diff options
173 files changed, 3586 insertions, 3381 deletions
diff --git a/Documentation/ABI/testing/procfs-smaps_rollup b/Documentation/ABI/testing/procfs-smaps_rollup index 0a54ed0d63c9..274df44d8b1b 100644 --- a/Documentation/ABI/testing/procfs-smaps_rollup +++ b/Documentation/ABI/testing/procfs-smaps_rollup @@ -3,18 +3,28 @@ Date: August 2017 Contact: Daniel Colascione <dancol@google.com> Description: This file provides pre-summed memory information for a - process. The format is identical to /proc/pid/smaps, + process. The format is almost identical to /proc/pid/smaps, except instead of an entry for each VMA in a process, smaps_rollup has a single entry (tagged "[rollup]") for which each field is the sum of the corresponding fields from all the maps in /proc/pid/smaps. - For more details, see the procfs man page. + Additionally, the fields Pss_Anon, Pss_File and Pss_Shmem + are not present in /proc/pid/smaps. These fields represent + the sum of the Pss field of each type (anon, file, shmem). + For more details, see Documentation/filesystems/proc.txt + and the procfs man page. Typical output looks like this: 00100000-ff709000 ---p 00000000 00:00 0 [rollup] + Size: 1192 kB + KernelPageSize: 4 kB + MMUPageSize: 4 kB Rss: 884 kB Pss: 385 kB + Pss_Anon: 301 kB + Pss_File: 80 kB + Pss_Shmem: 4 kB Shared_Clean: 696 kB Shared_Dirty: 0 kB Private_Clean: 120 kB diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst index a5c845338d6d..a9548de56ac9 100644 --- a/Documentation/admin-guide/cgroup-v2.rst +++ b/Documentation/admin-guide/cgroup-v2.rst @@ -1146,6 +1146,11 @@ PAGE_SIZE multiple when read back. otherwise, a value change in this file generates a file modified event. + Note that all fields in this file are hierarchical and the + file modified event can be generated due to an event down the + hierarchy. For for the local events at the cgroup level see + memory.events.local. + low The number of times the cgroup is reclaimed due to high memory pressure even though its usage is under @@ -1185,6 +1190,11 @@ PAGE_SIZE multiple when read back. The number of processes belonging to this cgroup killed by any kind of OOM killer. + memory.events.local + Similar to memory.events but the fields in the file are local + to the cgroup i.e. not hierarchical. The file modified event + generated on this file reflects only the local events. + memory.stat A read-only flat-keyed file which exists on non-root cgroups. diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index f1c433daef6b..099c5a4be95b 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -805,12 +805,10 @@ tracking down these problems. debug_pagealloc= - [KNL] When CONFIG_DEBUG_PAGEALLOC is set, this - parameter enables the feature at boot time. In - default, it is disabled. We can avoid allocating huge - chunk of memory for debug pagealloc if we don't enable - it at boot time and the system will work mostly same - with the kernel built without CONFIG_DEBUG_PAGEALLOC. + [KNL] When CONFIG_DEBUG_PAGEALLOC is set, this parameter + enables the feature at boot time. By default, it is + disabled and the system will work mostly the same as a + kernel built without CONFIG_DEBUG_PAGEALLOC. on: enable the feature debugpat [X86] Enable PAT debugging @@ -1670,6 +1668,15 @@ initrd= [BOOT] Specify the location of the initial ramdisk + init_on_alloc= [MM] Fill newly allocated pages and heap objects with + zeroes. + Format: 0 | 1 + Default set by CONFIG_INIT_ON_ALLOC_DEFAULT_ON. + + init_on_free= [MM] Fill freed pages and heap objects with zeroes. + Format: 0 | 1 + Default set by CONFIG_INIT_ON_FREE_DEFAULT_ON. + init_pkru= [x86] Specify the default memory protection keys rights register contents for all processes. 0x55555554 by default (disallow access to all but pkey 0). Can diff --git a/Documentation/core-api/kernel-api.rst b/Documentation/core-api/kernel-api.rst index 824f24ccf401..08af5caf036d 100644 --- a/Documentation/core-api/kernel-api.rst +++ b/Documentation/core-api/kernel-api.rst @@ -54,7 +54,7 @@ The Linux kernel provides more basic utility functions. Bit Operations -------------- -.. kernel-doc:: arch/x86/include/asm/bitops.h +.. kernel-doc:: include/asm-generic/bitops-instrumented.h :internal: Bitmap Operations diff --git a/Documentation/dev-tools/kmemleak.rst b/Documentation/dev-tools/kmemleak.rst index e6f51260ff32..3621cd5e1eef 100644 --- a/Documentation/dev-tools/kmemleak.rst +++ b/Documentation/dev-tools/kmemleak.rst @@ -2,8 +2,8 @@ Kernel Memory Leak Detector =========================== Kmemleak provides a way of detecting possible kernel memory leaks in a -way similar to a tracing garbage collector -(https://en.wikipedia.org/wiki/Garbage_collection_%28computer_science%29#Tracing_garbage_collectors), +way similar to a `tracing garbage collector +<https://en.wikipedia.org/wiki/Tracing_garbage_collection>`_, with the difference that the orphan objects are not freed but only reported via /sys/kernel/debug/kmemleak. A similar method is used by the Valgrind tool (``memcheck --leak-check``) to detect the memory leaks in @@ -15,10 +15,13 @@ Usage CONFIG_DEBUG_KMEMLEAK in "Kernel hacking" has to be enabled. A kernel thread scans the memory every 10 minutes (by default) and prints the -number of new unreferenced objects found. To display the details of all -the possible memory leaks:: +number of new unreferenced objects found. If the ``debugfs`` isn't already +mounted, mount with:: # mount -t debugfs nodev /sys/kernel/debug/ + +To display the details of all the possible scanned memory leaks:: + # cat /sys/kernel/debug/kmemleak To trigger an intermediate memory scan:: @@ -72,6 +75,9 @@ If CONFIG_DEBUG_KMEMLEAK_DEFAULT_OFF are enabled, the kmemleak is disabled by default. Passing ``kmemleak=on`` on the kernel command line enables the function. +If you are getting errors like "Error while writing to stdout" or "write_loop: +Invalid argument", make sure kmemleak is properly enabled. + Basic Algorithm --------------- @@ -218,3 +224,37 @@ the pointer is calculated by other methods than the usual container_of macro or the pointer is stored in a location not scanned by kmemleak. Page allocations and ioremap are not tracked. + +Testing with kmemleak-test +-------------------------- + +To check if you have all set up to use kmemleak, you can use the kmemleak-test +module, a module that deliberately leaks memory. Set CONFIG_DEBUG_KMEMLEAK_TEST +as module (it can't be used as bult-in) and boot the kernel with kmemleak +enabled. Load the module and perform a scan with:: + + # modprobe kmemleak-test + # echo scan > /sys/kernel/debug/kmemleak + +Note that the you may not get results instantly or on the first scanning. When +kmemleak gets results, it'll log ``kmemleak: <count of leaks> new suspected +memory leaks``. Then read the file to see then:: + + # cat /sys/kernel/debug/kmemleak + unreferenced object 0xffff89862ca702e8 (size 32): + comm "modprobe", pid 2088, jiffies 4294680594 (age 375.486s) + hex dump (first 32 bytes): + 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b kkkkkkkkkkkkkkkk + 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b a5 kkkkkkkkkkkkkkk. + backtrace: + [<00000000e0a73ec7>] 0xffffffffc01d2036 + [<000000000c5d2a46>] do_one_initcall+0x41/0x1df + [<0000000046db7e0a>] do_init_module+0x55/0x200 + [<00000000542b9814>] load_module+0x203c/0x2480 + [<00000000c2850256>] __do_sys_finit_module+0xba/0xe0 + [<000000006564e7ef>] do_syscall_64+0x43/0x110 + [<000000007c873fa6>] entry_SYSCALL_64_after_hwframe+0x44/0xa9 + ... + +Removing the module with ``rmmod kmemleak_test`` should also trigger some +kmemleak results. diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt index a226061fa109..d750b6926899 100644 --- a/Documentation/filesystems/proc.txt +++ b/Documentation/filesystems/proc.txt @@ -154,9 +154,11 @@ Table 1-1: Process specific entries in /proc symbol the task is blocked in - or "0" if not blocked. pagemap Page table stack Report full stack trace, enable via CONFIG_STACKTRACE - smaps an extension based on maps, showing the memory consumption of + smaps An extension based on maps, showing the memory consumption of each mapping and flags associated with it - numa_maps an extension based on maps, showing the memory locality and + smaps_rollup Accumulated smaps stats for all mappings of the process. This + can be derived from smaps, but is faster and more convenient + numa_maps An extension based on maps, showing the memory locality and binding policy as well as mem usage (in pages) of each mapping. .............................................................................. @@ -366,7 +368,7 @@ Table 1-4: Contents of the stat files (as of 2.6.30-rc7) exit_code the thread's exit_code in the form reported by the waitpid system call .............................................................................. -The /proc/PID/maps file containing the currently mapped memory regions and +The /proc/PID/maps file contains the currently mapped memory regions and their access permissions. The format is: @@ -417,11 +419,14 @@ is not associated with a file: or if empty, the mapping is anonymous. The /proc/PID/smaps is an extension based on maps, showing the memory -consumption for each of the process's mappings. For each of mappings there -is a series of lines such as the following: +consumption for each of the process's mappings. For each mapping (aka Virtual +Memory Area, or VMA) there is a series of lines such as the following: 08048000-080bc000 r-xp 00000000 03:02 13130 /bin/bash + Size: 1084 kB +KernelPageSize: 4 kB +MMUPageSize: 4 kB Rss: 892 kB Pss: 374 kB Shared_Clean: 892 kB @@ -443,11 +448,14 @@ Locked: 0 kB THPeligible: 0 VmFlags: rd ex mr mw me dw -the first of these lines shows the same information as is displayed for the -mapping in /proc/PID/maps. The remaining lines show the size of the mapping -(size), the amount of the mapping that is currently resident in RAM (RSS), the -process' proportional share of this mapping (PSS), the number of clean and -dirty private pages in the mapping. +The first of these lines shows the same information as is displayed for the +mapping in /proc/PID/maps. Following lines show the size of the mapping +(size); the size of each page allocated when backing a VMA (KernelPageSize), +which is usually the same as the size in the page table entries; the page size +used by the MMU when backing a VMA (in most cases, the same as KernelPageSize); +the amount of the mapping that is currently resident in RAM (RSS); the +process' proportional share of this mapping (PSS); and the number of clean and +dirty shared and private pages in the mapping. The "proportional set size" (PSS) of a process is the count of pages it has in memory, where each page is divided by the number of processes sharing it. @@ -532,6 +540,19 @@ guarantees: 2) If there is something at a given vaddr during the entirety of the life of the smaps/maps walk, there will be some output for it. +The /proc/PID/smaps_rollup file includes the same fields as /proc/PID/smaps, +but their values are the sums of the corresponding values for all mappings of +the process. Additionally, it contains these fields: + +Pss_Anon +Pss_File +Pss_Shmem + +They represent the proportional shares of anonymous, file, and shmem pages, as +described for smaps above. These fields are omitted in smaps since each +mapping identifies the type (anon, file, or shmem) of all pages it contains. +Thus all information in smaps_rollup can be derived from smaps, but at a +significantly higher cost. The /proc/PID/clear_refs is used to reset the PG_Referenced and ACCESSED/YOUNG bits on both physical and virtual pages associated with a process, and the diff --git a/MAINTAINERS b/MAINTAINERS index 133ec3cc11ae..60218e6a60ec 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -11260,7 +11260,7 @@ F: include/uapi/linux/nfs* F: include/uapi/linux/sunrpc/ NILFS2 FILESYSTEM -M: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp> +M: Ryusuke Konishi <konishi.ryusuke@gmail.com> L: linux-nilfs@vger.kernel.org W: https://nilfs.sourceforge.io/ W: https://nilfs.osdn.jp/ diff --git a/arch/alpha/include/asm/pgalloc.h b/arch/alpha/include/asm/pgalloc.h index 02f9f91bb4f0..71ded3b7d82d 100644 --- a/arch/alpha/include/asm/pgalloc.h +++ b/arch/alpha/include/asm/pgalloc.h @@ -5,6 +5,8 @@ #include <linux/mm.h> #include <linux/mmzone.h> +#include <asm-generic/pgalloc.h> /* for pte_{alloc,free}_one */ + /* * Allocate and free page tables. The xxx_kernel() versions are * used to allocate a kernel page table - this turns on ASN bits @@ -41,7 +43,7 @@ pgd_free(struct mm_struct *mm, pgd_t *pgd) static inline pmd_t * pmd_alloc_one(struct mm_struct *mm, unsigned long address) { - pmd_t *ret = (pmd_t *)__get_free_page(GFP_KERNEL|__GFP_ZERO); + pmd_t *ret = (pmd_t *)__get_free_page(GFP_PGTABLE_USER); return ret; } @@ -51,42 +53,6 @@ pmd_free(struct mm_struct *mm, pmd_t *pmd) free_page((unsigned long)pmd); } -static inline pte_t * -pte_alloc_one_kernel(struct mm_struct *mm) -{ - pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_ZERO); - return pte; -} - -static inline void -pte_free_kernel(struct mm_struct *mm, pte_t *pte) -{ - free_page((unsigned long)pte); -} - -static inline pgtable_t -pte_alloc_one(struct mm_struct *mm) -{ - pte_t *pte = pte_alloc_one_kernel(mm); - struct page *page; - - if (!pte) - return NULL; - page = virt_to_page(pte); - if (!pgtable_page_ctor(page)) { - __free_page(page); - return NULL; - } - return page; -} - -static inline void -pte_free(struct mm_struct *mm, pgtable_t page) -{ - pgtable_page_dtor(page); - __free_page(page); -} - #define check_pgt_cache() do { } while (0) #endif /* _ALPHA_PGALLOC_H */ diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index d850feb5cc0a..2bf1ce39a96d 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -75,6 +75,7 @@ config ARM select HAVE_DYNAMIC_FTRACE_WITH_REGS if HAVE_DYNAMIC_FTRACE select HAVE_EFFICIENT_UNALIGNED_ACCESS if (CPU_V6 || CPU_V6K || CPU_V7) && MMU select HAVE_EXIT_THREAD + select HAVE_FAST_GUP if ARM_LPAE select HAVE_FTRACE_MCOUNT_RECORD if !XIP_KERNEL select HAVE_FUNCTION_GRAPH_TRACER if !THUMB2_KERNEL && !CC_IS_CLANG select HAVE_FUNCTION_TRACER if !XIP_KERNEL @@ -1622,16 +1623,9 @@ config ARCH_SPARSEMEM_ENABLE config ARCH_SPARSEMEM_DEFAULT def_bool ARCH_SPARSEMEM_ENABLE -config ARCH_SELECT_MEMORY_MODEL - def_bool ARCH_SPARSEMEM_ENABLE - config HAVE_ARCH_PFN_VALID def_bool ARCH_HAS_HOLES_MEMORYMODEL || !SPARSEMEM -config HAVE_GENERIC_GUP - def_bool y - depends on ARM_LPAE - config HIGHMEM bool "High Memory Support" depends on MMU diff --git a/arch/arm/include/asm/pgalloc.h b/arch/arm/include/asm/pgalloc.h index c038cff6fdd3..a2a68b751971 100644 --- a/arch/arm/include/asm/pgalloc.h +++ b/arch/arm/include/asm/pgalloc.h @@ -54,8 +54,6 @@ static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd) extern pgd_t *pgd_alloc(struct mm_struct *mm); extern void pgd_free(struct mm_struct *mm, pgd_t *pgd); -#define PGALLOC_GFP (GFP_KERNEL | __GFP_ZERO) - static inline void clean_pte_table(pte_t *pte) { clean_dcache_area(pte + PTE_HWTABLE_PTRS, PTE_HWTABLE_SIZE); @@ -77,54 +75,41 @@ static inline void clean_pte_table(pte_t *pte) * | h/w pt 1 | * +------------+ */ + +#define __HAVE_ARCH_PTE_ALLOC_ONE_KERNEL +#define __HAVE_ARCH_PTE_ALLOC_ONE +#include <asm-generic/pgalloc.h> + static inline pte_t * pte_alloc_one_kernel(struct mm_struct *mm) { - pte_t *pte; + pte_t *pte = __pte_alloc_one_kernel(mm); - pte = (pte_t *)__get_free_page(PGALLOC_GFP); if (pte) clean_pte_table(pte); return pte; } +#ifdef CONFIG_HIGHPTE +#define PGTABLE_HIGHMEM __GFP_HIGHMEM +#else +#define PGTABLE_HIGHMEM 0 +#endif + static inline pgtable_t pte_alloc_one(struct mm_struct *mm) { struct page *pte; -#ifdef CONFIG_HIGHPTE - pte = alloc_pages(PGALLOC_GFP | __GFP_HIGHMEM, 0); -#else - pte = alloc_pages(PGALLOC_GFP, 0); -#endif + pte = __pte_alloc_one(mm, GFP_PGTABLE_USER | PGTABLE_HIGHMEM); if (!pte) return NULL; if (!PageHighMem(pte)) clean_pte_table(page_address(pte)); - if (!pgtable_page_ctor(pte)) { - __free_page(pte); - return NULL; - } return pte; } -/* - * Free one PTE table. - */ -static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) -{ - if (pte) - free_page((unsigned long)pte); -} - -static inline void pte_free(struct mm_struct *mm, pgtable_t pte) -{ - pgtable_page_dtor(pte); - __free_page(pte); -} - static inline void __pmd_populate(pmd_t *pmdp, phys_addr_t pte, pmdval_t prot) { diff --git a/arch/arm/kernel/efi.c b/arch/arm/kernel/efi.c index ed005870671a..e57dbcc89123 100644 --- a/arch/arm/kernel/efi.c +++ b/arch/arm/kernel/efi.c @@ -8,8 +8,7 @@ #include <asm/mach/map.h> #include <asm/mmu_context.h> -static int __init set_permissions(pte_t *ptep, pgtable_t token, - unsigned long addr, void *data) +static int __init set_permissions(pte_t *ptep, unsigned long addr, void *data) { efi_memory_desc_t *md = data; pte_t pte = *ptep; diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index 439bb6a59a04..1fb5c0ca1ed8 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -493,8 +493,7 @@ void __init dma_contiguous_remap(void) } } -static int __dma_update_pte(pte_t *pte, pgtable_t token, unsigned long addr, - void *data) +static int __dma_update_pte(pte_t *pte, unsigned long addr, void *data) { struct page *page = virt_to_page(addr); pgprot_t prot = *(pgprot_t *)data; diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index 1aa2586fa597..d9a0038774a6 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -729,7 +729,7 @@ static void __init *early_alloc(unsigned long sz) static void *__init late_alloc(unsigned long sz) { - void *ptr = (void *)__get_free_pages(PGALLOC_GFP, get_order(sz)); + void *ptr = (void *)__get_free_pages(GFP_PGTABLE_KERNEL, get_order(sz)); if (!ptr || !pgtable_page_ctor(virt_to_page(ptr))) BUG(); diff --git a/arch/arm/mm/pageattr.c b/arch/arm/mm/pageattr.c index 0f5faf30d9bf..d546efad7e97 100644 --- a/arch/arm/mm/pageattr.c +++ b/arch/arm/mm/pageattr.c @@ -14,8 +14,7 @@ struct page_change_data { pgprot_t clear_mask; }; -static int change_page_range(pte_t *ptep, pgtable_t token, unsigned long addr, - void *data) +static int change_page_range(pte_t *ptep, unsigned long addr, void *data) { struct page_change_data *cdata = data; pte_t pte = *ptep; diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index c085aec9459b..a36ff61321ce 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -143,6 +143,7 @@ config ARM64 select HAVE_DMA_CONTIGUOUS select HAVE_DYNAMIC_FTRACE select HAVE_EFFICIENT_UNALIGNED_ACCESS + select HAVE_FAST_GUP select HAVE_FTRACE_MCOUNT_RECORD select HAVE_FUNCTION_TRACER select HAVE_FUNCTION_GRAPH_TRACER @@ -267,9 +268,6 @@ config ZONE_DMA32 bool "Support DMA32 zone" if EXPERT default y -config HAVE_GENERIC_GUP - def_bool y - config ARCH_ENABLE_MEMORY_HOTPLUG def_bool y diff --git a/arch/arm64/include/asm/pgalloc.h b/arch/arm64/include/asm/pgalloc.h index cdced518378d..14d0bc44d451 100644 --- a/arch/arm64/include/asm/pgalloc.h +++ b/arch/arm64/include/asm/pgalloc.h @@ -13,18 +13,23 @@ #include <asm/cacheflush.h> #include <asm/tlbflush.h> +#include <asm-generic/pgalloc.h> /* for pte_{alloc,free}_one */ + #define check_pgt_cache() do { } while (0) -#define PGALLOC_GFP (GFP_KERNEL | __GFP_ZERO) #define PGD_SIZE (PTRS_PER_PGD * sizeof(pgd_t)) #if CONFIG_PGTABLE_LEVELS > 2 static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr) { + gfp_t gfp = GFP_PGTABLE_USER; struct page *page; - page = alloc_page(PGALLOC_GFP); + if (mm == &init_mm) + gfp = GFP_PGTABLE_KERNEL; + + page = alloc_page(gfp); if (!page) return NULL; if (!pgtable_pmd_page_ctor(page)) { @@ -61,7 +66,7 @@ static inline void __pud_populate(pud_t *pudp, phys_addr_t pmdp, pudval_t prot) static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr) { - return (pud_t *)__get_free_page(PGALLOC_GFP); + return (pud_t *)__get_free_page(GFP_PGTABLE_USER); } static inline void pud_free(struct mm_struct *mm, pud_t *pudp) @@ -89,42 +94,6 @@ static inline void __pgd_populate(pgd_t *pgdp, phys_addr_t pudp, pgdval_t prot) extern pgd_t *pgd_alloc(struct mm_struct *mm); extern void pgd_free(struct mm_struct *mm, pgd_t *pgdp); -static inline pte_t * -pte_alloc_one_kernel(struct mm_struct *mm) -{ - return (pte_t *)__get_free_page(PGALLOC_GFP); -} - -static inline pgtable_t -pte_alloc_one(struct mm_struct *mm) -{ - struct page *pte; - - pte = alloc_pages(PGALLOC_GFP, 0); - if (!pte) - return NULL; - if (!pgtable_page_ctor(pte)) { - __free_page(pte); - return NULL; - } - return pte; -} - -/* - * Free a PTE table. - */ -static inline void pte_free_kernel(struct mm_struct *mm, pte_t *ptep) -{ - if (ptep) - free_page((unsigned long)ptep); -} - -static inline void pte_free(struct mm_struct *mm, pgtable_t pte) -{ - pgtable_page_dtor(pte); - __free_page(pte); -} - static inline void __pmd_populate(pmd_t *pmdp, phys_addr_t ptep, pmdval_t prot) { diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c index 3c33d0dd8e0e..d0cf596db82c 100644 --- a/arch/arm64/kernel/efi.c +++ b/arch/arm64/kernel/efi.c @@ -82,8 +82,7 @@ int __init efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md) return 0; } -static int __init set_permissions(pte_t *ptep, pgtable_t token, - unsigned long addr, void *data) +static int __init set_permissions(pte_t *ptep, unsigned long addr, void *data) { efi_memory_desc_t *md = data; pte_t pte = READ_ONCE(*ptep); diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index 7e541f947b4c..9c4bad7d7131 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -283,6 +283,11 @@ void __init setup_arch(char **cmdline_p) setup_machine_fdt(__fdt_pointer); + /* + * Initialise the static keys early as they may be enabled by the + * cpufeature code and early parameters. + */ + jump_label_init(); parse_early_param(); /* diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index 9286ee6749e8..ea90d3bd9253 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -420,11 +420,6 @@ void __init smp_cpus_done(unsigned int max_cpus) void __init smp_prepare_boot_cpu(void) { set_my_cpu_offset(per_cpu_offset(smp_processor_id())); - /* - * Initialise the static keys early as they may be enabled by the - * cpufeature code. - */ - jump_label_init(); cpuinfo_store_boot_cpu(); /* diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 3645f29bd814..1b49c08dfa2b 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -362,7 +362,7 @@ static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys, static phys_addr_t __pgd_pgtable_alloc(int shift) { - void *ptr = (void *)__get_free_page(PGALLOC_GFP); + void *ptr = (void *)__get_free_page(GFP_PGTABLE_KERNEL); BUG_ON(!ptr); /* Ensure the zeroed page is visible to the page table walker */ diff --git a/arch/arm64/mm/pageattr.c b/arch/arm64/mm/pageattr.c index fcdcf6cd7677..03c53f16ee77 100644 --- a/arch/arm64/mm/pageattr.c +++ b/arch/arm64/mm/pageattr.c @@ -19,8 +19,7 @@ struct page_change_data { bool rodata_full __ro_after_init = IS_ENABLED(CONFIG_RODATA_FULL_DEFAULT_ENABLED); -static int change_page_range(pte_t *ptep, pgtable_t token, unsigned long addr, - void *data) +static int change_page_range(pte_t *ptep, unsigned long addr, void *data) { struct page_change_data *cdata = data; pte_t pte = READ_ONCE(*ptep); diff --git a/arch/arm64/mm/pgd.c b/arch/arm64/mm/pgd.c index 9a0c7d5090d6..7548f9ca1f11 100644 --- a/arch/arm64/mm/pgd.c +++ b/arch/arm64/mm/pgd.c @@ -19,10 +19,12 @@ static struct kmem_cache *pgd_cache __ro_after_init; pgd_t *pgd_alloc(struct mm_struct *mm) { + gfp_t gfp = GFP_PGTABLE_USER; + if (PGD_SIZE == PAGE_SIZE) - return (pgd_t *)__get_free_page(PGALLOC_GFP); + return (pgd_t *)__get_free_page(gfp); else - return kmem_cache_alloc(pgd_cache, PGALLOC_GFP); + return kmem_cache_alloc(pgd_cache, gfp); } void pgd_free(struct mm_struct *mm, pgd_t *pgd) diff --git a/arch/csky/include/asm/pgalloc.h b/arch/csky/include/asm/pgalloc.h index d213bb47b717..98c5716708d6 100644 --- a/arch/csky/include/asm/pgalloc.h +++ b/arch/csky/include/asm/pgalloc.h @@ -8,6 +8,9 @@ #include <linux/mm.h> #include <linux/sched.h> +#define __HAVE_ARCH_PTE_ALLOC_ONE_KERNEL +#include <asm-generic/pgalloc.h> /* for pte_{alloc,free}_one */ + static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, pte_t *pte) { @@ -39,33 +42,6 @@ static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm) return pte; } -static inline struct page *pte_alloc_one(struct mm_struct *mm) -{ - struct page *pte; - - pte = alloc_pages(GFP_KERNEL | __GFP_ZERO, 0); - if (!pte) - return NULL; - - if (!pgtable_page_ctor(pte)) { - __free_page(pte); - return NULL; - } - - return pte; -} - -static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) -{ - free_pages((unsigned long)pte, PTE_ORDER); -} - -static inline void pte_free(struct mm_struct *mm, pgtable_t pte) -{ - pgtable_page_dtor(pte); - __free_pages(pte, PTE_ORDER); -} - static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) { free_pages((unsigned long)pgd, PGD_ORDER); diff --git a/arch/m68k/include/asm/sun3_pgalloc.h b/arch/m68k/include/asm/sun3_pgalloc.h index 1456c5eecbd9..1a8ddbd0d23c 100644 --- a/arch/m68k/include/asm/sun3_pgalloc.h +++ b/arch/m68k/include/asm/sun3_pgalloc.h @@ -13,55 +13,18 @@ #include <asm/tlb.h> +#include <asm-generic/pgalloc.h> /* for pte_{alloc,free}_one */ + extern const char bad_pmd_string[]; #define pmd_alloc_one(mm,address) ({ BUG(); ((pmd_t *)2); }) - -static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) -{ - free_page((unsigned long) pte); -} - -static inline void pte_free(struct mm_struct *mm, pgtable_t page) -{ - pgtable_page_dtor(page); - __free_page(page); -} - #define __pte_free_tlb(tlb,pte,addr) \ do { \ pgtable_page_dtor(pte); \ tlb_remove_page((tlb), pte); \ } while (0) -static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm) -{ - unsigned long page = __get_free_page(GFP_KERNEL); - - if (!page) - return NULL; - - memset((void *)page, 0, PAGE_SIZE); - return (pte_t *) (page); -} - -static inline pgtable_t pte_alloc_one(struct mm_struct *mm) -{ - struct page *page = alloc_pages(GFP_KERNEL, 0); - - if (page == NULL) - return NULL; - - clear_highpage(page); - if (!pgtable_page_ctor(page)) { - __free_page(page); - return NULL; - } - return page; - -} - static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, pte_t *pte) { pmd_val(*pmd) = __pa((unsigned long)pte); diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 70d3200476bf..7957d3457156 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -34,6 +34,7 @@ config MIPS select GENERIC_SCHED_CLOCK if !CAVIUM_OCTEON_SOC select GENERIC_SMP_IDLE_THREAD select GENERIC_TIME_VSYSCALL + select GUP_GET_PTE_LOW_HIGH if CPU_MIPS32 && PHYS_ADDR_T_64BIT select HANDLE_DOMAIN_IRQ select HAVE_ARCH_COMPILER_H select HAVE_ARCH_JUMP_LABEL @@ -52,6 +53,7 @@ config MIPS select HAVE_DMA_CONTIGUOUS select HAVE_DYNAMIC_FTRACE select HAVE_EXIT_THREAD + select HAVE_FAST_GUP select HAVE_FTRACE_MCOUNT_RECORD select HAVE_FUNCTION_GRAPH_TRACER select HAVE_FUNCTION_TRACER diff --git a/arch/mips/include/asm/pgalloc.h b/arch/mips/include/asm/pgalloc.h index 27808d9461f4..aa16b85ddffc 100644 --- a/arch/mips/include/asm/pgalloc.h +++ b/arch/mips/include/asm/pgalloc.h @@ -13,6 +13,8 @@ #include <linux/mm.h> #include <linux/sched.h> +#include <asm-generic/pgalloc.h> /* for pte_{alloc,free}_one */ + static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, pte_t *pte) { @@ -50,37 +52,6 @@ static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) free_pages((unsigned long)pgd, PGD_ORDER); } -static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm) -{ - return (pte_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, PTE_ORDER); -} - -static inline struct page *pte_alloc_one(struct mm_struct *mm) -{ - struct page *pte; - - pte = alloc_pages(GFP_KERNEL, PTE_ORDER); - if (!pte) - return NULL; - clear_highpage(pte); - if (!pgtable_page_ctor(pte)) { - __free_page(pte); - return NULL; - } - return pte; -} - -static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) -{ - free_pages((unsigned long)pte, PTE_ORDER); -} - -static inline void pte_free(struct mm_struct *mm, pgtable_t pte) -{ - pgtable_page_dtor(pte); - __free_pages(pte, PTE_ORDER); -} - #define __pte_free_tlb(tlb,pte,address) \ do { \ pgtable_page_dtor(pte); \ diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h index 4ccb465ef3f2..7d27194e3b45 100644 --- a/arch/mips/include/asm/pgtable.h +++ b/arch/mips/include/asm/pgtable.h @@ -20,6 +20,7 @@ #include <asm/cmpxchg.h> #include <asm/io.h> #include <asm/pgtable-bits.h> +#include <asm/cpu-features.h> struct mm_struct; struct vm_area_struct; @@ -626,6 +627,8 @@ static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ +#define gup_fast_permitted(start, end) (!cpu_has_dc_aliases) + #include <asm-generic/pgtable.h> /* diff --git a/arch/mips/mm/Makefile b/arch/mips/mm/Makefile index f34d7ff5eb60..1e8d335025d7 100644 --- a/arch/mips/mm/Makefile +++ b/arch/mips/mm/Makefile @@ -7,7 +7,6 @@ obj-y += cache.o obj-y += context.o obj-y += extable.o obj-y += fault.o -obj-y += gup.o obj-y += init.o obj-y += mmap.o obj-y += page.o diff --git a/arch/mips/mm/gup.c b/arch/mips/mm/gup.c deleted file mode 100644 index 4c2b4483683c..000000000000 --- a/arch/mips/mm/gup.c +++ /dev/null @@ -1,303 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Lockless get_user_pages_fast for MIPS - * - * Copyright (C) 2008 Nick Piggin - * Copyright (C) 2008 Novell Inc. - * Copyright (C) 2011 Ralf Baechle - */ -#include <linux/sched.h> -#include <linux/mm.h> -#include <linux/vmstat.h> -#include <linux/highmem.h> -#include <linux/swap.h> -#include <linux/hugetlb.h> - -#include <asm/cpu-features.h> -#include <asm/pgtable.h> - -static inline pte_t gup_get_pte(pte_t *ptep) -{ -#if defined(CONFIG_PHYS_ADDR_T_64BIT) && defined(CONFIG_CPU_MIPS32) - pte_t pte; - -retry: - pte.pte_low = ptep->pte_low; - smp_rmb(); - pte.pte_high = ptep->pte_high; - smp_rmb(); - if (unlikely(pte.pte_low != ptep->pte_low)) - goto retry; - - return pte; -#else - return READ_ONCE(*ptep); -#endif -} - -static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end, - int write, struct page **pages, int *nr) -{ - pte_t *ptep = pte_offset_map(&pmd, addr); - do { - pte_t pte = gup_get_pte(ptep); - struct page *page; - - if (!pte_present(pte) || - pte_special(pte) || (write && !pte_write(pte))) { - pte_unmap(ptep); - return 0; - } - VM_BUG_ON(!pfn_valid(pte_pfn(pte))); - page = pte_page(pte); - get_page(page); - SetPageReferenced(page); - pages[*nr] = page; - (*nr)++; - - } while (ptep++, addr += PAGE_SIZE, addr != end); - - pte_unmap(ptep - 1); - return 1; -} - -static inline void get_head_page_multiple(struct page *page, int nr) -{ - VM_BUG_ON(page != compound_head(page)); - VM_BUG_ON(page_count(page) == 0); - page_ref_add(page, nr); - SetPageReferenced(page); -} - -static int gup_huge_pmd(pmd_t pmd, unsigned long addr, unsigned long end, - int write, struct page **pages, int *nr) -{ - pte_t pte = *(pte_t *)&pmd; - struct page *head, *page; - int refs; - - if (write && !pte_write(pte)) - return 0; - /* hugepages are never "special" */ - VM_BUG_ON(pte_special(pte)); - VM_BUG_ON(!pfn_valid(pte_pfn(pte))); - - refs = 0; - head = pte_page(pte); - page = head + ((addr & ~PMD_MASK) >> PAGE_SHIFT); - do { - VM_BUG_ON(compound_head(page) != head); - pages[*nr] = page; - (*nr)++; - page++; - refs++; - } while (addr += PAGE_SIZE, addr != end); - - get_head_page_multiple(head, refs); - return 1; -} - -static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end, - int write, struct page **pages, int *nr) -{ - unsigned long next; - pmd_t *pmdp; - - pmdp = pmd_offset(&pud, addr); - do { - pmd_t pmd = *pmdp; - - next = pmd_addr_end(addr, end); - if (pmd_none(pmd)) - return 0; - if (unlikely(pmd_huge(pmd))) { - if (!gup_huge_pmd(pmd, addr, next, write, pages,nr)) - return 0; - } else { - if (!gup_pte_range(pmd, addr, next, write, pages,nr)) - return 0; - } - } while (pmdp++, addr = next, addr != end); - - return 1; -} - -static int gup_huge_pud(pud_t pud, unsigned long addr, unsigned long end, - int write, struct page **pages, int *nr) -{ - pte_t pte = *(pte_t *)&pud; - struct page *head, *page; - int refs; - - if (write && !pte_write(pte)) - return 0; - /* hugepages are never "special" */ - VM_BUG_ON(pte_special(pte)); - VM_BUG_ON(!pfn_valid(pte_pfn(pte))); - - refs = 0; - head = pte_page(pte); - page = head + ((addr & ~PUD_MASK) >> PAGE_SHIFT); - do { - VM_BUG_ON(compound_head(page) != head); - pages[*nr] = page; - (*nr)++; - page++; - refs++; - } while (addr += PAGE_SIZE, addr != end); - - get_head_page_multiple(head, refs); - return 1; -} - -static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end, - int write, struct page **pages, int *nr) -{ - unsigned long next; - pud_t *pudp; - - pudp = pud_offset(&pgd, addr); - do { - pud_t pud = *pudp; - - next = pud_addr_end(addr, end); - if (pud_none(pud)) - return 0; - if (unlikely(pud_huge(pud))) { - if (!gup_huge_pud(pud, addr, next, write, pages,nr)) - return 0; - } else { - if (!gup_pmd_range(pud, addr, next, write, pages,nr)) - return 0; - } - } while (pudp++, addr = next, addr != end); - - return 1; -} - -/* - * Like get_user_pages_fast() except its IRQ-safe in that it won't fall - * back to the regular GUP. - * Note a difference with get_user_pages_fast: this always returns the - * number of pages pinned, 0 if no pages were pinned. - */ -int __get_user_pages_fast(unsigned long start, int nr_pages, int write, - struct page **pages) -{ - struct mm_struct *mm = current->mm; - unsigned long addr, len, end; - unsigned long next; - unsigned long flags; - pgd_t *pgdp; - int nr = 0; - - start &= PAGE_MASK; - addr = start; - len = (unsigned long) nr_pages << PAGE_SHIFT; - end = start + len; - if (unlikely(!access_ok((void __user *)start, len))) - return 0; - - /* - * XXX: batch / limit 'nr', to avoid large irq off latency - * needs some instrumenting to determine the common sizes used by - * important workloads (eg. DB2), and whether limiting the batch - * size will decrease performance. - * - * It seems like we're in the clear for the moment. Direct-IO is - * the main guy that batches up lots of get_user_pages, and even - * they are limited to 64-at-a-time which is not so many. - */ - /* - * This doesn't prevent pagetable teardown, but does prevent - * the pagetables and pages from being freed. - * - * So long as we atomically load page table pointers versus teardown, - * we can follow the address down to the page and take a ref on it. - */ - local_irq_save(flags); - pgdp = pgd_offset(mm, addr); - do { - pgd_t pgd = *pgdp; - - next = pgd_addr_end(addr, end); - if (pgd_none(pgd)) - break; - if (!gup_pud_range(pgd, addr, next, write, pages, &nr)) - break; - } while (pgdp++, addr = next, addr != end); - local_irq_restore(flags); - - return nr; -} - -/** - * get_user_pages_fast() - pin user pages in memory - * @start: starting user address - * @nr_pages: number of pages from start to pin - * @gup_flags: flags modifying pin behaviour - * @pages: array that receives pointers to the pages pinned. - * Should be at least nr_pages long. - * - * Attempt to pin user pages in memory without taking mm->mmap_sem. - * If not successful, it will fall back to taking the lock and - * calling get_user_pages(). - * - * Returns number of pages pinned. This may be fewer than the number - * requested. If nr_pages is 0 or negative, returns 0. If no pages - * were pinned, returns -errno. - */ -int get_user_pages_fast(unsigned long start, int nr_pages, - unsigned int gup_flags, struct page **pages) -{ - struct mm_struct *mm = current->mm; - unsigned long addr, len, end; - unsigned long next; - pgd_t *pgdp; - int ret, nr = 0; - - start &= PAGE_MASK; - addr = start; - len = (unsigned long) nr_pages << PAGE_SHIFT; - - end = start + len; - if (end < start || cpu_has_dc_aliases) - goto slow_irqon; - - /* XXX: batch / limit 'nr' */ - local_irq_disable(); - pgdp = pgd_offset(mm, addr); - do { - pgd_t pgd = *pgdp; - - next = pgd_addr_end(addr, end); - if (pgd_none(pgd)) - goto slow; - if (!gup_pud_range(pgd, addr, next, gup_flags & FOLL_WRITE, - pages, &nr)) - goto slow; - } while (pgdp++, addr = next, addr != end); - local_irq_enable(); - - VM_BUG_ON(nr != (end - start) >> PAGE_SHIFT); - return nr; -slow: - local_irq_enable(); - -slow_irqon: - /* Try to get the remaining pages with get_user_pages */ - start += nr << PAGE_SHIFT; - pages += nr; - - ret = get_user_pages_unlocked(start, (end - start) >> PAGE_SHIFT, - pages, gup_flags); - - /* Have to be a bit careful with return values */ - if (nr > 0) { - if (ret < 0) - ret = nr; - else - ret += nr; - } - return ret; -} diff --git a/arch/nds32/include/asm/pgalloc.h b/arch/nds32/include/asm/pgalloc.h index 3cbc749c79aa..e78b43d8389f 100644 --- a/arch/nds32/include/asm/pgalloc.h +++ b/arch/nds32/include/asm/pgalloc.h @@ -9,6 +9,9 @@ #include <asm/tlbflush.h> #include <asm/proc-fns.h> +#define __HAVE_ARCH_PTE_ALLOC_ONE +#include <asm-generic/pgalloc.h> /* for pte_{alloc,free}_one */ + /* * Since we have only two-level page tables, these are trivial */ @@ -22,22 +25,11 @@ extern void pgd_free(struct mm_struct *mm, pgd_t * pgd); #define check_pgt_cache() do { } while (0) -static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm) -{ - pte_t *pte; - - pte = - (pte_t *) __get_free_page(GFP_KERNEL | __GFP_RETRY_MAYFAIL | - __GFP_ZERO); - - return pte; -} - static inline pgtable_t pte_alloc_one(struct mm_struct *mm) { pgtable_t pte; - pte = alloc_pages(GFP_KERNEL | __GFP_RETRY_MAYFAIL | __GFP_ZERO, 0); + pte = __pte_alloc_one(mm, GFP_PGTABLE_USER); if (pte) cpu_dcache_wb_page((unsigned long)page_address(pte)); @@ -45,21 +37,6 @@ static inline pgtable_t pte_alloc_one(struct mm_struct *mm) } /* - * Free one PTE table. - */ -static inline void pte_free_kernel(struct mm_struct *mm, pte_t * pte) -{ - if (pte) { - free_page((unsigned long)pte); - } -} - -static inline void pte_free(struct mm_struct *mm, pgtable_t pte) -{ - __free_page(pte); -} - -/* * Populate the pmdp entry with a pointer to the pte. This pmd is part * of the mm address space. * diff --git a/arch/nios2/include/asm/pgalloc.h b/arch/nios2/include/asm/pgalloc.h index 3a149ead1207..4bc8cf72067e 100644 --- a/arch/nios2/include/asm/pgalloc.h +++ b/arch/nios2/include/asm/pgalloc.h @@ -12,6 +12,8 @@ #include <linux/mm.h> +#include <asm-generic/pgalloc.h> /* for pte_{alloc,free}_one */ + static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, pte_t *pte) { @@ -37,41 +39,6 @@ static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) free_pages((unsigned long)pgd, PGD_ORDER); } -static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm) -{ - pte_t *pte; - - pte = (pte_t *) __get_free_pages(GFP_KERNEL|__GFP_ZERO, PTE_ORDER); - - return pte; -} - -static inline pgtable_t pte_alloc_one(struct mm_struct *mm) -{ - struct page *pte; - - pte = alloc_pages(GFP_KERNEL, PTE_ORDER); - if (pte) { - if (!pgtable_page_ctor(pte)) { - __free_page(pte); - return NULL; - } - clear_highpage(pte); - } - return pte; -} - -static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) -{ - free_pages((unsigned long)pte, PTE_ORDER); -} - -static inline void pte_free(struct mm_struct *mm, struct page *pte) -{ - pgtable_page_dtor(pte); - __free_pages(pte, PTE_ORDER); -} - #define __pte_free_tlb(tlb, pte, addr) \ do { \ pgtable_page_dtor(pte); \ diff --git a/arch/parisc/include/asm/pgalloc.h b/arch/parisc/include/asm/pgalloc.h index ea75cc966dae..4f2059a50fae 100644 --- a/arch/parisc/include/asm/pgalloc.h +++ b/arch/parisc/include/asm/pgalloc.h @@ -10,6 +10,8 @@ #include <asm/cache.h> +#include <asm-generic/pgalloc.h> /* for pte_{alloc,free}_one */ + /* Allocate the top level pgd (page directory) * * Here (for 64 bit kernels) we implement a Hybrid L2/L3 scheme: we @@ -122,37 +124,6 @@ pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, pte_t *pte) pmd_populate_kernel(mm, pmd, page_address(pte_page)) #define pmd_pgtable(pmd) pmd_page(pmd) -static inline pgtable_t -pte_alloc_one(struct mm_struct *mm) -{ - struct page *page = alloc_page(GFP_KERNEL|__GFP_ZERO); - if (!page) - return NULL; - if (!pgtable_page_ctor(page)) { - __free_page(page); - return NULL; - } - return page; -} - -static inline pte_t * -pte_alloc_one_kernel(struct mm_struct *mm) -{ - pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_ZERO); - return pte; -} - -static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) -{ - free_page((unsigned long)pte); -} - -static inline void pte_free(struct mm_struct *mm, struct page *pte) -{ - pgtable_page_dtor(pte); - pte_free_kernel(mm, page_address(pte)); -} - #define check_pgt_cache() do { } while (0) #endif diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 3b795a0cab62..24a41f919309 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -125,6 +125,7 @@ config PPC select ARCH_HAS_FORTIFY_SOURCE select ARCH_HAS_GCOV_PROFILE_ALL select ARCH_HAS_KCOV + select ARCH_HAS_HUGEPD if HUGETLB_PAGE select ARCH_HAS_MMIOWB if PPC64 select ARCH_HAS_PHYS_TO_DMA select ARCH_HAS_PMEM_API if PPC64 @@ -185,12 +186,12 @@ config PPC select HAVE_DYNAMIC_FTRACE_WITH_REGS if MPROFILE_KERNEL select HAVE_EBPF_JIT if PPC64 select HAVE_EFFICIENT_UNALIGNED_ACCESS if !