diff --git a/Documentation/admin-guide/hw-vuln/processor_mmio_stale_data.rst b/Documentation/admin-guide/hw-vuln/processor_mmio_stale_data.rst index 9393c50b5afc9..c98fd11907cc8 100644 --- a/Documentation/admin-guide/hw-vuln/processor_mmio_stale_data.rst +++ b/Documentation/admin-guide/hw-vuln/processor_mmio_stale_data.rst @@ -230,6 +230,20 @@ The possible values in this file are: * - 'Mitigation: Clear CPU buffers' - The processor is vulnerable and the CPU buffer clearing mitigation is enabled. + * - 'Unknown: No mitigations' + - The processor vulnerability status is unknown because it is + out of Servicing period. Mitigation is not attempted. + +Definitions: +------------ + +Servicing period: The process of providing functional and security updates to +Intel processors or platforms, utilizing the Intel Platform Update (IPU) +process or other similar mechanisms. + +End of Servicing Updates (ESU): ESU is the date at which Intel will no +longer provide Servicing, such as through IPU or other similar update +processes. ESU dates will typically be aligned to end of quarter. If the processor is vulnerable then the following information is appended to the above information: diff --git a/Makefile b/Makefile index e54b9a1659b4f..cecfe23f521f1 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 5 PATCHLEVEL = 4 -SUBLEVEL = 211 +SUBLEVEL = 212 EXTRAVERSION = NAME = Kleptomaniac Octopus diff --git a/arch/parisc/kernel/unaligned.c b/arch/parisc/kernel/unaligned.c index 286cec4d86d7b..cc6ed74960501 100644 --- a/arch/parisc/kernel/unaligned.c +++ b/arch/parisc/kernel/unaligned.c @@ -107,7 +107,7 @@ #define R1(i) (((i)>>21)&0x1f) #define R2(i) (((i)>>16)&0x1f) #define R3(i) ((i)&0x1f) -#define FR3(i) ((((i)<<1)&0x1f)|(((i)>>6)&1)) +#define FR3(i) ((((i)&0x1f)<<1)|(((i)>>6)&1)) #define IM(i,n) (((i)>>1&((1<<(n-1))-1))|((i)&1?((0-1L)<<(n-1)):0)) #define IM5_2(i) IM((i)>>16,5) #define IM5_3(i) IM((i),5) diff --git a/arch/s390/hypfs/hypfs_diag.c b/arch/s390/hypfs/hypfs_diag.c index f0bc4dc3e9bf0..6511d15ace45e 100644 --- a/arch/s390/hypfs/hypfs_diag.c +++ b/arch/s390/hypfs/hypfs_diag.c @@ -437,7 +437,7 @@ __init int hypfs_diag_init(void) int rc; if (diag204_probe()) { - pr_err("The hardware system does not support hypfs\n"); + pr_info("The hardware system does not support hypfs\n"); return -ENODATA; } diff --git a/arch/s390/hypfs/inode.c b/arch/s390/hypfs/inode.c index 70139d0791b61..ca4fc66a361fb 100644 --- a/arch/s390/hypfs/inode.c +++ b/arch/s390/hypfs/inode.c @@ -501,9 +501,9 @@ fail_hypfs_sprp_exit: hypfs_vm_exit(); fail_hypfs_diag_exit: hypfs_diag_exit(); + pr_err("Initialization of hypfs failed with rc=%i\n", rc); fail_dbfs_exit: hypfs_dbfs_exit(); - pr_err("Initialization of hypfs failed with rc=%i\n", rc); return rc; } device_initcall(hypfs_init) diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c index 4e6299e2ca947..fdd5f37ac1fb8 100644 --- a/arch/s390/kernel/process.c +++ b/arch/s390/kernel/process.c @@ -76,6 +76,18 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) memcpy(dst, src, arch_task_struct_size); dst->thread.fpu.regs = dst->thread.fpu.fprs; + + /* + * Don't transfer over the runtime instrumentation or the guarded + * storage control block pointers. These fields are cleared here instead + * of in copy_thread() to avoid premature freeing of associated memory + * on fork() failure. Wait to clear the RI flag because ->stack still + * refers to the source thread. + */ + dst->thread.ri_cb = NULL; + dst->thread.gs_cb = NULL; + dst->thread.gs_bc_cb = NULL; + return 0; } @@ -133,13 +145,11 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long new_stackp, frame->childregs.flags = 0; if (new_stackp) frame->childregs.gprs[15] = new_stackp; - - /* Don't copy runtime instrumentation info */ - p->thread.ri_cb = NULL; + /* + * Clear the runtime instrumentation flag after the above childregs + * copy. The CB pointer was already cleared in arch_dup_task_struct(). + */ frame->childregs.psw.mask &= ~PSW_MASK_RI; - /* Don't copy guarded storage control block */ - p->thread.gs_cb = NULL; - p->thread.gs_bc_cb = NULL; /* Set a new TLS ? */ if (clone_flags & CLONE_SETTLS) { diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index 7b0bb475c1664..9770381776a63 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -432,7 +432,9 @@ static inline vm_fault_t do_exception(struct pt_regs *regs, int access) flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; if (user_mode(regs)) flags |= FAULT_FLAG_USER; - if (access == VM_WRITE || (trans_exc_code & store_indication) == 0x400) + if ((trans_exc_code & store_indication) == 0x400) + access = VM_WRITE; + if (access == VM_WRITE) flags |= FAULT_FLAG_WRITE; down_read(&mm->mmap_sem); diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c index aec6e63c6a04a..0258e0065771a 100644 --- a/arch/x86/events/intel/uncore_snb.c +++ b/arch/x86/events/intel/uncore_snb.c @@ -575,6 +575,22 @@ int snb_pci2phy_map_init(int devid) return 0; } +static u64 snb_uncore_imc_read_counter(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + + /* + * SNB IMC counters are 32-bit and are laid out back to back + * in MMIO space. Therefore we must use a 32-bit accessor function + * using readq() from uncore_mmio_read_counter() causes problems + * because it is reading 64-bit at a time. This is okay for the + * uncore_perf_event_update() function because it drops the upper + * 32-bits but not okay for plain uncore_read_counter() as invoked + * in uncore_pmu_event_start(). + */ + return (u64)readl(box->io_addr + hwc->event_base); +} + static struct pmu snb_uncore_imc_pmu = { .task_ctx_nr = perf_invalid_context, .event_init = snb_uncore_imc_event_init, @@ -594,7 +610,7 @@ static struct intel_uncore_ops snb_uncore_imc_ops = { .disable_event = snb_uncore_imc_disable_event, .enable_event = snb_uncore_imc_enable_event, .hw_config = snb_uncore_imc_hw_config, - .read_counter = uncore_mmio_read_counter, + .read_counter = snb_uncore_imc_read_counter, }; static struct intel_uncore_type snb_uncore_imc = { diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index a3e32bc938562..736b0e412344b 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -407,6 +407,7 @@ #define X86_BUG_ITLB_MULTIHIT X86_BUG(23) /* CPU may incur MCE during certain page attribute changes */ #define X86_BUG_SRBDS X86_BUG(24) /* CPU may leak RNG bits if not mitigated */ #define X86_BUG_MMIO_STALE_DATA X86_BUG(25) /* CPU is affected by Processor MMIO Stale Data vulnerabilities */ -#define X86_BUG_EIBRS_PBRSB X86_BUG(26) /* EIBRS is vulnerable to Post Barrier RSB Predictions */ +#define X86_BUG_MMIO_UNKNOWN X86_BUG(26) /* CPU is too old and its MMIO Stale Data status is unknown */ +#define X86_BUG_EIBRS_PBRSB X86_BUG(27) /* EIBRS is vulnerable to Post Barrier RSB Predictions */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 57efa90f3fbd0..c90d91cb14341 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -396,7 +396,8 @@ static void __init mmio_select_mitigation(void) u64 ia32_cap; if (!boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA) || - cpu_mitigations_off()) { + boot_cpu_has_bug(X86_BUG_MMIO_UNKNOWN) || + cpu_mitigations_off()) { mmio_mitigation = MMIO_MITIGATION_OFF; return; } @@ -501,6 +502,8 @@ out: pr_info("TAA: %s\n", taa_strings[taa_mitigation]); if (boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA)) pr_info("MMIO Stale Data: %s\n", mmio_strings[mmio_mitigation]); + else if (boot_cpu_has_bug(X86_BUG_MMIO_UNKNOWN)) + pr_info("MMIO Stale Data: Unknown: No mitigations\n"); } static void __init md_clear_select_mitigation(void) @@ -1880,6 +1883,9 @@ static ssize_t tsx_async_abort_show_state(char *buf) static ssize_t mmio_stale_data_show_state(char *buf) { + if (boot_cpu_has_bug(X86_BUG_MMIO_UNKNOWN)) + return sysfs_emit(buf, "Unknown: No mitigations\n"); + if (mmio_mitigation == MMIO_MITIGATION_OFF) return sysfs_emit(buf, "%s\n", mmio_strings[mmio_mitigation]); @@ -2007,6 +2013,7 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr return srbds_show_state(buf); case X86_BUG_MMIO_STALE_DATA: + case X86_BUG_MMIO_UNKNOWN: return mmio_stale_data_show_state(buf); default: @@ -2063,6 +2070,9 @@ ssize_t cpu_show_srbds(struct device *dev, struct device_attribute *attr, char * ssize_t cpu_show_mmio_stale_data(struct device *dev, struct device_attribute *attr, char *buf) { - return cpu_show_common(dev, attr, buf, X86_BUG_MMIO_STALE_DATA); + if (boot_cpu_has_bug(X86_BUG_MMIO_UNKNOWN)) + return cpu_show_common(dev, attr, buf, X86_BUG_MMIO_UNKNOWN); + else + return cpu_show_common(dev, attr, buf, X86_BUG_MMIO_STALE_DATA); } #endif diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index b926b7244d42d..59413e741ecf1 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1026,6 +1026,7 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c) #define NO_ITLB_MULTIHIT BIT(7) #define NO_SPECTRE_V2 BIT(8) #define NO_EIBRS_PBRSB BIT(9) +#define NO_MMIO BIT(10) #define VULNWL(_vendor, _family, _model, _whitelist) \ { X86_VENDOR_##_vendor, _family, _model, X86_FEATURE_ANY, _whitelist } @@ -1046,6 +1047,11 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { VULNWL(NSC, 5, X86_MODEL_ANY, NO_SPECULATION), /* Intel Family 6 */ + VULNWL_INTEL(TIGERLAKE, NO_MMIO), + VULNWL_INTEL(TIGERLAKE_L, NO_MMIO), + VULNWL_INTEL(ALDERLAKE, NO_MMIO), + VULNWL_INTEL(ALDERLAKE_L, NO_MMIO), + VULNWL_INTEL(ATOM_SALTWELL, NO_SPECULATION | NO_ITLB_MULTIHIT), VULNWL_INTEL(ATOM_SALTWELL_TABLET, NO_SPECULATION | NO_ITLB_MULTIHIT), VULNWL_INTEL(ATOM_SALTWELL_MID, NO_SPECULATION | NO_ITLB_MULTIHIT), @@ -1064,9 +1070,9 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { VULNWL_INTEL(ATOM_AIRMONT_MID, NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT), VULNWL_INTEL(ATOM_AIRMONT_NP, NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT), - VULNWL_INTEL(ATOM_GOLDMONT, NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT), - VULNWL_INTEL(ATOM_GOLDMONT_D, NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT), - VULNWL_INTEL(ATOM_GOLDMONT_PLUS, NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_EIBRS_PBRSB), + VULNWL_INTEL(ATOM_GOLDMONT, NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO), + VULNWL_INTEL(ATOM_GOLDMONT_D, NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO), + VULNWL_INTEL(ATOM_GOLDMONT_PLUS, NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_EIBRS_PBRSB), /* * Technically, swapgs isn't serializing on AMD (despite it previously @@ -1081,18 +1087,18 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { VULNWL_INTEL(ATOM_TREMONT_D, NO_ITLB_MULTIHIT | NO_EIBRS_PBRSB), /* AMD Family 0xf - 0x12 */ - VULNWL_AMD(0x0f, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT), - VULNWL_AMD(0x10, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT), - VULNWL_AMD(0x11, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT), - VULNWL_AMD(0x12, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_AMD(0x0f, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO), + VULNWL_AMD(0x10, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO), + VULNWL_AMD(0x11, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO), + VULNWL_AMD(0x12, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO), /* FAMILY_ANY must be last, otherwise 0x0f - 0x12 matches won't work */ - VULNWL_AMD(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT), - VULNWL_HYGON(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_AMD(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO), + VULNWL_HYGON(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO), /* Zhaoxin Family 7 */ - VULNWL(CENTAUR, 7, X86_MODEL_ANY, NO_SPECTRE_V2), - VULNWL(ZHAOXIN, 7, X86_MODEL_ANY, NO_SPECTRE_V2), + VULNWL(CENTAUR, 7, X86_MODEL_ANY, NO_SPECTRE_V2 | NO_MMIO), + VULNWL(ZHAOXIN, 7, X86_MODEL_ANY, NO_SPECTRE_V2 | NO_MMIO), {} }; @@ -1234,10 +1240,16 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) * Affected CPU list is generally enough to enumerate the vulnerability, * but for virtualization case check for ARCH_CAP MSR bits also, VMM may * not want the guest to enumerate the bug. + * + * Set X86_BUG_MMIO_UNKNOWN for CPUs that are neither in the blacklist, + * nor in the whitelist and also don't enumerate MSR ARCH_CAP MMIO bits. */ - if (cpu_matches(cpu_vuln_blacklist, MMIO) && - !arch_cap_mmio_immune(ia32_cap)) - setup_force_cpu_bug(X86_BUG_MMIO_STALE_DATA); + if (!arch_cap_mmio_immune(ia32_cap)) { + if (cpu_matches(cpu_vuln_blacklist, MMIO)) + setup_force_cpu_bug(X86_BUG_MMIO_STALE_DATA); + else if (!cpu_matches(cpu_vuln_whitelist, NO_MMIO)) + setup_force_cpu_bug(X86_BUG_MMIO_UNKNOWN); + } if (cpu_has(c, X86_FEATURE_IBRS_ENHANCED) && !cpu_matches(cpu_vuln_whitelist, NO_EIBRS_PBRSB) && diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c index b934f9f68a168..4e7c49fcf0030 100644 --- a/arch/x86/kernel/unwind_orc.c +++ b/arch/x86/kernel/unwind_orc.c @@ -90,22 +90,27 @@ static struct orc_entry *orc_find(unsigned long ip); static struct orc_entry *orc_ftrace_find(unsigned long ip) { struct ftrace_ops *ops; - unsigned long caller; + unsigned long tramp_addr, offset; ops = ftrace_ops_trampoline(ip); if (!ops) return NULL; + /* Set tramp_addr to the start of the code copied by the trampoline */ if (ops->flags & FTRACE_OPS_FL_SAVE_REGS) - caller = (unsigned long)ftrace_regs_call; + tramp_addr = (unsigned long)ftrace_regs_caller; else - caller = (unsigned long)ftrace_call; + tramp_addr = (unsigned long)ftrace_caller; + + /* Now place tramp_addr to the location within the trampoline ip is at */ + offset = ip - ops->trampoline; + tramp_addr += offset; /* Prevent unlikely recursion */ - if (ip == caller) + if (ip == tramp_addr) return NULL; - return orc_find(caller); + return orc_find(tramp_addr); } #else static struct orc_entry *orc_ftrace_find(unsigned long ip) diff --git a/drivers/acpi/processor_thermal.c b/drivers/acpi/processor_thermal.c index 41feb88ee92d6..458b4d99fb4e5 100644 --- a/drivers/acpi/processor_thermal.c +++ b/drivers/acpi/processor_thermal.c @@ -150,7 +150,7 @@ void acpi_thermal_cpufreq_exit(struct cpufreq_policy *policy) unsigned int cpu; for_each_cpu(cpu, policy->related_cpus) { - struct acpi_processor *pr = per_cpu(processors, policy->cpu); + struct acpi_processor *pr = per_cpu(processors, cpu); if (pr) freq_qos_remove_request(&pr->thermal_req); diff --git a/drivers/android/binder.c b/drivers/android/binder.c index b9fb2a9269443..c273d0df69394 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -6083,6 +6083,7 @@ const struct file_operations binder_fops = { .open = binder_open, .flush = binder_flush, .release = binder_release, + .may_pollfree = true, }; static int __init init_binder_device(const char *name) diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 6b3e27b8cd245..b8f57b1c2864b 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -1397,6 +1397,11 @@ loop_get_status(struct loop_device *lo, struct loop_info64 *info) info->lo_number = lo->lo_number; info->lo_offset = lo->lo_offset; info->lo_sizelimit = lo->lo_sizelimit; + + /* loff_t vars have been assigned __u64 */ + if (lo->lo_offset < 0 || lo->lo_sizelimit < 0) + return -EOVERFLOW; + info->lo_flags = lo->lo_flags; memcpy(info->lo_file_name, lo->lo_file_name, LO_NAME_SIZE); memcpy(info->lo_crypt_name, lo->lo_crypt_name, LO_NAME_SIZE); diff --git a/drivers/dma-buf/udmabuf.c b/drivers/dma-buf/udmabuf.c index c6e9b7bd7618c..80ccdf96093ff 100644 --- a/drivers/dma-buf/udmabuf.c +++ b/drivers/dma-buf/udmabuf.c @@ -287,7 +287,23 @@ static struct miscdevice udmabuf_misc = { static int __init udmabuf_dev_init(void) { - return misc_register(&udmabuf_misc); + int ret; + + ret = misc_register(&udmabuf_misc); + if (ret < 0) { + pr_err("Could not initialize udmabuf device\n"); + return ret; + } + + ret = dma_coerce_mask_and_coherent(udmabuf_misc.this_device, + DMA_BIT_MASK(64)); + if (ret < 0) { + pr_err("Could not setup DMA mask for udmabuf device\n"); + misc_deregister(&udmabuf_misc); + return ret; + } + + return 0; } static void __exit udmabuf_dev_exit(void) diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c b/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c index eca67d5d5b10d..721be82ccebec 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c @@ -546,9 +546,11 @@ static void dce112_get_pix_clk_dividers_helper ( switch (pix_clk_params->color_depth) { case COLOR_DEPTH_101010: actual_pixel_clock_100hz = (actual_pixel_clock_100hz * 5) >> 2; + actual_pixel_clock_100hz -= actual_pixel_clock_100hz % 10; break; case COLOR_DEPTH_121212: actual_pixel_clock_100hz = (actual_pixel_clock_100hz * 6) >> 2; + actual_pixel_clock_100hz -= actual_pixel_clock_100hz % 10; break; case COLOR_DEPTH_161616: actual_pixel_clock_100hz = actual_pixel_clock_100hz * 2; diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.c index 8b2f29f6dabd2..068e79fa3490d 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.c @@ -118,6 +118,12 @@ struct mpcc *mpc1_get_mpcc_for_dpp(struct mpc_tree *tree, int dpp_id) while (tmp_mpcc != NULL) { if (tmp_mpcc->dpp_id == dpp_id) return tmp_mpcc; + + /* avoid circular linked list */ + ASSERT(tmp_mpcc != tmp_mpcc->mpcc_bot); + if (tmp_mpcc == tmp_mpcc->mpcc_bot) + break; + tmp_mpcc = tmp_mpcc->mpcc_bot; } return NULL; diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c index e74a07d03fde9..4b0200e96eb77 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c @@ -425,6 +425,11 @@ void optc1_enable_optc_clock(struct timing_generator *optc, bool enable) OTG_CLOCK_ON, 1, 1, 1000); } else { + + //last chance to clear underflow, otherwise, it will always there due to clock is off. + if (optc->funcs->is_optc_underflow_occurred(optc) == true) + optc->funcs->clear_optc_underflow(optc); + REG_UPDATE_2(OTG_CLOCK_CONTROL, OTG_CLOCK_GATE_DIS, 0, OTG_CLOCK_EN, 0); diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_mpc.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_mpc.c index 5a188b2bc033c..0a00bd8e00abc 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_mpc.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_mpc.c @@ -488,6 +488,12 @@ struct mpcc *mpc2_get_mpcc_for_dpp(struct mpc_tree *tree, int dpp_id) while (tmp_mpcc != NULL) { if (tmp_mpcc->dpp_id == 0xf || tmp_mpcc->dpp_id == dpp_id) return tmp_mpcc; + + /* avoid circular linked list */ + ASSERT(tmp_mpcc != tmp_mpcc->mpcc_bot); + if (tmp_mpcc == tmp_mpcc->mpcc_bot) + break; + tmp_mpcc = tmp_mpcc->mpcc_bot; } return NULL; diff --git a/drivers/hid/hid-steam.c b/drivers/hid/hid-steam.c index a3b151b29bd71..fc616db4231bb 100644 --- a/drivers/hid/hid-steam.c +++ b/drivers/hid/hid-steam.c @@ -134,6 +134,11 @@ static int steam_recv_report(struct steam_device *steam, int ret; r = steam->hdev->report_enum[HID_FEATURE_REPORT].report_id_hash[0]; + if (!r) { + hid_err(steam->hdev, "No HID_FEATURE_REPORT submitted - nothing to read\n"); + return -EINVAL; + } + if (hid_report_len(r) < 64) return -EINVAL; @@ -165,6 +170,11 @@ static int steam_send_report(struct steam_device *steam, int ret; r = steam->hdev->report_enum[HID_FEATURE_REPORT].report_id_hash[0]; + if (!r) { + hid_err(steam->hdev, "No HID_FEATURE_REPORT submitted - nothing to read\n"); + return -EINVAL; + } + if (hid_report_len(r) < 64) return -EINVAL; diff --git a/drivers/hid/hidraw.c b/drivers/hid/hidraw.c index b382c6bf2c5cb..f8ef6268f3f29 100644 --- a/drivers/hid/hidraw.c +++ b/drivers/hid/hidraw.c @@ -346,10 +346,13 @@ static int hidraw_release(struct inode * inode, struct file * file) unsigned int minor = iminor(inode); struct hidraw_list *list = file->private_data; unsigned long flags; + int i; mutex_lock(&minors_lock); spin_lock_irqsave(&hidraw_table[minor]->list_lock, flags); + for (i = list->tail; i < list->head; i++) + kfree(list->buffer[i].value); list_del(&list->node); spin_unlock_irqrestore(&hidraw_table[minor]->list_lock, flags); kfree(list); diff --git a/drivers/md/md.c b/drivers/md/md.c index 11fd3b32b5621..5226a23c72dba 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -6094,6 +6094,7 @@ void md_stop(struct mddev *mddev) /* stop the array and free an attached data structures. * This is called from dm-raid */ + __md_stop_writes(mddev); __md_stop(mddev); bioset_exit(&mddev->bio_set); bioset_exit(&mddev->sync_set); diff --git a/drivers/media/usb/pvrusb2/pvrusb2-hdw.c b/drivers/media/usb/pvrusb2/pvrusb2-hdw.c index 11e7fcfc3f195..d101fa8d61bb0 100644 --- a/drivers/media/usb/pvrusb2/pvrusb2-hdw.c +++ b/drivers/media/usb/pvrusb2/pvrusb2-hdw.c @@ -2611,6 +2611,7 @@ struct pvr2_hdw *pvr2_hdw_create(struct usb_interface *intf, del_timer_sync(&hdw->encoder_run_timer); del_timer_sync(&hdw->encoder_wait_timer); flush_work(&hdw->workpoll); + v4l2_device_unregister(&hdw->v4l2_dev); usb_free_urb(hdw->ctl_read_urb); usb_free_urb(hdw->ctl_write_urb); kfree(hdw->ctl_read_buffer); diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c index 31ed7616e84e7..0d6cd2a4cc416 100644 --- a/drivers/net/bonding/bond_3ad.c +++ b/drivers/net/bonding/bond_3ad.c @@ -1997,30 +1997,24 @@ void bond_3ad_initiate_agg_selection(struct bonding *bond, int timeout) */ void bond_3ad_initialize(struct bonding *bond, u16 tick_resolution) { - /* check that the bond is not initialized yet */ - if (!MAC_ADDRESS_EQUAL(&(BOND_AD_INFO(bond).system.sys_mac_addr), - bond->dev->dev_addr)) { - - BOND_AD_INFO(bond).aggregator_identifier = 0; - - BOND_AD_INFO(bond).system.sys_priority = - bond->params.ad_actor_sys_prio; - if (is_zero_ether_addr(bond->params.ad_actor_system)) - BOND_AD_INFO(bond).system.sys_mac_addr = - *((struct mac_addr *)bond->dev->dev_addr); - else - BOND_AD_INFO(bond).system.sys_mac_addr = - *((struct mac_addr *)bond->params.ad_actor_system); + BOND_AD_INFO(bond).aggregator_identifier = 0; + BOND_AD_INFO(bond).system.sys_priority = + bond->params.ad_actor_sys_prio; + if (is_zero_ether_addr(bond->params.ad_actor_system)) + BOND_AD_INFO(bond).system.sys_mac_addr = + *((struct mac_addr *)bond->dev->dev_addr); + else + BOND_AD_INFO(bond).system.sys_mac_addr = + *((struct mac_addr *)bond->params.ad_actor_system); - /* initialize how many times this module is called in one - * second (should be about every 100ms) - */ - ad_ticks_per_sec = tick_resolution; + /* initialize how many times this module is called in one + * second (should be about every 100ms) + */ + ad_ticks_per_sec = tick_resolution; - bond_3ad_initiate_agg_selection(bond, - AD_AGGREGATOR_SELECTION_TIMER * - ad_ticks_per_sec); - } + bond_3ad_initiate_agg_selection(bond, + AD_AGGREGATOR_SELECTION_TIMER * + ad_ticks_per_sec); } /** diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c index 452be9749827a..3434ad6824a05 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c @@ -597,7 +597,7 @@ static int bnxt_hwrm_func_vf_resc_cfg(struct bnxt *bp, int