diff --git a/Documentation/cpu-freq/pcc-cpufreq.txt b/Documentation/cpu-freq/pcc-cpufreq.txt index 0a94224ad296..9e3c3b33514c 100644 --- a/Documentation/cpu-freq/pcc-cpufreq.txt +++ b/Documentation/cpu-freq/pcc-cpufreq.txt @@ -159,8 +159,8 @@ to be strictly associated with a P-state. 2.2 cpuinfo_transition_latency: ------------------------------- -The cpuinfo_transition_latency field is CPUFREQ_ETERNAL. The PCC specification -does not include a field to expose this value currently. +The cpuinfo_transition_latency field is 0. The PCC specification does +not include a field to expose this value currently. 2.3 cpuinfo_cur_freq: --------------------- diff --git a/Documentation/x86/pat.txt b/Documentation/x86/pat.txt index 54944c71b819..2a4ee6302122 100644 --- a/Documentation/x86/pat.txt +++ b/Documentation/x86/pat.txt @@ -196,3 +196,35 @@ Another, more verbose way of getting PAT related debug messages is with "debugpat" boot parameter. With this parameter, various debug messages are printed to dmesg log. +PAT Initialization +------------------ + +The following table describes how PAT is initialized under various +configurations. The PAT MSR must be updated by Linux in order to support WC +and WT attributes. Otherwise, the PAT MSR has the value programmed in it +by the firmware. Note, Xen enables WC attribute in the PAT MSR for guests. + + MTRR PAT Call Sequence PAT State PAT MSR + ========================================================= + E E MTRR -> PAT init Enabled OS + E D MTRR -> PAT init Disabled - + D E MTRR -> PAT disable Disabled BIOS + D D MTRR -> PAT disable Disabled - + - np/E PAT -> PAT disable Disabled BIOS + - np/D PAT -> PAT disable Disabled - + E !P/E MTRR -> PAT init Disabled BIOS + D !P/E MTRR -> PAT disable Disabled BIOS + !M !P/E MTRR stub -> PAT disable Disabled BIOS + + Legend + ------------------------------------------------ + E Feature enabled in CPU + D Feature disabled/unsupported in CPU + np "nopat" boot option specified + !P CONFIG_X86_PAT option unset + !M CONFIG_MTRR option unset + Enabled PAT state set to enabled + Disabled PAT state set to disabled + OS PAT initializes PAT MSR with OS setting + BIOS PAT keeps PAT MSR with BIOS setting + diff --git a/Makefile b/Makefile index bee1a1692fed..5fe9a7a9cd65 100644 --- a/Makefile +++ b/Makefile @@ -1,6 +1,6 @@ VERSION = 4 PATCHLEVEL = 6 -SUBLEVEL = 6 +SUBLEVEL = 7 EXTRAVERSION = NAME = Charred Weasel diff --git a/arch/arm/kernel/sys_oabi-compat.c b/arch/arm/kernel/sys_oabi-compat.c index 087acb569b63..5f221acd21ae 100644 --- a/arch/arm/kernel/sys_oabi-compat.c +++ b/arch/arm/kernel/sys_oabi-compat.c @@ -279,8 +279,12 @@ asmlinkage long sys_oabi_epoll_wait(int epfd, mm_segment_t fs; long ret, err, i; - if (maxevents <= 0 || maxevents > (INT_MAX/sizeof(struct epoll_event))) + if (maxevents <= 0 || + maxevents > (INT_MAX/sizeof(*kbuf)) || + maxevents > (INT_MAX/sizeof(*events))) return -EINVAL; + if (!access_ok(VERIFY_WRITE, events, sizeof(*events) * maxevents)) + return -EFAULT; kbuf = kmalloc(sizeof(*kbuf) * maxevents, GFP_KERNEL); if (!kbuf) return -ENOMEM; @@ -317,6 +321,8 @@ asmlinkage long sys_oabi_semtimedop(int semid, if (nsops < 1 || nsops > SEMOPM) return -EINVAL; + if (!access_ok(VERIFY_READ, tsops, sizeof(*tsops) * nsops)) + return -EFAULT; sops = kmalloc(sizeof(*sops) * nsops, GFP_KERNEL); if (!sops) return -ENOMEM; diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S index 71f99d5f7a06..6021318bfbb0 100644 --- a/arch/mips/kernel/scall64-n32.S +++ b/arch/mips/kernel/scall64-n32.S @@ -344,7 +344,7 @@ EXPORT(sysn32_call_table) PTR sys_ni_syscall /* available, was setaltroot */ PTR sys_add_key PTR sys_request_key - PTR sys_keyctl /* 6245 */ + PTR compat_sys_keyctl /* 6245 */ PTR sys_set_thread_area PTR sys_inotify_init PTR sys_inotify_add_watch diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S index 91b43eea2d5a..71fe3259a5e3 100644 --- a/arch/mips/kernel/scall64-o32.S +++ b/arch/mips/kernel/scall64-o32.S @@ -500,7 +500,7 @@ EXPORT(sys32_call_table) PTR sys_ni_syscall /* available, was setaltroot */ PTR sys_add_key /* 4280 */ PTR sys_request_key - PTR sys_keyctl + PTR compat_sys_keyctl PTR sys_set_thread_area PTR sys_inotify_init PTR sys_inotify_add_watch /* 4285 */ diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 7cd32c038286..4e1b060b8481 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -126,7 +126,7 @@ config PPC select IRQ_FORCED_THREADING select HAVE_RCU_TABLE_FREE if SMP select HAVE_SYSCALL_TRACEPOINTS - select HAVE_BPF_JIT + select HAVE_BPF_JIT if CPU_BIG_ENDIAN select HAVE_ARCH_JUMP_LABEL select ARCH_HAVE_NMI_SAFE_CMPXCHG select ARCH_HAS_GCOV_PROFILE_ALL diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index 31e4c7e1a4b4..c42627645b54 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -648,7 +648,6 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus, if (pe->type & EEH_PE_VF) { eeh_pe_dev_traverse(pe, eeh_rmv_device, NULL); } else { - eeh_pe_state_clear(pe, EEH_PE_PRI_BUS); pci_lock_rescan_remove(); pcibios_remove_pci_devices(bus); pci_unlock_rescan_remove(); @@ -698,10 +697,12 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus, */ edev = list_first_entry(&pe->edevs, struct eeh_dev, list); eeh_pe_traverse(pe, eeh_pe_detach_dev, NULL); - if (pe->type & EEH_PE_VF) + if (pe->type & EEH_PE_VF) { eeh_add_virt_device(edev, NULL); - else + } else { + eeh_pe_state_clear(pe, EEH_PE_PRI_BUS); pcibios_add_pci_devices(bus); + } } else if (frozen_bus && rmv_data->removed) { pr_info("EEH: Sleep 5s ahead of partial hotplug\n"); ssleep(5); diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index 4cddd17153fb..f848572169ea 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -294,7 +294,7 @@ # 285 sys_setaltroot 286 i386 add_key sys_add_key 287 i386 request_key sys_request_key -288 i386 keyctl sys_keyctl +288 i386 keyctl sys_keyctl compat_sys_keyctl 289 i386 ioprio_set sys_ioprio_set 290 i386 ioprio_get sys_ioprio_get 291 i386 inotify_init sys_inotify_init diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h index 9d3a96c4da78..01c2d14ec05f 100644 --- a/arch/x86/include/asm/microcode.h +++ b/arch/x86/include/asm/microcode.h @@ -133,13 +133,11 @@ static inline unsigned int x86_cpuid_family(void) #ifdef CONFIG_MICROCODE extern void __init load_ucode_bsp(void); extern void load_ucode_ap(void); -extern int __init save_microcode_in_initrd(void); void reload_early_microcode(void); extern bool get_builtin_firmware(struct cpio_data *cd, const char *name); #else static inline void __init load_ucode_bsp(void) { } static inline void load_ucode_ap(void) { } -static inline int __init save_microcode_in_initrd(void) { return 0; } static inline void reload_early_microcode(void) { } static inline bool get_builtin_firmware(struct cpio_data *cd, const char *name) { return false; } diff --git a/arch/x86/include/asm/mtrr.h b/arch/x86/include/asm/mtrr.h index b94f6f64e23d..dbff1456d215 100644 --- a/arch/x86/include/asm/mtrr.h +++ b/arch/x86/include/asm/mtrr.h @@ -24,6 +24,7 @@ #define _ASM_X86_MTRR_H #include +#include /* @@ -83,9 +84,12 @@ static inline int mtrr_trim_uncached_memory(unsigned long end_pfn) static inline void mtrr_centaur_report_mcr(int mcr, u32 lo, u32 hi) { } +static inline void mtrr_bp_init(void) +{ + pat_disable("MTRRs disabled, skipping PAT initialization too."); +} #define mtrr_ap_init() do {} while (0) -#define mtrr_bp_init() do {} while (0) #define set_mtrr_aps_delayed_init() do {} while (0) #define mtrr_aps_init() do {} while (0) #define mtrr_bp_restore() do {} while (0) diff --git a/arch/x86/include/asm/pat.h b/arch/x86/include/asm/pat.h index ca6c228d5e62..0b1ff4c1c14e 100644 --- a/arch/x86/include/asm/pat.h +++ b/arch/x86/include/asm/pat.h @@ -5,8 +5,8 @@ #include bool pat_enabled(void); +void pat_disable(const char *reason); extern void pat_init(void); -void pat_init_cache_modes(u64); extern int reserve_memtype(u64 start, u64 end, enum page_cache_mode req_pcm, enum page_cache_mode *ret_pcm); diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index ac360bfbbdb6..12823b6ebd6d 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -175,7 +175,7 @@ void load_ucode_ap(void) } } -int __init save_microcode_in_initrd(void) +static int __init save_microcode_in_initrd(void) { struct cpuinfo_x86 *c = &boot_cpu_data; @@ -691,4 +691,5 @@ int __init microcode_init(void) return error; } +fs_initcall(save_microcode_in_initrd); late_initcall(microcode_init); diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index 19f57360dfd2..8d7a29ed9377 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -444,11 +444,24 @@ static void __init print_mtrr_state(void) pr_debug("TOM2: %016llx aka %lldM\n", mtrr_tom2, mtrr_tom2>>20); } +/* PAT setup for BP. We need to go through sync steps here */ +void __init mtrr_bp_pat_init(void) +{ + unsigned long flags; + + local_irq_save(flags); + prepare_set(); + + pat_init(); + + post_set(); + local_irq_restore(flags); +} + /* Grab all of the MTRR state for this CPU into *state */ bool __init get_mtrr_state(void) { struct mtrr_var_range *vrs; - unsigned long flags; unsigned lo, dummy; unsigned int i; @@ -481,15 +494,6 @@ bool __init get_mtrr_state(void) mtrr_state_set = 1; - /* PAT setup for BP. We need to go through sync steps here */ - local_irq_save(flags); - prepare_set(); - - pat_init(); - - post_set(); - local_irq_restore(flags); - return !!(mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED); } diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c index 10f8d4796240..7d393ecdeee6 100644 --- a/arch/x86/kernel/cpu/mtrr/main.c +++ b/arch/x86/kernel/cpu/mtrr/main.c @@ -752,6 +752,9 @@ void __init mtrr_bp_init(void) /* BIOS may override */ __mtrr_enabled = get_mtrr_state(); + if (mtrr_enabled()) + mtrr_bp_pat_init(); + if (mtrr_cleanup(phys_addr)) { changed_by_mtrr_cleanup = 1; mtrr_if->set_all(); @@ -759,8 +762,16 @@ void __init mtrr_bp_init(void) } } - if (!mtrr_enabled()) + if (!mtrr_enabled()) { pr_info("MTRR: Disabled\n"); + + /* + * PAT initialization relies on MTRR's rendezvous handler. + * Skip PAT init until the handler can initialize both + * features independently. + */ + pat_disable("MTRRs disabled, skipping PAT initialization too."); + } } void mtrr_ap_init(void) diff --git a/arch/x86/kernel/cpu/mtrr/mtrr.h b/arch/x86/kernel/cpu/mtrr/mtrr.h index 951884dcc433..6c7ced07d16d 100644 --- a/arch/x86/kernel/cpu/mtrr/mtrr.h +++ b/arch/x86/kernel/cpu/mtrr/mtrr.h @@ -52,6 +52,7 @@ void set_mtrr_prepare_save(struct set_mtrr_context *ctxt); void fill_mtrr_var_range(unsigned int index, u32 base_lo, u32 base_hi, u32 mask_lo, u32 mask_hi); bool get_mtrr_state(void); +void mtrr_bp_pat_init(void); extern void set_mtrr_ops(const struct mtrr_ops *ops); diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index 9d56f271d519..6df291c2987c 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -696,13 +696,6 @@ void free_initmem(void) void __init free_initrd_mem(unsigned long start, unsigned long end) { /* - * Remember, initrd memory may contain microcode or other useful things. - * Before we lose initrd mem, we need to find a place to hold them - * now that normal virtual memory is enabled. - */ - save_microcode_in_initrd(); - - /* * end could be not aligned, and We can not align that, * decompresser could be confused by aligned initrd_end * We already reserve the end partial page before in diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c index faec01e7a17d..fb0604f11eec 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -40,11 +40,22 @@ static bool boot_cpu_done; static int __read_mostly __pat_enabled = IS_ENABLED(CONFIG_X86_PAT); +static void init_cache_modes(void); -static inline void pat_disable(const char *reason) +void pat_disable(const char *reason) { + if (!__pat_enabled) + return; + + if (boot_cpu_done) { + WARN_ONCE(1, "x86/PAT: PAT cannot be disabled after initialization\n"); + return; + } + __pat_enabled = 0; pr_info("x86/PAT: %s\n", reason); + + init_cache_modes(); } static int __init nopat(char *str) @@ -181,7 +192,7 @@ static enum page_cache_mode pat_get_cache_mode(unsigned pat_val, char *msg) * configuration. * Using lower indices is preferred, so we start with highest index. */ -void pat_init_cache_modes(u64 pat) +static void __init_cache_modes(u64 pat) { enum page_cache_mode cache; char pat_msg[33]; @@ -202,14 +213,11 @@ static void pat_bsp_init(u64 pat) { u64 tmp_pat; - if (!cpu_has_pat) { + if (!boot_cpu_has(X86_FEATURE_PAT)) { pat_disable("PAT not supported by CPU."); return; } - if (!pat_enabled()) - goto done; - rdmsrl(MSR_IA32_CR_PAT, tmp_pat); if (!tmp_pat) { pat_disable("PAT MSR is 0, disabled."); @@ -218,16 +226,12 @@ static void pat_bsp_init(u64 pat) wrmsrl(MSR_IA32_CR_PAT, pat); -done: - pat_init_cache_modes(pat); + __init_cache_modes(pat); } static void pat_ap_init(u64 pat) { - if (!pat_enabled()) - return; - - if (!cpu_has_pat) { + if (!boot_cpu_has(X86_FEATURE_PAT)) { /* * If this happens we are on a secondary CPU, but switched to * PAT on the boot CPU. We have no way to undo PAT. @@ -238,18 +242,32 @@ static void pat_ap_init(u64 pat) wrmsrl(MSR_IA32_CR_PAT, pat); } -void pat_init(void) +static void init_cache_modes(void) { - u64 pat; - struct cpuinfo_x86 *c = &boot_cpu_data; + u64 pat = 0; + static int init_cm_done; - if (!pat_enabled()) { + if (init_cm_done) + return; + + if (boot_cpu_has(X86_FEATURE_PAT)) { + /* + * CPU supports PAT. Set PAT table to be consistent with + * PAT MSR. This case supports "nopat" boot option, and + * virtual machine environments which support PAT without + * MTRRs. In specific, Xen has unique setup to PAT MSR. + * + * If PAT MSR returns 0, it is considered invalid and emulates + * as No PAT. + */ + rdmsrl(MSR_IA32_CR_PAT, pat); + } + + if (!pat) { /* * No PAT. Emulate the PAT table that corresponds to the two - * cache bits, PWT (Write Through) and PCD (Cache Disable). This - * setup is the same as the BIOS default setup when the system - * has PAT but the "nopat" boot option has been specified. This - * emulated PAT table is used when MSR_IA32_CR_PAT returns 0. + * cache bits, PWT (Write Through) and PCD (Cache Disable). + * This setup is also the same as the BIOS default setup. * * PTE encoding: * @@ -266,10 +284,36 @@ void pat_init(void) */ pat = PAT(0, WB) | PAT(1, WT) | PAT(2, UC_MINUS) | PAT(3, UC) | PAT(4, WB) | PAT(5, WT) | PAT(6, UC_MINUS) | PAT(7, UC); + } + + __init_cache_modes(pat); + + init_cm_done = 1; +} + +/** + * pat_init - Initialize PAT MSR and PAT table + * + * This function initializes PAT MSR and PAT table with an OS-defined value + * to enable additional cache attributes, WC and WT. + * + * This function must be called on all CPUs using the specific sequence of + * operations defined in Intel SDM. mtrr_rendezvous_handler() provides this + * procedure for PAT. + */ +void pat_init(void) +{ + u64 pat; + struct cpuinfo_x86 *c = &boot_cpu_data; + + if (!pat_enabled()) { + init_cache_modes(); + return; + } - } else if ((c->x86_vendor == X86_VENDOR_INTEL) && - (((c->x86 == 0x6) && (c->x86_model <= 0xd)) || - ((c->x86 == 0xf) && (c->x86_model <= 0x6)))) { + if ((c->x86_vendor == X86_VENDOR_INTEL) && + (((c->x86 == 0x6) && (c->x86_model <= 0xd)) || + ((c->x86 == 0xf) && (c->x86_model <= 0x6)))) { /* * PAT support with the lower four entries. Intel Pentium 2, * 3, M, and 4 are affected by PAT errata, which makes the @@ -734,25 +778,6 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn, if (file->f_flags & O_DSYNC) pcm = _PAGE_CACHE_MODE_UC_MINUS; -#ifdef CONFIG_X86_32 - /* - * On the PPro and successors, the MTRRs are used to set - * memory types for physical addresses outside main memory, - * so blindly setting UC or PWT on those pages is wrong. - * For Pentiums and earlier, the surround logic should disable - * caching for the high addresses through the KEN pin, but - * we maintain the tradition of paranoia in this code. - */ - if (!pat_enabled() && - !