(CPU_LITTLE_ENDIAN && POWER7_CPU) + select HAVE_FAST_GUP select HAVE_FTRACE_MCOUNT_RECORD select HAVE_FUNCTION_ERROR_INJECTION select HAVE_FUNCTION_GRAPH_TRACER select HAVE_FUNCTION_TRACER select HAVE_GCC_PLUGINS if GCC_VERSION >= 50200 # plugin support on gcc <= 5.1 is buggy on PPC - select HAVE_GENERIC_GUP select HAVE_HW_BREAKPOINT if PERF_EVENTS && (PPC_BOOK3S || PPC_8xx) select HAVE_IDE select HAVE_IOREMAP_PROT diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h index 3f53be60fb01..64145751b2fd 100644 --- a/arch/powerpc/include/asm/pgtable.h +++ b/arch/powerpc/include/asm/pgtable.h @@ -140,6 +140,20 @@ static inline void pte_frag_set(mm_context_t *ctx, void *p) } #endif +#ifdef CONFIG_PPC64 +#define is_ioremap_addr is_ioremap_addr +static inline bool is_ioremap_addr(const void *x) +{ +#ifdef CONFIG_MMU + unsigned long addr = (unsigned long)x; + + return addr >= IOREMAP_BASE && addr < IOREMAP_END; +#else + return false; +#endif +} +#endif /* CONFIG_PPC64 */ + #endif /* __ASSEMBLY__ */ #endif /* _ASM_POWERPC_PGTABLE_H */ diff --git a/arch/powerpc/kvm/book3s_xics.c b/arch/powerpc/kvm/book3s_xics.c index e8276161872e..381bf8dea193 100644 --- a/arch/powerpc/kvm/book3s_xics.c +++ b/arch/powerpc/kvm/book3s_xics.c @@ -827,7 +827,7 @@ static noinline int kvmppc_h_eoi(struct kvm_vcpu *vcpu, unsigned long xirr) * * Note: If EOI is incorrectly used by SW to lower the CPPR * value (ie more favored), we do not check for rejection of - * a pending interrupt, this is a SW error and PAPR sepcifies + * a pending interrupt, this is a SW error and PAPR specifies * that we don't have to deal with it. * * The sending of an EOI to the ICS is handled after the diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index b5d92dc32844..51716c11d0fb 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -511,13 +511,6 @@ retry: return page; } -static unsigned long hugepte_addr_end(unsigned long addr, unsigned long end, - unsigned long sz) -{ - unsigned long __boundary = (addr + sz) & ~(sz-1); - return (__boundary - 1 < end - 1) ? __boundary : end; -} - #ifdef CONFIG_PPC_MM_SLICES unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, @@ -665,68 +658,3 @@ void flush_dcache_icache_hugepage(struct page *page) } } } - -static int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr, - unsigned long end, int write, struct page **pages, int *nr) -{ - unsigned long pte_end; - struct page *head, *page; - pte_t pte; - int refs; - - pte_end = (addr + sz) & ~(sz-1); - if (pte_end < end) - end = pte_end; - - pte = READ_ONCE(*ptep); - - if (!pte_access_permitted(pte, write)) - return 0; - - /* hugepages are never "special" */ - VM_BUG_ON(!pfn_valid(pte_pfn(pte))); - - refs = 0; - head = pte_page(pte); - - page = head + ((addr & (sz-1)) >> PAGE_SHIFT); - do { - VM_BUG_ON(compound_head(page) != head); - pages[*nr] = page; - (*nr)++; - page++; - refs++; - } while (addr += PAGE_SIZE, addr != end); - - if (!page_cache_add_speculative(head, refs)) { - *nr -= refs; - return 0; - } - - if (unlikely(pte_val(pte) != pte_val(*ptep))) { - /* Could be optimized better */ - *nr -= refs; - while (refs--) - put_page(head); - return 0; - } - - return 1; -} - -int gup_huge_pd(hugepd_t hugepd, unsigned long addr, unsigned int pdshift, - unsigned long end, int write, struct page **pages, int *nr) -{ - pte_t *ptep; - unsigned long sz = 1UL << hugepd_shift(hugepd); - unsigned long next; - - ptep = hugepte_offset(hugepd, addr, pdshift); - do { - next = hugepte_addr_end(addr, end, sz); - if (!gup_hugepte(ptep, sz, addr, end, write, pages, nr)) - return 0; - } while (ptep++, addr = next, addr != end); - - return 1; -} diff --git a/arch/riscv/include/asm/pgalloc.h b/arch/riscv/include/asm/pgalloc.h index eb8b0195f27f..56a67d66f72f 100644 --- a/arch/riscv/include/asm/pgalloc.h +++ b/arch/riscv/include/asm/pgalloc.h @@ -10,6 +10,8 @@ #include <linux/mm.h> #include <asm/tlb.h> +#include <asm-generic/pgalloc.h> /* for pte_{alloc,free}_one */ + static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, pte_t *pte) { @@ -74,33 +76,6 @@ static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd) #endif /* __PAGETABLE_PMD_FOLDED */ -static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm) -{ - return (pte_t *)__get_free_page( - GFP_KERNEL | __GFP_RETRY_MAYFAIL | __GFP_ZERO); -} - -static inline struct page *pte_alloc_one(struct mm_struct *mm) -{ - struct page *pte; - - pte = alloc_page(GFP_KERNEL | __GFP_RETRY_MAYFAIL | __GFP_ZERO); - if (likely(pte != NULL)) - pgtable_page_ctor(pte); - return pte; -} - -static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) -{ - free_page((unsigned long)pte); -} - -static inline void pte_free(struct mm_struct *mm, pgtable_t pte) -{ - pgtable_page_dtor(pte); - __free_page(pte); -} - #define __pte_free_tlb(tlb, pte, buf) \ do { \ pgtable_page_dtor(pte); \ diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index fdb4246265a5..5d8570ed6cab 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -139,6 +139,7 @@ config S390 select HAVE_DMA_CONTIGUOUS select HAVE_DYNAMIC_FTRACE select HAVE_DYNAMIC_FTRACE_WITH_REGS + select HAVE_FAST_GUP select HAVE_EFFICIENT_UNALIGNED_ACCESS select HAVE_FENTRY select HAVE_FTRACE_MCOUNT_RECORD @@ -146,7 +147,6 @@ config S390 select HAVE_FUNCTION_TRACER select HAVE_FUTEX_CMPXCHG if FUTEX select HAVE_GCC_PLUGINS - select HAVE_GENERIC_GUP select HAVE_KERNEL_BZIP2 select HAVE_KERNEL_GZIP select HAVE_KERNEL_LZ4 @@ -641,9 +641,6 @@ config ARCH_SPARSEMEM_ENABLE config ARCH_SPARSEMEM_DEFAULT def_bool y -config ARCH_SELECT_MEMORY_MODEL - def_bool y - config ARCH_ENABLE_MEMORY_HOTPLUG def_bool y if SPARSEMEM diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 9f0195d5fa16..9b274fcaacb6 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -1270,14 +1270,8 @@ static inline pte_t *pte_offset(pmd_t *pmd, unsigned long address) #define pte_offset_map(pmd, address) pte_offset_kernel(pmd, address) #define pte_unmap(pte) do { } while (0) -static inline bool gup_fast_permitted(unsigned long start, int nr_pages) +static inline bool gup_fast_permitted(unsigned long start, unsigned long end) { - unsigned long len, end; - - len = (unsigned long) nr_pages << PAGE_SHIFT; - end = start + len; - if (end < start) - return false; return end <= current->mm->context.asce_limit; } #define gup_fast_permitted gup_fast_permitted diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index c7c99e18d5ff..31a7d12db705 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -15,6 +15,7 @@ config SUPERH select HAVE_ARCH_TRACEHOOK select HAVE_PERF_EVENTS select HAVE_DEBUG_BUGVERBOSE + select HAVE_FAST_GUP if MMU select ARCH_HAVE_CUSTOM_GPIO_H select ARCH_HAVE_NMI_SAFE_CMPXCHG if (GUSA_RB || CPU_SH4A) select ARCH_HAS_GCOV_PROFILE_ALL @@ -64,6 +65,7 @@ config SUPERH config SUPERH32 def_bool "$(ARCH)" = "sh" select ARCH_32BIT_OFF_T + select GUP_GET_PTE_LOW_HIGH if X2TLB select HAVE_KPROBES select HAVE_KRETPROBES select HAVE_IOREMAP_PROT if MMU && !X2TLB diff --git a/arch/sh/configs/hp6xx_defconfig b/arch/sh/configs/hp6xx_defconfig index 4dcf7f552582..91d43e2bffea 100644 --- a/arch/sh/configs/hp6xx_defconfig +++ b/arch/sh/configs/hp6xx_defconfig @@ -40,7 +40,6 @@ CONFIG_FB=y CONFIG_FIRMWARE_EDID=y CONFIG_FB_HIT=y CONFIG_FB_SH_MOBILE_LCDC=y -CONFIG_BACKLIGHT_LCD_SUPPORT=y CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_FONTS=y CONFIG_FONT_PEARL_8x8=y diff --git a/arch/sh/configs/sdk7786_defconfig b/arch/sh/configs/sdk7786_defconfig index 5209889765ad..49a29338789b 100644 --- a/arch/sh/configs/sdk7786_defconfig +++ b/arch/sh/configs/sdk7786_defconfig @@ -191,7 +191,6 @@ CONFIG_CONFIGFS_FS=y CONFIG_JFFS2_FS=m CONFIG_JFFS2_FS_XATTR=y CONFIG_UBIFS_FS=m -CONFIG_LOGFS=m CONFIG_CRAMFS=m CONFIG_SQUASHFS=m CONFIG_ROMFS_FS=m diff --git a/arch/sh/configs/sh2007_defconfig b/arch/sh/configs/sh2007_defconfig index a1cf6447dbb1..cbd6742eb423 100644 --- a/arch/sh/configs/sh2007_defconfig +++ b/arch/sh/configs/sh2007_defconfig @@ -85,7 +85,6 @@ CONFIG_WATCHDOG=y CONFIG_SH_WDT=y CONFIG_SSB=y CONFIG_FB=y -CONFIG_BACKLIGHT_LCD_SUPPORT=y # CONFIG_LCD_CLASS_DEVICE is not set CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y diff --git a/arch/sh/include/asm/io.h b/arch/sh/include/asm/io.h index c28e37a344ad..ac0561960c52 100644 --- a/arch/sh/include/asm/io.h +++ b/arch/sh/include/asm/io.h @@ -369,7 +369,11 @@ static inline int iounmap_fixed(void __iomem *addr) { return -EINVAL; } #define ioremap_nocache ioremap #define ioremap_uc ioremap -#define iounmap __iounmap + +static inline void iounmap(void __iomem *addr) +{ + __iounmap(addr); +} /* * Convert a physical pointer to a virtual kernel pointer for /dev/mem diff --git a/arch/sh/include/asm/pgtable-3level.h b/arch/sh/include/asm/pgtable-3level.h index 7d8587eb65ff..779260b721ca 100644 --- a/arch/sh/include/asm/pgtable-3level.h +++ b/arch/sh/include/asm/pgtable-3level.h @@ -38,6 +38,9 @@ static inline unsigned long pud_page_vaddr(pud_t pud) return pud_val(pud); } +/* only used by the stubbed out hugetlb gup code, should never be called */ +#define pud_page(pud) NULL + #define pmd_index(address) (((address) >> PMD_SHIFT) & (PTRS_PER_PMD-1)) static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address) { diff --git a/arch/sh/include/asm/pgtable.h b/arch/sh/include/asm/pgtable.h index 3587103afe59..9085d1142fa3 100644 --- a/arch/sh/include/asm/pgtable.h +++ b/arch/sh/include/asm/pgtable.h @@ -149,6 +149,43 @@ extern void paging_init(void); extern void page_table_range_init(unsigned long start, unsigned long end, pgd_t *pgd); +static inline bool __pte_access_permitted(pte_t pte, u64 prot) +{ + return (pte_val(pte) & (prot | _PAGE_SPECIAL)) == prot; +} + +#ifdef CONFIG_X2TLB +static inline bool pte_access_permitted(pte_t pte, bool write) +{ + u64 prot = _PAGE_PRESENT; + + prot |= _PAGE_EXT(_PAGE_EXT_KERN_READ | _PAGE_EXT_USER_READ); + if (write) + prot |= _PAGE_EXT(_PAGE_EXT_KERN_WRITE | _PAGE_EXT_USER_WRITE); + return __pte_access_permitted(pte, prot); +} +#elif defined(CONFIG_SUPERH64) +static inline bool pte_access_permitted(pte_t pte, bool write) +{ + u64 prot = _PAGE_PRESENT | _PAGE_USER | _PAGE_READ; + + if (write) + prot |= _PAGE_WRITE; + return __pte_access_permitted(pte, prot); +} +#else +static inline bool pte_access_permitted(pte_t pte, bool write) +{ + u64 prot = _PAGE_PRESENT | _PAGE_USER; + + if (write) + prot |= _PAGE_RW; + return __pte_access_permitted(pte, prot); +} +#endif + +#define pte_access_permitted pte_access_permitted + /* arch/sh/mm/mmap.c */ #define HAVE_ARCH_UNMAPPED_AREA #define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN diff --git a/arch/sh/mm/Makefile b/arch/sh/mm/Makefile index fbe5e79751b3..5051b38fd5b6 100644 --- a/arch/sh/mm/Makefile +++ b/arch/sh/mm/Makefile @@ -17,7 +17,7 @@ cacheops-$(CONFIG_CPU_SHX3) += cache-shx3.o obj-y += $(cacheops-y) mmu-y := nommu.o extable_32.o -mmu-$(CONFIG_MMU) := extable_$(BITS).o fault.o gup.o ioremap.o kmap.o \ +mmu-$(CONFIG_MMU) := extable_$(BITS).o fault.o ioremap.o kmap.o \ pgtable.o tlbex_$(BITS).o tlbflush_$(BITS).o obj-y += $(mmu-y) diff --git a/arch/sh/mm/gup.c b/arch/sh/mm/gup.c deleted file mode 100644 index 277c882f7489..000000000000 --- a/arch/sh/mm/gup.c +++ /dev/null @@ -1,277 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Lockless get_user_pages_fast for SuperH - * - * Copyright (C) 2009 - 2010 Paul Mundt - * - * Cloned from the x86 and PowerPC versions, by: - * - * Copyright (C) 2008 Nick Piggin - * Copyright (C) 2008 Novell Inc. - */ -#include <linux/sched.h> -#include <linux/mm.h> -#include <linux/vmstat.h> -#include <linux/highmem.h> -#include <asm/pgtable.h> - -static inline pte_t gup_get_pte(pte_t *ptep) -{ -#ifndef CONFIG_X2TLB - return READ_ONCE(*ptep); -#else - /* - * With get_user_pages_fast, we walk down the pagetables without - * taking any locks. For this we would like to load the pointers - * atomically, but that is not possible with 64-bit PTEs. What - * we do have is the guarantee that a pte will only either go - * from not present to present, or present to not present or both - * -- it will not switch to a completely different present page - * without a TLB flush in between; something that we are blocking - * by holding interrupts off. - * - * Setting ptes from not present to present goes: - * ptep->pte_high = h; - * smp_wmb(); - * ptep->pte_low = l; - * - * And present to not present goes: - * ptep->pte_low = 0; - * smp_wmb(); - * ptep->pte_high = 0; - * - * We must ensure here that the load of pte_low sees l iff pte_high - * sees h. We load pte_high *after* loading pte_low, which ensures we - * don't see an older value of pte_high. *Then* we recheck pte_low, - * which ensures that we haven't picked up a changed pte high. We might - * have got rubbish values from pte_low and pte_high, but we are - * guaranteed that pte_low will not have the present bit set *unless* - * it is 'l'. And get_user_pages_fast only operates on present ptes, so - * we're safe. - * - * gup_get_pte should not be used or copied outside gup.c without being - * very careful -- it does not atomically load the pte or anything that - * is likely to be useful for you. - */ - pte_t pte; - -retry: - pte.pte_low = ptep->pte_low; - smp_rmb(); - pte.pte_high = ptep->pte_high; - smp_rmb(); - if (unlikely(pte.pte_low != ptep->pte_low)) - goto retry; - - return pte; -#endif -} - -/* - * The performance critical leaf functions are made noinline otherwise gcc - * inlines everything into a single function which results in too much - * register pressure. - */ -static noinline int gup_pte_range(pmd_t pmd, unsigned long addr, - unsigned long end, int write, struct page **pages, int *nr) -{ - u64 mask, result; - pte_t *ptep; - -#ifdef CONFIG_X2TLB - result = _PAGE_PRESENT | _PAGE_EXT(_PAGE_EXT_KERN_READ | _PAGE_EXT_USER_READ); - if (write) - result |= _PAGE_EXT(_PAGE_EXT_KERN_WRITE | _PAGE_EXT_USER_WRITE); -#elif defined(CONFIG_SUPERH64) - result = _PAGE_PRESENT | _PAGE_USER | _PAGE_READ; - if (write) - result |= _PAGE_WRITE; -#else - result = _PAGE_PRESENT | _PAGE_USER; - if (write) - result |= _PAGE_RW; -#endif - - mask = result | _PAGE_SPECIAL; - - ptep = pte_offset_map(&pmd, addr); - do { - pte_t pte = gup_get_pte(ptep); - struct page *page; - - if ((pte_val(pte) & mask) != result) { - pte_unmap(ptep); - return 0; - } - VM_BUG_ON(!pfn_valid(pte_pfn(pte))); - page = pte_page(pte); - get_page(page); - __flush_anon_page(page, addr); - flush_dcache_page(page); - pages[*nr] = page; - (*nr)++; - - } while (ptep++, addr += PAGE_SIZE, addr != end); - pte_unmap(ptep - 1); - - return 1; -} - -static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end, - int write, struct page **pages, int *nr) -{ - unsigned long next; - pmd_t *pmdp; - - pmdp = pmd_offset(&pud, addr); - do { - pmd_t pmd = *pmdp; - - next = pmd_addr_end(addr, end); - if (pmd_none(pmd)) - return 0; - if (!gup_pte_range(pmd, addr, next, write, pages, nr)) - return 0; - } while (pmdp++, addr = next, addr != end); - - return 1; -} - -static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end, - int write, struct page **pages, int *nr) -{ - unsigned long next; - pud_t *pudp; - - pudp = pud_offset(&pgd, addr); - do { - pud_t pud = *pudp; - - next = pud_addr_end(addr, end); - if (pud_none(pud)) - return 0; - if (!gup_pmd_range(pud, addr, next, write, pages, nr)) - return 0; - } while (pudp++, addr = next, addr != end); - - return 1; -} - -/* - * Like get_user_pages_fast() except its IRQ-safe in that it won't fall - * back to the regular GUP. - * Note a difference with get_user_pages_fast: this always returns the - * number of pages pinned, 0 if no pages were pinned. - */ -int __get_user_pages_fast(unsigned long start, int nr_pages, int write, - struct page **pages) -{ - struct mm_struct *mm = current->mm; - unsigned long addr, len, end; - unsigned long next; - unsigned long flags; - pgd_t *pgdp; - int nr = 0; - - start &= PAGE_MASK; - addr = start; - len = (unsigned long) nr_pages << PAGE_SHIFT; - end = start + len; - if (unlikely(!access_ok((void __user *)start, len))) - return 0; - - /* - * This doesn't prevent pagetable teardown, but does prevent - * the pagetables and pages from being freed. - */ - local_irq_save(flags); - pgdp = pgd_offset(mm, addr); - do { - pgd_t pgd = *pgdp; - - next = pgd_addr_end(addr, end); - if (pgd_none(pgd)) - break; - if (!gup_pud_range(pgd, addr, next, write, pages, &nr)) - break; - } while (pgdp++, addr = next, addr != end); - local_irq_restore(flags); - - return nr; -} - -/** - * get_user_pages_fast() - pin user pages in memory - * @start: starting user address - * @nr_pages: number of pages from start to pin - * @gup_flags: flags modifying pin behaviour - * @pages: array that receives pointers to the pages pinned. - * Should be at least nr_pages long. - * - * Attempt to pin user pages in memory without taking mm->mmap_sem. - * If not successful, it will fall back to taking the lock and - * calling get_user_pages(). - * - * Returns number of pages pinned. This may be fewer than the number - * requested. If nr_pages is 0 or negative, returns 0. If no pages - * were pinned, returns -errno. - */ -int get_user_pages_fast(unsigned long start, int nr_pages, - unsigned int gup_flags, struct page **pages) -{ - struct mm_struct *mm = current->mm; - unsigned long addr, len, end; - unsigned long next; - pgd_t *pgdp; - int nr = 0; - - start &= PAGE_MASK; - addr = start; - len = (unsigned long) nr_pages << PAGE_SHIFT; - - end = start + len; - if (end < start) - goto slow_irqon; - - local_irq_disable(); - pgdp = pgd_offset(mm, addr); - do { - pgd_t pgd = *pgdp; - - next = pgd_addr_end(addr, end); - if (pgd_none(pgd)) - goto slow; - if (!gup_pud_range(pgd, addr, next, gup_flags & FOLL_WRITE, - pages, &nr)) - goto slow; - } while (pgdp++, addr = next, addr != end); - local_irq_enable(); - - VM_BUG_ON(nr != (end - start) >> PAGE_SHIFT); - return nr; - - { - int ret; - -slow: - local_irq_enable(); -slow_irqon: - /* Try to get the remaining pages with get_user_pages */ - start += nr << PAGE_SHIFT; - pages += nr; - - ret = get_user_pages_unlocked(start, - (end - start) >> PAGE_SHIFT, pages, - gup_flags); - - /* Have to be a bit careful with return values */ - if (nr > 0) { - if (ret < 0) - ret = nr; - else - ret += nr; - } - - return ret; - } -} diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index 26ab6f5bbaaf..e9f5d62e9817 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -28,6 +28,7 @@ config SPARC select RTC_DRV_M48T59 select RTC_SYSTOHC select HAVE_ARCH_JUMP_LABEL if SPARC64 + select HAVE_FAST_GUP if SPARC64 select GENERIC_IRQ_SHOW select ARCH_WANT_IPC_PARSE_VERSION select GENERIC_PCI_IOMAP @@ -300,9 +301,6 @@ config NODES_SPAN_OTHER_NODES def_bool y depends on NEED_MULTIPLE_NODES -config ARCH_SELECT_MEMORY_MODEL - def_bool y if SPARC64 - config ARCH_SPARSEMEM_ENABLE def_bool y if SPARC64 select SPARSEMEM_VMEMMAP_ENABLE diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h index 22500c3be7a9..1599de730532 100644 --- a/arch/sparc/include/asm/pgtable_64.h +++ b/arch/sparc/include/asm/pgtable_64.h @@ -864,6 +864,9 @@ static inline unsigned long pud_page_vaddr(pud_t pud) #define pgd_present(pgd) (pgd_val(pgd) != 0U) #define pgd_clear(pgdp) (pgd_val(*(pgdp)) = 0UL) +/* only used by the stubbed out hugetlb gup code, should never be called */ +#define pgd_page(pgd) NULL + static inline unsigned long pud_large(pud_t pud) { pte_t pte = __pte(pud_val(pud)); @@ -1075,6 +1078,46 @@ static inline int io_remap_pfn_range(struct vm_area_struct *vma, } #define io_remap_pfn_range io_remap_pfn_range +static inline unsigned long untagged_addr(unsigned long start) +{ + if (adi_capable()) { + long addr = start; + + /* If userspace has passed a versioned address, kernel + * will not find it in the VMAs since it does not store + * the version tags in the list of VMAs. Storing version + * tags in list of VMAs is impractical since they can be + * changed any time from userspace without dropping into + * kernel. Any address search in VMAs will be done with + * non-versioned addresses. Ensure the ADI version bits + * are dropped here by sign extending the last bit before + * ADI bits. IOMMU does not implement version tags. + */ + return (addr << (long)adi_nbits()) >> (long)adi_nbits(); + } + + return start; +} +#define untagged_addr untagged_addr + +static inline bool pte_access_permitted(pte_t pte, bool write) +{ + u64 prot; + + if (tlb_type == hypervisor) { + prot = _PAGE_PRESENT_4V | _PAGE_P_4V; + if (write) + prot |= _PAGE_WRITE_4V; + } else { + prot = _PAGE_PRESENT_4U | _PAGE_P_4U; + if (write) + prot |= _PAGE_WRITE_4U; + } + + return (pte_val(pte) & (prot | _PAGE_SPECIAL)) == prot; +} +#define pte_access_permitted pte_access_permitted + #include <asm/tlbflush.h> #include <asm-generic/pgtable.h> diff --git a/arch/sparc/mm/Makefile b/arch/sparc/mm/Makefile index d39075b1e3b7..b078205b70e0 100644 --- a/arch/sparc/mm/Makefile +++ b/arch/sparc/mm/Makefile @@ -5,7 +5,7 @@ asflags-y := -ansi ccflags-y := -Werror -obj-$(CONFIG_SPARC64) += ultra.o tlb.o tsb.o gup.o +obj-$(CONFIG_SPARC64) += ultra.o tlb.o tsb.o obj-y += fault_$(BITS).o obj-y += init_$(BITS).o obj-$(CONFIG_SPARC32) += extable.o srmmu.o iommu.o io-unit.o diff --git a/arch/sparc/mm/gup.c b/arch/sparc/mm/gup.c deleted file mode 100644 index 1e770a517d4a..000000000000 --- a/arch/sparc/mm/gup.c +++ /dev/null @@ -1,340 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Lockless get_user_pages_fast for sparc, cribbed from powerpc - * - * Copyright (C) 2008 Nick Piggin - * Copyright (C) 2008 Novell Inc. - */ - -#include <linux/sched.h> -#include <linux/mm.h> -#include <linux/vmstat.h> -#include <linux/pagemap.h> -#include <linux/rwsem.h> -#include <asm/pgtable.h> -#include <asm/adi.h> - -/* - * The performance critical leaf functions are made noinline otherwise gcc - * inlines everything into a single function which results in too much - * register pressure. - */ -static noinline int gup_pte_range(pmd_t pmd, unsigned long addr, - unsigned long end, int write, struct page **pages, int *nr) -{ - unsigned long mask, result; - pte_t *ptep; - - if (tlb_type == hypervisor) { - result = _PAGE_PRESENT_4V|_PAGE_P_4V; - if (write) - result |= _PAGE_WRITE_4V; - } else { - result = _PAGE_PRESENT_4U|_PAGE_P_4U; - if (write) - result |= _PAGE_WRITE_4U; - } - mask = result | _PAGE_SPECIAL; - - ptep = pte_offset_kernel(&pmd, addr); - do { - struct page *page, *head; - pte_t pte = *ptep; - - if ((pte_val(pte) & mask) != result) - return 0; - VM_BUG_ON(!pfn_valid(pte_pfn(pte))); - - /* The hugepage case is simplified on sparc64 because - * we encode the sub-page pfn offsets into the - * hugepage PTEs. We could optimize this in the future - * use page_cache_add_speculative() for the hugepage case. - */ - page = pte_page(pte); - head = compound_head(page); - if (!page_cache_get_speculative(head)) - return 0; - if (unlikely(pte_val(pte) != pte_val(*ptep))) { - put_page(head); - return 0; - } - - pages[*nr] = page; - (*nr)++; - } while (ptep++, addr += PAGE_SIZE, addr != end); - - return 1; -} - -static int gup_huge_pmd(pmd_t *pmdp, pmd_t pmd, unsigned long addr, - unsigned long end, int write, struct page **pages, - int *nr) -{ - struct page *head, *page; - int refs; - - if (!(pmd_val(pmd) & _PAGE_VALID)) - return 0; - - if (write && !pmd_write(pmd)) - return 0; - - refs = 0; - page = pmd_page(pmd) + ((addr & ~PMD_MASK) >> PAGE_SHIFT); - head = compound_head(page); - do { - VM_BUG_ON(compound_head(page) != head); - pages[*nr] = page; - (*nr)++; - page++; - refs++; - } while (addr += PAGE_SIZE, addr != end); - - if (!page_cache_add_speculative(head, refs)) { - *nr -= refs; - return 0; - } - - if (unlikely(pmd_val(pmd) != pmd_val(*pmdp))) { - *nr -= refs; - while (refs--) - put_page(head); - return 0; - } - - return 1; -} - -static int gup_huge_pud(pud_t *pudp, pud_t pud, unsigned long addr, - unsigned long end, int write, struct page **pages, - int *nr) -{ - struct page *head, *page; - int refs; - - if (!(pud_val(pud) & _PAGE_VALID)) - return 0; - - if (write && !pud_write(pud)) - return 0; - - refs = 0; - page = pud_page(pud) + ((addr & ~PUD_MASK) >> PAGE_SHIFT); - head = compound_head(page); - do { - VM_BUG_ON(compound_head(page) != head); - pages[*nr] = page; - (*nr)++; - page++; - refs++; - } while (addr += PAGE_SIZE, addr != end); - - if (!page_cache_add_speculative(head, refs)) { - *nr -= refs; - return 0; - } - - if (unlikely(pud_val(pud) != pud_val(*pudp))) { - *nr -= refs; - while (refs--) - put_page(head); - return 0; - } - - return 1; -} - -static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end, - int write, struct page **pages, int *nr) -{ - unsigned long next; - pmd_t *pmdp; - - pmdp = pmd_offset(&pud, addr); - do { - pmd_t pmd = *pmdp; - - next = pmd_addr_end(addr, end); - if (pmd_none(pmd)) - return 0; - if (unlikely(pmd_large(pmd))) { - if (!gup_huge_pmd(pmdp, pmd, addr, next, - write, pages, nr)) - return 0; - } else if (!gup_pte_range(pmd, addr, next, write, - pages, nr)) - return 0; - } while (pmdp++, addr = next, addr != end); - - return 1; -} - -static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end, - int write, struct page **pages, int *nr) -{ - unsigned long next; - pud_t *pudp; - - pudp = pud_offset(&pgd, addr); - do { - pud_t pud = *pudp; - - next = pud_addr_end(addr, end); - if (pud_none(pud)) - return 0; - if (unlikely(pud_large(pud))) { - if (!gup_huge_pud(pudp, pud, addr, next, - write, pages, nr)) - return 0; - } else if (!gup_pmd_range(pud, addr, next, write, pages, nr)) - return 0; - } while (pudp++, addr = next, addr != end); - - return 1; -} - -/* - * Note a difference with get_user_pages_fast: this always returns the - * number of pages pinned, 0 if no pages were pinned. - */ -int __get_user_pages_fast(unsigned long start, int nr_pages, int write, - struct page **pages) -{ - struct mm_struct *mm = current->mm; - unsigned long addr, len, end; - unsigned long next, flags; - pgd_t *pgdp; - int nr = 0; - -#ifdef CONFIG_SPARC64 - if (adi_capable()) { - long addr = start; - - /* If userspace has passed a versioned address, kernel - * will not find it in the VMAs since it does not store - * the version tags in the list of VMAs. Storing version - * tags in list of VMAs is impractical since they can be - * changed any time from userspace without dropping into - * kernel. Any address search in VMAs will be done with - * non-versioned addresses. Ensure the ADI version bits - * are dropped here by sign extending the last bit before - * ADI bits. IOMMU does not implement version tags. - */ - addr = (addr << (long)adi_nbits()) >> (long)adi_nbits(); - start = addr; - } -#endif - start &= PAGE_MASK; - addr = start; - len = (unsigned long) nr_pages << PAGE_SHIFT; - end = start + len; - - local_irq_save(flags); - pgdp = pgd_offset(mm, addr); - do { - pgd_t pgd = *pgdp; - - next = pgd_addr_end(addr, end); - if (pgd_none(pgd)) - break; - if (!gup_pud_range(pgd, addr, next, write, pages, &nr)) - break; - } while (pgdp++, addr = next, addr != end); - local_irq_restore(flags); - - return nr; -} - -int get_user_pages_fast(unsigned long start, int nr_pages, - unsigned int gup_flags, struct page **pages) -{ - struct mm_struct *mm = current->mm; - unsigned long addr, len, end; - unsigned long next; - pgd_t *pgdp; - int nr = 0; - -#ifdef CONFIG_SPARC64 - if (adi_capable()) { - long addr = start; - - /* If userspace has passed a versioned address, kernel - * will not find it in the VMAs since it does not store - * the version tags in the list of VMAs. Storing version - * tags in list of VMAs is impractical since they can be - * changed any time from userspace without dropping into - * kernel. Any address search in VMAs will be done with - * non-versioned addresses. Ensure the ADI version bits - * are dropped here by sign extending the last bit before - * ADI bits. IOMMU does not implements version tags, - */ - addr = (addr << (long)adi_nbits()) >> (long)adi_nbits(); - start = addr; - } -#endif - start &= PAGE_MASK; - addr = start; - len = (unsigned long) nr_pages << PAGE_SHIFT; - end = start + len; - - /* - * XXX: batch / limit 'nr', to avoid large irq off latency - * needs some instrumenting to determine the common sizes used by - * important workloads (eg. DB2), and whether limiting the batch size - * will decrease performance. - * - * It seems like we're in the clear for the moment. Direct-IO is - * the main guy that batches up lots of get_user_pages, and even - * they are limited to 64-at-a-time which is not so many. - */ - /* - * This doesn't prevent pagetable teardown, but does prevent - * the pagetables from being freed on sparc. - * - * So long as we atomically load page table pointers versus teardown, - * we can follow the address down to the the page and take a ref on it. - */ - local_irq_disable(); - - pgdp = pgd_offset(mm, addr); - do { - pgd_t pgd = *pgdp; - - next = pgd_addr_end(addr, end); - if (pgd_none(pgd)) - goto slow; - if (!gup_pud_range(pgd, addr, next, gup_flags & FOLL_WRITE, - pages, &nr)) - goto slow; - } while (pgdp++, addr = next, addr != end); - - local_irq_enable(); - - VM_BUG_ON(nr != (end - start) >> PAGE_SHIFT); - return nr; - - { - int ret; - -slow: - local_irq_enable(); - - /* Try to get the remaining pages with get_user_pages */ - start += nr << PAGE_SHIFT; - pages += nr; - - ret = get_user_pages_unlocked(start, - (end - start) >> PAGE_SHIFT, pages, - gup_flags); - - /* Have to be a bit careful with return values */ - if (nr > 0) { - if (ret < 0) - ret = nr; - else - ret += nr; - } - - return ret; - } -} diff --git a/arch/um/include/asm/pgalloc.h b/arch/um/include/asm/pgalloc.h index 99eb5682792a..d7b282e9c4d5 100644 --- a/arch/um/include/asm/pgalloc.h +++ b/arch/um/include/asm/pgalloc.h @@ -10,6 +10,8 @@ #include <linux/mm.h> +#include <asm-generic/pgalloc.h> /* for pte_{alloc,free}_one */ + #define pmd_populate_kernel(mm, pmd, pte) \ set_pmd(pmd, __pmd(_PAGE_TABLE + (unsigned long) __pa(pte))) @@ -25,20 +27,6 @@ extern pgd_t *pgd_alloc(struct mm_struct *); extern void pgd_free(struct mm_struct *mm, pgd_t *pgd); -extern pte_t *pte_alloc_one_kernel(struct mm_struct *); -extern pgtable_t pte_alloc_one(struct mm_struct *); - -static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) -{ - free_page((unsigned long) pte); -} - -static inline void pte_free(struct mm_struct *mm, pgtable_t pte) -{ - pgtable_page_dtor(pte); - __free_page(pte); -} - #define __pte_free_tlb(tlb,pte, address) \ do { \ pgtable_page_dtor(pte); \ diff --git a/arch/um/kernel/mem.c b/arch/um/kernel/mem.c index a9c9a94c096f..de58e976b9bc 100644 --- a/arch/um/kernel/mem.c +++ b/arch/um/kernel/mem.c @@ -208,28 +208,6 @@ void pgd_free(struct mm_struct *mm, pgd_t *pgd) free_page((unsigned long) pgd); } -pte_t *pte_alloc_one_kernel(struct mm_struct *mm) -{ - pte_t *pte; - - pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_ZERO); - return pte; -} - -pgtable_t pte_alloc_one(struct mm_struct *mm) -{ - struct page *pte; - - pte = alloc_page(GFP_KERNEL|__GFP_ZERO); - if (!pte) - return NULL; - if (!pgtable_page_ctor(pte)) { - __free_page(pte); - return NULL; - } - return pte; -} - #ifdef CONFIG_3_LEVEL_PGTABLES pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address) { diff --git a/arch/unicore32/include/asm/pgalloc.h b/arch/unicore32/include/asm/pgalloc.h index ec64834b1c6a..3f0903bd98e9 100644 --- a/arch/unicore32/include/asm/pgalloc.h +++ b/arch/unicore32/include/asm/pgalloc.h @@ -14,6 +14,10 @@ #include <asm/cacheflush.h> #include <asm/tlbflush.h> +#define __HAVE_ARCH_PTE_ALLOC_ONE_KERNEL +#define __HAVE_ARCH_PTE_ALLOC_ONE +#include <asm-generic/pgalloc.h> + #define check_pgt_cache() do { } while (0) #define _PAGE_USER_TABLE (PMD_TYPE_TABLE | PMD_PRESENT) @@ -25,17 +29,14 @@ extern void free_pgd_slow(struct mm_struct *mm, pgd_t *pgd); #define pgd_alloc(mm) get_pgd_slow(mm) #define pgd_free(mm, pgd) free_pgd_slow(mm, pgd) -#define PGALLOC_GFP (GFP_KERNEL | __GFP_ZERO) - /* * Allocate one PTE table. */ static inline pte_t * pte_alloc_one_kernel(struct mm_struct *mm) { - pte_t *pte; + pte_t *pte = __pte_alloc_one_kernel(mm); - pte = (pte_t *)__get_free_page(PGALLOC_GFP); if (pte) clean_dcache_area(pte, PTRS_PER_PTE * sizeof(pte_t)); @@ -47,35 +48,14 @@ pte_alloc_one(struct mm_struct *mm) { struct page *pte; - pte = alloc_pages(PGALLOC_GFP, 0); + pte = __pte_alloc_one(mm, GFP_PGTABLE_USER); if (!pte) return NULL; - if (!PageHighMem(pte)) { - void *page = page_address(pte); - clean_dcache_area(page, PTRS_PER_PTE * sizeof(pte_t)); - } - if (!pgtable_page_ctor(pte)) { - __free_page(pte); - } - + if (!PageHighMem(pte)) + clean_pte_table(page_address(pte)); return pte; } -/* - * Free one PTE table. - */ -static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) -{ - if (pte) - free_page((unsigned long)pte); -} - -static inline void pte_free(struct mm_struct *mm, pgtable_t pte) -{ - pgtable_page_dtor(pte); - __free_page(pte); -} - static inline void __pmd_populate(pmd_t *pmdp, unsigned long pmdval) { set_pmd(pmdp, __pmd(pmdval)); diff --git a/arch/unicore32/include/mach/regs-gpio.h b/arch/unicore32/include/mach/regs-gpio.h index 806350e1ccb6..5fc701ee33e3 100644 --- a/arch/unicore32/include/mach/regs-gpio.h +++ b/arch/unicore32/include/mach/regs-gpio.h @@ -32,7 +32,7 @@ */ #define GPIO_GEDR (PKUNITY_GPIO_BASE + 0x0018) /* - * Sepcial Voltage Detect Reg GPIO_GPIR. + * Special Voltage Detect Reg GPIO_GPIR. */ #define GPIO_GPIR (PKUNITY_GPIO_BASE + 0x0020) diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index dce10b18f4bc..9df2d1cb7a9e 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -123,6 +123,7 @@ config X86 select GENERIC_STRNLEN_USER select GENERIC_TIME_VSYSCALL select GENERIC_GETTIMEOFDAY + select GUP_GET_PTE_LOW_HIGH if X86_PAE select HARDLOCKUP_CHECK_TIMESTAMP if X86_64 select HAVE_ACPI_APEI if ACPI select HAVE_ACPI_APEI_NMI if ACPI @@ -158,6 +159,7 @@ config X86 select HAVE_EFFICIENT_UNALIGNED_ACCESS select HAVE_EISA select HAVE_EXIT_THREAD + select HAVE_FAST_GUP select HAVE_FENTRY if X86_64 || DYNAMIC_FTRACE select HAVE_FTRACE_MCOUNT_RECORD select HAVE_FUNCTION_GRAPH_TRACER @@ -2906,9 +2908,6 @@ config HAVE_ATOMIC_IOMAP config X86_DEV_DMA_OPS bool -config HAVE_GENERIC_GUP - def_bool y - source "drivers/firmware/Kconfig" source "arch/x86/kvm/Kconfig" diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c index 629d1ee05599..1cee10091b9f 100644 --- a/arch/x86/ia32/ia32_signal.c +++ b/arch/x86/ia32/ia32_signal.c @@ -358,7 +358,7 @@ int ia32_setup_rt_frame(int sig, struct ksignal *ksig, put_user_ex(ptr_to_compat(&frame->uc), &frame->puc); /* Create the ucontext. */ - if (boot_cpu_has(X86_FEATURE_XSAVE)) + if (static_cpu_has(X86_FEATURE_XSAVE)) put_user_ex(UC_FP_XSTATE, &frame->uc.uc_flags); else put_user_ex(0, &frame->uc.uc_flags); diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h index 8e790ec219a5..ba15d53c1ca7 100644 --- a/arch/x86/include/asm/bitops.h +++ b/arch/x86/include/asm/bitops.h @@ -49,23 +49,8 @@ #define CONST_MASK_ADDR(nr, addr) WBYTE_ADDR((void *)(addr) + ((nr)>>3)) #define CONST_MASK(nr) (1 << ((nr) & 7)) -/** - * set_bit - Atomically set a bit in memory - * @nr: the bit to set - * @addr: the address to start counting from - * - * This function is atomic and may not be reordered. See __set_bit() - * if you do not require the atomic guarantees. - * - * Note: there are no guarantees that this function will not be reordered - * on non x86 architectures, so if you are writing portable code, - * make sure not to rely on its reordering guarantees. - * - * Note that @nr may be almost arbitrarily large; this function is not - * restricted to acting on a single-word quantity. - */ static __always_inline void -set_bit(long nr, volatile unsigned long *addr) +arch_set_bit(long nr, volatile unsigned long *addr) { if (IS_IMMEDIATE(nr)) { asm volatile(LOCK_PREFIX "orb %1,%0" @@ -78,32 +63,14 @@ set_bit(long nr, volatile unsigned long *addr) } } -/** - * __set_bit - Set a bit in memory - * @nr: the bit to set - * @addr: the address to start counting from - * - * Unlike set_bit(), this function is non-atomic and may be reordered. - * If it's called on the same region of memory simultaneously, the effect - * may be that only one operation succeeds. - */ -static __always_inline void __set_bit(long nr, volatile unsigned long *addr) +static __always_inline void +arch___set_bit(long nr, volatile unsigned long *addr) { asm volatile(__ASM_SIZE(bts) " %1,%0" : : ADDR, "Ir" (nr) : "memory"); } -/** - * clear_bit - Clears a bit in memory - * @nr: Bit to clear - * @addr: Address to start counting from - * - * clear_bit() is atomic and may not be reordered. However, it does - * not contain a memory barrier, so if it is used for locking purposes, - * you should call smp_mb__before_atomic() and/or smp_mb__after_atomic() - * in order to ensure changes are visible on other processors. - */ static __always_inline void -clear_bit(long nr, volatile unsigned long *addr) +arch_clear_bit(long nr, volatile unsigned long *addr) { if (IS_IMMEDIATE(nr)) { asm volatile(LOCK_PREFIX "andb %1,%0" @@ -115,26 +82,21 @@ clear_bit(long nr, volatile unsigned long *addr) } } -/* - * clear_bit_unlock - Clears a bit in memory - * @nr: Bit to clear - * @addr: Address to start counting from - * - * clear_bit() is atomic and implies release semantics before the memory - * operation. It can be used for an unlock. - */ -static __always_inline void clear_bit_unlock(long nr, volatile unsigned long *addr) +static __always_inline void +arch_clear_bit_unlock(long nr, volatile unsigned long *addr) { barrier(); - clear_bit(nr, addr); + arch_clear_bit(nr, addr); } -static __always_inline void __clear_bit(long nr, volatile unsigned long *addr) +static __always_inline void +arch___clear_bit(long nr, volatile unsigned long *addr) { asm volatile(__ASM_SIZE(btr) " %1,%0" : : ADDR, "Ir" (nr) : "memory"); } -static __always_inline bool clear_bit_unlock_is_negative_byte(long nr, volatile unsigned long *addr) +static __always_inline bool +arch_clear_bit_unlock_is_negative_byte(long nr, volatile unsigned long *addr) { bool negative; asm volatile(LOCK_PREFIX "andb %2,%1" @@ -143,48 +105,23 @@ static __always_inline bool clear_bit_unlock_is_negative_byte(long nr, volatile : "ir" ((char) ~(1 << nr)) : "memory"); return negative; } +#define arch_clear_bit_unlock_is_negative_byte \ + arch_clear_bit_unlock_is_negative_byte -// Let everybody know we have it -#define clear_bit_unlock_is_negative_byte clear_bit_unlock_is_negative_byte - -/* - * __clear_bit_unlock - Clears a bit in memory - * @nr: Bit to clear - * @addr: Address to start counting from - * - * __clear_bit() is non-atomic and implies release semantics before the memory - * operation. It can be used for an unlock if no other CPUs can concurrently - * modify other bits in the word. - */ -static __always_inline void __clear_bit_unlock(long nr, volatile unsigned long *addr) +static __always_inline void +arch___clear_bit_unlock(long nr, volatile unsigned long *addr) { - __clear_bit(nr, addr); + arch___clear_bit(nr, addr); } -/** - * __change_bit - Toggle a bit in memory - * @nr: the bit to change - * @addr: the address to start counting from - * - * Unlike change_bit(), this function is non-atomic and may be reordered. - * If it's called on the same region of memory simultaneously, the effect - * may be that only one operation succeeds. - */ -static __always_inline void __change_bit(long nr, volatile unsigned long *addr) +static __always_inline void +arch___change_bit(long nr, volatile unsigned long *addr) { asm volatile(__ASM_SIZE(btc) " %1,%0" : : ADDR, "Ir" (nr) : "memory"); } -/** - * change_bit - Toggle a bit in memory - * @nr: Bit to change - * @addr: Address to start counting from - * - * change_bit() is atomic and may not be reordered. - * Note that @nr may be almost arbitrarily large; this function is not - * restricted to acting on a single-word quantity. - */ -static __always_inline void change_bit(long nr, volatile unsigned long *addr) +static __always_inline void +arch_change_bit(long nr, volatile unsigned long *addr) { if (IS_IMMEDIATE(nr)) { asm volatile(LOCK_PREFIX "xorb %1,%0" @@ -196,42 +133,20 @@ static __always_inline void change_bit(long nr, volatile unsigned long *addr) } } -/** - * test_and_set_bit - Set a bit and return its old value - * @nr: Bit to set - * @addr: Address to count from - * - * This operation is atomic and cannot be reordered. - * It also implies a memory barrier. - */ -static __always_inline bool test_and_set_bit(long nr, volatile unsigned long *addr) +static __always_inline bool +arch_test_and_set_bit(long nr, volatile unsigned long *addr) { return GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(bts), *addr, c, "Ir", nr); } -/** - * test_and_set_bit_lock - Set a bit and return its old value for lock - * @nr: Bit to set - * @addr: Address to count from - * - * This is the same as test_and_set_bit on x86. - */ static __always_inline bool -test_and_set_bit_lock(long nr, volatile unsigned long *addr) +arch_test_and_set_bit_lock(long nr, volatile unsigned long *addr) { - return test_and_set_bit(nr, addr); + return arch_test_and_set_bit(nr, addr); } -/** - * __test_and_set_bit - Set a bit and return its old value - * @nr: Bit to set - * @addr: Address to count from - * - * This operation is non-atomic and can be reordered. - * If two examples of this operation race, one can appear to succeed - * but actually fail. You must protect multiple accesses with a lock. - */ -static __always_inline bool __test_and_set_bit(long nr, volatile unsigned long *addr) +static __always_inline bool +arch___test_and_set_bit(long nr, volatile unsigned long *addr) { bool oldbit; @@ -242,28 +157,13 @@ static __always_inline bool __test_and_set_bit(long nr, volatile unsigned long * return oldbit; } -/** - * test_and_clear_bit - Clear a bit and return its old value - * @nr: Bit to clear - * @addr: Address to count from - * - * This operation is atomic and cannot be reordered. - * It also implies a memory barrier. - */ -static __always_inline bool test_and_clear_bit(long nr, volatile unsigned long *addr) +static __always_inline bool +arch_test_and_clear_bit(long nr, volatile unsigned long *addr) { return GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(btr), *addr, c, "Ir", nr); } -/** - * __test_and_clear_bit - Clear a bit and return its old value - * @nr: Bit to clear - * @addr: Address to count from - * - * This operation is non-atomic and can be reordered. - * If two examples of this operation race, one can appear to succeed - * but actually fail. You must protect multiple accesses with a lock. - * +/* * Note: the operation is performed atomically with respect to * the local CPU, but not other CPUs. Portable code should not * rely on this behaviour. @@ -271,7 +171,8 @@ static __always_inline bool test_and_clear_bit(long nr, volatile unsigned long * * accessed from a hypervisor on the same CPU if running in a VM: don't change * this without also updating arch/x86/kernel/kvm.c */ -static __always_inline bool __test_and_clear_bit(long nr, volatile unsigned long *addr) +static __always_inline bool +arch___test_and_clear_bit(long nr, volatile unsigned long *addr) { bool oldbit; @@ -282,8 +183,8 @@ static __always_inline bool __test_and_clear_bit(long nr, volatile unsigned long return oldbit; } -/* WARNING: non atomic and it can be reordered! */ -static __always_inline bool __test_and_change_bit(long nr, volatile unsigned long *addr) +static __always_inline bool +arch___test_and_change_bit(long nr, volatile unsigned long *addr) { bool oldbit; @@ -295,15 +196,8 @@ static __always_inline bool __test_and_change_bit(long nr, volatile unsigned lon return oldbit; } -/** - * test_and_change_bit - Change a bit and return its old value - * @nr: Bit to change - * @addr: Address to count from - * - * This operation is atomic and cannot be reordered. - * It also implies a memory barrier. - */ -static __always_inline bool test_and_change_bit(long nr, volatile unsigned long *addr) +static __always_inline bool +arch_test_and_change_bit(long nr, volatile unsigned long *addr) { return GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(btc), *addr, c, "Ir", nr); } @@ -326,16 +220,7 @@ static __always_inline bool variable_test_bit(long nr, volatile const unsigned l return oldbit; } -#if 0 /* Fool kernel-doc since it doesn't do macros yet */ -/** - * test_bit - Determine whether a bit is set - * @nr: bit number to test - * @addr: Address to start counting from - */ -static bool test_bit(int nr, const volatile unsigned long *addr); -#endif - -#define test_bit(nr, addr) \ +#define arch_test_bit(nr, addr) \ (__builtin_constant_p((nr)) \ ? constant_test_bit((nr), (addr)) \ : variable_test_bit((nr), (addr))) @@ -504,6 +389,8 @@ static __always_inline int fls64(__u64 x) #include <asm-generic/bitops/const_hweight.h> +#include <asm-generic/bitops-instrumented.h> + #include <asm-generic/bitops/le.h> #include <asm-generic/bitops/ext2-atomic-setbit.h> diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h index a281e61ec60c..29aa7859bdee 100644 --- a/arch/x86/include/asm/pgalloc.h +++ b/arch/x86/include/asm/pgalloc.h @@ -6,6 +6,9 @@ #include <linux/mm.h> /* for struct page */ #include <linux/pagemap.h> +#define __HAVE_ARCH_PTE_ALLOC_ONE +#include <asm-generic/pgalloc.h> /* for pte_{alloc,free}_one */ + static inline int __paravirt_pgd_alloc(struct mm_struct *mm) { return 0; } #ifdef CONFIG_PARAVIRT_XXL @@ -47,24 +50,8 @@ extern gfp_t __userpte_alloc_gfp; extern pgd_t *pgd_alloc(struct mm_struct *); extern void pgd_free(struct mm_struct *mm, pgd_t *pgd); -extern pte_t *pte_alloc_one_kernel(struct mm_struct *); extern pgtable_t pte_alloc_one(struct mm_struct *); -/* Should really implement gc for free page table pages. This could be - done with a reference count in struct page. */ - -static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) -{ - BUG_ON((unsigned long)pte & (PAGE_SIZE-1)); - free_page((unsigned long)pte); -} - -static inline void pte_free(struct mm_struct *mm, struct page *pte) -{ - pgtable_page_dtor(pte); - __free_page(pte); -} - extern void ___pte_free_tlb(struct mmu_gather *tlb, struct page *pte); static inline void __pte_free_tlb(struct mmu_gather *tlb, struct page *pte, diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h index f8b1ad2c3828..e3633795fb22 100644 --- a/arch/x86/include/asm/pgtable-3level.h +++ b/arch/x86/include/asm/pgtable-3level.h @@ -285,53 +285,6 @@ static inline pud_t native_pudp_get_and_clear(pud_t *pudp) #define __pte_to_swp_entry(pte) (__swp_entry(__pteval_swp_type(pte), \ __pteval_swp_offset(pte))) -#define gup_get_pte gup_get_pte -/* - * WARNING: only to be used in the get_user_pages_fast() implementation. - * - * With get_user_pages_fast(), we walk down the pagetables without taking - * any locks. For this we would like to load the pointers atomically, - * but that is not possible (without expensive cmpxchg8b) on PAE. What - * we do have is the guarantee that a PTE will only either go from not - * present to present, or present to not present or both -- it will not - * switch to a completely different present page without a TLB flush in - * between; something that we are blocking by holding interrupts off. - * - * Setting ptes from not present to present goes: - * - * ptep->pte_high = h; - * smp_wmb(); - * ptep->pte_low = l; - * - * And present to not present goes: - * - * ptep->pte_low = 0; - * smp_wmb(); - * ptep->pte_high = 0; - * - * We must ensure here that the load of pte_low sees 'l' iff pte_high - * sees 'h'. We load pte_high *after* loading pte_low, which ensures we - * don't see an older value of pte_high. *Then* we recheck pte_low, - * which ensures that we haven't picked up a changed pte high. We might - * have gotten rubbish values from pte_low and pte_high, but we are - * guaranteed that pte_low will not have the present bit set *unless* - * it is 'l'. Because get_user_pages_fast() only operates on present ptes - * we're safe. - */ -static inline pte_t gup_get_pte(pte_t *ptep) -{ - pte_t pte; - - do { - pte.pte_low = ptep->pte_low; - smp_rmb(); - pte.pte_high = ptep->pte_high; - smp_rmb(); - } while (unlikely(pte.pte_low != ptep->pte_low)); - - return pte; -} - #include <asm/pgtable-invert.h> #endif /* _ASM_X86_PGTABLE_3LEVEL_H */ diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h index 0bb566315621..4990d26dfc73 100644 --- a/arch/x86/include/asm/pgtable_64.h +++ b/arch/x86/include/asm/pgtable_64.h @@ -259,14 +259,8 @@ extern void init_extra_mapping_uc(unsigned long phys, unsigned long size); extern void init_extra_mapping_wb(unsigned long phys, unsigned long size); #define gup_fast_permitted gup_fast_permitted -static inline bool gup_fast_permitted(unsigned long start, int nr_pages) +static inline bool gup_fast_permitted(unsigned long start, unsigned long end) { - unsigned long len, end; - - len = (unsigned long)nr_pages << PAGE_SHIFT; - end = start + len; - if (end < start) - return false; if (end >> __VIRTUAL_MASK_SHIFT) return false; return true; diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 7cf508f78c8c..8eb7193e158d 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -391,7 +391,7 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig, put_user_ex(&frame->uc, &frame->puc); /* Create the ucontext. */ - if (boot_cpu_has(X86_FEATURE_XSAVE)) + if (static_cpu_has(X86_FEATURE_XSAVE)) put_user_ex(UC_FP_XSTATE, &frame->uc.uc_flags); else put_user_ex(0, &frame->uc.uc_flags); diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 98f6e4f88b04..4a9c63d1c20a 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -650,7 +650,7 @@ static u64 __update_clear_spte_slow(u64 *sptep, u64 spte) /* * The idea using the light way get the spte on x86_32 guest is from - * gup_get_pte(arch/x86/mm/gup.c). + * gup_get_pte (mm/gup.c). * * An spte tlb flush may be pending, because kvm_set_pte_rmapp * coalesces them and we are running out of the MMU lock. Therefore diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index 1f67b1e15bf6..44816ff6411f 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -13,33 +13,17 @@ phys_addr_t physical_mask __ro_after_init = (1ULL << __PHYSICAL_MASK_SHIFT) - 1; EXPORT_SYMBOL(physical_mask); #endif -#define PGALLOC_GFP (GFP_KERNEL_ACCOUNT | __GFP_ZERO) - #ifdef CONFIG_HIGHPTE -#define PGALLOC_USER_GFP __GFP_HIGHMEM +#define PGTABLE_HIGHMEM __GFP_HIGHMEM #else -#define PGALLOC_USER_GFP 0 +#define PGTABLE_HIGHMEM 0 #endif -gfp_t __userpte_alloc_gfp = PGALLOC_GFP | PGALLOC_USER_GFP; - -pte_t *pte_alloc_one_kernel(struct mm_struct *mm) -{ - return (pte_t *)__get_free_page(PGALLOC_GFP & ~__GFP_ACCOUNT); -} +gfp_t __userpte_alloc_gfp = GFP_PGTABLE_USER | PGTABLE_HIGHMEM; pgtable_t pte_alloc_one(struct mm_struct *mm) { - struct page *pte; - - pte = alloc_pages(__userpte_alloc_gfp, 0); - if (!pte) - return NULL; - if (!pgtable_page_ctor(pte)) { - __free_page(pte); - return NULL; - } - return pte; + return __pte_alloc_one(mm, __userpte_alloc_gfp); } static int __init setup_userpte(char *arg) @@ -235,7 +219,7 @@ static int preallocate_pmds(struct mm_struct *mm, pmd_t *pmds[], int count) { int i; bool failed = false; - gfp_t gfp = PGALLOC_GFP; + gfp_t gfp = GFP_PGTABLE_USER; if (mm == &init_mm) gfp &= ~__GFP_ACCOUNT; @@ -399,14 +383,14 @@ static inline pgd_t *_pgd_alloc(void) * We allocate one page for pgd. */ if (!SHARED_KERNEL_PMD) - return (pgd_t *)__get_free_pages(PGALLOC_GFP, + return (pgd_t *)__get_free_pages(GFP_PGTABLE_USER, PGD_ALLOCATION_ORDER); /* * Now PAE kernel is not running as a Xen domain. We can allocate * a 32-byte slab for pgd to save memory space. */ - return kmem_cache_alloc(pgd_cache, PGALLOC_GFP); + return kmem_cache_alloc(pgd_cache, GFP_PGTABLE_USER); } static inline void _pgd_free(pgd_t *pgd) @@ -424,7 +408,8 @@ void __init pgd_cache_init(void) static inline pgd_t *_pgd_alloc(void) { - return (pgd_t *)__get_free_pages(PGALLOC_GFP, PGD_ALLOCATION_ORDER); + return (pgd_t *)__get_free_pages(GFP_PGTABLE_USER, + PGD_ALLOCATION_ORDER); } static inline void _pgd_free(pgd_t *pgd) diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index beb44e22afdf..f6e5eeecfc69 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -2700,8 +2700,7 @@ struct remap_data { struct mmu_update *mmu_update; }; -static int remap_area_pfn_pte_fn(pte_t *ptep, pgtable_t token, - unsigned long addr, void *data) +static int remap_area_pfn_pte_fn(pte_t *ptep, unsigned long addr, void *data) { struct remap_data *rmd = data; pte_t pte = pte_mkspecial(mfn_pte(*rmd->pfn, rmd->prot)); diff --git a/drivers/clk/renesas/r8a77470-cpg-mssr.c b/drivers/clk/renesas/r8a77470-cpg-mssr.c index ab0fb10b6bf0..d81ae65f0d18 100644 --- a/drivers/clk/renesas/r8a77470-cpg-mssr.c +++ b/drivers/clk/renesas/r8a77470-cpg-mssr.c @@ -175,7 +175,7 @@ static const unsigned int r8a77470_crit_mod_clks[] __initconst = { *--------------------------------------------------- * 0 0 20 x80 x78 x50 * 0 1 26 x60 x60 x56 - * 1 0 Prohibitted setting + * 1 0 Prohibited setting * 1 1 30 x52 x52 x50 * * *1 : Table 7.4 indicates VCO output (PLL0 = VCO) diff --git a/drivers/gpu/drm/i915/i915_mm.c b/drivers/gpu/drm/i915/i915_mm.c index e4935dd1fd37..c23bb29e6d3e 100644 --- a/drivers/gpu/drm/i915/i915_mm.c +++ b/drivers/gpu/drm/i915/i915_mm.c @@ -35,8 +35,7 @@ struct remap_pfn { pgprot_t prot; }; -static int remap_pfn(pte_t *pte, pgtable_t token, - unsigned long addr, void *data) +static int remap_pfn(pte_t *pte, unsigned long addr, void *data) { struct remap_pfn *r = data; diff --git a/drivers/infiniband/core/uverbs_ioctl.c b/drivers/infiniband/core/uverbs_ioctl.c index 829b0c6944d8..61758201d9b2 100644 --- a/drivers/infiniband/core/uverbs_ioctl.c +++ b/drivers/infiniband/core/uverbs_ioctl.c @@ -127,7 +127,7 @@ __malloc void *_uverbs_alloc(struct uverbs_attr_bundle *bundle, size_t size, res = (void *)pbundle->internal_buffer + pbundle->internal_used; pbundle->internal_used = ALIGN(new_used, sizeof(*pbundle->internal_buffer)); - if (flags & __GFP_ZERO) + if (want_init_on_alloc(flags)) memset(res, 0, size); return res; } diff --git a/drivers/misc/lkdtm/core.c b/drivers/misc/lkdtm/core.c index 756794ac8fd8..e9767bdcdb44 100644 --- a/drivers/misc/lkdtm/core.c +++ b/drivers/misc/lkdtm/core.c @@ -121,6 +121,9 @@ static const struct crashtype crashtypes[] = { CRASHTYPE(READ_AFTER_FREE), CRASHTYPE(WRITE_BUDDY_AFTER_FREE), CRASHTYPE(READ_BUDDY_AFTER_FREE), + CRASHTYPE(SLAB_FREE_DOUBLE), + CRASHTYPE(SLAB_FREE_CROSS), + CRASHTYPE(SLAB_FREE_PAGE), CRASHTYPE(SOFTLOCKUP), CRASHTYPE(HARDLOCKUP), CRASHTYPE(SPINLOCKUP), @@ -427,6 +430,7 @@ static int __init lkdtm_module_init(void) lkdtm_bugs_init(&recur_count); lkdtm_perms_init(); lkdtm_usercopy_init(); + lkdtm_heap_init(); /* Register debugfs interface */ lkdtm_debugfs_root = debugfs_create_dir("provoke-crash", NULL); @@ -473,6 +477,7 @@ static void __exit lkdtm_module_exit(void) debugfs_remove_recursive(lkdtm_debugfs_root); /* Handle test-specific clean-up. */ + lkdtm_heap_exit(); lkdtm_usercopy_exit(); if (lkdtm_kprobe != NULL) diff --git a/drivers/misc/lkdtm/heap.c b/drivers/misc/lkdtm/heap.c index 65026d7de130..3c5cec85edce 100644 --- a/drivers/misc/lkdtm/heap.c +++ b/drivers/misc/lkdtm/heap.c @@ -7,6 +7,10 @@ #include <linux/slab.h> #include <linux/sched.h> +static struct kmem_cache *double_free_cache; +static struct kmem_cache *a_cache; +static struct kmem_cache *b_cache; + /* * This tries to stay within the next largest power-of-2 kmalloc cache * to avoid actually overwriting anything important if it's not detected @@ -146,3 +150,71 @@ void lkdtm_READ_BUDDY_AFTER_FREE(void) kfree(val); } + +void lkdtm_SLAB_FREE_DOUBLE(void) +{ + int *val; + + val = kmem_cache_alloc(double_free_cache, GFP_KERNEL); + if (!val) { + pr_info("Unable to allocate double_free_cache memory.\n"); + return; + } + + /* Just make sure we got real memory. */ + *val = 0x12345678; + pr_info("Attempting double slab free ...\n"); + kmem_cache_free(double_free_cache, val); + kmem_cache_free(double_free_cache, val); +} + +void lkdtm_SLAB_FREE_CROSS(void) +{ + int *val; + + val = kmem_cache_alloc(a_cache, GFP_KERNEL); + if (!val) { + pr_info("Unable to allocate a_cache memory.\n"); + return; + } + + /* Just make sure we got real memory. */ + *val = 0x12345679; + pr_info("Attempting cross-cache slab free ...\n"); + kmem_cache_free(b_cache, val); +} + +void lkdtm_SLAB_FREE_PAGE(void) +{ + unsigned long p = __get_free_page(GFP_KERNEL); + + pr_info("Attempting non-Slab slab free ...\n"); + kmem_cache_free(NULL, (void *)p); + free_page(p); +} + +/* + * We have constructors to keep the caches distinctly separated without + * needing to boot with "slab_nomerge". + */ +static void ctor_double_free(void *region) +{ } +static void ctor_a(void *region) +{ } +static void ctor_b(void *region) +{ } + +void __init lkdtm_heap_init(void) +{ + double_free_cache = kmem_cache_create("lkdtm-heap-double_free", + 64, 0, 0, ctor_double_free); + a_cache = kmem_cache_create("lkdtm-heap-a", 64, 0, 0, ctor_a); + b_cache = kmem_cache_create("lkdtm-heap-b", 64, 0, 0, ctor_b); +} + +void __exit lkdtm_heap_exit(void) +{ + kmem_cache_destroy(double_free_cache); + kmem_cache_destroy(a_cache); + kmem_cache_destroy(b_cache); +} diff --git a/drivers/misc/lkdtm/lkdtm.h b/drivers/misc/lkdtm/lkdtm.h index bbcd370786d4..6a284a87a037 100644 --- a/drivers/misc/lkdtm/lkdtm.h +++ b/drivers/misc/lkdtm/lkdtm.h @@ -29,11 +29,16 @@ void lkdtm_STACK_GUARD_PAGE_TRAILING(void); void lkdtm_UNSET_SMEP(void); /* lkdtm_heap.c */ +void __init lkdtm_heap_init(void); +void __exit lkdtm_heap_exit(void); void lkdtm_OVERWRITE_ALLOCATION(void); void lkdtm_WRITE_AFTER_FREE(void); void lkdtm_READ_AFTER_FREE(void); void lkdtm_WRITE_BUDDY_AFTER_FREE(void); void lkdtm_READ_BUDDY_AFTER_FREE(void); +void lkdtm_SLAB_FREE_DOUBLE(void); +void lkdtm_SLAB_FREE_CROSS(void); +void lkdtm_SLAB_FREE_PAGE(void); /* lkdtm_perms.c */ void __init lkdtm_perms_init(void); diff --git a/drivers/net/wireless/realtek/rtlwifi/wifi.h b/drivers/net/wireless/realtek/rtlwifi/wifi.h index 81caa3782ec0..3bdda1c98339 100644 --- a/drivers/net/wireless/realtek/rtlwifi/wifi.h +++ b/drivers/net/wireless/realtek/rtlwifi/wifi.h @@ -598,7 +598,7 @@ enum ht_channel_width { HT_CHANNEL_WIDTH_MAX, }; -/* Ref: 802.11i sepc D10.0 7.3.2.25.1 +/* Ref: 802.11i spec D10.0 7.3.2.25.1 * Cipher Suites Encryption Algorithms */ enum rt_enc_alg { diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c index 6d6b14295734..faf43b1d3dbe 100644 --- a/drivers/scsi/lpfc/lpfc_init.c +++ b/drivers/scsi/lpfc/lpfc_init.c @@ -2965,7 +2965,7 @@ lpfc_stop_hba_timers(struct lpfc_hba *phba) del_timer_sync(&phba->fcp_poll_timer); break; case LPFC_PCI_DEV_OC: - /* Stop any OneConnect device sepcific driver timers */ + /* Stop any OneConnect device specific driver timers */ lpfc_sli4_stop_fcf_redisc_wait_timer(phba); break; default: diff --git a/drivers/staging/rtl8723bs/hal/rtl8723b_phycfg.c b/drivers/staging/rtl8723bs/hal/rtl8723b_phycfg.c index d26bdfd11266..25c75b977666 100644 --- a/drivers/staging/rtl8723bs/hal/rtl8723b_phycfg.c +++ b/drivers/staging/rtl8723bs/hal/rtl8723b_phycfg.c @@ -45,7 +45,7 @@ static u32 phy_CalculateBitShift(u32 BitMask) /** * Function: PHY_QueryBBReg * -* OverView: Read "sepcific bits" from BB register +* OverView: Read "specific bits" from BB register * * Input: * struct adapter * Adapter, diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c index 469dfbd6cf90..4c339c7e66e5 100644 --- a/drivers/xen/gntdev.c +++ b/drivers/xen/gntdev.c @@ -264,8 +264,7 @@ void gntdev_put_map(struct gntdev_priv *priv, struct gntdev_grant_map *map) /* ------------------------------------------------------------------ */ -static int find_grant_ptes(pte_t *pte, pgtable_t token, - unsigned long addr, void *data) +static int find_grant_ptes(pte_t *pte, unsigned long addr, void *data) { struct gntdev_grant_map *map = data; unsigned int pgnr = (addr - map->vma->vm_start) >> PAGE_SHIFT; @@ -292,8 +291,7 @@ static int find_grant_ptes(pte_t *pte, pgtable_t token, } #ifdef CONFIG_X86 -static int set_grant_ptes_as_special(pte_t *pte, pgtable_t token, - unsigned long addr, void *data) +static int set_grant_ptes_as_special(pte_t *pte, unsigned long addr, void *data) { set_pte_at(current->mm, addr, pte, pte_mkspecial(*pte)); return 0; diff --git a/drivers/xen/privcmd.c b/drivers/xen/privcmd.c index 1ff38d8036e9..2f5ce7230a43 100644 --- a/drivers/xen/privcmd.c +++ b/drivers/xen/privcmd.c @@ -731,8 +731,7 @@ struct remap_pfn { unsigned long i; }; -static int remap_pfn_fn(pte_t *ptep, pgtable_t token, unsigned long addr, - void *data) +static int remap_pfn_fn(pte_t *ptep, unsigned long addr, void *data) { struct remap_pfn *r = data; struct page *page = r->pages[r->i]; @@ -966,8 +965,7 @@ static int privcmd_mmap(struct file *file, struct vm_area_struct *vma) * on a per pfn/pte basis. Mapping calls that fail with ENOENT * can be then retried until success. */ -static int is_mapped_fn(pte_t *pte, struct page *pmd_page, - unsigned long addr, void *data) +static int is_mapped_fn(pte_t *pte, unsigned long addr, void *data) { return pte_none(*pte) ? 0 : -EBUSY; } diff --git a/drivers/xen/xlate_mmu.c b/drivers/xen/xlate_mmu.c index e7df65d32c91..ba883a80b3c0 100644 --- a/drivers/xen/xlate_mmu.c +++ b/drivers/xen/xlate_mmu.c @@ -93,8 +93,7 @@ static void setup_hparams(unsigned long gfn, void *data) info->fgfn++; } -static int remap_pte_fn(pte_t *ptep, pgtable_t token, unsigned long addr, - void *data) +static int remap_pte_fn(pte_t *ptep, unsigned long addr, void *data) { struct remap_data *info = data; struct page *page = info->pages[info->index++]; diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c index bc57ae9e2963..cce9ace651a2 100644 --- a/fs/9p/vfs_addr.c +++ b/fs/9p/vfs_addr.c @@ -35,8 +35,9 @@ * @page: structure to page * */ -static int v9fs_fid_readpage(struct p9_fid *fid, struct page *page) +static int v9fs_fid_readpage(void *data, struct page *page) { + struct p9_fid *fid = data; struct inode *inode = page->mapping->host; struct bio_vec bvec = {.bv_page = page, .bv_len = PAGE_SIZE}; struct iov_iter to; @@ -107,7 +108,8 @@ static int v9fs_vfs_readpages(struct file *filp, struct address_space *mapping, if (ret == 0) return ret; - ret = read_cache_pages(mapping, pages, (void *)v9fs_vfs_readpage, filp); + ret = read_cache_pages(mapping, pages, v9fs_fid_readpage, + filp->private_data); p9_debug(P9_DEBUG_VFS, " = %d\n", ret); return ret; } diff --git a/fs/jffs2/file.c b/fs/jffs2/file.c index 7d8654a1472e..f8fb89b10227 100644 --- a/fs/jffs2/file.c +++ b/fs/jffs2/file.c @@ -109,9 +109,9 @@ static int jffs2_do_readpage_nolock (struct inode *inode, struct page *pg) return ret; } -int jffs2_do_readpage_unlock(struct inode *inode, struct page *pg) +int jffs2_do_readpage_unlock(void *data, struct page *pg) { - int ret = jffs2_do_readpage_nolock(inode, pg); + int ret = jffs2_do_readpage_nolock(data, pg); unlock_page(pg); return ret; } diff --git a/fs/jffs2/fs.c b/fs/jffs2/fs.c index 112d85849db1..8a20ddd25f2d 100644 --- a/fs/jffs2/fs.c +++ b/fs/jffs2/fs.c @@ -687,7 +687,7 @@ unsigned char *jffs2_gc_fetch_page(struct jffs2_sb_info *c, struct page *pg; pg = read_cache_page(inode->i_mapping, offset >> PAGE_SHIFT, - (void *)jffs2_do_readpage_unlock, inode); + jffs2_do_readpage_unlock, inode); if (IS_ERR(pg)) return (void *)pg; diff --git a/fs/jffs2/os-linux.h b/fs/jffs2/os-linux.h index a2dbbb3f4c74..bd3d5f0ddc34 100644 --- a/fs/jffs2/os-linux.h +++ b/fs/jffs2/os-linux.h @@ -155,7 +155,7 @@ extern const struct file_operations jffs2_file_operations; extern const struct inode_operations jffs2_file_inode_operations; extern const struct address_space_operations jffs2_file_address_operations; int jffs2_fsync(struct file *, loff_t, loff_t, int); -int jffs2_do_readpage_unlock (struct inode *inode, struct page *pg); +int jffs2_do_readpage_unlock(void *data, struct page *pg); /* ioctl.c */ long jffs2_ioctl(struct file *, unsigned int, unsigned long); diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index b428c295d13f..5778d1347b35 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -288,10 +288,13 @@ struct fanotify_event *fanotify_alloc_event(struct fsnotify_group *group, /* * For queues with unlimited length lost events are not expected and * can possibly have security implications. Avoid losing events when - * memory is short. + * memory is short. For the limited size queues, avoid OOM killer in the + * target monitoring memcg as it may have security repercussion. */ if (group->max_events == UINT_MAX) gfp |= __GFP_NOFAIL; + else + gfp |= __GFP_RETRY_MAYFAIL; /* Whoever is interested in the event, pays for the allocation. */ memalloc_use_memcg(group->memcg); diff --git a/fs/notify/inotify/inotify_fsnotify.c b/fs/notify/inotify/inotify_fsnotify.c index 2fda08b2b885..d510223d302c 100644 --- a/fs/notify/inotify/inotify_fsnotify.c +++ b/fs/notify/inotify/inotify_fsnotify.c @@ -90,9 +90,13 @@ int inotify_handle_event(struct fsnotify_group *group, i_mark = container_of(inode_mark, struct inotify_inode_mark, fsn_mark); - /* Whoever is interested in the event, pays for the allocation. */ + /* + * Whoever is interested in the event, pays for the allocation. Do not + * trigger OOM killer in the target monitoring memcg as it may have + * security repercussion. + */ memalloc_use_memcg(group->memcg); - event = kmalloc(alloc_len, GFP_KERNEL_ACCOUNT); + event = kmalloc(alloc_len, GFP_KERNEL_ACCOUNT | __GFP_RETRY_MAYFAIL); memalloc_unuse_memcg(); if (unlikely(!event)) { diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c index d1348fc4ca6d..0c335b51043d 100644 --- a/fs/ocfs2/alloc.c +++ b/fs/ocfs2/alloc.c @@ -6191,17 +6191,17 @@ int ocfs2_begin_truncate_log_recovery(struct ocfs2_super *osb, if (le16_to_cpu(tl->tl_used)) { trace_ocfs2_truncate_log_recovery_num(le16_to_cpu(tl->tl_used)); - *tl_copy = kmalloc(tl_bh->b_size, GFP_KERNEL); + /* + * Assuming the write-out below goes well, this copy will be + * passed back to recovery for processing. + */ + *tl_copy = kmemdup(tl_bh->b_data, tl_bh->b_size, GFP_KERNEL); if (!(*tl_copy)) { status = -ENOMEM; mlog_errno(status); goto bail; } - /* Assuming the write-out below goes well, this copy - * will be passed back to recovery for processing. */ - memcpy(*tl_copy, tl_bh->b_data, tl_bh->b_size); - /* All we need to do to clear the truncate log is set * tl_used. */ tl->tl_used = 0; diff --git a/fs/ocfs2/blockcheck.c b/fs/ocfs2/blockcheck.c index 005b813a56b6..429e6a8359a5 100644 --- a/fs/ocfs2/blockcheck.c +++ b/fs/ocfs2/blockcheck.c @@ -242,57 +242,29 @@ static struct dentry *blockcheck_debugfs_create(const char *name, static void ocfs2_blockcheck_debug_remove(struct ocfs2_blockcheck_stats *stats) { if (stats) { - debugfs_remove(stats->b_debug_check); - stats->b_debug_check = NULL; - debugfs_remove(stats->b_debug_failure); - stats->b_debug_failure = NULL; - debugfs_remove(stats->b_debug_recover); - stats->b_debug_recover = NULL; - debugfs_remove(stats->b_debug_dir); + debugfs_remove_recursive(stats->b_debug_dir); stats->b_debug_dir = NULL; } } -static int ocfs2_blockcheck_debug_install(struct ocfs2_blockcheck_stats *stats, - struct dentry *parent) +static void ocfs2_blockcheck_debug_install(struct ocfs2_blockcheck_stats *stats, + struct dentry *parent) { - int rc = -EINVAL; - - if (!stats) - goto out; - stats->b_debug_dir = debugfs_create_dir("blockcheck", parent); - if (!stats->b_debug_dir) - goto out; - stats->b_debug_check = - blockcheck_debugfs_create("blocks_checked", - stats->b_debug_dir, - &stats->b_check_count); + blockcheck_debugfs_create("blocks_checked", stats->b_debug_dir, + &stats->b_check_count); - stats->b_debug_failure = - blockcheck_debugfs_create("checksums_failed", - stats->b_debug_dir, - &stats->b_failure_count); + blockcheck_debugfs_create("checksums_failed", stats->b_debug_dir, + &stats->b_failure_count); - stats->b_debug_recover = - blockcheck_debugfs_create("ecc_recoveries", - stats->b_debug_dir, - &stats->b_recover_count); - if (stats->b_debug_check && stats->b_debug_failure && - stats->b_debug_recover) - rc = 0; - -out: - if (rc) - ocfs2_blockcheck_debug_remove(stats); - return rc; + blockcheck_debugfs_create("ecc_recoveries", stats->b_debug_dir, + &stats->b_recover_count); } #else -static inline int ocfs2_blockcheck_debug_install(struct ocfs2_blockcheck_stats *stats, - struct dentry *parent) +static inline void ocfs2_blockcheck_debug_install(struct ocfs2_blockcheck_stats *stats, + struct dentry *parent) { - return 0; } static inline void ocfs2_blockcheck_debug_remove(struct ocfs2_blockcheck_stats *stats) @@ -301,10 +273,10 @@ static inline void ocfs2_blockcheck_debug_remove(struct ocfs2_blockcheck_stats * #endif /* CONFIG_DEBUG_FS */ /* Always-called wrappers for starting and stopping the debugfs files */ -int ocfs2_blockcheck_stats_debugfs_install(struct ocfs2_blockcheck_stats *stats, - struct dentry *parent) +void ocfs2_blockcheck_stats_debugfs_install(struct ocfs2_blockcheck_stats *stats, + struct dentry *parent) { - return ocfs2_blockcheck_debug_install(stats, parent); + ocfs2_blockcheck_debug_install(stats, parent); } void ocfs2_blockcheck_stats_debugfs_remove(struct ocfs2_blockcheck_stats *stats) diff --git a/fs/ocfs2/blockcheck.h b/fs/ocfs2/blockcheck.h index f2d2689407fa..8f17d2c85f40 100644 --- a/fs/ocfs2/blockcheck.h +++ b/fs/ocfs2/blockcheck.h @@ -25,9 +25,6 @@ struct ocfs2_blockcheck_stats { * ocfs2_blockcheck_stats_debugfs_install() */ struct dentry *b_debug_dir; /* Parent of the debugfs files */ - struct dentry *b_debug_check; /* Exposes b_check_count */ - struct dentry *b_debug_failure; /* Exposes b_failure_count */ - struct dentry *b_debug_recover; /* Exposes b_recover_count */ }; @@ -56,8 +53,8 @@ int ocfs2_block_check_validate_bhs(struct buffer_head **bhs, int nr, struct ocfs2_blockcheck_stats *stats); /* Debug Initialization */ -int ocfs2_blockcheck_stats_debugfs_install(struct ocfs2_blockcheck_stats *stats, - struct dentry *parent); +void ocfs2_blockcheck_stats_debugfs_install(struct ocfs2_blockcheck_stats *stats, + struct dentry *parent); void ocfs2_blockcheck_stats_debugfs_remove(struct ocfs2_blockcheck_stats *stats); /* diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c index 7a3a096856a8..f1b613327ac8 100644 --- a/fs/ocfs2/cluster/heartbeat.c +++ b/fs/ocfs2/cluster/heartbeat.c @@ -92,10 +92,6 @@ static struct o2hb_debug_buf *o2hb_db_failedregions; #define O2HB_DEBUG_REGION_PINNED "pinned" static struct dentry *o2hb_debug_dir; -static struct dentry *o2hb_debug_livenodes; -static struct dentry *o2hb_debug_liveregions; -static struct dentry *o2hb_debug_quorumregions; -static struct dentry *o2hb_debug_failedregions; static LIST_HEAD(o2hb_all_regions); @@ -1184,7 +1180,7 @@ bail: if (atomic_read(®->hr_steady_iterations) != 0) { if (atomic_dec_and_test(®->hr_unsteady_iterations)) { printk(KERN_NOTICE "o2hb: Unable to stabilize " - "heartbeart on region %s (%s)\n", + "heartbeat on region %s (%s)\n", config_item_name(®->hr_item), reg->hr_dev_name); atomic_set(®->hr_steady_iterations, 0); @@ -1391,11 +1387,7 @@ static const struct file_operations o2hb_debug_fops = { void o2hb_exit(void) { - debugfs_remove(o2hb_debug_failedregions); - debugfs_remove(o2hb_debug_quorumregions); - debugfs_remove(o2hb_debug_liveregions); - debugfs_remove(o2hb_debug_livenodes); - debugfs_remove(o2hb_debug_dir); + debugfs_remove_recursive(o2hb_debug_dir); kfree(o2hb_db_livenodes); kfree(o2hb_db_liveregions); kfree(o2hb_db_quorumregions); @@ -1419,79 +1411,37 @@ static struct dentry *o2hb_debug_create(const char *name, struct dentry *dir, &o2hb_debug_fops); } -static int o2hb_debug_init(void) +static void o2hb_debug_init(void) { - int ret = -ENOMEM; - o2hb_debug_dir = debugfs_create_dir(O2HB_DEBUG_DIR, NULL); - if (!o2hb_debug_dir) { - mlog_errno(ret); - goto bail; - } - o2hb_debug_livenodes = o2hb_debug_create(O2HB_DEBUG_LIVENODES, - o2hb_debug_dir, - &o2hb_db_livenodes, - sizeof(*o2hb_db_livenodes), - O2HB_DB_TYPE_LIVENODES, - sizeof(o2hb_live_node_bitmap), - O2NM_MAX_NODES, - o2hb_live_node_bitmap); - if (!o2hb_debug_livenodes) { - mlog_errno(ret); - goto bail; - } + o2hb_debug_create(O2HB_DEBUG_LIVENODES, o2hb_debug_dir, + &o2hb_db_livenodes, sizeof(*o2hb_db_livenodes), + O2HB_DB_TYPE_LIVENODES, sizeof(o2hb_live_node_bitmap), + O2NM_MAX_NODES, o2hb_live_node_bitmap); - o2hb_debug_liveregions = o2hb_debug_create(O2HB_DEBUG_LIVEREGIONS, - o2hb_debug_dir, - &o2hb_db_liveregions, - sizeof(*o2hb_db_liveregions), - O2HB_DB_TYPE_LIVEREGIONS, - sizeof(o2hb_live_region_bitmap), - O2NM_MAX_REGIONS, - o2hb_live_region_bitmap); - if (!o2hb_debug_liveregions) { - mlog_errno(ret); - goto bail; - } + o2hb_debug_create(O2HB_DEBUG_LIVEREGIONS, o2hb_debug_dir, + &o2hb_db_liveregions, sizeof(*o2hb_db_liveregions), + O2HB_DB_TYPE_LIVEREGIONS, + sizeof(o2hb_live_region_bitmap), O2NM_MAX_REGIONS, + o2hb_live_region_bitmap); - o2hb_debug_quorumregions = - o2hb_debug_create(O2HB_DEBUG_QUORUMREGIONS, - o2hb_debug_dir, - &o2hb_db_quorumregions, - sizeof(*o2hb_db_quorumregions), - O2HB_DB_TYPE_QUORUMREGIONS, - sizeof(o2hb_quorum_region_bitmap), - O2NM_MAX_REGIONS, - o2hb_quorum_region_bitmap); - if (!o2hb_debug_quorumregions) { - mlog_errno(ret); - goto bail; - } - - o2hb_debug_failedregions = - o2hb_debug_create(O2HB_DEBUG_FAILEDREGIONS, - o2hb_debug_dir, - &o2hb_db_failedregions, - sizeof(*o2hb_db_failedregions), - O2HB_DB_TYPE_FAILEDREGIONS, - sizeof(o2hb_failed_region_bitmap), - O2NM_MAX_REGIONS, - o2hb_failed_region_bitmap); - if (!o2hb_debug_failedregions) { - mlog_errno(ret); - goto bail; - } + o2hb_debug_create(O2HB_DEBUG_QUORUMREGIONS, o2hb_debug_dir, + &o2hb_db_quorumregions, + sizeof(*o2hb_db_quorumregions), + O2HB_DB_TYPE_QUORUMREGIONS, + sizeof(o2hb_quorum_region_bitmap), O2NM_MAX_REGIONS, + o2hb_quorum_region_bitmap); - ret = 0; -bail: - if (ret) - o2hb_exit(); - - return ret; + o2hb_debug_create(O2HB_DEBUG_FAILEDREGIONS, o2hb_debug_dir, + &o2hb_db_failedregions, + sizeof(*o2hb_db_failedregions), + O2HB_DB_TYPE_FAILEDREGIONS, + sizeof(o2hb_failed_region_bitmap), O2NM_MAX_REGIONS, + o2hb_failed_region_bitmap); } -int o2hb_init(void) +void o2hb_init(void) { int i; @@ -1511,7 +1461,7 @@ int o2hb_init(void) o2hb_dependent_users = 0; - return o2hb_debug_init(); + o2hb_debug_init(); } /* if we're already in a callback then we're already serialized by the sem */ diff --git a/fs/ocfs2/cluster/heartbeat.h b/fs/ocfs2/cluster/heartbeat.h index 7f37540ac4ab..beed31ea86cf 100644 --- a/fs/ocfs2/cluster/heartbeat.h +++ b/fs/ocfs2/cluster/heartbeat.h @@ -63,7 +63,7 @@ void o2hb_unregister_callback(const char *region_uuid, void o2hb_fill_node_map(unsigned long *map, unsigned bytes); void o2hb_exit(void); -int o2hb_init(void); +void o2hb_init(void); int o2hb_check_node_heartbeating_no_sem(u8 node_num); int o2hb_check_node_heartbeating_from_callback(u8 node_num); void o2hb_stop_all_regions(void); diff --git a/fs/ocfs2/cluster/netdebug.c b/fs/ocfs2/cluster/netdebug.c index 0784575f4c2a..02bf4a1774cc 100644 --- a/fs/ocfs2/cluster/netdebug.c +++ b/fs/ocfs2/cluster/netdebug.c @@ -38,10 +38,6 @@ #define SHOW_SOCK_STATS 1 static struct dentry *o2net_dentry; -static struct dentry *sc_dentry; -static struct dentry *nst_dentry; -static struct dentry *stats_dentry; -static struct dentry *nodes_dentry; static DEFINE_SPINLOCK(o2net_debug_lock); @@ -490,36 +486,23 @@ static const struct file_operations nodes_fops = { void o2net_debugfs_exit(void) { - debugfs_remove(nodes_dentry); - debugfs_remove(stats_dentry); - debugfs_remove(sc_dentry); - debugfs_remove(nst_dentry); - debugfs_remove(o2net_dentry); + debugfs_remove_recursive(o2net_dentry); } -int o2net_debugfs_init(void) +void o2net_debugfs_init(void) { umode_t mode = S_IFREG|S_IRUSR; o2net_dentry = debugfs_create_dir(O2NET_DEBUG_DIR, NULL); - if (o2net_dentry) - nst_dentry = debugfs_create_file(NST_DEBUG_NAME, mode, - o2net_dentry, NULL, &nst_seq_fops); - if (nst_dentry) - sc_dentry = debugfs_create_file(SC_DEBUG_NAME, mode, - o2net_dentry, NULL, &sc_seq_fops); - if (sc_dentry) - stats_dentry = debugfs_create_file(STATS_DEBUG_NAME, mode, - o2net_dentry, NULL, &stats_seq_fops); - if (stats_dentry) - nodes_dentry = debugfs_create_file(NODES_DEBUG_NAME, mode, - o2net_dentry, NULL, &nodes_fops); - if (nodes_dentry) - return 0; - - o2net_debugfs_exit(); - mlog_errno(-ENOMEM); - return -ENOMEM; + + debugfs_create_file(NST_DEBUG_NAME, mode, o2net_dentry, NULL, + &nst_seq_fops); + debugfs_create_file(SC_DEBUG_NAME, mode, o2net_dentry, NULL, + &sc_seq_fops); + debugfs_create_file(STATS_DEBUG_NAME, mode, o2net_dentry, NULL, + &stats_seq_fops); + debugfs_create_file(NODES_DEBUG_NAME, mode, o2net_dentry, NULL, + &nodes_fops); } #endif /* CONFIG_DEBUG_FS */ diff --git a/fs/ocfs2/cluster/nodemanager.c b/fs/ocfs2/cluster/nodemanager.c index 2234f7fd1f7c..7a7640c59f3c 100644 --- a/fs/ocfs2/cluster/nodemanager.c +++ b/fs/ocfs2/cluster/nodemanager.c @@ -828,9 +828,7 @@ static int __init init_o2nm(void) { int ret = -1; - ret = o2hb_init(); - if (ret) - goto out; + o2hb_init(); ret = o2net_init(); if (ret) diff --git a/fs/ocfs2/cluster/quorum.c b/fs/ocfs2/cluster/quorum.c index 3d5d4b2b1356..5c424a099280 100644 --- a/fs/ocfs2/cluster/quorum.c +++ b/fs/ocfs2/cluster/quorum.c @@ -76,7 +76,7 @@ static void o2quo_fence_self(void) }; } -/* Indicate that a timeout occurred on a hearbeat region write. The +/* Indicate that a timeout occurred on a heartbeat region write. The * other nodes in the cluster may consider us dead at that time so we * want to "fence" ourselves so that we don't scribble on the disk * after they think they've recovered us. This can't solve all diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c index c599463d0694..48a3398f0bf5 100644 --- a/fs/ocfs2/cluster/tcp.c +++ b/fs/ocfs2/cluster/tcp.c @@ -1762,7 +1762,7 @@ static void o2net_hb_node_up_cb(struct o2nm_node *node, int node_num, (msecs_to_jiffies(o2net_reconnect_delay()) + 1); if (node_num != o2nm_this_node()) { - /* believe it or not, accept and node hearbeating testing + /* believe it or not, accept and node heartbeating testing * can succeed for this node before we got here.. so * only use set_nn_state to clear the persistent error * if that hasn't already happened */ @@ -2129,8 +2129,7 @@ int o2net_init(void) o2quo_init(); - if (o2net_debugfs_init()) - goto out; + o2net_debugfs_init(); o2net_hand = kzalloc(sizeof(struct o2net_handshake), GFP_KERNEL); o2net_keep_req = kzalloc(sizeof(struct o2net_msg), GFP_KERNEL); diff --git a/fs/ocfs2/cluster/tcp.h b/fs/ocfs2/cluster/tcp.h index dd4242be3f1f..de87cbffd175 100644 --- a/fs/ocfs2/cluster/tcp.h +++ b/fs/ocfs2/cluster/tcp.h @@ -109,16 +109,15 @@ struct o2net_send_tracking; struct o2net_sock_container; #ifdef CONFIG_DEBUG_FS -int o2net_debugfs_init(void); +void o2net_debugfs_init(void); void o2net_debugfs_exit(void); void o2net_debug_add_nst(struct o2net_send_tracking *nst); void o2net_debug_del_nst(struct o2net_send_tracking *nst); void o2net_debug_add_sc(struct o2net_sock_container *sc); void o2net_debug_del_sc(struct o2net_sock_container *sc); #else -static inline int o2net_debugfs_init(void) +static inline void o2net_debugfs_init(void) { - return 0; } static inline void o2net_debugfs_exit(void) { diff --git a/fs/ocfs2/dlm/dlmdebug.c b/fs/ocfs2/dlm/dlmdebug.c index c8af5bc9e980..a4b58ba99927 100644 --- a/fs/ocfs2/dlm/dlmdebug.c +++ b/fs/ocfs2/dlm/dlmdebug.c @@ -851,7 +851,7 @@ static const struct file_operations debug_state_fops = { /* end - debug state funcs */ /* files in subroot */ -int dlm_debug_init(struct dlm_ctxt *dlm) +void dlm_debug_init(struct dlm_ctxt *dlm) { struct dlm_debug_ctxt *dc = dlm->dlm_debug_ctxt; @@ -860,10 +860,6 @@ int dlm_debug_init(struct dlm_ctxt *dlm) S_IFREG|S_IRUSR, dlm->dlm_debugfs_subroot, dlm, &debug_state_fops); - if (!dc->debug_state_dentry) { - mlog_errno(-ENOMEM); - goto bail; - } /* for dumping lockres */ dc->debug_lockres_dentry = @@ -871,20 +867,12 @@ int dlm_debug_init(struct dlm_ctxt *dlm) S_IFREG|S_IRUSR, dlm->dlm_debugfs_subroot, dlm, &debug_lockres_fops); - if (!dc->debug_lockres_dentry) { - mlog_errno(-ENOMEM); - goto bail; - } /* for dumping mles */ dc->debug_mle_dentry = debugfs_create_file(DLM_DEBUGFS_MLE_STATE, S_IFREG|S_IRUSR, dlm->dlm_debugfs_subroot, dlm, &debug_mle_fops); - if (!dc->debug_mle_dentry) { - mlog_errno(-ENOMEM); - goto bail; - } /* for dumping lockres on the purge list */ dc->debug_purgelist_dentry = @@ -892,15 +880,6 @@ int dlm_debug_init(struct dlm_ctxt *dlm) S_IFREG|S_IRUSR, dlm->dlm_debugfs_subroot, dlm, &debug_purgelist_fops); - if (!dc->debug_purgelist_dentry) { - mlog_errno(-ENOMEM); - goto bail; - } - - return 0; - -bail: - return -ENOMEM; } void dlm_debug_shutdown(struct dlm_ctxt *dlm) @@ -920,24 +899,16 @@ void dlm_debug_shutdown(struct dlm_ctxt *dlm) /* subroot - domain dir */ int dlm_create_debugfs_subroot(struct dlm_ctxt *dlm) { - dlm->dlm_debugfs_subroot = debugfs_create_dir(dlm->name, - dlm_debugfs_root); - if (!dlm->dlm_debugfs_subroot) { - mlog_errno(-ENOMEM); - goto bail; - } - dlm->dlm_debug_ctxt = kzalloc(sizeof(struct dlm_debug_ctxt), GFP_KERNEL); if (!dlm->dlm_debug_ctxt) { mlog_errno(-ENOMEM); - goto bail; + return -ENOMEM; } + dlm->dlm_debugfs_subroot = debugfs_create_dir(dlm->name, + dlm_debugfs_root); return 0; -bail: - dlm_destroy_debugfs_subroot(dlm); - return -ENOMEM; } void dlm_destroy_debugfs_subroot(struct dlm_ctxt *dlm) @@ -946,14 +917,9 @@ void dlm_destroy_debugfs_subroot(struct dlm_ctxt *dlm) } /* debugfs root */ -int dlm_create_debugfs_root(void) +void dlm_create_debugfs_root(void) { dlm_debugfs_root = debugfs_create_dir(DLM_DEBUGFS_DIR, NULL); - if (!dlm_debugfs_root) { - mlog_errno(-ENOMEM); - return -ENOMEM; - } - return 0; } void dlm_destroy_debugfs_root(void) diff --git a/fs/ocfs2/dlm/dlmdebug.h b/fs/ocfs2/dlm/dlmdebug.h index 74d019694c7e..7d0c7c9013ce 100644 --- a/fs/ocfs2/dlm/dlmdebug.h +++ b/fs/ocfs2/dlm/dlmdebug.h @@ -28,20 +28,19 @@ struct debug_lockres { struct dlm_lock_resource *dl_res; }; -int dlm_debug_init(struct dlm_ctxt *dlm); +void dlm_debug_init(struct dlm_ctxt *dlm); void dlm_debug_shutdown(struct dlm_ctxt *dlm); int dlm_create_debugfs_subroot(struct dlm_ctxt *dlm); void dlm_destroy_debugfs_subroot(struct dlm_ctxt *dlm); -int dlm_create_debugfs_root(void); +void dlm_create_debugfs_root(void); void dlm_destroy_debugfs_root(void); #else -static inline int dlm_debug_init(struct dlm_ctxt *dlm) +static inline void dlm_debug_init(struct dlm_ctxt *dlm) { - return 0; } static inline void dlm_debug_shutdown(struct dlm_ctxt *dlm) { @@ -53,9 +52,8 @@ static inline int dlm_create_debugfs_subroot(struct dlm_ctxt *dlm) static inline void dlm_destroy_debugfs_subroot(struct dlm_ctxt *dlm) { } -static inline int dlm_create_debugfs_root(void) +static inline void dlm_create_debugfs_root(void) { - return 0; } static inline void dlm_destroy_debugfs_root(void) { diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c index 9021e72e1f98..7338b5d4647c 100644 --- a/fs/ocfs2/dlm/dlmdomain.c +++ b/fs/ocfs2/dlm/dlmdomain.c @@ -1881,11 +1881,7 @@ static int dlm_join_domain(struct dlm_ctxt *dlm) goto bail; } - status = dlm_debug_init(dlm); - if (status < 0) { - mlog_errno(status); - goto bail; - } + dlm_debug_init(dlm); snprintf(wq_name, O2NM_MAX_NAME_LEN, "dlm_wq-%s", dlm->name); dlm->dlm_worker = alloc_workqueue(wq_name, WQ_MEM_RECLAIM, 0); @@ -2346,9 +2342,7 @@ static int __init dlm_init(void) goto error; } - status = dlm_create_debugfs_root(); - if (status) - goto error; + dlm_create_debugfs_root(); return 0; error: diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c index 810f841494ef..74b768ca1cd8 100644 --- a/fs/ocfs2/dlm/dlmmaster.c +++ b/fs/ocfs2/dlm/dlmmaster.c @@ -2161,7 +2161,7 @@ put: * think that $RECOVERY is currently mastered by a dead node. If so, * we wait a short time to allow that node to get notified by its own * heartbeat stack, then check again. All $RECOVERY lock resources - * mastered by dead nodes are purged when the hearbeat callback is + * mastered by dead nodes are purged when the heartbeat callback is * fired, so we can know for sure that it is safe to continue once * the node returns a live node or no node. */ static int dlm_pre_master_reco_lockres(struct dlm_ctxt *dlm, diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c index e22d6a115220..064ce5bbc3f6 100644 --- a/fs/ocfs2/dlm/dlmrecovery.c +++ b/fs/ocfs2/dlm/dlmrecovery.c @@ -1109,7 +1109,7 @@ static int dlm_send_mig_lockres_msg(struct dlm_ctxt *dlm, { u64 mig_cookie = be64_to_cpu(mres->mig_cookie); int mres_total_locks = be32_to_cpu(mres->total_locks); - int sz, ret = 0, status = 0; + int ret = 0, status = 0; u8 orig_flags = mres->flags, orig_master = mres->master; @@ -1117,9 +1117,6 @@ static int dlm_send_mig_lockres_msg(struct dlm_ctxt *dlm, if (!mres->num_locks) return 0; - sz = sizeof(struct dlm_migratable_lockres) + - (mres->num_locks * sizeof(struct dlm_migratable_lock)); - /* add an all-done flag if we reached the last lock */ orig_flags = mres->flags; BUG_ON(total_locks > mres_total_locks); @@ -1133,7 +1130,8 @@ static int dlm_send_mig_lockres_msg(struct dlm_ctxt *dlm, /* send it */ ret = o2net_send_message(DLM_MIG_LOCKRES_MSG, dlm->key, mres, - sz, send_to, &status); + struct_size(mres, ml, mres->num_locks), + send_to, &status); if (ret < 0) { /* XXX: negative status is not handled. * this will end up killing this node. */ diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c index b5fc5d3c7525..14207234fa3d 100644 --- a/fs/ocfs2/dlmglue.c +++ b/fs/ocfs2/dlmglue.c @@ -426,6 +426,7 @@ static void ocfs2_remove_lockres_tracking(struct ocfs2_lock_res *res) static void ocfs2_init_lock_stats(struct ocfs2_lock_res *res) { res->l_lock_refresh = 0; + res->l_lock_wait = 0; memset(&res->l_lock_prmode, 0, sizeof(struct ocfs2_lock_stats)); memset(&res->l_lock_exmode, 0, sizeof(struct ocfs2_lock_stats)); } @@ -460,6 +461,8 @@ static void ocfs2_update_lock_stats(struct ocfs2_lock_res *res, int level, if (ret) stats->ls_fail++; + + stats->ls_last = ktime_to_us(ktime_get_real()); } static inline void ocfs2_track_lock_refresh(struct ocfs2_lock_res *lockres) @@ -467,6 +470,21 @@ static inline void ocfs2_track_lock_refresh(struct ocfs2_lock_res *lockres) lockres->l_lock_refresh++; } +static inline void ocfs2_track_lock_wait(struct ocfs2_lock_res *lockres) +{ + struct ocfs2_mask_waiter *mw; + + if (list_empty(&lockres->l_mask_waiters)) { + lockres->l_lock_wait = 0; + return; + } + + mw = list_first_entry(&lockres->l_mask_waiters, + struct ocfs2_mask_waiter, mw_item); + lockres->l_lock_wait = + ktime_to_us(ktime_mono_to_real(mw->mw_lock_start)); +} + static inline void ocfs2_init_start_time(struct ocfs2_mask_waiter *mw) { mw->mw_lock_start = ktime_get(); @@ -482,6 +500,9 @@ static inline void ocfs2_update_lock_stats(struct ocfs2_lock_res *res, static inline void ocfs2_track_lock_refresh(struct ocfs2_lock_res *lockres) { } +static inline void ocfs2_track_lock_wait(struct ocfs2_lock_res *lockres) +{ +} static inline void ocfs2_init_start_time(struct ocfs2_mask_waiter *mw) { } @@ -875,6 +896,7 @@ static void lockres_set_flags(struct ocfs2_lock_res *lockres, list_del_init(&mw->mw_item); mw->mw_status = 0; complete(&mw->mw_complete); + ocfs2_track_lock_wait(lockres); } } static void lockres_or_flags(struct ocfs2_lock_res *lockres, unsigned long or) @@ -1386,6 +1408,7 @@ static void lockres_add_mask_waiter(struct ocfs2_lock_res *lockres, list_add_tail(&mw->mw_item, &lockres->l_mask_waiters); mw->mw_mask = mask; mw->mw_goal = goal; + ocfs2_track_lock_wait(lockres); } /* returns 0 if the mw that was removed was already satisfied, -EBUSY @@ -1402,6 +1425,7 @@ static int __lockres_remove_mask_waiter(struct ocfs2_lock_res *lockres, list_del_init(&mw->mw_item); init_completion(&mw->mw_complete); + ocfs2_track_lock_wait(lockres); } return ret; @@ -2989,6 +3013,8 @@ struct ocfs2_dlm_debug *ocfs2_new_dlm_debug(void) kref_init(&dlm_debug->d_refcnt); INIT_LIST_HEAD(&dlm_debug->d_lockres_tracking); dlm_debug->d_locking_state = NULL; + dlm_debug->d_locking_filter = NULL; + dlm_debug->d_filter_secs = 0; out: return dlm_debug; } @@ -3079,17 +3105,43 @@ static void *ocfs2_dlm_seq_next(struct seq_file *m, void *v, loff_t *pos) * - Lock stats printed * New in version 3 * - Max time in lock stats is in usecs (instead of nsecs) + * New in version 4 + * - Add last pr/ex unlock times and first lock wait time in usecs */ -#define OCFS2_DLM_DEBUG_STR_VERSION 3 +#define OCFS2_DLM_DEBUG_STR_VERSION 4 static int ocfs2_dlm_seq_show(struct seq_file *m, void *v) { int i; char *lvb; struct ocfs2_lock_res *lockres = v; +#ifdef CONFIG_OCFS2_FS_STATS + u64 now, last; + struct ocfs2_dlm_debug *dlm_debug = + ((struct ocfs2_dlm_seq_priv *)m->private)->p_dlm_debug; +#endif if (!lockres) return -EINVAL; +#ifdef CONFIG_OCFS2_FS_STATS + if (!lockres->l_lock_wait && dlm_debug->d_filter_secs) { + now = ktime_to_us(ktime_get_real()); + if (lockres->l_lock_prmode.ls_last > + lockres->l_lock_exmode.ls_last) + last = lockres->l_lock_prmode.ls_last; + else + last = lockres->l_lock_exmode.ls_last; + /* + * Use d_filter_secs field to filter lock resources dump, + * the default d_filter_secs(0) value filters nothing, + * otherwise, only dump the last N seconds active lock + * resources. + */ + if (div_u64(now - last, 1000000) > dlm_debug->d_filter_secs) + return 0; + } +#endif + seq_printf(m, "0x%x\t", OCFS2_DLM_DEBUG_STR_VERSION); if (lockres->l_type == OCFS2_LOCK_TYPE_DENTRY) @@ -3131,6 +3183,9 @@ static int ocfs2_dlm_seq_show(struct seq_file *m, void *v) # define lock_max_prmode(_l) ((_l)->l_lock_prmode.ls_max) # define lock_max_exmode(_l) ((_l)->l_lock_exmode.ls_max) # define lock_refresh(_l) ((_l)->l_lock_refresh) +# define lock_last_prmode(_l) ((_l)->l_lock_prmode.ls_last) +# define lock_last_exmode(_l) ((_l)->l_lock_exmode.ls_last) +# define lock_wait(_l) ((_l)->l_lock_wait) #else # define lock_num_prmode(_l) (0) # define lock_num_exmode(_l) (0) @@ -3141,6 +3196,9 @@ static int ocfs2_dlm_seq_show(struct seq_file *m, void *v) # define lock_max_prmode(_l) (0) # define lock_max_exmode(_l) (0) # define lock_refresh(_l) (0) +# define lock_last_prmode(_l) (0ULL) +# define lock_last_exmode(_l) (0ULL) +# define lock_wait(_l) (0ULL) #endif /* The following seq_print was added in version 2 of this output */ seq_printf(m, "%u\t" @@ -3151,7 +3209,10 @@ static int ocfs2_dlm_seq_show(struct seq_file *m, void *v) "%llu\t" "%u\t" "%u\t" - "%u\t", + "%u\t" + "%llu\t" + "%llu\t" + "%llu\t", lock_num_prmode(lockres), lock_num_exmode(lockres), lock_num_prmode_failed(lockres), @@ -3160,7 +3221,10 @@ static int ocfs2_dlm_seq_show(struct seq_file *m, void *v) lock_total_exmode(lockres), lock_max_prmode(lockres), lock_max_exmode(lockres), - lock_refresh(lockres)); + lock_refresh(lockres), + lock_last_prmode(lockres), + lock_last_exmode(lockres), + lock_wait(lockres)); /* End the line */ seq_printf(m, "\n"); @@ -3214,9 +3278,8 @@ static const struct file_operations ocfs2_dlm_debug_fops = { .llseek = seq_lseek, }; -static int ocfs2_dlm_init_debug(struct ocfs2_super *osb) +static void ocfs2_dlm_init_debug(struct ocfs2_super *osb) { - int ret = 0; struct ocfs2_dlm_debug *dlm_debug = osb->osb_dlm_debug; dlm_debug->d_locking_state = debugfs_create_file("locking_state", @@ -3224,16 +3287,11 @@ static int ocfs2_dlm_init_debug(struct ocfs2_super *osb) osb->osb_debug_root, osb, &ocfs2_dlm_debug_fops); - if (!dlm_debug->d_locking_state) { - ret = -EINVAL; - mlog(ML_ERROR, - "Unable to create locking state debugfs file.\n"); - goto out; - } - ocfs2_get_dlm_debug(dlm_debug); -out: - return ret; + dlm_debug->d_locking_filter = debugfs_create_u32("locking_filter", + 0600, + osb->osb_debug_root, + &dlm_debug->d_filter_secs); } static void ocfs2_dlm_shutdown_debug(struct ocfs2_super *osb) @@ -3242,6 +3300,7 @@ static void ocfs2_dlm_shutdown_debug(struct ocfs2_super *osb) if (dlm_debug) { debugfs_remove(dlm_debug->d_locking_state); + debugfs_remove(dlm_debug->d_locking_filter); ocfs2_put_dlm_debug(dlm_debug); } } @@ -3256,11 +3315,7 @@ int ocfs2_dlm_init(struct ocfs2_super *osb) goto local; } - status = ocfs2_dlm_init_debug(osb); - if (status < 0) { - mlog_errno(status); - goto bail; - } + ocfs2_dlm_init_debug(osb); /* launch downconvert thread */ osb->dc_task = kthread_run(ocfs2_downconvert_thread, osb, "ocfs2dc-%s", @@ -4352,7 +4407,6 @@ static int ocfs2_downconvert_thread_should_wake(struct ocfs2_super *osb) static int ocfs2_downconvert_thread(void *arg) { - int status = 0; struct ocfs2_super *osb = arg; /* only quit once we've been asked to stop and there is no more @@ -4370,7 +4424,7 @@ static int ocfs2_downconvert_thread(void *arg) } osb->dc_task = NULL; - return status; + return 0; } void ocfs2_wake_downconvert_thread(struct ocfs2_super *osb) diff --git a/fs/ocfs2/localalloc.c b/fs/ocfs2/localalloc.c index f03674afbd30..158e5af767fd 100644 --- a/fs/ocfs2/localalloc.c +++ b/fs/ocfs2/localalloc.c @@ -424,12 +424,11 @@ void ocfs2_shutdown_local_alloc(struct ocfs2_super *osb) bh = osb->local_alloc_bh; alloc = (struct ocfs2_dinode *) bh->b_data; - alloc_copy = kmalloc(bh->b_size, GFP_NOFS); + alloc_copy = kmemdup(alloc, bh->b_size, GFP_NOFS); if (!alloc_copy) { status = -ENOMEM; goto out_commit; } - memcpy(alloc_copy, alloc, bh->b_size); status = ocfs2_journal_access_di(handle, INODE_CACHE(local_alloc_inode), bh, OCFS2_JOURNAL_ACCESS_WRITE); @@ -1272,13 +1271,12 @@ static int ocfs2_local_alloc_slide_window(struct ocfs2_super *osb, * local alloc shutdown won't try to double free main bitmap * bits. Make a copy so the sync function knows which bits to * free. */ - alloc_copy = kmalloc(osb->local_alloc_bh->b_size, GFP_NOFS); + alloc_copy = kmemdup(alloc, osb->local_alloc_bh->b_size, GFP_NOFS); if (!alloc_copy) { status = -ENOMEM; mlog_errno(status); goto bail; } - memcpy(alloc_copy, alloc, osb->local_alloc_bh->b_size); status = ocfs2_journal_access_di(handle, INODE_CACHE(local_alloc_inode), diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h index a4647a646f07..fddbbd60f434 100644 --- a/fs/ocfs2/ocfs2.h +++ b/fs/ocfs2/ocfs2.h @@ -150,6 +150,7 @@ struct ocfs2_lock_stats { /* Storing max wait in usecs saves 24 bytes per inode */ u32 ls_max; /* Max wait in USEC */ + u64 ls_last; /* Last unlock time in USEC */ }; #endif @@ -191,6 +192,7 @@ struct ocfs2_lock_res { #ifdef CONFIG_OCFS2_FS_STATS struct ocfs2_lock_stats l_lock_prmode; /* PR mode stats */ u32 l_lock_refresh; /* Disk refreshes */ + u64 l_lock_wait; /* First lock wait time */ struct ocfs2_lock_stats l_lock_exmode; /* EX mode stats */ #endif #ifdef CONFIG_DEBUG_LOCK_ALLOC @@ -222,6 +224,8 @@ struct ocfs2_orphan_scan { struct ocfs2_dlm_debug { struct kref d_refcnt; struct dentry *d_locking_state; + struct dentry *d_locking_filter; + u32 d_filter_secs; struct list_head d_lockres_tracking; }; diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index a201f9780b35..8b2f39506648 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -1079,33 +1079,15 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent) osb->osb_debug_root = debugfs_create_dir(osb->uuid_str, ocfs2_debugfs_root); - if (!osb->osb_debug_root) { - status = -EINVAL; - mlog(ML_ERROR, "Unable to create per-mount debugfs root.