From 376a34efa4eeb699d285c1a741b186d44b44c429 Mon Sep 17 00:00:00 2001 From: John Hubbard Date: Wed, 3 Jun 2020 15:56:30 -0700 Subject: mm/gup: refactor and de-duplicate gup_fast() code There were two nearly identical sets of code for gup_fast() style of walking the page tables with interrupts disabled. This has lead to the usual maintenance problems that arise from having duplicated code. There is already a core internal routine in gup.c for gup_fast(), so just enhance it very slightly: allow skipping the fall-back to "slow" (regular) get_user_pages(), via the new FOLL_FAST_ONLY flag. Then, just call internal_get_user_pages_fast() from __get_user_pages_fast(), and adjust the API to match pre-existing API behavior. There is a change in behavior from this refactoring: the nested form of interrupt disabling is used in all gup_fast() variants now. That's because there is only one place that interrupt disabling for page walking is done, and so the safer form is required. This should, if anything, eliminate possible (rare) bugs, because the non-nested form of enabling interrupts was fragile at best. [jhubbard@nvidia.com: fixup] Link: http://lkml.kernel.org/r/20200521233841.1279742-1-jhubbard@nvidia.com Signed-off-by: John Hubbard Signed-off-by: Andrew Morton Reviewed-by: Chris Wilson Cc: Daniel Vetter Cc: David Airlie Cc: Jani Nikula Cc: "Joonas Lahtinen" Cc: Matthew Auld Cc: Matthew Wilcox Cc: Rodrigo Vivi Cc: Souptick Joarder Cc: Tvrtko Ursulin Link: http://lkml.kernel.org/r/20200519002124.2025955-3-jhubbard@nvidia.com Signed-off-by: Linus Torvalds --- include/linux/mm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index 7e07f4f490cb..e6b884715da1 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2816,6 +2816,7 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address, #define FOLL_LONGTERM 0x10000 /* mapping lifetime is indefinite: see below */ #define FOLL_SPLIT_PMD 0x20000 /* split huge pmd before returning */ #define FOLL_PIN 0x40000 /* pages must be released via unpin_user_page */ +#define FOLL_FAST_ONLY 0x80000 /* gup_fast: prevent fall-back to slow gup */ /* * FOLL_PIN and FOLL_LONGTERM may be used in various combinations with each -- cgit v1.2.3 From 104acc327648b347d1716374586803e82fa1dc95 Mon Sep 17 00:00:00 2001 From: John Hubbard Date: Wed, 3 Jun 2020 15:56:34 -0700 Subject: mm/gup: introduce pin_user_pages_fast_only() This is the FOLL_PIN equivalent of __get_user_pages_fast(), except with a more descriptive name, and gup_flags instead of a boolean "write" in the argument list. Signed-off-by: John Hubbard Signed-off-by: Andrew Morton Reviewed-by: Chris Wilson Cc: Daniel Vetter Cc: David Airlie Cc: Jani Nikula Cc: "Joonas Lahtinen" Cc: Matthew Auld Cc: Matthew Wilcox Cc: Rodrigo Vivi Cc: Souptick Joarder Cc: Tvrtko Ursulin Link: http://lkml.kernel.org/r/20200519002124.2025955-4-jhubbard@nvidia.com Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 ++ mm/gup.c | 36 ++++++++++++++++++++++++++++++++++++ 2 files changed, 38 insertions(+) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index e6b884715da1..6c236c5b0015 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1827,6 +1827,8 @@ extern int mprotect_fixup(struct vm_area_struct *vma, */ int __get_user_pages_fast(unsigned long start, int nr_pages, int write, struct page **pages); +int pin_user_pages_fast_only(unsigned long start, int nr_pages, + unsigned int gup_flags, struct page **pages); /* * per-process(per-mm_struct) statistics. */ diff --git a/mm/gup.c b/mm/gup.c index 67b5e96cd2c7..0702c1a7e041 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -2917,6 +2917,42 @@ int pin_user_pages_fast(unsigned long start, int nr_pages, } EXPORT_SYMBOL_GPL(pin_user_pages_fast); +/* + * This is the FOLL_PIN equivalent of __get_user_pages_fast(). Behavior is the + * same, except that this one sets FOLL_PIN instead of FOLL_GET. + * + * The API rules are the same, too: no negative values may be returned. + */ +int pin_user_pages_fast_only(unsigned long start, int nr_pages, + unsigned int gup_flags, struct page **pages) +{ + int nr_pinned; + + /* + * FOLL_GET and FOLL_PIN are mutually exclusive. Note that the API + * rules require returning 0, rather than -errno: + */ + if (WARN_ON_ONCE(gup_flags & FOLL_GET)) + return 0; + /* + * FOLL_FAST_ONLY is required in order to match the API description of + * this routine: no fall back to regular ("slow") GUP. + */ + gup_flags |= (FOLL_PIN | FOLL_FAST_ONLY); + nr_pinned = internal_get_user_pages_fast(start, nr_pages, gup_flags, + pages); + /* + * This routine is not allowed to return negative values. However, + * internal_get_user_pages_fast() *can* return -errno. Therefore, + * correct for that here: + */ + if (nr_pinned < 0) + nr_pinned = 0; + + return nr_pinned; +} +EXPORT_SYMBOL_GPL(pin_user_pages_fast_only); + /** * pin_user_pages_remote() - pin pages of a remote process (task != current) * -- cgit v1.2.3 From 47227d27e2fcb01a9e8f5958d8997cf47a820afc Mon Sep 17 00:00:00 2001 From: Daniel Axtens Date: Wed, 3 Jun 2020 15:56:46 -0700 Subject: string.h: fix incompatibility between FORTIFY_SOURCE and KASAN The memcmp KASAN self-test fails on a kernel with both KASAN and FORTIFY_SOURCE. When FORTIFY_SOURCE is on, a number of functions are replaced with fortified versions, which attempt to check the sizes of the operands. However, these functions often directly invoke __builtin_foo() once they have performed the fortify check. Using __builtins may bypass KASAN checks if the compiler decides to inline it's own implementation as sequence of instructions, rather than emit a function call that goes out to a KASAN-instrumented implementation. Why is only memcmp affected? ============================ Of the string and string-like functions that kasan_test tests, only memcmp is replaced by an inline sequence of instructions in my testing on x86 with gcc version 9.2.1 20191008 (Ubuntu 9.2.1-9ubuntu2). I believe this is due to compiler heuristics. For example, if I annotate kmalloc calls with the alloc_size annotation (and disable some fortify compile-time checking!), the compiler will replace every memset except the one in kmalloc_uaf_memset with inline instructions. (I have some WIP patches to add this annotation.) Does this affect other functions in string.h? ============================================= Yes. Anything that uses __builtin_* rather than __real_* could be affected. This looks like: - strncpy - strcat - strlen - strlcpy maybe, under some circumstances? - strncat under some circumstances - memset - memcpy - memmove - memcmp (as noted) - memchr - strcpy Whether a function call is emitted always depends on the compiler. Most bugs should get caught by FORTIFY_SOURCE, but the missed memcmp test shows that this is not always the case. Isn't FORTIFY_SOURCE disabled with KASAN? ========================================- The string headers on all arches supporting KASAN disable fortify with kasan, but only when address sanitisation is _also_ disabled. For example from x86: #if defined(CONFIG_KASAN) && !defined(__SANITIZE_ADDRESS__) /* * For files that are not instrumented (e.g. mm/slub.c) we * should use not instrumented version of mem* functions. */ #define memcpy(dst, src, len) __memcpy(dst, src, len) #define memmove(dst, src, len) __memmove(dst, src, len) #define memset(s, c, n) __memset(s, c, n) #ifndef __NO_FORTIFY #define __NO_FORTIFY /* FORTIFY_SOURCE uses __builtin_memcpy, etc. */ #endif #endif This comes from commit 6974f0c4555e ("include/linux/string.h: add the option of fortified string.h functions"), and doesn't work when KASAN is enabled and the file is supposed to be sanitised - as with test_kasan.c I'm pretty sure this is not wrong, but not as expansive it should be: * we shouldn't use __builtin_memcpy etc in files where we don't have instrumentation - it could devolve into a function call to memcpy, which will be instrumented. Rather, we should use __memcpy which by convention is not instrumented. * we also shouldn't be using __builtin_memcpy when we have a KASAN instrumented file, because it could be replaced with inline asm that will not be instrumented. What is correct behaviour? ========================== Firstly, there is some overlap between fortification and KASAN: both provide some level of _runtime_ checking. Only fortify provides compile-time checking. KASAN and fortify can pick up different things at runtime: - Some fortify functions, notably the string functions, could easily be modified to consider sub-object sizes (e.g. members within a struct), and I have some WIP patches to do this. KASAN cannot detect these because it cannot insert poision between members of a struct. - KASAN can detect many over-reads/over-writes when the sizes of both operands are unknown, which fortify cannot. So there are a couple of options: 1) Flip the test: disable fortify in santised files and enable it in unsanitised files. This at least stops us missing KASAN checking, but we lose the fortify checking. 2) Make the fortify code always call out to real versions. Do this only for KASAN, for fear of losing the inlining opportunities we get from __builtin_*. (We can't use kasan_check_{read,write}: because the fortify functions are _extern inline_, you can't include _static_ inline functions without a compiler warning. kasan_check_{read,write} are static inline so we can't use them even when they would otherwise be suitable.) Take approach 2 and call out to real versions when KASAN is enabled. Use __underlying_foo to distinguish from __real_foo: __real_foo always refers to the kernel's implementation of foo, __underlying_foo could be either the kernel implementation or the __builtin_foo implementation. This is sometimes enough to make the memcmp test succeed with FORTIFY_SOURCE enabled. It is at least enough to get the function call into the module. One more fix is needed to make it reliable: see the next patch. Fixes: 6974f0c4555e ("include/linux/string.h: add the option of fortified string.h functions") Signed-off-by: Daniel Axtens Signed-off-by: Andrew Morton Tested-by: David Gow Reviewed-by: Dmitry Vyukov Cc: Daniel Micay Cc: Andrey Ryabinin Cc: Alexander Potapenko Link: http://lkml.kernel.org/r/20200423154503.5103-3-dja@axtens.net Signed-off-by: Linus Torvalds --- include/linux/string.h | 60 ++++++++++++++++++++++++++++++++++++++++---------- 1 file changed, 48 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/linux/string.h b/include/linux/string.h index 6dfbb2efa815..9b7a0632e87a 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -272,6 +272,31 @@ void __read_overflow3(void) __compiletime_error("detected read beyond size of ob void __write_overflow(void) __compiletime_error("detected write beyond size of object passed as 1st parameter"); #if !defined(__NO_FORTIFY) && defined(__OPTIMIZE__) && defined(CONFIG_FORTIFY_SOURCE) + +#ifdef CONFIG_KASAN +extern void *__underlying_memchr(const void *p, int c, __kernel_size_t size) __RENAME(memchr); +extern int __underlying_memcmp(const void *p, const void *q, __kernel_size_t size) __RENAME(memcmp); +extern void *__underlying_memcpy(void *p, const void *q, __kernel_size_t size) __RENAME(memcpy); +extern void *__underlying_memmove(void *p, const void *q, __kernel_size_t size) __RENAME(memmove); +extern void *__underlying_memset(void *p, int c, __kernel_size_t size) __RENAME(memset); +extern char *__underlying_strcat(char *p, const char *q) __RENAME(strcat); +extern char *__underlying_strcpy(char *p, const char *q) __RENAME(strcpy); +extern __kernel_size_t __underlying_strlen(const char *p) __RENAME(strlen); +extern char *__underlying_strncat(char *p, const char *q, __kernel_size_t count) __RENAME(strncat); +extern char *__underlying_strncpy(char *p, const char *q, __kernel_size_t size) __RENAME(strncpy); +#else +#define __underlying_memchr __builtin_memchr +#define __underlying_memcmp __builtin_memcmp +#define __underlying_memcpy __builtin_memcpy +#define __underlying_memmove __builtin_memmove +#define __underlying_memset __builtin_memset +#define __underlying_strcat __builtin_strcat +#define __underlying_strcpy __builtin_strcpy +#define __underlying_strlen __builtin_strlen +#define __underlying_strncat __builtin_strncat +#define __underlying_strncpy __builtin_strncpy +#endif + __FORTIFY_INLINE char *strncpy(char *p, const char *q, __kernel_size_t size) { size_t p_size = __builtin_object_size(p, 0); @@ -279,14 +304,14 @@ __FORTIFY_INLINE char *strncpy(char *p, const char *q, __kernel_size_t size) __write_overflow(); if (p_size < size) fortify_panic(__func__); - return __builtin_strncpy(p, q, size); + return __underlying_strncpy(p, q, size); } __FORTIFY_INLINE char *strcat(char *p, const char *q) { size_t p_size = __builtin_object_size(p, 0); if (p_size == (size_t)-1) - return __builtin_strcat(p, q); + return __underlying_strcat(p, q); if (strlcat(p, q, p_size) >= p_size) fortify_panic(__func__); return p; @@ -300,7 +325,7 @@ __FORTIFY_INLINE __kernel_size_t strlen(const char *p) /* Work around gcc excess stack consumption issue */ if (p_size == (size_t)-1 || (__builtin_constant_p(p[p_size - 1]) && p[p_size - 1] == '\0')) - return __builtin_strlen(p); + return __underlying_strlen(p); ret = strnlen(p, p_size); if (p_size <= ret) fortify_panic(__func__); @@ -333,7 +358,7 @@ __FORTIFY_INLINE size_t strlcpy(char *p, const char *q, size_t size) __write_overflow(); if (len >= p_size) fortify_panic(__func__); - __builtin_memcpy(p, q, len); + __underlying_memcpy(p, q, len); p[len] = '\0'; } return ret; @@ -346,12 +371,12 @@ __FORTIFY_INLINE char *strncat(char *p, const char *q, __kernel_size_t count) size_t p_size = __builtin_object_size(p, 0); size_t q_size = __builtin_object_size(q, 0); if (p_size == (size_t)-1 && q_size == (size_t)-1) - return __builtin_strncat(p, q, count); + return __underlying_strncat(p, q, count); p_len = strlen(p); copy_len = strnlen(q, count); if (p_size < p_len + copy_len + 1) fortify_panic(__func__); - __builtin_memcpy(p + p_len, q, copy_len); + __underlying_memcpy(p + p_len, q, copy_len); p[p_len + copy_len] = '\0'; return p; } @@ -363,7 +388,7 @@ __FORTIFY_INLINE void *memset(void *p, int c, __kernel_size_t size) __write_overflow(); if (p_size < size) fortify_panic(__func__); - return __builtin_memset(p, c, size); + return __underlying_memset(p, c, size); } __FORTIFY_INLINE void *memcpy(void *p, const void *q, __kernel_size_t size) @@ -378,7 +403,7 @@ __FORTIFY_INLINE void *memcpy(void *p, const void *q, __kernel_size_t size) } if (p_size < size || q_size < size) fortify_panic(__func__); - return __builtin_memcpy(p, q, size); + return __underlying_memcpy(p, q, size); } __FORTIFY_INLINE void *memmove(void *p, const void *q, __kernel_size_t size) @@ -393,7 +418,7 @@ __FORTIFY_INLINE void *memmove(void *p, const void *q, __kernel_size_t size) } if (p_size < size || q_size < size) fortify_panic(__func__); - return __builtin_memmove(p, q, size); + return __underlying_memmove(p, q, size); } extern void *__real_memscan(void *, int, __kernel_size_t) __RENAME(memscan); @@ -419,7 +444,7 @@ __FORTIFY_INLINE int memcmp(const void *p, const void *q, __kernel_size_t size) } if (p_size < size || q_size < size) fortify_panic(__func__); - return __builtin_memcmp(p, q, size); + return __underlying_memcmp(p, q, size); } __FORTIFY_INLINE void *memchr(const void *p, int c, __kernel_size_t size) @@ -429,7 +454,7 @@ __FORTIFY_INLINE void *memchr(const void *p, int c, __kernel_size_t size) __read_overflow(); if (p_size < size) fortify_panic(__func__); - return __builtin_memchr(p, c, size); + return __underlying_memchr(p, c, size); } void *__real_memchr_inv(const void *s, int c, size_t n) __RENAME(memchr_inv); @@ -460,11 +485,22 @@ __FORTIFY_INLINE char *strcpy(char *p, const char *q) size_t p_size = __builtin_object_size(p, 0); size_t q_size = __builtin_object_size(q, 0); if (p_size == (size_t)-1 && q_size == (size_t)-1) - return __builtin_strcpy(p, q); + return __underlying_strcpy(p, q); memcpy(p, q, strlen(q) + 1); return p; } +/* Don't use these outside the FORITFY_SOURCE implementation */ +#undef __underlying_memchr +#undef __underlying_memcmp +#undef __underlying_memcpy +#undef __underlying_memmove +#undef __underlying_memset +#undef __underlying_strcat +#undef __underlying_strcpy +#undef __underlying_strlen +#undef __underlying_strncat +#undef __underlying_strncpy #endif /** -- cgit v1.2.3 From 574c1ae66c12410a08aeef8474936baa50e0371d Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Wed, 3 Jun 2020 15:56:49 -0700 Subject: mm: clarify __GFP_MEMALLOC usage It seems that the existing documentation is not explicit about the expected usage and potential risks enough. While it is calls out that users have to free memory when using this flag it is not really apparent that users have to careful to not deplete memory reserves and that they should implement some sort of throttling wrt. freeing process. This is partly based on Neil's explanation [1]. Let's also call out that a pre allocated pool allocator should be considered. [1] http://lkml.kernel.org/r/877dz0yxoa.fsf@notabene.neil.brown.name [akpm@linux-foundation.org: coding style fixes] [mhocko@kernel.org: update] Link: http://lkml.kernel.org/r/20200406070137.GC19426@dhcp22.suse.cz Signed-off-by: Michal Hocko Signed-off-by: Andrew Morton Cc: David Rientjes Cc: Joel Fernandes Cc: Neil Brown Cc: Paul E. McKenney Cc: John Hubbard Link: http://lkml.kernel.org/r/20200403083543.11552-2-mhocko@kernel.org Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 4aba4c86c626..fab6d486cbb7 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -110,6 +110,11 @@ struct vm_area_struct; * the caller guarantees the allocation will allow more memory to be freed * very shortly e.g. process exiting or swapping. Users either should * be the MM or co-ordinating closely with the VM (e.g. swap over NFS). + * Users of this flag have to be extremely careful to not deplete the reserve + * completely and implement a throttling mechanism which controls the + * consumption of the reserve based on the amount of freed memory. + * Usage of a pre-allocated pool (e.g. mempool) should be always considered + * before using this flag. * * %__GFP_NOMEMALLOC is used to explicitly forbid access to emergency reserves. * This takes precedence over the %__GFP_MEMALLOC flag if both are set. -- cgit v1.2.3 From 6f24fbd38c4e05f7905814791806c01dc6c4b9de Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Wed, 3 Jun 2020 15:56:57 -0700 Subject: mm: make early_pfn_to_nid() and related defintions close to each other early_pfn_to_nid() and its helper __early_pfn_to_nid() are spread around include/linux/mm.h, include/linux/mmzone.h and mm/page_alloc.c. Drop unused stub for __early_pfn_to_nid() and move its actual generic implementation close to its users. Signed-off-by: Mike Rapoport Signed-off-by: Andrew Morton Tested-by: Hoan Tran [arm64] Reviewed-by: Baoquan He Cc: Brian Cain Cc: Catalin Marinas Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Ungerer Cc: Guan Xuetao Cc: Guo Ren Cc: Heiko Carstens Cc: Helge Deller Cc: "James E.J. Bottomley" Cc: Jonathan Corbet Cc: Ley Foon Tan Cc: Mark Salter Cc: Matt Turner Cc: Max Filippov Cc: Michael Ellerman Cc: Michal Hocko Cc: Michal Simek Cc: Nick Hu Cc: Paul Walmsley Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Stafford Horne Cc: Thomas Bogendoerfer Cc: Tony Luck Cc: Vineet Gupta Cc: Yoshinori Sato Link: http://lkml.kernel.org/r/20200412194859.12663-3-rppt@kernel.org Signed-off-by: Linus Torvalds --- include/linux/mm.h | 4 ++-- include/linux/mmzone.h | 9 --------- mm/page_alloc.c | 51 +++++++++++++++++++++++++------------------------- 3 files changed, 27 insertions(+), 37 deletions(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index 6c236c5b0015..4288e6993dc8 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2445,9 +2445,9 @@ extern void sparse_memory_present_with_active_regions(int nid); #if !defined(CONFIG_HAVE_MEMBLOCK_NODE_MAP) && \ !defined(CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID) -static inline int __early_pfn_to_nid(unsigned long pfn, - struct mminit_pfnnid_cache *state) +static inline int early_pfn_to_nid(unsigned long pfn) { + BUILD_BUG_ON(IS_ENABLED(CONFIG_NUMA)); return 0; } #else diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index fdd9beb5efed..c3a77eb85b42 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -1080,15 +1080,6 @@ static inline struct zoneref *first_zones_zonelist(struct zonelist *zonelist, #include #endif -#if !defined(CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID) && \ - !defined(CONFIG_HAVE_MEMBLOCK_NODE_MAP) -static inline unsigned long early_pfn_to_nid(unsigned long pfn) -{ - BUILD_BUG_ON(IS_ENABLED(CONFIG_NUMA)); - return 0; -} -#endif - #ifdef CONFIG_FLATMEM #define pfn_to_nid(pfn) (0) #endif diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 511602288e2d..8741ae0828e1 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1504,6 +1504,31 @@ void __free_pages_core(struct page *page, unsigned int order) static struct mminit_pfnnid_cache early_pfnnid_cache __meminitdata; +#ifndef CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID + +/* + * Required by SPARSEMEM. Given a PFN, return what node the PFN is on. + */ +int __meminit __early_pfn_to_nid(unsigned long pfn, + struct mminit_pfnnid_cache *state) +{ + unsigned long start_pfn, end_pfn; + int nid; + + if (state->last_start <= pfn && pfn < state->last_end) + return state->last_nid; + + nid = memblock_search_pfn_nid(pfn, &start_pfn, &end_pfn); + if (nid != NUMA_NO_NODE) { + state->last_start = start_pfn; + state->last_end = end_pfn; + state->last_nid = nid; + } + + return nid; +} +#endif /* CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID */ + int __meminit early_pfn_to_nid(unsigned long pfn) { static DEFINE_SPINLOCK(early_pfn_lock); @@ -6310,32 +6335,6 @@ void __meminit init_currently_empty_zone(struct zone *zone, zone->initialized = 1; } -#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP -#ifndef CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID - -/* - * Required by SPARSEMEM. Given a PFN, return what node the PFN is on. - */ -int __meminit __early_pfn_to_nid(unsigned long pfn, - struct mminit_pfnnid_cache *state) -{ - unsigned long start_pfn, end_pfn; - int nid; - - if (state->last_start <= pfn && pfn < state->last_end) - return state->last_nid; - - nid = memblock_search_pfn_nid(pfn, &start_pfn, &end_pfn); - if (nid != NUMA_NO_NODE) { - state->last_start = start_pfn; - state->last_end = end_pfn; - state->last_nid = nid; - } - - return nid; -} -#endif /* CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID */ - /** * free_bootmem_with_active_regions - Call memblock_free_early_nid for each active range * @nid: The node to free memory on. If MAX_NUMNODES, all nodes are freed. -- cgit v1.2.3 From 3f08a302f533f74ad2e909e7a61274aa7eebc0ab Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Wed, 3 Jun 2020 15:57:02 -0700 Subject: mm: remove CONFIG_HAVE_MEMBLOCK_NODE_MAP option CONFIG_HAVE_MEMBLOCK_NODE_MAP is used to differentiate initialization of nodes and zones structures between the systems that have region to node mapping in memblock and those that don't. Currently all the NUMA architectures enable this option and for the non-NUMA systems we can presume that all the memory belongs to node 0 and therefore the compile time configuration option is not required. The remaining few architectures that use DISCONTIGMEM without NUMA are easily updated to use memblock_add_node() instead of memblock_add() and thus have proper correspondence of memblock regions to NUMA nodes. Still, free_area_init_node() must have a backward compatible version because its semantics with and without CONFIG_HAVE_MEMBLOCK_NODE_MAP is different. Once all the architectures will use the new semantics, the entire compatibility layer can be dropped. To avoid addition of extra run time memory to store node id for architectures that keep memblock but have only a single node, the node id field of the memblock_region is guarded by CONFIG_NEED_MULTIPLE_NODES and the corresponding accessors presume that in those cases it is always 0. Signed-off-by: Mike Rapoport Signed-off-by: Andrew Morton Tested-by: Hoan Tran [arm64] Acked-by: Catalin Marinas [arm64] Cc: Baoquan He Cc: Brian Cain Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Ungerer Cc: Guan Xuetao Cc: Guo Ren Cc: Heiko Carstens Cc: Helge Deller Cc: "James E.J. Bottomley" Cc: Jonathan Corbet Cc: Ley Foon Tan Cc: Mark Salter Cc: Matt Turner Cc: Max Filippov Cc: Michael Ellerman Cc: Michal Hocko Cc: Michal Simek Cc: Nick Hu Cc: Paul Walmsley Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Stafford Horne Cc: Thomas Bogendoerfer Cc: Tony Luck Cc: Vineet Gupta Cc: Yoshinori Sato Link: http://lkml.kernel.org/r/20200412194859.12663-4-rppt@kernel.org Signed-off-by: Linus Torvalds --- .../features/vm/numa-memblock/arch-support.txt | 34 ------- arch/alpha/mm/numa.c | 4 +- arch/arm64/Kconfig | 1 - arch/ia64/Kconfig | 1 - arch/m68k/mm/motorola.c | 4 +- arch/microblaze/Kconfig | 1 - arch/mips/Kconfig | 1 - arch/powerpc/Kconfig | 1 - arch/riscv/Kconfig | 1 - arch/s390/Kconfig | 1 - arch/sh/Kconfig | 1 - arch/sparc/Kconfig | 1 - arch/x86/Kconfig | 1 - include/linux/memblock.h | 8 +- include/linux/mm.h | 12 +-- include/linux/mmzone.h | 2 +- mm/Kconfig | 3 - mm/memblock.c | 11 +-- mm/memory_hotplug.c | 4 - mm/page_alloc.c | 101 ++++++++++++--------- 20 files changed, 74 insertions(+), 119 deletions(-) delete mode 100644 Documentation/features/vm/numa-memblock/arch-support.txt (limited to 'include') diff --git a/Documentation/features/vm/numa-memblock/arch-support.txt b/Documentation/features/vm/numa-memblock/arch-support.txt deleted file mode 100644 index 3004beb0fd71..000000000000 --- a/Documentation/features/vm/numa-memblock/arch-support.txt +++ /dev/null @@ -1,34 +0,0 @@ -# -# Feature name: numa-memblock -# Kconfig: HAVE_MEMBLOCK_NODE_MAP -# description: arch supports NUMA aware memblocks -# - ----------------------- - | arch |status| - ----------------------- - | alpha: | TODO | - | arc: | .. | - | arm: | .. | - | arm64: | ok | - | c6x: | .. | - | csky: | .. | - | h8300: | .. | - | hexagon: | .. | - | ia64: | ok | - | m68k: | .. | - | microblaze: | ok | - | mips: | ok | - | nds32: | TODO | - | nios2: | .. | - | openrisc: | .. | - | parisc: | .. | - | powerpc: | ok | - | riscv: | ok | - | s390: | ok | - | sh: | ok | - | sparc: | ok | - | um: | .. | - | unicore32: | .. | - | x86: | ok | - | xtensa: | .. | - ----------------------- diff --git a/arch/alpha/mm/numa.c b/arch/alpha/mm/numa.c index d0b73371e985..a24cd13e71cb 100644 --- a/arch/alpha/mm/numa.c +++ b/arch/alpha/mm/numa.c @@ -144,8 +144,8 @@ setup_memory_node(int nid, void *kernel_end) if (!nid && (node_max_pfn < end_kernel_pfn || node_min_pfn > start_kernel_pfn)) panic("kernel loaded out of ram"); - memblock_add(PFN_PHYS(node_min_pfn), - (node_max_pfn - node_min_pfn) << PAGE_SHIFT); + memblock_add_node(PFN_PHYS(node_min_pfn), + (node_max_pfn - node_min_pfn) << PAGE_SHIFT, nid); /* Zone start phys-addr must be 2^(MAX_ORDER-1) aligned. Note that we round this down, not up - node memory diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 552d36cacc05..1a9b480c6f1d 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -162,7 +162,6 @@ config ARM64 select HAVE_GCC_PLUGINS select HAVE_HW_BREAKPOINT if PERF_EVENTS select HAVE_IRQ_TIME_ACCOUNTING - select HAVE_MEMBLOCK_NODE_MAP if NUMA select HAVE_NMI select HAVE_PATA_PLATFORM select HAVE_PERF_EVENTS diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig index bab7cd878464..88b05b5256a9 100644 --- a/arch/ia64/Kconfig +++ b/arch/ia64/Kconfig @@ -31,7 +31,6 @@ config IA64 select HAVE_FUNCTION_TRACER select TTY select HAVE_ARCH_TRACEHOOK - select HAVE_MEMBLOCK_NODE_MAP select HAVE_VIRT_CPU_ACCOUNTING select DMA_NONCOHERENT_MMAP select ARCH_HAS_SYNC_DMA_FOR_CPU diff --git a/arch/m68k/mm/motorola.c b/arch/m68k/mm/motorola.c index fc16190ec2d6..84ab5963cabb 100644 --- a/arch/m68k/mm/motorola.c +++ b/arch/m68k/mm/motorola.c @@ -386,7 +386,7 @@ void __init paging_init(void) min_addr = m68k_memory[0].addr; max_addr = min_addr + m68k_memory[0].size; - memblock_add(m68k_memory[0].addr, m68k_memory[0].size); + memblock_add_node(m68k_memory[0].addr, m68k_memory[0].size, 0); for (i = 1; i < m68k_num_memory;) { if (m68k_memory[i].addr < min_addr) { printk("Ignoring memory chunk at 0x%lx:0x%lx before the first chunk\n", @@ -397,7 +397,7 @@ void __init paging_init(void) (m68k_num_memory - i) * sizeof(struct m68k_mem_info)); continue; } - memblock_add(m68k_memory[i].addr, m68k_memory[i].size); + memblock_add_node(m68k_memory[i].addr, m68k_memory[i].size, i); addr = m68k_memory[i].addr + m68k_memory[i].size; if (addr > max_addr) max_addr = addr; diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig index 9606c244b5b8..d262ac0c8714 100644 --- a/arch/microblaze/Kconfig +++ b/arch/microblaze/Kconfig @@ -32,7 +32,6 @@ config MICROBLAZE select HAVE_FTRACE_MCOUNT_RECORD select HAVE_FUNCTION_GRAPH_TRACER select HAVE_FUNCTION_TRACER - select HAVE_MEMBLOCK_NODE_MAP select HAVE_OPROFILE select HAVE_PCI select IRQ_DOMAIN diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 690718b3701a..94a91b5b7759 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -72,7 +72,6 @@ config MIPS select HAVE_KPROBES select HAVE_KRETPROBES select HAVE_LD_DEAD_CODE_DATA_ELIMINATION - select HAVE_MEMBLOCK_NODE_MAP select HAVE_MOD_ARCH_SPECIFIC select HAVE_NMI select HAVE_OPROFILE diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index b29d7cb38368..41ba42b107c0 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -211,7 +211,6 @@ config PPC select HAVE_KRETPROBES select HAVE_LD_DEAD_CODE_DATA_ELIMINATION select HAVE_LIVEPATCH if HAVE_DYNAMIC_FTRACE_WITH_REGS - select HAVE_MEMBLOCK_NODE_MAP select HAVE_MOD_ARCH_SPECIFIC select HAVE_NMI if PERF_EVENTS || (PPC64 && PPC_BOOK3S) select HAVE_HARDLOCKUP_DETECTOR_ARCH if (PPC64 && PPC_BOOK3S) diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index a31e1a41913a..5c07ca4d5cd6 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -32,7 +32,6 @@ config RISCV select HAVE_ARCH_AUDITSYSCALL select HAVE_ARCH_SECCOMP_FILTER select HAVE_ASM_MODVERSIONS - select HAVE_MEMBLOCK_NODE_MAP select HAVE_DMA_CONTIGUOUS if MMU select HAVE_FUTEX_CMPXCHG if FUTEX select HAVE_PERF_EVENTS diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 2167bce993ff..d6dc6933adc2 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -162,7 +162,6 @@ config S390 select HAVE_LIVEPATCH select HAVE_PERF_REGS select HAVE_PERF_USER_STACK_DUMP - select HAVE_MEMBLOCK_NODE_MAP select HAVE_MEMBLOCK_PHYS_MAP select MMU_GATHER_NO_GATHER select HAVE_MOD_ARCH_SPECIFIC diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index 97656d20b9ea..0424b8f2f8d3 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -9,7 +9,6 @@ config SUPERH select CLKDEV_LOOKUP select DMA_DECLARE_COHERENT select HAVE_IDE if HAS_IOPORT_MAP - select HAVE_MEMBLOCK_NODE_MAP select HAVE_OPROFILE select HAVE_ARCH_TRACEHOOK select HAVE_PERF_EVENTS diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index da515fdad83d..795206b7b552 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -65,7 +65,6 @@ config SPARC64 select HAVE_KRETPROBES select HAVE_KPROBES select MMU_GATHER_RCU_TABLE_FREE if SMP - select HAVE_MEMBLOCK_NODE_MAP select HAVE_ARCH_TRANSPARENT_HUGEPAGE select HAVE_DYNAMIC_FTRACE select HAVE_FTRACE_MCOUNT_RECORD diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index e5d38cd11df0..c669328abf58 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -192,7 +192,6 @@ config X86 select HAVE_KRETPROBES select HAVE_KVM select HAVE_LIVEPATCH if X86_64 - select HAVE_MEMBLOCK_NODE_MAP select HAVE_MIXED_BREAKPOINTS_REGS select HAVE_MOD_ARCH_SPECIFIC select HAVE_MOVE_PMD diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 6bc37a731d27..45abfc54da37 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -50,7 +50,7 @@ struct memblock_region { phys_addr_t base; phys_addr_t size; enum memblock_flags flags; -#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP +#ifdef CONFIG_NEED_MULTIPLE_NODES int nid; #endif }; @@ -215,7 +215,6 @@ static inline bool memblock_is_nomap(struct memblock_region *m) return m->flags & MEMBLOCK_NOMAP; } -#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP int memblock_search_pfn_nid(unsigned long pfn, unsigned long *start_pfn, unsigned long *end_pfn); void __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn, @@ -234,7 +233,6 @@ void __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn, #define for_each_mem_pfn_range(i, nid, p_start, p_end, p_nid) \ for (i = -1, __next_mem_pfn_range(&i, nid, p_start, p_end, p_nid); \ i >= 0; __next_mem_pfn_range(&i, nid, p_start, p_end, p_nid)) -#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT void __next_mem_pfn_range_in_zone(u64 *idx, struct zone *zone, @@ -310,10 +308,10 @@ void __next_mem_pfn_range_in_zone(u64 *idx, struct zone *zone, for_each_mem_range_rev(i, &memblock.memory, &memblock.reserved, \ nid, flags, p_start, p_end, p_nid) -#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP int memblock_set_node(phys_addr_t base, phys_addr_t size, struct memblock_type *type, int nid); +#ifdef CONFIG_NEED_MULTIPLE_NODES static inline void memblock_set_region_node(struct memblock_region *r, int nid) { r->nid = nid; @@ -332,7 +330,7 @@ static inline int memblock_get_region_node(const struct memblock_region *r) { return 0; } -#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ +#endif /* CONFIG_NEED_MULTIPLE_NODES */ /* Flags for memblock allocation APIs */ #define MEMBLOCK_ALLOC_ANYWHERE (~(phys_addr_t)0) diff --git a/include/linux/mm.h b/include/linux/mm.h index 4288e6993dc8..5f15d8723167 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2401,9 +2401,8 @@ static inline unsigned long get_num_physpages(void) return phys_pages; } -#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP /* - * With CONFIG_HAVE_MEMBLOCK_NODE_MAP set, an architecture may initialise its + * Using memblock node mappings, an architecture may initialise its * zones, allocate the backing mem_map and account for memory holes in a more * architecture independent manner. This is a substitute for creating the * zone_sizes[] and zholes_size[] arrays and passing them to @@ -2424,9 +2423,6 @@ static inline unsigned long get_num_physpages(void) * registered physical page range. Similarly * sparse_memory_present_with_active_regions() calls memory_present() for * each range when SPARSEMEM is enabled. - * - * See mm/page_alloc.c for more information on each function exposed by - * CONFIG_HAVE_MEMBLOCK_NODE_MAP. */ extern void free_area_init_nodes(unsigned long *max_zone_pfn); unsigned long node_map_pfn_alignment(void); @@ -2441,13 +2437,9 @@ extern void free_bootmem_with_active_regions(int nid, unsigned long max_low_pfn); extern void sparse_memory_present_with_active_regions(int nid); -#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ - -#if !defined(CONFIG_HAVE_MEMBLOCK_NODE_MAP) && \ - !defined(CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID) +#ifndef CONFIG_NEED_MULTIPLE_NODES static inline int early_pfn_to_nid(unsigned long pfn) { - BUILD_BUG_ON(IS_ENABLED(CONFIG_NUMA)); return 0; } #else diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index c3a77eb85b42..0c575c3d7feb 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -876,7 +876,7 @@ extern int movable_zone; #ifdef CONFIG_HIGHMEM static inline int zone_movable_is_highmem(void) { -#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP +#ifdef CONFIG_NEED_MULTIPLE_NODES return movable_zone == ZONE_HIGHMEM; #else return (ZONE_MOVABLE - 1) == ZONE_HIGHMEM; diff --git a/mm/Kconfig b/mm/Kconfig index 5c0362bd8d56..3af64646f343 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -126,9 +126,6 @@ config SPARSEMEM_VMEMMAP pfn_to_page and page_to_pfn operations. This is the most efficient option when sufficient kernel resources are available. -config HAVE_MEMBLOCK_NODE_MAP - bool - config HAVE_MEMBLOCK_PHYS_MAP bool diff --git a/mm/memblock.c b/mm/memblock.c index 43e2fd3006c1..743659d88fc4 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -620,7 +620,7 @@ repeat: * area, insert that portion. */ if (rbase > base) { -#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP +#ifdef CONFIG_NEED_MULTIPLE_NODES WARN_ON(nid != memblock_get_region_node(rgn)); #endif WARN_ON(flags != rgn->flags); @@ -1197,7 +1197,6 @@ void __init_memblock __next_mem_range_rev(u64 *idx, int nid, *idx = ULLONG_MAX; } -#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP /* * Common iterator interface used to define for_each_mem_pfn_range(). */ @@ -1247,6 +1246,7 @@ void __init_memblock __next_mem_pfn_range(int *idx, int nid, int __init_memblock memblock_set_node(phys_addr_t base, phys_addr_t size, struct memblock_type *type, int nid) { +#ifdef CONFIG_NEED_MULTIPLE_NODES int start_rgn, end_rgn; int i, ret; @@ -1258,9 +1258,10 @@ int __init_memblock memblock_set_node(phys_addr_t base, phys_addr_t size, memblock_set_region_node(&type->regions[i], nid); memblock_merge_regions(type); +#endif return 0; } -#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ + #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT /** * __next_mem_pfn_range_in_zone - iterator for for_each_*_range_in_zone() @@ -1799,7 +1800,6 @@ bool __init_memblock memblock_is_map_memory(phys_addr_t addr) return !memblock_is_nomap(&memblock.memory.regions[i]); } -#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP int __init_memblock memblock_search_pfn_nid(unsigned long pfn, unsigned long *start_pfn, unsigned long *end_pfn) { @@ -1814,7 +1814,6 @@ int __init_memblock memblock_search_pfn_nid(unsigned long pfn, return memblock_get_region_node(&type->regions[mid]); } -#endif /** * memblock_is_region_memory - check if a region is a subset of memory @@ -1905,7 +1904,7 @@ static void __init_memblock memblock_dump(struct memblock_type *type) size = rgn->size; end = base + size - 1; flags = rgn->flags; -#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP +#ifdef CONFIG_NEED_MULTIPLE_NODES if (memblock_get_region_node(rgn) != MAX_NUMNODES) snprintf(nid_buf, sizeof(nid_buf), " on node %d", memblock_get_region_node(rgn)); diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index fc0aad0bc1f5..e67dc501576a 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1372,11 +1372,7 @@ check_pages_isolated_cb(unsigned long start_pfn, unsigned long nr_pages, static int __init cmdline_parse_movable_node(char *p) { -#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP movable_node_enabled = true; -#else - pr_warn("movable_node parameter depends on CONFIG_HAVE_MEMBLOCK_NODE_MAP to work properly\n"); -#endif return 0; } early_param("movable_node", cmdline_parse_movable_node); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 8741ae0828e1..430e35384b78 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -335,7 +335,6 @@ static unsigned long nr_kernel_pages __initdata; static unsigned long nr_all_pages __initdata; static unsigned long dma_reserve __initdata; -#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP static unsigned long arch_zone_lowest_possible_pfn[MAX_NR_ZONES] __initdata; static unsigned long arch_zone_highest_possible_pfn[MAX_NR_ZONES] __initdata; static unsigned long required_kernelcore __initdata; @@ -348,7 +347,6 @@ static bool mirrored_kernelcore __meminitdata; /* movable_zone is the "real" zone pages in ZONE_MOVABLE are taken from */ int movable_zone; EXPORT_SYMBOL(movable_zone); -#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ #if MAX_NUMNODES > 1 unsigned int nr_node_ids __read_mostly = MAX_NUMNODES; @@ -1499,8 +1497,7 @@ void __free_pages_core(struct page *page, unsigned int order) __free_pages(page, order); } -#if defined(CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID) || \ - defined(CONFIG_HAVE_MEMBLOCK_NODE_MAP) +#ifdef CONFIG_NEED_MULTIPLE_NODES static struct mminit_pfnnid_cache early_pfnnid_cache __meminitdata; @@ -1542,7 +1539,7 @@ int __meminit early_pfn_to_nid(unsigned long pfn) return nid; } -#endif +#endif /* CONFIG_NEED_MULTIPLE_NODES */ #ifdef CONFIG_NODES_SPAN_OTHER_NODES /* Only safe to use early in boot when initialisation is single-threaded */ @@ -5936,7 +5933,6 @@ void __ref build_all_zonelists(pg_data_t *pgdat) static bool __meminit overlap_memmap_init(unsigned long zone, unsigned long *pfn) { -#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP static struct memblock_region *r; if (mirrored_kernelcore && zone == ZONE_MOVABLE) { @@ -5952,7 +5948,6 @@ overlap_memmap_init(unsigned long zone, unsigned long *pfn) return true; } } -#endif return false; } @@ -6585,8 +6580,7 @@ static unsigned long __init zone_absent_pages_in_node(int nid, return nr_absent; } -#else /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ -static inline unsigned long __init zone_spanned_pages_in_node(int nid, +static inline unsigned long __init compat_zone_spanned_pages_in_node(int nid, unsigned long zone_type, unsigned long node_start_pfn, unsigned long node_end_pfn, @@ -6605,7 +6599,7 @@ static inline unsigned long __init zone_spanned_pages_in_node(int nid, return zones_size[zone_type]; } -static inline unsigned long __init zone_absent_pages_in_node(int nid, +static inline unsigned long __init compat_zone_absent_pages_in_node(int nid, unsigned long zone_type, unsigned long node_start_pfn, unsigned long node_end_pfn, @@ -6617,13 +6611,12 @@ static inline unsigned long __init zone_absent_pages_in_node(int nid, return zholes_size[zone_type]; } -#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ - static void __init calculate_node_totalpages(struct pglist_data *pgdat, unsigned long node_start_pfn, unsigned long node_end_pfn, unsigned long *zones_size, - unsigned long *zholes_size) + unsigned long *zholes_size, + bool compat) { unsigned long realtotalpages = 0, totalpages = 0; enum zone_type i; @@ -6631,17 +6624,38 @@ static void __init calculate_node_totalpages(struct pglist_data *pgdat, for (i = 0; i < MAX_NR_ZONES; i++) { struct zone *zone = pgdat->node_zones + i; unsigned long zone_start_pfn, zone_end_pfn; + unsigned long spanned, absent; unsigned long size, real_size; - size = zone_spanned_pages_in_node(pgdat->node_id, i, - node_start_pfn, - node_end_pfn, - &zone_start_pfn, - &zone_end_pfn, - zones_size); - real_size = size - zone_absent_pages_in_node(pgdat->node_id, i, - node_start_pfn, node_end_pfn, - zholes_size); + if (compat) { + spanned = compat_zone_spanned_pages_in_node( + pgdat->node_id, i, + node_start_pfn, + node_end_pfn, + &zone_start_pfn, + &zone_end_pfn, + zones_size); + absent = compat_zone_absent_pages_in_node( + pgdat->node_id, i, + node_start_pfn, + node_end_pfn, + zholes_size); + } else { + spanned = zone_spanned_pages_in_node(pgdat->node_id, i, + node_start_pfn, + node_end_pfn, + &zone_start_pfn, + &zone_end_pfn, + zones_size); + absent = zone_absent_pages_in_node(pgdat->node_id, i, + node_start_pfn, + node_end_pfn, + zholes_size); + } + + size = spanned; + real_size = size - absent; + if (size) zone->zone_start_pfn = zone_start_pfn; else @@ -6941,10 +6955,8 @@ static void __ref alloc_node_mem_map(struct pglist_data *pgdat) */ if (pgdat == NODE_DATA(0)) { mem_map = NODE_DATA(0)->node_mem_map; -#if defined(CONFIG_HAVE_MEMBLOCK_NODE_MAP) || defined(CONFIG_FLATMEM) if (page_to_pfn(mem_map) != pgdat->node_start_pfn) mem_map -= offset; -#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ } #endif } @@ -6961,9 +6973,10 @@ static inline void pgdat_set_deferred_range(pg_data_t *pgdat) static inline void pgdat_set_deferred_range(pg_data_t *pgdat) {} #endif -void __init free_area_init_node(int nid, unsigned long *zones_size, - unsigned long node_start_pfn, - unsigned long *zholes_size) +static void __init __free_area_init_node(int nid, unsigned long *zones_size, + unsigned long node_start_pfn, + unsigned long *zholes_size, + bool compat) { pg_data_t *pgdat = NODE_DATA(nid); unsigned long start_pfn = 0; @@ -6975,16 +6988,16 @@ void __init free_area_init_node(int nid, unsigned long *zones_size, pgdat->node_id = nid; pgdat->node_start_pfn = node_start_pfn; pgdat->per_cpu_nodestats = NULL; -#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP - get_pfn_range_for_nid(nid, &start_pfn, &end_pfn); - pr_info("Initmem setup node %d [mem %#018Lx-%#018Lx]\n", nid, - (u64)start_pfn << PAGE_SHIFT, - end_pfn ? ((u64)end_pfn << PAGE_SHIFT) - 1 : 0); -#else - start_pfn = node_start_pfn; -#endif + if (!compat) { + get_pfn_range_for_nid(nid, &start_pfn, &end_pfn); + pr_info("Initmem setup node %d [mem %#018Lx-%#018Lx]\n", nid, + (u64)start_pfn << PAGE_SHIFT, + end_pfn ? ((u64)end_pfn << PAGE_SHIFT) - 1 : 0); + } else { + start_pfn = node_start_pfn; + } calculate_node_totalpages(pgdat, start_pfn, end_pfn, - zones_size, zholes_size); + zones_size, zholes_size, compat); alloc_node_mem_map(pgdat); pgdat_set_deferred_range(pgdat); @@ -6992,6 +7005,14 @@ void __init free_area_init_node(int nid, unsigned long *zones_size, free_area_init_core(pgdat); } +void __init free_area_init_node(int nid, unsigned long *zones_size, + unsigned long node_start_pfn, + unsigned long *zholes_size) +{ + __free_area_init_node(nid, zones_size, node_start_pfn, zholes_size, + true); +} + #if !defined(CONFIG_FLAT_NODE_MEM_MAP) /* * Initialize all valid struct pages in the range [spfn, epfn) and mark them @@ -7075,8 +7096,6 @@ static inline void __init init_unavailable_mem(void) } #endif /* !CONFIG_FLAT_NODE_MEM_MAP */ -#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP - #if MAX_NUMNODES > 1 /* * Figure out the number of possible node ids. @@ -7505,8 +7524,8 @@ void __init free_area_init_nodes(unsigned long *max_zone_pfn) init_unavailable_mem(); for_each_online_node(nid) { pg_data_t *pgdat = NODE_DATA(nid); - free_area_init_node(nid, NULL, - find_min_pfn_for_node(nid), NULL); + __free_area_init_node(nid, NULL, + find_min_pfn_for_node(nid), NULL, false); /* Any memory on that node */ if (pgdat->node_present_pages) @@ -7571,8 +7590,6 @@ static int __init cmdline_parse_movablecore(char *p) early_param("kernelcore", cmdline_parse_kernelcore); early_param("movablecore", cmdline_parse_movablecore); -#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ - void adjust_managed_page_count(struct page *page, long count) { atomic_long_add(count, &page_zone(page)->managed_pages); -- cgit v1.2.3 From fa3354e4ea39e97af906c05551a36396541d70b4 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Wed, 3 Jun 2020 15:57:06 -0700 Subject: mm: free_area_init: use maximal zone PFNs rather than zone sizes Currently, architectures that use free_area_init() to initialize memory map and node and zone structures need to calculate zone and hole sizes. We can use free_area_init_nodes() instead and let it detect the zone boundaries while the architectures will only have to supply the possible limits for the zones. Signed-off-by: Mike Rapoport Signed-off-by: Andrew Morton Tested-by: Hoan Tran [arm64] Reviewed-by: Baoquan He Cc: Brian Cain Cc: Catalin Marinas Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Ungerer Cc: Guan Xuetao Cc: Guo Ren Cc: Heiko Carstens Cc: Helge Deller Cc: "James E.J. Bottomley" Cc: Jonathan Corbet Cc: Ley Foon Tan Cc: Mark Salter Cc: Matt Turner Cc: Max Filippov Cc: Michael Ellerman Cc: Michal Hocko Cc: Michal Simek Cc: Nick Hu Cc: Paul Walmsley Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Stafford Horne Cc: Thomas Bogendoerfer Cc: Tony Luck Cc: Vineet Gupta Cc: Yoshinori Sato Link: http://lkml.kernel.org/r/20200412194859.12663-5-rppt@kernel.org Signed-off-by: Linus Torvalds --- arch/alpha/mm/init.c | 16 ++++++---------- arch/c6x/mm/init.c | 8 +++----- arch/h8300/mm/init.c | 6 +++--- arch/hexagon/mm/init.c | 6 +++--- arch/m68k/mm/init.c | 6 +++--- arch/m68k/mm/mcfmmu.c | 9 +++------ arch/nds32/mm/init.c | 11 ++++------- arch/nios2/mm/init.c | 8 +++----- arch/openrisc/mm/init.c | 9 +++------ arch/um/kernel/mem.c | 12 ++++-------- include/linux/mm.h | 2 +- mm/page_alloc.c | 5 ++--- 12 files changed, 38 insertions(+), 60 deletions(-) (limited to 'include') diff --git a/arch/alpha/mm/init.c b/arch/alpha/mm/init.c index 12e218d3792a..667cd21393b5 100644 --- a/arch/alpha/mm/init.c +++ b/arch/alpha/mm/init.c @@ -243,21 +243,17 @@ callback_init(void * kernel_end) */ void __init paging_init(void) { - unsigned long zones_size[MAX_NR_ZONES] = {0, }; - unsigned long dma_pfn, high_pfn; + unsigned long max_zone_pfn[MAX_NR_ZONES] = {0, }; + unsigned long dma_pfn; dma_pfn = virt_to_phys((char *)MAX_DMA_ADDRESS) >> PAGE_SHIFT; - high_pfn = max_pfn = max_low_pfn; + max_pfn = max_low_pfn; - if (dma_pfn >= high_pfn) - zones_size[ZONE_DMA] = high_pfn; - else { - zones_size[ZONE_DMA] = dma_pfn; - zones_size[ZONE_NORMAL] = high_pfn - dma_pfn; - } + max_zone_pfn[ZONE_DMA] = dma_pfn; + max_zone_pfn[ZONE_NORMAL] = max_pfn; /* Initialize mem_map[]. */ - free_area_init(zones_size); + free_area_init(max_zone_pfn); /* Initialize the kernel's ZERO_PGE. */ memset((void *)ZERO_PGE, 0, PAGE_SIZE); diff --git a/arch/c6x/mm/init.c b/arch/c6x/mm/init.c index 9b374393a8f4..a97e51a3e26d 100644 --- a/arch/c6x/mm/init.c +++ b/arch/c6x/mm/init.c @@ -33,7 +33,7 @@ EXPORT_SYMBOL(empty_zero_page); void __init paging_init(void) { struct pglist_data *pgdat = NODE_DATA(0); - unsigned long zones_size[MAX_NR_ZONES] = {0, }; + unsigned long max_zone_pfn[MAX_NR_ZONES] = {0, }; empty_zero_page = (unsigned long) memblock_alloc(PAGE_SIZE, PAGE_SIZE); @@ -49,11 +49,9 @@ void __init paging_init(void) /* * Define zones */ - zones_size[ZONE_NORMAL] = (memory_end - PAGE_OFFSET) >> PAGE_SHIFT; - pgdat->node_zones[ZONE_NORMAL].zone_start_pfn = - __pa(PAGE_OFFSET) >> PAGE_SHIFT; + max_zone_pfn[ZONE_NORMAL] = memory_end >> PAGE_SHIFT; - free_area_init(zones_size); + free_area_init(max_zone_pfn); } void __init mem_init(void) diff --git a/arch/h8300/mm/init.c b/arch/h8300/mm/init.c index 1eab16b1a0bc..27a0020e3771 100644 --- a/arch/h8300/mm/init.c +++ b/arch/h8300/mm/init.c @@ -83,10 +83,10 @@ void __init paging_init(void) start_mem, end_mem); { - unsigned long zones_size[MAX_NR_ZONES] = {0, }; + unsigned long max_zone_pfn[MAX_NR_ZONES] = {0, }; - zones_size[ZONE_NORMAL] = (end_mem - PAGE_OFFSET) >> PAGE_SHIFT; - free_area_init(zones_size); + max_zone_pfn[ZONE_NORMAL] = end_mem >> PAGE_SHIFT; + free_area_init(max_zone_pfn); } } diff --git a/arch/hexagon/mm/init.c b/arch/hexagon/mm/init.c index c961773a6fff..f2e6c868e477 100644 --- a/arch/hexagon/mm/init.c +++ b/arch/hexagon/mm/init.c @@ -91,7 +91,7 @@ void sync_icache_dcache(pte_t pte) */ void __init paging_init(void) { - unsigned long zones_sizes[MAX_NR_ZONES] = {0, }; + unsigned long max_zone_pfn[MAX_NR_ZONES] = {0, }; /* * This is not particularly well documented anywhere, but @@ -101,9 +101,9 @@ void __init paging_init(void) * adjust accordingly. */ - zones_sizes[ZONE_NORMAL] = max_low_pfn; + max_zone_pfn[ZONE_NORMAL] = max_low_pfn; - free_area_init(zones_sizes); /* sets up the zonelists and mem_map */ + free_area_init(max_zone_pfn); /* sets up the zonelists and mem_map */ /* * Start of high memory area. Will probably need something more diff --git a/arch/m68k/mm/init.c b/arch/m68k/mm/init.c index b88d510d4fe3..6d3147662ff2 100644 --- a/arch/m68k/mm/init.c +++ b/arch/m68k/mm/init.c @@ -84,7 +84,7 @@ void __init paging_init(void) * page_alloc get different views of the world. */ unsigned long end_mem = memory_end & PAGE_MASK; - unsigned long zones_size[MAX_NR_ZONES] = { 0, }; + unsigned long max_zone_pfn[MAX_NR_ZONES] = { 0, }; high_memory = (void *) end_mem; @@ -98,8 +98,8 @@ void __init paging_init(void) */ set_fs (USER_DS); - zones_size[ZONE_DMA] = (end_mem - PAGE_OFFSET) >> PAGE_SHIFT; - free_area_init(zones_size); + max_zone_pfn[ZONE_DMA] = end_mem >> PAGE_SHIFT; + free_area_init(max_zone_pfn); } #endif /* CONFIG_MMU */ diff --git a/arch/m68k/mm/mcfmmu.c b/arch/m68k/mm/mcfmmu.c index 0ea375607767..80064e6d064f 100644 --- a/arch/m68k/mm/mcfmmu.c +++ b/arch/m68k/mm/mcfmmu.c @@ -39,7 +39,7 @@ void __init paging_init(void) pte_t *pg_table; unsigned long address, size; unsigned long next_pgtable, bootmem_end; - unsigned long zones_size[MAX_NR_ZONES]; + unsigned long max_zone_pfn[MAX_NR_ZONES] = { 0 }; enum zone_type zone; int i; @@ -80,11 +80,8 @@ void __init paging_init(void) } current->mm = NULL; - - for (zone = 0; zone < MAX_NR_ZONES; zone++) - zones_size[zone] = 0x0; - zones_size[ZONE_DMA] = num_pages; - free_area_init(zones_size); + max_zone_pfn[ZONE_DMA] = PFN_DOWN(_ramend); + free_area_init(max_zone_pfn); } int cf_tlb_miss(struct pt_regs *regs, int write, int dtlb, int extension_word) diff --git a/arch/nds32/mm/init.c b/arch/nds32/mm/init.c index 0be3833f6814..91147cca4b64 100644 --- a/arch/nds32/mm/init.c +++ b/arch/nds32/mm/init.c @@ -31,16 +31,13 @@ EXPORT_SYMBOL(empty_zero_page); static void __init zone_sizes_init(void) { - unsigned long zones_size[MAX_NR_ZONES]; + unsigned long max_zone_pfn[MAX_NR_ZONES] = { 0 }; - /* Clear the zone sizes */ - memset(zones_size, 0, sizeof(zones_size)); - - zones_size[ZONE_NORMAL] = max_low_pfn; + max_zone_pfn[ZONE_NORMAL] = max_low_pfn; #ifdef CONFIG_HIGHMEM - zones_size[ZONE_HIGHMEM] = max_pfn; + max_zone_pfn[ZONE_HIGHMEM] = max_pfn; #endif - free_area_init(zones_size); + free_area_init(max_zone_pfn); } diff --git a/arch/nios2/mm/init.c b/arch/nios2/mm/init.c index 2c609c2516b2..9afca77d10b1 100644 --- a/arch/nios2/mm/init.c +++ b/arch/nios2/mm/init.c @@ -46,17 +46,15 @@ pgd_t *pgd_current; */ void __init paging_init(void) { - unsigned long zones_size[MAX_NR_ZONES]; - - memset(zones_size, 0, sizeof(zones_size)); + unsigned long max_zone_pfn[MAX_NR_ZONES] = { 0 }; pagetable_init(); pgd_current = swapper_pg_dir; - zones_size[ZONE_NORMAL] = max_mapnr; + max_zone_pfn[ZONE_NORMAL] = max_mapnr; /* pass the memory from the bootmem allocator to the main allocator */ - free_area_init(zones_size); + free_area_init(max_zone_pfn); flush_dcache_range((unsigned long)empty_zero_page, (unsigned long)empty_zero_page + PAGE_SIZE); diff --git a/arch/openrisc/mm/init.c b/arch/openrisc/mm/init.c index 1f87b524db78..f94fe6d3f499 100644 --- a/arch/openrisc/mm/init.c +++ b/arch/openrisc/mm/init.c @@ -45,17 +45,14 @@ DEFINE_PER_CPU(struct mmu_gather, mmu_gathers); static void __init zone_sizes_init(void) { - unsigned long zones_size[MAX_NR_ZONES]; - - /* Clear the zone sizes */ - memset(zones_size, 0, sizeof(zones_size)); + unsigned long max_zone_pfn[MAX_NR_ZONES] = { 0 }; /* * We use only ZONE_NORMAL */ - zones_size[ZONE_NORMAL] = max_low_pfn; + max_zone_pfn[ZONE_NORMAL] = max_low_pfn; - free_area_init(zones_size); + free_area_init(max_zone_pfn); } extern const char _s_kernel_ro[], _e_kernel_ro[]; diff --git a/arch/um/kernel/mem.c b/arch/um/kernel/mem.c index 30885d0b94ac..401b22f14743 100644 --- a/arch/um/kernel/mem.c +++ b/arch/um/kernel/mem.c @@ -158,8 +158,8 @@ static void __init fixaddr_user_init( void) void __init paging_init(void) { - unsigned long zones_size[MAX_NR_ZONES], vaddr; - int i; + unsigned long max_zone_pfn[MAX_NR_ZONES] = { 0 }; + unsigned long vaddr; empty_zero_page = (unsigned long *) memblock_alloc_low(PAGE_SIZE, PAGE_SIZE); @@ -167,12 +167,8 @@ void __init paging_init(void) panic("%s: Failed to allocate %lu bytes align=%lx\n", __func__, PAGE_SIZE, PAGE_SIZE); - for (i = 0; i < ARRAY_SIZE(zones_size); i++) - zones_size[i] = 0; - - zones_size[ZONE_NORMAL] = (end_iomem >> PAGE_SHIFT) - - (uml_physmem >> PAGE_SHIFT); - free_area_init(zones_size); + max_zone_pfn[ZONE_NORMAL] = end_iomem >> PAGE_SHIFT; + free_area_init(max_zone_pfn); /* * Fixed mappings, only the page table structure has to be diff --git a/include/linux/mm.h b/include/linux/mm.h index 5f15d8723167..788704977de0 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2329,7 +2329,7 @@ static inline spinlock_t *pud_lock(struct mm_struct *mm, pud_t *pud) } extern void __init pagecache_init(void); -extern void free_area_init(unsigned long * zones_size); +extern void free_area_init(unsigned long * max_zone_pfn); extern void __init free_area_init_node(int nid, unsigned long * zones_size, unsigned long zone_start_pfn, unsigned long *zholes_size); extern void free_initmem(void); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 430e35384b78..cf420e947d9c 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -7712,11 +7712,10 @@ void __init set_dma_reserve(unsigned long new_dma_reserve) dma_reserve = new_dma_reserve; } -void __init free_area_init(unsigned long *zones_size) +void __init free_area_init(unsigned long *max_zone_pfn) { init_unavailable_mem(); - free_area_init_node(0, zones_size, - __pa(PAGE_OFFSET) >> PAGE_SHIFT, NULL); + free_area_init_nodes(max_zone_pfn); } static int page_alloc_cpu_dead(unsigned int cpu) -- cgit v1.2.3 From 9691a071aa26a21fc8dac804a2b98d3c24f76f9a Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Wed, 3 Jun 2020 15:57:10 -0700 Subject: mm: use free_area_init() instead of free_area_init_nodes() free_area_init() has effectively became a wrapper for free_area_init_nodes() and there is no point of keeping it. Still free_area_init() name is shorter and more general as it does not imply necessity to initialize multiple nodes. Rename free_area_init_nodes() to free_area_init(), update the callers and drop old version of free_area_init(). Signed-off-by: Mike Rapoport Signed-off-by: Andrew Morton Tested-by: Hoan Tran [arm64] Reviewed-by: Baoquan He Acked-by: Catalin Marinas Cc: Brian Cain Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Ungerer Cc: Guan Xuetao Cc: Guo Ren Cc: Heiko Carstens Cc: Helge Deller Cc: "James E.J. Bottomley" Cc: Jonathan Corbet Cc: Ley Foon Tan Cc: Mark Salter Cc: Matt Turner Cc: Max Filippov Cc: Michael Ellerman Cc: Michal Hocko Cc: Michal Simek Cc: Nick Hu Cc: Paul Walmsley Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Stafford Horne Cc: Thomas Bogendoerfer Cc: Tony Luck Cc: Vineet Gupta Cc: Yoshinori Sato Link: http://lkml.kernel.org/r/20200412194859.12663-6-rppt@kernel.org Signed-off-by: Linus Torvalds --- arch/arm64/mm/init.c | 2 +- arch/ia64/mm/contig.c | 2 +- arch/ia64/mm/discontig.c | 2 +- arch/microblaze/mm/init.c | 2 +- arch/mips/loongson64/numa.c | 2 +- arch/mips/mm/init.c | 2 +- arch/mips/sgi-ip27/ip27-memory.c | 2 +- arch/powerpc/mm/mem.c | 2 +- arch/riscv/mm/init.c | 2 +- arch/s390/mm/init.c | 2 +- arch/sh/mm/init.c | 2 +- arch/sparc/mm/init_64.c | 2 +- arch/x86/mm/init.c | 2 +- include/linux/mm.h | 7 +++---- mm/page_alloc.c | 10 ++-------- 15 files changed, 18 insertions(+), 25 deletions(-) (limited to 'include') diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index d2df416b840e..5dae97f2f628 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -206,7 +206,7 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max) #endif max_zone_pfns[ZONE_NORMAL] = max; - free_area_init_nodes(max_zone_pfns); + free_area_init(max_zone_pfns); } #else diff --git a/arch/ia64/mm/contig.c b/arch/ia64/mm/contig.c index 5b00dc3898e1..8786fa5c7612 100644 --- a/arch/ia64/mm/contig.c +++ b/arch/ia64/mm/contig.c @@ -210,6 +210,6 @@ paging_init (void) printk("Virtual mem_map starts at 0x%p\n", mem_map); } #endif /* !CONFIG_VIRTUAL_MEM_MAP */ - free_area_init_nodes(max_zone_pfns); + free_area_init(max_zone_pfns); zero_page_memmap_ptr = virt_to_page(ia64_imva(empty_zero_page)); } diff --git a/arch/ia64/mm/discontig.c b/arch/ia64/mm/discontig.c index 4f33f6e7e206..dd8284bcbf16 100644 --- a/arch/ia64/mm/discontig.c +++ b/arch/ia64/mm/discontig.c @@ -627,7 +627,7 @@ void __init paging_init(void) max_zone_pfns[ZONE_DMA32] = max_dma; #endif max_zone_pfns[ZONE_NORMAL] = max_pfn; - free_area_init_nodes(max_zone_pfns); + free_area_init(max_zone_pfns); zero_page_memmap_ptr = virt_to_page(ia64_imva(empty_zero_page)); } diff --git a/arch/microblaze/mm/init.c b/arch/microblaze/mm/init.c index 1ffbfa96b9b8..dcaa53d11339 100644 --- a/arch/microblaze/mm/init.c +++ b/arch/microblaze/mm/init.c @@ -112,7 +112,7 @@ static void __init paging_init(void) #endif /* We don't have holes in memory map */ - free_area_init_nodes(zones_size); + free_area_init(zones_size); } void __init setup_memory(void) diff --git a/arch/mips/loongson64/numa.c b/arch/mips/loongson64/numa.c index 1ae072df4831..901f5be5ee76 100644 --- a/arch/mips/loongson64/numa.c +++ b/arch/mips/loongson64/numa.c @@ -247,7 +247,7 @@ void __init paging_init(void) zones_size[ZONE_DMA32] = MAX_DMA32_PFN; #endif zones_size[ZONE_NORMAL] = max_low_pfn; - free_area_init_nodes(zones_size); + free_area_init(zones_size); } void __init mem_init(void) diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c index 79684000de0e..19719e8b41a5 100644 --- a/arch/mips/mm/init.c +++ b/arch/mips/mm/init.c @@ -418,7 +418,7 @@ void __init paging_init(void) } #endif - free_area_init_nodes(max_zone_pfns); + free_area_init(max_zone_pfns); } #ifdef CONFIG_64BIT diff --git a/arch/mips/sgi-ip27/ip27-memory.c b/arch/mips/sgi-ip27/ip27-memory.c index a45691e6ab90..1213215ea965 100644 --- a/arch/mips/sgi-ip27/ip27-memory.c +++ b/arch/mips/sgi-ip27/ip27-memory.c @@ -419,7 +419,7 @@ void __init paging_init(void) pagetable_init(); zones_size[ZONE_NORMAL] = max_low_pfn; - free_area_init_nodes(zones_size); + free_area_init(zones_size); } void __init mem_init(void) diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 041ed7cfd341..0fcea21f26b4 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -271,7 +271,7 @@ void __init paging_init(void) max_zone_pfns[ZONE_HIGHMEM] = max_pfn; #endif - free_area_init_nodes(max_zone_pfns); + free_area_init(max_zone_pfns); mark_nonram_nosave(); } diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index 736de6c8739f..6168b1985b77 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -39,7 +39,7 @@ static void __init zone_sizes_init(void) #endif max_zone_pfns[ZONE_NORMAL] = max_low_pfn; - free_area_init_nodes(max_zone_pfns); + free_area_init(max_zone_pfns); } static void setup_zero_page(void) diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c index 87b2d024e75a..b11bcf4da531 100644 --- a/arch/s390/mm/init.c +++ b/arch/s390/mm/init.c @@ -122,7 +122,7 @@ void __init paging_init(void) memset(max_zone_pfns, 0, sizeof(max_zone_pfns)); max_zone_pfns[ZONE_DMA] = PFN_DOWN(MAX_DMA_ADDRESS); max_zone_pfns[ZONE_NORMAL] = max_low_pfn; - free_area_init_nodes(max_zone_pfns); + free_area_init(max_zone_pfns); } void mark_rodata_ro(void) diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c index 8d2a68aea1fc..628f461b8993 100644 --- a/arch/sh/mm/init.c +++ b/arch/sh/mm/init.c @@ -334,7 +334,7 @@ void __init paging_init(void) memset(max_zone_pfns, 0, sizeof(max_zone_pfns)); max_zone_pfns[ZONE_NORMAL] = max_low_pfn; - free_area_init_nodes(max_zone_pfns); + free_area_init(max_zone_pfns); } unsigned int mem_init_done = 0; diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c index 1cf0d666dea3..79d3c5e0802e 100644 --- a/arch/sparc/mm/init_64.c +++ b/arch/sparc/mm/init_64.c @@ -2488,7 +2488,7 @@ void __init paging_init(void) max_zone_pfns[ZONE_NORMAL] = end_pfn; - free_area_init_nodes(max_zone_pfns); + free_area_init(max_zone_pfns); } printk("Booting Linux...\n"); diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index a573a3e63f02..1decb645dac0 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -947,7 +947,7 @@ void __init zone_sizes_init(void) max_zone_pfns[ZONE_HIGHMEM] = max_pfn; #endif - free_area_init_nodes(max_zone_pfns); + free_area_init(max_zone_pfns); } __visible DEFINE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate) = { diff --git a/include/linux/mm.h b/include/linux/mm.h index 788704977de0..ff2c19e14c1e 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2329,7 +2329,6 @@ static inline spinlock_t *pud_lock(struct mm_struct *mm, pud_t *pud) } extern void __init pagecache_init(void); -extern void free_area_init(unsigned long * max_zone_pfn); extern void __init free_area_init_node(int nid, unsigned long * zones_size, unsigned long zone_start_pfn, unsigned long *zholes_size); extern void free_initmem(void); @@ -2410,21 +2409,21 @@ static inline unsigned long get_num_physpages(void) * * An architecture is expected to register range of page frames backed by * physical memory with memblock_add[_node]() before calling - * free_area_init_nodes() passing in the PFN each zone ends at. At a basic + * free_area_init() passing in the PFN each zone ends at. At a basic * usage, an architecture is expected to do something like * * unsigned long max_zone_pfns[MAX_NR_ZONES] = {max_dma, max_normal_pfn, * max_highmem_pfn}; * for_each_valid_physical_page_range() * memblock_add_node(base, size, nid) - * free_area_init_nodes(max_zone_pfns); + * free_area_init(max_zone_pfns); * * free_bootmem_with_active_regions() calls free_bootmem_node() for each * registered physical page range. Similarly * sparse_memory_present_with_active_regions() calls memory_present() for * each range when SPARSEMEM is enabled. */ -extern void free_area_init_nodes(unsigned long *max_zone_pfn); +void free_area_init(unsigned long *max_zone_pfn); unsigned long node_map_pfn_alignment(void); unsigned long __absent_pages_in_range(int nid, unsigned long start_pfn, unsigned long end_pfn); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index cf420e947d9c..644a59d17318 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -7440,7 +7440,7 @@ static void check_for_memory(pg_data_t *pgdat, int nid) } /** - * free_area_init_nodes - Initialise all pg_data_t and zone data + * free_area_init - Initialise all pg_data_t and zone data * @max_zone_pfn: an array of max PFNs for each zone * * This will call free_area_init_node() for each active node in the system. @@ -7452,7 +7452,7 @@ static void check_for_memory(pg_data_t *pgdat, int nid) * starts where the previous one ended. For example, ZONE_DMA32 starts * at arch_max_dma_pfn. */ -void __init free_area_init_nodes(unsigned long *max_zone_pfn) +void __init free_area_init(unsigned long *max_zone_pfn) { unsigned long start_pfn, end_pfn; int i, nid; @@ -7712,12 +7712,6 @@ void __init set_dma_reserve(unsigned long new_dma_reserve) dma_reserve = new_dma_reserve; } -void __init free_area_init(unsigned long *max_zone_pfn) -{ - init_unavailable_mem(); - free_area_init_nodes(max_zone_pfn); -} - static int page_alloc_cpu_dead(unsigned int cpu) { -- cgit v1.2.3 From 51930df5801e4da60e962ea52b811634d257a148 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Wed, 3 Jun 2020 15:58:03 -0700 Subject: mm: free_area_init: allow defining max_zone_pfn in descending order Some architectures (e.g. ARC) have the ZONE_HIGHMEM zone below the ZONE_NORMAL. Allowing free_area_init() parse max_zone_pfn array even it is sorted in descending order allows using free_area_init() on such architectures. Add top -> down traversal of max_zone_pfn array in free_area_init() and use the latter in ARC node/zone initialization. [rppt@kernel.org: ARC fix] Link: http://lkml.kernel.org/r/20200504153901.GM14260@kernel.org [rppt@linux.ibm.com: arc: free_area_init(): take into account PAE40 mode] Link: http://lkml.kernel.org/r/20200507205900.GH683243@linux.ibm.com [akpm@linux-foundation.org: declare arch_has_descending_max_zone_pfns()] Signed-off-by: Mike Rapoport Signed-off-by: Andrew Morton Tested-by: Hoan Tran [arm64] Reviewed-by: Baoquan He Cc: Brian Cain Cc: Catalin Marinas Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Ungerer Cc: Guan Xuetao Cc: Guo Ren Cc: Heiko Carstens Cc: Helge Deller Cc: "James E.J. Bottomley" Cc: Jonathan Corbet Cc: Ley Foon Tan Cc: Mark Salter Cc: Matt Turner Cc: Max Filippov Cc: Michael Ellerman Cc: Michal Hocko Cc: Michal Simek Cc: Nick Hu Cc: Paul Walmsley Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Stafford Horne Cc: Thomas Bogendoerfer Cc: Tony Luck Cc: Vineet Gupta Cc: Yoshinori Sato Cc: Guenter Roeck Link: http://lkml.kernel.org/r/20200412194859.12663-18-rppt@kernel.org Signed-off-by: Linus Torvalds --- arch/arc/mm/init.c | 41 ++++++++++++----------------------------- include/linux/mm.h | 1 + mm/page_alloc.c | 26 +++++++++++++++++++++----- 3 files changed, 34 insertions(+), 34 deletions(-) (limited to 'include') diff --git a/arch/arc/mm/init.c b/arch/arc/mm/init.c index 0920c969c466..e7bdc2ac1c87 100644 --- a/arch/arc/mm/init.c +++ b/arch/arc/mm/init.c @@ -63,11 +63,13 @@ void __init early_init_dt_add_memory_arch(u64 base, u64 size) low_mem_sz = size; in_use = 1; + memblock_add_node(base, size, 0); } else { #ifdef CONFIG_HIGHMEM high_mem_start = base; high_mem_sz = size; in_use = 1; + memblock_add_node(base, size, 1); #endif } @@ -75,6 +77,11 @@ void __init early_init_dt_add_memory_arch(u64 base, u64 size) base, TO_MB(size), !in_use ? "Not used":""); } +bool arch_has_descending_max_zone_pfns(void) +{ + return !IS_ENABLED(CONFIG_ARC_HAS_PAE40); +} + /* * First memory setup routine called from setup_arch() * 1. setup swapper's mm @init_mm @@ -83,8 +90,7 @@ void __init early_init_dt_add_memory_arch(u64 base, u64 size) */ void __init setup_arch_memory(void) { - unsigned long zones_size[MAX_NR_ZONES]; - unsigned long zones_holes[MAX_NR_ZONES]; + unsigned long max_zone_pfn[MAX_NR_ZONES] = { 0 }; init_mm.start_code = (unsigned long)_text; init_mm.end_code = (unsigned long)_etext; @@ -115,7 +121,6 @@ void __init setup_arch_memory(void) * the crash */ - memblock_add_node(low_mem_start, low_mem_sz, 0); memblock_reserve(CONFIG_LINUX_LINK_BASE, __pa(_end) - CONFIG_LINUX_LINK_BASE); @@ -133,22 +138,7 @@ void __init setup_arch_memory(void) memblock_dump_all(); /*----------------- node/zones setup --------------------------*/ - memset(zones_size, 0, sizeof(zones_size)); - memset(zones_holes, 0, sizeof(zones_holes)); - - zones_size[ZONE_NORMAL] = max_low_pfn - min_low_pfn; - zones_holes[ZONE_NORMAL] = 0; - - /* - * We can't use the helper free_area_init(zones[]) because it uses - * PAGE_OFFSET to compute the @min_low_pfn which would be wrong - * when our kernel doesn't start at PAGE_OFFSET, i.e. - * PAGE_OFFSET != CONFIG_LINUX_RAM_BASE - */ - free_area_init_node(0, /* node-id */ - zones_size, /* num pages per zone */ - min_low_pfn, /* first pfn of node */ - zones_holes); /* holes */ + max_zone_pfn[ZONE_NORMAL] = max_low_pfn; #ifdef CONFIG_HIGHMEM /* @@ -168,20 +158,13 @@ void __init setup_arch_memory(void) min_high_pfn = PFN_DOWN(high_mem_start); max_high_pfn = PFN_DOWN(high_mem_start + high_mem_sz); - zones_size[ZONE_NORMAL] = 0; - zones_holes[ZONE_NORMAL] = 0; - - zones_size[ZONE_HIGHMEM] = max_high_pfn - min_high_pfn; - zones_holes[ZONE_HIGHMEM] = 0; - - free_area_init_node(1, /* node-id */ - zones_size, /* num pages per zone */ - min_high_pfn, /* first pfn of node */ - zones_holes); /* holes */ + max_zone_pfn[ZONE_HIGHMEM] = max_high_pfn; high_memory = (void *)(min_high_pfn << PAGE_SHIFT); kmap_init(); #endif + + free_area_init(max_zone_pfn); } /* diff --git a/include/linux/mm.h b/include/linux/mm.h index ff2c19e14c1e..21cf171ae9de 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2473,6 +2473,7 @@ extern void setup_per_cpu_pageset(void); extern int min_free_kbytes; extern int watermark_boost_factor; extern int watermark_scale_factor; +extern bool arch_has_descending_max_zone_pfns(void); /* nommu.c */ extern atomic_long_t mmap_pages_allocated; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 1f7eff7120d7..36d93c73f2bb 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -7408,6 +7408,15 @@ static void check_for_memory(pg_data_t *pgdat, int nid) } } +/* + * Some architecturs, e.g. ARC may have ZONE_HIGHMEM below ZONE_NORMAL. For + * such cases we allow max_zone_pfn sorted in the descending order + */ +bool __weak arch_has_descending_max_zone_pfns(void) +{ + return false; +} + /** * free_area_init - Initialise all pg_data_t and zone data * @max_zone_pfn: an array of max PFNs for each zone @@ -7424,7 +7433,8 @@ static void check_for_memory(pg_data_t *pgdat, int nid) void __init free_area_init(unsigned long *max_zone_pfn) { unsigned long start_pfn, end_pfn; - int i, nid; + int i, nid, zone; + bool descending; /* Record where the zone boundaries are */ memset(arch_zone_lowest_possible_pfn, 0, @@ -7433,14 +7443,20 @@ void __init free_area_init(unsigned long *max_zone_pfn) sizeof(arch_zone_highest_possible_pfn)); start_pfn = find_min_pfn_with_active_regions(); + descending = arch_has_descending_max_zone_pfns(); for (i = 0; i < MAX_NR_ZONES; i++) { - if (i == ZONE_MOVABLE) + if (descending) + zone = MAX_NR_ZONES - i - 1; + else + zone = i; + + if (zone == ZONE_MOVABLE) continue; - end_pfn = max(max_zone_pfn[i], start_pfn); - arch_zone_lowest_possible_pfn[i] = start_pfn; - arch_zone_highest_possible_pfn[i] = end_pfn; + end_pfn = max(max_zone_pfn[zone], start_pfn); + arch_zone_lowest_possible_pfn[zone] = start_pfn; + arch_zone_highest_possible_pfn[zone] = end_pfn; start_pfn = end_pfn; } -- cgit v1.2.3 From bc9331a19d758706493cbebba67ca70382edddac Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Wed, 3 Jun 2020 15:58:09 -0700 Subject: mm: rename free_area_init_node() to free_area_init_memoryless_node() free_area_init_node() is only used by x86 to initialize a memory-less nodes. Make its name reflect this and drop all the function parameters except node ID as they are anyway zero. Signed-off-by: Mike Rapoport Signed-off-by: Andrew Morton Tested-by: Hoan Tran [arm64] Cc: Baoquan He Cc: Brian Cain Cc: Catalin Marinas Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Ungerer Cc: Guan Xuetao Cc: Guo Ren Cc: Heiko Carstens Cc: Helge Deller Cc: "James E.J. Bottomley" Cc: Jonathan Corbet Cc: Ley Foon Tan Cc: Mark Salter Cc: Matt Turner Cc: Max Filippov Cc: Michael Ellerman Cc: Michal Hocko Cc: Michal Simek Cc: Nick Hu Cc: Paul Walmsley Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Stafford Horne Cc: Thomas Bogendoerfer Cc: Tony Luck Cc: Vineet Gupta Cc: Yoshinori Sato Link: http://lkml.kernel.org/r/20200412194859.12663-19-rppt@kernel.org Signed-off-by: Linus Torvalds --- arch/x86/mm/numa.c | 5 +---- include/linux/mm.h | 9 +++------ mm/page_alloc.c | 7 ++----- 3 files changed, 6 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index fe024b2ac796..8ee952038c80 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -737,12 +737,9 @@ void __init x86_numa_init(void) static void __init init_memory_less_node(int nid) { - unsigned long zones_size[MAX_NR_ZONES] = {0}; - unsigned long zholes_size[MAX_NR_ZONES] = {0}; - /* Allocate and initialize node data. Memory-less node is now online.*/ alloc_node_data(nid); - free_area_init_node(nid, zones_size, 0, zholes_size); + free_area_init_memoryless_node(nid); /* * All zonelists will be built later in start_kernel() after per cpu diff --git a/include/linux/mm.h b/include/linux/mm.h index 21cf171ae9de..0d998c84231c 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2329,8 +2329,7 @@ static inline spinlock_t *pud_lock(struct mm_struct *mm, pud_t *pud) } extern void __init pagecache_init(void); -extern void __init free_area_init_node(int nid, unsigned long * zones_size, - unsigned long zone_start_pfn, unsigned long *zholes_size); +extern void __init free_area_init_memoryless_node(int nid); extern void free_initmem(void); /* @@ -2402,10 +2401,8 @@ static inline unsigned long get_num_physpages(void) /* * Using memblock node mappings, an architecture may initialise its - * zones, allocate the backing mem_map and account for memory holes in a more - * architecture independent manner. This is a substitute for creating the - * zone_sizes[] and zholes_size[] arrays and passing them to - * free_area_init_node() + * zones, allocate the backing mem_map and account for memory holes in an + * architecture independent manner. * * An architecture is expected to register range of page frames backed by * physical memory with memblock_add[_node]() before calling diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 36d93c73f2bb..cc96ecbe52f7 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -6974,12 +6974,9 @@ static void __init __free_area_init_node(int nid, unsigned long *zones_size, free_area_init_core(pgdat); } -void __init free_area_init_node(int nid, unsigned long *zones_size, - unsigned long node_start_pfn, - unsigned long *zholes_size) +void __init free_area_init_memoryless_node(int nid) { - __free_area_init_node(nid, zones_size, node_start_pfn, zholes_size, - true); + __free_area_init_node(nid, NULL, 0, NULL, false); } #if !defined(CONFIG_FLAT_NODE_MEM_MAP) -- cgit v1.2.3 From 4ca7be24eeb3198dffdae9472d7464c8b8cadadb Mon Sep 17 00:00:00 2001 From: Baoquan He Date: Wed, 3 Jun 2020 15:58:45 -0700 Subject: mm/page_alloc.c: remove unused free_bootmem_with_active_regions Since commit 397dc00e249ec64e10 ("mips: sgi-ip27: switch from DISCONTIGMEM to SPARSEMEM"), the last caller of free_bootmem_with_active_regions() was gone. Now no user calls it any more. Let's remove it. Signed-off-by: Baoquan He Signed-off-by: Andrew Morton Reviewed-by: David Hildenbrand Acked-by: Michal Hocko Link: http://lkml.kernel.org/r/20200402143455.5145-1-bhe@redhat.com Signed-off-by: Linus Torvalds --- include/linux/mm.h | 4 ---- mm/page_alloc.c | 25 ------------------------- 2 files changed, 29 deletions(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index 0d998c84231c..4141ebcb3a65 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2415,8 +2415,6 @@ static inline unsigned long get_num_physpages(void) * memblock_add_node(base, size, nid) * free_area_init(max_zone_pfns); * - * free_bootmem_with_active_regions() calls free_bootmem_node() for each - * registered physical page range. Similarly * sparse_memory_present_with_active_regions() calls memory_present() for * each range when SPARSEMEM is enabled. */ @@ -2429,8 +2427,6 @@ extern unsigned long absent_pages_in_range(unsigned long start_pfn, extern void get_pfn_range_for_nid(unsigned int nid, unsigned long *start_pfn, unsigned long *end_pfn); extern unsigned long find_min_pfn_with_active_regions(void); -extern void free_bootmem_with_active_regions(int nid, - unsigned long max_low_pfn); extern void sparse_memory_present_with_active_regions(int nid); #ifndef CONFIG_NEED_MULTIPLE_NODES diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 5207a9e86388..a1a4f883b7f5 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -6295,31 +6295,6 @@ void __meminit init_currently_empty_zone(struct zone *zone, zone->initialized = 1; } -/** - * free_bootmem_with_active_regions - Call memblock_free_early_nid for each active range - * @nid: The node to free memory on. If MAX_NUMNODES, all nodes are freed. - * @max_low_pfn: The highest PFN that will be passed to memblock_free_early_nid - * - * If an architecture guarantees that all ranges registered contain no holes - * and may be freed, this this function may be used instead of calling - * memblock_free_early_nid() manually. - */ -void __init free_bootmem_with_active_regions(int nid, unsigned long max_low_pfn) -{ - unsigned long start_pfn, end_pfn; - int i, this_nid; - - for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, &this_nid) { - start_pfn = min(start_pfn, max_low_pfn); - end_pfn = min(end_pfn, max_low_pfn); - - if (start_pfn < end_pfn) - memblock_free_early_nid(PFN_PHYS(start_pfn), - (end_pfn - start_pfn) << PAGE_SHIFT, - this_nid); - } -} - /** * sparse_memory_present_with_active_regions - Call memory_present for each active range * @nid: The node to call memory_present for. If MAX_NUMNODES, all nodes will be used. -- cgit v1.2.3 From 97a225e69a1f880886f33d2e65a7ace13f152caa Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Wed, 3 Jun 2020 15:59:01 -0700 Subject: mm/page_alloc: integrate classzone_idx and high_zoneidx classzone_idx is just different name for high_zoneidx now. So, integrate them and add some comment to struct alloc_context in order to reduce future confusion about the meaning of this variable. The accessor, ac_classzone_idx() is also removed since it isn't needed after integration. In addition to integration, this patch also renames high_zoneidx to highest_zoneidx since it represents more precise meaning. Signed-off-by: Joonsoo Kim Signed-off-by: Andrew Morton Reviewed-by: Baoquan He Acked-by: Vlastimil Babka Acked-by: David Rientjes Cc: Johannes Weiner Cc: Mel Gorman Cc: Michal Hocko Cc: Minchan Kim Cc: Ye Xiaolong Link: http://lkml.kernel.org/r/1587095923-7515-3-git-send-email-iamjoonsoo.kim@lge.com Signed-off-by: Linus Torvalds --- include/linux/compaction.h | 9 ++-- include/linux/mmzone.h | 12 ++--- include/trace/events/compaction.h | 22 ++++---- include/trace/events/vmscan.h | 14 +++-- mm/compaction.c | 64 +++++++++++------------ mm/internal.h | 21 +++++--- mm/memory_hotplug.c | 6 +-- mm/oom_kill.c | 4 +- mm/page_alloc.c | 60 +++++++++++----------- mm/slab.c | 4 +- mm/slub.c | 4 +- mm/vmscan.c | 105 ++++++++++++++++++++------------------ 12 files changed, 175 insertions(+), 150 deletions(-) (limited to 'include') diff --git a/include/linux/compaction.h b/include/linux/compaction.h index 4b898cdbdf05..3ed2f22b588a 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -97,7 +97,7 @@ extern enum compact_result try_to_compact_pages(gfp_t gfp_mask, struct page **page); extern void reset_isolation_suitable(pg_data_t *pgdat); extern enum compact_result compaction_suitable(struct zone *zone, int order, - unsigned int alloc_flags, int classzone_idx); + unsigned int alloc_flags, int highest_zoneidx); extern void defer_compaction(struct zone *zone, int order); extern bool compaction_deferred(struct zone *zone, int order); @@ -182,7 +182,7 @@ bool compaction_zonelist_suitable(struct alloc_context *ac, int order, extern int kcompactd_run(int nid); extern void kcompactd_stop(int nid); -extern void wakeup_kcompactd(pg_data_t *pgdat, int order, int classzone_idx); +extern void wakeup_kcompactd(pg_data_t *pgdat, int order, int highest_zoneidx); #else static inline void reset_isolation_suitable(pg_data_t *pgdat) @@ -190,7 +190,7 @@ static inline void reset_isolation_suitable(pg_data_t *pgdat) } static inline enum compact_result compaction_suitable(struct zone *zone, int order, - int alloc_flags, int classzone_idx) + int alloc_flags, int highest_zoneidx) { return COMPACT_SKIPPED; } @@ -232,7 +232,8 @@ static inline void kcompactd_stop(int nid) { } -static inline void wakeup_kcompactd(pg_data_t *pgdat, int order, int classzone_idx) +static inline void wakeup_kcompactd(pg_data_t *pgdat, + int order, int highest_zoneidx) { } diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 0c575c3d7feb..cd8bd5f90552 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -699,13 +699,13 @@ typedef struct pglist_data { struct task_struct *kswapd; /* Protected by mem_hotplug_begin/end() */ int kswapd_order; - enum zone_type kswapd_classzone_idx; + enum zone_type kswapd_highest_zoneidx; int kswapd_failures; /* Number of 'reclaimed == 0' runs */ #ifdef CONFIG_COMPACTION int kcompactd_max_order; - enum zone_type kcompactd_classzone_idx; + enum zone_type kcompactd_highest_zoneidx; wait_queue_head_t kcompactd_wait; struct task_struct *kcompactd; #endif @@ -783,15 +783,15 @@ static inline bool pgdat_is_empty(pg_data_t *pgdat) void build_all_zonelists(pg_data_t *pgdat); void wakeup_kswapd(struct zone *zone, gfp_t gfp_mask, int order, - enum zone_type classzone_idx); + enum zone_type highest_zoneidx); bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark, - int classzone_idx, unsigned int alloc_flags, + int highest_zoneidx, unsigned int alloc_flags, long free_pages); bool zone_watermark_ok(struct zone *z, unsigned int order, - unsigned long mark, int classzone_idx, + unsigned long mark, int highest_zoneidx, unsigned int alloc_flags); bool zone_watermark_ok_safe(struct zone *z, unsigned int order, - unsigned long mark, int classzone_idx); + unsigned long mark, int highest_zoneidx); enum memmap_context { MEMMAP_EARLY, MEMMAP_HOTPLUG, diff --git a/include/trace/events/compaction.h b/include/trace/events/compaction.h index e5bf6ee4e814..54e5bf081171 100644 --- a/include/trace/events/compaction.h +++ b/include/trace/events/compaction.h @@ -314,40 +314,44 @@ TRACE_EVENT(mm_compaction_kcompactd_sleep, DECLARE_EVENT_CLASS(kcompactd_wake_template, - TP_PROTO(int nid, int order, enum zone_type classzone_idx), + TP_PROTO(int nid, int order, enum zone_type highest_zoneidx), - TP_ARGS(nid, order, classzone_idx), + TP_ARGS(nid, order, highest_zoneidx), TP_STRUCT__entry( __field(int, nid) __field(int, order) - __field(enum zone_type, classzone_idx) + __field(enum zone_type, highest_zoneidx) ), TP_fast_assign( __entry->nid = nid; __entry->order = order; - __entry->classzone_idx = classzone_idx; + __entry->highest_zoneidx = highest_zoneidx; ), + /* + * classzone_idx is previous name of the highest_zoneidx. + * Reason not to change it is the ABI requirement of the tracepoint. + */ TP_printk("nid=%d order=%d classzone_idx=%-8s", __entry->nid, __entry->order, - __print_symbolic(__entry->classzone_idx, ZONE_TYPE)) + __print_symbolic(__entry->highest_zoneidx, ZONE_TYPE)) ); DEFINE_EVENT(kcompactd_wake_template, mm_compaction_wakeup_kcompactd, - TP_PROTO(int nid, int order, enum zone_type classzone_idx), + TP_PROTO(int nid, int order, enum zone_type highest_zoneidx), - TP_ARGS(nid, order, classzone_idx) + TP_ARGS(nid, order, highest_zoneidx) ); DEFINE_EVENT(kcompactd_wake_template, mm_compaction_kcompactd_wake, - TP_PROTO(int nid, int order, enum zone_type classzone_idx), + TP_PROTO(int nid, int order, enum zone_type highest_zoneidx), - TP_ARGS(nid, order, classzone_idx) + TP_ARGS(nid, order, highest_zoneidx) ); #endif diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h index 74bb594ccb25..2070df64958e 100644 --- a/include/trace/events/vmscan.h +++ b/include/trace/events/vmscan.h @@ -265,7 +265,7 @@ TRACE_EVENT(mm_shrink_slab_end, ); TRACE_EVENT(mm_vmscan_lru_isolate, - TP_PROTO(int classzone_idx, + TP_PROTO(int highest_zoneidx, int order, unsigned long nr_requested, unsigned long nr_scanned, @@ -274,10 +274,10 @@ TRACE_EVENT(mm_vmscan_lru_isolate, isolate_mode_t isolate_mode, int lru), - TP_ARGS(classzone_idx, order, nr_requested, nr_scanned, nr_skipped, nr_taken, isolate_mode, lru), + TP_ARGS(highest_zoneidx, order, nr_requested, nr_scanned, nr_skipped, nr_taken, isolate_mode, lru), TP_STRUCT__entry( - __field(int, classzone_idx) + __field(int, highest_zoneidx) __field(int, order) __field(unsigned long, nr_requested) __field(unsigned long, nr_scanned) @@ -288,7 +288,7 @@ TRACE_EVENT(mm_vmscan_lru_isolate, ), TP_fast_assign( - __entry->classzone_idx = classzone_idx; + __entry->highest_zoneidx = highest_zoneidx; __entry->order = order; __entry->nr_requested = nr_requested; __entry->nr_scanned = nr_scanned; @@ -298,9 +298,13 @@ TRACE_EVENT(mm_vmscan_lru_isolate, __entry->lru = lru; ), + /* + * classzone is previous name of the highest_zoneidx. + * Reason not to change it is the ABI requirement of the tracepoint. + */ TP_printk("isolate_mode=%d classzone=%d order=%d nr_requested=%lu nr_scanned=%lu nr_skipped=%lu nr_taken=%lu lru=%s", __entry->isolate_mode, - __entry->classzone_idx, + __entry->highest_zoneidx, __entry->order, __entry->nr_requested, __entry->nr_scanned, diff --git a/mm/compaction.c b/mm/compaction.c index 8c2961100840..883355de4ace 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -1968,7 +1968,7 @@ static enum compact_result compact_finished(struct compact_control *cc) */ static enum compact_result __compaction_suitable(struct zone *zone, int order, unsigned int alloc_flags, - int classzone_idx, + int highest_zoneidx, unsigned long wmark_target) { unsigned long watermark; @@ -1981,7 +1981,7 @@ static enum compact_result __compaction_suitable(struct zone *zone, int order, * If watermarks for high-order allocation are already met, there * should be no need for compaction at all. */ - if (zone_watermark_ok(zone, order, watermark, classzone_idx, + if (zone_watermark_ok(zone, order, watermark, highest_zoneidx, alloc_flags)) return COMPACT_SUCCESS; @@ -1991,9 +1991,9 @@ static enum compact_result __compaction_suitable(struct zone *zone, int order, * watermark and alloc_flags have to match, or be more pessimistic than * the check in __isolate_free_page(). We don't use the direct * compactor's alloc_flags, as they are not relevant for freepage - * isolation. We however do use the direct compactor's classzone_idx to - * skip over zones where lowmem reserves would prevent allocation even - * if compaction succeeds. + * isolation. We however do use the direct compactor's highest_zoneidx + * to skip over zones where lowmem reserves would prevent allocation + * even if compaction succeeds. * For costly orders, we require low watermark instead of min for * compaction to proceed to increase its chances. * ALLOC_CMA is used, as pages in CMA pageblocks are considered @@ -2002,7 +2002,7 @@ static enum compact_result __compaction_suitable(struct zone *zone, int order, watermark = (order > PAGE_ALLOC_COSTLY_ORDER) ? low_wmark_pages(zone) : min_wmark_pages(zone); watermark += compact_gap(order); - if (!__zone_watermark_ok(zone, 0, watermark, classzone_idx, + if (!