From 3fe0313e6ec572e6bb3f9d247316a834336db4be Mon Sep 17 00:00:00 2001 From: Zhang Rui Date: Sun, 26 Oct 2008 20:50:26 +0100 Subject: Hibernate: Call platform_begin before swsusp_shrink_memory Call platform_begin() before swsusp_shrink_memory() so that we can always allocate enough memory to save the ACPI NVS region from platform_begin(). Signed-off-by: Zhang Rui Acked-by: Nigel Cunningham Acked-by: Pavel Machek Signed-off-by: Rafael J. Wysocki Signed-off-by: Len Brown --- kernel/power/disk.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/power/disk.c b/kernel/power/disk.c index c9d74083746f..096fe4899ea4 100644 --- a/kernel/power/disk.c +++ b/kernel/power/disk.c @@ -259,12 +259,12 @@ int hibernation_snapshot(int platform_mode) { int error, ftrace_save; - /* Free memory before shutting down devices. */ - error = swsusp_shrink_memory(); + error = platform_begin(platform_mode); if (error) return error; - error = platform_begin(platform_mode); + /* Free memory before shutting down devices. */ + error = swsusp_shrink_memory(); if (error) goto Close; -- cgit v1.2.3 From 3f4b0ef7f2899c91b1d6958779f084b44dd59d32 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sun, 26 Oct 2008 20:52:15 +0100 Subject: ACPI hibernate: Add a mechanism to save/restore ACPI NVS memory According to the ACPI Specification 3.0b, Section 15.3.2, "OSPM will call the _PTS control method some time before entering a sleeping state, to allow the platform's AML code to update this memory image before entering the sleeping state. After the system awakes from an S4 state, OSPM will restore this memory area and call the _WAK control method to enable the BIOS to reclaim its memory image." For this reason, implement a mechanism allowing us to save the NVS memory during hibernation and to restore it during the subsequent resume. Based on a patch by Zhang Rui. Signed-off-by: Rafael J. Wysocki Acked-by: Nigel Cunningham Cc: Zhang Rui Signed-off-by: Len Brown --- drivers/acpi/sleep/main.c | 53 +++++++++++++++++--- include/linux/suspend.h | 13 +++++ kernel/power/swsusp.c | 122 ++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 180 insertions(+), 8 deletions(-) (limited to 'kernel') diff --git a/drivers/acpi/sleep/main.c b/drivers/acpi/sleep/main.c index 28a691cc625e..45a8015e4217 100644 --- a/drivers/acpi/sleep/main.c +++ b/drivers/acpi/sleep/main.c @@ -394,9 +394,25 @@ void __init acpi_no_s4_hw_signature(void) static int acpi_hibernation_begin(void) { - acpi_target_sleep_state = ACPI_STATE_S4; - acpi_sleep_tts_switch(acpi_target_sleep_state); - return 0; + int error; + + error = hibernate_nvs_alloc(); + if (!error) { + acpi_target_sleep_state = ACPI_STATE_S4; + acpi_sleep_tts_switch(acpi_target_sleep_state); + } + + return error; +} + +static int acpi_hibernation_pre_snapshot(void) +{ + int error = acpi_pm_prepare(); + + if (!error) + hibernate_nvs_save(); + + return error; } static int acpi_hibernation_enter(void) @@ -417,6 +433,12 @@ static int acpi_hibernation_enter(void) return ACPI_SUCCESS(status) ? 0 : -EFAULT; } +static void acpi_hibernation_finish(void) +{ + hibernate_nvs_free(); + acpi_pm_finish(); +} + static void acpi_hibernation_leave(void) { /* @@ -432,6 +454,8 @@ static void acpi_hibernation_leave(void) "cannot resume!\n"); panic("ACPI S4 hardware signature mismatch"); } + /* Restore the NVS memory area */ + hibernate_nvs_restore(); } static void acpi_pm_enable_gpes(void) @@ -442,8 +466,8 @@ static void acpi_pm_enable_gpes(void) static struct platform_hibernation_ops acpi_hibernation_ops = { .begin = acpi_hibernation_begin, .end = acpi_pm_end, - .pre_snapshot = acpi_pm_prepare, - .finish = acpi_pm_finish, + .pre_snapshot = acpi_hibernation_pre_snapshot, + .finish = acpi_hibernation_finish, .prepare = acpi_pm_prepare, .enter = acpi_hibernation_enter, .leave = acpi_hibernation_leave, @@ -469,8 +493,21 @@ static int acpi_hibernation_begin_old(void) error = acpi_sleep_prepare(ACPI_STATE_S4); + if (!error) { + error = hibernate_nvs_alloc(); + if (!error) + acpi_target_sleep_state = ACPI_STATE_S4; + } + return error; +} + +static int acpi_hibernation_pre_snapshot_old(void) +{ + int error = acpi_pm_disable_gpes(); + if (!error) - acpi_target_sleep_state = ACPI_STATE_S4; + hibernate_nvs_save(); + return error; } @@ -481,8 +518,8 @@ static int acpi_hibernation_begin_old(void) static struct platform_hibernation_ops acpi_hibernation_ops_old = { .begin = acpi_hibernation_begin_old, .end = acpi_pm_end, - .pre_snapshot = acpi_pm_disable_gpes, - .finish = acpi_pm_finish, + .pre_snapshot = acpi_hibernation_pre_snapshot_old, + .finish = acpi_hibernation_finish, .prepare = acpi_pm_disable_gpes, .enter = acpi_hibernation_enter, .leave = acpi_hibernation_leave, diff --git a/include/linux/suspend.h b/include/linux/suspend.h index 2ce8207686e2..2b409c44db83 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -232,6 +232,11 @@ extern unsigned long get_safe_page(gfp_t gfp_mask); extern void hibernation_set_ops(struct platform_hibernation_ops *ops); extern int hibernate(void); +extern int hibernate_nvs_register(unsigned long start, unsigned long size); +extern int hibernate_nvs_alloc(void); +extern void hibernate_nvs_free(void); +extern void hibernate_nvs_save(void); +extern void hibernate_nvs_restore(void); #else /* CONFIG_HIBERNATION */ static inline int swsusp_page_is_forbidden(struct page *p) { return 0; } static inline void swsusp_set_page_free(struct page *p) {} @@ -239,6 +244,14 @@ static inline void swsusp_unset_page_free(struct page *p) {} static inline void hibernation_set_ops(struct platform_hibernation_ops *ops) {} static inline int hibernate(void) { return -ENOSYS; } +static inline int hibernate_nvs_register(unsigned long a, unsigned long b) +{ + return 0; +} +static inline int hibernate_nvs_alloc(void) { return 0; } +static inline void hibernate_nvs_free(void) {} +static inline void hibernate_nvs_save(void) {} +static inline void hibernate_nvs_restore(void) {} #endif /* CONFIG_HIBERNATION */ #ifdef CONFIG_PM_SLEEP diff --git a/kernel/power/swsusp.c b/kernel/power/swsusp.c index 023ff2a31d89..a92c91451559 100644 --- a/kernel/power/swsusp.c +++ b/kernel/power/swsusp.c @@ -262,3 +262,125 @@ int swsusp_shrink_memory(void) return 0; } + +/* + * Platforms, like ACPI, may want us to save some memory used by them during + * hibernation and to restore the contents of this memory during the subsequent + * resume. The code below implements a mechanism allowing us to do that. + */ + +struct nvs_page { + unsigned long phys_start; + unsigned int size; + void *kaddr; + void *data; + struct list_head node; +}; + +static LIST_HEAD(nvs_list); + +/** + * hibernate_nvs_register - register platform NVS memory region to save + * @start - physical address of the region + * @size - size of the region + * + * The NVS region need not be page-aligned (both ends) and we arrange + * things so that the data from page-aligned addresses in this region will + * be copied into separate RAM pages. + */ +int hibernate_nvs_register(unsigned long start, unsigned long size) +{ + struct nvs_page *entry, *next; + + while (size > 0) { + unsigned int nr_bytes; + + entry = kzalloc(sizeof(struct nvs_page), GFP_KERNEL); + if (!entry) + goto Error; + + list_add_tail(&entry->node, &nvs_list); + entry->phys_start = start; + nr_bytes = PAGE_SIZE - (start & ~PAGE_MASK); + entry->size = (size < nr_bytes) ? size : nr_bytes; + + start += entry->size; + size -= entry->size; + } + return 0; + + Error: + list_for_each_entry_safe(entry, next, &nvs_list, node) { + list_del(&entry->node); + kfree(entry); + } + return -ENOMEM; +} + +/** + * hibernate_nvs_free - free data pages allocated for saving NVS regions + */ +void hibernate_nvs_free(void) +{ + struct nvs_page *entry; + + list_for_each_entry(entry, &nvs_list, node) + if (entry->data) { + free_page((unsigned long)entry->data); + entry->data = NULL; + if (entry->kaddr) { + iounmap(entry->kaddr); + entry->kaddr = NULL; + } + } +} + +/** + * hibernate_nvs_alloc - allocate memory necessary for saving NVS regions + */ +int hibernate_nvs_alloc(void) +{ + struct nvs_page *entry; + + list_for_each_entry(entry, &nvs_list, node) { + entry->data = (void *)__get_free_page(GFP_KERNEL); + if (!entry->data) { + hibernate_nvs_free(); + return -ENOMEM; + } + } + return 0; +} + +/** + * hibernate_nvs_save - save NVS memory regions + */ +void hibernate_nvs_save(void) +{ + struct nvs_page *entry; + + printk(KERN_INFO "PM: Saving platform NVS memory\n"); + + list_for_each_entry(entry, &nvs_list, node) + if (entry->data) { + entry->kaddr = ioremap(entry->phys_start, entry->size); + memcpy(entry->data, entry->kaddr, entry->size); + } +} + +/** + * hibernate_nvs_restore - restore NVS memory regions + * + * This function is going to be called with interrupts disabled, so it + * cannot iounmap the virtual addresses used to access the NVS region. + */ +void hibernate_nvs_restore(void) +{ + struct nvs_page *entry; + + printk(KERN_INFO "PM: Restoring platform NVS memory\n"); + + list_for_each_entry(entry, &nvs_list, node) + if (entry->data) + memcpy(entry->kaddr, entry->data, entry->size); +} -- cgit