\n"); - goto read_super_error; - } osb->osb_ctxt = debugfs_create_file("fs_state", S_IFREG|S_IRUSR, osb->osb_debug_root, osb, &ocfs2_osb_debug_fops); - if (!osb->osb_ctxt) { - status = -EINVAL; - mlog_errno(status); - goto read_super_error; - } - if (ocfs2_meta_ecc(osb)) { - status = ocfs2_blockcheck_stats_debugfs_install( - &osb->osb_ecc_stats, - osb->osb_debug_root); - if (status) { - mlog(ML_ERROR, - "Unable to create blockcheck statistics " - "files\n"); - goto read_super_error; - } - } + if (ocfs2_meta_ecc(osb)) + ocfs2_blockcheck_stats_debugfs_install( &osb->osb_ecc_stats, + osb->osb_debug_root); status = ocfs2_mount_volume(sb); if (status < 0) @@ -1592,11 +1574,6 @@ static int __init ocfs2_init(void) goto out2; ocfs2_debugfs_root = debugfs_create_dir("ocfs2", NULL); - if (!ocfs2_debugfs_root) { - status = -ENOMEM; - mlog(ML_ERROR, "Unable to create ocfs2 debugfs root.\n"); - goto out3; - } ocfs2_set_locking_protocol(); diff --git a/fs/proc/base.c b/fs/proc/base.c index c40fca98f2b7..77eb628ecc7f 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -532,8 +532,7 @@ static int proc_oom_score(struct seq_file *m, struct pid_namespace *ns, unsigned long totalpages = totalram_pages() + total_swap_pages; unsigned long points = 0; - points = oom_badness(task, NULL, NULL, totalpages) * - 1000 / totalpages; + points = oom_badness(task, totalpages) * 1000 / totalpages; seq_printf(m, "%lu\n", points); return 0; @@ -1962,9 +1961,12 @@ static int map_files_d_revalidate(struct dentry *dentry, unsigned int flags) goto out; if (!dname_to_vma_addr(dentry, &vm_start, &vm_end)) { - down_read(&mm->mmap_sem); - exact_vma_exists = !!find_exact_vma(mm, vm_start, vm_end); - up_read(&mm->mmap_sem); + status = down_read_killable(&mm->mmap_sem); + if (!status) { + exact_vma_exists = !!find_exact_vma(mm, vm_start, + vm_end); + up_read(&mm->mmap_sem); + } } mmput(mm); @@ -2010,8 +2012,11 @@ static int map_files_get_link(struct dentry *dentry, struct path *path) if (rc) goto out_mmput; + rc = down_read_killable(&mm->mmap_sem); + if (rc) + goto out_mmput; + rc = -ENOENT; - down_read(&mm->mmap_sem); vma = find_exact_vma(mm, vm_start, vm_end); if (vma && vma->vm_file) { *path = vma->vm_file->f_path; @@ -2107,7 +2112,11 @@ static struct dentry *proc_map_files_lookup(struct inode *dir, if (!mm) goto out_put_task; - down_read(&mm->mmap_sem); + result = ERR_PTR(-EINTR); + if (down_read_killable(&mm->mmap_sem)) + goto out_put_mm; + + result = ERR_PTR(-ENOENT); vma = find_exact_vma(mm, vm_start, vm_end); if (!vma) goto out_no_vma; @@ -2118,6 +2127,7 @@ static struct dentry *proc_map_files_lookup(struct inode *dir, out_no_vma: up_read(&mm->mmap_sem); +out_put_mm: mmput(mm); out_put_task: put_task_struct(task); @@ -2160,7 +2170,12 @@ proc_map_files_readdir(struct file *file, struct dir_context *ctx) mm = get_task_mm(task); if (!mm) goto out_put_task; - down_read(&mm->mmap_sem); + + ret = down_read_killable(&mm->mmap_sem); + if (ret) { + mmput(mm); + goto out_put_task; + } nr_files = 0; diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c index 568d90e17c17..465ea0153b2a 100644 --- a/fs/proc/meminfo.c +++ b/fs/proc/meminfo.c @@ -120,7 +120,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v) show_val_kb(m, "Committed_AS: ", committed); seq_printf(m, "VmallocTotal: %8lu kB\n", (unsigned long)VMALLOC_TOTAL >> 10); - show_val_kb(m, "VmallocUsed: ", 0ul); + show_val_kb(m, "VmallocUsed: ", vmalloc_nr_pages()); show_val_kb(m, "VmallocChunk: ", 0ul); show_val_kb(m, "Percpu: ", pcpu_nr_pages()); diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 01d4eb0e6bd1..dedca3da428a 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -166,7 +166,11 @@ static void *m_start(struct seq_file *m, loff_t *ppos) if (!mm || !mmget_not_zero(mm)) return NULL; - down_read(&mm->mmap_sem); + if (down_read_killable(&mm->mmap_sem)) { + mmput(mm); + return ERR_PTR(-EINTR); + } + hold_task_mempolicy(priv); priv->tail_vma = get_gate_vma(mm); @@ -417,17 +421,53 @@ struct mem_size_stats { unsigned long shared_hugetlb; unsigned long private_hugetlb; u64 pss; + u64 pss_anon; + u64 pss_file; + u64 pss_shmem; u64 pss_locked; u64 swap_pss; bool check_shmem_swap; }; +static void smaps_page_accumulate(struct mem_size_stats *mss, + struct page *page, unsigned long size, unsigned long pss, + bool dirty, bool locked, bool private) +{ + mss->pss += pss; + + if (PageAnon(page)) + mss->pss_anon += pss; + else if (PageSwapBacked(page)) + mss->pss_shmem += pss; + else + mss->pss_file += pss; + + if (locked) + mss->pss_locked += pss; + + if (dirty || PageDirty(page)) { + if (private) + mss->private_dirty += size; + else + mss->shared_dirty += size; + } else { + if (private) + mss->private_clean += size; + else + mss->shared_clean += size; + } +} + static void smaps_account(struct mem_size_stats *mss, struct page *page, bool compound, bool young, bool dirty, bool locked) { int i, nr = compound ? 1 << compound_order(page) : 1; unsigned long size = nr * PAGE_SIZE; + /* + * First accumulate quantities that depend only on |size| and the type + * of the compound page. + */ if (PageAnon(page)) { mss->anonymous += size; if (!PageSwapBacked(page) && !dirty && !PageDirty(page)) @@ -440,42 +480,25 @@ static void smaps_account(struct mem_size_stats *mss, struct page *page, mss->referenced += size; /* + * Then accumulate quantities that may depend on sharing, or that may + * differ page-by-page. + * * page_count(page) == 1 guarantees the page is mapped exactly once. * If any subpage of the compound page mapped with PTE it would elevate * page_count(). */ if (page_count(page) == 1) { - if (dirty || PageDirty(page)) - mss->private_dirty += size; - else - mss->private_clean += size; - mss->pss += (u64)size << PSS_SHIFT; - if (locked) - mss->pss_locked += (u64)size << PSS_SHIFT; + smaps_page_accumulate(mss, page, size, size << PSS_SHIFT, dirty, + locked, true); return; } - for (i = 0; i < nr; i++, page++) { int mapcount = page_mapcount(page); - unsigned long pss = (PAGE_SIZE << PSS_SHIFT); - - if (mapcount >= 2) { - if (dirty || PageDirty(page)) - mss->shared_dirty += PAGE_SIZE; - else - mss->shared_clean += PAGE_SIZE; - mss->pss += pss / mapcount; - if (locked) - mss->pss_locked += pss / mapcount; - } else { - if (dirty || PageDirty(page)) - mss->private_dirty += PAGE_SIZE; - else - mss->private_clean += PAGE_SIZE; - mss->pss += pss; - if (locked) - mss->pss_locked += pss; - } + unsigned long pss = PAGE_SIZE << PSS_SHIFT; + if (mapcount >= 2) + pss /= mapcount; + smaps_page_accumulate(mss, page, PAGE_SIZE, pss, dirty, locked, + mapcount < 2); } } @@ -754,10 +777,23 @@ static void smap_gather_stats(struct vm_area_struct *vma, seq_put_decimal_ull_width(m, str, (val) >> 10, 8) /* Show the contents common for smaps and smaps_rollup */ -static void __show_smap(struct seq_file *m, const struct mem_size_stats *mss) +static void __show_smap(struct seq_file *m, const struct mem_size_stats *mss, + bool rollup_mode) { SEQ_PUT_DEC("Rss: ", mss->resident); SEQ_PUT_DEC(" kB\nPss: ", mss->pss >> PSS_SHIFT); + if (rollup_mode) { + /* + * These are meaningful only for smaps_rollup, otherwise two of + * them are zero, and the other one is the same as Pss. + */ + SEQ_PUT_DEC(" kB\nPss_Anon: ", + mss->pss_anon >> PSS_SHIFT); + SEQ_PUT_DEC(" kB\nPss_File: ", + mss->pss_file >> PSS_SHIFT); + SEQ_PUT_DEC(" kB\nPss_Shmem: ", + mss->pss_shmem >> PSS_SHIFT); + } SEQ_PUT_DEC(" kB\nShared_Clean: ", mss->shared_clean); SEQ_PUT_DEC(" kB\nShared_Dirty: ", mss->shared_dirty); SEQ_PUT_DEC(" kB\nPrivate_Clean: ", mss->private_clean); @@ -794,7 +830,7 @@ static int show_smap(struct seq_file *m, void *v) SEQ_PUT_DEC(" kB\nMMUPageSize: ", vma_mmu_pagesize(vma)); seq_puts(m, " kB\n"); - __show_smap(m, &mss); + __show_smap(m, &mss, false); seq_printf(m, "THPeligible: %d\n", transparent_hugepage_enabled(vma)); @@ -828,7 +864,10 @@ static int show_smaps_rollup(struct seq_file *m, void *v) memset(&mss, 0, sizeof(mss)); - down_read(&mm->mmap_sem); + ret = down_read_killable(&mm->mmap_sem); + if (ret) + goto out_put_mm; + hold_task_mempolicy(priv); for (vma = priv->mm->mmap; vma; vma = vma->vm_next) { @@ -841,12 +880,13 @@ static int show_smaps_rollup(struct seq_file *m, void *v) seq_pad(m, ' '); seq_puts(m, "[rollup]\n"); - __show_smap(m, &mss); + __show_smap(m, &mss, true); release_task_mempolicy(priv); up_read(&mm->mmap_sem); - mmput(mm); +out_put_mm: + mmput(mm); out_put_task: put_task_struct(priv->task); priv->task = NULL; @@ -1132,7 +1172,10 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf, goto out_mm; } - down_read(&mm->mmap_sem); + if (down_read_killable(&mm->mmap_sem)) { + count = -EINTR; + goto out_mm; + } tlb_gather_mmu(&tlb, mm, 0, -1); if (type == CLEAR_REFS_SOFT_DIRTY) { for (vma = mm->mmap; vma; vma = vma->vm_next) { @@ -1539,7 +1582,9 @@ static ssize_t pagemap_read(struct file *file, char __user *buf, /* overflow ? */ if (end < start_vaddr || end > end_vaddr) end = end_vaddr; - down_read(&mm->mmap_sem); + ret = down_read_killable(&mm->mmap_sem); + if (ret) + goto out_free; ret = walk_page_range(start_vaddr, end, &pagemap_walk); up_read(&mm->mmap_sem); start_vaddr = end; diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c index 36bf0f2e102e..7907e6419e57 100644 --- a/fs/proc/task_nommu.c +++ b/fs/proc/task_nommu.c @@ -211,7 +211,11 @@ static void *m_start(struct seq_file *m, loff_t *pos) if (!mm || !mmget_not_zero(mm)) return NULL; - down_read(&mm->mmap_sem); + if (down_read_killable(&mm->mmap_sem)) { + mmput(mm); + return ERR_PTR(-EINTR); + } + /* start from the Nth VMA */ for (p = rb_first(&mm->mm_rb); p; p = rb_next(p)) if (n-- == 0) diff --git a/include/asm-generic/bitops-instrumented.h b/include/asm-generic/bitops-instrumented.h new file mode 100644 index 000000000000..ddd1c6d9d8db --- /dev/null +++ b/include/asm-generic/bitops-instrumented.h @@ -0,0 +1,263 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* + * This file provides wrappers with sanitizer instrumentation for bit + * operations. + * + * To use this functionality, an arch's bitops.h file needs to define each of + * the below bit operations with an arch_ prefix (e.g. arch_set_bit(), + * arch___set_bit(), etc.). + */ +#ifndef _ASM_GENERIC_BITOPS_INSTRUMENTED_H +#define _ASM_GENERIC_BITOPS_INSTRUMENTED_H + +#include <linux/kasan-checks.h> + +/** + * set_bit - Atomically set a bit in memory + * @nr: the bit to set + * @addr: the address to start counting from + * + * This is a relaxed atomic operation (no implied memory barriers). + * + * Note that @nr may be almost arbitrarily large; this function is not + * restricted to acting on a single-word quantity. + */ +static inline void set_bit(long nr, volatile unsigned long *addr) +{ + kasan_check_write(addr + BIT_WORD(nr), sizeof(long)); + arch_set_bit(nr, addr); +} + +/** + * __set_bit - Set a bit in memory + * @nr: the bit to set + * @addr: the address to start counting from + * + * Unlike set_bit(), this function is non-atomic. If it is called on the same + * region of memory concurrently, the effect may be that only one operation + * succeeds. + */ +static inline void __set_bit(long nr, volatile unsigned long *addr) +{ + kasan_check_write(addr + BIT_WORD(nr), sizeof(long)); + arch___set_bit(nr, addr); +} + +/** + * clear_bit - Clears a bit in memory + * @nr: Bit to clear + * @addr: Address to start counting from + * + * This is a relaxed atomic operation (no implied memory barriers). + */ +static inline void clear_bit(long nr, volatile unsigned long *addr) +{ + kasan_check_write(addr + BIT_WORD(nr), sizeof(long)); + arch_clear_bit(nr, addr); +} + +/** + * __clear_bit - Clears a bit in memory + * @nr: the bit to clear + * @addr: the address to start counting from + * + * Unlike clear_bit(), this function is non-atomic. If it is called on the same + * region of memory concurrently, the effect may be that only one operation + * succeeds. + */ +static inline void __clear_bit(long nr, volatile unsigned long *addr) +{ + kasan_check_write(addr + BIT_WORD(nr), sizeof(long)); + arch___clear_bit(nr, addr); +} + +/** + * clear_bit_unlock - Clear a bit in memory, for unlock + * @nr: the bit to set + * @addr: the address to start counting from + * + * This operation is atomic and provides release barrier semantics. + */ +static inline void clear_bit_unlock(long nr, volatile unsigned long *addr) +{ + kasan_check_write(addr + BIT_WORD(nr), sizeof(long)); + arch_clear_bit_unlock(nr, addr); +} + +/** + * __clear_bit_unlock - Clears a bit in memory + * @nr: Bit to clear + * @addr: Address to start counting from + * + * This is a non-atomic operation but implies a release barrier before the + * memory operation. It can be used for an unlock if no other CPUs can + * concurrently modify other bits in the word. + */ +static inline void __clear_bit_unlock(long nr, volatile unsigned long *addr) +{ + kasan_check_write(addr + BIT_WORD(nr), sizeof(long)); + arch___clear_bit_unlock(nr, addr); +} + +/** + * change_bit - Toggle a bit in memory + * @nr: Bit to change + * @addr: Address to start counting from + * + * This is a relaxed atomic operation (no implied memory barriers). + * + * Note that @nr may be almost arbitrarily large; this function is not + * restricted to acting on a single-word quantity. + */ +static inline void change_bit(long nr, volatile unsigned long *addr) +{ + kasan_check_write(addr + BIT_WORD(nr), sizeof(long)); + arch_change_bit(nr, addr); +} + +/** + * __change_bit - Toggle a bit in memory + * @nr: the bit to change + * @addr: the address to start counting from + * + * Unlike change_bit(), this function is non-atomic. If it is called on the same + * region of memory concurrently, the effect may be that only one operation + * succeeds. + */ +static inline void __change_bit(long nr, volatile unsigned long *addr) +{ + kasan_check_write(addr + BIT_WORD(nr), sizeof(long)); + arch___change_bit(nr, addr); +} + +/** + * test_and_set_bit - Set a bit and return its old value + * @nr: Bit to set + * @addr: Address to count from + * + * This is an atomic fully-ordered operation (implied full memory barrier). + */ +static inline bool test_and_set_bit(long nr, volatile unsigned long *addr) +{ + kasan_check_write(addr + BIT_WORD(nr), sizeof(long)); + return arch_test_and_set_bit(nr, addr); +} + +/** + * __test_and_set_bit - Set a bit and return its old value + * @nr: Bit to set + * @addr: Address to count from + * + * This operation is non-atomic. If two instances of this operation race, one + * can appear to succeed but actually fail. + */ +static inline bool __test_and_set_bit(long nr, volatile unsigned long *addr) +{ + kasan_check_write(addr + BIT_WORD(nr), sizeof(long)); + return arch___test_and_set_bit(nr, addr); +} + +/** + * test_and_set_bit_lock - Set a bit and return its old value, for lock + * @nr: Bit to set + * @addr: Address to count from + * + * This operation is atomic and provides acquire barrier semantics if + * the returned value is 0. + * It can be used to implement bit locks. + */ +static inline bool test_and_set_bit_lock(long nr, volatile unsigned long *addr) +{ + kasan_check_write(addr + BIT_WORD(nr), sizeof(long)); + return arch_test_and_set_bit_lock(nr, addr); +} + +/** + * test_and_clear_bit - Clear a bit and return its old value + * @nr: Bit to clear + * @addr: Address to count from + * + * This is an atomic fully-ordered operation (implied full memory barrier). + */ +static inline bool test_and_clear_bit(long nr, volatile unsigned long *addr) +{ + kasan_check_write(addr + BIT_WORD(nr), sizeof(long)); + return arch_test_and_clear_bit(nr, addr); +} + +/** + * __test_and_clear_bit - Clear a bit and return its old value + * @nr: Bit to clear + * @addr: Address to count from + * + * This operation is non-atomic. If two instances of this operation race, one + * can appear to succeed but actually fail. + */ +static inline bool __test_and_clear_bit(long nr, volatile unsigned long *addr) +{ + kasan_check_write(addr + BIT_WORD(nr), sizeof(long)); + return arch___test_and_clear_bit(nr, addr); +} + +/** + * test_and_change_bit - Change a bit and return its old value + * @nr: Bit to change + * @addr: Address to count from + * + * This is an atomic fully-ordered operation (implied full memory barrier). + */ +static inline bool test_and_change_bit(long nr, volatile unsigned long *addr) +{ + kasan_check_write(addr + BIT_WORD(nr), sizeof(long)); + return arch_test_and_change_bit(nr, addr); +} + +/** + * __test_and_change_bit - Change a bit and return its old value + * @nr: Bit to change + * @addr: Address to count from + * + * This operation is non-atomic. If two instances of this operation race, one + * can appear to succeed but actually fail. + */ +static inline bool __test_and_change_bit(long nr, volatile unsigned long *addr) +{ + kasan_check_write(addr + BIT_WORD(nr), sizeof(long)); + return arch___test_and_change_bit(nr, addr); +} + +/** + * test_bit - Determine whether a bit is set + * @nr: bit number to test + * @addr: Address to start counting from + */ +static inline bool test_bit(long nr, const volatile unsigned long *addr) +{ + kasan_check_read(addr + BIT_WORD(nr), sizeof(long)); + return arch_test_bit(nr, addr); +} + +#if defined(arch_clear_bit_unlock_is_negative_byte) +/** + * clear_bit_unlock_is_negative_byte - Clear a bit in memory and test if bottom + * byte is negative, for unlock. + * @nr: the bit to clear + * @addr: the address to start counting from + * + * This operation is atomic and provides release barrier semantics. + * + * This is a bit of a one-trick-pony for the filemap code, which clears + * PG_locked and tests PG_waiters, + */ +static inline bool +clear_bit_unlock_is_negative_byte(long nr, volatile unsigned long *addr) +{ + kasan_check_write(addr + BIT_WORD(nr), sizeof(long)); + return arch_clear_bit_unlock_is_negative_byte(nr, addr); +} +/* Let everybody know we have it. */ +#define clear_bit_unlock_is_negative_byte clear_bit_unlock_is_negative_byte +#endif + +#endif /* _ASM_GENERIC_BITOPS_INSTRUMENTED_H */ diff --git a/include/asm-generic/pgalloc.h b/include/asm-generic/pgalloc.h index 948714c1535a..8476175c07e7 100644 --- a/include/asm-generic/pgalloc.h +++ b/include/asm-generic/pgalloc.h @@ -1,13 +1,112 @@ /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __ASM_GENERIC_PGALLOC_H #define __ASM_GENERIC_PGALLOC_H -/* - * an empty file is enough for a nommu architecture - */ + #ifdef CONFIG_MMU -#error need to implement an architecture specific asm/pgalloc.h + +#define GFP_PGTABLE_KERNEL (GFP_KERNEL | __GFP_ZERO) +#define GFP_PGTABLE_USER (GFP_PGTABLE_KERNEL | __GFP_ACCOUNT) + +/** + * __pte_alloc_one_kernel - allocate a page for PTE-level kernel page table + * @mm: the mm_struct of the current context + * + * This function is intended for architectures that need + * anything beyond simple page allocation. + * + * Return: pointer to the allocated memory or %NULL on error + */ +static inline pte_t *__pte_alloc_one_kernel(struct mm_struct *mm) +{ + return (pte_t *)__get_free_page(GFP_PGTABLE_KERNEL); +} + +#ifndef __HAVE_ARCH_PTE_ALLOC_ONE_KERNEL +/** + * pte_alloc_one_kernel - allocate a page for PTE-level kernel page table + * @mm: the mm_struct of the current context + * + * Return: pointer to the allocated memory or %NULL on error + */ +static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm) +{ + return __pte_alloc_one_kernel(mm); +} +#endif + +/** + * pte_free_kernel - free PTE-level kernel page table page + * @mm: the mm_struct of the current context + * @pte: pointer to the memory containing the page table + */ +static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) +{ + free_page((unsigned long)pte); +} + +/** + * __pte_alloc_one - allocate a page for PTE-level user page table + * @mm: the mm_struct of the current context + * @gfp: GFP flags to use for the allocation + * + * Allocates a page and runs the pgtable_page_ctor(). + * + * This function is intended for architectures that need + * anything beyond simple page allocation or must have custom GFP flags. + * + * Return: `struct page` initialized as page table or %NULL on error + */ +static inline pgtable_t __pte_alloc_one(struct mm_struct *mm, gfp_t gfp) +{ + struct page *pte; + + pte = alloc_page(gfp); + if (!pte) + return NULL; + if (!pgtable_page_ctor(pte)) { + __free_page(pte); + return NULL; + } + + return pte; +} + +#ifndef __HAVE_ARCH_PTE_ALLOC_ONE +/** + * pte_alloc_one - allocate a page for PTE-level user page table + * @mm: the mm_struct of the current context + * + * Allocates a page and runs the pgtable_page_ctor(). + * + * Return: `struct page` initialized as page table or %NULL on error + */ +static inline pgtable_t pte_alloc_one(struct mm_struct *mm) +{ + return __pte_alloc_one(mm, GFP_PGTABLE_USER); +} #endif +/* + * Should really implement gc for free page table pages. This could be + * done with a reference count in struct page. + */ + +/** + * pte_free - free PTE-level user page table page + * @mm: the mm_struct of the current context + * @pte_page: the `struct page` representing the page table + */ +static inline void pte_free(struct mm_struct *mm, struct page *pte_page) +{ + pgtable_page_dtor(pte_page); + __free_page(pte_page); +} + +#else /* CONFIG_MMU */ + +/* This is enough for a nommu architecture */ #define check_pgt_cache() do { } while (0) +#endif /* CONFIG_MMU */ + #endif /* __ASM_GENERIC_PGALLOC_H */ diff --git a/include/linux/dmar.h b/include/linux/dmar.h index 28813c6f44b6..a7cf3599d9a1 100644 --- a/include/linux/dmar.h +++ b/include/linux/dmar.h @@ -92,12 +92,14 @@ static inline bool dmar_rcu_check(void) #define dmar_rcu_dereference(p) rcu_dereference_check((p), dmar_rcu_check()) -#define for_each_dev_scope(a, c, p, d) \ - for ((p) = 0; ((d) = (p) < (c) ? dmar_rcu_dereference((a)[(p)].dev) : \ - NULL, (p) < (c)); (p)++) - -#define for_each_active_dev_scope(a, c, p, d) \ - for_each_dev_scope((a), (c), (p), (d)) if (!(d)) { continue; } else +#define for_each_dev_scope(devs, cnt, i, tmp) \ + for ((i) = 0; ((tmp) = (i) < (cnt) ? \ + dmar_rcu_dereference((devs)[(i)].dev) : NULL, (i) < (cnt)); \ + (i)++) + +#define for_each_active_dev_scope(devs, cnt, i, tmp) \ + for_each_dev_scope((devs), (cnt), (i), (tmp)) \ + if (!(tmp)) { continue; } else extern int dmar_table_init(void); extern int dmar_dev_scope_init(void); diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index edf476c8cfb9..edfca4278319 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -16,29 +16,11 @@ struct user_struct; struct mmu_gather; #ifndef is_hugepd -/* - * Some architectures requires a hugepage directory format that is - * required to support multiple hugepage sizes. For example - * a4fe3ce76 "powerpc/mm: Allow more flexible layouts for hugepage pagetables" - * introduced the same on powerpc. This allows for a more flexible hugepage - * pagetable layout. - */ typedef struct { unsigned long pd; } hugepd_t; #define is_hugepd(hugepd) (0) #define __hugepd(x) ((hugepd_t) { (x) }) -static inline int gup_huge_pd(hugepd_t hugepd, unsigned long addr, - unsigned pdshift, unsigned long end, - int write, struct page **pages, int *nr) -{ - return 0; -} -#else -extern int gup_huge_pd(hugepd_t hugepd, unsigned long addr, - unsigned pdshift, unsigned long end, - int write, struct page **pages, int *nr); #endif - #ifdef CONFIG_HUGETLB_PAGE #include <linux/mempolicy.h> @@ -608,22 +590,92 @@ static inline void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, #else /* CONFIG_HUGETLB_PAGE */ struct hstate {}; -#define alloc_huge_page(v, a, r) NULL -#define alloc_huge_page_node(h, nid) NULL -#define alloc_huge_page_nodemask(h, preferred_nid, nmask) NULL -#define alloc_huge_page_vma(h, vma, address) NULL -#define alloc_bootmem_huge_page(h) NULL -#define hstate_file(f) NULL -#define hstate_sizelog(s) NULL -#define hstate_vma(v) NULL -#define hstate_inode(i) NULL -#define page_hstate(page) NULL -#define huge_page_size(h) PAGE_SIZE -#define huge_page_mask(h) PAGE_MASK -#define vma_kernel_pagesize(v) PAGE_SIZE -#define vma_mmu_pagesize(v) PAGE_SIZE -#define huge_page_order(h) 0 -#define huge_page_shift(h) PAGE_SHIFT + +static inline struct page *alloc_huge_page(struct vm_area_struct *vma, + unsigned long addr, + int avoid_reserve) +{ + return NULL; +} + +static inline struct page *alloc_huge_page_node(struct hstate *h, int nid) +{ + return NULL; +} + +static inline struct page * +alloc_huge_page_nodemask(struct hstate *h, int preferred_nid, nodemask_t *nmask) +{ + return NULL; +} + +static inline struct page *alloc_huge_page_vma(struct hstate *h, + struct vm_area_struct *vma, + unsigned long address) +{ + return NULL; +} + +static inline int __alloc_bootmem_huge_page(struct hstate *h) +{ + return 0; +} + +static inline struct hstate *hstate_file(struct file *f) +{ + return NULL; +} + +static inline struct hstate *hstate_sizelog(int page_size_log) +{ + return NULL; +} + +static inline struct hstate *hstate_vma(struct vm_area_struct *vma) +{ + return NULL; +} + +static inline struct hstate *hstate_inode(struct inode *i) +{ + return NULL; +} + +static inline struct hstate *page_hstate(struct page *page) +{ + return NULL; +} + +static inline unsigned long huge_page_size(struct hstate *h) +{ + return PAGE_SIZE; +} + +static inline unsigned long huge_page_mask(struct hstate *h) +{ + return PAGE_MASK; +} + +static inline unsigned long vma_kernel_pagesize(struct vm_area_struct *vma) +{ + return PAGE_SIZE; +} + +static inline unsigned long vma_mmu_pagesize(struct vm_area_struct *vma) +{ + return PAGE_SIZE; +} + +static inline unsigned int huge_page_order(struct hstate *h) +{ + return 0; +} + +static inline unsigned int huge_page_shift(struct hstate *h) +{ + return PAGE_SHIFT; +} + static inline bool hstate_is_gigantic(struct hstate *h) { return false; diff --git a/include/linux/kasan-checks.h b/include/linux/kasan-checks.h index a61dc075e2ce..ac6aba632f2d 100644 --- a/include/linux/kasan-checks.h +++ b/include/linux/kasan-checks.h @@ -2,14 +2,43 @@ #ifndef _LINUX_KASAN_CHECKS_H #define _LINUX_KASAN_CHECKS_H -#if defined(__SANITIZE_ADDRESS__) || defined(__KASAN_INTERNAL) -void kasan_check_read(const volatile void *p, unsigned int size); -void kasan_check_write(const volatile void *p, unsigned int size); +#include <linux/types.h> + +/* + * __kasan_check_*: Always available when KASAN is enabled. This may be used + * even in compilation units that selectively disable KASAN, but must use KASAN + * to validate access to an address. Never use these in header files! + */ +#ifdef CONFIG_KASAN +bool __kasan_check_read(const volatile void *p, unsigned int size); +bool __kasan_check_write(const volatile void *p, unsigned int size); +#else +static inline bool __kasan_check_read(const volatile void *p, unsigned int size) +{ + return true; +} +static inline bool __kasan_check_write(const volatile void *p, unsigned int size) +{ + return true; +} +#endif + +/* + * kasan_check_*: Only available when the particular compilation unit has KASAN + * instrumentation enabled. May be used in header files. + */ +#ifdef __SANITIZE_ADDRESS__ +#define kasan_check_read __kasan_check_read +#define kasan_check_write __kasan_check_write #else -static inline void kasan_check_read(const volatile void *p, unsigned int size) -{ } -static inline void kasan_check_write(const volatile void *p, unsigned int size) -{ } +static inline bool kasan_check_read(const volatile void *p, unsigned int size) +{ + return true; +} +static inline bool kasan_check_write(const volatile void *p, unsigned int size) +{ + return true; +} #endif #endif diff --git a/include/linux/kasan.h b/include/linux/kasan.h index b40ea104dd36..cc8a03cc9674 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -76,8 +76,11 @@ void kasan_free_shadow(const struct vm_struct *vm); int kasan_add_zero_shadow(void *start, unsigned long size); void kasan_remove_zero_shadow(void *start, unsigned long size); -size_t ksize(const void *); -static inline void kasan_unpoison_slab(const void *ptr) { ksize(ptr); } +size_t __ksize(const void *); +static inline void kasan_unpoison_slab(const void *ptr) +{ + kasan_unpoison_shadow(ptr, __ksize(ptr)); +} size_t kasan_metadata_size(struct kmem_cache *cache); bool kasan_save_enable_multi_shot(void); diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 1dcb763bb610..44c41462be33 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -233,8 +233,9 @@ struct mem_cgroup { /* OOM-Killer disable */ int oom_kill_disable; - /* memory.events */ + /* memory.events and memory.events.local */ struct cgroup_file events_file; + struct cgroup_file events_local_file; /* handle for "memory.swap.events" */ struct cgroup_file swap_events_file; @@ -281,6 +282,7 @@ struct mem_cgroup { /* memory.events */ atomic_long_t memory_events[MEMCG_NR_MEMORY_EVENTS]; + atomic_long_t memory_events_local[MEMCG_NR_MEMORY_EVENTS]; unsigned long socket_pressure; @@ -392,7 +394,6 @@ out: struct lruvec *mem_cgroup_page_lruvec(struct page *, struct pglist_data *); -bool task_in_mem_cgroup(struct task_struct *task, struct mem_cgroup *memcg); struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p); struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm); @@ -747,6 +748,9 @@ static inline void count_memcg_event_mm(struct mm_struct *mm, static inline void memcg_memory_event(struct mem_cgroup *memcg, enum memcg_memory_event event) { + atomic_long_inc(&memcg->memory_events_local[event]); + cgroup_file_notify(&memcg->events_local_file); + do { atomic_long_inc(&memcg->memory_events[event]); cgroup_file_notify(&memcg->events_file); @@ -870,12 +874,6 @@ static inline bool mm_match_cgroup(struct mm_struct *mm, return true; } -static inline bool task_in_mem_cgroup(struct task_struct *task, - const struct mem_cgroup *memcg) -{ - return true; -} - static inline struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm) { return NULL; @@ -1273,6 +1271,8 @@ int __memcg_kmem_charge(struct page *page, gfp_t gfp, int order); void __memcg_kmem_uncharge(struct page *page, int order); int __memcg_kmem_charge_memcg(struct page *page, gfp_t gfp, int order, struct mem_cgroup *memcg); +void __memcg_kmem_uncharge_memcg(struct mem_cgroup *memcg, + unsigned int nr_pages); extern struct static_key_false memcg_kmem_enabled_key; extern struct workqueue_struct *memcg_kmem_cache_wq; @@ -1314,6 +1314,14 @@ static inline int memcg_kmem_charge_memcg(struct page *page, gfp_t gfp, return __memcg_kmem_charge_memcg(page, gfp, order, memcg); return 0; } + +static inline void memcg_kmem_uncharge_memcg(struct page *page, int order, + struct mem_cgroup *memcg) +{ + if (memcg_kmem_enabled()) + __memcg_kmem_uncharge_memcg(memcg, 1 << order); +} + /* * helper for accessing a memcg's index. It will be used as an index in the * child cache array in kmem_cache, and also to derive its name. This function diff --git a/include/linux/mm.h b/include/linux/mm.h index dd0b5f4e1e45..f88f0eabcc5e 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -633,6 +633,11 @@ static inline bool is_vmalloc_addr(const void *x) return false; #endif } + +#ifndef is_ioremap_addr +#define is_ioremap_addr(x) is_vmalloc_addr(x) +#endif + #ifdef CONFIG_MMU extern int is_vmalloc_or_module_addr(const void *x); #else @@ -2681,8 +2686,7 @@ static inline int vm_fault_to_errno(vm_fault_t vm_fault, int foll_flags) return 0; } -typedef int (*pte_fn_t)(pte_t *pte, pgtable_t token, unsigned long addr, - void *data); +typedef int (*pte_fn_t)(pte_t *pte, unsigned long addr, void *data); extern int apply_to_page_range(struct mm_struct *mm, unsigned long address, unsigned long size, pte_fn_t fn, void *data); @@ -2696,11 +2700,42 @@ static inline void kernel_poison_pages(struct page *page, int numpages, int enable) { } #endif -extern bool _debug_pagealloc_enabled; +#ifdef CONFIG_INIT_ON_ALLOC_DEFAULT_ON +DECLARE_STATIC_KEY_TRUE(init_on_alloc); +#else +DECLARE_STATIC_KEY_FALSE(init_on_alloc); +#endif +static inline bool want_init_on_alloc(gfp_t flags) +{ + if (static_branch_unlikely(&init_on_alloc) && + !page_poisoning_enabled()) + return true; + return flags & __GFP_ZERO; +} + +#ifdef CONFIG_INIT_ON_FREE_DEFAULT_ON +DECLARE_STATIC_KEY_TRUE(init_on_free); +#else +DECLARE_STATIC_KEY_FALSE(init_on_free); +#endif +static inline bool want_init_on_free(void) +{ + return static_branch_unlikely(&init_on_free) && + !page_poisoning_enabled(); +} + +#ifdef CONFIG_DEBUG_PAGEALLOC_ENABLE_DEFAULT +DECLARE_STATIC_KEY_TRUE(_debug_pagealloc_enabled); +#else +DECLARE_STATIC_KEY_FALSE(_debug_pagealloc_enabled); +#endif static inline bool debug_pagealloc_enabled(void) { - return IS_ENABLED(CONFIG_DEBUG_PAGEALLOC) && _debug_pagealloc_enabled; + if (!IS_ENABLED(CONFIG_DEBUG_PAGEALLOC)) + return false; + + return static_branch_unlikely(&_debug_pagealloc_enabled); } #if defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_ARCH_HAS_SET_DIRECT_MAP) @@ -2850,11 +2885,9 @@ extern long copy_huge_page_from_user(struct page *dst_page, bool allow_pagefault); #endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLBFS */ -extern struct page_ext_operations debug_guardpage_ops; - #ifdef CONFIG_DEBUG_PAGEALLOC extern unsigned int _debug_guardpage_minorder; -extern bool _debug_guardpage_enabled; +DECLARE_STATIC_KEY_FALSE(_debug_guardpage_enabled); static inline unsigned int debug_guardpage_minorder(void) { @@ -2863,21 +2896,15 @@ static inline unsigned int debug_guardpage_minorder(void) static inline bool debug_guardpage_enabled(void) { - return _debug_guardpage_enabled; + return static_branch_unlikely(&_debug_guardpage_enabled); } static inline bool page_is_guard(struct page *page) { - struct page_ext *page_ext; - if (!debug_guardpage_enabled()) return false; - page_ext = lookup_page_ext(page); - if (unlikely(!page_ext)) - return false; - - return test_bit(PAGE_EXT_DEBUG_GUARD, &page_ext->flags); + return PageGuard(page); } #else static inline unsigned int debug_guardpage_minorder(void) { return 0; } diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 8ec38b11b361..1d1093474c1a 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -329,7 +329,9 @@ struct vm_area_struct { struct file * vm_file; /* File we map to (can be NULL). */ void * vm_private_data; /* was vm_pte (shared mem) */ +#ifdef CONFIG_SWAP atomic_long_t swap_readahead_info; +#endif #ifndef CONFIG_MMU struct vm_region *vm_region; /* NOMMU mapping region */ #endif diff --git a/include/linux/oom.h b/include/linux/oom.h index d07992009265..c696c265f019 100644 --- a/include/linux/oom.h +++ b/include/linux/oom.h @@ -108,7 +108,6 @@ static inline vm_fault_t check_stable_address_space(struct mm_struct *mm) bool __oom_reap_task_mm(struct mm_struct *mm); extern unsigned long oom_badness(struct task_struct *p, - struct mem_cgroup *memcg, const nodemask_t *nodemask, unsigned long totalpages); extern bool out_of_memory(struct oom_control *oc); diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 9f8712a4b1a5..b848517da64c 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -703,6 +703,7 @@ PAGEFLAG_FALSE(DoubleMap) #define PG_offline 0x00000100 #define PG_kmemcg 0x00000200 #define PG_table 0x00000400 +#define PG_guard 0x00000800 #define PageType(page, flag) \ ((page->page_type & (PAGE_TYPE_BASE | flag)) == PAGE_TYPE_BASE) @@ -754,6 +755,11 @@ PAGE_TYPE_OPS(Kmemcg, kmemcg) */ PAGE_TYPE_OPS(Table, table) +/* + * Marks guardpages used with debug_pagealloc. + */ +PAGE_TYPE_OPS(Guard, guard) + extern bool is_free_buddy_page(struct page *page); __PAGEFLAG(Isolated, isolated, PF_ANY); diff --git a/include/linux/page-isolation.h b/include/linux/page-isolation.h index 280ae96dc4c3..1099c2fee20f 100644 --- a/include/linux/page-isolation.h +++ b/include/linux/page-isolation.h @@ -50,7 +50,7 @@ start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, * Changes MIGRATE_ISOLATE to MIGRATE_MOVABLE. * target range is [start_pfn, end_pfn) */ -int +void undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, unsigned migratetype); diff --git a/include/linux/page_ext.h b/include/linux/page_ext.h index f84f167ec04c..09592951725c 100644 --- a/include/linux/page_ext.h +++ b/include/linux/page_ext.h @@ -17,7 +17,6 @@ struct page_ext_operations { #ifdef CONFIG_PAGE_EXTENSION enum page_ext_flags { - PAGE_EXT_DEBUG_GUARD, PAGE_EXT_OWNER, #if defined(CONFIG_IDLE_PAGE_TRACKING) && !defined(CONFIG_64BIT) PAGE_EXT_YOUNG, diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index fe0b29bf2df7..c7552459a15f 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -383,8 +383,7 @@ extern int read_cache_pages(struct address_space *mapping, static inline struct page *read_mapping_page(struct address_space *mapping, pgoff_t index, void *data) { - filler_t *filler = (filler_t *)mapping->a_ops->readpage; - return read_cache_page(mapping, index, filler, data); + return read_cache_page(mapping, index, NULL, data); } /* @@ -452,6 +451,9 @@ extern int __lock_page_or_retry(struct page *page, struct mm_struct *mm, unsigned int flags); extern void unlock_page(struct page *page); +/* + * Return true if the page was successfully locked + */ static inline int trylock_page(struct page *page) { page = compound_head(page); diff --git a/include/linux/pfn_t.h b/include/linux/pfn_t.h index 3c202a11a79e..01e8037023f7 100644 --- a/include/linux/pfn_t.h +++ b/include/linux/pfn_t.h @@ -66,13 +66,6 @@ static inline phys_addr_t pfn_t_to_phys(pfn_t pfn) return PFN_PHYS(pfn_t_to_pfn(pfn)); } -static inline void *pfn_t_to_virt(pfn_t pfn) -{ - if (pfn_t_has_page(pfn) && !is_device_private_page(pfn_t_to_page(pfn))) - return __va(pfn_t_to_phys(pfn)); - return NULL; -} - static inline pfn_t page_to_pfn_t(struct page *page) { return pfn_to_pfn_t(page_to_pfn(page)); diff --git a/include/linux/slab.h b/include/linux/slab.h index 9449b19c5f10..56c9c7eed34e 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -16,6 +16,7 @@ #include <linux/overflow.h> #include <linux/types.h> #include <linux/workqueue.h> +#include <linux/percpu-refcount.h> /* @@ -115,6 +116,10 @@ /* Objects are reclaimable */ #define SLAB_RECLAIM_ACCOUNT ((slab_flags_t __force)0x00020000U) #define SLAB_TEMPORARY SLAB_RECLAIM_ACCOUNT /* Objects are short-lived */ + +/* Slab deactivation flag */ +#define SLAB_DEACTIVATED ((slab_flags_t __force)0x10000000U) + /* * ZERO_SIZE_PTR will be returned for zero sized kmalloc requests. * @@ -151,8 +156,7 @@ void kmem_cache_destroy(struct kmem_cache *); int kmem_cache_shrink(struct kmem_cache *); void memcg_create_kmem_cache(struct mem_cgroup *, struct kmem_cache *); -void memcg_deactivate_kmem_caches(struct mem_cgroup *); -void memcg_destroy_kmem_caches(struct mem_cgroup *); +void memcg_deactivate_kmem_caches(struct mem_cgroup *, struct mem_cgroup *); /* * Please use this macro to create slab caches. Simply specify the @@ -184,6 +188,7 @@ void * __must_check __krealloc(const void *, size_t, gfp_t); void * __must_check krealloc(const void *, size_t, gfp_t); void kfree(const void *); void kzfree(const void *); +size_t __ksize(const void *); size_t ksize(const void *); #ifdef CONFIG_HAVE_HARDENED_USERCOPY_ALLOCATOR @@ -641,11 +646,12 @@ struct memcg_cache_params { struct mem_cgroup *memcg; struct list_head children_node; struct list_head kmem_caches_node; + struct percpu_ref refcnt; - void (*deact_fn)(struct kmem_cache *); + void (*work_fn)(struct kmem_cache *); union { - struct rcu_head deact_rcu_head; - struct work_struct deact_work; + struct rcu_head rcu_head; + struct work_struct work; }; }; }; diff --git a/include/linux/swap.h b/include/linux/swap.h index 4bfb5c4ac108..de2c67a33b7e 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -148,7 +148,7 @@ struct zone; * We always assume that blocks are of size PAGE_SIZE. */ struct swap_extent { - struct list_head list; + struct rb_node rb_node; pgoff_t start_page; pgoff_t nr_pages; sector_t start_block; @@ -175,8 +175,9 @@ enum { SWP_PAGE_DISCARD = (1 << 10), /* freed swap page-cluster discards */ SWP_STABLE_WRITES = (1 << 11), /* no overwrite PG_writeback pages */ SWP_SYNCHRONOUS_IO = (1 << 12), /* synchronous IO is efficient */ + SWP_VALID = (1 << 13), /* swap is valid to be operated on? */ /* add others here before... */ - SWP_SCANNING = (1 << 13), /* refcount in scan_swap_map */ + SWP_SCANNING = (1 << 14), /* refcount in scan_swap_map */ }; #define SWAP_CLUSTER_MAX 32UL @@ -247,8 +248,7 @@ struct swap_info_struct { unsigned int cluster_next; /* likely index for next allocation */ unsigned int cluster_nr; /* countdown to next cluster search */ struct percpu_cluster __percpu *percpu_cluster; /* per cpu's swap location */ - struct swap_extent *curr_swap_extent; - struct swap_extent first_swap_extent; + struct rb_root swap_extent_root;/* root of the swap extent rbtree */ struct block_device *bdev; /* swap device or bdev of swap file */ struct file *swap_file; /* seldom referenced */ unsigned int old_block_size; /* seldom referenced */ @@ -460,7 +460,7 @@ extern unsigned int count_swap_pages(int, int); extern sector_t map_swap_page(struct page *, struct block_device **); extern sector_t swapdev_block(int, pgoff_t); extern int page_swapcount(struct page *); -extern int __swap_count(struct swap_info_struct *si, swp_entry_t entry); +extern int __swap_count(swp_entry_t entry); extern int __swp_swapcount(swp_entry_t entry); extern int swp_swapcount(swp_entry_t entry); extern struct swap_info_struct *page_swap_info(struct page *); @@ -470,6 +470,12 @@ extern int try_to_free_swap(struct page *); struct backing_dev_info; extern int init_swap_address_space(unsigned int type, unsigned long nr_pages); extern void exit_swap_address_space(unsigned int type); +extern struct swap_info_struct *get_swap_device(swp_entry_t entry); + +static inline void put_swap_device(struct swap_info_struct *si) +{ + rcu_read_unlock(); +} #else /* CONFIG_SWAP */ @@ -576,7 +582,7 @@ static inline int page_swapcount(struct page *page) return 0; } -static inline int __swap_count(struct swap_info_struct *si, swp_entry_t entry) +static inline int __swap_count(swp_entry_t entry) { return 0; } diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 51e131245379..9b21d0047710 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -72,10 +72,12 @@ extern void vm_unmap_aliases(void); #ifdef CONFIG_MMU extern void __init vmalloc_init(void); +extern unsigned long vmalloc_nr_pages(void); #else static inline void vmalloc_init(void) { } +static inline unsigned long vmalloc_nr_pages(void) { return 0; } #endif extern void *vmalloc(unsigned long size); diff --git a/include/linux/vmpressure.h b/include/linux/vmpressure.h index 61e6fddfb26f..6d28bc433c1c 100644 --- a/include/linux/vmpressure.h +++ b/include/linux/vmpressure.h @@ -17,7 +17,7 @@ struct vmpressure { unsigned long tree_scanned; unsigned long tree_reclaimed; /* The lock is used to keep the scanned/reclaimed above in sync. */ - struct spinlock sr_lock; + spinlock_t sr_lock; /* The list of vmpressure_event structs. */ struct list_head events; diff --git a/include/uapi/linux/nilfs2_ondisk.h b/include/uapi/linux/nilfs2_ondisk.h index a7e66ab11d1d..c23f91ae5fe8 100644 --- a/include/uapi/linux/nilfs2_ondisk.h +++ b/include/uapi/linux/nilfs2_ondisk.h @@ -29,7 +29,7 @@ #include <linux/types.h> #include <linux/magic.h> - +#include <asm/byteorder.h> #define NILFS_INODE_BMAP_SIZE 7 @@ -533,19 +533,19 @@ enum { static inline void \ nilfs_checkpoint_set_##name(struct nilfs_checkpoint *cp) \ { \ - cp->cp_flags = cpu_to_le32(le32_to_cpu(cp->cp_flags) | \ - (1UL << NILFS_CHECKPOINT_##flag)); \ + cp->cp_flags = __cpu_to_le32(__le32_to_cpu(cp->cp_flags) | \ + (1UL << NILFS_CHECKPOINT_##flag)); \ } \ static inline void \ nilfs_checkpoint_clear_##name(struct nilfs_checkpoint *cp) \ { \ - cp->cp_flags = cpu_to_le32(le32_to_cpu(cp->cp_flags) & \ + cp->cp_flags = __cpu_to_le32(__le32_to_cpu(cp->cp_flags) & \ ~(1UL << NILFS_CHECKPOINT_##flag)); \ } \ static inline int \ nilfs_checkpoint_##name(const struct nilfs_checkpoint *cp) \ { \ - return !!