num_vfs, bool reset) hw_resc->max_stat_ctxs -= le16_to_cpu(req.min_stat_ctx) * n; hw_resc->max_vnics -= le16_to_cpu(req.min_vnics) * n; if (bp->flags & BNXT_FLAG_CHIP_P5) - hw_resc->max_irqs -= vf_msix * n; + hw_resc->max_nqs -= vf_msix; rc = pf->active_vfs; } diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c index 0be13a90ff792..d155181b939e4 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c @@ -1211,7 +1211,6 @@ void ixgbe_ptp_start_cyclecounter(struct ixgbe_adapter *adapter) struct cyclecounter cc; unsigned long flags; u32 incval = 0; - u32 tsauxc = 0; u32 fuse0 = 0; /* For some of the boards below this mask is technically incorrect. @@ -1246,18 +1245,6 @@ void ixgbe_ptp_start_cyclecounter(struct ixgbe_adapter *adapter) case ixgbe_mac_x550em_a: case ixgbe_mac_X550: cc.read = ixgbe_ptp_read_X550; - - /* enable SYSTIME counter */ - IXGBE_WRITE_REG(hw, IXGBE_SYSTIMR, 0); - IXGBE_WRITE_REG(hw, IXGBE_SYSTIML, 0); - IXGBE_WRITE_REG(hw, IXGBE_SYSTIMH, 0); - tsauxc = IXGBE_READ_REG(hw, IXGBE_TSAUXC); - IXGBE_WRITE_REG(hw, IXGBE_TSAUXC, - tsauxc & ~IXGBE_TSAUXC_DISABLE_SYSTIME); - IXGBE_WRITE_REG(hw, IXGBE_TSIM, IXGBE_TSIM_TXTS); - IXGBE_WRITE_REG(hw, IXGBE_EIMS, IXGBE_EIMS_TIMESYNC); - - IXGBE_WRITE_FLUSH(hw); break; case ixgbe_mac_X540: cc.read = ixgbe_ptp_read_82599; @@ -1289,6 +1276,50 @@ void ixgbe_ptp_start_cyclecounter(struct ixgbe_adapter *adapter) spin_unlock_irqrestore(&adapter->tmreg_lock, flags); } +/** + * ixgbe_ptp_init_systime - Initialize SYSTIME registers + * @adapter: the ixgbe private board structure + * + * Initialize and start the SYSTIME registers. + */ +static void ixgbe_ptp_init_systime(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + u32 tsauxc; + + switch (hw->mac.type) { + case ixgbe_mac_X550EM_x: + case ixgbe_mac_x550em_a: + case ixgbe_mac_X550: + tsauxc = IXGBE_READ_REG(hw, IXGBE_TSAUXC); + + /* Reset SYSTIME registers to 0 */ + IXGBE_WRITE_REG(hw, IXGBE_SYSTIMR, 0); + IXGBE_WRITE_REG(hw, IXGBE_SYSTIML, 0); + IXGBE_WRITE_REG(hw, IXGBE_SYSTIMH, 0); + + /* Reset interrupt settings */ + IXGBE_WRITE_REG(hw, IXGBE_TSIM, IXGBE_TSIM_TXTS); + IXGBE_WRITE_REG(hw, IXGBE_EIMS, IXGBE_EIMS_TIMESYNC); + + /* Activate the SYSTIME counter */ + IXGBE_WRITE_REG(hw, IXGBE_TSAUXC, + tsauxc & ~IXGBE_TSAUXC_DISABLE_SYSTIME); + break; + case ixgbe_mac_X540: + case ixgbe_mac_82599EB: + /* Reset SYSTIME registers to 0 */ + IXGBE_WRITE_REG(hw, IXGBE_SYSTIML, 0); + IXGBE_WRITE_REG(hw, IXGBE_SYSTIMH, 0); + break; + default: + /* Other devices aren't supported */ + return; + }; + + IXGBE_WRITE_FLUSH(hw); +} + /** * ixgbe_ptp_reset * @adapter: the ixgbe private board structure @@ -1315,6 +1346,8 @@ void ixgbe_ptp_reset(struct ixgbe_adapter *adapter) ixgbe_ptp_start_cyclecounter(adapter); + ixgbe_ptp_init_systime(adapter); + spin_lock_irqsave(&adapter->tmreg_lock, flags); timecounter_init(&adapter->hw_tc, &adapter->hw_cc, ktime_to_ns(ktime_get_real())); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 88b51f64a64ea..f448a139e222e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -1434,6 +1434,8 @@ static void mlx5e_build_rep_params(struct net_device *netdev) params->num_tc = 1; params->tunneled_offload_en = false; + if (rep->vport != MLX5_VPORT_UPLINK) + params->vlan_strip_disable = true; mlx5_query_min_inline(mdev, ¶ms->tx_min_inline_mode); diff --git a/drivers/net/ethernet/moxa/moxart_ether.c b/drivers/net/ethernet/moxa/moxart_ether.c index 383d72415c659..87327086ea8ca 100644 --- a/drivers/net/ethernet/moxa/moxart_ether.c +++ b/drivers/net/ethernet/moxa/moxart_ether.c @@ -74,11 +74,6 @@ static int moxart_set_mac_address(struct net_device *ndev, void *addr) static void moxart_mac_free_memory(struct net_device *ndev) { struct moxart_mac_priv_t *priv = netdev_priv(ndev); - int i; - - for (i = 0; i < RX_DESC_NUM; i++) - dma_unmap_single(&priv->pdev->dev, priv->rx_mapping[i], - priv->rx_buf_size, DMA_FROM_DEVICE); if (priv->tx_desc_base) dma_free_coherent(&priv->pdev->dev, @@ -193,6 +188,7 @@ static int moxart_mac_open(struct net_device *ndev) static int moxart_mac_stop(struct net_device *ndev) { struct moxart_mac_priv_t *priv = netdev_priv(ndev); + int i; napi_disable(&priv->napi); @@ -204,6 +200,11 @@ static int moxart_mac_stop(struct net_device *ndev) /* disable all functions */ writel(0, priv->base + REG_MAC_CTRL); + /* unmap areas mapped in moxart_mac_setup_desc_ring() */ + for (i = 0; i < RX_DESC_NUM; i++) + dma_unmap_single(&priv->pdev->dev, priv->rx_mapping[i], + priv->rx_buf_size, DMA_FROM_DEVICE); + return 0; } diff --git a/drivers/net/ipvlan/ipvtap.c b/drivers/net/ipvlan/ipvtap.c index 1cedb634f4f7b..f01078b2581ce 100644 --- a/drivers/net/ipvlan/ipvtap.c +++ b/drivers/net/ipvlan/ipvtap.c @@ -194,7 +194,7 @@ static struct notifier_block ipvtap_notifier_block __read_mostly = { .notifier_call = ipvtap_device_event, }; -static int ipvtap_init(void) +static int __init ipvtap_init(void) { int err; @@ -228,7 +228,7 @@ out1: } module_init(ipvtap_init); -static void ipvtap_exit(void) +static void __exit ipvtap_exit(void) { rtnl_link_unregister(&ipvtap_link_ops); unregister_netdevice_notifier(&ipvtap_notifier_block); diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c index 4c02439d3776d..ca3f18aa16acb 100644 --- a/drivers/pinctrl/pinctrl-amd.c +++ b/drivers/pinctrl/pinctrl-amd.c @@ -793,6 +793,7 @@ static int amd_gpio_suspend(struct device *dev) { struct amd_gpio *gpio_dev = dev_get_drvdata(dev); struct pinctrl_desc *desc = gpio_dev->pctrl->desc; + unsigned long flags; int i; for (i = 0; i < desc->npins; i++) { @@ -801,7 +802,9 @@ static int amd_gpio_suspend(struct device *dev) if (!amd_gpio_should_save(gpio_dev, pin)) continue; - gpio_dev->saved_regs[i] = readl(gpio_dev->base + pin*4); + raw_spin_lock_irqsave(&gpio_dev->lock, flags); + gpio_dev->saved_regs[i] = readl(gpio_dev->base + pin * 4) & ~PIN_IRQ_PENDING; + raw_spin_unlock_irqrestore(&gpio_dev->lock, flags); } return 0; @@ -811,6 +814,7 @@ static int amd_gpio_resume(struct device *dev) { struct amd_gpio *gpio_dev = dev_get_drvdata(dev); struct pinctrl_desc *desc = gpio_dev->pctrl->desc; + unsigned long flags; int i; for (i = 0; i < desc->npins; i++) { @@ -819,7 +823,10 @@ static int amd_gpio_resume(struct device *dev) if (!amd_gpio_should_save(gpio_dev, pin)) continue; - writel(gpio_dev->saved_regs[i], gpio_dev->base + pin*4); + raw_spin_lock_irqsave(&gpio_dev->lock, flags); + gpio_dev->saved_regs[i] |= readl(gpio_dev->base + pin * 4) & PIN_IRQ_PENDING; + writel(gpio_dev->saved_regs[i], gpio_dev->base + pin * 4); + raw_spin_unlock_irqrestore(&gpio_dev->lock, flags); } return 0; diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c index 5087ed6afbdc3..8d1b19b2322f5 100644 --- a/drivers/scsi/storvsc_drv.c +++ b/drivers/scsi/storvsc_drv.c @@ -1846,7 +1846,7 @@ static int storvsc_probe(struct hv_device *device, */ host_dev->handle_error_wq = alloc_ordered_workqueue("storvsc_error_wq_%d", - WQ_MEM_RECLAIM, + 0, host->host_no); if (!host_dev->handle_error_wq) goto err_out2; diff --git a/drivers/usb/cdns3/gadget.c b/drivers/usb/cdns3/gadget.c index a9399f2b39308..8bedf0504e92f 100644 --- a/drivers/usb/cdns3/gadget.c +++ b/drivers/usb/cdns3/gadget.c @@ -2166,6 +2166,7 @@ int __cdns3_gadget_ep_clear_halt(struct cdns3_endpoint *priv_ep) struct usb_request *request; struct cdns3_request *priv_req; struct cdns3_trb *trb = NULL; + struct cdns3_trb trb_tmp; int ret; int val; @@ -2175,8 +2176,10 @@ int __cdns3_gadget_ep_clear_halt(struct cdns3_endpoint *priv_ep) if (request) { priv_req = to_cdns3_request(request); trb = priv_req->trb; - if (trb) + if (trb) { + trb_tmp = *trb; trb->control = trb->control ^ TRB_CYCLE; + } } writel(EP_CMD_CSTALL | EP_CMD_EPRST, &priv_dev->regs->ep_cmd); @@ -2191,7 +2194,8 @@ int __cdns3_gadget_ep_clear_halt(struct cdns3_endpoint *priv_ep) if (request) { if (trb) - trb->control = trb->control ^ TRB_CYCLE; + *trb = trb_tmp; + cdns3_rearm_transfer(priv_ep, 1); } diff --git a/drivers/video/fbdev/pm2fb.c b/drivers/video/fbdev/pm2fb.c index 1dcf02e12af4f..8ae010f07d7da 100644 --- a/drivers/video/fbdev/pm2fb.c +++ b/drivers/video/fbdev/pm2fb.c @@ -616,6 +616,11 @@ static int pm2fb_check_var(struct fb_var_screeninfo *var, struct fb_info *info) return -EINVAL; } + if (!var->pixclock) { + DPRINTK("pixclock is zero\n"); + return -EINVAL; + } + if (PICOS2KHZ(var->pixclock) > PM2_MAX_PIXCLOCK) { DPRINTK("pixclock too high (%ldKHz)\n", PICOS2KHZ(var->pixclock)); diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index cd77c0621a555..c2e5fe972f566 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -2727,7 +2727,7 @@ struct btrfs_dir_item * btrfs_lookup_dir_index_item(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, u64 dir, - u64 objectid, const char *name, int name_len, + u64 index, const char *name, int name_len, int mod); struct btrfs_dir_item * btrfs_search_dir_index_item(struct btrfs_root *root, diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c index 1cb7f5d79765d..444e1e5d012e4 100644 --- a/fs/btrfs/dev-replace.c +++ b/fs/btrfs/dev-replace.c @@ -125,7 +125,7 @@ no_valid_dev_replace_entry_found: if (btrfs_find_device(fs_info->fs_devices, BTRFS_DEV_REPLACE_DEVID, NULL, NULL, false)) { btrfs_err(fs_info, - "replace devid present without an active replace item"); +"replace without active item, run 'device scan --forget' on the target device"); ret = -EUCLEAN; } else { dev_replace->srcdev = NULL; @@ -918,8 +918,7 @@ int btrfs_dev_replace_cancel(struct btrfs_fs_info *fs_info) up_write(&dev_replace->rwsem); /* Scrub for replace must not be running in suspended state */ - ret = btrfs_scrub_cancel(fs_info); - ASSERT(ret != -ENOTCONN); + btrfs_scrub_cancel(fs_info); trans = btrfs_start_transaction(root, 0); if (IS_ERR(trans)) { diff --git a/fs/btrfs/dir-item.c b/fs/btrfs/dir-item.c index 863367c2c6205..98c6faa8ce15b 100644 --- a/fs/btrfs/dir-item.c +++ b/fs/btrfs/dir-item.c @@ -171,10 +171,40 @@ out_free: return 0; } +static struct btrfs_dir_item *btrfs_lookup_match_dir( + struct btrfs_trans_handle *trans, + struct btrfs_root *root, struct btrfs_path *path, + struct btrfs_key *key, const char *name, + int name_len, int mod) +{ + const int ins_len = (mod < 0 ? -1 : 0); + const int cow = (mod != 0); + int ret; + + ret = btrfs_search_slot(trans, root, key, path, ins_len, cow); + if (ret < 0) + return ERR_PTR(ret); + if (ret > 0) + return ERR_PTR(-ENOENT); + + return btrfs_match_dir_item_name(root->fs_info, path, name, name_len); +} + /* - * lookup a directory item based on name. 