diff options
Diffstat (limited to 'mm')
| -rw-r--r-- | mm/Kconfig | 3 | ||||
| -rw-r--r-- | mm/Makefile | 2 | ||||
| -rw-r--r-- | mm/backing-dev.c | 17 | ||||
| -rw-r--r-- | mm/bootmem.c | 24 | ||||
| -rw-r--r-- | mm/highmem.c | 7 | ||||
| -rw-r--r-- | mm/memblock.c | 541 | ||||
| -rw-r--r-- | mm/memory-failure.c | 33 | ||||
| -rw-r--r-- | mm/memory.c | 16 | ||||
| -rw-r--r-- | mm/page-writeback.c | 3 | ||||
| -rw-r--r-- | mm/page_alloc.c | 8 | ||||
| -rw-r--r-- | mm/page_cgroup.c | 7 | ||||
| -rw-r--r-- | mm/percpu.c | 85 | ||||
| -rw-r--r-- | mm/vmscan.c | 10 |
13 files changed, 694 insertions, 62 deletions
diff --git a/mm/Kconfig b/mm/Kconfig index 527136b2238..f4e516e9c37 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 8982504bd03..34b2546a9e3 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/backing-dev.c b/mm/backing-dev.c index 660a87a2251..123bcef13e5 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -104,15 +104,13 @@ static int bdi_debug_stats_show(struct seq_file *m, void *v) "b_more_io: %8lu\n" "bdi_list: %8u\n" "state: %8lx\n" - "wb_mask: %8lx\n" - "wb_list: %8u\n" - "wb_cnt: %8u\n", + "wb_list: %8u\n", (unsigned long) K(bdi_stat(bdi, BDI_WRITEBACK)), (unsigned long) K(bdi_stat(bdi, BDI_RECLAIMABLE)), K(bdi_thresh), K(dirty_thresh), K(background_thresh), nr_wb, nr_dirty, nr_io, nr_more_io, - !list_empty(&bdi->bdi_list), bdi->state, bdi->wb_mask, - !list_empty(&bdi->wb_list), bdi->wb_cnt); + !list_empty(&bdi->bdi_list), bdi->state, + !list_empty(&bdi->wb_list)); #undef K return 0; @@ -340,14 +338,13 @@ int bdi_has_dirty_io(struct backing_dev_info *bdi) static void bdi_flush_io(struct backing_dev_info *bdi) { struct writeback_control wbc = { - .bdi = bdi, .sync_mode = WB_SYNC_NONE, .older_than_this = NULL, .range_cyclic = 1, .nr_to_write = 1024, }; - writeback_inodes_wbc(&wbc); + writeback_inodes_wb(&bdi->wb, &wbc); } /* @@ -675,12 +672,6 @@ int bdi_init(struct backing_dev_info *bdi) bdi_wb_init(&bdi->wb, bdi); - /* - * Just one thread support for now, hard code mask and count - */ - bdi->wb_mask = 1; - bdi->wb_cnt = 1; - for (i = 0; i < NR_BDI_STAT_ITEMS; i++) { err = percpu_counter_init(&bdi->bdi_stat[i], 0); if (err) diff --git a/mm/bootmem.c b/mm/bootmem.c index 58c66cc5056..142c84a5499 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/highmem.c b/mm/highmem.c index 66baa20f78f..7a0aa1be499 100644 --- a/mm/highmem.c +++ b/mm/highmem.c @@ -26,6 +26,7 @@ #include <linux/init.h> #include <linux/hash.h> #include <linux/highmem.h> +#include <linux/kgdb.h> #include <asm/tlbflush.h> /* @@ -470,6 +471,12 @@ void debug_kmap_atomic(enum km_type type) warn_count--; } } +#ifdef CONFIG_KGDB_KDB + if (unlikely(type == KM_KDB && atomic_read(&kgdb_active) == -1)) { + WARN_ON(1); + warn_count--; + } +#endif /* CONFIG_KGDB_KDB */ } #endif diff --git a/mm/memblock.c b/mm/memblock.c new file mode 100644 index 00000000000..3024eb30fc2 --- /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-failure.c b/mm/memory-failure.c index 620b0b46159..6b44e52caca 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -45,6 +45,7 @@ #include <linux/page-isolation.h> #include <linux/suspend.h> #include <linux/slab.h> +#include <linux/swapops.h> #include "internal.h" int sysctl_memory_failure_early_kill __read_mostly = 0; @@ -1296,3 +1297,35 @@ done: /* keep elevated page count for bad page */ return ret; } + +/* + * The caller must hold current->mm->mmap_sem in read mode. + */ +int is_hwpoison_address(unsigned long addr) +{ + pgd_t *pgdp; + pud_t pud, *pudp; + pmd_t pmd, *pmdp; + pte_t pte, *ptep; + swp_entry_t entry; + + pgdp = pgd_offset(current->mm, addr); + if (!pgd_present(*pgdp)) + return 0; + pudp = pud_offset(pgdp, addr); + pud = *pudp; + if (!pud_present(pud) || pud_large(pud)) + return 0; + pmdp = pmd_offset(pudp, addr); + pmd = *pmdp; + if (!pmd_present(pmd) || pmd_large(pmd)) + return 0; + ptep = pte_offset_map(pmdp, addr); + pte = *ptep; + pte_unmap(ptep); + if (!is_swap_pte(pte)) + return 0; + entry = pte_to_swp_entry(pte); + return is_hwpoison_entry(entry); +} +EXPORT_SYMBOL_GPL(is_hwpoison_address); diff --git a/mm/memory.c b/mm/memory.c index 119b7ccdf39..bde42c6d363 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-writeback.c b/mm/page-writeback.c index 54f28bd493d..37498ef6154 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -495,7 +495,6 @@ static void balance_dirty_pages(struct address_space *mapping, for (;;) { struct writeback_control wbc = { - .bdi = bdi, .sync_mode = WB_SYNC_NONE, .older_than_this = NULL, .nr_to_write = write_chunk, @@ -537,7 +536,7 @@ static void balance_dirty_pages(struct address_space *mapping, * up. */ if (bdi_nr_reclaimable > bdi_thresh) { - writeback_inodes_wbc(&wbc); + writeback_inodes_wb(&bdi->wb, &wbc); pages_written += write_chunk - wbc.nr_to_write; get_dirty_limits(&background_thresh, &dirty_thresh, &bdi_thresh, bdi); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 431214b941a..9bd339eb04c 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 6c0081441a3..5bffada7cde 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/percpu.c b/mm/percpu.c index 6470e771023..e61dc2cc587 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -282,6 +282,9 @@ static void __maybe_unused pcpu_next_pop(struct pcpu_chunk *chunk, */ static void *pcpu_mem_alloc(size_t size) { + if (WARN_ON_ONCE(!slab_is_available())) + return NULL; + if (size <= PAGE_SIZE) return kzalloc(size, GFP_KERNEL); else { @@ -392,13 +395,6 @@ static int pcpu_extend_area_map(struct pcpu_chunk *chunk, int new_alloc) old_size = chunk->map_alloc * sizeof(chunk->map[0]); memcpy(new, chunk->map, old_size); - /* - * map_alloc < PCPU_DFL_MAP_ALLOC indicates that the chunk is - * one of the first chunks and still using static map. - */ - if (chunk->map_alloc >= PCPU_DFL_MAP_ALLOC) - old = chunk->map; - chunk->map_alloc = new_alloc; chunk->map = new; new = NULL; @@ -604,7 +600,7 @@ static struct pcpu_chunk *pcpu_alloc_chunk(void) { struct pcpu_chunk *chunk; - chunk = kzalloc(pcpu_chunk_struct_size, GFP_KERNEL); + chunk = pcpu_mem_alloc(pcpu_chunk_struct_size); if (!chunk) return NULL; @@ -1013,20 +1009,6 @@ phys_addr_t per_cpu_ptr_to_phys(void *addr) return page_to_phys(pcpu_addr_to_page(addr)); } -static inline size_t pcpu_calc_fc_sizes(size_t static_size, - size_t reserved_size, - ssize_t *dyn_sizep) -{ - size_t size_sum; - - size_sum = PFN_ALIGN(static_size + reserved_size + - (*dyn_sizep >= 0 ? *dyn_sizep : 0)); - if (*dyn_sizep != 0) - *dyn_sizep = size_sum - static_size - reserved_size; - - return size_sum; -} - /** * pcpu_alloc_alloc_info - allocate percpu allocation info * @nr_groups: the number of groups @@ -1085,7 +1067,7 @@ void __init pcpu_free_alloc_info(struct pcpu_alloc_info *ai) /** * pcpu_build_alloc_info - build alloc_info considering distances between CPUs * @reserved_size: the size of reserved percpu area in bytes - * @dyn_size: free size for dynamic allocation in bytes, -1 for auto + * @dyn_size: minimum free size for dynamic allocation in bytes * @atom_size: allocation atom size * @cpu_distance_fn: callback to determine distance between cpus, optional * @@ -1103,8 +1085,8 @@ void __init pcpu_free_alloc_info(struct pcpu_alloc_info *ai) * On success, pointer to the new allocation_info is returned. On * failure, ERR_PTR value is returned. */ -struct pcpu_alloc_info * __init pcpu_build_alloc_info( - size_t reserved_size, ssize_t dyn_size, +static struct pcpu_alloc_info * __init pcpu_build_alloc_info( + size_t reserved_size, size_t dyn_size, size_t atom_size, pcpu_fc_cpu_distance_fn_t cpu_distance_fn) { @@ -1123,13 +1105,17 @@ struct pcpu_alloc_info * __init pcpu_build_alloc_info( memset(group_map, 0, sizeof(group_map)); memset(group_cnt, 0, sizeof(group_cnt)); + /* calculate size_sum and ensure dyn_size is enough for early alloc */ + size_sum = PFN_ALIGN(static_size + reserved_size + + max_t(size_t, dyn_size, PERCPU_DYNAMIC_EARLY_SIZE)); + dyn_size = size_sum - static_size - reserved_size; + /* * Determine min_unit_size, alloc_size and max_upa such that * alloc_size is multiple of atom_size and is the smallest * which can accomodate 4k aligned