(le32_to_cpu(cp->cp_flags) & \ + return !!(__le32_to_cpu(cp->cp_flags) & \ (1UL << NILFS_CHECKPOINT_##flag)); \ } @@ -595,20 +595,20 @@ enum { static inline void \ nilfs_segment_usage_set_##name(struct nilfs_segment_usage *su) \ { \ - su->su_flags = cpu_to_le32(le32_to_cpu(su->su_flags) | \ + su->su_flags = __cpu_to_le32(__le32_to_cpu(su->su_flags) | \ (1UL << NILFS_SEGMENT_USAGE_##flag));\ } \ static inline void \ nilfs_segment_usage_clear_##name(struct nilfs_segment_usage *su) \ { \ su->su_flags = \ - cpu_to_le32(le32_to_cpu(su->su_flags) & \ + __cpu_to_le32(__le32_to_cpu(su->su_flags) & \ ~(1UL << NILFS_SEGMENT_USAGE_##flag)); \ } \ static inline int \ nilfs_segment_usage_##name(const struct nilfs_segment_usage *su) \ { \ - return !!(le32_to_cpu(su->su_flags) & \ + return !!(__le32_to_cpu(su->su_flags) & \ (1UL << NILFS_SEGMENT_USAGE_##flag)); \ } @@ -619,15 +619,15 @@ NILFS_SEGMENT_USAGE_FNS(ERROR, error) static inline void nilfs_segment_usage_set_clean(struct nilfs_segment_usage *su) { - su->su_lastmod = cpu_to_le64(0); - su->su_nblocks = cpu_to_le32(0); - su->su_flags = cpu_to_le32(0); + su->su_lastmod = __cpu_to_le64(0); + su->su_nblocks = __cpu_to_le32(0); + su->su_flags = __cpu_to_le32(0); } static inline int nilfs_segment_usage_clean(const struct nilfs_segment_usage *su) { - return !le32_to_cpu(su->su_flags); + return !__le32_to_cpu(su->su_flags); } /** diff --git a/init/main.c b/init/main.c index 66a196c5e4c3..ff5803b0841c 100644 --- a/init/main.c +++ b/init/main.c @@ -520,6 +520,29 @@ static inline void initcall_debug_enable(void) } #endif +/* Report memory auto-initialization states for this boot. */ +static void __init report_meminit(void) +{ + const char *stack; + + if (IS_ENABLED(CONFIG_INIT_STACK_ALL)) + stack = "all"; + else if (IS_ENABLED(CONFIG_GCC_PLUGIN_STRUCTLEAK_BYREF_ALL)) + stack = "byref_all"; + else if (IS_ENABLED(CONFIG_GCC_PLUGIN_STRUCTLEAK_BYREF)) + stack = "byref"; + else if (IS_ENABLED(CONFIG_GCC_PLUGIN_STRUCTLEAK_USER)) + stack = "__user"; + else + stack = "off"; + + pr_info("mem auto-init: stack:%s, heap alloc:%s, heap free:%s\n", + stack, want_init_on_alloc(GFP_KERNEL) ? "on" : "off", + want_init_on_free() ? "on" : "off"); + if (want_init_on_free()) + pr_info("mem auto-init: clearing system memory may take some time...\n"); +} + /* * Set up kernel memory allocators */ @@ -530,6 +553,7 @@ static void __init mm_init(void) * bigger than MAX_ORDER unless SPARSEMEM. */ page_ext_init_flatmem(); + report_meminit(); mem_init(); kmem_cache_init(); pgtable_init(); diff --git a/kernel/iomem.c b/kernel/iomem.c index 93c264444510..62c92e43aa0d 100644 --- a/kernel/iomem.c +++ b/kernel/iomem.c @@ -121,7 +121,7 @@ EXPORT_SYMBOL(memremap); void memunmap(void *addr) { - if (is_vmalloc_addr(addr)) + if (is_ioremap_addr(addr)) iounmap((void __iomem *) addr); } EXPORT_SYMBOL(memunmap); diff --git a/lib/test_kasan.c b/lib/test_kasan.c index e3c593c38eff..b63b367a94e8 100644 --- a/lib/test_kasan.c +++ b/lib/test_kasan.c @@ -7,16 +7,17 @@ #define pr_fmt(fmt) "kasan test: %s " fmt, __func__ +#include <linux/bitops.h> #include <linux/delay.h> +#include <linux/kasan.h> #include <linux/kernel.h> -#include <linux/mman.h> #include <linux/mm.h> +#include <linux/mman.h> +#include <linux/module.h> #include <linux/printk.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/uaccess.h> -#include <linux/module.h> -#include <linux/kasan.h> /* * Note: test functions are marked noinline so that their names appear in @@ -619,6 +620,95 @@ static noinline void __init kasan_strings(void) strnlen(ptr, 1); } +static noinline void __init kasan_bitops(void) +{ + /* + * Allocate 1 more byte, which causes kzalloc to round up to 16-bytes; + * this way we do not actually corrupt other memory. + */ + long *bits = kzalloc(sizeof(*bits) + 1, GFP_KERNEL); + if (!bits) + return; + + /* + * Below calls try to access bit within allocated memory; however, the + * below accesses are still out-of-bounds, since bitops are defined to + * operate on the whole long the bit is in. + */ + pr_info("out-of-bounds in set_bit\n"); + set_bit(BITS_PER_LONG, bits); + + pr_info("out-of-bounds in __set_bit\n"); + __set_bit(BITS_PER_LONG, bits); + + pr_info("out-of-bounds in clear_bit\n"); + clear_bit(BITS_PER_LONG, bits); + + pr_info("out-of-bounds in __clear_bit\n"); + __clear_bit(BITS_PER_LONG, bits); + + pr_info("out-of-bounds in clear_bit_unlock\n"); + clear_bit_unlock(BITS_PER_LONG, bits); + + pr_info("out-of-bounds in __clear_bit_unlock\n"); + __clear_bit_unlock(BITS_PER_LONG, bits); + + pr_info("out-of-bounds in change_bit\n"); + change_bit(BITS_PER_LONG, bits); + + pr_info("out-of-bounds in __change_bit\n"); + __change_bit(BITS_PER_LONG, bits); + + /* + * Below calls try to access bit beyond allocated memory. + */ + pr_info("out-of-bounds in test_and_set_bit\n"); + test_and_set_bit(BITS_PER_LONG + BITS_PER_BYTE, bits); + + pr_info("out-of-bounds in __test_and_set_bit\n"); + __test_and_set_bit(BITS_PER_LONG + BITS_PER_BYTE, bits); + + pr_info("out-of-bounds in test_and_set_bit_lock\n"); + test_and_set_bit_lock(BITS_PER_LONG + BITS_PER_BYTE, bits); + + pr_info("out-of-bounds in test_and_clear_bit\n"); + test_and_clear_bit(BITS_PER_LONG + BITS_PER_BYTE, bits); + + pr_info("out-of-bounds in __test_and_clear_bit\n"); + __test_and_clear_bit(BITS_PER_LONG + BITS_PER_BYTE, bits); + + pr_info("out-of-bounds in test_and_change_bit\n"); + test_and_change_bit(BITS_PER_LONG + BITS_PER_BYTE, bits); + + pr_info("out-of-bounds in __test_and_change_bit\n"); + __test_and_change_bit(BITS_PER_LONG + BITS_PER_BYTE, bits); + + pr_info("out-of-bounds in test_bit\n"); + (void)test_bit(BITS_PER_LONG + BITS_PER_BYTE, bits); + +#if defined(clear_bit_unlock_is_negative_byte) + pr_info("out-of-bounds in clear_bit_unlock_is_negative_byte\n"); + clear_bit_unlock_is_negative_byte(BITS_PER_LONG + BITS_PER_BYTE, bits); +#endif + kfree(bits); +} + +static noinline void __init kmalloc_double_kzfree(void) +{ + char *ptr; + size_t size = 16; + + pr_info("double-free (kzfree)\n"); + ptr = kmalloc(size, GFP_KERNEL); + if (!ptr) { + pr_err("Allocation failed\n"); + return; + } + + kzfree(ptr); + kzfree(ptr); +} + static int __init kmalloc_tests_init(void) { /* @@ -660,6 +750,8 @@ static int __init kmalloc_tests_init(void) kasan_memchr(); kasan_memcmp(); kasan_strings(); + kasan_bitops(); + kmalloc_double_kzfree(); kasan_restore_multi_shot(multishot); diff --git a/mm/Kconfig b/mm/Kconfig index ef6efedc5921..0b4352557dd5 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -132,7 +132,8 @@ config HAVE_MEMBLOCK_NODE_MAP config HAVE_MEMBLOCK_PHYS_MAP bool -config HAVE_GENERIC_GUP +config HAVE_FAST_GUP + depends on MMU bool config ARCH_KEEP_MEMBLOCK @@ -762,7 +763,20 @@ config GUP_BENCHMARK See tools/testing/selftests/vm/gup_benchmark.c +config GUP_GET_PTE_LOW_HIGH + bool + config ARCH_HAS_PTE_SPECIAL bool +# +# Some architectures require a special hugepage directory format that is +# required to support multiple hugepage sizes. For example a4fe3ce76 +# "powerpc/mm: Allow more flexible layouts for hugepage pagetables" +# introduced it on powerpc. This allows for a more flexible hugepage +# pagetable layouts. +# +config ARCH_HAS_HUGEPD + bool + endmenu diff --git a/mm/Kconfig.debug b/mm/Kconfig.debug index fa6d79281368..82b6a20898bd 100644 --- a/mm/Kconfig.debug +++ b/mm/Kconfig.debug @@ -12,19 +12,23 @@ config DEBUG_PAGEALLOC bool "Debug page memory allocations" depends on DEBUG_KERNEL depends on !HIBERNATION || ARCH_SUPPORTS_DEBUG_PAGEALLOC && !PPC && !SPARC - select PAGE_EXTENSION select PAGE_POISONING if !ARCH_SUPPORTS_DEBUG_PAGEALLOC ---help--- Unmap pages from the kernel linear mapping after free_pages(). Depending on runtime enablement, this results in a small or large slowdown, but helps to find certain types of memory corruption. + Also, the state of page tracking structures is checked more often as + pages are being allocated and freed, as unexpected state changes + often happen for same reasons as memory corruption (e.g. double free, + use-after-free). + For architectures which don't enable ARCH_SUPPORTS_DEBUG_PAGEALLOC, fill the pages with poison patterns after free_pages() and verify - the patterns before alloc_pages(). Additionally, - this option cannot be enabled in combination with hibernation as - that would result in incorrect warnings of memory corruption after - a resume because free pages are not saved to the suspend image. + the patterns before alloc_pages(). Additionally, this option cannot + be enabled in combination with hibernation as that would result in + incorrect warnings of memory corruption after a resume because free + pages are not saved to the suspend image. By default this option will have a small overhead, e.g. by not allowing the kernel mapping to be backed by large pages on some diff --git a/mm/Makefile b/mm/Makefile index ac5e5ba78874..dc0746ca1109 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -22,7 +22,7 @@ KCOV_INSTRUMENT_mmzone.o := n KCOV_INSTRUMENT_vmstat.o := n mmu-y := nommu.o -mmu-$(CONFIG_MMU) := gup.o highmem.o memory.o mincore.o \ +mmu-$(CONFIG_MMU) := highmem.o memory.o mincore.o \ mlock.o mmap.o mmu_gather.o mprotect.o mremap.o \ msync.o page_vma_mapped.o pagewalk.o \ pgtable-generic.o rmap.o vmalloc.o @@ -39,7 +39,7 @@ obj-y := filemap.o mempool.o oom_kill.o fadvise.o \ mm_init.o mmu_context.o percpu.o slab_common.o \ compaction.o vmacache.o \ interval_tree.o list_lru.o workingset.o \ - debug.o $(mmu-y) + debug.o gup.o $(mmu-y) # Give 'page_alloc' its own module-parameter namespace page-alloc-y := page_alloc.o diff --git a/mm/dmapool.c b/mm/dmapool.c index 8c94c89a6f7e..fe5d33060415 100644 --- a/mm/dmapool.c +++ b/mm/dmapool.c @@ -378,7 +378,7 @@ void *dma_pool_alloc(struct dma_pool *pool, gfp_t mem_flags, #endif spin_unlock_irqrestore(&pool->lock, flags); - if (mem_flags & __GFP_ZERO) + if (want_init_on_alloc(mem_flags)) memset(retval, 0, pool->size); return retval; @@ -428,6 +428,8 @@ void dma_pool_free(struct dma_pool *pool, void *vaddr, dma_addr_t dma) } offset = vaddr - page->vaddr; + if (want_init_on_free()) + memset(vaddr, 0, pool->size); #ifdef DMAPOOL_DEBUG if ((dma - page->dma) != offset) { spin_unlock_irqrestore(&pool->lock, flags); diff --git a/mm/failslab.c b/mm/failslab.c index ec5aad211c5b..f92fed91ac23 100644 --- a/mm/failslab.c +++ b/mm/failslab.c @@ -23,7 +23,8 @@ bool __should_failslab(struct kmem_cache *s, gfp_t gfpflags) if (gfpflags & __GFP_NOFAIL) return false; - if (failslab.ignore_gfp_reclaim && (gfpflags & __GFP_RECLAIM)) + if (failslab.ignore_gfp_reclaim && + (gfpflags & __GFP_DIRECT_RECLAIM)) return false; if (failslab.cache_filter && !(s->flags & SLAB_FAILSLAB)) diff --git a/mm/filemap.c b/mm/filemap.c index f1aa20ab8434..d0cf700bf201 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2504,10 +2504,8 @@ static struct file *do_async_mmap_readahead(struct vm_fault *vmf, * * vma->vm_mm->mmap_sem must be held on entry. * - * If our return value has VM_FAULT_RETRY set, it's because - * lock_page_or_retry() returned 0. - * The mmap_sem has usually been released in this case. - * See __lock_page_or_retry() for the exception. + * If our return value has VM_FAULT_RETRY set, it's because the mmap_sem + * may be dropped before doing I/O or by lock_page_maybe_drop_mmap(). * * If our return value does not have VM_FAULT_RETRY set, the mmap_sem * has not been released. @@ -2825,7 +2823,11 @@ repeat: } filler: - err = filler(data, page); + if (filler) + err = filler(data, page); + else + err = mapping->a_ops->readpage(data, page); + if (err < 0) { put_page(page); return ERR_PTR(err); @@ -2915,7 +2917,8 @@ struct page *read_cache_page(struct address_space *mapping, int (*filler)(void *, struct page *), void *data) { - return do_read_cache_page(mapping, index, filler, data, mapping_gfp_mask(mapping)); + return do_read_cache_page(mapping, index, filler, data, + mapping_gfp_mask(mapping)); } EXPORT_SYMBOL(read_cache_page); @@ -2936,9 +2939,7 @@ struct page *read_cache_page_gfp(struct address_space *mapping, pgoff_t index, gfp_t gfp) { - filler_t *filler = (filler_t *)mapping->a_ops->readpage; - - return do_read_cache_page(mapping, index, filler, NULL, gfp); + return do_read_cache_page(mapping, index, NULL, NULL, gfp); } EXPORT_SYMBOL(read_cache_page_gfp); @@ -134,6 +134,7 @@ void put_user_pages(struct page **pages, unsigned long npages) } EXPORT_SYMBOL(put_user_pages); +#ifdef CONFIG_MMU static struct page *no_page_table(struct vm_area_struct *vma, unsigned int flags) { @@ -515,7 +516,7 @@ static struct page *follow_p4d_mask(struct vm_area_struct *vma, * an error pointer if there is a mapping to something not represented * by a page descriptor (see also vm_normal_page()). */ -struct page *follow_page_mask(struct vm_area_struct *vma, +static struct page *follow_page_mask(struct vm_area_struct *vma, unsigned long address, unsigned int flags, struct follow_page_context *ctx) { @@ -585,11 +586,14 @@ static int get_gate_page(struct mm_struct *mm, unsigned long address, pgd = pgd_offset_k(address); else pgd = pgd_offset_gate(mm, address); - BUG_ON(pgd_none(*pgd)); + if (pgd_none(*pgd)) + return -EFAULT; p4d = p4d_offset(pgd, address); - BUG_ON(p4d_none(*p4d)); + if (p4d_none(*p4d)) + return -EFAULT; pud = pud_offset(p4d, address); - BUG_ON(pud_none(*pud)); + if (pud_none(*pud)) + return -EFAULT; pmd = pmd_offset(pud, address); if (!pmd_present(*pmd)) return -EFAULT; @@ -1101,86 +1105,6 @@ static __always_inline long __get_user_pages_locked(struct task_struct *tsk, } /* - * We can leverage the VM_FAULT_RETRY functionality in the page fault - * paths better by using either get_user_pages_locked() or - * get_user_pages_unlocked(). - * - * get_user_pages_locked() is suitable to replace the form: - * - * down_read(&mm->mmap_sem); - * do_something() - * get_user_pages(tsk, mm, ..., pages, NULL); - * up_read(&mm->mmap_sem); - * - * to: - * - * int locked = 1; - * down_read(&mm->mmap_sem); - * do_something() - * get_user_pages_locked(tsk, mm, ..., pages, &locked); - * if (locked) - * up_read(&mm->mmap_sem); - */ -long get_user_pages_locked(unsigned long start, unsigned long nr_pages, - unsigned int gup_flags, struct page **pages, - int *locked) -{ - /* - * FIXME: Current FOLL_LONGTERM behavior is incompatible with - * FAULT_FLAG_ALLOW_RETRY because of the FS DAX check requirement on - * vmas. As there are no users of this flag in this call we simply - * disallow this option for now. - */ - if (WARN_ON_ONCE(gup_flags & FOLL_LONGTERM)) - return -EINVAL; - - return __get_user_pages_locked(current, current->mm, start, nr_pages, - pages, NULL, locked, - gup_flags | FOLL_TOUCH); -} -EXPORT_SYMBOL(get_user_pages_locked); - -/* - * get_user_pages_unlocked() is suitable to replace the form: - * - * down_read(&mm->mmap_sem); - * get_user_pages(tsk, mm, ..., pages, NULL); - * up_read(&mm->mmap_sem); - * - * with: - * - * get_user_pages_unlocked(tsk, mm, ..., pages); - * - * It is functionally equivalent to get_user_pages_fast so - * get_user_pages_fast should be used instead if specific gup_flags - * (e.g. FOLL_FORCE) are not required. - */ -long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages, - struct page **pages, unsigned int gup_flags) -{ - struct mm_struct *mm = current->mm; - int locked = 1; - long ret; - - /* - * FIXME: Current FOLL_LONGTERM behavior is incompatible with - * FAULT_FLAG_ALLOW_RETRY because of the FS DAX check requirement on - * vmas. As there are no users of this flag in this call we simply - * disallow this option for now. - */ - if (WARN_ON_ONCE(gup_flags & FOLL_LONGTERM)) - return -EINVAL; - - down_read(&mm->mmap_sem); - ret = __get_user_pages_locked(current, mm, start, nr_pages, pages, NULL, - &locked, gup_flags | FOLL_TOUCH); - if (locked) - up_read(&mm->mmap_sem); - return ret; -} -EXPORT_SYMBOL(get_user_pages_unlocked); - -/* * get_user_pages_remote() - pin user pages in memory * @tsk: the task_struct to use for page fault accounting, or * NULL if faults are not to be recorded. @@ -1256,6 +1180,198 @@ long get_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm, } EXPORT_SYMBOL(get_user_pages_remote); +/** + * populate_vma_page_range() - populate a range of pages in the vma. + * @vma: target vma + * @start: start address + * @end: end address + * @nonblocking: + * + * This takes care of mlocking the pages too if VM_LOCKED is set. + * + * return 0 on success, negative error code on error. + * + * vma->vm_mm->mmap_sem must be held. + * + * If @nonblocking is NULL, it may be held for read or write and will + * be unperturbed. + * + * If @nonblocking is non-NULL, it must held for read only and may be + * released. If it's released, *@nonblocking will be set to 0. + */ +long populate_vma_page_range(struct vm_area_struct *vma, + unsigned long start, unsigned long end, int *nonblocking) +{ + struct mm_struct *mm = vma->vm_mm; + unsigned long nr_pages = (end - start) / PAGE_SIZE; + int gup_flags; + + VM_BUG_ON(start & ~PAGE_MASK); + VM_BUG_ON(end & ~PAGE_MASK); + VM_BUG_ON_VMA(start < vma->vm_start, vma); + VM_BUG_ON_VMA(end > vma->vm_end, vma); + VM_BUG_ON_MM(!rwsem_is_locked(&mm->mmap_sem), mm); + + gup_flags = FOLL_TOUCH | FOLL_POPULATE | FOLL_MLOCK; + if (vma->vm_flags & VM_LOCKONFAULT) + gup_flags &= ~FOLL_POPULATE; + /* + * We want to touch writable mappings with a write fault in order + * to break COW, except for shared mappings because these don't COW + * and we would not want to dirty them for nothing. + */ + if ((vma->vm_flags & (VM_WRITE | VM_SHARED)) == VM_WRITE) + gup_flags |= FOLL_WRITE; + + /* + * We want mlock to succeed for regions that have any permissions + * other than PROT_NONE. + */ + if (vma->vm_flags & (VM_READ | VM_WRITE | VM_EXEC)) + gup_flags |= FOLL_FORCE; + + /* + * We made sure addr is within a VMA, so the following will + * not result in a stack expansion that recurses back here. + */ + return __get_user_pages(current, mm, start, nr_pages, gup_flags, + NULL, NULL, nonblocking); +} + +/* + * __mm_populate - populate and/or mlock pages within a range of address space. + * + * This is used to implement mlock() and the MAP_POPULATE / MAP_LOCKED mmap + * flags. VMAs must be already marked with the desired vm_flags, and + * mmap_sem must not be held. + */ +int __mm_populate(unsigned long start, unsigned long len, int ignore_errors) +{ + struct mm_struct *mm = current->mm; + unsigned long end, nstart, nend; + struct vm_area_struct *vma = NULL; + int locked = 0; + long ret = 0; + + end = start + len; + + for (nstart = start; nstart < end; nstart = nend) { + /* + * We want to fault in pages for [nstart; end) address range. + * Find first corresponding VMA. + */ + if (!locked) { + locked = 1; + down_read(&mm->mmap_sem); + vma = find_vma(mm, nstart); + } else if (nstart >= vma->vm_end) + vma = vma->vm_next; + if (!vma || vma->vm_start >= end) + break; + /* + * Set [nstart; nend) to intersection of desired address + * range with the first VMA. Also, skip undesirable VMA types. + */ + nend = min(end, vma->vm_end); + if (vma->vm_flags & (VM_IO | VM_PFNMAP)) + continue; + if (nstart < vma->vm_start) + nstart = vma->vm_start; + /* + * Now fault in a range of pages. populate_vma_page_range() + * double checks the vma flags, so that it won't mlock pages + * if the vma was already munlocked. + */ + ret = populate_vma_page_range(vma, nstart, nend, &locked); + if (ret < 0) { + if (ignore_errors) { + ret = 0; + continue; /* continue at next VMA */ + } + break; + } + nend = nstart + ret * PAGE_SIZE; + ret = 0; + } + if (locked) + up_read(&mm->mmap_sem); + return ret; /* 0 or negative error code */ +} + +/** + * get_dump_page() - pin user page in memory while writing it to core dump + * @addr: user address + * + * Returns struct page pointer of user page pinned for dump, + * to be freed afterwards by put_page(). + * + * Returns NULL on any kind of failure - a hole must then be inserted into + * the corefile, to preserve alignment with its headers; and also returns + * NULL wherever the ZERO_PAGE, or an anonymous pte_none, has been found - + * allowing a hole to be left in the corefile to save diskspace. + * + * Called without mmap_sem, but after all other threads have been killed. + */ +#ifdef CONFIG_ELF_CORE +struct page *get_dump_page(unsigned long addr) +{ + struct vm_area_struct *vma; + struct page *page; + + if (__get_user_pages(current, current->mm, addr, 1, + FOLL_FORCE | FOLL_DUMP | FOLL_GET, &page, &vma, + NULL) < 1) + return NULL; + flush_cache_page(vma, addr, page_to_pfn(page)); + return page; +} +#endif /* CONFIG_ELF_CORE */ +#else /* CONFIG_MMU */ +static long __get_user_pages_locked(struct task_struct *tsk, + struct mm_struct *mm, unsigned long start, + unsigned long nr_pages, struct page **pages, + struct vm_area_struct **vmas, int *locked, + unsigned int foll_flags) +{ + struct vm_area_struct *vma; + unsigned long vm_flags; + int i; + + /* calculate required read or write permissions. + * If FOLL_FORCE is set, we only require the "MAY" flags. + */ + vm_flags = (foll_flags & FOLL_WRITE) ? + (VM_WRITE | VM_MAYWRITE) : (VM_READ | VM_MAYREAD); + vm_flags &= (foll_flags & FOLL_FORCE) ? + (VM_MAYREAD | VM_MAYWRITE) : (VM_READ | VM_WRITE); + + for (i = 0; i < nr_pages; i++) { + vma = find_vma(mm, start); + if (!vma) + goto finish_or_fault; + + /* protect what we can, including chardevs */ + if ((vma->vm_flags & (VM_IO | VM_PFNMAP)) || + !(vm_flags & vma->vm_flags)) + goto finish_or_fault; + + if (pages) { + pages[i] = virt_to_page(start); + if (pages[i]) + get_page(pages[i]); + } + if (vmas) + vmas[i] = vma; + start = (start + PAGE_SIZE) & PAGE_MASK; + } + + return i; + +finish_or_fault: + return i ? : -EFAULT; +} +#endif /* !CONFIG_MMU */ + #if defined(CONFIG_FS_DAX) || defined (CONFIG_CMA) static bool check_dax_vmas(struct vm_area_struct **vmas, long nr_pages) { @@ -1336,25 +1452,31 @@ static long check_and_migrate_cma_pages(struct task_struct *tsk, struct vm_area_struct **vmas, unsigned int gup_flags) { - long i; + unsigned long i; + unsigned long step; bool drain_allow = true; bool migrate_allow = true; LIST_HEAD(cma_page_list); check_again: - for (i = 0; i < nr_pages; i++) { + for (i = 0; i < nr_pages;) { + + struct page *head = compound_head(pages[i]); + + /* + * gup may start from a tail page. Advance step by the left + * part. + */ + step = (1 << compound_order(head)) - (pages[i] - head); /* * If we get a page from the CMA zone, since we are going to * be pinning these entries, we might as well move them out * of the CMA zone if possible. */ - if (is_migrate_cma_page(pages[i])) { - - struct page *head = compound_head(pages[i]); - - if (PageHuge(head)) { + if (is_migrate_cma_page(head)) { + if (PageHuge(head)) isolate_huge_page(head, &cma_page_list); - } else { + else { if (!PageLRU(head) && drain_allow) { lru_add_drain_all(); drain_allow = false; @@ -1369,6 +1491,8 @@ check_again: } } } + + i += step; } if (!list_empty(&cma_page_list)) { @@ -1417,7 +1541,7 @@ static long check_and_migrate_cma_pages(struct task_struct *tsk, { return nr_pages; } -#endif +#endif /* CONFIG_CMA */ /* * __gup_longterm_locked() is a wrapper for __get_user_pages_locked which @@ -1503,155 +1627,88 @@ long get_user_pages(unsigned long start, unsigned long nr_pages, } EXPORT_SYMBOL(get_user_pages); -/** - * populate_vma_page_range() - populate a range of pages in the vma. - * @vma: target vma - * @start: start address - * @end: end address - * @nonblocking: - * - * This takes care of mlocking the pages too if VM_LOCKED is set. +/* + * We can leverage the VM_FAULT_RETRY functionality in the page fault + * paths better by using either get_user_pages_locked() or + * get_user_pages_unlocked(). * - * return 0 on success, negative error code on error. + * get_user_pages_locked() is suitable to replace the form: * - * vma->vm_mm->mmap_sem must be held. + * down_read(&mm->mmap_sem); + * do_something() + * get_user_pages(tsk, mm, ..., pages, NULL); + * up_read(&mm->mmap_sem); * - * If @nonblocking is NULL, it may be held for read or write and will - * be unperturbed. + * to: * - * If @nonblocking is non-NULL, it must held for read only and may be - * released. If it's released, *@nonblocking will be set to 0. + * int locked = 1; + * down_read(&mm->mmap_sem); + * do_something() + * get_user_pages_locked(tsk, mm, ..., pages, &locked); + * if (locked) + * up_read(&mm->mmap_sem); */ -long populate_vma_page_range(struct vm_area_struct *vma, - unsigned long start, unsigned long end, int *nonblocking) +long get_user_pages_locked(unsigned long start, unsigned long nr_pages, + unsigned int gup_flags, struct page **pages, + int *locked) { - struct mm_struct *mm = vma->vm_mm; - unsigned long nr_pages = (end - start) / PAGE_SIZE; - int gup_flags; - - VM_BUG_ON(start & ~PAGE_MASK); - VM_BUG_ON(end & ~PAGE_MASK); - VM_BUG_ON_VMA(start < vma->vm_start, vma); - VM_BUG_ON_VMA(end > vma->vm_end, vma); - VM_BUG_ON_MM(!rwsem_is_locked(&mm->mmap_sem), mm); - - gup_flags = FOLL_TOUCH | FOLL_POPULATE | FOLL_MLOCK; - if (vma->vm_flags & VM_LOCKONFAULT) - gup_flags &= ~FOLL_POPULATE; - /* - * We want to touch writable mappings with a write fault in order - * to break COW, except for shared mappings because these don't COW - * and we would not want to dirty them for nothing. - */ - if ((vma->vm_flags & (VM_WRITE | VM_SHARED)) == VM_WRITE) - gup_flags |= FOLL_WRITE; - /* - * We want mlock to succeed for regions that have any permissions - * other than PROT_NONE. + * FIXME: Current FOLL_LONGTERM behavior is incompatible with + * FAULT_FLAG_ALLOW_RETRY because of the FS DAX check requirement on + * vmas. As there are no users of this flag in this call we simply + * disallow this option for now. */ - if (vma->vm_flags & (VM_READ | VM_WRITE | VM_EXEC)) - gup_flags |= FOLL_FORCE; + if (WARN_ON_ONCE(gup_flags & FOLL_LONGTERM)) + return -EINVAL; - /* - * We made sure addr is within a VMA, so the following will - * not result in a stack expansion that recurses back here. - */ - return __get_user_pages(current, mm, start, nr_pages, gup_flags, - NULL, NULL, nonblocking); + return __get_user_pages_locked(current, current->mm, start, nr_pages, + pages, NULL, locked, + gup_flags | FOLL_TOUCH); } +EXPORT_SYMBOL(get_user_pages_locked); /* - * __mm_populate - populate and/or mlock pages within a range of address space. + * get_user_pages_unlocked() is suitable to replace the form: * - * This is used to implement mlock() and the MAP_POPULATE / MAP_LOCKED mmap - * flags. VMAs must be already marked with the desired vm_flags, and - * mmap_sem must not be held. + * down_read(&mm->mmap_sem); + * get_user_pages(tsk, mm, ..., pages, NULL); + * up_read(&mm->mmap_sem); + * + * with: + * + * get_user_pages_unlocked(tsk, mm, ..., pages); + * + * It is functionally equivalent to get_user_pages_fast so + * get_user_pages_fast should be used instead if specific gup_flags + * (e.g. FOLL_FORCE) are not required. */ -int __mm_populate(unsigned long start, unsigned long len, int ignore_errors) +long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages, + struct page **pages, unsigned int gup_flags) { struct mm_struct *mm = current->mm; - unsigned long end, nstart, nend; - struct vm_area_struct *vma = NULL; - int locked = 0; - long ret = 0; + int locked = 1; + long ret; - end = start + len; + /* + * FIXME: Current FOLL_LONGTERM behavior is incompatible with + * FAULT_FLAG_ALLOW_RETRY because of the FS DAX check requirement on + * vmas. As there are no users of this flag in this call we simply + * disallow this option for now. + */ + if (WARN_ON_ONCE(gup_flags & FOLL_LONGTERM)) + return -EINVAL; - for (nstart = start; nstart < end; nstart = nend) { - /* - * We want to fault in pages for [nstart; end) address range. - * Find first corresponding VMA. - */ - if (!locked) { - locked = 1; - down_read(&mm->mmap_sem); - vma = find_vma(mm, nstart); - } else if (nstart >= vma->vm_end) - vma = vma->vm_next; - if (!vma || vma->vm_start >= end) - break; - /* - * Set [nstart; nend) to intersection of desired address - * range with the first VMA. Also, skip undesirable VMA types. - */ - nend = min(end, vma->vm_end); - if (vma->vm_flags & (VM_IO | VM_PFNMAP)) - continue; - if (nstart < vma->vm_start) - nstart = vma->vm_start; - /* - * Now fault in a range of pages. populate_vma_page_range() - * double checks the vma flags, so that it won't mlock pages - * if the vma was already munlocked. - */ - ret = populate_vma_page_range(vma, nstart, nend, &locked); - if (ret < 0) { - if (ignore_errors) { - ret = 0; - continue; /* continue at next VMA */ - } - break; - } - nend = nstart + ret * PAGE_SIZE; - ret = 0; - } + down_read(&mm->mmap_sem); + ret = __get_user_pages_locked(current, mm, start, nr_pages, pages, NULL, + &locked, gup_flags | FOLL_TOUCH); if (locked) up_read(&mm->mmap_sem); - return ret; /* 0 or negative error code */ -} - -/** - * get_dump_page() - pin user page in memory while writing it to core dump - * @addr: user address - * - * Returns struct page pointer of user page pinned for dump, - * to be freed afterwards by put_page(). - * - * Returns NULL on any kind of failure - a hole must then be inserted into - * the corefile, to preserve alignment with its headers; and also returns - * NULL wherever the ZERO_PAGE, or an anonymous pte_none, has been found - - * allowing a hole to be left in the corefile to save diskspace. - * - * Called without mmap_sem, but after all other threads have been killed. - */ -#ifdef CONFIG_ELF_CORE -struct page *get_dump_page(unsigned long addr) -{ - struct vm_area_struct *vma; - struct page *page; - - if (__get_user_pages(current, current->mm, addr, 1, - FOLL_FORCE | FOLL_DUMP | FOLL_GET, &page, &vma, - NULL) < 1) - return NULL; - flush_cache_page(vma, addr, page_to_pfn(page)); - return page; + return ret; } -#endif /* CONFIG_ELF_CORE */ +EXPORT_SYMBOL(get_user_pages_unlocked); /* - * Generic Fast GUP + * Fast GUP * * get_user_pages_fast attempts to pin user pages by walking the page * tables directly and avoids taking locks. Thus the walker needs to be @@ -1683,20 +1740,64 @@ struct page *get_dump_page(unsigned long addr) * * This code is based heavily on the PowerPC implementation by Nick Piggin. */ -#ifdef CONFIG_HAVE_GENERIC_GUP +#ifdef CONFIG_HAVE_FAST_GUP +#ifdef CONFIG_GUP_GET_PTE_LOW_HIGH +/* + * WARNING: only to be used in the get_user_pages_fast() implementation. + * + * With get_user_pages_fast(), we walk down the pagetables without taking any + * locks. For this we would like to load the pointers atomically, but sometimes + * that is not possible (e.g. without expensive cmpxchg8b on x86_32 PAE). What + * we do have is the guarantee that a PTE will only either go from not present + * to present, or present to not present or both -- it will not switch to a + * completely different present page without a TLB flush in between; something + * that we are blocking by holding interrupts off. + * + * Setting ptes from not present to present goes: + * + * ptep->pte_high = h; + * smp_wmb(); + * ptep->pte_low = l; + * + * And present to not present goes: + * + * ptep->pte_low = 0; + * smp_wmb(); + * ptep->pte_high = 0; + * + * We must ensure here that the load of pte_low sees 'l' IFF pte_high sees 'h'. + * We load pte_high *after* loading pte_low, which ensures we don't see an older + * value of pte_high. *Then* we recheck pte_low, which ensures that we haven't + * picked up a changed pte high. We might have gotten rubbish values from + * pte_low and pte_high, but we are guaranteed that pte_low will not have the + * present bit set *unless* it is 'l'. Because get_user_pages_fast() only + * operates on present ptes we're safe. + */ +static inline pte_t gup_get_pte(pte_t *ptep) +{ + pte_t pte; -#ifndef gup_get_pte + do { + pte.pte_low = ptep->pte_low; + smp_rmb(); + pte.pte_high = ptep->pte_high; + smp_rmb(); + } while (unlikely(pte.pte_low != ptep->pte_low)); + + return pte; +} +#else /* CONFIG_GUP_GET_PTE_LOW_HIGH */ /* - * We assume that the PTE can be read atomically. If this is not the case for - * your architecture, please provide the helper. + * We require that the PTE can be read atomically. */ static inline pte_t gup_get_pte(pte_t *ptep) { return READ_ONCE(*ptep); } -#endif +#endif /* CONFIG_GUP_GET_PTE_LOW_HIGH */ -static void undo_dev_pagemap(int *nr, int nr_start, struct page **pages) +static void __maybe_unused undo_dev_pagemap(int *nr, int nr_start, + struct page **pages) { while ((*nr) - nr_start) { struct page *page = pages[--(*nr)]; @@ -1877,6 +1978,90 @@ static int __gup_device_huge_pud(pud_t pud, pud_t *pudp, unsigned long addr, } #endif +#ifdef CONFIG_ARCH_HAS_HUGEPD +static unsigned long hugepte_addr_end(unsigned long addr, unsigned long end, + unsigned long sz) +{ + unsigned long __boundary = (addr + sz) & ~(sz-1); + return (__boundary - 1 < end - 1) ? __boundary : end; +} + +static int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr, + unsigned long end, int write, struct page **pages, int *nr) +{ + unsigned long pte_end; + struct page *head, *page; + pte_t pte; + int refs; + + pte_end = (addr + sz) & ~(sz-1); + if (pte_end < end) + end = pte_end; + + pte = READ_ONCE(*ptep); + + if (!pte_access_permitted(pte, write)) + return 0; + + /* hugepages are never "special" */ + VM_BUG_ON(!pfn_valid(pte_pfn(pte))); + + refs = 0; + head = pte_page(pte); + + page = head + ((addr & (sz-1)) >> PAGE_SHIFT); + do { + VM_BUG_ON(compound_head(page) != head); + pages[*nr] = page; + (*nr)++; + page++; + refs++; + } while (addr += PAGE_SIZE, addr != end); + + head = try_get_compound_head(head, refs); + if (!head) { + *nr -= refs; + return 0; + } + + if (unlikely(pte_val(pte) != pte_val(*ptep))) { + /* Could be optimized better */ + *nr -= refs; + while (refs--) + put_page(head); + return 0; + } + + SetPageReferenced(head); + return 1; +} + +static int gup_huge_pd(hugepd_t hugepd, unsigned long addr, + unsigned int pdshift, unsigned long end, int write, + struct page **pages, int *nr) +{ + pte_t *ptep; + unsigned long sz = 1UL << hugepd_shift(hugepd); + unsigned long next; + + ptep = hugepte_offset(hugepd, addr, pdshift); + do { + next = hugepte_addr_end(addr, end, sz); + if (!gup_hugepte(ptep, sz, addr, end, write, pages, nr)) + return 0; + } while (ptep++, addr = next, addr != end); + + return 1; +} +#else +static inline int gup_huge_pd(hugepd_t hugepd, unsigned long addr, + unsigned pdshift, unsigned long end, int write, + struct page **pages, int *nr) +{ + return 0; +} +#endif /* CONFIG_ARCH_HAS_HUGEPD */ + static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { @@ -2117,19 +2302,21 @@ static void gup_pgd_range(unsigned long addr, unsigned long end, return; } while (pgdp++, addr = next, addr != end); } +#else +static inline void gup_pgd_range(unsigned long addr, unsigned long end, + unsigned int flags, struct page **pages, int *nr) +{ +} +#endif /* CONFIG_HAVE_FAST_GUP */ #ifndef gup_fast_permitted /* * Check if it's allowed to use __get_user_pages_fast() for the range, or * we need to fall back to the slow version: */ -bool gup_fast_permitted(unsigned long start, int nr_pages) +static bool gup_fast_permitted(unsigned long start, unsigned long end) { - unsigned long len, end; - - len = (unsigned long) nr_pages << PAGE_SHIFT; - end = start + len; - return end >= start; + return true; } #endif @@ -2138,6 +2325,9 @@ bool gup_fast_permitted(unsigned long start, int nr_pages) * the regular GUP. * Note a difference with get_user_pages_fast: this always returns the * number of pages pinned, 0 if no pages were pinned. + * + * If the architecture does not support this function, simply return with no + * pages pinned. */ int __get_user_pages_fast(unsigned long start, int nr_pages, int write, struct page **pages) @@ -2146,10 +2336,12 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write, unsigned long flags; int nr = 0; - start &= PAGE_MASK; + start = untagged_addr(start) & PAGE_MASK; len = (unsigned long) nr_pages << PAGE_SHIFT; end = start + len; + if (end <= start) + return 0; if (unlikely(!access_ok((void __user *)start, len))) return 0; @@ -2165,7 +2357,8 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write, * block IPIs that come from THPs splitting. */ - if (gup_fast_permitted(start, nr_pages)) { + if (IS_ENABLED(CONFIG_HAVE_FAST_GUP) && + gup_fast_permitted(start, end)) { local_irq_save(flags); gup_pgd_range(start, end, write ? FOLL_WRITE : 0, pages, &nr); local_irq_restore(flags); @@ -2173,6 +2366,7 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write, return nr; } +EXPORT_SYMBOL_GPL(__get_user_pages_fast); static int __gup_longterm_unlocked(unsigned long start, int nr_pages, unsigned int gup_flags, struct page **pages) @@ -2219,18 +2413,21 @@ int get_user_pages_fast(unsigned long start, int nr_pages, unsigned long addr, len, end; int nr = 0, ret = 0; - start &= PAGE_MASK; + if (WARN_ON_ONCE(gup_flags & ~(FOLL_WRITE | FOLL_LONGTERM))) + return -EINVAL; + + start = untagged_addr(start) & PAGE_MASK; addr = start; len = (unsigned long) nr_pages << PAGE_SHIFT; end = start + len; - if (nr_pages <= 0) + if (end <= start) return 0; - if (unlikely(!access_ok((void __user *)start, len))) return -EFAULT; - if (gup_fast_permitted(start, nr_pages)) { + if (IS_ENABLED(CONFIG_HAVE_FAST_GUP) && + gup_fast_permitted(start, end)) { local_irq_disable(); gup_pgd_range(addr, end, gup_flags, pages, &nr); local_irq_enable(); @@ -2256,5 +2453,4 @@ int get_user_pages_fast(unsigned long start, int nr_pages, return ret; } - -#endif /* CONFIG_HAVE_GENERIC_GUP */ +EXPORT_SYMBOL_GPL(get_user_pages_fast); diff --git a/mm/kasan/common.c b/mm/kasan/common.c index 242fdc01aaa9..2277b82902d8 100644 --- a/mm/kasan/common.c +++ b/mm/kasan/common.c @@ -14,8 +14,6 @@ * */ -#define __KASAN_INTERNAL - #include <linux/export.h> #include <linux/interrupt.h> #include <linux/init.h> @@ -89,17 +87,17 @@ void kasan_disable_current(void) current->kasan_depth--; } -void kasan_check_read(const volatile void *p, unsigned int size) +bool __kasan_check_read(const volatile void *p, unsigned int size) { - check_memory_region((unsigned long)p, size, false, _RET_IP_); + return check_memory_region((unsigned long)p, size, false, _RET_IP_); } -EXPORT_SYMBOL(kasan_check_read); +EXPORT_SYMBOL(__kasan_check_read); -void kasan_check_write(const volatile void *p, unsigned int size) +bool __kasan_check_write(const volatile void *p, unsigned int size) { - check_memory_region((unsigned long)p, size, true, _RET_IP_); + return check_memory_region((unsigned long)p, size, true, _RET_IP_); } -EXPORT_SYMBOL(kasan_check_write); +EXPORT_SYMBOL(__kasan_check_write); #undef memset void *memset(void *addr, int c, size_t len) diff --git a/mm/kasan/generic.c b/mm/kasan/generic.c index 504c79363a34..616f9dd82d12 100644 --- a/mm/kasan/generic.c +++ b/mm/kasan/generic.c @@ -166,29 +166,30 @@ static __always_inline bool memory_is_poisoned(unsigned long addr, size_t size) return memory_is_poisoned_n(addr, size); } -static __always_inline void check_memory_region_inline(unsigned long addr, +static __always_inline bool check_memory_region_inline(unsigned long addr, size_t size, bool write, unsigned long ret_ip) { if (unlikely(size == 0)) - return; + return true; if (unlikely((void *)addr < kasan_shadow_to_mem((void *)KASAN_SHADOW_START))) { kasan_report(addr, size, write, ret_ip); - return; + return false; } if (likely(!memory_is_poisoned(addr, size))) - return; + return true; kasan_report(addr, size, write, ret_ip); + return false; } -void check_memory_region(unsigned long addr, size_t size, bool write, +bool check_memory_region(unsigned long addr, size_t size, bool write, unsigned long ret_ip) { - check_memory_region_inline(addr, size, write, ret_ip); + return check_memory_region_inline(addr, size, write, ret_ip); } void kasan_cache_shrink(struct kmem_cache *cache) diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h index 3ce956efa0cb..014f19e76247 100644 --- a/mm/kasan/kasan.h +++ b/mm/kasan/kasan.h @@ -43,6 +43,11 @@ #define KASAN_ALLOCA_REDZONE_SIZE 32 +/* + * Stack frame marker (compiler ABI). + */ +#define KASAN_CURRENT_STACK_FRAME_MAGIC 0x41B58AB3 + /* Don't break randconfig/all*config builds */ #ifndef KASAN_ABI_VERSION #define KASAN_ABI_VERSION 1 @@ -123,7 +128,15 @@ static inline bool addr_has_shadow(const void *addr) void kasan_poison_shadow(const void *address, size_t size, u8 value); -void check_memory_region(unsigned long addr, size_t size, bool write, +/** + * check_memory_region - Check memory region, and report if invalid access. + * @addr: the accessed address + * @size: the accessed size + * @write: true if access is a write access + * @ret_ip: return address + * @return: true if access was valid, false if invalid + */ +bool check_memory_region(unsigned long addr, size_t size, bool write, unsigned long ret_ip); void *find_first_bad_addr(void *addr, size_t size); diff --git a/mm/kasan/report.c b/mm/kasan/report.c index 03a443579386..0e5f965f1882 100644 --- a/mm/kasan/report.c +++ b/mm/kasan/report.c @@ -28,6 +28,7 @@ #include <linux/types.h> #include <linux/kasan.h> #include <linux/module.h> +#include <linux/sched/task_stack.h> #include <asm/sections.h> @@ -181,6 +182,168 @@ static inline bool init_task_stack_addr(const void *addr) sizeof(init_thread_union.stack)); } +static bool __must_check tokenize_frame_descr(const char **frame_descr, + char *token, size_t max_tok_len, + unsigned long *value) +{ + const char *sep = strchr(*frame_descr, ' '); + + if (sep == NULL) + sep = *frame_descr + strlen(*frame_descr); + + if (token != NULL) { + const size_t tok_len = sep - *frame_descr; + + if (tok_len + 1 > max_tok_len) { + pr_err("KASAN internal error: frame description too long: %s\n", + *frame_descr); + return false; + } + + /* Copy token (+ 1 byte for '\0'). */ + strlcpy(token, *frame_descr, tok_len + 1); + } + + /* Advance frame_descr past separator. */ + *frame_descr = sep + 1; + + if (value != NULL && kstrtoul(token, 10, value)) { + pr_err("KASAN internal error: not a valid number: %s\n", token); + return false; + } + + return true; +} + +static void print_decoded_frame_descr(const char *frame_descr) +{ + /* + * We need to parse the following string: + * "n alloc_1 alloc_2 ... alloc_n" + * where alloc_i looks like + * "offset size len name" + * or "offset size len name:line". + */ + + char token[64]; + unsigned long num_objects; + + if (!tokenize_frame_descr(&frame_descr, token, sizeof(token), + &num_objects)) + return; + + pr_err("\n"); + pr_err("this frame has %lu %s:\n", num_objects, + num_objects == 1 ? "object" : "objects"); + + while (num_objects--) { + unsigned long offset; + unsigned long size; + + /* access offset */ + if (!tokenize_frame_descr(&frame_descr, token, sizeof(token), + &offset)) + return; + /* access size */ + if (!tokenize_frame_descr(&frame_descr, token, sizeof(token), + &size)) + return; + /* name length (unused) */ + if (!tokenize_frame_descr(&frame_descr, NULL, 0, NULL)) + return; + /* object name */ + if (!tokenize_frame_descr(&frame_descr, token, sizeof(token), + NULL)) + return; + + /* Strip line number; without filename it's not very helpful. */ + strreplace(token, ':', '\0'); + + /* Finally, print object information. */ + pr_err(" [%lu, %lu) '%s'", offset, offset + size, token); + } +} + +static bool __must_check get_address_stack_frame_info(const void *addr, + unsigned long *offset, + const char **frame_descr, + const void **frame_pc) +{ + unsigned long aligned_addr; + unsigned long mem_ptr; + const u8 *shadow_bottom; + const u8 *shadow_ptr; + const unsigned long *frame; + + BUILD_BUG_ON(IS_ENABLED(CONFIG_STACK_GROWSUP)); + + /* + * NOTE: We currently only support printing frame information for + * accesses to the task's own stack. + */ + if (!object_is_on_stack(addr)) + return false; + + aligned_addr = round_down((unsigned long)addr, sizeof(long)); + mem_ptr = round_down(aligned_addr, KASAN_SHADOW_SCALE_SIZE); + shadow_ptr = kasan_mem_to_shadow((void *)aligned_addr); + shadow_bottom = kasan_mem_to_shadow(end_of_stack(current)); + + while (shadow_ptr >= shadow_bottom && *shadow_ptr != KASAN_STACK_LEFT) { + shadow_ptr--; + mem_ptr -= KASAN_SHADOW_SCALE_SIZE; + } + + while (shadow_ptr >= shadow_bottom && *shadow_ptr == KASAN_STACK_LEFT) { + shadow_ptr--; + mem_ptr -= KASAN_SHADOW_SCALE_SIZE; + } + + if (shadow_ptr < shadow_bottom) + return false; + + frame = (const unsigned long *)(mem_ptr + KASAN_SHADOW_SCALE_SIZE); + if (frame[0] != KASAN_CURRENT_STACK_FRAME_MAGIC) { + pr_err("KASAN internal error: frame info validation failed; invalid marker: %lu\n", + frame[0]); + return false; + } + + *offset = (unsigned long)addr - (unsigned long)frame; + *frame_descr = (const char *)frame[1]; + *frame_pc = (void *)frame[2]; + + return true; +} + +static void print_address_stack_frame(const void *addr) +{ + unsigned long offset; + const char *frame_descr; + const void *frame_pc; + + if (IS_ENABLED(CONFIG_KASAN_SW_TAGS)) + return; + + if (!get_address_stack_frame_info(addr, &offset, &frame_descr, + &frame_pc)) + return; + + /* + * get_address_stack_frame_info only returns true if the given addr is + * on the current task's stack. + */ + pr_err("\n"); + pr_err("addr %px is located in stack of task %s/%d at offset %lu in frame:\n", + addr, current->comm, task_pid_nr(current), offset); + pr_err(" %pS\n", frame_pc); + + if (!frame_descr) + return; + + print_decoded_frame_descr(frame_descr); +} + static void print_address_description(void *addr) { struct page *page = addr_to_page(addr); @@ -204,6 +367,8 @@ static void print_address_description(void *addr) pr_err("The buggy address belongs to the page:\n"); dump_page(page, "kasan: bad access detected"); } + + print_address_stack_frame(addr); } static bool row_is_guilty(const void *row, const void *guilty) diff --git a/mm/kasan/tags.c b/mm/kasan/tags.c index 63fca3172659..0e987c9ca052 100644 --- a/mm/kasan/tags.c +++ b/mm/kasan/tags.c @@ -76,7 +76,7 @@ void *kasan_reset_tag(const void *addr) return reset_tag(addr); } -void check_memory_region(unsigned long addr, size_t size, bool write, +bool check_memory_region(unsigned long addr, size_t size, bool write, unsigned long ret_ip) { u8 tag; @@ -84,7 +84,7 @@ void check_memory_region(unsigned long addr, size_t size, bool write, void *untagged_addr; if (unlikely(size == 0)) - return; + return true; tag = get_tag((const void *)addr); @@ -106,22 +106,24 @@ void check_memory_region(unsigned long addr, size_t size, bool write, * set to KASAN_TAG_KERNEL (0xFF)). */ if (tag == KASAN_TAG_KERNEL) - return; + return true; untagged_addr = reset_tag((const void *)addr); if (unlikely(untagged_addr < kasan_shadow_to_mem((void *)KASAN_SHADOW_START))) { kasan_report(addr, size, write, ret_ip); - return; + return false; } shadow_first = kasan_mem_to_shadow(untagged_addr); shadow_last = kasan_mem_to_shadow(untagged_addr + size - 1); for (shadow = shadow_first; shadow <= shadow_last; shadow++) { if (*shadow != tag) { kasan_report(addr, size, write, ret_ip); - return; + return false; } } + + return true; } #define DEFINE_HWASAN_LOAD_STORE(size) \ diff --git a/mm/kmemleak.c b/mm/kmemleak.c index 9dd581d11565..aa8f4fa93ca3 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -575,7 +575,7 @@ static struct kmemleak_object *create_object(unsigned long ptr, size_t size, if (in_irq()) { object->pid = 0; strncpy(object->comm, "hardirq", sizeof(object->comm)); - } else if (in_softirq()) { + } else if (in_serving_softirq()) { object->pid = 0; strncpy(object->comm, "softirq", sizeof(object->comm)); } else { @@ -1866,7 +1866,7 @@ static ssize_t kmemleak_write(struct file *file, const char __user *user_buf, } if (!kmemleak_enabled) { - ret = -EBUSY; + ret = -EPERM; goto out; } diff --git a/mm/list_lru.c b/mm/list_lru.c index 927d85be32f6..0f1f6b06b7f3 100644 --- a/mm/list_lru.c +++ b/mm/list_lru.c @@ -12,6 +12,7 @@ #include <linux/slab.h> #include <linux/mutex.h> #include <linux/memcontrol.h> +#include "slab.h" #ifdef CONFIG_MEMCG_KMEM static LIST_HEAD(list_lrus); @@ -63,7 +64,7 @@ static __always_inline struct mem_cgroup *mem_cgroup_from_kmem(void *ptr) if (!memcg_kmem_enabled()) return NULL; page = virt_to_head_page(ptr); - return page->mem_cgroup; + return memcg_from_slab_page(page); } static inline struct list_lru_one * diff --git a/mm/memcontrol.c b/mm/memcontrol.c index ba9138a4a1de..4f05735b02d3 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -57,6 +57,7 @@ #include <linux/lockdep.h> #include <linux/file.h> #include <linux/tracehook.h> +#include <linux/seq_buf.h> #include "internal.h" #include <net/sock.h> #include <net/ip.h> @@ -485,7 +486,10 @@ ino_t page_cgroup_ino(struct page *page) unsigned long ino = 0; rcu_read_lock(); - memcg = READ_ONCE(page->mem_cgroup); + if (PageHead(page) && PageSlab(page)) + memcg = memcg_from_slab_page(page); + else + memcg = READ_ONCE(page->mem_cgroup); while (memcg && !