'dir' is the objectid - * we're searching in, and 'mod' tells us if you plan on deleting the - * item (use mod < 0) or changing the options (use mod > 0) + * Lookup for a directory item by name. + * + * @trans: The transaction handle to use. Can be NULL if @mod is 0. + * @root: The root of the target tree. + * @path: Path to use for the search. + * @dir: The inode number (objectid) of the directory. + * @name: The name associated to the directory entry we are looking for. + * @name_len: The length of the name. + * @mod: Used to indicate if the tree search is meant for a read only + * lookup, for a modification lookup or for a deletion lookup, so + * its value should be 0, 1 or -1, respectively. + * + * Returns: NULL if the dir item does not exists, an error pointer if an error + * happened, or a pointer to a dir item if a dir item exists for the given name. */ struct btrfs_dir_item *btrfs_lookup_dir_item(struct btrfs_trans_handle *trans, struct btrfs_root *root, @@ -182,23 +212,18 @@ struct btrfs_dir_item *btrfs_lookup_dir_item(struct btrfs_trans_handle *trans, const char *name, int name_len, int mod) { - int ret; struct btrfs_key key; - int ins_len = mod < 0 ? -1 : 0; - int cow = mod != 0; + struct btrfs_dir_item *di; key.objectid = dir; key.type = BTRFS_DIR_ITEM_KEY; - key.offset = btrfs_name_hash(name, name_len); - ret = btrfs_search_slot(trans, root, &key, path, ins_len, cow); - if (ret < 0) - return ERR_PTR(ret); - if (ret > 0) + di = btrfs_lookup_match_dir(trans, root, path, &key, name, name_len, mod); + if (IS_ERR(di) && PTR_ERR(di) == -ENOENT) return NULL; - return btrfs_match_dir_item_name(root->fs_info, path, name, name_len); + return di; } int btrfs_check_dir_item_collision(struct btrfs_root *root, u64 dir, @@ -212,7 +237,6 @@ int btrfs_check_dir_item_collision(struct btrfs_root *root, u64 dir, int slot; struct btrfs_path *path; - path = btrfs_alloc_path(); if (!path) return -ENOMEM; @@ -221,20 +245,20 @@ int btrfs_check_dir_item_collision(struct btrfs_root *root, u64 dir, key.type = BTRFS_DIR_ITEM_KEY; key.offset = btrfs_name_hash(name, name_len); - ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); - - /* return back any errors */ - if (ret < 0) - goto out; + di = btrfs_lookup_match_dir(NULL, root, path, &key, name, name_len, 0); + if (IS_ERR(di)) { + ret = PTR_ERR(di); + /* Nothing found, we're safe */ + if (ret == -ENOENT) { + ret = 0; + goto out; + } - /* nothing found, we're safe */ - if (ret > 0) { - ret = 0; - goto out; + if (ret < 0) + goto out; } /* we found an item, look for our name in the item */ - di = btrfs_match_dir_item_name(root->fs_info, path, name, name_len); if (di) { /* our exact name was found */ ret = -EEXIST; @@ -261,35 +285,42 @@ out: } /* - * lookup a directory item based on index. 'dir' is the objectid - * we're searching in, and 'mod' tells us if you plan on deleting the - * item (use mod < 0) or changing the options (use mod > 0) + * Lookup for a directory index item by name and index number. + * + * @trans: The transaction handle to use. Can be NULL if @mod is 0. + * @root: The root of the target tree. + * @path: Path to use for the search. + * @dir: The inode number (objectid) of the directory. + * @index: The index number. + * @name: The name associated to the directory entry we are looking for. + * @name_len: The length of the name. + * @mod: Used to indicate if the tree search is meant for a read only + * lookup, for a modification lookup or for a deletion lookup, so + * its value should be 0, 1 or -1, respectively. * - * The name is used to make sure the index really points to the name you were - * looking for. + * Returns: NULL if the dir index item does not exists, an error pointer if an + * error happened, or a pointer to a dir item if the dir index item exists and + * matches the criteria (name and index number). */ struct btrfs_dir_item * btrfs_lookup_dir_index_item(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, u64 dir, - u64 objectid, const char *name, int name_len, + u64 index, const char *name, int name_len, int mod) { - int ret; + struct btrfs_dir_item *di; struct btrfs_key key; - int ins_len = mod < 0 ? -1 : 0; - int cow = mod != 0; key.objectid = dir; key.type = BTRFS_DIR_INDEX_KEY; - key.offset = objectid; + key.offset = index; - ret = btrfs_search_slot(trans, root, &key, path, ins_len, cow); - if (ret < 0) - return ERR_PTR(ret); - if (ret > 0) - return ERR_PTR(-ENOENT); - return btrfs_match_dir_item_name(root->fs_info, path, name, name_len); + di = btrfs_lookup_match_dir(trans, root, path, &key, name, name_len, mod); + if (di == ERR_PTR(-ENOENT)) + return NULL; + + return di; } struct btrfs_dir_item * @@ -346,21 +377,18 @@ struct btrfs_dir_item *btrfs_lookup_xattr(struct btrfs_trans_handle *trans, const char *name, u16 name_len, int mod) { - int ret; struct btrfs_key key; - int ins_len = mod < 0 ? -1 : 0; - int cow = mod != 0; + struct btrfs_dir_item *di; key.objectid = dir; key.type = BTRFS_XATTR_ITEM_KEY; key.offset = btrfs_name_hash(name, name_len); - ret = btrfs_search_slot(trans, root, &key, path, ins_len, cow); - if (ret < 0) - return ERR_PTR(ret); - if (ret > 0) + + di = btrfs_lookup_match_dir(trans, root, path, &key, name, name_len, mod); + if (IS_ERR(di) && PTR_ERR(di) == -ENOENT) return NULL; - return btrfs_match_dir_item_name(root->fs_info, path, name, name_len); + return di; } /* diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 7755a0362a3ad..20c5db8ef8427 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -9751,8 +9751,6 @@ static int btrfs_rename_exchange(struct inode *old_dir, /* force full log commit if subvolume involved. */ btrfs_set_log_full_commit(trans); } else { - btrfs_pin_log_trans(root); - root_log_pinned = true; ret = btrfs_insert_inode_ref(trans, dest, new_dentry->d_name.name, new_dentry->d_name.len, @@ -9768,8 +9766,6 @@ static int btrfs_rename_exchange(struct inode *old_dir, /* force full log commit if subvolume involved. */ btrfs_set_log_full_commit(trans); } else { - btrfs_pin_log_trans(dest); - dest_log_pinned = true; ret = btrfs_insert_inode_ref(trans, root, old_dentry->d_name.name, old_dentry->d_name.len, @@ -9797,6 +9793,29 @@ static int btrfs_rename_exchange(struct inode *old_dir, BTRFS_I(new_inode), 1); } + /* + * Now pin the logs of the roots. We do it to ensure that no other task + * can sync the logs while we are in progress with the rename, because + * that could result in an inconsistency in case any of the inodes that + * are part of this rename operation were logged before. + * + * We pin the logs even if at this precise moment none of the inodes was + * logged before. This is because right after we checked for that, some + * other task fsyncing some other inode not involved with this rename + * operation could log that one of our inodes exists. + * + * We don't need to pin the logs before the above calls to + * btrfs_insert_inode_ref(), since those don't ever need to change a log. + */ + if (old_ino != BTRFS_FIRST_FREE_OBJECTID) { + btrfs_pin_log_trans(root); + root_log_pinned = true; + } + if (new_ino != BTRFS_FIRST_FREE_OBJECTID) { + btrfs_pin_log_trans(dest); + dest_log_pinned = true; + } + /* src is a subvolume */ if (old_ino == BTRFS_FIRST_FREE_OBJECTID) { ret = btrfs_unlink_subvol(trans, old_dir, old_dentry); @@ -10046,8 +10065,6 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry, /* force full log commit if subvolume involved. */ btrfs_set_log_full_commit(trans); } else { - btrfs_pin_log_trans(root); - log_pinned = true; ret = btrfs_insert_inode_ref(trans, dest, new_dentry->d_name.name, new_dentry->d_name.len, @@ -10071,6 +10088,25 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry, if (unlikely(old_ino == BTRFS_FIRST_FREE_OBJECTID)) { ret = btrfs_unlink_subvol(trans, old_dir, old_dentry); } else { + /* + * Now pin the log. We do it to ensure that no other task can + * sync the log while we are in progress with the rename, as + * that could result in an inconsistency in case any of the + * inodes that are part of this rename operation were logged + * before. + * + * We pin the log even if at this precise moment none of the + * inodes was logged before. This is because right after we + * checked for that, some other task fsyncing some other inode + * not involved with this rename operation could log that one of + * our inodes exists. + * + * We don't need to pin the logs before the above call to + * btrfs_insert_inode_ref(), since that does not need to change + * a log. + */ + btrfs_pin_log_trans(root); + log_pinned = true; ret = __btrfs_unlink_inode(trans, root, BTRFS_I(old_dir), BTRFS_I(d_inode(old_dentry)), old_dentry->d_name.name, diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c index 0d07ebe511e7f..ba4e198811a47 100644 --- a/fs/btrfs/root-tree.c +++ b/fs/btrfs/root-tree.c @@ -371,9 +371,10 @@ int btrfs_del_root_ref(struct btrfs_trans_handle *trans, u64 root_id, key.offset = ref_id; again: ret = btrfs_search_slot(trans, tree_root, &key, path, -1, 1); - if (ret < 0) + if (ret < 0) { + err = ret; goto out; - if (ret == 0) { + } else if (ret == 0) { leaf = path->nodes[0]; ref = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_root_ref); diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index 368c43c6cbd08..d15de5abb562d 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -1019,7 +1019,8 @@ static void extent_err(const struct extent_buffer *eb, int slot, } static int check_extent_item(struct extent_buffer *leaf, - struct btrfs_key *key, int slot) + struct btrfs_key *key, int slot, + struct btrfs_key *prev_key) { struct btrfs_fs_info *fs_info = leaf->fs_info; struct btrfs_extent_item *ei; @@ -1230,6 +1231,26 @@ static int check_extent_item(struct extent_buffer *leaf, total_refs, inline_refs); return -EUCLEAN; } + + if ((prev_key->type == BTRFS_EXTENT_ITEM_KEY) || + (prev_key->type == BTRFS_METADATA_ITEM_KEY)) { + u64 prev_end = prev_key->objectid; + + if (prev_key->type == BTRFS_METADATA_ITEM_KEY) + prev_end += fs_info->nodesize; + else + prev_end += prev_key->offset; + + if (unlikely(prev_end > key->objectid)) { + extent_err(leaf, slot, + "previous extent [%llu %u %llu] overlaps current extent [%llu %u %llu]", + prev_key->objectid, prev_key->type, + prev_key->offset, key->objectid, key->type, + key->offset); + return -EUCLEAN; + } + } + return 0; } @@ -1343,7 +1364,7 @@ static int check_leaf_item(struct extent_buffer *leaf, break; case BTRFS_EXTENT_ITEM_KEY: case BTRFS_METADATA_ITEM_KEY: - ret = check_extent_item(leaf, key, slot); + ret = check_extent_item(leaf, key, slot, prev_key); break; case BTRFS_TREE_BLOCK_REF_KEY: case BTRFS_SHARED_DATA_REF_KEY: diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index bebd74267bed6..926b1d34e55cc 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -918,8 +918,7 @@ static noinline int inode_in_dir(struct btrfs_root *root, di = btrfs_lookup_dir_index_item(NULL, root, path, dirid, index, name, name_len, 0); if (IS_ERR(di)) { - if (PTR_ERR(di) != -ENOENT) - ret = PTR_ERR(di); + ret = PTR_ERR(di); goto out; } else if (di) { btrfs_dir_item_key_to_cpu(path->nodes[0], di, &location); @@ -1171,8 +1170,7 @@ next: di = btrfs_lookup_dir_index_item(trans, root, path, btrfs_ino(dir), ref_index, name, namelen, 0); if (IS_ERR(di)) { - if (PTR_ERR(di) != -ENOENT) - return PTR_ERR(di); + return PTR_ERR(di); } else if (di) { ret = drop_one_dir_item(trans, root, path, dir, di); if (ret) @@ -2022,9 +2020,6 @@ static noinline int replay_one_name(struct btrfs_trans_handle *trans, goto out; } - if (dst_di == ERR_PTR(-ENOENT)) - dst_di = NULL; - if (IS_ERR(dst_di)) { ret = PTR_ERR(dst_di); goto out; @@ -2309,7 +2304,7 @@ again: dir_key->offset, name, name_len, 0); } - if (!log_di || log_di == ERR_PTR(-ENOENT)) { + if (!log_di) { btrfs_dir_item_key_to_cpu(eb, di, &location); btrfs_release_path(path); btrfs_release_path(log_path); @@ -3522,8 +3517,7 @@ out_unlock: if (err == -ENOSPC) { btrfs_set_log_full_commit(trans); err = 0; - } else if (err < 0 && err != -ENOENT) { - /* ENOENT can be returned if the entry hasn't been fsynced yet */ + } else if (err < 0) { btrfs_abort_transaction(trans, err); } diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c index 48858510739b2..cd7ddf24157a3 