From 320cc51d90832231cece478f0db6550ef367f8f3 Mon Sep 17 00:00:00 2001 From: Greg Thelen Date: Mon, 15 Mar 2010 15:27:28 +0100 Subject: mm: fix typo in refill_stock() comment Change refill_stock() comment: s/consumt_stock()/consume_stock()/ Signed-off-by: Greg Thelen Acked-by: Daisuke Nishimura Signed-off-by: Jiri Kosina --- mm/memcontrol.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'mm') diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 7973b5221fb8..6e8533e2861b 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1435,7 +1435,7 @@ static void drain_local_stock(struct work_struct *dummy) /* * Cache charges(val) which is from res_counter, to local per_cpu area. - * This will be consumed by consumt_stock() function, later. + * This will be consumed by consume_stock() function, later. */ static void refill_stock(struct mem_cgroup *mem, int val) { -- cgit v1.2.3 From 88393161210493e317ae391696ee8ef463cb3c23 Mon Sep 17 00:00:00 2001 From: Thomas Weber Date: Tue, 16 Mar 2010 11:47:56 +0100 Subject: Fix typos in comments [Ss]ytem => [Ss]ystem udpate => update paramters => parameters orginal => original Signed-off-by: Thomas Weber Acked-by: Randy Dunlap Signed-off-by: Jiri Kosina --- mm/page_alloc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'mm') diff --git a/mm/page_alloc.c b/mm/page_alloc.c index d03c946d5566..a6326c71b663 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -2579,7 +2579,7 @@ static int default_zonelist_order(void) struct zone *z; int average_size; /* - * ZONE_DMA and ZONE_DMA32 can be very small area in the sytem. + * ZONE_DMA and ZONE_DMA32 can be very small area in the system. * If they are really small and used heavily, the system can fall * into OOM very easily. * This function detect ZONE_DMA/DMA32 size and confgigures zone order. -- cgit v1.2.3 From faa4602e47690fb11221e00f9b9697c8dc0d4b19 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 25 Mar 2010 14:51:50 +0100 Subject: x86, perf, bts, mm: Delete the never used BTS-ptrace code Support for the PMU's BTS features has been upstreamed in v2.6.32, but we still have the old and disabled ptrace-BTS, as Linus noticed it not so long ago. It's buggy: TIF_DEBUGCTLMSR is trampling all over that MSR without regard for other uses (perf) and doesn't provide the flexibility needed for perf either. Its users are ptrace-block-step and ptrace-bts, since ptrace-bts was never used and ptrace-block-step can be implemented using a much simpler approach. So axe all 3000 lines of it. That includes the *locked_memory*() APIs in mm/mlock.c as well. Reported-by: Linus Torvalds Signed-off-by: Peter Zijlstra Cc: Roland McGrath Cc: Oleg Nesterov Cc: Markus Metzger Cc: Steven Rostedt Cc: Andrew Morton LKML-Reference: <20100325135413.938004390@chello.nl> Signed-off-by: Ingo Molnar --- mm/mlock.c | 41 ----------------------------------------- 1 file changed, 41 deletions(-) (limited to 'mm') diff --git a/mm/mlock.c b/mm/mlock.c index 8f4e2dfceec1..3f82720e0515 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -607,44 +607,3 @@ void user_shm_unlock(size_t size, struct user_struct *user) spin_unlock(&shmlock_user_lock); free_uid(user); } - -int account_locked_memory(struct mm_struct *mm, struct rlimit *rlim, - size_t size) -{ - unsigned long lim, vm, pgsz; - int error = -ENOMEM; - - pgsz = PAGE_ALIGN(size) >> PAGE_SHIFT; - - down_write(&mm->mmap_sem); - - lim = ACCESS_ONCE(rlim[RLIMIT_AS].rlim_cur) >> PAGE_SHIFT; - vm = mm->total_vm + pgsz; - if (lim < vm) - goto out; - - lim = ACCESS_ONCE(rlim[RLIMIT_MEMLOCK].rlim_cur) >> PAGE_SHIFT; - vm = mm->locked_vm + pgsz; - if (lim < vm) - goto out; - - mm->total_vm += pgsz; - mm->locked_vm += pgsz; - - error = 0; - out: - up_write(&mm->mmap_sem); - return error; -} - -void refund_locked_memory(struct mm_struct *mm, size_t size) -{ - unsigned long pgsz = PAGE_ALIGN(size) >> PAGE_SHIFT; - - down_write(&mm->mmap_sem); - - mm->total_vm -= pgsz; - mm->locked_vm -= pgsz; - - up_write(&mm->mmap_sem); -} -- cgit v1.2.3 From 020ec6537aa65c18e9084c568d7b94727f2026fd Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 9 Apr 2010 18:57:00 +0900 Subject: percpu: factor out pcpu_addr_in_first/reserved_chunk() and update per_cpu_ptr_to_phys() Factor out pcpu_addr_in_first/reserved_chunk() from pcpu_chunk_addr_search() and use it to update per_cpu_ptr_to_phys() such that it handles first chunk differently from the rest. This patch doesn't cause any functional change and is to prepare for percpu nommu support. Signed-off-by: Tejun Heo Reviewed-by: David Howells Cc: Graff Yang Cc: Sonic Zhang --- mm/percpu.c | 32 ++++++++++++++++++++++++-------- 1 file changed, 24 insertions(+), 8 deletions(-) (limited to 'mm') diff --git a/mm/percpu.c b/mm/percpu.c index 6e09741ddc62..1aeb081f30ec 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -177,6 +177,21 @@ static struct list_head *pcpu_slot __read_mostly; /* chunk list slots */ static void pcpu_reclaim(struct work_struct *work); static DECLARE_WORK(pcpu_reclaim_work, pcpu_reclaim); +static bool pcpu_addr_in_first_chunk(void *addr) +{ + void *first_start = pcpu_first_chunk->base_addr; + + return addr >= first_start && addr < first_start + pcpu_unit_size; +} + +static bool pcpu_addr_in_reserved_chunk(void *addr) +{ + void *first_start = pcpu_first_chunk->base_addr; + + return addr >= first_start && + addr < first_start + pcpu_reserved_chunk_limit; +} + static int __pcpu_size_to_slot(int size) { int highbit = fls(size); /* size is in bytes */ @@ -334,12 +349,10 @@ static void pcpu_chunk_relocate(struct pcpu_chunk *chunk, int oslot) */ static struct pcpu_chunk *pcpu_chunk_addr_search(void *addr) { - void *first_start = pcpu_first_chunk->base_addr; - /* is it in the first chunk? */ - if (addr >= first_start && addr < first_start + pcpu_unit_size) { + if (pcpu_addr_in_first_chunk(addr)) { /* is it in the reserved area? */ - if (addr < first_start + pcpu_reserved_chunk_limit) + if (pcpu_addr_in_reserved_chunk(addr)) return pcpu_reserved_chunk; return pcpu_first_chunk; } @@ -1343,10 +1356,13 @@ bool is_kernel_percpu_address(unsigned long addr) */ phys_addr_t per_cpu_ptr_to_phys(void *addr) { - if ((unsigned long)addr < VMALLOC_START || - (unsigned long)addr >= VMALLOC_END) - return __pa(addr); - else + if (pcpu_addr_in_first_chunk(addr)) { + if ((unsigned long)addr < VMALLOC_START || + (unsigned long)addr >= VMALLOC_END) + return __pa(addr); + else + return page_to_phys(vmalloc_to_page(addr)); + } else return page_to_phys(vmalloc_to_page(addr)); } -- cgit v1.2.3 From 6081089fd6f216b0eb8849205ad0c350cd5ed9bc Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 9 Apr 2010 18:57:01 +0900 Subject: percpu: reorganize chunk creation and destruction Reorganize alloc/free_pcpu_chunk() such that chunk struct alloc/free live in pcpu_alloc/free_chunk() and the rest in pcpu_create/destroy_chunk(). While at it, add missing error handling for chunk->map allocation failure. This is to allow alternate chunk management implementation for percpu nommu support. Signed-off-by: Tejun Heo Reviewed-by: David Howells Cc: Graff Yang Cc: Sonic Zhang --- mm/percpu.c | 70 ++++++++++++++++++++++++++++++++++++++++--------------------- 1 file changed, 46 insertions(+), 24 deletions(-) (limited to 'mm') diff --git a/mm/percpu.c b/mm/percpu.c index 1aeb081f30ec..105f171aad29 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -636,6 +636,38 @@ static void pcpu_free_area(struct pcpu_chunk *chunk, int freeme) pcpu_chunk_relocate(chunk, oslot); } +static struct pcpu_chunk *pcpu_alloc_chunk(void) +{ + struct pcpu_chunk *chunk; + + chunk = kzalloc(pcpu_chunk_struct_size, GFP_KERNEL); + if (!chunk) + return NULL; + + chunk->map = pcpu_mem_alloc(PCPU_DFL_MAP_ALLOC * sizeof(chunk->map[0])); + if (!chunk->map) { + kfree(chunk); + return NULL; + } + + chunk->map_alloc = PCPU_DFL_MAP_ALLOC; + chunk->map[chunk->map_used++] = pcpu_unit_size; + + INIT_LIST_HEAD(&chunk->list); + chunk->free_size = pcpu_unit_size; + chunk->contig_hint = pcpu_unit_size; + + return chunk; +} + +static void pcpu_free_chunk(struct