From 8e7a7f8619f1f93736d9bb7e31caf4721bdc739d Mon Sep 17 00:00:00 2001 From: Robin Holt Date: Tue, 30 Jun 2015 14:56:41 -0700 Subject: memblock: introduce a for_each_reserved_mem_region iterator Struct page initialisation had been identified as one of the reasons why large machines take a long time to boot. Patches were posted a long time ago to defer initialisation until they were first used. This was rejected on the grounds it should not be necessary to hurt the fast paths. This series reuses much of the work from that time but defers the initialisation of memory to kswapd so that one thread per node initialises memory local to that node. After applying the series and setting the appropriate Kconfig variable I see this in the boot log on a 64G machine [ 7.383764] kswapd 0 initialised deferred memory in 188ms [ 7.404253] kswapd 1 initialised deferred memory in 208ms [ 7.411044] kswapd 3 initialised deferred memory in 216ms [ 7.411551] kswapd 2 initialised deferred memory in 216ms On a 1TB machine, I see [ 8.406511] kswapd 3 initialised deferred memory in 1116ms [ 8.428518] kswapd 1 initialised deferred memory in 1140ms [ 8.435977] kswapd 0 initialised deferred memory in 1148ms [ 8.437416] kswapd 2 initialised deferred memory in 1148ms Once booted the machine appears to work as normal. Boot times were measured from the time shutdown was called until ssh was available again. In the 64G case, the boot time savings are negligible. On the 1TB machine, the savings were 16 seconds. Nate Zimmer said: : On an older 8 TB box with lots and lots of cpus the boot time, as : measure from grub to login prompt, the boot time improved from 1484 : seconds to exactly 1000 seconds. Waiman Long said: : I ran a bootup timing test on a 12-TB 16-socket IvyBridge-EX system. From : grub menu to ssh login, the bootup time was 453s before the patch and 265s : after the patch - a saving of 188s (42%). Daniel Blueman said: : On a 7TB, 1728-core NumaConnect system with 108 NUMA nodes, we're seeing : stock 4.0 boot in 7136s. This drops to 2159s, or a 70% reduction with : this patchset. Non-temporal PMD init (https://lkml.org/lkml/2015/4/23/350) : drops this to 1045s. This patch (of 13): As part of initializing struct page's in 2MiB chunks, we noticed that at the end of free_all_bootmem(), there was nothing which had forced the reserved/allocated 4KiB pages to be initialized. This helper function will be used for that expansion. Signed-off-by: Robin Holt Signed-off-by: Nate Zimmer Signed-off-by: Mel Gorman Tested-by: Nate Zimmer Tested-by: Waiman Long Tested-by: Daniel J Blueman Acked-by: Pekka Enberg Cc: Robin Holt Cc: Dave Hansen Cc: Waiman Long Cc: Scott Norton Cc: "Luck, Tony" Cc: Ingo Molnar Cc: "H. Peter Anvin" Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memblock.h | 18 ++++++++++++++++++ mm/memblock.c | 32 ++++++++++++++++++++++++++++++++ 2 files changed, 50 insertions(+) diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 0215ffd63069..cc4b01972060 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -101,6 +101,9 @@ void __next_mem_range_rev(u64 *idx, int nid, ulong flags, struct memblock_type *type_b, phys_addr_t *out_start, phys_addr_t *out_end, int *out_nid); +void __next_reserved_mem_region(u64 *idx, phys_addr_t *out_start, + phys_addr_t *out_end); + /** * for_each_mem_range - iterate through memblock areas from type_a and not * included in type_b. Or just type_a if type_b is NULL. @@ -142,6 +145,21 @@ void __next_mem_range_rev(u64 *idx, int nid, ulong flags, __next_mem_range_rev(&i, nid, flags, type_a, type_b, \ p_start, p_end, p_nid)) +/** + * for_each_reserved_mem_region - iterate over all reserved memblock areas + * @i: u64 used as loop variable + * @p_start: ptr to phys_addr_t for start address of the range, can be %NULL + * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL + * + * Walks over reserved areas of memblock. Available as soon as memblock + * is initialized. + */ +#define for_each_reserved_mem_region(i, p_start, p_end) \ + for (i = 0UL, \ + __next_reserved_mem_region(&i, p_start, p_end); \ + i != (u64)ULLONG_MAX; \ + __next_reserved_mem_region(&i, p_start, p_end)) + #ifdef CONFIG_MOVABLE_NODE static inline bool memblock_is_hotpluggable(struct memblock_region *m) { diff --git a/mm/memblock.c b/mm/memblock.c index 1b444c730846..114df622853f 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -819,6 +819,38 @@ int __init_memblock memblock_mark_mirror(phys_addr_t base, phys_addr_t size) } +/** + * __next_reserved_mem_region - next function for for_each_reserved_region() + * @idx: pointer to u64 loop variable + * @out_start: ptr to phys_addr_t for start address of the region, can be %NULL + * @out_end: ptr to phys_addr_t for end address of the region, can be %NULL + * + * Iterate over all reserved memory regions. + */ +void __init_memblock __next_reserved_mem_region(u64 *idx, + phys_addr_t *out_start, + phys_addr_t *out_end) +{ + struct memblock_type *rsv = &memblock.reserved; + + if (*idx >= 0 && *idx < rsv->cnt) { + struct memblock_region *r = &rsv->regions[*idx]; + phys_addr_t base = r->base; + phys_addr_t size = r->size; + + if (out_start) + *out_start = base; + if (out_end) + *out_end = base + size - 1; + + *idx += 1; + return; + } + + /* signal end of iteration */ + *idx = ULLONG_MAX; +} + /** * __next__mem_range - next function for for_each_free_mem_range() etc. * @idx: pointer to u64 loop variable -- cgit v1.2.3 From 1e8ce83cd17fd0f549a7ad145ddd2bfcdd7dfe37 Mon Sep 17 00:00:00 2001 From: Robin Holt Date: Tue, 30 Jun 2015 14:56:45 -0700 Subject: mm: meminit: move page initialization into a separate function Currently, memmap_init_zone() has all the smarts for initializing a single page. A subset of this is required for parallel page initialisation and so this patch breaks up the monolithic function in preparation. Signed-off-by: Robin Holt Signed-off-by: Nathan Zimmer Signed-off-by: Mel Gorman Tested-by: Nate Zimmer Tested-by: Waiman Long Tested-by: Daniel J Blueman Acked-by: Pekka Enberg Cc: Robin Holt Cc: Dave Hansen Cc: Waiman Long Cc: Scott Norton Cc: "Luck, Tony" Cc: Ingo Molnar Cc: "H. Peter Anvin" Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 79 +++++++++++++++++++++++++++++++++------------------------ 1 file changed, 46 insertions(+), 33 deletions(-) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 5e6fa06f2784..bc5da2cdfc84 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -764,6 +764,51 @@ static int free_tail_pages_check(struct page *head_page, struct page *page) return 0; } +static void __meminit __init_single_page(struct page *page, unsigned long pfn, + unsigned long zone, int nid) +{ + struct zone *z = &NODE_DATA(nid)->node_zones[zone]; + + set_page_links(page, zone, nid, pfn); + mminit_verify_page_links(page, zone, nid, pfn); + init_page_count(page); + page_mapcount_reset(page); + page_cpupid_reset_last(page); + SetPageReserved(page); + + /* + * Mark the block movable so that blocks are reserved for + * movable at startup. This will force kernel allocations + * to reserve their blocks rather than leaking throughout + * the address space during boot when many long-lived + * kernel allocations are made. Later some blocks near + * the start are marked MIGRATE_RESERVE by + * setup_zone_migrate_reserve() + * + * bitmap is created for zone's valid pfn range. but memmap + * can be created for invalid pages (for alignment) + * check here not to call set_pageblock_migratetype() against + * pfn out of zone. + */ + if ((z->zone_start_pfn <= pfn) + && (pfn < zone_end_pfn(z)) + && !(pfn & (pageblock_nr_pages - 1))) + set_pageblock_migratetype(page, MIGRATE_MOVABLE); + + INIT_LIST_HEAD(&page->lru); +#ifdef WANT_PAGE_VIRTUAL + /* The shift won't overflow because ZONE_NORMAL is below 4G. */ + if (!is_highmem_idx(zone)) + set_page_address(page, __va(pfn << PAGE_SHIFT)); +#endif +} + +static void __meminit __init_single_pfn(unsigned long pfn, unsigned long zone, + int nid) +{ + return __init_single_page(pfn_to_page(pfn), pfn, zone, nid); +} + static bool free_pages_prepare(struct page *page, unsigned int order) { bool compound = PageCompound(page); @@ -4212,7 +4257,6 @@ static void setup_zone_migrate_reserve(struct zone *zone) void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, unsigned long start_pfn, enum memmap_context context) { - struct page *page; unsigned long end_pfn = start_pfn + size; unsigned long pfn; struct zone *z; @@ -4233,38 +4277,7 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, if (!early_pfn_in_nid(pfn, nid)) continue; } - page = pfn_to_page(pfn); - set_page_links(page, zone, nid, pfn); - mminit_verify_page_links(page, zone, nid, pfn); - init_page_count(page); - page_mapcount_reset(page); - page_cpupid_reset_last(page); - SetPageReserved(page); - /* - * Mark the block movable so that blocks are reserved for - * movable at startup. This will force kernel allocations - * to reserve their blocks rather than leaking throughout - * the address space during boot when many long-lived - * kernel allocations are made. Later some blocks near - * the start are marked MIGRATE_RESERVE by - * setup_zone_migrate_reserve() - * - * bitmap is created for zone's valid pfn range. but memmap - * can be created for invalid pages (for alignment) - * check here not to call set_pageblock_migratetype() against - * pfn out of zone. - */ - if ((z->zone_start_pfn <= pfn) - && (pfn < zone_end_pfn(z)) - && !(pfn & (pageblock_nr_pages - 1))) - set_pageblock_migratetype(page, MIGRATE_MOVABLE); - - INIT_LIST_HEAD(&page->lru); -#ifdef WANT_PAGE_VIRTUAL - /* The shift won't overflow because ZONE_NORMAL is below 4G. */ - if (!is_highmem_idx(zone)) - set_page_address(page, __va(pfn << PAGE_SHIFT)); -#endif + __init_single_pfn(pfn, zone, nid); } } -- cgit v1.2.3 From 92923ca3aacef63c92dc297a75ad0c6dfe4eab37 Mon Sep 17 00:00:00 2001 From: Nathan Zimmer Date: Tue, 30 Jun 2015 14:56:48 -0700 Subject: mm: meminit: only set page reserved in the memblock region Currently each page struct is set as reserved upon initialization. This patch leaves the reserved bit clear and only sets the reserved bit when it is known the memory was allocated by the bootmem allocator. This makes it easier to distinguish between uninitialised struct pages and reserved struct pages in later patches. Signed-off-by: Robin Holt Signed-off-by: Nathan Zimmer Signed-off-by: Mel Gorman Tested-by: Nate Zimmer Tested-by: Waiman Long Tested-by: Daniel J Blueman Acked-by: Pekka Enberg Cc: Robin Holt Cc: Dave Hansen Cc: Waiman Long Cc: Scott Norton Cc: "Luck, Tony" Cc: Ingo Molnar Cc: "H. Peter Anvin" Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 ++ mm/nobootmem.c | 3 +++ mm/page_alloc.c | 17 ++++++++++++++++- 3 files changed, 21 insertions(+), 1 deletion(-) diff --git a/include/linux/mm.h b/include/linux/mm.h index 99959a34f4f1..d662af2d0d01 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1635,6 +1635,8 @@ extern void free_highmem_page(struct page *page); extern void adjust_managed_page_count(struct page *page, long count); extern void mem_init_print_info(const char *str); +extern void reserve_bootmem_region(unsigned long start, unsigned long end); + /* Free the reserved page into the buddy system, so it gets managed. */ static inline void __free_reserved_page(struct page *page) { diff --git a/mm/nobootmem.c b/mm/nobootmem.c index 5258386fa1be..4af8f88c2bd1 100644 --- a/mm/nobootmem.c +++ b/mm/nobootmem.c @@ -130,6 +130,9 @@ static unsigned long __init free_low_memory_core_early(void) memblock_clear_hotplug(0, -1); + for_each_reserved_mem_region(i, &start, &end) + reserve_bootmem_region(start, end); + for_each_free_mem_range(i, NUMA_NO_NODE, MEMBLOCK_NONE, &start, &end, NULL) count += __free_memory_core(start, end); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index bc5da2cdfc84..39c8d56a4056 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -774,7 +774,6 @@ static void __meminit __init_single_page(struct page *page, unsigned long pfn, init_page_count(page); page_mapcount_reset(page); page_cpupid_reset_last(page); - SetPageReserved(page); /* * Mark the block movable so that blocks are reserved for @@ -809,6 +808,22 @@ static void __meminit __init_single_pfn(unsigned long pfn, unsigned long zone, return __init_single_page(pfn_to_page(pfn), pfn, zone, nid); } +/* + * Initialised pages do not have PageReserved set. This function is + * called for each range allocated by the bootmem allocator and + * marks the pages PageReserved. The remaining valid pages are later + * sent to the buddy page allocator. + */ +void reserve_bootmem_region(unsigned long start, unsigned long end) +{ + unsigned long start_pfn = PFN_DOWN(start); + unsigned long end_pfn = PFN_UP(end); + + for (; start_pfn < end_pfn; start_pfn++) + if (pfn_valid(start_pfn)) + SetPageReserved(pfn_to_page(start_pfn)); +} + static bool free_pages_prepare(struct page *page, unsigned int order) { bool compound = PageCompound(page); -- cgit v1.2.3 From d70ddd7a5d9aa335f9b4b0c3d879e1e70ee1e4e3 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Tue, 30 Jun 2015 14:56:52 -0700 Subject: mm: page_alloc: pass PFN to __free_pages_bootmem __free_pages_bootmem prepares a page for release to the buddy allocator and assumes that the struct page is initialised. Parallel initialisation of struct pages defers initialisation and __free_pages_bootmem can be called for struct pages that cannot yet map struct page to PFN. This patch passes PFN to __free_pages_bootmem with no other functional change. Signed-off-by: Mel Gorman Tested-by: Nate Zimmer Tested-by: Waiman Long Tested-by: Daniel J Blueman Acked-by: Pekka Enberg Cc: Robin Holt Cc: Nate Zimmer Cc: Dave Hansen Cc: Waiman Long Cc: Scott Norton Cc: "Luck, Tony" Cc: Ingo Molnar Cc: "H. Peter Anvin" Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/bootmem.c | 13 +++++++------ mm/internal.h | 3 ++- mm/memblock.c | 2 +- mm/nobootmem.c | 4 ++-- mm/page_alloc.c | 3 ++- 5 files changed, 14 insertions(+), 11 deletions(-) diff --git a/mm/bootmem.c b/mm/bootmem.c index 477be696511d..a23dd1934654 100644 --- a/mm/bootmem.c +++ b/mm/bootmem.c @@ -164,7 +164,7 @@ void __init free_bootmem_late(unsigned long physaddr, unsigned long size) end = PFN_DOWN(physaddr + size); for (; cursor < end; cursor++) { - __free_pages_bootmem(pfn_to_page(cursor), 0); + __free_pages_bootmem(pfn_to_page(cursor), cursor, 0); totalram_pages++; } } @@ -172,7 +172,7 @@ void __init free_bootmem_late(unsigned long physaddr, unsigned long size) static unsigned long __init free_all_bootmem_core(bootmem_data_t *bdata) { struct page *page; - unsigned long *map, start, end, pages, count = 0; + unsigned long *map, start, end, pages, cur, count = 0; if (!bdata->node_bootmem_map) return 0; @@ -210,17 +210,17 @@ static unsigned long __init free_all_bootmem_core(bootmem_data_t *bdata) if (IS_ALIGNED(start, BITS_PER_LONG) && vec == ~0UL) { int order = ilog2(BITS_PER_LONG); - __free_pages_bootmem(pfn_to_page(start), order); + __free_pages_bootmem(pfn_to_page(start), start, order); count += BITS_PER_LONG; start += BITS_PER_LONG; } else { - unsigned long cur = start; + cur = start; start = ALIGN(start + 1, BITS_PER_LONG); while (vec && cur != start) { if (vec & 1) { page = pfn_to_page(cur); - __free_pages_bootmem(page, 0); + __free_pages_bootmem(page, cur, 0); count++; } vec >>= 1; @@ -229,12 +229,13 @@ static unsigned long __init free_all_bootmem_core(bootmem_data_t *bdata) } } + cur = bdata->node_min_pfn; page = virt_to_page(bdata->node_bootmem_map); pages = bdata->node_low_pfn - bdata->node_min_pfn; pages = bootmem_bootmap_pages(pages); count += pages; while (pages--) - __free_pages_bootmem(page++, 0); + __free_pages_bootmem(page++, cur++, 0); bdebug("nid=%td released=%lx\n", bdata - bootmem_node_data, count); diff --git a/mm/internal.h b/mm/internal.h index a25e359a4039..58e9022e3757 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -155,7 +155,8 @@ __find_buddy_index(unsigned long page_idx, unsigned int order) } extern int __isolate_free_page(struct page *page, unsigned int order); -extern void __free_pages_bootmem(struct page *page, unsigned int order); +extern void __free_pages_bootmem(struct page *page, unsigned long pfn, + unsigned int order); extern void prep_compound_page(struct page *page, unsigned long order); #ifdef CONFIG_MEMORY_FAILURE extern bool is_free_buddy_page(struct page *page); diff --git a/mm/memblock.c b/mm/memblock.c index 114df622853f..87108e77e476 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -1419,7 +1419,7 @@ void __init __memblock_free_late(phys_addr_t base, phys_addr_t size) end = PFN_DOWN(base + size); for (; cursor < end; cursor++) { - __free_pages_bootmem(pfn_to_page(cursor), 0); + __free_pages_bootmem(pfn_to_page(cursor), cursor, 0); totalram_pages++; } } diff --git a/mm/nobootmem.c b/mm/nobootmem.c index 4af8f88c2bd1..e57cf24babd6 100644 --- a/mm/nobootmem.c +++ b/mm/nobootmem.c @@ -86,7 +86,7 @@ void __init free_bootmem_late(unsigned long addr, unsigned long size) end = PFN_DOWN(addr + size); for (; cursor < end; cursor++) { - __free_pages_bootmem(pfn_to_page(cursor), 0); + __free_pages_bootmem(pfn_to_page(cursor), cursor, 0); totalram_pages++; } } @@ -101,7 +101,7 @@ static void __init __free_pages_memory(unsigned long start, unsigned long end) while (start + (1UL << order) > end) order--; - __free_pages_bootmem(pfn_to_page(start), order); + __free_pages_bootmem(pfn_to_page(start), start, order); start += (1UL << order); } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 39c8d56a4056..c2ee4ecad083 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -878,7 +878,8 @@ static void __free_pages_ok(struct page *page, unsigned int order) local_irq_restore(flags); } -void __init __free_pages_bootmem(struct page *page, unsigned int order) +void __init __free_pages_bootmem(struct page *page, unsigned long pfn, + unsigned int order) { unsigned int nr_pages = 1 << order; struct page *p = page; -- cgit v1.2.3 From 8a942fdea560d4ac0e9d9fabcd5201ad20e0c382 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Tue, 30 Jun 2015 14:56:55 -0700 Subject: mm: meminit: make __early_pfn_to_nid SMP-safe and introduce meminit_pfn_in_nid __early_pfn_to_nid() use static variables to cache recent lookups as memblock lookups are very expensive but it assumes that memory initialisation is single-threaded. Parallel initialisation of struct pages will break that assumption so this patch makes __early_pfn_to_nid() SMP-safe by requiring the caller to cache recent search information. early_pfn_to_nid() keeps the same interface but is only safe to use early in boot due to the use of a global static variable. meminit_pfn_in_nid() is an SMP-safe version that callers must maintain their own state for. Signed-off-by: Mel Gorman Tested-by: Nate Zimmer Tested-by: Waiman Long Tested-by: Daniel J Blueman Acked-by: Pekka Enberg Cc: Robin Holt Cc: Nate Zimmer Cc: Dave Hansen Cc: Waiman Long Cc: Scott Norton Cc: "Luck, Tony" Cc: Ingo Molnar Cc: "H. Peter Anvin" Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/ia64/mm/numa.c | 19 +++++++------------ include/linux/mm.h | 6 ++++-- include/linux/mmzone.h | 16 +++++++++++++++- mm/page_alloc.c | 40 +++++++++++++++++++++++++--------------- 4 files changed, 51 insertions(+), 30 deletions(-) diff --git a/arch/ia64/mm/numa.c b/arch/ia64/mm/numa.c index ea21d4cad540..aa19b7ac8222 100644 --- a/arch/ia64/mm/numa.c +++ b/arch/ia64/mm/numa.c @@ -58,27 +58,22 @@ paddr_to_nid(unsigned long paddr) * SPARSEMEM to allocate the SPARSEMEM sectionmap on the NUMA node where * the section resides. */ -int __meminit __early_pfn_to_nid(unsigned long pfn) +int __meminit __early_pfn_to_nid(unsigned long pfn, + struct mminit_pfnnid_cache *state) { int i, section = pfn >> PFN_SECTION_SHIFT, ssec, esec; - /* - * NOTE: The following SMP-unsafe globals are only used early in boot - * when the kernel is running single-threaded. - */ - static int __meminitdata last_ssec, last_esec; - static int __meminitdata last_nid; - if (section >= last_ssec && section < last_esec) - return last_nid; + if (section >= state->last_start && section < state->last_end) + return state->last_nid; for (i = 0; i < num_node_memblks; i++) { ssec = node_memblk[i].start_paddr >> PA_SECTION_SHIFT; esec = (node_memblk[i].start_paddr + node_memblk[i].size + ((1L << PA_SECTION_SHIFT) - 1)) >> PA_SECTION_SHIFT; if (section >= ssec && section < esec) { - last_ssec = ssec; - last_esec = esec; - last_nid = node_memblk[i].nid; + state->last_start = ssec; + state->last_end = esec; + state->last_nid = node_memblk[i].nid; return node_memblk[i].nid; } } diff --git a/include/linux/mm.h b/include/linux/mm.h index d662af2d0d01..2e872f92dbac 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1726,7 +1726,8 @@ extern void sparse_memory_present_with_active_regions(int nid); #if !defined(CONFIG_HAVE_MEMBLOCK_NODE_MAP) && \ !defined(CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID) -static inline int __early_pfn_to_nid(unsigned long pfn) +static inline int __early_pfn_to_nid(unsigned long pfn, + struct mminit_pfnnid_cache *state) { return 0; } @@ -1734,7 +1735,8 @@ static inline int __early_pfn_to_nid(unsigned long pfn) /* please see mm/page_alloc.c */ extern int __meminit early_pfn_to_nid(unsigned long pfn); /* there is a per-arch backend function. */ -extern int __meminit __early_pfn_to_nid(unsigned long pfn); +extern int __meminit __early_pfn_to_nid(unsigned long pfn, + struct mminit_pfnnid_cache *state); #endif extern void set_dma_reserve(unsigned long new_dma_reserve); diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 54d74f6eb233..b2473d822549 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -1216,10 +1216,24 @@ void sparse_init(void); #define sparse_index_init(_sec, _nid) do {} while (0) #endif /* CONFIG_SPARSEMEM */ +/* + * During memory init memblocks map pfns to nids. The search is expensive and + * this caches recent lookups. The implementation of __early_pfn_to_nid + * may treat start/end as pfns or sections. + */ +struct mminit_pfnnid_cache { + unsigned long last_start; + unsigned long last_end; + int last_nid; +}; + #ifdef CONFIG_NODES_SPAN_OTHER_NODES bool early_pfn_in_nid(unsigned long pfn, int nid); +bool meminit_pfn_in_nid(unsigned long pfn, int node, + struct mminit_pfnnid_cache *state); #else -#define early_pfn_in_nid(pfn, nid) (1) +#define early_pfn_in_nid(pfn, nid) (1) +#define meminit_pfn_in_nid(pfn, nid, state) (1) #endif #ifndef early_pfn_valid diff --git a/mm/page_alloc.c b/mm/page_alloc.c index c2ee4ecad083..ffdb2308848d 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -4551,39 +4551,41 @@ int __meminit init_currently_empty_zone(struct zone *zone, #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP #ifndef CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID + /* * Required by SPARSEMEM. Given a PFN, return what node the PFN is on. */ -int __meminit __early_pfn_to_nid(unsigned long pfn) +int __meminit __early_pfn_to_nid(unsigned long pfn, + struct mminit_pfnnid_cache *state) { unsigned long start_pfn, end_pfn; int nid; - /* - * NOTE: The following SMP-unsafe globals are only used early in boot - * when the kernel is running single-threaded. - */ - static unsigned long __meminitdata last_start_pfn, last_end_pfn; - static int __meminitdata last_nid; - if (last_start_pfn <= pfn && pfn < last_end_pfn) - return last_nid; + if (state->last_start <= pfn && pfn < state->last_end) + return state->last_nid; nid = memblock_search_pfn_nid(pfn, &start_pfn, &end_pfn); if (nid != -1) { - last_start_pfn = start_pfn; - last_end_pfn = end_pfn; - last_nid = nid; + state->last_start = start_pfn; + state->last_end = end_pfn; + state->last_nid = nid; } return nid; } #endif /* CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID */ +static struct mminit_pfnnid_cache early_pfnnid_cache __meminitdata; + +/* Only safe to use early in boot when initialisation is single-threaded */ int __meminit early_pfn_to_nid(unsigned long pfn) { int nid; - nid = __early_pfn_to_nid(pfn); + /* The system will behave unpredictably otherwise */ + BUG_ON(system_state != SYSTEM_BOOTING); + + nid = __early_pfn_to_nid(pfn, &early_pfnnid_cache); if (nid >= 0) return nid; /* just returns 0 */ @@ -4591,15 +4593,23 @@ int __meminit early_pfn_to_nid(unsigned long pfn) } #ifdef CONFIG_NODES_SPAN_OTHER_NODES -bool __meminit early_pfn_in_nid(unsigned long pfn, int node) +bool __meminit meminit_pfn_in_nid(unsigned long pfn, int node, + struct mminit_pfnnid_cache *state) { int nid; - nid = __early_pfn_to_nid(pfn); + nid = __early_pfn_to_nid(pfn, state); if (nid >= 0 && nid != node) return false; return true; } + +/* Only safe to use early in boot when initialisation is single-threaded */ +bool __meminit early_pfn_in_nid(unsigned long pfn, int node) +{ + return meminit_pfn_in_nid(pfn, node, &early_pfnnid_cache); +} + #endif /** -- cgit v1.2.3 From 75a592a47129dcfc1aec40e7d3cdf239a767d441 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Tue, 30 Jun 2015 14:56:59 -0700 Subject: mm: meminit: inline some helper functions early_pfn_in_nid() and meminit_pfn_in_nid() are small functions that are unnecessarily visible outside memory initialisation. As well as unnecessary visibility, it's unnecessary function call overhead when initialising pages. This patch moves the helpers inline. [akpm@linux-foundation.org: fix build] [mhocko@suse.cz: fix build] Signed-off-by: Mel Gorman Tested-by: Nate Zimmer Tested-by: Waiman Long Tested-by: Daniel J Blueman Acked-by: Pekka Enberg Cc: Robin Holt Cc: Nate Zimmer Cc: Dave Hansen Cc: Waiman Long Cc: Scott Norton Cc: "Luck, Tony" Cc: Ingo Molnar Cc: "H. Peter Anvin" Cc: Thomas Gleixner Signed-off-by: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 9 ----- mm/page_alloc.c | 89 +++++++++++++++++++++++++++++--------------------- 2 files changed, 52 insertions(+), 46 deletions(-) diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index b2473d822549..1e05dc7449cd 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -1227,15 +1227,6 @@ struct mminit_pfnnid_cache { int last_nid; }; -#ifdef CONFIG_NODES_SPAN_OTHER_NODES -bool early_pfn_in_nid(unsigned long pfn, int nid); -bool meminit_pfn_in_nid(unsigned long pfn, int node, - struct mminit_pfnnid_cache *state); -#else -#define early_pfn_in_nid(pfn, nid) (1) -#define meminit_pfn_in_nid(pfn, nid, state) (1) -#endif - #ifndef early_pfn_valid #define early_pfn_valid(pfn) (1) #endif diff --git a/mm/page_alloc.c b/mm/page_alloc.c index ffdb2308848d..12a81870815f 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -899,6 +899,58 @@ void __init __free_pages_bootmem(struct page *page, unsigned long pfn, __free_pages(page, order); } +#if defined(CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID) || \ + defined(CONFIG_HAVE_MEMBLOCK_NODE_MAP) +/* Only safe to use early in boot when initialisation is single-threaded */ +static struct mminit_pfnnid_cache early_pfnnid_cache __meminitdata; + +int __meminit early_pfn_to_nid(unsigned long pfn) +{ + int nid; + + /* The system will behave unpredictably otherwise */ + BUG_ON(system_state != SYSTEM_BOOTING); + + nid = __early_pfn_to_nid(pfn, &early_pfnnid_cache); + if (nid >= 0) + return nid; + /* just returns 0 */ + return 0; +} +#endif + +#ifdef CONFIG_NODES_SPAN_OTHER_NODES +static inline bool __meminit meminit_pfn_in_nid(unsigned long pfn, int node, + struct mminit_pfnnid_cache *state) +{ + int nid; + + nid = __early_pfn_to_nid(pfn, state); + if (nid >= 0 && nid != node) + return false; + return true; +} + +/* Only safe to use early in boot when initialisation is single-threaded */ +static inline bool __meminit early_pfn_in_nid(unsigned long pfn, int node) +{ + return meminit_pfn_in_nid(pfn, node, &early_pfnnid_cache); +} + +#else + +static inline bool __meminit early_pfn_in_nid(unsigned long pfn, int node) +{ + return true; +} +static inline bool __meminit meminit_pfn_in_nid(unsigned long pfn, int node, + struct mminit_pfnnid_cache *state) +{ + return true; +} +#endif + + #ifdef CONFIG_CMA /* Free whole pageblock and set its migration type to MIGRATE_CMA. */ void __init init_cma_reserved_pageblock(struct page *page) @@ -4575,43 +4627,6 @@ int __meminit __early_pfn_to_nid(unsigned long pfn, } #endif /* CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID */ -static struct mminit_pfnnid_cache early_pfnnid_cache __meminitdata; - -/* Only safe to use early in boot when initialisation is single-threaded */ -int __meminit early_pfn_to_nid(unsigned long pfn) -{ - int nid; - - /* The system will behave unpredictably otherwise */ - BUG_ON(system_state != SYSTEM_BOOTING); - - nid = __early_pfn_to_nid(pfn, &early_pfnnid_cache); - if (nid >= 0) - return nid; - /* just returns 0 */ - return 0; -} - -#ifdef CONFIG_NODES_SPAN_OTHER_NODES -bool __meminit meminit_pfn_in_nid(unsigned long pfn, int node, - struct mminit_pfnnid_cache *state) -{ - int nid; - - nid = __early_pfn_to_nid(pfn, state); - if (nid >= 0 && nid != node) - return false; - return true; -} - -/* Only safe to use early in boot when initialisation is single-threaded */ -bool __meminit early_pfn_in_nid(unsigned long pfn, int node) -{ - return meminit_pfn_in_nid(pfn, node, &early_pfnnid_cache); -} - -#endif - /** * free_bootmem_with_active_regions - Call memblock_free_early_nid for each active range * @nid: The node to free memory on. If MAX_NUMNODES, all nodes are freed. -- cgit v1.2.3 From 3a80a7fa7989fbb6aa56bb6ad31811b62cf99e60 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Tue, 30 Jun 2015 14:57:02 -0700 Subject: mm: meminit: initialise a subset of struct pages if CONFIG_DEFERRED_STRUCT_PAGE_INIT is set This patch initalises all low memory struct pages and 2G of the highest zone on each node during memory initialisation if CONFIG_DEFERRED_STRUCT_PAGE_INIT is set. That config option cannot be set but will be available in a later patch. Parallel initialisation of struct page depends on some features from memory hotplug and it is necessary to alter alter section annotations. Signed-off-by: Mel Gorman Tested-by: Nate Zimmer Tested-by: Waiman Long Tested-by: Daniel J Blueman Acked-by: Pekka Enberg Cc: Robin Holt Cc: Nate Zimmer Cc: Dave Hansen Cc: Waiman Long Cc: Scott Norton Cc: "Luck, Tony" Cc: Ingo Molnar Cc: "H. Peter Anvin" Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/base/node.c | 6 +++- include/linux/mmzone.h | 8 ++++++ mm/Kconfig | 18 ++++++++++++ mm/internal.h | 18 ++++++++++++ mm/page_alloc.c | 78 ++++++++++++++++++++++++++++++++++++++++++++++++-- 5 files changed, 124 insertions(+), 4 deletions(-) diff --git a/drivers/base/node.c b/drivers/base/node.c index a2aa65b4215d..31df474d72f4 100644 --- a/drivers/base/node.c +++ b/drivers/base/node.c @@ -359,12 +359,16 @@ int unregister_cpu_under_node(unsigned int cpu, unsigned int nid) #ifdef CONFIG_MEMORY_HOTPLUG_SPARSE #define page_initialized(page) (page->lru.next) -static int get_nid_for_pfn(unsigned long pfn) +static int __init_refok get_nid_for_pfn(unsigned long pfn) { struct page *page; if (!pfn_valid_within(pfn)) return -1; +#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT + if (system_state == SYSTEM_BOOTING) + return early_pfn_to_nid(pfn); +#endif page = pfn_to_page(pfn); if (!page_initialized(page)) return -1; diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 1e05dc7449cd..754c25966a0a 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -762,6 +762,14 @@ typedef struct pglist_data { /* Number of pages migrated during the rate limiting time interval */ unsigned long numabalancing_migrate_nr_pages; #endif + +#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT + /* + * If memory initialisation on large machines is deferred then this + * is the first PFN that needs to be initialised. + */ + unsigned long first_deferred_pfn; +#endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */ } pg_data_t; #define node_present_pages(nid) (NODE_DATA(nid)->node_present_pages) diff --git a/mm/Kconfig b/mm/Kconfig index c180af880ed5..e79de2bd12cd 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -636,3 +636,21 @@ config MAX_STACK_SIZE_MB changed to a smaller value in which case that is used. A sane initial value is 80 MB. + +# For architectures that support deferred memory initialisation +config ARCH_SUPPORTS_DEFERRED_STRUCT_PAGE_INIT + bool + +config DEFERRED_STRUCT_PAGE_INIT + bool "Defer initialisation of struct pages to kswapd" + default n + depends on ARCH_SUPPORTS_DEFERRED_STRUCT_PAGE_INIT + depends on MEMORY_HOTPLUG + help + Ordinarily all struct pages are initialised during early boot in a + single thread. On very large machines this can take a considerable + amount of time. If this option is set, large machines will bring up + a subset of memmap at boot and then initialise the rest in parallel + when kswapd starts. This has a potential performance impact on + processes running early in the lifetime of the systemm until kswapd + finishes the initialisation. diff --git a/mm/internal.h b/mm/internal.h index 58e9022e3757..88ac7be741ca 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -387,6 +387,24 @@ static inline void mminit_verify_zonelist(void) } #endif /* CONFIG_DEBUG_MEMORY_INIT */ +/* + * Deferred struct page initialisation requires init functions that are freed + * before kswapd is available. Reuse the memory hotplug section annotation + * to mark the required code. + * + * __defermem_init is code that always exists but is annotated __meminit to + * avoid section warnings. + * __defer_init code gets marked __meminit when deferring struct page + * initialistion but is otherwise in the init section. + */ +#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT +#define __defermem_init __meminit +#define __defer_init __meminit +#else +#define __defermem_init +#define __defer_init __init +#endif + /* mminit_validate_memmodel_limits is independent of CONFIG_DEBUG_MEMORY_INIT */ #if defined(CONFIG_SPARSEMEM) extern void mminit_validate_memmodel_limits(unsigned long *start_pfn, diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 12a81870815f..7af45b2e8870 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -235,6 +235,64 @@ EXPORT_SYMBOL(nr_online_nodes); int page_group_by_mobility_disabled __read_mostly; +#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT +static inline void reset_deferred_meminit(pg_data_t *pgdat) +{ + pgdat->first_deferred_pfn = ULONG_MAX; +} + +/* Returns true if the struct page for the pfn is uninitialised */ +static inline bool __defermem_init early_page_uninitialised(unsigned long pfn) +{ + int nid = early_pfn_to_nid(pfn); + + if (pfn >= NODE_DATA(nid)->first_deferred_pfn) + return true; + + return false; +} + +/* + * Returns false when the remaining initialisation should be deferred until + * later in the boot cycle when it can be parallelised. + */ +static inline bool update_defer_init(pg_data_t *pgdat, + unsigned long pfn, unsigned long zone_end, + unsigned long *nr_initialised) +{ + /* Always populate low zones for address-contrained allocations */ + if (zone_end < pgdat_end_pfn(pgdat)) + return true; + + /* Initialise at least 2G of the highest zone */ + (*nr_initialised)++; + if (*nr_initialised > (2UL << (30 - PAGE_SHIFT)) && + (pfn & (PAGES_PER_SECTION - 1)) == 0) { + pgdat->first_deferred_pfn = pfn; + return false; + } + + return true; +} +#else +static inline void reset_deferred_meminit(pg_data_t *pgdat) +{ +} + +static inline bool early_page_uninitialised(unsigned long pfn) +{ + return false; +} + +static inline bool update_defer_init(pg_data_t *pgdat, + unsigned long pfn, unsigned long zone_end, + unsigned long *nr_initialised) +{ + return true; +} +#endif + + void set_pageblock_migratetype(struct page *page, int migratetype) { if (unlikely(page_group_by_mobility_disabled && @@ -878,8 +936,8 @@ static void __free_pages_ok(struct page *page, unsigned int order) local_irq_restore(flags); } -void __init __free_pages_bootmem(struct page *page, unsigned long pfn, - unsigned int order) +static void __defer_init __free_pages_boot_core(struct page *page, + unsigned long pfn, unsigned int order) { unsigned int nr_pages = 1 << order; struct page *p = page; @@ -951,6 +1009,14 @@ static inline bool __meminit meminit_pfn_in_nid(unsigned long pfn, int node, #endif +void __defer_init __free_pages_bootmem(struct page *page, unsigned long pfn, + unsigned int order) +{ + if (early_page_uninitialised(pfn)) + return; + return __free_pages_boot_core(page, pfn, order); +} + #ifdef CONFIG_CMA /* Free whole pageblock and set its migration type to MIGRATE_CMA. */ void __init init_cma_reserved_pageblock(struct page *page) @@ -4325,14 +4391,16 @@ static void setup_zone_migrate_reserve(struct zone *zone) void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, unsigned long start_pfn, enum memmap_context context) { + pg_data_t *pgdat = NODE_DATA(nid); unsigned long end_pfn = start_pfn + size; unsigned long pfn; struct zone *z; + unsigned long nr_initialised = 0; if (highest_memmap_pfn < end_pfn - 1) highest_memmap_pfn = end_pfn - 1; - z = &NODE_DATA(nid)->node_zones[zone]; + z = &pgdat->node_zones[zone]; for (pfn = start_pfn; pfn < end_pfn; pfn++) { /* * There can be holes in boot-time mem_map[]s @@ -4344,6 +4412,9 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, continue; if (!early_pfn_in_nid(pfn, nid)) continue; + if (!update_defer_init(pgdat, pfn, end_pfn, + &nr_initialised)) + break; } __init_single_pfn(pfn, zone, nid); } @@ -5144,6 +5215,7 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size, /* pg_data_t should be reset to zero when it's allocated */ WARN_ON(pgdat->nr_zones || pgdat->classzone_idx); + reset_deferred_meminit(pgdat); pgdat->node_id = nid; pgdat->node_start_pfn = node_start_pfn; #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP -- cgit v1.2.3 From 7e18adb4f80bea90d30b62158694d97c31f71d37 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Tue, 30 Jun 2015 14:57:05 -0700 Subject: mm: meminit: initialise remaining struct pages in parallel with kswapd Only a subset of struct pages are initialised at the moment. When this patch is applied kswapd initialise the remaining struct pages in parallel. This should boot faster by spreading the work to multiple CPUs and initialising data that is local to the CPU. The user-visible effect on large machines is that free memory will appear to rapidly increase early in the lifetime of the system until kswapd reports that all memory is initialised in the kernel log. Once initialised there should be no other user-visibile effects. Signed-off-by: Mel Gorman Tested-by: Nate Zimmer Tested-by: Waiman Long Tested-by: Daniel J Blueman Acked-by: Pekka Enberg Cc: Robin Holt Cc: Nate Zimmer Cc: Dave Hansen Cc: Waiman Long Cc: Scott Norton Cc: "Luck, Tony" Cc: Ingo Molnar Cc: "H. Peter Anvin" Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/internal.h | 6 +++ mm/mm_init.c | 1 + mm/page_alloc.c | 123 ++++++++++++++++++++++++++++++++++++++++++++++++++++++-- mm/vmscan.c | 6 ++- 4 files changed, 130 insertions(+), 6 deletions(-) diff --git a/mm/internal.h b/mm/internal.h index 88ac7be741ca..71d160437205 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -400,9 +400,15 @@ static inline void mminit_verify_zonelist(void) #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT #define __defermem_init __meminit #define __defer_init __meminit + +void deferred_init_memmap(int nid); #else #define __defermem_init #define __defer_init __init + +static inline void deferred_init_memmap(int nid) +{ +} #endif /* mminit_validate_memmodel_limits is independent of CONFIG_DEBUG_MEMORY_INIT */ diff --git a/mm/mm_init.c b/mm/mm_init.c index 5f420f7fafa1..28fbf87b20aa 100644 --- a/mm/mm_init.c +++ b/mm/mm_init.c @@ -11,6 +11,7 @@ #include #include #include +#include #include "internal.h" #ifdef CONFIG_DEBUG_MEMORY_INIT diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 7af45b2e8870..c30f5a0535fd 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -252,6 +252,14 @@ static inline bool __defermem_init early_page_uninitialised(unsigned long pfn) return false; } +static inline bool early_page_nid_uninitialised(unsigned long pfn, int nid) +{ + if (pfn >= NODE_DATA(nid)->first_deferred_pfn) + return true; + + return false; +} + /* * Returns false when the remaining initialisation should be deferred until * later in the boot cycle when it can be parallelised. @@ -284,6 +292,11 @@ static inline bool early_page_uninitialised(unsigned long pfn) return false; } +static inline bool early_page_nid_uninitialised(unsigned long pfn, int nid) +{ + return false; +} + static inline bool update_defer_init(pg_data_t *pgdat, unsigned long pfn, unsigned long zone_end, unsigned long *nr_initialised) @@ -866,20 +879,51 @@ static void __meminit __init_single_pfn(unsigned long pfn, unsigned long zone, return __init_single_page(pfn_to_page(pfn), pfn, zone, nid); } +#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT +static void init_reserved_page(unsigned long pfn) +{ + pg_data_t *pgdat; + int nid, zid; + + if (!early_page_uninitialised(pfn)) + return; + + nid = early_pfn_to_nid(pfn); + pgdat = NODE_DATA(nid); + + for (zid = 0; zid < MAX_NR_ZONES; zid++) { + struct zone *zone = &pgdat->node_zones[zid]; + + if (pfn >= zone->zone_start_pfn && pfn < zone_end_pfn(zone)) + break; + } + __init_single_pfn(pfn, zid, nid); +} +#else +static inline void init_reserved_page(unsigned long pfn) +{ +} +#endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */ + /* * Initialised pages do not have PageReserved set. This function is * called for each range allocated by the bootmem allocator and * marks the pages PageReserved. The remaining valid pages are later * sent to the buddy page allocator. */ -void reserve_bootmem_region(unsigned long start, unsigned long end) +void __meminit reserve_bootmem_region(unsigned long start, unsigned long end) { unsigned long start_pfn = PFN_DOWN(start); unsigned long end_pfn = PFN_UP(end); - for (; start_pfn < end_pfn; start_pfn++) - if (pfn_valid(start_pfn)) - SetPageReserved(pfn_to_page(start_pfn)); + for (; start_pfn < end_pfn; start_pfn++) { + if (pfn_valid(start_pfn)) { + struct page *page = pfn_to_page(start_pfn); + + init_reserved_page(start_pfn); + SetPageReserved(page); + } + } } static bool free_pages_prepare(struct page *page, unsigned int order) @@ -1017,6 +1061,74 @@ void __defer_init __free_pages_bootmem(struct page *page, unsigned long pfn, return __free_pages_boot_core(page, pfn, order); } +#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT +/* Initialise remaining memory on a node */ +void __defermem_init deferred_init_memmap(int nid) +{ + struct mminit_pfnnid_cache nid_init_state = { }; + unsigned long start = jiffies; + unsigned long nr_pages = 0; + unsigned long walk_start, walk_end; + int i, zid; + struct zone *zone; + pg_data_t *pgdat = NODE_DATA(nid); + unsigned long first_init_pfn = pgdat->first_deferred_pfn; + + if (first_init_pfn == ULONG_MAX) + return; + + /* Sanity check boundaries */ + BUG_ON(pgdat->first_deferred_pfn < pgdat->node_start_pfn); + BUG_ON(pgdat->first_deferred_pfn > pgdat_end_pfn(pgdat)); + pgdat->first_deferred_pfn = ULONG_MAX; + + /* Only the highest zone is deferred so find it */ + for (zid = 0; zid < MAX_NR_ZONES; zid++) { + zone = pgdat->node_zones + zid; + if (first_init_pfn < zone_end_pfn(zone)) + break; + } + + for_each_mem_pfn_range(i, nid, &walk_start, &walk_end, NULL) { + unsigned long pfn, end_pfn; + + end_pfn = min(walk_end, zone_end_pfn(zone)); + pfn = first_init_pfn; + if (pfn < walk_start) + pfn = walk_start; + if (pfn < zone->zone_start_pfn) + pfn = zone->zone_start_pfn; + + for (; pfn < end_pfn; pfn++) { + struct page *page; + + if (!pfn_valid(pfn)) + continue; + + if (!meminit_pfn_in_nid(pfn, nid, &nid_init_state)) + continue; + + if (page->flags) { + VM_BUG_ON(page_zone(page) != zone); + continue; + } + + __init_single_page(page, pfn, zid, nid); + __free_pages_boot_core(page, pfn, 0); + nr_pages++; + cond_resched(); + } + first_init_pfn = max(end_pfn, first_init_pfn); + } + + /* Sanity check that the next zone really is unpopulated */ + WARN_ON(++zid < MAX_NR_ZONES && populated_zone(++zone)); + + pr_info("kswapd %d initialised %lu pages in %ums\n", nid, nr_pages, + jiffies_to_msecs(jiffies - start)); +} +#endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */ + #ifdef CONFIG_CMA /* Free whole pageblock and set its migration type to MIGRATE_CMA. */ void __init init_cma_reserved_pageblock(struct page *page) @@ -4329,6 +4441,9 @@ static void setup_zone_migrate_reserve(struct zone *zone) zone->nr_migrate_reserve_block = reserve; for (pfn = start_pfn; pfn < end_pfn; pfn += pageblock_nr_pages) { + if (!early_page_nid_uninitialised(pfn, zone_to_nid(zone))) + return; + if (!pfn_valid(pfn)) continue; page = pfn_to_page(pfn); diff --git a/mm/vmscan.c b/mm/vmscan.c index e61445dce04e..f4a487110764 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -3386,7 +3386,7 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order, int classzone_idx) * If there are applications that are active memory-allocators * (most normal use), this basically shouldn't matter. */ -static int kswapd(void *p) +static int __defermem_init kswapd(void *p) { unsigned long order, new_order; unsigned balanced_order; @@ -3421,6 +3421,8 @@ static int kswapd(void *p) tsk->flags |= PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD; set_freezable(); + deferred_init_memmap(pgdat->node_id); + order = new_order = 0; balanced_order = 0; classzone_idx = new_classzone_idx = pgdat->nr_zones - 1; @@ -3576,7 +3578,7 @@ static int cpu_callback(struct notifier_block *nfb, unsigned long action, * This kswapd start function will be called by init and node-hot-add. * On node-hot-add, kswapd will moved to proper cpus if cpus are hot-added. */ -int kswapd_run(int nid) +int __defermem_init kswapd_run(int nid) { pg_data_t *pgdat = NODE_DATA(nid); int ret = 0; -- cgit v1.2.3 From 54608c3f3a448f1e042f5d9f3b873cc8dc022f27 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Tue, 30 Jun 2015 14:57:09 -0700 Subject: mm: meminit: minimise number of pfn->page lookups during initialisation Deferred struct page initialisation is using pfn_to_page() on every PFN unnecessarily. This patch minimises the number of lookups and scheduler checks. Signed-off-by: Mel Gorman Tested-by: Nate Zimmer Tested-by: Waiman Long Tested-by: Daniel J Blueman Acked-by: Pekka Enberg Cc: Robin Holt Cc: Nate Zimmer Cc: Dave Hansen Cc: Waiman Long Cc: Scott Norton Cc: "Luck, Tony" Cc: Ingo Molnar Cc: "H. Peter Anvin" Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 29 ++++++++++++++++++++++++----- 1 file changed, 24 insertions(+), 5 deletions(-) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index c30f5a0535fd..0f770cc13450 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1091,6 +1091,7 @@ void __defermem_init deferred_init_memmap(int nid) for_each_mem_pfn_range(i, nid, &walk_start, &walk_end, NULL) { unsigned long pfn, end_pfn; + struct page *page = NULL; end_pfn = min(walk_end, zone_end_pfn(zone)); pfn = first_init_pfn; @@ -1100,13 +1101,32 @@ void __defermem_init deferred_init_memmap(int nid) pfn = zone->zone_start_pfn; for (; pfn < end_pfn; pfn++) { - struct page *page; - - if (!pfn_valid(pfn)) + if (!pfn_valid_within(pfn)) continue; - if (!meminit_pfn_in_nid(pfn, nid, &nid_init_state)) + /* + * Ensure pfn_valid is checked every + * MAX_ORDER_NR_PAGES for memory holes + */ + if ((pfn & (MAX_ORDER_NR_PAGES - 1)) == 0) { + if (!pfn_valid(pfn)) { + page = NULL; + continue; + } + } + + if (!meminit_pfn_in_nid(pfn, nid, &nid_init_state)) { + page = NULL; continue; + } + + /* Minimise pfn page lookups and scheduler checks */ + if (page && (pfn & (MAX_ORDER_NR_PAGES - 1)) != 0) { + page++; + } else { + page = pfn_to_page(pfn); + cond_resched(); + } if (page->flags) { VM_BUG_ON(page_zone(page) != zone); @@ -1116,7 +1136,6 @@ void __defermem_init deferred_init_memmap(int nid) __init_single_page(page, pfn, zid, nid); __free_pages_boot_core(page, pfn, 0); nr_pages++; - cond_resched(); } first_init_pfn = max(end_pfn, first_init_pfn); } -- cgit v1.2.3 From 3b242c66ccbd60cf47ab0e8992119d9617548c23 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Tue, 30 Jun 2015 14:57:13 -0700 Subject: x86: mm: enable deferred struct page initialisation on x86-64 Subject says it all. Other architectures may enable on a case-by-case basis after auditing early_pfn_to_nid and testing. Signed-off-by: Mel Gorman Tested-by: Nate Zimmer Tested-by: Waiman Long Tested-by: Daniel J Blueman Acked-by: Pekka Enberg Cc: Robin Holt Cc: Nate Zimmer Cc: Dave Hansen Cc: Waiman Long Cc: Scott Norton Cc: "Luck, Tony" Cc: Ingo Molnar Cc: "H. Peter Anvin" Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index d05a42357ef0..47365c7b9f47 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -34,6 +34,7 @@ config X86 select ARCH_MIGHT_HAVE_PC_PARPORT select ARCH_MIGHT_HAVE_PC_SERIO select ARCH_SUPPORTS_ATOMIC_RMW + select ARCH_SUPPORTS_DEFERRED_STRUCT_PAGE_INIT select ARCH_SUPPORTS_INT128 if X86_64 select ARCH_SUPPORTS_NUMA_BALANCING if X86_64 select ARCH_USE_BUILTIN_BSWAP -- cgit v1.2.3 From a4de83dd3377eb43ad95387cc16c27a11aae2feb Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Tue, 30 Jun 2015 14:57:16 -0700 Subject: mm: meminit: free pages in large chunks where possible Parallel struct page frees pages one at a time. Try free pages as single large pages where possible. Signed-off-by: Mel Gorman Tested-by: Nate Zimmer Tested-by: Waiman Long Tested-by: Daniel J Blueman Acked-by: Pekka Enberg Cc: Robin Holt Cc: Nate Zimmer Cc: Dave Hansen Cc: Waiman Long Cc: Scott Norton Cc: "Luck, Tony" Cc: Ingo Molnar Cc: "H. Peter Anvin" Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 55 +++++++++++++++++++++++++++++++++++++++++++++++++------ 1 file changed, 49 insertions(+), 6 deletions(-) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 0f770cc13450..e3f00f622f28 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1062,6 +1062,25 @@ void __defer_init __free_pages_bootmem(struct page *page, unsigned long pfn, } #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT +static void __defermem_init deferred_free_range(struct page *page, + unsigned long pfn, int nr_pages) +{ + int i; + + if (!page) + return; + + /* Free a large naturally-aligned chunk if possible */ + if (nr_pages == MAX_ORDER_NR_PAGES && + (pfn & (MAX_ORDER_NR_PAGES-1)) == 0) { + __free_pages_boot_core(page, pfn, MAX_ORDER-1); + return; + } + + for (i = 0; i < nr_pages; i++, page++, pfn++) + __free_pages_boot_core(page, pfn, 0); +} + /* Initialise remaining memory on a node */ void __defermem_init deferred_init_memmap(int nid) { @@ -1092,6 +1111,9 @@ void __defermem_init deferred_init_memmap(int nid) for_each_mem_pfn_range(i, nid, &walk_start, &walk_end, NULL) { unsigned long pfn, end_pfn; struct page *page = NULL; + struct page *free_base_page = NULL; + unsigned long free_base_pfn = 0; + int nr_to_free = 0; end_pfn = min(walk_end, zone_end_pfn(zone)); pfn = first_init_pfn; @@ -1102,7 +1124,7 @@ void __defermem_init deferred_init_memmap(int nid) for (; pfn < end_pfn; pfn++) { if (!pfn_valid_within(pfn)) - continue; + goto free_range; /* * Ensure pfn_valid is checked every @@ -1111,32 +1133,53 @@ void __defermem_init deferred_init_memmap(int nid) if ((pfn & (MAX_ORDER_NR_PAGES - 1)) == 0) { if (!pfn_valid(pfn)) { page = NULL; - continue; + goto free_range; } } if (!meminit_pfn_in_nid(pfn, nid, &nid_init_state)) { page = NULL; - continue; + goto free_range; } /* Minimise pfn page lookups and scheduler checks */ if (page && (pfn & (MAX_ORDER_NR_PAGES - 1)) != 0) { page++; } else { + nr_pages += nr_to_free; + deferred_free_range(free_base_page, + free_base_pfn, nr_to_free); + free_base_page = NULL; + free_base_pfn = nr_to_free = 0; + page = pfn_to_page(pfn); cond_resched(); } if (page->flags) { VM_BUG_ON(page_zone(page) != zone); - continue; + goto free_range; } __init_single_page(page, pfn, zid, nid); - __free_pages_boot_core(page, pfn, 0); - nr_pages++; + if (!free_base_page) { + free_base_page = page; + free_base_pfn = pfn; + nr_to_free = 0; + } + nr_to_free++; + + /* Where possible, batch up pages for a single free */ + continue; +free_range: + /* Free the current block of pages to allocator */ + nr_pages += nr_to_free; + deferred_free_range(free_base_page, free_base_pfn, + nr_to_free); + free_base_page = NULL; + free_base_pfn = nr_to_free = 0; } + first_init_pfn = max(end_pfn, first_init_pfn); } -- cgit v1.2.3 From ac5d2539b2382689b1cdb90bd60dcd49f61c2773 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Tue, 30 Jun 2015 14:57:20 -0700 Subject: mm: meminit: reduce number of times pageblocks are set during struct page init During parallel sturct page initialisation, ranges are checked for every PFN unnecessarily which increases boot times. This patch alters when the ranges are checked. Signed-off-by: Mel Gorman Tested-by: Nate Zimmer Tested-by: Waiman Long Tested-by: Daniel J Blueman Acked-by: Pekka Enberg Cc: Robin Holt Cc: Nate Zimmer Cc: Dave Hansen Cc: Waiman Long Cc: Scott Norton Cc: "Luck, Tony" Cc: Ingo Molnar Cc: "H. Peter Anvin" Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 46 ++++++++++++++++++++++++---------------------- 1 file changed, 24 insertions(+), 22 deletions(-) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index e3f00f622f28..f1f455a69cef 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -838,33 +838,12 @@ static int free_tail_pages_check(struct page *head_page, struct page *page) static void __meminit __init_single_page(struct page *page, unsigned long pfn, unsigned long zone, int nid) { - struct zone *z = &NODE_DATA(nid)->node_zones[zone]; - set_page_links(page, zone, nid, pfn); mminit_verify_page_links(page, zone, nid, pfn); init_page_count(page); page_mapcount_reset(page); page_cpupid_reset_last(page); - /* - * Mark the block movable so that blocks are reserved for - * movable at startup. This will force kernel allocations - * to reserve their blocks rather than leaking throughout - * the address space during boot when many long-lived - * kernel allocations are made. Later some blocks near - * the start are marked MIGRATE_RESERVE by - * setup_zone_migrate_reserve() - * - * bitmap is created for zone's valid pfn range. but memmap - * can be created for invalid pages (for alignment) - * check here not to call set_pageblock_migratetype() against - * pfn out of zone. - */ - if ((z->zone_start_pfn <= pfn) - && (pfn < zone_end_pfn(z)) - && !(pfn & (pageblock_nr_pages - 1))) - set_pageblock_migratetype(page, MIGRATE_MOVABLE); - INIT_LIST_HEAD(&page->lru); #ifdef WANT_PAGE_VIRTUAL /* The shift won't overflow because ZONE_NORMAL is below 4G. */ @@ -1073,6 +1052,7 @@ static void __defermem_init deferred_free_range(struct page *page, /* Free a large naturally-aligned chunk if possible */ if (nr_pages == MAX_ORDER_NR_PAGES && (pfn & (MAX_ORDER_NR_PAGES-1)) == 0) { + set_pageblock_migratetype(page, MIGRATE_MOVABLE); __free_pages_boot_core(page, pfn, MAX_ORDER-1); return; } @@ -4593,7 +4573,29 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, &nr_initialised)) break; } - __init_single_pfn(pfn, zone, nid); + + /* + * Mark the block movable so that blocks are reserved for + * movable at startup. This will force kernel allocations + * to reserve their blocks rather than leaking throughout + * the address space during boot when many long-lived + * kernel allocations are made. Later some blocks near + * the start are marked MIGRATE_RESERVE by + * setup_zone_migrate_reserve() + * + * bitmap is created for zone's valid pfn range. but memmap + * can be created for invalid pages (for alignment) + * check here not to call set_pageblock_migratetype() against + * pfn out of zone. + */ + if (!(pfn & (pageblock_nr_pages - 1))) { + struct page *page = pfn_to_page(pfn); + + __init_single_page(page, pfn, zone, nid); + set_pageblock_migratetype(page, MIGRATE_MOVABLE); + } else { + __init_single_pfn(pfn, zone, nid); + } } } -- cgit v1.2.3 From 74033a798f5a5db368126ee6f690111cf019bf7a Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Tue, 30 Jun 2015 14:57:23 -0700 Subject: mm: meminit: remove mminit_verify_page_links mminit_verify_page_links() is an extremely paranoid check that was introduced when memory initialisation was being heavily reworked. Profiles indicated that up to 10% of parallel memory initialisation was spent on checking this for every page. The cost could be reduced but in practice this check only found problems very early during the initialisation rewrite and has found nothing since. This patch removes an expensive unnecessary check. Signed-off-by: Mel Gorman Tested-by: Nate Zimmer Tested-by: Waiman Long Tested-by: Daniel J Blueman Acked-by: Pekka Enberg Cc: Robin Holt Cc: Nate Zimmer Cc: Dave Hansen Cc: Waiman Long Cc: Scott Norton Cc: "Luck, Tony" Cc: Ingo Molnar Cc: "H. Peter Anvin" Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/internal.h | 8 -------- mm/mm_init.c | 8 -------- mm/page_alloc.c | 1 - 3 files changed, 17 deletions(-) diff --git a/mm/internal.h b/mm/internal.h index 71d160437205..a48cbefde8ca 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -362,10 +362,7 @@ do { \ } while (0) extern void mminit_verify_pageflags_layout(void); -extern void mminit_verify_page_links(struct page *page, - enum zone_type zone, unsigned long nid, unsigned long pfn); extern void mminit_verify_zonelist(void); - #else static inline void mminit_dprintk(enum mminit_level level, @@ -377,11 +374,6 @@ static inline void mminit_verify_pageflags_layout(void) { } -static inline void mminit_verify_page_links(struct page *page, - enum zone_type zone, unsigned long nid, unsigned long pfn) -{ -} - static inline void mminit_verify_zonelist(void) { } diff --git a/mm/mm_init.c b/mm/mm_init.c index 28fbf87b20aa..fdadf918de76 100644 --- a/mm/mm_init.c +++ b/mm/mm_init.c @@ -131,14 +131,6 @@ void __init mminit_verify_pageflags_layout(void) BUG_ON(or_mask != add_mask); } -void __meminit mminit_verify_page_links(struct page *page, enum zone_type zone, - unsigned long nid, unsigned long pfn) -{ - BUG_ON(page_to_nid(page) != nid); - BUG_ON(page_zonenum(page) != zone); - BUG_ON(page_to_pfn(page) != pfn); -} - static __init int set_mminit_loglevel(char *str) { get_option(&str, &mminit_loglevel); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index f1f455a69cef..5a38e39b30d1 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -839,7 +839,6 @@ static void __meminit __init_single_page(struct page *page, unsigned long pfn, unsigned long zone, int nid) { set_page_links(page, zone, nid, pfn); - mminit_verify_page_links(page, zone, nid, pfn); init_page_count(page); page_mapcount_reset(page); page_cpupid_reset_last(page); -- cgit v1.2.3 From 0e1cc95b4cc7293bb7b39175035e7f7e45c90977 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Tue, 30 Jun 2015 14:57:27 -0700 Subject: mm: meminit: finish initialisation of struct pages before basic setup Waiman Long reported that 24TB machines hit OOM during basic setup when struct page initialisation was deferred. One approach is to initialise memory on demand but it interferes with page allocator paths. This patch creates dedicated threads to initialise memory before basic setup. It then blocks on a rw_semaphore until completion as a wait_queue and counter is overkill. This may be slower to boot but it's simplier overall and also gets rid of a section mangling which existed so kswapd could do the initialisation. [akpm@linux-foundation.org: include rwsem.h, use DECLARE_RWSEM, fix comment, remove unneeded cast] Signed-off-by: Mel Gorman Cc: Waiman Long Cc: Dave Hansen Cc: Scott Norton Tested-by: Daniel J Blueman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 8 ++++++++ init/main.c | 2 ++ mm/internal.h | 24 ------------------------ mm/page_alloc.c | 46 +++++++++++++++++++++++++++++++++++++--------- mm/vmscan.c | 6 ++---- 5 files changed, 49 insertions(+), 37 deletions(-) diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 6ba7cf23748f..ad35f300b9a4 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -384,6 +384,14 @@ void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp); void drain_all_pages(struct zone *zone); void drain_local_pages(struct zone *zone); +#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT +void page_alloc_init_late(void); +#else +static inline void page_alloc_init_late(void) +{ +} +#endif + /* * gfp_allowed_mask is set to GFP_BOOT_MASK during early boot to restrict what * GFP flags are used before interrupts are enabled. Once interrupts are diff --git a/init/main.c b/init/main.c index c599aea23bb1..c5d5626289ce 100644 --- a/init/main.c +++ b/init/main.c @@ -1004,6 +1004,8 @@ static noinline void __init kernel_init_freeable(void) smp_init(); sched_init_smp(); + page_alloc_init_late(); + do_basic_setup(); /* Open the /dev/console on the rootfs, this should never fail */ diff --git a/mm/internal.h b/mm/internal.h index a48cbefde8ca..36b23f1e2ca6 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -379,30 +379,6 @@ static inline void mminit_verify_zonelist(void) } #endif /* CONFIG_DEBUG_MEMORY_INIT */ -/* - * Deferred struct page initialisation requires init functions that are freed - * before kswapd is available. Reuse the memory hotplug section annotation - * to mark the required code. - * - * __defermem_init is code that always exists but is annotated __meminit to - * avoid section warnings. - * __defer_init code gets marked __meminit when deferring struct page - * initialistion but is otherwise in the init section. - */ -#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT -#define __defermem_init __meminit -#define __defer_init __meminit - -void deferred_init_memmap(int nid); -#else -#define __defermem_init -#define __defer_init __init - -static inline void deferred_init_memmap(int nid) -{ -} -#endif - /* mminit_validate_memmodel_limits is independent of CONFIG_DEBUG_MEMORY_INIT */ #if defined(CONFIG_SPARSEMEM) extern void mminit_validate_memmodel_limits(unsigned long *start_pfn, diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 5a38e39b30d1..506eac8b38af 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include #include @@ -61,6 +62,7 @@ #include #include #include +#include #include #include @@ -242,7 +244,7 @@ static inline void reset_deferred_meminit(pg_data_t *pgdat) } /* Returns true if the struct page for the pfn is uninitialised */ -static inline bool __defermem_init early_page_uninitialised(unsigned long pfn) +static inline bool __meminit early_page_uninitialised(unsigned long pfn) { int nid = early_pfn_to_nid(pfn); @@ -958,7 +960,7 @@ static void __free_pages_ok(struct page *page, unsigned int order) local_irq_restore(flags); } -static void __defer_init __free_pages_boot_core(struct page *page, +static void __init __free_pages_boot_core(struct page *page, unsigned long pfn, unsigned int order) { unsigned int nr_pages = 1 << order; @@ -1031,7 +1033,7 @@ static inline bool __meminit meminit_pfn_in_nid(unsigned long pfn, int node, #endif -void __defer_init __free_pages_bootmem(struct page *page, unsigned long pfn, +void __init __free_pages_bootmem(struct page *page, unsigned long pfn, unsigned int order) { if (early_page_uninitialised(pfn)) @@ -1040,7 +1042,7 @@ void __defer_init __free_pages_bootmem(struct page *page, unsigned long pfn, } #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT -static void __defermem_init deferred_free_range(struct page *page, +static void __init deferred_free_range(struct page *page, unsigned long pfn, int nr_pages) { int i; @@ -1060,20 +1062,30 @@ static void __defermem_init deferred_free_range(struct page *page, __free_pages_boot_core(page, pfn, 0); } +static __initdata DECLARE_RWSEM(pgdat_init_rwsem); + /* Initialise remaining memory on a node */ -void __defermem_init deferred_init_memmap(int nid) +static int __init deferred_init_memmap(void *data) { + pg_data_t *pgdat = data; + int nid = pgdat->node_id; struct mminit_pfnnid_cache nid_init_state = { }; unsigned long start = jiffies; unsigned long nr_pages = 0; unsigned long walk_start, walk_end; int i, zid; struct zone *zone; - pg_data_t *pgdat = NODE_DATA(nid); unsigned long first_init_pfn = pgdat->first_deferred_pfn; + const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id); - if (first_init_pfn == ULONG_MAX) - return; + if (first_init_pfn == ULONG_MAX) { + up_read(&pgdat_init_rwsem); + return 0; + } + + /* Bind memory initialisation thread to a local node if possible */ + if (!cpumask_empty(cpumask)) + set_cpus_allowed_ptr(current, cpumask); /* Sanity check boundaries */ BUG_ON(pgdat->first_deferred_pfn < pgdat->node_start_pfn); @@ -1165,8 +1177,24 @@ free_range: /* Sanity check that the next zone really is unpopulated */ WARN_ON(++zid < MAX_NR_ZONES && populated_zone(++zone)); - pr_info("kswapd %d initialised %lu pages in %ums\n", nid, nr_pages, + pr_info("node %d initialised, %lu pages in %ums\n", nid, nr_pages, jiffies_to_msecs(jiffies - start)); + up_read(&pgdat_init_rwsem); + return 0; +} + +void __init page_alloc_init_late(void) +{ + int nid; + + for_each_node_state(nid, N_MEMORY) { + down_read(&pgdat_init_rwsem); + kthread_run(deferred_init_memmap, NODE_DATA(nid), "pgdatinit%d", nid); + } + + /* Block until all are initialised */ + down_write(&pgdat_init_rwsem); + up_write(&pgdat_init_rwsem); } #endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */ diff --git a/mm/vmscan.c b/mm/vmscan.c index f4a487110764..e61445dce04e 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -3386,7 +3386,7 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order, int classzone_idx) * If there are applications that are active memory-allocators * (most normal use), this basically shouldn't matter. */ -static int __defermem_init kswapd(void *p) +static int kswapd(void *p) { unsigned long order, new_order; unsigned balanced_order; @@ -3421,8 +3421,6 @@ static int __defermem_init kswapd(void *p) tsk->flags |= PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD; set_freezable(); - deferred_init_memmap(pgdat->node_id); - order = new_order = 0; balanced_order = 0; classzone_idx = new_classzone_idx = pgdat->nr_zones - 1; @@ -3578,7 +3576,7 @@ static int cpu_callback(struct notifier_block *nfb, unsigned long action, * This kswapd start function will be called by init and node-hot-add. * On node-hot-add, kswapd will moved to proper cpus if cpus are hot-added. */ -int __defermem_init kswapd_run(int nid) +int kswapd_run(int nid) { pg_data_t *pgdat = NODE_DATA(nid); int ret = 0; -- cgit v1.2.3 From ede1bf0dcff2b07001c760992b1ca18fd0f419bc Mon Sep 17 00:00:00 2001 From: Yann Droneaud Date: Tue, 30 Jun 2015 14:57:30 -0700 Subject: fs: use seq_open_private() for proc_mounts A patchset to remove support for passing pre-allocated struct seq_file to seq_open(). Such feature is undocumented and prone to error. In particular, if seq_release() is used in release handler, it will kfree() a pointer which was not allocated by seq_open(). So this patchset drops support for pre-allocated struct seq_file: it's only of use in proc_namespace.c and can be easily replaced by using seq_open_private()/seq_release_private(). Additionally, it documents the use of file->private_data to hold pointer to struct seq_file by seq_open(). This patch (of 3): Since patch described below, from v2.6.15-rc1, seq_open() could use a struct seq_file already allocated by the caller if the pointer to the structure is stored in file->private_data before calling the function. Commit 1abe77b0fc4b485927f1f798ae81a752677e1d05 Author: Al Viro Date: Mon Nov 7 17:15:34 2005 -0500 [PATCH] allow callers of seq_open do allocation themselves Allow caller of seq_open() to kmalloc() seq_file + whatever else they want and set ->private_data to it. seq_open() will then abstain from doing allocation itself. Such behavior is only used by mounts_open_common(). In order to drop support for such uncommon feature, proc_mounts is converted to use seq_open_private(), which take care of allocating the proc_mounts structure, making it available through ->private in struct seq_file. Conversely, proc_mounts is converted to use seq_release_private(), in order to release the private structure allocated by seq_open_private(). Then, ->private is used directly instead of proc_mounts() macro to access to the proc_mounts structure. Link: http://lkml.kernel.org/r/cover.1433193673.git.ydroneaud@opteya.com Signed-off-by: Yann Droneaud Cc: Al Viro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/mount.h | 3 --- fs/namespace.c | 6 +++--- fs/proc_namespace.c | 34 ++++++++++++++++------------------ 3 files changed, 19 insertions(+), 24 deletions(-) diff --git a/fs/mount.h b/fs/mount.h index b5b8082bfa42..14db05d424f7 100644 --- a/fs/mount.h +++ b/fs/mount.h @@ -118,7 +118,6 @@ static inline void unlock_mount_hash(void) } struct proc_mounts { - struct seq_file m; struct mnt_namespace *ns; struct path root; int (*show)(struct seq_file *, struct vfsmount *); @@ -127,8 +126,6 @@ struct proc_mounts { loff_t cached_index; }; -#define proc_mounts(p) (container_of((p), struct proc_mounts, m)) - extern const struct seq_operations mounts_op; extern bool __is_local_mountpoint(struct dentry *dentry); diff --git a/fs/namespace.c b/fs/namespace.c index 9c1c43d0d4f1..e99f1f4e00cd 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -1226,7 +1226,7 @@ EXPORT_SYMBOL(replace_mount_options); /* iterator; we want it to have access to namespace_sem, thus here... */ static void *m_start(struct seq_file *m, loff_t *pos) { - struct proc_mounts *p = proc_mounts(m); + struct proc_mounts *p = m->private; down_read(&namespace_sem); if (p->cached_event == p->ns->event) { @@ -1247,7 +1247,7 @@ static void *m_start(struct seq_file *m, loff_t *pos) static void *m_next(struct seq_file *m, void *v, loff_t *pos) { - struct proc_mounts *p = proc_mounts(m); + struct proc_mounts *p = m->private; p->cached_mount = seq_list_next(v, &p->ns->list, pos); p->cached_index = *pos; @@ -1261,7 +1261,7 @@ static void m_stop(struct seq_file *m, void *v) static int m_show(struct seq_file *m, void *v) { - struct proc_mounts *p = proc_mounts(m); + struct proc_mounts *p = m->private; struct mount *r = list_entry(v, struct mount, mnt_list); return p->show(m, &r->mnt); } diff --git a/fs/proc_namespace.c b/fs/proc_namespace.c index 8db932da4009..8ebd9a334085 100644 --- a/fs/proc_namespace.c +++ b/fs/proc_namespace.c @@ -17,7 +17,8 @@ static unsigned mounts_poll(struct file *file, poll_table *wait) { - struct proc_mounts *p = proc_mounts(file->private_data); + struct seq_file *m = file->private_data; + struct proc_mounts *p = m->private; struct mnt_namespace *ns = p->ns; unsigned res = POLLIN | POLLRDNORM; int event; @@ -25,8 +26,8 @@ static unsigned mounts_poll(struct file *file, poll_table *wait) poll_wait(file, &p->ns->poll, wait); event = ACCESS_ONCE(ns->event); - if (p->m.poll_event != event) { - p->m.poll_event = event; + if (m->poll_event != event) { + m->poll_event = event; res |= POLLERR | POLLPRI; } @@ -92,7 +93,7 @@ static void show_type(struct seq_file *m, struct super_block *sb) static int show_vfsmnt(struct seq_file *m, struct vfsmount *mnt) { - struct proc_mounts *p = proc_mounts(m); + struct proc_mounts *p = m->private; struct mount *r = real_mount(mnt); int err = 0; struct path mnt_path = { .dentry = mnt->mnt_root, .mnt = mnt }; @@ -126,7 +127,7 @@ out: static int show_mountinfo(struct seq_file *m, struct vfsmount *mnt) { - struct proc_mounts *p = proc_mounts(m); + struct proc_mounts *p = m->private; struct mount *r = real_mount(mnt); struct super_block *sb = mnt->mnt_sb; struct path mnt_path = { .dentry = mnt->mnt_root, .mnt = mnt }; @@ -186,7 +187,7 @@ out: static int show_vfsstat(struct seq_file *m, struct vfsmount *mnt) { - struct proc_mounts *p = proc_mounts(m); + struct proc_mounts *p = m->private; struct mount *r = real_mount(mnt); struct path mnt_path = { .dentry = mnt->mnt_root, .mnt = mnt }; struct super_block *sb = mnt_path.dentry->d_sb; @@ -236,6 +237,7 @@ static int mounts_open_common(struct inode *inode, struct file *file, struct mnt_namespace *ns = NULL; struct path root; struct proc_mounts *p; + struct seq_file *m; int ret = -EINVAL; if (!task) @@ -260,26 +262,21 @@ static int mounts_open_common(struct inode *inode, struct file *file, task_unlock(task); put_task_struct(task); - ret = -ENOMEM; - p = kmalloc(sizeof(struct proc_mounts), GFP_KERNEL); - if (!p) + ret = seq_open_private(file, &mounts_op, sizeof(struct proc_mounts)); + if (ret) goto err_put_path; - file->private_data = &p->m; - ret = seq_open(file, &mounts_op); - if (ret) - goto err_free; + m = file->private_data; + m->poll_event = ns->event; + p = m->private; p->ns = ns; p->root = root; - p->m.poll_event = ns->event; p->show = show; p->cached_event = ~0ULL; return 0; - err_free: - kfree(p); err_put_path: path_put(&root); err_put_ns: @@ -290,10 +287,11 @@ static int mounts_open_common(struct inode *inode, struct file *file, static int mounts_release(struct inode *inode, struct file *file) { - struct proc_mounts *p = proc_mounts(file->private_data); + struct seq_file *m = file->private_data; + struct proc_mounts *p = m->private; path_put(&p->root); put_mnt_ns(p->ns); - return seq_release(inode, file); + return seq_release_private(inode, file); } static int mounts_open(struct inode *inode, struct file *file) -- cgit v1.2.3 From 189f9841de23a58ecb4b2602db8581512ff08ba4 Mon Sep 17 00:00:00 2001 From: Yann Droneaud Date: Tue, 30 Jun 2015 14:57:33 -0700 Subject: fs: allocate structure unconditionally in seq_open() Since patch described below, from v2.6.15-rc1, seq_open() could use a struct seq_file already allocated by the caller if the pointer to the structure is stored in file->private_data before calling the function. Commit 1abe77b0fc4b485927f1f798ae81a752677e1d05 Author: Al Viro Date: Mon Nov 7 17:15:34 2005 -0500 [PATCH] allow callers of seq_open do allocation themselves Allow caller of seq_open() to kmalloc() seq_file + whatever else they want and set ->private_data to it. seq_open() will then abstain from doing allocation itself. As there's no more use for such feature, as it could be easily replaced by calls to seq_open_private() (see commit 39699037a5c9 ("[FS] seq_file: Introduce the seq_open_private()")) and seq_release_private() (see v2.6.0-test3), support for this uncommon feature can be removed from seq_open(). Link: http://lkml.kernel.org/r/cover.1433193673.git.ydroneaud@opteya.com Signed-off-by: Yann Droneaud Cc: Al Viro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/seq_file.c | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) diff --git a/fs/seq_file.c b/fs/seq_file.c index 555f82155be8..5f163c6c821c 100644 --- a/fs/seq_file.c +++ b/fs/seq_file.c @@ -51,15 +51,16 @@ static void *seq_buf_alloc(unsigned long size) */ int seq_open(struct file *file, const struct seq_operations *op) { - struct seq_file *p = file->private_data; + struct seq_file *p; + + WARN_ON(file->private_data); + + p = kzalloc(sizeof(*p), GFP_KERNEL); + if (!p) + return -ENOMEM; + + file->private_data = p; - if (!p) { - p = kmalloc(sizeof(*p), GFP_KERNEL); - if (!p) - return -ENOMEM; - file->private_data = p; - } - memset(p, 0, sizeof(*p)); mutex_init(&p->lock); p->op = op; #ifdef CONFIG_USER_NS -- cgit v1.2.3 From 460b865e53c347ebf110e50d499718cd9b39d810 Mon Sep 17 00:00:00 2001 From: Yann Droneaud Date: Tue, 30 Jun 2015 14:57:36 -0700 Subject: fs: document seq_open()'s usage of file->private_data seq_open() stores its struct seq_file in file->private_data, thus it must not be modified by user of seq_file. Link: http://lkml.kernel.org/r/cover.1433193673.git.ydroneaud@opteya.com Signed-off-by: Yann Droneaud Cc: Al Viro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/seq_file.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/seq_file.c b/fs/seq_file.c index 5f163c6c821c..760e25dad985 100644 --- a/fs/seq_file.c +++ b/fs/seq_file.c @@ -48,6 +48,8 @@ static void *seq_buf_alloc(unsigned long size) * ERR_PTR(error). In the end of sequence they return %NULL. ->show() * returns 0 in case of success and negative number in case of error. * Returning SEQ_SKIP means "discard this element and move on". + * Note: seq_open() will allocate a struct seq_file and store its + * pointer in @file->private_data. This pointer should not be modified. */ int seq_open(struct file *file, const struct seq_operations *op) { -- cgit v1.2.3 From a846f47962e4643b33847c9a0b2b6387f02a93be Mon Sep 17 00:00:00 2001 From: KarimAllah Ahmed Date: Tue, 30 Jun 2015 14:57:39 -0700 Subject: x86/kexec: prepend elfcorehdr instead of appending it to the crash-kernel command-line. Any parameter passed after '--' in the kernel command-line will not be parsed by the kernel at all, instead it will be passed directly to init process. Currently the kernel appends elfcorehdr= to the cmdline passed from kexec load, and if this command-line is used to pass parameters to init process this means that 'elfcorehdr' will not be parsed as a kernel parameter at all which will be a problem for vmcore subsystem since it will know nothing about the location of the ELF structure! Prepending 'elfcorehdr' instead of appending it fixes this problem since it ensures that it always comes before '--' and so it's always parsed as a kernel command-line parameter. Even with this patch things can still go wrong if 'CONFIG_CMDLINE' was also used to embedd a command-line to the crash dump kernel and this command-line contains '--' since the current behavior of the kernel is to actually append the boot loader command-line to the embedded command-line. Signed-off-by: KarimAllah Ahmed Cc: Thomas Gleixner Cc: Ingo Molnar Cc: H. Peter Anvin Acked-by: Vivek Goyal Cc: Haren Myneni Cc: Eric Biederman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/kernel/kexec-bzimage64.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c index ca05f86481aa..ca83f7ac388b 100644 --- a/arch/x86/kernel/kexec-bzimage64.c +++ b/arch/x86/kernel/kexec-bzimage64.c @@ -72,15 +72,16 @@ static int setup_cmdline(struct kimage *image, struct boot_params *params, unsigned long cmdline_len) { char *cmdline_ptr = ((char *)params) + cmdline_offset; - unsigned long cmdline_ptr_phys, len; + unsigned long cmdline_ptr_phys, len = 0; uint32_t cmdline_low_32, cmdline_ext_32; - memcpy(cmdline_ptr, cmdline, cmdline_len); if (image->type == KEXEC_TYPE_CRASH) { - len = sprintf(cmdline_ptr + cmdline_len - 1, - " elfcorehdr=0x%lx", image->arch.elf_load_addr); - cmdline_len += len; + len = sprintf(cmdline_ptr, + "elfcorehdr=0x%lx ", image->arch.elf_load_addr); } + memcpy(cmdline_ptr + len, cmdline, cmdline_len); + cmdline_len += len; + cmdline_ptr[cmdline_len - 1] = '\0'; pr_debug("Final command line is: %s\n", cmdline_ptr); -- cgit v1.2.3 From f45d85ff1f3f13d5b67fecb291edc6a771db0c53 Mon Sep 17 00:00:00 2001 From: HATAYAMA Daisuke Date: Tue, 30 Jun 2015 14:57:43 -0700 Subject: kernel/panic: call the 2nd crash_kexec() only if crash_kexec_post_notifiers is enabled For compatibility with the behaviour before the commit f06e5153f4ae2e ("kernel/panic.c: add "crash_kexec_post_notifiers" option for kdump after panic_notifers"), the 2nd crash_kexec() should be called only if crash_kexec_post_notifiers is enabled. Note that crash_kexec() returns immediately if kdump crash kernel is not loaded, so in this case, this patch makes no functionality change, but the point is to make it explicit, from the caller panic() side, that the 2nd crash_kexec() does nothing. Signed-off-by: HATAYAMA Daisuke Suggested-by: Ingo Molnar Cc: "Eric W. Biederman" Cc: Vivek Goyal Cc: Masami Hiramatsu Cc: Hidehiro Kawai Cc: Baoquan He Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/panic.