(memcg->css.flags & CSS_ONLINE)) memcg = parent_mem_cgroup(memcg); if (memcg) @@ -1163,7 +1167,7 @@ int mem_cgroup_scan_tasks(struct mem_cgroup *memcg, struct css_task_iter it; struct task_struct *task; - css_task_iter_start(&iter->css, 0, &it); + css_task_iter_start(&iter->css, CSS_TASK_ITER_PROCS, &it); while (!ret && (task = css_task_iter_next(&it))) ret = fn(task, arg); css_task_iter_end(&it); @@ -1255,32 +1259,6 @@ void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru, *lru_size += nr_pages; } -bool task_in_mem_cgroup(struct task_struct *task, struct mem_cgroup *memcg) -{ - struct mem_cgroup *task_memcg; - struct task_struct *p; - bool ret; - - p = find_lock_task_mm(task); - if (p) { - task_memcg = get_mem_cgroup_from_mm(p->mm); - task_unlock(p); - } else { - /* - * All threads may have already detached their mm's, but the oom - * killer still needs to detect if they have already been oom - * killed to prevent needlessly killing additional tasks. - */ - rcu_read_lock(); - task_memcg = mem_cgroup_from_task(task); - css_get(&task_memcg->css); - rcu_read_unlock(); - } - ret = mem_cgroup_is_descendant(task_memcg, memcg); - css_put(&task_memcg->css); - return ret; -} - /** * mem_cgroup_margin - calculate chargeable space of a memory cgroup * @memcg: the memory cgroup @@ -1356,27 +1334,114 @@ static bool mem_cgroup_wait_acct_move(struct mem_cgroup *memcg) return false; } -static const unsigned int memcg1_stats[] = { - MEMCG_CACHE, - MEMCG_RSS, - MEMCG_RSS_HUGE, - NR_SHMEM, - NR_FILE_MAPPED, - NR_FILE_DIRTY, - NR_WRITEBACK, - MEMCG_SWAP, -}; +static char *memory_stat_format(struct mem_cgroup *memcg) +{ + struct seq_buf s; + int i; -static const char *const memcg1_stat_names[] = { - "cache", - "rss", - "rss_huge", - "shmem", - "mapped_file", - "dirty", - "writeback", - "swap", -}; + seq_buf_init(&s, kmalloc(PAGE_SIZE, GFP_KERNEL), PAGE_SIZE); + if (!s.buffer) + return NULL; + + /* + * Provide statistics on the state of the memory subsystem as + * well as cumulative event counters that show past behavior. + * + * This list is ordered following a combination of these gradients: + * 1) generic big picture -> specifics and details + * 2) reflecting userspace activity -> reflecting kernel heuristics + * + * Current memory state: + */ + + seq_buf_printf(&s, "anon %llu\n", + (u64)memcg_page_state(memcg, MEMCG_RSS) * + PAGE_SIZE); + seq_buf_printf(&s, "file %llu\n", + (u64)memcg_page_state(memcg, MEMCG_CACHE) * + PAGE_SIZE); + seq_buf_printf(&s, "kernel_stack %llu\n", + (u64)memcg_page_state(memcg, MEMCG_KERNEL_STACK_KB) * + 1024); + seq_buf_printf(&s, "slab %llu\n", + (u64)(memcg_page_state(memcg, NR_SLAB_RECLAIMABLE) + + memcg_page_state(memcg, NR_SLAB_UNRECLAIMABLE)) * + PAGE_SIZE); + seq_buf_printf(&s, "sock %llu\n", + (u64)memcg_page_state(memcg, MEMCG_SOCK) * + PAGE_SIZE); + + seq_buf_printf(&s, "shmem %llu\n", + (u64)memcg_page_state(memcg, NR_SHMEM) * + PAGE_SIZE); + seq_buf_printf(&s, "file_mapped %llu\n", + (u64)memcg_page_state(memcg, NR_FILE_MAPPED) * + PAGE_SIZE); + seq_buf_printf(&s, "file_dirty %llu\n", + (u64)memcg_page_state(memcg, NR_FILE_DIRTY) * + PAGE_SIZE); + seq_buf_printf(&s, "file_writeback %llu\n", + (u64)memcg_page_state(memcg, NR_WRITEBACK) * + PAGE_SIZE); + + /* + * TODO: We should eventually replace our own MEMCG_RSS_HUGE counter + * with the NR_ANON_THP vm counter, but right now it's a pain in the + * arse because it requires migrating the work out of rmap to a place + * where the page->mem_cgroup is set up and stable. + */ + seq_buf_printf(&s, "anon_thp %llu\n", + (u64)memcg_page_state(memcg, MEMCG_RSS_HUGE) * + PAGE_SIZE); + + for (i = 0; i < NR_LRU_LISTS; i++) + seq_buf_printf(&s, "%s %llu\n", mem_cgroup_lru_names[i], + (u64)memcg_page_state(memcg, NR_LRU_BASE + i) * + PAGE_SIZE); + + seq_buf_printf(&s, "slab_reclaimable %llu\n", + (u64)memcg_page_state(memcg, NR_SLAB_RECLAIMABLE) * + PAGE_SIZE); + seq_buf_printf(&s, "slab_unreclaimable %llu\n", + (u64)memcg_page_state(memcg, NR_SLAB_UNRECLAIMABLE) * + PAGE_SIZE); + + /* Accumulated memory events */ + + seq_buf_printf(&s, "pgfault %lu\n", memcg_events(memcg, PGFAULT)); + seq_buf_printf(&s, "pgmajfault %lu\n", memcg_events(memcg, PGMAJFAULT)); + + seq_buf_printf(&s, "workingset_refault %lu\n", + memcg_page_state(memcg, WORKINGSET_REFAULT)); + seq_buf_printf(&s, "workingset_activate %lu\n", + memcg_page_state(memcg, WORKINGSET_ACTIVATE)); + seq_buf_printf(&s, "workingset_nodereclaim %lu\n", + memcg_page_state(memcg, WORKINGSET_NODERECLAIM)); + + seq_buf_printf(&s, "pgrefill %lu\n", memcg_events(memcg, PGREFILL)); + seq_buf_printf(&s, "pgscan %lu\n", + memcg_events(memcg, PGSCAN_KSWAPD) + + memcg_events(memcg, PGSCAN_DIRECT)); + seq_buf_printf(&s, "pgsteal %lu\n", + memcg_events(memcg, PGSTEAL_KSWAPD) + + memcg_events(memcg, PGSTEAL_DIRECT)); + seq_buf_printf(&s, "pgactivate %lu\n", memcg_events(memcg, PGACTIVATE)); + seq_buf_printf(&s, "pgdeactivate %lu\n", memcg_events(memcg, PGDEACTIVATE)); + seq_buf_printf(&s, "pglazyfree %lu\n", memcg_events(memcg, PGLAZYFREE)); + seq_buf_printf(&s, "pglazyfreed %lu\n", memcg_events(memcg, PGLAZYFREED)); + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + seq_buf_printf(&s, "thp_fault_alloc %lu\n", + memcg_events(memcg, THP_FAULT_ALLOC)); + seq_buf_printf(&s, "thp_collapse_alloc %lu\n", + memcg_events(memcg, THP_COLLAPSE_ALLOC)); +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + + /* The above should easily fit into one page */ + WARN_ON_ONCE(seq_buf_has_overflowed(&s)); + + return s.buffer; +} #define K(x) ((x) << (PAGE_SHIFT-10)) /** @@ -1411,39 +1476,32 @@ void mem_cgroup_print_oom_context(struct mem_cgroup *memcg, struct task_struct * */ void mem_cgroup_print_oom_meminfo(struct mem_cgroup *memcg) { - struct mem_cgroup *iter; - unsigned int i; + char *buf; pr_info("memory: usage %llukB, limit %llukB, failcnt %lu\n", K((u64)page_counter_read(&memcg->memory)), K((u64)memcg->memory.max), memcg->memory.failcnt); - pr_info("memory+swap: usage %llukB, limit %llukB, failcnt %lu\n", - K((u64)page_counter_read(&memcg->memsw)), - K((u64)memcg->memsw.max), memcg->memsw.failcnt); - pr_info("kmem: usage %llukB, limit %llukB, failcnt %lu\n", - K((u64)page_counter_read(&memcg->kmem)), - K((u64)memcg->kmem.max), memcg->kmem.failcnt); - - for_each_mem_cgroup_tree(iter, memcg) { - pr_info("Memory cgroup stats for "); - pr_cont_cgroup_path(iter->css.cgroup); - pr_cont(":"); - - for (i = 0; i < ARRAY_SIZE(memcg1_stats); i++) { - if (memcg1_stats[i] == MEMCG_SWAP && !do_swap_account) - continue; - pr_cont(" %s:%luKB", memcg1_stat_names[i], - K(memcg_page_state_local(iter, - memcg1_stats[i]))); - } - - for (i = 0; i < NR_LRU_LISTS; i++) - pr_cont(" %s:%luKB", mem_cgroup_lru_names[i], - K(memcg_page_state_local(iter, - NR_LRU_BASE + i))); - - pr_cont("\n"); + if (cgroup_subsys_on_dfl(memory_cgrp_subsys)) + pr_info("swap: usage %llukB, limit %llukB, failcnt %lu\n", + K((u64)page_counter_read(&memcg->swap)), + K((u64)memcg->swap.max), memcg->swap.failcnt); + else { + pr_info("memory+swap: usage %llukB, limit %llukB, failcnt %lu\n", + K((u64)page_counter_read(&memcg->memsw)), + K((u64)memcg->memsw.max), memcg->memsw.failcnt); + pr_info("kmem: usage %llukB, limit %llukB, failcnt %lu\n", + K((u64)page_counter_read(&memcg->kmem)), + K((u64)memcg->kmem.max), memcg->kmem.failcnt); } + + pr_info("Memory cgroup stats for "); + pr_cont_cgroup_path(memcg->css.cgroup); + pr_cont(":"); + buf = memory_stat_format(memcg); + if (!buf) + return; + pr_info("%s", buf); + kfree(buf); } /* @@ -2279,7 +2337,6 @@ static int try_charge(struct mem_cgroup *memcg, gfp_t gfp_mask, unsigned long nr_reclaimed; bool may_swap = true; bool drained = false; - bool oomed = false; enum oom_status oom_status; if (mem_cgroup_is_root(memcg)) @@ -2366,7 +2423,7 @@ retry: if (nr_retries--) goto retry; - if (gfp_mask & __GFP_RETRY_MAYFAIL && oomed) + if (gfp_mask & __GFP_RETRY_MAYFAIL) goto nomem; if (gfp_mask & __GFP_NOFAIL) @@ -2385,7 +2442,6 @@ retry: switch (oom_status) { case OOM_SUCCESS: nr_retries = MEM_CGROUP_RECLAIM_RETRIES; - oomed = true; goto retry; case OOM_FAILED: goto force; @@ -2588,12 +2644,13 @@ static void memcg_schedule_kmem_cache_create(struct mem_cgroup *memcg, { struct memcg_kmem_cache_create_work *cw; + if (!css_tryget_online(&memcg->css)) + return; + cw = kmalloc(sizeof(*cw), GFP_NOWAIT | __GFP_NOWARN); if (!cw) return; - css_get(&memcg->css); - cw->memcg = memcg; cw->cachep = cachep; INIT_WORK(&cw->work, memcg_kmem_cache_create_func); @@ -2628,6 +2685,7 @@ struct kmem_cache *memcg_kmem_get_cache(struct kmem_cache *cachep) { struct mem_cgroup *memcg; struct kmem_cache *memcg_cachep; + struct memcg_cache_array *arr; int kmemcg_id; VM_BUG_ON(!is_root_cache(cachep)); @@ -2635,14 +2693,28 @@ struct kmem_cache *memcg_kmem_get_cache(struct kmem_cache *cachep) if (memcg_kmem_bypass()) return cachep; - memcg = get_mem_cgroup_from_current(); + rcu_read_lock(); + + if (unlikely(current->active_memcg)) + memcg = current->active_memcg; + else + memcg = mem_cgroup_from_task(current); + + if (!memcg || memcg == root_mem_cgroup) + goto out_unlock; + kmemcg_id = READ_ONCE(memcg->kmemcg_id); if (kmemcg_id < 0) - goto out; + goto out_unlock; - memcg_cachep = cache_from_memcg_idx(cachep, kmemcg_id); - if (likely(memcg_cachep)) - return memcg_cachep; + arr = rcu_dereference(cachep->memcg_params.memcg_caches); + + /* + * Make sure we will access the up-to-date value. The code updating + * memcg_caches issues a write barrier to match the data dependency + * barrier inside READ_ONCE() (see memcg_create_kmem_cache()). + */ + memcg_cachep = READ_ONCE(arr->entries[kmemcg_id]); /* * If we are in a safe context (can wait, and not in interrupt @@ -2655,10 +2727,20 @@ struct kmem_cache *memcg_kmem_get_cache(struct kmem_cache *cachep) * memcg_create_kmem_cache, this means no further allocation * could happen with the slab_mutex held. So it's better to * defer everything. + * + * If the memcg is dying or memcg_cache is about to be released, + * don't bother creating new kmem_caches. Because memcg_cachep + * is ZEROed as the fist step of kmem offlining, we don't need + * percpu_ref_tryget_live() here. css_tryget_online() check in + * memcg_schedule_kmem_cache_create() will prevent us from + * creation of a new kmem_cache. */ - memcg_schedule_kmem_cache_create(memcg, cachep); -out: - css_put(&memcg->css); + if (unlikely(!memcg_cachep)) + memcg_schedule_kmem_cache_create(memcg, cachep); + else if (percpu_ref_tryget(&memcg_cachep->memcg_params.refcnt)) + cachep = memcg_cachep; +out_unlock: + rcu_read_unlock(); return cachep; } @@ -2669,7 +2751,7 @@ out: void memcg_kmem_put_cache(struct kmem_cache *cachep) { if (!is_root_cache(cachep)) - css_put(&cachep->memcg_params.memcg->css); + percpu_ref_put(&cachep->memcg_params.refcnt); } /** @@ -2697,9 +2779,6 @@ int __memcg_kmem_charge_memcg(struct page *page, gfp_t gfp, int order, cancel_charge(memcg, nr_pages); return -ENOMEM; } - - page->mem_cgroup = memcg; - return 0; } @@ -2722,12 +2801,30 @@ int __memcg_kmem_charge(struct page *page, gfp_t gfp, int order) memcg = get_mem_cgroup_from_current(); if (!mem_cgroup_is_root(memcg)) { ret = __memcg_kmem_charge_memcg(page, gfp, order, memcg); - if (!ret) + if (!ret) { + page->mem_cgroup = memcg; __SetPageKmemcg(page); + } } css_put(&memcg->css); return ret; } + +/** + * __memcg_kmem_uncharge_memcg: uncharge a kmem page + * @memcg: memcg to uncharge + * @nr_pages: number of pages to uncharge + */ +void __memcg_kmem_uncharge_memcg(struct mem_cgroup *memcg, + unsigned int nr_pages) +{ + if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) + page_counter_uncharge(&memcg->kmem, nr_pages); + + page_counter_uncharge(&memcg->memory, nr_pages); + if (do_memsw_account()) + page_counter_uncharge(&memcg->memsw, nr_pages); +} /** * __memcg_kmem_uncharge: uncharge a kmem page * @page: page to uncharge @@ -2742,14 +2839,7 @@ void __memcg_kmem_uncharge(struct page *page, int order) return; VM_BUG_ON_PAGE(mem_cgroup_is_root(memcg), page); - - if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) - page_counter_uncharge(&memcg->kmem, nr_pages); - - page_counter_uncharge(&memcg->memory, nr_pages); - if (do_memsw_account()) - page_counter_uncharge(&memcg->memsw, nr_pages); - + __memcg_kmem_uncharge_memcg(memcg, nr_pages); page->mem_cgroup = NULL; /* slab pages do not have PageKmemcg flag set */ @@ -3168,15 +3258,15 @@ static void memcg_offline_kmem(struct mem_cgroup *memcg) */ memcg->kmem_state = KMEM_ALLOCATED; - memcg_deactivate_kmem_caches(memcg); - - kmemcg_id = memcg->kmemcg_id; - BUG_ON(kmemcg_id < 0); - parent = parent_mem_cgroup(memcg); if (!parent) parent = root_mem_cgroup; + memcg_deactivate_kmem_caches(memcg, parent); + + kmemcg_id = memcg->kmemcg_id; + BUG_ON(kmemcg_id < 0); + /* * Change kmemcg_id of this cgroup and all its descendants to the * parent's id, and then move all entries from this cgroup's list_lrus @@ -3207,9 +3297,8 @@ static void memcg_free_kmem(struct mem_cgroup *memcg) memcg_offline_kmem(memcg); if (memcg->kmem_state == KMEM_ALLOCATED) { - memcg_destroy_kmem_caches(memcg); + WARN_ON(!list_empty(&memcg->kmem_caches)); static_branch_dec(&memcg_kmem_enabled_key); - WARN_ON(page_counter_read(&memcg->kmem)); } } #else @@ -3472,6 +3561,28 @@ static int memcg_numa_stat_show(struct seq_file *m, void *v) } #endif /* CONFIG_NUMA */ +static const unsigned int memcg1_stats[] = { + MEMCG_CACHE, + MEMCG_RSS, + MEMCG_RSS_HUGE, + NR_SHMEM, + NR_FILE_MAPPED, + NR_FILE_DIRTY, + NR_WRITEBACK, + MEMCG_SWAP, +}; + +static const char *const memcg1_stat_names[] = { + "cache", + "rss", + "rss_huge", + "shmem", + "mapped_file", + "dirty", + "writeback", + "swap", +}; + /* Universal VM events cgroup1 shows, original sort order */ static const unsigned int memcg1_events[] = { PGPGIN, @@ -3530,12 +3641,13 @@ static int memcg_stat_show(struct seq_file *m, void *v) if (memcg1_stats[i] == MEMCG_SWAP && !do_memsw_account()) continue; seq_printf(m, "total_%s %llu\n", memcg1_stat_names[i], - (u64)memcg_page_state(memcg, i) * PAGE_SIZE); + (u64)memcg_page_state(memcg, memcg1_stats[i]) * + PAGE_SIZE); } for (i = 0; i < ARRAY_SIZE(memcg1_events); i++) seq_printf(m, "total_%s %llu\n", memcg1_event_names[i], - (u64)memcg_events(memcg, i)); + (u64)memcg_events(memcg, memcg1_events[i])); for (i = 0; i < NR_LRU_LISTS; i++) seq_printf(m, "total_%s %llu\n", mem_cgroup_lru_names[i], @@ -4634,6 +4746,9 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) /* The following stuff does not apply to the root */ if (!parent) { +#ifdef CONFIG_MEMCG_KMEM + INIT_LIST_HEAD(&memcg->kmem_caches); +#endif root_mem_cgroup = memcg; return &memcg->css; } @@ -5625,112 +5740,42 @@ static ssize_t memory_max_write(struct kernfs_open_file *of, return nbytes; } +static void __memory_events_show(struct seq_file *m, atomic_long_t *events) +{ + seq_printf(m, "low %lu\n", atomic_long_read(&events[MEMCG_LOW])); + seq_printf(m, "high %lu\n", atomic_long_read(&events[MEMCG_HIGH])); + seq_printf(m, "max %lu\n", atomic_long_read(&events[MEMCG_MAX])); + seq_printf(m, "oom %lu\n", atomic_long_read(&events[MEMCG_OOM])); + seq_printf(m, "oom_kill %lu\n", + atomic_long_read(&events[MEMCG_OOM_KILL])); +} + static int memory_events_show(struct seq_file *m, void *v) { struct mem_cgroup *memcg = mem_cgroup_from_seq(m); - seq_printf(m, "low %lu\n", - atomic_long_read(&memcg->memory_events[MEMCG_LOW])); - seq_printf(m, "high %lu\n", - atomic_long_read(&memcg->memory_events[MEMCG_HIGH])); - seq_printf(m, "max %lu\n", - atomic_long_read(&memcg->memory_events[MEMCG_MAX])); - seq_printf(m, "oom %lu\n", - atomic_long_read(&memcg->memory_events[MEMCG_OOM])); - seq_printf(m, "oom_kill %lu\n", - atomic_long_read(&memcg->memory_events[MEMCG_OOM_KILL])); - + __memory_events_show(m, memcg->memory_events); return 0; } -static int memory_stat_show(struct seq_file *m, void *v) +static int memory_events_local_show(struct seq_file *m, void *v) { struct mem_cgroup *memcg = mem_cgroup_from_seq(m); - int i; - - /* - * Provide statistics on the state of the memory subsystem as - * well as cumulative event counters that show past behavior. - * - * This list is ordered following a combination of these gradients: - * 1) generic big picture -> specifics and details - * 2) reflecting userspace activity -> reflecting kernel heuristics - * - * Current memory state: - */ - - seq_printf(m, "anon %llu\n", - (u64)memcg_page_state(memcg, MEMCG_RSS) * PAGE_SIZE); - seq_printf(m, "file %llu\n", - (u64)memcg_page_state(memcg, MEMCG_CACHE) * PAGE_SIZE); - seq_printf(m, "kernel_stack %llu\n", - (u64)memcg_page_state(memcg, MEMCG_KERNEL_STACK_KB) * 1024); - seq_printf(m, "slab %llu\n", - (u64)(memcg_page_state(memcg, NR_SLAB_RECLAIMABLE) + - memcg_page_state(memcg, NR_SLAB_UNRECLAIMABLE)) * - PAGE_SIZE); - seq_printf(m, "sock %llu\n", - (u64)memcg_page_state(memcg, MEMCG_SOCK) * PAGE_SIZE); - - seq_printf(m, "shmem %llu\n", - (u64)memcg_page_state(memcg, NR_SHMEM) * PAGE_SIZE); - seq_printf(m, "file_mapped %llu\n", - (u64)memcg_page_state(memcg, NR_FILE_MAPPED) * PAGE_SIZE); - seq_printf(m, "file_dirty %llu\n", - (u64)memcg_page_state(memcg, NR_FILE_DIRTY) * PAGE_SIZE); - seq_printf(m, "file_writeback %llu\n", - (u64)memcg_page_state(memcg, NR_WRITEBACK) * PAGE_SIZE); - /* - * TODO: We should eventually replace our own MEMCG_RSS_HUGE counter - * with the NR_ANON_THP vm counter, but right now it's a pain in the - * arse because it requires migrating the work out of rmap to a place - * where the page->mem_cgroup is set up and stable. - */ - seq_printf(m, "anon_thp %llu\n", - (u64)memcg_page_state(memcg, MEMCG_RSS_HUGE) * PAGE_SIZE); - - for (i = 0; i < NR_LRU_LISTS; i++) - seq_printf(m, "%s %llu\n", mem_cgroup_lru_names[i], - (u64)memcg_page_state(memcg, NR_LRU_BASE + i) * - PAGE_SIZE); - - seq_printf(m, "slab_reclaimable %llu\n", - (u64)memcg_page_state(memcg, NR_SLAB_RECLAIMABLE) * - PAGE_SIZE); - seq_printf(m, "slab_unreclaimable %llu\n", - (u64)memcg_page_state(memcg, NR_SLAB_UNRECLAIMABLE) * - PAGE_SIZE); - - /* Accumulated memory events */ - - seq_printf(m, "pgfault %lu\n", memcg_events(memcg, PGFAULT)); - seq_printf(m, "pgmajfault %lu\n", memcg_events(memcg, PGMAJFAULT)); - - seq_printf(m, "workingset_refault %lu\n", - memcg_page_state(memcg, WORKINGSET_REFAULT)); - seq_printf(m, "workingset_activate %lu\n", - memcg_page_state(memcg, WORKINGSET_ACTIVATE)); - seq_printf(m, "workingset_nodereclaim %lu\n", - memcg_page_state(memcg, WORKINGSET_NODERECLAIM)); - - seq_printf(m, "pgrefill %lu\n", memcg_events(memcg, PGREFILL)); - seq_printf(m, "pgscan %lu\n", memcg_events(memcg, PGSCAN_KSWAPD) + - memcg_events(memcg, PGSCAN_DIRECT)); - seq_printf(m, "pgsteal %lu\n", memcg_events(memcg, PGSTEAL_KSWAPD) + - memcg_events(memcg, PGSTEAL_DIRECT)); - seq_printf(m, "pgactivate %lu\n", memcg_events(memcg, PGACTIVATE)); - seq_printf(m, "pgdeactivate %lu\n", memcg_events(memcg, PGDEACTIVATE)); - seq_printf(m, "pglazyfree %lu\n", memcg_events(memcg, PGLAZYFREE)); - seq_printf(m, "pglazyfreed %lu\n", memcg_events(memcg, PGLAZYFREED)); + __memory_events_show(m, memcg->memory_events_local); + return 0; +} -#ifdef CONFIG_TRANSPARENT_HUGEPAGE - seq_printf(m, "thp_fault_alloc %lu\n", - memcg_events(memcg, THP_FAULT_ALLOC)); - seq_printf(m, "thp_collapse_alloc %lu\n", - memcg_events(memcg, THP_COLLAPSE_ALLOC)); -#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ +static int memory_stat_show(struct seq_file *m, void *v) +{ + struct mem_cgroup *memcg = mem_cgroup_from_seq(m); + char *buf; + buf = memory_stat_format(memcg); + if (!buf) + return -ENOMEM; + seq_puts(m, buf); + kfree(buf); return 0; } @@ -5802,6 +5847,12 @@ static struct cftype memory_files[] = { .seq_show = memory_events_show, }, { + .name = "events.local", + .flags = CFTYPE_NOT_ON_ROOT, + .file_offset = offsetof(struct mem_cgroup, events_local_file), + .seq_show = memory_events_local_show, + }, + { .name = "stat", .flags = CFTYPE_NOT_ON_ROOT, .seq_show = memory_stat_show, diff --git a/mm/memory-failure.c b/mm/memory-failure.c index f045514d8d20..7e08cbf3ba49 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -213,7 +213,7 @@ static int kill_proc(struct to_kill *tk, unsigned long pfn, int flags) short addr_lsb = tk->size_shift; int ret; - pr_err("Memory failure: %#lx: Killing %s:%d due to hardware memory corruption\n", + pr_err("Memory failure: %#lx: Sending SIGBUS to %s:%d due to hardware memory corruption\n", pfn, t->comm, t->pid); if ((flags & MF_ACTION_REQUIRED) && t->mm == current->mm) { diff --git a/mm/memory.c b/mm/memory.c index ddf20bd0c317..53bd59579861 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1475,8 +1475,6 @@ static int insert_page(struct vm_area_struct *vma, unsigned long addr, set_pte_at(mm, addr, pte, mk_pte(page, prot)); retval = 0; - pte_unmap_unlock(pte, ptl); - return retval; out_unlock: pte_unmap_unlock(pte, ptl); out: @@ -1547,7 +1545,7 @@ static int __vm_map_pages(struct vm_area_struct *vma, struct page **pages, int ret, i; /* Fail if the user requested offset is beyond the end of the object */ - if (offset > num) + if (offset >= num) return -ENXIO; /* Fail if the user requested size exceeds available object size */ @@ -2038,7 +2036,6 @@ static int apply_to_pte_range(struct mm_struct *mm, pmd_t *pmd, { pte_t *pte; int err; - pgtable_t token; spinlock_t *uninitialized_var(ptl); pte = (mm == &init_mm) ? @@ -2051,10 +2048,8 @@ static int apply_to_pte_range(struct mm_struct *mm, pmd_t *pmd, arch_enter_lazy_mmu_mode(); - token = pmd_pgtable(*pmd); - do { - err = fn(pte++, token, addr, data); + err = fn(pte++, addr, data); if (err) break; } while (addr += PAGE_SIZE, addr != end); @@ -2807,7 +2802,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) struct swap_info_struct *si = swp_swap_info(entry); if (si->flags & SWP_SYNCHRONOUS_IO && - __swap_count(si, entry) == 1) { + __swap_count(entry) == 1) { /* skip swapcache */ page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, vmf->address); @@ -4349,7 +4344,9 @@ int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm, void *old_buf = buf; int write = gup_flags & FOLL_WRITE; - down_read(&mm->mmap_sem); + if (down_read_killable(&mm->mmap_sem)) + return 0; + /* ignore errors, just check how much was successfully transferred */ while (len) { int bytes, ret, offset; diff --git a/mm/mincore.c b/mm/mincore.c index c3f058bd0faf..4fe91d497436 100644 --- a/mm/mincore.c +++ b/mm/mincore.c @@ -68,8 +68,16 @@ static unsigned char mincore_page(struct address_space *mapping, pgoff_t pgoff) */ if (xa_is_value(page)) { swp_entry_t swp = radix_to_swp_entry(page); - page = find_get_page(swap_address_space(swp), - swp_offset(swp)); + struct swap_info_struct *si; + + /* Prevent swap device to being swapoff under us */ + si = get_swap_device(swp); + if (si) { + page = find_get_page(swap_address_space(swp), + swp_offset(swp)); + put_swap_device(si); + } else + page = NULL; } } else page = find_get_page(mapping, pgoff); diff --git a/mm/mmu_notifier.c b/mm/mmu_notifier.c index 513b9607409d..b5670620aea0 100644 --- a/mm/mmu_notifier.c +++ b/mm/mmu_notifier.c @@ -274,7 +274,7 @@ static int do_mmu_notifier_register(struct mmu_notifier *mn, * thanks to mm_take_all_locks(). */ spin_lock(&mm->mmu_notifier_mm->lock); - hlist_add_head(&mn->hlist, &mm->mmu_notifier_mm->list); + hlist_add_head_rcu(&mn->hlist, &mm->mmu_notifier_mm->list); spin_unlock(&mm->mmu_notifier_mm->lock); mm_drop_all_locks(mm); diff --git a/mm/nommu.c b/mm/nommu.c index d8c02fbe03b5..eb3e2e558da1 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -111,94 +111,6 @@ unsigned int kobjsize(const void *objp) return PAGE_SIZE << compound_order(page); } -static long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, - unsigned long start, unsigned long nr_pages, - unsigned int foll_flags, struct page **pages, - struct vm_area_struct **vmas, int *nonblocking) -{ - struct vm_area_struct *vma; - unsigned long vm_flags; - int i; - - /* calculate required read or write permissions. - * If FOLL_FORCE is set, we only require the "MAY" flags. - */ - vm_flags = (foll_flags & FOLL_WRITE) ? - (VM_WRITE | VM_MAYWRITE) : (VM_READ | VM_MAYREAD); - vm_flags &= (foll_flags & FOLL_FORCE) ? - (VM_MAYREAD | VM_MAYWRITE) : (VM_READ | VM_WRITE); - - for (i = 0; i < nr_pages; i++) { - vma = find_vma(mm, start); - if (!vma) - goto finish_or_fault; - - /* protect what we can, including chardevs */ - if ((vma->vm_flags & (VM_IO | VM_PFNMAP)) || - !(vm_flags & vma->vm_flags)) - goto finish_or_fault; - - if (pages) { - pages[i] = virt_to_page(start); - if (pages[i]) - get_page(pages[i]); - } - if (vmas) - vmas[i] = vma; - start = (start + PAGE_SIZE) & PAGE_MASK; - } - - return i; - -finish_or_fault: - return i ? : -EFAULT; -} - -/* - * get a list of pages in an address range belonging to the specified process - * and indicate the VMA that covers each page - * - this is potentially dodgy as we may end incrementing the page count of a - * slab page or a secondary page from a compound page - * - don't permit access to VMAs that don't support it, such as I/O mappings - */ -long get_user_pages(unsigned long start, unsigned long nr_pages, - unsigned int gup_flags, struct page **pages, - struct vm_area_struct **vmas) -{ - return __get_user_pages(current, current->mm, start, nr_pages, - gup_flags, pages, vmas, NULL); -} -EXPORT_SYMBOL(get_user_pages); - -long get_user_pages_locked(unsigned long start, unsigned long nr_pages, - unsigned int gup_flags, struct page **pages, - int *locked) -{ - return get_user_pages(start, nr_pages, gup_flags, pages, NULL); -} -EXPORT_SYMBOL(get_user_pages_locked); - -static long __get_user_pages_unlocked(struct task_struct *tsk, - struct mm_struct *mm, unsigned long start, - unsigned long nr_pages, struct page **pages, - unsigned int gup_flags) -{ - long ret; - down_read(&mm->mmap_sem); - ret = __get_user_pages(tsk, mm, start, nr_pages, gup_flags, pages, - NULL, NULL); - up_read(&mm->mmap_sem); - return ret; -} - -long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages, - struct page **pages, unsigned int gup_flags) -{ - return __get_user_pages_unlocked(current, current->mm, start, nr_pages, - pages, gup_flags); -} -EXPORT_SYMBOL(get_user_pages_unlocked); - /** * follow_pfn - look up PFN at a user virtual address * @vma: memory mapping @@ -1792,7 +1704,8 @@ int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm, struct vm_area_struct *vma; int write = gup_flags & FOLL_WRITE; - down_read(&mm->mmap_sem); + if (down_read_killable(&mm->mmap_sem)) + return 0; /* the access must start within one of the target process's mappings */ vma = find_vma(mm, addr); diff --git a/mm/oom_kill.c b/mm/oom_kill.c index f719b64741d6..eda2e2a0bdc6 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -64,21 +64,33 @@ int sysctl_oom_dump_tasks = 1; */ DEFINE_MUTEX(oom_lock); +static inline bool is_memcg_oom(struct oom_control *oc) +{ + return oc->memcg != NULL; +} + #ifdef CONFIG_NUMA /** - * has_intersects_mems_allowed() - check task eligiblity for kill + * oom_cpuset_eligible() - check task eligiblity for kill * @start: task struct of which task to consider * @mask: nodemask passed to page allocator for mempolicy ooms * * Task eligibility is determined by whether or not a candidate task, @tsk, * shares the same mempolicy nodes as current if it is bound by such a policy * and whether or not it has the same set of allowed cpuset nodes. + * + * This function is assuming oom-killer context and 'current' has triggered + * the oom-killer. */ -static bool has_intersects_mems_allowed(struct task_struct *start, - const nodemask_t *mask) +static bool oom_cpuset_eligible(struct task_struct *start, + struct oom_control *oc) { struct task_struct *tsk; bool ret = false; + const nodemask_t *mask = oc->nodemask; + + if (is_memcg_oom(oc)) + return true; rcu_read_lock(); for_each_thread(start, tsk) { @@ -105,8 +117,7 @@ static bool has_intersects_mems_allowed(struct task_struct *start, return ret; } #else -static bool has_intersects_mems_allowed(struct task_struct *tsk, - const nodemask_t *mask) +static bool oom_cpuset_eligible(struct task_struct *tsk, struct oom_control *oc) { return true; } @@ -146,28 +157,13 @@ static inline bool is_sysrq_oom(struct oom_control *oc) return oc->order == -1; } -static inline bool is_memcg_oom(struct oom_control *oc) -{ - return oc->memcg != NULL; -} - /* return true if the task is not adequate as candidate victim task. */ -static bool oom_unkillable_task(struct task_struct *p, - struct mem_cgroup *memcg, const nodemask_t *nodemask) +static bool oom_unkillable_task(struct task_struct *p) { if (is_global_init(p)) return true; if (p->flags & PF_KTHREAD) return true; - - /* When mem_cgroup_out_of_memory() and p is not member of the group */ - if (memcg && !task_in_mem_cgroup(p, memcg)) - return true; - - /* p may not have freeable memory in nodemask */ - if (!has_intersects_mems_allowed(p, nodemask)) - return true; - return false; } @@ -194,20 +190,17 @@ static bool is_dump_unreclaim_slabs(void) * oom_badness - heuristic function to determine which candidate task to kill * @p: task struct of which task we should calculate * @totalpages: total present RAM allowed for page allocation - * @memcg: task's memory controller, if constrained - * @nodemask: nodemask passed to page allocator for mempolicy ooms * * The heuristic for determining which task to kill is made to be as simple and * predictable as possible. The goal is to return the highest value for the * task consuming the most memory to avoid subsequent oom failures. */ -unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg, - const nodemask_t *nodemask, unsigned long totalpages) +unsigned long oom_badness(struct task_struct *p, unsigned long totalpages) { long points; long adj; - if (oom_unkillable_task(p, memcg, nodemask)) + if (oom_unkillable_task(p)) return 0; p = find_lock_task_mm(p); @@ -318,7 +311,11 @@ static int oom_evaluate_task(struct task_struct *task, void *arg) struct oom_control *oc = arg; unsigned long points; - if (oom_unkillable_task(task, NULL, oc->nodemask)) + if (oom_unkillable_task(task)) + goto next; + + /* p may not have freeable memory in nodemask */ + if (!is_memcg_oom(oc) && !oom_cpuset_eligible(task, oc)) goto next; /* @@ -342,13 +339,10 @@ static int oom_evaluate_task(struct task_struct *task, void *arg) goto select; } - points = oom_badness(task, NULL, oc->nodemask, oc->totalpages); + points = oom_badness(task, oc->totalpages); if (!points || points < oc->chosen_points) goto next; - /* Prefer thread group leaders for display purposes */ - if (points == oc->chosen_points && thread_group_leader(oc->chosen)) - goto next; select: if (oc->chosen) put_task_struct(oc->chosen); @@ -381,14 +375,44 @@ static void select_bad_process(struct oom_control *oc) break; rcu_read_unlock(); } +} - oc->chosen_points = oc->chosen_points * 1000 / oc->totalpages; +static int dump_task(struct task_struct *p, void *arg) +{ + struct oom_control *oc = arg; + struct task_struct *task; + + if (oom_unkillable_task(p)) + return 0; + + /* p may not have freeable memory in nodemask */ + if (!is_memcg_oom(oc) && !oom_cpuset_eligible(p, oc)) + return 0; + + task = find_lock_task_mm(p); + if (!task) { + /* + * This is a kthread or all of p's threads have already + * detached their mm's. There's no need to report + * them; they can't be oom killed anyway. + */ + return 0; + } + + pr_info("[%7d] %5d %5d %8lu %8lu %8ld %8lu %5hd %s\n", + task->pid, from_kuid(&init_user_ns, task_uid(task)), + task->tgid, task->mm->total_vm, get_mm_rss(task->mm), + mm_pgtables_bytes(task->mm), + get_mm_counter(task->mm, MM_SWAPENTS), + task->signal->oom_score_adj, task->comm); + task_unlock(task); + + return 0; } /** * dump_tasks - dump current memory state of all system tasks - * @memcg: current's memory controller, if constrained - * @nodemask: nodemask passed to page allocator for mempolicy ooms + * @oc: pointer to struct oom_control * * Dumps the current memory state of all eligible tasks. Tasks not in the same * memcg, not in the same cpuset, or bound to a disjoint set of mempolicy nodes @@ -396,37 +420,21 @@ static void select_bad_process(struct oom_control *oc) * State information includes task's pid, uid, tgid, vm size, rss, * pgtables_bytes, swapents, oom_score_adj value, and name. */ -static void dump_tasks(struct mem_cgroup *memcg, const nodemask_t *nodemask) +static void dump_tasks(struct oom_control *oc) { - struct task_struct *p; - struct task_struct *task; - pr_info("Tasks state (memory values in pages):\n"); pr_info("[ pid ] uid tgid total_vm rss pgtables_bytes swapents oom_score_adj name\n"); - rcu_read_lock(); - for_each_process(p) { - if (oom_unkillable_task(p, memcg, nodemask)) - continue; - task = find_lock_task_mm(p); - if (!task) { - /* - * This is a kthread or all of p's threads have already - * detached their mm's. There's no need to report - * them; they can't be oom killed anyway. - */ - continue; - } + if (is_memcg_oom(oc)) + mem_cgroup_scan_tasks(oc->memcg, dump_task, oc); + else { + struct task_struct *p; - pr_info("[%7d] %5d %5d %8lu %8lu %8ld %8lu %5hd %s\n", - task->pid, from_kuid(&init_user_ns, task_uid(task)), - task->tgid, task->mm->total_vm, get_mm_rss(task->mm), - mm_pgtables_bytes(task->mm), - get_mm_counter(task->mm, MM_SWAPENTS), - task->signal->oom_score_adj, task->comm); - task_unlock(task); + rcu_read_lock(); + for_each_process(p) + dump_task(p, oc); + rcu_read_unlock(); } - rcu_read_unlock(); } static void dump_oom_summary(struct oom_control *oc, struct task_struct *victim) @@ -458,7 +466,7 @@ static void dump_header(struct oom_control *oc, struct task_struct *p) dump_unreclaimable_slab(); } if (sysctl_oom_dump_tasks) - dump_tasks(oc->memcg, oc->nodemask); + dump_tasks(oc); if (p) dump_oom_summary(oc, p); } @@ -1075,7 +1083,8 @@ bool out_of_memory(struct oom_control *oc) check_panic_on_oom(oc); if (!is_memcg_oom(oc) && sysctl_oom_kill_allocating_task && - current->mm && !oom_unkillable_task(current, NULL, oc->nodemask) && + current->mm && !oom_unkillable_task(current) && + oom_cpuset_eligible(current, oc) && current->signal->oom_score_adj != OOM_SCORE_ADJ_MIN) { get_task_struct(current); oc->chosen = current; diff --git a/mm/page-writeback.c b/mm/page-writeback.c index bdbe8b6b1225..1804f64ff43c 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -2429,7 +2429,6 @@ void account_page_dirtied(struct page *page, struct address_space *mapping) this_cpu_inc(bdp_ratelimits); } } -EXPORT_SYMBOL(account_page_dirtied); /* * Helper function for deaccounting dirty page without writeback. diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 8e3bc949ebcc..dbd0d5cbbcbb 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -50,7 +50,6 @@ #include <linux/backing-dev.h> #include <linux/fault-inject.h> #include <linux/page-isolation.h> -#include <linux/page_ext.h> #include <linux/debugobjects.h> #include <linux/kmemleak.h> #include <linux/compaction.h> @@ -136,6 +135,55 @@ unsigned long totalcma_pages __read_mostly; int percpu_pagelist_fraction; gfp_t gfp_allowed_mask __read_mostly = GFP_BOOT_MASK; +#ifdef CONFIG_INIT_ON_ALLOC_DEFAULT_ON +DEFINE_STATIC_KEY_TRUE(init_on_alloc); +#else +DEFINE_STATIC_KEY_FALSE(init_on_alloc); +#endif +EXPORT_SYMBOL(init_on_alloc); + +#ifdef CONFIG_INIT_ON_FREE_DEFAULT_ON +DEFINE_STATIC_KEY_TRUE(init_on_free); +#else +DEFINE_STATIC_KEY_FALSE(init_on_free); +#endif +EXPORT_SYMBOL(init_on_free); + +static int __init early_init_on_alloc(char *buf) +{ + int ret; + bool bool_result; + + if (!buf) + return -EINVAL; + ret = kstrtobool(buf, &bool_result); + if (bool_result && page_poisoning_enabled()) + pr_info("mem auto-init: CONFIG_PAGE_POISONING is on, will take precedence over init_on_alloc\n"); + if (bool_result) + static_branch_enable(&init_on_alloc); + else + static_branch_disable(&init_on_alloc); + return ret; +} +early_param("init_on_alloc", early_init_on_alloc); + +static int __init early_init_on_free(char *buf) +{ + int ret; + bool bool_result; + + if (!buf) + return -EINVAL; + ret = kstrtobool(buf, &bool_result); + if (bool_result && page_poisoning_enabled()) + pr_info("mem auto-init: CONFIG_PAGE_POISONING is on, will take precedence over init_on_free\n"); + if (bool_result) + static_branch_enable(&init_on_free); + else + static_branch_disable(&init_on_free); + return ret; +} +early_param("init_on_free", early_init_on_free); /* * A cached value of the page's pageblock's migratetype, used when the page is @@ -224,8 +272,6 @@ int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES] = { [ZONE_MOVABLE] = 0, }; -EXPORT_SYMBOL(totalram_pages); - static char * const zone_names[MAX_NR_ZONES] = { #ifdef CONFIG_ZONE_DMA "DMA", @@ -646,30 +692,29 @@ void prep_compound_page(struct page *page, unsigned int order) #ifdef CONFIG_DEBUG_PAGEALLOC unsigned int _debug_guardpage_minorder; -bool _debug_pagealloc_enabled __read_mostly - = IS_ENABLED(CONFIG_DEBUG_PAGEALLOC_ENABLE_DEFAULT); + +#ifdef CONFIG_DEBUG_PAGEALLOC_ENABLE_DEFAULT +DEFINE_STATIC_KEY_TRUE(_debug_pagealloc_enabled); +#else +DEFINE_STATIC_KEY_FALSE(_debug_pagealloc_enabled); +#endif EXPORT_SYMBOL(_debug_pagealloc_enabled); -bool _debug_guardpage_enabled __read_mostly; + +DEFINE_STATIC_KEY_FALSE(_debug_guardpage_enabled); static int __init early_debug_pagealloc(char *buf) { - if (!buf) + bool enable = false; + + if (kstrtobool(buf, &enable)) return -EINVAL; - return kstrtobool(buf, &_debug_pagealloc_enabled); -} -early_param("debug_pagealloc", early_debug_pagealloc); -static bool need_debug_guardpage(void) -{ - /* If we don't use debug_pagealloc, we don't need guard page */ - if (!debug_pagealloc_enabled()) - return false; + if (enable) + static_branch_enable(&_debug_pagealloc_enabled); - if (!debug_guardpage_minorder()) - return false; - - return true; + return 0; } +early_param("debug_pagealloc", early_debug_pagealloc); static void init_debug_guardpage(void) { @@ -679,14 +724,9 @@ static void init_debug_guardpage(void) if (!debug_guardpage_minorder()) return; - _debug_guardpage_enabled = true; + static_branch_enable(&_debug_guardpage_enabled); } -struct page_ext_operations debug_guardpage_ops = { - .need = need_debug_guardpage, - .init = init_debug_guardpage, -}; - static int __init debug_guardpage_minorder_setup(char *buf) { unsigned long res; @@ -704,20 +744,13 @@ early_param("debug_guardpage_minorder", debug_guardpage_minorder_setup); static inline bool set_page_guard(struct zone *zone, struct page *page, unsigned int order, int migratetype) { - struct page_ext *page_ext; - if (!debug_guardpage_enabled()) return false; if (order >= debug_guardpage_minorder()) return false; - page_ext = lookup_page_ext(page); - if (unlikely(!page_ext)) - return false; - - __set_bit(PAGE_EXT_DEBUG_GUARD, &page_ext->flags); - + __SetPageGuard(page); INIT_LIST_HEAD(&page->lru); set_page_private(page, order); /* Guard pages are not available for any usage */ @@ -729,23 +762,16 @@ static inline bool set_page_guard(struct zone *zone, struct page *page, static inline void clear_page_guard(struct zone *zone, struct page *page, unsigned int order, int migratetype) { - struct page_ext *page_ext; - if (!debug_guardpage_enabled()) return; - page_ext = lookup_page_ext(page); - if (unlikely(!page_ext)) - return; - - __clear_bit(PAGE_EXT_DEBUG_GUARD, &page_ext->flags); + __ClearPageGuard(page); set_page_private(page, 0); if (!is_migrate_isolate(migratetype)) __mod_zone_freepage_state(zone, (1 << order), migratetype); } #else -struct page_ext_operations debug_guardpage_ops; static inline bool set_page_guard(struct zone *zone, struct page *page, unsigned int order, int migratetype) { return false; } static inline void clear_page_guard(struct zone *zone, struct page *page, @@ -1090,6 +1116,14 @@ out: return ret; } +static void kernel_init_free_pages(struct page *page, int numpages) +{ + int i; + + for (i = 0; i < numpages; i++) + clear_highpage(page + i); +} + static __always_inline bool free_pages_prepare(struct page *page, unsigned int order, bool check_free) { @@ -1141,6 +1175,9 @@ static __always_inline bool free_pages_prepare(struct page *page, PAGE_SIZE << order); } arch_free_page(page, order); + if (want_init_on_free()) + kernel_init_free_pages(page, 1 << order); + kernel_poison_pages(page, 1 << order, 0); if (debug_pagealloc_enabled()) kernel_map_pages(page, 1 << order, 0); @@ -1151,19 +1188,36 @@ static __always_inline bool free_pages_prepare(struct page *page, } #ifdef CONFIG_DEBUG_VM -static inline bool free_pcp_prepare(struct page *page) +/* + * With DEBUG_VM enabled, order-0 pages are checked immediately when being freed + * to pcp lists. With debug_pagealloc also enabled, they are also rechecked when + * moved from pcp lists to free lists. + */ +static bool free_pcp_prepare(struct page *page) { return free_pages_prepare(page, 0, true); } -static inline bool bulkfree_pcp_prepare(struct page *page) +static bool bulkfree_pcp_prepare(struct page *page) { - return false; + if (debug_pagealloc_enabled()) + return free_pages_check(page); + else + return false; } #else +/* + * With DEBUG_VM disabled, order-0 pages being freed are checked only when + * moving from pcp lists to free list in order to reduce overhead. With + * debug_pagealloc enabled, they