__zone_watermark_ok(zone, 0, watermark, highest_zoneidx, ALLOC_CMA, wmark_target)) return COMPACT_SKIPPED; @@ -2011,12 +2011,12 @@ static enum compact_result __compaction_suitable(struct zone *zone, int order, enum compact_result compaction_suitable(struct zone *zone, int order, unsigned int alloc_flags, - int classzone_idx) + int highest_zoneidx) { enum compact_result ret; int fragindex; - ret = __compaction_suitable(zone, order, alloc_flags, classzone_idx, + ret = __compaction_suitable(zone, order, alloc_flags, highest_zoneidx, zone_page_state(zone, NR_FREE_PAGES)); /* * fragmentation index determines if allocation failures are due to @@ -2057,8 +2057,8 @@ bool compaction_zonelist_suitable(struct alloc_context *ac, int order, * Make sure at least one zone would pass __compaction_suitable if we continue * retrying the reclaim. */ - for_each_zone_zonelist_nodemask(zone, z, ac->zonelist, ac->high_zoneidx, - ac->nodemask) { + for_each_zone_zonelist_nodemask(zone, z, ac->zonelist, + ac->highest_zoneidx, ac->nodemask) { unsigned long available; enum compact_result compact_result; @@ -2071,7 +2071,7 @@ bool compaction_zonelist_suitable(struct alloc_context *ac, int order, available = zone_reclaimable_pages(zone) / order; available += zone_page_state_snapshot(zone, NR_FREE_PAGES); compact_result = __compaction_suitable(zone, order, alloc_flags, - ac_classzone_idx(ac), available); + ac->highest_zoneidx, available); if (compact_result != COMPACT_SKIPPED) return true; } @@ -2102,7 +2102,7 @@ compact_zone(struct compact_control *cc, struct capture_control *capc) cc->migratetype = gfpflags_to_migratetype(cc->gfp_mask); ret = compaction_suitable(cc->zone, cc->order, cc->alloc_flags, - cc->classzone_idx); + cc->highest_zoneidx); /* Compaction is likely to fail */ if (ret == COMPACT_SUCCESS || ret == COMPACT_SKIPPED) return ret; @@ -2293,7 +2293,7 @@ out: static enum compact_result compact_zone_order(struct zone *zone, int order, gfp_t gfp_mask, enum compact_priority prio, - unsigned int alloc_flags, int classzone_idx, + unsigned int alloc_flags, int highest_zoneidx, struct page **capture) { enum compact_result ret; @@ -2305,7 +2305,7 @@ static enum compact_result compact_zone_order(struct zone *zone, int order, .mode = (prio == COMPACT_PRIO_ASYNC) ? MIGRATE_ASYNC : MIGRATE_SYNC_LIGHT, .alloc_flags = alloc_flags, - .classzone_idx = classzone_idx, + .highest_zoneidx = highest_zoneidx, .direct_compaction = true, .whole_zone = (prio == MIN_COMPACT_PRIORITY), .ignore_skip_hint = (prio == MIN_COMPACT_PRIORITY), @@ -2361,8 +2361,8 @@ enum compact_result try_to_compact_pages(gfp_t gfp_mask, unsigned int order, trace_mm_compaction_try_to_compact_pages(order, gfp_mask, prio); /* Compact each zone in the list */ - for_each_zone_zonelist_nodemask(zone, z, ac->zonelist, ac->high_zoneidx, - ac->nodemask) { + for_each_zone_zonelist_nodemask(zone, z, ac->zonelist, + ac->highest_zoneidx, ac->nodemask) { enum compact_result status; if (prio > MIN_COMPACT_PRIORITY @@ -2372,7 +2372,7 @@ enum compact_result try_to_compact_pages(gfp_t gfp_mask, unsigned int order, } status = compact_zone_order(zone, order, gfp_mask, prio, - alloc_flags, ac_classzone_idx(ac), capture); + alloc_flags, ac->highest_zoneidx, capture); rc = max(status, rc); /* The allocation should succeed, stop compacting */ @@ -2507,16 +2507,16 @@ static bool kcompactd_node_suitable(pg_data_t *pgdat) { int zoneid; struct zone *zone; - enum zone_type classzone_idx = pgdat->kcompactd_classzone_idx; + enum zone_type highest_zoneidx = pgdat->kcompactd_highest_zoneidx; - for (zoneid = 0; zoneid <= classzone_idx; zoneid++) { + for (zoneid = 0; zoneid <= highest_zoneidx; zoneid++) { zone = &pgdat->node_zones[zoneid]; if (!populated_zone(zone)) continue; if (compaction_suitable(zone, pgdat->kcompactd_max_order, 0, - classzone_idx) == COMPACT_CONTINUE) + highest_zoneidx) == COMPACT_CONTINUE) return true; } @@ -2534,16 +2534,16 @@ static void kcompactd_do_work(pg_data_t *pgdat) struct compact_control cc = { .order = pgdat->kcompactd_max_order, .search_order = pgdat->kcompactd_max_order, - .classzone_idx = pgdat->kcompactd_classzone_idx, + .highest_zoneidx = pgdat->kcompactd_highest_zoneidx, .mode = MIGRATE_SYNC_LIGHT, .ignore_skip_hint = false, .gfp_mask = GFP_KERNEL, }; trace_mm_compaction_kcompactd_wake(pgdat->node_id, cc.order, - cc.classzone_idx); + cc.highest_zoneidx); count_compact_event(KCOMPACTD_WAKE); - for (zoneid = 0; zoneid <= cc.classzone_idx; zoneid++) { + for (zoneid = 0; zoneid <= cc.highest_zoneidx; zoneid++) { int status; zone = &pgdat->node_zones[zoneid]; @@ -2592,16 +2592,16 @@ static void kcompactd_do_work(pg_data_t *pgdat) /* * Regardless of success, we are done until woken up next. But remember - * the requested order/classzone_idx in case it was higher/tighter than - * our current ones + * the requested order/highest_zoneidx in case it was higher/tighter + * than our current ones */ if (pgdat->kcompactd_max_order <= cc.order) pgdat->kcompactd_max_order = 0; - if (pgdat->kcompactd_classzone_idx >= cc.classzone_idx) - pgdat->kcompactd_classzone_idx = pgdat->nr_zones - 1; + if (pgdat->kcompactd_highest_zoneidx >= cc.highest_zoneidx) + pgdat->kcompactd_highest_zoneidx = pgdat->nr_zones - 1; } -void wakeup_kcompactd(pg_data_t *pgdat, int order, int classzone_idx) +void wakeup_kcompactd(pg_data_t *pgdat, int order, int highest_zoneidx) { if (!order) return; @@ -2609,8 +2609,8 @@ void wakeup_kcompactd(pg_data_t *pgdat, int order, int classzone_idx) if (pgdat->kcompactd_max_order < order) pgdat->kcompactd_max_order = order; - if (pgdat->kcompactd_classzone_idx > classzone_idx) - pgdat->kcompactd_classzone_idx = classzone_idx; + if (pgdat->kcompactd_highest_zoneidx > highest_zoneidx) + pgdat->kcompactd_highest_zoneidx = highest_zoneidx; /* * Pairs with implicit barrier in wait_event_freezable() @@ -2623,7 +2623,7 @@ void wakeup_kcompactd(pg_data_t *pgdat, int order, int classzone_idx) return; trace_mm_compaction_wakeup_kcompactd(pgdat->node_id, order, - classzone_idx); + highest_zoneidx); wake_up_interruptible(&pgdat->kcompactd_wait); } @@ -2644,7 +2644,7 @@ static int kcompactd(void *p) set_freezable(); pgdat->kcompactd_max_order = 0; - pgdat->kcompactd_classzone_idx = pgdat->nr_zones - 1; + pgdat->kcompactd_highest_zoneidx = pgdat->nr_zones - 1; while (!kthread_should_stop()) { unsigned long pflags; diff --git a/mm/internal.h b/mm/internal.h index 6220a5e6b3c7..b1f0afcbe016 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -127,10 +127,10 @@ extern pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address); * between functions involved in allocations, including the alloc_pages* * family of functions. * - * nodemask, migratetype and high_zoneidx are initialized only once in + * nodemask, migratetype and highest_zoneidx are initialized only once in * __alloc_pages_nodemask() and then never change. * - * zonelist, preferred_zone and classzone_idx are set first in + * zonelist, preferred_zone and highest_zoneidx are set first in * __alloc_pages_nodemask() for the fast path, and might be later changed * in __alloc_pages_slowpath(). All other functions pass the whole strucure * by a const pointer. @@ -140,12 +140,21 @@ struct alloc_context { nodemask_t *nodemask; struct zoneref *preferred_zoneref; int migratetype; - enum zone_type high_zoneidx; + + /* + * highest_zoneidx represents highest usable zone index of + * the allocation request. Due to the nature of the zone, + * memory on lower zone than the highest_zoneidx will be + * protected by lowmem_reserve[highest_zoneidx]. + * + * highest_zoneidx is also used by reclaim/compaction to limit + * the target zone since higher zone than this index cannot be + * usable for this allocation request. + */ + enum zone_type highest_zoneidx; bool spread_dirty_pages; }; -#define ac_classzone_idx(ac) (ac->high_zoneidx) - /* * Locate the struct page for both the matching buddy in our * pair (buddy1) and the combined O(n+1) page they form (page). @@ -224,7 +233,7 @@ struct compact_control { int order; /* order a direct compactor needs */ int migratetype; /* migratetype of direct compactor */ const unsigned int alloc_flags; /* alloc flags of a direct compactor */ - const int classzone_idx; /* zone index of a direct compactor */ + const int highest_zoneidx; /* zone index of a direct compactor */ enum migrate_mode mode; /* Async or sync migration mode */ bool ignore_skip_hint; /* Scan blocks even if marked skip */ bool no_set_skip_hint; /* Don't mark blocks for skipping */ diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index e67dc501576a..926ec704e835 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -879,13 +879,13 @@ static pg_data_t __ref *hotadd_new_pgdat(int nid, u64 start) } else { int cpu; /* - * Reset the nr_zones, order and classzone_idx before reuse. - * Note that kswapd will init kswapd_classzone_idx properly + * Reset the nr_zones, order and highest_zoneidx before reuse. + * Note that kswapd will init kswapd_highest_zoneidx properly * when it starts in the near future. */ pgdat->nr_zones = 0; pgdat->kswapd_order = 0; - pgdat->kswapd_classzone_idx = 0; + pgdat->kswapd_highest_zoneidx = 0; for_each_online_cpu(cpu) { struct per_cpu_nodestat *p; diff --git a/mm/oom_kill.c b/mm/oom_kill.c index dfc357614e56..4daedf7b91f6 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -254,7 +254,7 @@ static enum oom_constraint constrained_alloc(struct oom_control *oc) { struct zone *zone; struct zoneref *z; - enum zone_type high_zoneidx = gfp_zone(oc->gfp_mask); + enum zone_type highest_zoneidx = gfp_zone(oc->gfp_mask); bool cpuset_limited = false; int nid; @@ -294,7 +294,7 @@ static enum oom_constraint constrained_alloc(struct oom_control *oc) /* Check this allocation failure is caused by cpuset's wall function */ for_each_zone_zonelist_nodemask(zone, z, oc->zonelist, - high_zoneidx, oc->nodemask) + highest_zoneidx, oc->nodemask) if (!cpuset_zone_allowed(zone, oc->gfp_mask)) cpuset_limited = true; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 5b8d0966d429..5ef1eff330a2 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -2593,7 +2593,7 @@ static bool unreserve_highatomic_pageblock(const struct alloc_context *ac, int order; bool ret; - for_each_zone_zonelist_nodemask(zone, z, zonelist, ac->high_zoneidx, + for_each_zone_zonelist_nodemask(zone, z, zonelist, ac->highest_zoneidx, ac->nodemask) { /* * Preserve at least one pageblock unless memory pressure @@ -3462,7 +3462,7 @@ ALLOW_ERROR_INJECTION(should_fail_alloc_page, TRUE); * to check in the allocation paths if no pages are free. */ bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark, - int classzone_idx, unsigned int alloc_flags, + int highest_zoneidx, unsigned int alloc_flags, long free_pages) { long min = mark; @@ -3507,7 +3507,7 @@ bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark, * are not met, then a high-order request also cannot go ahead * even if a suitable page happened to be free. */ - if (free_pages <= min + z->lowmem_reserve[classzone_idx]) + if (free_pages <= min + z->lowmem_reserve[highest_zoneidx]) return false; /* If this is an order-0 request then the watermark is fine */ @@ -3540,14 +3540,15 @@ bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark, } bool zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark, - int classzone_idx, unsigned int alloc_flags) + int highest_zoneidx, unsigned int alloc_flags) { - return __zone_watermark_ok(z, order, mark, classzone_idx, alloc_flags, + return __zone_watermark_ok(z, order, mark, highest_zoneidx, alloc_flags, zone_page_state(z, NR_FREE_PAGES)); } static inline bool zone_watermark_fast(struct zone *z, unsigned int order, - unsigned long mark, int classzone_idx, unsigned int alloc_flags) + unsigned long mark, int highest_zoneidx, + unsigned int alloc_flags) { long free_pages = zone_page_state(z, NR_FREE_PAGES); long cma_pages = 0; @@ -3565,22 +3566,23 @@ static inline bool zone_watermark_fast(struct zone *z, unsigned int order, * the caller is !atomic then it'll uselessly search the free * list. That corner case is then slower but it is harmless. */ - if (!order && (free_pages - cma_pages) > mark + z->lowmem_reserve[classzone_idx]) + if (!order && (free_pages - cma_pages) > + mark + z->lowmem_reserve[highest_zoneidx]) return true; - return __zone_watermark_ok(z, order, mark, classzone_idx, alloc_flags, + return __zone_watermark_ok(z, order, mark, highest_zoneidx, alloc_flags, free_pages); } bool zone_watermark_ok_safe(struct zone *z, unsigned int order, - unsigned long mark, int classzone_idx) + unsigned long mark, int highest_zoneidx) { long free_pages = zone_page_state(z, NR_FREE_PAGES); if (z->percpu_drift_mark && free_pages < z->percpu_drift_mark) free_pages = zone_page_state_snapshot(z, NR_FREE_PAGES); - return __zone_watermark_ok(z, order, mark, classzone_idx, 0, + return __zone_watermark_ok(z, order, mark, highest_zoneidx, 0, free_pages); } @@ -3657,8 +3659,8 @@ retry: */ no_fallback = alloc_flags & ALLOC_NOFRAGMENT; z = ac->preferred_zoneref; - for_next_zone_zonelist_nodemask(zone, z, ac->zonelist, ac->high_zoneidx, - ac->nodemask) { + for_next_zone_zonelist_nodemask(zone, z, ac->zonelist, + ac->highest_zoneidx, ac->nodemask) { struct page *page; unsigned long mark; @@ -3713,7 +3715,7 @@ retry: mark = wmark_pages(zone, alloc_flags & ALLOC_WMARK_MASK); if (!zone_watermark_fast(zone, order, mark, - ac_classzone_idx(ac), alloc_flags)) { + ac->highest_zoneidx, alloc_flags)) { int ret; #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT @@ -3746,7 +3748,7 @@ retry: default: /* did we reclaim enough */ if (zone_watermark_ok(zone, order, mark, - ac_classzone_idx(ac), alloc_flags)) + ac->highest_zoneidx, alloc_flags)) goto try_this_zone; continue; @@ -3905,7 +3907,7 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order, if (gfp_mask & __GFP_RETRY_MAYFAIL) goto out; /* The OOM killer does not needlessly kill tasks for lowmem */ - if (ac->high_zoneidx < ZONE_NORMAL) + if (ac->highest_zoneidx < ZONE_NORMAL) goto out; if (pm_suspended_storage()) goto out; @@ -4108,10 +4110,10 @@ should_compact_retry(struct alloc_context *ac, unsigned int order, int alloc_fla * Let's give them a good hope and keep retrying while the order-0 * watermarks are OK. */ - for_each_zone_zonelist_nodemask(zone, z, ac->zonelist, ac->high_zoneidx, - ac->nodemask) { + for_each_zone_zonelist_nodemask(zone, z, ac->zonelist, + ac->highest_zoneidx, ac->nodemask) { if (zone_watermark_ok(zone, 0, min_wmark_pages(zone), - ac_classzone_idx(ac), alloc_flags)) + ac->highest_zoneidx, alloc_flags)) return true; } return false; @@ -4235,12 +4237,12 @@ static void wake_all_kswapds(unsigned int order, gfp_t gfp_mask, struct zoneref *z; struct zone *zone; pg_data_t *last_pgdat = NULL; - enum zone_type high_zoneidx = ac->high_zoneidx; + enum zone_type highest_zoneidx = ac->highest_zoneidx; - for_each_zone_zonelist_nodemask(zone, z, ac->zonelist, high_zoneidx, + for_each_zone_zonelist_nodemask(zone, z, ac->zonelist, highest_zoneidx, ac->nodemask) { if (last_pgdat != zone->zone_pgdat) - wakeup_kswapd(zone, gfp_mask, order, high_zoneidx); + wakeup_kswapd(zone, gfp_mask, order, highest_zoneidx); last_pgdat = zone->zone_pgdat; } } @@ -4375,8 +4377,8 @@ should_reclaim_retry(gfp_t gfp_mask, unsigned order, * request even if all reclaimable pages are considered then we are * screwed and have to go OOM. */ - for_each_zone_zonelist_nodemask(zone, z, ac->zonelist, ac->high_zoneidx, - ac->nodemask) { + for_each_zone_zonelist_nodemask(zone, z, ac->zonelist, + ac->highest_zoneidx, ac->nodemask) { unsigned long available; unsigned long reclaimable; unsigned long min_wmark = min_wmark_pages(zone); @@ -4390,7 +4392,7 @@ should_reclaim_retry(gfp_t gfp_mask, unsigned order, * reclaimable pages? */ wmark = __zone_watermark_ok(zone, order, min_wmark, - ac_classzone_idx(ac), alloc_flags, available); + ac->highest_zoneidx, alloc_flags, available); trace_reclaim_retry_zone(z, order, reclaimable, available, min_wmark, *no_progress_loops, wmark); if (wmark) { @@ -4509,7 +4511,7 @@ retry_cpuset: * could end up iterating over non-eligible zones endlessly. */ ac->preferred_zoneref = first_zones_zonelist(ac->zonelist, - ac->high_zoneidx, ac->nodemask); + ac->highest_zoneidx, ac->nodemask); if (!ac->preferred_zoneref->zone) goto nopage; @@ -4596,7 +4598,7 @@ retry: if (!(alloc_flags & ALLOC_CPUSET) || reserve_flags) { ac->nodemask = NULL; ac->preferred_zoneref = first_zones_zonelist(ac->zonelist, - ac->high_zoneidx, ac->nodemask); + ac->highest_zoneidx, ac->nodemask); } /* Attempt with potentially adjusted zonelist and alloc_flags */ @@ -4730,7 +4732,7 @@ static inline bool prepare_alloc_pages(gfp_t gfp_mask, unsigned int order, struct alloc_context *ac, gfp_t *alloc_mask, unsigned int *alloc_flags) { - ac->high_zoneidx = gfp_zone(gfp_mask); + ac->highest_zoneidx = gfp_zone(gfp_mask); ac->zonelist = node_zonelist(preferred_nid, gfp_mask); ac->nodemask = nodemask; ac->migratetype = gfpflags_to_migratetype(gfp_mask); @@ -4769,7 +4771,7 @@ static inline void finalise_ac(gfp_t gfp_mask, struct alloc_context *ac) * may get reset for allocations that ignore memory policies. */ ac->preferred_zoneref = first_zones_zonelist(ac->zonelist, - ac->high_zoneidx, ac->nodemask); + ac->highest_zoneidx, ac->nodemask); } /* @@ -6867,7 +6869,7 @@ static void __init free_area_init_node(int nid) unsigned long end_pfn = 0; /* pg_data_t should be reset to zero when it's allocated */ - WARN_ON(pgdat->nr_zones || pgdat->kswapd_classzone_idx); + WARN_ON(pgdat->nr_zones || pgdat->kswapd_highest_zoneidx); get_pfn_range_for_nid(nid, &start_pfn, &end_pfn); diff --git a/mm/slab.c b/mm/slab.c index a89633603b2d..9350062ffc1a 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -3106,7 +3106,7 @@ static void *fallback_alloc(struct kmem_cache *cache, gfp_t flags) struct zonelist *zonelist; struct zoneref *z; struct zone *zone; - enum zone_type high_zoneidx = gfp_zone(flags); + enum zone_type highest_zoneidx = gfp_zone(flags); void *obj = NULL; struct page *page; int nid; @@ -3124,7 +3124,7 @@ retry: * Look through allowed nodes for objects available * from existing per node queues. */ - for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) { + for_each_zone_zonelist(zone, z, zonelist, highest_zoneidx) { nid = zone_to_nid(zone); if (cpuset_zone_allowed(zone, flags) && diff --git a/mm/slub.c b/mm/slub.c index 527209d63278..d52487919278 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -1938,7 +1938,7 @@ static void *get_any_partial(struct kmem_cache *s, gfp_t flags, struct zonelist *zonelist; struct zoneref *z; struct zone *zone; - enum zone_type high_zoneidx = gfp_zone(flags); + enum zone_type highest_zoneidx = gfp_zone(flags); void *object; unsigned int cpuset_mems_cookie; @@ -1967,7 +1967,7 @@ static void *get_any_partial(struct kmem_cache *s, gfp_t flags, do { cpuset_mems_cookie = read_mems_allowed_begin(); zonelist = node_zonelist(mempolicy_slab_node(), flags); - for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) { + for_each_zone_zonelist(zone, z, zonelist, highest_zoneidx) { struct kmem_cache_node *n; n = get_node(s, zone_to_nid(zone)); diff --git a/mm/vmscan.c b/mm/vmscan.c index b2f5deb3603c..18bfbee9a581 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -3131,8 +3131,8 @@ static bool allow_direct_reclaim(pg_data_t *pgdat) /* kswapd must be awake if processes are being throttled */ if (!wmark_ok && waitqueue_active(&pgdat->kswapd_wait)) { - if (READ_ONCE(pgdat->kswapd_classzone_idx) > ZONE_NORMAL) - WRITE_ONCE(pgdat->kswapd_classzone_idx, ZONE_NORMAL); + if (READ_ONCE(pgdat->kswapd_highest_zoneidx) > ZONE_NORMAL) + WRITE_ONCE(pgdat->kswapd_highest_zoneidx, ZONE_NORMAL); wake_up_interruptible(&pgdat->kswapd_wait); } @@ -3385,7 +3385,7 @@ static void age_active_anon(struct pglist_data *pgdat, } while (memcg); } -static bool pgdat_watermark_boosted(pg_data_t *pgdat, int classzone_idx) +static bool pgdat_watermark_boosted(pg_data_t *pgdat, int highest_zoneidx) { int i; struct zone *zone; @@ -3397,7 +3397,7 @@ static bool pgdat_watermark_boosted(pg_data_t *pgdat, int classzone_idx) * start prematurely when there is no boosting and a lower * zone is balanced. */ - for (i = classzone_idx; i >= 0; i--) { + for (i = highest_zoneidx; i >= 0; i--) { zone = pgdat->node_zones + i; if (!managed_zone(zone)) continue; @@ -3411,9 +3411,9 @@ static bool pgdat_watermark_boosted(pg_data_t *pgdat, int classzone_idx) /* * Returns true if there is an eligible zone balanced for the request order - * and classzone_idx + * and highest_zoneidx */ -static bool pgdat_balanced(pg_data_t *pgdat, int order, int classzone_idx) +static bool pgdat_balanced(pg_data_t *pgdat, int order, int highest_zoneidx) { int i; unsigned long mark = -1; @@ -3423,19 +3423,19 @@ static bool pgdat_balanced(pg_data_t *pgdat, int order, int classzone_idx) * Check watermarks bottom-up as lower zones are more likely to * meet watermarks. */ - for (i = 0; i <= classzone_idx; i++) { + for (i = 0; i <= highest_zoneidx; i++) { zone = pgdat->node_zones + i; if (!managed_zone(zone)) continue; mark = high_wmark_pages(zone); - if (zone_watermark_ok_safe(zone, order, mark, classzone_idx)) + if (zone_watermark_ok_safe(zone, order, mark, highest_zoneidx)) return true; } /* - * If a node has no populated zone within classzone_idx, it does not + * If a node has no populated zone within highest_zoneidx, it does not * need balancing by definition. This can happen if a zone-restricted * allocation tries to wake a remote kswapd. */ @@ -3461,7 +3461,8 @@ static void clear_pgdat_congested(pg_data_t *pgdat) * * Returns true if kswapd is ready to sleep */ -static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, int classzone_idx) +static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, + int highest_zoneidx) { /* * The throttled processes are normally woken up in balance_pgdat() as @@ -3483,7 +3484,7 @@ static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, int classzone_idx) if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES) return true; - if (pgdat_balanced(pgdat, order, classzone_idx)) { + if (pgdat_balanced(pgdat, order, highest_zoneidx)) { clear_pgdat_congested(pgdat); return true; } @@ -3547,7 +3548,7 @@ static bool kswapd_shrink_node(pg_data_t *pgdat, * or lower is eligible for reclaim until at least one usable zone is * balanced. */ -static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx) +static int balance_pgdat(pg_data_t *pgdat, int order, int highest_zoneidx) { int i; unsigned long nr_soft_reclaimed; @@ -3575,7 +3576,7 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx) * stall or direct reclaim until kswapd is finished. */ nr_boost_reclaim = 0; - for (i = 0; i <= classzone_idx; i++) { + for (i = 0; i <= highest_zoneidx; i++) { zone = pgdat->node_zones + i; if (!managed_zone(zone)) continue; @@ -3593,7 +3594,7 @@ restart: bool balanced; bool ret; - sc.reclaim_idx = classzone_idx; + sc.reclaim_idx = highest_zoneidx; /* * If the number of buffer_heads exceeds the maximum allowed @@ -3623,7 +3624,7 @@ restart: * on the grounds that the normal reclaim should be enough to * re-evaluate if boosting is required when kswapd next wakes. */ - balanced = pgdat_balanced(pgdat, sc.order, classzone_idx); + balanced = pgdat_balanced(pgdat, sc.order, highest_zoneidx); if (!balanced && nr_boost_reclaim) { nr_boost_reclaim = 0; goto restart; @@ -3723,7 +3724,7 @@ out: if (boosted) { unsigned long flags; - for (i = 0; i <= classzone_idx; i++) { + for (i = 0; i <= highest_zoneidx; i++) { if (!zone_boosts[i]) continue; @@ -3738,7 +3739,7 @@ out: * As there is now likely space, wakeup kcompact to defragment * pageblocks. */ - wakeup_kcompactd(pgdat, pageblock_order, classzone_idx); + wakeup_kcompactd(pgdat, pageblock_order, highest_zoneidx); } snapshot_refaults(NULL, pgdat); @@ -3756,22 +3757,22 @@ out: } /* - * The pgdat->kswapd_classzone_idx is used to pass the highest zone index to be - * reclaimed by kswapd from the waker. If the value is MAX_NR_ZONES which is not - * a valid index then either kswapd runs for first time or kswapd couldn't sleep - * after previous reclaim attempt (node is still unbalanced). In that case - * return the zone index of the previous kswapd reclaim cycle. + * The pgdat->kswapd_highest_zoneidx is used to pass the highest zone index to + * be reclaimed by kswapd from the waker. If the value is MAX_NR_ZONES which is + * not a valid index then either kswapd runs for first time or kswapd couldn't + * sleep after previous reclaim attempt (node is still unbalanced). In that + * case return the zone index of the previous kswapd reclaim cycle. */ -static enum zone_type kswapd_classzone_idx(pg_data_t *pgdat, - enum zone_type prev_classzone_idx) +static enum zone_type kswapd_highest_zoneidx(pg_data_t *pgdat, + enum zone_type prev_highest_zoneidx) { - enum zone_type curr_idx = READ_ONCE(pgdat->kswapd_classzone_idx); + enum zone_type curr_idx = READ_ONCE(pgdat->kswapd_highest_zoneidx); - return curr_idx == MAX_NR_ZONES ? prev_classzone_idx : curr_idx; + return curr_idx == MAX_NR_ZONES ? prev_highest_zoneidx : curr_idx; } static void kswapd_try_to_sleep(pg_data_t *pgdat, int alloc_order, int reclaim_order, - unsigned int classzone_idx) + unsigned int highest_zoneidx) { long remaining = 0; DEFINE_WAIT(wait); @@ -3788,7 +3789,7 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int alloc_order, int reclaim_o * eligible zone balanced that it's also unlikely that compaction will * succeed. */ - if (prepare_kswapd_sleep(pgdat, reclaim_order, classzone_idx)) { + if (prepare_kswapd_sleep(pgdat, reclaim_order, highest_zoneidx)) { /* * Compaction records what page blocks it recently failed to * isolate pages from and skips them in the future scanning. @@ -3801,18 +3802,19 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int alloc_order, int reclaim_o * We have freed the memory, now we should compact it to make * allocation of the requested order possible. */ - wakeup_kcompactd(pgdat, alloc_order, classzone_idx); + wakeup_kcompactd(pgdat, alloc_order, highest_zoneidx); remaining = schedule_timeout(HZ/10); /* - * If woken prematurely then reset kswapd_classzone_idx and + * If woken prematurely then reset kswapd_highest_zoneidx and * order. The values will either be from a wakeup request or * the previous request that slept prematurely. */ if (remaining) { - WRITE_ONCE(pgdat->kswapd_classzone_idx, - kswapd_classzone_idx(pgdat, classzone_idx)); + WRITE_ONCE(pgdat->kswapd_highest_zoneidx, + kswapd_highest_zoneidx(pgdat, + highest_zoneidx)); if (READ_ONCE(pgdat->kswapd_order) < reclaim_order) WRITE_ONCE(pgdat->kswapd_order, reclaim_order); @@ -3827,7 +3829,7 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int alloc_order, int reclaim_o * go fully to sleep until explicitly woken up. */ if (!remaining && - prepare_kswapd_sleep(pgdat, reclaim_order, classzone_idx)) { + prepare_kswapd_sleep(pgdat, reclaim_order, highest_zoneidx)) { trace_mm_vmscan_kswapd_sleep(pgdat->node_id); /* @@ -3869,7 +3871,7 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int alloc_order, int reclaim_o static int kswapd(void *p) { unsigned int alloc_order, reclaim_order; - unsigned int classzone_idx = MAX_NR_ZONES - 1; + unsigned int highest_zoneidx = MAX_NR_ZONES - 1; pg_data_t *pgdat = (pg_data_t*)p; struct task_struct *tsk = current; const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id); @@ -3893,22 +3895,24 @@ static int kswapd(void *p) set_freezable(); WRITE_ONCE(pgdat->kswapd_order, 0); - WRITE_ONCE(pgdat->kswapd_classzone_idx, MAX_NR_ZONES); + WRITE_ONCE(pgdat->kswapd_highest_zoneidx, MAX_NR_ZONES); for ( ; ; ) { bool ret; alloc_order = reclaim_order = READ_ONCE(pgdat->kswapd_order); - classzone_idx = kswapd_classzone_idx(pgdat, classzone_idx); + highest_zoneidx = kswapd_highest_zoneidx(pgdat, + highest_zoneidx); kswapd_try_sleep: kswapd_try_to_sleep(pgdat, alloc_order, reclaim_order, - classzone_idx); + highest_zoneidx); - /* Read the new order and classzone_idx */ + /* Read the new order and highest_zoneidx */ alloc_order = reclaim_order = READ_ONCE(pgdat->kswapd_order); - classzone_idx = kswapd_classzone_idx(pgdat, classzone_idx); + highest_zoneidx = kswapd_highest_zoneidx(pgdat, + highest_zoneidx); WRITE_ONCE(pgdat->kswapd_order, 0); - WRITE_ONCE(pgdat->kswapd_classzone_idx, MAX_NR_ZONES); + WRITE_ONCE(pgdat->kswapd_highest_zoneidx, MAX_NR_ZONES); ret = try_to_freeze(); if (kthread_should_stop()) @@ -3929,9 +3933,10 @@ kswapd_try_sleep: * but kcompactd is woken to compact for the original * request (alloc_order). */ - trace_mm_vmscan_kswapd_wake(pgdat->node_id, classzone_idx, + trace_mm_vmscan_kswapd_wake(pgdat->node_id, highest_zoneidx, alloc_order); - reclaim_order = balance_pgdat(pgdat, alloc_order, classzone_idx); + reclaim_order = balance_pgdat(pgdat, alloc_order, + highest_zoneidx); if (reclaim_order < alloc_order) goto kswapd_try_sleep; } @@ -3949,7 +3954,7 @@ kswapd_try_sleep: * needed. */ void wakeup_kswapd(struct zone *zone, gfp_t gfp_flags, int order, - enum zone_type classzone_idx) + enum zone_type highest_zoneidx) { pg_data_t *pgdat; enum zone_type curr_idx; @@ -3961,10 +3966,10 @@ void wakeup_kswapd(struct zone *zone, gfp_t gfp_flags, int order, return; pgdat = zone->zone_pgdat; - curr_idx = READ_ONCE(pgdat->kswapd_classzone_idx); + curr_idx = READ_ONCE(pgdat->kswapd_highest_zoneidx); - if (curr_idx == MAX_NR_ZONES || curr_idx < classzone_idx) - WRITE_ONCE(pgdat->kswapd_classzone_idx, classzone_idx); + if (curr_idx == MAX_NR_ZONES || curr_idx < highest_zoneidx) + WRITE_ONCE(pgdat->kswapd_highest_zoneidx, highest_zoneidx); if (READ_ONCE(pgdat->kswapd_order) < order) WRITE_ONCE(pgdat->kswapd_order, order); @@ -3974,8 +3979,8 @@ void wakeup_kswapd(struct zone *zone, gfp_t gfp_flags, int order, /* Hopeless node, leave it to direct reclaim if possible */ if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES || - (pgdat_balanced(pgdat, order, classzone_idx) && - !pgdat_watermark_boosted(pgdat, classzone_idx))) { + (pgdat_balanced(pgdat, order, highest_zoneidx) && + !pgdat_watermark_boosted(pgdat, highest_zoneidx))) { /* * There may be plenty of free memory available, but it's too * fragmented for high-order allocations. Wake up kcompactd @@ -3984,11 +3989,11 @@ void wakeup_kswapd(struct zone *zone, gfp_t gfp_flags, int order, * ratelimit its work. */ if (!(gfp_flags & __GFP_DIRECT_RECLAIM)) - wakeup_kcompactd(pgdat, order, classzone_idx); + wakeup_kcompactd(pgdat, order, highest_zoneidx); return; } - trace_mm_vmscan_wakeup_kswapd(pgdat->node_id, classzone_idx, order, + trace_mm_vmscan_wakeup_kswapd(pgdat->node_id, highest_zoneidx, order, gfp_flags); wake_up_interruptible(&pgdat->kswapd_wait); } -- cgit v1.2.3 From 01c0bfe061f309b848d51619f20495ee2acd7727 Mon Sep 17 00:00:00 2001 From: Wei Yang Date: Wed, 3 Jun 2020 15:59:08 -0700 Subject: mm: rename gfpflags_to_migratetype to gfp_migratetype for same convention Pageblock migrate type is encoded in GFP flags, just as zone_type and zonelist. Currently we use gfp_zone() and gfp_zonelist() to extract related information, it would be proper to use the same naming convention for migrate type. Signed-off-by: Wei Yang Signed-off-by: Andrew Morton Reviewed-by: Pankaj Gupta Link: http://lkml.kernel.org/r/20200329080823.7735-1-richard.weiyang@gmail.com Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 2 +- mm/compaction.c | 2 +- mm/page_alloc.c | 4 ++-- mm/page_owner.c | 7 +++---- 4 files changed, 7 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index fab6d486cbb7..67a0774e080b 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -312,7 +312,7 @@ struct vm_area_struct; #define GFP_MOVABLE_MASK (__GFP_RECLAIMABLE|__GFP_MOVABLE) #define GFP_MOVABLE_SHIFT 3 -static inline int gfpflags_to_migratetype(const gfp_t gfp_flags) +static inline int gfp_migratetype(const gfp_t gfp_flags) { VM_WARN_ON((gfp_flags & GFP_MOVABLE_MASK) == GFP_MOVABLE_MASK); BUILD_BUG_ON((1UL << GFP_MOVABLE_SHIFT) != ___GFP_MOVABLE); diff --git a/mm/compaction.c b/mm/compaction.c index 883355de4ace..5e3e3a972cd2 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -2100,7 +2100,7 @@ compact_zone(struct compact_control *cc, struct capture_control *capc) INIT_LIST_HEAD(&cc->freepages); INIT_LIST_HEAD(&cc->migratepages); - cc->migratetype = gfpflags_to_migratetype(cc->gfp_mask); + cc->migratetype = gfp_migratetype(cc->gfp_mask); ret = compaction_suitable(cc->zone, cc->order, cc->alloc_flags, cc->highest_zoneidx); /* Compaction is likely to fail */ diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 818c2644a200..2bd8d6893b3f 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -4285,7 +4285,7 @@ gfp_to_alloc_flags(gfp_t gfp_mask) alloc_flags |= ALLOC_HARDER; #ifdef CONFIG_CMA - if (gfpflags_to_migratetype(gfp_mask) == MIGRATE_MOVABLE) + if (gfp_migratetype(gfp_mask) == MIGRATE_MOVABLE) alloc_flags |= ALLOC_CMA; #endif return alloc_flags; @@ -4735,7 +4735,7 @@ static inline bool prepare_alloc_pages(gfp_t gfp_mask, unsigned int order, ac->highest_zoneidx = gfp_zone(gfp_mask); ac->zonelist = node_zonelist(preferred_nid, gfp_mask); ac->nodemask = nodemask; - ac->migratetype = gfpflags_to_migratetype(gfp_mask); + ac->migratetype = gfp_migratetype(gfp_mask); if (cpusets_enabled()) { *alloc_mask |= __GFP_HARDWALL; diff --git a/mm/page_owner.c b/mm/page_owner.c index 18ecde9f45b2..360461509423 100644 --- a/mm/page_owner.c +++ b/mm/page_owner.c @@ -312,8 +312,7 @@ void pagetypeinfo_showmixedcount_print(struct seq_file *m, continue; page_owner = get_page_owner(page_ext); - page_mt = gfpflags_to_migratetype( - page_owner->gfp_mask); + page_mt = gfp_migratetype(page_owner->gfp_mask); if (pageblock_mt != page_mt) { if (is_migrate_cma(pageblock_mt)) count[MIGRATE_MOVABLE]++; @@ -359,7 +358,7 @@ print_page_owner(char __user *buf, size_t count, unsigned long pfn, /* Print information relevant to grouping pages by mobility */ pageblock_mt = get_pageblock_migratetype(page); - page_mt = gfpflags_to_migratetype(page_owner->gfp_mask); + page_mt = gfp_migratetype(page_owner->gfp_mask); ret += snprintf(kbuf + ret, count - ret, "PFN %lu type %s Block %lu type %s Flags %#lx(%pGp)\n", pfn, @@ -416,7 +415,7 @@ void __dump_page_owner(struct page *page) page_owner = get_page_owner(page_ext); gfp_mask = page_owner->gfp_mask; - mt = gfpflags_to_migratetype(gfp_mask); + mt = gfp_migratetype(gfp_mask); if (!test_bit(PAGE_EXT_OWNER, &page_ext->flags)) { pr_alert("page_owner info is not present (never set?)\n"); -- cgit v1.2.3 From ae70eddd5633fc71dccf210f237c5aefc96f4332 Mon Sep 17 00:00:00 2001 From: Anshuman Khandual Date: Wed, 3 Jun 2020 15:59:17 -0700 Subject: mm/page_alloc: restrict and formalize compound_page_dtors[] Restrict elements in compound_page_dtors[] array per NR_COMPOUND_DTORS and explicitly position them according to enum compound_dtor_id. This improves protection against possible misalignment between compound_page_dtors[] and enum compound_dtor_id later on. Signed-off-by: Anshuman Khandual Signed-off-by: Andrew Morton Reviewed-by: David Hildenbrand Link: http://lkml.kernel.org/r/1589795958-19317-1-git-send-email-anshuman.khandual@arm.com Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 +- mm/page_alloc.c | 10 +++++----- 2 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index 4141ebcb3a65..32f3c17715ac 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -867,7 +867,7 @@ enum compound_dtor_id { #endif NR_COMPOUND_DTORS, }; -extern compound_page_dtor * const compound_page_dtors[]; +extern compound_page_dtor * const compound_page_dtors[NR_COMPOUND_DTORS]; static inline void set_compound_page_dtor(struct page *page, enum compound_dtor_id compound_dtor) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index d95442f7e478..045c4aeeec9a 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -302,14 +302,14 @@ const char * const migratetype_names[MIGRATE_TYPES] = { #endif }; -compound_page_dtor * const compound_page_dtors[] = { - NULL, - free_compound_page, +compound_page_dtor * const compound_page_dtors[NR_COMPOUND_DTORS] = { + [NULL_COMPOUND_DTOR] = NULL, + [COMPOUND_PAGE_DTOR] = free_compound_page, #ifdef CONFIG_HUGETLB_PAGE - free_huge_page, + [HUGETLB_PAGE_DTOR] = free_huge_page, #endif #ifdef CONFIG_TRANSPARENT_HUGEPAGE - free_transhuge_page, + [TRANSHUGE_PAGE_DTOR] = free_transhuge_page, #endif }; -- cgit v1.2.3 From 3d060856adfc59afb9d029c233141334cfaba418 Mon Sep 17 00:00:00 2001 From: Pavel Tatashin Date: Wed, 3 Jun 2020 15:59:24 -0700 Subject: mm: initialize deferred pages with interrupts enabled Initializing struct pages is a long task and keeping interrupts disabled for the duration of this operation introduces a number of problems. 1. jiffies are not updated for long period of time, and thus incorrect time is reported. See proposed solution and discussion here: lkml/20200311123848.118638-1-shile.zhang@linux.alibaba.com 2. It prevents farther improving deferred page initialization by allowing intra-node multi-threading. We are keeping interrupts disabled to solve a rather theoretical problem that was never observed in real world (See 3a2d7fa8a3d5). Let's keep interrupts enabled. In case we ever encounter a scenario where an interrupt thread wants to allocate large amount of memory this early in boot we can deal with that by growing zone (see deferred_grow_zone()) by the needed amount before starting deferred_init_memmap() threads. Before: [ 1.232459] node 0 initialised, 12058412 pages in 1ms After: [ 1.632580] node 0 initialised, 12051227 pages in 436ms Fixes: 3a2d7fa8a3d5 ("mm: disable interrupts while initializing deferred pages") Reported-by: Shile Zhang Signed-off-by: Pavel Tatashin Signed-off-by: Andrew Morton Reviewed-by: Daniel Jordan Reviewed-by: David Hildenbrand Acked-by: Michal Hocko Acked-by: Vlastimil Babka Cc: Dan Williams Cc: James Morris Cc: Kirill Tkhai Cc: Sasha Levin Cc: Yiqian Wei Cc: [4.17+] Link: http://lkml.kernel.org/r/20200403140952.17177-3-pasha.tatashin@soleen.com Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 2 ++ mm/page_alloc.c | 20 +++++++------------- 2 files changed, 9 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index cd8bd5f90552..2f79ff4477ba 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -680,6 +680,8 @@ typedef struct pglist_data { /* * Must be held any time you expect node_start_pfn, * node_present_pages, node_spanned_pages or nr_zones to stay constant. + * Also synchronizes pgdat->first_deferred_pfn during deferred page + * init. * * pgdat_resize_lock() and pgdat_resize_unlock() are provided to * manipulate node_size_lock without checking for CONFIG_MEMORY_HOTPLUG diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 148cf9a73f0b..c75561a3f144 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1844,6 +1844,13 @@ static int __init deferred_init_memmap(void *data) BUG_ON(pgdat->first_deferred_pfn > pgdat_end_pfn(pgdat)); pgdat->first_deferred_pfn = ULONG_MAX; + /* + * Once we unlock here, the zone cannot be grown anymore, thus if an + * interrupt thread must allocate this early in boot, zone must be + * pre-grown prior to start of deferred page initialization. + */ + pgdat_resize_unlock(pgdat, &flags); + /* Only the highest zone is deferred so find it */ for (zid = 0; zid < MAX_NR_ZONES; zid++) { zone = pgdat->node_zones + zid; @@ -1866,8 +1873,6 @@ static int __init deferred_init_memmap(void *data) touch_nmi_watchdog(); } zone_empty: - pgdat_resize_unlock(pgdat, &flags); - /* Sanity check that the next zone really is unpopulated */ WARN_ON(++zid < MAX_NR_ZONES && populated_zone(++zone)); @@ -1909,17 +1914,6 @@ deferred_grow_zone(struct zone *zone, unsigned int order) pgdat_resize_lock(pgdat, &flags); - /* - * If deferred pages have been initialized while we were waiting for - * the lock, return true, as the zone was grown. The caller will retry - * this zone. We won't return to this function since the caller also - * has this static branch. - */ - if (!static_branch_unlikely(&deferred_pages)) { - pgdat_resize_unlock(pgdat, &flags); - return true; - } - /* * If someone grew this zone while we were waiting for spinlock, return * true, as there might be enough pages already. -- cgit v1.2.3 From f1b192b117cd418bacf42a9583d7a01855a18fe5 Mon Sep 17 00:00:00 2001 From: Daniel Jordan Date: Wed, 3 Jun 2020 15:59:35 -0700 Subject: padata: initialize earlier padata will soon initialize the system's struct pages in parallel, so it needs to be ready by page_alloc_init_late(). The error return from padata_driver_init() triggers an initcall warning, so add a warning to padata_init() to avoid silent failure. Signed-off-by: Daniel Jordan Signed-off-by: Andrew Morton Tested-by: Josh Triplett Cc: Alexander Duyck Cc: Alex Williamson Cc: Dan Williams Cc: Dave Hansen Cc: David Hildenbrand Cc: Herbert Xu Cc: Jason Gunthorpe Cc: Jonathan Corbet Cc: Kirill Tkhai Cc: Michal Hocko Cc: Pavel Machek Cc: Pavel Tatashin Cc: Peter Zijlstra Cc: Randy Dunlap Cc: Robert Elliott Cc: Shile Zhang Cc: Steffen Klassert Cc: Steven Sistare Cc: Tejun Heo Cc: Zi Yan Link: http://lkml.kernel.org/r/20200527173608.2885243-3-daniel.m.jordan@oracle.com Signed-off-by: Linus Torvalds --- include/linux/padata.h | 6 ++++++ init/main.c | 2 ++ kernel/padata.c | 17 ++++++++--------- 3 files changed, 16 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/padata.h b/include/linux/padata.h index 693cae9bfe66..d50bd1a7756f 100644 --- a/include/linux/padata.h +++ b/include/linux/padata.h @@ -166,6 +166,12 @@ struct padata_instance { #define PADATA_INVALID 4 }; +#ifdef CONFIG_PADATA +extern void __init padata_init(void); +#else +static inline void __init padata_init(void) {} +#endif + extern struct padata_instance *padata_alloc_possible(const char *name); extern void padata_free(struct padata_instance *pinst); extern struct padata_shell *padata_alloc_shell(struct padata_instance *pinst); diff --git a/init/main.c b/init/main.c index 03371976d387..df32f67214d2 100644 --- a/init/main.c +++ b/init/main.c @@ -63,6 +63,7 @@ #include #include #include +#include #include #include #include @@ -1482,6 +1483,7 @@ static noinline void __init kernel_init_freeable(void) smp_init(); sched_init_smp(); + padata_init(); page_alloc_init_late(); /* Initialize page ext after all struct pages are initialized. */ page_ext_init(); diff --git a/kernel/padata.c b/kernel/padata.c index b4c7e3e38a05..0c5f4f78f2c2 100644 --- a/kernel/padata.c +++ b/kernel/padata.c @@ -31,7 +31,6 @@ #include #include #include -#include #define MAX_OBJ_NUM 1000 @@ -1052,26 +1051,26 @@ void padata_free_shell(struct padata_shell *ps) } EXPORT_SYMBOL(padata_free_shell); -#ifdef CONFIG_HOTPLUG_CPU - -static __init int padata_driver_init(void) +void __init padata_init(void) { +#ifdef CONFIG_HOTPLUG_CPU int ret; ret = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN, "padata:online", padata_cpu_online, NULL); if (ret < 0) - return ret; + goto err; hp_online = ret; ret = cpuhp_setup_state_multi(CPUHP_PADATA_DEAD, "padata:dead", NULL, padata_cpu_dead); if (ret < 0) { cpuhp_remove_multi_state(hp_online); - return ret; + goto err; } - return 0; -} -module_init(padata_driver_init); + return; +err: + pr_warn("padata: initialization failed\n"); #endif +} -- cgit v1.2.3 From 4611ce22468895acd61fee9ac1da810d60617d9a Mon Sep 17 00:00:00 2001 From: Daniel Jordan Date: Wed, 3 Jun 2020 15:59:39 -0700 Subject: padata: allocate work structures for parallel jobs from a pool padata allocates per-CPU, per-instance work structs for parallel jobs. A do_parallel call assigns a job to a sequence number and hashes the number to a CPU, where the job will eventually run using the corresponding work. This approach fit with how padata used to bind a job to each CPU round-robin, makes less sense after commit bfde23ce200e6 ("padata: unbind parallel jobs from specific CPUs") because a work isn't bound to a particular CPU anymore, and isn't needed at all for multithreaded jobs because they don't have sequence numbers. Replace the per-CPU works with a preallocated pool, which allows sharing them between existing padata users and the upcoming multithreaded user. The pool will also facilitate setting NUMA-aware concurrency limits with later users. The pool is sized according to the number of possible CPUs. With this limit, MAX_OBJ_NUM no longer makes sense, so remove it. If the global pool is exhausted, a parallel job is run in the current task instead to throttle a system trying to do too much in parallel. Signed-off-by: Daniel Jordan Signed-off-by: Andrew Morton Tested-by: Josh Triplett Cc: Alexander Duyck Cc: Alex Williamson Cc: Dan Williams Cc: Dave Hansen Cc: David Hildenbrand Cc: Herbert Xu Cc: Jason Gunthorpe Cc: Jonathan Corbet Cc: Kirill Tkhai Cc: Michal Hocko Cc: Pavel Machek Cc: Pavel Tatashin Cc: Peter Zijlstra Cc: Randy Dunlap Cc: Robert Elliott Cc: Shile Zhang Cc: Steffen Klassert Cc: Steven Sistare Cc: Tejun Heo Cc: Zi Yan Link: http://lkml.kernel.org/r/20200527173608.2885243-4-daniel.m.jordan@oracle.com Signed-off-by: Linus Torvalds --- include/linux/padata.h | 8 +--- kernel/padata.c | 118 ++++++++++++++++++++++++++++++++----------------- 2 files changed, 78 insertions(+), 48 deletions(-) (limited to 'include') diff --git a/include/linux/padata.h b/include/linux/padata.h index d50bd1a7756f..b4da88f8588c 100644 --- a/include/linux/padata.h +++ b/include/linux/padata.h @@ -24,7 +24,6 @@ * @list: List entry, to attach to the padata lists. * @pd: Pointer to the internal control structure. * @cb_cpu: Callback cpu for serializatioon. - * @cpu: Cpu for parallelization. * @seq_nr: Sequence number of the parallelized data object. * @info: Used to pass information from the parallel to the serial function. * @parallel: Parallel execution function. @@ -34,7 +33,6 @@ struct padata_priv { struct list_head list; struct parallel_data *pd; int cb_cpu; - int cpu; unsigned int seq_nr; int info; void (*parallel)(struct padata_priv *padata); @@ -68,15 +66,11 @@ struct padata_serial_queue { /** * struct padata_parallel_queue - The percpu padata parallel queue * - * @parallel: List to wait for parallelization. * @reorder: List to wait for reordering after parallel processing. - * @work: work struct for parallelization. * @num_obj: Number of objects that are processed by this cpu. */ struct padata_parallel_queue { - struct padata_list parallel; struct padata_list reorder; - struct work_struct work; atomic_t num_obj; }; @@ -111,7 +105,7 @@ struct parallel_data { struct padata_parallel_queue __percpu *pqueue; struct padata_serial_queue __percpu *squeue; atomic_t refcnt; - atomic_t seq_nr; + unsigned int seq_nr; unsigned int processed; int cpu; struct padata_cpumask cpumask; diff --git a/kernel/padata.c b/kernel/padata.c index 0c5f4f78f2c2..d779a73d4d92 100644 --- a/kernel/padata.c +++ b/kernel/padata.c @@ -32,7 +32,15 @@ #include #include -#define MAX_OBJ_NUM 1000 +struct padata_work { + struct work_struct pw_work; + struct list_head pw_list; /* padata_free_works linkage */ + void *pw_data; +}; + +static DEFINE_SPINLOCK(padata_works_lock); +static struct padata_work *padata_works; +static LIST_HEAD(padata_free_works); static void padata_free_pd(struct parallel_data *pd); @@ -58,30 +66,44 @@ static int padata_cpu_hash(struct parallel_data *pd, unsigned int seq_nr) return padata_index_to_cpu(pd, cpu_index); } -static void padata_parallel_worker(struct work_struct *parallel_work) +static struct padata_work *padata_work_alloc(void) { - struct padata_parallel_queue *pqueue; - LIST_HEAD(local_list); + struct padata_work *pw; - local_bh_disable(); - pqueue = container_of(parallel_work, - struct padata_parallel_queue, work); + lockdep_assert_held(&padata_works_lock); - spin_lock(&pqueue->parallel.lock); - list_replace_init(&pqueue->parallel.list, &local_list); - spin_unlock(&pqueue->parallel.lock); + if (list_empty(&padata_free_works)) + return NULL; /* No more work items allowed to be queued. */ - while (!list_empty(&local_list)) { - struct padata_priv *padata; + pw = list_first_entry(&padata_free_works, struct padata_work, pw_list); + list_del(&pw->pw_list); + return pw; +} - padata = list_entry(local_list.next, - struct padata_priv, list); +static void padata_work_init(struct padata_work *pw, work_func_t work_fn, + void *data) +{ + INIT_WORK(&pw->pw_work, work_fn); + pw->pw_data = data; +} - list_del_init(&padata->list); +static void padata_work_free(struct padata_work *pw) +{ + lockdep_assert_held(&padata_works_lock); + list_add(&pw->pw_list, &padata_free_works); +} - padata->parallel(padata); - } +static void padata_parallel_worker(struct work_struct *parallel_work) +{ + struct padata_work *pw = container_of(parallel_work, struct padata_work, + pw_work); + struct padata_priv *padata = pw->pw_data; + local_bh_disable(); + padata->parallel(padata); + spin_lock(&padata_works_lock); + padata_work_free(pw); + spin_unlock(&padata_works_lock); local_bh_enable(); } @@ -105,9 +127,9 @@ int padata_do_parallel(struct padata_shell *ps, struct padata_priv *padata, int *cb_cpu) { struct padata_instance *pinst = ps->pinst; - int i, cpu, cpu_index, target_cpu, err; - struct padata_parallel_queue *queue; + int i, cpu, cpu_index, err; struct parallel_data *pd; + struct padata_work *pw; rcu_read_lock_bh(); @@ -135,25 +157,25 @@ int padata_do_parallel(struct padata_shell *ps, if ((pinst->flags & PADATA_RESET)) goto out; - if (atomic_read(&pd->refcnt) >= MAX_OBJ_NUM) - goto out; - - err = 0; atomic_inc(&pd->refcnt); padata->pd = pd; padata->cb_cpu = *cb_cpu; - padata->seq_nr = atomic_inc_return(&pd->seq_nr); - target_cpu = padata_cpu_hash(pd, padata->seq_nr); - padata->cpu = target_cpu; - queue = per_cpu_ptr(pd->pqueue, target_cpu); - - spin_lock(&queue->parallel.lock); - list_add_tail(&padata->list, &queue->parallel.list); - spin_unlock(&queue->parallel.lock); + rcu_read_unlock_bh(); - queue_work(pinst->parallel_wq, &queue->work); + spin_lock(&padata_works_lock); + padata->seq_nr = ++pd->seq_nr; + pw = padata_work_alloc(); + spin_unlock(&padata_works_lock); + if (pw) { + padata_work_init(pw, padata_parallel_worker, padata); + queue_work(pinst->parallel_wq, &pw->pw_work); + } else { + /* Maximum works limit exceeded, run in the current task. */ + padata->parallel(padata); + } + return 0; out: rcu_read_unlock_bh(); @@ -324,8 +346,9 @@ static void padata_serial_worker(struct work_struct *serial_work) void padata_do_serial(struct padata_priv *padata) { struct parallel_data *pd = padata->pd; + int hashed_cpu = padata_cpu_hash(pd, padata->seq_nr); struct padata_parallel_queue *pqueue = per_cpu_ptr(pd->pqueue, - padata->cpu); + hashed_cpu); struct padata_priv *cur; spin_lock(&pqueue->reorder.lock); @@ -416,8 +439,6 @@ static void padata_init_pqueues(struct parallel_data *pd) pqueue = per_cpu_ptr(pd->pqueue, cpu); __padata_list_init(&pqueue->reorder); - __padata_list_init(&pqueue->parallel); - INIT_WORK(&pqueue->work, padata_parallel_worker); atomic_set(&pqueue->num_obj, 0); } } @@ -451,7 +472,7 @@ static struct parallel_data *padata_alloc_pd(struct padata_shell *ps) padata_init_pqueues(pd); padata_init_squeues(pd); - atomic_set(&pd->seq_nr, -1); + pd->seq_nr = -1; atomic_set(&pd->refcnt, 1); spin_lock_init(&pd->lock); pd->cpu = cpumask_first(pd->cpumask.pcpu); @@ -1053,6 +1074,7 @@ EXPORT_SYMBOL(padata_free_shell); void __init padata_init(void) { + unsigned int i, possible_cpus; #ifdef CONFIG_HOTPLUG_CPU int ret; @@ -1064,13 +1086,27 @@ void __init padata_init(void) ret = cpuhp_setup_state_multi(CPUHP_PADATA_DEAD, "padata:dead", NULL, padata_cpu_dead); - if (ret < 0) { - cpuhp_remove_multi_state(hp_online); - goto err; - } + if (ret < 0) + goto remove_online_state; +#endif + + possible_cpus = num_possible_cpus(); + padata_works = kmalloc_array(possible_cpus, sizeof(struct padata_work), + GFP_KERNEL); + if (!padata_works) + goto remove_dead_state; + + for (i = 0; i < possible_cpus; ++i) + list_add(&padata_works[i].pw_list, &padata_free_works); return; + +remove_dead_state: +#ifdef CONFIG_HOTPLUG_CPU + cpuhp_remove_multi_state(CPUHP_PADATA_DEAD); +remove_online_state: + cpuhp_remove_multi_state(hp_online); err: - pr_warn("padata: initialization failed\n"); #endif + pr_warn("padata: initialization failed\n"); } -- cgit v1.2.3 From 004ed42638f4428e70ead59d170f3d17ff761a0f Mon Sep 17 00:00:00 2001 From: Daniel Jordan Date: Wed, 3 Jun 2020 15:59:43 -0700 Subject: padata: add basic support for multithreaded jobs Sometimes the kernel doesn't take full advantage of system memory bandwidth, leading to a single CPU spending excessive time in initialization paths where the data scales with memory size. Multithreading naturally addresses this problem. Extend padata, a framework that handles many parallel yet singlethreaded jobs, to also handle multithreaded jobs by adding support for splitting up the work evenly, specifying a minimum amount of work that's appropriate for one helper thread to do, load balancing between helpers, and coordinating them. This is inspired by work from Pavel Tatashin and Steve Sistare. Signed-off-by: Daniel Jordan Signed-off-by: Andrew Morton Tested-by: Josh Triplett Cc: Alexander Duyck Cc: Alex Williamson Cc: Dan Williams Cc: Dave Hansen Cc: David Hildenbrand Cc: Herbert Xu Cc: Jason Gunthorpe Cc: Jonathan Corbet Cc: Kirill Tkhai Cc: Michal Hocko Cc: Pavel Machek Cc: Pavel Tatashin Cc: Peter Zijlstra Cc: Randy Dunlap Cc: Robert Elliott Cc: Shile Zhang Cc: Steffen Klassert Cc: Steven Sistare Cc: Tejun Heo Cc: Zi Yan Link: http://lkml.kernel.org/r/20200527173608.2885243-5-daniel.m.jordan@oracle.com Signed-off-by: Linus Torvalds --- include/linux/padata.h | 29 ++++++++++ kernel/padata.c | 152 ++++++++++++++++++++++++++++++++++++++++++++++++- 2 files changed, 178 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/padata.h b/include/linux/padata.h index b4da88f8588c..7302efff5e65 100644 --- a/include/linux/padata.h +++ b/include/linux/padata.h @@ -4,6 +4,9 @@ * * Copyright (C) 2008, 2009 secunet Security Networks AG * Copyright (C) 2008, 2009 Steffen Klassert + * + * Copyright (c) 2020 Oracle and/or its affiliates. + * Author: Daniel Jordan */ #ifndef PADATA_H @@ -130,6 +133,31 @@ struct padata_shell { struct list_head list; }; +/** + * struct padata_mt_job - represents one multithreaded job + * + * @thread_fn: Called for each chunk of work that a padata thread does. + * @fn_arg: The thread function argument. + * @start: The start of the job (units are job-specific). + * @size: size of this node's work (units are job-specific). + * @align: Ranges passed to the thread function fall on this boundary, with the + * possible exceptions of the beginning and end of the job. + * @min_chunk: The minimum chunk size in job-specific units. This allows + * the client to communicate the minimum amount of work that's + * appropriate for one worker thread to do at once. + * @max_threads: Max threads to use for the job, actual number may be less + * depending on task size and minimum chunk size. + */ +struct padata_mt_job { + void (*thread_fn)(unsigned long start, unsigned long end, void *arg); + void *fn_arg; + unsigned long start; + unsigned long size; + unsigned long align; + unsigned long min_chunk; + int max_threads; +}; + /** * struct padata_instance - The overall control structure. * @@ -173,6 +201,7 @@ extern void padata_free_shell(struct padata_shell *ps); extern int padata_do_parallel(struct padata_shell *ps, struct padata_priv *padata, int *cb_cpu); extern void padata_do_serial(struct padata_priv *padata); +extern void __init padata_do_multithreaded(struct padata_mt_job *job); extern int padata_set_cpumask(struct padata_instance *pinst, int cpumask_type, cpumask_var_t cpumask); extern int padata_start(struct padata_instance *pinst); diff --git a/kernel/padata.c b/kernel/padata.c index d779a73d4d92..29fc5d87a4cd 100644 --- a/kernel/padata.c +++ b/kernel/padata.c @@ -7,6 +7,9 @@ * Copyright (C) 2008, 2009 secunet Security Networks AG * Copyright (C) 2008, 2009 Steffen Klassert * + * Copyright (c) 2020 Oracle and/or its affiliates. + * Author: Daniel Jordan + * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, * version 2, as published by the Free Software Foundation. @@ -21,6 +24,7 @@ * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. */ +#include #include #include #include @@ -32,6 +36,8 @@ #include #include +#define PADATA_WORK_ONSTACK 1 /* Work's memory is on stack */ + struct padata_work { struct work_struct pw_work; struct list_head pw_list; /* padata_free_works linkage */ @@ -42,7 +48,17 @@ static DEFINE_SPINLOCK(padata_works_lock); static struct padata_work *padata_works; static LIST_HEAD(padata_free_works); +struct padata_mt_job_state { + spinlock_t lock; + struct completion completion; + struct padata_mt_job *job; + int nworks; + int nworks_fini; + unsigned long chunk_size; +}; + static void padata_free_pd(struct parallel_data *pd); +static void __init padata_mt_helper(struct work_struct *work); static int padata_index_to_cpu(struct parallel_data *pd, int cpu_index) { @@ -81,18 +97,56 @@ static struct padata_work *padata_work_alloc(void) } static void padata_work_init(struct padata_work *pw, work_func_t work_fn, - void *data) + void *data, int flags) { - INIT_WORK(&pw->pw_work, work_fn); + if (flags & PADATA_WORK_ONSTACK) + INIT_WORK_ONSTACK(&pw->pw_work, work_fn); + else + INIT_WORK(&pw->pw_work, work_fn); pw->pw_data = data; } +static int __init padata_work_alloc_mt(int nworks, void *data, + struct list_head *head) +{ + int i; + + spin_lock(&padata_works_lock); + /* Start at 1 because the current task participates in the job. */ + for (i = 1; i < nworks; ++i) { + struct padata_work *pw = padata_work_alloc(); + + if (!pw) + break; + padata_work_init(pw, padata_mt_helper, data, 0); + list_add(&pw->pw_list, head); + } + spin_unlock(&padata_works_lock); + + return i; +} + static void padata_work_free(struct padata_work *pw) { lockdep_assert_held(&padata_works_lock); list_add(&pw->pw_list, &padata_free_works); } +static void __init padata_works_free(struct list_head *works) +{ + struct padata_work *cur, *next; + + if (list_empty(works)) + return; + + spin_lock(&padata_works_lock); + list_for_each_entry_safe(cur, next, works, pw_list) { + list_del(&cur->pw_list); + padata_work_free(cur); + } + spin_unlock(&padata_works_lock); +} + static void padata_parallel_worker(struct work_struct *parallel_work) { struct padata_work *pw = container_of(parallel_work, struct padata_work, @@ -168,7 +222,7 @@ int padata_do_parallel(struct padata_shell *ps, pw = padata_work_alloc(); spin_unlock(&padata_works_lock); if (pw) { - padata_work_init(pw, padata_parallel_worker, padata); + padata_work_init(pw, padata_parallel_worker, padata, 0); queue_work(pinst->parallel_wq, &pw->pw_work); } else { /* Maximum works limit exceeded, run in the current task. */ @@ -409,6 +463,98 @@ out: return err; } +static void __init padata_mt_helper(struct work_struct *w) +{ + struct padata_work *pw = container_of(w, struct padata_work, pw_work); + struct padata_mt_job_state *ps = pw->pw_data; + struct padata_mt_job *job = ps->job; + bool done; + + spin_lock(&ps->lock); + + while (job->size > 0) { + unsigned long start, size, end; + + start = job->start; + /* So end is chunk size aligned if enough work remains. */ + size = roundup(start + 1, ps->chunk_size) - start; + size = min(size, job->size); + end = start + size; + + job->start = end; + job->size -= size; + + spin_unlock(&ps->lock); + job->thread_fn(start, end, job->fn_arg); + spin_lock(&ps->lock); + } + + ++ps->nworks_fini; + done = (ps->nworks_fini == ps->nworks); + spin_unlock(&ps->lock); + + if (done) + complete(&ps->completion); +} + +/** + * padata_do_multithreaded - run a multithreaded job + * @job: Description of the job. + * + * See the definition of struct padata_mt_job for more details. + */ +void __init padata_do_multithreaded(struct padata_mt_job *job) +{ + /* In case threads finish at different times. */ + static const unsigned long load_balance_factor = 4; + struct padata_work my_work, *pw; + struct padata_mt_job_state ps; + LIST_HEAD(works); + int nworks; + + if (job->size == 0) + return; + + /* Ensure at least one thread when size < min_chunk. */ + nworks = max(job->size / job->min_chunk, 1ul); + nworks = min(nworks, job->max_threads); + + if (nworks == 1) { + /* Single thread, no coordination needed, cut to the chase. */ + job->thread_fn(job->start, job->start + job->size, job->fn_arg); + return; + } + + spin_lock_init(&ps.lock); + init_completion(&ps.completion); + ps.job = job; + ps.nworks = padata_work_alloc_mt(nworks, &ps, &works); + ps.nworks_fini = 0; + + /* + * Chunk size is the amount of work a helper does per call to the + * thread function. Load balance large jobs between threads by + * increasing the number of chunks, guarantee at least the minimum + * chunk size from the caller, and honor the caller's alignment. + */ + ps.chunk_size = job->size / (ps.nworks * load_balance_factor); + ps.chunk_size = max(ps.chunk_size, job->min_chunk); + ps.chunk_size = roundup(ps.chunk_size, job->align); + + list_for_each_entry(pw, &works, pw_list) + queue_work(system_unbound_wq, &pw->pw_work); + + /* Use the current thread, which saves starting a workqueue worker. */ + padata_work_init(&my_work, padata_mt_helper, &ps, PADATA_WORK_ONSTACK); + padata_mt_helper(&my_work.pw_work); + + /* Wait for all the helpers to finish. */ + wait_for_completion(&ps.completion); + + destroy_work_on_stack(&my_work.pw_work); + padata_works_free(&works); +} + static void __padata_list_init(struct padata_list *pd_list) { INIT_LIST_HEAD(&pd_list->list); -- cgit v1.2.3 From ecd096506922332fdb36ff1211e03601befe6e18 Mon Sep 17 00:00:00 2001 From: Daniel Jordan Date: Wed, 3 Jun 2020 15:59:55 -0700 Subject: mm: make deferred init's max threads arch-specific Using padata during deferred init has only been tested on x86, so for now limit it to this architecture. If another arch wants this, it can find the max thread limit that's best for it and override deferred_page_init_max_threads(). Signed-off-by: Daniel Jordan Signed-off-by: Andrew Morton Tested-by: Josh Triplett Cc: Alexander Duyck Cc: Alex Williamson Cc: Dan Williams Cc: Dave Hansen Cc: David Hildenbrand Cc: Herbert Xu Cc: Jason Gunthorpe Cc: Jonathan Corbet Cc: Kirill Tkhai Cc: Michal Hocko Cc: Pavel Machek Cc: Pavel Tatashin Cc: Peter Zijlstra Cc: Randy Dunlap Cc: Robert Elliott Cc: Shile Zhang Cc: Steffen Klassert Cc: Steven Sistare Cc: Tejun Heo Cc: Zi Yan Link: http://lkml.kernel.org/r/20200527173608.2885243-8-daniel.m.jordan@oracle.com Signed-off-by: Linus Torvalds --- arch/x86/mm/init_64.c | 12 ++++++++++++ include/linux/memblock.h | 3 +++ mm/page_alloc.c | 13 ++++++++----- 3 files changed, 23 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 96274a90c5ff..e08f1007f776 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -1265,6 +1265,18 @@ void __init mem_init(void) mem_init_print_info(NULL); } +#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT +int __init deferred_page_init_max_threads(const struct cpumask *node_cpumask) +{ + /* + * More CPUs always led to greater speedups on tested systems, up to + * all the nodes' CPUs. Use all since the system is otherwise idle + * now. + */ + return max_t(int, cpumask_weight(node_cpumask), 1); +} +#endif + int kernel_set_to_readonly; void mark_rodata_ro(void) diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 45abfc54da37..807ab9daf0cd 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -273,6 +273,9 @@ void __next_mem_pfn_range_in_zone(u64 *idx, struct zone *zone, #define for_each_free_mem_pfn_range_in_zone_from(i, zone, p_start, p_end) \ for (; i != U64_MAX; \ __next_mem_pfn_range_in_zone(&i, zone, p_start, p_end)) + +int __init deferred_page_init_max_threads(const struct cpumask *node_cpumask); + #endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */ /** diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 27ec5dc4db33..fb9dec1c1976 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1836,6 +1836,13 @@ deferred_init_memmap_chunk(unsigned long start_pfn, unsigned long end_pfn, } } +/* An arch may override for more concurrency. */ +__weak int __init +deferred_page_init_max_threads(const struct cpumask *node_cpumask) +{ + return 1; +} + /* Initialise remaining memory on a node */ static int __init deferred_init_memmap(void *data) { @@ -1884,11 +1891,7 @@ static int __init deferred_init_memmap(void *data) first_init_pfn)) goto zone_empty; - /* - * More CPUs always led to greater speedups on tested systems, up to - * all the nodes' CPUs. Use all since the system is otherwise idle now. - */ - max_threads = max(cpumask_weight(cpumask), 1u); + max_threads = deferred_page_init_max_threads(cpumask); while (spfn < epfn) { unsigned long epfn_align = ALIGN(epfn, PAGES_PER_SECTION); -- cgit v1.2.3 From 71a2c112a0f6da497e1b44e18e97b1716c240518 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Wed, 3 Jun 2020 16:00:30 -0700 Subject: khugepaged: introduce 'max_ptes_shared' tunable 'max_ptes_shared' specifies how many pages can be shared across multiple processes. Exceeding the number would block the collapse:: /sys/kernel/mm/transparent_hugepage/khugepaged/max_ptes_shared A higher value may increase memory footprint for some workloads. By default, at least half of pages has to be not shared. [colin.king@canonical.com: fix several spelling mistakes] Link: http://lkml.kernel.org/r/20200420084241.65433-1-colin.king@canonical.com Signed-off-by: Kirill A. Shutemov Signed-off-by: Colin Ian King Signed-off-by: Andrew Morton Tested-by: Zi Yan Reviewed-by: William Kucharski Reviewed-by: Zi Yan Acked-by: Yang Shi Cc: Andrea Arcangeli Cc: John Hubbard Cc: Mike Kravetz Cc: Ralph Campbell Link: http://lkml.kernel.org/r/20200416160026.16538-9-kirill.shutemov@linux.intel.com Signed-off-by: Linus Torvalds --- Documentation/admin-guide/mm/transhuge.rst | 7 +++ include/trace/events/huge_memory.h | 3 +- mm/khugepaged.c | 52 +++++++++++++++++-- tools/testing/selftests/vm/khugepaged.c | 83 ++++++++++++++++++++++++++++++ 4 files changed, 140 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/Documentation/admin-guide/mm/transhuge.rst b/Documentation/admin-guide/mm/transhuge.rst index 2f31de8f7c74..6a233e42be08 100644 --- a/Documentation/admin-guide/mm/transhuge.rst +++ b/Documentation/admin-guide/mm/transhuge.rst @@ -220,6 +220,13 @@ memory. A lower value can prevent THPs from being collapsed, resulting fewer pages being collapsed into THPs, and lower memory access performance. +``max_ptes_shared`` specifies how many pages can be shared across multiple +processes. Exceeding the number would block the collapse:: + + /sys/kernel/mm/transparent_hugepage/khugepaged/max_ptes_shared + +A higher value may increase memory footprint for some workloads. + Boot parameter ============== diff --git a/include/trace/events/huge_memory.h b/include/trace/events/huge_memory.h index 70e32ff096ec..4fdb14a81108 100644 --- a/include/trace/events/huge_memory.h +++ b/include/trace/events/huge_memory.h @@ -12,6 +12,8 @@ EM( SCAN_SUCCEED, "succeeded") \ EM( SCAN_PMD_NULL, "pmd_null") \ EM( SCAN_EXCEED_NONE_PTE, "exceed_none_pte") \ + EM( SCAN_EXCEED_SWAP_PTE, "exceed_swap_pte") \ + EM( SCAN_EXCEED_SHARED_PTE, "exceed_shared_pte") \ EM( SCAN_PTE_NON_PRESENT, "pte_non_present") \ EM( SCAN_PTE_UFFD_WP, "pte_uffd_wp") \ EM( SCAN_PAGE_RO, "no_writable_page") \ @@ -31,7 +33,6 @@ EM( SCAN_DEL_PAGE_LRU, "could_not_delete_page_from_lru")\ EM( SCAN_ALLOC_HUGE_PAGE_FAIL, "alloc_huge_page_failed") \ EM( SCAN_CGROUP_CHARGE_FAIL, "ccgroup_charge_failed") \ - EM( SCAN_EXCEED_SWAP_PTE, "exceed_swap_pte") \ EM( SCAN_TRUNCATED, "truncated") \ EMe(SCAN_PAGE_HAS_PRIVATE, "page_has_private") \ diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 1bae66327f82..e7897a7dfbec 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -28,6 +28,8 @@ enum scan_result { SCAN_SUCCEED, SCAN_PMD_NULL, SCAN_EXCEED_NONE_PTE, + SCAN_EXCEED_SWAP_PTE, + SCAN_EXCEED_SHARED_PTE, SCAN_PTE_NON_PRESENT, SCAN_PTE_UFFD_WP, SCAN_PAGE_RO, @@ -47,7 +49,6 @@ enum scan_result { SCAN_DEL_PAGE_LRU, SCAN_ALLOC_HUGE_PAGE_FAIL, SCAN_CGROUP_CHARGE_FAIL, - SCAN_EXCEED_SWAP_PTE, SCAN_TRUNCATED, SCAN_PAGE_HAS_PRIVATE, }; @@ -72,6 +73,7 @@ static DECLARE_WAIT_QUEUE_HEAD(khugepaged_wait); */ static unsigned int khugepaged_max_ptes_none __read_mostly; static unsigned int khugepaged_max_ptes_swap __read_mostly; +static unsigned int khugepaged_max_ptes_shared __read_mostly; #define MM_SLOTS_HASH_BITS 10 static __read_mostly DEFINE_HASHTABLE(mm_slots_hash, MM_SLOTS_HASH_BITS); @@ -291,15 +293,43 @@ static struct kobj_attribute khugepaged_max_ptes_swap_attr = __ATTR(max_ptes_swap, 0644, khugepaged_max_ptes_swap_show, khugepaged_max_ptes_swap_store); +static ssize_t khugepaged_max_ptes_shared_show(struct kobject *kobj, + struct kobj_attribute *attr, + char *buf) +{ + return sprintf(buf, "%u\n", khugepaged_max_ptes_shared); +} + +static ssize_t khugepaged_max_ptes_shared_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + int err; + unsigned long max_ptes_shared; + + err = kstrtoul(buf, 10, &max_ptes_shared); + if (err || max_ptes_shared > HPAGE_PMD_NR-1) + return -EINVAL; + + khugepaged_max_ptes_shared = max_ptes_shared; + + return count; +} + +static struct kobj_attribute khugepaged_max_ptes_shared_attr = + __ATTR(max_ptes_shared, 0644, khugepaged_max_ptes_shared_show, + khugepaged_max_ptes_shared_store); + static struct attribute *khugepaged_attr[] = { &khugepaged_defrag_attr.attr, &khugepaged_max_ptes_none_attr.attr, + &khugepaged_max_ptes_swap_attr.attr, + &khugepaged_max_ptes_shared_attr.attr, &pages_to_scan_attr.attr, &pages_collapsed_attr.attr, &full_scans_attr.attr, &scan_sleep_millisecs_attr.attr, &alloc_sleep_millisecs_attr.attr, - &khugepaged_max_ptes_swap_attr.attr, NULL, }; @@ -359,6 +389,7 @@ int __init khugepaged_init(void) khugepaged_pages_to_scan = HPAGE_PMD_NR * 8; khugepaged_max_ptes_none = HPAGE_PMD_NR - 1; khugepaged_max_ptes_swap = HPAGE_PMD_NR / 8; + khugepaged_max_ptes_shared = HPAGE_PMD_NR / 2; return 0; } @@ -557,7 +588,7 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma, { struct page *page = NULL; pte_t *_pte; - int none_or_zero = 0, result = 0, referenced = 0; + int none_or_zero = 0, shared = 0, result = 0, referenced = 0; bool writable = false; for (_pte = pte; _pte < pte+HPAGE_PMD_NR; @@ -585,6 +616,12 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma, VM_BUG_ON_PAGE(!PageAnon(page), page); + if (page_mapcount(page) > 1 && + ++shared > khugepaged_max_ptes_shared) { + result = SCAN_EXCEED_SHARED_PTE; + goto out; + } + if (PageCompound(page)) { struct page *p; page = compound_head(page); @@ -1168,7 +1205,8 @@ static int khugepaged_scan_pmd(struct mm_struct *mm, { pmd_t *pmd; pte_t *pte, *_pte; - int ret = 0, none_or_zero = 0, result = 0, referenced = 0; + int ret = 0, result = 0, referenced = 0; + int none_or_zero = 0, shared = 0; struct page *page = NULL; unsigned long _address; spinlock_t *ptl; @@ -1240,6 +1278,12 @@ static int khugepaged_scan_pmd(struct mm_struct *mm, goto out_unmap; } + if (page_mapcount(page) > 1 && + ++shared > khugepaged_max_ptes_shared) { + result = SCAN_EXCEED_SHARED_PTE; + goto out_unmap; + } + page = compound_head(page); /* diff --git a/tools/testing/selftests/vm/khugepaged.c b/tools/testing/selftests/vm/khugepaged.c index ef67a8a3d784..51b89cedd09d 100644 --- a/tools/testing/selftests/vm/khugepaged.c +++ b/tools/testing/selftests/vm/khugepaged.c @@ -78,6 +78,7 @@ struct khugepaged_settings { unsigned int scan_sleep_millisecs; unsigned int max_ptes_none; unsigned int max_ptes_swap; + unsigned int max_ptes_shared; unsigned long pages_to_scan; }; @@ -277,6 +278,7 @@ static void write_settings(struct settings *settings) khugepaged->scan_sleep_millisecs); write_num("khugepaged/max_ptes_none", khugepaged->max_ptes_none); write_num("khugepaged/max_ptes_swap", khugepaged->max_ptes_swap); + write_num("khugepaged/max_ptes_shared", khugepaged->max_ptes_shared); write_num("khugepaged/pages_to_scan", khugepaged->pages_to_scan); } @@ -313,6 +315,7 @@ static void save_settings(void) read_num("khugepaged/scan_sleep_millisecs"), .max_ptes_none = read_num("khugepaged/max_ptes_none"), .max_ptes_swap = read_num("khugepaged/max_ptes_swap"), + .max_ptes_shared = read_num("khugepaged/max_ptes_shared"), .pages_to_scan = read_num("khugepaged/pages_to_scan"), }; success("OK"); @@ -896,12 +899,90 @@ static void collapse_fork_compound(void) fail("Fail"); fill_memory(p, 0, page_size); + write_num("khugepaged/max_ptes_shared", hpage_pmd_nr - 1); if (wait_for_scan("Collapse PTE table full of compound pages in child", p)) fail("Timeout"); else if (check_huge(p)) success("OK"); else fail("Fail"); + write_num("khugepaged/max_ptes_shared", + default_settings.khugepaged.max_ptes_shared); + + validate_memory(p, 0, hpage_pmd_size); + munmap(p, hpage_pmd_size); + exit(exit_status); + } + + wait(&wstatus); + exit_status += WEXITSTATUS(wstatus); + + printf("Check if parent still has huge page..."); + if (check_huge(p)) + success("OK"); + else + fail("Fail"); + validate_memory(p, 0, hpage_pmd_size); + munmap(p, hpage_pmd_size); +} + +static void collapse_max_ptes_shared() +{ + int max_ptes_shared = read_num("khugepaged/max_ptes_shared"); + int wstatus; + void *p; + + p = alloc_mapping(); + + printf("Allocate huge page..."); + madvise(p, hpage_pmd_size, MADV_HUGEPAGE); + fill_memory(p, 0, hpage_pmd_size); + if (check_huge(p)) + success("OK"); + else + fail("Fail"); + + printf("Share huge page over fork()..."); + if (!fork()) { + /* Do not touch settings on child exit */ + skip_settings_restore = true; + exit_status = 0; + + if (check_huge(p)) + success("OK"); + else + fail("Fail"); + + printf("Trigger CoW on page %d of %d...", + hpage_pmd_nr - max_ptes_shared - 1, hpage_pmd_nr); + fill_memory(p, 0, (hpage_pmd_nr - max_ptes_shared - 1) * page_size); + if (!check_huge(p)) + success("OK"); + else + fail("Fail"); + + if (wait_for_scan("Do not collapse with max_ptes_shared exceeded", p)) + fail("Timeout"); + else if (!check_huge(p)) + success("OK"); + else + fail("Fail"); + + printf("Trigger CoW on page %d of %d...", + hpage_pmd_nr - max_ptes_shared, hpage_pmd_nr); + fill_memory(p, 0, (hpage_pmd_nr - max_ptes_shared) * page_size); + if (!check_huge(p)) + success("OK"); + else + fail("Fail"); + + + if (wait_for_scan("Collapse with max_ptes_shared PTEs shared", p)) + fail("Timeout"); + else if (check_huge(p)) + success("OK"); + else + fail("Fail"); validate_memory(p, 0, hpage_pmd_size); munmap(p, hpage_pmd_size); @@ -930,6 +1011,7 @@ int main(void) default_settings.khugepaged.max_ptes_none = hpage_pmd_nr - 1; default_settings.khugepaged.max_ptes_swap = hpage_pmd_nr / 8; + default_settings.khugepaged.max_ptes_shared = hpage_pmd_nr / 2; default_settings.khugepaged.pages_to_scan = hpage_pmd_nr * 8; save_settings(); @@ -947,6 +1029,7 @@ int main(void) collapse_compound_extreme(); collapse_fork(); collapse_fork_compound(); + collapse_max_ptes_shared(); restore_settings(0); } -- cgit v1.2.3 From ae94da898133947c2d1f005da10838478e4548db Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Wed, 3 Jun 2020 16:00:34 -0700 Subject: hugetlbfs: add arch_hugetlb_valid_size Patch series "Clean up hugetlb boot command line processing", v4. Longpeng(Mike) reported a weird message from hugetlb command line processing and proposed a solution [1]. While the proposed patch does address the specific issue, there are other related issues in command line processing. As hugetlbfs evolved, updates to command line processing have been made to meet immediate needs and not necessarily in a coordinated manner. The result is that some processing is done in arch specific code, some is done in arch independent code and coordination is problematic. Semantics can vary between architectures. The patch series does the following: - Define arch specific arch_hugetlb_valid_size routine used to validate passed huge page sizes. - Move hugepagesz= command line parsing out of arch specific code and into an arch independent routine. - Clean up command line processing to follow desired semantics and document those semantics. [1] https://lore.kernel.org/linux-mm/20200305033014.1152-1-longpeng2@huawei.com This patch (of 3): The architecture independent routine hugetlb_default_setup sets up the default huge pages size. It has no way to verify if the passed value is valid, so it accepts it and attempts to validate at a later time. This requires undocumented cooperation between the arch specific and arch independent code. For architectures that support more than one huge page size, provide a routine arch_hugetlb_valid_size to validate a huge page size. hugetlb_default_setup can use this to validate passed values. arch_hugetlb_valid_size will also be used in a subsequent patch to move processing of the "hugepagesz=" in arch specific code to a common routine in arch independent code. Signed-off-by: Mike Kravetz Signed-off-by: Andrew Morton Acked-by: Gerald Schaefer [s390] Acked-by: Will Deacon Cc: Catalin Marinas Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Paul Walmsley Cc: Palmer Dabbelt Cc: Albert Ou Cc: Heiko Carstens Cc: Vasily Gorbik Cc: Christian Borntraeger Cc: David S. Miller Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Dave Hansen Cc: Jonathan Corbet Cc: Longpeng Cc: Christophe Leroy Cc: Randy Dunlap Cc: Mina Almasry Cc: Peter Xu Cc: Nitesh Narayan Lal Cc: Anders Roxell Cc: "Aneesh Kumar K.V" Cc: Qian Cai Cc: Stephen Rothwell Link: http://lkml.kernel.org/r/20200428205614.246260-1-mike.kravetz@oracle.com Link: http://lkml.kernel.org/r/20200428205614.246260-2-mike.kravetz@oracle.com Link: http://lkml.kernel.org/r/20200417185049.275845-1-mike.kravetz@oracle.com Link: http://lkml.kernel.org/r/20200417185049.275845-2-mike.kravetz@oracle.com Signed-off-by: Linus Torvalds --- arch/arm64/mm/hugetlbpage.c | 17 +++++++++++++---- arch/powerpc/mm/hugetlbpage.c | 20 +++++++++++++------- arch/riscv/mm/hugetlbpage.c | 26 +++++++++++++++++--------- arch/s390/mm/hugetlbpage.c | 16 ++++++++++++---- arch/sparc/mm/init_64.c | 24 ++++++++++++++++-------- arch/x86/mm/hugetlbpage.c | 17 +++++++++++++---- include/linux/hugetlb.h | 1 + mm/hugetlb.c | 21 ++++++++++++++++++--- 8 files changed, 103 insertions(+), 39 deletions(-) (limited to 'include') diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c index 0be3355e3499..2ac41cefe699 100644 --- a/arch/arm64/mm/hugetlbpage.c +++ b/arch/arm64/mm/hugetlbpage.c @@ -464,17 +464,26 @@ static int __init hugetlbpage_init(void) } arch_initcall(hugetlbpage_init); -static __init int setup_hugepagesz(char *opt) +bool __init arch_hugetlb_valid_size(unsigned long size) { - unsigned long ps = memparse(opt, &opt); - - switch (ps) { + switch (size) { #ifdef CONFIG_ARM64_4K_PAGES case PUD_SIZE: #endif case CONT_PMD_SIZE: case PMD_SIZE: case CONT_PTE_SIZE: + return true; + } + + return false; +} + +static __init int setup_hugepagesz(char *opt) +{ + unsigned long ps = memparse(opt, &opt); + + if (arch_hugetlb_valid_size(ps)) { add_huge_page_size(ps); return 1; } diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index 33b3461d91e8..de54d2a37830 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -558,7 +558,7 @@ unsigned long vma_mmu_pagesize(struct vm_area_struct *vma) return vma_kernel_pagesize(vma); } -static int __init add_huge_page_size(unsigned long long size) +bool __init arch_hugetlb_valid_size(unsigned long size) { int shift = __ffs(size); int mmu_psize; @@ -566,20 +566,26 @@ static int __init add_huge_page_size(unsigned long long size) /* Check that it is a page size supported by the hardware and * that it fits within pagetable and slice limits. */ if (size <= PAGE_SIZE || !is_power_of_2(size)) - return -EINVAL; + return false; mmu_psize = check_and_get_huge_psize(shift); if (mmu_psize < 0) - return -EINVAL; + return false; BUG_ON(mmu_psize_defs[mmu_psize].shift != shift); - /* Return if huge page size has already been setup */ - if (size_to_hstate(size)) - return 0; + return true; +} - hugetlb_add_hstate(shift - PAGE_SHIFT); +static int __init add_huge_page_size(unsigned long long size) +{ + int shift = __ffs(size); + + if (!arch_hugetlb_valid_size((unsigned long)size)) + return -EINVAL; + if (!size_to_hstate(size)) + hugetlb_add_hstate(shift - PAGE_SHIFT); return 0; } diff --git a/arch/riscv/mm/hugetlbpage.c b/arch/riscv/mm/hugetlbpage.c index a6189ed36c5f..da1f516bc451 100644 --- a/arch/riscv/mm/hugetlbpage.c +++ b/arch/riscv/mm/hugetlbpage.c @@ -12,21 +12,29 @@ int pmd_huge(pmd_t pmd) return pmd_leaf(pmd); } +bool __init arch_hugetlb_valid_size(unsigned long size) +{ + if (size == HPAGE_SIZE) + return true; + else if (IS_ENABLED(CONFIG_64BIT) && size == PUD_SIZE) + return true; + else + return false; +} + static __init int setup_hugepagesz(char *opt) { unsigned long ps = memparse(opt, &opt); - if (ps == HPAGE_SIZE) { - hugetlb_add_hstate(HPAGE_SHIFT - PAGE_SHIFT); - } else if (IS_ENABLED(CONFIG_64BIT) && ps == PUD_SIZE) { - hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT); - } else { - hugetlb_bad_size(); - pr_err("hugepagesz: Unsupported page size %lu M\n", ps >> 20); - return 0; + if (arch_hugetlb_valid_size(ps)) { + hugetlb_add_hstate(ilog2(ps) - PAGE_SHIFT); + return 1; } - return 1; + hugetlb_bad_size(); + pr_err("hugepagesz: Unsupported page size %lu M\n", ps >> 20); + return 0; + } __setup("hugepagesz=", setup_hugepagesz); diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c index 4632d4e26b66..2f2b6b5b3d29 100644 --- a/arch/s390/mm/hugetlbpage.c +++ b/arch/s390/mm/hugetlbpage.c @@ -254,16 +254,24 @@ follow_huge_pud(struct mm_struct *mm, unsigned long address, return pud_page(*pud) + ((address & ~PUD_MASK) >> PAGE_SHIFT); } +bool __init arch_hugetlb_valid_size(unsigned long size) +{ + if (MACHINE_HAS_EDAT1 && size == PMD_SIZE) + return true; + else if (MACHINE_HAS_EDAT2 && size == PUD_SIZE) + return true; + else + return false; +} + static __init int setup_hugepagesz(char *opt) { unsigned long size; char *string = opt; size = memparse(opt, &opt); - if (MACHINE_HAS_EDAT1 && size == PMD_SIZE) { - hugetlb_add_hstate(PMD_SHIFT - PAGE_SHIFT); - } else if (MACHINE_HAS_EDAT2 && size == PUD_SIZE) { - hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT); + if (arch_hugetlb_valid_size(size)) { + hugetlb_add_hstate(ilog2(size) - PAGE_SHIFT); } else { hugetlb_bad_size(); pr_err("hugepagesz= specifies an unsupported page size %s\n", diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c index 79d3c5e0802e..24475b73657a 100644 --- a/arch/sparc/mm/init_64.c +++ b/arch/sparc/mm/init_64.c @@ -360,16 +360,11 @@ static void __init pud_huge_patch(void) __asm__ __volatile__("flush %0" : : "r" (addr)); } -static int __init setup_hugepagesz(char *string) +bool __init arch_hugetlb_valid_size(unsigned long size) { - unsigned long long hugepage_size; - unsigned int hugepage_shift; + unsigned int hugepage_shift = ilog2(size); unsigned short hv_pgsz_idx; unsigned int hv_pgsz_mask; - int rc = 0; - - hugepage_size = memparse(string, &string); - hugepage_shift = ilog2(hugepage_size); switch (hugepage_shift) { case HPAGE_16GB_SHIFT: @@ -397,7 +392,20 @@ static int __init setup_hugepagesz(char *string) hv_pgsz_mask = 0; } - if ((hv_pgsz_mask & cpu_pgsz_mask) == 0U) { + if ((hv_pgsz_mask & cpu_pgsz_mask) == 0U) + return false; + + return true; +} + +static int __init setup_hugepagesz(char *string) +{ + unsigned long long hugepage_size; + int rc = 0; + + hugepage_size = memparse(string, &string); + + if (!arch_hugetlb_valid_size((unsigned long)hugepage_size)) { hugetlb_bad_size(); pr_err("hugepagesz=%llu not supported by MMU.\n", hugepage_size); diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c index 5bfd5aef5378..1c4372bfe782 100644 --- a/arch/x86/mm/hugetlbpage.c +++ b/arch/x86/mm/hugetlbpage.c @@ -181,13 +181,22 @@ get_unmapped_area: #endif /* CONFIG_HUGETLB_PAGE */ #ifdef CONFIG_X86_64 +bool __init arch_hugetlb_valid_size(unsigned long size) +{ + if (size == PMD_SIZE) + return true; + else if (size == PUD_SIZE && boot_cpu_has(X86_FEATURE_GBPAGES)) + return true; + else + return false; +} + static __init int setup_hugepagesz(char *opt) { unsigned long ps = memparse(opt, &opt); - if (ps == PMD_SIZE) { - hugetlb_add_hstate(PMD_SHIFT - PAGE_SHIFT); - } else if (ps == PUD_SIZE && boot_cpu_has(X86_FEATURE_GBPAGES)) { - hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT); + + if (arch_hugetlb_valid_size(ps)) { + hugetlb_add_hstate(ilog2(ps) - PAGE_SHIFT); } else { hugetlb_bad_size(); printk(KERN_ERR "hugepagesz: Unsupported page size %lu M\n", diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 43a1cef8f0f1..2eb15f5ab01e 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -521,6 +521,7 @@ int __init alloc_bootmem_huge_page(struct hstate *h); void __init hugetlb_bad_size(void); void __init hugetlb_add_hstate(unsigned order); +bool __init arch_hugetlb_valid_size(unsigned long size); struct hstate *size_to_hstate(unsigned long size); #ifndef HUGE_MAX_HSTATE diff --git a/mm/hugetlb.c b/mm/hugetlb.c index bcabbe02192b..63ca4241ea87 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -3256,6 +3256,12 @@ static int __init hugetlb_init(void) } subsys_initcall(hugetlb_init); +/* Overwritten by architectures with more huge page sizes */ +bool __init __attribute((weak)) arch_hugetlb_valid_size(unsigned long size) +{ + return size == HPAGE_SIZE; +} + /* Should be called on processing a hugepagesz=... option */ void __init hugetlb_bad_size(void) { @@ -3331,12 +3337,21 @@ static int __init hugetlb_nrpages_setup(char *s) } __setup("hugepages=", hugetlb_nrpages_setup); -static int __init hugetlb_default_setup(char *s) +static int __init default_hugepagesz_setup(char *s) { - default_hstate_size = memparse(s, &s); + unsigned long size; + + size = (unsigned long)memparse(s, NULL); + + if (!arch_hugetlb_valid_size(size)) { + pr_err("HugeTLB: unsupported default_hugepagesz %s\n", s); + return 0; + } + + default_hstate_size = size; return 1; } -__setup("default_hugepagesz=", hugetlb_default_setup); +__setup("default_hugepagesz=", default_hugepagesz_setup); static unsigned int cpuset_mems_nr(unsigned int *array) { -- cgit v1.2.3 From 359f25443a8dada0fb709dd044a422017031790f Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Wed, 3 Jun 2020 16:00:38 -0700 Subject: hugetlbfs: move hugepagesz= parsing to arch independent code Now that architectures provide arch_hugetlb_valid_size(), parsing of "hugepagesz=" can be done in architecture independent code. Create a single routine to handle hugepagesz= parsing and remove all arch specific routines. We can also remove the interface hugetlb_bad_size() as this is no longer used outside arch independent code. This also provides consistent behavior of hugetlbfs command line options. The hugepagesz= option should only be specified once for a specific size, but some architectures allow multiple instances. This appears to be more of an oversight when code was added by some architectures to set up ALL huge pages sizes. Signed-off-by: Mike Kravetz Signed-off-by: Andrew Morton Tested-by: Sandipan Das Reviewed-by: Peter Xu Acked-by: Mina Almasry Acked-by: Gerald Schaefer [s390] Acked-by: Will Deacon Cc: Albert Ou Cc: Benjamin Herrenschmidt Cc: Catalin Marinas Cc: Christian Borntraeger Cc: Christophe Leroy Cc: Dave Hansen Cc: David S. Miller Cc: Heiko Carstens Cc: Ingo Molnar Cc: Jonathan Corbet Cc: Longpeng Cc: Nitesh Narayan Lal Cc: Palmer Dabbelt Cc: Paul Mackerras Cc: Paul Walmsley Cc: Randy Dunlap Cc: Thomas Gleixner Cc: Vasily Gorbik Cc: Anders Roxell Cc: "Aneesh Kumar K.V" Cc: Qian Cai Cc: Stephen Rothwell Link: http://lkml.kernel.org/r/20200417185049.275845-3-mike.kravetz@oracle.com Link: http://lkml.kernel.org/r/20200428205614.246260-3-mike.kravetz@oracle.com Signed-off-by: Linus Torvalds --- arch/arm64/mm/hugetlbpage.c | 15 --------------- arch/powerpc/mm/hugetlbpage.c | 15 --------------- arch/riscv/mm/hugetlbpage.c | 16 ---------------- arch/s390/mm/hugetlbpage.c | 18 ------------------ arch/sparc/mm/init_64.c | 22 ---------------------- arch/x86/mm/hugetlbpage.c | 16 ---------------- include/linux/hugetlb.h | 1 - mm/hugetlb.c | 23 +++++++++++++++++------ 8 files changed, 17 insertions(+), 109 deletions(-) (limited to 'include') diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c index 2ac41cefe699..d6cb9fe71b44 100644 --- a/arch/arm64/mm/hugetlbpage.c +++ b/arch/arm64/mm/hugetlbpage.c @@ -478,18 +478,3 @@ bool __init arch_hugetlb_valid_size(unsigned long size) return false; } - -static __init int setup_hugepagesz(char *opt) -{ - unsigned long ps = memparse(opt, &opt); - - if (arch_hugetlb_valid_size(ps)) { - add_huge_page_size(ps); - return 1; - } - - hugetlb_bad_size(); - pr_err("hugepagesz: Unsupported page size %lu K\n", ps >> 10); - return 0; -} -__setup("hugepagesz=", setup_hugepagesz); diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index de54d2a37830..2c3fa0a7787b 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -589,21 +589,6 @@ static int __init add_huge_page_size(unsigned long long size) return 0; } -static int __init hugepage_setup_sz(char *str) -{ - unsigned long long size; - - size = memparse(str, &str); - - if (add_huge_page_size(size) != 0) { - hugetlb_bad_size(); - pr_err("Invalid huge page size specified(%llu)\n", size); - } - - return 1; -} -__setup("hugepagesz=", hugepage_setup_sz); - static int __init hugetlbpage_init(void) { bool configured = false; diff --git a/arch/riscv/mm/hugetlbpage.c b/arch/riscv/mm/hugetlbpage.c index da1f516bc451..4e5d7e9f0eef 100644 --- a/arch/riscv/mm/hugetlbpage.c +++ b/arch/riscv/mm/hugetlbpage.c @@ -22,22 +22,6 @@ bool __init arch_hugetlb_valid_size(unsigned long size) return false; } -static __init int setup_hugepagesz(char *opt) -{ - unsigned long ps = memparse(opt, &opt); - - if (arch_hugetlb_valid_size(ps)) { - hugetlb_add_hstate(ilog2(ps) - PAGE_SHIFT); - return 1; - } - - hugetlb_bad_size(); - pr_err("hugepagesz: Unsupported page size %lu M\n", ps >> 20); - return 0; - -} -__setup("hugepagesz=", setup_hugepagesz); - #ifdef CONFIG_CONTIG_ALLOC static __init int gigantic_pages_init(void) { diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c index 2f2b6b5b3d29..82df06d720e8 100644 --- a/arch/s390/mm/hugetlbpage.c +++ b/arch/s390/mm/hugetlbpage.c @@ -264,24 +264,6 @@ bool __init arch_hugetlb_valid_size(unsigned long size) return false; } -static __init int setup_hugepagesz(char *opt) -{ - unsigned long size; - char *string = opt; - - size = memparse(opt, &opt); - if (arch_hugetlb_valid_size(size)) { - hugetlb_add_hstate(ilog2(size) - PAGE_SHIFT); - } else { - hugetlb_bad_size(); - pr_err("hugepagesz= specifies an unsupported page size %s\n", - string); - return 0; - } - return 1; -} -__setup("hugepagesz=", setup_hugepagesz); - static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c index 24475b73657a..1b1f1ac1869e 100644 --- a/arch/sparc/mm/init_64.c +++ b/arch/sparc/mm/init_64.c @@ -397,28 +397,6 @@ bool __init arch_hugetlb_valid_size(unsigned long size) return true; } - -static int __init setup_hugepagesz(char *string) -{ - unsigned long long hugepage_size; - int rc = 0; - - hugepage_size = memparse(string, &string); - - if (!arch_hugetlb_valid_size((unsigned long)hugepage_size)) { - hugetlb_bad_size(); - pr_err("hugepagesz=%llu not supported by MMU.\n", - hugepage_size); - goto out; - } - - add_huge_page_size(hugepage_size); - rc = 1; - -out: - return rc; -} -__setup("hugepagesz=", setup_hugepagesz); #endif /* CONFIG_HUGETLB_PAGE */ void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c index 1c4372bfe782..937d640a89e3 100644 --- a/arch/x86/mm/hugetlbpage.c +++ b/arch/x86/mm/hugetlbpage.c @@ -191,22 +191,6 @@ bool __init arch_hugetlb_valid_size(unsigned long size) return false; } -static __init int setup_hugepagesz(char *opt) -{ - unsigned long ps = memparse(opt, &opt); - - if (arch_hugetlb_valid_size(ps)) { - hugetlb_add_hstate(ilog2(ps) - PAGE_SHIFT); - } else { - hugetlb_bad_size(); - printk(KERN_ERR "hugepagesz: Unsupported page size %lu M\n", - ps >> 20); - return 0; - } - return 1; -} -__setup("hugepagesz=", setup_hugepagesz); - #ifdef CONFIG_CONTIG_ALLOC static __init int gigantic_pages_init(void) { diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 2eb15f5ab01e..0c13706054ef 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -519,7 +519,6 @@ int huge_add_to_page_cache(struct page *page, struct address_space *mapping, int __init __alloc_bootmem_huge_page(struct hstate *h); int __init alloc_bootmem_huge_page(struct hstate *h); -void __init hugetlb_bad_size(void); void __init hugetlb_add_hstate(unsigned order); bool __init arch_hugetlb_valid_size(unsigned long size); struct hstate *size_to_hstate(unsigned long size); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 63ca4241ea87..6a8454bc2917 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -3262,12 +3262,6 @@ bool __init __attribute((weak)) arch_hugetlb_valid_size(unsigned long size) return size == HPAGE_SIZE; } -/* Should be called on processing a hugepagesz=... option */ -void __init hugetlb_bad_size(void) -{ - parsed_valid_hugepagesz = false; -} - void __init hugetlb_add_hstate(unsigned int order) { struct hstate *h; @@ -3337,6 +3331,23 @@ static int __init hugetlb_nrpages_setup(char *s) } __setup("hugepages=", hugetlb_nrpages_setup); +static int __init hugepagesz_setup(char *s) +{ + unsigned long size; + + size = (unsigned long)memparse(s, NULL); + + if (!arch_hugetlb_valid_size(size)) { + parsed_valid_hugepagesz = false; + pr_err("HugeTLB: unsupported hugepagesz %s\n", s); + return 0; + } + + hugetlb_add_hstate(ilog2(size) - PAGE_SHIFT); + return 1; +} +__setup("hugepagesz=", hugepagesz_setup); + static int __init default_hugepagesz_setup(char *s) { unsigned long size; -- cgit v1.2.3 From be51e3fde5c10f269c065fdca2caf28e4708e21e Mon Sep 17 00:00:00 2001 From: Anshuman Khandual Date: Wed, 3 Jun 2020 16:00:56 -0700 Subject: arm64/mm: drop __HAVE_ARCH_HUGE_PTEP_GET Patch series "mm/hugetlb: Add some new generic fallbacks", v3. This series adds the following new generic fallbacks. Before that it drops __HAVE_ARCH_HUGE_PTEP_GET from arm64 platform. 