(boot_cpu_has(X86_FEATURE_MTRR) || - boot_cpu_has(X86_FEATURE_K6_MTRR) || - boot_cpu_has(X86_FEATURE_CYRIX_ARR) || - boot_cpu_has(X86_FEATURE_CENTAUR_MCR)) && - (pfn << PAGE_SHIFT) >= __pa(high_memory)) { - pcm = _PAGE_CACHE_MODE_UC; - } -#endif - *vma_prot = __pgprot((pgprot_val(*vma_prot) & ~_PAGE_CACHE_MASK) | cachemode2protval(pcm)); return 1; diff --git a/arch/x86/power/hibernate_asm_64.S b/arch/x86/power/hibernate_asm_64.S index 4400a43b9e28..f2a990285a5c 100644 --- a/arch/x86/power/hibernate_asm_64.S +++ b/arch/x86/power/hibernate_asm_64.S @@ -24,7 +24,6 @@ #include ENTRY(swsusp_arch_suspend) - FRAME_BEGIN movq $saved_context, %rax movq %rsp, pt_regs_sp(%rax) movq %rbp, pt_regs_bp(%rax) @@ -51,6 +50,7 @@ ENTRY(swsusp_arch_suspend) movq %cr3, %rax movq %rax, restore_cr3(%rip) + FRAME_BEGIN call swsusp_save FRAME_END ret @@ -111,7 +111,6 @@ ENTRY(core_restore_code) */ ENTRY(restore_registers) - FRAME_BEGIN /* go back to the original page tables */ movq %rbx, %cr3 @@ -152,6 +151,5 @@ ENTRY(restore_registers) /* tell the hibernation core that we've just restored the memory */ movq %rax, in_suspend(%rip) - FRAME_END ret ENDPROC(restore_registers) diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 880862c7d9dd..d8cca75e3b3e 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -75,7 +75,6 @@ #include #include #include -#include #include #ifdef CONFIG_ACPI @@ -1511,7 +1510,6 @@ asmlinkage __visible void __init xen_start_kernel(void) { struct physdev_set_iopl set_iopl; unsigned long initrd_start = 0; - u64 pat; int rc; if (!xen_start_info) @@ -1618,13 +1616,6 @@ asmlinkage __visible void __init xen_start_kernel(void) xen_start_info->nr_pages); xen_reserve_special_pages(); - /* - * Modify the cache mode translation tables to match Xen's PAT - * configuration. - */ - rdmsrl(MSR_IA32_CR_PAT, pat); - pat_init_cache_modes(pat); - /* keep using Xen gdt for now; no urgent need to change it */ #ifdef CONFIG_X86_32 diff --git a/block/genhd.c b/block/genhd.c index 9f42526b4d62..3eebd256b765 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -856,6 +856,7 @@ static void disk_seqf_stop(struct seq_file *seqf, void *v) if (iter) { class_dev_iter_exit(iter); kfree(iter); + seqf->private = NULL; } } diff --git a/crypto/gcm.c b/crypto/gcm.c index bec329b3de8d..d9ea5f9c0574 100644 --- a/crypto/gcm.c +++ b/crypto/gcm.c @@ -639,7 +639,9 @@ static int crypto_gcm_create_common(struct crypto_template *tmpl, ghash_alg = crypto_find_alg(ghash_name, &crypto_ahash_type, CRYPTO_ALG_TYPE_HASH, - CRYPTO_ALG_TYPE_AHASH_MASK); + CRYPTO_ALG_TYPE_AHASH_MASK | + crypto_requires_sync(algt->type, + algt->mask)); if (IS_ERR(ghash_alg)) return PTR_ERR(ghash_alg); diff --git a/crypto/scatterwalk.c b/crypto/scatterwalk.c index ea5815c5e128..bc769c448d4a 100644 --- a/crypto/scatterwalk.c +++ b/crypto/scatterwalk.c @@ -72,7 +72,8 @@ static void scatterwalk_pagedone(struct scatter_walk *walk, int out, void scatterwalk_done(struct scatter_walk *walk, int out, int more) { - if (!(scatterwalk_pagelen(walk) & (PAGE_SIZE - 1)) || !more) + if (!more || walk->offset >= walk->sg->offset + walk->sg->length || + !(walk->offset & (PAGE_SIZE - 1))) scatterwalk_pagedone(walk, out, more); } EXPORT_SYMBOL_GPL(scatterwalk_done); diff --git a/drivers/char/random.c b/drivers/char/random.c index b583e5336630..e511f34be177 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -722,15 +722,18 @@ retry: } } -static void credit_entropy_bits_safe(struct entropy_store *r, int nbits) +static int credit_entropy_bits_safe(struct entropy_store *r, int nbits) { const int nbits_max = (int)(~0U >> (ENTROPY_SHIFT + 1)); + if (nbits < 0) + return -EINVAL; + /* Cap the value to avoid overflows */ nbits = min(nbits, nbits_max); - nbits = max(nbits, -nbits_max); credit_entropy_bits(r, nbits); + return 0; } /********************************************************************* @@ -1542,8 +1545,7 @@ static long random_ioctl(struct file *f, unsigned int cmd, unsigned long arg) return -EPERM; if (get_user(ent_count, p)) return -EFAULT; - credit_entropy_bits_safe(&input_pool, ent_count); - return 0; + return credit_entropy_bits_safe(&input_pool, ent_count); case RNDADDENTROPY: if (!capable(CAP_SYS_ADMIN)) return -EPERM; @@ -1557,8 +1559,7 @@ static long random_ioctl(struct file *f, unsigned int cmd, unsigned long arg) size); if (retval < 0) return retval; - credit_entropy_bits_safe(&input_pool, ent_count); - return 0; + return credit_entropy_bits_safe(&input_pool, ent_count); case RNDZAPENTCNT: case RNDCLEARPOOL: /* diff --git a/drivers/cpufreq/pcc-cpufreq.c b/drivers/cpufreq/pcc-cpufreq.c index 808a320e9d5d..2a0d58959acf 100644 --- a/drivers/cpufreq/pcc-cpufreq.c +++ b/drivers/cpufreq/pcc-cpufreq.c @@ -555,8 +555,6 @@ static int pcc_cpufreq_cpu_init(struct cpufreq_policy *policy) policy->min = policy->cpuinfo.min_freq = ioread32(&pcch_hdr->minimum_frequency) * 1000; - policy->cpuinfo.transition_latency = CPUFREQ_ETERNAL; - pr_debug("init: policy->max is %d, policy->min is %d\n", policy->max, policy->min); out: diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c index 585a3b7915bd..f1b0eafecd0d 100644 --- a/drivers/i2c/busses/i2c-i801.c +++ b/drivers/i2c/busses/i2c-i801.c @@ -244,6 +244,13 @@ struct i801_priv { struct platform_device *mux_pdev; #endif struct platform_device *tco_pdev; + + /* + * If set to true the host controller registers are reserved for + * ACPI AML use. Protected by acpi_lock. + */ + bool acpi_reserved; + struct mutex acpi_lock; }; #define FEATURE_SMBUS_PEC (1 << 0) @@ -714,9 +721,15 @@ static s32 i801_access(struct i2c_adapter *adap, u16 addr, { int hwpec; int block = 0; - int ret, xact = 0; + int ret = 0, xact = 0; struct i801_priv *priv = i2c_get_adapdata(adap); + mutex_lock(&priv->acpi_lock); + if (priv->acpi_reserved) { + mutex_unlock(&priv->acpi_lock); + return -EBUSY; + } + hwpec = (priv->features & FEATURE_SMBUS_PEC) && (flags & I2C_CLIENT_PEC) && size != I2C_SMBUS_QUICK && size != I2C_SMBUS_I2C_BLOCK_DATA; @@ -773,7 +786,8 @@ static s32 i801_access(struct i2c_adapter *adap, u16 addr, default: dev_err(&priv->pci_dev->dev, "Unsupported transaction %d\n", size); - return -EOPNOTSUPP; + ret = -EOPNOTSUPP; + goto out; } if (hwpec) /* enable/disable hardware PEC */ @@ -796,11 +810,11 @@ static s32 i801_access(struct i2c_adapter *adap, u16 addr, ~(SMBAUXCTL_CRC | SMBAUXCTL_E32B), SMBAUXCTL(priv)); if (block) - return ret; + goto out; if (ret) - return ret; + goto out; if ((read_write == I2C_SMBUS_WRITE) || (xact == I801_QUICK)) - return 0; + goto out; switch (xact & 0x7f) { case I801_BYTE: /* Result put in SMBHSTDAT0 */ @@ -812,7 +826,10 @@ static s32 i801_access(struct i2c_adapter *adap, u16 addr, (inb_p(SMBHSTDAT1(priv)) << 8); break; } - return 0; + +out: + mutex_unlock(&priv->acpi_lock); + return ret; } @@ -1249,6 +1266,72 @@ static void i801_add_tco(struct i801_priv *priv) priv->tco_pdev = pdev; } +#ifdef CONFIG_ACPI +static acpi_status +i801_acpi_io_handler(u32 function, acpi_physical_address address, u32 bits, + u64 *value, void *handler_context, void *region_context) +{ + struct i801_priv *priv = handler_context; + struct pci_dev *pdev = priv->pci_dev; + acpi_status status; + + /* + * Once BIOS AML code touches the OpRegion we warn and inhibit any + * further access from the driver itself. This device is now owned + * by the system firmware. + */ + mutex_lock(&priv->acpi_lock); + + if (!priv->acpi_reserved) { + priv->acpi_reserved = true; + + dev_warn(&pdev->dev, "BIOS is accessing SMBus registers\n"); + dev_warn(&pdev->dev, "Driver SMBus register access inhibited\n"); + } + + if ((function & ACPI_IO_MASK) == ACPI_READ) + status = acpi_os_read_port(address, (u32 *)value, bits); + else + status = acpi_os_write_port(address, (u32)*value, bits); + + mutex_unlock(&priv->acpi_lock); + + return status; +} + +static int i801_acpi_probe(struct i801_priv *priv) +{ + struct acpi_device *adev; + acpi_status status; + + adev = ACPI_COMPANION(&priv->pci_dev->dev); + if (adev) { + status = acpi_install_address_space_handler(adev->handle, + ACPI_ADR_SPACE_SYSTEM_IO, i801_acpi_io_handler, + NULL, priv); + if (ACPI_SUCCESS(status)) + return 0; + } + + return acpi_check_resource_conflict(&priv->pci_dev->resource[SMBBAR]); +} + +static void i801_acpi_remove(struct i801_priv *priv) +{ + struct acpi_device *adev; + + adev = ACPI_COMPANION(&priv->pci_dev->dev); + if (!adev) + return; + + acpi_remove_address_space_handler(adev->handle, + ACPI_ADR_SPACE_SYSTEM_IO, i801_acpi_io_handler); +} +#else +static inline int i801_acpi_probe(struct i801_priv *priv) { return 0; } +static inline void i801_acpi_remove(struct i801_priv *priv) { } +#endif + static int i801_probe(struct pci_dev *dev, const struct pci_device_id *id) { unsigned char temp; @@ -1266,6 +1349,7 @@ static int i801_probe(struct pci_dev *dev, const struct pci_device_id *id) priv->adapter.dev.parent = &dev->dev; ACPI_COMPANION_SET(&priv->adapter.dev, ACPI_COMPANION(&dev->dev)); priv->adapter.retries = 3; + mutex_init(&priv->acpi_lock); priv->pci_dev = dev; switch (dev->device) { @@ -1328,10 +1412,8 @@ static int i801_probe(struct pci_dev *dev, const struct pci_device_id *id) return -ENODEV; } - err = acpi_check_resource_conflict(&dev->resource[SMBBAR]); - if (err) { + if (i801_acpi_probe(priv)) return -ENODEV; - } err = pcim_iomap_regions(dev, 1 << SMBBAR, dev_driver_string(&dev->dev)); @@ -1340,6 +1422,7 @@ static int i801_probe(struct pci_dev *dev, const struct pci_device_id *id) "Failed to request SMBus region 0x%lx-0x%Lx\n", priv->smba, (unsigned long long)pci_resource_end(dev, SMBBAR)); + i801_acpi_remove(priv); return err; } @@ -1404,6 +1487,7 @@ static int i801_probe(struct pci_dev *dev, const struct pci_device_id *id) err = i2c_add_adapter(&priv->adapter); if (err) { dev_err(&dev->dev, "Failed to add SMBus adapter\n"); + i801_acpi_remove(priv); return err; } @@ -1422,6 +1506,7 @@ static void i801_remove(struct pci_dev *dev) i801_del_mux(priv); i2c_del_adapter(&priv->adapter); + i801_acpi_remove(priv); pci_write_config_byte(dev, SMBHSTCFG, priv->original_hstcfg); platform_device_unregister(priv->tco_pdev); diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c index db760e84119f..b8df0f5e8c25 100644 --- a/drivers/net/bonding/bond_netlink.c +++ b/drivers/net/bonding/bond_netlink.c @@ -446,7 +446,11 @@ static int bond_newlink(struct net *src_net, struct net_device *bond_dev, if (err < 0) return err; - return register_netdevice(bond_dev); + err = register_netdevice(bond_dev); + + netif_carrier_off(bond_dev); + + return err; } static size_t bond_get_size(const struct net_device *bond_dev) diff --git a/drivers/net/ethernet/broadcom/bgmac.c b/drivers/net/ethernet/broadcom/bgmac.c index 38db2e4d7d54..832401b41b98 100644 --- a/drivers/net/ethernet/broadcom/bgmac.c +++ b/drivers/net/ethernet/broadcom/bgmac.c @@ -231,7 +231,7 @@ err_dma: dma_unmap_single(dma_dev, slot->dma_addr, skb_headlen(skb), DMA_TO_DEVICE); - while (i > 0) { + while (i-- > 0) { int index = (ring->end + i) % BGMAC_TX_RING_SLOTS; struct bgmac_slot_info *slot = &ring->slots[index]; u32 ctl1 = le32_to_cpu(ring->cpu_base[index].ctl1); diff --git a/drivers/net/ethernet/qlogic/qed/qed_spq.c b/drivers/net/ethernet/qlogic/qed/qed_spq.c index 89469d5aae25..40e6f6c11f20 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_spq.c +++ b/drivers/net/ethernet/qlogic/qed/qed_spq.c @@ -791,13 +791,12 @@ int qed_spq_completion(struct qed_hwfn *p_hwfn, * in a bitmap and increasing the chain consumer only * for the first successive completed entries. */ - bitmap_set(p_spq->p_comp_bitmap, pos, SPQ_RING_SIZE); + __set_bit(pos, p_spq->p_comp_bitmap); while (test_bit(p_spq->comp_bitmap_idx, p_spq->p_comp_bitmap)) { - bitmap_clear(p_spq->p_comp_bitmap, - p_spq->comp_bitmap_idx, - SPQ_RING_SIZE); + __clear_bit(p_spq->comp_bitmap_idx, + p_spq->p_comp_bitmap); p_spq->comp_bitmap_idx++; qed_chain_return_produced(&p_spq->chain); } diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 8f3c55d03d5d..f58858b7972c 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -914,7 +914,6 @@ static struct sk_buff *macsec_decrypt(struct sk_buff *skb, } macsec_skb_cb(skb)->req = req; - macsec_skb_cb(skb)->rx_sa = rx_sa; skb->dev = dev; aead_request_set_callback(req, 0, macsec_decrypt_done, skb); @@ -1141,6 +1140,8 @@ static rx_handler_result_t macsec_handle_frame(struct sk_buff **pskb) } } + macsec_skb_cb(skb)->rx_sa = rx_sa; + /* Disabled && !changed text => skip validation */ if (hdr->tci_an & MACSEC_TCI_C || secy->validate_frames != MACSEC_VALIDATE_DISABLED) diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c index f572b31a2b20..9ab88e1ed394 100644 --- a/drivers/net/ppp/ppp_generic.c +++ b/drivers/net/ppp/ppp_generic.c @@ -2404,8 +2404,6 @@ ppp_unregister_channel(struct ppp_channel *chan) spin_lock_bh(&pn->all_channels_lock); list_del(&pch->list); spin_unlock_bh(&pn->all_channels_lock); - put_net(pch->chan_net); - pch->chan_net = NULL; pch->file.dead = 1; wake_up_interruptible(&pch->file.rwait); @@ -2999,6 +2997,9 @@ ppp_disconnect_channel(struct channel *pch) */ static void ppp_destroy_channel(struct channel *pch) { + put_net(pch->chan_net); + pch->chan_net = NULL; + atomic_dec(&channel_count); if (!pch->file.dead) { diff --git a/drivers/nvdimm/pfn.h b/drivers/nvdimm/pfn.h index 8e343a3ca873..9d2704c83fa7 100644 --- a/drivers/nvdimm/pfn.h +++ b/drivers/nvdimm/pfn.h @@ -33,7 +33,9 @@ struct nd_pfn_sb { /* minor-version-1 additions for section alignment */ __le32 start_pad; __le32 end_trunc; - u8 padding[4004]; + /* minor-version-2 record the base alignment of the mapping */ + __le32 align; + u8 padding[4000]; __le64 checksum; }; diff --git a/drivers/nvdimm/pfn_devs.c b/drivers/nvdimm/pfn_devs.c index e071e214feba..84f2372dd0bb 100644 --- a/drivers/nvdimm/pfn_devs.c +++ b/drivers/nvdimm/pfn_devs.c @@ -329,6 +329,8 @@ struct device *nd_pfn_create(struct nd_region *nd_region) int nd_pfn_validate(struct nd_pfn *nd_pfn) { u64 checksum, offset; + unsigned long align; + enum nd_pfn_mode mode; struct nd_namespace_io *nsio; struct nd_pfn_sb *pfn_sb = nd_pfn->pfn_sb; struct nd_namespace_common *ndns = nd_pfn->ndns; @@ -360,6 +362,9 @@ int nd_pfn_validate(struct nd_pfn *nd_pfn) pfn_sb->end_trunc = 0; } + if (__le16_to_cpu(pfn_sb->version_minor) < 2) + pfn_sb->align = 0; + switch (le32_to_cpu(pfn_sb->mode)) { case PFN_MODE_RAM: case PFN_MODE_PMEM: @@ -368,20 +373,50 @@ int nd_pfn_validate(struct nd_pfn *nd_pfn) return -ENXIO; } + align = le32_to_cpu(pfn_sb->align); + offset = le64_to_cpu(pfn_sb->dataoff); + if (align == 0) + align = 1UL << ilog2(offset); + mode = le32_to_cpu(pfn_sb->mode); + if (!nd_pfn->uuid) { - /* from probe we allocate */ + /* + * When probing a namepace via nd_pfn_probe() the uuid + * is NULL (see: nd_pfn_devinit()) we init settings from + * pfn_sb + */ nd_pfn->uuid = kmemdup(pfn_sb->uuid, 16, GFP_KERNEL); if (!nd_pfn->uuid) return -ENOMEM; + nd_pfn->align = align; + nd_pfn->mode = mode; } else { - /* from init we validate */ + /* + * When probing a pfn / dax instance we validate the + * live settings against the pfn_sb + */ if (memcmp(nd_pfn->uuid, pfn_sb->uuid, 16) != 0) return -ENODEV; + + /* + * If the uuid validates, but other settings mismatch + * return EINVAL because userspace has managed to change + * the configuration without specifying new + * identification. + */ + if (nd_pfn->align != align || nd_pfn->mode != mode) { + dev_err(&nd_pfn->dev, + "init failed, settings mismatch\n"); + dev_dbg(&nd_pfn->dev, "align: %lx:%lx mode: %d:%d\n", + nd_pfn->align, align, nd_pfn->mode, + mode); + return -EINVAL; + } } - if (nd_pfn->align > nvdimm_namespace_capacity(ndns)) { + if (align > nvdimm_namespace_capacity(ndns)) { dev_err(&nd_pfn->dev, "alignment: %lx exceeds capacity %llx\n", - nd_pfn->align, nvdimm_namespace_capacity(ndns)); + align, nvdimm_namespace_capacity(ndns)); return -EINVAL; } @@ -391,7 +426,6 @@ int nd_pfn_validate(struct nd_pfn *nd_pfn) * namespace has changed since the pfn superblock was * established. */ - offset = le64_to_cpu(pfn_sb->dataoff); nsio = to_nd_namespace_io(&ndns->dev); if (offset >= resource_size(&nsio->res)) { dev_err(&nd_pfn->dev, "pfn array size exceeds capacity of %s\n", @@ -399,10 +433,11 @@ int nd_pfn_validate(struct nd_pfn *nd_pfn) return -EBUSY; } - nd_pfn->align = 1UL << ilog2(offset); - if (!is_power_of_2(offset) || offset < PAGE_SIZE) { - dev_err(&nd_pfn->dev, "bad offset: %#llx dax disabled\n", - offset); + if ((align && !IS_ALIGNED(offset, align)) + || !IS_ALIGNED(offset, PAGE_SIZE)) { + dev_err(&nd_pfn->dev, + "bad offset: %#llx dax disabled align: %#lx\n", + offset, align); return -ENXIO; } diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c index 92f536596b24..368efac7a950 100644 --- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -426,9 +426,10 @@ static int nd_pfn_init(struct nd_pfn *nd_pfn) memcpy(pfn_sb->uuid, nd_pfn->uuid, 16); memcpy(pfn_sb->parent_uuid, nd_dev_to_uuid(&ndns->dev), 16); pfn_sb->version_major = cpu_to_le16(1); - pfn_sb->version_minor = cpu_to_le16(1); + pfn_sb->version_minor = cpu_to_le16(2); pfn_sb->start_pad = cpu_to_le32(start_pad); pfn_sb->end_trunc = cpu_to_le32(end_trunc); + pfn_sb->align = cpu_to_le32(nd_pfn->align); checksum = nd_sb_checksum((struct nd_gen_sb *) pfn_sb); pfn_sb->checksum = cpu_to_le64(checksum); @@ -501,7 +502,6 @@ static int __nvdimm_namespace_attach_pfn(struct nd_pfn *nd_pfn) pmem = dev_get_drvdata(dev); pmem->data_offset = le64_to_cpu(pfn_sb->dataoff); pmem->pfn_pad = start_pad + end_trunc; - nd_pfn->mode = le32_to_cpu(nd_pfn->pfn_sb->mode); if (nd_pfn->mode == PFN_MODE_RAM) { if (pmem->data_offset < SZ_8K) return -EINVAL; diff --git a/drivers/regulator/qcom_smd-regulator.c b/drivers/regulator/qcom_smd-regulator.c index 6c7fe4778793..7e156a0b65dd 100644 --- a/drivers/regulator/qcom_smd-regulator.c +++ b/drivers/regulator/qcom_smd-regulator.c @@ -140,7 +140,6 @@ static const struct regulator_ops rpm_smps_ldo_ops = { .enable = rpm_reg_enable, .disable = rpm_reg_disable, .is_enabled = rpm_reg_is_enabled, - .list_voltage = regulator_list_voltage_linear_range, .get_voltage = rpm_reg_get_voltage, .set_voltage = rpm_reg_set_voltage, diff --git a/drivers/staging/rdma/hfi1/ud.c b/drivers/staging/rdma/hfi1/ud.c index ae8a70f703eb..23e60feb81bb 100644 --- a/drivers/staging/rdma/hfi1/ud.c +++ b/drivers/staging/rdma/hfi1/ud.c @@ -678,8 +678,7 @@ void hfi1_ud_rcv(struct hfi1_packet *packet) u32 tlen = packet->tlen; struct rvt_qp *qp = packet->qp; bool has_grh = rcv_flags & HFI1_HAS_GRH; - bool sc4_bit = has_sc4_bit(packet); - u8 sc; + u8 sc5 = hdr2sc((struct hfi1_message_header *)hdr, packet->rhf); u32 bth1; int is_mcast; struct ib_grh *grh = NULL; @@ -697,10 +696,8 @@ void hfi1_ud_rcv(struct hfi1_packet *packet) */ struct hfi1_pportdata *ppd = ppd_from_ibp(ibp); u32 lqpn = be32_to_cpu(ohdr->bth[1]) & RVT_QPN_MASK; - u8 sl, sc5; + u8 sl; - sc5 = (be16_to_cpu(hdr->lrh[0]) >> 12) & 0xf; - sc5 |= sc4_bit; sl = ibp->sc_to_sl[sc5]; process_becn(ppd, sl, 0, lqpn, 0, IB_CC_SVCTYPE_UD); @@ -717,10 +714,6 @@ void hfi1_ud_rcv(struct hfi1_packet *packet) if (!is_mcast && (opcode != IB_OPCODE_CNP) && bth1 & HFI1_FECN_SMASK) { u16 slid = be16_to_cpu(hdr->lrh[3]); - u8 sc5; - - sc5 = (be16_to_cpu(hdr->lrh[0]) >> 12) & 0xf; - sc5 |= sc4_bit; return_cnp(ibp, qp, src_qp, pkey, dlid, slid, sc5, grh); } @@ -745,10 +738,6 @@ void hfi1_ud_rcv(struct hfi1_packet *packet) if (qp->ibqp.qp_num > 1) { struct hfi1_pportdata *ppd = ppd_from_ibp(ibp); u16 slid; - u8 sc5; - - sc5 = (be16_to_cpu(hdr->lrh[0]) >> 12) & 0xf; - sc5 |= sc4_bit; slid = be16_to_cpu(hdr->lrh[3]); if (unlikely(rcv_pkey_check(ppd, pkey, sc5, slid))) { @@ -790,10 +779,6 @@ void hfi1_ud_rcv(struct hfi1_packet *packet) /* Received on QP0, and so by definition, this is an SMP */ struct opa_smp *smp = (struct opa_smp *)data; u16 slid = be16_to_cpu(hdr->lrh[3]); - u8 sc5; - - sc5 = (be16_to_cpu(hdr->lrh[0]) >> 12) & 0xf; - sc5 |= sc4_bit; if (opa_smp_check(ibp, pkey, sc5, qp, slid, smp)) goto drop; @@ -890,9 +875,7 @@ void hfi1_ud_rcv(struct hfi1_packet *packet) } wc.slid = be16_to_cpu(hdr->lrh[3]); - sc = (be16_to_cpu(hdr->lrh[0]) >> 12) & 0xf; - sc |= sc4_bit; - wc.sl = ibp->sc_to_sl[sc]; + wc.sl = ibp->sc_to_sl[sc5]; /* * Save the LMC lower bits if the destination LID is a unicast LID. diff --git a/drivers/staging/rdma/hfi1/verbs_txreq.c b/drivers/staging/rdma/hfi1/verbs_txreq.c index bc95c4112c61..d8fb056526f8 100644 --- a/drivers/staging/rdma/hfi1/verbs_txreq.c +++ b/drivers/staging/rdma/hfi1/verbs_txreq.c @@ -92,11 +92,10 @@ void hfi1_put_txreq(struct verbs_txreq *tx) struct verbs_txreq *__get_txreq(struct hfi1_ibdev *dev, struct rvt_qp *qp) + __must_hold(&qp->s_lock) { struct verbs_txreq *tx = ERR_PTR(-EBUSY); - unsigned long flags; - spin_lock_irqsave(&qp->s_lock, flags); write_seqlock(&dev->iowait_lock); if (ib_rvt_state_ops[qp->state] & RVT_PROCESS_RECV_OK) { struct hfi1_qp_priv *priv; @@ -116,7 +115,6 @@ struct verbs_txreq *__get_txreq(struct hfi1_ibdev *dev, } out: write_sequnlock(&dev->iowait_lock); - spin_unlock_irqrestore(&qp->s_lock, flags); return tx; } diff --git a/drivers/staging/rdma/hfi1/verbs_txreq.h b/drivers/staging/rdma/hfi1/verbs_txreq.h index 1cf69b2fe4a5..a1d6e0807f97 100644 --- a/drivers/staging/rdma/hfi1/verbs_txreq.h +++ b/drivers/staging/rdma/hfi1/verbs_txreq.h @@ -73,6 +73,7 @@ struct verbs_txreq *__get_txreq(struct hfi1_ibdev *dev, static inline struct verbs_txreq *get_txreq(struct hfi1_ibdev *dev, struct rvt_qp *qp) + __must_hold(&qp->slock) { struct verbs_txreq *tx; struct hfi1_qp_priv *priv = qp->priv; diff --git a/drivers/tty/serial/mvebu-uart.c b/drivers/tty/serial/mvebu-uart.c index 0ff27818bb87..25b9f178c8d3 100644 --- a/drivers/tty/serial/mvebu-uart.c +++ b/drivers/tty/serial/mvebu-uart.c @@ -299,6 +299,8 @@ static int mvebu_uart_startup(struct uart_port *port) static void mvebu_uart_shutdown(struct uart_port *port) { writel(0, port->membase + UART_CTRL); + + free_irq(port->irq, port); } static void mvebu_uart_set_termios(struct uart_port *port, diff --git a/fs/dcache.c b/fs/dcache.c index 44008e3fafc4..5612631b7b46 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -578,7 +578,6 @@ static struct dentry *dentry_kill(struct dentry *dentry) failed: spin_unlock(&dentry->d_lock); - cpu_relax(); return dentry; /* try again with same dentry */ } @@ -752,6 +751,8 @@ void dput(struct dentry *dentry) return; repeat: + might_sleep(); + rcu_read_lock(); if (likely(fast_dput(dentry))) { rcu_read_unlock(); @@ -783,8 +784,10 @@ repeat: kill_it: dentry = dentry_kill(dentry); - if (dentry) + if (dentry) { + cond_resched(); goto repeat; + } } EXPORT_SYMBOL(dput); diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index fe1f50fe764f..f97110461c19 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -208,6 +208,9 @@ static int ext4_init_block_bitmap(struct super_block *sb, memset(bh->b_data, 0, sb->s_blocksize); bit_max = ext4_num_base_meta_clusters(sb, block_group); + if ((bit_max >> 3) >= bh->b_size) + return -EFSCORRUPTED; + for (bit = 0; bit < bit_max; bit++) ext4_set_bit(bit, bh->b_data); diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index de692b91c166..8211698600c2 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -376,9 +376,13 @@ static int ext4_valid_extent(struct inode *inode, struct ext4_extent *ext) ext4_fsblk_t block = ext4_ext_pblock(ext); int len = ext4_ext_get_actual_len(ext); ext4_lblk_t lblock = le32_to_cpu(ext->ee_block); - ext4_lblk_t last = lblock + len - 1; - if (len == 0 || lblock > last) + /* + * We allow neither: + * - zero length + * - overflow/wrap-around + */ + if (lblock + len <= lblock) return 0; return ext4_data_block_valid(EXT4_SB(inode->i_sb), block, len); } diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 250c2df04a92..58197a7c3c2c 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -205,9 +205,9 @@ void ext4_evict_inode(struct inode *inode) * Note that directories do not have this problem because they * don't use page cache. */ - if (ext4_should_journal_data(inode) && - (S_ISLNK(inode->i_mode) || S_ISREG(inode->i_mode)) && - inode->i_ino != EXT4_JOURNAL_INO) { + if (inode->i_ino != EXT4_JOURNAL_INO && + ext4_should_journal_data(inode) && + (S_ISLNK(inode->i_mode) || S_ISREG(inode->i_mode))) { journal_t *journal = EXT4_SB(inode->i_sb)->s_journal; tid_t commit_tid = EXT4_I(inode)->i_datasync_tid; @@ -2741,13 +2741,36 @@ retry: done = true; } } - ext4_journal_stop(handle); + /* + * Caution: If the handle is synchronous, + * ext4_journal_stop() can wait for transaction commit + * to finish which may depend on writeback of pages to + * complete or on page lock to be released. In that + * case, we have to wait until after after we have + * submitted all the IO, released page locks we hold, + * and dropped io_end reference (for extent conversion + * to be able to complete) before stopping the handle. + */ + if (!ext4_handle_valid(handle) || handle->h_sync == 0) { + ext4_journal_stop(handle); + handle = NULL; + } /* Submit prepared bio */ ext4_io_submit(&mpd.io_submit); /* Unlock pages we didn't use */ mpage_release_unused_pages(&mpd, give_up_on_write); - /* Drop our io_end reference we got from init */ - ext4_put_io_end(mpd.io_submit.io_end); + /* + * Drop our io_end reference we got from init. We have + * to be careful and use deferred io_end finishing if + * we are still holding the transaction as we can + * release the last reference to io_end which may end + * up doing unwritten extent conversion. + */ + if (handle) { + ext4_put_io_end_defer(mpd.io_submit.io_end); + ext4_journal_stop(handle); + } else + ext4_put_io_end(mpd.io_submit.io_end); if (ret == -ENOSPC && sbi->s_journal) { /* diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 9d26fa2188f6..5f7ae0898ef7 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -2939,7 +2939,7 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac, ext4_error(sb, "Allocating blocks %llu-%llu which overlap " "fs metadata", block, block+len); /* File system mounted not to panic on error - * Fix the bitmap and repeat the block allocation + * Fix the bitmap and return EFSCORRUPTED * We leak some of the blocks here. */ ext4_lock_group(sb, ac->ac_b_ex.fe_group); @@ -2948,7 +2948,7 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac, ext4_unlock_group(sb, ac->ac_b_ex.fe_group); err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh); if (!err) - err = -EAGAIN; + err = -EFSCORRUPTED; goto out_err; } @@ -4513,18 +4513,7 @@ repeat: } if (likely(ac->ac_status == AC_STATUS_FOUND)) { *errp = ext4_mb_mark_diskspace_used(ac, handle, reserv_clstrs); - if (*errp == -EAGAIN) { - /* - * drop the reference that we took - * in ext4_mb_use_best_found - */ - ext4_mb_release_context(ac); - ac->ac_b_ex.fe_group = 0; - ac->ac_b_ex.fe_start = 0; - ac->ac_b_ex.fe_len = 0; - ac->ac_status = AC_STATUS_CONTINUE; - goto repeat; - } else if (*errp) { + if (*errp) { ext4_discard_allocated_blocks(ac); goto errout; } else { diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 304c712dbe12..7fca76b6cd61 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -2277,6 +2277,16 @@ static void ext4_orphan_cleanup(struct super_block *sb, while (es->s_last_orphan) { struct inode *inode; + /* + * We may have encountered an error during cleanup; if + * so, skip the rest. + */ + if (EXT4_SB(sb)->s_mount_state & EXT4_ERROR_FS) { + jbd_debug(1, "Skipping orphan recovery on fs with errors.\n"); + es->s_last_orphan = 0; + break; + } + inode = ext4_orphan_get(sb, le32_to_cpu(es->s_last_orphan)); if (IS_ERR(inode)) { es->s_last_orphan = 0; @@ -3415,6 +3425,13 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) goto failed_mount; } + if (le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks) > (blocksize / 4)) { + ext4_msg(sb, KERN_ERR, + "Number of reserved GDT blocks insanely large: %d", + le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks)); + goto failed_mount; + } + if (sbi->s_mount_opt & EXT4_MOUNT_DAX) { if (blocksize != PAGE_SIZE) { ext4_msg(sb, KERN_ERR, diff --git a/fs/fuse/file.c b/fs/fuse/file.c index dcad5e210525..3c7675fa664f 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -417,6 +417,15 @@ static int fuse_flush(struct file *file, fl_owner_t id) fuse_sync_writes(inode); inode_unlock(inode); + if (test_bit(AS_ENOSPC, &file->f_mapping->flags) && + test_and_clear_bit(AS_ENOSPC, &file->f_mapping->flags)) + err = -ENOSPC; + if (test_bit(AS_EIO, &file->f_mapping->flags) && + test_and_clear_bit(AS_EIO, &file->f_mapping->flags)) + err = -EIO; + if (err) + return err; + req = fuse_get_req_nofail_nopages(fc, file); memset(&inarg, 0, sizeof(inarg)); inarg.fh = ff->fh; @@ -462,6 +471,21 @@ int fuse_fsync_common(struct file *file, loff_t start, loff_t end, goto out; fuse_sync_writes(inode); + + /* + * Due to implementation of fuse writeback + * filemap_write_and_wait_range() does not catch errors. + * We have to do this directly after fuse_sync_writes() + */ + if (test_bit(AS_ENOSPC, &file->f_mapping->flags) && + test_and_clear_bit(AS_ENOSPC, &file->f_mapping->flags)) + err = -ENOSPC; + if (test_bit(AS_EIO, &file->f_mapping->flags) && + test_and_clear_bit(AS_EIO, &file->f_mapping->flags)) + err = -EIO; + if (err) + goto out; + err = sync_inode_metadata(inode, 1); if (err) goto out; diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 1ce67668a8e1..d302a5fff9ba 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -926,7 +926,7 @@ static void fuse_send_init(struct fuse_conn *fc, struct fuse_req *req) arg->flags |= FUSE_ASYNC_READ | FUSE_POSIX_LOCKS | FUSE_ATOMIC_O_TRUNC | FUSE_EXPORT_SUPPORT | FUSE_BIG_WRITES | FUSE_DONT_MASK | FUSE_SPLICE_WRITE | FUSE_SPLICE_MOVE | FUSE_SPLICE_READ | - FUSE_FLOCK_LOCKS | FUSE_IOCTL_DIR | FUSE_AUTO_INVAL_DATA | + FUSE_FLOCK_LOCKS | FUSE_HAS_IOCTL_DIR | FUSE_AUTO_INVAL_DATA | FUSE_DO_READDIRPLUS | FUSE_READDIRPLUS_AUTO | FUSE_ASYNC_DIO | FUSE_WRITEBACK_CACHE | FUSE_NO_OPEN_SUPPORT; req->in.h.opcode = FUSE_INIT; diff --git a/fs/inode.c b/fs/inode.c index 721fa18ead59..fd832eba4596 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -344,7 +344,7 @@ EXPORT_SYMBOL(inc_nlink); void address_space_init_once(struct address_space *mapping) { memset(mapping, 0, sizeof(*mapping)); - INIT_RADIX_TREE(&mapping->page_tree, GFP_ATOMIC); + INIT_RADIX_TREE(&mapping->page_tree, GFP_ATOMIC | __GFP_ACCOUNT); spin_lock_init(&mapping->tree_lock); init_rwsem(&mapping->i_mmap_rwsem); INIT_LIST_HEAD(&mapping->private_list); diff --git a/fs/udf/super.c b/fs/udf/super.c index 36661acaf33b..5e2c8c814e1b 100644 --- a/fs/udf/super.c +++ b/fs/udf/super.c @@ -78,6 +78,15 @@ #define VSD_FIRST_SECTOR_OFFSET 32768 #define VSD_MAX_SECTOR_OFFSET 0x800000 +/* + * Maximum number of Terminating Descriptor / Logical Volume Integrity + * Descriptor redirections. The chosen numbers are arbitrary - just that we + * hopefully don't limit any real use of rewritten inode on write-once media + * but avoid looping for too long on corrupted media. + */ +#define UDF_MAX_TD_NESTING 64 +#define UDF_MAX_LVID_NESTING 1000 + enum { UDF_MAX_LINKS = 0xffff }; /* These are the "meat" - everything else is stuffing */ @@ -1541,42 +1550,52 @@ out_bh: } /* - * udf_load_logicalvolint - * + * Find the prevailing Logical Volume Integrity Descriptor. */ static void udf_load_logicalvolint(struct super_block *sb, struct kernel_extent_ad loc) { - struct buffer_head *bh = NULL; + struct buffer_head *bh, *final_bh; uint16_t ident; struct udf_sb_info *sbi = UDF_SB(sb); struct logicalVolIntegrityDesc *lvid; + int indirections = 0; + + while (++indirections <= UDF_MAX_LVID_NESTING) { + final_bh = NULL; + while (loc.extLength > 0 && + (bh = udf_read_tagged(sb, loc.extLocation, + loc.extLocation, &ident))) { + if (ident != TAG_IDENT_LVID) { + brelse(bh); + break; + } + + brelse(final_bh); + final_bh = bh; - while (loc.extLength > 0 && - (bh = udf_read_tagged(sb, loc.extLocation, - loc.extLocation, &ident)) && - ident == TAG_IDENT_LVID) { - sbi->s_lvid_bh = bh; - lvid = (struct logicalVolIntegrityDesc *)bh->b_data; + loc.extLength -= sb->s_blocksize; + loc.extLocation++; + } - if (lvid->nextIntegrityExt.extLength) - udf_load_logicalvolint(sb, - leea_to_cpu(lvid->nextIntegrityExt)); + if (!final_bh) + return; - if (sbi->s_lvid_bh != bh) - brelse(bh); - loc.extLength -= sb->s_blocksize; - loc.extLocation++; + brelse(sbi->s_lvid_bh); + sbi->s_lvid_bh = final_bh; + + lvid = (struct logicalVolIntegrityDesc *)final_bh->b_data; + if (lvid->nextIntegrityExt.extLength == 0) + return; + + loc = leea_to_cpu(lvid->nextIntegrityExt); } - if (sbi->s_lvid_bh != bh) - brelse(bh); + + udf_warn(sb, "Too many LVID indirections (max %u), ignoring.