matching packets."); - goto err_kfree_flow; + goto err_kfree_key; } reply = ovs_flow_cmd_alloc_info(acts, &new_flow->id, info, false, @@ -1063,10 +1063,10 @@ err_unlock_ovs: kfree_skb(reply); err_kfree_acts: ovs_nla_free_flow_actions(acts); -err_kfree_flow: - ovs_flow_free(new_flow, false); err_kfree_key: kfree(key); +err_kfree_flow: + ovs_flow_free(new_flow, false); error: return error; } diff --git a/net/rds/message.c b/net/rds/message.c index 92b6b22884d4c..be6a0a073b12a 100644 --- a/net/rds/message.c +++ b/net/rds/message.c @@ -104,9 +104,9 @@ static void rds_rm_zerocopy_callback(struct rds_sock *rs, spin_lock_irqsave(&q->lock, flags); head = &q->zcookie_head; if (!list_empty(head)) { - info = list_entry(head, struct rds_msg_zcopy_info, - rs_zcookie_next); - if (info && rds_zcookie_add(info, cookie)) { + info = list_first_entry(head, struct rds_msg_zcopy_info, + rs_zcookie_next); + if (rds_zcookie_add(info, cookie)) { spin_unlock_irqrestore(&q->lock, flags); kfree(rds_info_from_znotifier(znotif)); /* caller invokes rds_wake_sk_sleep() */ diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c index 95dda29058a0e..6fb158172ddc2 100644 --- a/net/rose/af_rose.c +++ b/net/rose/af_rose.c @@ -465,6 +465,12 @@ static int rose_listen(struct socket *sock, int backlog) { struct sock *sk = sock->sk; + lock_sock(sk); + if (sock->state != SS_UNCONNECTED) { + release_sock(sk); + return -EINVAL; + } + if (sk->sk_state != TCP_LISTEN) { struct rose_sock *rose = rose_sk(sk); @@ -474,8 +480,10 @@ static int rose_listen(struct socket *sock, int backlog) memset(rose->dest_digis, 0, AX25_ADDR_LEN * ROSE_MAX_DIGIS); sk->sk_max_ack_backlog = backlog; sk->sk_state = TCP_LISTEN; + release_sock(sk); return 0; } + release_sock(sk); return -EOPNOTSUPP; } diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 8184c87da8bec..27cb82b6237da 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -405,7 +405,10 @@ static void htb_activate_prios(struct htb_sched *q, struct htb_class *cl) while (cl->cmode == HTB_MAY_BORROW && p && mask) { m = mask; while (m) { - int prio = ffz(~m); + unsigned int prio = ffz(~m); + + if (WARN_ON_ONCE(prio >= ARRAY_SIZE(p->inner.clprio))) + break; m &= ~(1 << prio); if (p->inner.clprio[prio].feed.rb_node) diff --git a/net/sctp/diag.c b/net/sctp/diag.c index 5a918e74bb82b..2d0318a7352c2 100644 --- a/net/sctp/diag.c +++ b/net/sctp/diag.c @@ -349,11 +349,9 @@ static int sctp_sock_filter(struct sctp_endpoint *ep, struct sctp_transport *tsp struct sctp_comm_param *commp = p; struct sock *sk = ep->base.sk; const struct inet_diag_req_v2 *r = commp->r; - struct sctp_association *assoc = - list_entry(ep->asocs.next, struct sctp_association, asocs); /* find the ep only once through the transports by this condition */ - if (tsp->asoc != assoc) + if (!list_is_first(&tsp->asoc->asocs, &ep->asocs)) return 0; if (r->sdiag_family != AF_UNSPEC && sk->sk_family != r->sdiag_family) diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index 0f4d39fdb48f2..cfae1a871578f 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -1034,9 +1034,9 @@ struct rpcrdma_req *rpcrdma_req_create(struct rpcrdma_xprt *r_xprt, size_t size, return req; out4: - kfree(req->rl_sendbuf); + rpcrdma_regbuf_free(req->rl_sendbuf); out3: - kfree(req->rl_rdmabuf); + rpcrdma_regbuf_free(req->rl_rdmabuf); out2: kfree(req); out1: diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index c94aa587e0c92..43dd489ad6db9 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -492,6 +492,12 @@ static int x25_listen(struct socket *sock, int backlog) int rc = -EOPNOTSUPP; lock_sock(sk); + if (sock->state != SS_UNCONNECTED) { + rc = -EINVAL; + release_sock(sk); + return rc; + } + if (sk->sk_state != TCP_LISTEN) { memset(&x25_sk(sk)->dest_addr, 0, X25_ADDR_LEN); sk->sk_max_ack_backlog = backlog; diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index e120df0a6da13..4d8d7cf3d1994 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -274,8 +274,7 @@ static int xfrm6_remove_tunnel_encap(struct xfrm_state *x, struct sk_buff *skb) goto out; if (x->props.flags & XFRM_STATE_DECAP_DSCP) - ipv6_copy_dscp(ipv6_get_dsfield(ipv6_hdr(skb)), - ipipv6_hdr(skb)); + ipv6_copy_dscp(XFRM_MODE_SKB_CB(skb)->tos, ipipv6_hdr(skb)); if (!(x->props.flags & XFRM_STATE_NOECN)) ipip6_ecn_decapsulate(skb); diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c index d181dc31cd8d6..51f65d634a15e 100644 --- a/sound/pci/hda/patch_conexant.c +++ b/sound/pci/hda/patch_conexant.c @@ -1093,6 +1093,7 @@ static const struct hda_device_id snd_hda_id_conexant[] = { HDA_CODEC_ENTRY(0x14f11f86, "CX8070", patch_conexant_auto), HDA_CODEC_ENTRY(0x14f12008, "CX8200", patch_conexant_auto), HDA_CODEC_ENTRY(0x14f120d0, "CX11970", patch_conexant_auto), + HDA_CODEC_ENTRY(0x14f120d1, "SN6180", patch_conexant_auto), HDA_CODEC_ENTRY(0x14f15045, "CX20549 (Venice)", patch_conexant_auto), HDA_CODEC_ENTRY(0x14f15047, "CX20551 (Waikiki)", patch_conexant_auto), HDA_CODEC_ENTRY(0x14f15051, "CX20561 (Hermosa)", patch_conexant_auto), diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 413d4886f3d28..75c1645dd5c14 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -770,7 +770,7 @@ do_sku: alc_setup_gpio(codec, 0x02); break; case 7: - alc_setup_gpio(codec, 0x03); + alc_setup_gpio(codec, 0x04); break; case 5: default: diff --git a/sound/pci/hda/patch_via.c b/sound/pci/hda/patch_via.c index 3edb4e25797de..4a74ccf7cf3e6 100644 --- a/sound/pci/hda/patch_via.c +++ b/sound/pci/hda/patch_via.c @@ -821,6 +821,9 @@ static int add_secret_dac_path(struct hda_codec *codec) return 0; nums = snd_hda_get_connections(codec, spec->gen.mixer_nid, conn, ARRAY_SIZE(conn) - 1); + if (nums < 0) + return nums; + for (i = 0; i < nums; i++) { if (get_wcaps_type(get_wcaps(codec, conn[i])) == AC_WID_AUD_OUT) return 0; diff --git a/sound/pci/lx6464es/lx_core.c b/sound/pci/lx6464es/lx_core.c index dd3a873777eb5..00975e86473c5 100644 --- a/sound/pci/lx6464es/lx_core.c +++ b/sound/pci/lx6464es/lx_core.c @@ -493,12 +493,11 @@ int lx_buffer_ask(struct lx6464es *chip, u32 pipe, int is_capture, dev_dbg(chip->card->dev, "CMD_08_ASK_BUFFERS: needed %d, freed %d\n", *r_needed, *r_freed); - for (i = 0; i < MAX_STREAM_BUFFER; ++i) { - for (i = 0; i != chip->rmh.stat_len; ++i) - dev_dbg(chip->card->dev, - " stat[%d]: %x, %x\n", i, - chip->rmh.stat[i], - chip->rmh.stat[i] & MASK_DATA_SIZE); + for (i = 0; i < MAX_STREAM_BUFFER && i < chip->rmh.stat_len; + ++i) { + dev_dbg(chip->card->dev, " stat[%d]: %x, %x\n", i, + chip->rmh.stat[i], + chip->rmh.stat[i] & MASK_DATA_SIZE); } } diff --git a/sound/soc/codecs/cs42l56.c b/sound/soc/codecs/cs42l56.c index 8be7d83f0ce9a..732405587c5a4 100644 --- a/sound/soc/codecs/cs42l56.c +++ b/sound/soc/codecs/cs42l56.c @@ -1192,18 +1192,12 @@ static int cs42l56_i2c_probe(struct i2c_client *i2c_client, if (pdata) { cs42l56->pdata = *pdata; } else { - pdata = devm_kzalloc(&i2c_client->dev, sizeof(*pdata), - GFP_KERNEL); - if (!pdata) - return -ENOMEM; - if (i2c_client->dev.of_node) { ret = cs42l56_handle_of_data(i2c_client, &cs42l56->pdata); if (ret != 0) return ret; } - cs42l56->pdata = *pdata; } if (cs42l56->pdata.gpio_nreset) { diff --git a/sound/soc/intel/boards/bytcr_rt5651.c b/sound/soc/intel/boards/bytcr_rt5651.c index 921c09cdb4800..0c1c8628b9917 100644 --- a/sound/soc/intel/boards/bytcr_rt5651.c +++ b/sound/soc/intel/boards/bytcr_rt5651.c @@ -919,7 +919,6 @@ static int snd_byt_rt5651_mc_probe(struct platform_device *pdev) if (adev) { snprintf(byt_rt5651_codec_name, sizeof(byt_rt5651_codec_name), "i2c-%s", acpi_dev_name(adev)); - put_device(&adev->dev); byt_rt5651_dais[dai_index].codecs->name = byt_rt5651_codec_name; } else { dev_err(&pdev->dev, "Error cannot find '%s' dev\n", mach->id); @@ -928,6 +927,7 @@ static int snd_byt_rt5651_mc_probe(struct platform_device *pdev) codec_dev = bus_find_device_by_name(&i2c_bus_type, NULL, byt_rt5651_codec_name); + acpi_dev_put(adev); if (!codec_dev) return -EPROBE_DEFER; diff --git a/sound/soc/sof/intel/hda-dai.c b/sound/soc/sof/intel/hda-dai.c index b3cdd10c83ae1..c30e450fa9702 100644 --- a/sound/soc/sof/intel/hda-dai.c +++ b/sound/soc/sof/intel/hda-dai.c @@ -211,6 +211,10 @@ static int hda_link_hw_params(struct snd_pcm_substream *substream, int stream_tag; int ret; + link = snd_hdac_ext_bus_get_link(bus, codec_dai->component->name); + if (!link) + return -EINVAL; + /* get stored dma data if resuming from system suspend */ link_dev = snd_soc_dai_get_dma_data(dai, substream); if (!link_dev) { @@ -231,10 +235,6 @@ static int hda_link_hw_params(struct snd_pcm_substream *substream, if (ret < 0) return ret; - link = snd_hdac_ext_bus_get_link(bus, codec_dai->component->name); - if (!link) - return -EINVAL; - /* set the