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/kernel/panic.c b/kernel/panic.c index 8136ad76e5fd..774614f72cbd 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -142,7 +142,8 @@ void panic(const char *fmt, ...) * Note: since some panic_notifiers can make crashed kernel * more unstable, it can increase risks of the kdump failure too. */ - crash_kexec(NULL); + if (crash_kexec_post_notifiers) + crash_kexec(NULL); bust_spinlocks(0); -- cgit v1.2.3 From 5375b708f2547f70cd2bee2fd8663ab7035f9551 Mon Sep 17 00:00:00 2001 From: HATAYAMA Daisuke Date: Tue, 30 Jun 2015 14:57:46 -0700 Subject: kernel/panic/kexec: fix "crash_kexec_post_notifiers" option issue in oops path Commit f06e5153f4ae2e ("kernel/panic.c: add "crash_kexec_post_notifiers" option for kdump after panic_notifers") introduced "crash_kexec_post_notifiers" kernel boot option, which toggles wheather panic() calls crash_kexec() before panic_notifiers and dump kmsg or after. The problem is that the commit overlooks panic_on_oops kernel boot option. If it is enabled, crash_kexec() is called directly without going through panic() in oops path. To fix this issue, this patch adds a check to "crash_kexec_post_notifiers" in the condition of kexec_should_crash(). Also, put a comment in kexec_should_crash() to explain not obvious things on this patch. Signed-off-by: HATAYAMA Daisuke Acked-by: Baoquan He Tested-by: Hidehiro Kawai Reviewed-by: Masami Hiramatsu Cc: Vivek Goyal Cc: Ingo Molnar Cc: Hidehiro Kawai Cc: Baoquan He Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 3 +++ kernel/kexec.c | 11 +++++++++++ kernel/panic.c | 2 +- 3 files changed, 15 insertions(+), 1 deletion(-) diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 5acf5b70866d..0dfa4e31563d 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -439,6 +439,9 @@ extern int panic_on_unrecovered_nmi; extern int panic_on_io_nmi; extern int panic_on_warn; extern int sysctl_panic_on_stackoverflow; + +extern bool crash_kexec_post_notifiers; + /* * Only to be used by arch init code. If the user over-wrote the default * CONFIG_PANIC_TIMEOUT, honor it. diff --git a/kernel/kexec.c b/kernel/kexec.c index 7a36fdcca5bf..a785c1015e25 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -84,6 +84,17 @@ struct resource crashk_low_res = { int kexec_should_crash(struct task_struct *p) { + /* + * If crash_kexec_post_notifiers is enabled, don't run + * crash_kexec() here yet, which must be run after panic + * notifiers in panic(). + */ + if (crash_kexec_post_notifiers) + return 0; + /* + * There are 4 panic() calls in do_exit() path, each of which + * corresponds to each of these 4 conditions. + */ if (in_interrupt() || !p->pid || is_global_init(p) || panic_on_oops) return 1; return 0; diff --git a/kernel/panic.c b/kernel/panic.c index 774614f72cbd..04e91ff7560b 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -32,7 +32,7 @@ static unsigned long tainted_mask; static int pause_on_oops; static int pause_on_oops_flag; static DEFINE_SPINLOCK(pause_on_oops_lock); -static bool crash_kexec_post_notifiers; +bool crash_kexec_post_notifiers; int panic_on_warn __read_mostly; int panic_timeout = CONFIG_PANIC_TIMEOUT; -- cgit v1.2.3 From 3e44c471a2dab210f7e9b1e5f7d4d54d52df59eb Mon Sep 17 00:00:00 2001 From: Lorenzo Stoakes Date: Tue, 30 Jun 2015 14:57:49 -0700 Subject: gcov: add support for GCC 5.1 Fix kernel gcov support for GCC 5.1. Similar to commit a992bf836f9 ("gcov: add support for GCC 4.9"), this patch takes into account the existence of a new gcov counter (see gcc's gcc/gcov-counter.def.) Firstly, it increments GCOV_COUNTERS (to 10), which makes the data structure struct gcov_info compatible with GCC 5.1. Secondly, a corresponding counter function __gcov_merge_icall_topn (Top N value tracking for indirect calls) is included in base.c with the other gcov counters unused for kernel profiling. Signed-off-by: Lorenzo Stoakes Cc: Andrey Ryabinin Cc: Yuan Pengfei Tested-by: Peter Oberparleiter Reviewed-by: Peter Oberparleiter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/gcov/base.c | 6 ++++++ kernel/gcov/gcc_4_7.c | 4 +++- 2 files changed, 9 insertions(+), 1 deletion(-) diff --git a/kernel/gcov/base.c b/kernel/gcov/base.c index a744098e4eb7..7080ae1eb6c1 100644 --- a/kernel/gcov/base.c +++ b/kernel/gcov/base.c @@ -92,6 +92,12 @@ void __gcov_merge_time_profile(gcov_type *counters, unsigned int n_counters) } EXPORT_SYMBOL(__gcov_merge_time_profile); +void __gcov_merge_icall_topn(gcov_type *counters, unsigned int n_counters) +{ + /* Unused. */ +} +EXPORT_SYMBOL(__gcov_merge_icall_topn); + /** * gcov_enable_events - enable event reporting through gcov_event() * diff --git a/kernel/gcov/gcc_4_7.c b/kernel/gcov/gcc_4_7.c index 826ba9fb5e32..e25e92fb44fa 100644 --- a/kernel/gcov/gcc_4_7.c +++ b/kernel/gcov/gcc_4_7.c @@ -18,7 +18,9 @@ #include #include "gcov.h" -#if __GNUC__ == 4 && __GNUC_MINOR__ >= 9 +#if __GNUC__ == 5 && __GNUC_MINOR__ >= 1 +#define GCOV_COUNTERS 10 +#elif __GNUC__ == 4 && __GNUC_MINOR__ >= 9 #define GCOV_COUNTERS 9 #else #define GCOV_COUNTERS 8 -- cgit v1.2.3 From d96f184532e9a9bff6cf41af1254edeffa29ff90 Mon Sep 17 00:00:00 2001 From: Firo Yang Date: Tue, 30 Jun 2015 14:57:52 -0700 Subject: fs/adfs: remove unneeded cast kmem_cache_alloc() returns void*. Signed-off-by: Firo Yang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/adfs/super.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/adfs/super.c b/fs/adfs/super.c index a19c31d3f369..4d4a0df8344f 100644 --- a/fs/adfs/super.c +++ b/fs/adfs/super.c @@ -242,7 +242,7 @@ static struct kmem_cache *adfs_inode_cachep; static struct inode *adfs_alloc_inode(struct super_block *sb) { struct adfs_inode_info *ei; - ei = (struct adfs_inode_info *)kmem_cache_alloc(adfs_inode_cachep, GFP_KERNEL); + ei = kmem_cache_alloc(adfs_inode_cachep, GFP_KERNEL); if (!ei) return NULL; return &ei->vfs_inode; -- cgit v1.2.3 From 78f444f6736ed9a264fc3e801ca620daee4d5d9f Mon Sep 17 00:00:00 2001 From: Fabian Frederick Date: Tue, 30 Jun 2015 14:57:55 -0700 Subject: fs/affs/inode.c: remove unneeded initialization bh is initialized unconditionally in affs_add_entry() Signed-off-by: Fabian Frederick Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/affs/inode.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/affs/inode.c b/fs/affs/inode.c index a022f4accd76..17349500592d 100644 --- a/fs/affs/inode.c +++ b/fs/affs/inode.c @@ -346,7 +346,7 @@ affs_add_entry(struct inode *dir, struct inode *inode, struct dentry *dentry, s3 { struct super_block *sb = dir->i_sb; struct buffer_head *inode_bh = NULL; - struct buffer_head *bh = NULL; + struct buffer_head *bh; u32 block = 0; int retval; -- cgit v1.2.3 From 4709187ef2412419bea366bebc0a541dbd620b3c Mon Sep 17 00:00:00 2001 From: Fabian Frederick Date: Tue, 30 Jun 2015 14:57:58 -0700 Subject: fs/affs/amigaffs.c: remove unneeded initialization bh is initialized unconditionally in affs_remove_link() Signed-off-by: Fabian Frederick Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/affs/amigaffs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/affs/amigaffs.c b/fs/affs/amigaffs.c index a8f463c028ce..5fa92bc790ef 100644 --- a/fs/affs/amigaffs.c +++ b/fs/affs/amigaffs.c @@ -140,7 +140,7 @@ affs_remove_link(struct dentry *dentry) { struct inode *dir, *inode = d_inode(dentry); struct super_block *sb = inode->i_sb; - struct buffer_head *bh = NULL, *link_bh = NULL; + struct buffer_head *bh, *link_bh = NULL; u32 link_ino, ino; int retval; -- cgit v1.2.3 From 196a4f82bddb2c4cb23736c5d467abcb9e716c63 Mon Sep 17 00:00:00 2001 From: Fabian Frederick Date: Tue, 30 Jun 2015 14:58:01 -0700 Subject: fs/affs/symlink.c: remove unneeded err variable err is only assigned to -EIO. Return that value at the end of fail context. Signed-off-by: Fabian Frederick Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/affs/symlink.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/fs/affs/symlink.c b/fs/affs/symlink.c index f39b71c3981e..ea5b69a18ba9 100644 --- a/fs/affs/symlink.c +++ b/fs/affs/symlink.c @@ -16,14 +16,12 @@ static int affs_symlink_readpage(struct file *file, struct page *page) struct inode *inode = page->mapping->host; char *link = kmap(page); struct slink_front *lf; - int err; int i, j; char c; char lc; pr_debug("follow_link(ino=%lu)\n", inode->i_ino); - err = -EIO; bh = affs_bread(inode->i_sb, inode->i_ino); if (!bh) goto fail; @@ -66,7 +64,7 @@ fail: SetPageError(page); kunmap(page); unlock_page(page); - return err; + return -EIO; } const struct address_space_operations affs_symlink_aops = { -- cgit v1.2.3 From 43abdbcecea0673fa7f2f04422b57765935b2d5b Mon Sep 17 00:00:00 2001 From: Quentin Lambert Date: Tue, 30 Jun 2015 14:58:04 -0700 Subject: memstick: remove deprecated use of pci api Replace occurences of the pci api by appropriate call to the dma api. A simplified version of the semantic patch that finds this problem is as follows: (http://coccinelle.lip6.fr) @deprecated@ idexpression id; position p; @@ ( pci_dma_supported@p ( id, ...) | pci_alloc_consistent@p ( id, ...) ) @bad1@ idexpression id; position deprecated.p; @@ ...when != &id->dev when != pci_get_drvdata ( id ) when != pci_enable_device ( id ) ( pci_dma_supported@p ( id, ...) | pci_alloc_consistent@p ( id, ...) ) @depends on !bad1@ idexpression id; expression direction; position deprecated.p; @@ ( - pci_dma_supported@p ( id, + dma_supported ( &id->dev, ... + , GFP_ATOMIC ) | - pci_alloc_consistent@p ( id, + dma_alloc_coherent ( &id->dev, ... + , GFP_ATOMIC ) ) Signed-off-by: Quentin Lambert Cc: Maxim Levitsky Cc: Greg KH Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/memstick/host/jmb38x_ms.c | 12 ++++++------ drivers/memstick/host/r592.c | 10 +++++----- 2 files changed, 11 insertions(+), 11 deletions(-) diff --git a/drivers/memstick/host/jmb38x_ms.c b/drivers/memstick/host/jmb38x_ms.c index aeabaa5aedf7..48db922075e2 100644 --- a/drivers/memstick/host/jmb38x_ms.c +++ b/drivers/memstick/host/jmb38x_ms.c @@ -419,10 +419,10 @@ static int jmb38x_ms_issue_cmd(struct memstick_host *msh) } if (host->cmd_flags & DMA_DATA) { - if (1 != pci_map_sg(host->chip->pdev, &host->req->sg, 1, + if (1 != dma_map_sg(&host->chip->pdev->dev, &host->req->sg, 1, host->req->data_dir == READ - ? PCI_DMA_FROMDEVICE - : PCI_DMA_TODEVICE)) { + ? DMA_FROM_DEVICE + : DMA_TO_DEVICE)) { host->req->error = -ENOMEM; return host->req->error; } @@ -487,9 +487,9 @@ static void jmb38x_ms_complete_cmd(struct memstick_host *msh, int last) writel(0, host->addr + DMA_CONTROL); if (host->cmd_flags & DMA_DATA) { - pci_unmap_sg(host->chip->pdev, &host->req->sg, 1, + dma_unmap_sg(&host->chip->pdev->dev, &host->req->sg, 1, host->req->data_dir == READ - ? PCI_DMA_FROMDEVICE : PCI_DMA_TODEVICE); + ? DMA_FROM_DEVICE : DMA_TO_DEVICE); } else { t_val = readl(host->addr + INT_STATUS_ENABLE); if (host->req->data_dir == READ) @@ -925,7 +925,7 @@ static int jmb38x_ms_probe(struct pci_dev *pdev, int pci_dev_busy = 0; int rc, cnt; - rc = pci_set_dma_mask(pdev, DMA_BIT_MASK(32)); + rc = dma_set_mask(&pdev->dev, DMA_BIT_MASK(32)); if (rc) return rc; diff --git a/drivers/memstick/host/r592.c b/drivers/memstick/host/r592.c index e2a4f5f415b2..ef09ba0289d7 100644 --- a/drivers/memstick/host/r592.c +++ b/drivers/memstick/host/r592.c @@ -754,7 +754,7 @@ static int r592_probe(struct pci_dev *pdev, const struct pci_device_id *id) goto error2; pci_set_master(pdev); - error = pci_set_dma_mask(pdev, DMA_BIT_MASK(32)); + error = dma_set_mask(&pdev->dev, DMA_BIT_MASK(32)); if (error) goto error3; @@ -787,8 +787,8 @@ static int r592_probe(struct pci_dev *pdev, const struct pci_device_id *id) } /* This is just a precation, so don't fail */ - dev->dummy_dma_page = pci_alloc_consistent(pdev, PAGE_SIZE, - &dev->dummy_dma_page_physical_address); + dev->dummy_dma_page = dma_alloc_coherent(&pdev->dev, PAGE_SIZE, + &dev->dummy_dma_page_physical_address, GFP_KERNEL); r592_stop_dma(dev , 0); if (request_irq(dev->irq, &r592_irq, IRQF_SHARED, @@ -805,7 +805,7 @@ error7: free_irq(dev->irq, dev); error6: if (dev->dummy_dma_page) - pci_free_consistent(pdev, PAGE_SIZE, dev->dummy_dma_page, + dma_free_coherent(&pdev->dev, PAGE_SIZE, dev->dummy_dma_page, dev->dummy_dma_page_physical_address); kthread_stop(dev->io_thread); @@ -845,7 +845,7 @@ static void r592_remove(struct pci_dev *pdev) memstick_free_host(dev->host); if (dev->dummy_dma_page) - pci_free_consistent(pdev, PAGE_SIZE, dev->dummy_dma_page, + dma_free_coherent(&pdev->dev, PAGE_SIZE, dev->dummy_dma_page, dev->dummy_dma_page_physical_address); } -- cgit v1.2.3 From 084f6b1ec65170c2f8e38688bc83ff15b9a963e0 Mon Sep 17 00:00:00 2001 From: Thiébaud Weksteen Date: Tue, 30 Jun 2015 14:58:07 -0700 Subject: scripts/gdb: add command to check list consistency Add a gdb script to verify the consistency of lists. Signed-off-by: Thiébaud Weksteen Signed-off-by: Jan Kiszka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- scripts/gdb/linux/lists.py | 89 ++++++++++++++++++++++++++++++++++++++++++++++ scripts/gdb/vmlinux-gdb.py | 1 + 2 files changed, 90 insertions(+) create mode 100644 scripts/gdb/linux/lists.py diff --git a/scripts/gdb/linux/lists.py b/scripts/gdb/linux/lists.py new file mode 100644 index 000000000000..2a94b5462d06 --- /dev/null +++ b/scripts/gdb/linux/lists.py @@ -0,0 +1,89 @@ +# +# gdb helper commands and functions for Linux kernel debugging +# +# list tools +# +# Copyright (c) Thiebaud Weksteen, 2015 +# +# Authors: +# Thiebaud Weksteen +# +# This work is licensed under the terms of the GNU GPL version 2. +# + +import gdb + +from linux import utils + +list_head = utils.CachedType("struct list_head") + + +def list_check(head): + nb = 0 + c = head + if (c.type != list_head.get_type()): + raise gdb.GdbError('The argument should be of type (struct list_head)') + try: + gdb.write("Starting with: {}\n".format(c)) + except gdb.MemoryError: + gdb.write('head is not accessible\n') + return + while True: + p = c['prev'].dereference() + n = c['next'].dereference() + try: + if p['next'] != c.address: + gdb.write('prev.next != current: ' + 'current@{current_addr}={current} ' + 'prev@{p_addr}={p}\n'.format( + current_addr=c.address, + current=c, + p_addr=p.address, + p=p, + )) + return + except gdb.MemoryError: + gdb.write('prev is not accessible: ' + 'current@{current_addr}={current}\n'.format( + current_addr=c.address, + current=c + )) + return + try: + if n['prev'] != c.address: + gdb.write('next.prev != current: ' + 'current@{current_addr}={current} ' + 'next@{n_addr}={n}\n'.format( + current_addr=c.address, + current=c, + n_addr=n.address, + n=n, + )) + return + except gdb.MemoryError: + gdb.write('next is not accessible: ' + 'current@{current_addr}={current}\n'.format( + current_addr=c.address, + current=c + )) + return + c = n + nb += 1 + if c == head: + gdb.write("list is consistent: {} node(s)\n".format(nb)) + return + + +class LxListChk(gdb.Command): + """Verify a list consistency""" + + def __init__(self): + super(LxListChk, self).__init__("lx-list-check", gdb.COMMAND_DATA) + + def invoke(self, arg, from_tty): + argv = gdb.string_to_argv(arg) + if len(argv) != 1: + raise gdb.GdbError("lx-list-check takes one argument") + list_check(gdb.parse_and_eval(argv[0])) + +LxListChk() diff --git a/scripts/gdb/vmlinux-gdb.py b/scripts/gdb/vmlinux-gdb.py index 48489285f119..ce82bf5c3943 100644 --- a/scripts/gdb/vmlinux-gdb.py +++ b/scripts/gdb/vmlinux-gdb.py @@ -28,3 +28,4 @@ else: import linux.dmesg import linux.tasks import linux.cpus + import linux.lists -- cgit v1.2.3 From 433296b32b39bd2f8a8717ccb2385b4c8654017d Mon Sep 17 00:00:00 2001 From: Jan Kiszka Date: Tue, 30 Jun 2015 14:58:10 -0700 Subject: scripts/gdb: also allow list_head pointer as lx-list-check paramter This makes the usage more flexible. Signed-off-by: Jan Kiszka Cc: Thiébaud Weksteen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- scripts/gdb/linux/lists.py | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/scripts/gdb/linux/lists.py b/scripts/gdb/linux/lists.py index 2a94b5462d06..71fba6afcb55 100644 --- a/scripts/gdb/linux/lists.py +++ b/scripts/gdb/linux/lists.py @@ -20,9 +20,11 @@ list_head = utils.CachedType("struct list_head") def list_check(head): nb = 0 + if (head.type == list_head.get_type().pointer()): + head = head.dereference() + elif (head.type != list_head.get_type()): + raise gdb.GdbError('argument must be of type (struct list_head [*])') c = head - if (c.type != list_head.get_type()): - raise gdb.GdbError('The argument should be of type (struct list_head)') try: gdb.write("Starting with: {}\n".format(c)) except gdb.MemoryError: -- cgit v1.2.3 From 3328bc9ee47fbf2e35d146bed0d41cff1c68e8f3 Mon Sep 17 00:00:00 2001 From: Jan Kiszka Date: Tue, 30 Jun 2015 14:58:13 -0700 Subject: scripts/gdb: enable completion for lx-list-check parameter Signed-off-by: Jan Kiszka Cc: Thiébaud Weksteen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- scripts/gdb/linux/lists.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/scripts/gdb/linux/lists.py b/scripts/gdb/linux/lists.py index 71fba6afcb55..3a3775bc162b 100644 --- a/scripts/gdb/linux/lists.py +++ b/scripts/gdb/linux/lists.py @@ -80,7 +80,8 @@ class LxListChk(gdb.Command): """Verify a list consistency""" def __init__(self): - super(LxListChk, self).__init__("lx-list-check", gdb.COMMAND_DATA) + super(LxListChk, self).__init__("lx-list-check", gdb.COMMAND_DATA, + gdb.COMPLETE_EXPRESSION) def invoke(self, arg, from_tty): argv = gdb.string_to_argv(arg) -- cgit v1.2.3 From a2e73c480494101f5f6932b6904acb15c44180ee Mon Sep 17 00:00:00 2001 From: Thiébaud Weksteen Date: Tue, 30 Jun 2015 14:58:16 -0700 Subject: scripts/gdb: fix typo in exception name Signed-off-by: Thiébaud Weksteen Signed-off-by: Jan Kiszka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- scripts/gdb/linux/utils.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/scripts/gdb/linux/utils.py b/scripts/gdb/linux/utils.py index 128c306db3ee..d7ff3a39b672 100644 --- a/scripts/gdb/linux/utils.py +++ b/scripts/gdb/linux/utils.py @@ -83,7 +83,7 @@ def get_target_endianness(): elif "big endian" in endian: target_endianness = BIG_ENDIAN else: - raise gdb.GdgError("unknown endianness '{0}'".format(str(endian))) + raise gdb.GdbError("unknown endianness '{0}'".format(str(endian))) return target_endianness -- cgit v1.2.3 From 6ad18b73317714e7d0fad08ee78365ecc817e923 Mon Sep 17 00:00:00 2001 From: Thiébaud Weksteen Date: Tue, 30 Jun 2015 14:58:18 -0700 Subject: scripts/gdb: fix PEP8 compliance Signed-off-by: Thiébaud Weksteen Signed-off-by: Jan Kiszka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- scripts/gdb/linux/dmesg.py | 1 - scripts/gdb/linux/symbols.py | 9 ++++----- scripts/gdb/linux/tasks.py | 2 ++ scripts/gdb/linux/utils.py | 2 +- 4 files changed, 7 insertions(+), 7 deletions(-) diff --git a/scripts/gdb/linux/dmesg.py b/scripts/gdb/linux/dmesg.py index 3c947f0c5dad..927d0d2a3145 100644 --- a/scripts/gdb/linux/dmesg.py +++ b/scripts/gdb/linux/dmesg.py @@ -12,7 +12,6 @@ # import gdb -import string from linux import utils diff --git a/scripts/gdb/linux/symbols.py b/scripts/gdb/linux/symbols.py index cd5bea965d4e..627750cb420d 100644 --- a/scripts/gdb/linux/symbols.py +++ b/scripts/gdb/linux/symbols.py @@ -14,9 +14,8 @@ import gdb import os import re -import string -from linux import modules, utils +from linux import modules if hasattr(gdb, 'Breakpoint'): @@ -97,7 +96,7 @@ lx-symbols command.""" return "" attrs = sect_attrs['attrs'] section_name_to_address = { - attrs[n]['name'].string() : attrs[n]['address'] + attrs[n]['name'].string(): attrs[n]['address'] for n in range(int(sect_attrs['nsections']))} args = [] for section_name in [".data", ".data..read_mostly", ".rodata", ".bss"]: @@ -124,7 +123,7 @@ lx-symbols command.""" addr=module_addr, sections=self._section_arguments(module)) gdb.execute(cmdline, to_string=True) - if not module_name in self.loaded_modules: + if module_name not in self.loaded_modules: self.loaded_modules.append(module_name) else: gdb.write("no module object found for '{0}'\n".format(module_name)) @@ -164,7 +163,7 @@ lx-symbols command.""" self.load_all_symbols() if hasattr(gdb, 'Breakpoint'): - if not self.breakpoint is None: + if self.breakpoint is not None: self.breakpoint.delete() self.breakpoint = None self.breakpoint = LoadModuleBreakpoint( diff --git a/scripts/gdb/linux/tasks.py b/scripts/gdb/linux/tasks.py index e2037d9bb7eb..89d38e1580e3 100644 --- a/scripts/gdb/linux/tasks.py +++ b/scripts/gdb/linux/tasks.py @@ -18,6 +18,7 @@ from linux import utils task_type = utils.CachedType("struct task_struct") + def task_lists(): global task_type task_ptr_type = task_type.get_type().pointer() @@ -38,6 +39,7 @@ def task_lists(): if t == init_task: return + def get_task_by_pid(pid): for task in task_lists(): if int(task['pid']) == pid: diff --git a/scripts/gdb/linux/utils.py b/scripts/gdb/linux/utils.py index d7ff3a39b672..0893b326a28b 100644 --- a/scripts/gdb/linux/utils.py +++ b/scripts/gdb/linux/utils.py @@ -151,6 +151,6 @@ def get_gdbserver_type(): gdbserver_type = GDBSERVER_QEMU elif probe_kgdb(): gdbserver_type = GDBSERVER_KGDB - if not gdbserver_type is None and hasattr(gdb, 'events'): + if gdbserver_type is not None and hasattr(gdb, 'events'): gdb.events.exited.connect(exit_handler) return gdbserver_type -- cgit v1.2.3 From a930850b628497601309513dc894ea23218a19fa Mon Sep 17 00:00:00 2001 From: Thiébaud Weksteen Date: Tue, 30 Jun 2015 14:58:21 -0700 Subject: scripts/gdb: add ps command Signed-off-by: Thiébaud Weksteen Signed-off-by: Jan Kiszka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- scripts/gdb/linux/tasks.py | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/scripts/gdb/linux/tasks.py b/scripts/gdb/linux/tasks.py index 89d38e1580e3..3191f4792398 100644 --- a/scripts/gdb/linux/tasks.py +++ b/scripts/gdb/linux/tasks.py @@ -67,6 +67,22 @@ return that task_struct variable which PID matches.""" LxTaskByPidFunc() +class LxPs(gdb.Command): + """Dump Linux tasks.""" + + def __init__(self): + super(LxPs, self).