100644 --- a/fs/btrfs/xattr.c +++ b/fs/btrfs/xattr.c @@ -387,6 +387,9 @@ static int btrfs_xattr_handler_set(const struct xattr_handler *handler, const char *name, const void *buffer, size_t size, int flags) { + if (btrfs_root_readonly(BTRFS_I(inode)->root)) + return -EROFS; + name = xattr_full_name(handler, name); return btrfs_setxattr_trans(inode, name, buffer, size, flags); } diff --git a/fs/io_uring.c b/fs/io_uring.c index e73969fa96bcb..501c7e14c07cf 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -1908,6 +1908,9 @@ static int io_poll_add(struct io_kiocb *req, const struct io_uring_sqe *sqe) __poll_t mask; u16 events; + if (req->file->f_op->may_pollfree) + return -EOPNOTSUPP; + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; if (sqe->addr || sqe->ioprio || sqe->off || sqe->len || sqe->buf_index) diff --git a/fs/signalfd.c b/fs/signalfd.c index 3e94d181930fd..c3415d969ecfc 100644 --- a/fs/signalfd.c +++ b/fs/signalfd.c @@ -248,6 +248,7 @@ static const struct file_operations signalfd_fops = { .poll = signalfd_poll, .read = signalfd_read, .llseek = noop_llseek, + .may_pollfree = true, }; static int do_signalfd4(int ufd, sigset_t *mask, int flags) diff --git a/include/asm-generic/sections.h b/include/asm-generic/sections.h index 66397ed10acb7..69ab5942bd14f 100644 --- a/include/asm-generic/sections.h +++ b/include/asm-generic/sections.h @@ -114,7 +114,7 @@ static inline bool memory_contains(void *begin, void *end, void *virt, /** * memory_intersects - checks if the region occupied by an object intersects * with another memory region - * @begin: virtual address of the beginning of the memory regien + * @begin: virtual address of the beginning of the memory region * @end: virtual address of the end of the memory region * @virt: virtual address of the memory object * @size: size of the memory object @@ -127,7 +127,10 @@ static inline bool memory_intersects(void *begin, void *end, void *virt, { void *vend = virt + size; - return (virt >= begin && virt < end) || (vend >= begin && vend < end); + if (virt < end && vend > begin) + return true; + + return false; } /** diff --git a/include/linux/fs.h b/include/linux/fs.h index ef118b8ba6993..4ecbe12f62152 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1859,6 +1859,7 @@ struct file_operations { struct file *file_out, loff_t pos_out, loff_t len, unsigned int remap_flags); int (*fadvise)(struct file *, loff_t, loff_t, int); + bool may_pollfree; } __randomize_layout; struct inode_operations { diff --git a/include/linux/netfilter_bridge/ebtables.h b/include/linux/netfilter_bridge/ebtables.h index db472c9cd8e9d..f0d846df3a424 100644 --- a/include/linux/netfilter_bridge/ebtables.h +++ b/include/linux/netfilter_bridge/ebtables.h @@ -94,10 +94,6 @@ struct ebt_table { struct ebt_replace_kernel *table; unsigned int valid_hooks; rwlock_t lock; - /* e.g. could be the table explicitly only allows certain - * matches, targets, ... 0 == let it in */ - int (*check)(const struct ebt_table_info *info, - unsigned int valid_hooks); /* the data used by the kernel */ struct ebt_table_info *private; struct module *me; diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 91ccae9467164..c80bd129e9399 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -39,12 +39,15 @@ struct anon_vma { atomic_t refcount; /* - * Count of child anon_vmas and VMAs which points to this anon_vma. + * Count of child anon_vmas. Equals to the count of all anon_vmas that + * have ->parent pointing to this one, including itself. * * This counter is used for making decision about reusing anon_vma * instead of forking new one. See comments in function anon_vma_clone. */ - unsigned degree; + unsigned long num_children; + /* Count of VMAs whose ->anon_vma pointer points to this object. */ + unsigned long num_active_vmas; struct anon_vma *parent; /* Parent of this anon_vma */ diff --git a/include/linux/sched.h b/include/linux/sched.h index 171cb7475b450..d0e639497b107 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -526,10 +526,6 @@ struct sched_dl_entity { * task has to wait for a replenishment to be performed at the * next firing of dl_timer. * - * @dl_boosted tells if we are boosted due to DI. If so we are - * outside bandwidth enforcement mechanism (but only until we - * exit the critical section); - * * @dl_yielded tells if task gave up the CPU before consuming * all its available runtime during the last job. * @@ -544,7 +540,6 @@ struct sched_dl_entity { * overruns. */ unsigned int dl_throttled : 1; - unsigned int dl_boosted : 1; unsigned int dl_yielded : 1; unsigned int dl_non_contending : 1; unsigned int dl_overrun : 1; @@ -563,6 +558,15 @@ struct sched_dl_entity { * time. */ struct hrtimer inactive_timer; + +#ifdef CONFIG_RT_MUTEXES + /* + * Priority Inheritance. When a DEADLINE scheduling entity is boosted + * pi_se points to the donor, otherwise points to the dl_se it belongs + * to (the original one/itself). + */ + struct sched_dl_entity *pi_se; +#endif }; #ifdef CONFIG_UCLAMP_TASK diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index b04b5bd43f541..680f71ecdc08b 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2201,6 +2201,14 @@ static inline void skb_set_tail_pointer(struct sk_buff *skb, const int offset) #endif /* NET_SKBUFF_DATA_USES_OFFSET */ +static inline void skb_assert_len(struct sk_buff *skb) +{ +#ifdef CONFIG_DEBUG_NET + if (WARN_ONCE(!skb->len, "%s\n", __func__)) + DO_ONCE_LITE(skb_dump, KERN_ERR, skb, false); +#endif /* CONFIG_DEBUG_NET */ +} + /* * Add data to an sk_buff */ diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h index 9899b9af7f22f..16258c0c7319e 100644 --- a/include/net/busy_poll.h +++ b/include/net/busy_poll.h @@ -31,7 +31,7 @@ extern unsigned int sysctl_net_busy_poll __read_mostly; static inline bool net_busy_loop_on(void) { - return sysctl_net_busy_poll; + return READ_ONCE(sysctl_net_busy_poll); } static inline bool sk_can_busy_loop(const struct sock *sk) diff --git a/kernel/audit_fsnotify.c b/kernel/audit_fsnotify.c index f0d2433184521..2973878162962 100644 --- a/kernel/audit_fsnotify.c +++ b/kernel/audit_fsnotify.c @@ -102,6 +102,7 @@ struct audit_fsnotify_mark *audit_alloc_mark(struct audit_krule *krule, char *pa ret = fsnotify_add_inode_mark(&audit_mark->mark, inode, true); if (ret < 0) { + audit_mark->path = NULL; fsnotify_put_mark(&audit_mark->mark); audit_mark = ERR_PTR(ret); } diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 671b51782182b..9631ecc8a34c9 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -1737,11 +1737,12 @@ static struct kprobe *__disable_kprobe(struct kprobe *p) /* Try to disarm and disable this/parent probe */ if (p == orig_p || aggr_kprobe_disabled(orig_p)) { /* - * If kprobes_all_disarmed is set, orig_p - * should have already been disarmed, so - * skip unneed disarming process. + * Don't be lazy here. Even if 'kprobes_all_disarmed' + * is false, 'orig_p' might not have been armed yet. + * Note arm_all_kprobes() __tries__ to arm all kprobes + * on the best effort basis. */ - if (!kprobes_all_disarmed) { + if (!kprobes_all_disarmed && !kprobe_disabled(orig_p)) { ret = disarm_kprobe(orig_p, true); if (ret) { p->flags &= ~KPROBE_FLAG_DISABLED; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 5befdecefe947..06b686ef36e68 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -4554,20 +4554,21 @@ void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task) if (!dl_prio(p->normal_prio) || (pi_task && dl_prio(pi_task->prio) && dl_entity_preempt(&pi_task->dl, &p->dl))) { - p->dl.dl_boosted = 1; + p->dl.pi_se = pi_task->dl.pi_se; queue_flag |= ENQUEUE_REPLENISH; - } else - p->dl.dl_boosted = 0; + } else { + p->dl.pi_se = &p->dl; + } p->sched_class = &dl_sched_class; } else if (rt_prio(prio)) { if (dl_prio(oldprio)) - p->dl.dl_boosted = 0; + p->dl.pi_se = &p->dl; if (oldprio < prio) queue_flag |= ENQUEUE_HEAD; p->sched_class = &rt_sched_class; } else { if (dl_prio(oldprio)) - p->dl.dl_boosted = 0; + p->dl.pi_se = &p->dl; if (rt_prio(oldprio)) p->rt.timeout = 0; p->sched_class = &fair_sched_class; diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 2bda9fdba31c4..d8052c2d87e49 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -43,6 +43,28 @@ static inline int on_dl_rq(struct sched_dl_entity *dl_se) return !RB_EMPTY_NODE(&dl_se->rb_node); } +#ifdef CONFIG_RT_MUTEXES +static inline struct sched_dl_entity *pi_of(struct sched_dl_entity *dl_se) +{ + return dl_se->pi_se; +} + +static inline bool is_dl_boosted(struct sched_dl_entity *dl_se) +{ + return pi_of(dl_se) != dl_se; +} +#else +static inline struct sched_dl_entity *pi_of(struct sched_dl_entity *dl_se) +{ + return dl_se; +} + +static inline bool is_dl_boosted(struct sched_dl_entity *dl_se) +{ + return false; +} +#endif + #ifdef CONFIG_SMP static inline struct dl_bw *dl_bw_of(int i) { @@ -657,7 +679,7 @@ static inline void setup_new_dl_entity(struct sched_dl_entity *dl_se) struct dl_rq *dl_rq = dl_rq_of_se(dl_se); struct rq *rq = rq_of_dl_rq(dl_rq); - WARN_ON(dl_se->dl_boosted); + WARN_ON(is_dl_boosted(dl_se)); WARN_ON(dl_time_before(rq_clock(rq), dl_se->deadline)); /* @@ -695,21 +717,20 @@ static inline void setup_new_dl_entity(struct sched_dl_entity *dl_se) * could happen are, typically, a entity voluntarily trying to overcome its * runtime, or it just underestimated it during sched_setattr(). */ -static void replenish_dl_entity(struct sched_dl_entity *dl_se, - struct sched_dl_entity *pi_se) +static void replenish_dl_entity(struct sched_dl_entity *dl_se) { struct dl_rq *dl_rq = dl_rq_of_se(dl_se); struct rq *rq = rq_of_dl_rq(dl_rq); - BUG_ON(pi_se->dl_runtime <= 0); + BUG_ON(pi_of(dl_se)->dl_runtime <= 0); /* * This could be the case for a !