diff options
Diffstat (limited to 'mm')
| -rw-r--r-- | mm/Kconfig | 3 | ||||
| -rw-r--r-- | mm/Makefile | 2 | ||||
| -rw-r--r-- | mm/bootmem.c | 24 | ||||
| -rw-r--r-- | mm/memblock.c | 541 | ||||
| -rw-r--r-- | mm/memory.c | 16 | ||||
| -rw-r--r-- | mm/page_alloc.c | 8 | ||||
| -rw-r--r-- | mm/page_cgroup.c | 7 | ||||
| -rw-r--r-- | mm/slab.c | 2 | ||||
| -rw-r--r-- | mm/slub.c | 86 | ||||
| -rw-r--r-- | mm/vmscan.c | 10 |
10 files changed, 644 insertions, 55 deletions
diff --git a/mm/Kconfig b/mm/Kconfig index 527136b22384..f4e516e9c37c 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -128,6 +128,9 @@ 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 + boolean + # eventually, we can have this option just 'select SPARSEMEM' config MEMORY_HOTPLUG bool "Allow for memory hot-add" diff --git a/mm/Makefile b/mm/Makefile index 8982504bd03b..34b2546a9e37 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -15,6 +15,8 @@ obj-y := bootmem.o filemap.o mempool.o oom_kill.o fadvise.o \ $(mmu-y) obj-y += init-mm.o +obj-$(CONFIG_HAVE_MEMBLOCK) += memblock.o + obj-$(CONFIG_BOUNCE) += bounce.o obj-$(CONFIG_SWAP) += page_io.o swap_state.o swapfile.o thrash.o obj-$(CONFIG_HAS_DMA) += dmapool.o diff --git a/mm/bootmem.c b/mm/bootmem.c index 58c66cc5056a..142c84a54993 100644 --- a/mm/bootmem.c +++ b/mm/bootmem.c @@ -833,15 +833,24 @@ static void * __init ___alloc_bootmem_node(bootmem_data_t *bdata, void * __init __alloc_bootmem_node(pg_data_t *pgdat, unsigned long size, unsigned long align, unsigned long goal) { + void *ptr; + if (WARN_ON_ONCE(slab_is_available())) return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id); #ifdef CONFIG_NO_BOOTMEM - return __alloc_memory_core_early(pgdat->node_id, size, align, + ptr = __alloc_memory_core_early(pgdat->node_id, size, align, + goal, -1ULL); + if (ptr) + return ptr; + + ptr = __alloc_memory_core_early(MAX_NUMNODES, size, align, goal, -1ULL); #else - return ___alloc_bootmem_node(pgdat->bdata, size, align, goal, 0); + ptr = ___alloc_bootmem_node(pgdat->bdata, size, align, goal, 0); #endif + + return ptr; } void * __init __alloc_bootmem_node_high(pg_data_t *pgdat, unsigned long size, @@ -977,14 +986,21 @@ void * __init __alloc_bootmem_low(unsigned long size, unsigned long align, void * __init __alloc_bootmem_low_node(pg_data_t *pgdat, unsigned long size, unsigned long align, unsigned long goal) { + void *ptr; + if (WARN_ON_ONCE(slab_is_available())) return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id); #ifdef CONFIG_NO_BOOTMEM - return __alloc_memory_core_early(pgdat->node_id, size, align, + ptr = __alloc_memory_core_early(pgdat->node_id, size, align, + goal, ARCH_LOW_ADDRESS_LIMIT); + if (ptr) + return ptr; + ptr = __alloc_memory_core_early(MAX_NUMNODES, size, align, goal, ARCH_LOW_ADDRESS_LIMIT); #else - return ___alloc_bootmem_node(pgdat->bdata, size, align, + ptr = ___alloc_bootmem_node(pgdat->bdata, size, align, goal, ARCH_LOW_ADDRESS_LIMIT); #endif + return ptr; } diff --git a/mm/memblock.c b/mm/memblock.c new file mode 100644 index 000000000000..3024eb30fc27 --- /dev/null +++ b/mm/memblock.c @@ -0,0 +1,541 @@ +/* + * Procedures for maintaining information about logical memory blocks. + * + * Peter Bergner, IBM Corp. June 2001. + * Copyright (C) 2001 Peter Bergner. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/bitops.h> +#include <linux/memblock.h> + +#define MEMBLOCK_ALLOC_ANYWHERE 0 + +struct memblock memblock; + +static int memblock_debug; + +static int __init early_memblock(char *p) +{ + if (p && strstr(p, "debug")) + memblock_debug = 1; + return 0; +} +early_param("memblock", early_memblock); + +static void memblock_dump(struct memblock_region *region, char *name) +{ + unsigned long long base, size; + int i; + + pr_info(" %s.cnt = 0x%lx\n", name, region->cnt); + + for (i = 0; i < region->cnt; i++) { + base = region->region[i].base; + size = region->region[i].size; + + pr_info(" %s[0x%x]\t0x%016llx - 0x%016llx, 0x%llx bytes\n", + name, i, base, base + size - 1, size); + } +} + +void memblock_dump_all(void) +{ + if (!memblock_debug) + return; + + pr_info("MEMBLOCK configuration:\n"); + pr_info(" rmo_size = 0x%llx\n", (unsigned long long)memblock.rmo_size); + pr_info(" memory.size = 0x%llx\n", (unsigned long long)memblock.memory.size); + + memblock_dump(&memblock.memory, "memory"); + memblock_dump(&memblock.reserved, "reserved"); +} + +static unsigned long memblock_addrs_overlap(u64 base1, u64 size1, u64 base2, + u64 size2) +{ + return ((base1 < (base2 + size2)) && (base2 < (base1 + size1))); +} + +static long memblock_addrs_adjacent(u64 base1, u64 size1, u64 base2, u64 size2) +{ + if (base2 == base1 + size1) + return 1; + else if (base1 == base2 + size2) + return -1; + + return 0; +} + +static long memblock_regions_adjacent(struct memblock_region *rgn, + unsigned long r1, unsigned long r2) +{ + u64 base1 = rgn->region[r1].base; + u64 size1 = rgn->region[r1].size; + u64 base2 = rgn->region[r2].base; + u64 size2 = rgn->region[r2].size; + + return memblock_addrs_adjacent(base1, size1, base2, size2); +} + +static void memblock_remove_region(struct memblock_region *rgn, unsigned long r) +{ + unsigned long i; + + for (i = r; i < rgn->cnt - 1; i++) { + rgn->region[i].base = rgn->region[i + 1].base; + rgn->region[i].size = rgn->region[i + 1].size; + } + rgn->cnt--; +} + +/* Assumption: base addr of region 1 < base addr of region 2 */ +static void memblock_coalesce_regions(struct memblock_region *rgn, + unsigned long r1, unsigned long r2) +{ + rgn->region[r1].size += rgn->region[r2].size; + memblock_remove_region(rgn, r2); +} + +void __init memblock_init(void) +{ + /* Create a dummy zero size MEMBLOCK which will get coalesced away later. + * This simplifies the memblock_add() code below... + */ + memblock.memory.region[0].base = 0; + memblock.memory.region[0].size = 0; + memblock.memory.cnt = 1; + + /* Ditto. */ + memblock.reserved.region[0].base = 0; + memblock.reserved.region[0].size = 0; + memblock.reserved.cnt = 1; +} + +void __init memblock_analyze(void) +{ + int i; + + memblock.memory.size = 0; + + for (i = 0; i < memblock.memory.cnt; i++) + memblock.memory.size += memblock.memory.region[i].size; +} + +static long memblock_add_region(struct memblock_region *rgn, u64 base, u64 size) +{ + unsigned long coalesced = 0; + long adjacent, i; + + if ((rgn->cnt == 1) && (rgn->region[0].size == 0)) { + rgn->region[0].base = base; + rgn->region[0].size = size; + return 0; + } + + /* First try and coalesce this MEMBLOCK with another. */ + for (i = 0; i < rgn->cnt; i++) { + u64 rgnbase = rgn->region[i].base; + u64 rgnsize = rgn->region[i].size; + + if ((rgnbase == base) && (rgnsize == size)) + /* Already have this region, so we're done */ + return 0; + + adjacent = memblock_addrs_adjacent(base, size, rgnbase, rgnsize); + if (adjacent > 0) { + rgn->region[i].base -= size; + rgn->region[i].size += size; + coalesced++; + break; + } else if (adjacent < 0) { + rgn->region[i].size += size; + coalesced++; + break; + } + } + + if ((i < rgn->cnt - 1) && memblock_regions_adjacent(rgn, i, i+1)) { + memblock_coalesce_regions(rgn, i, i+1); + coalesced++; + } + + if (coalesced) + return coalesced; + if (rgn->cnt >= MAX_MEMBLOCK_REGIONS) + return -1; + + /* Couldn't coalesce the MEMBLOCK, so add it to the sorted table. */ + for (i = rgn->cnt - 1; i >= 0; i--) { + if (base < rgn->region[i].base) { + rgn->region[i+1].base = rgn->region[i].base; + rgn->region[i+1].size = rgn->region[i].size; + } else { + rgn->region[i+1].base = base; + rgn->region[i+1].size = size; + break; + } + } + + if (base < rgn->region[0].base) { + rgn->region[0].base = base; + rgn->region[0].size = size; + } + rgn->cnt++; + + return 0; +} + +long memblock_add(u64 base, u64 size) +{ + struct memblock_region *_rgn = &memblock.memory; + + /* On pSeries LPAR systems, the first MEMBLOCK is our RMO region. */ + if (base == 0) + memblock.rmo_size = size; + + return memblock_add_region(_rgn, base, size); + +} + +static long __memblock_remove(struct memblock_region *rgn, u64 base, u64 size) +{ + u64 rgnbegin, rgnend; + u64 end = base + size; + int i; + + rgnbegin = rgnend = 0; /* supress gcc warnings */ + + /* Find the region where (base, size) belongs to */ + for (i=0; i < rgn->cnt; i++) { + rgnbegin = rgn->region[i].base; + rgnend = rgnbegin + rgn->region[i].size; + + if ((rgnbegin <= base) && (end <= rgnend)) + break; + } + + /* Didn't find the region */ + if (i == rgn->cnt) + return -1; + + /* Check to see if we are removing entire region */ + if ((rgnbegin == base) && (rgnend == end)) { + memblock_remove_region(rgn, i); + return 0; + } + + /* Check to see if region is matching at the front */ + if (rgnbegin == base) { + rgn->region[i].base = end; + rgn->region[i].size -= size; + return 0; + } + + /* Check to see if the region is matching at the end */ + if (rgnend == end) { + rgn->region[i].size -= size; + return 0; + } + + /* + * We need to split the entry - adjust the current one to the + * beginging of the hole and add the region after hole. + */ + rgn->region[i].size = base - rgn->region[i].base; + return memblock_add_region(rgn, end, rgnend - end); +} + +long memblock_remove(u64 base, u64 size) +{ + return __memblock_remove(&memblock.memory, base, size); +} + +long __init memblock_free(u64 base, u64 size) +{ + return __memblock_remove(&memblock.reserved, base, size); +} + +long __init memblock_reserve(u64 base, u64 size) +{ + struct memblock_region *_rgn = &memblock.reserved; + + BUG_ON(0 == size); + + return memblock_add_region(_rgn, base, size); +} + +long memblock_overlaps_region(struct memblock_region *rgn, u64 base, u64 size) +{ + unsigned long i; + + for (i = 0; i < rgn->cnt; i++) { + u64 rgnbase = rgn->region[i].base; + u64 rgnsize = rgn->region[i].size; + if (memblock_addrs_overlap(base, size, rgnbase, rgnsize)) + break; + } + + return (i < rgn->cnt) ? i : -1; +} + +static u64 memblock_align_down(u64 addr, u64 size) +{ + return addr & ~(size - 1); +} + +static u64 memblock_align_up(u64 addr, u64 size) +{ + return (addr + (size - 1)) & ~(size - 1); +} + +static u64 __init memblock_alloc_nid_unreserved(u64 start, u64 end, + u64 size, u64 align) +{ + u64 base, res_base; + long j; + + base = memblock_align_down((end - size), align); + while (start <= base) { + j = memblock_overlaps_region(&memblock.reserved, base, size); + if (j < 0) { + /* this area isn't reserved, take it */ + if (memblock_add_region(&memblock.reserved, base, size) < 0) + base = ~(u64)0; + return base; + } + res_base = memblock.reserved.region[j].base; + if (res_base < size) + break; + base = memblock_align_down(res_base - size, align); + } + + return ~(u64)0; +} + +static u64 __init memblock_alloc_nid_region(struct memblock_property *mp, + u64 (*nid_range)(u64, u64, int *), + u64 size, u64 align, int nid) +{ + u64 start, end; + + start = mp->base; + end = start + mp->size; + + start = memblock_align_up(start, align); + while (start < end) { + u64 this_end; + int this_nid; + + this_end = nid_range(start, end, &this_nid); + if (this_nid == nid) { + u64 ret = memblock_alloc_nid_unreserved(start, this_end, + size, align); + if (ret != ~(u64)0) + return ret; + } + start = this_end; + } + + return ~(u64)0; +} + +u64 __init memblock_alloc_nid(u64 size, u64 align, int nid, + u64 (*nid_range)(u64 start, u64 end, int *nid)) +{ + struct memblock_region *mem = &memblock.memory; + int i; + + BUG_ON(0 == size); + + size = memblock_align_up(size, align); + + for (i = 0; i < mem->cnt; i++) { + u64 ret = memblock_alloc_nid_region(&mem->region[i], + nid_range, + size, align, nid); + if (ret != ~(u64)0) + return ret; + } + + return memblock_alloc(size, align); +} + +u64 __init memblock_alloc(u64 size, u64 align) +{ + return memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ANYWHERE); +} + +u64 __init memblock_alloc_base(u64 size, u64 align, u64 max_addr) +{ + u64 alloc; + + alloc = __memblock_alloc_base(size, align, max_addr); + + if (alloc == 0) + panic("ERROR: Failed to allocate 0x%llx bytes below 0x%llx.\n", + (unsigned long long) size, (unsigned long long) max_addr); + + return alloc; +} + +u64 __init __memblock_alloc_base(u64 size, u64 align, u64 max_addr) +{ + long i, j; + u64 base = 0; + u64 res_base; + + BUG_ON(0 == size); + + size = memblock_align_up(size, align); + + /* On some platforms, make sure we allocate lowmem */ + /* Note that MEMBLOCK_REAL_LIMIT may be MEMBLOCK_ALLOC_ANYWHERE */ + if (max_addr == MEMBLOCK_ALLOC_ANYWHERE) + max_addr = MEMBLOCK_REAL_LIMIT; + + for (i = memblock.memory.cnt - 1; i >= 0; i--) { + u64 memblockbase = memblock.memory.region[i].base; + u64 memblocksize = memblock.memory.region[i].size; + + if (memblocksize < size) + continue; + if (max_addr == MEMBLOCK_ALLOC_ANYWHERE) + base = memblock_align_down(memblockbase + memblocksize - size, align); + else if (memblockbase < max_addr) { + base = min(memblockbase + memblocksize, max_addr); + base = memblock_align_down(base - size, align); + } else + continue; + + while (base && memblockbase <= base) { + j = memblock_overlaps_region(&memblock.reserved, base, size); + if (j < 0) { + /* this area isn't reserved, take it */ + if (memblock_add_region(&memblock.reserved, base, size) < 0) + return 0; + return base; + } + res_base = memblock.reserved.region[j].base; + if (res_base < size) + break; + base = memblock_align_down(res_base - size, align); + } + } + return 0; +} + +/* You must call memblock_analyze() before this. */ +u64 __init memblock_phys_mem_size(void) +{ + return memblock.memory.size; +} + +u64 memblock_end_of_DRAM(void) +{ + int idx = memblock.memory.cnt - 1; + + return (memblock.memory.region[idx].base + memblock.memory.region[idx].size); +} + +/* You must call memblock_analyze() after this. */ +void __init memblock_enforce_memory_limit(u64 