pcpu_chunk *chunk) +{ + if (!chunk) + return; + pcpu_mem_free(chunk->map, chunk->map_alloc * sizeof(chunk->map[0])); + kfree(chunk); +} + /** * pcpu_get_pages_and_bitmap - get temp pages array and bitmap * @chunk: chunk of interest @@ -1028,41 +1060,31 @@ err_free: return rc; } -static void free_pcpu_chunk(struct pcpu_chunk *chunk) +static void pcpu_destroy_chunk(struct pcpu_chunk *chunk) { - if (!chunk) - return; - if (chunk->vms) + if (chunk && chunk->vms) pcpu_free_vm_areas(chunk->vms, pcpu_nr_groups); - pcpu_mem_free(chunk->map, chunk->map_alloc * sizeof(chunk->map[0])); - kfree(chunk); + pcpu_free_chunk(chunk); } -static struct pcpu_chunk *alloc_pcpu_chunk(void) +static struct pcpu_chunk *pcpu_create_chunk(void) { struct pcpu_chunk *chunk; + struct vm_struct **vms; - chunk = kzalloc(pcpu_chunk_struct_size, GFP_KERNEL); + chunk = pcpu_alloc_chunk(); if (!chunk) return NULL; - chunk->map = pcpu_mem_alloc(PCPU_DFL_MAP_ALLOC * sizeof(chunk->map[0])); - chunk->map_alloc = PCPU_DFL_MAP_ALLOC; - chunk->map[chunk->map_used++] = pcpu_unit_size; - - chunk->vms = pcpu_get_vm_areas(pcpu_group_offsets, pcpu_group_sizes, - pcpu_nr_groups, pcpu_atom_size, - GFP_KERNEL); - if (!chunk->vms) { - free_pcpu_chunk(chunk); + vms = pcpu_get_vm_areas(pcpu_group_offsets, pcpu_group_sizes, + pcpu_nr_groups, pcpu_atom_size, GFP_KERNEL); + if (!vms) { + pcpu_free_chunk(chunk); return NULL; } - INIT_LIST_HEAD(&chunk->list); - chunk->free_size = pcpu_unit_size; - chunk->contig_hint = pcpu_unit_size; - chunk->base_addr = chunk->vms[0]->addr - pcpu_group_offsets[0]; - + chunk->vms = vms; + chunk->base_addr = vms[0]->addr - pcpu_group_offsets[0]; return chunk; } @@ -1155,7 +1177,7 @@ restart: /* hmmm... no space left, create a new chunk */ spin_unlock_irqrestore(&pcpu_lock, flags); - chunk = alloc_pcpu_chunk(); + chunk = pcpu_create_chunk(); if (!chunk) { err = "failed to allocate new chunk"; goto fail_unlock_mutex; @@ -1267,7 +1289,7 @@ static void pcpu_reclaim(struct work_struct *work) list_for_each_entry_safe(chunk, next, &todo, list) { pcpu_depopulate_chunk(chunk, 0, pcpu_unit_size); - free_pcpu_chunk(chunk); + pcpu_destroy_chunk(chunk); } mutex_unlock(&pcpu_alloc_mutex); -- cgit v1.2.3 From 88999a898b565960690f18e4a13a1e8a9fa4dfef Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 9 Apr 2010 18:57:01 +0900 Subject: percpu: misc preparations for nommu support Make the following misc preparations for percpu nommu support. * Remove refernces to vmalloc in common comments as nommu percpu won't use it. * Rename chunk->vms to chunk->data and make it void *. Its use is determined by chunk management implementation. * Relocate utility functions and add __maybe_unused to functions which might not be used by different chunk management implementations. This patch doesn't cause any functional change. This is to allow alternate chunk management implementation for percpu nommu support. Signed-off-by: Tejun Heo Reviewed-by: David Howells Cc: Graff Yang Cc: Sonic Zhang --- mm/percpu.c | 111 ++++++++++++++++++++++++++++++------------------------------ 1 file changed, 56 insertions(+), 55 deletions(-) (limited to 'mm') diff --git a/mm/percpu.c b/mm/percpu.c index 105f171aad29..b403d7c02c67 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -1,5 +1,5 @@ /* - * linux/mm/percpu.c - percpu memory allocator + * mm/percpu.c - percpu memory allocator * * Copyright (C) 2009 SUSE Linux Products GmbH * Copyright (C) 2009 Tejun Heo @@ -7,14 +7,13 @@ * This file is released under the GPLv2. * * This is percpu allocator which can handle both static and dynamic - * areas. Percpu areas are allocated in chunks in vmalloc area. Each - * chunk is consisted of boot-time determined number of units and the - * first chunk is used for static percpu variables in the kernel image + * areas. Percpu areas are allocated in chunks. Each chunk is + * consisted of boot-time determined number of units and the first + * chunk is used for static percpu variables in the kernel image * (special boot time alloc/init handling necessary as these areas * need to be brought up before allocation services are running). * Unit grows as necessary and all units grow or shrink in unison. - * When a chunk is filled up, another chunk is allocated. ie. in - * vmalloc area + * When a chunk is filled up, another chunk is allocated. * * c0 c1 c2 * ------------------- ------------------- ------------ @@ -99,7 +98,7 @@ struct pcpu_chunk { int map_used; /* # of map entries used */ int map_alloc; /* # of map entries allocated */ int *map; /* allocation map */ - struct vm_struct **vms; /* mapped vmalloc regions */ + void *data; /* chunk data */ bool immutable; /* no [de]population allowed */ unsigned long populated[]; /* populated bitmap */ }; @@ -213,13 +212,25 @@ static int pcpu_chunk_slot(const struct pcpu_chunk *chunk) return pcpu_size_to_slot(chunk->free_size); } -static int pcpu_page_idx(unsigned int cpu, int page_idx) +/* set the pointer to a chunk in a page struct */ +static void pcpu_set_page_chunk(struct page *page, struct pcpu_chunk *pcpu) +{ + page->index = (unsigned long)pcpu; +} + +/* obtain pointer to a chunk from a page struct */ +static struct pcpu_chunk *pcpu_get_page_chunk(struct page *page) +{ + return (struct pcpu_chunk *)page->index; +} + +static int __maybe_unused pcpu_page_idx(unsigned int cpu, int page_idx) { return pcpu_unit_map[cpu] * pcpu_unit_pages + page_idx; } -static unsigned long pcpu_chunk_addr(struct pcpu_chunk *chunk, - unsigned int cpu, int page_idx) +static unsigned long __maybe_unused pcpu_chunk_addr(struct pcpu_chunk *chunk, + unsigned int cpu, int page_idx) { return (unsigned long)chunk->base_addr + pcpu_unit_offsets[cpu] + (page_idx << PAGE_SHIFT); @@ -234,25 +245,15 @@ static struct page *pcpu_chunk_page(struct pcpu_chunk *chunk, return vmalloc_to_page((void *)pcpu_chunk_addr(chunk, cpu, page_idx)); } -/* set the pointer to a chunk in a page struct */ -static void pcpu_set_page_chunk(struct page *page, struct pcpu_chunk *pcpu) -{ - page->index = (unsigned long)pcpu; -} - -/* obtain pointer to a chunk from a page struct */ -static struct pcpu_chunk *pcpu_get_page_chunk(struct page *page) -{ - return (struct pcpu_chunk *)page->index; -} - -static void pcpu_next_unpop(struct pcpu_chunk *chunk, int *rs, int *re, int end) +static void __maybe_unused pcpu_next_unpop(struct pcpu_chunk *chunk, + int *rs, int *re, int end) { *rs = find_next_zero_bit(chunk->populated, end, *rs); *re = find_next_bit(chunk->populated, end, *rs + 1); } -static void pcpu_next_pop(struct pcpu_chunk *chunk, int *rs, int *re, int end) +static void __maybe_unused pcpu_next_pop(struct pcpu_chunk *chunk, + int *rs, int *re, int end) { *rs = find_next_bit(chunk->populated, end, *rs); *re = find_next_zero_bit(chunk->populated, end, *rs + 1); @@ -340,34 +341,6 @@ static void pcpu_chunk_relocate(struct pcpu_chunk *chunk, int oslot) } } -/** - * pcpu_chunk_addr_search - determine chunk containing specified address - * @addr: address for which the chunk needs to be determined. - * - * RETURNS: - * The address of the found chunk. - */ -static struct pcpu_chunk *pcpu_chunk_addr_search(void *addr) -{ - /* is it in the first chunk? */ - if (pcpu_addr_in_first_chunk(addr)) { - /* is it in the reserved area? */ - if (pcpu_addr_in_reserved_chunk(addr)) - return pcpu_reserved_chunk; - return pcpu_first_chunk; - } - - /* - * The address is relative to unit0 which might be unused and - * thus unmapped. Offset the address to the unit space of the - * current processor before looking it up in the vmalloc - * space. Note that any possible cpu id can be used here, so - * there's no need to worry about preemption or cpu hotplug. - */ - addr += pcpu_unit_offsets[raw_smp_processor_id()]; - return pcpu_get_page_chunk(vmalloc_to_page(addr)); -} - /** * pcpu_need_to_extend - determine whether chunk area map needs to be extended * @chunk: chunk of interest @@ -1062,8 +1035,8 @@ err_free: static void pcpu_destroy_chunk(struct pcpu_chunk *chunk) { - if (chunk && chunk->vms) - pcpu_free_vm_areas(chunk->vms, pcpu_nr_groups); + if (chunk && chunk->data) + pcpu_free_vm_areas(chunk->data, pcpu_nr_groups); pcpu_free_chunk(chunk); } @@ -1083,11 +1056,39 @@ static struct pcpu_chunk *pcpu_create_chunk(void) return NULL; } - chunk->vms = vms; + chunk->data = vms; chunk->base_addr = vms[0]->addr - pcpu_group_offsets[0]; return chunk; } +/** + * pcpu_chunk_addr_search - determine chunk containing specified address + * @addr: address for which the chunk needs to be determined. + * + * RETURNS: + * The address of the found chunk. + */ +static struct pcpu_chunk *pcpu_chunk_addr_search(void *addr) +{ + /* is it in the first chunk? */ + if (pcpu_addr_in_first_chunk(addr)) { + /* is it in the reserved area? */ + if (pcpu_addr_in_reserved_chunk(addr)) + return pcpu_reserved_chunk; + return pcpu_first_chunk; + } + + /* + * The address is relative to unit0 which might be unused and + * thus unmapped. Offset the address to the unit space of the + * current processor before looking it up in the vmalloc + * space. Note that any possible cpu id can be used here, so + * there's no need to worry about preemption or cpu hotplug. + */ + addr += pcpu_unit_offsets[raw_smp_processor_id()]; + return pcpu_get_page_chunk(vmalloc_to_page(addr)); +} + /** * pcpu_alloc - the percpu allocator * @size: size of area to allocate in bytes -- cgit v1.2.3 From 9f6455325618821dcf6775d7972881fde32e77c5 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 9 Apr 2010 18:57:01 +0900 Subject: percpu: move vmalloc based chunk management into percpu-vm.c Separate out and move chunk management (creation/desctruction and [de]population) code into percpu-vm.c which is included by percpu.c and compiled together. The interface for chunk management is defined as follows. * pcpu_populate_chunk - populate the specified range of a chunk * pcpu_depopulate_chunk - depopulate the specified range of a chunk * pcpu_create_chunk - create a new chunk * pcpu_destroy_chunk - destroy a chunk, always preceded by full depop * pcpu_addr_to_page - translate address to physical address * pcpu_verify_alloc_info - check alloc_info is acceptable during init Other than wrapping vmalloc_to_page() inside pcpu_addr_to_page() and dummy pcpu_verify_alloc_info() implementation, this patch only moves code around. This separation is to allow alternate chunk management implementation. Signed-off-by: Tejun Heo Reviewed-by: David Howells Cc: Graff Yang Cc: Sonic Zhang --- mm/percpu-vm.c | 451 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++ mm/percpu.c | 452 +++------------------------------------------------------ 2 files changed, 475 insertions(+), 428 deletions(-) create mode 100644 mm/percpu-vm.c (limited to 'mm') diff --git a/mm/percpu-vm.c b/mm/percpu-vm.c new file mode 100644 index 000000000000..7d9c1d0ebd3f --- /dev/null +++ b/mm/percpu-vm.c @@ -0,0 +1,451 @@ +/* + * mm/percpu-vm.c - vmalloc area based chunk allocation + * + * Copyright (C) 2010 SUSE Linux Products GmbH + * Copyright (C) 2010 Tejun Heo + * + * This file is released under the GPLv2. + * + * Chunks are mapped into vmalloc areas and populated page by page. + * This is the default chunk allocator. + */ + +static struct page *pcpu_chunk_page(struct pcpu_chunk *chunk, + unsigned int cpu, int page_idx) +{ + /* must not be used on pre-mapped chunk */ + WARN_ON(chunk->immutable); + + return vmalloc_to_page((void *)pcpu_chunk_addr(chunk, cpu, page_idx)); +} + +/** + * pcpu_get_pages_and_bitmap - get temp pages array and bitmap + * @chunk: chunk of interest + * @bitmapp: output parameter for bitmap + * @may_alloc: may allocate the array + * + * Returns pointer to array of pointers to struct page and bitmap, + * both of which can be indexed with pcpu_page_idx(). The returned + * array is cleared to zero and *@bitmapp is copied from + * @chunk->populated. Note that there is only one array and bitmap + * and access exclusion is the caller's responsibility. + * + * CONTEXT: + * pcpu_alloc_mutex and does GFP_KERNEL allocation if @may_alloc. + * Otherwise, don't care. + * + * RETURNS: + * Pointer to temp pages array on success, NULL on failure. + */ +static struct page **pcpu_get_pages_and_bitmap(struct pcpu_chunk *chunk, + unsigned long **bitmapp, + bool may_alloc) +{ + static struct page **pages; + static unsigned long *bitmap; + size_t pages_size = pcpu_nr_units * pcpu_unit_pages * sizeof(pages[0]); + size_t bitmap_size = BITS_TO_LONGS(pcpu_unit_pages) * + sizeof(unsigned long); + + if (!pages || !bitmap) { + if (may_alloc && !pages) + pages = pcpu_mem_alloc(pages_size); + if (may_alloc && !bitmap) + bitmap = pcpu_mem_alloc(bitmap_size); + if (!pages || !bitmap) + return NULL; + } + + memset(pages, 0, pages_size); + bitmap_copy(bitmap, chunk->populated, pcpu_unit_pages); + + *bitmapp = bitmap; + return pages; +} + +/** + * pcpu_free_pages - free pages which were allocated for @chunk + * @chunk: chunk pages were allocated for + * @pages: array of pages to be freed, indexed by pcpu_page_idx() + * @populated: populated bitmap + * @page_start: page index of the first page to be freed + * @page_end: page index of the last page to be freed + 1 + * + * Free pages [@page_start and @page_end) in @pages for all units. + * The pages were allocated for @chunk. + */ +static void pcpu_free_pages(struct pcpu_chunk *chunk, + struct page **pages, unsigned long *populated, + int page_start, int page_end) +{ + unsigned int cpu; + int i; + + for_each_possible_cpu(cpu) { + for (i = page_start; i < page_end; i++) { + struct page *page = pages[pcpu_page_idx(cpu, i)]; + + if (page) + __free_page(page); + } + } +} + +/** + * pcpu_alloc_pages - allocates pages for @chunk + * @chunk: target chunk + * @pages: array to put the allocated pages into, indexed by pcpu_page_idx() + * @populated: populated bitmap + * @page_start: page index of the first page to be allocated + * @page_end: page index of the last page to be allocated + 1 + * + * Allocate pages [@page_start,@page_end) into @pages for all units. + * The allocation is for @chunk. Percpu core doesn't care about the + * content of @pages and will pass it verbatim to pcpu_map_pages(). + */ +static int pcpu_alloc_pages(struct pcpu_chunk *chunk, + struct page **pages, unsigned long *populated, + int page_start, int page_end) +{ + const gfp_t gfp = GFP_KERNEL | __GFP_HIGHMEM | __GFP_COLD; + unsigned int cpu; + int i; + + for_each_possible_cpu(cpu) { + for (i = page_start; i < page_end; i++) { + struct page **pagep = &pages[pcpu_page_idx(cpu, i)]; + + *pagep = alloc_pages_node(cpu_to_node(cpu), gfp, 0); + if (!*pagep) { + pcpu_free_pages(chunk, pages, populated, + page_start, page_end); + return -ENOMEM; + } + } + } + return 0; +} + +/** + * pcpu_pre_unmap_flush - flush cache prior to unmapping + * @chunk: chunk the regions to be flushed belongs to + * @page_start: page index of the first page to be flushed + * @page_end: page index of the last page to be flushed + 1 + * + * Pages in [@page_start,@page_end) of @chunk are about to be + * unmapped. Flush cache. As each flushing trial can be very + * expensive, issue flush on the whole region at once rather than + * doing it for each cpu. This could be an overkill but is more + * scalable. + */ +static void pcpu_pre_unmap_flush(struct pcpu_chunk *chunk, + int page_start, int page_end) +{ + flush_cache_vunmap( + pcpu_chunk_addr(chunk, pcpu_first_unit_cpu, page_start), + pcpu_chunk_addr(chunk, pcpu_last_unit_cpu, page_end)); +} + +static void __pcpu_unmap_pages(unsigned long addr, int nr_pages) +{ + unmap_kernel_range_noflush(addr, nr_pages << PAGE_SHIFT); +} + +/** + * pcpu_unmap_pages - unmap pages out of a pcpu_chunk + * @chunk: chunk of interest + * @pages: pages array which can be used to pass information to free + * @populated: populated bitmap + * @page_start: page index of the first page to unmap + * @page_end: page index of the last page to unmap + 1 + * + * For each cpu, unmap pages [@page_start,@page_end) out of @chunk. + * Corresponding elements in @pages were cleared by the caller and can + * be used to carry information to pcpu_free_pages() which