__init__("lx-ps", gdb.COMMAND_DATA) + + def invoke(self, arg, from_tty): + for task in task_lists(): + gdb.write("{address} {pid} {comm}\n".format( + address=task, + pid=task["pid"], + comm=task["comm"].string())) + +LxPs() + + thread_info_type = utils.CachedType("struct thread_info") ia64_task_size = None -- cgit v1.2.3 From 15f1d827810e085496eb7ae82aa3ed2dba9901cc Mon Sep 17 00:00:00 2001 From: Thiébaud Weksteen Date: Tue, 30 Jun 2015 14:58:24 -0700 Subject: scripts/gdb: remove useless global instruction Signed-off-by: Thiébaud Weksteen Signed-off-by: Jan Kiszka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- scripts/gdb/linux/tasks.py | 2 -- 1 file changed, 2 deletions(-) diff --git a/scripts/gdb/linux/tasks.py b/scripts/gdb/linux/tasks.py index 3191f4792398..862a4ae24d49 100644 --- a/scripts/gdb/linux/tasks.py +++ b/scripts/gdb/linux/tasks.py @@ -20,7 +20,6 @@ task_type = utils.CachedType("struct task_struct") def task_lists(): - global task_type task_ptr_type = task_type.get_type().pointer() init_task = gdb.parse_and_eval("init_task").address t = g = init_task @@ -89,7 +88,6 @@ ia64_task_size = None def get_thread_info(task): - global thread_info_type thread_info_ptr_type = thread_info_type.get_type().pointer() if utils.is_target_arch("ia64"): global ia64_task_size -- cgit v1.2.3 From 9ce71148b027e2bd27016139cae1c39401587695 Mon Sep 17 00:00:00 2001 From: Josh Triplett Date: Tue, 30 Jun 2015 14:58:27 -0700 Subject: devpts: if initialization failed, don't crash when opening /dev/ptmx If devpts failed to initialize, it would store an ERR_PTR in the global devpts_mnt. A subsequent open of /dev/ptmx would call devpts_new_index, which would dereference devpts_mnt and crash. Avoid storing invalid values in devpts_mnt; leave it NULL instead. Make both devpts_new_index and devpts_pty_new fail gracefully with ENODEV in that case, which then becomes the return value to the userspace open call on /dev/ptmx. [akpm@linux-foundation.org: remove unneeded static] Signed-off-by: Josh Triplett Reported-by: Fengguang Wu Reviewed-by: Peter Hurley Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/devpts/inode.c | 31 ++++++++++++++++++++++++------- 1 file changed, 24 insertions(+), 7 deletions(-) diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c index add566303c68..c35ffdc12bba 100644 --- a/fs/devpts/inode.c +++ b/fs/devpts/inode.c @@ -142,6 +142,8 @@ static inline struct super_block *pts_sb_from_inode(struct inode *inode) if (inode->i_sb->s_magic == DEVPTS_SUPER_MAGIC) return inode->i_sb; #endif + if (!devpts_mnt) + return NULL; return devpts_mnt->mnt_sb; } @@ -525,10 +527,14 @@ static struct file_system_type devpts_fs_type = { int devpts_new_index(struct inode *ptmx_inode) { struct super_block *sb = pts_sb_from_inode(ptmx_inode); - struct pts_fs_info *fsi = DEVPTS_SB(sb); + struct pts_fs_info *fsi; int index; int ida_ret; + if (!sb) + return -ENODEV; + + fsi = DEVPTS_SB(sb); retry: if (!ida_pre_get(&fsi->allocated_ptys, GFP_KERNEL)) return -ENOMEM; @@ -584,11 +590,18 @@ struct inode *devpts_pty_new(struct inode *ptmx_inode, dev_t device, int index, struct dentry *dentry; struct super_block *sb = pts_sb_from_inode(ptmx_inode); struct inode *inode; - struct dentry *root = sb->s_root; - struct pts_fs_info *fsi = DEVPTS_SB(sb); - struct pts_mount_opts *opts = &fsi->mount_opts; + struct dentry *root; + struct pts_fs_info *fsi; + struct pts_mount_opts *opts; char s[12]; + if (!sb) + return ERR_PTR(-ENODEV); + + root = sb->s_root; + fsi = DEVPTS_SB(sb); + opts = &fsi->mount_opts; + inode = new_inode(sb); if (!inode) return ERR_PTR(-ENOMEM); @@ -676,12 +689,16 @@ static int __init init_devpts_fs(void) struct ctl_table_header *table; if (!err) { + struct vfsmount *mnt; + table = register_sysctl_table(pty_root_table); - devpts_mnt = kern_mount(&devpts_fs_type); - if (IS_ERR(devpts_mnt)) { - err = PTR_ERR(devpts_mnt); + mnt = kern_mount(&devpts_fs_type); + if (IS_ERR(mnt)) { + err = PTR_ERR(mnt); unregister_filesystem(&devpts_fs_type); unregister_sysctl_table(table); + } else { + devpts_mnt = mnt; } } return err; -- cgit v1.2.3 From 92ed932d3081e494a6c61d22c093af100a313034 Mon Sep 17 00:00:00 2001 From: Akinobu Mita Date: Tue, 30 Jun 2015 14:58:30 -0700 Subject: arc: use for_each_sg() This replaces the plain loop over the sglist array with for_each_sg() macro which consists of sg_next() function calls. Since arc doesn't select ARCH_HAS_SG_CHAIN, it is not necessary to use for_each_sg() in order to loop over each sg element. But this can help find problems with drivers that do not properly initialize their sg tables when CONFIG_DEBUG_SG is enabled. Signed-off-by: Akinobu Mita Acked-by: Vineet Gupta Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arc/include/asm/dma-mapping.h | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/arch/arc/include/asm/dma-mapping.h b/arch/arc/include/asm/dma-mapping.h index 45b8e0cea176..f787894613ad 100644 --- a/arch/arc/include/asm/dma-mapping.h +++ b/arch/arc/include/asm/dma-mapping.h @@ -178,22 +178,24 @@ dma_sync_single_range_for_device(struct device *dev, dma_addr_t dma_handle, } static inline void -dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, int nelems, +dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sglist, int nelems, enum dma_data_direction dir) { int i; + struct scatterlist *sg; - for (i = 0; i < nelems; i++, sg++) + for_each_sg(sglist, sg, nelems, i) _dma_cache_sync((unsigned int)sg_virt(sg), sg->length, dir); } static inline void -dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, int nelems, - enum dma_data_direction dir) +dma_sync_sg_for_device(struct device *dev, struct scatterlist *sglist, + int nelems, enum dma_data_direction dir) { int i; + struct scatterlist *sg; - for (i = 0; i < nelems; i++, sg++) + for_each_sg(sglist, sg, nelems, i) _dma_cache_sync((unsigned int)sg_virt(sg), sg->length, dir); } -- cgit v1.2.3 From c859aa83113dcad165d986e66aa21c5b73745f42 Mon Sep 17 00:00:00 2001 From: Pekka Enberg Date: Tue, 30 Jun 2015 14:58:33 -0700 Subject: ipc/util.c: use kvfree() in ipc_rcu_free() Use kvfree() instead of open-coding it. Signed-off-by: Pekka Enberg Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- ipc/util.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/ipc/util.c b/ipc/util.c index ff3323ef8d8b..537a41c7f633 100644 --- a/ipc/util.c +++ b/ipc/util.c @@ -467,10 +467,7 @@ void ipc_rcu_free(struct rcu_head *head) { struct ipc_rcu *p = container_of(head, struct ipc_rcu, rcu); - if (is_vmalloc_addr(p)) - vfree(p); - else - kfree(p); + kvfree(p); } /** -- cgit v1.2.3 From c5c8975b2eb4eb7604e8ce4f762987f56d2a96a2 Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Tue, 30 Jun 2015 14:58:36 -0700 Subject: ipc,shm: move BUG_ON check into shm_lock Upon every shm_lock call, we BUG_ON if an error was returned, indicating racing either in idr or in shm_destroy. Move this logic into the locking. [akpm@linux-foundation.org: simplify code] Signed-off-by: Davidlohr Bueso Cc: Manfred Spraul Cc: Davidlohr Bueso Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- ipc/shm.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/ipc/shm.c b/ipc/shm.c index 6d767071c367..bd9c91f433c1 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -155,8 +155,11 @@ static inline struct shmid_kernel *shm_lock(struct ipc_namespace *ns, int id) { struct kern_ipc_perm *ipcp = ipc_lock(&shm_ids(ns), id); - if (IS_ERR(ipcp)) - return (struct shmid_kernel *)ipcp; + /* + * We raced in the idr lookup or with shm_destroy(). Either way, the + * ID is busted. + */ + BUG_ON(IS_ERR(ipcp)); return container_of(ipcp, struct shmid_kernel, shm_perm); } @@ -191,7 +194,6 @@ static void shm_open(struct vm_area_struct *vma) struct shmid_kernel *shp; shp = shm_lock(sfd->ns, sfd->id); - BUG_ON(IS_ERR(shp)); shp->shm_atim = get_seconds(); shp->shm_lprid = task_tgid_vnr(current); shp->shm_nattch++; @@ -258,7 +260,6 @@ static void shm_close(struct vm_area_struct *vma) down_write(&shm_ids(ns).rwsem); /* remove from the list of attaches of the shm segment */ shp = shm_lock(ns, sfd->id); - BUG_ON(IS_ERR(shp)); shp->shm_lprid = task_tgid_vnr(current); shp->shm_dtim = get_seconds(); shp->shm_nattch--; @@ -1191,7 +1192,6 @@ out_fput: out_nattch: down_write(&shm_ids(ns).rwsem); shp = shm_lock(ns, shmid); - BUG_ON(IS_ERR(shp)); shp->shm_nattch--; if (shm_may_destroy(ns, shp)) shm_destroy(ns, shp); -- cgit v1.2.3 From ff35e5ef86fea1fa84eb7fdc939d0b1e3f1222bf Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Tue, 30 Jun 2015 14:58:39 -0700 Subject: ipc,msg: provide barrier pairings for lockless receive We currently use a full barrier on the sender side to to avoid receiver tasks disappearing on us while still performing on the sender side wakeup. We lack however, the proper CPU-CPU interactions pairing on the receiver side which busy-waits for the message. Similarly, we do not need a full smp_mb, and can relax the semantics for the writer and reader sides of the message. This is safe as we are only ordering loads and stores to r_msg. And in both smp_wmb and smp_rmb, there are no stores after the calls _anyway_. This obviously applies for pipelined_send and expunge_all, for EIRDM when destroying a queue. Signed-off-by: Davidlohr Bueso Cc: Manfred Spraul Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- ipc/msg.c | 48 ++++++++++++++++++++++++++++++++++++++---------- 1 file changed, 38 insertions(+), 10 deletions(-) diff --git a/ipc/msg.c b/ipc/msg.c index 2b6fdbb9e0e9..a9c3c519490a 100644 --- a/ipc/msg.c +++ b/ipc/msg.c @@ -196,7 +196,7 @@ static void expunge_all(struct msg_queue *msq, int res) * or dealing with -EAGAIN cases. See lockless receive part 1 * and 2 in do_msgrcv(). */ - smp_mb(); + smp_wmb(); /* barrier (B) */ msr->r_msg = ERR_PTR(res); } } @@ -580,7 +580,8 @@ static inline int pipelined_send(struct msg_queue *msq, struct msg_msg *msg) /* initialize pipelined send ordering */ msr->r_msg = NULL; wake_up_process(msr->r_tsk); - smp_mb(); /* see barrier comment below */ + /* barrier (B) see barrier comment below */ + smp_wmb(); msr->r_msg = ERR_PTR(-E2BIG); } else { msr->r_msg = NULL; @@ -589,11 +590,12 @@ static inline int pipelined_send(struct msg_queue *msq, struct msg_msg *msg) wake_up_process(msr->r_tsk); /* * Ensure that the wakeup is visible before - * setting r_msg, as the receiving end depends - * on it. See lockless receive part 1 and 2 in - * do_msgrcv(). + * setting r_msg, as the receiving can otherwise + * exit - once r_msg is set, the receiver can + * continue. See lockless receive part 1 and 2 + * in do_msgrcv(). Barrier (B). */ - smp_mb(); + smp_wmb(); msr->r_msg = msg; return 1; @@ -932,12 +934,38 @@ long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp, int msgfl /* Lockless receive, part 2: * Wait until pipelined_send or expunge_all are outside of * wake_up_process(). There is a race with exit(), see - * ipc/mqueue.c for the details. + * ipc/mqueue.c for the details. The correct serialization + * ensures that a receiver cannot continue without the wakeup + * being visibible _before_ setting r_msg: + * + * CPU 0 CPU 1 + * + * smp_rmb(); (A) <-- pair -. + * r_msg> | msr->r_msg = NULL; + * | wake_up_process(); + * `------> smp_wmb(); (B) + * msr->r_msg = msg; + * + * Where (A) orders the message value read and where (B) orders + * the write to the r_msg -- done in both pipelined_send and + * expunge_all. */ - msg = (struct msg_msg *)msr_d.r_msg; - while (msg == NULL) { - cpu_relax(); + for (;;) { + /* + * Pairs with writer barrier in pipelined_send + * or expunge_all. + */ + smp_rmb(); /* barrier (A) */ msg = (struct msg_msg *)msr_d.r_msg; + if (msg) + break; + + /* + * The cpu_relax() call is a compiler barrier + * which forces everything in this loop to be + * re-loaded. + */ + cpu_relax(); } /* Lockless receive, part 3: -- cgit v1.2.3 From 55b7ae50167efc9b1c4f8fb60a99478cd46a82f7 Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Tue, 30 Jun 2015 14:58:42 -0700 Subject: ipc: rename ipc_obtain_object ... to ipc_obtain_object_idr, which is more meaningful and makes the code slightly easier to follow. Signed-off-by: Davidlohr Bueso Cc: Manfred Spraul Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- ipc/msg.c | 2 +- ipc/sem.c | 4 ++-- ipc/shm.c | 2 +- ipc/util.c | 8 ++++---- ipc/util.h | 2 +- 5 files changed, 9 insertions(+), 9 deletions(-) diff --git a/ipc/msg.c b/ipc/msg.c index a9c3c519490a..66c4f567eb73 100644 --- a/ipc/msg.c +++ b/ipc/msg.c @@ -76,7 +76,7 @@ struct msg_sender { static inline struct msg_queue *msq_obtain_object(struct ipc_namespace *ns, int id) { - struct kern_ipc_perm *ipcp = ipc_obtain_object(&msg_ids(ns), id); + struct kern_ipc_perm *ipcp = ipc_obtain_object_idr(&msg_ids(ns), id); if (IS_ERR(ipcp)) return ERR_CAST(ipcp); diff --git a/ipc/sem.c b/ipc/sem.c index d1a6edd17eba..bc3d530cb23e 100644 --- a/ipc/sem.c +++ b/ipc/sem.c @@ -391,7 +391,7 @@ static inline struct sem_array *sem_obtain_lock(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp; struct sem_array *sma; - ipcp = ipc_obtain_object(&sem_ids(ns), id); + ipcp = ipc_obtain_object_idr(&sem_ids(ns), id); if (IS_ERR(ipcp)) return ERR_CAST(ipcp); @@ -410,7 +410,7 @@ static inline struct sem_array *sem_obtain_lock(struct ipc_namespace *ns, static inline struct sem_array *sem_obtain_object(struct ipc_namespace *ns, int id) { - struct kern_ipc_perm *ipcp = ipc_obtain_object(&sem_ids(ns), id); + struct kern_ipc_perm *ipcp = ipc_obtain_object_idr(&sem_ids(ns), id); if (IS_ERR(ipcp)) return ERR_CAST(ipcp); diff --git a/ipc/shm.c b/ipc/shm.c index bd9c91f433c1..06e5cf2fe019 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -129,7 +129,7 @@ void __init shm_init(void) static inline struct shmid_kernel *shm_obtain_object(struct ipc_namespace *ns, int id) { - struct kern_ipc_perm *ipcp = ipc_obtain_object(&shm_ids(ns), id); + struct kern_ipc_perm *ipcp = ipc_obtain_object_idr(&shm_ids(ns), id); if (IS_ERR(ipcp)) return ERR_CAST(ipcp); diff --git a/ipc/util.c b/ipc/util.c index 537a41c7f633..3fdfabfdd9c3 100644 --- a/ipc/util.c +++ b/ipc/util.c @@ -555,7 +555,7 @@ void ipc64_perm_to_ipc_perm(struct ipc64_perm *in, struct ipc_perm *out) * Call inside the RCU critical section. * The ipc object is *not* locked on exit. */ -struct kern_ipc_perm *ipc_obtain_object(struct ipc_ids *ids, int id) +struct kern_ipc_perm *ipc_obtain_object_idr(struct ipc_ids *ids, int id) { struct kern_ipc_perm *out; int lid = ipcid_to_idx(id); @@ -581,7 +581,7 @@ struct kern_ipc_perm *ipc_lock(struct ipc_ids *ids, int id) struct kern_ipc_perm *out; rcu_read_lock(); - out = ipc_obtain_object(ids, id); + out = ipc_obtain_object_idr(ids, id); if (IS_ERR(out)) goto err1; @@ -605,7 +605,7 @@ err1: * @ids: ipc identifier set * @id: ipc id to look for * - * Similar to ipc_obtain_object() but also checks + * Similar to ipc_obtain_object_idr() but also checks * the ipc object reference counter. * * Call inside the RCU critical section. @@ -613,7 +613,7 @@ err1: */ struct kern_ipc_perm *ipc_obtain_object_check(struct ipc_ids *ids, int id) { - struct kern_ipc_perm *out = ipc_obtain_object(ids, id); + struct kern_ipc_perm *out = ipc_obtain_object_idr(ids, id); if (IS_ERR(out)) goto out; diff --git a/ipc/util.h b/ipc/util.h index 1a5a0fcd099c..3a8a5a0eca62 100644 --- a/ipc/util.h +++ b/ipc/util.h @@ -132,7 +132,7 @@ void ipc_rcu_putref(void *ptr, void (*func)(struct rcu_head *head)); void ipc_rcu_free(struct rcu_head *head); struct kern_ipc_perm *ipc_lock(struct ipc_ids *, int); -struct kern_ipc_perm *ipc_obtain_object(struct ipc_ids *ids, int id); +struct kern_ipc_perm *ipc_obtain_object_idr(struct ipc_ids *ids, int id); void kernel_to_ipc64_perm(struct kern_ipc_perm *in, struct ipc64_perm *out); void ipc64_perm_to_ipc_perm(struct ipc64_perm *in, struct ipc_perm *out); -- cgit v1.2.3 From f8b5918495be32807c4f878de959540eb63a9b9f Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Tue, 30 Jun 2015 14:58:45 -0700 Subject: ipc,sysv: make return -EIDRM when racing with RMID consistent The ipc_lock helper is used by all forms of sysv ipc to acquire the ipc object's spinlock. Upon error (bogus identifier), we always return -EINVAL, whether the problem be in the idr path or because we raced with a task performing RMID. For the later, however, all ipc related manpages, state the that for: EIDRM points to a removed identifier. And return: EINVAL Invalid value, or unaligned, etc. Which (EINVAL) should only return once the ipc resource is deleted. For all types of ipc this is done immediately upon a RMID command. However, shared memory behaves slightly different as it can merely mark a segment for deletion, and delay the actual freeing until there are no more active consumers. Per shmctl(IPC_RMID) manpage: "" Mark the segment to be destroyed. The segment will only actually be destroyed after the last process detaches it (i.e., when the shm_nattch member of the associated structure shmid_ds is zero). "" Unlike ipc_lock, paths that behave "correctly", at least per the manpage, involve controlling the ipc resource via *ctl(), doing the exact same validity check as ipc_lock after right acquiring the spinlock: if (!ipc_valid_object()) { err = -EIDRM; goto out_unlock; } Thus make ipc_lock consistent with the rest of ipc code and return -EIDRM in ipc_lock when !ipc_valid_object(). Signed-off-by: Davidlohr Bueso Cc: Manfred Spraul Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- ipc/util.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/ipc/util.c b/ipc/util.c index 3fdfabfdd9c3..b99038699fee 100644 --- a/ipc/util.c +++ b/ipc/util.c @@ -583,19 +583,22 @@ struct kern_ipc_perm *ipc_lock(struct ipc_ids *ids, int id) rcu_read_lock(); out = ipc_obtain_object_idr(ids, id); if (IS_ERR(out)) - goto err1; + goto err; spin_lock(&out->lock); - /* ipc_rmid() may have already freed the ID while ipc_lock - * was spinning: here verify that the structure is still valid + /* + * ipc_rmid() may have already freed the ID while ipc_lock() + * was spinning: here verify that the structure is still valid. + * Upon races with RMID, return -EIDRM, thus indicating that + * the ID points to a removed identifier. */ if (ipc_valid_object(out)) return out; spin_unlock(&out->lock); - out = ERR_PTR(-EINVAL); -err1: + out = ERR_PTR(-EIDRM); +err: rcu_read_unlock(); return out; } -- cgit v1.2.3 From 6157dbbfbf9d8e4a2b6d4e5ee35e864ab9ee8414 Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Tue, 30 Jun 2015 14:58:48 -0700 Subject: ipc,sysv: return -EINVAL upon incorrect id/seqnum In ipc_obtain_object_check we return -EIDRM when a bogus sequence number is detected via ipc_checkid, while the ipc manpages state the following return codes for such errors: EIDRM points to a removed identifier. EINVAL Invalid value, or unaligned, etc. EIDRM should only be returned upon a RMID call (->deleted check), and thus return EINVAL for wrong seq. This difference in semantics has also caused real bugs, ie: https://bugzilla.redhat.com/show_bug.cgi?id=246509 Signed-off-by: Davidlohr Bueso Cc: Manfred Spraul Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- ipc/util.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/ipc/util.c b/ipc/util.c index b99038699fee..be4230020a1f 100644 --- a/ipc/util.c +++ b/ipc/util.c @@ -622,7 +622,7 @@ struct kern_ipc_perm *ipc_obtain_object_check(struct ipc_ids *ids, int id) goto out; if (ipc_checkid(out, id)) - return ERR_PTR(-EIDRM); + return ERR_PTR(-EINVAL); out: return out; } -- cgit v1.2.3 From 4dc7daf843f3914c9c0c7efb71b8f251c9c4636f Mon Sep 17 00:00:00 2001 From: Dave Gordon Date: Tue, 30 Jun 2015 14:58:52 -0700 Subject: lib/scatterlist.c: fix kerneldoc for sg_pcopy_{to,from}_buffer() The kerneldoc for the functions doesn't match the code; the last two parameters (buflen, skip) have been transposed, which is confusing, especially as they're both integral types and the compiler won't warn about swapping them. These functions and the kerneldoc were introduced in commit: df642cea lib/scatterlist: introduce sg_pcopy_from_buffer() ... Author: Akinobu Mita Date: Mon Jul 8 16:01:54 2013 -0700 The only difference between sg_pcopy_{from,to}_buffer() and sg_copy_{from,to}_buffer() is an additional argument that specifies the number of bytes to skip the SG list before copying. The functions have the extra argument at the end, but the kerneldoc lists it in penultimate position. Signed-off-by: Dave Gordon Reviewed-by: Akinobu Mita Cc: "Martin K. Petersen" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/scatterlist.