\n", + UDF_MAX_LVID_NESTING); + brelse(sbi->s_lvid_bh); + sbi->s_lvid_bh = NULL; } -/* - * Maximum number of Terminating Descriptor redirections. The chosen number is - * arbitrary - just that we hopefully don't limit any real use of rewritten - * inode on write-once media but avoid looping for too long on corrupted media. - */ -#define UDF_MAX_TD_NESTING 64 /* * Process a main/reserve volume descriptor sequence. diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 78181a88903b..54355a7e46de 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4156,6 +4156,13 @@ static inline void netif_keep_dst(struct net_device *dev) dev->priv_flags &= ~(IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM); } +/* return true if dev can't cope with mtu frames that need vlan tag insertion */ +static inline bool netif_reduces_vlan_mtu(struct net_device *dev) +{ + /* TODO: reserve and use an additional IFF bit, if we get more users */ + return dev->priv_flags & IFF_MACSEC; +} + extern struct pernet_operations __net_initdata loopback_net_ops; /* Logging, debugging and troubleshooting/diagnostic helpers. */ diff --git a/ipc/msg.c b/ipc/msg.c index 1471db9a7e61..c6521c205cb4 100644 --- a/ipc/msg.c +++ b/ipc/msg.c @@ -680,7 +680,7 @@ long do_msgsnd(int msqid, long mtype, void __user *mtext, rcu_read_lock(); ipc_lock_object(&msq->q_perm); - ipc_rcu_putref(msq, ipc_rcu_free); + ipc_rcu_putref(msq, msg_rcu_free); /* raced with RMID? */ if (!ipc_valid_object(&msq->q_perm)) { err = -EIDRM; diff --git a/ipc/sem.c b/ipc/sem.c index b3757ea0694b..5d2f875e8e2e 100644 --- a/ipc/sem.c +++ b/ipc/sem.c @@ -449,7 +449,7 @@ static inline struct sem_array *sem_obtain_object_check(struct ipc_namespace *ns static inline void sem_lock_and_putref(struct sem_array *sma) { sem_lock(sma, NULL, -1); - ipc_rcu_putref(sma, ipc_rcu_free); + ipc_rcu_putref(sma, sem_rcu_free); } static inline void sem_rmid(struct ipc_namespace *ns, struct sem_array *s) @@ -1392,7 +1392,7 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum, rcu_read_unlock(); sem_io = ipc_alloc(sizeof(ushort)*nsems); if (sem_io == NULL) { - ipc_rcu_putref(sma, ipc_rcu_free); + ipc_rcu_putref(sma, sem_rcu_free); return -ENOMEM; } @@ -1426,20 +1426,20 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum, if (nsems > SEMMSL_FAST) { sem_io = ipc_alloc(sizeof(ushort)*nsems); if (sem_io == NULL) { - ipc_rcu_putref(sma, ipc_rcu_free); + ipc_rcu_putref(sma, sem_rcu_free); return -ENOMEM; } } if (copy_from_user(sem_io, p, nsems*sizeof(ushort))) { - ipc_rcu_putref(sma, ipc_rcu_free); + ipc_rcu_putref(sma, sem_rcu_free); err = -EFAULT; goto out_free; } for (i = 0; i < nsems; i++) { if (sem_io[i] > SEMVMX) { - ipc_rcu_putref(sma, ipc_rcu_free); + ipc_rcu_putref(sma, sem_rcu_free); err = -ERANGE; goto out_free; } @@ -1731,7 +1731,7 @@ static struct sem_undo *find_alloc_undo(struct ipc_namespace *ns, int semid) /* step 2: allocate new undo structure */ new = kzalloc(sizeof(struct sem_undo) + sizeof(short)*nsems, GFP_KERNEL); if (!new) { - ipc_rcu_putref(sma, ipc_rcu_free); + ipc_rcu_putref(sma, sem_rcu_free); return ERR_PTR(-ENOMEM); } diff --git a/lib/radix-tree.c b/lib/radix-tree.c index 1624c4117961..9b9be3ffa1f6 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -228,10 +228,11 @@ radix_tree_node_alloc(struct radix_tree_root *root) /* * Even if the caller has preloaded, try to allocate from the - * cache first for the new node to get accounted. + * cache first for the new node to get accounted to the memory + * cgroup. */ ret = kmem_cache_alloc(radix_tree_node_cachep, - gfp_mask | __GFP_ACCOUNT | __GFP_NOWARN); + gfp_mask | __GFP_NOWARN); if (ret) goto out; @@ -254,8 +255,7 @@ radix_tree_node_alloc(struct radix_tree_root *root) kmemleak_update_trace(ret); goto out; } - ret = kmem_cache_alloc(radix_tree_node_cachep, - gfp_mask | __GFP_ACCOUNT); + ret = kmem_cache_alloc(radix_tree_node_cachep, gfp_mask); out: BUG_ON(radix_tree_is_indirect_ptr(ret)); return ret; @@ -302,6 +302,12 @@ static int __radix_tree_preload(gfp_t gfp_mask) struct radix_tree_node *node; int ret = -ENOMEM; + /* + * Nodes preloaded by one cgroup can be be used by another cgroup, so + * they should never be accounted to any particular memory cgroup. + */ + gfp_mask &= ~__GFP_ACCOUNT; + preempt_disable(); rtp = this_cpu_ptr(&radix_tree_preloads); while (rtp->nr < RADIX_TREE_PRELOAD_SIZE) { diff --git a/mm/memcontrol.c b/mm/memcontrol.c index bf860dbdd26e..eb2d761a83a2 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -4064,14 +4064,32 @@ static struct cftype mem_cgroup_legacy_files[] = { static DEFINE_IDR(mem_cgroup_idr); -static void mem_cgroup_id_get(struct mem_cgroup *memcg) +static void mem_cgroup_id_get_many(struct mem_cgroup *memcg, unsigned int n) { - atomic_inc(&memcg->id.ref); + atomic_add(n, &memcg->id.ref); } -static void mem_cgroup_id_put(struct mem_cgroup *memcg) +static struct mem_cgroup *mem_cgroup_id_get_online(struct mem_cgroup *memcg) { - if (atomic_dec_and_test(&memcg->id.ref)) { + while (!atomic_inc_not_zero(&memcg->id.ref)) { + /* + * The root cgroup cannot be destroyed, so it's refcount must + * always be >= 1. + */ + if (WARN_ON_ONCE(memcg == root_mem_cgroup)) { + VM_BUG_ON(1); + break; + } + memcg = parent_mem_cgroup(memcg); + if (!memcg) + memcg = root_mem_cgroup; + } + return memcg; +} + +static void mem_cgroup_id_put_many(struct mem_cgroup *memcg, unsigned int n) +{ + if (atomic_sub_and_test(n, &memcg->id.ref)) { idr_remove(&mem_cgroup_idr, memcg->id.id); memcg->id.id = 0; @@ -4080,6 +4098,16 @@ static void mem_cgroup_id_put(struct mem_cgroup *memcg) } } +static inline void mem_cgroup_id_get(struct mem_cgroup *memcg) +{ + mem_cgroup_id_get_many(memcg, 1); +} + +static inline void mem_cgroup_id_put(struct mem_cgroup *memcg) +{ + mem_cgroup_id_put_many(memcg, 1); +} + /** * mem_cgroup_from_id - look up a memcg from a memcg id * @id: the memcg id to look up @@ -4716,6 +4744,8 @@ static void __mem_cgroup_clear_mc(void) if (!mem_cgroup_is_root(mc.from)) page_counter_uncharge(&mc.from->memsw, mc.moved_swap); + mem_cgroup_id_put_many(mc.from, mc.moved_swap); + /* * we charged both to->memory and to->memsw, so we * should uncharge to->memory. @@ -4723,9 +4753,9 @@ static void __mem_cgroup_clear_mc(void) if (!mem_cgroup_is_root(mc.to)) page_counter_uncharge(&mc.to->memory, mc.moved_swap); - css_put_many(&mc.from->css, mc.moved_swap); + mem_cgroup_id_get_many(mc.to, mc.moved_swap); + css_put_many(&mc.to->css, mc.moved_swap); - /* we've already done css_get(mc.to) */ mc.moved_swap = 0; } memcg_oom_recover(from); @@ -5785,7 +5815,7 @@ subsys_initcall(mem_cgroup_init); */ void mem_cgroup_swapout(struct page *page, swp_entry_t entry) { - struct mem_cgroup *memcg; + struct mem_cgroup *memcg, *swap_memcg; unsigned short oldid; VM_BUG_ON_PAGE(PageLRU(page), page); @@ -5800,16 +5830,27 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry) if (!memcg) return; - mem_cgroup_id_get(memcg); - oldid = swap_cgroup_record(entry, mem_cgroup_id(memcg)); + /* + * In case the memcg owning these pages has been offlined and doesn't + * have an ID allocated to it anymore, charge the closest online + * ancestor for the swap instead and transfer the memory+swap charge. + */ + swap_memcg = mem_cgroup_id_get_online(memcg); + oldid = swap_cgroup_record(entry, mem_cgroup_id(swap_memcg)); VM_BUG_ON_PAGE(oldid, page); - mem_cgroup_swap_statistics(memcg, true); + mem_cgroup_swap_statistics(swap_memcg, true); page->mem_cgroup = NULL; if (!mem_cgroup_is_root(memcg)) page_counter_uncharge(&memcg->memory, 1); + if (memcg != swap_memcg) { + if (!mem_cgroup_is_root(swap_memcg)) + page_counter_charge(&swap_memcg->memsw, 1); + page_counter_uncharge(&memcg->memsw, 1); + } + /* * Interrupts should be disabled here because the caller holds the * mapping->tree_lock lock which is taken with interrupts-off. It is @@ -5848,11 +5889,14 @@ int mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry) if (!memcg) return 0; + memcg = mem_cgroup_id_get_online(memcg); + if (!mem_cgroup_is_root(memcg) && - !page_counter_try_charge(&memcg->swap, 1, &counter)) + !page_counter_try_charge(&memcg->swap, 1, &counter)) { + mem_cgroup_id_put(memcg); return -ENOMEM; + } - mem_cgroup_id_get(memcg); oldid = swap_cgroup_record(entry, mem_cgroup_id(memcg)); VM_BUG_ON_PAGE(oldid, page); mem_cgroup_swap_statistics(memcg, true); diff --git a/mm/mempool.c b/mm/mempool.c index 9b7a14a791cc..fd3a393b9eea 100644 --- a/mm/mempool.c +++ b/mm/mempool.c @@ -310,7 +310,7 @@ EXPORT_SYMBOL(mempool_resize); * returns NULL. Note that due to preallocation, this function * *never* fails when called from process contexts. (it might * fail if called from an IRQ context.) - * Note: neither __GFP_NOMEMALLOC nor __GFP_ZERO are supported. + * Note: using __GFP_ZERO is not supported. */ void *mempool_alloc(mempool_t *pool, gfp_t gfp_mask) { @@ -319,27 +319,16 @@ void *mempool_alloc(mempool_t *pool, gfp_t gfp_mask) wait_queue_t wait; gfp_t gfp_temp; - /* If oom killed, memory reserves are essential to prevent livelock */ - VM_WARN_ON_ONCE(gfp_mask & __GFP_NOMEMALLOC); - /* No element size to zero on allocation */ VM_WARN_ON_ONCE(gfp_mask & __GFP_ZERO); - might_sleep_if(gfp_mask & __GFP_DIRECT_RECLAIM); + gfp_mask |= __GFP_NOMEMALLOC; /* don't allocate emergency reserves */ gfp_mask |= __GFP_NORETRY; /* don't loop in __alloc_pages */ gfp_mask |= __GFP_NOWARN; /* failures are OK */ gfp_temp = gfp_mask & ~(__GFP_DIRECT_RECLAIM|__GFP_IO); repeat_alloc: - if (likely(pool->curr_nr)) { - /* - * Don't allocate from emergency reserves if there are - * elements available. This check is racy, but it will - * be rechecked each loop. - */ - gfp_temp |= __GFP_NOMEMALLOC; - } element = pool->alloc(gfp_temp, pool->pool_data); if (likely(element != NULL)) @@ -363,12 +352,11 @@ repeat_alloc: * We use gfp mask w/o direct reclaim or IO for the first round. If * alloc failed with that and @pool was empty, retry immediately. */ - if ((gfp_temp & ~__GFP_NOMEMALLOC) != gfp_mask) { + if (gfp_temp != gfp_mask) { spin_unlock_irqrestore(&pool->lock, flags); gfp_temp = gfp_mask; goto repeat_alloc; } - gfp_temp = gfp_mask; /* We must not sleep if !