-dl task that is boosted. * Just go with full inherited parameters. */ if (dl_se->dl_deadline == 0) { - dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline; - dl_se->runtime = pi_se->dl_runtime; + dl_se->deadline = rq_clock(rq) + pi_of(dl_se)->dl_deadline; + dl_se->runtime = pi_of(dl_se)->dl_runtime; } if (dl_se->dl_yielded && dl_se->runtime > 0) @@ -722,8 +743,8 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se, * arbitrary large. */ while (dl_se->runtime <= 0) { - dl_se->deadline += pi_se->dl_period; - dl_se->runtime += pi_se->dl_runtime; + dl_se->deadline += pi_of(dl_se)->dl_period; + dl_se->runtime += pi_of(dl_se)->dl_runtime; } /* @@ -737,8 +758,8 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se, */ if (dl_time_before(dl_se->deadline, rq_clock(rq))) { printk_deferred_once("sched: DL replenish lagged too much\n"); - dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline; - dl_se->runtime = pi_se->dl_runtime; + dl_se->deadline = rq_clock(rq) + pi_of(dl_se)->dl_deadline; + dl_se->runtime = pi_of(dl_se)->dl_runtime; } if (dl_se->dl_yielded) @@ -771,8 +792,7 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se, * task with deadline equal to period this is the same of using * dl_period instead of dl_deadline in the equation above. */ -static bool dl_entity_overflow(struct sched_dl_entity *dl_se, - struct sched_dl_entity *pi_se, u64 t) +static bool dl_entity_overflow(struct sched_dl_entity *dl_se, u64 t) { u64 left, right; @@ -794,9 +814,9 @@ static bool dl_entity_overflow(struct sched_dl_entity *dl_se, * of anything below microseconds resolution is actually fiction * (but still we want to give the user that illusion >;). */ - left = (pi_se->dl_deadline >> DL_SCALE) * (dl_se->runtime >> DL_SCALE); + left = (pi_of(dl_se)->dl_deadline >> DL_SCALE) * (dl_se->runtime >> DL_SCALE); right = ((dl_se->deadline - t) >> DL_SCALE) * - (pi_se->dl_runtime >> DL_SCALE); + (pi_of(dl_se)->dl_runtime >> DL_SCALE); return dl_time_before(right, left); } @@ -881,24 +901,23 @@ static inline bool dl_is_implicit(struct sched_dl_entity *dl_se) * Please refer to the comments update_dl_revised_wakeup() function to find * more about the Revised CBS rule. */ -static void update_dl_entity(struct sched_dl_entity *dl_se, - struct sched_dl_entity *pi_se) +static void update_dl_entity(struct sched_dl_entity *dl_se) { struct dl_rq *dl_rq = dl_rq_of_se(dl_se); struct rq *rq = rq_of_dl_rq(dl_rq); if (dl_time_before(dl_se->deadline, rq_clock(rq)) || - dl_entity_overflow(dl_se, pi_se, rq_clock(rq))) { + dl_entity_overflow(dl_se, rq_clock(rq))) { if (unlikely(!dl_is_implicit(dl_se) && !dl_time_before(dl_se->deadline, rq_clock(rq)) && - !dl_se->dl_boosted)){ + !is_dl_boosted(dl_se))) { update_dl_revised_wakeup(dl_se, rq); return; } - dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline; - dl_se->runtime = pi_se->dl_runtime; + dl_se->deadline = rq_clock(rq) + pi_of(dl_se)->dl_deadline; + dl_se->runtime = pi_of(dl_se)->dl_runtime; } } @@ -997,7 +1016,7 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer) * The task might have been boosted by someone else and might be in the * boosting/deboosting path, its not throttled. */ - if (dl_se->dl_boosted) + if (is_dl_boosted(dl_se)) goto unlock; /* @@ -1025,7 +1044,7 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer) * but do not enqueue -- wait for our wakeup to do that. */ if (!task_on_rq_queued(p)) { - replenish_dl_entity(dl_se, dl_se); + replenish_dl_entity(dl_se); goto unlock; } @@ -1115,7 +1134,7 @@ static inline void dl_check_constrained_dl(struct sched_dl_entity *dl_se) if (dl_time_before(dl_se->deadline, rq_clock(rq)) && dl_time_before(rq_clock(rq), dl_next_period(dl_se))) { - if (unlikely(dl_se->dl_boosted || !start_dl_timer(p))) + if (unlikely(is_dl_boosted(dl_se) || !start_dl_timer(p))) return; dl_se->dl_throttled = 1; if (dl_se->runtime > 0) @@ -1246,7 +1265,7 @@ throttle: dl_se->dl_overrun = 1; __dequeue_task_dl(rq, curr, 0); - if (unlikely(dl_se->dl_boosted || !start_dl_timer(curr))) + if (unlikely(is_dl_boosted(dl_se) || !start_dl_timer(curr))) enqueue_task_dl(rq, curr, ENQUEUE_REPLENISH); if (!is_leftmost(curr, &rq->dl)) @@ -1440,8 +1459,7 @@ static void __dequeue_dl_entity(struct sched_dl_entity *dl_se) } static void -enqueue_dl_entity(struct sched_dl_entity *dl_se, - struct sched_dl_entity *pi_se, int flags) +enqueue_dl_entity(struct sched_dl_entity *dl_se, int flags) { BUG_ON(on_dl_rq(dl_se)); @@ -1452,9 +1470,9 @@ enqueue_dl_entity(struct sched_dl_entity *dl_se, */ if (flags & ENQUEUE_WAKEUP) { task_contending(dl_se, flags); - update_dl_entity(dl_se, pi_se); + update_dl_entity(dl_se); } else if (flags & ENQUEUE_REPLENISH) { - replenish_dl_entity(dl_se, pi_se); + replenish_dl_entity(dl_se); } else if ((flags & ENQUEUE_RESTORE) && dl_time_before(dl_se->deadline, rq_clock(rq_of_dl_rq(dl_rq_of_se(dl_se))))) { @@ -1471,28 +1489,40 @@ static void dequeue_dl_entity(struct sched_dl_entity *dl_se) static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags) { - struct task_struct *pi_task = rt_mutex_get_top_task(p); - struct sched_dl_entity *pi_se = &p->dl; - - /* - * Use the scheduling parameters of the top pi-waiter task if: - * - we have a top pi-waiter which is a SCHED_DEADLINE task AND - * - our dl_boosted is set (i.e. the pi-waiter's (absolute) deadline is - * smaller than our deadline OR we are a !SCHED_DEADLINE task getting - * boosted due to a SCHED_DEADLINE pi-waiter). - * Otherwise we keep our runtime and deadline. - */ - if (pi_task && dl_prio(pi_task->normal_prio) && p->dl.dl_boosted) { - pi_se = &pi_task->dl; + if (is_dl_boosted(&p->dl)) { + /* + * Because of delays in the detection of the overrun of a + * thread's runtime, it might be the case that a thread + * goes to sleep in a rt mutex with negative runtime. As + * a consequence, the thread will be throttled. + * + * While waiting for the mutex, this thread can also be + * boosted via PI, resulting in a thread that is throttled + * and boosted at the same time. + * + * In this case, the boost overrides the throttle. + */ + if (p->dl.dl_throttled) { + /* + * The replenish timer needs to be canceled. No + * problem if it fires concurrently: boosted threads + * are ignored in dl_task_timer(). + */ + hrtimer_try_to_cancel(&p->dl.dl_timer); + p->dl.dl_throttled = 0; + } } else if (!dl_prio(p->normal_prio)) { /* - * Special case in which we have a !SCHED_DEADLINE task - * that is going to be deboosted, but exceeds its - * runtime while doing so. No point in replenishing - * it, as it's going to return back to its original - * scheduling class after this. + * Special case in which we have a !SCHED_DEADLINE task that is going + * to be deboosted, but exceeds its runtime while doing so. No point in + * replenishing it, as it's going to return back to its original + * scheduling class after this. If it has been throttled, we need to + * clear the flag, otherwise the task may wake up as throttled after + * being boosted again with no means to replenish the runtime and clear + * the throttle. */ - BUG_ON(!p->dl.dl_boosted || flags != ENQUEUE_REPLENISH); + p->dl.dl_throttled = 0; + BUG_ON(!is_dl_boosted(&p->dl) || flags != ENQUEUE_REPLENISH); return; } @@ -1529,7 +1559,7 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags) return; } - enqueue_dl_entity(&p->dl, pi_se, flags); + enqueue_dl_entity(&p->dl, flags); if (!task_current(rq, p) && p->nr_cpus_allowed > 1) enqueue_pushable_dl_task(rq, p); @@ -2698,11 +2728,14 @@ void __dl_clear_params(struct task_struct *p) dl_se->dl_bw = 0; dl_se->dl_density = 0; - dl_se->dl_boosted = 0; dl_se->dl_throttled = 0; dl_se->dl_yielded = 0; dl_se->dl_non_contending = 0; dl_se->dl_overrun = 0; + +#ifdef CONFIG_RT_MUTEXES + dl_se->pi_se = dl_se; +#endif } bool dl_param_changed(struct task_struct *p, const struct sched_attr *attr) diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index 34b76895b81e8..189eed03e4e34 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -268,6 +268,7 @@ COND_SYSCALL_COMPAT(keyctl); /* mm/fadvise.c */ COND_SYSCALL(fadvise64_64); +COND_SYSCALL_COMPAT(fadvise64_64); /* mm/, CONFIG_MMU only */ COND_SYSCALL(swapon); diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 7719d444bda12..44f1469af842b 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -2732,6 +2732,16 @@ int ftrace_startup(struct ftrace_ops *ops, int command) ftrace_startup_enable(command); + /* + * If ftrace is in an undefined state, we just remove ops from list + * to prevent the NULL pointer, instead of totally rolling it back and + * free trampoline, because those actions could cause further damage. + */ + if (unlikely(ftrace_disabled)) { + __unregister_ftrace_function(ops); + return -ENODEV; + } + ops->flags &= ~FTRACE_OPS_FL_ADDING; return 0; diff --git a/lib/ratelimit.c b/lib/ratelimit.c index e01a93f46f833..ce945c17980b9 100644 --- a/lib/ratelimit.c +++ b/lib/ratelimit.c @@ -26,10 +26,16 @@ */ int ___ratelimit(struct ratelimit_state *rs, const char *func) { + /* Paired with WRITE_ONCE() in .proc_handler(). + * Changing two values seperately could be inconsistent + * and some message could be lost. (See: net_ratelimit_state). + */ + int interval = READ_ONCE(rs->interval); + int burst = READ_ONCE(rs->burst); unsigned long flags; int ret; - if (!rs->interval) + if (!interval) return 1; /* @@ -44,7 +50,7 @@ int ___ratelimit(struct ratelimit_state *rs, const char *func) if (!rs->begin) rs->begin = jiffies; - if (time_is_before_jiffies(rs->begin + rs->interval)) { + if (time_is_before_jiffies(rs->begin + interval)) { if (rs->missed) { if (!(rs->flags & RATELIMIT_MSG_ON_RELEASE)) { printk_deferred(KERN_WARNING @@ -56,7 +62,7 @@ int ___ratelimit(struct ratelimit_state *rs, const char *func) rs->begin = jiffies; rs->printed = 0; } - if (rs->burst && rs->burst > rs->printed) { + if (burst && burst > rs->printed) { rs->printed++; ret = 1; } else { diff --git a/lib/vdso/gettimeofday.c b/lib/vdso/gettimeofday.c index 45f57fd2db649..5667fb746a1fe 100644 --- a/lib/vdso/gettimeofday.c +++ b/lib/vdso/gettimeofday.c @@ -38,7 +38,7 @@ u64 vdso_calc_delta(u64 cycles, u64 last, u64 mask, u32 mult) } #endif -static int do_hres(const struct vdso_data *vd, clockid_t clk, +static __always_inline int do_hres(const struct vdso_data *vd, clockid_t clk, struct __kernel_timespec *ts) { const struct vdso_timestamp *vdso_ts = &vd->basetime[clk]; @@ -68,8 +68,8 @@ static int do_hres(const struct vdso_data *vd, clockid_t clk, return 0; } -static void do_coarse(const struct vdso_data *vd, clockid_t clk, - struct __kernel_timespec *ts) +static __always_inline int do_coarse(const struct vdso_data *vd, clockid_t clk, + struct __kernel_timespec *ts) { const struct vdso_timestamp *vdso_ts = &vd->basetime[clk]; u32 seq; @@ -79,6 +79,8 @@ static void do_coarse(const struct vdso_data *vd, clockid_t clk, ts->tv_sec = vdso_ts->sec; ts->tv_nsec = vdso_ts->nsec; } while (unlikely(vdso_read_retry(vd, seq))); + + return 0; } static __maybe_unused int @@ -96,15 +98,16 @@ __cvdso_clock_gettime_common(clockid_t clock, struct __kernel_timespec *ts) * clocks are handled in the VDSO directly. */ msk = 1U << clock; - if (likely(msk & VDSO_HRES)) { - return do_hres(&vd[CS_HRES_COARSE], clock, ts); - } else if (msk & VDSO_COARSE) { - do_coarse(&vd[CS_HRES_COARSE], clock, ts); - return 0; - } else if (msk & VDSO_RAW) { - return do_hres(&vd[CS_RAW], clock, ts); - } - return -1; + if (likely(msk & VDSO_HRES)) + vd = &vd[CS_HRES_COARSE]; + else if (msk & VDSO_COARSE) + return do_coarse(&vd[CS_HRES_COARSE], clock, ts); + else if (msk & VDSO_RAW) + vd = &vd[CS_RAW]; + else + return -1; + + return do_hres(vd, clock, ts); } static __maybe_unused int diff --git a/mm/mmap.c b/mm/mmap.c index 8873ef114d280..e8cf6f88933c3 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1679,8 +1679,12 @@ int vma_wants_writenotify(struct vm_area_struct *vma, pgprot_t vm_page_prot) pgprot_val(vm_pgprot_modify(vm_page_prot, vm_flags))) return 0; - /* Do we need to track softdirty? */ - if (IS_ENABLED(CONFIG_MEM_SOFT_DIRTY) && !(vm_flags & VM_SOFTDIRTY)) + /* + * Do we need to track softdirty? hugetlb does not support softdirty + * tracking yet. + */ + if (IS_ENABLED(CONFIG_MEM_SOFT_DIRTY) && !