1. is_hugepage_only_range() 2. arch_clear_hugepage_flags() After this arm (32 bit) remains the sole platform defining it's own huge_ptep_get() via __HAVE_ARCH_HUGE_PTEP_GET. This patch (of 3): Platform specific huge_ptep_get() is required only when fetching the huge PTE involves more than just dereferencing the page table pointer. This is not the case on arm64 platform. Hence huge_ptep_pte() can be dropped along with it's __HAVE_ARCH_HUGE_PTEP_GET subscription. Before that, it updates the generic huge_ptep_get() with READ_ONCE() which will prevent known page table issues with THP on arm64. Signed-off-by: Anshuman Khandual Signed-off-by: Andrew Morton Acked-by: Mike Kravetz Cc: Catalin Marinas Cc: Will Deacon Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Christian Borntraeger Cc: "David S. Miller" Cc: Fenghua Yu Cc: Heiko Carstens Cc: Helge Deller Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Michael Ellerman Cc: Palmer Dabbelt Cc: Paul Mackerras Cc: Paul Walmsley Cc: Rich Felker Cc: Russell King Cc: Thomas Bogendoerfer Cc: Thomas Gleixner Cc: Tony Luck Cc: Vasily Gorbik Cc: Yoshinori Sato Link: http://lkml.kernel.org/r/1588907271-11920-1-git-send-email-anshuman.khandual@arm.com Link: http://lkml.kernel.org/r//1506527369-19535-1-git-send-email-will.deacon@arm.com/ Link: http://lkml.kernel.org/r/1588907271-11920-2-git-send-email-anshuman.khandual@arm.com Signed-off-by: Linus Torvalds --- arch/arm64/include/asm/hugetlb.h | 6 ------ include/asm-generic/hugetlb.h | 2 +- 2 files changed, 1 insertion(+), 7 deletions(-) (limited to 'include') diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h index 2eb6c234d594..b88878ddc88b 100644 --- a/arch/arm64/include/asm/hugetlb.h +++ b/arch/arm64/include/asm/hugetlb.h @@ -17,12 +17,6 @@ extern bool arch_hugetlb_migration_supported(struct hstate *h); #endif -#define __HAVE_ARCH_HUGE_PTEP_GET -static inline pte_t huge_ptep_get(pte_t *ptep) -{ - return READ_ONCE(*ptep); -} - static inline int is_hugepage_only_range(struct mm_struct *mm, unsigned long addr, unsigned long len) { diff --git a/include/asm-generic/hugetlb.h b/include/asm-generic/hugetlb.h index 822f433ac95c..40f85decc2ee 100644 --- a/include/asm-generic/hugetlb.h +++ b/include/asm-generic/hugetlb.h @@ -122,7 +122,7 @@ static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma, #ifndef __HAVE_ARCH_HUGE_PTEP_GET static inline pte_t huge_ptep_get(pte_t *ptep) { - return *ptep; + return READ_ONCE(*ptep); } #endif -- cgit v1.2.3 From b0eae98c66fe4ccac3a5a79a1479c057f2c7cdd7 Mon Sep 17 00:00:00 2001 From: Anshuman Khandual Date: Wed, 3 Jun 2020 16:01:01 -0700 Subject: mm/hugetlb: define a generic fallback for is_hugepage_only_range() There are multiple similar definitions for is_hugepage_only_range() on various platforms. Lets just add it's generic fallback definition for platforms that do not override. This help reduce code duplication. Signed-off-by: Anshuman Khandual Signed-off-by: Andrew Morton Acked-by: Mike Kravetz Cc: Russell King Cc: Catalin Marinas Cc: Will Deacon Cc: Tony Luck Cc: Fenghua Yu Cc: Thomas Bogendoerfer Cc: "James E.J. Bottomley" Cc: Helge Deller Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Michael Ellerman Cc: Paul Walmsley Cc: Palmer Dabbelt Cc: Heiko Carstens Cc: Vasily Gorbik Cc: Christian Borntraeger Cc: Yoshinori Sato Cc: Rich Felker Cc: "David S. Miller" Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: "H. Peter Anvin" Link: http://lkml.kernel.org/r/1588907271-11920-3-git-send-email-anshuman.khandual@arm.com Signed-off-by: Linus Torvalds --- arch/arm/include/asm/hugetlb.h | 6 ------ arch/arm64/include/asm/hugetlb.h | 6 ------ arch/ia64/include/asm/hugetlb.h | 1 + arch/mips/include/asm/hugetlb.h | 7 ------- arch/parisc/include/asm/hugetlb.h | 6 ------ arch/powerpc/include/asm/hugetlb.h | 1 + arch/riscv/include/asm/hugetlb.h | 6 ------ arch/s390/include/asm/hugetlb.h | 7 ------- arch/sh/include/asm/hugetlb.h | 6 ------ arch/sparc/include/asm/hugetlb.h | 6 ------ arch/x86/include/asm/hugetlb.h | 6 ------ include/linux/hugetlb.h | 9 +++++++++ 12 files changed, 11 insertions(+), 56 deletions(-) (limited to 'include') diff --git a/arch/arm/include/asm/hugetlb.h b/arch/arm/include/asm/hugetlb.h index 318dcf5921ab..9ecd516d1ff7 100644 --- a/arch/arm/include/asm/hugetlb.h +++ b/arch/arm/include/asm/hugetlb.h @@ -14,12 +14,6 @@ #include #include -static inline int is_hugepage_only_range(struct mm_struct *mm, - unsigned long addr, unsigned long len) -{ - return 0; -} - static inline void arch_clear_hugepage_flags(struct page *page) { clear_bit(PG_dcache_clean, &page->flags); diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h index b88878ddc88b..8f58e052697a 100644 --- a/arch/arm64/include/asm/hugetlb.h +++ b/arch/arm64/include/asm/hugetlb.h @@ -17,12 +17,6 @@ extern bool arch_hugetlb_migration_supported(struct hstate *h); #endif -static inline int is_hugepage_only_range(struct mm_struct *mm, - unsigned long addr, unsigned long len) -{ - return 0; -} - static inline void arch_clear_hugepage_flags(struct page *page) { clear_bit(PG_dcache_clean, &page->flags); diff --git a/arch/ia64/include/asm/hugetlb.h b/arch/ia64/include/asm/hugetlb.h index 36cc0396b214..6ef50b9a4bdf 100644 --- a/arch/ia64/include/asm/hugetlb.h +++ b/arch/ia64/include/asm/hugetlb.h @@ -20,6 +20,7 @@ static inline int is_hugepage_only_range(struct mm_struct *mm, return (REGION_NUMBER(addr) == RGN_HPAGE || REGION_NUMBER((addr)+(len)-1) == RGN_HPAGE); } +#define is_hugepage_only_range is_hugepage_only_range #define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH static inline void huge_ptep_clear_flush(struct vm_area_struct *vma, diff --git a/arch/mips/include/asm/hugetlb.h b/arch/mips/include/asm/hugetlb.h index 425bb6fc3bda..8b201e281f67 100644 --- a/arch/mips/include/asm/hugetlb.h +++ b/arch/mips/include/asm/hugetlb.h @@ -11,13 +11,6 @@ #include -static inline int is_hugepage_only_range(struct mm_struct *mm, - unsigned long addr, - unsigned long len) -{ - return 0; -} - #define __HAVE_ARCH_PREPARE_HUGEPAGE_RANGE static inline int prepare_hugepage_range(struct file *file, unsigned long addr, diff --git a/arch/parisc/include/asm/hugetlb.h b/arch/parisc/include/asm/hugetlb.h index 7cb595dcb7d7..411d9d867baa 100644 --- a/arch/parisc/include/asm/hugetlb.h +++ b/arch/parisc/include/asm/hugetlb.h @@ -12,12 +12,6 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep); -static inline int is_hugepage_only_range(struct mm_struct *mm, - unsigned long addr, - unsigned long len) { - return 0; -} - /* * If the arch doesn't supply something else, assume that hugepage * size aligned regions are ok without further preparation. diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h index bd6504c28c2f..b167c869d72d 100644 --- a/arch/powerpc/include/asm/hugetlb.h +++ b/arch/powerpc/include/asm/hugetlb.h @@ -30,6 +30,7 @@ static inline int is_hugepage_only_range(struct mm_struct *mm, return slice_is_hugepage_only_range(mm, addr, len); return 0; } +#define is_hugepage_only_range is_hugepage_only_range #define __HAVE_ARCH_HUGETLB_FREE_PGD_RANGE void hugetlb_free_pgd_range(struct mmu_gather *tlb, unsigned long addr, diff --git a/arch/riscv/include/asm/hugetlb.h b/arch/riscv/include/asm/hugetlb.h index 728a5db66597..866f6ae6467c 100644 --- a/arch/riscv/include/asm/hugetlb.h +++ b/arch/riscv/include/asm/hugetlb.h @@ -5,12 +5,6 @@ #include #include -static inline int is_hugepage_only_range(struct mm_struct *mm, - unsigned long addr, - unsigned long len) { - return 0; -} - static inline void arch_clear_hugepage_flags(struct page *page) { } diff --git a/arch/s390/include/asm/hugetlb.h b/arch/s390/include/asm/hugetlb.h index de8f0bf5f238..7d27ea96ec2f 100644 --- a/arch/s390/include/asm/hugetlb.h +++ b/arch/s390/include/asm/hugetlb.h @@ -21,13 +21,6 @@ pte_t huge_ptep_get(pte_t *ptep); pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep); -static inline bool is_hugepage_only_range(struct mm_struct *mm, - unsigned long addr, - unsigned long len) -{ - return false; -} - /* * If the arch doesn't supply something else, assume that hugepage * size aligned regions are ok without further preparation. diff --git a/arch/sh/include/asm/hugetlb.h b/arch/sh/include/asm/hugetlb.h index 6f025fe18146..536ad2cb8aa4 100644 --- a/arch/sh/include/asm/hugetlb.h +++ b/arch/sh/include/asm/hugetlb.h @@ -5,12 +5,6 @@ #include #include -static inline int is_hugepage_only_range(struct mm_struct *mm, - unsigned long addr, - unsigned long len) { - return 0; -} - /* * If the arch doesn't supply something else, assume that hugepage * size aligned regions are ok without further preparation. diff --git a/arch/sparc/include/asm/hugetlb.h b/arch/sparc/include/asm/hugetlb.h index 3963f80d1cb3..a056fe1119f5 100644 --- a/arch/sparc/include/asm/hugetlb.h +++ b/arch/sparc/include/asm/hugetlb.h @@ -20,12 +20,6 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep); -static inline int is_hugepage_only_range(struct mm_struct *mm, - unsigned long addr, - unsigned long len) { - return 0; -} - #define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH static inline void huge_ptep_clear_flush(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) diff --git a/arch/x86/include/asm/hugetlb.h b/arch/x86/include/asm/hugetlb.h index f65cfb48cfdd..cc98f79074d0 100644 --- a/arch/x86/include/asm/hugetlb.h +++ b/arch/x86/include/asm/hugetlb.h @@ -7,12 +7,6 @@ #define hugepages_supported() boot_cpu_has(X86_FEATURE_PSE) -static inline int is_hugepage_only_range(struct mm_struct *mm, - unsigned long addr, - unsigned long len) { - return 0; -} - static inline void arch_clear_hugepage_flags(struct page *page) { } diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 0c13706054ef..bf97b17ab206 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -591,6 +591,15 @@ static inline unsigned int blocks_per_huge_page(struct hstate *h) #include +#ifndef is_hugepage_only_range +static inline int is_hugepage_only_range(struct mm_struct *mm, + unsigned long addr, unsigned long len) +{ + return 0; +} +#define is_hugepage_only_range is_hugepage_only_range +#endif + #ifndef arch_make_huge_pte static inline pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma, struct page *page, int writable) -- cgit v1.2.3 From 5be993432821750f382809df5e20bf4c129b24f7 Mon Sep 17 00:00:00 2001 From: Anshuman Khandual Date: Wed, 3 Jun 2020 16:01:05 -0700 Subject: mm/hugetlb: define a generic fallback for arch_clear_hugepage_flags() There are multiple similar definitions for arch_clear_hugepage_flags() on various platforms. Lets just add it's generic fallback definition for platforms that do not override. This help reduce code duplication. Signed-off-by: Anshuman Khandual Signed-off-by: Andrew Morton Acked-by: Mike Kravetz Cc: Russell King Cc: Catalin Marinas Cc: Will Deacon Cc: Tony Luck Cc: Fenghua Yu Cc: Thomas Bogendoerfer Cc: "James E.J. Bottomley" Cc: Helge Deller Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Michael Ellerman Cc: Paul Walmsley Cc: Palmer Dabbelt Cc: Heiko Carstens Cc: Vasily Gorbik Cc: Christian Borntraeger Cc: Yoshinori Sato Cc: Rich Felker Cc: "David S. Miller" Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: "H. Peter Anvin" Link: http://lkml.kernel.org/r/1588907271-11920-4-git-send-email-anshuman.khandual@arm.com Signed-off-by: Linus Torvalds --- arch/arm/include/asm/hugetlb.h | 1 + arch/arm64/include/asm/hugetlb.h | 1 + arch/ia64/include/asm/hugetlb.h | 4 ---- arch/mips/include/asm/hugetlb.h | 4 ---- arch/parisc/include/asm/hugetlb.h | 4 ---- arch/powerpc/include/asm/hugetlb.h | 4 ---- arch/riscv/include/asm/hugetlb.h | 4 ---- arch/s390/include/asm/hugetlb.h | 1 + arch/sh/include/asm/hugetlb.h | 1 + arch/sparc/include/asm/hugetlb.h | 4 ---- arch/x86/include/asm/hugetlb.h | 4 ---- include/linux/hugetlb.h | 5 +++++ 12 files changed, 9 insertions(+), 28 deletions(-) (limited to 'include') diff --git a/arch/arm/include/asm/hugetlb.h b/arch/arm/include/asm/hugetlb.h index 9ecd516d1ff7..d02d6ca88e92 100644 --- a/arch/arm/include/asm/hugetlb.h +++ b/arch/arm/include/asm/hugetlb.h @@ -18,5 +18,6 @@ static inline void arch_clear_hugepage_flags(struct page *page) { clear_bit(PG_dcache_clean, &page->flags); } +#define arch_clear_hugepage_flags arch_clear_hugepage_flags #endif /* _ASM_ARM_HUGETLB_H */ diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h index 8f58e052697a..94ba0c5bced2 100644 --- a/arch/arm64/include/asm/hugetlb.h +++ b/arch/arm64/include/asm/hugetlb.h @@ -21,6 +21,7 @@ static inline void arch_clear_hugepage_flags(struct page *page) { clear_bit(PG_dcache_clean, &page->flags); } +#define arch_clear_hugepage_flags arch_clear_hugepage_flags extern pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma, struct page *page, int writable); diff --git a/arch/ia64/include/asm/hugetlb.h b/arch/ia64/include/asm/hugetlb.h index 6ef50b9a4bdf..7e46ebde8c0c 100644 --- a/arch/ia64/include/asm/hugetlb.h +++ b/arch/ia64/include/asm/hugetlb.h @@ -28,10 +28,6 @@ static inline void huge_ptep_clear_flush(struct vm_area_struct *vma, { } -static inline void arch_clear_hugepage_flags(struct page *page) -{ -} - #include #endif /* _ASM_IA64_HUGETLB_H */ diff --git a/arch/mips/include/asm/hugetlb.h b/arch/mips/include/asm/hugetlb.h index 8b201e281f67..10e3be870df7 100644 --- a/arch/mips/include/asm/hugetlb.h +++ b/arch/mips/include/asm/hugetlb.h @@ -75,10 +75,6 @@ static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma, return changed; } -static inline void arch_clear_hugepage_flags(struct page *page) -{ -} - #include #endif /* __ASM_HUGETLB_H */ diff --git a/arch/parisc/include/asm/hugetlb.h b/arch/parisc/include/asm/hugetlb.h index 411d9d867baa..a69cf9efb0c1 100644 --- a/arch/parisc/include/asm/hugetlb.h +++ b/arch/parisc/include/asm/hugetlb.h @@ -42,10 +42,6 @@ int huge_ptep_set_access_flags(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t pte, int dirty); -static inline void arch_clear_hugepage_flags(struct page *page) -{ -} - #include #endif /* _ASM_PARISC64_HUGETLB_H */ diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h index b167c869d72d..e6dfa63da552 100644 --- a/arch/powerpc/include/asm/hugetlb.h +++ b/arch/powerpc/include/asm/hugetlb.h @@ -61,10 +61,6 @@ int huge_ptep_set_access_flags(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t pte, int dirty); -static inline void arch_clear_hugepage_flags(struct page *page) -{ -} - #include #else /* ! CONFIG_HUGETLB_PAGE */ diff --git a/arch/riscv/include/asm/hugetlb.h b/arch/riscv/include/asm/hugetlb.h index 866f6ae6467c..a5c2ca1d1cd8 100644 --- a/arch/riscv/include/asm/hugetlb.h +++ b/arch/riscv/include/asm/hugetlb.h @@ -5,8 +5,4 @@ #include #include -static inline void arch_clear_hugepage_flags(struct page *page) -{ -} - #endif /* _ASM_RISCV_HUGETLB_H */ diff --git a/arch/s390/include/asm/hugetlb.h b/arch/s390/include/asm/hugetlb.h index 7d27ea96ec2f..9ddf4a43a590 100644 --- a/arch/s390/include/asm/hugetlb.h +++ b/arch/s390/include/asm/hugetlb.h @@ -39,6 +39,7 @@ static inline void arch_clear_hugepage_flags(struct page *page) { clear_bit(PG_arch_1, &page->flags); } +#define arch_clear_hugepage_flags arch_clear_hugepage_flags static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned long sz) diff --git a/arch/sh/include/asm/hugetlb.h b/arch/sh/include/asm/hugetlb.h index 536ad2cb8aa4..ae4de7b89210 100644 --- a/arch/sh/include/asm/hugetlb.h +++ b/arch/sh/include/asm/hugetlb.h @@ -30,6 +30,7 @@ static inline void arch_clear_hugepage_flags(struct page *page) { clear_bit(PG_dcache_clean, &page->flags); } +#define arch_clear_hugepage_flags arch_clear_hugepage_flags #include diff --git a/arch/sparc/include/asm/hugetlb.h b/arch/sparc/include/asm/hugetlb.h index a056fe1119f5..53838a173f62 100644 --- a/arch/sparc/include/asm/hugetlb.h +++ b/arch/sparc/include/asm/hugetlb.h @@ -47,10 +47,6 @@ static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma, return changed; } -static inline void arch_clear_hugepage_flags(struct page *page) -{ -} - #define __HAVE_ARCH_HUGETLB_FREE_PGD_RANGE void hugetlb_free_pgd_range(struct mmu_gather *tlb, unsigned long addr, unsigned long end, unsigned long floor, diff --git a/arch/x86/include/asm/hugetlb.h b/arch/x86/include/asm/hugetlb.h index cc98f79074d0..1721b1aadeb1 100644 --- a/arch/x86/include/asm/hugetlb.h +++ b/arch/x86/include/asm/hugetlb.h @@ -7,8 +7,4 @@ #define hugepages_supported() boot_cpu_has(X86_FEATURE_PSE) -static inline void arch_clear_hugepage_flags(struct page *page) -{ -} - #endif /* _ASM_X86_HUGETLB_H */ diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index bf97b17ab206..2e66b71c1236 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -600,6 +600,11 @@ static inline int is_hugepage_only_range(struct mm_struct *mm, #define is_hugepage_only_range is_hugepage_only_range #endif +#ifndef arch_clear_hugepage_flags +static inline void arch_clear_hugepage_flags(struct page *page) { } +#define arch_clear_hugepage_flags arch_clear_hugepage_flags +#endif + #ifndef arch_make_huge_pte static inline pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma, struct page *page, int writable) -- cgit v1.2.3 From ff45fc3ca0f3c38e752d75f71b8d8efcf409e42d Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Wed, 3 Jun 2020 16:01:09 -0700 Subject: mm: simplify calling a compound page destructor None of the three callers of get_compound_page_dtor() want to know the value; they just want to call the function. Replace it with destroy_compound_page() which calls the dtor for them. Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton Reviewed-by: Anshuman Khandual Reviewed-by: David Hildenbrand Acked-by: Kirill A. Shutemov Link: http://lkml.kernel.org/r/20200517105051.9352-1-willy@infradead.org Signed-off-by: Linus Torvalds --- include/linux/mm.h | 4 ++-- mm/swap.c | 5 +---- mm/vmscan.c | 4 ++-- 3 files changed, 5 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index 32f3c17715ac..ff73187c3fd4 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -876,10 +876,10 @@ static inline void set_compound_page_dtor(struct page *page, page[1].compound_dtor = compound_dtor; } -static inline compound_page_dtor *get_compound_page_dtor(struct page *page) +static inline void destroy_compound_page(struct page *page) { VM_BUG_ON_PAGE(page[1].compound_dtor >= NR_COMPOUND_DTORS, page); - return compound_page_dtors[page[1].compound_dtor]; + compound_page_dtors[page[1].compound_dtor](page); } static inline unsigned int compound_order(struct page *page) diff --git a/mm/swap.c b/mm/swap.c index 0ac463d44cff..6e454a5c5ab9 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -102,8 +102,6 @@ static void __put_single_page(struct page *page) static void __put_compound_page(struct page *page) { - compound_page_dtor *dtor; - /* * __page_cache_release() is supposed to be called for thp, not for * hugetlb. This is because hugetlb page does never have PageLRU set @@ -112,8 +110,7 @@ static void __put_compound_page(struct page *page) */ if (!PageHuge(page)) __page_cache_release(page); - dtor = get_compound_page_dtor(page); - (*dtor)(page); + destroy_compound_page(page); } void __put_page(struct page *page) diff --git a/mm/vmscan.c b/mm/vmscan.c index 18bfbee9a581..1d1d25306ca2 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1438,7 +1438,7 @@ free_it: * appear not as the counts should be low */ if (unlikely(PageTransHuge(page))) - (*get_compound_page_dtor(page))(page); + destroy_compound_page(page); else list_add(&page->lru, &free_pages); continue; @@ -1859,7 +1859,7 @@ static unsigned noinline_for_stack move_pages_to_lru(struct lruvec *lruvec, if (unlikely(PageCompound(page))) { spin_unlock_irq(&pgdat->lru_lock); - (*get_compound_page_dtor(page))(page); + destroy_compound_page(page); spin_lock_irq(&pgdat->lru_lock); } else list_add(&page->lru, &pages_to_free); -- cgit v1.2.3 From 1f318a9b0dc3990490e98eef48f21e6f15185781 Mon Sep 17 00:00:00 2001 From: Jaewon Kim Date: Wed, 3 Jun 2020 16:01:15 -0700 Subject: mm/vmscan: count layzfree pages and fix nr_isolated_* mismatch Fix an nr_isolate_* mismatch problem between cma and dirty lazyfree pages. If try_to_unmap_one is used for reclaim and it detects a dirty lazyfree page, then the lazyfree page is changed to a normal anon page having SwapBacked by commit 802a3a92ad7a ("mm: reclaim MADV_FREE pages"). Even with the change, reclaim context correctly counts isolated files because it uses is_file_lru to distinguish file. And the change to anon is not happened if try_to_unmap_one is used for migration. So migration context like compaction also correctly counts isolated files even though it uses page_is_file_lru insted of is_file_lru. Recently page_is_file_cache was renamed to page_is_file_lru by commit 9de4f22a60f7 ("mm: code cleanup for MADV_FREE"). But the nr_isolate_* mismatch problem happens on cma alloc. There is reclaim_clean_pages_from_list which is being used only by cma. It was introduced by commit 02c6de8d757c ("mm: cma: discard clean pages during contiguous allocation instead of migration") to reclaim clean file pages without migration. The cma alloc uses both reclaim_clean_pages_from_list and migrate_pages, and it uses page_is_file_lru to count isolated files. If there are dirty lazyfree pages allocated from cma memory region, the pages are counted as isolated file at the beginging but are counted as isolated anon after finished. Mem-Info: Node 0 active_anon:3045904kB inactive_anon:611448kB active_file:14892kB inactive_file:205636kB unevictable:10416kB isolated(anon):0kB isolated(file):37664kB mapped:630216kB dirty:384kB writeback:0kB shmem:42576kB writeback_tmp:0kB unstable:0kB all_unreclaimable? no Like log above, there were too much isolated files, 37664kB, which triggers too_many_isolated in reclaim even when there is no actually isolated file in system wide. It could be reproducible by running two programs, writing on MADV_FREE page and doing cma alloc, respectively. Although isolated anon is 0, I found that the internal value of isolated anon was the negative value of isolated file. Fix this by compensating the isolated count for both LRU lists. Count non-discarded lazyfree pages in shrink_page_list, then compensate the counted number in reclaim_clean_pages_from_list. Reported-by: Yong-Taek Lee Suggested-by: Minchan Kim Signed-off-by: Jaewon Kim Signed-off-by: Andrew Morton Acked-by: Minchan Kim Cc: Mel Gorman Cc: Johannes Weiner Cc: Marek Szyprowski Cc: Michal Nazarewicz Cc: Shaohua Li Link: http://lkml.kernel.org/r/20200426011718.30246-1-jaewon31.kim@samsung.com Signed-off-by: Linus Torvalds --- include/linux/vmstat.h | 1 + mm/vmscan.c | 26 ++++++++++++++++++++------ 2 files changed, 21 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 292485f3d24d..10cc932e209a 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -29,6 +29,7 @@ struct reclaim_stat { unsigned nr_activate[2]; unsigned nr_ref_keep; unsigned nr_unmap_fail; + unsigned nr_lazyfree_fail; }; enum writeback_stat_item { diff --git a/mm/vmscan.c b/mm/vmscan.c index 197eba50e157..8be3d52548ca 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1295,11 +1295,15 @@ static unsigned long shrink_page_list(struct list_head *page_list, */ if (page_mapped(page)) { enum ttu_flags flags = ttu_flags | TTU_BATCH_FLUSH; + bool was_swapbacked = PageSwapBacked(page); if (unlikely(PageTransHuge(page))) flags |= TTU_SPLIT_HUGE_PMD; + if (!try_to_unmap(page, flags)) { stat->nr_unmap_fail += nr_pages; + if (!was_swapbacked && PageSwapBacked(page)) + stat->nr_lazyfree_fail += nr_pages; goto activate_locked; } } @@ -1491,8 +1495,8 @@ unsigned long reclaim_clean_pages_from_list(struct zone *zone, .priority = DEF_PRIORITY, .may_unmap = 1, }; - struct reclaim_stat dummy_stat; - unsigned long ret; + struct reclaim_stat stat; + unsigned long nr_reclaimed; struct page *page, *next; LIST_HEAD(clean_pages); @@ -1504,11 +1508,21 @@ unsigned long reclaim_clean_pages_from_list(struct zone *zone, } } - ret = shrink_page_list(&clean_pages, zone->zone_pgdat, &sc, - TTU_IGNORE_ACCESS, &dummy_stat, true); + nr_reclaimed = shrink_page_list(&clean_pages, zone->zone_pgdat, &sc, + TTU_IGNORE_ACCESS, &stat, true); list_splice(&clean_pages, page_list); - mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE, -ret); - return ret; + mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE, -nr_reclaimed); + /* + * Since lazyfree pages are isolated from file LRU from the beginning, + * they will rotate back to anonymous LRU in the end if it failed to + * discard so isolated count will be mismatched. + * Compensate the isolated count for both LRU lists. + */ + mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_ANON, + stat.nr_lazyfree_fail); + mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE, + -stat.nr_lazyfree_fail); + return nr_reclaimed; } /* -- cgit v1.2.3 From 3fba69a56e16e8dcf182fe6ca77735dd65a898aa Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 3 Jun 2020 16:01:31 -0700 Subject: mm: memcontrol: drop @compound parameter from memcg charging API The memcg charging API carries a boolean @compound parameter that tells whether the page we're dealing with is a hugepage. mem_cgroup_commit_charge() has another boolean @lrucare that indicates whether the page needs LRU locking or not while charging. The majority of callsites know those parameters at compile time, which results in a lot of naked "false, false" argument lists. This makes for cryptic code and is a breeding ground for subtle mistakes. Thankfully, the huge page state can be inferred from the page itself and doesn't need to be passed along. This is safe because charging completes before the page is published and somebody may split it. Simplify the callsites by removing @compound, and let memcg infer the state by using hpage_nr_pages() unconditionally. That function does PageTransHuge() to identify huge pages, which also helpfully asserts that nobody passes in tail pages by accident. The following patches will introduce a new charging API, best not to carry over unnecessary weight. Signed-off-by: Johannes Weiner Signed-off-by: Andrew Morton Reviewed-by: Alex Shi Reviewed-by: Joonsoo Kim Reviewed-by: Shakeel Butt Cc: Hugh Dickins Cc: "Kirill A. Shutemov" Cc: Michal Hocko Cc: Roman Gushchin Cc: Balbir Singh Link: http://lkml.kernel.org/r/20200508183105.225460-4-hannes@cmpxchg.org Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 22 ++++++++-------------- kernel/events/uprobes.c | 6 +++--- mm/filemap.c | 6 +++--- mm/huge_memory.c | 8 ++++---- mm/khugepaged.c | 20 ++++++++++---------- mm/memcontrol.c | 38 +++++++++++++++----------------------- mm/memory.c | 32 +++++++++++++++----------------- mm/migrate.c | 6 +++--- mm/shmem.c | 22 +++++++++------------- mm/swapfile.c | 9 ++++----- mm/userfaultfd.c | 6 +++--- 11 files changed, 77 insertions(+), 98 deletions(-) (limited to 'include') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index bfe9533bb67e..fc400002c7be 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -359,15 +359,12 @@ enum mem_cgroup_protection mem_cgroup_protected(struct mem_cgroup *root, struct mem_cgroup *memcg); int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm, - gfp_t gfp_mask, struct mem_cgroup **memcgp, - bool compound); + gfp_t gfp_mask, struct mem_cgroup **memcgp); int mem_cgroup_try_charge_delay(struct page *page, struct mm_struct *mm, - gfp_t gfp_mask, struct mem_cgroup **memcgp, - bool compound); + gfp_t gfp_mask, struct mem_cgroup **memcgp); void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg, - bool lrucare, bool compound); -void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg, - bool compound); + bool lrucare); +void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg); void mem_cgroup_uncharge(struct page *page); void mem_cgroup_uncharge_list(struct list_head *page_list); @@ -849,8 +846,7 @@ static inline enum mem_cgroup_protection mem_cgroup_protected( static inline int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask, - struct mem_cgroup **memcgp, - bool compound) + struct mem_cgroup **memcgp) { *memcgp = NULL; return 0; @@ -859,8 +855,7 @@ static inline int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm, static inline int mem_cgroup_try_charge_delay(struct page *page, struct mm_struct *mm, gfp_t gfp_mask, - struct mem_cgroup **memcgp, - bool compound) + struct mem_cgroup **memcgp) { *memcgp = NULL; return 0; @@ -868,13 +863,12 @@ static inline int mem_cgroup_try_charge_delay(struct page *page, static inline void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg, - bool lrucare, bool compound) + bool lrucare) { } static inline void mem_cgroup_cancel_charge(struct page *page, - struct mem_cgroup *memcg, - bool compound) + struct mem_cgroup *memcg) { } diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index ece7e13f6e4a..40e7488ce467 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -169,7 +169,7 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr, if (new_page) { err = mem_cgroup_try_charge(new_page, vma->vm_mm, GFP_KERNEL, - &memcg, false); + &memcg); if (err) return err; } @@ -181,7 +181,7 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr, err = -EAGAIN; if (!page_vma_mapped_walk(&pvmw)) { if (new_page) - mem_cgroup_cancel_charge(new_page, memcg, false); + mem_cgroup_cancel_charge(new_page, memcg); goto unlock; } VM_BUG_ON_PAGE(addr != pvmw.address, old_page); @@ -189,7 +189,7 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr, if (new_page) { get_page(new_page); page_add_new_anon_rmap(new_page, vma, addr, false); - mem_cgroup_commit_charge(new_page, memcg, false, false); + mem_cgroup_commit_charge(new_page, memcg, false); lru_cache_add_active_or_unevictable(new_page, vma); } else /* no new page, just dec_mm_counter for old_page */ diff --git a/mm/filemap.c b/mm/filemap.c index 9af4af660ef1..f268cfffbc6e 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -842,7 +842,7 @@ static int __add_to_page_cache_locked(struct page *page, if (!huge) { error = mem_cgroup_try_charge(page, current->mm, - gfp_mask, &memcg, false); + gfp_mask, &memcg); if (error) return error; } @@ -878,14 +878,14 @@ unlock: goto error; if (!huge) - mem_cgroup_commit_charge(page, memcg, false, false); + mem_cgroup_commit_charge(page, memcg, false); trace_mm_filemap_add_to_page_cache(page); return 0; error: page->mapping = NULL; /* Leave page->index set: truncation relies upon it */ if (!huge) - mem_cgroup_cancel_charge(page, memcg, false); + mem_cgroup_cancel_charge(page, memcg); put_page(page); return xas_error(&xas); } diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 693c0ff2256c..672e34932b53 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -594,7 +594,7 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf, VM_BUG_ON_PAGE(!PageCompound(page), page); - if (mem_cgroup_try_charge_delay(page, vma->vm_mm, gfp, &memcg, true)) { + if (mem_cgroup_try_charge_delay(page, vma->vm_mm, gfp, &memcg)) { put_page(page); count_vm_event(THP_FAULT_FALLBACK); count_vm_event(THP_FAULT_FALLBACK_CHARGE); @@ -630,7 +630,7 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf, vm_fault_t ret2; spin_unlock(vmf->ptl); - mem_cgroup_cancel_charge(page, memcg, true); + mem_cgroup_cancel_charge(page, memcg); put_page(page); pte_free(vma->vm_mm, pgtable); ret2 = handle_userfault(vmf, VM_UFFD_MISSING); @@ -641,7 +641,7 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf, entry = mk_huge_pmd(page, vma->vm_page_prot); entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); page_add_new_anon_rmap(page, vma, haddr, true); - mem_cgroup_commit_charge(page, memcg, false, true); + mem_cgroup_commit_charge(page, memcg, false); lru_cache_add_active_or_unevictable(page, vma); pgtable_trans_huge_deposit(vma->vm_mm, vmf->pmd, pgtable); set_pmd_at(vma->vm_mm, haddr, vmf->pmd, entry); @@ -658,7 +658,7 @@ unlock_release: release: if (pgtable) pte_free(vma->vm_mm, pgtable); - mem_cgroup_cancel_charge(page, memcg, true); + mem_cgroup_cancel_charge(page, memcg); put_page(page); return ret; diff --git a/mm/khugepaged.c b/mm/khugepaged.c index e7897a7dfbec..0a29b51494fd 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -1060,7 +1060,7 @@ static void collapse_huge_page(struct mm_struct *mm, goto out_nolock; } - if (unlikely(mem_cgroup_try_charge(new_page, mm, gfp, &memcg, true))) { + if (unlikely(mem_cgroup_try_charge(new_page, mm, gfp, &memcg))) { result = SCAN_CGROUP_CHARGE_FAIL; goto out_nolock; } @@ -1068,7 +1068,7 @@ static void collapse_huge_page(struct mm_struct *mm, down_read(&mm->mmap_sem); result = hugepage_vma_revalidate(mm, address, &vma); if (result) { - mem_cgroup_cancel_charge(new_page, memcg, true); + mem_cgroup_cancel_charge(new_page, memcg); up_read(&mm->mmap_sem); goto out_nolock; } @@ -1076,7 +1076,7 @@ static void collapse_huge_page(struct mm_struct *mm, pmd = mm_find_pmd(mm, address); if (!pmd) { result = SCAN_PMD_NULL; - mem_cgroup_cancel_charge(new_page, memcg, true); + mem_cgroup_cancel_charge(new_page, memcg); up_read(&mm->mmap_sem); goto out_nolock; } @@ -1088,7 +1088,7 @@ static void collapse_huge_page(struct mm_struct *mm, */ if (unmapped && !__collapse_huge_page_swapin(mm, vma, address, pmd, referenced)) { - mem_cgroup_cancel_charge(new_page, memcg, true); + mem_cgroup_cancel_charge(new_page, memcg); up_read(&mm->mmap_sem); goto out_nolock; } @@ -1176,7 +1176,7 @@ static void collapse_huge_page(struct mm_struct *mm, spin_lock(pmd_ptl); BUG_ON(!pmd_none(*pmd)); page_add_new_anon_rmap(new_page, vma, address, true); - mem_cgroup_commit_charge(new_page, memcg, false, true); + mem_cgroup_commit_charge(new_page, memcg, false); count_memcg_events(memcg, THP_COLLAPSE_ALLOC, 1); lru_cache_add_active_or_unevictable(new_page, vma); pgtable_trans_huge_deposit(mm, pmd, pgtable); @@ -1194,7 +1194,7 @@ out_nolock: trace_mm_collapse_huge_page(mm, isolated, result); return; out: - mem_cgroup_cancel_charge(new_page, memcg, true); + mem_cgroup_cancel_charge(new_page, memcg); goto out_up_write; } @@ -1637,7 +1637,7 @@ static void collapse_file(struct mm_struct *mm, goto out; } - if (unlikely(mem_cgroup_try_charge(new_page, mm, gfp, &memcg, true))) { + if (unlikely(mem_cgroup_try_charge(new_page, mm, gfp, &memcg))) { result = SCAN_CGROUP_CHARGE_FAIL; goto out; } @@ -1650,7 +1650,7 @@ static void collapse_file(struct mm_struct *mm, break; xas_unlock_irq(&xas); if (!xas_nomem(&xas, GFP_KERNEL)) { - mem_cgroup_cancel_charge(new_page, memcg, true); + mem_cgroup_cancel_charge(new_page, memcg); result = SCAN_FAIL; goto out; } @@ -1887,7 +1887,7 @@ xa_unlocked: SetPageUptodate(new_page); page_ref_add(new_page, HPAGE_PMD_NR - 1); - mem_cgroup_commit_charge(new_page, memcg, false, true); + mem_cgroup_commit_charge(new_page, memcg, false); if (is_shmem) { set_page_dirty(new_page); @@ -1942,7 +1942,7 @@ xa_unlocked: VM_BUG_ON(nr_none); xas_unlock_irq(&xas); - mem_cgroup_cancel_charge(new_page, memcg, true); + mem_cgroup_cancel_charge(new_page, memcg); new_page->mapping = NULL; } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 8f95896c5aa1..340c580f8363 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -834,7 +834,7 @@ static unsigned long memcg_events_local(struct mem_cgroup *memcg, int event) static void mem_cgroup_charge_statistics(struct mem_cgroup *memcg, struct page *page, - bool compound, int nr_pages) + int nr_pages) { /* * Here, RSS means 'mapped anon' and anon's SwapCache. Shmem/tmpfs is @@ -848,7 +848,7 @@ static void mem_cgroup_charge_statistics(struct mem_cgroup *memcg, __mod_memcg_state(memcg, NR_SHMEM, nr_pages); } - if (compound) { + if (abs(nr_pages) > 1) { VM_BUG_ON_PAGE(!PageTransHuge(page), page); __mod_memcg_state(memcg, MEMCG_RSS_HUGE, nr_pages); } @@ -5501,9 +5501,9 @@ static int mem_cgroup_move_account(struct page *page, ret = 0; local_irq_disable(); - mem_cgroup_charge_statistics(to, page, compound, nr_pages); + mem_cgroup_charge_statistics(to, page, nr_pages); memcg_check_events(to, page); - mem_cgroup_charge_statistics(from, page, compound, -nr_pages); + mem_cgroup_charge_statistics(from, page, -nr_pages); memcg_check_events(from, page); local_irq_enable(); out_unlock: @@ -6494,7 +6494,6 @@ out: * @mm: mm context of the victim * @gfp_mask: reclaim mode * @memcgp: charged memcg return - * @compound: charge the page as compound or small page * * Try to charge @page to the memcg that @mm belongs to, reclaiming * pages according to @gfp_mask if necessary. @@ -6507,11 +6506,10 @@ out: * with mem_cgroup_cancel_charge() in case page instantiation fails. */ int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm, - gfp_t gfp_mask, struct mem_cgroup **memcgp, - bool compound) + gfp_t gfp_mask, struct mem_cgroup **memcgp) { + unsigned int nr_pages = hpage_nr_pages(page); struct mem_cgroup *memcg = NULL; - unsigned int nr_pages = compound ? hpage_nr_pages(page) : 1; int ret = 0; if (mem_cgroup_disabled()) @@ -6553,13 +6551,12 @@ out: } int mem_cgroup_try_charge_delay(struct page *page, struct mm_struct *mm, - gfp_t gfp_mask, struct mem_cgroup **memcgp, - bool compound) + gfp_t gfp_mask, struct mem_cgroup **memcgp) { struct mem_cgroup *memcg; int ret; - ret = mem_cgroup_try_charge(page, mm, gfp_mask, memcgp, compound); + ret = mem_cgroup_try_charge(page, mm, gfp_mask, memcgp); memcg = *memcgp; mem_cgroup_throttle_swaprate(memcg, page_to_nid(page), gfp_mask); return ret; @@ -6570,7 +6567,6 @@ int mem_cgroup_try_charge_delay(struct page *page, struct mm_struct *mm, * @page: page to charge * @memcg: memcg to charge the page to * @lrucare: page might be on LRU already - * @compound: charge the page as compound or small page * * Finalize a charge transaction started by mem_cgroup_try_charge(), * after page->mapping has been set up. This must happen atomically @@ -6583,9 +6579,9 @@ int mem_cgroup_try_charge_delay(struct page *page, struct mm_struct *mm, * Use mem_cgroup_cancel_charge() to cancel the transaction instead. */ void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg, - bool lrucare, bool compound) + bool lrucare) { - unsigned int nr_pages = compound ? hpage_nr_pages(page) : 1; + unsigned int nr_pages = hpage_nr_pages(page); VM_BUG_ON_PAGE(!page->mapping, page); VM_BUG_ON_PAGE(PageLRU(page) && !lrucare, page); @@ -6603,7 +6599,7 @@ void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg, commit_charge(page, memcg, lrucare); local_irq_disable(); - mem_cgroup_charge_statistics(memcg, page, compound, nr_pages); + mem_cgroup_charge_statistics(memcg, page, nr_pages); memcg_check_events(memcg, page); local_irq_enable(); @@ -6622,14 +6618,12 @@ void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg, * mem_cgroup_cancel_charge - cancel a page charge * @page: page to charge * @memcg: memcg to charge the page to - * @compound: charge the page as compound or small page * * Cancel a charge transaction started by mem_cgroup_try_charge(). */ -void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg, - bool compound) +void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg) { - unsigned int nr_pages = compound ? hpage_nr_pages(page) : 1; + unsigned int nr_pages = hpage_nr_pages(page); if (mem_cgroup_disabled()) return; @@ -6844,8 +6838,7 @@ void mem_cgroup_migrate(struct page *oldpage, struct page *newpage) commit_charge(newpage, memcg, false); local_irq_save(flags); - mem_cgroup_charge_statistics(memcg, newpage, PageTransHuge(newpage), - nr_pages); + mem_cgroup_charge_statistics(memcg, newpage, nr_pages); memcg_check_events(memcg, newpage); local_irq_restore(flags); } @@ -7075,8 +7068,7 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry) * only synchronisation we have for updating the per-CPU variables. */ VM_BUG_ON(!irqs_disabled()); - mem_cgroup_charge_statistics(memcg, page, PageTransHuge(page), - -nr_entries); + mem_cgroup_charge_statistics(memcg, page, -nr_entries); memcg_check_events(memcg, page); if (!mem_cgroup_is_root(memcg)) diff --git a/mm/memory.c b/mm/memory.c index 21438278afca..6b8c5900e9a4 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -2676,7 +2676,7 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) } } - if (mem_cgroup_try_charge_delay(new_page, mm, GFP_KERNEL, &memcg, false)) + if (mem_cgroup_try_charge_delay(new_page, mm, GFP_KERNEL, &memcg)) goto oom_free_new; __SetPageUptodate(new_page); @@ -2711,7 +2711,7 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) */ ptep_clear_flush_notify(vma, vmf->address, vmf->pte); page_add_new_anon_rmap(new_page, vma, vmf->address, false); - mem_cgroup_commit_charge(new_page, memcg, false, false); + mem_cgroup_commit_charge(new_page, memcg, false); lru_cache_add_active_or_unevictable(new_page, vma); /* * We call the notify macro here because, when using secondary @@ -2750,7 +2750,7 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) new_page = old_page; page_copied = 1; } else { - mem_cgroup_cancel_charge(new_page, memcg, false); + mem_cgroup_cancel_charge(new_page, memcg); } if (new_page) @@ -3193,8 +3193,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) goto out_page; } - if (mem_cgroup_try_charge_delay(page, vma->vm_mm, GFP_KERNEL, - &memcg, false)) { + if (mem_cgroup_try_charge_delay(page, vma->vm_mm, GFP_KERNEL, &memcg)) { ret = VM_FAULT_OOM; goto out_page; } @@ -3245,11 +3244,11 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) /* ksm created a completely new copy */ if (unlikely(page != swapcache && swapcache)) { page_add_new_anon_rmap(page, vma, vmf->address, false); - mem_cgroup_commit_charge(page, memcg, false, false); + mem_cgroup_commit_charge(page, memcg, false); lru_cache_add_active_or_unevictable(page, vma); } else { do_page_add_anon_rmap(page, vma, vmf->address, exclusive); - mem_cgroup_commit_charge(page, memcg, true, false); + mem_cgroup_commit_charge(page, memcg, true); activate_page(page); } @@ -3285,7 +3284,7 @@ unlock: out: return ret; out_nomap: - mem_cgroup_cancel_charge(page, memcg, false); + mem_cgroup_cancel_charge(page, memcg); pte_unmap_unlock(vmf->pte, vmf->ptl); out_page: unlock_page(page); @@ -3359,8 +3358,7 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf) if (!page) goto oom; - if (mem_cgroup_try_charge_delay(page, vma->vm_mm, GFP_KERNEL, &memcg, - false)) + if (mem_cgroup_try_charge_delay(page, vma->vm_mm, GFP_KERNEL, &memcg)) goto oom_free_page; /* @@ -3386,14 +3384,14 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf) /* Deliver the page fault to userland, check inside PT lock */ if (userfaultfd_missing(vma)) { pte_unmap_unlock(vmf->pte, vmf->ptl); - mem_cgroup_cancel_charge(page, memcg, false); + mem_cgroup_cancel_charge(page, memcg); put_page(page); return handle_userfault(vmf, VM_UFFD_MISSING); } inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES); page_add_new_anon_rmap(page, vma, vmf->address, false); - mem_cgroup_commit_charge(page, memcg, false, false); + mem_cgroup_commit_charge(page, memcg, false); lru_cache_add_active_or_unevictable(page, vma); setpte: set_pte_at(vma->vm_mm, vmf->address, vmf->pte, entry); @@ -3404,7 +3402,7 @@ unlock: pte_unmap_unlock(vmf->pte, vmf->ptl); return ret; release: - mem_cgroup_cancel_charge(page, memcg, false); + mem_cgroup_cancel_charge(page, memcg); put_page(page); goto unlock; oom_free_page: @@ -3655,7 +3653,7 @@ vm_fault_t alloc_set_pte(struct vm_fault *vmf, struct mem_cgroup *memcg, if (write && !