are checked also immediately when being freed + * to the pcp lists. + */ static bool free_pcp_prepare(struct page *page) { - return free_pages_prepare(page, 0, false); + if (debug_pagealloc_enabled()) + return free_pages_prepare(page, 0, true); + else + return free_pages_prepare(page, 0, false); } static bool bulkfree_pcp_prepare(struct page *page) @@ -1904,6 +1958,10 @@ void __init page_alloc_init_late(void) for_each_populated_zone(zone) set_zone_contiguous(zone); + +#ifdef CONFIG_DEBUG_PAGEALLOC + init_debug_guardpage(); +#endif } #ifdef CONFIG_CMA @@ -2021,28 +2079,44 @@ static inline int check_new_page(struct page *page) static inline bool free_pages_prezeroed(void) { - return IS_ENABLED(CONFIG_PAGE_POISONING_ZERO) && - page_poisoning_enabled(); + return (IS_ENABLED(CONFIG_PAGE_POISONING_ZERO) && + page_poisoning_enabled()) || want_init_on_free(); } #ifdef CONFIG_DEBUG_VM -static bool check_pcp_refill(struct page *page) +/* + * With DEBUG_VM enabled, order-0 pages are checked for expected state when + * being allocated from pcp lists. With debug_pagealloc also enabled, they are + * also checked when pcp lists are refilled from the free lists. + */ +static inline bool check_pcp_refill(struct page *page) { - return false; + if (debug_pagealloc_enabled()) + return check_new_page(page); + else + return false; } -static bool check_new_pcp(struct page *page) +static inline bool check_new_pcp(struct page *page) { return check_new_page(page); } #else -static bool check_pcp_refill(struct page *page) +/* + * With DEBUG_VM disabled, free order-0 pages are checked for expected state + * when pcp lists are being refilled from the free lists. With debug_pagealloc + * enabled, they are also checked when being allocated from the pcp lists. + */ +static inline bool check_pcp_refill(struct page *page) { return check_new_page(page); } -static bool check_new_pcp(struct page *page) +static inline bool check_new_pcp(struct page *page) { - return false; + if (debug_pagealloc_enabled()) + return check_new_page(page); + else + return false; } #endif /* CONFIG_DEBUG_VM */ @@ -2076,13 +2150,10 @@ inline void post_alloc_hook(struct page *page, unsigned int order, static void prep_new_page(struct page *page, unsigned int order, gfp_t gfp_flags, unsigned int alloc_flags) { - int i; - post_alloc_hook(page, order, gfp_flags); - if (!free_pages_prezeroed() && (gfp_flags & __GFP_ZERO)) - for (i = 0; i < (1 << order); i++) - clear_highpage(page + i); + if (!free_pages_prezeroed() && want_init_on_alloc(gfp_flags)) + kernel_init_free_pages(page, 1 << order); if (order && (gfp_flags & __GFP_COMP)) prep_compound_page(page, order); @@ -7520,10 +7591,28 @@ static int page_alloc_cpu_dead(unsigned int cpu) return 0; } +#ifdef CONFIG_NUMA +int hashdist = HASHDIST_DEFAULT; + +static int __init set_hashdist(char *str) +{ + if (!str) + return 0; + hashdist = simple_strtoul(str, &str, 0); + return 1; +} +__setup("hashdist=", set_hashdist); +#endif + void __init page_alloc_init(void) { int ret; +#ifdef CONFIG_NUMA + if (num_node_state(N_MEMORY) == 1) + hashdist = 0; +#endif + ret = cpuhp_setup_state_nocalls(CPUHP_PAGE_ALLOC_DEAD, "mm/page_alloc:dead", NULL, page_alloc_cpu_dead); @@ -7908,19 +7997,6 @@ out: return ret; } -#ifdef CONFIG_NUMA -int hashdist = HASHDIST_DEFAULT; - -static int __init set_hashdist(char *str) -{ - if (!str) - return 0; - hashdist = simple_strtoul(str, &str, 0); - return 1; -} -__setup("hashdist=", set_hashdist); -#endif - #ifndef __HAVE_ARCH_RESERVED_KERNEL_PAGES /* * Returns the number of pages that arch has reserved but @@ -7967,6 +8043,7 @@ void *__init alloc_large_system_hash(const char *tablename, unsigned long log2qty, size; void *table = NULL; gfp_t gfp_flags; + bool virt; /* allow the kernel cmdline to have a say */ if (!numentries) { @@ -8023,6 +8100,7 @@ void *__init alloc_large_system_hash(const char *tablename, gfp_flags = (flags & HASH_ZERO) ? GFP_ATOMIC | __GFP_ZERO : GFP_ATOMIC; do { + virt = false; size = bucketsize << log2qty; if (flags & HASH_EARLY) { if (flags & HASH_ZERO) @@ -8030,26 +8108,26 @@ void *__init alloc_large_system_hash(const char *tablename, else table = memblock_alloc_raw(size, SMP_CACHE_BYTES); - } else if (hashdist) { + } else if (get_order(size) >= MAX_ORDER || hashdist) { table = __vmalloc(size, gfp_flags, PAGE_KERNEL); + virt = true; } else { /* * If bucketsize is not a power-of-two, we may free * some pages at the end of hash table which * alloc_pages_exact() automatically does */ - if (get_order(size) < MAX_ORDER) { - table = alloc_pages_exact(size, gfp_flags); - kmemleak_alloc(table, size, 1, gfp_flags); - } + table = alloc_pages_exact(size, gfp_flags); + kmemleak_alloc(table, size, 1, gfp_flags); } } while (!table && size > PAGE_SIZE && --log2qty); if (!table) panic("Failed to allocate %s hash table\n", tablename); - pr_info("%s hash table entries: %ld (order: %d, %lu bytes)\n", - tablename, 1UL << log2qty, ilog2(size) - PAGE_SHIFT, size); + pr_info("%s hash table entries: %ld (order: %d, %lu bytes, %s)\n", + tablename, 1UL << log2qty, ilog2(size) - PAGE_SHIFT, size, + virt ? "vmalloc" : "linear"); if (_hash_shift) *_hash_shift = log2qty; diff --git a/mm/page_ext.c b/mm/page_ext.c index d8f1aca4ad43..5f5769c7db3b 100644 --- a/mm/page_ext.c +++ b/mm/page_ext.c @@ -59,9 +59,6 @@ */ static struct page_ext_operations *page_ext_ops[] = { -#ifdef CONFIG_DEBUG_PAGEALLOC - &debug_guardpage_ops, -#endif #ifdef CONFIG_PAGE_OWNER &page_owner_ops, #endif diff --git a/mm/page_io.c b/mm/page_io.c index a39aac2f8c8d..24ee600f9131 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -163,7 +163,7 @@ int generic_swapfile_activate(struct swap_info_struct *sis, blocks_per_page = PAGE_SIZE >> blkbits; /* - * Map all the blocks into the extent list. This code doesn't try + * Map all the blocks into the extent tree. This code doesn't try * to be very smart. */ probe_block = 0; diff --git a/mm/page_isolation.c b/mm/page_isolation.c index e3638a5bafff..89c19c0feadb 100644 --- a/mm/page_isolation.c +++ b/mm/page_isolation.c @@ -230,7 +230,7 @@ undo: /* * Make isolated pages available again. */ -int undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, +void undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, unsigned migratetype) { unsigned long pfn; @@ -247,7 +247,6 @@ int undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, continue; unset_migratetype_isolate(page, migratetype); } - return 0; } /* * Test all pages in the range is free(means isolated) or not. diff --git a/mm/slab.c b/mm/slab.c index f7117ad9b3a3..9df370558e5d 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -371,12 +371,6 @@ static void **dbg_userword(struct kmem_cache *cachep, void *objp) static int slab_max_order = SLAB_MAX_ORDER_LO; static bool slab_max_order_set __initdata; -static inline struct kmem_cache *virt_to_cache(const void *obj) -{ - struct page *page = virt_to_head_page(obj); - return page->slab_cache; -} - static inline void *index_to_obj(struct kmem_cache *cache, struct page *page, unsigned int idx) { @@ -1245,7 +1239,7 @@ void __init kmem_cache_init(void) nr_node_ids * sizeof(struct kmem_cache_node *), SLAB_HWCACHE_ALIGN, 0, 0); list_add(&kmem_cache->list, &slab_caches); - memcg_link_cache(kmem_cache); + memcg_link_cache(kmem_cache, NULL); slab_state = PARTIAL; /* @@ -1366,7 +1360,6 @@ static struct page *kmem_getpages(struct kmem_cache *cachep, gfp_t flags, int nodeid) { struct page *page; - int nr_pages; flags |= cachep->allocflags; @@ -1376,17 +1369,11 @@ static struct page *kmem_getpages(struct kmem_cache *cachep, gfp_t flags, return NULL; } - if (memcg_charge_slab(page, flags, cachep->gfporder, cachep)) { + if (charge_slab_page(page, flags, cachep->gfporder, cachep)) { __free_pages(page, cachep->gfporder); return NULL; } - nr_pages = (1 << cachep->gfporder); - if (cachep->flags & SLAB_RECLAIM_ACCOUNT) - mod_lruvec_page_state(page, NR_SLAB_RECLAIMABLE, nr_pages); - else - mod_lruvec_page_state(page, NR_SLAB_UNRECLAIMABLE, nr_pages); - __SetPageSlab(page); /* Record if ALLOC_NO_WATERMARKS was set when allocating the slab */ if (sk_memalloc_socks() && page_is_pfmemalloc(page)) @@ -1401,12 +1388,6 @@ static struct page *kmem_getpages(struct kmem_cache *cachep, gfp_t flags, static void kmem_freepages(struct kmem_cache *cachep, struct page *page) { int order = cachep->gfporder; - unsigned long nr_freed = (1 << order); - - if (cachep->flags & SLAB_RECLAIM_ACCOUNT) - mod_lruvec_page_state(page, NR_SLAB_RECLAIMABLE, -nr_freed); - else - mod_lruvec_page_state(page, NR_SLAB_UNRECLAIMABLE, -nr_freed); BUG_ON(!PageSlab(page)); __ClearPageSlabPfmemalloc(page); @@ -1415,8 +1396,8 @@ static void kmem_freepages(struct kmem_cache *cachep, struct page *page) page->mapping = NULL; if (current->reclaim_state) - current->reclaim_state->reclaimed_slab += nr_freed; - memcg_uncharge_slab(page, order, cachep); + current->reclaim_state->reclaimed_slab += 1 << order; + uncharge_slab_page(page, order, cachep); __free_pages(page, order); } @@ -1830,6 +1811,14 @@ static bool set_objfreelist_slab_cache(struct kmem_cache *cachep, cachep->num = 0; + /* + * If slab auto-initialization on free is enabled, store the freelist + * off-slab, so that its contents don't end up in one of the allocated + * objects. + */ + if (unlikely(slab_want_init_on_free(cachep))) + return false; + if (cachep->ctor || flags & SLAB_TYPESAFE_BY_RCU) return false; @@ -2258,6 +2247,10 @@ void __kmemcg_cache_deactivate(struct kmem_cache *cachep) { __kmem_cache_shrink(cachep); } + +void __kmemcg_cache_deactivate_after_rcu(struct kmem_cache *s) +{ +} #endif int __kmem_cache_shutdown(struct kmem_cache *cachep) @@ -3263,7 +3256,7 @@ slab_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid, local_irq_restore(save_flags); ptr = cache_alloc_debugcheck_after(cachep, flags, ptr, caller); - if (unlikely(flags & __GFP_ZERO) && ptr) + if (unlikely(slab_want_init_on_alloc(flags, cachep)) && ptr) memset(ptr, 0, cachep->object_size); slab_post_alloc_hook(cachep, flags, 1, &ptr); @@ -3320,7 +3313,7 @@ slab_alloc(struct kmem_cache *cachep, gfp_t flags, unsigned long caller) objp = cache_alloc_debugcheck_after(cachep, flags, objp, caller); prefetchw(objp); - if (unlikely(flags & __GFP_ZERO) && objp) + if (unlikely(slab_want_init_on_alloc(flags, cachep)) && objp) memset(objp, 0, cachep->object_size); slab_post_alloc_hook(cachep, flags, 1, &objp); @@ -3441,6 +3434,8 @@ void ___cache_free(struct kmem_cache *cachep, void *objp, struct array_cache *ac = cpu_cache_get(cachep); check_irq_off(); + if (unlikely(slab_want_init_on_free(cachep))) + memset(objp, 0, cachep->object_size); kmemleak_free_recursive(objp, cachep->flags); objp = cache_free_debugcheck(cachep, objp, caller); @@ -3528,7 +3523,7 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size, cache_alloc_debugcheck_after_bulk(s, flags, size, p, _RET_IP_); /* Clear memory outside IRQ disabled section */ - if (unlikely(flags & __GFP_ZERO)) + if (unlikely(slab_want_init_on_alloc(flags, s))) for (i = 0; i < size; i++) memset(p[i], 0, s->object_size); @@ -3715,6 +3710,8 @@ void kmem_cache_free_bulk(struct kmem_cache *orig_s, size_t size, void **p) s = virt_to_cache(objp); else s = cache_from_obj(orig_s, objp); + if (!s) + continue; debug_check_no_locks_freed(objp, s->object_size); if (!(s->flags & SLAB_DEBUG_OBJECTS)) @@ -3749,6 +3746,10 @@ void kfree(const void *objp) local_irq_save(flags); kfree_debugcheck(objp); c = virt_to_cache(objp); + if (!c) { + local_irq_restore(flags); + return; + } debug_check_no_locks_freed(objp, c->object_size); debug_check_no_obj_freed(objp, c->object_size); @@ -4204,33 +4205,23 @@ void __check_heap_object(const void *ptr, unsigned long n, struct page *page, #endif /* CONFIG_HARDENED_USERCOPY */ /** - * ksize - get the actual amount of memory allocated for a given object - * @objp: Pointer to the object - * - * kmalloc may internally round up allocations and return more memory - * than requested. ksize() can be used to determine the actual amount of - * memory allocated. The caller may use this additional memory, even though - * a smaller amount of memory was initially specified with the kmalloc call. - * The caller must guarantee that objp points to a valid object previously - * allocated with either kmalloc() or kmem_cache_alloc(). The object - * must not be freed during the duration of the call. + * __ksize -- Uninstrumented ksize. * - * Return: size of the actual memory used by @objp in bytes + * Unlike ksize(), __ksize() is uninstrumented, and does not provide the same + * safety checks as ksize() with KASAN instrumentation enabled. */ -size_t ksize(const void *objp) +size_t __ksize(const void *objp) { + struct kmem_cache *c; size_t size; BUG_ON(!objp); if (unlikely(objp == ZERO_SIZE_PTR)) return 0; - size = virt_to_cache(objp)->object_size; - /* We assume that ksize callers could use the whole allocated area, - * so we need to unpoison this area. - */ - kasan_unpoison_shadow(objp, size); + c = virt_to_cache(objp); + size = c ? c->object_size : 0; return size; } -EXPORT_SYMBOL(ksize); +EXPORT_SYMBOL(__ksize); diff --git a/mm/slab.h b/mm/slab.h index 43ac818b8592..9057b8056b07 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -172,6 +172,7 @@ int __kmem_cache_shutdown(struct kmem_cache *); void __kmem_cache_release(struct kmem_cache *); int __kmem_cache_shrink(struct kmem_cache *); void __kmemcg_cache_deactivate(struct kmem_cache *s); +void __kmemcg_cache_deactivate_after_rcu(struct kmem_cache *s); void slab_kmem_cache_release(struct kmem_cache *); struct seq_file; @@ -204,6 +205,12 @@ ssize_t slabinfo_write(struct file *file, const char __user *buffer, void __kmem_cache_free_bulk(struct kmem_cache *, size_t, void **); int __kmem_cache_alloc_bulk(struct kmem_cache *, gfp_t, size_t, void **); +static inline int cache_vmstat_idx(struct kmem_cache *s) +{ + return (s->flags & SLAB_RECLAIM_ACCOUNT) ? + NR_SLAB_RECLAIMABLE : NR_SLAB_UNRECLAIMABLE; +} + #ifdef CONFIG_MEMCG_KMEM /* List of all root caches. */ @@ -241,31 +248,6 @@ static inline const char *cache_name(struct kmem_cache *s) return s->name; } -/* - * Note, we protect with RCU only the memcg_caches array, not per-memcg caches. - * That said the caller must assure the memcg's cache won't go away by either - * taking a css reference to the owner cgroup, or holding the slab_mutex. - */ -static inline struct kmem_cache * -cache_from_memcg_idx(struct kmem_cache *s, int idx) -{ - struct kmem_cache *cachep; - struct memcg_cache_array *arr; - - rcu_read_lock(); - arr = rcu_dereference(s->memcg_params.memcg_caches); - - /* - * Make sure we will access the up-to-date value. The code updating - * memcg_caches issues a write barrier to match this (see - * memcg_create_kmem_cache()). - */ - cachep = READ_ONCE(arr->entries[idx]); - rcu_read_unlock(); - - return cachep; -} - static inline struct kmem_cache *memcg_root_cache(struct kmem_cache *s) { if (is_root_cache(s)) @@ -273,25 +255,94 @@ static inline struct kmem_cache *memcg_root_cache(struct kmem_cache *s) return s->memcg_params.root_cache; } +/* + * Expects a pointer to a slab page. Please note, that PageSlab() check + * isn't sufficient, as it returns true also for tail compound slab pages, + * which do not have slab_cache pointer set. + * So this function assumes that the page can pass PageHead() and PageSlab() + * checks. + * + * The kmem_cache can be reparented asynchronously. The caller must ensure + * the memcg lifetime, e.g. by taking rcu_read_lock() or cgroup_mutex. + */ +static inline struct mem_cgroup *memcg_from_slab_page(struct page *page) +{ + struct kmem_cache *s; + + s = READ_ONCE(page->slab_cache); + if (s && !is_root_cache(s)) + return READ_ONCE(s->memcg_params.memcg); + + return NULL; +} + +/* + * Charge the slab page belonging to the non-root kmem_cache. + * Can be called for non-root kmem_caches only. + */ static __always_inline int memcg_charge_slab(struct page *page, gfp_t gfp, int order, struct kmem_cache *s) { - if (is_root_cache(s)) + struct mem_cgroup *memcg; + struct lruvec *lruvec; + int ret; + + rcu_read_lock(); + memcg = READ_ONCE(s->memcg_params.memcg); + while (memcg && !css_tryget_online(&memcg->css)) + memcg = parent_mem_cgroup(memcg); + rcu_read_unlock(); + + if (unlikely(!memcg || mem_cgroup_is_root(memcg))) { + mod_node_page_state(page_pgdat(page), cache_vmstat_idx(s), + (1 << order)); + percpu_ref_get_many(&s->memcg_params.refcnt, 1 << order); return 0; - return memcg_kmem_charge_memcg(page, gfp, order, s->memcg_params.memcg); + } + + ret = memcg_kmem_charge_memcg(page, gfp, order, memcg); + if (ret) + goto out; + + lruvec = mem_cgroup_lruvec(page_pgdat(page), memcg); + mod_lruvec_state(lruvec, cache_vmstat_idx(s), 1 << order); + + /* transer try_charge() page references to kmem_cache */ + percpu_ref_get_many(&s->memcg_params.refcnt, 1 << order); + css_put_many(&memcg->css, 1 << order); +out: + css_put(&memcg->css); + return ret; } +/* + * Uncharge a slab page belonging to a non-root kmem_cache. + * Can be called for non-root kmem_caches only. + */ static __always_inline void memcg_uncharge_slab(struct page *page, int order, struct kmem_cache *s) { - memcg_kmem_uncharge(page, order); + struct mem_cgroup *memcg; + struct lruvec *lruvec; + + rcu_read_lock(); + memcg = READ_ONCE(s->memcg_params.memcg); + if (likely(!mem_cgroup_is_root(memcg))) { + lruvec = mem_cgroup_lruvec(page_pgdat(page), memcg); + mod_lruvec_state(lruvec, cache_vmstat_idx(s), -(1 << order)); + memcg_kmem_uncharge_memcg(page, order, memcg); + } else { + mod_node_page_state(page_pgdat(page), cache_vmstat_idx(s), + -(1 << order)); + } + rcu_read_unlock(); + + percpu_ref_put_many(&s->memcg_params.refcnt, 1 << order); } extern void slab_init_memcg_params(struct kmem_cache *); -extern void memcg_link_cache(struct kmem_cache *s); -extern void slab_deactivate_memcg_cache_rcu_sched(struct kmem_cache *s, - void (*deact_fn)(struct kmem_cache *)); +extern void memcg_link_cache(struct kmem_cache *s, struct mem_cgroup *memcg); #else /* CONFIG_MEMCG_KMEM */ @@ -310,7 +361,7 @@ static inline bool is_root_cache(struct kmem_cache *s) static inline bool slab_equal_or_root(struct kmem_cache *s, struct kmem_cache *p) { - return true; + return s == p; } static inline const char *cache_name(struct kmem_cache *s) @@ -318,15 +369,14 @@ static inline const char *cache_name(struct kmem_cache *s) return s->name; } -static inline struct kmem_cache * -cache_from_memcg_idx(struct kmem_cache *s, int idx) +static inline struct kmem_cache *memcg_root_cache(struct kmem_cache *s) { - return NULL; + return s; } -static inline struct kmem_cache *memcg_root_cache(struct kmem_cache *s) +static inline struct mem_cgroup *memcg_from_slab_page(struct page *page) { - return s; + return NULL; } static inline int memcg_charge_slab(struct page *page, gfp_t gfp, int order, @@ -344,16 +394,52 @@ static inline void slab_init_memcg_params(struct kmem_cache *s) { } -static inline void memcg_link_cache(struct kmem_cache *s) +static inline void memcg_link_cache(struct kmem_cache *s, + struct mem_cgroup *memcg) { } #endif /* CONFIG_MEMCG_KMEM */ +static inline struct kmem_cache *virt_to_cache(const void *obj) +{ + struct page *page; + + page = virt_to_head_page(obj); + if (WARN_ONCE(!PageSlab(page), "%s: Object is not a Slab page!\n", + __func__)) + return NULL; + return page->slab_cache; +} + +static __always_inline int charge_slab_page(struct page *page, + gfp_t gfp, int order, + struct kmem_cache *s) +{ + if (is_root_cache(s)) { + mod_node_page_state(page_pgdat(page), cache_vmstat_idx(s), + 1 << order); + return 0; + } + + return memcg_charge_slab(page, gfp, order, s); +} + +static __always_inline void uncharge_slab_page(struct page *page, int order, + struct kmem_cache *s) +{ + if (is_root_cache(s)) { + mod_node_page_state(page_pgdat(page), cache_vmstat_idx(s), + -(1 << order)); + return; + } + + memcg_uncharge_slab(page, order, s); +} + static inline struct kmem_cache *cache_from_obj(struct kmem_cache *s, void *x) { struct kmem_cache *cachep; - struct page *page; /* * When kmemcg is not being used, both assignments should return the @@ -363,18 +449,15 @@ static inline struct kmem_cache *cache_from_obj(struct kmem_cache *s, void *x) * will also be a constant. */ if (!memcg_kmem_enabled() && + !IS_ENABLED(CONFIG_SLAB_FREELIST_HARDENED) && !unlikely(s->flags & SLAB_CONSISTENCY_CHECKS)) return s; - page = virt_to_head_page(x); - cachep = page->slab_cache; - if (slab_equal_or_root(cachep, s)) - return cachep; - - pr_err("%s: Wrong slab cache. %s but object is from %s\n", - __func__, s->name, cachep->name); - WARN_ON_ONCE(1); - return s; + cachep = virt_to_cache(x); + WARN_ONCE(cachep && !slab_equal_or_root(cachep, s), + "%s: Wrong slab cache. %s but object is from %s\n", + __func__, s->name, cachep->name); + return cachep; } static inline size_t slab_ksize(const struct kmem_cache *s) @@ -524,4 +607,24 @@ static inline int cache_random_seq_create(struct kmem_cache *cachep, static inline void cache_random_seq_destroy(struct kmem_cache *cachep) { } #endif /* CONFIG_SLAB_FREELIST_RANDOM */ +static inline bool slab_want_init_on_alloc(gfp_t flags, struct kmem_cache *c) +{ + if (static_branch_unlikely(&init_on_alloc)) { + if (c->ctor) + return false; + if (c->flags & (SLAB_TYPESAFE_BY_RCU | SLAB_POISON)) + return flags & __GFP_ZERO; + return true; + } + return flags & __GFP_ZERO; +} + +static inline bool slab_want_init_on_free(struct kmem_cache *c) +{ + if (static_branch_unlikely(&init_on_free)) + return !(c->ctor || + (c->flags & (SLAB_TYPESAFE_BY_RCU | SLAB_POISON))); + return false; +} + #endif /* MM_SLAB_H */ diff --git a/mm/slab_common.c b/mm/slab_common.c index 58251ba63e4a..6c49dbb3769e 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -17,6 +17,7 @@ #include <linux/uaccess.h> #include <linux/seq_file.h> #include <linux/proc_fs.h> +#include <linux/debugfs.h> #include <asm/cacheflush.h> #include <asm/tlbflush.h> #include <asm/page.h> @@ -130,6 +131,9 @@ int __kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t nr, #ifdef CONFIG_MEMCG_KMEM LIST_HEAD(slab_root_caches); +static DEFINE_SPINLOCK(memcg_kmem_wq_lock); + +static void kmemcg_cache_shutdown(struct percpu_ref *percpu_ref); void slab_init_memcg_params(struct kmem_cache *s) { @@ -140,13 +144,18 @@ void slab_init_memcg_params(struct kmem_cache *s) } static int init_memcg_params(struct kmem_cache *s, - struct mem_cgroup *memcg, struct kmem_cache *root_cache) + struct kmem_cache *root_cache) { struct memcg_cache_array *arr; if (root_cache) { + int ret = percpu_ref_init(&s->memcg_params.refcnt, + kmemcg_cache_shutdown, + 0, GFP_KERNEL); + if (ret) + return ret; + s->memcg_params.root_cache = root_cache; - s->memcg_params.memcg = memcg; INIT_LIST_HEAD(&s->memcg_params.children_node); INIT_LIST_HEAD(&s->memcg_params.kmem_caches_node); return 0; @@ -171,6 +180,8 @@ static void destroy_memcg_params(struct kmem_cache *s) { if (is_root_cache(s)) kvfree(rcu_access_pointer(s->memcg_params.memcg_caches)); + else + percpu_ref_exit(&s->memcg_params.refcnt); } static void free_memcg_params(struct rcu_head *rcu) @@ -221,11 +232,13 @@ int memcg_update_all_caches(int num_memcgs) return ret; } -void memcg_link_cache(struct kmem_cache *s) +void memcg_link_cache(struct kmem_cache *s, struct mem_cgroup *memcg) { if (is_root_cache(s)) { list_add(&s->root_caches_node, &slab_root_caches); } else { + css_get(&memcg->css); + s->memcg_params.memcg = memcg; list_add(&s->memcg_params.children_node, &s->memcg_params.root_cache->memcg_params.children); list_add(&s->memcg_params.kmem_caches_node, @@ -240,11 +253,13 @@ static void memcg_unlink_cache(struct kmem_cache *s) } else { list_del(&s->memcg_params.children_node); list_del(&s->memcg_params.kmem_caches_node); + mem_cgroup_put(s->memcg_params.memcg); + WRITE_ONCE(s->memcg_params.memcg, NULL); } } #else static inline int init_memcg_params(struct kmem_cache *s, - struct mem_cgroup *memcg, struct kmem_cache *root_cache) + struct kmem_cache *root_cache) { return 0; } @@ -384,7 +399,7 @@ static struct kmem_cache *create_cache(const char *name, s->useroffset = useroffset; s->usersize = usersize; - err = init_memcg_params(s, memcg, root_cache); + err = init_memcg_params(s, root_cache); if (err) goto out_free_cache; @@ -394,7 +409,7 @@ static struct kmem_cache *create_cache(const char *name, s->refcount = 1; list_add(&s->list, &slab_caches); - memcg_link_cache(s); + memcg_link_cache(s, memcg); out: if (err) return ERR_PTR(err); @@ -640,7 +655,7 @@ void memcg_create_kmem_cache(struct mem_cgroup *memcg, * The memory cgroup could have been offlined while the cache * creation work was pending. */ - if (memcg->kmem_state != KMEM_ONLINE || root_cache->memcg_params.dying) + if (memcg->kmem_state != KMEM_ONLINE) goto out_unlock; idx = memcg_cache_id(memcg); @@ -677,7 +692,7 @@ void memcg_create_kmem_cache(struct mem_cgroup *memcg, } /* - * Since readers won't lock (see cache_from_memcg_idx()), we need a + * Since readers won't lock (see memcg_kmem_get_cache()), we need a * barrier here to ensure nobody will see the kmem_cache partially * initialized. */ @@ -691,74 +706,95 @@ out_unlock: put_online_cpus(); } -static void kmemcg_deactivate_workfn(struct work_struct *work) +static void kmemcg_workfn(struct work_struct *work) { struct kmem_cache *s = container_of(work, struct kmem_cache, - memcg_params.deact_work); + memcg_params.work); get_online_cpus(); get_online_mems(); mutex_lock(&slab_mutex); - - s->memcg_params.deact_fn(s); - + s->memcg_params.work_fn(s); mutex_unlock(&slab_mutex); put_online_mems(); put_online_cpus(); - - /* done, put the ref from slab_deactivate_memcg_cache_rcu_sched() */ - css_put(&s->memcg_params.memcg->css); } -static void kmemcg_deactivate_rcufn(struct rcu_head *head) +static void kmemcg_rcufn(struct rcu_head *head) { struct kmem_cache *s = container_of(head, struct kmem_cache, - memcg_params.deact_rcu_head); + memcg_params.rcu_head); /* - * We need to grab blocking locks. Bounce to ->deact_work. The + * We need to grab blocking locks. Bounce to ->work. The * work item shares the space with the RCU head and can't be * initialized eariler. */ - INIT_WORK(&s->memcg_params.deact_work, kmemcg_deactivate_workfn); - queue_work(memcg_kmem_cache_wq, &s->memcg_params.deact_work); + INIT_WORK(&s->memcg_params.work, kmemcg_workfn); + queue_work(memcg_kmem_cache_wq, &s->memcg_params.work); } -/** - * slab_deactivate_memcg_cache_rcu_sched - schedule deactivation after a - * sched RCU grace period - * @s: target kmem_cache - * @deact_fn: deactivation function to call - * - * Schedule @deact_fn to be invoked with online cpus, mems and slab_mutex - * held after a sched RCU grace period. The slab is guaranteed to stay - * alive until @deact_fn is finished. This is to be used from - * __kmemcg_cache_deactivate(). - */ -void slab_deactivate_memcg_cache_rcu_sched(struct kmem_cache *s, - void (*deact_fn)(struct kmem_cache *)) +static void kmemcg_cache_shutdown_fn(struct kmem_cache *s) { - if (WARN_ON_ONCE(is_root_cache(s)) || - WARN_ON_ONCE(s->memcg_params.deact_fn)) - return; + WARN_ON(shutdown_cache(s)); +} + +static void kmemcg_cache_shutdown(struct percpu_ref *percpu_ref) +{ + struct kmem_cache *s = container_of(percpu_ref, struct kmem_cache, + memcg_params.refcnt); + unsigned long flags; + spin_lock_irqsave(&memcg_kmem_wq_lock, flags); if (s->memcg_params.root_cache->memcg_params.dying) + goto unlock; + + s->memcg_params.work_fn = kmemcg_cache_shutdown_fn; + INIT_WORK(&s->memcg_params.work, kmemcg_workfn); + queue_work(memcg_kmem_cache_wq, &s->memcg_params.work); + +unlock: + spin_unlock_irqrestore(&memcg_kmem_wq_lock, flags); +} + +static void kmemcg_cache_deactivate_after_rcu(struct kmem_cache *s) +{ + __kmemcg_cache_deactivate_after_rcu(s); + percpu_ref_kill(&s->memcg_params.refcnt); +} + +static void kmemcg_cache_deactivate(struct kmem_cache *s) +{ + if (WARN_ON_ONCE(is_root_cache(s))) return; - /* pin memcg so that @s doesn't get destroyed in the middle */ - css_get(&s->memcg_params.memcg->css); + __kmemcg_cache_deactivate(s); + s->flags |= SLAB_DEACTIVATED; + + /* + * memcg_kmem_wq_lock is used to synchronize memcg_params.dying + * flag and make sure that no new kmem_cache deactivation tasks + * are queued (see flush_memcg_workqueue() ). + */ + spin_lock_irq(&memcg_kmem_wq_lock); + if (s->memcg_params.root_cache->memcg_params.dying) + goto unlock; - s->memcg_params.deact_fn = deact_fn; - call_rcu(&s->memcg_params.deact_rcu_head, kmemcg_deactivate_rcufn); + s->memcg_params.work_fn = kmemcg_cache_deactivate_after_rcu; + call_rcu(&s->memcg_params.rcu_head, kmemcg_rcufn); +unlock: + spin_unlock_irq(&memcg_kmem_wq_lock); } -void memcg_deactivate_kmem_caches(struct mem_cgroup *memcg) +void memcg_deactivate_kmem_caches(struct mem_cgroup *memcg, + struct mem_cgroup *parent) { int idx; struct memcg_cache_array *arr; struct kmem_cache *s, *c; + unsigned int nr_reparented; idx = memcg_cache_id(memcg); @@ -773,30 +809,20 @@ void memcg_deactivate_kmem_caches(struct mem_cgroup *memcg) if (!c) continue; - __kmemcg_cache_deactivate(c); + kmemcg_cache_deactivate(c); arr->entries[idx] = NULL; } - mutex_unlock(&slab_mutex); - - put_online_mems(); - put_online_cpus(); -} - -void memcg_destroy_kmem_caches(struct mem_cgroup *memcg) -{ - struct kmem_cache *s, *s2; - - get_online_cpus(); - get_online_mems(); - - mutex_lock(&slab_mutex); - list_for_each_entry_safe(s, s2, &memcg->kmem_caches, - memcg_params.kmem_caches_node) { - /* - * The cgroup is about to be freed and therefore has no charges - * left. Hence, all its caches must be empty by now. - */ - BUG_ON(shutdown_cache(s)); + nr_reparented = 0; + list_for_each_entry(s, &memcg->kmem_caches, + memcg_params.kmem_caches_node) { + WRITE_ONCE(s->memcg_params.memcg, parent); + css_put(&memcg->css); + nr_reparented++; + } + if (nr_reparented) { + list_splice_init(&memcg->kmem_caches, + &parent->kmem_caches); + css_get_many(&parent->css, nr_reparented); } mutex_unlock(&slab_mutex); @@ -861,16 +887,15 @@ static int shutdown_memcg_caches(struct kmem_cache *s) static void flush_memcg_workqueue(struct kmem_cache *s) { - mutex_lock(&slab_mutex); + spin_lock_irq(&memcg_kmem_wq_lock); s->memcg_params.dying = true; - mutex_unlock(&slab_mutex); + spin_unlock_irq(&memcg_kmem_wq_lock); /* - * SLUB deactivates the kmem_caches through call_rcu. Make + * SLAB and SLUB deactivate the kmem_caches through call_rcu. Make * sure all registered rcu callbacks have been invoked. */ - if (IS_ENABLED(CONFIG_SLUB)) - rcu_barrier(); + rcu_barrier(); /* * SLAB and SLUB create memcg kmem_caches through workqueue and SLUB @@ -997,7 +1022,7 @@ struct kmem_cache *__init create_kmalloc_cache(const char *name, create_boot_cache(s, name, size, flags, useroffset, usersize); list_add(&s->list, &slab_caches); - memcg_link_cache(s); + memcg_link_cache(s, NULL); s->refcount = 1; return s; } @@ -1498,6 +1523,64 @@ static int __init slab_proc_init(void) return 0; } module_init(slab_proc_init); + +#if defined(CONFIG_DEBUG_FS) && defined(CONFIG_MEMCG_KMEM) +/* + * Display information about kmem caches that have child memcg caches. + */ +static int memcg_slabinfo_show(struct seq_file *m, void *unused) +{ + struct kmem_cache *s, *c; + struct slabinfo sinfo; + + mutex_lock(&slab_mutex); + seq_puts(m, "# <name> <css_id[:dead|deact]> <active_objs> <num_objs>"); + seq_puts(m, " <active_slabs> <num_slabs>\n"); + list_for_each_entry(s, &slab_root_caches, root_caches_node) { + /* + * Skip kmem caches that don't have any memcg children. + */ + if (list_empty(&s->memcg_params.children)) + continue; + + memset(&sinfo, 0, sizeof(sinfo)); + get_slabinfo(s, &sinfo); + seq_printf(m, "%-17s root %6lu %6lu %6lu %6lu\n", + cache_name(s), sinfo.active_objs, sinfo.num_objs, + sinfo.active_slabs, sinfo.num_slabs); + + for_each_memcg_cache(c, s) { + struct cgroup_subsys_state *css; + char *status = ""; + + css = &c->memcg_params.memcg->css; + if (!(css->flags & CSS_ONLINE)) + status = ":dead"; + else if (c->flags & SLAB_DEACTIVATED) + status = ":deact"; + + memset(&sinfo, 0, sizeof(sinfo)); + get_slabinfo(c, &sinfo); + seq_printf(m, "%-17s %4d%-6s %6lu %6lu %6lu %6lu\n", + cache_name(c), css->id, status, + sinfo.active_objs, sinfo.num_objs, + sinfo.active_slabs, sinfo.num_slabs); + } + } + mutex_unlock(&slab_mutex); + return 0; +} +DEFINE_SHOW_ATTRIBUTE(memcg_slabinfo); + +static int __init memcg_slabinfo_init(void) +{ + debugfs_create_file("memcg_slabinfo", S_IFREG | S_IRUGO, + NULL, NULL, &memcg_slabinfo_fops); + return 0; +} + +late_initcall(memcg_slabinfo_init); +#endif /* CONFIG_DEBUG_FS && CONFIG_MEMCG_KMEM */ #endif /* CONFIG_SLAB || CONFIG_SLUB_DEBUG */ static __always_inline void *__do_krealloc(const void *p, size_t new_size, @@ -1597,6 +1680,52 @@ void kzfree(const void *p) } EXPORT_SYMBOL(kzfree); +/** + * ksize - get the actual amount of memory allocated for a given object + * @objp: Pointer to the object + * + * kmalloc may internally round up allocations and return more memory + * than requested. ksize() can be used to determine the actual amount of + * memory allocated. The caller may use this additional memory, even though + * a smaller amount of memory was initially specified with the kmalloc call. + * The caller must guarantee that objp points to a valid object previously + * allocated with either kmalloc() or kmem_cache_alloc(). The object + * must not be freed during the duration of the call. + * + * Return: size of the actual memory used by @objp in bytes + */ +size_t ksize(const void *objp) +{ + size_t size; + + if (WARN_ON_ONCE(!objp)) + return 0; + /* + * We need to check that the pointed to object is valid, and only then + * unpoison the shadow memory below. We use __kasan_check_read(), to + * generate a more useful report at the time ksize() is called (rather + * than later where behaviour is undefined due to potential + * use-after-free or double-free). + * + * If the pointed to memory is invalid we return 0, to avoid users of + * ksize() writing to and potentially corrupting the memory region. + * + * We want to perform the check before __ksize(), to avoid potentially + * crashing in __ksize() due to accessing invalid metadata. + */ + if (unlikely(objp == ZERO_SIZE_PTR) || !__kasan_check_read(objp, 1)) + return 0; + + size = __ksize(objp); + /* + * We assume that ksize callers could use whole allocated area, + * so we need to unpoison this area. + */ + kasan_unpoison_shadow(objp, size); + return size; +} +EXPORT_SYMBOL(ksize); + /* Tracepoints definitions. */ EXPORT_TRACEPOINT_SYMBOL(kmalloc); EXPORT_TRACEPOINT_SYMBOL(kmem_cache_alloc); diff --git a/mm/slob.c b/mm/slob.c index 84aefd9b91ee..7f421d0ca9ab 100644 --- a/mm/slob.c +++ b/mm/slob.c @@ -527,7 +527,7 @@ void kfree(const void *block) EXPORT_SYMBOL(kfree); /* can't use ksize for kmem_cache_alloc memory, only kmalloc */ -size_t ksize(const void *block) +size_t __ksize(const void *block) { struct page *sp; int align; @@ -545,7 +545,7 @@ size_t ksize(const void *block) m = (unsigned int *)(block - align); return SLOB_UNITS(*m) * SLOB_UNIT; } -EXPORT_SYMBOL(ksize); +EXPORT_SYMBOL(__ksize); int __kmem_cache_create(struct kmem_cache *c, slab_flags_t flags) { diff --git a/mm/slub.c b/mm/slub.c index cd04dbd2b5d0..e6c030e47364 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -1279,6 +1279,10 @@ check_slabs: if (*str == ',') slub_debug_slabs = str + 1; out: + if ((static_branch_unlikely(&init_on_alloc) || + static_branch_unlikely(&init_on_free)) && + (slub_debug & SLAB_POISON)) + pr_info("mem auto-init: SLAB_POISON will take precedence over init_on_alloc/init_on_free\n"); return 1; } @@ -1313,9 +1317,7 @@ slab_flags_t kmem_cache_flags(unsigned int object_size, char *end, *glob; size_t cmplen; - end = strchr(iter, ','); - if (!end) - end = iter + strlen(iter); + end = strchrnul(iter, ','); glob = strnchr(iter, end - iter, '*'); if (glob) @@ -1424,6 +1426,28 @@ static __always_inline bool slab_free_hook(struct kmem_cache *s, void *x) static inline bool slab_free_freelist_hook(struct kmem_cache *s, void **head, void **tail) { + + void *object; + void *next = *head; + void *old_tail = *tail ? *tail : *head; + int rsize; + + if (slab_want_init_on_free(s)) + do { + object = next; + next = get_freepointer(s, object); + /* + * Clear the object and the metadata, but don't touch + * the redzone. + */ + memset(object, 0, s->object_size); + rsize = (s->flags & SLAB_RED_ZONE) ? s->red_left_pad + : 0; + memset((char *)object + s->inuse, 0, + s->size - s->inuse - rsize); + set_freepointer(s, object, next); + } while (object != old_tail); + /* * Compiler cannot detect this function can be removed if slab_free_hook() * evaluates to nothing. Thus, catch all relevant config debug options here. @@ -1433,9 +1457,7 @@ static inline bool slab_free_freelist_hook(struct kmem_cache *s, defined(CONFIG_DEBUG_OBJECTS_FREE) || \ defined(CONFIG_KASAN) - void *object; - void *next = *head; - void *old_tail = *tail ? *tail : *head; + next = *head; /* Head and tail of the reconstructed freelist */ *head = NULL; @@ -1490,7 +1512,7 @@ static inline struct page *alloc_slab_page(struct kmem_cache *s, else page = __alloc_pages_node(node, flags, order); - if (page && memcg_charge_slab(page, flags, order, s)) { + if (page && charge_slab_page(page, flags, order, s)) { __free_pages(page, order); page = NULL; } @@ -1683,11 +1705,6 @@ out: if (!page) return NULL; - mod_lruvec_page_state(page, - (s->flags & SLAB_RECLAIM_ACCOUNT) ? - NR_SLAB_RECLAIMABLE : NR_SLAB_UNRECLAIMABLE, - 1 << oo_order(oo)); - inc_slabs_node(s, page_to_nid(page), page->objects); return page; @@ -1721,18 +1738,13 @@ static void __free_slab(struct kmem_cache *s, struct page *page) check_object(s, page, p, SLUB_RED_INACTIVE); } - mod_lruvec_page_state(page, - (s->flags & SLAB_RECLAIM_ACCOUNT) ? - NR_SLAB_RECLAIMABLE : NR_SLAB_UNRECLAIMABLE, - -pages); - __ClearPageSlabPfmemalloc(page); __ClearPageSlab(page); page->mapping = NULL; if (current->reclaim_state) current->reclaim_state->reclaimed_slab += pages; - memcg_uncharge_slab(page, order, s); + uncharge_slab_page(page, order, s); __free_pages(page, order); } @@ -2741,8 +2753,14 @@ redo: prefetch_freepointer(s, next_object); stat(s, ALLOC_FASTPATH); } + /* + * If the object has been wiped upon free, make sure it's fully + * initialized by zeroing out freelist pointer. + */ + if (unlikely(slab_want_init_on_free(s)) && object) + memset(object + s->offset, 0, sizeof(void *)); - if (unlikely(gfpflags & __GFP_ZERO) && object) + if (unlikely(slab_want_init_on_alloc(gfpflags, s)) && object) memset(object, 0, s->object_size); slab_post_alloc_hook(s, gfpflags, 1, &object); @@ -3163,7 +3181,7 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size, local_irq_enable(); /* Clear memory outside IRQ disabled fastpath loop */ - if (unlikely(flags & __GFP_ZERO)) { + if (unlikely(slab_want_init_on_alloc(flags, s))) { int j; for (j = 0; j < i; j++) @@ -3652,10 +3670,6 @@ static int kmem_cache_open(struct kmem_cache *s, slab_flags_t flags) free_kmem_cache_nodes(s); error: - if (flags & SLAB_PANIC) - panic("Cannot create slab %s size=%u realsize=%u order=%u offset=%u flags=%lx\n", - s->name, s->size, s->size, - oo_order(s->oo), s->offset, (unsigned long)flags); return -EINVAL; } @@ -3901,7 +3915,7 @@ void __check_heap_object(const void *ptr, unsigned long n, struct page *page, } #endif /* CONFIG_HARDENED_USERCOPY */ -static size_t __ksize(const void *object) +size_t __ksize(const void *object) { struct page *page; @@ -3917,17 +3931,7 @@ static size_t __ksize(const void *object) return slab_ksize(page->slab_cache); } - -size_t ksize(const void *object) -{ - size_t size = __ksize(object); - /* We assume that ksize callers could use whole allocated area, - * so we need to unpoison this area. - */ - kasan_unpoison_shadow(object, size); - return size; -} -EXPORT_SYMBOL(ksize); +EXPORT_SYMBOL(__ksize); void kfree(const void *x) { @@ -4024,7 +4028,7 @@ int __kmem_cache_shrink(struct kmem_cache *s) } #ifdef CONFIG_MEMCG -static void kmemcg_cache_deact_after_rcu(struct kmem_cache *s) +void __kmemcg_cache_deactivate_after_rcu(struct kmem_cache *s) { /* * Called with all the locks held after a sched RCU grace period. @@ -4050,12 +4054,6 @@ void __kmemcg_cache_deactivate(struct kmem_cache *s) */ slub_set_cpu_partial(s, 0); s->min_partial = 0; - - /* - * s->cpu_partial is checked locklessly (see put_cpu_partial), so - * we have to make sure the change is visible before shrinking. - */ - slab_deactivate_memcg_cache_rcu_sched(s, kmemcg_cache_deact_after_rcu); } #endif /* CONFIG_MEMCG */ @@ -4215,7 +4213,7 @@ static struct kmem_cache * __init bootstrap(struct kmem_cache *static_cache) } slab_init_memcg_params(s); list_add(&s->list, &slab_caches); - memcg_link_cache(s); + memcg_link_cache(s, NULL); return s; } diff --git a/mm/swap_state.c b/mm/swap_state.c index 85245fdec8d9..8368621a0fc7 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -73,23 +73,24 @@ unsigned long total_swapcache_pages(void) unsigned int i, j, nr; unsigned long ret = 0; struct address_space *spaces; + struct swap_info_struct *si; - rcu_read_lock(); for (i = 0; i < MAX_SWAPFILES; i++) { - /* - * The corresponding entries in nr_swapper_spaces and - * swapper_spaces will be reused only after at least - * one grace period. So it is impossible for them - * belongs to different usage. - */ - nr = nr_swapper_spaces[i]; - spaces = rcu_dereference(swapper_spaces[i]); - if (!nr || !spaces) + swp_entry_t entry = swp_entry(i, 1); + + /* Avoid get_swap_device() to warn for bad swap entry */ + if (!swp_swap_info(entry)) + continue; + /* Prevent swapoff to free swapper_spaces */ + si = get_swap_device(entry); + if (!si) continue; + nr = nr_swapper_spaces[i]; + spaces = swapper_spaces[i]; for (j = 0; j < nr; j++) ret += spaces[j].nrpages; + put_swap_device(si); } - rcu_read_unlock(); return ret; } @@ -310,8 +311,13 @@ struct page *lookup_swap_cache(swp_entry_t entry, struct vm_area_struct *vma, unsigned long addr) { struct page *page; + struct swap_info_struct *si; + si = get_swap_device(entry); + if (!si) + return NULL; page = find_get_page(swap_address_space(entry), swp_offset(entry)); + put_swap_device(si); INC_CACHE_INFO(find_total); if (page) { @@ -354,8 +360,8 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, struct vm_area_struct *vma, unsigned long addr, bool *new_page_allocated) { - struct page *found_page, *new_page = NULL; - struct address_space *swapper_space = swap_address_space(entry); + struct page *found_page = NULL, *new_page = NULL; + struct swap_info_struct *si; int err; *new_page_allocated = false; @@ -365,7 +371,12 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, * called after lookup_swap_cache() failed, re-calling * that would confuse statistics. */ - found_page = find_get_page(swapper_space, swp_offset(entry)); + si = get_swap_device(entry); + if (!si) + break; + found_page = find_get_page(swap_address_space(entry), + swp_offset(entry)); + put_swap_device(si); if (found_page) break; @@ -601,20 +612,16 @@ int init_swap_address_space(unsigned int type, unsigned long nr_pages) mapping_set_no_writeback_tags(space); } nr_swapper_spaces[type] = nr; - rcu_assign_pointer(swapper_spaces[type], spaces); + swapper_spaces[type] = spaces; return 0; } void exit_swap_address_space(unsigned int type) { - struct address_space *spaces; - - spaces = swapper_spaces[type]; + kvfree(swapper_spaces[type]); nr_swapper_spaces[type] = 0; - rcu_assign_pointer(swapper_spaces[type], NULL); - synchronize_rcu(); - kvfree(spaces); + swapper_spaces[type] = NULL; } static inline void swap_ra_clamp_pfn(struct vm_area_struct *vma, diff --git a/mm/swapfile.c b/mm/swapfile.c index 596ac98051c5..0789a762ce2f 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -152,6 +152,18 @@ static int __try_to_reclaim_swap(struct swap_info_struct *si, return ret; } +static inline struct swap_extent *first_se(struct swap_info_struct *sis) +{ + struct rb_node *rb = rb_first(&sis->swap_extent_root); + return rb_entry(rb, struct swap_extent, rb_node); +} + +static inline struct swap_extent *next_se(struct swap_extent *se) +{ + struct rb_node *rb = rb_next(&se->rb_node); + return rb ? rb_entry(rb, struct swap_extent, rb_node) : NULL; +} + /* * swapon tell device that all the old swap contents can be discarded, * to allow the swap device to optimize its wear-levelling. @@ -164,7 +176,7 @@ static int discard_swap(struct swap_info_struct *si) int err = 0; /* Do not discard the swap header page! */ - se = &si->first_swap_extent; + se = first_se(si); start_block = (se->start_block + 1) << (PAGE_SHIFT - 9); nr_blocks = ((sector_t)se->nr_pages - 1) << (PAGE_SHIFT - 9); if (nr_blocks) { @@ -175,7 +187,7 @@ static int discard_swap(struct swap_info_struct *si) cond_resched(); } - list_for_each_entry(se, &si->first_swap_extent.list, list) { + for (se = next_se(se); se; se = next_se(se)) { start_block = se->start_block << (PAGE_SHIFT - 9); nr_blocks = (sector_t)se->nr_pages << (PAGE_SHIFT - 9); @@ -189,6 +201,26 @@ static int discard_swap(struct swap_info_struct *si) return err; /* That will often be -EOPNOTSUPP */ } +static struct swap_extent * +offset_to_swap_extent(struct swap_info_struct *sis, unsigned long offset) +{ + struct swap_extent *se; + struct rb_node *rb; + + rb = sis->swap_extent_root.rb_node; + while (rb) { + se = rb_entry(rb, struct swap_extent, rb_node); + if (offset < se->start_page) + rb = rb->rb_left; + else if (offset >= se->start_page + se->nr_pages) + rb = rb->rb_right; + else + return se; + } + /* It *must* be present */ + BUG(); +} + /* * swap allocation tell device that a cluster of swap can now be discarded, * to allow the swap device to optimize its wear-levelling. @@ -196,32 +228,25 @@ static int discard_swap(struct swap_info_struct *si) static void discard_swap_cluster(struct swap_info_struct *si, pgoff_t start_page, pgoff_t nr_pages) { - struct swap_extent *se = si->curr_swap_extent; - int found_extent = 0; + struct swap_extent *se = offset_to_swap_extent(si, start_page); while (nr_pages) { - if (se->start_page <= start_page && - start_page < se->start_page + se->nr_pages) { - pgoff_t offset = start_page - se->start_page; - sector_t start_block = se->start_block + offset; - sector_t nr_blocks = se->nr_pages - offset; - - if (nr_blocks > nr_pages) - nr_blocks = nr_pages; - start_page += nr_blocks; - nr_pages -= nr_blocks; - - if (!found_extent++) - si->curr_swap_extent = se; - - start_block <<= PAGE_SHIFT - 9; - nr_blocks <<= PAGE_SHIFT - 9; - if (blkdev_issue_discard(si->bdev, start_block, - nr_blocks, GFP_NOIO, 0)) - break; - } + pgoff_t offset = start_page - se->start_page; + sector_t start_block = se->start_block + offset; + sector_t nr_blocks = se->nr_pages - offset; + + if (nr_blocks > nr_pages) + nr_blocks = nr_pages; + start_page += nr_blocks; + nr_pages -= nr_blocks; + + start_block <<= PAGE_SHIFT - 9; + nr_blocks <<= PAGE_SHIFT - 9; + if (blkdev_issue_discard(si->bdev, start_block, + nr_blocks, GFP_NOIO, 0)) + break; - se = list_next_entry(se, list); + se = next_se(se); } } @@ -1079,12 +1104,11 @@ fail: static struct swap_info_struct *__swap_info_get(swp_entry_t entry) { struct swap_info_struct *p; - unsigned long offset, type; + unsigned long offset; if (!entry.val) goto out; - type = swp_type(entry); - p = swap_type_to_swap_info(type); + p = swp_swap_info(entry); if (!p) goto bad_nofile; if (!