(vm_flags & VM_SOFTDIRTY) && + !is_vm_hugetlb_page(vma)) return 1; /* Specialty mapping? */ @@ -2606,6 +2610,18 @@ static void unmap_region(struct mm_struct *mm, tlb_gather_mmu(&tlb, mm, start, end); update_hiwater_rss(mm); unmap_vmas(&tlb, vma, start, end); + + /* + * Ensure we have no stale TLB entries by the time this mapping is + * removed from the rmap. + * Note that we don't have to worry about nested flushes here because + * we're holding the mm semaphore for removing the mapping - so any + * concurrent flush in this region has to be coming through the rmap, + * and we synchronize against that using the rmap lock. + */ + if ((vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) != 0) + tlb_flush_mmu(&tlb); + free_pgtables(&tlb, vma, prev ? prev->vm_end : FIRST_USER_ADDRESS, next ? next->vm_start : USER_PGTABLES_CEILING); tlb_finish_mmu(&tlb, start, end); diff --git a/mm/rmap.c b/mm/rmap.c index 6d80e92688fe7..c64da910bb731 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -83,7 +83,8 @@ static inline struct anon_vma *anon_vma_alloc(void) anon_vma = kmem_cache_alloc(anon_vma_cachep, GFP_KERNEL); if (anon_vma) { atomic_set(&anon_vma->refcount, 1); - anon_vma->degree = 1; /* Reference for first vma */ + anon_vma->num_children = 0; + anon_vma->num_active_vmas = 0; anon_vma->parent = anon_vma; /* * Initialise the anon_vma root to point to itself. If called @@ -191,6 +192,7 @@ int __anon_vma_prepare(struct vm_area_struct *vma) anon_vma = anon_vma_alloc(); if (unlikely(!anon_vma)) goto out_enomem_free_avc; + anon_vma->num_children++; /* self-parent link for new root */ allocated = anon_vma; } @@ -200,8 +202,7 @@ int __anon_vma_prepare(struct vm_area_struct *vma) if (likely(!vma->anon_vma)) { vma->anon_vma = anon_vma; anon_vma_chain_link(vma, avc, anon_vma); - /* vma reference or self-parent link for new root */ - anon_vma->degree++; + anon_vma->num_active_vmas++; allocated = NULL; avc = NULL; } @@ -280,19 +281,19 @@ int anon_vma_clone(struct vm_area_struct *dst, struct vm_area_struct *src) anon_vma_chain_link(dst, avc, anon_vma); /* - * Reuse existing anon_vma if its degree lower than two, - * that means it has no vma and only one anon_vma child. + * Reuse existing anon_vma if it has no vma and only one + * anon_vma child. * - * Do not chose parent anon_vma, otherwise first child - * will always reuse it. Root anon_vma is never reused: + * Root anon_vma is never reused: * it has self-parent reference and at least one child. */ - if (!dst->anon_vma && anon_vma != src->anon_vma && - anon_vma->degree < 2) + if (!dst->anon_vma && + anon_vma->num_children < 2 && + anon_vma->num_active_vmas == 0) dst->anon_vma = anon_vma; } if (dst->anon_vma) - dst->anon_vma->degree++; + dst->anon_vma->num_active_vmas++; unlock_anon_vma_root(root); return 0; @@ -342,6 +343,7 @@ int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma) anon_vma = anon_vma_alloc(); if (!anon_vma) goto out_error; + anon_vma->num_active_vmas++; avc = anon_vma_chain_alloc(GFP_KERNEL); if (!avc) goto out_error_free_anon_vma; @@ -362,7 +364,7 @@ int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma) vma->anon_vma = anon_vma; anon_vma_lock_write(anon_vma); anon_vma_chain_link(vma, avc, anon_vma); - anon_vma->parent->degree++; + anon_vma->parent->num_children++; anon_vma_unlock_write(anon_vma); return 0; @@ -394,7 +396,7 @@ void unlink_anon_vmas(struct vm_area_struct *vma) * to free them outside the lock. */ if (RB_EMPTY_ROOT(&anon_vma->rb_root.rb_root)) { - anon_vma->parent->degree--; + anon_vma->parent->num_children--; continue; } @@ -402,7 +404,7 @@ void unlink_anon_vmas(struct vm_area_struct *vma) anon_vma_chain_free(avc); } if (vma->anon_vma) - vma->anon_vma->degree--; + vma->anon_vma->num_active_vmas--; unlock_anon_vma_root(root); /* @@ -413,7 +415,8 @@ void unlink_anon_vmas(struct vm_area_struct *vma) list_for_each_entry_safe(avc, next, &vma->anon_vma_chain, same_vma) { struct anon_vma *anon_vma = avc->anon_vma; - VM_WARN_ON(anon_vma->degree); + VM_WARN_ON(anon_vma->num_children); + VM_WARN_ON(anon_vma->num_active_vmas); put_anon_vma(anon_vma); list_del(&avc->same_vma); diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 7aa64f300422e..3682d2e1cd7d2 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -1835,11 +1835,11 @@ static struct l2cap_chan *l2cap_global_chan_by_psm(int state, __le16 psm, src_match = !bacmp(&c->src, src); dst_match = !bacmp(&c->dst, dst); if (src_match && dst_match) { - c = l2cap_chan_hold_unless_zero(c); - if (c) { - read_unlock(&chan_list_lock); - return c; - } + if (!l2cap_chan_hold_unless_zero(c)) + continue; + + read_unlock(&chan_list_lock); + return c; } /* Closest match */ diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index 1153bbcdff721..5e6428cbd7580 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -200,6 +200,9 @@ static int convert___skb_to_skb(struct sk_buff *skb, struct __sk_buff *__skb) { struct qdisc_skb_cb *cb = (struct qdisc_skb_cb *)skb->cb; + if (!skb->len) + return -EINVAL; + if (!__skb) return 0; diff --git a/net/bridge/netfilter/ebtable_broute.c b/net/bridge/netfilter/ebtable_broute.c index 32bc2821027f3..57f91efce0f73 100644 --- a/net/bridge/netfilter/ebtable_broute.c +++ b/net/bridge/netfilter/ebtable_broute.c @@ -36,18 +36,10 @@ static struct ebt_replace_kernel initial_table = { .entries = (char *)&initial_chain, }; -static int check(const struct ebt_table_info *info, unsigned int valid_hooks) -{ - if (valid_hooks & ~(1 << NF_BR_BROUTING)) - return -EINVAL; - return 0; -} - static const struct ebt_table broute_table = { .name = "broute", .table = &initial_table, .valid_hooks = 1 << NF_BR_BROUTING, - .check = check, .me = THIS_MODULE, }; diff --git a/net/bridge/netfilter/ebtable_filter.c b/net/bridge/netfilter/ebtable_filter.c index bcf982e12f16b..7f2e620f4978f 100644 --- a/net/bridge/netfilter/ebtable_filter.c +++ b/net/bridge/netfilter/ebtable_filter.c @@ -43,18 +43,10 @@ static struct ebt_replace_kernel initial_table = { .entries = (char *)initial_chains, }; -static int check(const struct ebt_table_info *info, unsigned int valid_hooks) -{ - if (valid_hooks & ~FILTER_VALID_HOOKS) - return -EINVAL; - return 0; -} - static const struct ebt_table frame_filter = { .name = "filter", .table = &initial_table, .valid_hooks = FILTER_VALID_HOOKS, - .check = check, .me = THIS_MODULE, }; diff --git a/net/bridge/netfilter/ebtable_nat.c b/net/bridge/netfilter/ebtable_nat.c index 0d092773f8161..1743a105485c4 100644 --- a/net/bridge/netfilter/ebtable_nat.c +++ b/net/bridge/netfilter/ebtable_nat.c @@ -43,18 +43,10 @@ static struct ebt_replace_kernel initial_table = { .entries = (char *)initial_chains, }; -static int check(const struct ebt_table_info *info, unsigned int valid_hooks) -{ - if (valid_hooks & ~NAT_VALID_HOOKS) - return -EINVAL; - return 0; -} - static const struct ebt_table frame_nat = { .name = "nat", .table = &initial_table, .valid_hooks = NAT_VALID_HOOKS, - .check = check, .me = THIS_MODULE, }; diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index d9375c52f50e6..ddb988c339c17 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -999,8 +999,7 @@ static int do_replace_finish(struct net *net, struct ebt_replace *repl, goto free_iterate; } - /* the table doesn't like it */ - if (t->check && (ret = t->check(newinfo, repl->valid_hooks))) + if (repl->valid_hooks != t->valid_hooks) goto free_unlock; if (repl->num_counters && repl->num_counters != t->private->nentries) { @@ -1193,11 +1192,6 @@ int ebt_register_table(struct net *net, const struct ebt_table *input_table, if (ret != 0) goto free_chainstack; - if (table->check && table->check(newinfo, table->valid_hooks)) { - ret = -EINVAL; - goto free_chainstack; - } - table->private = newinfo; rwlock_init(&table->lock); mutex_lock(&ebt_mutex); diff --git a/net/core/dev.c b/net/core/dev.c index a03036456221b..84bc6d0e8560b 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3712,6 +3712,7 @@ static int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev) bool again = false; skb_reset_mac_header(skb); + skb_assert_len(skb); if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_SCHED_TSTAMP)) __skb_tstamp_tx(skb, NULL, skb->sk, SCM_TSTAMP_SCHED); @@ -4411,7 +4412,7 @@ static int netif_rx_internal(struct sk_buff *skb) { int ret; - net_timestamp_check(netdev_tstamp_prequeue, skb); + net_timestamp_check(READ_ONCE(netdev_tstamp_prequeue), skb); trace_netif_rx(skb); @@ -4753,7 +4754,7 @@ static int __netif_receive_skb_core(struct sk_buff **pskb, bool pfmemalloc, int ret = NET_RX_DROP; __be16 type; - net_timestamp_check(!netdev_tstamp_prequeue, skb); + net_timestamp_check(!READ_ONCE(netdev_tstamp_prequeue), skb); trace_netif_receive_skb(skb); @@ -5135,7 +5136,7 @@ static int netif_receive_skb_internal(struct sk_buff *skb) { int ret; - net_timestamp_check(netdev_tstamp_prequeue, skb); + net_timestamp_check(READ_ONCE(netdev_tstamp_prequeue), skb); if (skb_defer_rx_timestamp(skb)) return NET_RX_SUCCESS; @@ -5165,7 +5166,7 @@ static void netif_receive_skb_list_internal(struct list_head *head) INIT_LIST_HEAD(&sublist); list_for_each_entry_safe(skb, next, head, list) { - net_timestamp_check(netdev_tstamp_prequeue, skb); + net_timestamp_check(READ_ONCE(netdev_tstamp_prequeue), skb); skb_list_del_init(skb); if (!skb_defer_rx_timestamp(skb)) list_add_tail(&skb->list, &sublist); @@ -5892,7 +5893,7 @@ static int process_backlog(struct napi_struct *napi, int quota) net_rps_action_and_irq_enable(sd); } - napi->weight = dev_rx_weight; + napi->weight = READ_ONCE(dev_rx_weight); while (again) { struct sk_buff *skb; @@ -6393,8 +6394,8 @@ static __latent_entropy void net_rx_action(struct softirq_action *h) { struct softnet_data *sd = this_cpu_ptr(&softnet_data); unsigned long time_limit = jiffies + - usecs_to_jiffies(netdev_budget_usecs); - int budget = netdev_budget; + usecs_to_jiffies(READ_ONCE(netdev_budget_usecs)); + int budget = READ_ONCE(netdev_budget); LIST_HEAD(list); LIST_HEAD(repoll); diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 8b6140e67e7f8..aa81aead0a654 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -280,11 +280,26 @@ static int neigh_del_timer(struct neighbour *n) return 0; } -static void pneigh_queue_purge(struct sk_buff_head *list) +static void pneigh_queue_purge(struct sk_buff_head *list, struct net *net) { + struct sk_buff_head tmp; + unsigned long flags; struct sk_buff *skb; - while ((skb = skb_dequeue(list)) != NULL) { + skb_queue_head_init(&tmp); + spin_lock_irqsave(&list->lock, flags); + skb = skb_peek(list); + while (skb != NULL) { + struct sk_buff *skb_next = skb_peek_next(skb, list); + if (net == NULL || net_eq(dev_net(skb->dev), net)) { + __skb_unlink(skb, list); + __skb_queue_tail(&tmp, skb); + } + skb = skb_next; + } + spin_unlock_irqrestore(&list->lock, flags); + + while ((skb = __skb_dequeue(&tmp))) { dev_put(skb->dev); kfree_skb(skb); } @@ -358,9 +373,9 @@ static int __neigh_ifdown(struct neigh_table *tbl, struct net_device *dev, write_lock_bh(&tbl->lock); neigh_flush_dev(tbl, dev, skip_perm); pneigh_ifdown_and_unlock(tbl, dev); - - del_timer_sync(&tbl->proxy_timer); - pneigh_queue_purge(&tbl->proxy_queue); + pneigh_queue_purge(&tbl->proxy_queue, dev_net(dev)); + if (skb_queue_empty_lockless(&tbl->proxy_queue)) + del_timer_sync(&tbl->proxy_timer); return 0; } @@ -1741,7 +1756,7 @@ int neigh_table_clear(int index, struct neigh_table *tbl) /* It is not clean... Fix it to unload IPv6 module safely */ cancel_delayed_work_sync(&tbl->gc_work); del_timer_sync(&tbl->proxy_timer); - pneigh_queue_purge(&tbl->proxy_queue); + pneigh_queue_purge(&tbl->proxy_queue, NULL); neigh_ifdown(tbl, NULL); if (atomic_read(&tbl->entries)) pr_crit("neighbour leakage\n"); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 5bdb3cd20d619..c9fe2c0b8cae3 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -4564,7 +4564,7 @@ static bool skb_may_tx_timestamp(struct sock *sk, bool tsonly) { bool ret; - if (likely(sysctl_tstamp_allow_data || tsonly)) + if (likely(READ_ONCE(sysctl_tstamp_allow_data) || tsonly)) return true; read_lock_bh(&sk->sk_callback_lock); diff --git a/net/core/sock.c b/net/core/sock.c