stream tag in the codec dai dma params */ if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) snd_soc_dai_set_tdm_slot(codec_dai, stream_tag, 0, 0, 0); diff --git a/sound/synth/emux/emux_nrpn.c b/sound/synth/emux/emux_nrpn.c index 1ac22676d4648..641dc02ff709e 100644 --- a/sound/synth/emux/emux_nrpn.c +++ b/sound/synth/emux/emux_nrpn.c @@ -349,6 +349,9 @@ int snd_emux_xg_control(struct snd_emux_port *port, struct snd_midi_channel *chan, int param) { + if (param >= ARRAY_SIZE(chan->control)) + return -EINVAL; + return send_converted_effect(xg_effects, ARRAY_SIZE(xg_effects), port, chan, param, chan->control[param], diff --git a/tools/testing/selftests/bpf/verifier/search_pruning.c b/tools/testing/selftests/bpf/verifier/search_pruning.c index 7e50cb80873a5..7e36078f8f482 100644 --- a/tools/testing/selftests/bpf/verifier/search_pruning.c +++ b/tools/testing/selftests/bpf/verifier/search_pruning.c @@ -154,3 +154,39 @@ .result_unpriv = ACCEPT, .insn_processed = 15, }, +/* The test performs a conditional 64-bit write to a stack location + * fp[-8], this is followed by an unconditional 8-bit write to fp[-8], + * then data is read from fp[-8]. This sequence is unsafe. + * + * The test would be mistakenly marked as safe w/o dst register parent + * preservation in verifier.c:copy_register_state() function. + * + * Note the usage of BPF_F_TEST_STATE_FREQ to force creation of the + * checkpoint state after conditional 64-bit assignment. + */ +{ + "write tracking and register parent chain bug", + .insns = { + /* r6 = ktime_get_ns() */ + BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_0), + /* r0 = ktime_get_ns() */ + BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns), + /* if r0 > r6 goto +1 */ + BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_6, 1), + /* *(u64 *)(r10 - 8) = 0xdeadbeef */ + BPF_ST_MEM(BPF_DW, BPF_REG_FP, -8, 0xdeadbeef), + /* r1 = 42 */ + BPF_MOV64_IMM(BPF_REG_1, 42), + /* *(u8 *)(r10 - 8) = r1 */ + BPF_STX_MEM(BPF_B, BPF_REG_FP, BPF_REG_1, -8), + /* r2 = *(u64 *)(r10 - 8) */ + BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_FP, -8), + /* exit(0) */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .flags = BPF_F_TEST_STATE_FREQ, + .errstr = "invalid read from stack off -8+1 size 8", + .result = REJECT, +}, diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh new file mode 100644 index 0000000000000..6986086035d6c --- /dev/null +++ b/tools/testing/selftests/net/fib_tests.sh @@ -0,0 +1,1727 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# This test is for checking IPv4 and IPv6 FIB behavior in response to +# different events. + +ret=0 +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + +# all tests in this script. Can be overridden with -t option +TESTS="unregister down carrier nexthop suppress ipv6_rt ipv4_rt ipv6_addr_metric ipv4_addr_metric ipv6_route_metrics ipv4_route_metrics ipv4_route_v6_gw rp_filter" + +VERBOSE=0 +PAUSE_ON_FAIL=no +PAUSE=no +IP="ip -netns ns1" +NS_EXEC="ip netns exec ns1" + +which ping6 > /dev/null 2>&1 && ping6=$(which ping6) || ping6=$(which ping) + +log_test() +{ + local rc=$1 + local expected=$2 + local msg="$3" + + if [ ${rc} -eq ${expected} ]; then + printf " TEST: %-60s [ OK ]\n" "${msg}" + nsuccess=$((nsuccess+1)) + else + ret=1 + nfail=$((nfail+1)) + printf " TEST: %-60s [FAIL]\n" "${msg}" + if [ "${PAUSE_ON_FAIL}" = "yes" ]; then + echo + echo "hit enter to continue, 'q' to quit" + read a + [ "$a" = "q" ] && exit 1 + fi + fi + + if [ "${PAUSE}" = "yes" ]; then + echo + echo "hit enter to continue, 'q' to quit" + read a + [ "$a" = "q" ] && exit 1 + fi +} + +setup() +{ + set -e + ip netns add ns1 + ip netns set ns1 auto + $IP link set dev lo up + ip netns exec ns1 sysctl -qw net.ipv4.ip_forward=1 + ip netns exec ns1 sysctl -qw net.ipv6.conf.all.forwarding=1 + + $IP link add dummy0 type dummy + $IP link set dev dummy0 up + $IP address add 198.51.100.1/24 dev dummy0 + $IP -6 address add 2001:db8:1::1/64 dev dummy0 + set +e + +} + +cleanup() +{ + $IP link del dev dummy0 &> /dev/null + ip netns del ns1 + ip netns del ns2 &> /dev/null +} + +get_linklocal() +{ + local dev=$1 + local addr + + addr=$($IP -6 -br addr show dev ${dev} | \ + awk '{ + for (i = 3; i <= NF; ++i) { + if ($i ~ /^fe80/) + print $i + } + }' + ) + addr=${addr/\/*} + + [ -z "$addr" ] && return 1 + + echo $addr + + return 0 +} + +fib_unreg_unicast_test() +{ + echo + echo "Single path route test" + + setup + + echo " Start point" + $IP route get fibmatch 198.51.100.2 &> /dev/null + log_test $? 0 "IPv4 fibmatch" + $IP -6 route get fibmatch 2001:db8:1::2 &> /dev/null + log_test $? 0 "IPv6 fibmatch" + + set -e + $IP link del dev dummy0 + set +e + + echo " Nexthop device deleted" + $IP route get fibmatch 198.51.100.2 &> /dev/null + log_test $? 2 "IPv4 fibmatch - no route" + $IP -6 route get fibmatch 2001:db8:1::2 &> /dev/null + log_test $? 2 "IPv6 fibmatch - no route" + + cleanup +} + +fib_unreg_multipath_test() +{ + + echo + echo "Multipath route test" + + setup + + set -e + $IP link add dummy1 type dummy + $IP link set dev dummy1 up + $IP address add 192.0.2.1/24 dev dummy1 + $IP -6 address add 2001:db8:2::1/64 dev dummy1 + + $IP route add 203.0.113.0/24 \ + nexthop via 198.51.100.2 dev dummy0 \ + nexthop via 192.0.2.2 dev dummy1 + $IP -6 route add 2001:db8:3::/64 \ + nexthop via 2001:db8:1::2 dev dummy0 \ + nexthop via 2001:db8:2::2 dev dummy1 + set +e + + echo " Start point" + $IP route get fibmatch 203.0.113.1 &> /dev/null + log_test $? 0 "IPv4 fibmatch" + $IP -6 route get fibmatch 2001:db8:3::1 &> /dev/null + log_test $? 0 "IPv6 fibmatch" + + set -e + $IP link del dev dummy0 + set +e + + echo " One nexthop device deleted" + $IP route get fibmatch 203.0.113.1 &> /dev/null + log_test $? 2 "IPv4 - multipath route removed on delete" + + $IP -6 route get fibmatch 2001:db8:3::1 &> /dev/null + # In IPv6 we do not flush the entire multipath route. + log_test $? 0 "IPv6 - multipath down to single path" + + set -e + $IP link del dev dummy1 + set +e + + echo " Second nexthop device deleted" + $IP -6 route get fibmatch 2001:db8:3::1 &> /dev/null + log_test $? 2 "IPv6 - no route" + + cleanup +} + +fib_unreg_test() +{ + fib_unreg_unicast_test + fib_unreg_multipath_test +} + +fib_down_unicast_test() +{ + echo + echo "Single path, admin down" + + setup + + echo " Start point" + $IP route get fibmatch 198.51.100.2 &> /dev/null + log_test $? 0 "IPv4 fibmatch" + $IP -6 route get fibmatch 2001:db8:1::2 &> /dev/null + log_test $? 0 "IPv6 fibmatch" + + set -e + $IP link set dev dummy0 down + set +e + + echo " Route deleted on down" + $IP route get fibmatch 198.51.100.2 &> /dev/null + log_test $? 2 "IPv4 fibmatch" + $IP -6 route get fibmatch 2001:db8:1::2 &> /dev/null + log_test $? 2 "IPv6 fibmatch" + + cleanup +} + +fib_down_multipath_test_do() +{ + local down_dev=$1 + local up_dev=$2 + + $IP route get fibmatch 203.0.113.1 \ + oif $down_dev &> /dev/null + log_test $? 2 "IPv4 fibmatch on down device" + $IP -6 route get fibmatch 2001:db8:3::1 \ + oif $down_dev &> /dev/null + log_test $? 2 "IPv6 fibmatch on down device" + + $IP route get fibmatch 203.0.113.1 \ + oif $up_dev &> /dev/null + log_test $? 0 "IPv4 fibmatch on up device" + $IP -6 route get fibmatch 2001:db8:3::1 \ + oif $up_dev &> /dev/null + log_test $? 0 "IPv6 fibmatch on up device" + + $IP route get fibmatch 203.0.113.1 | \ + grep $down_dev | grep -q "dead linkdown" + log_test $? 0 "IPv4 flags on down device" + $IP -6 route get fibmatch 2001:db8:3::1 | \ + grep $down_dev | grep -q "dead linkdown" + log_test $? 0 "IPv6 flags on down device" + + $IP route get fibmatch 203.0.113.1 | \ + grep $up_dev | grep -q "dead linkdown" + log_test $? 1 "IPv4 flags on up device" + $IP -6 route get fibmatch 2001:db8:3::1 | \ + grep $up_dev | grep -q "dead linkdown" + log_test $? 1 "IPv6 flags on up device" +} + +fib_down_multipath_test() +{ + echo + echo "Admin down multipath" + + setup + + set -e + $IP link add dummy1 type dummy + $IP link set dev dummy1 up + + $IP address add 192.0.2.1/24 dev dummy1 + $IP -6 address add 2001:db8:2::1/64 dev dummy1 + + $IP route add 203.0.113.0/24 \ + nexthop via 198.51.100.2 dev dummy0 \ + nexthop via 192.0.2.2 dev dummy1 + $IP -6 route add 2001:db8:3::/64 \ + nexthop via 2001:db8:1::2 dev dummy0 \ + nexthop via 2001:db8:2::2 dev dummy1 + set +e + + echo " Verify start point" + $IP route get fibmatch 203.0.113.1 &> /dev/null + log_test $? 0 "IPv4 fibmatch" + + $IP -6 route get fibmatch 2001:db8:3::1 &> /dev/null + log_test $? 