(vma->vm_flags & VM_SHARED)) { inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES); page_add_new_anon_rmap(page, vma, vmf->address, false); - mem_cgroup_commit_charge(page, memcg, false, false); + mem_cgroup_commit_charge(page, memcg, false); lru_cache_add_active_or_unevictable(page, vma); } else { inc_mm_counter_fast(vma->vm_mm, mm_counter_file(page)); @@ -3864,8 +3862,8 @@ static vm_fault_t do_cow_fault(struct vm_fault *vmf) if (!vmf->cow_page) return VM_FAULT_OOM; - if (mem_cgroup_try_charge_delay(vmf->cow_page, vma->vm_mm, GFP_KERNEL, - &vmf->memcg, false)) { + if (mem_cgroup_try_charge_delay(vmf->cow_page, vma->vm_mm, + GFP_KERNEL, &vmf->memcg)) { put_page(vmf->cow_page); return VM_FAULT_OOM; } @@ -3886,7 +3884,7 @@ static vm_fault_t do_cow_fault(struct vm_fault *vmf) goto uncharge_out; return ret; uncharge_out: - mem_cgroup_cancel_charge(vmf->cow_page, vmf->memcg, false); + mem_cgroup_cancel_charge(vmf->cow_page, vmf->memcg); put_page(vmf->cow_page); return ret; } diff --git a/mm/migrate.c b/mm/migrate.c index 846af96b84a5..93c732213d12 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -2780,7 +2780,7 @@ static void migrate_vma_insert_page(struct migrate_vma *migrate, if (unlikely(anon_vma_prepare(vma))) goto abort; - if (mem_cgroup_try_charge(page, vma->vm_mm, GFP_KERNEL, &memcg, false)) + if (mem_cgroup_try_charge(page, vma->vm_mm, GFP_KERNEL, &memcg)) goto abort; /* @@ -2826,7 +2826,7 @@ static void migrate_vma_insert_page(struct migrate_vma *migrate, inc_mm_counter(mm, MM_ANONPAGES); page_add_new_anon_rmap(page, vma, addr, false); - mem_cgroup_commit_charge(page, memcg, false, false); + mem_cgroup_commit_charge(page, memcg, false); if (!is_zone_device_page(page)) lru_cache_add_active_or_unevictable(page, vma); get_page(page); @@ -2848,7 +2848,7 @@ static void migrate_vma_insert_page(struct migrate_vma *migrate, unlock_abort: pte_unmap_unlock(ptep, ptl); - mem_cgroup_cancel_charge(page, memcg, false); + mem_cgroup_cancel_charge(page, memcg); abort: *src &= ~MIGRATE_PFN_MIGRATE; } diff --git a/mm/shmem.c b/mm/shmem.c index bd8840082c94..d505b6cce4ab 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1664,8 +1664,7 @@ static int shmem_swapin_page(struct inode *inode, pgoff_t index, goto failed; } - error = mem_cgroup_try_charge_delay(page, charge_mm, gfp, &memcg, - false); + error = mem_cgroup_try_charge_delay(page, charge_mm, gfp, &memcg); if (!error) { error = shmem_add_to_page_cache(page, mapping, index, swp_to_radix_entry(swap), gfp); @@ -1680,14 +1679,14 @@ static int shmem_swapin_page(struct inode *inode, pgoff_t index, * the rest. */ if (error) { - mem_cgroup_cancel_charge(page, memcg, false); + mem_cgroup_cancel_charge(page, memcg); delete_from_swap_cache(page); } } if (error) goto failed; - mem_cgroup_commit_charge(page, memcg, true, false); + mem_cgroup_commit_charge(page, memcg, true); spin_lock_irq(&info->lock); info->swapped--; @@ -1859,8 +1858,7 @@ alloc_nohuge: if (sgp == SGP_WRITE) __SetPageReferenced(page); - error = mem_cgroup_try_charge_delay(page, charge_mm, gfp, &memcg, - PageTransHuge(page)); + error = mem_cgroup_try_charge_delay(page, charge_mm, gfp, &memcg); if (error) { if (PageTransHuge(page)) { count_vm_event(THP_FILE_FALLBACK); @@ -1871,12 +1869,10 @@ alloc_nohuge: error = shmem_add_to_page_cache(page, mapping, hindex, NULL, gfp & GFP_RECLAIM_MASK); if (error) { - mem_cgroup_cancel_charge(page, memcg, - PageTransHuge(page)); + mem_cgroup_cancel_charge(page, memcg); goto unacct; } - mem_cgroup_commit_charge(page, memcg, false, - PageTransHuge(page)); + mem_cgroup_commit_charge(page, memcg, false); lru_cache_add_anon(page); spin_lock_irq(&info->lock); @@ -2364,7 +2360,7 @@ static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, if (unlikely(offset >= max_off)) goto out_release; - ret = mem_cgroup_try_charge_delay(page, dst_mm, gfp, &memcg, false); + ret = mem_cgroup_try_charge_delay(page, dst_mm, gfp, &memcg); if (ret) goto out_release; @@ -2373,7 +2369,7 @@ static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, if (ret) goto out_release_uncharge; - mem_cgroup_commit_charge(page, memcg, false, false); + mem_cgroup_commit_charge(page, memcg, false); _dst_pte = mk_pte(page, dst_vma->vm_page_prot); if (dst_vma->vm_flags & VM_WRITE) @@ -2424,7 +2420,7 @@ out_release_uncharge_unlock: ClearPageDirty(page); delete_from_page_cache(page); out_release_uncharge: - mem_cgroup_cancel_charge(page, memcg, false); + mem_cgroup_cancel_charge(page, memcg); out_release: unlock_page(page); put_page(page); diff --git a/mm/swapfile.c b/mm/swapfile.c index 63ac67208453..40a80617cb03 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -1902,15 +1902,14 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd, if (unlikely(!page)) return -ENOMEM; - if (mem_cgroup_try_charge(page, vma->vm_mm, GFP_KERNEL, - &memcg, false)) { + if (mem_cgroup_try_charge(page, vma->vm_mm, GFP_KERNEL, &memcg)) { ret = -ENOMEM; goto out_nolock; } pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); if (unlikely(!pte_same_as_swp(*pte, swp_entry_to_pte(entry)))) { - mem_cgroup_cancel_charge(page, memcg, false); + mem_cgroup_cancel_charge(page, memcg); ret = 0; goto out; } @@ -1922,10 +1921,10 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd, pte_mkold(mk_pte(page, vma->vm_page_prot))); if (page == swapcache) { page_add_anon_rmap(page, vma, addr, false); - mem_cgroup_commit_charge(page, memcg, true, false); + mem_cgroup_commit_charge(page, memcg, true); } else { /* ksm created a completely new copy */ page_add_new_anon_rmap(page, vma, addr, false); - mem_cgroup_commit_charge(page, memcg, false, false); + mem_cgroup_commit_charge(page, memcg, false); lru_cache_add_active_or_unevictable(page, vma); } swap_free(entry); diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 512576e171ce..bb57d0a3fca7 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -97,7 +97,7 @@ static int mcopy_atomic_pte(struct mm_struct *dst_mm, __SetPageUptodate(page); ret = -ENOMEM; - if (mem_cgroup_try_charge(page, dst_mm, GFP_KERNEL, &memcg, false)) + if (mem_cgroup_try_charge(page, dst_mm, GFP_KERNEL, &memcg)) goto out_release; _dst_pte = pte_mkdirty(mk_pte(page, dst_vma->vm_page_prot)); @@ -124,7 +124,7 @@ static int mcopy_atomic_pte(struct mm_struct *dst_mm, inc_mm_counter(dst_mm, MM_ANONPAGES); page_add_new_anon_rmap(page, dst_vma, dst_addr, false); - mem_cgroup_commit_charge(page, memcg, false, false); + mem_cgroup_commit_charge(page, memcg, false); lru_cache_add_active_or_unevictable(page, dst_vma); set_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte); @@ -138,7 +138,7 @@ out: return ret; out_release_uncharge_unlock: pte_unmap_unlock(dst_pte, ptl); - mem_cgroup_cancel_charge(page, memcg, false); + mem_cgroup_cancel_charge(page, memcg); out_release: put_page(page); goto out; -- cgit v1.2.3 From 6caa6a0703e03236f46461342e31ca53d0e3c091 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 3 Jun 2020 16:01:38 -0700 Subject: mm: memcontrol: move out cgroup swaprate throttling The cgroup swaprate throttling is about matching new anon allocations to the rate of available IO when that is being throttled. It's the io controller hooking into the VM, rather than a memory controller thing. Rename mem_cgroup_throttle_swaprate() to cgroup_throttle_swaprate(), and drop the @memcg argument which is only used to check whether the preceding page charge has succeeded and the fault is proceeding. We could decouple the call from mem_cgroup_try_charge() here as well, but that would cause unnecessary churn: the following patches convert all callsites to a new charge API and we'll decouple as we go along. Signed-off-by: Johannes Weiner Signed-off-by: Andrew Morton Reviewed-by: Alex Shi Reviewed-by: Joonsoo Kim Reviewed-by: Shakeel Butt Cc: Hugh Dickins Cc: "Kirill A. Shutemov" Cc: Michal Hocko Cc: Roman Gushchin Cc: Balbir Singh Link: http://lkml.kernel.org/r/20200508183105.225460-5-hannes@cmpxchg.org Signed-off-by: Linus Torvalds --- include/linux/swap.h | 6 ++---- mm/memcontrol.c | 5 ++--- mm/swapfile.c | 14 +++++++------- 3 files changed, 11 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/include/linux/swap.h b/include/linux/swap.h index e92176fc8824..6cea1eb97d45 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -651,11 +651,9 @@ static inline int mem_cgroup_swappiness(struct mem_cgroup *mem) #endif #if defined(CONFIG_SWAP) && defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP) -extern void mem_cgroup_throttle_swaprate(struct mem_cgroup *memcg, int node, - gfp_t gfp_mask); +extern void cgroup_throttle_swaprate(struct page *page, gfp_t gfp_mask); #else -static inline void mem_cgroup_throttle_swaprate(struct mem_cgroup *memcg, - int node, gfp_t gfp_mask) +static inline void cgroup_throttle_swaprate(struct page *page, gfp_t gfp_mask) { } #endif diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 340c580f8363..bc0f55d0cc08 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -6553,12 +6553,11 @@ out: int mem_cgroup_try_charge_delay(struct page *page, struct mm_struct *mm, gfp_t gfp_mask, struct mem_cgroup **memcgp) { - struct mem_cgroup *memcg; int ret; ret = mem_cgroup_try_charge(page, mm, gfp_mask, memcgp); - memcg = *memcgp; - mem_cgroup_throttle_swaprate(memcg, page_to_nid(page), gfp_mask); + if (*memcgp) + cgroup_throttle_swaprate(page, gfp_mask); return ret; } diff --git a/mm/swapfile.c b/mm/swapfile.c index 40a80617cb03..1829fc4b3ca2 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -3798,11 +3798,12 @@ static void free_swap_count_continuations(struct swap_info_struct *si) } #if defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP) -void mem_cgroup_throttle_swaprate(struct mem_cgroup *memcg, int node, - gfp_t gfp_mask) +void cgroup_throttle_swaprate(struct page *page, gfp_t gfp_mask) { struct swap_info_struct *si, *next; - if (!(gfp_mask & __GFP_IO) || !memcg) + int nid = page_to_nid(page); + + if (!(gfp_mask & __GFP_IO)) return; if (!blk_cgroup_congested()) @@ -3816,11 +3817,10 @@ void mem_cgroup_throttle_swaprate(struct mem_cgroup *memcg, int node, return; spin_lock(&swap_avail_lock); - plist_for_each_entry_safe(si, next, &swap_avail_heads[node], - avail_lists[node]) { + plist_for_each_entry_safe(si, next, &swap_avail_heads[nid], + avail_lists[nid]) { if (si->bdev) { - blkcg_schedule_throttle(bdev_get_queue(si->bdev), - true); + blkcg_schedule_throttle(bdev_get_queue(si->bdev), true); break; } } -- cgit v1.2.3 From 3fea5a499d57dec46043fcdb08e38eac1767bb0d Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 3 Jun 2020 16:01:41 -0700 Subject: mm: memcontrol: convert page cache to a new mem_cgroup_charge() API The try/commit/cancel protocol that memcg uses dates back to when pages used to be uncharged upon removal from the page cache, and thus couldn't be committed before the insertion had succeeded. Nowadays, pages are uncharged when they are physically freed; it doesn't matter whether the insertion was successful or not. For the page cache, the transaction dance has become unnecessary. Introduce a mem_cgroup_charge() function that simply charges a newly allocated page to a cgroup and sets up page->mem_cgroup in one single step. If the insertion fails, the caller doesn't have to do anything but free/put the page. Then switch the page cache over to this new API. Subsequent patches will also convert anon pages, but it needs a bit more prep work. Right now, memcg depends on page->mapping being already set up at the time of charging, so that it can maintain its own MEMCG_CACHE and MEMCG_RSS counters. For anon, page->mapping is set under the same pte lock under which the page is publishd, so a single charge point that can block doesn't work there just yet. The following prep patches will replace the private memcg counters with the generic vmstat counters, thus removing the page->mapping dependency, then complete the transition to the new single-point charge API and delete the old transactional scheme. v2: leave shmem swapcache when charging fails to avoid double IO (Joonsoo) v3: rebase on preceeding shmem simplification patch Signed-off-by: Johannes Weiner Signed-off-by: Andrew Morton Reviewed-by: Alex Shi Cc: Hugh Dickins Cc: Joonsoo Kim Cc: "Kirill A. Shutemov" Cc: Michal Hocko Cc: Roman Gushchin Cc: Shakeel Butt Cc: Balbir Singh Link: http://lkml.kernel.org/r/20200508183105.225460-6-hannes@cmpxchg.org Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 10 +++++++ mm/filemap.c | 24 +++++++-------- mm/memcontrol.c | 29 ++++++++++++++++-- mm/shmem.c | 73 +++++++++++++++++++--------------------------- 4 files changed, 77 insertions(+), 59 deletions(-) (limited to 'include') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index fc400002c7be..898925bdd676 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -365,6 +365,10 @@ int mem_cgroup_try_charge_delay(struct page *page, struct mm_struct *mm, void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg, bool lrucare); void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg); + +int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask, + bool lrucare); + void mem_cgroup_uncharge(struct page *page); void mem_cgroup_uncharge_list(struct list_head *page_list); @@ -872,6 +876,12 @@ static inline void mem_cgroup_cancel_charge(struct page *page, { } +static inline int mem_cgroup_charge(struct page *page, struct mm_struct *mm, + gfp_t gfp_mask, bool lrucare) +{ + return 0; +} + static inline void mem_cgroup_uncharge(struct page *page) { } diff --git a/mm/filemap.c b/mm/filemap.c index f268cfffbc6e..38e6a37336a6 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -832,7 +832,6 @@ static int __add_to_page_cache_locked(struct page *page, { XA_STATE(xas, &mapping->i_pages, offset); int huge = PageHuge(page); - struct mem_cgroup *memcg; int error; void *old; @@ -840,17 +839,16 @@ static int __add_to_page_cache_locked(struct page *page, VM_BUG_ON_PAGE(PageSwapBacked(page), page); mapping_set_update(&xas, mapping); - if (!huge) { - error = mem_cgroup_try_charge(page, current->mm, - gfp_mask, &memcg); - if (error) - return error; - } - get_page(page); page->mapping = mapping; page->index = offset; + if (!huge) { + error = mem_cgroup_charge(page, current->mm, gfp_mask, false); + if (error) + goto error; + } + do { xas_lock_irq(&xas); old = xas_load(&xas); @@ -874,20 +872,18 @@ unlock: xas_unlock_irq(&xas); } while (xas_nomem(&xas, gfp_mask & GFP_RECLAIM_MASK)); - if (xas_error(&xas)) + if (xas_error(&xas)) { + error = xas_error(&xas); goto error; + } - if (!huge) - mem_cgroup_commit_charge(page, memcg, false); trace_mm_filemap_add_to_page_cache(page); return 0; error: page->mapping = NULL; /* Leave page->index set: truncation relies upon it */ - if (!huge) - mem_cgroup_cancel_charge(page, memcg); put_page(page); - return xas_error(&xas); + return error; } ALLOW_ERROR_INJECTION(__add_to_page_cache_locked, ERRNO); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index bc0f55d0cc08..c414b7f85e48 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -6637,6 +6637,33 @@ void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg) cancel_charge(memcg, nr_pages); } +/** + * mem_cgroup_charge - charge a newly allocated page to a cgroup + * @page: page to charge + * @mm: mm context of the victim + * @gfp_mask: reclaim mode + * @lrucare: page might be on the LRU already + * + * Try to charge @page to the memcg that @mm belongs to, reclaiming + * pages according to @gfp_mask if necessary. + * + * Returns 0 on success. Otherwise, an error code is returned. + */ +int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask, + bool lrucare) +{ + struct mem_cgroup *memcg; + int ret; + + VM_BUG_ON_PAGE(!page->mapping, page); + + ret = mem_cgroup_try_charge(page, mm, gfp_mask, &memcg); + if (ret) + return ret; + mem_cgroup_commit_charge(page, memcg, lrucare); + return 0; +} + struct uncharge_gather { struct mem_cgroup *memcg; unsigned long pgpgout; @@ -6684,8 +6711,6 @@ static void uncharge_batch(const struct uncharge_gather *ug) static void uncharge_page(struct page *page, struct uncharge_gather *ug) { VM_BUG_ON_PAGE(PageLRU(page), page); - VM_BUG_ON_PAGE(page_count(page) && !is_zone_device_page(page) && - !PageHWPoison(page) , page); if (!page->mem_cgroup) return; diff --git a/mm/shmem.c b/mm/shmem.c index 729bbb3513cd..0d9615723152 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -605,11 +605,13 @@ static inline bool is_huge_enabled(struct shmem_sb_info *sbinfo) */ static int shmem_add_to_page_cache(struct page *page, struct address_space *mapping, - pgoff_t index, void *expected, gfp_t gfp) + pgoff_t index, void *expected, gfp_t gfp, + struct mm_struct *charge_mm) { XA_STATE_ORDER(xas, &mapping->i_pages, index, compound_order(page)); unsigned long i = 0; unsigned long nr = compound_nr(page); + int error; VM_BUG_ON_PAGE(PageTail(page), page); VM_BUG_ON_PAGE(index != round_down(index, nr), page); @@ -621,6 +623,16 @@ static int shmem_add_to_page_cache(struct page *page, page->mapping = mapping; page->index = index; + error = mem_cgroup_charge(page, charge_mm, gfp, PageSwapCache(page)); + if (error) { + if (!PageSwapCache(page) && PageTransHuge(page)) { + count_vm_event(THP_FILE_FALLBACK); + count_vm_event(THP_FILE_FALLBACK_CHARGE); + } + goto error; + } + cgroup_throttle_swaprate(page, gfp); + do { void *entry; xas_lock_irq(&xas); @@ -648,12 +660,15 @@ unlock: } while (xas_nomem(&xas, gfp)); if (xas_error(&xas)) { - page->mapping = NULL; - page_ref_sub(page, nr); - return xas_error(&xas); + error = xas_error(&xas); + goto error; } return 0; +error: + page->mapping = NULL; + page_ref_sub(page, nr); + return error; } /* @@ -1619,7 +1634,6 @@ static int shmem_swapin_page(struct inode *inode, pgoff_t index, struct address_space *mapping = inode->i_mapping; struct shmem_inode_info *info = SHMEM_I(inode); struct mm_struct *charge_mm = vma ? vma->vm_mm : current->mm; - struct mem_cgroup *memcg; struct page *page; swp_entry_t swap; int error; @@ -1664,18 +1678,11 @@ static int shmem_swapin_page(struct inode *inode, pgoff_t index, goto failed; } - error = mem_cgroup_try_charge_delay(page, charge_mm, gfp, &memcg); - if (error) - goto failed; - error = shmem_add_to_page_cache(page, mapping, index, - swp_to_radix_entry(swap), gfp); - if (error) { - mem_cgroup_cancel_charge(page, memcg); + swp_to_radix_entry(swap), gfp, + charge_mm); + if (error) goto failed; - } - - mem_cgroup_commit_charge(page, memcg, true); spin_lock_irq(&info->lock); info->swapped--; @@ -1722,7 +1729,6 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index, struct shmem_inode_info *info = SHMEM_I(inode); struct shmem_sb_info *sbinfo; struct mm_struct *charge_mm; - struct mem_cgroup *memcg; struct page *page; enum sgp_type sgp_huge = sgp; pgoff_t hindex = index; @@ -1847,21 +1853,11 @@ alloc_nohuge: if (sgp == SGP_WRITE) __SetPageReferenced(page); - error = mem_cgroup_try_charge_delay(page, charge_mm, gfp, &memcg); - if (error) { - if (PageTransHuge(page)) { - count_vm_event(THP_FILE_FALLBACK); - count_vm_event(THP_FILE_FALLBACK_CHARGE); - } - goto unacct; - } error = shmem_add_to_page_cache(page, mapping, hindex, - NULL, gfp & GFP_RECLAIM_MASK); - if (error) { - mem_cgroup_cancel_charge(page, memcg); + NULL, gfp & GFP_RECLAIM_MASK, + charge_mm); + if (error) goto unacct; - } - mem_cgroup_commit_charge(page, memcg, false); lru_cache_add_anon(page); spin_lock_irq(&info->lock); @@ -2299,7 +2295,6 @@ static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, struct address_space *mapping = inode->i_mapping; gfp_t gfp = mapping_gfp_mask(mapping); pgoff_t pgoff = linear_page_index(dst_vma, dst_addr); - struct mem_cgroup *memcg; spinlock_t *ptl; void *page_kaddr; struct page *page; @@ -2349,16 +2344,10 @@ static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, if (unlikely(offset >= max_off)) goto out_release; - ret = mem_cgroup_try_charge_delay(page, dst_mm, gfp, &memcg); - if (ret) - goto out_release; - ret = shmem_add_to_page_cache(page, mapping, pgoff, NULL, - gfp & GFP_RECLAIM_MASK); + gfp & GFP_RECLAIM_MASK, dst_mm); if (ret) - goto out_release_uncharge; - - mem_cgroup_commit_charge(page, memcg, false); + goto out_release; _dst_pte = mk_pte(page, dst_vma->vm_page_prot); if (dst_vma->vm_flags & VM_WRITE) @@ -2379,11 +2368,11 @@ static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, ret = -EFAULT; max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); if (unlikely(offset >= max_off)) - goto out_release_uncharge_unlock; + goto out_release_unlock; ret = -EEXIST; if (!pte_none(*dst_pte)) - goto out_release_uncharge_unlock; + goto out_release_unlock; lru_cache_add_anon(page); @@ -2404,12 +2393,10 @@ static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, ret = 0; out: return ret; -out_release_uncharge_unlock: +out_release_unlock: pte_unmap_unlock(dst_pte, ptl); ClearPageDirty(page); delete_from_page_cache(page); -out_release_uncharge: - mem_cgroup_cancel_charge(page, memcg); out_release: unlock_page(page); put_page(page); -- cgit v1.2.3 From 9da7b5216869f80e91f78403a57c72b42357758c Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 3 Jun 2020 16:01:51 -0700 Subject: mm: memcontrol: prepare cgroup vmstat infrastructure for native anon counters Anonymous compound pages can be mapped by ptes, which means that if we want to track NR_MAPPED_ANON, NR_ANON_THPS on a per-cgroup basis, we have to be prepared to see tail pages in our accounting functions. Make mod_lruvec_page_state() and lock_page_memcg() deal with tail pages correctly, namely by redirecting to the head page which has the page->mem_cgroup set up. Signed-off-by: Johannes Weiner Signed-off-by: Andrew Morton Reviewed-by: Joonsoo Kim Cc: Alex Shi Cc: Hugh Dickins Cc: "Kirill A. Shutemov" Cc: Michal Hocko Cc: Roman Gushchin Cc: Shakeel Butt Cc: Balbir Singh Link: http://lkml.kernel.org/r/20200508183105.225460-9-hannes@cmpxchg.org Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 5 +++-- mm/memcontrol.c | 9 ++++++--- 2 files changed, 9 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 898925bdd676..8f00dd755818 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -709,16 +709,17 @@ static inline void mod_lruvec_state(struct lruvec *lruvec, static inline void __mod_lruvec_page_state(struct page *page, enum node_stat_item idx, int val) { + struct page *head = compound_head(page); /* rmap on tail pages */ pg_data_t *pgdat = page_pgdat(page); struct lruvec *lruvec; /* Untracked pages have no memcg, no lruvec. Update only the node */ - if (!page->mem_cgroup) { + if (!head->mem_cgroup) { __mod_node_page_state(pgdat, idx, val); return; } - lruvec = mem_cgroup_lruvec(page->mem_cgroup, pgdat); + lruvec = mem_cgroup_lruvec(head->mem_cgroup, pgdat); __mod_lruvec_state(lruvec, idx, val); } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index f82ae3723760..a875a97067a3 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1981,6 +1981,7 @@ void mem_cgroup_print_oom_group(struct mem_cgroup *memcg) */ struct mem_cgroup *lock_page_memcg(struct page *page) { + struct page *head = compound_head(page); /* rmap on tail pages */ struct mem_cgroup *memcg; unsigned long flags; @@ -2000,7 +2001,7 @@ struct mem_cgroup *lock_page_memcg(struct page *page) if (mem_cgroup_disabled()) return NULL; again: - memcg = page->mem_cgroup; + memcg = head->mem_cgroup; if (unlikely(!memcg)) return NULL; @@ -2008,7 +2009,7 @@ again: return memcg; spin_lock_irqsave(&memcg->move_lock, flags); - if (memcg != page->mem_cgroup) { + if (memcg != head->mem_cgroup) { spin_unlock_irqrestore(&memcg->move_lock, flags); goto again; } @@ -2051,7 +2052,9 @@ void __unlock_page_memcg(struct mem_cgroup *memcg) */ void unlock_page_memcg(struct page *page) { - __unlock_page_memcg(page->mem_cgroup); + struct page *head = compound_head(page); + + __unlock_page_memcg(head->mem_cgroup); } EXPORT_SYMBOL(unlock_page_memcg); -- cgit v1.2.3 From 0d1c20722ab333ac0ac03ae2188922c1021d3abc Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 3 Jun 2020 16:01:54 -0700 Subject: mm: memcontrol: switch to native NR_FILE_PAGES and NR_SHMEM counters Memcg maintains private MEMCG_CACHE and NR_SHMEM counters. This divergence from the generic VM accounting means unnecessary code overhead, and creates a dependency for memcg that page->mapping is set up at the time of charging, so that page types can be told apart. Convert the generic accounting sites to mod_lruvec_page_state and friends to maintain the per-cgroup vmstat counters of NR_FILE_PAGES and NR_SHMEM. The page is already locked in these places, so page->mem_cgroup is stable; we only need minimal tweaks of two mem_cgroup_migrate() calls to ensure it's set up in time. Then replace MEMCG_CACHE with NR_FILE_PAGES and delete the private NR_SHMEM accounting sites. Signed-off-by: Johannes Weiner Signed-off-by: Andrew Morton Reviewed-by: Joonsoo Kim Cc: Alex Shi Cc: Hugh Dickins Cc: "Kirill A. Shutemov" Cc: Michal Hocko Cc: Roman Gushchin Cc: Shakeel Butt Cc: Balbir Singh Link: http://lkml.kernel.org/r/20200508183105.225460-10-hannes@cmpxchg.org Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 3 +-- mm/filemap.c | 17 +++++++++-------- mm/khugepaged.c | 16 +++++++++++----- mm/memcontrol.c | 28 +++++++++++----------------- mm/migrate.c | 15 +++++++++++---- mm/shmem.c | 14 +++++++------- 6 files changed, 50 insertions(+), 43 deletions(-) (limited to 'include') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 8f00dd755818..f6ea68ceed2c 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -29,8 +29,7 @@ struct kmem_cache; /* Cgroup-specific page state, on top of universal node page state */ enum memcg_stat_item { - MEMCG_CACHE = NR_VM_NODE_STAT_ITEMS, - MEMCG_RSS, + MEMCG_RSS = NR_VM_NODE_STAT_ITEMS, MEMCG_RSS_HUGE, MEMCG_SWAP, MEMCG_SOCK, diff --git a/mm/filemap.c b/mm/filemap.c index 38e6a37336a6..a6565890cdf0 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -199,9 +199,9 @@ static void unaccount_page_cache_page(struct address_space *mapping, nr = hpage_nr_pages(page); - __mod_node_page_state(page_pgdat(page), NR_FILE_PAGES, -nr); + __mod_lruvec_page_state(page, NR_FILE_PAGES, -nr); if (PageSwapBacked(page)) { - __mod_node_page_state(page_pgdat(page), NR_SHMEM, -nr); + __mod_lruvec_page_state(page, NR_SHMEM, -nr); if (PageTransHuge(page)) __dec_node_page_state(page, NR_SHMEM_THPS); } else if (PageTransHuge(page)) { @@ -802,21 +802,22 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask) new->mapping = mapping; new->index = offset; + mem_cgroup_migrate(old, new); + xas_lock_irqsave(&xas, flags); xas_store(&xas, new); old->mapping = NULL; /* hugetlb pages do not participate in page cache accounting. */ if (!PageHuge(old)) - __dec_node_page_state(old, NR_FILE_PAGES); + __dec_lruvec_page_state(old, NR_FILE_PAGES); if (!PageHuge(new)) - __inc_node_page_state(new, NR_FILE_PAGES); + __inc_lruvec_page_state(new, NR_FILE_PAGES); if (PageSwapBacked(old)) - __dec_node_page_state(old, NR_SHMEM); + __dec_lruvec_page_state(old, NR_SHMEM); if (PageSwapBacked(new)) - __inc_node_page_state(new, NR_SHMEM); + __inc_lruvec_page_state(new, NR_SHMEM); xas_unlock_irqrestore(&xas, flags); - mem_cgroup_migrate(old, new); if (freepage) freepage(old); put_page(old); @@ -867,7 +868,7 @@ static int __add_to_page_cache_locked(struct page *page, /* hugetlb pages do not participate in page cache accounting */ if (!huge) - __inc_node_page_state(page, NR_FILE_PAGES); + __inc_lruvec_page_state(page, NR_FILE_PAGES); unlock: xas_unlock_irq(&xas); } while (xas_nomem(&xas, gfp_mask & GFP_RECLAIM_MASK)); diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 0a29b51494fd..ddbdc1e3a694 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -1844,12 +1844,18 @@ out_unlock: } if (nr_none) { - struct zone *zone = page_zone(new_page); - - __mod_node_page_state(zone->zone_pgdat, NR_FILE_PAGES, nr_none); + struct lruvec *lruvec; + /* + * XXX: We have started try_charge and pinned the + * memcg, but the page isn't committed yet so we + * cannot use mod_lruvec_page_state(). This hackery + * will be cleaned up when remove the page->mapping + * dependency from memcg and fully charge above. + */ + lruvec = mem_cgroup_lruvec(memcg, page_pgdat(new_page)); + __mod_lruvec_state(lruvec, NR_FILE_PAGES, nr_none); if (is_shmem) - __mod_node_page_state(zone->zone_pgdat, - NR_SHMEM, nr_none); + __mod_lruvec_state(lruvec, NR_SHMEM, nr_none); } xa_locked: diff --git a/mm/memcontrol.c b/mm/memcontrol.c index a875a97067a3..ab3497ba0e35 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -842,11 +842,6 @@ static void mem_cgroup_charge_statistics(struct mem_cgroup *memcg, */ if (PageAnon(page)) __mod_memcg_state(memcg, MEMCG_RSS, nr_pages); - else { - __mod_memcg_state(memcg, MEMCG_CACHE, nr_pages); - if (PageSwapBacked(page)) - __mod_memcg_state(memcg, NR_SHMEM, nr_pages); - } if (abs(nr_pages) > 1) { VM_BUG_ON_PAGE(!PageTransHuge(page), page); @@ -1392,7 +1387,7 @@ static char *memory_stat_format(struct mem_cgroup *memcg) (u64)memcg_page_state(memcg, MEMCG_RSS) * PAGE_SIZE); seq_buf_printf(&s, "file %llu\n", - (u64)memcg_page_state(memcg, MEMCG_CACHE) * + (u64)memcg_page_state(memcg, NR_FILE_PAGES) * PAGE_SIZE); seq_buf_printf(&s, "kernel_stack %llu\n", (u64)memcg_page_state(memcg, MEMCG_KERNEL_STACK_KB) * @@ -3357,7 +3352,7 @@ static unsigned long mem_cgroup_usage(struct mem_cgroup *memcg, bool swap) unsigned long val; if (mem_cgroup_is_root(memcg)) { - val = memcg_page_state(memcg, MEMCG_CACHE) + + val = memcg_page_state(memcg, NR_FILE_PAGES) + memcg_page_state(memcg, MEMCG_RSS); if (swap) val += memcg_page_state(memcg, MEMCG_SWAP); @@ -3828,7 +3823,7 @@ static int memcg_numa_stat_show(struct seq_file *m, void *v) #endif /* CONFIG_NUMA */ static const unsigned int memcg1_stats[] = { - MEMCG_CACHE, + NR_FILE_PAGES, MEMCG_RSS, MEMCG_RSS_HUGE, NR_SHMEM, @@ -5461,6 +5456,14 @@ static int mem_cgroup_move_account(struct page *page, lock_page_memcg(page); if (!PageAnon(page)) { + __mod_lruvec_state(from_vec, NR_FILE_PAGES, -nr_pages); + __mod_lruvec_state(to_vec, NR_FILE_PAGES, nr_pages); + + if (PageSwapBacked(page)) { + __mod_lruvec_state(from_vec, NR_SHMEM, -nr_pages); + __mod_lruvec_state(to_vec, NR_SHMEM, nr_pages); + } + if (page_mapped(page)) { __mod_lruvec_state(from_vec, NR_FILE_MAPPED, -nr_pages); __mod_lruvec_state(to_vec, NR_FILE_MAPPED, nr_pages); @@ -6673,10 +6676,8 @@ struct uncharge_gather { unsigned long nr_pages; unsigned long pgpgout; unsigned long nr_anon; - unsigned long nr_file; unsigned long nr_kmem; unsigned long nr_huge; - unsigned long nr_shmem; struct page *dummy_page; }; @@ -6700,9 +6701,7 @@ static void uncharge_batch(const struct uncharge_gather *ug) local_irq_save(flags); __mod_memcg_state(ug->memcg, MEMCG_RSS, -ug->nr_anon); - __mod_memcg_state(ug->memcg, MEMCG_CACHE, -ug->nr_file); __mod_memcg_state(ug->memcg, MEMCG_RSS_HUGE, -ug->nr_huge); - __mod_memcg_state(ug->memcg, NR_SHMEM, -ug->nr_shmem); __count_memcg_events(ug->memcg, PGPGOUT, ug->pgpgout); __this_cpu_add(ug->memcg->vmstats_percpu->nr_page_events, ug->nr_pages); memcg_check_events(ug->memcg, ug->dummy_page); @@ -6743,11 +6742,6 @@ static void uncharge_page(struct page *page, struct uncharge_gather *ug) ug->nr_huge += nr_pages; if (PageAnon(page)) ug->nr_anon += nr_pages; - else { - ug->nr_file += nr_pages; - if (PageSwapBacked(page)) - ug->nr_shmem += nr_pages; - } ug->pgpgout++; } else { ug->nr_kmem += nr_pages; diff --git a/mm/migrate.c b/mm/migrate.c index 93c732213d12..0d1f796df75f 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -490,11 +490,18 @@ int migrate_page_move_mapping(struct address_space *mapping, * are mapped to swap space. */ if (newzone != oldzone) { - __dec_node_state(oldzone->zone_pgdat, NR_FILE_PAGES); - __inc_node_state(newzone->zone_pgdat, NR_FILE_PAGES); + struct lruvec *old_lruvec, *new_lruvec; + struct mem_cgroup *memcg; + + memcg = page_memcg(page); + old_lruvec = mem_cgroup_lruvec(memcg, oldzone->zone_pgdat); + new_lruvec = mem_cgroup_lruvec(memcg, newzone->zone_pgdat); + + __dec_lruvec_state(old_lruvec, NR_FILE_PAGES); + __inc_lruvec_state(new_lruvec, NR_FILE_PAGES); if (PageSwapBacked(page) && !PageSwapCache(page)) { - __dec_node_state(oldzone->zone_pgdat, NR_SHMEM); - __inc_node_state(newzone->zone_pgdat, NR_SHMEM); + __dec_lruvec_state(old_lruvec, NR_SHMEM); + __inc_lruvec_state(new_lruvec, NR_SHMEM); } if (dirty && mapping_cap_account_dirty(mapping)) { __dec_node_state(oldzone->zone_pgdat, NR_FILE_DIRTY); diff --git a/mm/shmem.c b/mm/shmem.c index 0d9615723152..71842fd4a9d0 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -653,8 +653,8 @@ next: __inc_node_page_state(page, NR_SHMEM_THPS); } mapping->nrpages += nr; - __mod_node_page_state(page_pgdat(page), NR_FILE_PAGES, nr); - __mod_node_page_state(page_pgdat(page), NR_SHMEM, nr); + __mod_lruvec_page_state(page, NR_FILE_PAGES, nr); + __mod_lruvec_page_state(page, NR_SHMEM, nr); unlock: xas_unlock_irq(&xas); } while (xas_nomem(&xas, gfp)); @@ -685,8 +685,8 @@ static void shmem_delete_from_page_cache(struct page *page, void *radswap) error = shmem_replace_entry(mapping, page->index, page, radswap); page->mapping = NULL; mapping->nrpages--; - __dec_node_page_state(page, NR_FILE_PAGES); - __dec_node_page_state(page, NR_SHMEM); + __dec_lruvec_page_state(page, NR_FILE_PAGES); + __dec_lruvec_page_state(page, NR_SHMEM); xa_unlock_irq(&mapping->i_pages); put_page(page); BUG_ON(error); @@ -1593,8 +1593,9 @@ static int shmem_replace_page(struct page **pagep, gfp_t gfp, xa_lock_irq(&swap_mapping->i_pages); error = shmem_replace_entry(swap_mapping, swap_index, oldpage, newpage); if (!error) { - __inc_node_page_state(newpage, NR_FILE_PAGES); - __dec_node_page_state(oldpage, NR_FILE_PAGES); + mem_cgroup_migrate(oldpage, newpage); + __inc_lruvec_page_state(newpage, NR_FILE_PAGES); + __dec_lruvec_page_state(oldpage, NR_FILE_PAGES); } xa_unlock_irq(&swap_mapping->i_pages); @@ -1606,7 +1607,6 @@ static int shmem_replace_page(struct page **pagep, gfp_t gfp, */ oldpage = newpage; } else { - mem_cgroup_migrate(oldpage, newpage); lru_cache_add_anon(newpage); *pagep = newpage; } -- cgit v1.2.3 From be5d0a74c62d8da43f9526a5b08cdd18e2bbc37a Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 3 Jun 2020 16:01:57 -0700 Subject: mm: memcontrol: switch to native NR_ANON_MAPPED counter Memcg maintains a private MEMCG_RSS counter. This divergence from the generic VM accounting means unnecessary code overhead, and creates a dependency for memcg that page->mapping is set up at the time of charging, so that page types can be told apart. Convert the generic accounting sites to mod_lruvec_page_state and friends to maintain the per-cgroup vmstat counter of NR_ANON_MAPPED. We use lock_page_memcg() to stabilize page->mem_cgroup during rmap changes, the same way we do for NR_FILE_MAPPED. With the previous patch removing MEMCG_CACHE and the private NR_SHMEM counter, this patch finally eliminates the need to have page->mapping set up at charge time. However, we need to have page->mem_cgroup set up by the time rmap runs and does the accounting, so switch the commit and the rmap callbacks around. v2: fix temporary accounting bug by switching rmap<->commit (Joonsoo) Signed-off-by: Johannes Weiner Signed-off-by: Andrew Morton Cc: Alex Shi Cc: Hugh Dickins Cc: Joonsoo Kim Cc: "Kirill A. Shutemov" Cc: Michal Hocko Cc: Roman Gushchin Cc: Shakeel Butt Cc: Balbir Singh Link: http://lkml.kernel.org/r/20200508183105.225460-11-hannes@cmpxchg.org Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 3 +-- kernel/events/uprobes.c | 2 +- mm/huge_memory.c | 2 +- mm/khugepaged.c | 2 +- mm/memcontrol.c | 27 +++++++++----------------- mm/memory.c | 10 +++++----- mm/migrate.c | 2 +- mm/rmap.c | 47 ++++++++++++++++++++++++++++------------------ mm/swapfile.c | 4 ++-- mm/userfaultfd.c | 2 +- 10 files changed, 51 insertions(+), 50 deletions(-) (limited to 'include') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index f6ea68ceed2c..acacc3018957 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -29,8 +29,7 @@ struct kmem_cache; /* Cgroup-specific page state, on top of universal node page state */ enum memcg_stat_item { - MEMCG_RSS = NR_VM_NODE_STAT_ITEMS, - MEMCG_RSS_HUGE, + MEMCG_RSS_HUGE = NR_VM_NODE_STAT_ITEMS, MEMCG_SWAP, MEMCG_SOCK, /* XXX: why are these zone and not node counters? */ diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 40e7488ce467..89ef81b65bcb 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -188,8 +188,8 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr, if (new_page) { get_page(new_page); - page_add_new_anon_rmap(new_page, vma, addr, false); mem_cgroup_commit_charge(new_page, memcg, false); + page_add_new_anon_rmap(new_page, vma, addr, false); lru_cache_add_active_or_unevictable(new_page, vma); } else /* no new page, just dec_mm_counter for old_page */ diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 672e34932b53..2caf2494db66 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -640,8 +640,8 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf, entry = mk_huge_pmd(page, vma->vm_page_prot); entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); - page_add_new_anon_rmap(page, vma, haddr, true); mem_cgroup_commit_charge(page, memcg, false); + page_add_new_anon_rmap(page, vma, haddr, true); lru_cache_add_active_or_unevictable(page, vma); pgtable_trans_huge_deposit(vma->vm_mm, vmf->pmd, pgtable); set_pmd_at(vma->vm_mm, haddr, vmf->pmd, entry); diff --git a/mm/khugepaged.c b/mm/khugepaged.c index ddbdc1e3a694..34eff4dfae80 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -1175,8 +1175,8 @@ static void collapse_huge_page(struct mm_struct *mm, spin_lock(pmd_ptl); BUG_ON(!pmd_none(*pmd)); - page_add_new_anon_rmap(new_page, vma, address, true); mem_cgroup_commit_charge(new_page, memcg, false); + page_add_new_anon_rmap(new_page, vma, address, true); count_memcg_events(memcg, THP_COLLAPSE_ALLOC, 1); lru_cache_add_active_or_unevictable(new_page, vma); pgtable_trans_huge_deposit(mm, pmd, pgtable); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index ab3497ba0e35..b80125303c02 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -836,13 +836,6 @@ static void mem_cgroup_charge_statistics(struct mem_cgroup *memcg, struct page *page, int nr_pages) { - /* - * Here, RSS means 'mapped anon' and anon's SwapCache. Shmem/tmpfs is - * counted as CACHE even if it's on ANON LRU. - */ - if (PageAnon(page)) - __mod_memcg_state(memcg, MEMCG_RSS, nr_pages); - if (abs(nr_pages) > 1) { VM_BUG_ON_PAGE(!PageTransHuge(page), page); __mod_memcg_state(memcg, MEMCG_RSS_HUGE, nr_pages); @@ -1384,7 +1377,7 @@ static char *memory_stat_format(struct mem_cgroup *memcg) */ seq_buf_printf(&s, "anon %llu\n", - (u64)memcg_page_state(memcg, MEMCG_RSS) * + (u64)memcg_page_state(memcg, NR_ANON_MAPPED) * PAGE_SIZE); seq_buf_printf(&s, "file %llu\n", (u64)memcg_page_state(memcg, NR_FILE_PAGES) * @@ -3353,7 +3346,7 @@ static unsigned long mem_cgroup_usage(struct mem_cgroup *memcg, bool swap) if (mem_cgroup_is_root(memcg)) { val = memcg_page_state(memcg, NR_FILE_PAGES) + - memcg_page_state(memcg, MEMCG_RSS); + memcg_page_state(memcg, NR_ANON_MAPPED); if (swap) val += memcg_page_state(memcg, MEMCG_SWAP); } else { @@ -3824,7 +3817,7 @@ static int memcg_numa_stat_show(struct seq_file *m, void *v) static const unsigned int memcg1_stats[] = { NR_FILE_PAGES, - MEMCG_RSS, + NR_ANON_MAPPED, MEMCG_RSS_HUGE, NR_SHMEM, NR_FILE_MAPPED, @@ -5455,7 +5448,12 @@ static int mem_cgroup_move_account(struct page *page, lock_page_memcg(page); - if (!PageAnon(page)) { + if (PageAnon(page)) { + if (page_mapped(page)) { + __mod_lruvec_state(from_vec, NR_ANON_MAPPED, -nr_pages); + __mod_lruvec_state(to_vec, NR_ANON_MAPPED, nr_pages); + } + } else { __mod_lruvec_state(from_vec, NR_FILE_PAGES, -nr_pages); __mod_lruvec_state(to_vec, NR_FILE_PAGES, nr_pages); @@ -6589,7 +6587,6 @@ void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg, { unsigned int nr_pages = hpage_nr_pages(page); - VM_BUG_ON_PAGE(!page->mapping, page); VM_BUG_ON_PAGE(PageLRU(page) && !lrucare, page); if (mem_cgroup_disabled()) @@ -6662,8 +6659,6 @@ int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask, struct mem_cgroup *memcg; int ret; - VM_BUG_ON_PAGE(!page->mapping, page); - ret = mem_cgroup_try_charge(page, mm, gfp_mask, &memcg); if (ret) return ret; @@ -6675,7 +6670,6 @@ struct uncharge_gather { struct mem_cgroup *memcg; unsigned long nr_pages; unsigned long pgpgout; - unsigned long nr_anon; unsigned long nr_kmem; unsigned long nr_huge; struct page *dummy_page; @@ -6700,7 +6694,6 @@ static void uncharge_batch(const struct uncharge_gather *ug) } local_irq_save(flags); - __mod_memcg_state(ug->memcg, MEMCG_RSS, -ug->nr_anon); __mod_memcg_state(ug->memcg, MEMCG_RSS_HUGE, -ug->nr_huge); __count_memcg_events(ug->memcg, PGPGOUT, ug->pgpgout); __this_cpu_add(ug->memcg->vmstats_percpu->nr_page_events, ug->nr_pages); @@ -6740,8 +6733,6 @@ static void uncharge_page(struct page *page, struct uncharge_gather *ug) if (!PageKmemcg(page)) { if (PageTransHuge(page)) ug->nr_huge += nr_pages; - if (PageAnon(page)) - ug->nr_anon += nr_pages; ug->pgpgout++; } else { ug->nr_kmem += nr_pages; diff --git a/mm/memory.c b/mm/memory.c index 6b8c5900e9a4..543e41b1d57a 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -2710,8 +2710,8 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) * thread doing COW. */ ptep_clear_flush_notify(vma, vmf->address, vmf->pte); - page_add_new_anon_rmap(new_page, vma, vmf->address, false); mem_cgroup_commit_charge(new_page, memcg, false); + page_add_new_anon_rmap(new_page, vma, vmf->address, false); lru_cache_add_active_or_unevictable(new_page, vma); /* * We call the notify macro here because, when using secondary @@ -3243,12 +3243,12 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) /* ksm created a completely new copy */ if (unlikely(page != swapcache && swapcache)) { - page_add_new_anon_rmap(page, vma, vmf->address, false); mem_cgroup_commit_charge(page, memcg, false); + page_add_new_anon_rmap(page, vma, vmf->address, false); lru_cache_add_active_or_unevictable(page, vma); } else { - do_page_add_anon_rmap(page, vma, vmf->address, exclusive); mem_cgroup_commit_charge(page, memcg, true); + do_page_add_anon_rmap(page, vma, vmf->address, exclusive); activate_page(page); } @@ -3390,8 +3390,8 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf) } inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES); - page_add_new_anon_rmap(page, vma, vmf->address, false); mem_cgroup_commit_charge(page, memcg, false); + page_add_new_anon_rmap(page, vma, vmf->address, false); lru_cache_add_active_or_unevictable(page, vma); setpte: set_pte_at(vma->vm_mm, vmf->address, vmf->pte, entry); @@ -3652,8 +3652,8 @@ vm_fault_t alloc_set_pte(struct vm_fault *vmf, struct mem_cgroup *memcg, /* copy-on-write page */ if (write && !(vma->vm_flags & VM_SHARED)) { inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES); - page_add_new_anon_rmap(page, vma, vmf->address, false); mem_cgroup_commit_charge(page, memcg, false); + page_add_new_anon_rmap(page, vma, vmf->address, false); lru_cache_add_active_or_unevictable(page, vma); } else { inc_mm_counter_fast(vma->vm_mm, mm_counter_file(page)); diff --git a/mm/migrate.c b/mm/migrate.c index 0d1f796df75f..e72ed681634f 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -2832,8 +2832,8 @@ static void migrate_vma_insert_page(struct migrate_vma *migrate, goto unlock_abort; inc_mm_counter(mm, MM_ANONPAGES); - page_add_new_anon_rmap(page, vma, addr, false); mem_cgroup_commit_charge(page, memcg, false); + page_add_new_anon_rmap(page, vma, addr, false); if (!is_zone_device_page(page)) lru_cache_add_active_or_unevictable(page, vma); get_page(page); diff --git a/mm/rmap.c b/mm/rmap.c index f79a206b271a..150513d31efa 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1114,6 +1114,11 @@ void do_page_add_anon_rmap(struct page *page, bool compound = flags & RMAP_COMPOUND; bool first; + if (unlikely(PageKsm(page))) + lock_page_memcg(page); + else + VM_BUG_ON_PAGE(!PageLocked(page), page); + if (compound) { atomic_t *mapcount; VM_BUG_ON_PAGE(!PageLocked(page), page); @@ -1134,12 +1139,13 @@ void do_page_add_anon_rmap(struct page *page, */ if (compound) __inc_node_page_state(page, NR_ANON_THPS); - __mod_node_page_state(page_pgdat(page), NR_ANON_MAPPED, nr); + __mod_lruvec_page_state(page, NR_ANON_MAPPED, nr); } - if (unlikely(PageKsm(page))) - return; - VM_BUG_ON_PAGE(!PageLocked(page), page); + if (unlikely(PageKsm(page))) { + unlock_page_memcg(page); + return; + } /* address might be in next vma when migration races vma_adjust */ if (first) @@ -1181,7 +1187,7 @@ void page_add_new_anon_rmap(struct page *page, /* increment count (starts at -1) */ atomic_set(&page->_mapcount, 0); } - __mod_node_page_state(page_pgdat(page), NR_ANON_MAPPED, nr); + __mod_lruvec_page_state(page, NR_ANON_MAPPED, nr); __page_set_anon_rmap(page, vma, address, 1); } @@ -1230,13 +1236,12 @@ static void page_remove_file_rmap(struct page *page, bool compound) int i, nr = 1; VM_BUG_ON_PAGE(compound && !PageHead(page), page); - lock_page_memcg(page); /* Hugepages are not counted in NR_FILE_MAPPED for now. */ if (unlikely(PageHuge(page))) { /* hugetlb pages are always mapped with pmds */ atomic_dec(compound_mapcount_ptr(page)); - goto out; + return; } /* page still mapped by someone else? */ @@ -1246,14 +1251,14 @@ static void page_remove_file_rmap(struct page *page, bool compound) nr++; } if (!atomic_add_negative(-1, compound_mapcount_ptr(page))) - goto out; + return; if (PageSwapBacked(page)) __dec_node_page_state(page, NR_SHMEM_PMDMAPPED); else __dec_node_page_state(page, NR_FILE_PMDMAPPED); } else { if (!atomic_add_negative(-1, &page->_mapcount)) - goto out; + return; } /* @@ -1265,8 +1270,6 @@ static void page_remove_file_rmap(struct page *page, bool compound) if (unlikely(PageMlocked(page))) clear_page_mlock(page); -out: - unlock_page_memcg(page); } static void page_remove_anon_compound_rmap(struct page *page) @@ -1310,7 +1313,7 @@ static void page_remove_anon_compound_rmap(struct page *page) clear_page_mlock(page); if (nr) - __mod_node_page_state(page_pgdat(page), NR_ANON_MAPPED, -nr); + __mod_lruvec_page_state(page, NR_ANON_MAPPED, -nr); } /** @@ -1322,22 +1325,28 @@ static void page_remove_anon_compound_rmap(struct page *page) */ void page_remove_rmap(struct page *page, bool compound) { - if (!PageAnon(page)) - return page_remove_file_rmap(page, compound); + lock_page_memcg(page); - if (compound) - return page_remove_anon_compound_rmap(page); + if (!PageAnon(page)) { + page_remove_file_rmap(page, compound); + goto out; + } + + if (compound) { + page_remove_anon_compound_rmap(page); + goto out; + } /* page still mapped by someone else? */ if (!atomic_add_negative(-1, &page->_mapcount)) - return; + goto out; /* * We use the irq-unsafe __{inc|mod}_zone_page_stat because * these counters are not modified in interrupt context, and * pte lock(a spinlock) is held, which implies preemption disabled. */ - __dec_node_page_state(page, NR_ANON_MAPPED); + __dec_lruvec_page_state(page, NR_ANON_MAPPED); if (unlikely(PageMlocked(page))) clear_page_mlock(page); @@ -1354,6 +1363,8 @@ void page_remove_rmap(struct page *page, bool compound) * Leaving it set also helps swapoff to reinstate ptes * faster for those pages still in swapcache. */ +out: + unlock_page_memcg(page); } /* diff --git a/mm/swapfile.c b/mm/swapfile.c index 1829fc4b3ca2..01f6538bad2d 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -1920,11 +1920,11 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd, set_pte_at(vma->vm_mm, addr, pte, pte_mkold(mk_pte(page, vma->vm_page_prot))); if (page == swapcache) { - page_add_anon_rmap(page, vma, addr, false); mem_cgroup_commit_charge(page, memcg, true); + page_add_anon_rmap(page, vma, addr, false); } else { /* ksm created a completely new copy */ - page_add_new_anon_rmap(page, vma, addr, false); mem_cgroup_commit_charge(page, memcg, false); + page_add_new_anon_rmap(page, vma, addr, false); lru_cache_add_active_or_unevictable(page, vma); } swap_free(entry); diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index bb57d0a3fca7..3dea268d2850 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -123,8 +123,8 @@ static int mcopy_atomic_pte(struct mm_struct *dst_mm, goto out_release_uncharge_unlock; inc_mm_counter(dst_mm, MM_ANONPAGES); - page_add_new_anon_rmap(page, dst_vma, dst_addr, false); mem_cgroup_commit_charge(page, memcg, false); + page_add_new_anon_rmap(page, dst_vma, dst_addr, false); lru_cache_add_active_or_unevictable(page, dst_vma); set_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte); -- cgit v1.2.3 From 468c398233da208521a0f84c2068012a66a7489d Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 3 Jun 2020 16:02:01 -0700 Subject: mm: memcontrol: switch to native NR_ANON_THPS counter With rmap memcg locking already in place for NR_ANON_MAPPED, it's just a small step to remove the MEMCG_RSS_HUGE wart and switch memcg to the native NR_ANON_THPS accounting sites. [hannes@cmpxchg.org: fixes] Link: http://lkml.kernel.org/r/20200512121750.GA397968@cmpxchg.org Signed-off-by: Johannes Weiner Signed-off-by: Andrew Morton Tested-by: Naresh Kamboju Reviewed-by: Joonsoo Kim Acked-by: Randy Dunlap [build-tested] Cc: Alex Shi Cc: Hugh Dickins Cc: "Kirill A. Shutemov" Cc: Michal Hocko Cc: Roman Gushchin Cc: Shakeel Butt Cc: Balbir Singh Link: http://lkml.kernel.org/r/20200508183105.225460-12-hannes@cmpxchg.org Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 3 +-- mm/huge_memory.c | 4 +++- mm/memcontrol.c | 47 +++++++++++++++++++++++----------------------- mm/rmap.c | 6 +++--- 4 files changed, 31 insertions(+), 29 deletions(-) (limited to 'include') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index acacc3018957..63a31a6c3c69 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -29,8 +29,7 @@ struct kmem_cache; /* Cgroup-specific page state, on top of universal node page state */ enum memcg_stat_item { - MEMCG_RSS_HUGE = NR_VM_NODE_STAT_ITEMS, - MEMCG_SWAP, + MEMCG_SWAP = NR_VM_NODE_STAT_ITEMS, MEMCG_SOCK, /* XXX: why are these zone and not node counters? */ MEMCG_KERNEL_STACK_KB, diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 2caf2494db66..1fe980dafe03 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2159,15 +2159,17 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, atomic_inc(&page[i]._mapcount); } + lock_page_memcg(page); if (atomic_add_negative(-1, compound_mapcount_ptr(page))) { /* Last compound_mapcount is gone. */ - __dec_node_page_state(page, NR_ANON_THPS); + __dec_lruvec_page_state(page, NR_ANON_THPS); if (TestClearPageDoubleMap(page)) { /* No need in mapcount reference anymore */ for (i = 0; i < HPAGE_PMD_NR; i++) atomic_dec(&page[i]._mapcount); } } + unlock_page_memcg(page); smp_wmb(); /* make