will be + * called after all unmaps are finished. The caller should call + * proper pre/post flush functions. + */ +static void pcpu_unmap_pages(struct pcpu_chunk *chunk, + struct page **pages, unsigned long *populated, + int page_start, int page_end) +{ + unsigned int cpu; + int i; + + for_each_possible_cpu(cpu) { + for (i = page_start; i < page_end; i++) { + struct page *page; + + page = pcpu_chunk_page(chunk, cpu, i); + WARN_ON(!page); + pages[pcpu_page_idx(cpu, i)] = page; + } + __pcpu_unmap_pages(pcpu_chunk_addr(chunk, cpu, page_start), + page_end - page_start); + } + + for (i = page_start; i < page_end; i++) + __clear_bit(i, populated); +} + +/** + * pcpu_post_unmap_tlb_flush - flush TLB after unmapping + * @chunk: pcpu_chunk the regions to be flushed belong to + * @page_start: page index of the first page to be flushed + * @page_end: page index of the last page to be flushed + 1 + * + * Pages [@page_start,@page_end) of @chunk have been unmapped. Flush + * TLB for the regions. This can be skipped if the area is to be + * returned to vmalloc as vmalloc will handle TLB flushing lazily. + * + * As with pcpu_pre_unmap_flush(), TLB flushing also is done at once + * for the whole region. + */ +static void pcpu_post_unmap_tlb_flush(struct pcpu_chunk *chunk, + int page_start, int page_end) +{ + flush_tlb_kernel_range( + pcpu_chunk_addr(chunk, pcpu_first_unit_cpu, page_start), + pcpu_chunk_addr(chunk, pcpu_last_unit_cpu, page_end)); +} + +static int __pcpu_map_pages(unsigned long addr, struct page **pages, + int nr_pages) +{ + return map_kernel_range_noflush(addr, nr_pages << PAGE_SHIFT, + PAGE_KERNEL, pages); +} + +/** + * pcpu_map_pages - map pages into a pcpu_chunk + * @chunk: chunk of interest + * @pages: pages array containing pages to be mapped + * @populated: populated bitmap + * @page_start: page index of the first page to map + * @page_end: page index of the last page to map + 1 + * + * For each cpu, map pages [@page_start,@page_end) into @chunk. The + * caller is responsible for calling pcpu_post_map_flush() after all + * mappings are complete. + * + * This function is responsible for setting corresponding bits in + * @chunk->populated bitmap and whatever is necessary for reverse + * lookup (addr -> chunk). + */ +static int pcpu_map_pages(struct pcpu_chunk *chunk, + struct page **pages, unsigned long *populated, + int page_start, int page_end) +{ + unsigned int cpu, tcpu; + int i, err; + + for_each_possible_cpu(cpu) { + err = __pcpu_map_pages(pcpu_chunk_addr(chunk, cpu, page_start), + &pages[pcpu_page_idx(cpu, page_start)], + page_end - page_start); + if (err < 0) + goto err; + } + + /* mapping successful, link chunk and mark populated */ + for (i = page_start; i < page_end; i++) { + for_each_possible_cpu(cpu) + pcpu_set_page_chunk(pages[pcpu_page_idx(cpu, i)], + chunk); + __set_bit(i, populated); + } + + return 0; + +err: + for_each_possible_cpu(tcpu) { + if (tcpu == cpu) + break; + __pcpu_unmap_pages(pcpu_chunk_addr(chunk, tcpu, page_start), + page_end - page_start); + } + return err; +} + +/** + * pcpu_post_map_flush - flush cache after mapping + * @chunk: pcpu_chunk the regions to be flushed belong to + * @page_start: page index of the first page to be flushed + * @page_end: page index of the last page to be flushed + 1 + * + * Pages [@page_start,@page_end) of @chunk have been mapped. Flush + * cache. + * + * As with pcpu_pre_unmap_flush(), TLB flushing also is done at once + * for the whole region. + */ +static void pcpu_post_map_flush(struct pcpu_chunk *chunk, + int page_start, int page_end) +{ + flush_cache_vmap( + pcpu_chunk_addr(chunk, pcpu_first_unit_cpu, page_start), + pcpu_chunk_addr(chunk, pcpu_last_unit_cpu, page_end)); +} + +/** + * pcpu_populate_chunk - populate and map an area of a pcpu_chunk + * @chunk: chunk of interest + * @off: offset to the area to populate + * @size: size of the area to populate in bytes + * + * For each cpu, populate and map pages [@page_start,@page_end) into + * @chunk. The area is cleared on return. + * + * CONTEXT: + * pcpu_alloc_mutex, does GFP_KERNEL allocation. + */ +static int pcpu_populate_chunk(struct pcpu_chunk *chunk, int off, int size) +{ + int page_start = PFN_DOWN(off); + int page_end = PFN_UP(off + size); + int free_end = page_start, unmap_end = page_start; + struct page **pages; + unsigned long *populated; + unsigned int cpu; + int rs, re, rc; + + /* quick path, check whether all pages are already there */ + rs = page_start; + pcpu_next_pop(chunk, &rs, &re, page_end); + if (rs == page_start && re == page_end) + goto clear; + + /* need to allocate and map pages, this chunk can't be immutable */ + WARN_ON(chunk->immutable); + + pages = pcpu_get_pages_and_bitmap(chunk, &populated, true); + if (!pages) + return -ENOMEM; + + /* alloc and map */ + pcpu_for_each_unpop_region(chunk, rs, re, page_start, page_end) { + rc = pcpu_alloc_pages(chunk, pages, populated, rs, re); + if (rc) + goto err_free; + free_end = re; + } + + pcpu_for_each_unpop_region(chunk, rs, re, page_start, page_end) { + rc = pcpu_map_pages(chunk, pages, populated, rs, re); + if (rc) + goto err_unmap; + unmap_end = re; + } + pcpu_post_map_flush(chunk, page_start, page_end); + + /* commit new bitmap */ + bitmap_copy(chunk->populated, populated, pcpu_unit_pages); +clear: + for_each_possible_cpu(cpu) + memset((void *)pcpu_chunk_addr(chunk, cpu, 0) + off, 0, size); + return 0; + +err_unmap: + pcpu_pre_unmap_flush(chunk, page_start, unmap_end); + pcpu_for_each_unpop_region(chunk, rs, re, page_start, unmap_end) + pcpu_unmap_pages(chunk, pages, populated, rs, re); + pcpu_post_unmap_tlb_flush(chunk, page_start, unmap_end); +err_free: + pcpu_for_each_unpop_region(chunk, rs, re, page_start, free_end) + pcpu_free_pages(chunk, pages, populated, rs, re); + return rc; +} + +/** + * pcpu_depopulate_chunk - depopulate and unmap an area of a pcpu_chunk + * @chunk: chunk to depopulate + * @off: offset to the area to depopulate + * @size: size of the area to depopulate in bytes + * @flush: whether to flush cache and tlb or not + * + * For each cpu, depopulate and unmap pages [@page_start,@page_end) + * from @chunk. If @flush is true, vcache is flushed before unmapping + * and tlb after. + * + * CONTEXT: + * pcpu_alloc_mutex. + */ +static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk, int off, int size) +{ + int page_start = PFN_DOWN(off); + int page_end = PFN_UP(off + size); + struct page **pages; + unsigned long *populated; + int rs, re; + + /* quick path, check whether it's empty already */ + rs = page_start; + pcpu_next_unpop(chunk, &rs, &re, page_end); + if (rs == page_start && re == page_end) + return; + + /* immutable chunks can't be depopulated */ + WARN_ON(chunk->immutable); + + /* + * If control reaches here, there must have been at least one + * successful population attempt so the temp pages array must + * be available now. + */ + pages = pcpu_get_pages_and_bitmap(chunk, &populated, false); + BUG_ON(!pages); + + /* unmap and free */ + pcpu_pre_unmap_flush(chunk, page_start, page_end); + + pcpu_for_each_pop_region(chunk, rs, re, page_start, page_end) + pcpu_unmap_pages(chunk, pages, populated, rs, re); + + /* no need to flush tlb, vmalloc will handle it lazily */ + + pcpu_for_each_pop_region(chunk, rs, re, page_start, page_end) + pcpu_free_pages(chunk, pages, populated, rs, re); + + /* commit new bitmap */ + bitmap_copy(chunk->populated, populated, pcpu_unit_pages); +} + +static struct pcpu_chunk *pcpu_create_chunk(void) +{ + struct pcpu_chunk *chunk; + struct vm_struct **vms; + + chunk = pcpu_alloc_chunk(); + if (!chunk) + return NULL; + + vms = pcpu_get_vm_areas(pcpu_group_offsets, pcpu_group_sizes, + pcpu_nr_groups, pcpu_atom_size, GFP_KERNEL); + if (!vms) { + pcpu_free_chunk(chunk); + return NULL; + } + + chunk->data = vms; + chunk->base_addr = vms[0]->addr - pcpu_group_offsets[0]; + return chunk; +} + +static void pcpu_destroy_chunk(struct pcpu_chunk *chunk) +{ + if (chunk && chunk->data) + pcpu_free_vm_areas(chunk->data, pcpu_nr_groups); + pcpu_free_chunk(chunk); +} + +static