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 ac79aef4520be..18ccab9a01b06 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 4 PATCHLEVEL = 19 -SUBLEVEL = 256 +SUBLEVEL = 257 EXTRAVERSION = NAME = "People's Front" diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h index b37d185e0e841..3dda6ff32efd7 100644 --- a/arch/arm64/include/asm/mmu.h +++ b/arch/arm64/include/asm/mmu.h @@ -98,7 +98,7 @@ extern void init_mem_pgprot(void); extern void create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys, unsigned long virt, phys_addr_t size, pgprot_t prot, bool page_mappings_only); -extern void *fixmap_remap_fdt(phys_addr_t dt_phys); +extern void *fixmap_remap_fdt(phys_addr_t dt_phys, int *size, pgprot_t prot); extern void mark_linear_text_alias_ro(void); #endif /* !__ASSEMBLY__ */ diff --git a/arch/arm64/kernel/kaslr.c b/arch/arm64/kernel/kaslr.c index 06941c1fe418e..92bb53460401c 100644 --- a/arch/arm64/kernel/kaslr.c +++ b/arch/arm64/kernel/kaslr.c @@ -65,9 +65,6 @@ out: return default_cmdline; } -extern void *__init __fixmap_remap_fdt(phys_addr_t dt_phys, int *size, - pgprot_t prot); - /* * This routine will be executed with the kernel mapped at its default virtual * address, and if it returns successfully, the kernel will be remapped, and @@ -96,7 +93,7 @@ u64 __init kaslr_early_init(u64 dt_phys) * attempt at mapping the FDT in setup_machine() */ early_fixmap_init(); - fdt = __fixmap_remap_fdt(dt_phys, &size, PAGE_KERNEL); + fdt = fixmap_remap_fdt(dt_phys, &size, PAGE_KERNEL); if (!fdt) return 0; diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index b3354ff94e798..43e9786f1d604 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -183,9 +183,13 @@ static void __init smp_build_mpidr_hash(void) static void __init setup_machine_fdt(phys_addr_t dt_phys) { - void *dt_virt = fixmap_remap_fdt(dt_phys); + int size; + void *dt_virt = fixmap_remap_fdt(dt_phys, &size, PAGE_KERNEL); const char *name; + if (dt_virt) + memblock_reserve(dt_phys, size); + if (!dt_virt || !early_init_dt_scan(dt_virt)) { pr_crit("\n" "Error: invalid device tree blob at physical address %pa (virtual address 0x%p)\n" @@ -197,6 +201,9 @@ static void __init setup_machine_fdt(phys_addr_t dt_phys) cpu_relax(); } + /* Early fixups are done, map the FDT as read-only now */ + fixmap_remap_fdt(dt_phys, &size, PAGE_KERNEL_RO); + name = of_flat_dt_get_machine_name(); if (!name) return; diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index b0a83dbed2dc4..7042fbb6d92ba 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -859,7 +859,7 @@ void __set_fixmap(enum fixed_addresses idx, } } -void *__init __fixmap_remap_fdt(phys_addr_t dt_phys, int *size, pgprot_t prot) +void *__init fixmap_remap_fdt(phys_addr_t dt_phys, int *size, pgprot_t prot) { const u64 dt_virt_base = __fix_to_virt(FIX_FDT); int offset; @@ -912,19 +912,6 @@ void *__init __fixmap_remap_fdt(phys_addr_t dt_phys, int *size, pgprot_t prot) return dt_virt; } -void *__init fixmap_remap_fdt(phys_addr_t dt_phys) -{ - void *dt_virt; - int size; - - dt_virt = __fixmap_remap_fdt(dt_phys, &size, PAGE_KERNEL_RO); - if (!dt_virt) - return NULL; - - memblock_reserve(dt_phys, size); - return dt_virt; -} - int __init arch_ioremap_pud_supported(void) { /* diff --git a/arch/parisc/kernel/unaligned.c b/arch/parisc/kernel/unaligned.c index c16af267362e4..a8b5ad11c7a41 100644 --- a/arch/parisc/kernel/unaligned.c +++ b/arch/parisc/kernel/unaligned.c @@ -121,7 +121,7 @@ #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 3452e18bb1ca8..38105ba35c814 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; } if (diag204_info_type == DIAG204_INFO_EXT) { diff --git a/arch/s390/hypfs/inode.c b/arch/s390/hypfs/inode.c index e4d17d9ea93d8..4af5c0dd9fbe2 100644 --- a/arch/s390/hypfs/inode.c +++ b/arch/s390/hypfs/inode.c @@ -494,9 +494,9 @@ fail_hypfs_vm_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 99ef537e548a3..5772ef90dd26c 100644 --- a/arch/s390/kernel/process.c +++ b/arch/s390/kernel/process.c @@ -75,6 +75,18 @@ 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; } @@ -131,13 +143,11 @@ 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 a6e3c7022245d..d64b180caedaf 