v1.2.3 From 69643279a88dea000ac2f858091d0e365f778245 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Tue, 11 Nov 2008 21:32:44 +0100 Subject: Hibernate: Do not oops on resume if image data are incorrect During resume from hibernation using the userland interface image data are being passed from the used space process to the kernel. These data need not be valid, but currently the kernel sometimes oopses if it gets invalid image data, which is wrong. Make the kernel return error codes to the user space in such cases. Signed-off-by: Rafael J. Wysocki Acked-by: Pavel Machek Signed-off-by: Len Brown --- kernel/power/snapshot.c | 43 ++++++++++++++++++++++++++++++++----------- 1 file changed, 32 insertions(+), 11 deletions(-) (limited to 'kernel') diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index 5d2ab836e998..955c8cc91838 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -519,6 +519,14 @@ static int memory_bm_test_bit(struct memory_bitmap *bm, unsigned long pfn) return test_bit(bit, addr); } +static bool memory_bm_pfn_present(struct memory_bitmap *bm, unsigned long pfn) +{ + void *addr; + unsigned int bit; + + return !memory_bm_find_bit(bm, pfn, &addr, &bit); +} + /** * memory_bm_next_pfn - find the pfn that corresponds to the next set bit * in the bitmap @bm. If the pfn cannot be found, BM_END_OF_MAP is @@ -1459,9 +1467,7 @@ load_header(struct swsusp_info *info) * unpack_orig_pfns - for each element of @buf[] (1 page at a time) set * the corresponding bit in the memory bitmap @bm */ - -static inline void -unpack_orig_pfns(unsigned long *buf, struct memory_bitmap *bm) +static int unpack_orig_pfns(unsigned long *buf, struct memory_bitmap *bm) { int j; @@ -1469,8 +1475,13 @@ unpack_orig_pfns(unsigned long *buf, struct memory_bitmap *bm) if (unlikely(buf[j] == BM_END_OF_MAP)) break; - memory_bm_set_bit(bm, buf[j]); + if (memory_bm_pfn_present(bm, buf[j])) + memory_bm_set_bit(bm, buf[j]); + else + return -EFAULT; } + + return 0; } /* List of "safe" pages that may be used to store data loaded from the suspend @@ -1608,7 +1619,7 @@ get_highmem_page_buffer(struct page *page, struct chain_allocator *ca) pbe = chain_alloc(ca, sizeof(struct highmem_pbe)); if (!pbe) { swsusp_free(); - return NULL; + return ERR_PTR(-ENOMEM); } pbe->orig_page = page; if (safe_highmem_pages > 0) { @@ -1677,7 +1688,7 @@ prepare_highmem_image(struct memory_bitmap *bm, unsigned int *nr_highmem_p) static inline void * get_highmem_page_buffer(struct page *page, struct chain_allocator *ca) { - return NULL; + return ERR_PTR(-EINVAL); } static inline void copy_last_highmem_page(void) {} @@ -1788,8 +1799,13 @@ prepare_image(struct memory_bitmap *new_bm, struct memory_bitmap *bm) static void *get_buffer(struct memory_bitmap *bm, struct chain_allocator *ca) { struct pbe *pbe; - struct page *page = pfn_to_page(memory_bm_next_pfn(bm)); + struct page *page; + unsigned long pfn = memory_bm_next_pfn(bm); + if (pfn == BM_END_OF_MAP) + return ERR_PTR(-EFAULT); + + page = pfn_to_page(pfn); if (PageHighMem(page)) return get_highmem_page_buffer(page, ca); @@ -1805,7 +1821,7 @@ static void *get_buffer(struct memory_bitmap *bm, struct chain_allocator *ca) pbe = chain_alloc(ca, sizeof(struct pbe)); if (!pbe) { swsusp_free(); - return NULL; + return ERR_PTR(-ENOMEM); } pbe->orig_address = page_address(page); pbe->address = safe_pages_list; @@ -1868,7 +1884,10 @@ int snapshot_write_next(struct snapshot_handle *handle, size_t count) return error; } else if (handle->prev <= nr_meta_pages) { - unpack_orig_pfns(buffer, ©_bm); + error = unpack_orig_pfns(buffer, ©_bm); + if (error) + return error; + if (handle->prev == nr_meta_pages) { error = prepare_image(&orig_bm, ©_bm); if (error) @@ -1879,12 +1898,14 @@ int snapshot_write_next(struct snapshot_handle *handle, size_t count) restore_pblist = NULL; handle->buffer = get_buffer(&orig_bm, &ca); handle->sync_read = 0; - if (!handle->buffer) - return -ENOMEM; + if (IS_ERR(handle->buffer)) + return PTR_ERR(handle->buffer); } } else { copy_last_highmem_page(); handle->buffer = get_buffer(&orig_bm, &ca); + if (IS_ERR(handle->buffer)) + return PTR_ERR(handle->buffer); if (handle->buffer != buffer) handle->sync_read = 0; } -- cgit v1.2.3 From 846705deb059c352cc0e5806d5964f815b8c6d98 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Wed, 26 Nov 2008 18:00:24 -0500 Subject: Hibernate: Take overlapping zones into account (rev. 2) It has been requested to make hibernation work with memory hotplugging enabled and for this purpose the hibernation code has to be reworked to take the possible overlapping of zones into account. Thus, rework the hibernation memory bitmaps code to prevent duplication of PFNs from occuring and add checks to make sure that one page frame will not be marked as saveable many times. Additionally, use list.h lists instead of open-coded lists to implement the memory bitmaps. Signed-off-by: Rafael J. Wysocki Signed-off-by: Len Brown --- kernel/power/snapshot.c | 325 +++++++++++++++++++++++++----------------------- 1 file changed, 166 insertions(+), 159 deletions(-) (limited to 'kernel') diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index 955c8cc91838..ec9f153b2fc2 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -25,6 +25,7 @@ #include #include #include +#include #include #include @@ -192,12 +193,6 @@ static void *chain_alloc(struct chain_allocator *ca, unsigned int size) return ret; } -static void chain_free(struct chain_allocator *ca, int clear_page_nosave) -{ - free_list_of_pages(ca->chain, clear_page_nosave); - memset(ca, 0, sizeof(struct chain_allocator)); -} - /** * Data types related to memory bitmaps. * @@ -233,7 +228,7 @@ static void chain_free(struct chain_allocator *ca, int clear_page_nosave) #define BM_BITS_PER_BLOCK (PAGE_SIZE << 3) struct bm_block { - struct bm_block *next; /* next element of the list */ + struct list_head hook; /* hook into a list of bitmap blocks */ unsigned long start_pfn; /* pfn represented by the first bit */ unsigned long end_pfn; /* pfn represented by the last bit plus 1 */ unsigned long *data; /* bitmap representing pages */ @@ -244,24 +239,15 @@ static inline unsigned long bm_block_bits(struct bm_block *bb) return bb->end_pfn - bb->start_pfn; } -struct zone_bitmap { - struct zone_bitmap *next; /* next element of the list */ - unsigned long start_pfn; /* minimal pfn in this zone */ - unsigned long end_pfn; /* maximal pfn in this zone plus 1 */ - struct bm_block *bm_blocks; /* list of bitmap blocks */ - struct bm_block *cur_block; /* recently used bitmap block */ -}; - /* strcut bm_position is used for browsing memory bitmaps */ struct bm_position { - struct zone_bitmap *zone_bm; struct bm_block *block; int bit; }; struct memory_bitmap { - struct zone_bitmap *zone_bm_list; /* list of zone bitmaps */ + struct list_head blocks; /* list of bitmap blocks */ struct linked_page *p_list; /* list of pages used to store zone * bitmap objects and bitmap block * objects @@ -273,11 +259,7 @@ struct memory_bitmap { static void memory_bm_position_reset(struct memory_bitmap *bm) { - struct zone_bitmap *zone_bm; - - zone_bm = bm->zone_bm_list; - bm->cur.zone_bm = zone_bm; - bm->cur.block = zone_bm->bm_blocks; + bm->cur.block = list_entry(bm->blocks.next, struct bm_block, hook); bm->cur.bit = 0; } @@ -285,151 +267,184 @@ static void memory_bm_free(struct memory_bitmap *bm, int clear_nosave_free); /** * create_bm_block_list - create a list of block bitmap objects + * @nr_blocks - number of blocks to allocate + * @list - list to put the allocated blocks into + * @ca - chain allocator to be used for allocating memory */ - -static inline struct bm_block * -create_bm_block_list(unsigned int nr_blocks, struct chain_allocator *ca) +static int create_bm_block_list(unsigned long pages, + struct list_head *list, + struct chain_allocator *ca) { - struct bm_block *bblist = NULL; + unsigned int nr_blocks = DIV_ROUND_UP(pages, BM_BITS_PER_BLOCK); while (nr_blocks-- > 0) { struct bm_block *bb; bb = chain_alloc(ca, sizeof(struct bm_block)); if (!bb) - return NULL; - - bb->next = bblist; - bblist = bb; + return -ENOMEM; + list_add(&bb->hook, list); } - return bblist; + + return 0; } +struct mem_extent { + struct list_head hook; + unsigned long start; + unsigned long end; +}; + /** - * create_zone_bm_list - create a list of zone bitmap objects + * free_mem_extents - free a list of memory extents + * @list - list of extents to empty */ +static void free_mem_extents(struct list_head *list) +{ + struct mem_extent *ext, *aux; + + list_for_each_entry_safe(ext, aux, list, hook) { + list_del(&ext->hook); + kfree(ext); + } +} -static inline struct zone_bitmap * -create_zone_bm_list(unsigned int nr_zones, struct chain_allocator *ca) +/** + * create_mem_extents - create a list of memory extents representing + * contiguous ranges of PFNs + * @list - list to put the extents into + * @gfp_mask - mask to use for memory allocations + */ +static int create_mem_extents(struct list_head *list, gfp_t gfp_mask) { - struct zone_bitmap *zbmlist = NULL; + struct