struct page *pcpu_addr_to_page(void *addr) +{ + return vmalloc_to_page(addr); +} + +static int __init pcpu_verify_alloc_info(const struct pcpu_alloc_info *ai) +{ + /* no extra restriction */ + return 0; +} diff --git a/mm/percpu.c b/mm/percpu.c index b403d7c02c67..15f680430671 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -236,15 +236,6 @@ static unsigned long __maybe_unused pcpu_chunk_addr(struct pcpu_chunk *chunk, (page_idx << PAGE_SHIFT); } -static struct page *pcpu_chunk_page(struct pcpu_chunk *chunk, - unsigned int cpu, int page_idx) -{ - /* must not be used on pre-mapped chunk */ - WARN_ON(chunk->immutable); - - return vmalloc_to_page((void *)pcpu_chunk_addr(chunk, cpu, page_idx)); -} - static void __maybe_unused pcpu_next_unpop(struct pcpu_chunk *chunk, int *rs, int *re, int end) { @@ -641,425 +632,29 @@ static void pcpu_free_chunk(struct pcpu_chunk *chunk) kfree(chunk); } -/** - * pcpu_get_pages_and_bitmap - get temp pages array and bitmap - * @chunk: chunk of interest - * @bitmapp: output parameter for bitmap - * @may_alloc: may allocate the array - * - * Returns pointer to array of pointers to struct page and bitmap, - * both of which can be indexed with pcpu_page_idx(). The returned - * array is cleared to zero and *@bitmapp is copied from - * @chunk->populated. Note that there is only one array and bitmap - * and access exclusion is the caller's responsibility. - * - * CONTEXT: - * pcpu_alloc_mutex and does GFP_KERNEL allocation if @may_alloc. - * Otherwise, don't care. - * - * RETURNS: - * Pointer to temp pages array on success, NULL on failure. - */ -static struct page **pcpu_get_pages_and_bitmap(struct pcpu_chunk *chunk, - unsigned long **bitmapp, - bool may_alloc) -{ - static struct page **pages; - static unsigned long *bitmap; - size_t pages_size = pcpu_nr_units * pcpu_unit_pages * sizeof(pages[0]); - size_t bitmap_size = BITS_TO_LONGS(pcpu_unit_pages) * - sizeof(unsigned long); - - if (!pages || !bitmap) { - if (may_alloc && !pages) - pages = pcpu_mem_alloc(pages_size); - if (may_alloc && !bitmap) - bitmap = pcpu_mem_alloc(bitmap_size); - if (!pages || !bitmap) - return NULL; - } - - memset(pages, 0, pages_size); - bitmap_copy(bitmap, chunk->populated, pcpu_unit_pages); - - *bitmapp = bitmap; - return pages; -} - -/** - * pcpu_free_pages - free pages which were allocated for @chunk - * @chunk: chunk pages were allocated for - * @pages: array of pages to be freed, indexed by pcpu_page_idx() - * @populated: populated bitmap - * @page_start: page index of the first page to be freed - * @page_end: page index of the last page to be freed + 1 - * - * Free pages [@page_start and @page_end) in @pages for all units. - * The pages were allocated for @chunk. - */ -static void pcpu_free_pages(struct pcpu_chunk *chunk, - struct page **pages, unsigned long *populated, - int page_start, int page_end) -{ - unsigned int cpu; - int i; - - for_each_possible_cpu(cpu) { - for (i = page_start; i < page_end; i++) { - struct page *page = pages[pcpu_page_idx(cpu, i)]; - - if (page) - __free_page(page); - } - } -} - -/** - * pcpu_alloc_pages - allocates pages for @chunk - * @chunk: target chunk - * @pages: array to put the allocated pages into, indexed by pcpu_page_idx() - * @populated: populated bitmap - * @page_start: page index of the first page to be allocated - * @page_end: page index of the last page to be allocated + 1 - * - * Allocate pages [@page_start,@page_end) into @pages for all units. - * The allocation is for @chunk. Percpu core doesn't care about the - * content of @pages and will pass it verbatim to pcpu_map_pages(). - */ -static int pcpu_alloc_pages(struct pcpu_chunk *chunk, - struct page **pages, unsigned long *populated, - int page_start, int page_end) -{ - const gfp_t gfp = GFP_KERNEL | __GFP_HIGHMEM | __GFP_COLD; - unsigned int cpu; - int i; - - for_each_possible_cpu(cpu) { - for (i = page_start; i < page_end; i++) { - struct page **pagep = &pages[pcpu_page_idx(cpu, i)]; - - *pagep = alloc_pages_node(cpu_to_node(cpu), gfp, 0); - if (!*pagep) { - pcpu_free_pages(chunk, pages, populated, - page_start, page_end); - return -ENOMEM; - } - } - } - return 0; -} - -/** - * pcpu_pre_unmap_flush - flush cache prior to unmapping - * @chunk: chunk the regions to be flushed belongs to - * @page_start: page index of the first page to be flushed - * @page_end: page index of the last page to be flushed + 1 - * - * Pages in [@page_start,@page_end) of @chunk are about to be - * unmapped. Flush cache. As each flushing trial can be very - * expensive, issue flush on the whole region at once rather than - * doing it for each cpu. This could be an overkill but is more - * scalable. - */ -static void pcpu_pre_unmap_flush(struct pcpu_chunk *chunk, - int page_start, int page_end) -{ - flush_cache_vunmap( - pcpu_chunk_addr(chunk, pcpu_first_unit_cpu, page_start), - pcpu_chunk_addr(chunk, pcpu_last_unit_cpu, page_end)); -} - -static void __pcpu_unmap_pages(unsigned long addr, int nr_pages) -{ - unmap_kernel_range_noflush(addr, nr_pages << PAGE_SHIFT); -} - -/** - * pcpu_unmap_pages - unmap pages out of a pcpu_chunk - * @chunk: chunk of interest - * @pages: pages array which can be used to pass information to free - * @populated: populated bitmap - * @page_start: page index of the first page to unmap - * @page_end: page index of the last page to unmap + 1 - * - * For each cpu, unmap pages [@page_start,@page_end) out of @chunk. - * Corresponding elements in @pages were cleared by the caller and can - * be used to carry information to pcpu_free_pages() which will be - * called after all unmaps are finished. The caller should call - * proper pre/post flush functions. - */ -static void pcpu_unmap_pages(struct pcpu_chunk *chunk, - struct page **pages, unsigned long *populated, - int page_start, int page_end) -{ - unsigned int cpu; - int i; - - for_each_possible_cpu(cpu) { - for (i = page_start; i < page_end; i++) { - struct page *page; - - page = pcpu_chunk_page(chunk, cpu, i); - WARN_ON(!page); - pages[pcpu_page_idx(cpu, i)] = page; - } - __pcpu_unmap_pages(pcpu_chunk_addr(chunk, cpu, page_start), - page_end - page_start); - } - - for (i = page_start; i < page_end; i++) - __clear_bit(i, populated); -} - -/** - * pcpu_post_unmap_tlb_flush - flush TLB after unmapping - * @chunk: pcpu_chunk the regions to be flushed belong to - * @page_start: page index of the first page to be flushed - * @page_end: page index of the last page to be flushed + 1 - * - * Pages [@page_start,@page_end) of @chunk have been unmapped. Flush - * TLB for the regions. This can be skipped if the area is to be - * returned to vmalloc as vmalloc will handle TLB flushing lazily. - * - * As with pcpu_pre_unmap_flush(), TLB flushing also is done at once - * for the whole region. - */ -static void pcpu_post_unmap_tlb_flush(struct pcpu_chunk *chunk, - int page_start, int page_end) -{ - flush_tlb_kernel_range( - pcpu_chunk_addr(chunk, pcpu_first_unit_cpu, page_start), - pcpu_chunk_addr(chunk, pcpu_last_unit_cpu, page_end)); -} - -static int __pcpu_map_pages(unsigned long addr, struct page **pages, - int nr_pages) -{ - return map_kernel_range_noflush(addr, nr_pages << PAGE_SHIFT, - PAGE_KERNEL, pages); -} - -/** - * pcpu_map_pages - map pages into a pcpu_chunk - * @chunk: chunk of interest - * @pages: pages array containing pages to be mapped - * @populated: populated bitmap - * @page_start: page index of the first page to map - * @page_end: page index of the last page to map + 1 - * - * For each cpu, map pages [@page_start,@page_end) into @chunk. The - * caller is responsible for calling pcpu_post_map_flush() after all - * mappings are complete. - * - * This function is responsible for setting corresponding bits in - * @chunk->populated bitmap and whatever is necessary for reverse - * lookup (addr -> chunk). - */ -static int pcpu_map_pages(struct pcpu_chunk *chunk, - struct page **pages, unsigned long *populated, - int page_start, int page_end) -{ - unsigned int cpu, tcpu; - int i, err; - - for_each_possible_cpu(cpu) { - err = __pcpu_map_pages(pcpu_chunk_addr(chunk, cpu, page_start), - &pages[pcpu_page_idx(cpu, page_start)], - page_end - page_start); - if (err < 0) - goto err; - } - - /* mapping successful, link chunk and mark populated */ - for (i = page_start; i < page_end; i++) { - for_each_possible_cpu(cpu) - pcpu_set_page_chunk(pages[pcpu_page_idx(cpu, i)], - chunk); - __set_bit(i, populated); - } - - return 0; - -err: - for_each_possible_cpu(tcpu) { - if (tcpu == cpu) - break; - __pcpu_unmap_pages(pcpu_chunk_addr(chunk, tcpu, page_start), - page_end - page_start); - } - return err; -} - -/** - * pcpu_post_map_flush - flush cache after mapping - * @chunk: pcpu_chunk the regions to be flushed belong to - * @page_start: page index of the first page to be flushed - * @page_end: page index of the last page to be flushed + 1 - * - * Pages [@page_start,@page_end) of @chunk have been mapped. Flush - * cache. - * - * As with pcpu_pre_unmap_flush(), TLB flushing also is done at once - * for the whole region. - */ -static void pcpu_post_map_flush(struct pcpu_chunk *chunk, - int page_start, int page_end) -{ - flush_cache_vmap( - pcpu_chunk_addr(chunk, pcpu_first_unit_cpu, page_start), - pcpu_chunk_addr(chunk, pcpu_last_unit_cpu, page_end)); -} - -/** - * pcpu_depopulate_chunk - depopulate and unmap an area of a pcpu_chunk - * @chunk: chunk to depopulate - * @off: offset to the area to depopulate - * @size: size of the area to depopulate in bytes - * @flush: whether to flush cache and tlb or not - * - * For each cpu, depopulate and unmap pages [@page_start,@page_end) - * from @chunk. If @flush is true, vcache is flushed before unmapping - * and tlb after. - * - * CONTEXT: - * pcpu_alloc_mutex. - */ -static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk, int off, int size) -{ - int page_start = PFN_DOWN(off); - int page_end = PFN_UP(off + size); - struct page **pages; - unsigned long *populated; - int rs, re; - - /* quick path, check whether it's empty already */ - rs = page_start; - pcpu_next_unpop(chunk, &rs, &re, page_end); - if (rs == page_start && re == page_end) - return; - - /* immutable chunks can't be depopulated */ - WARN_ON(chunk->immutable); - - /* - * If control reaches here, there must have been at least one - * successful population attempt so the temp pages array must - * be available now. - */ - pages = pcpu_get_pages_and_bitmap(chunk, &populated, false); - BUG_ON(!pages); - - /* unmap and free */ - pcpu_pre_unmap_flush(chunk, page_start, page_end); - - pcpu_for_each_pop_region(chunk, rs, re, page_start, page_end) - pcpu_unmap_pages(chunk, pages, populated, rs, re); - - /* no need to flush tlb, vmalloc will handle it lazily */ - - pcpu_for_each_pop_region(chunk, rs, re, page_start, page_end) - pcpu_free_pages(chunk, pages, populated, rs, re); - - /* commit new bitmap */ - bitmap_copy(chunk->populated, populated, pcpu_unit_pages); -} - -/** - * pcpu_populate_chunk - populate and map an area of a pcpu_chunk - * @chunk: chunk of interest - * @off: offset to the area to populate - * @size: size of the area to populate in bytes - * - * For each cpu, populate and map pages [@page_start,@page_end) into - * @chunk. The area is cleared on return. - * - * CONTEXT: - * pcpu_alloc_mutex, does GFP_KERNEL allocation. +/* + * Chunk management implementation. + * + * To allow different implementations, chunk alloc/free and + * [de]population are implemented in a separate file which is pulled + * into this file and compiled together. The following functions + * should be implemented. + * + * pcpu_populate_chunk - populate the specified range of a chunk + * pcpu_depopulate_chunk - depopulate the specified range of a chunk + * pcpu_create_chunk - create a new chunk + * pcpu_destroy_chunk - destroy a chunk, always preceded by full depop + * pcpu_addr_to_page - translate address to physical address + * pcpu_verify_alloc_info - check alloc_info is acceptable during init */ -static int pcpu_populate_chunk(struct pcpu_chunk *chunk, int off, int size) -{ - int page_start = PFN_DOWN(off); - int page_end = PFN_UP(off + size); - int free_end = page_start, unmap_end = page_start; - struct page **pages; - unsigned long *populated; - unsigned int cpu; - int rs, re, rc; - - /* quick path, check whether all pages are already there */ - rs = page_start; - pcpu_next_pop(chunk, &rs, &re, page_end); - if (rs == page_start && re == page_end) - goto clear; - - /* need to allocate and map pages, this chunk can't be immutable */ - WARN_ON(chunk->immutable); - - pages = pcpu_get_pages_and_bitmap(chunk, &populated, true); - if (!pages) - return -ENOMEM; - - /* alloc and map */ - pcpu_for_each_unpop_region(chunk, rs, re, page_start, page_end) { - rc = pcpu_alloc_pages(chunk, pages, populated, rs, re); - if (rc) - goto err_free; - free_end = re; - } - - pcpu_for_each_unpop_region(chunk, rs, re, page_start, page_end) { - rc = pcpu_map_pages(chunk, pages, populated, rs, re); - if (rc) - goto err_unmap; - unmap_end = re; - } - pcpu_post_map_flush(chunk, page_start, page_end); - - /* commit new bitmap */ - bitmap_copy(chunk->populated, populated, pcpu_unit_pages); -clear: - for_each_possible_cpu(cpu) - memset((void *)pcpu_chunk_addr(chunk, cpu, 0) + off, 0, size); - return 0; - -err_unmap: - pcpu_pre_unmap_flush(chunk, page_start, unmap_end); - pcpu_for_each_unpop_region(chunk, rs, re, page_start, unmap_end) - pcpu_unmap_pages(chunk, pages, populated, rs, re); - pcpu_post_unmap_tlb_flush(chunk, page_start, unmap_end); -err_free: - pcpu_for_each_unpop_region(chunk, rs, re, page_start, free_end) - pcpu_free_pages(chunk, pages, populated, rs, re); - return rc; -} +static int pcpu_populate_chunk(struct pcpu_chunk *chunk, int off, int size); +static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk, int off, int size); +static struct pcpu_chunk *pcpu_create_chunk(void); +static void pcpu_destroy_chunk(struct pcpu_chunk *chunk); +static struct page *pcpu_addr_to_page(void *addr); +static int __init pcpu_verify_alloc_info(const struct pcpu_alloc_info *ai); -static void pcpu_destroy_chunk(struct pcpu_chunk *chunk) -{ - if (chunk && chunk->data) - pcpu_free_vm_areas(chunk->data, pcpu_nr_groups); - pcpu_free_chunk(chunk); -} - -static struct pcpu_chunk *pcpu_create_chunk(void) -{ - struct pcpu_chunk *chunk; - struct vm_struct **vms; - - chunk = pcpu_alloc_chunk(); - if (!chunk) - return NULL; - - vms = pcpu_get_vm_areas(pcpu_group_offsets, pcpu_group_sizes, - pcpu_nr_groups, pcpu_atom_size, GFP_KERNEL); - if (!vms) { - pcpu_free_chunk(chunk); - return NULL; - } - - chunk->data = vms; - chunk->base_addr = vms[0]->addr - pcpu_group_offsets[0]; - return chunk; -} +#include "percpu-vm.c" /** * pcpu_chunk_addr_search - determine chunk containing specified address @@ -1086,7 +681,7 @@ static struct pcpu_chunk *pcpu_chunk_addr_search(void *addr) * there's no need to worry about preemption or cpu hotplug. */ addr += pcpu_unit_offsets[raw_smp_processor_id()]; - return pcpu_get_page_chunk(vmalloc_to_page(addr)); + return pcpu_get_page_chunk(pcpu_addr_to_page(addr)); } /** @@ -1386,7 +981,7 @@ phys_addr_t per_cpu_ptr_to_phys(void *addr) else return page_to_phys(vmalloc_to_page(addr)); } else - return page_to_phys(vmalloc_to_page(addr)); + return page_to_phys(pcpu_addr_to_page(addr)); } static inline size_t pcpu_calc_fc_sizes(size_t static_size, @@ -1758,6 +1353,7 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai, PCPU_SETUP_BUG_ON(ai->unit_size < size_sum); PCPU_SETUP_BUG_ON(ai->unit_size & ~PAGE_MASK); PCPU_SETUP_BUG_ON(ai->unit_size < PCPU_MIN_UNIT_SIZE); + PCPU_SETUP_BUG_ON(pcpu_verify_alloc_info(ai) < 0); /* process group information and build config tables accordingly */ group_offsets = alloc_bootmem(ai->nr_groups * sizeof(group_offsets[0])); -- cgit v1.2.3 From b0c9778b1d07ed3aa7e411db201275553527b1b1 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 9 Apr 2010 18:57:01 +0900 Subject: percpu: implement kernel memory based chunk allocation Implement an alternate percpu chunk management based on kernel memeory for nommu SMP architectures. Instead of