index c84f68bff7f58..a2b12a5cf42bc 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2946,7 +2946,7 @@ void sock_init_data(struct socket *sock, struct sock *sk) #ifdef CONFIG_NET_RX_BUSY_POLL sk->sk_napi_id = 0; - sk->sk_ll_usec = sysctl_net_busy_read; + sk->sk_ll_usec = READ_ONCE(sysctl_net_busy_read); #endif sk->sk_max_pacing_rate = ~0UL; diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 48041f50ecfb4..586598887095d 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -238,14 +238,17 @@ static int set_default_qdisc(struct ctl_table *table, int write, static int proc_do_dev_weight(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { - int ret; + static DEFINE_MUTEX(dev_weight_mutex); + int ret, weight; + mutex_lock(&dev_weight_mutex); ret = proc_dointvec(table, write, buffer, lenp, ppos); - if (ret != 0) - return ret; - - dev_rx_weight = weight_p * dev_weight_rx_bias; - dev_tx_weight = weight_p * dev_weight_tx_bias; + if (!ret && write) { + weight = READ_ONCE(weight_p); + WRITE_ONCE(dev_rx_weight, weight * dev_weight_rx_bias); + WRITE_ONCE(dev_tx_weight, weight * dev_weight_tx_bias); + } + mutex_unlock(&dev_weight_mutex); return ret; } diff --git a/net/key/af_key.c b/net/key/af_key.c index 32fe99cd01fc8..c06cc48c68c90 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -1701,9 +1701,12 @@ static int pfkey_register(struct sock *sk, struct sk_buff *skb, const struct sad pfk->registered |= (1<sadb_msg_satype); } + mutex_lock(&pfkey_mutex); xfrm_probe_algs(); supp_skb = compose_sadb_supported(hdr, GFP_KERNEL | __GFP_ZERO); + mutex_unlock(&pfkey_mutex); + if (!supp_skb) { if (hdr->sadb_msg_satype != SADB_SATYPE_UNSPEC) pfk->registered &= ~(1<sadb_msg_satype); diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index ef72819d9d315..d569915da003c 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -118,7 +118,6 @@ config NF_CONNTRACK_ZONES config NF_CONNTRACK_PROCFS bool "Supply CT list in procfs (OBSOLETE)" - default y depends on PROC_FS ---help--- This option enables for the list of known conntrack entries diff --git a/net/netfilter/nft_osf.c b/net/netfilter/nft_osf.c index 4911f8eb394ff..d966a3aff1d33 100644 --- a/net/netfilter/nft_osf.c +++ b/net/netfilter/nft_osf.c @@ -115,9 +115,21 @@ static int nft_osf_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_LOCAL_IN) | - (1 << NF_INET_PRE_ROUTING) | - (1 << NF_INET_FORWARD)); + unsigned int hooks; + + switch (ctx->family) { + case NFPROTO_IPV4: + case NFPROTO_IPV6: + case NFPROTO_INET: + hooks = (1 << NF_INET_LOCAL_IN) | + (1 << NF_INET_PRE_ROUTING) | + (1 << NF_INET_FORWARD); + break; + default: + return -EOPNOTSUPP; + } + + return nft_chain_validate_hooks(ctx->chain, hooks); } static struct nft_expr_type nft_osf_type; diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c index cf0512fc648e7..6ed6ccef5e1ad 100644 --- a/net/netfilter/nft_payload.c +++ b/net/netfilter/nft_payload.c @@ -558,6 +558,8 @@ static int nft_payload_set_init(const struct nft_ctx *ctx, const struct nlattr * const tb[]) { struct nft_payload_set *priv = nft_expr_priv(expr); + u32 csum_offset, csum_type = NFT_PAYLOAD_CSUM_NONE; + int err; priv->base = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_BASE])); priv->offset = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_OFFSET])); @@ -565,11 +567,15 @@ static int nft_payload_set_init(const struct nft_ctx *ctx, priv->sreg = nft_parse_register(tb[NFTA_PAYLOAD_SREG]); if (tb[NFTA_PAYLOAD_CSUM_TYPE]) - priv->csum_type = - ntohl(nla_get_be32(tb[NFTA_PAYLOAD_CSUM_TYPE])); - if (tb[NFTA_PAYLOAD_CSUM_OFFSET]) - priv->csum_offset = - ntohl(nla_get_be32(tb[NFTA_PAYLOAD_CSUM_OFFSET])); + csum_type = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_CSUM_TYPE])); + if (tb[NFTA_PAYLOAD_CSUM_OFFSET]) { + err = nft_parse_u32_check(tb[NFTA_PAYLOAD_CSUM_OFFSET], U8_MAX, + &csum_offset); + if (err < 0) + return err; + + priv->csum_offset = csum_offset; + } if (tb[NFTA_PAYLOAD_CSUM_FLAGS]) { u32 flags; @@ -580,13 +586,14 @@ static int nft_payload_set_init(const struct nft_ctx *ctx, priv->csum_flags = flags; } - switch (priv->csum_type) { + switch (csum_type) { case NFT_PAYLOAD_CSUM_NONE: case NFT_PAYLOAD_CSUM_INET: break; default: return -EOPNOTSUPP; } + priv->csum_type = csum_type; return nft_validate_register_load(priv->sreg, priv->len); } @@ -624,6 +631,7 @@ nft_payload_select_ops(const struct nft_ctx *ctx, { enum nft_payload_bases base; unsigned int offset, len; + int err; if (tb[NFTA_PAYLOAD_BASE] == NULL || tb[NFTA_PAYLOAD_OFFSET] == NULL || @@ -649,8 +657,13 @@ nft_payload_select_ops(const struct nft_ctx *ctx, if (tb[NFTA_PAYLOAD_DREG] == NULL) return ERR_PTR(-EINVAL); - offset = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_OFFSET])); - len = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_LEN])); + err = nft_parse_u32_check(tb[NFTA_PAYLOAD_OFFSET], U8_MAX, &offset); + if (err < 0) + return ERR_PTR(err); + + err = nft_parse_u32_check(tb[NFTA_PAYLOAD_LEN], U8_MAX, &len); + if (err < 0) + return ERR_PTR(err); if (len <= 4 && is_power_of_2(len) && IS_ALIGNED(offset, len) && base != NFT_PAYLOAD_LL_HEADER) diff --git a/net/netfilter/nft_tunnel.c b/net/netfilter/nft_tunnel.c index 1effd4878619f..4e850c81ad8d8 100644 --- a/net/netfilter/nft_tunnel.c +++ b/net/netfilter/nft_tunnel.c @@ -134,6 +134,7 @@ static const struct nft_expr_ops nft_tunnel_get_ops = { static struct nft_expr_type nft_tunnel_type __read_mostly = { .name = "tunnel", + .family = NFPROTO_NETDEV, .ops = &nft_tunnel_get_ops, .policy = nft_tunnel_policy, .maxattr = NFTA_TUNNEL_MAX, diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index a2696acbcd9d2..8f5ef28411992 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2960,8 +2960,8 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) if (err) goto out_free; - if (sock->type == SOCK_RAW && - !dev_validate_header(dev, skb->data, len)) { + if ((sock->type == SOCK_RAW && + !dev_validate_header(dev, skb->data, len)) || !skb->len) { err = -EINVAL; goto out_free; } diff --git a/net/rose/rose_loopback.c b/net/rose/rose_loopback.c index 11c45c8c6c164..036d92c0ad794 100644 --- a/net/rose/rose_loopback.c +++ b/net/rose/rose_loopback.c @@ -96,7 +96,8 @@ static void rose_loopback_timer(struct timer_list *unused) } if (frametype == ROSE_CALL_REQUEST) { - if (!rose_loopback_neigh->dev) { + if (!rose_loopback_neigh->dev && + !rose_loopback_neigh->loopback) { kfree_skb(skb); continue; } diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index ae5847de94c88..81fcf6c5bde96 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -403,7 +403,7 @@ static inline bool qdisc_restart(struct Qdisc *q, int *packets) void __qdisc_run(struct Qdisc *q) { - int quota = dev_tx_weight; + int quota = READ_ONCE(dev_tx_weight); int packets; while (qdisc_restart(q, &packets)) { diff --git a/net/socket.c b/net/socket.c index 94358566c9d10..02feaf5bd84a3 100644 --- a/net/socket.c +++ b/net/socket.c @@ -1661,7 +1661,7 @@ int __sys_listen(int fd, int backlog) sock = sockfd_lookup_light(fd, &err, &fput_needed); if (sock) { - somaxconn = sock_net(sock->sk)->core.sysctl_somaxconn; + somaxconn = READ_ONCE(sock_net(sock->sk)->core.sysctl_somaxconn); if ((unsigned int)backlog > somaxconn) backlog = somaxconn; diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 08e1ccc01e983..1893203cc94fc 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -1896,7 +1896,7 @@ call_encode(struct rpc_task *task) break; case -EKEYEXPIRED: if (!task->tk_cred_retry) { - rpc_exit(task, task->tk_status); + rpc_call_rpcerror(task, task->tk_status); } else { task->tk_action = call_refresh; task->tk_cred_retry--; diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 28a8cdef8e51f..6f58be5a17711 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -3619,6 +3619,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, if (pols[1]) { if (IS_ERR(pols[1])) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLERROR); + xfrm_pol_put(pols[0]); return 0; } pols[1]->curlft.use_time = ktime_get_real_seconds(); diff --git a/scripts/Makefile.modpost b/scripts/Makefile.modpost index 952fff4855467..2dde6e5e9e69f 100644 --- a/scripts/Makefile.modpost +++ b/scripts/Makefile.modpost @@ -75,8 +75,7 @@ obj := $(KBUILD_EXTMOD) src := $(obj) # Include the module's Makefile to find KBUILD_EXTRA_SYMBOLS -include $(if $(wildcard $(KBUILD_EXTMOD)/Kbuild), \ - $(KBUILD_EXTMOD)/Kbuild, $(KBUILD_EXTMOD)/Makefile) +include $(if $(wildcard $(src)/Kbuild), $(src)/Kbuild, $(src)/Makefile) endif MODPOST += $(subst -i,-n,$(filter -i,$(MAKEFLAGS))) -s -T - $(wildcard vmlinux) diff --git a/tools/testing/selftests/bpf/test_align.c b/tools/testing/selftests/bpf/test_align.c index 4b9a26caa2c2e..6cc29b58d6707 100644 --- a/tools/testing/selftests/bpf/test_align.c +++ b/tools/testing/selftests/bpf/test_align.c @@ -475,10 +475,10 @@ static struct bpf_align_test tests[] = { */ {7, "R5_w=inv(id=0,smin_value=-9223372036854775806,smax_value=9223372036854775806,umin_value=2,umax_value=18446744073709551614,var_off=(0x2; 0xfffffffffffffffc)"}, /* Checked s>=0 */ - {9, "R5=inv(id=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc)"}, + {9, "R5=inv(id=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc))"}, /* packet pointer + nonnegative (4n+2) */ - {11, "R6_w=pkt(id=1,off=0,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc)"}, - {13, "R4_w=pkt(id=1,off=4,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc)"}, + {11, "R6_w=pkt(id=1,off=0,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc))"}, + {13, "R4_w=pkt(id=1,off=4,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc))"}, /* NET_IP_ALIGN + (4n+2) == (4n), alignment is fine. * We checked the bounds, but it might have been able * to overflow if the packet pointer started in the @@ -486,7 +486,7 @@ static struct bpf_align_test tests[] = { * So we did not get a 'range' on R6, and the access * attempt will fail. */ - {15, "R6_w=pkt(id=1,off=0,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc)"}, + {15, "R6_w=pkt(id=1,off=0,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc))"}, } }, { @@ -580,18 +580,18 @@ static struct bpf_align_test tests[] = { /* Adding 14 makes R6 be (4n+2) */ {11, "R6_w=inv(id=0,umin_value=14,umax_value=74,var_off=(0x2; 0x7c))"}, /* Subtracting from packet pointer overflows ubounds */ - {13, "R5_w=pkt(id=1,off=0,r=8,umin_value=18446744073709551542,umax_value=18446744073709551602,var_off=(0xffffffffffffff82; 0x7c)"}, + {13, "R5_w=pkt(id=1,off=0,r=8,umin_value=18446744073709551542,umax_value=18446744073709551602,var_off=(0xffffffffffffff82; 0x7c))"}, /* New unknown value in R7 is (4n), >= 76 */ {15, "R7_w=inv(id=0,umin_value=76,umax_value=1096,var_off=(0x0; 0x7fc))"}, /* Adding it to packet pointer gives nice bounds again */ - {16, "R5_w=pkt(id=2,off=0,r=0,umin_value=2,umax_value=1082,var_off=(0x2; 0xfffffffc)"}, + {16, "R5_w=pkt(id=2,off=0,r=0,umin_value=2,umax_value=1082,var_off=(0x2; 0x7fc))"}, /* At the time the word size load is performed from R5, * its total fixed offset is NET_IP_ALIGN + reg->off (0) * which is 2. Then the variable offset is (4n+2), so * the total offset is 4-byte aligned and meets the * load's requirements. */ - {20, "R5=pkt(id=2,off=0,r=4,umin_value=2,umax_value=1082,var_off=(0x2; 0xfffffffc)"}, + {20, "R5=pkt(id=2,off=0,r=4,umin_value=2,umax_value=1082,var_off=(0x2; 0x7fc))"}, }, }, };