zone *zone; - while (nr_zones-- > 0) { - struct zone_bitmap *zbm; + INIT_LIST_HEAD(list); - zbm = chain_alloc(ca, sizeof(struct zone_bitmap)); - if (!zbm) - return NULL; + for_each_zone(zone) { + unsigned long zone_start, zone_end; + struct mem_extent *ext, *cur, *aux; + + if (!populated_zone(zone)) + continue; + + zone_start = zone->zone_start_pfn; + zone_end = zone->zone_start_pfn + zone->spanned_pages; - zbm->next = zbmlist; - zbmlist = zbm; + list_for_each_entry(ext, list, hook) + if (zone_start <= ext->end) + break; + + if (&ext->hook == list || zone_end < ext->start) { + /* New extent is necessary */ + struct mem_extent *new_ext; + + new_ext = kzalloc(sizeof(struct mem_extent), gfp_mask); + if (!new_ext) { + free_mem_extents(list); + return -ENOMEM; + } + new_ext->start = zone_start; + new_ext->end = zone_end; + list_add_tail(&new_ext->hook, &ext->hook); + continue; + } + + /* Merge this zone's range of PFNs with the existing one */ + if (zone_start < ext->start) + ext->start = zone_start; + if (zone_end > ext->end) + ext->end = zone_end; + + /* More merging may be possible */ + cur = ext; + list_for_each_entry_safe_continue(cur, aux, list, hook) { + if (zone_end < cur->start) + break; + if (zone_end < cur->end) + ext->end = cur->end; + list_del(&cur->hook); + kfree(cur); + } } - return zbmlist; + + return 0; } /** * memory_bm_create - allocate memory for a memory bitmap */ - static int memory_bm_create(struct memory_bitmap *bm, gfp_t gfp_mask, int safe_needed) { struct chain_allocator ca; - struct zone *zone; - struct zone_bitmap *zone_bm; - struct bm_block *bb; - unsigned int nr; + struct list_head mem_extents; + struct mem_extent *ext; + int error; chain_init(&ca, gfp_mask, safe_needed); + INIT_LIST_HEAD(&bm->blocks); - /* Compute the number of zones */ - nr = 0; - for_each_zone(zone) - if (populated_zone(zone)) - nr++; - - /* Allocate the list of zones bitmap objects */ - zone_bm = create_zone_bm_list(nr, &ca); - bm->zone_bm_list = zone_bm; - if (!zone_bm) { - chain_free(&ca, PG_UNSAFE_CLEAR); - return -ENOMEM; - } - - /* Initialize the zone bitmap objects */ - for_each_zone(zone) { - unsigned long pfn; + error = create_mem_extents(&mem_extents, gfp_mask); + if (error) + return error; - if (!populated_zone(zone)) - continue; + list_for_each_entry(ext, &mem_extents, hook) { + struct bm_block *bb; + unsigned long pfn = ext->start; + unsigned long pages = ext->end - ext->start; - zone_bm->start_pfn = zone->zone_start_pfn; - zone_bm->end_pfn = zone->zone_start_pfn + zone->spanned_pages; - /* Allocate the list of bitmap block objects */ - nr = DIV_ROUND_UP(zone->spanned_pages, BM_BITS_PER_BLOCK); - bb = create_bm_block_list(nr, &ca); - zone_bm->bm_blocks = bb; - zone_bm->cur_block = bb; - if (!bb) - goto Free; + bb = list_entry(bm->blocks.prev, struct bm_block, hook); - nr = zone->spanned_pages; - pfn = zone->zone_start_pfn; - /* Initialize the bitmap block objects */ - while (bb) { - unsigned long *ptr; + error = create_bm_block_list(pages, bm->blocks.prev, &ca); + if (error) + goto Error; - ptr = get_image_page(gfp_mask, safe_needed); - bb->data = ptr; - if (!ptr) - goto Free; + list_for_each_entry_continue(bb, &bm->blocks, hook) { + bb->data = get_image_page(gfp_mask, safe_needed); + if (!bb->data) { + error = -ENOMEM; + goto Error; + } bb->start_pfn = pfn; - if (nr >= BM_BITS_PER_BLOCK) { + if (pages >= BM_BITS_PER_BLOCK) { pfn += BM_BITS_PER_BLOCK; - nr -= BM_BITS_PER_BLOCK; + pages -= BM_BITS_PER_BLOCK; } else { /* This is executed only once in the loop */ - pfn += nr; + pfn += pages; } bb->end_pfn = pfn; - bb = bb->next; } - zone_bm = zone_bm->next; } + bm->p_list = ca.chain; memory_bm_position_reset(bm); - return 0; + Exit: + free_mem_extents(&mem_extents); + return error; - Free: + Error: bm->p_list = ca.chain; memory_bm_free(bm, PG_UNSAFE_CLEAR); - return -ENOMEM; + goto Exit; } /** * memory_bm_free - free memory occupied by the memory bitmap @bm */ - static void memory_bm_free(struct memory_bitmap *bm, int clear_nosave_free) { - struct zone_bitmap *zone_bm; + struct bm_block *bb; - /* Free the list of bit blocks for each zone_bitmap object */ - zone_bm = bm->zone_bm_list; - while (zone_bm) { - struct bm_block *bb; + list_for_each_entry(bb, &bm->blocks, hook) + if (bb->data) + free_image_page(bb->data, clear_nosave_free); - bb = zone_bm->bm_blocks; - while (bb) { - if (bb->data) - free_image_page(bb->data, clear_nosave_free); - bb = bb->next; - } - zone_bm = zone_bm->next; - } free_list_of_pages(bm->p_list, clear_nosave_free); - bm->zone_bm_list = NULL; + + INIT_LIST_HEAD(&bm->blocks); } /** @@ -437,38 +452,33 @@ static void memory_bm_free(struct memory_bitmap *bm, int clear_nosave_free) * to given pfn. The cur_zone_bm member of @bm and the cur_block member * of @bm->cur_zone_bm are updated. */ - static int memory_bm_find_bit(struct memory_bitmap *bm, unsigned long pfn, void **addr, unsigned int *bit_nr) { - struct zone_bitmap *zone_bm; struct bm_block *bb; - /* Check if the pfn is from the current zone */ - zone_bm = bm->cur.zone_bm; - if (pfn < zone_bm->start_pfn || pfn >= zone_bm->end_pfn) { - zone_bm = bm->zone_bm_list; - /* We don't assume that the zones are sorted by pfns */ - while (pfn < zone_bm->start_pfn || pfn >= zone_bm->end_pfn) { - zone_bm = zone_bm->next; - - if (!zone_bm) - return -EFAULT; - } - bm->cur.zone_bm = zone_bm; - } - /* Check if the pfn corresponds to the current bitmap block */ - bb = zone_bm->cur_block; + /* + * Check if the pfn corresponds to the current bitmap block and find + * the block where it fits if this is not the case. + */ + bb = bm->cur.block; if (pfn < bb->start_pfn) - bb = zone_bm->bm_blocks; + list_for_each_entry_continue_reverse(bb, &bm->blocks, hook) + if (pfn >= bb->start_pfn) + break; - while (pfn >= bb->end_pfn) { - bb = bb->next; + if (pfn >= bb->end_pfn) + list_for_each_entry_continue(bb, &bm->blocks, hook) + if (pfn >= bb->start_pfn && pfn < bb->end_pfn) + break; - BUG_ON(!bb); - } - zone_bm->cur_block = bb; + if (&bb->hook == &bm->blocks) + return -EFAULT; + + /* The block has been found */ + bm->cur.block = bb; pfn -= bb->start_pfn; + bm->cur.bit = pfn + 1; *bit_nr = pfn; *addr = bb->data; return 0; @@ -538,29 +548,21 @@ static bool memory_bm_pfn_present(struct memory_bitmap *bm, unsigned long pfn) static unsigned long memory_bm_next_pfn(struct memory_bitmap *bm) { - struct zone_bitmap *zone_bm; struct bm_block *bb; int bit; + bb = bm->cur.block; do { - bb = bm->cur.block; - do { - bit = bm->cur.bit; - bit = find_next_bit(bb->data, bm_block_bits(bb), bit); - if (bit < bm_block_bits(bb)) - goto Return_pfn; - - bb = bb->next; - bm->cur.block = bb; - bm->cur.bit = 0; - } while (bb); - zone_bm = bm->cur.zone_bm->next; - if (zone_bm) { - bm->cur.zone_bm = zone_bm; - bm->cur.block = zone_bm->bm_blocks; - bm->cur.bit = 0; - } - } while (zone_bm); + bit = bm->cur.bit; + bit = find_next_bit(bb->data, bm_block_bits(bb), bit); + if (bit < bm_block_bits(bb)) + goto Return_pfn; + + bb = list_entry(bb->hook.next, struct bm_block, hook); + bm->cur.block = bb; + bm->cur.bit = 0; + } while (&bb->hook != &bm->blocks); + memory_bm_position_reset(bm); return BM_END_OF_MAP; @@ -816,8 +818,7 @@ static unsigned int count_free_highmem_pages(void) * We should save the page if it isn't Nosave or NosaveFree, or Reserved, * and it isn't a part of a free chunk of pages. */ - -static struct page *saveable_highmem_page(unsigned long pfn) +static struct page *saveable_highmem_page(struct zone *zone, unsigned long pfn) { struct page *page; @@ -825,6 +826,8 @@ static struct page *saveable_highmem_page(unsigned long pfn) return NULL; page = pfn_to_page(pfn); + if (page_zone(page) != zone) + return NULL; BUG_ON(!PageHighMem(page)); @@ -854,13 +857,16 @@ unsigned int count_highmem_pages(void) mark_free_pages(zone); max_zone_pfn = zone->zone_start_pfn + zone->spanned_pages; for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++) - if (saveable_highmem_page(pfn)) + if (saveable_highmem_page(zone, pfn)) n++; } return n; } #else -static inline void *saveable_highmem_page(unsigned long pfn) { return NULL; } +static inline void *saveable_highmem_page(struct zone *z, unsigned long p) +{ + return NULL; +} #endif /* CONFIG_HIGHMEM */ /** @@ -871,8 +877,7 @@ static inline void *saveable_highmem_page(unsigned long pfn) { return NULL; } * of pages statically defined as 'unsaveable', and it isn't a part of * a free chunk of pages. */ - -static struct page *saveable_page(unsigned long pfn) +static struct page *saveable_page(struct zone *zone, unsigned long pfn) { struct page *page; @@ -880,6 +885,8 @@ static struct page *saveable_page(unsigned long pfn) return NULL; page = pfn_to_page(pfn); + if (page_zone(page) != zone) + return NULL; BUG_ON(PageHighMem(page)); @@ -911,7 +918,7 @@ unsigned int count_data_pages(void) mark_free_pages(zone); max_zone_pfn = zone->zone_start_pfn + zone->spanned_pages; for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++) - if(saveable_page(pfn)) + if (saveable_page(zone, pfn)) n++; } return n; @@ -952,7 +959,7 @@ static inline struct page * page_is_saveable(struct zone *zone, unsigned long pfn) { return is_highmem(zone) ? - saveable_highmem_page(pfn) : saveable_page(pfn); + saveable_highmem_page(zone, pfn) : saveable_page(zone, pfn); } static void copy_data_page(unsigned long dst_pfn, unsigned long src_pfn) @@ -983,7 +990,7 @@ static void copy_data_page(unsigned long dst_pfn, unsigned long src_pfn) } } #else -#define page_is_saveable(zone, pfn) saveable_page(pfn) +#define page_is_saveable(zone, pfn) saveable_page(zone, pfn) static inline void copy_data_page(unsigned long dst_pfn, unsigned long src_pfn) { -- cgit v1.2.3 From baa5835df10254762aedb6cb23a9c1508f969736 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Mon, 8 Dec 2008 00:52:49 +0100 Subject: Hibernate: Replace unnecessary evaluation of pfn_to_page() Replace one evaluation of pfn_to_page() in copy_data_pages() with the value of a local variable containing the right number already. Signed-off-by: Rafael J. Wysocki Acked-by: Pavel Machek Signed-off-by: Len Brown --- kernel/power/snapshot.