pte visible before pmd */ pmd_populate(mm, pmd, pgtable); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index b80125303c02..17587ea2745a 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -836,11 +836,6 @@ static void mem_cgroup_charge_statistics(struct mem_cgroup *memcg, struct page *page, int nr_pages) { - if (abs(nr_pages) > 1) { - VM_BUG_ON_PAGE(!PageTransHuge(page), page); - __mod_memcg_state(memcg, MEMCG_RSS_HUGE, nr_pages); - } - /* pagein of a big page is an event. So, ignore page size */ if (nr_pages > 0) __count_memcg_events(memcg, PGPGIN, 1); @@ -1406,15 +1401,11 @@ static char *memory_stat_format(struct mem_cgroup *memcg) (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. - */ +#ifdef CONFIG_TRANSPARENT_HUGEPAGE seq_buf_printf(&s, "anon_thp %llu\n", - (u64)memcg_page_state(memcg, MEMCG_RSS_HUGE) * - PAGE_SIZE); + (u64)memcg_page_state(memcg, NR_ANON_THPS) * + HPAGE_PMD_SIZE); +#endif for (i = 0; i < NR_LRU_LISTS; i++) seq_buf_printf(&s, "%s %llu\n", lru_list_name(i), @@ -3061,8 +3052,6 @@ void mem_cgroup_split_huge_fixup(struct page *head) for (i = 1; i < HPAGE_PMD_NR; i++) head[i].mem_cgroup = head->mem_cgroup; - - __mod_memcg_state(head->mem_cgroup, MEMCG_RSS_HUGE, -HPAGE_PMD_NR); } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ @@ -3818,7 +3807,9 @@ static int memcg_numa_stat_show(struct seq_file *m, void *v) static const unsigned int memcg1_stats[] = { NR_FILE_PAGES, NR_ANON_MAPPED, - MEMCG_RSS_HUGE, +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + NR_ANON_THPS, +#endif NR_SHMEM, NR_FILE_MAPPED, NR_FILE_DIRTY, @@ -3829,7 +3820,9 @@ static const unsigned int memcg1_stats[] = { static const char *const memcg1_stat_names[] = { "cache", "rss", +#ifdef CONFIG_TRANSPARENT_HUGEPAGE "rss_huge", +#endif "shmem", "mapped_file", "dirty", @@ -3855,11 +3848,16 @@ static int memcg_stat_show(struct seq_file *m, void *v) BUILD_BUG_ON(ARRAY_SIZE(memcg1_stat_names) != ARRAY_SIZE(memcg1_stats)); for (i = 0; i < ARRAY_SIZE(memcg1_stats); i++) { + unsigned long nr; + if (memcg1_stats[i] == MEMCG_SWAP && !do_memsw_account()) continue; - seq_printf(m, "%s %lu\n", memcg1_stat_names[i], - memcg_page_state_local(memcg, memcg1_stats[i]) * - PAGE_SIZE); + nr = memcg_page_state_local(memcg, memcg1_stats[i]); +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + if (memcg1_stats[i] == NR_ANON_THPS) + nr *= HPAGE_PMD_NR; +#endif + seq_printf(m, "%s %lu\n", memcg1_stat_names[i], nr * PAGE_SIZE); } for (i = 0; i < ARRAY_SIZE(memcg1_events); i++) @@ -5452,6 +5450,13 @@ static int mem_cgroup_move_account(struct page *page, if (page_mapped(page)) { __mod_lruvec_state(from_vec, NR_ANON_MAPPED, -nr_pages); __mod_lruvec_state(to_vec, NR_ANON_MAPPED, nr_pages); + if (PageTransHuge(page)) { + __mod_lruvec_state(from_vec, NR_ANON_THPS, + -nr_pages); + __mod_lruvec_state(to_vec, NR_ANON_THPS, + nr_pages); + } + } } else { __mod_lruvec_state(from_vec, NR_FILE_PAGES, -nr_pages); @@ -6671,7 +6676,6 @@ struct uncharge_gather { unsigned long nr_pages; unsigned long pgpgout; unsigned long nr_kmem; - unsigned long nr_huge; struct page *dummy_page; }; @@ -6694,7 +6698,6 @@ static void uncharge_batch(const struct uncharge_gather *ug) } local_irq_save(flags); - __mod_memcg_state(ug->memcg, MEMCG_RSS_HUGE, -ug->nr_huge); __count_memcg_events(ug->memcg, PGPGOUT, ug->pgpgout); __this_cpu_add(ug->memcg->vmstats_percpu->nr_page_events, ug->nr_pages); memcg_check_events(ug->memcg, ug->dummy_page); @@ -6731,8 +6734,6 @@ static void uncharge_page(struct page *page, struct uncharge_gather *ug) ug->nr_pages += nr_pages; if (!PageKmemcg(page)) { - if (PageTransHuge(page)) - ug->nr_huge += nr_pages; ug->pgpgout++; } else { ug->nr_kmem += nr_pages; diff --git a/mm/rmap.c b/mm/rmap.c index 150513d31efa..ad4a0fdcc94c 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1138,7 +1138,7 @@ void do_page_add_anon_rmap(struct page *page, * disabled. */ if (compound) - __inc_node_page_state(page, NR_ANON_THPS); + __inc_lruvec_page_state(page, NR_ANON_THPS); __mod_lruvec_page_state(page, NR_ANON_MAPPED, nr); } @@ -1180,7 +1180,7 @@ void page_add_new_anon_rmap(struct page *page, if (hpage_pincount_available(page)) atomic_set(compound_pincount_ptr(page), 0); - __inc_node_page_state(page, NR_ANON_THPS); + __inc_lruvec_page_state(page, NR_ANON_THPS); } else { /* Anon THP always mapped first with PMD */ VM_BUG_ON_PAGE(PageTransCompound(page), page); @@ -1286,7 +1286,7 @@ static void page_remove_anon_compound_rmap(struct page *page) if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) return; - __dec_node_page_state(page, NR_ANON_THPS); + __dec_lruvec_page_state(page, NR_ANON_THPS); if (TestClearPageDoubleMap(page)) { /* -- cgit v1.2.3 From 9d82c69438d0dff8809061edbcce43a5a4bcf09f Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 3 Jun 2020 16:02:04 -0700 Subject: mm: memcontrol: convert anon and file-thp to new mem_cgroup_charge() API With the page->mapping requirement gone from memcg, we can charge anon and file-thp pages in one single step, right after they're allocated. This removes two out of three API calls - especially the tricky commit step that needed to happen at just the right time between when the page is "set up" and when it's "published" - somewhat vague and fluid concepts that varied by page type. All we need is a freshly allocated page and a memcg context to charge. v2: prevent double charges on pre-allocated hugepages in khugepaged [hannes@cmpxchg.org: Fix crash - *hpage could be ERR_PTR instead of NULL] Link: http://lkml.kernel.org/r/20200512215813.GA487759@cmpxchg.org Signed-off-by: Johannes Weiner Signed-off-by: Andrew Morton Reviewed-by: Joonsoo Kim Cc: Alex Shi Cc: Hugh Dickins Cc: "Kirill A. Shutemov" Cc: Michal Hocko Cc: Roman Gushchin Cc: Shakeel Butt Cc: Balbir Singh Cc: Qian Cai Link: http://lkml.kernel.org/r/20200508183105.225460-13-hannes@cmpxchg.org Signed-off-by: Linus Torvalds --- include/linux/mm.h | 4 +--- kernel/events/uprobes.c | 11 +++-------- mm/filemap.c | 2 +- mm/huge_memory.c | 9 +++------ mm/khugepaged.c | 35 ++++++++++------------------------- mm/memory.c | 36 ++++++++++-------------------------- mm/migrate.c | 5 +---- mm/swapfile.c | 6 +----- mm/userfaultfd.c | 5 +---- 9 files changed, 31 insertions(+), 82 deletions(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index ff73187c3fd4..4ef044fa09fa 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -501,7 +501,6 @@ struct vm_fault { pte_t orig_pte; /* Value of PTE at the time of fault */ struct page *cow_page; /* Page handler may use for COW fault */ - struct mem_cgroup *memcg; /* Cgroup cow_page belongs to */ struct page *page; /* ->fault handlers should return a * page here, unless VM_FAULT_NOPAGE * is set (which is also implied by @@ -946,8 +945,7 @@ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma) return pte; } -vm_fault_t alloc_set_pte(struct vm_fault *vmf, struct mem_cgroup *memcg, - struct page *page); +vm_fault_t alloc_set_pte(struct vm_fault *vmf, struct page *page); vm_fault_t finish_fault(struct vm_fault *vmf); vm_fault_t finish_mkwrite_fault(struct vm_fault *vmf); #endif diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 89ef81b65bcb..4253c153e985 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -162,14 +162,13 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr, }; int err; struct mmu_notifier_range range; - struct mem_cgroup *memcg; mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, mm, addr, addr + PAGE_SIZE); if (new_page) { - err = mem_cgroup_try_charge(new_page, vma->vm_mm, GFP_KERNEL, - &memcg); + err = mem_cgroup_charge(new_page, vma->vm_mm, GFP_KERNEL, + false); if (err) return err; } @@ -179,16 +178,12 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr, mmu_notifier_invalidate_range_start(&range); err = -EAGAIN; - if (!page_vma_mapped_walk(&pvmw)) { - if (new_page) - mem_cgroup_cancel_charge(new_page, memcg); + if (!page_vma_mapped_walk(&pvmw)) goto unlock; - } VM_BUG_ON_PAGE(addr != pvmw.address, old_page); if (new_page) { get_page(new_page); - mem_cgroup_commit_charge(new_page, memcg, false); page_add_new_anon_rmap(new_page, vma, addr, false); lru_cache_add_active_or_unevictable(new_page, vma); } else diff --git a/mm/filemap.c b/mm/filemap.c index a6565890cdf0..f08b0ca34e31 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2633,7 +2633,7 @@ void filemap_map_pages(struct vm_fault *vmf, if (vmf->pte) vmf->pte += xas.xa_index - last_pgoff; last_pgoff = xas.xa_index; - if (alloc_set_pte(vmf, NULL, page)) + if (alloc_set_pte(vmf, page)) goto unlock; unlock_page(page); goto next; diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 1fe980dafe03..e9201a88157e 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -587,19 +587,19 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf, struct page *page, gfp_t gfp) { struct vm_area_struct *vma = vmf->vma; - struct mem_cgroup *memcg; pgtable_t pgtable; unsigned long haddr = vmf->address & HPAGE_PMD_MASK; vm_fault_t ret = 0; VM_BUG_ON_PAGE(!PageCompound(page), page); - if (mem_cgroup_try_charge_delay(page, vma->vm_mm, gfp, &memcg)) { + if (mem_cgroup_charge(page, vma->vm_mm, gfp, false)) { put_page(page); count_vm_event(THP_FAULT_FALLBACK); count_vm_event(THP_FAULT_FALLBACK_CHARGE); return VM_FAULT_FALLBACK; } + cgroup_throttle_swaprate(page, gfp); pgtable = pte_alloc_one(vma->vm_mm); if (unlikely(!pgtable)) { @@ -630,7 +630,6 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf, vm_fault_t ret2; spin_unlock(vmf->ptl); - mem_cgroup_cancel_charge(page, memcg); put_page(page); pte_free(vma->vm_mm, pgtable); ret2 = handle_userfault(vmf, VM_UFFD_MISSING); @@ -640,7 +639,6 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf, entry = mk_huge_pmd(page, vma->vm_page_prot); entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); - mem_cgroup_commit_charge(page, memcg, false); page_add_new_anon_rmap(page, vma, haddr, true); lru_cache_add_active_or_unevictable(page, vma); pgtable_trans_huge_deposit(vma->vm_mm, vmf->pmd, pgtable); @@ -649,7 +647,7 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf, mm_inc_nr_ptes(vma->vm_mm); spin_unlock(vmf->ptl); count_vm_event(THP_FAULT_ALLOC); - count_memcg_events(memcg, THP_FAULT_ALLOC, 1); + count_memcg_event_mm(vma->vm_mm, THP_FAULT_ALLOC); } return 0; @@ -658,7 +656,6 @@ unlock_release: release: if (pgtable) pte_free(vma->vm_mm, pgtable); - mem_cgroup_cancel_charge(page, memcg); put_page(page); return ret; diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 34eff4dfae80..32c85b81837a 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -1037,7 +1037,6 @@ static void collapse_huge_page(struct mm_struct *mm, struct page *new_page; spinlock_t *pmd_ptl, *pte_ptl; int isolated = 0, result = 0; - struct mem_cgroup *memcg; struct vm_area_struct *vma; struct mmu_notifier_range range; gfp_t gfp; @@ -1060,15 +1059,15 @@ static void collapse_huge_page(struct mm_struct *mm, goto out_nolock; } - if (unlikely(mem_cgroup_try_charge(new_page, mm, gfp, &memcg))) { + if (unlikely(mem_cgroup_charge(new_page, mm, gfp, false))) { result = SCAN_CGROUP_CHARGE_FAIL; goto out_nolock; } + count_memcg_page_event(new_page, THP_COLLAPSE_ALLOC); down_read(&mm->mmap_sem); result = hugepage_vma_revalidate(mm, address, &vma); if (result) { - mem_cgroup_cancel_charge(new_page, memcg); up_read(&mm->mmap_sem); goto out_nolock; } @@ -1076,7 +1075,6 @@ static void collapse_huge_page(struct mm_struct *mm, pmd = mm_find_pmd(mm, address); if (!pmd) { result = SCAN_PMD_NULL; - mem_cgroup_cancel_charge(new_page, memcg); up_read(&mm->mmap_sem); goto out_nolock; } @@ -1088,7 +1086,6 @@ static void collapse_huge_page(struct mm_struct *mm, */ if (unmapped && !__collapse_huge_page_swapin(mm, vma, address, pmd, referenced)) { - mem_cgroup_cancel_charge(new_page, memcg); up_read(&mm->mmap_sem); goto out_nolock; } @@ -1175,9 +1172,7 @@ static void collapse_huge_page(struct mm_struct *mm, spin_lock(pmd_ptl); BUG_ON(!pmd_none(*pmd)); - mem_cgroup_commit_charge(new_page, memcg, false); page_add_new_anon_rmap(new_page, vma, address, true); - count_memcg_events(memcg, THP_COLLAPSE_ALLOC, 1); lru_cache_add_active_or_unevictable(new_page, vma); pgtable_trans_huge_deposit(mm, pmd, pgtable); set_pmd_at(mm, address, pmd, _pmd); @@ -1191,10 +1186,11 @@ static void collapse_huge_page(struct mm_struct *mm, out_up_write: up_write(&mm->mmap_sem); out_nolock: + if (!IS_ERR_OR_NULL(*hpage)) + mem_cgroup_uncharge(*hpage); trace_mm_collapse_huge_page(mm, isolated, result); return; out: - mem_cgroup_cancel_charge(new_page, memcg); goto out_up_write; } @@ -1618,7 +1614,6 @@ static void collapse_file(struct mm_struct *mm, struct address_space *mapping = file->f_mapping; gfp_t gfp; struct page *new_page; - struct mem_cgroup *memcg; pgoff_t index, end = start + HPAGE_PMD_NR; LIST_HEAD(pagelist); XA_STATE_ORDER(xas, &mapping->i_pages, start, HPAGE_PMD_ORDER); @@ -1637,10 +1632,11 @@ static void collapse_file(struct mm_struct *mm, goto out; } - if (unlikely(mem_cgroup_try_charge(new_page, mm, gfp, &memcg))) { + if (unlikely(mem_cgroup_charge(new_page, mm, gfp, false))) { result = SCAN_CGROUP_CHARGE_FAIL; goto out; } + count_memcg_page_event(new_page, THP_COLLAPSE_ALLOC); /* This will be less messy when we use multi-index entries */ do { @@ -1650,7 +1646,6 @@ static void collapse_file(struct mm_struct *mm, break; xas_unlock_irq(&xas); if (!xas_nomem(&xas, GFP_KERNEL)) { - mem_cgroup_cancel_charge(new_page, memcg); result = SCAN_FAIL; goto out; } @@ -1844,18 +1839,9 @@ out_unlock: } if (nr_none) { - struct lruvec *lruvec; - /* - * XXX: We have started try_charge and pinned the - * memcg, but the page isn't committed yet so we - * cannot use mod_lruvec_page_state(). This hackery - * will be cleaned up when remove the page->mapping - * dependency from memcg and fully charge above. - */ - lruvec = mem_cgroup_lruvec(memcg, page_pgdat(new_page)); - __mod_lruvec_state(lruvec, NR_FILE_PAGES, nr_none); + __mod_lruvec_page_state(new_page, NR_FILE_PAGES, nr_none); if (is_shmem) - __mod_lruvec_state(lruvec, NR_SHMEM, nr_none); + __mod_lruvec_page_state(new_page, NR_SHMEM, nr_none); } xa_locked: @@ -1893,7 +1879,6 @@ xa_unlocked: SetPageUptodate(new_page); page_ref_add(new_page, HPAGE_PMD_NR - 1); - mem_cgroup_commit_charge(new_page, memcg, false); if (is_shmem) { set_page_dirty(new_page); @@ -1901,7 +1886,6 @@ xa_unlocked: } else { lru_cache_add_file(new_page); } - count_memcg_events(memcg, THP_COLLAPSE_ALLOC, 1); /* * Remove pte page tables, so we can re-fault the page as huge. @@ -1948,13 +1932,14 @@ xa_unlocked: VM_BUG_ON(nr_none); xas_unlock_irq(&xas); - mem_cgroup_cancel_charge(new_page, memcg); new_page->mapping = NULL; } unlock_page(new_page); out: VM_BUG_ON(!list_empty(&pagelist)); + if (!IS_ERR_OR_NULL(*hpage)) + mem_cgroup_uncharge(*hpage); /* TODO: tracepoints */ } diff --git a/mm/memory.c b/mm/memory.c index 543e41b1d57a..27e225bef5d0 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -2645,7 +2645,6 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) struct page *new_page = NULL; pte_t entry; int page_copied = 0; - struct mem_cgroup *memcg; struct mmu_notifier_range range; if (unlikely(anon_vma_prepare(vma))) @@ -2676,8 +2675,9 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) } } - if (mem_cgroup_try_charge_delay(new_page, mm, GFP_KERNEL, &memcg)) + if (mem_cgroup_charge(new_page, mm, GFP_KERNEL, false)) goto oom_free_new; + cgroup_throttle_swaprate(new_page, GFP_KERNEL); __SetPageUptodate(new_page); @@ -2710,7 +2710,6 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) * thread doing COW. */ ptep_clear_flush_notify(vma, vmf->address, vmf->pte); - mem_cgroup_commit_charge(new_page, memcg, false); page_add_new_anon_rmap(new_page, vma, vmf->address, false); lru_cache_add_active_or_unevictable(new_page, vma); /* @@ -2749,8 +2748,6 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) /* Free the old page.. */ new_page = old_page; page_copied = 1; - } else { - mem_cgroup_cancel_charge(new_page, memcg); } if (new_page) @@ -3088,7 +3085,6 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct page *page = NULL, *swapcache; - struct mem_cgroup *memcg; swp_entry_t entry; pte_t pte; int locked; @@ -3193,10 +3189,11 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) goto out_page; } - if (mem_cgroup_try_charge_delay(page, vma->vm_mm, GFP_KERNEL, &memcg)) { + if (mem_cgroup_charge(page, vma->vm_mm, GFP_KERNEL, true)) { ret = VM_FAULT_OOM; goto out_page; } + cgroup_throttle_swaprate(page, GFP_KERNEL); /* * Back out if somebody else already faulted in this pte. @@ -3243,11 +3240,9 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) /* ksm created a completely new copy */ if (unlikely(page != swapcache && swapcache)) { - mem_cgroup_commit_charge(page, memcg, false); page_add_new_anon_rmap(page, vma, vmf->address, false); lru_cache_add_active_or_unevictable(page, vma); } else { - mem_cgroup_commit_charge(page, memcg, true); do_page_add_anon_rmap(page, vma, vmf->address, exclusive); activate_page(page); } @@ -3284,7 +3279,6 @@ unlock: out: return ret; out_nomap: - mem_cgroup_cancel_charge(page, memcg); pte_unmap_unlock(vmf->pte, vmf->ptl); out_page: unlock_page(page); @@ -3305,7 +3299,6 @@ out_release: static vm_fault_t do_anonymous_page(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; - struct mem_cgroup *memcg; struct page *page; vm_fault_t ret = 0; pte_t entry; @@ -3358,8 +3351,9 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf) if (!page) goto oom; - if (mem_cgroup_try_charge_delay(page, vma->vm_mm, GFP_KERNEL, &memcg)) + if (mem_cgroup_charge(page, vma->vm_mm, GFP_KERNEL, false)) goto oom_free_page; + cgroup_throttle_swaprate(page, GFP_KERNEL); /* * The memory barrier inside __SetPageUptodate makes sure that @@ -3384,13 +3378,11 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf) /* Deliver the page fault to userland, check inside PT lock */ if (userfaultfd_missing(vma)) { pte_unmap_unlock(vmf->pte, vmf->ptl); - mem_cgroup_cancel_charge(page, memcg); put_page(page); return handle_userfault(vmf, VM_UFFD_MISSING); } inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES); - mem_cgroup_commit_charge(page, memcg, false); page_add_new_anon_rmap(page, vma, vmf->address, false); lru_cache_add_active_or_unevictable(page, vma); setpte: @@ -3402,7 +3394,6 @@ unlock: pte_unmap_unlock(vmf->pte, vmf->ptl); return ret; release: - mem_cgroup_cancel_charge(page, memcg); put_page(page); goto unlock; oom_free_page: @@ -3607,7 +3598,6 @@ static vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page) * mapping. If needed, the fucntion allocates page table or use pre-allocated. * * @vmf: fault environment - * @memcg: memcg to charge page (only for private mappings) * @page: page to map * * Caller must take care of unlocking vmf->ptl, if vmf->pte is non-NULL on @@ -3618,8 +3608,7 @@ static vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page) * * Return: %0 on success, %VM_FAULT_ code in case of error. */ -vm_fault_t alloc_set_pte(struct vm_fault *vmf, struct mem_cgroup *memcg, - struct page *page) +vm_fault_t alloc_set_pte(struct vm_fault *vmf, struct page *page) { struct vm_area_struct *vma = vmf->vma; bool write = vmf->flags & FAULT_FLAG_WRITE; @@ -3627,9 +3616,6 @@ vm_fault_t alloc_set_pte(struct vm_fault *vmf, struct mem_cgroup *memcg, vm_fault_t ret; if (pmd_none(*vmf->pmd) && PageTransCompound(page)) { - /* THP on COW? */ - VM_BUG_ON_PAGE(memcg, page); - ret = do_set_pmd(vmf, page); if (ret != VM_FAULT_FALLBACK) return ret; @@ -3652,7 +3638,6 @@ vm_fault_t alloc_set_pte(struct vm_fault *vmf, struct mem_cgroup *memcg, /* copy-on-write page */ if (write && !(vma->vm_flags & VM_SHARED)) { inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES); - mem_cgroup_commit_charge(page, memcg, false); page_add_new_anon_rmap(page, vma, vmf->address, false); lru_cache_add_active_or_unevictable(page, vma); } else { @@ -3702,7 +3687,7 @@ vm_fault_t finish_fault(struct vm_fault *vmf) if (!(vmf->vma->vm_flags & VM_SHARED)) ret = check_stable_address_space(vmf->vma->vm_mm); if (!ret) - ret = alloc_set_pte(vmf, vmf->memcg, page); + ret = alloc_set_pte(vmf, page); if (vmf->pte) pte_unmap_unlock(vmf->pte, vmf->ptl); return ret; @@ -3862,11 +3847,11 @@ static vm_fault_t do_cow_fault(struct vm_fault *vmf) if (!vmf->cow_page) return VM_FAULT_OOM; - if (mem_cgroup_try_charge_delay(vmf->cow_page, vma->vm_mm, - GFP_KERNEL, &vmf->memcg)) { + if (mem_cgroup_charge(vmf->cow_page, vma->vm_mm, GFP_KERNEL, false)) { put_page(vmf->cow_page); return VM_FAULT_OOM; } + cgroup_throttle_swaprate(vmf->cow_page, GFP_KERNEL); ret = __do_fault(vmf); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) @@ -3884,7 +3869,6 @@ static vm_fault_t do_cow_fault(struct vm_fault *vmf) goto uncharge_out; return ret; uncharge_out: - mem_cgroup_cancel_charge(vmf->cow_page, vmf->memcg); put_page(vmf->cow_page); return ret; } diff --git a/mm/migrate.c b/mm/migrate.c index e72ed681634f..44cee40221ec 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -2740,7 +2740,6 @@ static void migrate_vma_insert_page(struct migrate_vma *migrate, { struct vm_area_struct *vma = migrate->vma; struct mm_struct *mm = vma->vm_mm; - struct mem_cgroup *memcg; bool flush = false; spinlock_t *ptl; pte_t entry; @@ -2787,7 +2786,7 @@ static void migrate_vma_insert_page(struct migrate_vma *migrate, if (unlikely(anon_vma_prepare(vma))) goto abort; - if (mem_cgroup_try_charge(page, vma->vm_mm, GFP_KERNEL, &memcg)) + if (mem_cgroup_charge(page, vma->vm_mm, GFP_KERNEL, false)) goto abort; /* @@ -2832,7 +2831,6 @@ static void migrate_vma_insert_page(struct migrate_vma *migrate, goto unlock_abort; inc_mm_counter(mm, MM_ANONPAGES); - mem_cgroup_commit_charge(page, memcg, false); page_add_new_anon_rmap(page, vma, addr, false); if (!is_zone_device_page(page)) lru_cache_add_active_or_unevictable(page, vma); @@ -2855,7 +2853,6 @@ static void migrate_vma_insert_page(struct migrate_vma *migrate, unlock_abort: pte_unmap_unlock(ptep, ptl); - mem_cgroup_cancel_charge(page, memcg); abort: *src &= ~MIGRATE_PFN_MIGRATE; } diff --git a/mm/swapfile.c b/mm/swapfile.c index 01f6538bad2d..720e9a924c01 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -1892,7 +1892,6 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, swp_entry_t entry, struct page *page) { struct page *swapcache; - struct mem_cgroup *memcg; spinlock_t *ptl; pte_t *pte; int ret = 1; @@ -1902,14 +1901,13 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd, if (unlikely(!page)) return -ENOMEM; - if (mem_cgroup_try_charge(page, vma->vm_mm, GFP_KERNEL, &memcg)) { + if (mem_cgroup_charge(page, vma->vm_mm, GFP_KERNEL, true)) { ret = -ENOMEM; goto out_nolock; } pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); if (unlikely(!pte_same_as_swp(*pte, swp_entry_to_pte(entry)))) { - mem_cgroup_cancel_charge(page, memcg); ret = 0; goto out; } @@ -1920,10 +1918,8 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd, set_pte_at(vma->vm_mm, addr, pte, pte_mkold(mk_pte(page, vma->vm_page_prot))); if (page == swapcache) { - mem_cgroup_commit_charge(page, memcg, true); page_add_anon_rmap(page, vma, addr, false); } else { /* ksm created a completely new copy */ - mem_cgroup_commit_charge(page, memcg, false); page_add_new_anon_rmap(page, vma, addr, false); lru_cache_add_active_or_unevictable(page, vma); } diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 3dea268d2850..2745489415cc 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -56,7 +56,6 @@ static int mcopy_atomic_pte(struct mm_struct *dst_mm, struct page **pagep, bool wp_copy) { - struct mem_cgroup *memcg; pte_t _dst_pte, *dst_pte; spinlock_t *ptl; void *page_kaddr; @@ -97,7 +96,7 @@ static int mcopy_atomic_pte(struct mm_struct *dst_mm, __SetPageUptodate(page); ret = -ENOMEM; - if (mem_cgroup_try_charge(page, dst_mm, GFP_KERNEL, &memcg)) + if (mem_cgroup_charge(page, dst_mm, GFP_KERNEL, false)) goto out_release; _dst_pte = pte_mkdirty(mk_pte(page, dst_vma->vm_page_prot)); @@ -123,7 +122,6 @@ static int mcopy_atomic_pte(struct mm_struct *dst_mm, goto out_release_uncharge_unlock; inc_mm_counter(dst_mm, MM_ANONPAGES); - mem_cgroup_commit_charge(page, memcg, false); page_add_new_anon_rmap(page, dst_vma, dst_addr, false); lru_cache_add_active_or_unevictable(page, dst_vma); @@ -138,7 +136,6 @@ out: return ret; out_release_uncharge_unlock: pte_unmap_unlock(dst_pte, ptl); - mem_cgroup_cancel_charge(page, memcg); out_release: put_page(page); goto out; -- cgit v1.2.3 From f0e45fb4da29746a116e810eb91423ccfa4830fc Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 3 Jun 2020 16:02:07 -0700 Subject: mm: memcontrol: drop unused try/commit/cancel charge API There are no more users. RIP in peace. [arnd@arndb.de: fix an unused-function warning] Link: http://lkml.kernel.org/r/20200528095640.151454-1-arnd@arndb.de Signed-off-by: Johannes Weiner Signed-off-by: Arnd Bergmann Signed-off-by: Andrew Morton Reviewed-by: Joonsoo Kim Cc: Alex Shi Cc: Hugh Dickins Cc: "Kirill A. Shutemov" Cc: Michal Hocko Cc: Roman Gushchin Cc: Shakeel Butt Cc: Balbir Singh Link: http://lkml.kernel.org/r/20200508183105.225460-14-hannes@cmpxchg.org Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 36 ------------- mm/memcontrol.c | 128 ++++++--------------------------------------- 2 files changed, 17 insertions(+), 147 deletions(-) (limited to 'include') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 63a31a6c3c69..46620c6343ef 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -355,14 +355,6 @@ static inline unsigned long mem_cgroup_protection(struct mem_cgroup *memcg, enum mem_cgroup_protection mem_cgroup_protected(struct mem_cgroup *root, struct mem_cgroup *memcg); -int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm, - gfp_t gfp_mask, struct mem_cgroup **memcgp); -int mem_cgroup_try_charge_delay(struct page *page, struct mm_struct *mm, - gfp_t gfp_mask, struct mem_cgroup **memcgp); -void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg, - bool lrucare); -void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg); - int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask, bool lrucare); @@ -846,34 +838,6 @@ static inline enum mem_cgroup_protection mem_cgroup_protected( return MEMCG_PROT_NONE; } -static inline int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm, - gfp_t gfp_mask, - struct mem_cgroup **memcgp) -{ - *memcgp = NULL; - return 0; -} - -static inline int mem_cgroup_try_charge_delay(struct page *page, - struct mm_struct *mm, - gfp_t gfp_mask, - struct mem_cgroup **memcgp) -{ - *memcgp = NULL; - return 0; -} - -static inline void mem_cgroup_commit_charge(struct page *page, - struct mem_cgroup *memcg, - bool lrucare) -{ -} - -static inline void mem_cgroup_cancel_charge(struct page *page, - struct mem_cgroup *memcg) -{ -} - static inline int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask, bool lrucare) { diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 17587ea2745a..1e7a10b450b2 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2641,6 +2641,7 @@ done_restock: return 0; } +#if defined(CONFIG_MEMCG_KMEM) || defined(CONFIG_MMU) static void cancel_charge(struct mem_cgroup *memcg, unsigned int nr_pages) { if (mem_cgroup_is_root(memcg)) @@ -2652,6 +2653,7 @@ static void cancel_charge(struct mem_cgroup *memcg, unsigned int nr_pages) css_put_many(&memcg->css, nr_pages); } +#endif static void lock_page_lru(struct page *page, int *isolated) { @@ -6499,29 +6501,26 @@ out: } /** - * mem_cgroup_try_charge - try charging a page + * mem_cgroup_charge - charge a newly allocated page to a cgroup * @page: page to charge * @mm: mm context of the victim * @gfp_mask: reclaim mode - * @memcgp: charged memcg return + * @lrucare: page might be on the LRU already * * Try to charge @page to the memcg that @mm belongs to, reclaiming * pages according to @gfp_mask if necessary. * - * Returns 0 on success, with *@memcgp pointing to the charged memcg. - * Otherwise, an error code is returned. - * - * After page->mapping has been set up, the caller must finalize the - * charge with mem_cgroup_commit_charge(). Or abort the transaction - * with mem_cgroup_cancel_charge() in case page instantiation fails. + * Returns 0 on success. Otherwise, an error code is returned. */ -int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm, - gfp_t gfp_mask, struct mem_cgroup **memcgp) +int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask, + bool lrucare) { unsigned int nr_pages = hpage_nr_pages(page); struct mem_cgroup *memcg = NULL; int ret = 0; + VM_BUG_ON_PAGE(PageLRU(page) && !lrucare, page); + if (mem_cgroup_disabled()) goto out; @@ -6553,56 +6552,8 @@ int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm, memcg = get_mem_cgroup_from_mm(mm); ret = try_charge(memcg, gfp_mask, nr_pages); - - css_put(&memcg->css); -out: - *memcgp = memcg; - return ret; -} - -int mem_cgroup_try_charge_delay(struct page *page, struct mm_struct *mm, - gfp_t gfp_mask, struct mem_cgroup **memcgp) -{ - int ret; - - ret = mem_cgroup_try_charge(page, mm, gfp_mask, memcgp); - if (*memcgp) - cgroup_throttle_swaprate(page, gfp_mask); - return ret; -} - -/** - * mem_cgroup_commit_charge - commit a page charge - * @page: page to charge - * @memcg: memcg to charge the page to - * @lrucare: page might be on LRU already - * - * Finalize a charge transaction started by mem_cgroup_try_charge(), - * after page->mapping has been set up. This must happen atomically - * as part of the page instantiation, i.e. under the page table lock - * for anonymous pages, under the page lock for page and swap cache. - * - * In addition, the page must not be on the LRU during the commit, to - * prevent racing with task migration. If it might be, use @lrucare. - * - * Use mem_cgroup_cancel_charge() to cancel the transaction instead. - */ -void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg, - bool lrucare) -{ - unsigned int nr_pages = hpage_nr_pages(page); - - VM_BUG_ON_PAGE(PageLRU(page) && !lrucare, page); - - if (mem_cgroup_disabled()) - return; - /* - * Swap faults will attempt to charge the same page multiple - * times. But reuse_swap_page() might have removed the page - * from swapcache already, so we can't check PageSwapCache(). - */ - if (!memcg) - return; + if (ret) + goto out_put; commit_charge(page, memcg, lrucare); @@ -6620,55 +6571,11 @@ void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg, */ mem_cgroup_uncharge_swap(entry, nr_pages); } -} -/** - * mem_cgroup_cancel_charge - cancel a page charge - * @page: page to charge - * @memcg: memcg to charge the page to - * - * Cancel a charge transaction started by mem_cgroup_try_charge(). - */ -void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg) -{ - unsigned int nr_pages = hpage_nr_pages(page); - - if (mem_cgroup_disabled()) - return; - /* - * Swap faults will attempt to charge the same page multiple - * times. But reuse_swap_page() might have removed the page - * from swapcache already, so we can't check PageSwapCache(). - */ - if (!memcg) - return; - - cancel_charge(memcg, nr_pages); -} - -/** - * mem_cgroup_charge - charge a newly allocated page to a cgroup - * @page: page to charge - * @mm: mm context of the victim - * @gfp_mask: reclaim mode - * @lrucare: page might be on the LRU already - * - * Try to charge @page to the memcg that @mm belongs to, reclaiming - * pages according to @gfp_mask if necessary. - * - * Returns 0 on success. Otherwise, an error code is returned. - */ -int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask, - bool lrucare) -{ - struct mem_cgroup *memcg; - int ret; - - ret = mem_cgroup_try_charge(page, mm, gfp_mask, &memcg); - if (ret) - return ret; - mem_cgroup_commit_charge(page, memcg, lrucare); - return 0; +out_put: + css_put(&memcg->css); +out: + return ret; } struct uncharge_gather { @@ -6773,8 +6680,7 @@ static void uncharge_list(struct list_head *page_list) * mem_cgroup_uncharge - uncharge a page * @page: page to uncharge * - * Uncharge a page previously charged with mem_cgroup_try_charge() and - * mem_cgroup_commit_charge(). + * Uncharge a page previously charged with mem_cgroup_charge(). */ void mem_cgroup_uncharge(struct page *page) { @@ -6797,7 +6703,7 @@ void mem_cgroup_uncharge(struct page *page) * @page_list: list of pages to uncharge * * Uncharge a list of pages previously charged with - * mem_cgroup_try_charge() and mem_cgroup_commit_charge(). + * mem_cgroup_charge(). */ void mem_cgroup_uncharge_list(struct list_head *page_list) { -- cgit v1.2.3 From eccb52e7880973f221ab2606e4d22ce04d96a1a9 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 3 Jun 2020 16:02:11 -0700 Subject: mm: memcontrol: prepare swap controller setup for integration A few cleanups to streamline the swap controller setup: - Replace the do_swap_account flag with cgroup_memory_noswap. This brings it in line with other functionality that is usually available unless explicitly opted out of - nosocket, nokmem. - Remove the really_do_swap_account flag that stores the boot option and is later used to switch the do_swap_account. It's not clear why this indirection is/was necessary. Use do_swap_account directly. - Minor coding style polishing Signed-off-by: Johannes Weiner Signed-off-by: Andrew Morton Reviewed-by: Joonsoo Kim Cc: Alex Shi Cc: Hugh Dickins Cc: "Kirill A. Shutemov" Cc: Michal Hocko Cc: Roman Gushchin Cc: Shakeel Butt Cc: Balbir Singh Link: http://lkml.kernel.org/r/20200508183105.225460-15-hannes@cmpxchg.org Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 2 +- mm/memcontrol.c | 59 ++++++++++++++++++++++------------------------ mm/swap_cgroup.c | 4 ++-- 3 files changed, 31 insertions(+), 34 deletions(-) (limited to 'include') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 46620c6343ef..96257f995caa 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -558,7 +558,7 @@ struct mem_cgroup *mem_cgroup_get_oom_group(struct task_struct *victim, void mem_cgroup_print_oom_group(struct mem_cgroup *memcg); #ifdef CONFIG_MEMCG_SWAP -extern int do_swap_account; +extern bool cgroup_memory_noswap; #endif struct mem_cgroup *lock_page_memcg(struct page *page); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 1e7a10b450b2..2d035e68a127 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -83,10 +83,14 @@ static bool cgroup_memory_nokmem; /* Whether the swap controller is active */ #ifdef CONFIG_MEMCG_SWAP -int do_swap_account __read_mostly; +#ifdef CONFIG_MEMCG_SWAP_ENABLED +bool cgroup_memory_noswap __read_mostly; #else -#define do_swap_account 0 -#endif +bool cgroup_memory_noswap __read_mostly = 1; +#endif /* CONFIG_MEMCG_SWAP_ENABLED */ +#else +#define cgroup_memory_noswap 1 +#endif /* CONFIG_MEMCG_SWAP */ #ifdef CONFIG_CGROUP_WRITEBACK static DECLARE_WAIT_QUEUE_HEAD(memcg_cgwb_frn_waitq); @@ -95,7 +99,7 @@ static DECLARE_WAIT_QUEUE_HEAD(memcg_cgwb_frn_waitq); /* Whether legacy memory+swap accounting is active */ static bool do_memsw_account(void) { - return !cgroup_subsys_on_dfl(memory_cgrp_subsys) && do_swap_account; + return !cgroup_subsys_on_dfl(memory_cgrp_subsys) && !cgroup_memory_noswap; } #define THRESHOLDS_EVENTS_TARGET 128 @@ -6528,18 +6532,19 @@ int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask, /* * Every swap fault against a single page tries to charge the * page, bail as early as possible. shmem_unuse() encounters - * already charged pages, too. The USED bit is protected by - * the page lock, which serializes swap cache removal, which + * already charged pages, too. page->mem_cgroup is protected + * by the page lock, which serializes swap cache removal, which * in turn serializes uncharging. */ VM_BUG_ON_PAGE(!PageLocked(page), page); if (compound_head(page)->mem_cgroup) goto out; - if (do_swap_account) { + if (!cgroup_memory_noswap) { swp_entry_t ent = { .val = page_private(page), }; - unsigned short id = lookup_swap_cgroup_id(ent); + unsigned short id; + id = lookup_swap_cgroup_id(ent); rcu_read_lock(); memcg = mem_cgroup_from_id(id); if (memcg && !css_tryget_online(&memcg->css)) @@ -7012,7 +7017,7 @@ int mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry) struct mem_cgroup *memcg; unsigned short oldid; - if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) || !do_swap_account) + if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) || cgroup_memory_noswap) return 0; memcg = page->mem_cgroup; @@ -7056,7 +7061,7 @@ void mem_cgroup_uncharge_swap(swp_entry_t entry, unsigned int nr_pages) struct mem_cgroup *memcg; unsigned short id; - if (!do_swap_account) + if (cgroup_memory_noswap) return; id = swap_cgroup_record(entry, 0, nr_pages); @@ -7079,7 +7084,7 @@ long mem_cgroup_get_nr_swap_pages(struct mem_cgroup *memcg) { long nr_swap_pages = get_nr_swap_pages(); - if (!do_swap_account || !cgroup_subsys_on_dfl(memory_cgrp_subsys)) + if (cgroup_memory_noswap || !cgroup_subsys_on_dfl(memory_cgrp_subsys)) return nr_swap_pages; for (; memcg != root_mem_cgroup; memcg = parent_mem_cgroup(memcg)) nr_swap_pages = min_t(long, nr_swap_pages, @@ -7096,7 +7101,7 @@ bool mem_cgroup_swap_full(struct page *page) if (vm_swap_full()) return true; - if (!do_swap_account || !cgroup_subsys_on_dfl(memory_cgrp_subsys)) + if (cgroup_memory_noswap || !cgroup_subsys_on_dfl(memory_cgrp_subsys)) return false; memcg = page->mem_cgroup; @@ -7114,22 +7119,15 @@ bool mem_cgroup_swap_full(struct page *page) return false; } -/* for remember boot option*/ -#ifdef CONFIG_MEMCG_SWAP_ENABLED -static int really_do_swap_account __initdata = 1; -#else -static int really_do_swap_account __initdata; -#endif - -static int __init enable_swap_account(char *s) +static int __init setup_swap_account(char *s) { if (!strcmp(s, "1")) - really_do_swap_account = 1; + cgroup_memory_noswap = 0; else if (!strcmp(s, "0")) - really_do_swap_account = 0; + cgroup_memory_noswap = 1; return 1; } -__setup("swapaccount=", enable_swap_account); +__setup("swapaccount=", setup_swap_account); static u64 swap_current_read(struct cgroup_subsys_state *css, struct cftype *cft) @@ -7226,7 +7224,7 @@ static struct cftype swap_files[] = { { } /* terminate */ }; -static struct cftype memsw_cgroup_files[] = { +static struct cftype memsw_files[] = { { .name = "memsw.usage_in_bytes", .private = MEMFILE_PRIVATE(_MEMSWAP, RES_USAGE), @@ -7255,13 +7253,12 @@ static struct cftype memsw_cgroup_files[] = { static int __init mem_cgroup_swap_init(void) { - if (!mem_cgroup_disabled() && really_do_swap_account) { - do_swap_account = 1; - WARN_ON(cgroup_add_dfl_cftypes(&memory_cgrp_subsys, - swap_files)); - WARN_ON(cgroup_add_legacy_cftypes(&memory_cgrp_subsys, - memsw_cgroup_files)); - } + if (mem_cgroup_disabled() || cgroup_memory_noswap) + return 0; + + WARN_ON(cgroup_add_dfl_cftypes(&memory_cgrp_subsys, swap_files)); + WARN_ON(cgroup_add_legacy_cftypes(&memory_cgrp_subsys, memsw_files)); + return 0; } subsys_initcall(mem_cgroup_swap_init); diff --git a/mm/swap_cgroup.c b/mm/swap_cgroup.c index 45affaef3bc6..7aa764f09079 100644 --- a/mm/swap_cgroup.c +++ b/mm/swap_cgroup.c @@ -171,7 +171,7 @@ int swap_cgroup_swapon(int type, unsigned long max_pages) unsigned long length; struct swap_cgroup_ctrl *ctrl; - if (!do_swap_account) + if (cgroup_memory_noswap) return 0; length = DIV_ROUND_UP(max_pages, SC_PER_PAGE); @@ -209,7 +209,7 @@ void swap_cgroup_swapoff(int type) unsigned long i, length; struct swap_cgroup_ctrl *ctrl; - if (!do_swap_account) + if (cgroup_memory_noswap) return; mutex_lock(&swap_cgroup_mutex); -- cgit v1.2.3 From d9eb1ea2bf8734afd8ec7d995270437a7242f82b Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 3 Jun 2020 16:02:24 -0700 Subject: mm: memcontrol: delete unused lrucare handling Swapin faults were the last event to charge pages after they had already been put on the LRU list. Now that we charge directly on swapin, the lrucare portion of the charge code is unused. Signed-off-by: Johannes Weiner Signed-off-by: Andrew Morton Reviewed-by: Joonsoo Kim Cc: Alex Shi Cc: Hugh Dickins Cc: "Kirill A. Shutemov" Cc: Michal Hocko Cc: Roman Gushchin Cc: Balbir Singh Cc: Shakeel Butt Link: http://lkml.kernel.org/r/20200508183105.225460-19-hannes@cmpxchg.org Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 5 ++-- kernel/events/uprobes.c | 3 +-- mm/filemap.c | 2 +- mm/huge_memory.c | 2 +- mm/khugepaged.c | 4 ++-- mm/memcontrol.c | 57 ++++------------------------------------------ mm/memory.c | 8 +++---- mm/migrate.c | 2 +- mm/shmem.c | 2 +- mm/swap_state.c | 2 +- mm/userfaultfd.c | 2 +- 11 files changed, 19 insertions(+), 70 deletions(-) (limited to 'include') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 96257f995caa..d5bf3b5bfe6d 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -355,8 +355,7 @@ static inline unsigned long mem_cgroup_protection(struct mem_cgroup *memcg, enum mem_cgroup_protection mem_cgroup_protected(struct mem_cgroup *root, struct mem_cgroup *memcg); -int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask, - bool lrucare); +int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask); void mem_cgroup_uncharge(struct page *page); void mem_cgroup_uncharge_list(struct list_head *page_list); @@ -839,7 +838,7 @@ static inline enum mem_cgroup_protection mem_cgroup_protected( } static inline int mem_cgroup_charge(struct page *page, struct mm_struct *mm, - gfp_t gfp_mask, bool lrucare) + gfp_t gfp_mask) { return 0; } diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 4253c153e985..eddc8db96027 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -167,8 +167,7 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr, addr + PAGE_SIZE); if (new_page) { - err = mem_cgroup_charge(new_page, vma->vm_mm, GFP_KERNEL, - false); + err = mem_cgroup_charge(new_page, vma->vm_mm, GFP_KERNEL); if (err) return err; } diff --git a/mm/filemap.c b/mm/filemap.c index f08b0ca34e31..455990621989 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -845,7 +845,7 @@ static int __add_to_page_cache_locked(struct page *page, page->index = offset; if (!huge) { - error = mem_cgroup_charge(page, current->mm, gfp_mask, false); + error = mem_cgroup_charge(page, current->mm, gfp_mask); if (error) goto error; } diff --git a/mm/huge_memory.c b/mm/huge_memory.c index e9201a88157e..6df182a18d2c 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -593,7 +593,7 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf, VM_BUG_ON_PAGE(!PageCompound(page), page); - if (mem_cgroup_charge(page, vma->vm_mm, gfp, false)) { + if (mem_cgroup_charge(page, vma->vm_mm, gfp)) { put_page(page); count_vm_event(THP_FAULT_FALLBACK); count_vm_event(THP_FAULT_FALLBACK_CHARGE); diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 32c85b81837a..f29038c485e0 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -1059,7 +1059,7 @@ static void collapse_huge_page(struct mm_struct *mm, goto out_nolock; } - if (unlikely(mem_cgroup_charge(new_page, mm, gfp, false))) { + if (unlikely(mem_cgroup_charge(new_page, mm, gfp))) { result = SCAN_CGROUP_CHARGE_FAIL; goto out_nolock; } @@ -1632,7 +1632,7 @@ static void collapse_file(struct mm_struct *mm, goto out; } - if (unlikely(mem_cgroup_charge(new_page, mm, gfp, false))) { + if (unlikely(mem_cgroup_charge(new_page, mm, gfp))) { result = SCAN_CGROUP_CHARGE_FAIL; goto out; } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 425a265dc2a0..316a84025090 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2655,51 +2655,9 @@ static void cancel_charge(struct mem_cgroup *memcg, unsigned int nr_pages) } #endif -static void lock_page_lru(struct page *page, int *isolated) +static void commit_charge(struct page *page, struct mem_cgroup *memcg) { - pg_data_t *pgdat = page_pgdat(page); - - spin_lock_irq(&pgdat->lru_lock); - if (PageLRU(page)) { - struct lruvec *lruvec; - - lruvec = mem_cgroup_page_lruvec(page, pgdat); - ClearPageLRU(page); - del_page_from_lru_list(page, lruvec, page_lru(page)); - *isolated = 1; - } else - *isolated = 0; -} - -static void unlock_page_lru(struct page *page, int isolated) -{ - pg_data_t *pgdat = page_pgdat(page); - - if (isolated) { - struct lruvec *lruvec; - - lruvec = mem_cgroup_page_lruvec(page, pgdat); - VM_BUG_ON_PAGE(PageLRU(page), page); - SetPageLRU(page); - add_page_to_lru_list(page, lruvec, page_lru(page)); - } - spin_unlock_irq(&pgdat->lru_lock); -} - -static void commit_charge(struct page *page, struct mem_cgroup *memcg, - bool lrucare) -{ - int isolated; - VM_BUG_ON_PAGE(page->mem_cgroup, page); - - /* - * In some cases, SwapCache and FUSE(splice_buf->radixtree), the page - * may already be on some other mem_cgroup's LRU. Take care of it. - */ - if (lrucare) - lock_page_lru(page, &isolated); - /* * Nobody should be changing or seriously looking at * page->mem_cgroup at this point: @@ -2715,9 +2673,6 @@ static void commit_charge(struct page *page, struct mem_cgroup *memcg, * have the page locked */ page->mem_cgroup = memcg; - - if (lrucare) - unlock_page_lru(page, isolated); } #ifdef CONFIG_MEMCG_KMEM @@ -6503,22 +6458,18 @@ out: * @page: page to charge * @mm: mm context of the victim * @gfp_mask: reclaim mode - * @lrucare: page might be on the LRU already * * Try to charge @page to the memcg that @mm belongs to, reclaiming * pages according to @gfp_mask if necessary. * * Returns 0 on success. Otherwise, an error code is returned. */ -int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask, - bool lrucare) +int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask) { unsigned int nr_pages = hpage_nr_pages(page); struct mem_cgroup *memcg = NULL; int ret = 0; - VM_BUG_ON_PAGE(PageLRU(page) && !lrucare, page); - if (mem_cgroup_disabled()) goto out; @@ -6552,7 +6503,7 @@ int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask, if (ret) goto out_put; - commit_charge(page, memcg, lrucare); + commit_charge(page, memcg); local_irq_disable(); mem_cgroup_charge_statistics(memcg, page, nr_pages); @@ -6753,7 +6704,7 @@ void mem_cgroup_migrate(struct page *oldpage, struct page *newpage) page_counter_charge(&memcg->memsw, nr_pages); css_get_many(&memcg->css, nr_pages); - commit_charge(newpage, memcg, false); + commit_charge(newpage, memcg); local_irq_save(flags); mem_cgroup_charge_statistics(memcg, newpage, nr_pages); diff --git a/mm/memory.c b/mm/memory.c index 