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -455,7 +455,9 @@ 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/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 89145ea183d6d..e9b79bac9b2af 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -396,6 +396,7 @@ #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 a36be67860432..501d09d59abcc 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) @@ -1868,6 +1871,9 @@ 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]); @@ -1995,6 +2001,7 @@ 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: @@ -2051,6 +2058,9 @@ 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 3ab35d5426b76..653ced7cb3964 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -955,6 +955,7 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c) #define NO_SWAPGS BIT(6) #define NO_ITLB_MULTIHIT BIT(7) #define NO_EIBRS_PBRSB BIT(8) +#define NO_MMIO BIT(9) #define VULNWL(_vendor, _family, _model, _whitelist) \ { X86_VENDOR_##_vendor, _family, _model, X86_FEATURE_ANY, _whitelist } @@ -972,6 +973,11 @@ 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), @@ -989,9 +995,9 @@ 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_GOLDMONT, NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT), - VULNWL_INTEL(ATOM_GOLDMONT_X, 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_X, 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 @@ -1006,13 +1012,13 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { VULNWL_INTEL(ATOM_TREMONT_X, 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_AMD(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO), {} }; @@ -1152,10 +1158,16 @@ 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 4f17c1c949498..5c48d2c4cabe6 100644 --- a/arch/x86/kernel/unwind_orc.c +++ b/arch/x86/kernel/unwind_orc.c @@ -89,22 +89,27 @@ 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/block/loop.c b/drivers/block/loop.c index c31a76485c9cb..12eb48980df7b 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -1351,6 +1351,11 @@ 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/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c index 411f89218e019..cb5c44b339e09 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c @@ -452,6 +452,11 @@ 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/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 c4ba2d28dd731..6a5c5ce85d85b 100644 --- a/drivers/hid/hidraw.c +++ b/drivers/hid/hidraw.c @@ -354,10 +354,13 @@ 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 4594a1ee88b9b..38cbde9061339 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -5937,6 +5937,7 @@ 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 bbb5ff16abd61..4cbb39bfb7da4 100644 --- a/drivers/media/usb/pvrusb2/pvrusb2-hdw.c +++ b/drivers/media/usb/pvrusb2/pvrusb2-hdw.c @@ -2602,6 +2602,7 @@ 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 b3eaef31b7673..a6bb7e915f74f 100644 --- a/drivers/net/bonding/bond_3ad.c +++ b/drivers/net/bonding/bond_3ad.c @@ -1977,30 +1977,24 @@ 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/intel/ixgbe/ixgbe_ptp.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c index b3e0d8bb5cbd8..eec68cc9288c8 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c @@ -1066,7 +1066,6 @@ 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. @@ -1101,18 +1100,6 @@ 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; @@ -1144,6 +1131,50 @@ 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 @@ -1170,6 +1201,8 @@ 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/ipvlan/ipvtap.c b/drivers/net/ipvlan/ipvtap.c index 0bcc07f346c3e..2e517e30c5ac1 100644 --- a/drivers/net/ipvlan/ipvtap.c +++ b/drivers/net/ipvlan/ipvtap.c @@ -193,7 +193,7 @@ 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; @@ -227,7 +227,7 @@ 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 8d2dbf607bd15..66b9c5826ec03 100644 --- a/drivers/pinctrl/pinctrl-amd.c +++ b/drivers/pinctrl/pinctrl-amd.c @@ -798,6 +798,7 @@ static int amd_gpio_suspend(struct device *dev) struct platform_device *pdev = to_platform_device(dev); struct amd_gpio *gpio_dev = platform_get_drvdata(pdev); struct pinctrl_desc *desc = gpio_dev->pctrl->desc; + unsigned