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index ec9f153b2fc2..f5fc2d7680f2 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -981,7 +981,7 @@ static void copy_data_page(unsigned long dst_pfn, unsigned long src_pfn) * data modified by kmap_atomic() */ safe_copy_page(buffer, s_page); - dst = kmap_atomic(pfn_to_page(dst_pfn), KM_USER0); + dst = kmap_atomic(d_page, KM_USER0); memcpy(dst, buffer, PAGE_SIZE); kunmap_atomic(dst, KM_USER0); } else { -- cgit v1.2.3 From da8d5089da6dfd54e5fd05d0c291a63c2bcf6885 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 7 Jan 2009 15:28:57 +0100 Subject: sched: fix possible recursive rq->lock Vaidyanathan Srinivasan reported: > ============================================= > [ INFO: possible recursive locking detected ] > 2.6.28-autotest-tip-sv #1 > --------------------------------------------- > klogd/5062 is trying to acquire lock: > (&rq->lock){++..}, at: [] task_rq_lock+0x45/0x7e > > but task is already holding lock: > (&rq->lock){++..}, at: [] schedule+0x158/0xa31 With sched_mc at 2. (it is default-off) Strictly speaking we'll not deadlock, because ttwu will not be able to place the migration task on our rq, but since the code can deal with both rqs getting unlocked, this seems the easiest way out. Signed-off-by: Peter Zijlstra Signed-off-by: Ingo Molnar --- kernel/sched.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'kernel') diff --git a/kernel/sched.c b/kernel/sched.c index 2e3545f57e77..deb5ac8c12f3 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -3728,8 +3728,13 @@ redo: } double_unlock_balance(this_rq, busiest); + /* + * Should not call ttwu while holding a rq->lock + */ + spin_unlock(&this_rq->lock); if (active_balance) wake_up_process(busiest->migration_thread); + spin_lock(&this_rq->lock); } else sd->nr_balance_failed = 0; -- cgit v1.2.3 From 22a9d645677feefd402befd02edd59b122289ef1 Mon Sep 17 00:00:00 2001 From: Arjan van de Ven Date: Wed, 7 Jan 2009 08:45:46 -0800 Subject: async: Asynchronous function calls to speed up kernel boot Right now, most of the kernel boot is strictly synchronous, such that various hardware delays are done sequentially. In order to make the kernel boot faster, this patch introduces infrastructure to allow doing some of the initialization steps asynchronously, which will hide significant portions of the hardware delays in practice. In order to not change device order and other similar observables, this patch does NOT do full parallel initialization. Rather, it operates more in the way an out of order CPU does; the work may be done out of order and asynchronous, but the observable effects (instruction retiring for the CPU) are still done in the original sequence. Signed-off-by: Arjan van de Ven --- include/linux/async.h | 25 ++++ init/do_mounts.c | 2 + init/main.c | 5 +- kernel/Makefile | 3 +- kernel/async.c | 321 +++++++++++++++++++++++++++++++++++++++++++++++++ kernel/irq/autoprobe.c | 5 + kernel/module.c | 2 + 7 files changed, 361 insertions(+), 2 deletions(-) create mode 100644 include/linux/async.h create mode 100644 kernel/async.c (limited to 'kernel') diff --git a/include/linux/async.h b/include/linux/async.h new file mode 100644 index 000000000000..c4ecacd0b327 --- /dev/null +++ b/include/linux/async.h @@ -0,0 +1,25 @@ +/* + * async.h: Asynchronous function calls for boot performance + * + * (C) Copyright 2009 Intel Corporation + * Author: Arjan van de Ven + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; version 2 + * of the License. + */ + +#include +#include + +typedef u64 async_cookie_t; +typedef void (async_func_ptr) (void *data, async_cookie_t cookie); + +extern async_cookie_t async_schedule(async_func_ptr *ptr, void *data); +extern async_cookie_t async_schedule_special(async_func_ptr *ptr, void *data, struct list_head *list); +extern void async_synchronize_full(void); +extern void async_synchronize_full_special(struct list_head *list); +extern void async_synchronize_cookie(async_cookie_t cookie); +extern void async_synchronize_cookie_special(async_cookie_t cookie, struct list_head *list); + diff --git a/init/do_mounts.c b/init/do_mounts.c index 5efca73b39f9..708105e163df 100644 --- a/init/do_mounts.c +++ b/init/do_mounts.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include @@ -372,6 +373,7 @@ void __init prepare_namespace(void) /* wait for the known devices to complete their probing */ while (driver_probe_done() != 0) msleep(100); + async_synchronize_full(); md_run_setup(); diff --git a/init/main.c b/init/main.c index b5a892c68375..f66715d8a853 100644 --- a/init/main.c +++ b/init/main.c @@ -62,6 +62,7 @@ #include #include #include +#include #include #include @@ -684,7 +685,7 @@ asmlinkage void __init start_kernel(void) rest_init(); } -static int initcall_debug; +int initcall_debug; core_param(initcall_debug, initcall_debug, bool, 0644); int do_one_initcall(initcall_t fn) @@ -785,6 +786,8 @@ static void run_init_process(char *init_filename) */ static noinline int init_post(void) { + /* need to finish all async __init code before freeing the memory */ + async_synchronize_full(); free_initmem(); unlock_kernel(); mark_rodata_ro(); diff --git a/kernel/Makefile b/kernel/Makefile index e1c5bf3365c0..2921d90ce32f 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -9,7 +9,8 @@ obj-y = sched.o fork.o exec_domain.o panic.o printk.o \ rcupdate.o extable.o params.o posix-timers.o \ kthread.o wait.o kfifo.o sys_ni.o posix-cpu-timers.o mutex.o \ hrtimer.o rwsem.o nsproxy.o srcu.o semaphore.o \ - notifier.o ksysfs.o pm_qos_params.o sched_clock.o cred.o + notifier.o ksysfs.o pm_qos_params.o sched_clock.o cred.o \ + async.o ifdef CONFIG_FUNCTION_TRACER # Do not trace debug files and internal ftrace files diff --git a/kernel/async.c b/kernel/async.c new file mode 100644 index 000000000000..afaa8a653d5a --- /dev/null +++ b/kernel/async.c @@ -0,0 +1,321 @@ +/* + * async.c: Asynchronous function calls for boot performance + * + * (C) Copyright 2009 Intel Corporation + * Author: Arjan van de Ven + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; version 2 + * of the License. + */ + + +/* + +Goals and Theory of Operation + +The primary goal of this feature is to reduce the kernel boot time, +by doing various independent hardware delays and discovery operations +decoupled and not strictly serialized. + +More specifically, the asynchronous function call concept allows +certain operations (primarily during system boot) to happen +asynchronously, out of order, while these operations still +have their externally visible parts happen sequentially and in-order. +(not unlike how out-of-order CPUs retire their instructions in order) + +Key to the asynchronous function call implementation is the concept of +a "sequence cookie" (which, although it has an abstracted type, can be +thought of as a monotonically incrementing number). + +The async core will assign each scheduled event such a sequence cookie and +pass this to the called functions. + +The asynchronously called function should before doing a globally visible +operation, such as registering device numbers, call the +async_synchronize_cookie() function and pass in its own cookie. The +async_synchronize_cookie() function will make sure that all asynchronous +operations that were scheduled prior to the operation corresponding with the +cookie have completed. + +Subsystem/driver initialization code that scheduled asynchronous probe +functions, but which shares global resources with other drivers/subsystems +that do not use the asynchronous call feature, need to do a full +synchronization with the async_synchronize_full() function, before returning +from their init function. This is to maintain strict ordering between the +asynchronous and synchronous parts of the kernel. + +*/ + +#include +#include +#include +#include +#include +#include +#include + +static async_cookie_t next_cookie = 1; + +#define MAX_THREADS 256 +#define MAX_WORK 32768 + +static LIST_HEAD(async_pending); +static LIST_HEAD(async_running); +static DEFINE_SPINLOCK(async_lock); + +struct