9c886e4207a2..d50d8b498af5 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -2675,7 +2675,7 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) } } - if (mem_cgroup_charge(new_page, mm, GFP_KERNEL, false)) + if (mem_cgroup_charge(new_page, mm, GFP_KERNEL)) goto oom_free_new; cgroup_throttle_swaprate(new_page, GFP_KERNEL); @@ -3134,7 +3134,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) /* Tell memcg to use swap ownership records */ SetPageSwapCache(page); err = mem_cgroup_charge(page, vma->vm_mm, - GFP_KERNEL, false); + GFP_KERNEL); ClearPageSwapCache(page); if (err) goto out_page; @@ -3358,7 +3358,7 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf) if (!page) goto oom; - if (mem_cgroup_charge(page, vma->vm_mm, GFP_KERNEL, false)) + if (mem_cgroup_charge(page, vma->vm_mm, GFP_KERNEL)) goto oom_free_page; cgroup_throttle_swaprate(page, GFP_KERNEL); @@ -3854,7 +3854,7 @@ static vm_fault_t do_cow_fault(struct vm_fault *vmf) if (!vmf->cow_page) return VM_FAULT_OOM; - if (mem_cgroup_charge(vmf->cow_page, vma->vm_mm, GFP_KERNEL, false)) { + if (mem_cgroup_charge(vmf->cow_page, vma->vm_mm, GFP_KERNEL)) { put_page(vmf->cow_page); return VM_FAULT_OOM; } diff --git a/mm/migrate.c b/mm/migrate.c index 44cee40221ec..7bfd0962149e 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -2786,7 +2786,7 @@ static void migrate_vma_insert_page(struct migrate_vma *migrate, if (unlikely(anon_vma_prepare(vma))) goto abort; - if (mem_cgroup_charge(page, vma->vm_mm, GFP_KERNEL, false)) + if (mem_cgroup_charge(page, vma->vm_mm, GFP_KERNEL)) goto abort; /* diff --git a/mm/shmem.c b/mm/shmem.c index b79116185046..e83de27ce8f4 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -624,7 +624,7 @@ static int shmem_add_to_page_cache(struct page *page, page->index = index; if (!PageSwapCache(page)) { - error = mem_cgroup_charge(page, charge_mm, gfp, false); + error = mem_cgroup_charge(page, charge_mm, gfp); if (error) { if (PageTransHuge(page)) { count_vm_event(THP_FILE_FALLBACK); diff --git a/mm/swap_state.c b/mm/swap_state.c index f841257a3014..ab0462819a5b 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -435,7 +435,7 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, goto fail_unlock; } - if (mem_cgroup_charge(page, NULL, gfp_mask, false)) { + if (mem_cgroup_charge(page, NULL, gfp_mask)) { delete_from_swap_cache(page); goto fail_unlock; } diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 2745489415cc..7f5194046b01 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -96,7 +96,7 @@ static int mcopy_atomic_pte(struct mm_struct *dst_mm, __SetPageUptodate(page); ret = -ENOMEM; - if (mem_cgroup_charge(page, dst_mm, GFP_KERNEL, false)) + if (mem_cgroup_charge(page, dst_mm, GFP_KERNEL)) goto out_release; _dst_pte = pte_mkdirty(mk_pte(page, dst_vma->vm_page_prot)); -- cgit v1.2.3 From 497a6c1b09902b22ceccc0f25ba4dd623e1ddb7d Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 3 Jun 2020 16:02:34 -0700 Subject: mm: keep separate anon and file statistics on page reclaim activity Having statistics on pages scanned and pages reclaimed for both anon and file pages makes it easier to evaluate changes to LRU balancing. While at it, clean up the stat-keeping mess for isolation, putback, reclaim stats etc. a bit: first the physical LRU operation (isolation and putback), followed by vmstats, reclaim_stats, and then vm events. Signed-off-by: Johannes Weiner Signed-off-by: Andrew Morton Cc: Joonsoo Kim Cc: Michal Hocko Cc: Minchan Kim Cc: Rik van Riel Link: http://lkml.kernel.org/r/20200520232525.798933-3-hannes@cmpxchg.org Signed-off-by: Linus Torvalds --- include/linux/vm_event_item.h | 4 ++++ mm/vmscan.c | 17 +++++++++-------- mm/vmstat.c | 4 ++++ 3 files changed, 17 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index ffef0f279747..24fc7c3ae7d6 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -35,6 +35,10 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, PGSCAN_KSWAPD, PGSCAN_DIRECT, PGSCAN_DIRECT_THROTTLE, + PGSCAN_ANON, + PGSCAN_FILE, + PGSTEAL_ANON, + PGSTEAL_FILE, #ifdef CONFIG_NUMA PGSCAN_ZONE_RECLAIM_FAILED, #endif diff --git a/mm/vmscan.c b/mm/vmscan.c index 779edd05b75e..1fa2417f7c2a 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1913,7 +1913,7 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, unsigned int nr_reclaimed = 0; unsigned long nr_taken; struct reclaim_stat stat; - int file = is_file_lru(lru); + bool file = is_file_lru(lru); enum vm_event_item item; struct pglist_data *pgdat = lruvec_pgdat(lruvec); struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat; @@ -1941,11 +1941,12 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, nr_taken); reclaim_stat->recent_scanned[file] += nr_taken; - item = current_is_kswapd() ? PGSCAN_KSWAPD : PGSCAN_DIRECT; if (!cgroup_reclaim(sc)) __count_vm_events(item, nr_scanned); __count_memcg_events(lruvec_memcg(lruvec), item, nr_scanned); + __count_vm_events(PGSCAN_ANON + file, nr_scanned); + spin_unlock_irq(&pgdat->lru_lock); if (nr_taken == 0) @@ -1956,16 +1957,16 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, spin_lock_irq(&pgdat->lru_lock); + move_pages_to_lru(lruvec, &page_list); + + __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken); + reclaim_stat->recent_rotated[0] += stat.nr_activate[0]; + reclaim_stat->recent_rotated[1] += stat.nr_activate[1]; item = current_is_kswapd() ? PGSTEAL_KSWAPD : PGSTEAL_DIRECT; if (!cgroup_reclaim(sc)) __count_vm_events(item, nr_reclaimed); __count_memcg_events(lruvec_memcg(lruvec), item, nr_reclaimed); - reclaim_stat->recent_rotated[0] += stat.nr_activate[0]; - reclaim_stat->recent_rotated[1] += stat.nr_activate[1]; - - move_pages_to_lru(lruvec, &page_list); - - __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken); + __count_vm_events(PGSTEAL_ANON + file, nr_reclaimed); spin_unlock_irq(&pgdat->lru_lock); diff --git a/mm/vmstat.c b/mm/vmstat.c index 068706a0a1a7..e55eda3b1a71 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1203,6 +1203,10 @@ const char * const vmstat_text[] = { "pgscan_kswapd", "pgscan_direct", "pgscan_direct_throttle", + "pgscan_anon", + "pgscan_file", + "pgsteal_anon", + "pgsteal_file", #ifdef CONFIG_NUMA "zone_reclaim_failed", -- cgit v1.2.3 From 6058eaec816f29fbe33c9d35694614c9a4ed75ba Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 3 Jun 2020 16:02:40 -0700 Subject: mm: fold and remove lru_cache_add_anon() and lru_cache_add_file() They're the same function, and for the purpose of all callers they are equivalent to lru_cache_add(). [akpm@linux-foundation.org: fix it for local_lock changes] Signed-off-by: Johannes Weiner Signed-off-by: Andrew Morton Reviewed-by: Rik van Riel Acked-by: Michal Hocko Acked-by: Minchan Kim Cc: Joonsoo Kim Link: http://lkml.kernel.org/r/20200520232525.798933-5-hannes@cmpxchg.org Signed-off-by: Linus Torvalds --- fs/cifs/file.c | 10 +++++----- fs/fuse/dev.c | 2 +- include/linux/swap.h | 2 -- mm/khugepaged.c | 8 ++------ mm/memory.c | 2 +- mm/shmem.c | 6 +++--- mm/swap.c | 42 ++++++++++-------------------------------- mm/swap_state.c | 2 +- 8 files changed, 23 insertions(+), 51 deletions(-) (limited to 'include') diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 75ddce8ef456..17a4f49c34f5 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -4162,7 +4162,7 @@ cifs_readv_complete(struct work_struct *work) for (i = 0; i < rdata->nr_pages; i++) { struct page *page = rdata->pages[i]; - lru_cache_add_file(page); + lru_cache_add(page); if (rdata->result == 0 || (rdata->result == -EAGAIN && got_bytes)) { @@ -4232,7 +4232,7 @@ readpages_fill_pages(struct TCP_Server_Info *server, * fill them until the writes are flushed. */ zero_user(page, 0, PAGE_SIZE); - lru_cache_add_file(page); + lru_cache_add(page); flush_dcache_page(page); SetPageUptodate(page); unlock_page(page); @@ -4242,7 +4242,7 @@ readpages_fill_pages(struct TCP_Server_Info *server, continue; } else { /* no need to hold page hostage */ - lru_cache_add_file(page); + lru_cache_add(page); unlock_page(page); put_page(page); rdata->pages[i] = NULL; @@ -4437,7 +4437,7 @@ static int cifs_readpages(struct file *file, struct address_space *mapping, /* best to give up if we're out of mem */ list_for_each_entry_safe(page, tpage, &tmplist, lru) { list_del(&page->lru); - lru_cache_add_file(page); + lru_cache_add(page); unlock_page(page); put_page(page); } @@ -4475,7 +4475,7 @@ static int cifs_readpages(struct file *file, struct address_space *mapping, add_credits_and_wake_if(server, &rdata->credits, 0); for (i = 0; i < rdata->nr_pages; i++) { page = rdata->pages[i]; - lru_cache_add_file(page); + lru_cache_add(page); unlock_page(page); put_page(page); } diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index c7a65cf2bcca..a01540b22122 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -840,7 +840,7 @@ static int fuse_try_move_page(struct fuse_copy_state *cs, struct page **pagep) get_page(newpage); if (!(buf->flags & PIPE_BUF_FLAG_LRU)) - lru_cache_add_file(newpage); + lru_cache_add(newpage); err = 0; spin_lock(&cs->req->waitq.lock); diff --git a/include/linux/swap.h b/include/linux/swap.h index 6cea1eb97d45..217bc8e13feb 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -335,8 +335,6 @@ extern unsigned long nr_free_pagecache_pages(void); /* linux/mm/swap.c */ extern void lru_cache_add(struct page *); -extern void lru_cache_add_anon(struct page *page); -extern void lru_cache_add_file(struct page *page); extern void lru_add_page_tail(struct page *page, struct page *page_tail, struct lruvec *lruvec, struct list_head *head); extern void activate_page(struct page *); diff --git a/mm/khugepaged.c b/mm/khugepaged.c index f29038c485e0..3f032487825b 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -1879,13 +1879,9 @@ xa_unlocked: SetPageUptodate(new_page); page_ref_add(new_page, HPAGE_PMD_NR - 1); - - if (is_shmem) { + if (is_shmem) set_page_dirty(new_page); - lru_cache_add_anon(new_page); - } else { - lru_cache_add_file(new_page); - } + lru_cache_add(new_page); /* * Remove pte page tables, so we can re-fault the page as huge. diff --git a/mm/memory.c b/mm/memory.c index d50d8b498af5..3431e76d0e75 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3139,7 +3139,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) if (err) goto out_page; - lru_cache_add_anon(page); + lru_cache_add(page); swap_readpage(page, true); } } else { diff --git a/mm/shmem.c b/mm/shmem.c index e83de27ce8f4..ea95a3e46fbb 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1609,7 +1609,7 @@ static int shmem_replace_page(struct page **pagep, gfp_t gfp, */ oldpage = newpage; } else { - lru_cache_add_anon(newpage); + lru_cache_add(newpage); *pagep = newpage; } @@ -1860,7 +1860,7 @@ alloc_nohuge: charge_mm); if (error) goto unacct; - lru_cache_add_anon(page); + lru_cache_add(page); spin_lock_irq(&info->lock); info->alloced += compound_nr(page); @@ -2376,7 +2376,7 @@ static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, if (!pte_none(*dst_pte)) goto out_release_unlock; - lru_cache_add_anon(page); + lru_cache_add(page); spin_lock_irq(&info->lock); info->alloced++; diff --git a/mm/swap.c b/mm/swap.c index f7026f72aca9..6196d792c952 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -424,37 +424,6 @@ void mark_page_accessed(struct page *page) } EXPORT_SYMBOL(mark_page_accessed); -static void __lru_cache_add(struct page *page) -{ - struct pagevec *pvec; - - local_lock(&lru_pvecs.lock); - pvec = this_cpu_ptr(&lru_pvecs.lru_add); - get_page(page); - if (!pagevec_add(pvec, page) || PageCompound(page)) - __pagevec_lru_add(pvec); - local_unlock(&lru_pvecs.lock); -} - -/** - * lru_cache_add_anon - add a page to the page lists - * @page: the page to add - */ -void lru_cache_add_anon(struct page *page) -{ - if (PageActive(page)) - ClearPageActive(page); - __lru_cache_add(page); -} - -void lru_cache_add_file(struct page *page) -{ - if (PageActive(page)) - ClearPageActive(page); - __lru_cache_add(page); -} -EXPORT_SYMBOL(lru_cache_add_file); - /** * lru_cache_add - add a page to a page list * @page: the page to be added to the LRU. @@ -466,10 +435,19 @@ EXPORT_SYMBOL(lru_cache_add_file); */ void lru_cache_add(struct page *page) { + struct pagevec *pvec; + VM_BUG_ON_PAGE(PageActive(page) && PageUnevictable(page), page); VM_BUG_ON_PAGE(PageLRU(page), page); - __lru_cache_add(page); + + get_page(page); + local_lock(&lru_pvecs.lock); + pvec = this_cpu_ptr(&lru_pvecs.lru_add); + if (!pagevec_add(pvec, page) || PageCompound(page)) + __pagevec_lru_add(pvec); + local_unlock(&lru_pvecs.lock); } +EXPORT_SYMBOL(lru_cache_add); /** * lru_cache_add_active_or_unevictable diff --git a/mm/swap_state.c b/mm/swap_state.c index ab0462819a5b..fa089002125f 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -442,7 +442,7 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, /* Caller will initiate read into locked page */ SetPageWorkingset(page); - lru_cache_add_anon(page); + lru_cache_add(page); *new_page_allocated = true; return page; -- cgit v1.2.3 From 1431d4d11abb265e79cd44bed2f5ea93f1bcc57b Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 3 Jun 2020 16:02:53 -0700 Subject: mm: base LRU balancing on an explicit cost model Currently, scan pressure between the anon and file LRU lists is balanced based on a mixture of reclaim efficiency and a somewhat vague notion of "value" of having certain pages in memory over others. That concept of value is problematic, because it has caused us to count any event that remotely makes one LRU list more or less preferrable for reclaim, even when these events are not directly comparable and impose very different costs on the system. One example is referenced file pages that we still deactivate and referenced anonymous pages that we actually rotate back to the head of the list. There is also conceptual overlap with the LRU algorithm itself. By rotating recently used pages instead of reclaiming them, the algorithm already biases the applied scan pressure based on page value. Thus, when rebalancing scan pressure due to rotations, we should think of reclaim cost, and leave assessing the page value to the LRU algorithm. Lastly, considering both value-increasing as well as value-decreasing events can sometimes cause the same type of event to be counted twice, i.e. how rotating a page increases the LRU value, while reclaiming it succesfully decreases the value. In itself this will balance out fine, but it quietly skews the impact of events that are only recorded once. The abstract metric of "value", the murky relationship with the LRU algorithm, and accounting both negative and positive events make the current pressure balancing model hard to reason about and modify. This patch switches to a balancing model of accounting the concrete, actually observed cost of reclaiming one LRU over another. For now, that cost includes pages that are scanned but rotated back to the list head. Subsequent patches will add consideration for IO caused by refaulting of recently evicted pages. Replace struct zone_reclaim_stat with two cost counters in the lruvec, and make everything that affects cost go through a new lru_note_cost() function. Signed-off-by: Johannes Weiner Signed-off-by: Andrew Morton Acked-by: Michal Hocko Cc: Joonsoo Kim Cc: Minchan Kim Cc: Rik van Riel Link: http://lkml.kernel.org/r/20200520232525.798933-9-hannes@cmpxchg.org Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 21 +++++++-------------- include/linux/swap.h | 2 ++ mm/memcontrol.c | 18 ++++++------------ mm/swap.c | 19 ++++++++----------- mm/vmscan.c | 44 ++++++++++++++++++++++---------------------- 5 files changed, 45 insertions(+), 59 deletions(-) (limited to 'include') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 2f79ff4477ba..e57248ccb63d 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -242,19 +242,6 @@ static inline bool is_active_lru(enum lru_list lru) return (lru == LRU_ACTIVE_ANON || lru == LRU_ACTIVE_FILE); } -struct zone_reclaim_stat { - /* - * The pageout code in vmscan.c keeps track of how many of the - * mem/swap backed and file backed pages are referenced. - * The higher the rotated/scanned ratio, the more valuable - * that cache is. - * - * The anon LRU stats live in [0], file LRU stats in [1] - */ - unsigned long recent_rotated[2]; - unsigned long recent_scanned[2]; -}; - enum lruvec_flags { LRUVEC_CONGESTED, /* lruvec has many dirty pages * backed by a congested BDI @@ -263,7 +250,13 @@ enum lruvec_flags { struct lruvec { struct list_head lists[NR_LRU_LISTS]; - struct zone_reclaim_stat reclaim_stat; + /* + * These track the cost of reclaiming one LRU - file or anon - + * over the other. As the observed cost of reclaiming one LRU + * increases, the reclaim scan balance tips toward the other. + */ + unsigned long anon_cost; + unsigned long file_cost; /* Evictions & activations on the inactive file list */ atomic_long_t inactive_age; /* Refaults at the time of last reclaim cycle */ diff --git a/include/linux/swap.h b/include/linux/swap.h index 217bc8e13feb..ce3c55747006 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -334,6 +334,8 @@ extern unsigned long nr_free_pagecache_pages(void); /* linux/mm/swap.c */ +extern void lru_note_cost(struct lruvec *lruvec, bool file, + unsigned int nr_pages); extern void lru_cache_add(struct page *); extern void lru_add_page_tail(struct page *page, struct page *page_tail, struct lruvec *lruvec, struct list_head *head); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index ee6fe8bb0bff..5381afb23d58 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3853,23 +3853,17 @@ static int memcg_stat_show(struct seq_file *m, void *v) { pg_data_t *pgdat; struct mem_cgroup_per_node *mz; - struct zone_reclaim_stat *rstat; - unsigned long recent_rotated[2] = {0, 0}; - unsigned long recent_scanned[2] = {0, 0}; + unsigned long anon_cost = 0; + unsigned long file_cost = 0; for_each_online_pgdat(pgdat) { mz = mem_cgroup_nodeinfo(memcg, pgdat->node_id); - rstat = &mz->lruvec.reclaim_stat; - recent_rotated[0] += rstat->recent_rotated[0]; - recent_rotated[1] += rstat->recent_rotated[1]; - recent_scanned[0] += rstat->recent_scanned[0]; - recent_scanned[1] += rstat->recent_scanned[1]; + anon_cost += mz->lruvec.anon_cost; + file_cost += mz->lruvec.file_cost; } - seq_printf(m, "recent_rotated_anon %lu\n", recent_rotated[0]); - seq_printf(m, "recent_rotated_file %lu\n", recent_rotated[1]); - seq_printf(m, "recent_scanned_anon %lu\n", recent_scanned[0]); - seq_printf(m, "recent_scanned_file %lu\n", recent_scanned[1]); + seq_printf(m, "anon_cost %lu\n", anon_cost); + seq_printf(m, "file_cost %lu\n", file_cost); } #endif diff --git a/mm/swap.c b/mm/swap.c index 116b609c25c1..fedeb925dbfe 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -278,15 +278,12 @@ void rotate_reclaimable_page(struct page *page) } } -static void update_page_reclaim_stat(struct lruvec *lruvec, - int file, int rotated, - unsigned int nr_pages) +void lru_note_cost(struct lruvec *lruvec, bool file, unsigned int nr_pages) { - struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat; - - reclaim_stat->recent_scanned[file] += nr_pages; - if (rotated) - reclaim_stat->recent_rotated[file] += nr_pages; + if (file) + lruvec->file_cost += nr_pages; + else + lruvec->anon_cost += nr_pages; } static void __activate_page(struct page *page, struct lruvec *lruvec, @@ -541,7 +538,7 @@ static void lru_deactivate_file_fn(struct page *page, struct lruvec *lruvec, if (active) __count_vm_event(PGDEACTIVATE); - update_page_reclaim_stat(lruvec, file, 0, hpage_nr_pages(page)); + lru_note_cost(lruvec, !file, hpage_nr_pages(page)); } static void lru_deactivate_fn(struct page *page, struct lruvec *lruvec, @@ -557,7 +554,7 @@ static void lru_deactivate_fn(struct page *page, struct lruvec *lruvec, add_page_to_lru_list(page, lruvec, lru); __count_vm_events(PGDEACTIVATE, hpage_nr_pages(page)); - update_page_reclaim_stat(lruvec, file, 0, hpage_nr_pages(page)); + lru_note_cost(lruvec, !file, hpage_nr_pages(page)); } } @@ -582,7 +579,7 @@ static void lru_lazyfree_fn(struct page *page, struct lruvec *lruvec, __count_vm_events(PGLAZYFREE, hpage_nr_pages(page)); count_memcg_page_event(page, PGLAZYFREE); - update_page_reclaim_stat(lruvec, 1, 0, hpage_nr_pages(page)); + lru_note_cost(lruvec, 0, hpage_nr_pages(page)); } } diff --git a/mm/vmscan.c b/mm/vmscan.c index a5a7a8d0764c..c5b2a68f4ef6 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1916,7 +1916,6 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, bool file = is_file_lru(lru); enum vm_event_item item; struct pglist_data *pgdat = lruvec_pgdat(lruvec); - struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat; bool stalled = false; while (unlikely(too_many_isolated(pgdat, file, sc))) { @@ -1940,7 +1939,6 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, &nr_scanned, sc, lru); __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, nr_taken); - reclaim_stat->recent_scanned[file] += nr_taken; item = current_is_kswapd() ? PGSCAN_KSWAPD : PGSCAN_DIRECT; if (!cgroup_reclaim(sc)) __count_vm_events(item, nr_scanned); @@ -1960,8 +1958,12 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, move_pages_to_lru(lruvec, &page_list); __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken); - reclaim_stat->recent_rotated[0] += stat.nr_activate[0]; - reclaim_stat->recent_rotated[1] += stat.nr_activate[1]; + /* + * Rotating pages costs CPU without actually + * progressing toward the reclaim goal. + */ + lru_note_cost(lruvec, 0, stat.nr_activate[0]); + lru_note_cost(lruvec, 1, stat.nr_activate[1]); item = current_is_kswapd() ? PGSTEAL_KSWAPD : PGSTEAL_DIRECT; if (!cgroup_reclaim(sc)) __count_vm_events(item, nr_reclaimed); @@ -2013,7 +2015,6 @@ static void shrink_active_list(unsigned long nr_to_scan, LIST_HEAD(l_active); LIST_HEAD(l_inactive); struct page *page; - struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat; unsigned nr_deactivate, nr_activate; unsigned nr_rotated = 0; int file = is_file_lru(lru); @@ -2027,7 +2028,6 @@ static void shrink_active_list(unsigned long nr_to_scan, &nr_scanned, sc, lru); __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, nr_taken); - reclaim_stat->recent_scanned[file] += nr_taken; __count_vm_events(PGREFILL, nr_scanned); __count_memcg_events(lruvec_memcg(lruvec), PGREFILL, nr_scanned); @@ -2085,7 +2085,7 @@ static void shrink_active_list(unsigned long nr_to_scan, * helps balance scan pressure between file and anonymous pages in * get_scan_count. */ - reclaim_stat->recent_rotated[file] += nr_rotated; + lru_note_cost(lruvec, file, nr_rotated); nr_activate = move_pages_to_lru(lruvec, &l_active); nr_deactivate = move_pages_to_lru(lruvec, &l_inactive); @@ -2242,13 +2242,13 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, { struct mem_cgroup *memcg = lruvec_memcg(lruvec); int swappiness = mem_cgroup_swappiness(memcg); - struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat; u64 fraction[2]; u64 denominator = 0; /* gcc */ struct pglist_data *pgdat = lruvec_pgdat(lruvec); unsigned long anon_prio, file_prio; enum scan_balance scan_balance; unsigned long anon, file; + unsigned long totalcost; unsigned long ap, fp; enum lru_list lru; @@ -2324,26 +2324,26 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, lruvec_lru_size(lruvec, LRU_INACTIVE_FILE, MAX_NR_ZONES); spin_lock_irq(&pgdat->lru_lock); - if (unlikely(reclaim_stat->recent_scanned[0] > anon / 4)) { - reclaim_stat->recent_scanned[0] /= 2; - reclaim_stat->recent_rotated[0] /= 2; - } - - if (unlikely(reclaim_stat->recent_scanned[1] > file / 4)) { - reclaim_stat->recent_scanned[1] /= 2; - reclaim_stat->recent_rotated[1] /= 2; + totalcost = lruvec->anon_cost + lruvec->file_cost; + if (unlikely(totalcost > (anon + file) / 4)) { + lruvec->anon_cost /= 2; + lruvec->file_cost /= 2; + totalcost /= 2; } /* * The amount of pressure on anon vs file pages is inversely - * proportional to the fraction of recently scanned pages on - * each list that were recently referenced and in active use. + * proportional to the assumed cost of reclaiming each list, + * as determined by the share of pages that are likely going + * to refault or rotate on each list (recently referenced), + * times the relative IO cost of bringing back a swapped out + * anonymous page vs reloading a filesystem page (swappiness). */ - ap = anon_prio * (reclaim_stat->recent_scanned[0] + 1); - ap /= reclaim_stat->recent_rotated[0] + 1; + ap = anon_prio * (totalcost + 1); + ap /= lruvec->anon_cost + 1; - fp = file_prio * (reclaim_stat->recent_scanned[1] + 1); - fp /= reclaim_stat->recent_rotated[1] + 1; + fp = file_prio * (totalcost + 1); + fp /= lruvec->file_cost + 1; spin_unlock_irq(&pgdat->lru_lock); fraction[0] = ap; -- cgit v1.2.3 From 314b57fb0460001a090b35ff8be987f2c868ad3c Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 3 Jun 2020 16:03:03 -0700 Subject: mm: balance LRU lists based on relative thrashing Since the LRUs were split into anon and file lists, the VM has been balancing between page cache and anonymous pages based on per-list ratios of scanned vs. rotated pages. In most cases that tips page reclaim towards the list that is easier to reclaim and has the fewest actively used pages, but there are a few problems with it: 1. Refaults and LRU rotations are weighted the same way, even though one costs IO and the other costs a bit of CPU. 2. The less we scan an LRU list based on already observed rotations, the more we increase the sampling interval for new references, and rotations become even more likely on that list. This can enter a death spiral in which we stop looking at one list completely until the other one is all but annihilated by page reclaim. Since commit a528910e12ec ("mm: thrash detection-based file cache sizing") we have refault detection for the page cache. Along with swapin events, they are good indicators of when the file or anon list, respectively, is too small for its workingset and needs to grow. For example, if the page cache is thrashing, the cache pages need more time in memory, while there may be colder pages on the anonymous list. Likewise, if swapped pages are faulting back in, it indicates that we reclaim anonymous pages too aggressively and should back off. Replace LRU rotations with refaults and swapins as the basis for relative reclaim cost of the two LRUs. This will have the VM target list balances that incur the least amount of IO on aggregate. Signed-off-by: Johannes Weiner Signed-off-by: Andrew Morton Cc: Joonsoo Kim Cc: Michal Hocko Cc: Minchan Kim Cc: Rik van Riel Link: http://lkml.kernel.org/r/20200520232525.798933-12-hannes@cmpxchg.org Signed-off-by: Linus Torvalds --- include/linux/swap.h | 3 +-- mm/swap.c | 11 +++++++---- mm/swap_state.c | 5 +++++ mm/vmscan.c | 39 ++++++++++----------------------------- mm/workingset.c | 4 ++++ 5 files changed, 27 insertions(+), 35 deletions(-) (limited to 'include') diff --git a/include/linux/swap.h b/include/linux/swap.h index ce3c55747006..0b71bf75fb67 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -334,8 +334,7 @@ extern unsigned long nr_free_pagecache_pages(void); /* linux/mm/swap.c */ -extern void lru_note_cost(struct lruvec *lruvec, bool file, - unsigned int nr_pages); +extern void lru_note_cost(struct page *); extern void lru_cache_add(struct page *); extern void lru_add_page_tail(struct page *page, struct page *page_tail, struct lruvec *lruvec, struct list_head *head); diff --git a/mm/swap.c b/mm/swap.c index 7d552af25797..2dc7d392642f 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -278,12 +278,15 @@ void rotate_reclaimable_page(struct page *page) } } -void lru_note_cost(struct lruvec *lruvec, bool file, unsigned int nr_pages) +void lru_note_cost(struct page *page) { - if (file) - lruvec->file_cost += nr_pages; + struct lruvec *lruvec = mem_cgroup_page_lruvec(page, page_pgdat(page)); + + /* Record new data point */ + if (page_is_file_lru(page)) + lruvec->file_cost++; else - lruvec->anon_cost += nr_pages; + lruvec->anon_cost++; } static void __activate_page(struct page *page, struct lruvec *lruvec, diff --git a/mm/swap_state.c b/mm/swap_state.c index fa089002125f..1cd0b345ff7e 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -440,6 +440,11 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, goto fail_unlock; } + /* XXX: Move to lru_cache_add() when it supports new vs putback */ + spin_lock_irq(&page_pgdat(page)->lru_lock); + lru_note_cost(page); + spin_unlock_irq(&page_pgdat(page)->lru_lock); + /* Caller will initiate read into locked page */ SetPageWorkingset(page); lru_cache_add(page); diff --git a/mm/vmscan.c b/mm/vmscan.c index 3c89eac629f3..76e823db21a7 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1958,12 +1958,6 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, move_pages_to_lru(lruvec, &page_list); __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken); - /* - * Rotating pages costs CPU without actually - * progressing toward the reclaim goal. - */ - lru_note_cost(lruvec, 0, stat.nr_activate[0]); - lru_note_cost(lruvec, 1, stat.nr_activate[1]); item = current_is_kswapd() ? PGSTEAL_KSWAPD : PGSTEAL_DIRECT; if (!cgroup_reclaim(sc)) __count_vm_events(item, nr_reclaimed); @@ -2079,11 +2073,6 @@ static void shrink_active_list(unsigned long nr_to_scan, * Move pages back to the lru list. */ spin_lock_irq(&pgdat->lru_lock); - /* - * Rotating pages costs CPU without actually - * progressing toward the reclaim goal. - */ - lru_note_cost(lruvec, file, nr_rotated); nr_activate = move_pages_to_lru(lruvec, &l_active); nr_deactivate = move_pages_to_lru(lruvec, &l_inactive); @@ -2298,22 +2287,23 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, scan_balance = SCAN_FRACT; /* - * With swappiness at 100, anonymous and file have the same priority. - * This scanning priority is essentially the inverse of IO cost. + * Calculate the pressure balance between anon and file pages. + * + * The amount of pressure we put on each LRU is inversely + * proportional to the cost of reclaiming each list, as + * determined by the share of pages that are refaulting, times + * the relative IO cost of bringing back a swapped out + * anonymous page vs reloading a filesystem page (swappiness). + * + * With swappiness at 100, anon and file have equal IO cost. */ anon_prio = swappiness; file_prio = 200 - anon_prio; /* - * OK, so we have swap space and a fair amount of page cache - * pages. We use the recently rotated / recently scanned - * ratios to determine how valuable each cache is. - * * Because workloads change over time (and to avoid overflow) * we keep these statistics as a floating average, which ends - * up weighing recent references more than old ones. - * - * anon in [0], file in [1] + * up weighing recent refaults more than old ones. */ anon = lruvec_lru_size(lruvec, LRU_ACTIVE_ANON, MAX_NR_ZONES) + @@ -2328,15 +2318,6 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, lruvec->file_cost /= 2; totalcost /= 2; } - - /* - * The amount of pressure on anon vs file pages is inversely - * proportional to the assumed cost of reclaiming each list, - * as determined by the share of pages that are likely going - * to refault or rotate on each list (recently referenced), - * times the relative IO cost of bringing back a swapped out - * anonymous page vs reloading a filesystem page (swappiness). - */ ap = anon_prio * (totalcost + 1); ap /= lruvec->anon_cost + 1; diff --git a/mm/workingset.c b/mm/workingset.c index e69865739539..a6a2a740ed0b 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -365,6 +365,10 @@ void workingset_refault(struct page *page, void *shadow) /* Page was active prior to eviction */ if (workingset) { SetPageWorkingset(page); + /* XXX: Move to lru_cache_add() when it supports new vs putback */ + spin_lock_irq(&page_pgdat(page)->lru_lock); + lru_note_cost(page); + spin_unlock_irq(&page_pgdat(page)->lru_lock); inc_lruvec_state(lruvec, WORKINGSET_RESTORE); } out: -- cgit v1.2.3 From 7cf111bc39f6792abedcdfbc4e6291a5603b0ef0 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 3 Jun 2020 16:03:06 -0700 Subject: mm: vmscan: determine anon/file pressure balance at the reclaim root We split the LRU lists into anon and file, and we rebalance the scan pressure between them when one of them begins thrashing: if the file cache experiences workingset refaults, we increase the pressure on anonymous pages; if the workload is stalled on swapins, we increase the pressure on the file cache instead. With cgroups and their nested LRU lists, we currently don't do this correctly. While recursive cgroup reclaim establishes a relative LRU order among the pages of all involved cgroups, LRU pressure balancing is done on an individual cgroup LRU level. As a result, when one cgroup is thrashing on the filesystem cache while a sibling may have cold anonymous pages, pressure doesn't get equalized between them. This patch moves LRU balancing decision to the root of reclaim - the same level where the LRU order is established. It does this by tracking LRU cost recursively, so that every level of the cgroup tree knows the aggregate LRU cost of all memory within its domain. When the page scanner calculates the scan balance for any given individual cgroup's LRU list, it uses the values from the ancestor cgroup that initiated the reclaim cycle. If one sibling is then thrashing on the cache, it will tip the pressure balance inside its ancestors, and the next hierarchical reclaim iteration will go more after the anon pages in the tree. Signed-off-by: Johannes Weiner Signed-off-by: Andrew Morton Cc: Joonsoo Kim Cc: Michal Hocko Cc: Minchan Kim Cc: Rik van Riel Link: http://lkml.kernel.org/r/20200520232525.798933-13-hannes@cmpxchg.org Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 13 +++++++++++++ mm/swap.c | 32 +++++++++++++++++++++++++++----- mm/vmscan.c | 41 +++++++++++++++++------------------------ 3 files changed, 57 insertions(+), 29 deletions(-) (limited to 'include') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index d5bf3b5bfe6d..e77197a62809 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1242,6 +1242,19 @@ static inline void dec_lruvec_page_state(struct page *page, mod_lruvec_page_state(page, idx, -1); } +static inline struct lruvec *parent_lruvec(struct lruvec *lruvec) +{ + struct mem_cgroup *memcg; + + memcg = lruvec_memcg(lruvec); + if (!memcg) + return NULL; + memcg = parent_mem_cgroup(memcg); + if (!memcg) + return NULL; + return mem_cgroup_lruvec(memcg, lruvec_pgdat(lruvec)); +} + #ifdef CONFIG_CGROUP_WRITEBACK struct wb_domain *mem_cgroup_wb_domain(struct bdi_writeback *wb); diff --git a/mm/swap.c b/mm/swap.c index 2dc7d392642f..4dff2123f695 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -282,11 +282,33 @@ void lru_note_cost(struct page *page) { struct lruvec *lruvec = mem_cgroup_page_lruvec(page, page_pgdat(page)); - /* Record new data point */ - if (page_is_file_lru(page)) - lruvec->file_cost++; - else - lruvec->anon_cost++; + do { + unsigned long lrusize; + + /* Record cost event */ + if (page_is_file_lru(page)) + lruvec->file_cost++; + else + lruvec->anon_cost++; + + /* + * Decay previous events + * + * Because workloads change over time (and to avoid + * overflow) we keep these statistics as a floating + * average, which ends up weighing recent refaults + * more than old ones. + */ + lrusize = lruvec_page_state(lruvec, NR_INACTIVE_ANON) + + lruvec_page_state(lruvec, NR_ACTIVE_ANON) + + lruvec_page_state(lruvec, NR_INACTIVE_FILE) + + lruvec_page_state(lruvec, NR_ACTIVE_FILE); + + if (lruvec->file_cost + lruvec->anon_cost > lrusize / 4) { + lruvec->file_cost /= 2; + lruvec->anon_cost /= 2; + } + } while ((lruvec = parent_lruvec(lruvec))); } static void __activate_page(struct page *page, struct lruvec *lruvec, diff --git a/mm/vmscan.c b/mm/vmscan.c index 76e823db21a7..d08640f0235c 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -79,6 +79,12 @@ struct scan_control { */ struct mem_cgroup *target_mem_cgroup; + /* + * Scan pressure balancing between anon and file LRUs + */ + unsigned long anon_cost; + unsigned long file_cost; + /* Can active pages be deactivated as part of reclaim? */ #define DEACTIVATE_ANON 1 #define DEACTIVATE_FILE 2 @@ -2231,10 +2237,8 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, int swappiness = mem_cgroup_swappiness(memcg); u64 fraction[2]; u64 denominator = 0; /* gcc */ - struct pglist_data *pgdat = lruvec_pgdat(lruvec); unsigned long anon_prio, file_prio; enum scan_balance scan_balance; - unsigned long anon, file; unsigned long totalcost; unsigned long ap, fp; enum lru_list lru; @@ -2285,7 +2289,6 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, } scan_balance = SCAN_FRACT; - /* * Calculate the pressure balance between anon and file pages. * @@ -2300,30 +2303,12 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, anon_prio = swappiness; file_prio = 200 - anon_prio; - /* - * Because workloads change over time (and to avoid overflow) - * we keep these statistics as a floating average, which ends - * up weighing recent refaults more than old ones. - */ - - anon = lruvec_lru_size(lruvec, LRU_ACTIVE_ANON, MAX_NR_ZONES) + - lruvec_lru_size(lruvec, LRU_INACTIVE_ANON, MAX_NR_ZONES); - file = lruvec_lru_size(lruvec, LRU_ACTIVE_FILE, MAX_NR_ZONES) + - lruvec_lru_size(lruvec, LRU_INACTIVE_FILE, MAX_NR_ZONES); - - spin_lock_irq(&pgdat->lru_lock); - totalcost = lruvec->anon_cost + lruvec->file_cost; - if (unlikely(totalcost > (anon + file) / 4)) { - lruvec->anon_cost /= 2; - lruvec->file_cost /= 2; - totalcost /= 2; - } + totalcost = sc->anon_cost + sc->file_cost; ap = anon_prio * (totalcost + 1); - ap /= lruvec->anon_cost + 1; + ap /= sc->anon_cost + 1; fp = file_prio * (totalcost + 1); - fp /= lruvec->file_cost + 1; - spin_unlock_irq(&pgdat->lru_lock); + fp /= sc->file_cost + 1; fraction[0] = ap; fraction[1] = fp; @@ -2687,6 +2672,14 @@ again: nr_reclaimed = sc->nr_reclaimed; nr_scanned = sc->nr_scanned; + /* + * Determine the scan balance between anon and file LRUs. + */ + spin_lock_irq(&pgdat->lru_lock); + sc->anon_cost = target_lruvec->anon_cost; + sc->file_cost = target_lruvec->file_cost; + spin_unlock_irq(&pgdat->lru_lock); + /* * Target desirable inactive:active list ratios for the anon * and file LRU lists. -- cgit v1.2.3 From 96f8bf4fb1dd2656ae3e92326be9ebf003bbfd45 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 3 Jun 2020 16:03:09 -0700 Subject: mm: vmscan: reclaim writepage is IO cost The VM tries to balance reclaim pressure between anon and file so as to reduce the amount of IO incurred due to the memory shortage. It already counts refaults and swapins, but in addition it should also count writepage calls during reclaim. For swap, this is obvious: it's IO that wouldn't have occurred if the anonymous memory hadn't been under memory pressure. From a relative balancing point of view this makes sense as well: even if anon is cold and reclaimable, a cache that isn't thrashing may have equally cold pages that don't require IO to reclaim. For file writeback, it's trickier: some of the reclaim writepage IO would have likely occurred anyway due to dirty expiration. But not all of it - premature writeback reduces batching and generates additional writes. Since the flushers are already woken up by the time the VM starts writing cache pages one by one, let's assume that we'e likely causing writes that wouldn't have happened without memory pressure. In addition, the per-page cost of IO would have probably been much cheaper if written in larger batches from the flusher thread rather than the single-page-writes from kswapd. For our purposes - getting the trend right to accelerate convergence on a stable state that doesn't require paging at all - this is sufficiently accurate. If we later wanted to optimize for sustained thrashing, we can still refine the measurements. Count all writepage calls from kswapd as IO cost toward the LRU that the page belongs to. Why do this dynamically? Don't we know in advance that anon pages require IO to reclaim, and so could build in a static bias? First, scanning is not the same as reclaiming. If all the anon pages are referenced, we may not swap for a while just because we're scanning the anon list. During this time, however, it's important that we age anonymous memory and the page cache at the same rate so that their hot-cold gradients are comparable. Everything else being equal, we still want to reclaim the coldest memory overall. Second, we keep copies in swap unless the page changes. If there is swap-backed data that's mostly read (tmpfs file) and has been swapped out before, we can reclaim it without incurring additional IO. Signed-off-by: Johannes Weiner Signed-off-by: Andrew Morton Cc: Joonsoo Kim Cc: Michal Hocko Cc: Minchan Kim Cc: Rik van Riel Link: http://lkml.kernel.org/r/20200520232525.798933-14-hannes@cmpxchg.org Signed-off-by: Linus Torvalds --- include/linux/swap.h | 4 +++- include/linux/vmstat.h | 1 + mm/swap.c | 16 ++++++++++------ mm/swap_state.c | 2 +- mm/vmscan.c | 3 +++ mm/workingset.c | 2 +- 6 files changed, 19 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/swap.h b/include/linux/swap.h index 0b71bf75fb67..4c5974bb9ba9 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -334,7 +334,9 @@ extern unsigned long nr_free_pagecache_pages(void); /* linux/mm/swap.c */ -extern void lru_note_cost(struct page *); +extern void lru_note_cost(struct lruvec *lruvec, bool file, + unsigned int nr_pages); +extern void lru_note_cost_page(struct page *); extern void lru_cache_add(struct page *); extern void lru_add_page_tail(struct page *page, struct page *page_tail, struct lruvec *lruvec, struct list_head *head); diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 10cc932e209a..3d12c34cd42a 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -26,6 +26,7 @@ struct reclaim_stat { unsigned nr_congested; unsigned nr_writeback; unsigned nr_immediate; + unsigned nr_pageout; unsigned nr_activate[2]; unsigned nr_ref_keep; unsigned nr_unmap_fail; diff --git a/mm/swap.c b/mm/swap.c index 4dff2123f695..343675d629ae 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -278,18 +278,16 @@ void rotate_reclaimable_page(struct page *page) } } -void lru_note_cost(struct page *page) +void lru_note_cost(struct lruvec *lruvec, bool file, unsigned int nr_pages) { - struct lruvec *lruvec = mem_cgroup_page_lruvec(page, page_pgdat(page)); - do { unsigned long lrusize; /* Record cost event */ - if (page_is_file_lru(page)) - lruvec->file_cost++; + if (file) + lruvec->file_cost += nr_pages; else - lruvec->anon_cost++; + lruvec->anon_cost += nr_pages; /* * Decay previous events @@ -311,6 +309,12 @@ void lru_note_cost(struct page *page) } while ((lruvec = parent_lruvec(lruvec))); } +void lru_note_cost_page(struct page *page) +{ + lru_note_cost(mem_cgroup_page_lruvec(page, page_pgdat(page)), + page_is_file_lru(page), hpage_nr_pages(page)); +} + static void __activate_page(struct page *page, struct lruvec *lruvec, void *arg) { diff --git a/mm/swap_state.c b/mm/swap_state.c index 1cd0b345ff7e..9d20b00627af 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -442,7 +442,7 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, /* XXX: Move to lru_cache_add() when it supports new vs putback */ spin_lock_irq(&page_pgdat(page)->lru_lock); - lru_note_cost(page); + lru_note_cost_page(page); spin_unlock_irq(&page_pgdat(page)->lru_lock); /* Caller will initiate read into locked page */ diff --git a/mm/vmscan.c b/mm/vmscan.c index d08640f0235c..14ffe9ccf7ef 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1359,6 +1359,8 @@ static unsigned int shrink_page_list(struct list_head *page_list, case PAGE_ACTIVATE: goto activate_locked; case PAGE_SUCCESS: + stat->nr_pageout += hpage_nr_pages(page); + if (PageWriteback(page)) goto keep; if (PageDirty(page)) @@ -1964,6 +1966,7 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, move_pages_to_lru(lruvec, &page_list); __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken); + lru_note_cost(lruvec, file, stat.nr_pageout); item = current_is_kswapd() ? PGSTEAL_KSWAPD : PGSTEAL_DIRECT; if (!cgroup_reclaim(sc)) __count_vm_events(item, nr_reclaimed); diff --git a/mm/workingset.c b/mm/workingset.c index a6a2a740ed0b..d481ea452eeb 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -367,7 +367,7 @@ void workingset_refault(struct page *page, void *shadow) SetPageWorkingset(page); /* XXX: Move to lru_cache_add() when it supports new vs putback */ spin_lock_irq(&page_pgdat(page)->lru_lock); - lru_note_cost(page); + lru_note_cost_page(page); spin_unlock_irq(&page_pgdat(page)->lru_lock); inc_lruvec_state(lruvec, WORKINGSET_RESTORE); } -- cgit v1.2.3 From 8cbd54f52997f43be3d09acd9fa9a10d202c5374 Mon Sep 17 00:00:00 2001 From: chenqiwu Date: Wed, 3 Jun 2020 16:03:28 -0700 Subject: include/linux/memblock.h: fix minor typo and unclear comment Fix a minor typo "usabe->usable" for the current discription of member variable "memory" in struct memblock. BTW, I think it's unclear the member variable "base" in struct memblock_type is currently described as the physical address of memory region, change it to base address of the region is clearer since the variable is decorated as phys_addr_t. Signed-off-by: chenqiwu Signed-off-by: Andrew Morton Reviewed-by: Mike Rapoport Link: http://lkml.kernel.org/r/1588846952-32166-1-git-send-email-qiwuchen55@gmail.com Signed-off-by: Linus Torvalds --- include/linux/memblock.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 807ab9daf0cd..017fae833d4a 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -41,7 +41,7 @@ enum memblock_flags { /** * struct memblock_region - represents a memory region - * @base: physical address of the region + * @base: base address of the region * @size: size of the region * @flags: memory region attributes * @nid: NUMA node id @@ -75,7 +75,7 @@ struct memblock_type { * struct memblock - memblock allocator metadata * @bottom_up: is bottom up direction? * @current_limit: physical address of the current allocation limit - * @memory: usabe memory regions + * @memory: usable memory regions * @reserved: reserved memory regions * @physmem: all physical memory */ -- cgit v1.2.3