(p->flags & SWP_USED)) @@ -1187,6 +1211,69 @@ static unsigned char __swap_entry_free_locked(struct swap_info_struct *p, return usage; } +/* + * Check whether swap entry is valid in the swap device. If so, + * return pointer to swap_info_struct, and keep the swap entry valid + * via preventing the swap device from being swapoff, until + * put_swap_device() is called. Otherwise return NULL. + * + * The entirety of the RCU read critical section must come before the + * return from or after the call to synchronize_rcu() in + * enable_swap_info() or swapoff(). So if "si->flags & SWP_VALID" is + * true, the si->map, si->cluster_info, etc. must be valid in the + * critical section. + * + * Notice that swapoff or swapoff+swapon can still happen before the + * rcu_read_lock() in get_swap_device() or after the rcu_read_unlock() + * in put_swap_device() if there isn't any other way to prevent + * swapoff, such as page lock, page table lock, etc. The caller must + * be prepared for that. For example, the following situation is + * possible. + * + * CPU1 CPU2 + * do_swap_page() + * ... swapoff+swapon + * __read_swap_cache_async() + * swapcache_prepare() + * __swap_duplicate() + * // check swap_map + * // verify PTE not changed + * + * In __swap_duplicate(), the swap_map need to be checked before + * changing partly because the specified swap entry may be for another + * swap device which has been swapoff. And in do_swap_page(), after + * the page is read from the swap device, the PTE is verified not + * changed with the page table locked to check whether the swap device + * has been swapoff or swapoff+swapon. + */ +struct swap_info_struct *get_swap_device(swp_entry_t entry) +{ + struct swap_info_struct *si; + unsigned long offset; + + if (!entry.val) + goto out; + si = swp_swap_info(entry); + if (!si) + goto bad_nofile; + + rcu_read_lock(); + if (!(si->flags & SWP_VALID)) + goto unlock_out; + offset = swp_offset(entry); + if (offset >= si->max) + goto unlock_out; + + return si; +bad_nofile: + pr_err("%s: %s%08lx\n", __func__, Bad_file, entry.val); +out: + return NULL; +unlock_out: + rcu_read_unlock(); + return NULL; +} + static unsigned char __swap_entry_free(struct swap_info_struct *p, swp_entry_t entry, unsigned char usage) { @@ -1358,11 +1445,18 @@ int page_swapcount(struct page *page) return count; } -int __swap_count(struct swap_info_struct *si, swp_entry_t entry) +int __swap_count(swp_entry_t entry) { + struct swap_info_struct *si; pgoff_t offset = swp_offset(entry); + int count = 0; - return swap_count(si->swap_map[offset]); + si = get_swap_device(entry); + if (si) { + count = swap_count(si->swap_map[offset]); + put_swap_device(si); + } + return count; } static int swap_swapcount(struct swap_info_struct *si, swp_entry_t entry) @@ -1387,9 +1481,11 @@ int __swp_swapcount(swp_entry_t entry) int count = 0; struct swap_info_struct *si; - si = __swap_info_get(entry); - if (si) + si = get_swap_device(entry); + if (si) { count = swap_swapcount(si, entry); + put_swap_device(si); + } return count; } @@ -1684,7 +1780,7 @@ int swap_type_of(dev_t device, sector_t offset, struct block_device **bdev_p) return type; } if (bdev == sis->bdev) { - struct swap_extent *se = &sis->first_swap_extent; + struct swap_extent *se = first_se(sis); if (se->start_block == offset) { if (bdev_p) @@ -2161,7 +2257,6 @@ static void drain_mmlist(void) static sector_t map_swap_entry(swp_entry_t entry, struct block_device **bdev) { struct swap_info_struct *sis; - struct swap_extent *start_se; struct swap_extent *se; pgoff_t offset; @@ -2169,18 +2264,8 @@ static sector_t map_swap_entry(swp_entry_t entry, struct block_device **bdev) *bdev = sis->bdev; offset = swp_offset(entry); - start_se = sis->curr_swap_extent; - se = start_se; - - for ( ; ; ) { - if (se->start_page <= offset && - offset < (se->start_page + se->nr_pages)) { - return se->start_block + (offset - se->start_page); - } - se = list_next_entry(se, list); - sis->curr_swap_extent = se; - BUG_ON(se == start_se); /* It *must* be present */ - } + se = offset_to_swap_extent(sis, offset); + return se->start_block + (offset - se->start_page); } /* @@ -2198,12 +2283,11 @@ sector_t map_swap_page(struct page *page, struct block_device **bdev) */ static void destroy_swap_extents(struct swap_info_struct *sis) { - while (!list_empty(&sis->first_swap_extent.list)) { - struct swap_extent *se; + while (!RB_EMPTY_ROOT(&sis->swap_extent_root)) { + struct rb_node *rb = sis->swap_extent_root.rb_node; + struct swap_extent *se = rb_entry(rb, struct swap_extent, rb_node); - se = list_first_entry(&sis->first_swap_extent.list, - struct swap_extent, list); - list_del(&se->list); + rb_erase(rb, &sis->swap_extent_root); kfree(se); } @@ -2219,7 +2303,7 @@ static void destroy_swap_extents(struct swap_info_struct *sis) /* * Add a block range (and the corresponding page range) into this swapdev's - * extent list. The extent list is kept sorted in page order. + * extent tree. * * This function rather assumes that it is called in ascending page order. */ @@ -2227,20 +2311,21 @@ int add_swap_extent(struct swap_info_struct *sis, unsigned long start_page, unsigned long nr_pages, sector_t start_block) { + struct rb_node **link = &sis->swap_extent_root.rb_node, *parent = NULL; struct swap_extent *se; struct swap_extent *new_se; - struct list_head *lh; - - if (start_page == 0) { - se = &sis->first_swap_extent; - sis->curr_swap_extent = se; - se->start_page = 0; - se->nr_pages = nr_pages; - se->start_block = start_block; - return 1; - } else { - lh = sis->first_swap_extent.list.prev; /* Highest extent */ - se = list_entry(lh, struct swap_extent, list); + + /* + * place the new node at the right most since the + * function is called in ascending page order. + */ + while (*link) { + parent = *link; + link = &parent->rb_right; + } + + if (parent) { + se = rb_entry(parent, struct swap_extent, rb_node); BUG_ON(se->start_page + se->nr_pages != start_page); if (se->start_block + se->nr_pages == start_block) { /* Merge it */ @@ -2249,9 +2334,7 @@ add_swap_extent(struct swap_info_struct *sis, unsigned long start_page, } } - /* - * No merge. Insert a new extent, preserving ordering. - */ + /* No merge, insert a new extent. */ new_se = kmalloc(sizeof(*se), GFP_KERNEL); if (new_se == NULL) return -ENOMEM; @@ -2259,7 +2342,8 @@ add_swap_extent(struct swap_info_struct *sis, unsigned long start_page, new_se->nr_pages = nr_pages; new_se->start_block = start_block; - list_add_tail(&new_se->list, &sis->first_swap_extent.list); + rb_link_node(&new_se->rb_node, parent, link); + rb_insert_color(&new_se->rb_node, &sis->swap_extent_root); return 1; } EXPORT_SYMBOL_GPL(add_swap_extent); @@ -2335,9 +2419,9 @@ static int swap_node(struct swap_info_struct *p) return bdev ? bdev->bd_disk->node_id : NUMA_NO_NODE; } -static void _enable_swap_info(struct swap_info_struct *p, int prio, - unsigned char *swap_map, - struct swap_cluster_info *cluster_info) +static void setup_swap_info(struct swap_info_struct *p, int prio, + unsigned char *swap_map, + struct swap_cluster_info *cluster_info) { int i; @@ -2362,7 +2446,11 @@ static void _enable_swap_info(struct swap_info_struct *p, int prio, } p->swap_map = swap_map; p->cluster_info = cluster_info; - p->flags |= SWP_WRITEOK; +} + +static void _enable_swap_info(struct swap_info_struct *p) +{ + p->flags |= SWP_WRITEOK | SWP_VALID; atomic_long_add(p->pages, &nr_swap_pages); total_swap_pages += p->pages; @@ -2389,7 +2477,17 @@ static void enable_swap_info(struct swap_info_struct *p, int prio, frontswap_init(p->type, frontswap_map); spin_lock(&swap_lock); spin_lock(&p->lock); - _enable_swap_info(p, prio, swap_map, cluster_info); + setup_swap_info(p, prio, swap_map, cluster_info); + spin_unlock(&p->lock); + spin_unlock(&swap_lock); + /* + * Guarantee swap_map, cluster_info, etc. fields are valid + * between get/put_swap_device() if SWP_VALID bit is set + */ + synchronize_rcu(); + spin_lock(&swap_lock); + spin_lock(&p->lock); + _enable_swap_info(p); spin_unlock(&p->lock); spin_unlock(&swap_lock); } @@ -2398,7 +2496,8 @@ static void reinsert_swap_info(struct swap_info_struct *p) { spin_lock(&swap_lock); spin_lock(&p->lock); - _enable_swap_info(p, p->prio, p->swap_map, p->cluster_info); + setup_swap_info(p, p->prio, p->swap_map, p->cluster_info); + _enable_swap_info(p); spin_unlock(&p->lock); spin_unlock(&swap_lock); } @@ -2501,6 +2600,17 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) reenable_swap_slots_cache_unlock(); + spin_lock(&swap_lock); + spin_lock(&p->lock); + p->flags &= ~SWP_VALID; /* mark swap device as invalid */ + spin_unlock(&p->lock); + spin_unlock(&swap_lock); + /* + * wait for swap operations protected by get/put_swap_device() + * to complete + */ + synchronize_rcu(); + flush_work(&p->discard_work); destroy_swap_extents(p); @@ -2749,7 +2859,7 @@ static struct swap_info_struct *alloc_swap_info(void) * would be relying on p->type to remain valid. */ } - INIT_LIST_HEAD(&p->first_swap_extent.list); + p->swap_extent_root = RB_ROOT; plist_node_init(&p->list, 0); for_each_node(i) plist_node_init(&p->avail_lists[i], 0); @@ -3265,17 +3375,11 @@ static int __swap_duplicate(swp_entry_t entry, unsigned char usage) unsigned char has_cache; int err = -EINVAL; - if (non_swap_entry(entry)) - goto out; - - p = swp_swap_info(entry); + p = get_swap_device(entry); if (!p) - goto bad_file; - - offset = swp_offset(entry); - if (unlikely(offset >= p->max)) goto out; + offset = swp_offset(entry); ci = lock_cluster_or_swap_info(p, offset); count = p->swap_map[offset]; @@ -3321,11 +3425,9 @@ static int __swap_duplicate(swp_entry_t entry, unsigned char usage) unlock_out: unlock_cluster_or_swap_info(p, ci); out: + if (p) + put_swap_device(p); return err; - -bad_file: - pr_err("swap_dup: %s%08lx\n", Bad_file, entry.val); - goto out; } /* @@ -3417,6 +3519,7 @@ int add_swap_count_continuation(swp_entry_t entry, gfp_t gfp_mask) struct page *list_page; pgoff_t offset; unsigned char count; + int ret = 0; /* * When debugging, it's easier to use __GFP_ZERO here; but it's better @@ -3424,15 +3527,15 @@ int add_swap_count_continuation(swp_entry_t entry, gfp_t gfp_mask) */ page = alloc_page(gfp_mask | __GFP_HIGHMEM); - si = swap_info_get(entry); + si = get_swap_device(entry); if (!si) { /* * An acceptable race has occurred since the failing - * __swap_duplicate(): the swap entry has been freed, - * perhaps even the whole swap_map cleared for swapoff. + * __swap_duplicate(): the swap device may be swapoff */ goto outer; } + spin_lock(&si->lock); offset = swp_offset(entry); @@ -3450,9 +3553,8 @@ int add_swap_count_continuation(swp_entry_t entry, gfp_t gfp_mask) } if (!page) { - unlock_cluster(ci); - spin_unlock(&si->lock); - return -ENOMEM; + ret = -ENOMEM; + goto out; } /* @@ -3504,10 +3606,11 @@ out_unlock_cont: out: unlock_cluster(ci); spin_unlock(&si->lock); + put_swap_device(si); outer: if (page) __free_page(page); - return 0; + return ret; } /* diff --git a/mm/util.c b/mm/util.c index 9834c4ab7d8e..68575a315dc5 100644 --- a/mm/util.c +++ b/mm/util.c @@ -300,53 +300,6 @@ void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack) } #endif -/* - * Like get_user_pages_fast() except its IRQ-safe in that it won't fall - * back to the regular GUP. - * Note a difference with get_user_pages_fast: this always returns the - * number of pages pinned, 0 if no pages were pinned. - * If the architecture does not support this function, simply return with no - * pages pinned. - */ -int __weak __get_user_pages_fast(unsigned long start, - int nr_pages, int write, struct page **pages) -{ - return 0; -} -EXPORT_SYMBOL_GPL(__get_user_pages_fast); - -/** - * get_user_pages_fast() - pin user pages in memory - * @start: starting user address - * @nr_pages: number of pages from start to pin - * @gup_flags: flags modifying pin behaviour - * @pages: array that receives pointers to the pages pinned. - * Should be at least nr_pages long. - * - * get_user_pages_fast provides equivalent functionality to get_user_pages, - * operating on current and current->mm, with force=0 and vma=NULL. However - * unlike get_user_pages, it must be called without mmap_sem held. - * - * get_user_pages_fast may take mmap_sem and page table locks, so no - * assumptions can be made about lack of locking. get_user_pages_fast is to be - * implemented in a way that is advantageous (vs get_user_pages()) when the - * user memory area is already faulted in and present in ptes. However if the - * pages have to be faulted in, it may turn out to be slightly slower so - * callers need to carefully consider what to use. On many architectures, - * get_user_pages_fast simply falls back to get_user_pages. - * - * Return: number of pages pinned. This may be fewer than the number - * requested. If nr_pages is 0 or negative, returns 0. If no pages - * were pinned, returns -errno. - */ -int __weak get_user_pages_fast(unsigned long start, - int nr_pages, unsigned int gup_flags, - struct page **pages) -{ - return get_user_pages_unlocked(start, nr_pages, pages, gup_flags); -} -EXPORT_SYMBOL_GPL(get_user_pages_fast); - unsigned long vm_mmap_pgoff(struct file *file, unsigned long addr, unsigned long len, unsigned long prot, unsigned long flag, unsigned long pgoff) diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 030a544e6602..4fa8d84599b0 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -365,6 +365,13 @@ static LIST_HEAD(free_vmap_area_list); */ static struct rb_root free_vmap_area_root = RB_ROOT; +/* + * Preload a CPU with one object for "no edge" split case. The + * aim is to get rid of allocations from the atomic context, thus + * to use more permissive allocation masks. + */ +static DEFINE_PER_CPU(struct vmap_area *, ne_fit_preload_node); + static __always_inline unsigned long va_size(struct vmap_area *va) { @@ -399,6 +406,13 @@ static void purge_vmap_area_lazy(void); static BLOCKING_NOTIFIER_HEAD(vmap_notify_list); static unsigned long lazy_max_pages(void); +static atomic_long_t nr_vmalloc_pages; + +unsigned long vmalloc_nr_pages(void) +{ + return atomic_long_read(&nr_vmalloc_pages); +} + static struct vmap_area *__find_vmap_area(unsigned long addr) { struct rb_node *n = vmap_area_root.rb_node; @@ -527,20 +541,17 @@ link_va(struct vmap_area *va, struct rb_root *root, static __always_inline void unlink_va(struct vmap_area *va, struct rb_root *root) { - /* - * During merging a VA node can be empty, therefore - * not linked with the tree nor list. Just check it. - */ - if (!RB_EMPTY_NODE(&va->rb_node)) { - if (root == &free_vmap_area_root) - rb_erase_augmented(&va->rb_node, - root, &free_vmap_area_rb_augment_cb); - else - rb_erase(&va->rb_node, root); + if (WARN_ON(RB_EMPTY_NODE(&va->rb_node))) + return; - list_del(&va->list); - RB_CLEAR_NODE(&va->rb_node); - } + if (root == &free_vmap_area_root) + rb_erase_augmented(&va->rb_node, + root, &free_vmap_area_rb_augment_cb); + else + rb_erase(&va->rb_node, root); + + list_del(&va->list); + RB_CLEAR_NODE(&va->rb_node); } #if DEBUG_AUGMENT_PROPAGATE_CHECK @@ -712,9 +723,6 @@ merge_or_add_vmap_area(struct vmap_area *va, /* Check and update the tree if needed. */ augment_tree_propagate_from(sibling); - /* Remove this VA, it has been merged. */ - unlink_va(va, root); - /* Free vmap_area object. */ kmem_cache_free(vmap_area_cachep, va); @@ -739,12 +747,11 @@ merge_or_add_vmap_area(struct vmap_area *va, /* Check and update the tree if needed. */ augment_tree_propagate_from(sibling); - /* Remove this VA, it has been merged. */ - unlink_va(va, root); + if (merged) + unlink_va(va, root); /* Free vmap_area object. */ kmem_cache_free(vmap_area_cachep, va); - return; } } @@ -951,9 +958,24 @@ adjust_va_to_fit_type(struct vmap_area *va, * L V NVA V R * |---|-------|---| */ - lva = kmem_cache_alloc(vmap_area_cachep, GFP_NOWAIT); - if (unlikely(!lva)) - return -1; + lva = __this_cpu_xchg(ne_fit_preload_node, NULL); + if (unlikely(!lva)) { + /* + * For percpu allocator we do not do any pre-allocation + * and leave it as it is. The reason is it most likely + * never ends up with NE_FIT_TYPE splitting. In case of + * percpu allocations offsets and sizes are aligned to + * fixed align request, i.e. RE_FIT_TYPE and FL_FIT_TYPE + * are its main fitting cases. + * + * There are a few exceptions though, as an example it is + * a first allocation (early boot up) when we have "one" + * big free space that has to be split. + */ + lva = kmem_cache_alloc(vmap_area_cachep, GFP_NOWAIT); + if (!lva) + return -1; + } /* * Build the remainder. @@ -986,7 +1008,7 @@ adjust_va_to_fit_type(struct vmap_area *va, */ static __always_inline unsigned long __alloc_vmap_area(unsigned long size, unsigned long align, - unsigned long vstart, unsigned long vend, int node) + unsigned long vstart, unsigned long vend) { unsigned long nva_start_addr; struct vmap_area *va; @@ -1032,7 +1054,7 @@ static struct vmap_area *alloc_vmap_area(unsigned long size, unsigned long vstart, unsigned long vend, int node, gfp_t gfp_mask) { - struct vmap_area *va; + struct vmap_area *va, *pva; unsigned long addr; int purged = 0; @@ -1057,13 +1079,38 @@ static struct vmap_area *alloc_vmap_area(unsigned long size, kmemleak_scan_area(&va->rb_node, SIZE_MAX, gfp_mask & GFP_RECLAIM_MASK); retry: + /* + * Preload this CPU with one extra vmap_area object to ensure + * that we have it available when fit type of free area is + * NE_FIT_TYPE. + * + * The preload is done in non-atomic context, thus it allows us + * to use more permissive allocation masks to be more stable under + * low memory condition and high memory pressure. + * + * Even if it fails we do not really care about that. Just proceed + * as it is. "overflow" path will refill the cache we allocate from. + */ + preempt_disable(); + if (!__this_cpu_read(ne_fit_preload_node)) { + preempt_enable(); + pva = kmem_cache_alloc_node(vmap_area_cachep, GFP_KERNEL, node); + preempt_disable(); + + if (__this_cpu_cmpxchg(ne_fit_preload_node, NULL, pva)) { + if (pva) + kmem_cache_free(vmap_area_cachep, pva); + } + } + spin_lock(&vmap_area_lock); + preempt_enable(); /* * If an allocation fails, the "vend" address is * returned. Therefore trigger the overflow path. */ - addr = __alloc_vmap_area(size, align, vstart, vend, node); + addr = __alloc_vmap_area(size, align, vstart, vend); if (unlikely(addr == vend)) goto overflow; @@ -1119,8 +1166,6 @@ EXPORT_SYMBOL_GPL(unregister_vmap_purge_notifier); static void __free_vmap_area(struct vmap_area *va) { - BUG_ON(RB_EMPTY_NODE(&va->rb_node)); - /* * Remove from the busy tree/list. */ @@ -2199,6 +2244,7 @@ static void __vunmap(const void *addr, int deallocate_pages) BUG_ON(!page); __free_pages(page, 0); } + atomic_long_sub(area->nr_pages, &nr_vmalloc_pages); kvfree(area->pages); } @@ -2376,12 +2422,14 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, if (unlikely(!page)) { /* Successfully allocated i pages, free them in __vunmap() */ area->nr_pages = i; + atomic_long_add(area->nr_pages, &nr_vmalloc_pages); goto fail; } area->pages[i] = page; if (gfpflags_allow_blocking(gfp_mask|highmem_mask)) cond_resched(); } + atomic_long_add(area->nr_pages, &nr_vmalloc_pages); if (map_vm_area(area, prot, pages)) goto fail; @@ -2774,7 +2822,7 @@ static int aligned_vwrite(char *buf, char *addr, unsigned long count) * Note: In usual ops, vread() is never necessary because the caller * should know vmalloc() area is valid and can use memcpy(). * This is for routines which have to access vmalloc area without - * any informaion, as /dev/kmem. + * any information, as /dev/kmem. * * Return: number of bytes for which addr and buf should be increased * (same number as @count) or %0 if [addr...addr+count) doesn't @@ -2853,7 +2901,7 @@ finished: * Note: In usual ops, vwrite() is never necessary because the caller * should know vmalloc() area is valid and can use memcpy(). * This is for routines which have to access vmalloc area without - * any informaion, as /dev/kmem. + * any information, as /dev/kmem. * * Return: number of bytes for which addr and buf should be * increased (same number as @count) or %0 if [addr...addr+count) @@ -2996,7 +3044,7 @@ void __weak vmalloc_sync_all(void) } -static int f(pte_t *pte, pgtable_t table, unsigned long addr, void *data) +static int f(pte_t *pte, unsigned long addr, void *data) { pte_t ***p = data; diff --git a/mm/vmscan.c b/mm/vmscan.c index 910e02c793ff..f8e3dcd527b8 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1118,6 +1118,7 @@ static unsigned long shrink_page_list(struct list_head *page_list, int may_enter_fs; enum page_references references = PAGEREF_RECLAIM_CLEAN; bool dirty, writeback; + unsigned int nr_pages; cond_resched(); @@ -1129,7 +1130,10 @@ static unsigned long shrink_page_list(struct list_head *page_list, VM_BUG_ON_PAGE(PageActive(page), page); - sc->nr_scanned++; + nr_pages = 1 << compound_order(page); + + /* Account the number of base pages even though THP */ + sc->nr_scanned += nr_pages; if (unlikely(!page_evictable(page))) goto activate_locked; @@ -1137,11 +1141,6 @@ static unsigned long shrink_page_list(struct list_head *page_list, if (!sc->may_unmap && page_mapped(page)) goto keep_locked; - /* Double the slab pressure for mapped and swapcache pages */ - if ((page_mapped(page) || PageSwapCache(page)) && - !(PageAnon(page) && !PageSwapBacked(page))) - sc->nr_scanned++; - may_enter_fs = (sc->gfp_mask & __GFP_FS) || (PageSwapCache(page) && (sc->gfp_mask & __GFP_IO)); @@ -1255,7 +1254,7 @@ static unsigned long shrink_page_list(struct list_head *page_list, case PAGEREF_ACTIVATE: goto activate_locked; case PAGEREF_KEEP: - stat->nr_ref_keep++; + stat->nr_ref_keep += nr_pages; goto keep_locked; case PAGEREF_RECLAIM: case PAGEREF_RECLAIM_CLEAN: @@ -1287,7 +1286,7 @@ static unsigned long shrink_page_list(struct list_head *page_list, } if (!add_to_swap(page)) { if (!PageTransHuge(page)) - goto activate_locked; + goto activate_locked_split; /* Fallback to swap normal pages */ if (split_huge_page_to_list(page, page_list)) @@ -1296,7 +1295,7 @@ static unsigned long shrink_page_list(struct list_head *page_list, count_vm_event(THP_SWPOUT_FALLBACK); #endif if (!add_to_swap(page)) - goto activate_locked; + goto activate_locked_split; } may_enter_fs = 1; @@ -1311,6 +1310,18 @@ static unsigned long shrink_page_list(struct list_head *page_list, } /* + * THP may get split above, need minus tail pages and update + * nr_pages to avoid accounting tail pages twice. + * + * The tail pages that are added into swap cache successfully + * reach here. + */ + if ((nr_pages > 1) && !PageTransHuge(page)) { + sc->nr_scanned -= (nr_pages - 1); + nr_pages = 1; + } + + /* * The page is mapped into the page tables of one or more * processes. Try to unmap it here. */ @@ -1320,7 +1331,7 @@ static unsigned long shrink_page_list(struct list_head *page_list, if (unlikely(PageTransHuge(page))) flags |= TTU_SPLIT_HUGE_PMD; if (!try_to_unmap(page, flags)) { - stat->nr_unmap_fail++; + stat->nr_unmap_fail += nr_pages; goto activate_locked; } } @@ -1447,7 +1458,11 @@ static unsigned long shrink_page_list(struct list_head *page_list, unlock_page(page); free_it: - nr_reclaimed++; + /* + * THP may get swapped out in a whole, need account + * all base pages. + */ + nr_reclaimed += nr_pages; /* * Is there need to periodically free_page_list? It would @@ -1460,6 +1475,15 @@ free_it: list_add(&page->lru, &free_pages); continue; +activate_locked_split: + /* + * The tail pages that are failed to add into swap cache + * reach here. Fixup nr_scanned and nr_pages. + */ + if (nr_pages > 1) { + sc->nr_scanned -= (nr_pages - 1); + nr_pages = 1; + } activate_locked: /* Not a candidate for swapping, so reclaim swap space. */ if (PageSwapCache(page) && (mem_cgroup_swap_full(page) || @@ -1469,8 +1493,7 @@ activate_locked: if (!PageMlocked(page)) { int type = page_is_file_cache(page); SetPageActive(page); - pgactivate++; - stat->nr_activate[type] += hpage_nr_pages(page); + stat->nr_activate[type] += nr_pages; count_memcg_page_event(page, PGACTIVATE); } keep_locked: @@ -1480,6 +1503,8 @@ keep: VM_BUG_ON_PAGE(PageLRU(page) || PageUnevictable(page), page); } + pgactivate = stat->nr_activate[0] + stat->nr_activate[1]; + mem_cgroup_uncharge_list(&free_pages); try_to_unmap_flush(); free_unref_page_list(&free_pages); @@ -1651,10 +1676,9 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan, LIST_HEAD(pages_skipped); isolate_mode_t mode = (sc->may_unmap ? 0 : ISOLATE_UNMAPPED); + total_scan = 0; scan = 0; - for (total_scan = 0; - scan < nr_to_scan && nr_taken < nr_to_scan && !list_empty(src); - total_scan++) { + while (scan < nr_to_scan && !list_empty(src)) { struct page *page; page = lru_to_page(src); @@ -1662,9 +1686,12 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan, VM_BUG_ON_PAGE(!PageLRU(page), page); + nr_pages = 1 << compound_order(page); + total_scan += nr_pages; + if (page_zonenum(page) > sc->reclaim_idx) { list_move(&page->lru, &pages_skipped); - nr_skipped[page_zonenum(page)]++; + nr_skipped[page_zonenum(page)] += nr_pages; continue; } @@ -1673,11 +1700,14 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan, * return with no isolated pages if the LRU mostly contains * ineligible pages. This causes the VM to not reclaim any * pages, triggering a premature OOM. + * + * Account all tail pages of THP. This would not cause + * premature OOM since __isolate_lru_page() returns -EBUSY + * only when the page is being freed somewhere else. */ - scan++; + scan += nr_pages; switch (__isolate_lru_page(page, mode)) { case 0: - nr_pages = hpage_nr_pages(page); nr_taken += nr_pages; nr_zone_taken[page_zonenum(page)] += nr_pages; list_move(&page->lru, dst); @@ -2125,7 +2155,7 @@ static void shrink_active_list(unsigned long nr_to_scan, * 10TB 320 32GB */ static bool inactive_list_is_low(struct lruvec *lruvec, bool file, - struct scan_control *sc, bool actual_reclaim) + struct scan_control *sc, bool trace) { enum lru_list active_lru = file * LRU_FILE + LRU_ACTIVE; struct pglist_data *pgdat = lruvec_pgdat(lruvec); @@ -2151,7 +2181,7 @@ static bool inactive_list_is_low(struct lruvec *lruvec, bool file, * rid of the stale workingset quickly. */ refaults = lruvec_page_state_local(lruvec, WORKINGSET_ACTIVATE); - if (file && actual_reclaim && lruvec->refaults != refaults) { + if (file && lruvec->refaults != refaults) { inactive_ratio = 0; } else { gb = (inactive + active) >> (30 - PAGE_SHIFT); @@ -2161,7 +2191,7 @@ static bool inactive_list_is_low(struct lruvec *lruvec, bool file, inactive_ratio = 1; } - if (actual_reclaim) + if (trace) trace_mm_vmscan_inactive_list_is_low(pgdat->node_id, sc->reclaim_idx, lruvec_lru_size(lruvec, inactive_lru, MAX_NR_ZONES), inactive, lruvec_lru_size(lruvec, active_lru, MAX_NR_ZONES), active, diff --git a/mm/z3fold.c b/mm/z3fold.c index 985732c8b025..dfcd69d08c1e 100644 --- a/mm/z3fold.c +++ b/mm/z3fold.c @@ -924,7 +924,16 @@ retry: set_bit(PAGE_HEADLESS, &page->private); goto headless; } - __SetPageMovable(page, pool->inode->i_mapping); + if (can_sleep) { + lock_page(page); + __SetPageMovable(page, pool->inode->i_mapping); + unlock_page(page); + } else { + if (trylock_page(page)) { + __SetPageMovable(page, pool->inode->i_mapping); + unlock_page(page); + } + } z3fold_page_lock(zhdr); found: @@ -1331,6 +1340,7 @@ static int z3fold_page_migrate(struct address_space *mapping, struct page *newpa VM_BUG_ON_PAGE(!PageMovable(page), page); VM_BUG_ON_PAGE(!PageIsolated(page), page); + VM_BUG_ON_PAGE(!PageLocked(newpage), newpage); zhdr = page_address(page); pool = zhdr_to_pool(zhdr); diff --git a/net/core/sock.c b/net/core/sock.c index 3e073ca6138f..d57b0cc995a0 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1597,7 +1597,7 @@ static struct sock *sk_prot_alloc(struct proto *prot, gfp_t priority, sk = kmem_cache_alloc(slab, priority & ~__GFP_ZERO); if (!sk) return sk; - if (priority & __GFP_ZERO) + if (want_init_on_alloc(priority)) sk_prot_clear_nulls(sk, prot->obj_size); } else sk = kmalloc(prot->obj_size, priority); diff --git a/scripts/decode_stacktrace.sh b/scripts/decode_stacktrace.sh index a7a36209a193..13e5fbafdf2f 100755 --- a/scripts/decode_stacktrace.sh +++ b/scripts/decode_stacktrace.sh @@ -28,7 +28,7 @@ parse_symbol() { local objfile=${modcache[$module]} else [[ $modpath == "" ]] && return - local objfile=$(find "$modpath" -name $module.ko -print -quit) + local objfile=$(find "$modpath" -name "${module//_/[-_]}.ko*" -print -quit) [[ $objfile == "" ]] && return modcache[$module]=$objfile fi @@ -85,7 +85,7 @@ parse_symbol() { fi # Strip out the base of the path - code=${code//^$basepath/""} + code=${code#$basepath/} # In the case of inlines, move everything to same line code=${code//$'\n'/' '} diff --git a/scripts/spelling.txt b/scripts/spelling.txt index 86b87332b9e5..de75b9feaaed 100644 --- a/scripts/spelling.txt +++ b/scripts/spelling.txt @@ -41,6 +41,7 @@ accquired||acquired accross||across acessable||accessible acess||access +acessing||accessing achitecture||architecture acient||ancient acitions||actions @@ -54,6 +55,7 @@ activete||activate actived||activated actualy||actually acumulating||accumulating +acumulative||accumulative acumulator||accumulator adapater||adapter addional||additional @@ -103,6 +105,7 @@ alogrithm||algorithm alot||a lot alow||allow alows||allows +alredy||already altough||although alue||value ambigious||ambiguous @@ -223,6 +226,7 @@ boardcast||broadcast borad||board boundry||boundary brievely||briefly +brigde||bridge broadcase||broadcast broadcat||broadcast bufufer||buffer @@ -239,6 +243,7 @@ calulate||calculate cancelation||cancellation cancle||cancel capabilites||capabilities +capabilties||capabilities capabilty||capability capabitilies||capabilities capablity||capability @@ -325,6 +330,7 @@ conector||connector connecetd||connected configuartion||configuration configuation||configuration +configued||configured configuratoin||configuration configuraton||configuration configuretion||configuration @@ -407,6 +413,7 @@ depreacte||deprecate desactivate||deactivate desciptor||descriptor desciptors||descriptors +descripto||descriptor descripton||description descrition||description descritptor||descriptor @@ -432,6 +439,7 @@ deveolpment||development devided||divided deviece||device diable||disable +dicline||decline dictionnary||dictionary didnt||didn't diferent||different @@ -461,6 +469,7 @@ disharge||discharge disnabled||disabled dispertion||dispersion dissapears||disappears +dissconect||disconnect distiction||distinction divisable||divisible divsiors||divisors @@ -469,11 +478,14 @@ documantation||documentation documentaion||documentation documment||document doesnt||doesn't +donwload||download +donwloading||downloading dorp||drop dosen||doesn downlad||download downlads||downloads droped||dropped +droput||dropout druing||during dynmaic||dynamic eanable||enable @@ -482,6 +494,7 @@ ecspecially||especially edditable||editable editting||editing efective||effective +effectivness||effectiveness efficently||efficiently ehther||ether eigth||eight @@ -543,6 +556,7 @@ extensability||extensibility extention||extension extenstion||extension extracter||extractor +faied||failed faield||failed falied||failed faild||failed @@ -567,6 +581,7 @@ fetaures||features fileystem||filesystem fimware||firmware firmare||firmware +firmaware||firmware firware||firmware finanize||finalize findn||find @@ -601,6 +616,8 @@ funtions||functions furthur||further futhermore||furthermore futrue||future +gatable||gateable +gateing||gating gauage||gauge gaurenteed||guaranteed generiously||generously @@ -641,9 +658,11 @@ iomaped||iomapped imblance||imbalance immeadiately||immediately immedaite||immediate +immedate||immediate immediatelly||immediately immediatly||immediately immidiate||immediate +immutible||immutable impelentation||implementation impementated||implemented implemantation||implementation @@ -661,10 +680,12 @@ incative||inactive incomming||incoming incompatabilities||incompatibilities incompatable||incompatible +incompatble||incompatible inconsistant||inconsistent increas||increase incremeted||incremented incrment||increment +inculde||include indendation||indentation indended||intended independant||independent @@ -778,6 +799,7 @@ libary||library librairies||libraries libraris||libraries licenceing||licencing +logaritmic||logarithmic loggging||logging loggin||login logile||logfile @@ -832,6 +854,7 @@ mispelled||misspelled mispelt||misspelt mising||missing mismactch||mismatch +missign||missing missmanaged||mismanaged missmatch||mismatch miximum||maximum @@ -848,6 +871,7 @@ mopdule||module mroe||more mulitplied||multiplied multidimensionnal||multidimensional +multipe||multiple multple||multiple mumber||number muticast||multicast @@ -870,7 +894,9 @@ nescessary||necessary nessessary||necessary noticable||noticeable notications||notifications +notifcations||notifications notifed||notified +notity||notify numebr||number numner||number obtaion||obtain @@ -887,6 +913,7 @@ occuring||occurring offser||offset offet||offset offloded||offloaded +offseting||offsetting omited||omitted omiting||omitting omitt||omit @@ -1009,6 +1036,8 @@ programers||programmers programm||program programms||programs progresss||progress +prohibitted||prohibited +prohibitting||prohibiting promiscous||promiscuous promps||prompts pronnounced||pronounced @@ -1023,6 +1052,7 @@ prosess||process protable||portable protcol||protocol protecion||protection +protedcted||protected protocoll||protocol promixity||proximity psudo||pseudo @@ -1037,6 +1067,7 @@ reasearcher||researcher reasearchers||researchers reasearch||research recepient||recipient +recevied||received receving||receiving recieved||received recieve||receive @@ -1110,6 +1141,7 @@ retreived||retrieved retreive||retrieve retreiving||retrieving retrive||retrieve +retrived||retrieved retuned||returned reudce||reduce reuest||request @@ -1145,7 +1177,6 @@ senarios||scenarios sentivite||sensitive separatly||separately sepcify||specify -sepc||spec seperated||separated seperately||separately seperate||separate @@ -1177,6 +1208,7 @@ singaled||signaled singal||signal singed||signed sleeped||slept +sliped||slipped softwares||software speach||speech specfic||specific @@ -1283,6 +1315,7 @@ threds||threads threshhold||threshold thresold||threshold throught||through +trackling||tracking troughput||throughput thses||these tiggers||triggers @@ -1409,5 +1442,6 @@ wnat||want workarould||workaround writeing||writing writting||writing +wtih||with zombe||zombie zomebie||zombie diff --git a/security/Kconfig.hardening b/security/Kconfig.hardening index c6cb2d9b2905..a1ffe2eb4d5f 100644 --- a/security/Kconfig.hardening +++ b/security/Kconfig.hardening @@ -160,6 +160,35 @@ config STACKLEAK_RUNTIME_DISABLE runtime to control kernel stack erasing for kernels built with CONFIG_GCC_PLUGIN_STACKLEAK. +config INIT_ON_ALLOC_DEFAULT_ON + bool "Enable heap memory zeroing on allocation by default" + help + This has the effect of setting "init_on_alloc=1" on the kernel + command line. This can be disabled with "init_on_alloc=0". + When "init_on_alloc" is enabled, all page allocator and slab + allocator memory will be zeroed when allocated, eliminating + many kinds of "uninitialized heap memory" flaws, especially + heap content exposures. The performance impact varies by + workload, but most cases see <1% impact. Some synthetic + workloads have measured as high as 7%. + +config INIT_ON_FREE_DEFAULT_ON + bool "Enable heap memory zeroing on free by default" + help + This has the effect of setting "init_on_free=1" on the kernel + command line. This can be disabled with "init_on_free=0". + Similar to "init_on_alloc", when "init_on_free" is enabled, + all page allocator and slab allocator memory will be zeroed + when freed, eliminating many kinds of "uninitialized heap memory" + flaws, especially heap content exposures. The primary difference + with "init_on_free" is that data lifetime in memory is reduced, + as anything freed is wiped immediately, making live forensics or + cold boot memory attacks unable to recover freed memory contents. + The performance impact varies by workload, but is more expensive + than "init_on_alloc" due to the negative cache effects of + touching "cold" memory areas. Most cases see 3-5% impact. Some + synthetic workloads have measured as high as 8%. + endmenu endmenu diff --git a/tools/vm/slabinfo.c b/tools/vm/slabinfo.c index 73818f1b2ef8..68092d15e12b 100644 --- a/tools/vm/slabinfo.c +++ b/tools/vm/slabinfo.c @@ -79,6 +79,7 @@ int sort_size; int sort_active; int set_debug; int show_ops; +int sort_partial; int show_activity; int output_lines = -1; int sort_loss; @@ -110,7 +111,7 @@ static void fatal(const char *x, ...) static void usage(void) { printf("slabinfo 4/15/2011. (c) 2007 sgi/(c) 2011 Linux Foundation.\n\n" - "slabinfo [-aADefhilnosrStTvz1LXBU] [N=K] [-dafzput] [slab-regexp]\n" + "slabinfo [-aABDefhilLnoPrsStTUvXz1] [N=K] [-dafzput] [slab-regexp]\n" "-a|--aliases Show aliases\n" "-A|--activity Most active slabs first\n" "-B|--Bytes Show size in bytes\n" @@ -124,6 +125,7 @@ static void usage(void) "-n|--numa Show NUMA information\n" "-N|--lines=K Show the first K slabs\n" "-o|--ops Show kmem_cache_ops\n" + "-P|--partial Sort by number of partial slabs\n" "-r|--report Detailed report on single slabs\n" "-s|--shrink Shrink slabs\n" "-S|--Size Sort by size\n" @@ -131,9 +133,9 @@ static void usage(void) "-T|--Totals Show summary information\n" "-U|--Unreclaim Show unreclaimable slabs only\n" "-v|--validate Validate slabs\n" + "-X|--Xtotals Show extended summary information\n" "-z|--zero Include empty slabs\n" "-1|--1ref Single reference\n" - "-X|--Xtotals Show extended summary information\n" "\n" "-d | --debug Switch off all debug options\n" @@ -146,6 +148,8 @@ static void usage(void) " p | P Poisoning\n" " u | U Tracking\n" " t | T Tracing\n" + + "\nSorting options (--Loss, --Size, --Partial) are mutually exclusive\n" ); } @@ -1047,6 +1051,8 @@ static void sort_slabs(void) result = slab_activity(s1) < slab_activity(s2); else if (sort_loss) result = slab_waste(s1) < slab_waste(s2); + else if (sort_partial) + result = s1->partial < s2->partial; else result = strcasecmp(s1->name, s2->name); @@ -1307,33 +1313,46 @@ static void output_slabs(void) } } +static void _xtotals(char *heading, char *underline, + int loss, int size, int partial) +{ + printf("%s%s", heading, underline); + line = 0; + sort_loss = loss; + sort_size = size; + sort_partial = partial; + sort_slabs(); + output_slabs(); +} + static void xtotals(void) { + char *heading, *underline; + totals(); link_slabs(); rename_slabs(); - printf("\nSlabs sorted by size\n"); - printf("--------------------\n"); - sort_loss = 0; - sort_size = 1; - sort_slabs(); - output_slabs(); + heading = "\nSlabs sorted by size\n"; + underline = "--------------------\n"; + _xtotals(heading, underline, 0, 1, 0); + + heading = "\nSlabs sorted by loss\n"; + underline = "--------------------\n"; + _xtotals(heading, underline, 1, 0, 0); + + heading = "\nSlabs sorted by number of partial slabs\n"; + underline = "---------------------------------------\n"; + _xtotals(heading, underline, 0, 0, 1); - printf("\nSlabs sorted by loss\n"); - printf("--------------------\n"); - line = 0; - sort_loss = 1; - sort_size = 0; - sort_slabs(); - output_slabs(); printf("\n"); } struct option opts[] = { { "aliases", no_argument, NULL, 'a' }, { "activity", no_argument, NULL, 'A' }, + { "Bytes", no_argument, NULL, 'B'}, { "debug", optional_argument, NULL, 'd' }, { "display-activity", no_argument, NULL, 'D' }, { "empty", no_argument, NULL, 'e' }, @@ -1341,21 +1360,21 @@ struct option opts[] = { { "help", no_argument, NULL, 'h' }, { "inverted", no_argument, NULL, 'i'}, { "slabs", no_argument, NULL, 'l' }, + { "Loss", no_argument, NULL, 'L'}, { "numa", no_argument, NULL, 'n' }, + { "lines", required_argument, NULL, 'N'}, { "ops", no_argument, NULL, 'o' }, - { "shrink", no_argument, NULL, 's' }, + { "partial", no_argument, NULL, 'p'}, { "report", no_argument, NULL, 'r' }, + { "shrink", no_argument, NULL, 's' }, { "Size", no_argument, NULL, 'S'}, { "tracking", no_argument, NULL, 't'}, { "Totals", no_argument, NULL, 'T'}, + { "Unreclaim", no_argument, NULL, 'U'}, { "validate", no_argument, NULL, 'v' }, + { "Xtotals", no_argument, NULL, 'X'}, { "zero", no_argument, NULL, 'z' }, { "1ref", no_argument, NULL, '1'}, - { "lines", required_argument, NULL, 'N'}, - { "Loss", no_argument, NULL, 'L'}, - { "Xtotals", no_argument, NULL, 'X'}, - { "Bytes", no_argument, NULL, 'B'}, - { "Unreclaim", no_argument, NULL, 'U'}, { NULL, 0, NULL, 0 } }; @@ -1367,18 +1386,18 @@ int main(int argc, char *argv[]) page_size = getpagesize(); - while ((c = getopt_long(argc, argv, "aAd::Defhil1noprstvzTSN:LXBU", + while ((c = getopt_long(argc, argv, "aABd::DefhilLnN:oPrsStTUvXz1", opts, NULL)) != -1) switch (c) { - case '1': - show_single_ref = 1; - break; case 'a': show_alias = 1; break; case 'A': sort_active = 1; break; + case 'B': + show_bytes = 1; + break; case 'd': set_debug = 1; if (!debug_opt_scan(optarg)) @@ -1399,45 +1418,48 @@ int main(int argc, char *argv[]) case 'i': show_inverted = 1; break; + case 'l': + show_slab = 1; + break; + case 'L': + sort_loss = 1; + break; case 'n': show_numa = 1; break; + case 'N': + if (optarg) { + output_lines = atoi(optarg); + if (output_lines < 1) + output_lines = 1; + } + break; case 'o': show_ops = 1; break; case 'r': show_report = 1; break; + case 'P': + sort_partial = 1; + break; case 's': shrink = 1; break; - case 'l': - show_slab = 1; + case 'S': + sort_size = 1; break; case 't': show_track = 1; break; - case 'v': - validate = 1; - break; - case 'z': - skip_zero = 0; - break; case 'T': show_totals = 1; break; - case 'S': - sort_size = 1; - break; - case 'N': - if (optarg) { - output_lines = atoi(optarg); - if (output_lines < 1) - output_lines = 1; - } + case 'U': + unreclaim_only = 1; break; - case 'L': - sort_loss = 1; + case 'v': + validate = 1; break; case 'X': if (output_lines == -1) @@ -1445,11 +1467,11 @@ int main(int argc, char *argv[]) extended_totals = 1; show_bytes = 1; break; - case 'B': - show_bytes = 1; + case 'z': + skip_zero = 0; break; - case 'U': - unreclaim_only = 1; + case '1': + show_single_ref = 1; break; default: fatal("%s: Invalid option '%c'\n", argv[0], optopt); diff --git a/virt/kvm/arm/mmu.c b/virt/kvm/arm/mmu.c index 198e5171e1f7..38b4c910b6c3 100644 --- a/virt/kvm/arm/mmu.c +++ b/virt/kvm/arm/mmu.c @@ -129,7 +129,7 @@ static int mmu_topup_memory_cache(struct kvm_mmu_memory_cache *cache, if (cache->nobjs >= min) return 0; while (cache->nobjs < max) { - page = (void *)__get_free_page(PGALLOC_GFP); + page = (void *)__get_free_page(GFP_PGTABLE_USER); if (!page) return -ENOMEM; cache->objects[cache->nobjs++] = page; |