async_entry { + struct list_head list; + async_cookie_t cookie; + async_func_ptr *func; + void *data; + struct list_head *running; +}; + +static DECLARE_WAIT_QUEUE_HEAD(async_done); +static DECLARE_WAIT_QUEUE_HEAD(async_new); + +static atomic_t entry_count; +static atomic_t thread_count; + +extern int initcall_debug; + + +/* + * MUST be called with the lock held! + */ +static async_cookie_t __lowest_in_progress(struct list_head *running) +{ + struct async_entry *entry; + if (!list_empty(&async_pending)) { + entry = list_first_entry(&async_pending, + struct async_entry, list); + return entry->cookie; + } else if (!list_empty(running)) { + entry = list_first_entry(running, + struct async_entry, list); + return entry->cookie; + } else { + /* nothing in progress... next_cookie is "infinity" */ + return next_cookie; + } + +} +/* + * pick the first pending entry and run it + */ +static void run_one_entry(void) +{ + unsigned long flags; + struct async_entry *entry; + ktime_t calltime, delta, rettime; + + /* 1) pick one task from the pending queue */ + + spin_lock_irqsave(&async_lock, flags); + if (list_empty(&async_pending)) + goto out; + entry = list_first_entry(&async_pending, struct async_entry, list); + + /* 2) move it to the running queue */ + list_del(&entry->list); + list_add_tail(&entry->list, &async_running); + spin_unlock_irqrestore(&async_lock, flags); + + /* 3) run it (and print duration)*/ + if (initcall_debug) { + printk("calling %lli_%pF @ %i\n", entry->cookie, entry->func, task_pid_nr(current)); + calltime = ktime_get(); + } + entry->func(entry->data, entry->cookie); + if (initcall_debug) { + rettime = ktime_get(); + delta = ktime_sub(rettime, calltime); + printk("initcall %lli_%pF returned 0 after %lld usecs\n", entry->cookie, + entry->func, ktime_to_ns(delta) >> 10); + } + + /* 4) remove it from the running queue */ + spin_lock_irqsave(&async_lock, flags); + list_del(&entry->list); + + /* 5) free the entry */ + kfree(entry); + atomic_dec(&entry_count); + + spin_unlock_irqrestore(&async_lock, flags); + + /* 6) wake up any waiters. */ + wake_up(&async_done); + return; + +out: + spin_unlock_irqrestore(&async_lock, flags); +} + + +static async_cookie_t __async_schedule(async_func_ptr *ptr, void *data, struct list_head *running) +{ + struct async_entry *entry; + unsigned long flags; + async_cookie_t newcookie; + + + /* allow irq-off callers */ + entry = kzalloc(sizeof(struct async_entry), GFP_ATOMIC); + + /* + * If we're out of memory or if there's too much work + * pending already, we execute synchronously. + */ + if (!entry || atomic_read(&entry_count) > MAX_WORK) { + kfree(entry); + spin_lock_irqsave(&async_lock, flags); + newcookie = next_cookie++; + spin_unlock_irqrestore(&async_lock, flags); + + /* low on memory.. run synchronously */ + ptr(data, newcookie); + return newcookie; + } + entry->func = ptr; + entry->data = data; + entry->running = running; + + spin_lock_irqsave(&async_lock, flags); + newcookie = entry->cookie = next_cookie++; + list_add_tail(&entry->list, &async_pending); + atomic_inc(&entry_count); + spin_unlock_irqrestore(&async_lock, flags); + wake_up(&async_new); + return newcookie; +} + +async_cookie_t async_schedule(async_func_ptr *ptr, void *data) +{ + return __async_schedule(ptr, data, &async_pending); +} +EXPORT_SYMBOL_GPL(async_schedule); + +async_cookie_t async_schedule_special(async_func_ptr *ptr, void *data, struct list_head *running) +{ + return __async_schedule(ptr, data, running); +} +EXPORT_SYMBOL_GPL(async_schedule_special); + +void async_synchronize_full(void) +{ + async_synchronize_cookie(next_cookie); +} +EXPORT_SYMBOL_GPL(async_synchronize_full); + +void async_synchronize_full_special(struct list_head *list) +{ + async_synchronize_cookie_special(next_cookie, list); +} +EXPORT_SYMBOL_GPL(async_synchronize_full_special); + +void async_synchronize_cookie_special(async_cookie_t cookie, struct list_head *running) +{ + ktime_t starttime, delta, endtime; + + if (initcall_debug) { + printk("async_waiting @ %i\n", task_pid_nr(current)); + starttime = ktime_get(); + } + + wait_event(async_done, __lowest_in_progress(running) >= cookie); + + if (initcall_debug) { + endtime = ktime_get(); + delta = ktime_sub(endtime, starttime); + + printk("async_continuing @ %i after %lli usec\n", + task_pid_nr(current), ktime_to_ns(delta) >> 10); + } +} +EXPORT_SYMBOL_GPL(async_synchronize_cookie_special); + +void async_synchronize_cookie(async_cookie_t cookie) +{ + async_synchronize_cookie_special(cookie, &async_running); +} +EXPORT_SYMBOL_GPL(async_synchronize_cookie); + + +static int async_thread(void *unused) +{ + DECLARE_WAITQUEUE(wq, current); + add_wait_queue(&async_new, &wq); + + while (!kthread_should_stop()) { + int ret = HZ; + set_current_state(TASK_INTERRUPTIBLE); + /* + * check the list head without lock.. false positives + * are dealt with inside run_one_entry() while holding + * the lock. + */ + rmb(); + if (!list_empty(&async_pending)) + run_one_entry(); + else + ret = schedule_timeout(HZ); + + if (ret == 0) { + /* + * we timed out, this means we as thread are redundant. + * we sign off and die, but we to avoid any races there + * is a last-straw check to see if work snuck in. + */ + atomic_dec(&thread_count); + wmb(); /* manager must see our departure first */ + if (list_empty(&async_pending)) + break; + /* + * woops work came in between us timing out and us + * signing off; we need to stay alive and keep working. + */ + atomic_inc(&thread_count); + } + } + remove_wait_queue(&async_new, &wq); + + return 0; +} + +static int async_manager_thread(void *unused) +{ + DECLARE_WAITQUEUE(wq, current); + add_wait_queue(&async_new, &wq); + + while (!kthread_should_stop()) { + int tc, ec; + + set_current_state(TASK_INTERRUPTIBLE); + + tc = atomic_read(&thread_count); + rmb(); + ec = atomic_read(&entry_count); + + while (tc < ec && tc < MAX_THREADS) { + kthread_run(async_thread, NULL, "async/%i", tc); + atomic_inc(&thread_count); + tc++; + } + + schedule(); + } + remove_wait_queue(&async_new, &wq); + + return 0; +} + +static int __init async_init(void) +{ + kthread_run(async_manager_thread, NULL, "async/mgr"); + return 0; +} + +core_initcall(async_init); diff --git a/kernel/irq/autoprobe.c b/kernel/irq/autoprobe.c index cc0f7321b8ce..1de9700f416e 100644 --- a/kernel/irq/autoprobe.c +++ b/kernel/irq/autoprobe.c @@ -10,6 +10,7 @@ #include #include #include +#include #include "internals.h" @@ -34,6 +35,10 @@ unsigned long probe_irq_on(void) unsigned int status; int i; + /* + * quiesce the kernel, or at least the asynchronous portion + */ + async_synchronize_full(); mutex_lock(&probing_active); /* * something may have generated an irq long ago and we want to diff --git a/kernel/module.c b/kernel/module.c index 496dcb57b608..c9332c90d5a0 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -50,6 +50,7 @@ #include #include #include +#include #if 0 #define DEBUGP printk @@ -816,6 +817,7 @@ sys_delete_module(const char __user *name_user, unsigned int flags) mod->exit(); blocking_notifier_call_chain(&module_notify_list, MODULE_STATE_GOING, mod); + async_synchronize_full(); mutex_lock(&module_mutex); /* Store the name of the last unloaded module for diagnostic purposes */ strlcpy(last_unloaded_module, mod->name, sizeof(last_unloaded_module)); -- cgit v1.2.3 From ad160d23198193135cb2bcc75222e0816b5838c0 Mon Sep 17 00:00:00 2001 From: Arjan van de Ven Date: Wed, 7 Jan 2009 09:28:53 -0800 Subject: async: don't do the initcall stuff post boot while tracking the asynchronous calls during boot using the initcall_debug convention is useful, doing it once the kernel is done is actually bad now that we use asynchronous operations post boot as well... Signed-off-by: Arjan van de Ven --- kernel/async.