memory_limit) +{ + unsigned long i; + u64 limit; + struct memblock_property *p; + + if (!memory_limit) + return; + + /* Truncate the memblock regions to satisfy the memory limit. */ + limit = memory_limit; + for (i = 0; i < memblock.memory.cnt; i++) { + if (limit > memblock.memory.region[i].size) { + limit -= memblock.memory.region[i].size; + continue; + } + + memblock.memory.region[i].size = limit; + memblock.memory.cnt = i + 1; + break; + } + + if (memblock.memory.region[0].size < memblock.rmo_size) + memblock.rmo_size = memblock.memory.region[0].size; + + memory_limit = memblock_end_of_DRAM(); + + /* And truncate any reserves above the limit also. */ + for (i = 0; i < memblock.reserved.cnt; i++) { + p = &memblock.reserved.region[i]; + + if (p->base > memory_limit) + p->size = 0; + else if ((p->base + p->size) > memory_limit) + p->size = memory_limit - p->base; + + if (p->size == 0) { + memblock_remove_region(&memblock.reserved, i); + i--; + } + } +} + +int __init memblock_is_reserved(u64 addr) +{ + int i; + + for (i = 0; i < memblock.reserved.cnt; i++) { + u64 upper = memblock.reserved.region[i].base + + memblock.reserved.region[i].size - 1; + if ((addr >= memblock.reserved.region[i].base) && (addr <= upper)) + return 1; + } + return 0; +} + +int memblock_is_region_reserved(u64 base, u64 size) +{ + return memblock_overlaps_region(&memblock.reserved, base, size); +} + +/* + * Given a <base, len>, find which memory regions belong to this range. + * Adjust the request and return a contiguous chunk. + */ +int memblock_find(struct memblock_property *res) +{ + int i; + u64 rstart, rend; + + rstart = res->base; + rend = rstart + res->size - 1; + + for (i = 0; i < memblock.memory.cnt; i++) { + u64 start = memblock.memory.region[i].base; + u64 end = start + memblock.memory.region[i].size - 1; + + if (start > rend) + return -1; + + if ((end >= rstart) && (start < rend)) { + /* adjust the request */ + if (rstart < start) + rstart = start; + if (rend > end) + rend = end; + res->base = rstart; + res->size = rend - rstart + 1; + return 0; + } + } + return -1; +} diff --git a/mm/memory.c b/mm/memory.c index 119b7ccdf39b..bde42c6d3633 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1394,10 +1394,20 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, return i ? : -EFAULT; } if (pages) { - struct page *page = vm_normal_page(gate_vma, start, *pte); + struct page *page; + + page = vm_normal_page(gate_vma, start, *pte); + if (!page) { + if (!(gup_flags & FOLL_DUMP) && + is_zero_pfn(pte_pfn(*pte))) + page = pte_page(*pte); + else { + pte_unmap(pte); + return i ? : -EFAULT; + } + } pages[i] = page; - if (page) - get_page(page); + get_page(page); } pte_unmap(pte); if (vmas) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 431214b941ac..9bd339eb04c6 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -3634,6 +3634,9 @@ void * __init __alloc_memory_core_early(int nid, u64 size, u64 align, int i; void *ptr; + if (limit > get_max_mapped()) + limit = get_max_mapped(); + /* need to go over early_node_map to find out good range for node */ for_each_active_range_index_in_nid(i, nid) { u64 addr; @@ -3659,6 +3662,11 @@ void * __init __alloc_memory_core_early(int nid, u64 size, u64 align, ptr = phys_to_virt(addr); memset(ptr, 0, size); reserve_early_without_check(addr, addr + size, "BOOTMEM"); + /* + * The min_count is set to 0 so that bootmem allocated blocks + * are never reported as leaks. + */ + kmemleak_alloc(ptr, size, 0, 0); return ptr; } diff --git a/mm/page_cgroup.c b/mm/page_cgroup.c index 6c0081441a32..5bffada7cde1 100644 --- a/mm/page_cgroup.c +++ b/mm/page_cgroup.c @@ -9,6 +9,7 @@ #include <linux/vmalloc.h> #include <linux/cgroup.h> #include <linux/swapops.h> +#include <linux/kmemleak.h> static void __meminit __init_page_cgroup(struct page_cgroup *pc, unsigned long pfn) @@ -126,6 +127,12 @@ static int __init_refok init_section_page_cgroup(unsigned long pfn) if (!base) base = vmalloc(table_size); } + /* + * The value stored in section->page_cgroup is (base - pfn) + * and it does not point to the memory block allocated above, + * causing kmemleak false positives. + */ + kmemleak_not_leak(base); } else { /* * We don't have to allocate page_cgroup again, but diff --git a/mm/slab.c b/mm/slab.c index e49f8f46f46d..29aad44a55c2 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -861,7 +861,7 @@ static void __cpuinit start_cpu_timer(int cpu) */ if (keventd_up() && reap_work->work.func == NULL) { init_reap_node(cpu); - INIT_DELAYED_WORK(reap_work, cache_reap); + INIT_DELAYED_WORK_DEFERRABLE(reap_work, cache_reap); schedule_delayed_work_on(cpu, reap_work, __round_jiffies_relative(HZ, cpu)); } diff --git a/mm/slub.c b/mm/slub.c index 578f68f3c51f..fba51d6d4cc4 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -107,11 +107,17 @@ * the fast path and disables lockless freelists. */ +#define SLAB_DEBUG_FLAGS (SLAB_RED_ZONE | SLAB_POISON | SLAB_STORE_USER | \ + SLAB_TRACE | SLAB_DEBUG_FREE) + +static inline int kmem_cache_debug(struct kmem_cache *s) +{ #ifdef CONFIG_SLUB_DEBUG -#define SLABDEBUG 1 + return unlikely(s->flags & SLAB_DEBUG_FLAGS); #else -#define SLABDEBUG 0 + return 0; #endif +} /* * Issues still to be resolved: @@ -162,8 +168,8 @@ #define MAX_OBJS_PER_PAGE 65535 /* since page.objects is u16 */ /* Internal SLUB flags */ -#define __OBJECT_POISON 0x80000000 /* Poison object */ -#define __SYSFS_ADD_DEFERRED 0x40000000 /* Not yet visible via sysfs */ +#define __OBJECT_POISON 0x80000000UL /* Poison object */ +#define __SYSFS_ADD_DEFERRED 0x40000000UL /* Not yet visible via sysfs */ static int kmem_size = sizeof(struct kmem_cache); @@ -1073,7 +1079,7 @@ static inline struct page *alloc_slab_page(gfp_t flags, int node, flags |= __GFP_NOTRACK; - if (node == -1) + if (node == NUMA_NO_NODE) return alloc_pages(flags, order); else return alloc_pages_exact_node(node, flags, order); @@ -1157,9 +1163,6 @@ static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node) inc_slabs_node(s, page_to_nid(page), page->objects); page->slab = s; page->flags |= 1 << PG_slab; - if (s->flags & (SLAB_DEBUG_FREE | SLAB_RED_ZONE | SLAB_POISON | - SLAB_STORE_USER | SLAB_TRACE)) - __SetPageSlubDebug(page); start = page_address(page); @@ -1186,14 +1189,13 @@ static void __free_slab(struct kmem_cache *s, struct page *page) int order = compound_order(page); int pages = 1 << order; - if (unlikely(SLABDEBUG && PageSlubDebug(page))) { + if (kmem_cache_debug(s)) { void *p; slab_pad_check(s, page); for_each_object(p, s, page_address(page), page->objects) check_object(s, page, p, 0); - __ClearPageSlubDebug(page); } kmemcheck_free_shadow(page, compound_order(page)); @@ -1387,10 +1389,10 @@ static struct page *get_any_partial(struct kmem_cache *s, gfp_t flags) static struct page *get_partial(struct kmem_cache *s, gfp_t flags, int node) { struct page *page; - int searchnode = (node == -1) ? numa_node_id() : node; + int searchnode = (node == NUMA_NO_NODE) ? numa_node_id() : node; page = get_partial_node(get_node(s, searchnode)); - if (page || (flags & __GFP_THISNODE)) + if (page || node != -1) return page; return get_any_partial(s, flags); @@ -1415,8 +1417,7 @@ static void unfreeze_slab(struct kmem_cache *s, struct page *page, int tail) stat(s, tail ? DEACTIVATE_TO_TAIL : DEACTIVATE_TO_HEAD); } else { stat(s, DEACTIVATE_FULL); - if (SLABDEBUG && PageSlubDebug(page) && - (s->flags & SLAB_STORE_USER)) + if (kmem_cache_debug(s) && (s->flags & SLAB_STORE_USER)) add_full(n, page); } slab_unlock(page); @@ -1515,7 +1516,7 @@ static void flush_all(struct kmem_cache *s) static inline int node_match(struct kmem_cache_cpu *c, int node) { #ifdef CONFIG_NUMA - if (node != -1 && c->node != node) + if (node != NUMA_NO_NODE && c->node != node) return 0; #endif return 1; @@ -1624,7 +1625,7 @@ load_freelist: object = c->page->freelist; if (unlikely(!object)) goto another_slab; - if (unlikely(SLABDEBUG && PageSlubDebug(c->page))) + if (kmem_cache_debug(s)) goto debug; c->freelist = get_freepointer(s, object); @@ -1727,7 +1728,7 @@ static __always_inline void *slab_alloc(struct kmem_cache *s, void *kmem_cache_alloc(struct kmem_cache *s, gfp_t gfpflags) { - void *ret = slab_alloc(s, gfpflags, -1, _RET_IP_); + void *ret = slab_alloc(s, gfpflags, NUMA_NO_NODE, _RET_IP_); trace_kmem_cache_alloc(_RET_IP_, ret, s->objsize, s->size, gfpflags); @@ -1738,7 +1739,7 @@ EXPORT_SYMBOL(kmem_cache_alloc); #ifdef CONFIG_TRACING void *kmem_cache_alloc_notrace(struct kmem_cache *s, gfp_t gfpflags) { - return slab_alloc(s, gfpflags, -1, _RET_IP_); + return slab_alloc(s, gfpflags, NUMA_NO_NODE, _RET_IP_); } EXPORT_SYMBOL(kmem_cache_alloc_notrace); #endif @@ -1783,7 +1784,7 @@ static void __slab_free(struct kmem_cache *s, struct page *page, stat(s, FREE_SLOWPATH); slab_lock(page); - if (unlikely(SLABDEBUG && PageSlubDebug(page))) + if (kmem_cache_debug(s)) goto debug; checks_ok: @@ -2490,7 +2491,6 @@ void kmem_cache_destroy(struct kmem_cache *s) s->refcount--; if (!s->refcount) { list_del(&s->list); - up_write(&slub_lock); if (kmem_cache_close(s)) { printk(KERN_ERR "SLUB %s: %s called for cache that " "still has objects.\n", s->name, __func__); @@ -2499,8 +2499,8 @@ void kmem_cache_destroy(struct kmem_cache *s) if (s->flags & SLAB_DESTROY_BY_RCU) rcu_barrier(); sysfs_slab_remove(s); - } else - up_write(&slub_lock); + } + up_write(&slub_lock); } EXPORT_SYMBOL(kmem_cache_destroy); @@ -2728,7 +2728,7 @@ void *__kmalloc(size_t size, gfp_t flags) if (unlikely(ZERO_OR_NULL_PTR(s))) return s; - ret = slab_alloc(s, flags, -1, _RET_IP_); + ret = slab_alloc(s, flags, NUMA_NO_NODE, _RET_IP_); trace_kmalloc(_RET_IP_, ret, size, s->size, flags); @@ -3118,9 +3118,12 @@ void __init kmem_cache_init(void) slab_state = UP; /* Provide the correct kmalloc names now that the caches are up */ - for (i = KMALLOC_SHIFT_LOW; i < SLUB_PAGE_SHIFT; i++) - kmalloc_caches[i]. name = - kasprintf(GFP_NOWAIT, "kmalloc-%d", 1 << i); + for (i = KMALLOC_SHIFT_LOW; i < SLUB_PAGE_SHIFT; i++) { + char *s = kasprintf(GFP_NOWAIT, "kmalloc-%d", 1 << i); + + BUG_ON(!s); + kmalloc_caches[i].name = s; + } #ifdef CONFIG_SMP register_cpu_notifier(&slab_notifier); @@ -3223,14 +3226,12 @@ struct kmem_cache *kmem_cache_create(const char *name, size_t size, */ s->objsize = max(s->objsize, (int)size); s->inuse = max_t(int, s->inuse, ALIGN(size, sizeof(void *))); - up_write(&slub_lock); if (sysfs_slab_alias(s, name)) { - down_write(&slub_lock); s->refcount--; - up_write(&slub_lock); goto err; } + up_write(&slub_lock); return s; } @@ -3239,14 +3240,12 @@ struct kmem_cache *kmem_cache_create(const char *name, size_t size, if (kmem_cache_open(s, GFP_KERNEL, name, size, align, flags, ctor)) { list_add(&s->list, &slab_caches); - up_write(&slub_lock); if (sysfs_slab_add(s)) { - down_write(&slub_lock); list_del(&s->list); - up_write(&slub_lock); kfree(s); goto err; } + up_write(&slub_lock); return s; } kfree(s); @@ -3312,7 +3311,7 @@ void *__kmalloc_track_caller(size_t size, gfp_t gfpflags, unsigned long caller) if (unlikely(ZERO_OR_NULL_PTR(s))) return s; - ret = slab_alloc(s, gfpflags, -1, caller); + ret = slab_alloc(s, gfpflags, NUMA_NO_NODE, caller); /* Honor the call site pointer we recieved. */ trace_kmalloc(caller, ret, size, s->size, gfpflags); @@ -3395,16 +3394,6 @@ static void validate_slab_slab(struct kmem_cache *s, struct page *page, } else printk(KERN_INFO "SLUB %s: Skipped busy slab 0x%p\n", s->name, page); - - if (s->flags & DEBUG_DEFAULT_FLAGS) { - if (!PageSlubDebug(page)) - printk(KERN_ERR "SLUB %s: SlubDebug not set " - "on slab 0x%p\n", s->name, page); - } else { - if (PageSlubDebug(page)) - printk(KERN_ERR "SLUB %s: SlubDebug set on " - "slab 0x%p\n", s->name, page); - } } static int validate_slab_node(struct kmem_cache *s, @@ -4504,6 +4493,13 @@ static int sysfs_slab_add(struct kmem_cache *s) static void sysfs_slab_remove(struct kmem_cache *s) { + if (slab_state < SYSFS) + /* + * Sysfs has not been setup yet so no need to remove the + * cache from sysfs. + */ + return; + kobject_uevent(&s->kobj, KOBJ_REMOVE); kobject_del(&s->kobj); kobject_put(&s->kobj); @@ -4549,8 +4545,11 @@ static int __init slab_sysfs_init(void) struct kmem_cache *s; int err; + down_write(&slub_lock); + slab_kset = kset_create_and_add("slab", &slab_uevent_ops, kernel_kobj); if (!slab_kset) { + up_write(&slub_lock); printk(KERN_ERR "Cannot register slab subsystem.\n"); return -ENOSYS; } @@ -4575,6 +4574,7 @@ static int __init slab_sysfs_init(void) kfree(al); } + up_write(&slub_lock); resiliency_test(); return 0; } diff --git a/mm/vmscan.c b/mm/vmscan.c index 9c7e57cc63a3..b94fe1b3da43 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -213,8 +213,9 @@ unsigned long shrink_slab(unsigned long scanned, gfp_t gfp_mask, list_for_each_entry(shrinker, &shrinker_list, list) { unsigned long long delta; unsigned long total_scan; - unsigned long max_pass = (*shrinker->shrink)(0, gfp_mask); + unsigned long max_pass; + max_pass = (*shrinker->shrink)(shrinker, 0, gfp_mask); delta = (4 * scanned) / shrinker->seeks; delta *= max_pass; do_div(delta, lru_pages + 1); @@ -242,8 +243,9 @@ unsigned long shrink_slab(unsigned long scanned, gfp_t gfp_mask, int shrink_ret; int nr_before; - nr_before = (*shrinker->shrink)(0, gfp_mask); - shrink_ret = (*shrinker->shrink)(this_scan, gfp_mask); + nr_before = (*shrinker->shrink)(shrinker, 0, gfp_mask); + shrink_ret = (*shrinker->shrink)(shrinker, this_scan, + gfp_mask); if (shrink_ret == -1) break; if (shrink_ret < nr_before) @@ -296,7 +298,7 @@ static int may_write_to_queue(struct backing_dev_info *bdi) static void handle_write_error(struct address_space *mapping, struct page *page, int error) { - lock_page(page); + lock_page_nosync(page); if (page_mapping(page) == mapping) mapping_set_error(mapping, error); unlock_page(page); |