segments which are equal to * or larger than min_unit_size. */ - size_sum = pcpu_calc_fc_sizes(static_size, reserved_size, &dyn_size); min_unit_size = max_t(size_t, size_sum, PCPU_MIN_UNIT_SIZE); alloc_size = roundup(min_unit_size, atom_size); @@ -1350,7 +1336,8 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai, void *base_addr) { static char cpus_buf[4096] __initdata; - static int smap[2], dmap[2]; + static int smap[PERCPU_DYNAMIC_EARLY_SLOTS] __initdata; + static int dmap[PERCPU_DYNAMIC_EARLY_SLOTS] __initdata; size_t dyn_size = ai->dyn_size; size_t size_sum = ai->static_size + ai->reserved_size + dyn_size; struct pcpu_chunk *schunk, *dchunk = NULL; @@ -1373,14 +1360,13 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai, } while (0) /* sanity checks */ - BUILD_BUG_ON(ARRAY_SIZE(smap) >= PCPU_DFL_MAP_ALLOC || - ARRAY_SIZE(dmap) >= PCPU_DFL_MAP_ALLOC); PCPU_SETUP_BUG_ON(ai->nr_groups <= 0); PCPU_SETUP_BUG_ON(!ai->static_size); PCPU_SETUP_BUG_ON(!base_addr); 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(ai->dyn_size < PERCPU_DYNAMIC_EARLY_SIZE); PCPU_SETUP_BUG_ON(pcpu_verify_alloc_info(ai) < 0); /* process group information and build config tables accordingly */ @@ -1532,7 +1518,7 @@ early_param("percpu_alloc", percpu_alloc_setup); /** * pcpu_embed_first_chunk - embed the first percpu chunk into bootmem * @reserved_size: the size of reserved percpu area in bytes - * @dyn_size: free size for dynamic allocation in bytes, -1 for auto + * @dyn_size: minimum free size for dynamic allocation in bytes * @atom_size: allocation atom size * @cpu_distance_fn: callback to determine distance between cpus, optional * @alloc_fn: function to allocate percpu page @@ -1553,10 +1539,7 @@ early_param("percpu_alloc", percpu_alloc_setup); * vmalloc space is not orders of magnitude larger than distances * between node memory addresses (ie. 32bit NUMA machines). * - * When @dyn_size is positive, dynamic area might be larger than - * specified to fill page alignment. When @dyn_size is auto, - * @dyn_size is just big enough to fill page alignment after static - * and reserved areas. + * @dyn_size specifies the minimum dynamic area size. * * If the needed size is smaller than the minimum or specified unit * size, the leftover is returned using @free_fn. @@ -1564,7 +1547,7 @@ early_param("percpu_alloc", percpu_alloc_setup); * RETURNS: * 0 on success, -errno on failure. */ -int __init pcpu_embed_first_chunk(size_t reserved_size, ssize_t dyn_size, +int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size, size_t atom_size, pcpu_fc_cpu_distance_fn_t cpu_distance_fn, pcpu_fc_alloc_fn_t alloc_fn, @@ -1695,7 +1678,7 @@ int __init pcpu_page_first_chunk(size_t reserved_size, snprintf(psize_str, sizeof(psize_str), "%luK", PAGE_SIZE >> 10); - ai = pcpu_build_alloc_info(reserved_size, -1, PAGE_SIZE, NULL); + ai = pcpu_build_alloc_info(reserved_size, 0, PAGE_SIZE, NULL); if (IS_ERR(ai)) return PTR_ERR(ai); BUG_ON(ai->nr_groups != 1); @@ -1821,3 +1804,33 @@ void __init setup_per_cpu_areas(void) __per_cpu_offset[cpu] = delta + pcpu_unit_offsets[cpu]; } #endif /* CONFIG_HAVE_SETUP_PER_CPU_AREA */ + +/* + * First and reserved chunks are initialized with temporary allocation + * map in initdata so that they can be used before slab is online. + * This function is called after slab is brought up and replaces those + * with properly allocated maps. + */ +void __init percpu_init_late(void) +{ + struct pcpu_chunk *target_chunks[] = + { pcpu_first_chunk, pcpu_reserved_chunk, NULL }; + struct pcpu_chunk *chunk; + unsigned long flags; + int i; + + for (i = 0; (chunk = target_chunks[i]); i++) { + int *map; + const size_t size = PERCPU_DYNAMIC_EARLY_SLOTS * sizeof(map[0]); + + BUILD_BUG_ON(size > PAGE_SIZE); + + map = pcpu_mem_alloc(size); + BUG_ON(!map); + + spin_lock_irqsave(&pcpu_lock, flags); + memcpy(map, chunk->map, size); + chunk->map = map; + spin_unlock_irqrestore(&pcpu_lock, flags); + } +} diff --git a/mm/vmscan.c b/mm/vmscan.c index 9c7e57cc63a..b94fe1b3da4 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); |