mapping into vmalloc area, chunks are allocated as a contiguous kernel memory using alloc_pages(). As such, percpu allocator on nommu will have the following restrictions. * It can't fill chunks on-demand page-by-page. It has to allocate each chunk fully upfront. * It can't support sparse chunk for NUMA configurations. SMP w/o mmu is crazy enough. Let's hope no one does NUMA w/o mmu. :-P * If chunk size isn't power-of-two multiple of PAGE_SIZE, the unaligned amount will be wasted on each chunk. So, archs which use this better align chunk size. For instructions on how to use this, read the comment on top of mm/percpu-km.c. Signed-off-by: Tejun Heo Reviewed-by: David Howells Cc: Graff Yang Cc: Sonic Zhang --- mm/percpu-km.c | 104 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++ mm/percpu.c | 4 +++ 2 files changed, 108 insertions(+) create mode 100644 mm/percpu-km.c (limited to 'mm') diff --git a/mm/percpu-km.c b/mm/percpu-km.c new file mode 100644 index 000000000000..df680855540a --- /dev/null +++ b/mm/percpu-km.c @@ -0,0 +1,104 @@ +/* + * mm/percpu-km.c - kernel memory based chunk allocation + * + * Copyright (C) 2010 SUSE Linux Products GmbH + * Copyright (C) 2010 Tejun Heo + * + * This file is released under the GPLv2. + * + * Chunks are allocated as a contiguous kernel memory using gfp + * allocation. This is to be used on nommu architectures. + * + * To use percpu-km, + * + * - define CONFIG_NEED_PER_CPU_KM from the arch Kconfig. + * + * - CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK must not be defined. It's + * not compatible with PER_CPU_KM. EMBED_FIRST_CHUNK should work + * fine. + * + * - NUMA is not supported. When setting up the first chunk, + * @cpu_distance_fn should be NULL or report all CPUs to be nearer + * than or at LOCAL_DISTANCE. + * + * - It's best if the chunk size is power of two multiple of + * PAGE_SIZE. Because each chunk is allocated as a contiguous + * kernel memory block using alloc_pages(), memory will be wasted if + * chunk size is not aligned. percpu-km code will whine about it. + */ + +#ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK +#error "contiguous percpu allocation is incompatible with paged first chunk" +#endif + +#include + +static int pcpu_populate_chunk(struct pcpu_chunk *chunk, int off, int size) +{ + /* noop */ + return 0; +} + +static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk, int off, int size) +{ + /* nada */ +} + +static struct pcpu_chunk *pcpu_create_chunk(void) +{ + const int nr_pages = pcpu_group_sizes[0] >> PAGE_SHIFT; + struct pcpu_chunk *chunk; + struct page *pages; + int i; + + chunk = pcpu_alloc_chunk(); + if (!chunk) + return NULL; + + pages = alloc_pages(GFP_KERNEL, order_base_2(nr_pages)); + if (!pages) { + pcpu_free_chunk(chunk); + return NULL; + } + + for (i = 0; i < nr_pages; i++) + pcpu_set_page_chunk(nth_page(pages, i), chunk); + + chunk->data = pages; + chunk->base_addr = page_address(pages) - pcpu_group_offsets[0]; + return chunk; +} + +static void pcpu_destroy_chunk(struct pcpu_chunk *chunk) +{ + const int nr_pages = pcpu_group_sizes[0] >> PAGE_SHIFT; + + if (chunk && chunk->data) + __free_pages(chunk->data, order_base_2(nr_pages)); + pcpu_free_chunk(chunk); +} + +static struct page *pcpu_addr_to_page(void *addr) +{ + return virt_to_page(addr); +} + +static int __init pcpu_verify_alloc_info(const struct pcpu_alloc_info *ai) +{ + size_t nr_pages, alloc_pages; + + /* all units must be in a single group */ + if (ai->nr_groups != 1) { + printk(KERN_CRIT "percpu: can't handle more than one groups\n"); + return -EINVAL; + } + + nr_pages = (ai->groups[0].nr_units * ai->unit_size) >> PAGE_SHIFT; + alloc_pages = roundup_pow_of_two(nr_pages); + + if (alloc_pages > nr_pages) + printk(KERN_WARNING "percpu: wasting %zu pages per chunk\n", + alloc_pages - nr_pages); + + return 0; +} diff --git a/mm/percpu.c b/mm/percpu.c index 15f680430671..39f7dfd59585 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -654,7 +654,11 @@ static void pcpu_destroy_chunk(struct pcpu_chunk *chunk); static struct page *pcpu_addr_to_page(void *addr); static int __init pcpu_verify_alloc_info(const struct pcpu_alloc_info *ai); +#ifdef CONFIG_NEED_PER_CPU_KM +#include "percpu-km.c" +#else #include "percpu-vm.c" +#endif /** * pcpu_chunk_addr_search - determine chunk containing specified address -- cgit v1.2.3 From ad4ba375373937817404fd92239ef4cadbded23b Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 23 Apr 2010 12:26:38 -0700 Subject: memcg: css_id() must be called under rcu_read_lock() This patch fixes task_in_mem_cgroup(), mem_cgroup_uncharge_swapcache(), mem_cgroup_move_swap_account(), and is_target_pte_for_mc() to protect calls to css_id(). An additional RCU lockdep splat was reported for memcg_oom_wake_function(), however, this function is not yet in mainline as of 2.6.34-rc5. Reported-by: Li Zefan Cc: Daisuke Nishimura Cc: Balbir Singh Signed-off-by: KAMEZAWA Hiroyuki Tested-by: Li Zefan Signed-off-by: Paul E. McKenney Cc: Andrew Morton --- mm/memcontrol.c | 21 ++++++++++++++++----- 1 file changed, 16 insertions(+), 5 deletions(-) (limited to 'mm') diff --git a/mm/memcontrol.c b/mm/memcontrol.c index f4ede99c8b9b..e06490d4ae5e 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -811,10 +811,12 @@ int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *mem) * enabled in "curr" and "curr" is a child of "mem" in *cgroup* * hierarchy(even if use_hierarchy is disabled in "mem"). */ + rcu_read_lock(); if (mem->use_hierarchy) ret = css_is_ancestor(&curr->css, &mem->css); else ret = (curr == mem); + rcu_read_unlock(); css_put(&curr->css); return ret; } @@ -2312,7 +2314,9 @@ mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent, bool swapout) /* record memcg information */ if (do_swap_account && swapout && memcg) { + rcu_read_lock(); swap_cgroup_record(ent, css_id(&memcg->css)); + rcu_read_unlock(); mem_cgroup_get(memcg); } if (swapout && memcg) @@ -2369,8 +2373,10 @@ static int mem_cgroup_move_swap_account(swp_entry_t entry, { unsigned short old_id, new_id; + rcu_read_lock(); old_id = css_id(&from->css); new_id = css_id(&to->css); + rcu_read_unlock(); if (swap_cgroup_cmpxchg(entry, old_id, new_id) == old_id) { mem_cgroup_swap_statistics(from, false); @@ -4038,11 +4044,16 @@ static int is_target_pte_for_mc(struct vm_area_struct *vma, put_page(page); } /* throught */ - if (ent.val && do_swap_account && !ret && - css_id(&mc.from->css) == lookup_swap_cgroup(ent)) { - ret = MC_TARGET_SWAP; - if (target) - target->ent = ent; + if (ent.val && do_swap_account && !ret) { + unsigned short id; + rcu_read_lock(); + id = css_id(&mc.from->css); + rcu_read_unlock(); + if (id == lookup_swap_cgroup(ent)) { + ret = MC_TARGET_SWAP; + if (target) + target->ent = ent; + } } return ret; } -- cgit v1.2.3 From 111c7d82436db4c7673922b6ba021cebb7d26dd8 Mon Sep 17 00:00:00 2001 From: "Zhang, Yanmin" Date: Thu, 1 Apr 2010 17:32:30 +0800 Subject: slub: Fix bad boundary check in init_kmem_cache_nodes() Function init_kmem_cache_nodes is incorrect when checking upper limitation of kmalloc_caches. The breakage was introduced by commit 91efd773c74bb26b5409c85ad755d536448e229c ("dma kmalloc handling fixes"). Acked-by: Christoph Lameter Signed-off-by: Pekka Enberg --- mm/slub.