0 "IPv6 fibmatch" + + set -e + $IP link set dev dummy0 down + set +e + + echo " One device down, one up" + fib_down_multipath_test_do "dummy0" "dummy1" + + set -e + $IP link set dev dummy0 up + $IP link set dev dummy1 down + set +e + + echo " Other device down and up" + fib_down_multipath_test_do "dummy1" "dummy0" + + set -e + $IP link set dev dummy0 down + set +e + + echo " Both devices down" + $IP route get fibmatch 203.0.113.1 &> /dev/null + log_test $? 2 "IPv4 fibmatch" + $IP -6 route get fibmatch 2001:db8:3::1 &> /dev/null + log_test $? 2 "IPv6 fibmatch" + + $IP link del dev dummy1 + cleanup +} + +fib_down_test() +{ + fib_down_unicast_test + fib_down_multipath_test +} + +# Local routes should not be affected when carrier changes. +fib_carrier_local_test() +{ + echo + echo "Local carrier tests - single path" + + setup + + set -e + $IP link set dev dummy0 carrier on + set +e + + echo " Start point" + $IP route get fibmatch 198.51.100.1 &> /dev/null + log_test $? 0 "IPv4 fibmatch" + $IP -6 route get fibmatch 2001:db8:1::1 &> /dev/null + log_test $? 0 "IPv6 fibmatch" + + $IP route get fibmatch 198.51.100.1 | \ + grep -q "linkdown" + log_test $? 1 "IPv4 - no linkdown flag" + $IP -6 route get fibmatch 2001:db8:1::1 | \ + grep -q "linkdown" + log_test $? 1 "IPv6 - no linkdown flag" + + set -e + $IP link set dev dummy0 carrier off + sleep 1 + set +e + + echo " Carrier off on nexthop" + $IP route get fibmatch 198.51.100.1 &> /dev/null + log_test $? 0 "IPv4 fibmatch" + $IP -6 route get fibmatch 2001:db8:1::1 &> /dev/null + log_test $? 0 "IPv6 fibmatch" + + $IP route get fibmatch 198.51.100.1 | \ + grep -q "linkdown" + log_test $? 1 "IPv4 - linkdown flag set" + $IP -6 route get fibmatch 2001:db8:1::1 | \ + grep -q "linkdown" + log_test $? 1 "IPv6 - linkdown flag set" + + set -e + $IP address add 192.0.2.1/24 dev dummy0 + $IP -6 address add 2001:db8:2::1/64 dev dummy0 + set +e + + echo " Route to local address with carrier down" + $IP route get fibmatch 192.0.2.1 &> /dev/null + log_test $? 0 "IPv4 fibmatch" + $IP -6 route get fibmatch 2001:db8:2::1 &> /dev/null + log_test $? 0 "IPv6 fibmatch" + + $IP route get fibmatch 192.0.2.1 | \ + grep -q "linkdown" + log_test $? 1 "IPv4 linkdown flag set" + $IP -6 route get fibmatch 2001:db8:2::1 | \ + grep -q "linkdown" + log_test $? 1 "IPv6 linkdown flag set" + + cleanup +} + +fib_carrier_unicast_test() +{ + ret=0 + + echo + echo "Single path route carrier test" + + setup + + set -e + $IP link set dev dummy0 carrier on + set +e + + echo " Start point" + $IP route get fibmatch 198.51.100.2 &> /dev/null + log_test $? 0 "IPv4 fibmatch" + $IP -6 route get fibmatch 2001:db8:1::2 &> /dev/null + log_test $? 0 "IPv6 fibmatch" + + $IP route get fibmatch 198.51.100.2 | \ + grep -q "linkdown" + log_test $? 1 "IPv4 no linkdown flag" + $IP -6 route get fibmatch 2001:db8:1::2 | \ + grep -q "linkdown" + log_test $? 1 "IPv6 no linkdown flag" + + set -e + $IP link set dev dummy0 carrier off + sleep 1 + set +e + + echo " Carrier down" + $IP route get fibmatch 198.51.100.2 &> /dev/null + log_test $? 0 "IPv4 fibmatch" + $IP -6 route get fibmatch 2001:db8:1::2 &> /dev/null + log_test $? 0 "IPv6 fibmatch" + + $IP route get fibmatch 198.51.100.2 | \ + grep -q "linkdown" + log_test $? 0 "IPv4 linkdown flag set" + $IP -6 route get fibmatch 2001:db8:1::2 | \ + grep -q "linkdown" + log_test $? 0 "IPv6 linkdown flag set" + + set -e + $IP address add 192.0.2.1/24 dev dummy0 + $IP -6 address add 2001:db8:2::1/64 dev dummy0 + set +e + + echo " Second address added with carrier down" + $IP route get fibmatch 192.0.2.2 &> /dev/null + log_test $? 0 "IPv4 fibmatch" + $IP -6 route get fibmatch 2001:db8:2::2 &> /dev/null + log_test $? 0 "IPv6 fibmatch" + + $IP route get fibmatch 192.0.2.2 | \ + grep -q "linkdown" + log_test $? 0 "IPv4 linkdown flag set" + $IP -6 route get fibmatch 2001:db8:2::2 | \ + grep -q "linkdown" + log_test $? 0 "IPv6 linkdown flag set" + + cleanup +} + +fib_carrier_test() +{ + fib_carrier_local_test + fib_carrier_unicast_test +} + +fib_rp_filter_test() +{ + echo + echo "IPv4 rp_filter tests" + + setup + + set -e + ip netns add ns2 + ip netns set ns2 auto + + ip -netns ns2 link set dev lo up + + $IP link add name veth1 type veth peer name veth2 + $IP link set dev veth2 netns ns2 + $IP address add 192.0.2.1/24 dev veth1 + ip -netns ns2 address add 192.0.2.1/24 dev veth2 + $IP link set dev veth1 up + ip -netns ns2 link set dev veth2 up + + $IP link set dev lo address 52:54:00:6a:c7:5e + $IP link set dev veth1 address 52:54:00:6a:c7:5e + ip -netns ns2 link set dev lo address 52:54:00:6a:c7:5e + ip -netns ns2 link set dev veth2 address 52:54:00:6a:c7:5e + + # 1. (ns2) redirect lo's egress to veth2's egress + ip netns exec ns2 tc qdisc add dev lo parent root handle 1: fq_codel + ip netns exec ns2 tc filter add dev lo parent 1: protocol arp basic \ + action mirred egress redirect dev veth2 + ip netns exec ns2 tc filter add dev lo parent 1: protocol ip basic \ + action mirred egress redirect dev veth2 + + # 2. (ns1) redirect veth1's ingress to lo's ingress + $NS_EXEC tc qdisc add dev veth1 ingress + $NS_EXEC tc filter add dev veth1 ingress protocol arp basic \ + action mirred ingress redirect dev lo + $NS_EXEC tc filter add dev veth1 ingress protocol ip basic \ + action mirred ingress redirect dev lo + + # 3. (ns1) redirect lo's egress to veth1's egress + $NS_EXEC tc qdisc add dev lo parent root handle 1: fq_codel + $NS_EXEC tc filter add dev lo parent 1: protocol arp basic \ + action mirred egress redirect dev veth1 + $NS_EXEC tc filter add dev lo parent 1: protocol ip basic \ + action mirred egress redirect dev veth1 + + # 4. (ns2) redirect veth2's ingress to lo's ingress + ip netns exec ns2 tc qdisc add dev veth2 ingress + ip netns exec ns2 tc filter add dev veth2 ingress protocol arp basic \ + action mirred ingress redirect dev lo + ip netns exec ns2 tc filter add dev veth2 ingress protocol ip basic \ + action mirred ingress redirect dev lo + + $NS_EXEC sysctl -qw net.ipv4.conf.all.rp_filter=1 + $NS_EXEC sysctl -qw net.ipv4.conf.all.accept_local=1 + $NS_EXEC sysctl -qw net.ipv4.conf.all.route_localnet=1 + ip netns exec ns2 sysctl -qw net.ipv4.conf.all.rp_filter=1 + ip netns exec ns2 sysctl -qw net.ipv4.conf.all.accept_local=1 + ip netns exec ns2 sysctl -qw net.ipv4.conf.all.route_localnet=1 + set +e + + run_cmd "ip netns exec ns2 ping -w1 -c1 192.0.2.1" + log_test $? 0 "rp_filter passes local packets" + + run_cmd "ip netns exec ns2 ping -w1 -c1 127.0.0.1" + log_test $? 0 "rp_filter passes loopback packets" + + cleanup +} + +################################################################################ +# Tests on nexthop spec + +# run 'ip route add' with given spec +add_rt() +{ + local desc="$1" + local erc=$2 + local vrf=$3 + local pfx=$4 + local gw=$5 + local dev=$6 + local cmd out rc + + [ "$vrf" = "-" ] && vrf="default" + [ -n "$gw" ] && gw="via $gw" + [ -n "$dev" ] && dev="dev $dev" + + cmd="$IP route add vrf $vrf $pfx $gw $dev" + if [ "$VERBOSE" = "1" ]; then + printf "\n COMMAND: $cmd\n" + fi + + out=$(eval $cmd 2>&1) + rc=$? + if [ "$VERBOSE" = "1" -a -n "$out" ]; then + echo " $out" + fi + log_test $rc $erc "$desc" +} + +fib4_nexthop() +{ + echo + echo "IPv4 nexthop tests" + + echo "<<< write me >>>" +} + +fib6_nexthop() +{ + local lldummy=$(get_linklocal dummy0) + local llv1=$(get_linklocal dummy0) + + if [ -z "$lldummy" ]; then + echo "Failed to get linklocal address for dummy0" + return 1 + fi + if [ -z "$llv1" ]; then + echo "Failed to get linklocal address for veth1" + return 1 + fi + + echo + echo "IPv6 nexthop tests" + + add_rt "Directly connected nexthop, unicast address" 0 \ + - 2001:db8:101::/64 2001:db8:1::2 + add_rt "Directly connected nexthop, unicast address with device" 0 \ + - 2001:db8:102::/64 2001:db8:1::2 "dummy0" + add_rt "Gateway is linklocal address" 0 \ + - 2001:db8:103::1/64 $llv1 "veth0" + + # fails because LL address requires a device + add_rt "Gateway is linklocal address, no device" 2 \ + - 2001:db8:104::1/64 $llv1 + + # local address can not be a gateway + add_rt "Gateway can not be local unicast address" 2 \ + - 2001:db8:105::/64 2001:db8:1::1 + add_rt "Gateway can not be local unicast address, with device" 2 \ + - 2001:db8:106::/64 2001:db8:1::1 "dummy0" + add_rt "Gateway can not be a local linklocal address" 2 \ + - 2001:db8:107::1/64 $lldummy "dummy0" + + # VRF tests + add_rt "Gateway can be local address in a VRF" 0 \ + - 2001:db8:108::/64 2001:db8:51::2 + add_rt "Gateway can be local address in a VRF, with device" 0 \ + - 2001:db8:109::/64 2001:db8:51::2 "veth0" + add_rt "Gateway can be local linklocal address in a VRF" 0 \ + - 2001:db8:110::1/64 $llv1 "veth0" + + add_rt "Redirect to VRF lookup" 0 \ + - 2001:db8:111::/64 "" "red" + + add_rt "VRF route, gateway can be local address in default VRF" 0 \ + red 2001:db8:112::/64 2001:db8:51::1 + + # local address in same VRF fails + add_rt "VRF route, gateway can not be a local address" 2 \ + red 2001:db8:113::1/64 2001:db8:2::1 + add_rt "VRF route, gateway can not be a local addr with device" 2 \ + red 2001:db8:114::1/64 2001:db8:2::1 "dummy1" +} + +# Default VRF: +# dummy0 - 198.51.100.1/24 2001:db8:1::1/64 +# veth0 - 192.0.2.1/24 2001:db8:51::1/64 +# +# VRF red: +# dummy1 - 192.168.2.1/24 2001:db8:2::1/64 +# veth1 - 192.0.2.2/24 2001:db8:51::2/64 +# +# [ dummy0 veth0 ]--[ veth1 dummy1 ] + +fib_nexthop_test() +{ + setup + + set -e + + $IP -4 rule add pref 32765 table local + $IP -4 rule del pref 0 + $IP -6 rule add pref 32765 table local + $IP -6 rule del pref 0 + + $IP link add red type vrf table 1 + $IP link set red up + $IP -4 route add vrf red unreachable default metric 4278198272 + $IP -6 route add vrf red unreachable default metric 4278198272 + + $IP link add veth0 type veth peer name veth1 + $IP link set dev veth0 up + $IP address add 192.0.2.1/24 dev veth0 + $IP -6 address add 2001:db8:51::1/64 dev veth0 + + $IP link set dev veth1 vrf red up + $IP address add 192.0.2.2/24 dev veth1 + $IP -6 address add 2001:db8:51::2/64 dev veth1 + + $IP link add dummy1 type dummy + $IP link set dev dummy1 vrf red up + $IP address add 192.168.2.1/24 dev dummy1 + $IP -6 address add 2001:db8:2::1/64 dev dummy1 + set +e + + sleep 1 + fib4_nexthop + fib6_nexthop + + ( + $IP link del dev dummy1 + $IP link del veth0 + $IP link del red + ) 2>/dev/null + cleanup +} + +fib_suppress_test() +{ + echo + echo "FIB rule with suppress_prefixlength" + setup + + $IP link add dummy1 type dummy + $IP link set dummy1 up + $IP -6 route add default dev dummy1 + $IP -6 rule add table main suppress_prefixlength 0 + ping -f -c 1000 -W 1 1234::1 >/dev/null 2>&1 + $IP -6 rule del table main suppress_prefixlength 0 + $IP link del dummy1 + + # If we got here without crashing, we're good. + log_test 0 0 "FIB rule suppress test" + + cleanup +} + +################################################################################ +# Tests on route add and replace + +run_cmd() +{ + local cmd="$1" + local out + local stderr="2>/dev/null" + + if [ "$VERBOSE" = "1" ]; then + printf " COMMAND: $cmd\n" + stderr= + fi + + out=$(eval $cmd $stderr) + rc=$? + if [ "$VERBOSE" = "1" -a -n "$out" ]; then + echo " $out" + fi + + [ "$VERBOSE" = "1" ] && echo + + return $rc +} + +check_expected() +{ + local out="$1" + local expected="$2" + local rc=0 + + [ "${out}" = "${expected}" ] && return 0 + + if [ -z "${out}" ]; then + if [ "$VERBOSE" = "1" ]; then + printf "\nNo route entry found\n" + printf "Expected:\n" + printf " ${expected}\n" + fi + return 1 + fi + + # tricky way to convert output to 1-line without ip's + # messy '\'; this drops all extra white space + out=$(echo ${out}) + if [ "${out}" != "${expected}" ]; then + rc=1 + if [ "${VERBOSE}" = "1" ]; then + printf " Unexpected route entry. Have:\n" + printf " ${out}\n" + printf " Expected:\n" + printf " ${expected}\n\n" + fi + fi + + return $rc +} + +# add route for a prefix, flushing any existing routes first +# expected to be the first step of a test +add_route6() +{ + local pfx="$1" + local nh="$2" + local out + + if [ "$VERBOSE" = "1" ]; then + echo + echo " ##################################################" + echo + fi + + run_cmd "$IP -6 ro flush ${pfx}" + [ $? -ne 0 ] && exit 1 + + out=$($IP -6 ro ls match ${pfx}) + if [ -n "$out" ]; then + echo "Failed to flush routes for prefix used for tests." + exit 1 + fi + + run_cmd "$IP -6 ro add ${pfx} ${nh}" + if [ $? -ne 0 ]; then + echo "Failed to add initial route for test." + exit 1 + fi +} + +# add initial route - used in replace route tests +add_initial_route6() +{ + add_route6 "2001:db8:104::/64" "$1" +} + +check_route6() +{ + local pfx + local expected="$1" + local out + local rc=0 + + set -- $expected + pfx=$1 + + out=$($IP -6 ro ls match ${pfx} | sed -e 's/ pref medium//') + check_expected "${out}" "${expected}" +} + +route_cleanup() +{ + $IP li del red 2>/dev/null + $IP li del dummy1 2>/dev/null + $IP li del veth1 2>/dev/null + $IP li del veth3 2>/dev/null + + cleanup &> /dev/null +} + +route_setup() +{ + route_cleanup + setup + + [ "${VERBOSE}" = "1" ] && set -x + set -e + + ip netns add ns2 + ip netns set ns2 auto + ip -netns ns2 link set dev lo up + ip netns exec ns2 sysctl -qw net.ipv4.ip_forward=1 + ip netns exec ns2 sysctl -qw net.ipv6.conf.all.forwarding=1 + + $IP li add veth1 type veth peer name veth2 + $IP li add veth3 type veth peer name veth4 + + $IP li set veth1 up + $IP li set veth3 up + $IP li set veth2 netns ns2 up + $IP li set veth4 netns ns2 up + ip -netns ns2 li add dummy1 type dummy + ip -netns ns2 li set dummy1 up + + $IP -6 addr add 2001:db8:101::1/64 dev veth1 nodad + $IP -6 addr add 2001:db8:103::1/64 dev veth3 nodad + $IP addr add 172.16.101.1/24 dev veth1 + $IP addr add 172.16.103.1/24 dev veth3 + + ip -netns ns2 -6 addr add 2001:db8:101::2/64 dev veth2 nodad + ip -netns ns2 -6 addr add 2001:db8:103::2/64 dev veth4 nodad + ip -netns ns2 -6 addr add 2001:db8:104::1/64 dev dummy1 nodad + + ip -netns ns2 addr add 172.16.101.2/24 dev veth2 + ip -netns ns2 addr add 172.16.103.2/24 dev veth4 + ip -netns ns2 addr add 172.16.104.1/24 dev dummy1 + + set +e +} + +# assumption is that basic add of a single path route works +# otherwise just adding an address on an interface is broken +ipv6_rt_add() +{ + local rc + + echo + echo "IPv6 route add / append tests" + + # route add same prefix - fails with EEXISTS b/c ip adds NLM_F_EXCL + add_route6 "2001:db8:104::/64" "via 2001:db8:101::2" + run_cmd "$IP -6 ro add 2001:db8:104::/64 via 2001:db8:103::2" + log_test $? 2 "Attempt to add duplicate route - gw" + + # route add same prefix - fails with EEXISTS b/c ip adds NLM_F_EXCL + add_route6 "2001:db8:104::/64" "via 2001:db8:101::2" + run_cmd "$IP -6 ro add 2001:db8:104::/64 dev veth3" + log_test $? 2 "Attempt to add duplicate route - dev only" + + # route add same prefix - fails with EEXISTS b/c ip adds NLM_F_EXCL + add_route6 "2001:db8:104::/64" "via 2001:db8:101::2" + run_cmd "$IP -6 ro add unreachable 2001:db8:104::/64" + log_test $? 2 "Attempt to add duplicate route - reject route" + + # route append with same prefix adds a new route + # - iproute2 sets NLM_F_CREATE | NLM_F_APPEND + add_route6 "2001:db8:104::/64" "via 2001:db8:101::2" + run_cmd "$IP -6 ro append 2001:db8:104::/64 via 2001:db8:103::2" + check_route6 "2001:db8:104::/64 metric 1024 nexthop via 2001:db8:101::2 dev veth1 weight 1 nexthop via 2001:db8:103::2 dev veth3 weight 1" + log_test $? 0 "Append nexthop to existing route - gw" + + # insert mpath directly + add_route6 "2001:db8:104::/64" "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2" + check_route6 "2001:db8:104::/64 metric 1024 nexthop via 2001:db8:101::2 dev veth1 weight 1 nexthop via 2001:db8:103::2 dev veth3 weight 1" + log_test $? 0 "Add multipath route" + + add_route6 "2001:db8:104::/64" "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2" + run_cmd "$IP -6 ro add 2001:db8:104::/64 nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2" + log_test $? 2 "Attempt to add duplicate multipath route" + + # insert of a second route without append but different metric + add_route6 "2001:db8:104::/64" "via 2001:db8:101::2" + run_cmd "$IP -6 ro add 2001:db8:104::/64 via 2001:db8:103::2 metric 512" + rc=$? + if [ $rc -eq 0 ]; then + run_cmd "$IP -6 ro add 2001:db8:104::/64 via 2001:db8:103::3 metric 256" + rc=$? + fi + log_test $rc 0 "Route add with different metrics" + + run_cmd "$IP -6 ro del 2001:db8:104::/64 metric 512" + rc=$? + if [ $rc -eq 0 ]; then + check_route6 "2001:db8:104::/64 via 2001:db8:103::3 dev veth3 metric 256 2001:db8:104::/64 via 2001:db8:101::2 dev veth1 metric 1024" + rc=$? + fi + log_test $rc 0 "Route delete with metric" +} + +ipv6_rt_replace_single() +{ + # single path with single path + # + add_initial_route6 "via 2001:db8:101::2" + run_cmd "$IP -6 ro replace 2001:db8:104::/64 via 2001:db8:103::2" + check_route6 "2001:db8:104::/64 via 2001:db8:103::2 dev veth3 metric 1024" + log_test $? 0 "Single path with single path" + + # single path with multipath + # + add_initial_route6 "nexthop via 2001:db8:101::2" + run_cmd "$IP -6 ro replace 2001:db8:104::/64 nexthop via 2001:db8:101::3 nexthop via 2001:db8:103::2" + check_route6 "2001:db8:104::/64 metric 1024 nexthop via 2001:db8:101::3 dev veth1 weight 1 nexthop via 2001:db8:103::2 dev veth3 weight 1" + log_test $? 0 "Single path with multipath" + + # single path with single path using MULTIPATH attribute + # + add_initial_route6 "via 2001:db8:101::2" + run_cmd "$IP -6 ro replace 2001:db8:104::/64 nexthop via 2001:db8:103::2" + check_route6 "2001:db8:104::/64 via 2001:db8:103::2 dev veth3 metric 1024" + log_test $? 