long flags; int i; for (i = 0; i < desc->npins; i++) { @@ -806,7 +807,9 @@ 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; @@ -817,6 +820,7 @@ static int amd_gpio_resume(struct device *dev) struct platform_device *pdev = to_platform_device(dev); struct amd_gpio *gpio_dev = platform_get_drvdata(pdev); struct pinctrl_desc *desc = gpio_dev->pctrl->desc; + unsigned long flags; int i; for (i = 0; i < desc->npins; i++) { @@ -825,7 +829,10 @@ 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 0c2ba075bc713..f3701b4e374b6 100644 --- a/drivers/scsi/storvsc_drv.c +++ b/drivers/scsi/storvsc_drv.c @@ -1858,7 +1858,7 @@ 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/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/xattr.c b/fs/btrfs/xattr.c index f141b45ce3498..6adee94637a93 100644 --- a/fs/btrfs/xattr.c +++ b/fs/btrfs/xattr.c @@ -369,6 +369,9 @@ 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(NULL, inode, name, buffer, size, flags); } diff --git a/include/asm-generic/sections.h b/include/asm-generic/sections.h index ea5987bb0b84a..40e03afa9ad10 100644 --- a/include/asm-generic/sections.h +++ b/include/asm-generic/sections.h @@ -100,7 +100,7 @@ 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 @@ -113,7 +113,10 @@ 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/netfilter_bridge/ebtables.h b/include/linux/netfilter_bridge/ebtables.h index c6935be7c6ca3..954ffe32f6227 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 f92d5ae6d04e7..fd4899236037f 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -528,10 +528,6 @@ 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. * @@ -546,7 +542,6 @@ 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; @@ -565,6 +560,15 @@ 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 }; union rcu_special { diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h index c76a5e9894dac..8f42f6f3af86f 100644 --- a/include/net/busy_poll.h +++ b/include/net/busy_poll.h @@ -43,7 +43,7 @@ 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 fba78047fb37c..57404292c6d14 100644 --- a/kernel/audit_fsnotify.c +++ b/kernel/audit_fsnotify.c @@ -111,6 +111,7 @@ 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 099191716d4c9..b2fcad8635bcf 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -1709,11 +1709,12 @@ 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 32af895bd86b3..a034642497718 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -3869,20 +3869,21 @@ 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 beec5081a55af..29ed5d8d30d68 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); @@ -2691,11 +2721,14 @@ 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 df556175be506..acd7e12217743 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -257,6 +257,7 @@ 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 998d141488a95..d2272fff2f591 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -2748,6 +2748,16 @@ static 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 d01f471352390..b805702de84dd 100644 --- a/lib/ratelimit.c +++ b/lib/ratelimit.c @@ -27,10 +27,16 @@ */ 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; /* @@ -45,7 +51,7 @@ 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 @@ -57,7 +63,7 @@ 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/mm/mmap.c b/mm/mmap.c index 590840c3a3b5f..5ee3c91450de1 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1640,8 +1640,12 @@ 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? */ @@ -2568,6 +2572,18 @@ 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 e578eb942317b..3c2a439381529 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -82,7 +82,8 @@ 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 @@ -190,6 +191,7 @@ 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; } @@ -199,8 +201,7 @@ 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; } @@ -279,19 +280,19 @@ 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; @@ -341,6 +342,7 @@ 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; @@ -361,7 +363,7 @@ 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; @@ -393,7 +395,7 @@ 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; } @@ -401,7 +403,7 @@ 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); /* @@ -412,7 +414,8 @@ 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 0dfc47adccb17..65d20bdff0238 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -1826,11 +1826,11 @@ 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/bridge/netfilter/ebtable_broute.c b/net/bridge/netfilter/ebtable_broute.c index 276b60262981c..b21c8a317be73 100644 --- a/net/bridge/netfilter/ebtable_broute.c +++ b/net/bridge/netfilter/ebtable_broute.c @@ -33,18 +33,10 @@ 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 550324c516ee3..c71795e4c18cf 100644 --- a/net/bridge/netfilter/ebtable_filter.c +++ b/net/bridge/netfilter/ebtable_filter.c @@ -42,18 +42,10 @@ 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 c0fb3ca518af8..44dde9e635e24 100644 --- a/net/bridge/netfilter/ebtable_nat.c +++ b/net/bridge/netfilter/ebtable_nat.c @@ -42,18 +42,10 @@ 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 f59230e4fc295..ea27bacbd0057 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -1003,8 +1003,7 @@ 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) { @@ -1197,11 +1196,6 @@ 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 42f6ff8b9703c..880b096eef8a6 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4474,7 +4474,7 @@ 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); @@ -4794,7 +4794,7 @@ 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); @@ -5146,7 +5146,7 @@ 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; @@ -5176,7 +5176,7 @@ 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); @@ -5851,7 +5851,7 @@ 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; @@ -6335,8 +6335,8 @@ 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 6233e9856016e..73042407eb5b4 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -224,11 +224,26 @@ 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); } @@ -297,9 +312,9 @@ int neigh_ifdown(struct neigh_table *tbl, struct net_device *dev) write_lock_bh(&tbl->lock); neigh_flush_dev(tbl, dev); 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; } EXPORT_SYMBOL(neigh_ifdown); @@ -1614,7 +1629,7 @@ 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 c623c129d0ab6..e0be1f8651bbe 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -4377,7 +4377,7 @@ 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 79f085df52cef..cd23a8e4556ca 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2856,7 +2856,7 @@ 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 = ~0U; diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 0a0bf80623658..d7e39167ceca0 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -231,14 +231,17 @@ 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 af67e0d265c05..337c6bc8211ed 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -1707,9 +1707,12 @@ 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 56cddadb65d0c..92e0514f624fa 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -117,7 +117,6 @@ 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 e259454b6a643..4fac2d9a4b885 100644 --- a/net/netfilter/nft_osf.c +++ b/net/netfilter/nft_osf.c @@ -81,9 +81,21 @@ 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 fd87216bc0a99..5732b32ab9320 100644 --- a/net/netfilter/nft_payload.c +++ b/net/netfilter/nft_payload.c @@ -332,6 +332,8 @@ 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])); @@ -339,11 +341,15 @@ 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; @@ -354,13 +360,14 @@ 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); } @@ -398,6 +405,7 @@ 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 || @@ -423,8 +431,13 @@ 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 8ae948fd9dcfc..3fc55c81f16ac 100644 --- a/net/netfilter/nft_tunnel.c +++ b/net/netfilter/nft_tunnel.c @@ -104,6 +104,7 @@ 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/rose/rose_loopback.c b/net/rose/rose_loopback.c index c318e5c9f6df3..56eea298b8ef7 100644 --- a/net/rose/rose_loopback.c +++ b/net/rose/rose_loopback.c @@ -99,7 +99,8 @@ 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 cad2586c34734..c966dacf1130b 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -397,7 +397,7 @@ 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 e5cc9f2b981ed..a5167f03c31db 100644 --- a/net/socket.c +++ b/net/socket.c @@ -1619,7 +1619,7 @@ 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/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 3582f77bab6a8..1cd21a8c4deac 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -2403,6 +2403,7 @@ 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 51884c7b80697..4eac2ecb35fb9 100644 --- a/scripts/Makefile.modpost +++ b/scripts/Makefile.modpost @@ -51,8 +51,7 @@ 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 include scripts/Makefile.lib diff --git a/tools/testing/selftests/bpf/test_align.c b/tools/testing/selftests/bpf/test_align.c index 3c789d03b629d..0ae7a74154146 100644 --- a/tools/testing/selftests/bpf/test_align.c +++ b/tools/testing/selftests/bpf/test_align.c @@ -359,15 +359,15 @@ static struct bpf_align_test tests[] = { * is still (4n), fixed offset is not changed. * Also, we create a new reg->id. */ - {29, "R5_w=pkt(id=4,off=18,r=0,umax_value=2040,var_off=(0x0; 0x7fc))"}, + {29, "R5_w=pkt(id=4,off=18,r=0,umax_value=2040,var_off=(0x0; 0x7fc)"}, /* At the time the word size load is performed from R5, * its total fixed offset is NET_IP_ALIGN + reg->off (18) * which is 20. Then the variable offset is (4n), so * the total offset is 4-byte aligned and meets the * load's requirements. */ - {33, "R4=pkt(id=4,off=22,r=22,umax_value=2040,var_off=(0x0; 0x7fc))"}, - {33, "R5=pkt(id=4,off=18,r=22,umax_value=2040,var_off=(0x0; 0x7fc))"}, + {33, "R4=pkt(id=4,off=22,r=22,umax_value=2040,var_off=(0x0; 0x7fc)"}, + {33, "R5=pkt(id=4,off=18,r=22,umax_value=2040,var_off=(0x0; 0x7fc)"}, }, }, { @@ -410,15 +410,15 @@ static struct bpf_align_test tests[] = { /* Adding 14 makes R6 be (4n+2) */ {9, "R6_w=inv(id=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc))"}, /* Packet pointer has (4n+2) offset */ - {11, "R5_w=pkt(id=1,off=0,r=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc))"}, - {13, "R4=pkt(id=1,off=4,r=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc))"}, + {11, "R5_w=pkt(id=1,off=0,r=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc)"}, + {13, "R4=pkt(id=1,off=4,r=0,umin_value=14,umax_value=1034,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. */ - {15, "R5=pkt(id=1,off=0,r=4,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc))"}, + {15, "R5=pkt(id=1,off=0,r=4,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc)"}, /* Newly read value in R6 was shifted left by 2, so has * known alignment of 4. */ @@ -426,15 +426,15 @@ static struct bpf_align_test tests[] = { /* Added (4n) to packet pointer's (4n+2) var_off, giving * another (4n+2). */ - {19, "R5_w=pkt(id=2,off=0,r=0,umin_value=14,umax_value=2054,var_off=(0x2; 0xffc))"}, - {21, "R4=pkt(id=2,off=4,r=0,umin_value=14,umax_value=2054,var_off=(0x2; 0xffc))"}, + {19, "R5_w=pkt(id=2,off=0,r=0,umin_value=14,umax_value=2054,var_off=(0x2; 0xffc)"}, + {21, "R4=pkt(id=2,off=4,r=0,umin_value=14,umax_value=2054,var_off=(0x2; 0xffc)"}, /* 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. */ - {23, "R5=pkt(id=2,off=0,r=4,umin_value=14,umax_value=2054,var_off=(0x2; 0xffc))"}, + {23, "R5=pkt(id=2,off=0,r=4,umin_value=14,umax_value=2054,var_off=(0x2; 0xffc)"}, }, }, { @@ -469,11 +469,11 @@ static struct bpf_align_test tests[] = { .matches = { {4, "R5_w=pkt_end(id=0,off=0,imm=0)"}, /* (ptr - ptr) << 2 == unknown, (4n) */ - {6, "R5_w=inv(id=0,smax_value=9223372036854775804,umax_value=18446744073709551612,var_off=(0x0; 0xfffffffffffffffc))"}, + {6, "R5_w=inv(id=0,smax_value=9223372036854775804,umax_value=18446744073709551612,var_off=(0x0; 0xfffffffffffffffc)"}, /* (4n) + 14 == (4n+2). We blow our bounds, because * the add could overflow. */ - {7, "R5=inv(id=0,var_off=(0x2; 0xfffffffffffffffc))"}, + {7, "R5=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))"}, /* packet pointer + nonnegative (4n+2) */ @@ -528,7 +528,7 @@ static struct bpf_align_test tests[] = { /* New unknown value in R7 is (4n) */ {11, "R7_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, /* Subtracting it from R6 blows our unsigned bounds */ - {12, "R6=inv(id=0,smin_value=-1006,smax_value=1034,var_off=(0x2; 0xfffffffffffffffc))"}, + {12, "R6=inv(id=0,smin_value=-1006,smax_value=1034,umin_value=2,umax_value=18446744073709551614,var_off=(0x2; 0xfffffffffffffffc)"}, /* Checked s>= 0 */ {14, "R6=inv(id=0,umin_value=2,umax_value=1034,var_off=(0x2; 0x7fc))"}, /* At the time the word size load is performed from R5, @@ -537,7 +537,8 @@ static struct bpf_align_test tests[] = { * the total offset is 4-byte aligned and meets the * load's requirements. */ - {20, "R5=pkt(id=1,off=0,r=4,umin_value=2,umax_value=1034,var_off=(0x2; 0x7fc))"}, + {20, "R5=pkt(id=1,off=0,r=4,umin_value=2,umax_value=1034,var_off=(0x2; 0x7fc)"}, + }, }, { diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index 858e551432339..9a103bd3542cf 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -9108,10 +9108,10 @@ static struct bpf_test tests[] = { BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data_end)), BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), - BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 6), BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_1, 1), BPF_JMP_IMM(BPF_JA, 0, 0, 1), - BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -6), BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, @@ -9166,10 +9166,10 @@ static struct bpf_test tests[] = { BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data_end)), BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), - BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 6), BPF_JMP_REG(BPF_JLT, BPF_REG_1, BPF_REG_3, 1), BPF_JMP_IMM(BPF_JA, 0, 0, 1), - BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -6), BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, @@ -9279,9 +9279,9 @@ static struct bpf_test tests[] = { BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data_end)), BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), - BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 6), BPF_JMP_REG(BPF_JGE, BPF_REG_1, BPF_REG_3, 1), - BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -6), BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, @@ -9451,9 +9451,9 @@ static struct bpf_test tests[] = { BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data_end)), BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), - BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 6), BPF_JMP_REG(BPF_JLE, BPF_REG_3, BPF_REG_1, 1), - BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -6), BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, @@ -9564,10 +9564,10 @@ static struct bpf_test tests[] = { BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)), BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), - BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 6), BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_1, 1), BPF_JMP_IMM(BPF_JA, 0, 0, 1), - BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -6), BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, @@ -9622,10 +9622,10 @@ static struct bpf_test tests[] = { BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)), BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), - BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 6), BPF_JMP_REG(BPF_JLT, BPF_REG_1, BPF_REG_3, 1), BPF_JMP_IMM(BPF_JA, 0, 0, 1), - BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -6), BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, @@ -9735,9 +9735,9 @@ static struct bpf_test tests[] = { BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)), BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), - BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 6), BPF_JMP_REG(BPF_JGE, BPF_REG_1, BPF_REG_3, 1), - BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -6), BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, @@ -9907,9 +9907,9 @@ static struct bpf_test tests[] = { BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)), BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), - BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 6), BPF_JMP_REG(BPF_JLE, BPF_REG_3, BPF_REG_1, 1), - BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -6), BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), },