__GFP_DIRECT_RECLAIM */ if (!(gfp_mask & __GFP_DIRECT_RECLAIM)) { diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index e7e62570bdb8..3a573a2dcee2 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -146,10 +146,12 @@ static netdev_tx_t vlan_dev_hard_start_xmit(struct sk_buff *skb, static int vlan_dev_change_mtu(struct net_device *dev, int new_mtu) { - /* TODO: gotta make sure the underlying layer can handle it, - * maybe an IFF_VLAN_CAPABLE flag for devices? - */ - if (vlan_dev_priv(dev)->real_dev->mtu < new_mtu) + struct net_device *real_dev = vlan_dev_priv(dev)->real_dev; + unsigned int max_mtu = real_dev->mtu; + + if (netif_reduces_vlan_mtu(real_dev)) + max_mtu -= VLAN_HLEN; + if (max_mtu < new_mtu) return -ERANGE; dev->mtu = new_mtu; diff --git a/net/8021q/vlan_netlink.c b/net/8021q/vlan_netlink.c index c92b52f37d38..1270207f3d7c 100644 --- a/net/8021q/vlan_netlink.c +++ b/net/8021q/vlan_netlink.c @@ -118,6 +118,7 @@ static int vlan_newlink(struct net *src_net, struct net_device *dev, { struct vlan_dev_priv *vlan = vlan_dev_priv(dev); struct net_device *real_dev; + unsigned int max_mtu; __be16 proto; int err; @@ -144,9 +145,11 @@ static int vlan_newlink(struct net *src_net, struct net_device *dev, if (err < 0) return err; + max_mtu = netif_reduces_vlan_mtu(real_dev) ? real_dev->mtu - VLAN_HLEN : + real_dev->mtu; if (!tb[IFLA_MTU]) - dev->mtu = real_dev->mtu; - else if (dev->mtu > real_dev->mtu) + dev->mtu = max_mtu; + else if (dev->mtu > max_mtu) return -EINVAL; err = vlan_changelink(dev, tb, data); diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index 160797722228..b32f5a4750bf 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -213,6 +213,16 @@ drop: } EXPORT_SYMBOL_GPL(br_handle_frame_finish); +static void __br_handle_local_finish(struct sk_buff *skb) +{ + struct net_bridge_port *p = br_port_get_rcu(skb->dev); + u16 vid = 0; + + /* check if vlan is allowed, to avoid spoofing */ + if (p->flags & BR_LEARNING && br_should_learn(p, skb, &vid)) + br_fdb_update(p->br, p, eth_hdr(skb)->h_source, vid, false); +} + /* note: already called with rcu_read_lock */ static int br_handle_local_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { @@ -279,6 +289,14 @@ rx_handler_result_t br_handle_frame(struct sk_buff **pskb) case 0x01: /* IEEE MAC (Pause) */ goto drop; + case 0x0E: /* 802.1AB LLDP */ + fwd_mask |= p->br->group_fwd_mask; + if (fwd_mask & (1u << dest[5])) + goto forward; + *pskb = skb; + __br_handle_local_finish(skb); + return RX_HANDLER_PASS; + default: /* Allow selective forwarding for most other protocols */ fwd_mask |= p->br->group_fwd_mask; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index c124c3c12f7c..e2e78843301c 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -87,7 +87,7 @@ int sysctl_tcp_adv_win_scale __read_mostly = 1; EXPORT_SYMBOL(sysctl_tcp_adv_win_scale); /* rfc5961 challenge ack rate limiting */ -int sysctl_tcp_challenge_ack_limit = 100; +int sysctl_tcp_challenge_ack_limit = 1000; int sysctl_tcp_stdurg __read_mostly; int sysctl_tcp_rfc1337 __read_mostly; @@ -3423,6 +3423,23 @@ static int tcp_ack_update_window(struct sock *sk, const struct sk_buff *skb, u32 return flag; } +static bool __tcp_oow_rate_limited(struct net *net, int mib_idx, + u32 *last_oow_ack_time) +{ + if (*last_oow_ack_time) { + s32 elapsed = (s32)(tcp_time_stamp - *last_oow_ack_time); + + if (0 <= elapsed && elapsed < sysctl_tcp_invalid_ratelimit) { + NET_INC_STATS_BH(net, mib_idx); + return true; /* rate-limited: don't send yet! */ + } + } + + *last_oow_ack_time = tcp_time_stamp; + + return false; /* not rate-limited: go ahead, send dupack now! */ +} + /* Return true if we're currently rate-limiting out-of-window ACKs and * thus shouldn't send a dupack right now. We rate-limit dupacks in * response to out-of-window SYNs or ACKs to mitigate ACK loops or DoS @@ -3436,21 +3453,9 @@ bool tcp_oow_rate_limited(struct net *net, const struct sk_buff *skb, /* Data packets without SYNs are not likely part of an ACK loop. */ if ((TCP_SKB_CB(skb)->seq != TCP_SKB_CB(skb)->end_seq) && !tcp_hdr(skb)->syn) - goto not_rate_limited; - - if (*last_oow_ack_time) { - s32 elapsed = (s32)(tcp_time_stamp - *last_oow_ack_time); - - if (0 <= elapsed && elapsed < sysctl_tcp_invalid_ratelimit) { - NET_INC_STATS_BH(net, mib_idx); - return true; /* rate-limited: don't send yet! */ - } - } - - *last_oow_ack_time = tcp_time_stamp; + return false; -not_rate_limited: - return false; /* not rate-limited: go ahead, send dupack now! */ + return __tcp_oow_rate_limited(net, mib_idx, last_oow_ack_time); } /* RFC 5961 7 [ACK Throttling] */ @@ -3460,21 +3465,26 @@ static void tcp_send_challenge_ack(struct sock *sk, const struct sk_buff *skb) static u32 challenge_timestamp; static unsigned int challenge_count; struct tcp_sock *tp = tcp_sk(sk); - u32 now; + u32 count, now; /* First check our per-socket dupack rate limit. */ - if (tcp_oow_rate_limited(sock_net(sk), skb, - LINUX_MIB_TCPACKSKIPPEDCHALLENGE, - &tp->last_oow_ack_time)) + if (__tcp_oow_rate_limited(sock_net(sk), + LINUX_MIB_TCPACKSKIPPEDCHALLENGE, + &tp->last_oow_ack_time)) return; - /* Then check the check host-wide RFC 5961 rate limit. */ + /* Then check host-wide RFC 5961 rate limit. */ now = jiffies / HZ; if (now != challenge_timestamp) { + u32 half = (sysctl_tcp_challenge_ack_limit + 1) >> 1; + challenge_timestamp = now; - challenge_count = 0; + WRITE_ONCE(challenge_count, half + + prandom_u32_max(sysctl_tcp_challenge_ack_limit)); } - if (++challenge_count <= sysctl_tcp_challenge_ack_limit) { + count = READ_ONCE(challenge_count); + if (count > 0) { + WRITE_ONCE(challenge_count, count - 1); NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPCHALLENGEACK); tcp_send_ack(sk); } diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 79a03b87a771..7b8e903b2a97 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -236,7 +236,8 @@ void tcp_select_initial_window(int __space, __u32 mss, /* Set window scaling on max possible window * See RFC1323 for an explanation of the limit to 14 */ - space = max_t(u32, sysctl_tcp_rmem[2], sysctl_rmem_max); + space = max_t(u32, space, sysctl_tcp_rmem[2]); + space = max_t(u32, space, sysctl_rmem_max); space = min_t(u32, space, *window_clamp); while (space > 65535 && (*rcv_wscale) < 14) { space >>= 1; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 8ec4b3089e20..e3fc0cdf82a9 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -3563,6 +3563,10 @@ restart: if (state != INET6_IFADDR_STATE_DEAD) { __ipv6_ifa_notify(RTM_DELADDR, ifa); inet6addr_notifier_call_chain(NETDEV_DOWN, ifa); + } else { + if (idev->cnf.forwarding) + addrconf_leave_anycast(ifa); + addrconf_leave_solict(ifa->idev, &ifa->addr); } write_lock_bh(&idev->lock); diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c index 923abd6b3064..8d2f7c9b491d 100644 --- a/net/irda/af_irda.c +++ b/net/irda/af_irda.c @@ -1024,8 +1024,11 @@ static int irda_connect(struct socket *sock, struct sockaddr *uaddr, } /* Check if we have opened a local TSAP */ - if (!self->tsap) - irda_open_tsap(self, LSAP_ANY, addr->sir_name); + if (!self->tsap) { + err = irda_open_tsap(self, LSAP_ANY, addr->sir_name); + if (err) + goto out; + } /* Move to connecting socket, start sending Connect Requests */ sock->state = SS_CONNECTING; diff --git a/security/apparmor/apparmorfs.c b/security/apparmor/apparmorfs.c index ad4fa49ad1db..9068369f8a1b 100644 --- a/security/apparmor/apparmorfs.c +++ b/security/apparmor/apparmorfs.c @@ -331,6 +331,7 @@ static int aa_fs_seq_hash_show(struct seq_file *seq, void *v) seq_printf(seq, "%.2x", profile->hash[i]); seq_puts(seq, "\n"); } + aa_put_profile(profile); return 0; }