0 "Single path with single path via multipath attribute" + + # route replace fails - invalid nexthop + add_initial_route6 "via 2001:db8:101::2" + run_cmd "$IP -6 ro replace 2001:db8:104::/64 via 2001:db8:104::2" + if [ $? -eq 0 ]; then + # previous command is expected to fail so if it returns 0 + # that means the test failed. + log_test 0 1 "Invalid nexthop" + else + check_route6 "2001:db8:104::/64 via 2001:db8:101::2 dev veth1 metric 1024" + log_test $? 0 "Invalid nexthop" + fi + + # replace non-existent route + # - note use of change versus replace since ip adds NLM_F_CREATE + # for replace + add_initial_route6 "via 2001:db8:101::2" + run_cmd "$IP -6 ro change 2001:db8:105::/64 via 2001:db8:101::2" + log_test $? 2 "Single path - replace of non-existent route" +} + +ipv6_rt_replace_mpath() +{ + # multipath with multipath + add_initial_route6 "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2" + run_cmd "$IP -6 ro replace 2001:db8:104::/64 nexthop via 2001:db8:101::3 nexthop via 2001:db8:103::3" + check_route6 "2001:db8:104::/64 metric 1024 nexthop via 2001:db8:101::3 dev veth1 weight 1 nexthop via 2001:db8:103::3 dev veth3 weight 1" + log_test $? 0 "Multipath with multipath" + + # multipath with single + add_initial_route6 "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2" + run_cmd "$IP -6 ro replace 2001:db8:104::/64 via 2001:db8:101::3" + check_route6 "2001:db8:104::/64 via 2001:db8:101::3 dev veth1 metric 1024" + log_test $? 0 "Multipath with single path" + + # multipath with single + add_initial_route6 "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2" + run_cmd "$IP -6 ro replace 2001:db8:104::/64 nexthop via 2001:db8:101::3" + check_route6 "2001:db8:104::/64 via 2001:db8:101::3 dev veth1 metric 1024" + log_test $? 0 "Multipath with single path via multipath attribute" + + # multipath with dev-only + add_initial_route6 "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2" + run_cmd "$IP -6 ro replace 2001:db8:104::/64 dev veth1" + check_route6 "2001:db8:104::/64 dev veth1 metric 1024" + log_test $? 0 "Multipath with dev-only" + + # route replace fails - invalid nexthop 1 + add_initial_route6 "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2" + run_cmd "$IP -6 ro replace 2001:db8:104::/64 nexthop via 2001:db8:111::3 nexthop via 2001:db8:103::3" + check_route6 "2001:db8:104::/64 metric 1024 nexthop via 2001:db8:101::2 dev veth1 weight 1 nexthop via 2001:db8:103::2 dev veth3 weight 1" + log_test $? 0 "Multipath - invalid first nexthop" + + # route replace fails - invalid nexthop 2 + add_initial_route6 "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2" + run_cmd "$IP -6 ro replace 2001:db8:104::/64 nexthop via 2001:db8:101::3 nexthop via 2001:db8:113::3" + check_route6 "2001:db8:104::/64 metric 1024 nexthop via 2001:db8:101::2 dev veth1 weight 1 nexthop via 2001:db8:103::2 dev veth3 weight 1" + log_test $? 0 "Multipath - invalid second nexthop" + + # multipath non-existent route + add_initial_route6 "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2" + run_cmd "$IP -6 ro change 2001:db8:105::/64 nexthop via 2001:db8:101::3 nexthop via 2001:db8:103::3" + log_test $? 2 "Multipath - replace of non-existent route" +} + +ipv6_rt_replace() +{ + echo + echo "IPv6 route replace tests" + + ipv6_rt_replace_single + ipv6_rt_replace_mpath +} + +ipv6_route_test() +{ + route_setup + + ipv6_rt_add + ipv6_rt_replace + + route_cleanup +} + +ip_addr_metric_check() +{ + ip addr help 2>&1 | grep -q metric + if [ $? -ne 0 ]; then + echo "iproute2 command does not support metric for addresses. Skipping test" + return 1 + fi + + return 0 +} + +ipv6_addr_metric_test() +{ + local rc + + echo + echo "IPv6 prefix route tests" + + ip_addr_metric_check || return 1 + + setup + + set -e + $IP li add dummy1 type dummy + $IP li add dummy2 type dummy + $IP li set dummy1 up + $IP li set dummy2 up + + # default entry is metric 256 + run_cmd "$IP -6 addr add dev dummy1 2001:db8:104::1/64" + run_cmd "$IP -6 addr add dev dummy2 2001:db8:104::2/64" + set +e + + check_route6 "2001:db8:104::/64 dev dummy1 proto kernel metric 256 2001:db8:104::/64 dev dummy2 proto kernel metric 256" + log_test $? 0 "Default metric" + + set -e + run_cmd "$IP -6 addr flush dev dummy1" + run_cmd "$IP -6 addr add dev dummy1 2001:db8:104::1/64 metric 257" + set +e + + check_route6 "2001:db8:104::/64 dev dummy2 proto kernel metric 256 2001:db8:104::/64 dev dummy1 proto kernel metric 257" + log_test $? 0 "User specified metric on first device" + + set -e + run_cmd "$IP -6 addr flush dev dummy2" + run_cmd "$IP -6 addr add dev dummy2 2001:db8:104::2/64 metric 258" + set +e + + check_route6 "2001:db8:104::/64 dev dummy1 proto kernel metric 257 2001:db8:104::/64 dev dummy2 proto kernel metric 258" + log_test $? 0 "User specified metric on second device" + + run_cmd "$IP -6 addr del dev dummy1 2001:db8:104::1/64 metric 257" + rc=$? + if [ $rc -eq 0 ]; then + check_route6 "2001:db8:104::/64 dev dummy2 proto kernel metric 258" + rc=$? + fi + log_test $rc 0 "Delete of address on first device" + + run_cmd "$IP -6 addr change dev dummy2 2001:db8:104::2/64 metric 259" + rc=$? + if [ $rc -eq 0 ]; then + check_route6 "2001:db8:104::/64 dev dummy2 proto kernel metric 259" + rc=$? + fi + log_test $rc 0 "Modify metric of address" + + # verify prefix route removed on down + run_cmd "ip netns exec ns1 sysctl -qw net.ipv6.conf.all.keep_addr_on_down=1" + run_cmd "$IP li set dev dummy2 down" + rc=$? + if [ $rc -eq 0 ]; then + out=$($IP -6 ro ls match 2001:db8:104::/64) + check_expected "${out}" "" + rc=$? + fi + log_test $rc 0 "Prefix route removed on link down" + + # verify prefix route re-inserted with assigned metric + run_cmd "$IP li set dev dummy2 up" + rc=$? + if [ $rc -eq 0 ]; then + check_route6 "2001:db8:104::/64 dev dummy2 proto kernel metric 259" + rc=$? + fi + log_test $rc 0 "Prefix route with metric on link up" + + # verify peer metric added correctly + set -e + run_cmd "$IP -6 addr flush dev dummy2" + run_cmd "$IP -6 addr add dev dummy2 2001:db8:104::1 peer 2001:db8:104::2 metric 260" + set +e + + check_route6 "2001:db8:104::1 dev dummy2 proto kernel metric 260" + log_test $? 0 "Set metric with peer route on local side" + check_route6 "2001:db8:104::2 dev dummy2 proto kernel metric 260" + log_test $? 0 "Set metric with peer route on peer side" + + set -e + run_cmd "$IP -6 addr change dev dummy2 2001:db8:104::1 peer 2001:db8:104::3 metric 261" + set +e + + check_route6 "2001:db8:104::1 dev dummy2 proto kernel metric 261" + log_test $? 0 "Modify metric and peer address on local side" + check_route6 "2001:db8:104::3 dev dummy2 proto kernel metric 261" + log_test $? 0 "Modify metric and peer address on peer side" + + $IP li del dummy1 + $IP li del dummy2 + cleanup +} + +ipv6_route_metrics_test() +{ + local rc + + echo + echo "IPv6 routes with metrics" + + route_setup + + # + # single path with metrics + # + run_cmd "$IP -6 ro add 2001:db8:111::/64 via 2001:db8:101::2 mtu 1400" + rc=$? + if [ $rc -eq 0 ]; then + check_route6 "2001:db8:111::/64 via 2001:db8:101::2 dev veth1 metric 1024 mtu 1400" + rc=$? + fi + log_test $rc 0 "Single path route with mtu metric" + + + # + # multipath via separate routes with metrics + # + run_cmd "$IP -6 ro add 2001:db8:112::/64 via 2001:db8:101::2 mtu 1400" + run_cmd "$IP -6 ro append 2001:db8:112::/64 via 2001:db8:103::2" + rc=$? + if [ $rc -eq 0 ]; then + check_route6 "2001:db8:112::/64 metric 1024 mtu 1400 nexthop via 2001:db8:101::2 dev veth1 weight 1 nexthop via 2001:db8:103::2 dev veth3 weight 1" + rc=$? + fi + log_test $rc 0 "Multipath route via 2 single routes with mtu metric on first" + + # second route is coalesced to first to make a multipath route. + # MTU of the second path is hidden from display! + run_cmd "$IP -6 ro add 2001:db8:113::/64 via 2001:db8:101::2" + run_cmd "$IP -6 ro append 2001:db8:113::/64 via 2001:db8:103::2 mtu 1400" + rc=$? + if [ $rc -eq 0 ]; then + check_route6 "2001:db8:113::/64 metric 1024 nexthop via 2001:db8:101::2 dev veth1 weight 1 nexthop via 2001:db8:103::2 dev veth3 weight 1" + rc=$? + fi + log_test $rc 0 "Multipath route via 2 single routes with mtu metric on 2nd" + + run_cmd "$IP -6 ro del 2001:db8:113::/64 via 2001:db8:101::2" + if [ $? -eq 0 ]; then + check_route6 "2001:db8:113::/64 via 2001:db8:103::2 dev veth3 metric 1024 mtu 1400" + log_test $? 0 " MTU of second leg" + fi + + # + # multipath with metrics + # + run_cmd "$IP -6 ro add 2001:db8:115::/64 mtu 1400 nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2" + rc=$? + if [ $rc -eq 0 ]; then + check_route6 "2001:db8:115::/64 metric 1024 mtu 1400 nexthop via 2001:db8:101::2 dev veth1 weight 1 nexthop via 2001:db8:103::2 dev veth3 weight 1" + rc=$? + fi + log_test $rc 0 "Multipath route with mtu metric" + + $IP -6 ro add 2001:db8:104::/64 via 2001:db8:101::2 mtu 1300 + run_cmd "ip netns exec ns1 ${ping6} -w1 -c1 -s 1500 2001:db8:104::1" + log_test $? 