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/lib/scatterlist.c b/lib/scatterlist.c index 99fbc2f238c4..965c36e7a5a4 100644 --- a/lib/scatterlist.c +++ b/lib/scatterlist.c @@ -729,8 +729,8 @@ EXPORT_SYMBOL(sg_copy_to_buffer); * @sgl: The SG list * @nents: Number of SG entries * @buf: Where to copy from - * @skip: Number of bytes to skip before copying * @buflen: The number of bytes to copy + * @skip: Number of bytes to skip before copying * * Returns the number of copied bytes. * @@ -747,8 +747,8 @@ EXPORT_SYMBOL(sg_pcopy_from_buffer); * @sgl: The SG list * @nents: Number of SG entries * @buf: Where to copy to - * @skip: Number of bytes to skip before copying * @buflen: The number of bytes to copy + * @skip: Number of bytes to skip before copying * * Returns the number of copied bytes. * -- cgit v1.2.3 From 2a1bf8f93b33992bb0457512b28d046e279bbd7e Mon Sep 17 00:00:00 2001 From: Dave Gordon Date: Tue, 30 Jun 2015 14:58:54 -0700 Subject: lib/scatterlist: mark input buffer parameters as 'const' The 'buf' parameter of sg(p)copy_from_buffer() can and should be const-qualified, although because of the shared implementation of _to_buffer() and _from_buffer(), we have to cast this away internally. This means that callers who have a 'const' buffer containing the data to be copied to the sg-list no longer have to cast away the const-ness themselves. It also enables improved coverage by code analysis tools. Signed-off-by: Dave Gordon Cc: Akinobu Mita Cc: "Martin K. Petersen" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/scatterlist.h | 4 ++-- lib/scatterlist.c | 8 ++++---- 2 files changed, 6 insertions(+), 6 deletions(-) diff --git a/include/linux/scatterlist.h b/include/linux/scatterlist.h index 50a8486c524b..505d0481df1e 100644 --- a/include/linux/scatterlist.h +++ b/include/linux/scatterlist.h @@ -266,12 +266,12 @@ int sg_alloc_table_from_pages(struct sg_table *sgt, gfp_t gfp_mask); size_t sg_copy_from_buffer(struct scatterlist *sgl, unsigned int nents, - void *buf, size_t buflen); + const void *buf, size_t buflen); size_t sg_copy_to_buffer(struct scatterlist *sgl, unsigned int nents, void *buf, size_t buflen); size_t sg_pcopy_from_buffer(struct scatterlist *sgl, unsigned int nents, - void *buf, size_t buflen, off_t skip); + const void *buf, size_t buflen, off_t skip); size_t sg_pcopy_to_buffer(struct scatterlist *sgl, unsigned int nents, void *buf, size_t buflen, off_t skip); diff --git a/lib/scatterlist.c b/lib/scatterlist.c index 965c36e7a5a4..317b62c6da3c 100644 --- a/lib/scatterlist.c +++ b/lib/scatterlist.c @@ -701,9 +701,9 @@ static size_t sg_copy_buffer(struct scatterlist *sgl, unsigned int nents, * **/ size_t sg_copy_from_buffer(struct scatterlist *sgl, unsigned int nents, - void *buf, size_t buflen) + const void *buf, size_t buflen) { - return sg_copy_buffer(sgl, nents, buf, buflen, 0, false); + return sg_copy_buffer(sgl, nents, (void *)buf, buflen, 0, false); } EXPORT_SYMBOL(sg_copy_from_buffer); @@ -736,9 +736,9 @@ EXPORT_SYMBOL(sg_copy_to_buffer); * **/ size_t sg_pcopy_from_buffer(struct scatterlist *sgl, unsigned int nents, - void *buf, size_t buflen, off_t skip) + const void *buf, size_t buflen, off_t skip) { - return sg_copy_buffer(sgl, nents, buf, buflen, skip, false); + return sg_copy_buffer(sgl, nents, (void *)buf, buflen, skip, false); } EXPORT_SYMBOL(sg_pcopy_from_buffer); -- cgit v1.2.3 From 386ecb1216f9e38947ce6a2af22e5e1e47256a97 Mon Sep 17 00:00:00 2001 From: Dave Gordon Date: Tue, 30 Jun 2015 14:58:57 -0700 Subject: drivers/scsi/scsi_debug.c: resolve sg buffer const-ness issue do_device_access() takes a separate parameter to indicate the direction of data transfer, which it used to use to select the appropriate function out of sg_pcopy_{to,from}_buffer(). However these two functions now have So this patch makes it bypass these wrappers and call the underlying function sg_copy_buffer() directly; this has the same calling style as do_device_access() i.e. a separate direction-of-transfer parameter and no pointers-to-const, so skipping the wrappers not only eliminates the warning, it also make the code simpler :) [akpm@linux-foundation.org: fix very broken build] Signed-off-by: Dave Gordon Acked-by: Arnd Bergmann Cc: James Bottomley Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/scsi/scsi_debug.c | 12 ++++-------- include/linux/scatterlist.h | 3 +++ lib/scatterlist.c | 6 +++--- 3 files changed, 10 insertions(+), 11 deletions(-) diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c index 1f8e2dc9c616..30268bb2ddb6 100644 --- a/drivers/scsi/scsi_debug.c +++ b/drivers/scsi/scsi_debug.c @@ -2363,17 +2363,13 @@ do_device_access(struct scsi_cmnd *scmd, u64 lba, u32 num, bool do_write) u64 block, rest = 0; struct scsi_data_buffer *sdb; enum dma_data_direction dir; - size_t (*func)(struct scatterlist *, unsigned int, void *, size_t, - off_t); if (do_write) { sdb = scsi_out(scmd); dir = DMA_TO_DEVICE; - func = sg_pcopy_to_buffer; } else { sdb = scsi_in(scmd); dir = DMA_FROM_DEVICE; - func = sg_pcopy_from_buffer; } if (!sdb->length) @@ -2385,16 +2381,16 @@ do_device_access(struct scsi_cmnd *scmd, u64 lba, u32 num, bool do_write) if (block + num > sdebug_store_sectors) rest = block + num - sdebug_store_sectors; - ret = func(sdb->table.sgl, sdb->table.nents, + ret = sg_copy_buffer(sdb->table.sgl, sdb->table.nents, fake_storep + (block * scsi_debug_sector_size), - (num - rest) * scsi_debug_sector_size, 0); + (num - rest) * scsi_debug_sector_size, 0, do_write); if (ret != (num - rest) * scsi_debug_sector_size) return ret; if (rest) { - ret += func(sdb->table.sgl, sdb->table.nents, + ret += sg_copy_buffer(sdb->table.sgl, sdb->table.nents, fake_storep, rest * scsi_debug_sector_size, - (num - rest) * scsi_debug_sector_size); + (num - rest) * scsi_debug_sector_size, do_write); } return ret; diff --git a/include/linux/scatterlist.h b/include/linux/scatterlist.h index 505d0481df1e..9b1ef0c820a7 100644 --- a/include/linux/scatterlist.h +++ b/include/linux/scatterlist.h @@ -265,6 +265,9 @@ int sg_alloc_table_from_pages(struct sg_table *sgt, unsigned long offset, unsigned long size, gfp_t gfp_mask); +size_t sg_copy_buffer(struct scatterlist *sgl, unsigned int nents, void *buf, + size_t buflen, off_t skip, bool to_buffer); + size_t sg_copy_from_buffer(struct scatterlist *sgl, unsigned int nents, const void *buf, size_t buflen); size_t sg_copy_to_buffer(struct scatterlist *sgl, unsigned int nents, diff --git a/lib/scatterlist.c b/lib/scatterlist.c index 317b62c6da3c..d105a9f56878 100644 --- a/lib/scatterlist.c +++ b/lib/scatterlist.c @@ -650,9 +650,8 @@ EXPORT_SYMBOL(sg_miter_stop); * Returns the number of copied bytes. * **/ -static size_t sg_copy_buffer(struct scatterlist *sgl, unsigned int nents, - void *buf, size_t buflen, off_t skip, - bool to_buffer) +size_t sg_copy_buffer(struct scatterlist *sgl, unsigned int nents, void *buf, + size_t buflen, off_t skip, bool to_buffer) { unsigned int offset = 0; struct sg_mapping_iter miter; @@ -689,6 +688,7 @@ static size_t sg_copy_buffer(struct scatterlist *sgl, unsigned int nents, local_irq_restore(flags); return offset; } +EXPORT_SYMBOL(sg_copy_buffer); /** * sg_copy_from_buffer - Copy from a linear buffer to an SG list -- cgit v1.2.3 From 9b597fd3c9d6864c580e75f390f1d2d104be6cbc Mon Sep 17 00:00:00 2001 From: Masanari Iida Date: Tue, 30 Jun 2015 14:59:00 -0700 Subject: arch/unicore32/kernel/fpu-ucf64.c: remove unnecessary KERN_ERR Signed-off-by: Masanari Iida Cc: Guan Xuetao Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/unicore32/kernel/fpu-ucf64.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/unicore32/kernel/fpu-ucf64.c b/arch/unicore32/kernel/fpu-ucf64.c index 282a60ac82ba..a53343a90ca2 100644 --- a/arch/unicore32/kernel/fpu-ucf64.c +++ b/arch/unicore32/kernel/fpu-ucf64.c @@ -90,8 +90,8 @@ void ucf64_exchandler(u32 inst, u32 fpexc, struct pt_regs *regs) tmp &= ~(FPSCR_CON); exc &= ~(FPSCR_CMPINSTR_BIT | FPSCR_CON); } else { - pr_debug(KERN_ERR "UniCore-F64 Error: unhandled exceptions\n"); - pr_debug(KERN_ERR "UniCore-F64 FPSCR 0x%08x INST 0x%08x\n", + pr_debug("UniCore-F64 Error: unhandled exceptions\n"); + pr_debug("UniCore-F64 FPSCR 0x%08x INST 0x%08x\n", cff(FPSCR), inst); ucf64_raise_sigfpe(0, regs); -- cgit v1.2.3 From b389645f041a9fc650819b1c1ce7abbef7f4912d Mon Sep 17 00:00:00 2001 From: Antonio Ospite Date: Tue, 30 Jun 2015 14:59:03 -0700 Subject: printk: improve the description of /dev/kmsg line format The comment about /dev/kmsg does not mention the additional values which may actually be exported, fix that. Also move up the part of the comment instructing the users to ignore these additional values, this way the reading is more fluent and logically compact. Signed-off-by: Antonio Ospite Cc: Joe Perches Cc: Jonathan Corbet Cc: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/printk/printk.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index de553849f3ac..cf8c24203368 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -207,14 +207,14 @@ static int console_may_schedule; * need to be changed in the future, when the requirements change. * * /dev/kmsg exports the structured data in the following line format: - * ",,,;\n" + * ",,,[,additional_values, ... ];\n" + * + * Users of the export format should ignore possible additional values + * separated by ',', and find the message after the ';' character. * * The optional key/value pairs are attached as continuation lines starting * with a space character and terminated by a newline. All possible * non-prinatable characters are escaped in the "\xff" notation. - * - * Users of the export format should ignore possible additional values - * separated by ',', and find the message after the ';' character. */ enum log_flags { -- cgit v1.2.3 From 200f1ce3656b8f466f74756677cea1b5e2aa851a Mon Sep 17 00:00:00 2001 From: Pekka Enberg Date: Tue, 30 Jun 2015 14:59:06 -0700 Subject: kernel/relay.c: use kvfree() in relay_free_page_array() Use kvfree() instead of open-coding it. Signed-off-by: Pekka Enberg Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/relay.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/kernel/relay.c b/kernel/relay.c index e9dbaeb8fd65..0b4570cfacae 100644 --- a/kernel/relay.c +++ b/kernel/relay.c @@ -81,10 +81,7 @@ static struct page **relay_alloc_page_array(unsigned int n_pages) */ static void relay_free_page_array(struct page **array) { - if (is_vmalloc_addr(array)) - vfree(array); - else - kfree(array); + kvfree(array); } /** -- cgit v1.2.3 From 68c61b93e89fef36a36086c4e686fe413d2caab7 Mon Sep 17 00:00:00 2001 From: Pekka Enberg Date: Tue, 30 Jun 2015 14:59:09 -0700 Subject: cxgb3: use kvfree() in cxgb_free_mem() Use kvfree() instead of open-coding it. Signed-off-by: Pekka Enberg Cc: Santosh Raspatur Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/net/ethernet/chelsio/cxgb3/cxgb3_offload.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_offload.c b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_offload.c index b0cbb2b7fd48..76684dcb874c 100644 --- a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_offload.c +++ b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_offload.c @@ -1169,10 +1169,7 @@ void *cxgb_alloc_mem(unsigned long size) */ void cxgb_free_mem(void *addr) { - if (is_vmalloc_addr(addr)) - vfree(addr); - else - kfree(addr); + kvfree(addr); } /* -- cgit v1.2.3 From d2fcb5486af754c990f9a11f91195e28ffd4c735 Mon Sep 17 00:00:00 2001 From: Pekka Enberg Date: Tue, 30 Jun 2015 14:59:12 -0700 Subject: cxgb4: use kvfree() in t4_free_mem() Use kvfree() instead of open-coding it. Signed-off-by: Pekka Enberg Cc: Hariprasad S Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index c64b5a99bfef..351f3b1bf800 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -1150,10 +1150,7 @@ void *t4_alloc_mem(size_t size) */ void t4_free_mem(void *addr) { - if (is_vmalloc_addr(addr)) - vfree(addr); - else - kfree(addr); + kvfree(addr); } /* Send a Work Request to write the filter at a specified index. We construct -- cgit v1.2.3 From 15e21cd1631e0eca16af545bbdf89e2ffa4cdaee Mon Sep 17 00:00:00 2001 From: Pekka Enberg Date: Tue, 30 Jun 2015 14:59:15 -0700 Subject: drm: use kvfree() in drm_free_large() Use kvfree() instead of open-coding it. Signed-off-by: Pekka Enberg Cc: David Airlie Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/drm/drm_mem_util.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/include/drm/drm_mem_util.h b/include/drm/drm_mem_util.h index 19a240446fca..e42495ad8136 100644 --- a/include/drm/drm_mem_util.h +++ b/include/drm/drm_mem_util.h @@ -56,10 +56,7 @@ static __inline__ void *drm_malloc_ab(size_t nmemb, size_t size) static __inline void drm_free_large(void *ptr) { - if (!is_vmalloc_addr(ptr)) - return kfree(ptr); - - vfree(ptr); + kvfree(ptr); } #endif -- cgit v1.2.3 From 48a20138abeb6d28cf781ae5c3c482e9ad9f89aa Mon Sep 17 00:00:00 2001 From: Pekka Enberg Date: Tue, 30 Jun 2015 14:59:18 -0700 Subject: drm/nouveau/gem: use kvfree() in u_free() Use kvfree() instead of open-coding it. Signed-off-by: Pekka Enberg Cc: David Airlie Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/gpu/drm/nouveau/nouveau_gem.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c b/drivers/gpu/drm/nouveau/nouveau_gem.c index 0e690bf19fc9..af1ee517f372 100644 --- a/drivers/gpu/drm/nouveau/nouveau_gem.c +++ b/drivers/gpu/drm/nouveau/nouveau_gem.c @@ -555,10 +555,7 @@ nouveau_gem_pushbuf_validate(struct nouveau_channel *chan, static inline void u_free(void *addr) { - if (!is_vmalloc_addr(addr)) - kfree(addr); - else - vfree(addr); + kvfree(addr); } static inline void * -- cgit v1.2.3 From f8c5b93947cd9a6bbc83ef22c060a6cfcc1572b0 Mon Sep 17 00:00:00 2001 From: Pekka Enberg Date: Tue, 30 Jun 2015 14:59:21 -0700 Subject: IB/ehca: use kvfree() in ipz_queue_{cd}tor() Use kvfree() instead of open-coding it. Signed-off-by: Pekka Enberg Cc: Hoang-Nam Nguyen Cc: Christoph Raisch Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/infiniband/hw/ehca/ipz_pt_fn.c | 10 ++-------- 1 file changed, 2 insertions(+), 8 deletions(-) diff --git a/drivers/infiniband/hw/ehca/ipz_pt_fn.c b/drivers/infiniband/hw/ehca/ipz_pt_fn.c index 8d594517cd29..7ffc748cb973 100644 --- a/drivers/infiniband/hw/ehca/ipz_pt_fn.c +++ b/drivers/infiniband/hw/ehca/ipz_pt_fn.c @@ -245,10 +245,7 @@ int ipz_queue_ctor(struct ehca_pd *pd, struct ipz_queue *queue, ipz_queue_ctor_exit0: ehca_gen_err("Couldn't alloc pages queue=%p " "nr_of_pages=%x", queue, nr_of_pages); - if (is_vmalloc_addr(queue->queue_pages)) - vfree(queue->queue_pages); - else - kfree(queue->queue_pages); + kvfree(queue->queue_pages); return 0; } @@ -270,10 +267,7 @@ int ipz_queue_dtor(struct ehca_pd *pd, struct ipz_queue *queue) free_page((unsigned long)queue->queue_pages[i]); } - if (is_vmalloc_addr(queue->queue_pages)) - vfree(queue->queue_pages); - else - kfree(queue->queue_pages); + kvfree(queue->queue_pages); return 1; } -- cgit v1.2.3 From de64d3a6c7c0cd9cbf673b68fd4a7ae6a2b8f035 Mon Sep 17 00:00:00 2001 From: Pekka Enberg Date: Tue, 30 Jun 2015 14:59:24 -0700 Subject: target: use kvfree() in session alloc and free Use kvfree() instead of open-coding it. Signed-off-by: Pekka Enberg Cc: "Nicholas A. Bellinger" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/target/target_core_transport.c | 10 ++-------- 1 file changed, 2 insertions(+), 8 deletions(-) diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index 0b4e24217564..cd3bfc16d25f 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -279,10 +279,7 @@ int transport_alloc_session_tags(struct se_session *se_sess, if (rc < 0) { pr_err("Unable to init se_sess->sess_tag_pool," " tag_num: %u\n", tag_num); - if (is_vmalloc_addr(se_sess->sess_cmd_map)) - vfree(se_sess->sess_cmd_map); - else - kfree(se_sess->sess_cmd_map); + kvfree(se_sess->sess_cmd_map); se_sess->sess_cmd_map = NULL; return -ENOMEM; } @@ -489,10 +486,7 @@ void transport_free_session(struct se_session *se_sess) { if (se_sess->sess_cmd_map) { percpu_ida_destroy(&se_sess->sess_tag_pool); - if (is_vmalloc_addr(se_sess->sess_cmd_map)) - vfree(se_sess->sess_cmd_map); - else - kfree(se_sess->sess_cmd_map); + kvfree(se_sess->sess_cmd_map); } kmem_cache_free(se_sess_cache, se_sess); } -- cgit v1.2.3 From 32a78facdd0a5e77d18d03dbe53e0823d249b0bb Mon Sep 17 00:00:00 2001 From: Pekka Enberg Date: Tue, 30 Jun 2015 14:59:27 -0700 Subject: libcxgbi: use kvfree() in cxgbi_free_big_mem() Use kvfree() instead of open-coding it. Signed-off-by: Pekka Enberg Cc: "James E.J. Bottomley" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/scsi/cxgbi/libcxgbi.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/scsi/cxgbi/libcxgbi.h b/drivers/scsi/cxgbi/libcxgbi.h index b3e5bd1d5d9c..9842301f7980 100644 --- a/drivers/scsi/cxgbi/libcxgbi.h +++ b/drivers/scsi/cxgbi/libcxgbi.h @@ -685,10 +685,7 @@ static inline void *cxgbi_alloc_big_mem(unsigned int size, static inline void cxgbi_free_big_mem(void *addr) { - if (is_vmalloc_addr(addr)) - vfree(addr); - else - kfree(addr); + kvfree(addr); } static inline void cxgbi_set_iscsi_ipv4(struct cxgbi_hba *chba, __be32 ipaddr) -- cgit v1.2.3 From 958b43384e41c129117284f48ba3fb9c11ebac75 Mon Sep 17 00:00:00 2001 From: Pekka Enberg Date: Tue, 30 Jun 2015 14:59:30 -0700 Subject: bcache: use kvfree() in various places Use kvfree() instead of open-coding it. Signed-off-by: Pekka Enberg Cc: Kent Overstreet Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/md/bcache/super.c | 10 ++-------- drivers/md/bcache/util.h | 10 ++-------- 2 files changed, 4 insertions(+), 16 deletions(-) diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index 4dd2bb7167f0..94980bfca434 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -760,14 +760,8 @@ static void bcache_device_free(struct bcache_device *d) bio_split_pool_free(&d->bio_split_hook); if (d->bio_split) bioset_free(d->bio_split); - if (is_vmalloc_addr(d->full_dirty_stripes)) - vfree(d->full_dirty_stripes); - else - kfree(d->full_dirty_stripes); - if (is_vmalloc_addr(d->stripe_sectors_dirty)) - vfree(d->stripe_sectors_dirty); - else - kfree(d->stripe_sectors_dirty); + kvfree(d->full_dirty_stripes); + kvfree(d->stripe_sectors_dirty); closure_debug_destroy(&d->cl); } diff --git a/drivers/md/bcache/util.h b/drivers/md/bcache/util.h index 98df7572b5f7..1d04c4859c70 100644 --- a/drivers/md/bcache/util.h +++ b/drivers/md/bcache/util.h @@ -52,10 +52,7 @@ struct closure; #define free_heap(heap) \ do { \ - if (is_vmalloc_addr((heap)->data)) \ - vfree((heap)->data); \ - else \ - kfree((heap)->data); \ + kvfree((heap)->data); \ (heap)->data = NULL; \ } while (0) @@ -163,10 +160,7 @@ do { \ #define free_fifo(fifo) \ do { \ - if (is_vmalloc_addr((fifo)->data)) \ - vfree((fifo)->data); \ - else \ - kfree((fifo)->data); \ + kvfree((fifo)->data); \ (fifo)->data = NULL; \ } while (0) -- cgit v1.2.3 From 2b8e7333431f90be12a6ef5c44f2efbc3625e7bf Mon Sep 17 00:00:00 2001 From: Laurent Navet Date: Tue, 30 Jun 2015 14:59:33 -0700 Subject: MAINTAINERS: update Emulex ocrdma email addresses @emulex.com addresses respond to use @avagotech.com. Signed-off-by: Laurent Navet Acked-By: Devesh Sharma Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- MAINTAINERS | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index 0e6b09150aad..90878f323457 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -9091,9 +9091,9 @@ S: Supported F: drivers/net/ethernet/emulex/benet/ EMULEX ONECONNECT ROCE DRIVER -M: Selvin Xavier -M: Devesh Sharma -M: Mitesh Ahuja +M: Selvin Xavier +M: Devesh Sharma +M: Mitesh Ahuja L: linux-rdma@vger.kernel.org W: http://www.emulex.com S: Supported -- cgit v1.2.3 From 712c0347902843c6a467e6c7ef90d0ee34eca110 Mon Sep 17 00:00:00 2001 From: Sudip Mukherjee Date: Tue, 30 Jun 2015 14:59:36 -0700 Subject: MAINTAINERS: remove website for paride The webpage mentioned is not working, Signed-off-by: Sudip Mukherjee Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- MAINTAINERS | 1 - 1 file changed, 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index 90878f323457..875d9d69b43d 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -7647,7 +7647,6 @@ F: arch/*/include/asm/paravirt.h PARIDE DRIVERS FOR PARALLEL PORT IDE DEVICES M: Tim Waugh L: linux-parport@lists.infradead.org (subscribers-only) -W: http://www.torque.net/linux-pp.html S: Maintained F: Documentation/blockdev/paride.txt F: drivers/block/paride/ -- cgit v1.2.3 From e8e1225da568eef733d69033ba1647237fbd3c45 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Tue, 30 Jun 2015 14:59:39 -0700 Subject: MAINTAINERS: update sound soc intel patterns Commit 2106241a6803 ("ASoC: Intel: create common folder and move common files in") moved the files around. Update the patterns. Signed-off-by: Joe Perches Cc: Jie Yang Acked-by: Jie Yang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- MAINTAINERS | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index 875d9d69b43d..2243d9142c06 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -5285,11 +5285,10 @@ INTEL ASoC BDW/HSW DRIVERS M: Jie Yang L: alsa-devel@alsa-project.org (moderated for non-subscribers) S: Supported -F: sound/soc/intel/sst-haswell* -F: sound/soc/intel/sst-dsp* -F: sound/soc/intel/sst-firmware.c -F: sound/soc/intel/broadwell.c -F: sound/soc/intel/haswell.c +F: sound/soc/intel/common/sst-dsp* +F: sound/soc/intel/common/sst-firmware.c +F: sound/soc/intel/boards/broadwell.c +F: sound/soc/intel/haswell/ INTEL C600 SERIES SAS CONTROLLER DRIVER M: Intel SCU Linux support -- cgit v1.2.3 From 338808de6cc8f2952ac15f71ddbb9230d95fa4f6 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Tue, 30 Jun 2015 14:59:42 -0700 Subject: MAINTAINERS: update brcm dts pattern Commit 8c0b9ee8665c ("MIPS: Move device-trees into vendor sub-directories") moved the files, update the pattern. Signed-off-by: Joe Perches Cc: Andrew Bresticker Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- MAINTAINERS | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index 2243d9142c06..6de33075d8f7 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2280,7 +2280,7 @@ S: Maintained F: arch/mips/bmips/* F: arch/mips/include/asm/mach-bmips/* F: arch/mips/kernel/*bmips* -F: arch/mips/boot/dts/bcm*.dts* +F: arch/mips/boot/dts/brcm/bcm*.dts* F: drivers/irqchip/irq-bcm7* F: drivers/irqchip/irq-brcmstb* -- cgit v1.2.3 From 1db12cde4c5b0ba586f29cd90387b654497faf45 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Tue, 30 Jun 2015 14:59:45 -0700 Subject: MAINTAINERS: update brcm gpio filename pattern Commit 23a71fd616bf ("dt-bindings: brcm: rationalize Broadcom documentation naming") renamed the file, update the pattern. Signed-off-by: Joe Perches Acked-by: Scott Branden Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- MAINTAINERS | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index 6de33075d8f7..44c63e54c9d7 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2339,7 +2339,7 @@ M: Ray Jui L: bcm-kernel-feedback-list@broadcom.com S: Supported F: drivers/gpio/gpio-bcm-kona.c -F: Documentation/devicetree/bindings/gpio/gpio-bcm-kona.txt +F: Documentation/devicetree/bindings/gpio/brcm,kona-gpio.txt BROADCOM NVRAM DRIVER M: Rafał Miłecki -- cgit v1.2.3 From 70a116dca45a8480429c4d0803e129a18f035c6e Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Tue, 30 Jun 2015 14:59:48 -0700 Subject: MAINTAINERS: remove unused nbd.h pattern Commit 13e71d69cc74 ("nbd: Remove kernel internal header") deleted the file, remove the pattern. Signed-off-by: Joe Perches Acked-by: Markus Pargmann Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- MAINTAINERS | 1 - 1 file changed, 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index 44c63e54c9d7..c8a392659dff 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -7018,7 +7018,6 @@ L: nbd-general@lists.sourceforge.net T: git git://git.pengutronix.de/git/mpa/linux-nbd.git F: Documentation/blockdev/nbd.txt F: drivers/block/nbd.c -F: include/linux/nbd.h F: include/uapi/linux/nbd.h NETWORK DROP MONITOR -- cgit v1.2.3 From 2b0d8f03d8211058babaa2122ccbc58e0f6e9d39 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Tue, 30 Jun 2015 14:59:51 -0700 Subject: MAINTAINERS: move Jens Osterkamp to CREDITS Jens' email address bounces, so move his name and entry to CREDITS. Signed-off-by: Joe Perches Cc: Ishizaki Kou Cc: Jens Osterkamp Cc: Benjamin Herrenschmidt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- CREDITS | 4 ++++ MAINTAINERS | 1 - 2 files changed, 4 insertions(+), 1 deletion(-) diff --git a/CREDITS b/CREDITS index 4df764ebe217..1d616640bbf6 100644 --- a/CREDITS +++ b/CREDITS @@ -2740,6 +2740,10 @@ S: C/ Mieses 20, 9-B S: Valladolid 47009 S: Spain +N: Jens Osterkamp +E: jens@de.ibm.com +D: Maintainer of Spidernet network driver for Cell + N: Gadi Oxman E: gadio@netvision.net.il D: Original author and maintainer of IDE/ATAPI floppy/tape drivers diff --git a/MAINTAINERS b/MAINTAINERS index c8a392659dff..67afc4de50ce 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -9590,7 +9590,6 @@ F: include/uapi/linux/spi/ SPIDERNET NETWORK DRIVER for CELL M: Ishizaki Kou -M: Jens Osterkamp L: netdev@vger.kernel.org S: Supported F: Documentation/networking/spider_net.txt -- cgit v1.2.3 From d1aa1ab33dcb0922e9088e37989a6d28d8702540 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Tue, 30 Jun 2015 14:59:54 -0700 Subject: MAINTAINERS: BCACHE: Kent Overstreet has changed email address Kent's email address in MAINTAINERS seems to be invalid. This was his last sign-off address, so use that if appropriate. Fix the S: status entry while there. Signed-off-by: Joe Perches Acked-by: Kent Overstreet Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- MAINTAINERS | 4 ++-- drivers/md/bcache/journal.c | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index 67afc4de50ce..79faf013c2ba 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2026,10 +2026,10 @@ S: Maintained F: drivers/net/hamradio/baycom* BCACHE (BLOCK LAYER CACHE) -M: Kent Overstreet +M: Kent Overstreet L: linux-bcache@vger.kernel.org W: http://bcache.evilpiepirate.org -S: Maintained: +S: Maintained F: drivers/md/bcache/ BDISP ST MEDIA DRIVER diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c index fe080ad0e558..ce64fc851251 100644 --- a/drivers/md/bcache/journal.c +++ b/drivers/md/bcache/journal.c @@ -157,7 +157,7 @@ int bch_journal_read(struct cache_set *c, struct list_head *list) for_each_cache(ca, c, iter) { struct journal_device *ja = &ca->journal; - unsigned long bitmap[SB_JOURNAL_BUCKETS / BITS_PER_LONG]; + DECLARE_BITMAP(bitmap, SB_JOURNAL_BUCKETS); unsigned i, l, r, m; uint64_t seq; -- cgit v1.2.3 From 2026302909b5dc1b3834a89654315abd8b4e040c Mon Sep 17 00:00:00 2001 From: Dan Streetman Date: Tue, 30 Jun 2015 14:59:57 -0700 Subject: MAINTAINERS: add zpool Add entry for zpool to MAINTAINERS file. Signed-off-by: Dan Streetman Cc: Seth Jennings Cc: Minchan Kim Cc: Nitin Gupta Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- MAINTAINERS | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index 79faf013c2ba..af61ea8d2162 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -11343,6 +11343,13 @@ L: zd1211-devs@lists.sourceforge.net (subscribers-only) S: Maintained F: drivers/net/wireless/zd1211rw/ +ZPOOL COMPRESSED PAGE STORAGE API +M: Dan Streetman +L: linux-mm@kvack.org +S: Maintained +F: mm/zpool.c +F: include/linux/zpool.h + ZR36067 VIDEO FOR LINUX DRIVER L: mjpeg-users@lists.sourceforge.net L: linux-media@vger.kernel.org -- cgit v1.2.3 From c1bd55f922a2df6038060ed48a82d146d301ca12 Mon Sep 17 00:00:00 2001 From: Josh Triplett Date: Tue, 30 Jun 2015 15:00:00 -0700 Subject: x86: opt into HAVE_COPY_THREAD_TLS, for both 32-bit and 64-bit For 32-bit userspace on a 64-bit kernel, this requires modifying stub32_clone to actually swap the appropriate arguments to match CONFIG_CLONE_BACKWARDS, rather than just leaving the C argument for tls broken. Patch co-authored by Josh Triplett and Thiago Macieira. Signed-off-by: Josh Triplett Acked-by: Andy Lutomirski Cc: Ingo Molnar Cc: "H. Peter Anvin" Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Thiago Macieira Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/Kconfig | 1 + arch/x86/kernel/process_32.c | 6 +++--- arch/x86/kernel/process_64.c | 8 ++++---- 3 files changed, 8 insertions(+), 7 deletions(-) diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 47365c7b9f47..55bced17dc95 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -88,6 +88,7 @@ config X86 select HAVE_CMPXCHG_DOUBLE select HAVE_CMPXCHG_LOCAL select HAVE_CONTEXT_TRACKING if X86_64 + select HAVE_COPY_THREAD_TLS select HAVE_C_RECORDMCOUNT select HAVE_DEBUG_KMEMLEAK select HAVE_DEBUG_STACKOVERFLOW diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index c09c99ccf3e3..f73c962fe636 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -128,8 +128,8 @@ void release_thread(struct task_struct *dead_task) release_vm86_irqs(dead_task); } -int copy_thread(unsigned long clone_flags, unsigned long sp, - unsigned long arg, struct task_struct *p) +int copy_thread_tls(unsigned long clone_flags, unsigned long sp, + unsigned long arg, struct task_struct *p, unsigned long tls) { struct pt_regs *childregs = task_pt_regs(p); struct task_struct *tsk; @@ -184,7 +184,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, */ if (clone_flags & CLONE_SETTLS) err = do_set_thread_area(p, -1, - (struct user_desc __user *)childregs->si, 0); + (struct user_desc __user *)tls, 0); if (err && p->thread.io_bitmap_ptr) { kfree(p->thread.io_bitmap_ptr); diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 843f92e4c711..71d7849a07f7 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -150,8 +150,8 @@ static inline u32 read_32bit_tls(struct task_struct *t, int tls) return get_desc_base(&t->thread.tls_array[tls]); } -int copy_thread(unsigned long clone_flags, unsigned long sp, - unsigned long arg, struct task_struct *p) +int copy_thread_tls(unsigned long clone_flags, unsigned long sp, + unsigned long arg, struct task_struct *p, unsigned long tls) { int err; struct pt_regs *childregs; @@ -207,10 +207,10 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, #ifdef CONFIG_IA32_EMULATION if (is_ia32_task()) err = do_set_thread_area(p, -1, - (struct user_desc __user *)childregs->si, 0); + (struct user_desc __user *)tls, 0); else #endif - err = do_arch_prctl(p, ARCH_SET_FS, childregs->r8); + err = do_arch_prctl(p, ARCH_SET_FS, tls); if (err) goto out; } -- cgit v1.2.3 From 0030edf296db8a7afb13573eb12977b7d399cd40 Mon Sep 17 00:00:00 2001 From: Vladimir Zapolskiy Date: Tue, 30 Jun 2015 15:00:03 -0700 Subject: genalloc: rename dev_get_gen_pool() to gen_pool_get() To be consistent with other genalloc interface namings, rename dev_get_gen_pool() to gen_pool_get(). The original omitted "dev_" prefix is removed, since it points to argument type of the function, and so it does not bring any useful information. [akpm@linux-foundation.org: update arch/arm/mach-socfpga/pm.c] Signed-off-by: Vladimir Zapolskiy Acked-by: Nicolas Ferre Cc: Philipp Zabel Cc: Shawn Guo Cc: Sascha Hauer Cc: Alexandre Belloni Cc: Russell King Cc: Mauro Carvalho Chehab Cc: Vinod Koul Cc: Takashi Iwai Cc: Jaroslav Kysela Cc: Mark Brown Cc: Nicolas Ferre Cc: Alan Tull Cc: Dinh Nguyen Cc: Kevin Hilman Cc: Stephen Rothwell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arm/mach-at91/pm.c | 2 +- arch/arm/mach-imx/pm-imx5.c | 2 +- arch/arm/mach-imx/pm-imx6.c | 2 +- arch/arm/mach-socfpga/pm.c | 2 +- drivers/media/platform/coda/coda-common.c | 2 +- include/linux/genalloc.h | 2 +- lib/genalloc.c | 8 ++++---- 7 files changed, 10 insertions(+), 10 deletions(-) diff --git a/arch/arm/mach-at91/pm.c b/arch/arm/mach-at91/pm.c index 1e184767c3be..e24df77abd79 100644 --- a/arch/arm/mach-at91/pm.c +++ b/arch/arm/mach-at91/pm.c @@ -369,7 +369,7 @@ static void __init at91_pm_sram_init(void) return; } - sram_pool = dev_get_gen_pool(&pdev->dev); + sram_pool = gen_pool_get(&pdev->dev); if (!sram_pool) { pr_warn("%s: sram pool unavailable!\n", __func__); return; diff --git a/arch/arm/mach-imx/pm-imx5.c b/arch/arm/mach-imx/pm-imx5.c index 0309ccda36a9..1885676c23c0 100644 --- a/arch/arm/mach-imx/pm-imx5.c +++ b/arch/arm/mach-imx/pm-imx5.c @@ -297,7 +297,7 @@ static int __init imx_suspend_alloc_ocram( goto put_node; } - ocram_pool = dev_get_gen_pool(&pdev->dev); + ocram_pool = gen_pool_get(&pdev->dev); if (!ocram_pool) { pr_warn("%s: ocram pool unavailable!\n", __func__); ret = -ENODEV; diff --git a/arch/arm/mach-imx/pm-imx6.c b/arch/arm/mach-imx/pm-imx6.c index b01650d94f91..93ecf559d06d 100644 --- a/arch/arm/mach-imx/pm-imx6.c +++ b/arch/arm/mach-imx/pm-imx6.c @@ -451,7 +451,7 @@ static int __init imx6q_suspend_init(const struct imx6_pm_socdata *socdata) goto put_node; } - ocram_pool = dev_get_gen_pool(&pdev->dev); + ocram_pool = gen_pool_get(&pdev->dev); if (!ocram_pool) { pr_warn("%s: ocram pool unavailable!\n", __func__); ret = -ENODEV; diff --git a/arch/arm/mach-socfpga/pm.c b/arch/arm/mach-socfpga/pm.c index 1ed89fc2b7a8..6a4199f2bffb 100644 --- a/arch/arm/mach-socfpga/pm.c +++ b/arch/arm/mach-socfpga/pm.c @@ -56,7 +56,7 @@ static int socfpga_setup_ocram_self_refresh(void) goto put_node; } - ocram_pool = dev_get_gen_pool(&pdev->dev); + ocram_pool = gen_pool_get(&pdev->dev); if (!ocram_pool) { pr_warn("%s: ocram pool unavailable!\n", __func__); ret = -ENODEV; diff --git a/drivers/media/platform/coda/coda-common.c b/drivers/media/platform/coda/coda-common.c index 6d6e0ca91fb4..6e640c0f0b35 100644 --- a/drivers/media/platform/coda/coda-common.c +++ b/drivers/media/platform/coda/coda-common.c @@ -2157,7 +2157,7 @@ static int coda_probe(struct platform_device *pdev) /* Get IRAM pool from device tree or platform data */ pool = of_get_named_gen_pool(np, "iram", 0); if (!pool && pdata) - pool = dev_get_gen_pool(pdata->iram_dev); + pool = gen_pool_get(pdata->iram_dev); if (!pool) { dev_err(&pdev->dev, "iram pool not available\n"); return -ENOMEM; diff --git a/include/linux/genalloc.h b/include/linux/genalloc.h index 1ccaab44abcc..015d17068615 100644 --- a/include/linux/genalloc.h +++ b/include/linux/genalloc.h @@ -119,7 +119,7 @@ extern unsigned long gen_pool_best_fit(unsigned long *map, unsigned long size, extern struct gen_pool *devm_gen_pool_create(struct device *dev, int min_alloc_order, int nid); -extern struct gen_pool *dev_get_gen_pool(struct device *dev); +extern struct gen_pool *gen_pool_get(struct device *dev); bool addr_in_gen_pool(struct gen_pool *pool, unsigned long start, size_t size); diff --git a/lib/genalloc.c b/lib/genalloc.c index d214866eeea2..948e92cd9794 100644 --- a/lib/genalloc.c +++ b/lib/genalloc.c @@ -602,12 +602,12 @@ struct gen_pool *devm_gen_pool_create(struct device *dev, int min_alloc_order, EXPORT_SYMBOL(devm_gen_pool_create); /** - * dev_get_gen_pool - Obtain the gen_pool (if any) for a device + * gen_pool_get - Obtain the gen_pool (if any) for a device * @dev: device to retrieve the gen_pool from * * Returns the gen_pool for the device if one is present, or NULL. */ -struct gen_pool *dev_get_gen_pool(struct device *dev) +struct gen_pool *gen_pool_get(struct device *dev) { struct gen_pool **p = devres_find(dev, devm_gen_pool_release, NULL, NULL); @@ -616,7 +616,7 @@ struct gen_pool *dev_get_gen_pool(struct device *dev) return NULL; return *p; } -EXPORT_SYMBOL_GPL(dev_get_gen_pool); +EXPORT_SYMBOL_GPL(gen_pool_get); #ifdef CONFIG_OF /** @@ -642,7 +642,7 @@ struct gen_pool *of_get_named_gen_pool(struct device_node *np, of_node_put(np_pool); if (!pdev) return NULL; - return dev_get_gen_pool(&pdev->dev); + return gen_pool_get(&pdev->dev); } EXPORT_SYMBOL_GPL(of_get_named_gen_pool); #endif /* CONFIG_OF */ -- cgit v1.2.3 From abdd4a7025282fbe3737e1bcb5f51afc8d8ea1b8 Mon Sep 17 00:00:00 2001 From: Vladimir Zapolskiy Date: Tue, 30 Jun 2015 15:00:07 -0700 Subject: genalloc: rename of_get_named_gen_pool() to of_gen_pool_get() To be consistent with other kernel interface namings, rename of_get_named_gen_pool() to of_gen_pool_get(). In the original function name "_named" suffix references to a device tree property, which contains a phandle to a device and the corresponding device driver is assumed to register a gen_pool object. Due to a weak relation and to avoid any confusion (e.g. in future possible scenario if gen_pool objects are named) the suffix is removed. [sfr@canb.auug.org.au: crypto/marvell/cesa - fix up for of_get_named_gen_pool() rename] Signed-off-by: Vladimir Zapolskiy Cc: Nicolas Ferre Cc: Philipp Zabel Cc: Shawn Guo Cc: Sascha Hauer Cc: Alexandre Belloni Cc: Russell King Cc: Mauro Carvalho Chehab Cc: Vinod Koul Cc: Takashi Iwai Cc: Jaroslav Kysela Signed-off-by: Stephen Rothwell Cc: Herbert Xu Cc: Boris BREZILLON Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/crypto/marvell/cesa.c | 5 ++--- drivers/dma/mmp_tdma.c | 2 +- drivers/media/platform/coda/coda-common.c | 2 +- include/linux/genalloc.h | 4 ++-- lib/genalloc.c | 6 +++--- sound/core/memalloc.c | 2 +- 6 files changed, 10 insertions(+), 11 deletions(-) diff --git a/drivers/crypto/marvell/cesa.c b/drivers/crypto/marvell/cesa.c index a432633bced4..1c6f98dd88f4 100644 --- a/drivers/crypto/marvell/cesa.c +++ b/drivers/crypto/marvell/cesa.c @@ -321,9 +321,8 @@ static int mv_cesa_get_sram(struct platform_device *pdev, int idx) const char *res_name = "sram"; struct resource *res; - engine->pool = of_get_named_gen_pool(cesa->dev->of_node, - "marvell,crypto-srams", - idx); + engine->pool = of_gen_pool_get(cesa->dev->of_node, + "marvell,crypto-srams", idx); if (engine->pool) { engine->sram = gen_pool_dma_alloc(engine->pool, cesa->sram_size, diff --git a/drivers/dma/mmp_tdma.c b/drivers/dma/mmp_tdma.c index 449e785def17..e683761e0f8f 100644 --- a/drivers/dma/mmp_tdma.c +++ b/drivers/dma/mmp_tdma.c @@ -657,7 +657,7 @@ static int mmp_tdma_probe(struct platform_device *pdev) INIT_LIST_HEAD(&tdev->device.channels); if (pdev->dev.of_node) - pool = of_get_named_gen_pool(pdev->dev.of_node, "asram", 0); + pool = of_gen_pool_get(pdev->dev.of_node, "asram", 0); else pool = sram_get_gpool("asram"); if (!pool) { diff --git a/drivers/media/platform/coda/coda-common.c b/drivers/media/platform/coda/coda-common.c index 6e640c0f0b35..58f65486de33 100644 --- a/drivers/media/platform/coda/coda-common.c +++ b/drivers/media/platform/coda/coda-common.c @@ -2155,7 +2155,7 @@ static int coda_probe(struct platform_device *pdev) } /* Get IRAM pool from device tree or platform data */ - pool = of_get_named_gen_pool(np, "iram", 0); + pool = of_gen_pool_get(np, "iram", 0); if (!pool && pdata) pool = gen_pool_get(pdata->iram_dev); if (!pool) { diff --git a/include/linux/genalloc.h b/include/linux/genalloc.h index 015d17068615..5383bb1394a1 100644 --- a/include/linux/genalloc.h +++ b/include/linux/genalloc.h @@ -125,10 +125,10 @@ bool addr_in_gen_pool(struct gen_pool *pool, unsigned long start, size_t size); #ifdef CONFIG_OF -extern struct gen_pool *of_get_named_gen_pool(struct device_node *np, +extern struct gen_pool *of_gen_pool_get(struct device_node *np, const char *propname, int index); #else -static inline struct gen_pool *of_get_named_gen_pool(struct device_node *np, +static inline struct gen_pool *of_gen_pool_get(struct device_node *np, const char *propname, int index) { return NULL; diff --git a/lib/genalloc.c b/lib/genalloc.c index 948e92cd9794..daf0afb6d979 100644 --- a/lib/genalloc.c +++ b/lib/genalloc.c @@ -620,7 +620,7 @@ EXPORT_SYMBOL_GPL(gen_pool_get); #ifdef CONFIG_OF /** - * of_get_named_gen_pool - find a pool by phandle property + * of_gen_pool_get - find a pool by phandle property * @np: device node * @propname: property name containing phandle(s) * @index: index into the phandle array @@ -629,7 +629,7 @@ EXPORT_SYMBOL_GPL(gen_pool_get); * address of the device tree node pointed at by the phandle property, * or NULL if not found. */ -struct gen_pool *of_get_named_gen_pool(struct device_node *np, +struct gen_pool *of_gen_pool_get(struct device_node *np, const char *propname, int index) { struct platform_device *pdev; @@ -644,5 +644,5 @@ struct gen_pool *of_get_named_gen_pool(struct device_node *np, return NULL; return gen_pool_get(&pdev->dev); } -EXPORT_SYMBOL_GPL(of_get_named_gen_pool); +EXPORT_SYMBOL_GPL(of_gen_pool_get); #endif /* CONFIG_OF */ diff --git a/sound/core/memalloc.c b/sound/core/memalloc.c index 082509eb805d..f05cb6a8cbe0 100644 --- a/sound/core/memalloc.c +++ b/sound/core/memalloc.c @@ -124,7 +124,7 @@ static void snd_malloc_dev_iram(struct snd_dma_buffer *dmab, size_t size) dmab->addr = 0; if (dev->of_node) - pool = of_get_named_gen_pool(dev->of_node, "iram", 0); + pool = of_gen_pool_get(dev->of_node, "iram", 0); if (!pool) return; -- cgit v1.2.3