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'mm') diff --git a/mm/slub.c b/mm/slub.c index 7d6c8b1ccf63..d2a54fe71ea2 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -2153,7 +2153,7 @@ static int init_kmem_cache_nodes(struct kmem_cache *s, gfp_t gfpflags) int local_node; if (slab_state >= UP && (s < kmalloc_caches || - s > kmalloc_caches + KMALLOC_CACHES)) + s >= kmalloc_caches + KMALLOC_CACHES)) local_node = page_to_nid(virt_to_page(s)); else local_node = 0; -- cgit v1.2.3 From 4a6018f7f4f1075c1a5403b5ec0ee7262187b86c Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Tue, 11 May 2010 14:06:53 -0700 Subject: hugetlbfs: kill applications that use MAP_NORESERVE with SIGBUS instead of OOM-killer Ordinarily, application using hugetlbfs will create mappings with reserves. For shared mappings, these pages are reserved before mmap() returns success and for private mappings, the caller process is guaranteed and a child process that cannot get the pages gets killed with sigbus. An application that uses MAP_NORESERVE gets no reservations and mmap() will always succeed at the risk the page will not be available at fault time. This might be used for example on very large sparse mappings where the developer is confident the necessary huge pages exist to satisfy all faults even though the whole mapping cannot be backed by huge pages. Unfortunately, if an allocation does fail, VM_FAULT_OOM is returned to the fault handler which proceeds to trigger the OOM-killer. This is unhelpful. Even without hugetlbfs mounted, a user using mmap() can trivially trigger the OOM-killer because VM_FAULT_OOM is returned (will provide example program if desired - it's a whopping 24 lines long). It could be considered a DOS available to an unprivileged user. This patch alters hugetlbfs to kill a process that uses MAP_NORESERVE where huge pages were not available with SIGBUS instead of triggering the OOM killer. This change affects hugetlb_cow() as well. I feel there is a failure case in there, but I didn't create one. It would need a fairly specific target in terms of the faulting application and the hugepage pool size. The hugetlb_no_page() path is much easier to hit but both might as well be closed. Signed-off-by: Mel Gorman Cc: Lee Schermerhorn Cc: David Rientjes Cc: Andi Kleen Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/hugetlb.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'mm') diff --git a/mm/hugetlb.c b/mm/hugetlb.c index ffbdfc86aedf..4c9e6bbf3772 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1039,7 +1039,7 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma, page = alloc_buddy_huge_page(h, vma, addr); if (!page) { hugetlb_put_quota(inode->i_mapping, chg); - return ERR_PTR(-VM_FAULT_OOM); + return ERR_PTR(-VM_FAULT_SIGBUS); } } -- cgit v1.2.3 From ab941e0fff3947b6dcc9c578d918d1bba54a6874 Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Tue, 11 May 2010 14:06:55 -0700 Subject: rmap: remove anon_vma check in page_address_in_vma() Currently page_address_in_vma() compares vma->anon_vma and page_anon_vma(page) for parameter check, but in 2.6.34 a vma can have multiple anon_vmas with anon_vma_chain, so current check does not work. (For anonymous page shared by multiple processes, some verified (page,vma) pairs return -EFAULT wrongly.) We can go to checking all anon_vmas in the "same_vma" chain, but it needs to meet lock requirement. Instead, we can remove anon_vma check safely because page_address_in_vma() assumes that page and vma are already checked to belong to the identical process. Signed-off-by: Naoya Horiguchi Reviewed-by: Rik van Riel Cc: Andi Kleen Cc: Andrea Arcangeli Cc: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/rmap.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) (limited to 'mm') diff --git a/mm/rmap.c b/mm/rmap.c index 07fc94758799..0feeef860a8f 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -336,14 +336,13 @@ vma_address(struct page *page, struct vm_area_struct *vma) /* * At what user virtual address is page expected in vma? - * checking that the page matches the vma. + * Caller should check the page is actually part of the vma. */ unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma) { - if (PageAnon(page)) { - if (vma->anon_vma != page_anon_vma(page)) - return -EFAULT; - } else if (page->mapping && !(vma->vm_flags & VM_NONLINEAR)) { + if (PageAnon(page)) + ; + else if (page->mapping && !(vma->vm_flags & VM_NONLINEAR)) { if (!vma->vm_file || vma->vm_file->f_mapping != page->mapping) return -EFAULT; -- cgit v1.2.3 From 7f0f15464185a92f9d8791ad231bcd7bf6df54e4 Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Tue, 11 May 2010 14:06:58 -0700 Subject: memcg: fix css_id() RCU locking for real Commit ad4ba375373937817404fd92239ef4cadbded23b ("memcg: css_id() must be called under rcu_read_lock()") modifies memcontol.c for fixing RCU check message. But Andrew Morton pointed out that the fix doesn't seems sane and it was just for hidining lockdep messages. This is a patch for do proper things. Checking again, all places, accessing without rcu_read_lock, that commit fixies was intentional.... all callers of css_id() has reference count on it. So, it's not necessary to be under rcu_read_lock(). Considering again, we can use rcu_dereference_check for css_id(). We know css->id is valid if css->refcnt > 0. (css->id never changes and freed after css->refcnt going to be 0.) This patch makes use of rcu_dereference_check() in css_id/depth and remove unnecessary rcu-read-lock added by the commit. Signed-off-by: KAMEZAWA Hiroyuki Cc: "Paul E. McKenney" Cc: Daisuke Nishimura Cc: Balbir Singh Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memcontrol.c | 19 +++++-------------- 1 file changed, 5 insertions(+), 14 deletions(-) (limited to 'mm') diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 0f711c213d2e..595d03f33b2c 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2314,9 +2314,7 @@ mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent, bool swapout) /* record memcg information */ if (do_swap_account && swapout && memcg) { - rcu_read_lock(); swap_cgroup_record(ent, css_id(&memcg->css)); - rcu_read_unlock(); mem_cgroup_get(memcg); } if (swapout && memcg) @@ -2373,10 +2371,8 @@ static int mem_cgroup_move_swap_account(swp_entry_t entry, { unsigned short old_id, new_id; - rcu_read_lock(); old_id = css_id(&from->css); new_id = css_id(&to->css); - rcu_read_unlock(); if (swap_cgroup_cmpxchg(entry, old_id, new_id) == old_id) { mem_cgroup_swap_statistics(from, false); @@ -4044,16 +4040,11 @@ static int is_target_pte_for_mc(struct vm_area_struct *vma, put_page(page); } /* throught */ - if (ent.val && do_swap_account && !ret) { - unsigned short id; - rcu_read_lock(); - id = css_id(&mc.from->css); - rcu_read_unlock(); - if (id == lookup_swap_cgroup(ent)) { - ret = MC_TARGET_SWAP; - if (target) - target->ent = ent; - } + if (ent.val && do_swap_account && !ret && + css_id(&mc.from->css) == lookup_swap_cgroup(ent)) { + ret = MC_TARGET_SWAP; + if (target) + target->ent = ent; } return ret; } -- cgit v1.2.3 From 747388d78a0ae768fd82b55c4ed38aa646a72364 Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Tue, 11 May 2010 14:06:59 -0700 Subject: memcg: fix css_is_ancestor() RCU locking Some callers (in memcontrol.c) calls css_is_ancestor() without rcu_read_lock. Because css_is_ancestor() has to access RCU protected data, it should be under rcu_read_lock(). This makes css_is_ancestor() itself does safe access to RCU protected area. (At least, "root" can have refcnt==0 if it's not an ancestor of "child". So, we need rcu_read_lock().) Signed-off-by: KAMEZAWA Hiroyuki Cc: "Paul E. McKenney" Cc: Daisuke Nishimura Cc: Balbir Singh Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memcontrol.c | 4 ---- 1 file changed, 4 deletions(-) (limited to 'mm') diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 595d03f33b2c..8a79a6f0f029 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -811,12 +811,10 @@ int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *mem) * enabled in "curr" and "curr" is a child of "mem" in *cgroup* * hierarchy(even if use_hierarchy is disabled in "mem"). */ - rcu_read_lock(); if (mem->use_hierarchy) ret = css_is_ancestor(&curr->css, &mem->css); else ret = (curr == mem); - rcu_read_unlock(); css_put(&curr->css); return ret; } @@ -1603,7 +1601,6 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm, * There is a small race that "from" or "to" can be * freed by rmdir, so we use css_tryget(). */ - rcu_read_lock(); from = mc.from; to = mc.to; if (from && css_tryget(&from->css)) { @@ -1624,7 +1621,6 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm, do_continue = (to == mem_over_limit); css_put(&to->css); } - rcu_read_unlock(); if (do_continue) { DEFINE_WAIT(wait); prepare_to_wait(&mc.waitq, &wait, -- cgit v1.2.3