0 "Using route with mtu metric" + + run_cmd "$IP -6 ro add 2001:db8:114::/64 via 2001:db8:101::2 congctl lock foo" + log_test $? 2 "Invalid metric (fails metric_convert)" + + route_cleanup +} + +# add route for a prefix, flushing any existing routes first +# expected to be the first step of a test +add_route() +{ + local pfx="$1" + local nh="$2" + local out + + if [ "$VERBOSE" = "1" ]; then + echo + echo " ##################################################" + echo + fi + + run_cmd "$IP ro flush ${pfx}" + [ $? -ne 0 ] && exit 1 + + out=$($IP ro ls match ${pfx}) + if [ -n "$out" ]; then + echo "Failed to flush routes for prefix used for tests." + exit 1 + fi + + run_cmd "$IP ro add ${pfx} ${nh}" + if [ $? -ne 0 ]; then + echo "Failed to add initial route for test." + exit 1 + fi +} + +# add initial route - used in replace route tests +add_initial_route() +{ + add_route "172.16.104.0/24" "$1" +} + +check_route() +{ + local pfx + local expected="$1" + local out + + set -- $expected + pfx=$1 + [ "${pfx}" = "unreachable" ] && pfx=$2 + + out=$($IP ro ls match ${pfx}) + check_expected "${out}" "${expected}" +} + +# assumption is that basic add of a single path route works +# otherwise just adding an address on an interface is broken +ipv4_rt_add() +{ + local rc + + echo + echo "IPv4 route add / append tests" + + # route add same prefix - fails with EEXISTS b/c ip adds NLM_F_EXCL + add_route "172.16.104.0/24" "via 172.16.101.2" + run_cmd "$IP ro add 172.16.104.0/24 via 172.16.103.2" + log_test $? 2 "Attempt to add duplicate route - gw" + + # route add same prefix - fails with EEXISTS b/c ip adds NLM_F_EXCL + add_route "172.16.104.0/24" "via 172.16.101.2" + run_cmd "$IP ro add 172.16.104.0/24 dev veth3" + log_test $? 2 "Attempt to add duplicate route - dev only" + + # route add same prefix - fails with EEXISTS b/c ip adds NLM_F_EXCL + add_route "172.16.104.0/24" "via 172.16.101.2" + run_cmd "$IP ro add unreachable 172.16.104.0/24" + log_test $? 2 "Attempt to add duplicate route - reject route" + + # iproute2 prepend only sets NLM_F_CREATE + # - adds a new route; does NOT convert existing route to ECMP + add_route "172.16.104.0/24" "via 172.16.101.2" + run_cmd "$IP ro prepend 172.16.104.0/24 via 172.16.103.2" + check_route "172.16.104.0/24 via 172.16.103.2 dev veth3 172.16.104.0/24 via 172.16.101.2 dev veth1" + log_test $? 0 "Add new nexthop for existing prefix" + + # route append with same prefix adds a new route + # - iproute2 sets NLM_F_CREATE | NLM_F_APPEND + add_route "172.16.104.0/24" "via 172.16.101.2" + run_cmd "$IP ro append 172.16.104.0/24 via 172.16.103.2" + check_route "172.16.104.0/24 via 172.16.101.2 dev veth1 172.16.104.0/24 via 172.16.103.2 dev veth3" + log_test $? 0 "Append nexthop to existing route - gw" + + add_route "172.16.104.0/24" "via 172.16.101.2" + run_cmd "$IP ro append 172.16.104.0/24 dev veth3" + check_route "172.16.104.0/24 via 172.16.101.2 dev veth1 172.16.104.0/24 dev veth3 scope link" + log_test $? 0 "Append nexthop to existing route - dev only" + + add_route "172.16.104.0/24" "via 172.16.101.2" + run_cmd "$IP ro append unreachable 172.16.104.0/24" + check_route "172.16.104.0/24 via 172.16.101.2 dev veth1 unreachable 172.16.104.0/24" + log_test $? 0 "Append nexthop to existing route - reject route" + + run_cmd "$IP ro flush 172.16.104.0/24" + run_cmd "$IP ro add unreachable 172.16.104.0/24" + run_cmd "$IP ro append 172.16.104.0/24 via 172.16.103.2" + check_route "unreachable 172.16.104.0/24 172.16.104.0/24 via 172.16.103.2 dev veth3" + log_test $? 0 "Append nexthop to existing reject route - gw" + + run_cmd "$IP ro flush 172.16.104.0/24" + run_cmd "$IP ro add unreachable 172.16.104.0/24" + run_cmd "$IP ro append 172.16.104.0/24 dev veth3" + check_route "unreachable 172.16.104.0/24 172.16.104.0/24 dev veth3 scope link" + log_test $? 0 "Append nexthop to existing reject route - dev only" + + # insert mpath directly + add_route "172.16.104.0/24" "nexthop via 172.16.101.2 nexthop via 172.16.103.2" + check_route "172.16.104.0/24 nexthop via 172.16.101.2 dev veth1 weight 1 nexthop via 172.16.103.2 dev veth3 weight 1" + log_test $? 0 "add multipath route" + + add_route "172.16.104.0/24" "nexthop via 172.16.101.2 nexthop via 172.16.103.2" + run_cmd "$IP ro add 172.16.104.0/24 nexthop via 172.16.101.2 nexthop via 172.16.103.2" + log_test $? 2 "Attempt to add duplicate multipath route" + + # insert of a second route without append but different metric + add_route "172.16.104.0/24" "via 172.16.101.2" + run_cmd "$IP ro add 172.16.104.0/24 via 172.16.103.2 metric 512" + rc=$? + if [ $rc -eq 0 ]; then + run_cmd "$IP ro add 172.16.104.0/24 via 172.16.103.3 metric 256" + rc=$? + fi + log_test $rc 0 "Route add with different metrics" + + run_cmd "$IP ro del 172.16.104.0/24 metric 512" + rc=$? + if [ $rc -eq 0 ]; then + check_route "172.16.104.0/24 via 172.16.101.2 dev veth1 172.16.104.0/24 via 172.16.103.3 dev veth3 metric 256" + rc=$? + fi + log_test $rc 0 "Route delete with metric" +} + +ipv4_rt_replace_single() +{ + # single path with single path + # + add_initial_route "via 172.16.101.2" + run_cmd "$IP ro replace 172.16.104.0/24 via 172.16.103.2" + check_route "172.16.104.0/24 via 172.16.103.2 dev veth3" + log_test $? 0 "Single path with single path" + + # single path with multipath + # + add_initial_route "nexthop via 172.16.101.2" + run_cmd "$IP ro replace 172.16.104.0/24 nexthop via 172.16.101.3 nexthop via 172.16.103.2" + check_route "172.16.104.0/24 nexthop via 172.16.101.3 dev veth1 weight 1 nexthop via 172.16.103.2 dev veth3 weight 1" + log_test $? 0 "Single path with multipath" + + # single path with reject + # + add_initial_route "nexthop via 172.16.101.2" + run_cmd "$IP ro replace unreachable 172.16.104.0/24" + check_route "unreachable 172.16.104.0/24" + log_test $? 0 "Single path with reject route" + + # single path with single path using MULTIPATH attribute + # + add_initial_route "via 172.16.101.2" + run_cmd "$IP ro replace 172.16.104.0/24 nexthop via 172.16.103.2" + check_route "172.16.104.0/24 via 172.16.103.2 dev veth3" + log_test $? 0 "Single path with single path via multipath attribute" + + # route replace fails - invalid nexthop + add_initial_route "via 172.16.101.2" + run_cmd "$IP ro replace 172.16.104.0/24 via 2001:db8:104::2" + if [ $? -eq 0 ]; then + # previous command is expected to fail so if it returns 0 + # that means the test failed. + log_test 0 1 "Invalid nexthop" + else + check_route "172.16.104.0/24 via 172.16.101.2 dev veth1" + log_test $? 0 "Invalid nexthop" + fi + + # replace non-existent route + # - note use of change versus replace since ip adds NLM_F_CREATE + # for replace + add_initial_route "via 172.16.101.2" + run_cmd "$IP ro change 172.16.105.0/24 via 172.16.101.2" + log_test $? 2 "Single path - replace of non-existent route" +} + +ipv4_rt_replace_mpath() +{ + # multipath with multipath + add_initial_route "nexthop via 172.16.101.2 nexthop via 172.16.103.2" + run_cmd "$IP ro replace 172.16.104.0/24 nexthop via 172.16.101.3 nexthop via 172.16.103.3" + check_route "172.16.104.0/24 nexthop via 172.16.101.3 dev veth1 weight 1 nexthop via 172.16.103.3 dev veth3 weight 1" + log_test $? 0 "Multipath with multipath" + + # multipath with single + add_initial_route "nexthop via 172.16.101.2 nexthop via 172.16.103.2" + run_cmd "$IP ro replace 172.16.104.0/24 via 172.16.101.3" + check_route "172.16.104.0/24 via 172.16.101.3 dev veth1" + log_test $? 0 "Multipath with single path" + + # multipath with single + add_initial_route "nexthop via 172.16.101.2 nexthop via 172.16.103.2" + run_cmd "$IP ro replace 172.16.104.0/24 nexthop via 172.16.101.3" + check_route "172.16.104.0/24 via 172.16.101.3 dev veth1" + log_test $? 0 "Multipath with single path via multipath attribute" + + # multipath with reject + add_initial_route "nexthop via 172.16.101.2 nexthop via 172.16.103.2" + run_cmd "$IP ro replace unreachable 172.16.104.0/24" + check_route "unreachable 172.16.104.0/24" + log_test $? 0 "Multipath with reject route" + + # route replace fails - invalid nexthop 1 + add_initial_route "nexthop via 172.16.101.2 nexthop via 172.16.103.2" + run_cmd "$IP ro replace 172.16.104.0/24 nexthop via 172.16.111.3 nexthop via 172.16.103.3" + check_route "172.16.104.0/24 nexthop via 172.16.101.2 dev veth1 weight 1 nexthop via 172.16.103.2 dev veth3 weight 1" + log_test $? 