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/async.c b/kernel/async.c index afaa8a653d5a..97373380c9e7 100644 --- a/kernel/async.c +++ b/kernel/async.c @@ -124,12 +124,12 @@ static void run_one_entry(void) spin_unlock_irqrestore(&async_lock, flags); /* 3) run it (and print duration)*/ - if (initcall_debug) { + if (initcall_debug && system_state == SYSTEM_BOOTING) { printk("calling %lli_%pF @ %i\n", entry->cookie, entry->func, task_pid_nr(current)); calltime = ktime_get(); } entry->func(entry->data, entry->cookie); - if (initcall_debug) { + if (initcall_debug && system_state == SYSTEM_BOOTING) { rettime = ktime_get(); delta = ktime_sub(rettime, calltime); printk("initcall %lli_%pF returned 0 after %lld usecs\n", entry->cookie, @@ -220,14 +220,14 @@ void async_synchronize_cookie_special(async_cookie_t cookie, struct list_head *r { ktime_t starttime, delta, endtime; - if (initcall_debug) { + if (initcall_debug && system_state == SYSTEM_BOOTING) { printk("async_waiting @ %i\n", task_pid_nr(current)); starttime = ktime_get(); } wait_event(async_done, __lowest_in_progress(running) >= cookie); - if (initcall_debug) { + if (initcall_debug && system_state == SYSTEM_BOOTING) { endtime = ktime_get(); delta = ktime_sub(endtime, starttime); -- cgit v1.2.3 From e8de1481fd7126ee9e93d6889da6f00c05e1e019 Mon Sep 17 00:00:00 2001 From: Arjan van de Ven Date: Wed, 22 Oct 2008 19:55:31 -0700 Subject: resource: allow MMIO exclusivity for device drivers Device drivers that use pci_request_regions() (and similar APIs) have a reasonable expectation that they are the only ones accessing their device. As part of the e1000e hunt, we were afraid that some userland (X or some bootsplash stuff) was mapping the MMIO region that the driver thought it had exclusively via /dev/mem or via various sysfs resource mappings. This patch adds the option for device drivers to cause their reserved regions to the "banned from /dev/mem use" list, so now both kernel memory and device-exclusive MMIO regions are banned. NOTE: This is only active when CONFIG_STRICT_DEVMEM is set. In addition to the config option, a kernel parameter iomem=relaxed is provided for the cases where developers want to diagnose, in the field, drivers issues from userspace. Reviewed-by: Matthew Wilcox Signed-off-by: Arjan van de Ven Signed-off-by: Jesse Barnes --- Documentation/kernel-parameters.txt | 4 ++ arch/x86/mm/init_32.c | 2 + arch/x86/mm/init_64.c | 2 + drivers/net/e1000e/netdev.c | 2 +- drivers/pci/pci-sysfs.c | 3 + drivers/pci/pci.c | 107 ++++++++++++++++++++++++++++++++---- include/linux/ioport.h | 11 +++- include/linux/pci.h | 3 + kernel/resource.c | 61 +++++++++++++++++++- 9 files changed, 176 insertions(+), 19 deletions(-) (limited to 'kernel') diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 0b3f6711d2f1..0072fabb1dd1 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -918,6 +918,10 @@ and is between 256 and 4096 characters. It is defined in the file inttest= [IA64] + iomem= Disable strict checking of access to MMIO memory + strict regions from userspace. + relaxed + iommu= [x86] off force diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index 544d724caeee..88f1b10de3be 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -328,6 +328,8 @@ int devmem_is_allowed(unsigned long pagenr) { if (pagenr <= 256) return 1; + if (iomem_is_exclusive(pagenr << PAGE_SHIFT)) + return 0; if (!page_is_ram(pagenr)) return 1; return 0; diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 54c437e96541..23f68e77ad1f 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -888,6 +888,8 @@ int devmem_is_allowed(unsigned long pagenr) { if (pagenr <= 256) return 1; + if (iomem_is_exclusive(pagenr << PAGE_SHIFT)) + return 0; if (!page_is_ram(pagenr)) return 1; return 0; diff --git a/drivers/net/e1000e/netdev.c b/drivers/net/e1000e/netdev.c index d4639facd1bd..91817d0afcaf 100644 --- a/drivers/net/e1000e/netdev.c +++ b/drivers/net/e1000e/netdev.c @@ -4807,7 +4807,7 @@ static int __devinit e1000_probe(struct pci_dev *pdev, } } - err = pci_request_selected_regions(pdev, + err = pci_request_selected_regions_exclusive(pdev, pci_select_bars(pdev, IORESOURCE_MEM), e1000e_driver_name); if (err) diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c index 388440e0d222..d5cdccf27a69 100644 --- a/drivers/pci/pci-sysfs.c +++ b/drivers/pci/pci-sysfs.c @@ -620,6 +620,9 @@ pci_mmap_resource(struct kobject *kobj, struct bin_attribute *attr, vma->vm_pgoff += start >> PAGE_SHIFT; mmap_type = res->flags & IORESOURCE_MEM ? pci_mmap_mem : pci_mmap_io; + if (res->flags & IORESOURCE_MEM && iomem_is_exclusive(start)) + return -EINVAL; + return pci_mmap_page_range(pdev, vma, mmap_type, write_combine); } diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 2cfa41e367a7..47663dc0daf7 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -1395,7 +1395,8 @@ void pci_release_region(struct pci_dev *pdev, int bar) * Returns 0 on success, or %EBUSY on error. A warning * message is also printed on failure. */ -int pci_request_region(struct pci_dev *pdev, int bar, const char *res_name) +static int __pci_request_region(struct pci_dev *pdev, int bar, const char *res_name, + int exclusive) { struct pci_devres *dr; @@ -1408,8 +1409,9 @@ int pci_request_region(struct pci_dev *pdev, int bar, const char *res_name) goto err_out; } else if (pci_resource_flags(pdev, bar) & IORESOURCE_MEM) { - if (!request_mem_region(pci_resource_start(pdev, bar), - pci_resource_len(pdev, bar), res_name)) + if (!__request_mem_region(pci_resource_start(pdev, bar), + pci_resource_len(pdev, bar), res_name, + exclusive)) goto err_out; } @@ -1427,6 +1429,47 @@ err_out: return -EBUSY; } +/** + * pci_request_region - Reserved PCI I/O and memory resource + * @pdev: PCI device whose resources are to be reserved + * @bar: BAR to be reserved + * @res_name: Name to be associated with resource. + * + * Mark the PCI region associated with PCI device @pdev BR @bar as + * being reserved by owner @res_name. Do not access any + * address inside the PCI regions unless this call returns + * successfully. + * + * Returns 0 on success, or %EBUSY on error. A warning + * message is also printed on failure. + */ +int pci_request_region(struct pci_dev *pdev, int bar, const char *res_name) +{ + return __pci_request_region(pdev, bar, res_name, 0); +} + +/** + * pci_request_region_exclusive - Reserved PCI I/O and memory resource + * @pdev: PCI device whose resources are to be reserved + * @bar: BAR to be reserved + * @res_name: Name to be associated with resource. + * + * Mark the PCI region associated with PCI device @pdev BR @bar as + * being reserved by owner @res_name. Do not access any + * address inside the PCI regions unless this call returns + * successfully. + * + * Returns 0 on success, or %EBUSY on error. A warning + * message is also printed on failure. + * + * The key difference that _exclusive makes it that userspace is + * explicitly not allowed to map the resource via /dev/mem or + * sysfs. + */ +int pci_request_region_exclusive(struct pci_dev *pdev, int bar, const char *res_name) +{ + return __pci_request_region(pdev, bar, res_name, IORESOURCE_EXCLUSIVE); +} /** * pci_release_selected_regions - Release selected PCI I/O and memory resources * @pdev: PCI device whose resources were previously reserved @@ -1444,20 +1487,14 @@ void pci_release_selected_regions(struct pci_dev *pdev, int bars) pci_release_region(pdev, i); } -/** - * pci_request_selected_regions - Reserve selected PCI I/O and memory resources - * @pdev: PCI device whose resources are to be reserved - * @bars: Bitmask of BARs to be requested - * @res_name: Name to be associated with resource - */ -int pci_request_selected_regions(struct pci_dev *pdev, int bars, - const char *res_name) +int __pci_request_selected_regions(struct pci_dev *pdev, int bars, + const char *res_name, int excl) { int i; for (i = 0; i < 6; i++) if (bars & (1 << i)) - if(pci_request_region(pdev, i, res_name)) + if (__pci_request_region(pdev, i, res_name, excl)) goto err_out; return 0; @@ -1469,6 +1506,26 @@ err_out: return -EBUSY; } + +/** + * pci_request_selected_regions - Reserve selected PCI I/O and memory resources + * @pdev: PCI device whose resources are to be reserved + * @bars: Bitmask of BARs to be requested + * @res_name: Name to be associated with resource + */ +int pci_request_selected_regions(struct pci_dev *pdev, int bars, + const char *res_name) +{ + return __pci_request_selected_regions(pdev, bars, res_name, 0); +} + +int pci_request_selected_regions_exclusive(struct pci_dev *pdev, + int bars, const char *res_name) +{ + return __pci_request_selected_regions(pdev, bars, res_name, + IORESOURCE_EXCLUSIVE); +} + /** * pci_release_regions - Release reserved PCI I/O and memory resources * @pdev: PCI device whose resources were previously reserved by pci_request_regions @@ -1501,6 +1558,29 @@ int pci_request_regions(struct pci_dev *pdev, const char *res_name) return pci_request_selected_regions(pdev, ((1 << 6) - 1), res_name); } +/** + * pci_request_regions_exclusive - Reserved PCI I/O and memory resources + * @pdev: PCI device whose resources are to be reserved + * @res_name: Name to be associated with resource. + * + * Mark all PCI regions associated with PCI device @pdev as + * being reserved by owner @res_name. Do not access any + * address inside the PCI regions unless this call returns + * successfully. + * + * pci_request_regions_exclusive() will mark the region so that + * /dev/mem and the sysfs MMIO access will not be allowed. + * + * Returns 0 on success, or %EBUSY on error. A warning + * message is also printed on failure. + */ +int pci_request_regions_exclusive(struct pci_dev *pdev, const char *res_name) +{ + return pci_request_selected_regions_exclusive(pdev, + ((1 << 6) - 1), res_name); +} + + /** * pci_set_master - enables bus-mastering for device dev * @dev: the PCI device to enable @@ -2149,10 +2229,13 @@ EXPORT_SYMBOL(pci_find_capability); EXPORT_SYMBOL(pci_bus_find_capability); EXPORT_SYMBOL(pci_release_regions); EXPORT_SYMBOL(pci_request_regions); +EXPORT_SYMBOL(pci_request_regions_exclusive); EXPORT_SYMBOL(pci_release_region); EXPORT_SYMBOL(pci_request_region); +EXPORT_SYMBOL(pci_request_region_exclusive); EXPORT_SYMBOL(pci_release_selected_regions); EXPORT_SYMBOL(pci_request_selected_regions); +EXPORT_SYMBOL(pci_request_selected_regions_exclusive); EXPORT_SYMBOL(pci_set_master); EXPORT_SYMBOL(pci_set_mwi); EXPORT_SYMBOL(pci_try_set_mwi); diff --git a/include/linux/ioport.h b/include/linux/ioport.h index 041e95aac2bf..f6bb2ca8e3ba 100644 --- a/include/linux/ioport.h +++ b/include/linux/ioport.h @@ -49,6 +49,7 @@ struct resource_list { #define IORESOURCE_SIZEALIGN 0x00020000 /* size indicates alignment */ #define IORESOURCE_STARTALIGN 0x00040000 /* start field is alignment */ +#define IORESOURCE_EXCLUSIVE 0x08000000 /* Userland may not map this resource */ #define IORESOURCE_DISABLED 0x10000000 #define IORESOURCE_UNSET 0x20000000 #define IORESOURCE_AUTO 0x40000000 @@ -133,13 +134,16 @@ static inline unsigned long resource_type(struct resource *res) } /* Convenience shorthand with allocation */ -#define request_region(start,n,name) __request_region(&ioport_resource, (start), (n), (name)) -#define request_mem_region(start,n,name) __request_region(&iomem_resource, (start), (n), (name)) +#define request_region(start,n,name) __request_region(&ioport_resource, (start), (n), (name), 0) +#define __request_mem_region(start,n,name, excl) __request_region(&iomem_resource, (start), (n), (name), excl) +#define request_mem_region(start,n,name) __request_region(&iomem_resource, (start), (n), (name), 0) +#define request_mem_region_exclusive(start,n,name) \ + __request_region(&iomem_resource, (start), (n), (name), IORESOURCE_EXCLUSIVE) #define rename_region(region, newname) do { (region)->name = (newname); } while (0) extern struct resource * __request_region(struct resource *, resource_size_t start, - resource_size_t n, const char *name); + resource_size_t n, const char *name, int relaxed); /* Compatibility cruft */ #define release_region(start,n) __release_region(&ioport_resource, (start), (n)) @@ -175,6 +179,7 @@ extern struct resource * __devm_request_region(struct device *dev, extern void __devm_release_region(struct device *dev, struct resource *parent, resource_size_t start, resource_size_t n); extern int iomem_map_sanity_check(resource_size_t addr, unsigned long size); +extern int iomem_is_exclusive(u64 addr); #endif /* __ASSEMBLY__ */ #endif /* _LINUX_IOPORT_H */ diff --git a/include/linux/pci.h b/include/linux/pci.h index 59a3dc2059d3..bfcb39ca8879 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -686,10 +686,13 @@ void pci_fixup_irqs(u8 (*)(struct pci_dev *, u8 *), int (*)(struct pci_dev *, u8, u8)); #define HAVE_PCI_REQ_REGIONS 2 int __must_check pci_request_regions(struct pci_dev *, const char *); +int __must_check pci_request_regions_exclusive(struct pci_dev *, const char *); void pci_release_regions(struct pci_dev *); int __must_check pci_request_region(struct pci_dev *, int, const char *); +int __must_check pci_request_region_exclusive(struct pci_dev *, int, const char *); void pci_release_region(struct pci_dev *, int); int pci_request_selected_regions(struct pci_dev *, int, const char *); +int pci_request_selected_regions_exclusive(struct pci_dev *, int, const char *); void pci_release_selected_regions(struct pci_dev *, int); /* drivers/pci/bus.c */ diff --git a/kernel/resource.c b/kernel/resource.c index e633106b12f6..ca6a1536b205 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -623,7 +623,7 @@ resource_size_t resource_alignment(struct resource *res) */ struct resource * __request_region(struct resource *parent, resource_size_t start, resource_size_t n, - const char *name) + const char *name, int flags) { struct resource *res = kzalloc(sizeof(*res), GFP_KERNEL); @@ -634,6 +634,7 @@ struct resource * __request_region(struct resource *parent, res->start = start; res->end = start + n - 1; res->flags = IORESOURCE_BUSY; + res->flags |= flags; write_lock(&resource_lock); @@ -679,7 +680,7 @@ int __check_region(struct resource *parent, resource_size_t start, { struct resource * res; - res = __request_region(parent, start, n, "check-region"); + res = __request_region(parent, start, n, "check-region", 0); if (!res) return -EBUSY; @@ -776,7 +777,7 @@ struct resource * __devm_request_region(struct device *dev, dr->start = start; dr->n = n; - res = __request_region(parent, start, n, name); + res = __request_region(parent, start, n, name, 0); if (res) devres_add(dev, dr); else @@ -876,3 +877,57 @@ int iomem_map_sanity_check(resource_size_t addr, unsigned long size) return err; } + +#ifdef CONFIG_STRICT_DEVMEM +static int strict_iomem_checks = 1; +#else +static int strict_iomem_checks; +#endif + +/* + * check if an address is reserved in the iomem resource tree + * returns 1 if reserved, 0 if not reserved. + */ +int iomem_is_exclusive(u64 addr) +{ + struct resource *p = &iomem_resource; + int err = 0; + loff_t l; + int size = PAGE_SIZE; + + if (!strict_iomem_checks) + return 0; + + addr = addr & PAGE_MASK; + + read_lock(&resource_lock); + for (p = p->child; p ; p = r_next(NULL, p, &l)) { + /* + * We can probably skip the resources without + * IORESOURCE_IO attribute? + */ + if (p->start >= addr + size) + break; + if (p->end < addr) + continue; + if (p->flags & IORESOURCE_BUSY && + p->flags & IORESOURCE_EXCLUSIVE) { + err = 1; + break; + } + } + read_unlock(&resource_lock); + + return err; +} + +static int __init strict_iomem(char *str) +{ + if (strstr(str, "relaxed")) + strict_iomem_checks = 0; + if (strstr(str, "strict")) + strict_iomem_checks = 1; + return 1; +} + +__setup("iomem=", strict_iomem); -- cgit v1.2.3 From 465634adc1d09b490c8ee31885575be39d375d53 Mon Sep 17 00:00:00 2001 From: Robert Richter Date: Wed, 7 Jan 2009 15:32:11 +0100 Subject: ring_buffer: fix ring_buffer_event_length() Function ring_buffer_event_length() provides an interface to detect the length of data stored in an entry. However, the length contains offsets depending on the internal usage. This makes it unusable. This patch fixes this and now ring_buffer_event_length() returns the alligned length that has been used in ring_buffer_lock_reserve(). Cc: Steven Rostedt Signed-off-by: Robert Richter --- kernel/trace/ring_buffer.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 30d57dd01a85..d42b882dfe4b 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -117,7 +117,13 @@ rb_event_length(struct ring_buffer_event *event) */ unsigned ring_buffer_event_length(struct ring_buffer_event *event) { - return rb_event_length(event); + unsigned length = rb_event_length(event); + if (event->type != RINGBUF_TYPE_DATA) + return length; + length -= RB_EVNT_HDR_SIZE; + if (length > RB_MAX_SMALL_DATA + sizeof(event->array[0])) + length -= sizeof(event->array[0]); + return length; } EXPORT_SYMBOL_GPL(ring_buffer_event_length); -- cgit v1.2.3 From 8feae13110d60cc6287afabc2887366b0eb226c2 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 8 Jan 2009 12:04:47 +0000 Subject: NOMMU: Make VMAs per MM as for MMU-mode linux Make VMAs per mm_struct as for MMU-mode linux. This solves two problems: (1) In SYSV SHM where nattch for a segment does not reflect the number of shmat's (and forks) done. (2) In mmap() where the VMA's vm_mm is set to point to the parent mm by an exec'ing process when VM_EXECUTABLE is specified, regardless of the fact that a VMA might be shared and already have its vm_mm assigned to another process or a dead process. A new struct (vm_region) is introduced to track a mapped region and to remember the circumstances under which it may be shared and the vm_list_struct structure is discarded as it's no longer required. This patch makes the following additional changes: (1) Regions are now allocated with alloc_pages() rather than kmalloc() and with no recourse to __GFP_COMP, so the pages are not composite. Instead, each page has a reference on it held by the region. Anything else that is interested in such a page will have to get a reference on it to retain it. When the pages are released due to unmapping, each page is passed to put_page() and will be freed when the page usage count reaches zero. (2) Excess pages are trimmed after an allocation as the allocation must be made as a power-of-2 quantity of pages. (3) VMAs are added to the parent MM's R/B tree and mmap lists. As an MM may end up with overlapping VMAs within the tree, the VMA struct address is appended to the sort key. (4) Non-anonymous VMAs are now added to the backing inode's prio list. (5) Holes may be punched in anonymous VMAs with munmap(), releasing parts of the backing region. The VMA and region structs will be split if necessary. (6) sys_shmdt() only releases one attachment to a SYSV IPC shared memory segment instead of all the attachments at that addresss. Multiple shmat()'s return the same address under NOMMU-mode instead of different virtual addresses as under MMU-mode. (7) Core dumping for ELF-FDPIC requires fewer exceptions for NOMMU-mode. (8) /proc/maps is now the global list of mapped regions, and may list bits that aren't actually mapped anywhere. (9) /proc/meminfo gains a line (tagged "MmapCopy") that indicates the amount of RAM currently allocated by mmap to hold mappable regions that can't be mapped directly. These are copies of the backing device or file if not anonymous. These changes make NOMMU mode more