0 "Multipath - invalid first nexthop" + + # route replace fails - invalid nexthop 2 + add_initial_route "nexthop via 172.16.101.2 nexthop via 172.16.103.2" + run_cmd "$IP ro replace 172.16.104.0/24 nexthop via 172.16.101.3 nexthop via 172.16.113.3" + check_route "172.16.104.0/24 nexthop via 172.16.101.2 dev veth1 weight 1 nexthop via 172.16.103.2 dev veth3 weight 1" + log_test $? 0 "Multipath - invalid second nexthop" + + # multipath non-existent route + add_initial_route "nexthop via 172.16.101.2 nexthop via 172.16.103.2" + run_cmd "$IP ro change 172.16.105.0/24 nexthop via 172.16.101.3 nexthop via 172.16.103.3" + log_test $? 2 "Multipath - replace of non-existent route" +} + +ipv4_rt_replace() +{ + echo + echo "IPv4 route replace tests" + + ipv4_rt_replace_single + ipv4_rt_replace_mpath +} + +ipv4_route_test() +{ + route_setup + + ipv4_rt_add + ipv4_rt_replace + + route_cleanup +} + +ipv4_addr_metric_test() +{ + local rc + + echo + echo "IPv4 prefix route tests" + + ip_addr_metric_check || return 1 + + setup + + set -e + $IP li add dummy1 type dummy + $IP li add dummy2 type dummy + $IP li set dummy1 up + $IP li set dummy2 up + + # default entry is metric 256 + run_cmd "$IP addr add dev dummy1 172.16.104.1/24" + run_cmd "$IP addr add dev dummy2 172.16.104.2/24" + set +e + + check_route "172.16.104.0/24 dev dummy1 proto kernel scope link src 172.16.104.1 172.16.104.0/24 dev dummy2 proto kernel scope link src 172.16.104.2" + log_test $? 0 "Default metric" + + set -e + run_cmd "$IP addr flush dev dummy1" + run_cmd "$IP addr add dev dummy1 172.16.104.1/24 metric 257" + set +e + + check_route "172.16.104.0/24 dev dummy2 proto kernel scope link src 172.16.104.2 172.16.104.0/24 dev dummy1 proto kernel scope link src 172.16.104.1 metric 257" + log_test $? 0 "User specified metric on first device" + + set -e + run_cmd "$IP addr flush dev dummy2" + run_cmd "$IP addr add dev dummy2 172.16.104.2/24 metric 258" + set +e + + check_route "172.16.104.0/24 dev dummy1 proto kernel scope link src 172.16.104.1 metric 257 172.16.104.0/24 dev dummy2 proto kernel scope link src 172.16.104.2 metric 258" + log_test $? 0 "User specified metric on second device" + + run_cmd "$IP addr del dev dummy1 172.16.104.1/24 metric 257" + rc=$? + if [ $rc -eq 0 ]; then + check_route "172.16.104.0/24 dev dummy2 proto kernel scope link src 172.16.104.2 metric 258" + rc=$? + fi + log_test $rc 0 "Delete of address on first device" + + run_cmd "$IP addr change dev dummy2 172.16.104.2/24 metric 259" + rc=$? + if [ $rc -eq 0 ]; then + check_route "172.16.104.0/24 dev dummy2 proto kernel scope link src 172.16.104.2 metric 259" + rc=$? + fi + log_test $rc 0 "Modify metric of address" + + # verify prefix route removed on down + run_cmd "$IP li set dev dummy2 down" + rc=$? + if [ $rc -eq 0 ]; then + out=$($IP ro ls match 172.16.104.0/24) + check_expected "${out}" "" + rc=$? + fi + log_test $rc 0 "Prefix route removed on link down" + + # verify prefix route re-inserted with assigned metric + run_cmd "$IP li set dev dummy2 up" + rc=$? + if [ $rc -eq 0 ]; then + check_route "172.16.104.0/24 dev dummy2 proto kernel scope link src 172.16.104.2 metric 259" + rc=$? + fi + log_test $rc 0 "Prefix route with metric on link up" + + # explicitly check for metric changes on edge scenarios + run_cmd "$IP addr flush dev dummy2" + run_cmd "$IP addr add dev dummy2 172.16.104.0/24 metric 259" + run_cmd "$IP addr change dev dummy2 172.16.104.0/24 metric 260" + rc=$? + if [ $rc -eq 0 ]; then + check_route "172.16.104.0/24 dev dummy2 proto kernel scope link src 172.16.104.0 metric 260" + rc=$? + fi + log_test $rc 0 "Modify metric of .0/24 address" + + run_cmd "$IP addr flush dev dummy2" + run_cmd "$IP addr add dev dummy2 172.16.104.1/32 peer 172.16.104.2 metric 260" + rc=$? + if [ $rc -eq 0 ]; then + check_route "172.16.104.2 dev dummy2 proto kernel scope link src 172.16.104.1 metric 260" + rc=$? + fi + log_test $rc 0 "Set metric of address with peer route" + + run_cmd "$IP addr change dev dummy2 172.16.104.1/32 peer 172.16.104.3 metric 261" + rc=$? + if [ $rc -eq 0 ]; then + check_route "172.16.104.3 dev dummy2 proto kernel scope link src 172.16.104.1 metric 261" + rc=$? + fi + log_test $rc 0 "Modify metric and peer address for peer route" + + $IP li del dummy1 + $IP li del dummy2 + cleanup +} + +ipv4_route_metrics_test() +{ + local rc + + echo + echo "IPv4 route add / append tests" + + route_setup + + run_cmd "$IP ro add 172.16.111.0/24 via 172.16.101.2 mtu 1400" + rc=$? + if [ $rc -eq 0 ]; then + check_route "172.16.111.0/24 via 172.16.101.2 dev veth1 mtu 1400" + rc=$? + fi + log_test $rc 0 "Single path route with mtu metric" + + + run_cmd "$IP ro add 172.16.112.0/24 mtu 1400 nexthop via 172.16.101.2 nexthop via 172.16.103.2" + rc=$? + if [ $rc -eq 0 ]; then + check_route "172.16.112.0/24 mtu 1400 nexthop via 172.16.101.2 dev veth1 weight 1 nexthop via 172.16.103.2 dev veth3 weight 1" + rc=$? + fi + log_test $rc 0 "Multipath route with mtu metric" + + $IP ro add 172.16.104.0/24 via 172.16.101.2 mtu 1300 + run_cmd "ip netns exec ns1 ping -w1 -c1 -s 1500 172.16.104.1" + log_test $? 0 "Using route with mtu metric" + + run_cmd "$IP ro add 172.16.111.0/24 via 172.16.101.2 congctl lock foo" + log_test $? 2 "Invalid metric (fails metric_convert)" + + route_cleanup +} + +ipv4_route_v6_gw_test() +{ + local rc + + echo + echo "IPv4 route with IPv6 gateway tests" + + route_setup + sleep 2 + + # + # single path route + # + run_cmd "$IP ro add 172.16.104.0/24 via inet6 2001:db8:101::2" + rc=$? + log_test $rc 0 "Single path route with IPv6 gateway" + if [ $rc -eq 0 ]; then + check_route "172.16.104.0/24 via inet6 2001:db8:101::2 dev veth1" + fi + + run_cmd "ip netns exec ns1 ping -w1 -c1 172.16.104.1" + log_test $rc 0 "Single path route with IPv6 gateway - ping" + + run_cmd "$IP ro del 172.16.104.0/24 via inet6 2001:db8:101::2" + rc=$? + log_test $rc 0 "Single path route delete" + if [ $rc -eq 0 ]; then + check_route "172.16.112.0/24" + fi + + # + # multipath - v6 then v4 + # + run_cmd "$IP ro add 172.16.104.0/24 nexthop via inet6 2001:db8:101::2 dev veth1 nexthop via 172.16.103.2 dev veth3" + rc=$? + log_test $rc 0 "Multipath route add - v6 nexthop then v4" + if [ $rc -eq 0 ]; then + check_route "172.16.104.0/24 nexthop via inet6 2001:db8:101::2 dev veth1 weight 1 nexthop via 172.16.103.2 dev veth3 weight 1" + fi + + run_cmd "$IP ro del 172.16.104.0/24 nexthop via 172.16.103.2 dev veth3 nexthop via inet6 2001:db8:101::2 dev veth1" + log_test $? 2 " Multipath route delete - nexthops in wrong order" + + run_cmd "$IP ro del 172.16.104.0/24 nexthop via inet6 2001:db8:101::2 dev veth1 nexthop via 172.16.103.2 dev veth3" + log_test $? 0 " Multipath route delete exact match" + + # + # multipath - v4 then v6 + # + run_cmd "$IP ro add 172.16.104.0/24 nexthop via 172.16.103.2 dev veth3 nexthop via inet6 2001:db8:101::2 dev veth1" + rc=$? + log_test $rc 0 "Multipath route add - v4 nexthop then v6" + if [ $rc -eq 0 ]; then + check_route "172.16.104.0/24 nexthop via 172.16.103.2 dev veth3 weight 1 nexthop via inet6 2001:db8:101::2 dev veth1 weight 1" + fi + + run_cmd "$IP ro del 172.16.104.0/24 nexthop via inet6 2001:db8:101::2 dev veth1 nexthop via 172.16.103.2 dev veth3" + log_test $? 2 " Multipath route delete - nexthops in wrong order" + + run_cmd "$IP ro del 172.16.104.0/24 nexthop via 172.16.103.2 dev veth3 nexthop via inet6 2001:db8:101::2 dev veth1" + log_test $? 0 " Multipath route delete exact match" + + route_cleanup +} + +################################################################################ +# usage + +usage() +{ + cat < Test(s) to run (default: all) + (options: $TESTS) + -p Pause on fail + -P Pause after each test before cleanup + -v verbose mode (show commands and output) +EOF +} + +################################################################################ +# main + +while getopts :t:pPhv o +do + case $o in + t) TESTS=$OPTARG;; + p) PAUSE_ON_FAIL=yes;; + P) PAUSE=yes;; + v) VERBOSE=$(($VERBOSE + 1));; + h) usage; exit 0;; + *) usage; exit 1;; + esac +done + +PEER_CMD="ip netns exec ${PEER_NS}" + +# make sure we don't pause twice +[ "${PAUSE}" = "yes" ] && PAUSE_ON_FAIL=no + +if [ "$(id -u)" -ne 0 ];then + echo "SKIP: Need root privileges" + exit $ksft_skip; +fi + +if [ ! -x "$(command -v ip)" ]; then + echo "SKIP: Could not run test without ip tool" + exit $ksft_skip +fi + +ip route help 2>&1 | grep -q fibmatch +if [ $? -ne 0 ]; then + echo "SKIP: iproute2 too old, missing fibmatch" + exit $ksft_skip +fi + +# start clean +cleanup &> /dev/null + +for t in $TESTS +do + case $t in + fib_unreg_test|unregister) fib_unreg_test;; + fib_down_test|down) fib_down_test;; + fib_carrier_test|carrier) fib_carrier_test;; + fib_rp_filter_test|rp_filter) fib_rp_filter_test;; + fib_nexthop_test|nexthop) fib_nexthop_test;; + fib_suppress_test|suppress) fib_suppress_test;; + ipv6_route_test|ipv6_rt) ipv6_route_test;; + ipv4_route_test|ipv4_rt) ipv4_route_test;; + ipv6_addr_metric) ipv6_addr_metric_test;; + ipv4_addr_metric) ipv4_addr_metric_test;; + ipv6_route_metrics) ipv6_route_metrics_test;; + ipv4_route_metrics) ipv4_route_metrics_test;; + ipv4_route_v6_gw) ipv4_route_v6_gw_test;; + + help) echo "Test names: $TESTS"; exit 0;; + esac +done + +if [ "$TESTS" != "none" ]; then + printf "\nTests passed: %3d\n" ${nsuccess} + printf "Tests failed: %3d\n" ${nfail} +fi + +exit $ret diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index f190ad58e00d4..4d8845a68cf28 100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -562,14 +562,14 @@ sysctl_set() local value=$1; shift SYSCTL_ORIG[$key]=$(sysctl -n $key) - sysctl -qw $key=$value + sysctl -qw $key="$value" } sysctl_restore() { local key=$1; shift - sysctl -qw $key=${SYSCTL_ORIG["$key"]} + sysctl -qw $key="${SYSCTL_ORIG[$key]}" } forwarding_enable() diff --git a/tools/testing/selftests/net/udpgso_bench.sh b/tools/testing/selftests/net/udpgso_bench.sh index dc932fd653634..640bc43452faa 100755 --- a/tools/testing/selftests/net/udpgso_bench.sh +++ b/tools/testing/selftests/net/udpgso_bench.sh @@ -7,6 +7,7 @@ readonly GREEN='\033[0;92m' readonly YELLOW='\033[0;33m' readonly RED='\033[0;31m' readonly NC='\033[0m' # No Color +readonly TESTPORT=8000 readonly KSFT_PASS=0 readonly KSFT_FAIL=1 @@ -56,11 +57,26 @@ trap wake_children EXIT run_one() { local -r args=$@ + local nr_socks=0 + local i=0 + local -r timeout=10 + + ./udpgso_bench_rx -p "$TESTPORT" & + ./udpgso_bench_rx -p "$TESTPORT" -t & + + # Wait for the above test program to get ready to receive connections. + while [ "$i" -lt "$timeout" ]; do + nr_socks="$(ss -lnHi | grep -c "\*:${TESTPORT}")" + [ "$nr_socks" -eq 2 ] && break + i=$((i + 1)) + sleep 1 + done + if [ "$nr_socks" -ne 2 ]; then + echo "timed out while waiting for udpgso_bench_rx" + exit 1 + fi - ./udpgso_bench_rx & - ./udpgso_bench_rx -t & - - ./udpgso_bench_tx ${args} + ./udpgso_bench_tx -p "$TESTPORT" ${args} } run_in_netns() { diff --git a/tools/testing/selftests/net/udpgso_bench_rx.c b/tools/testing/selftests/net/udpgso_bench_rx.c index 6a193425c367f..4058c7451e70d 100644 --- a/tools/testing/selftests/net/udpgso_bench_rx.c +++ b/tools/testing/selftests/net/udpgso_bench_rx.c @@ -250,7 +250,7 @@ static int recv_msg(int fd, char *buf, int len, int *gso_size) static void do_flush_udp(int fd) { static char rbuf[ETH_MAX_MTU]; - int ret, len, gso_size, budget = 256; + int ret, len, gso_size = 0, budget = 256; len = cfg_read_all ? sizeof(rbuf) : 0; while (budget--) { @@ -336,6 +336,8 @@ static void parse_opts(int argc, char **argv) cfg_verify = true; cfg_read_all = true; break; + default: + exit(1); } } diff --git a/tools/testing/selftests/net/udpgso_bench_tx.c b/tools/testing/selftests/net/udpgso_bench_tx.c index f1fdaa2702913..477392715a9ad 100644 --- a/tools/testing/selftests/net/udpgso_bench_tx.c +++ b/tools/testing/selftests/net/udpgso_bench_tx.c @@ -62,6 +62,7 @@ static int cfg_payload_len = (1472 * 42); static int cfg_port = 8000; static int cfg_runtime_ms = -1; static bool cfg_poll; +static int cfg_poll_loop_timeout_ms = 2000; static bool cfg_segment; static bool cfg_sendmmsg; static bool cfg_tcp; @@ -235,16 +236,17 @@ static void flush_errqueue_recv(int fd) } } -static void flush_errqueue(int fd, const bool do_poll) +static void flush_errqueue(int fd, const bool do_poll, + unsigned long poll_timeout, const bool poll_err) { if (do_poll) { struct pollfd fds = {0}; int ret; fds.fd = fd; - ret = poll(&fds, 1, 500); + ret = poll(&fds, 1, poll_timeout); if (ret == 0) { - if (cfg_verbose) + if ((cfg_verbose) && (poll_err)) fprintf(stderr, "poll timeout\n"); } else if (ret < 0) { error(1, errno, "poll"); @@ -254,6 +256,20 @@ static void flush_errqueue(int fd, const bool do_poll) flush_errqueue_recv(fd); } +static void flush_errqueue_retry(int fd, unsigned long num_sends) +{ + unsigned long tnow, tstop; + bool first_try = true; + + tnow = gettimeofday_ms(); + tstop = tnow + cfg_poll_loop_timeout_ms; + do { + flush_errqueue(fd, true, tstop - tnow, first_try); + first_try = false; + tnow = gettimeofday_ms(); + } while ((stat_zcopies != num_sends) && (tnow < tstop)); +} + static int send_tcp(int fd, char *data) { int ret, done = 0, count = 0; @@ -413,7 +429,8 @@ static int send_udp_segment(int fd, char *data) static void usage(const char *filepath) { - error(1, 0, "Usage: %s [-46acmHPtTuvz] [-C cpu] [-D dst ip] [-l secs] [-M messagenr] [-p port] [-s sendsize] [-S gsosize]", + error(1, 0, "Usage: %s [-46acmHPtTuvz] [-C cpu] [-D dst ip] [-l secs] " + "[-L secs] [-M messagenr] [-p port] [-s sendsize] [-S gsosize]", filepath); } @@ -423,7 +440,7 @@ static void parse_opts(int argc, char **argv) int max_len, hdrlen; int c; - while ((c = getopt(argc, argv, "46acC:D:Hl:mM:p:s:PS:tTuvz")) != -1) { + while ((c = getopt(argc, argv, "46acC:D:Hl:L:mM:p:s:PS:tTuvz")) != -1) { switch (c) { case '4': if (cfg_family != PF_UNSPEC) @@ -452,6 +469,9 @@ static void parse_opts(int argc, char **argv) case 'l': cfg_runtime_ms = strtoul(optarg, NULL, 10) * 1000; break; + case 'L': + cfg_poll_loop_timeout_ms = strtoul(optarg, NULL, 10) * 1000; + break; case 'm': cfg_sendmmsg = true; break; @@ -490,6 +510,8 @@ static void parse_opts(int argc, char **argv) case 'z': cfg_zerocopy = true; break; + default: + exit(1); } } @@ -677,7 +699,7 @@ int main(int argc, char **argv) num_sends += send_udp(fd, buf[i]); num_msgs++; if ((cfg_zerocopy && ((num_msgs & 0xF) == 0)) || cfg_tx_tstamp) - flush_errqueue(fd, cfg_poll); + flush_errqueue(fd, cfg_poll, 500, true); if (cfg_msg_nr && num_msgs >= cfg_msg_nr) break; @@ -696,7 +718,7 @@ int main(int argc, char **argv) } while (!interrupted && (cfg_runtime_ms == -1 || tnow < tstop)); if (cfg_zerocopy || cfg_tx_tstamp) - flush_errqueue(fd, true); + flush_errqueue_retry(fd, num_sends); if (close(fd)) error(1, errno, "close"); diff --git a/tools/virtio/linux/bug.h b/tools/virtio/linux/bug.h index b14c2c3b6b857..74aef964f5099 100644 --- a/tools/virtio/linux/bug.h +++ b/tools/virtio/linux/bug.h @@ -1,11 +1,9 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#ifndef BUG_H -#define BUG_H +#ifndef _LINUX_BUG_H +#define _LINUX_BUG_H #define BUG_ON(__BUG_ON_cond) assert(!(__BUG_ON_cond)) -#define BUILD_BUG_ON(x) - #define BUG() abort() -#endif /* BUG_H */ +#endif /* _LINUX_BUG_H */ diff --git a/tools/virtio/linux/build_bug.h b/tools/virtio/linux/build_bug.h new file mode 100644 index 0000000000000..cdbb75e28a604 --- /dev/null +++ b/tools/virtio/linux/build_bug.h @@ -0,0 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_BUILD_BUG_H +#define _LINUX_BUILD_BUG_H + +#define BUILD_BUG_ON(x) + +#endif /* _LINUX_BUILD_BUG_H */ diff --git a/tools/virtio/linux/cpumask.h b/tools/virtio/linux/cpumask.h new file mode 100644 index 0000000000000..307da69d6b26c --- /dev/null +++ b/tools/virtio/linux/cpumask.h @@ -0,0 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_CPUMASK_H +#define _LINUX_CPUMASK_H + +#include + +#endif /* _LINUX_CPUMASK_H */ diff --git a/tools/virtio/linux/gfp.h b/tools/virtio/linux/gfp.h new file mode 100644 index 0000000000000..43d146f236f14 --- /dev/null +++ b/tools/virtio/linux/gfp.h @@ -0,0 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LINUX_GFP_H +#define __LINUX_GFP_H + +#include + +#endif diff --git a/tools/virtio/linux/kernel.h b/tools/virtio/linux/kernel.h index 6683b4a70b059..3325cdf229410 100644 --- a/tools/virtio/linux/kernel.h +++ b/tools/virtio/linux/kernel.h @@ -10,6 +10,7 @@ #include #include +#include #include #include #include diff --git a/tools/virtio/linux/kmsan.h b/tools/virtio/linux/kmsan.h new file mode 100644 index 0000000000000..272b5aa285d5a --- /dev/null +++ b/tools/virtio/linux/kmsan.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_KMSAN_H +#define _LINUX_KMSAN_H + +#include + +inline void kmsan_handle_dma(struct page *page, size_t offset, size_t size, + enum dma_data_direction dir) +{ +} + +#endif /* _LINUX_KMSAN_H */ diff --git a/tools/virtio/linux/scatterlist.h b/tools/virtio/linux/scatterlist.h index 369ee308b6686..74d9e1825748e 100644 --- a/tools/virtio/linux/scatterlist.h +++ b/tools/virtio/linux/scatterlist.h @@ -2,6 +2,7 @@ #ifndef SCATTERLIST_H #define SCATTERLIST_H #include +#include struct scatterlist { unsigned long page_link; diff --git a/tools/virtio/linux/topology.h b/tools/virtio/linux/topology.h new file mode 100644 index 0000000000000..910794afb993a --- /dev/null +++ b/tools/virtio/linux/topology.h @@ -0,0 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_TOPOLOGY_H +#define _LINUX_TOPOLOGY_H + +#include + +#endif /* _LINUX_TOPOLOGY_H */