similar to MMU mode. The downside is that NOMMU mode requires some extra memory to track things over NOMMU without this patch (VMAs are no longer shared, and there are now region structs). Signed-off-by: David Howells Tested-by: Mike Frysinger Acked-by: Paul Mundt --- Documentation/nommu-mmap.txt | 18 +- arch/arm/include/asm/mmu.h | 1 - arch/blackfin/include/asm/mmu.h | 1 - arch/blackfin/kernel/ptrace.c | 6 +- arch/blackfin/kernel/traps.c | 11 +- arch/frv/kernel/ptrace.c | 11 +- arch/h8300/include/asm/mmu.h | 1 - arch/m68knommu/include/asm/mmu.h | 1 - arch/sh/include/asm/mmu.h | 1 - fs/binfmt_elf_fdpic.c | 27 +- fs/proc/internal.h | 2 - fs/proc/meminfo.c | 6 + fs/proc/nommu.c | 71 ++- fs/proc/task_nommu.c | 108 +++-- include/asm-frv/mmu.h | 1 - include/asm-m32r/mmu.h | 1 - include/linux/mm.h | 18 +- include/linux/mm_types.h | 18 +- ipc/shm.c | 12 + kernel/fork.c | 4 +- lib/Kconfig.debug | 7 + mm/mmap.c | 10 + mm/nommu.c | 960 +++++++++++++++++++++++++++------------ 23 files changed, 860 insertions(+), 436 deletions(-) (limited to 'kernel') diff --git a/Documentation/nommu-mmap.txt b/Documentation/nommu-mmap.txt index 7714f57caad5..02b89dcf38ac 100644 --- a/Documentation/nommu-mmap.txt +++ b/Documentation/nommu-mmap.txt @@ -109,12 +109,18 @@ and it's also much more restricted in the latter case: FURTHER NOTES ON NO-MMU MMAP ============================ - (*) A request for a private mapping of less than a page in size may not return - a page-aligned buffer. This is because the kernel calls kmalloc() to - allocate the buffer, not get_free_page(). - - (*) A list of all the mappings on the system is visible through /proc/maps in - no-MMU mode. + (*) A request for a private mapping of a file may return a buffer that is not + page-aligned. This is because XIP may take place, and the data may not be + paged aligned in the backing store. + + (*) A request for an anonymous mapping will always be page aligned. If + possible the size of the request should be a power of two otherwise some + of the space may be wasted as the kernel must allocate a power-of-2 + granule but will only discard the excess if appropriately configured as + this has an effect on fragmentation. + + (*) A list of all the private copy and anonymous mappings on the system is + visible through /proc/maps in no-MMU mode. (*) A list of all the mappings in use by a process is visible through /proc//maps in no-MMU mode. diff --git a/arch/arm/include/asm/mmu.h b/arch/arm/include/asm/mmu.h index 53099d4ee421..b561584d04a1 100644 --- a/arch/arm/include/asm/mmu.h +++ b/arch/arm/include/asm/mmu.h @@ -24,7 +24,6 @@ typedef struct { * modified for 2.6 by Hyok S. Choi */ typedef struct { - struct vm_list_struct *vmlist; unsigned long end_brk; } mm_context_t; diff --git a/arch/blackfin/include/asm/mmu.h b/arch/blackfin/include/asm/mmu.h index 757e43906ed4..dbfd686360e6 100644 --- a/arch/blackfin/include/asm/mmu.h +++ b/arch/blackfin/include/asm/mmu.h @@ -10,7 +10,6 @@ struct sram_list_struct { }; typedef struct { - struct vm_list_struct *vmlist; unsigned long end_brk; unsigned long stack_start; diff --git a/arch/blackfin/kernel/ptrace.c b/arch/blackfin/kernel/ptrace.c index d2d388536630..594e325b40e4 100644 --- a/arch/blackfin/kernel/ptrace.c +++ b/arch/blackfin/kernel/ptrace.c @@ -160,15 +160,15 @@ put_reg(struct task_struct *task, int regno, unsigned long data) static inline int is_user_addr_valid(struct task_struct *child, unsigned long start, unsigned long len) { - struct vm_list_struct *vml; + struct vm_area_struct *vma; struct sram_list_struct *sraml; /* overflow */ if (start + len < start) return -EIO; - for (vml = child->mm->context.vmlist; vml; vml = vml->next) - if (start >= vml->vma->vm_start && start + len < vml->vma->vm_end) + vma = find_vma(child->mm, start); + if (vma && start >= vma->vm_start && start + len <= vma->vm_end) return 0; for (sraml = child->mm->context.sram_list; sraml; sraml = sraml->next) diff --git a/arch/blackfin/kernel/traps.c b/arch/blackfin/kernel/traps.c index 17d8e4172896..5b0667da8d05 100644 --- a/arch/blackfin/kernel/traps.c +++ b/arch/blackfin/kernel/traps.c @@ -32,6 +32,7 @@ #include #include #include +#include #include #include #include @@ -83,6 +84,7 @@ static void decode_address(char *buf, unsigned long address) struct mm_struct *mm; unsigned long flags, offset; unsigned char in_atomic = (bfin_read_IPEND() & 0x10) || in_atomic(); + struct rb_node *n; #ifdef CONFIG_KALLSYMS unsigned long symsize; @@ -128,9 +130,10 @@ static void decode_address(char *buf, unsigned long address) if (!mm) continue; - vml = mm->context.vmlist; - while (vml) { - struct vm_area_struct *vma = vml->vma; + for (n = rb_first(&mm->mm_rb); n; n = rb_next(n)) { + struct vm_area_struct *vma; + + vma = rb_entry(n, struct vm_area_struct, vm_rb); if (address >= vma->vm_start && address < vma->vm_end) { char _tmpbuf[256]; @@ -176,8 +179,6 @@ static void decode_address(char *buf, unsigned long address) goto done; } - - vml = vml->next; } if (!in_atomic) mmput(mm); diff --git a/arch/frv/kernel/ptrace.c b/arch/frv/kernel/ptrace.c index 709e9bdc6126..5e7d401d21e7 100644 --- a/arch/frv/kernel/ptrace.c +++ b/arch/frv/kernel/ptrace.c @@ -69,7 +69,8 @@ static inline int put_reg(struct task_struct *task, int regno, } /* - * check that an address falls within the bounds of the target process's memory mappings + * check that an address falls within the bounds of the target process's memory + * mappings */ static inline int is_user_addr_valid(struct task_struct *child, unsigned long start, unsigned long len) @@ -79,11 +80,11 @@ static inline int is_user_addr_valid(struct task_struct *child, return -EIO; return 0; #else - struct vm_list_struct *vml; + struct vm_area_struct *vma; - for (vml = child->mm->context.vmlist; vml; vml = vml->next) - if (start >= vml->vma->vm_start && start + len <= vml->vma->vm_end) - return 0; + vma = find_vma(child->mm, start); + if (vma && start >= vma->vm_start && start + len <= vma->vm_end) + return 0; return -EIO; #endif diff --git a/arch/h8300/include/asm/mmu.h b/arch/h8300/include/asm/mmu.h index 2ce06ea46104..31309969df70 100644 --- a/arch/h8300/include/asm/mmu.h +++ b/arch/h8300/include/asm/mmu.h @@ -4,7 +4,6 @@ /* Copyright (C) 2002, David McCullough */ typedef struct { - struct vm_list_struct *vmlist; unsigned long end_brk; } mm_context_t; diff --git a/arch/m68knommu/include/asm/mmu.h b/arch/m68knommu/include/asm/mmu.h index 5fa6b68353ba..e2da1e6f09fe 100644 --- a/arch/m68knommu/include/asm/mmu.h +++ b/arch/m68knommu/include/asm/mmu.h @@ -4,7 +4,6 @@ /* Copyright (C) 2002, David McCullough */ typedef struct { - struct vm_list_struct *vmlist; unsigned long end_brk; } mm_context_t; diff --git a/arch/sh/include/asm/mmu.h b/arch/sh/include/asm/mmu.h index fdcb93bc6d11..6c43625bb1a5 100644 --- a/arch/sh/include/asm/mmu.h +++ b/arch/sh/include/asm/mmu.h @@ -9,7 +9,6 @@ typedef struct { mm_context_id_t id; void *vdso; #else - struct vm_list_struct *vmlist; unsigned long end_brk; #endif #ifdef CONFIG_BINFMT_ELF_FDPIC diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c index aa5b43205e37..22baf1b13493 100644 --- a/fs/binfmt_elf_fdpic.c +++ b/fs/binfmt_elf_fdpic.c @@ -1567,11 +1567,9 @@ end_coredump: static int elf_fdpic_dump_segments(struct file *file, size_t *size, unsigned long *limit, unsigned long mm_flags) { - struct vm_list_struct *vml; - - for (vml = current->mm->context.vmlist; vml; vml = vml->next) { - struct vm_area_struct *vma = vml->vma; + struct vm_area_struct *vma; + for (vma = current->mm->mmap; vma; vma = vma->vm_next) { if (!maydump(vma, mm_flags)) continue; @@ -1617,9 +1615,6 @@ static int elf_fdpic_core_dump(long signr, struct pt_regs *regs, elf_fpxregset_t *xfpu = NULL; #endif int thread_status_size = 0; -#ifndef CONFIG_MMU - struct vm_list_struct *vml; -#endif elf_addr_t *auxv; unsigned long mm_flags; @@ -1685,13 +1680,7 @@ static int elf_fdpic_core_dump(long signr, struct pt_regs *regs, fill_prstatus(prstatus, current, signr); elf_core_copy_regs(&prstatus->pr_reg, regs); -#ifdef CONFIG_MMU segs = current->mm->map_count; -#else - segs = 0; - for (vml = current->mm->context.vmlist; vml; vml = vml->next) - segs++; -#endif #ifdef ELF_CORE_EXTRA_PHDRS segs += ELF_CORE_EXTRA_PHDRS; #endif @@ -1766,20 +1755,10 @@ static int elf_fdpic_core_dump(long signr, struct pt_regs *regs, mm_flags = current->mm->flags; /* write program headers for segments dump */ - for ( -#ifdef CONFIG_MMU - vma = current->mm->mmap; vma; vma = vma->vm_next -#else - vml = current->mm->context.vmlist; vml; vml = vml->next -#endif - ) { + for (vma = current->mm->mmap; vma; vma = vma->vm_next) { struct elf_phdr phdr; size_t sz; -#ifndef CONFIG_MMU - vma = vml->vma; -#endif - sz = vma->vm_end - vma->vm_start; phdr.p_type = PT_LOAD; diff --git a/fs/proc/internal.h b/fs/proc/internal.h index 3e8aeb8b61ce..cd53ff838498 100644 --- a/fs/proc/internal.h +++ b/fs/proc/internal.h @@ -41,8 +41,6 @@ do { \ (vmi)->used = 0; \ (vmi)->largest_chunk = 0; \ } while(0) - -extern int nommu_vma_show(struct seq_file *, struct vm_area_struct *); #endif extern int proc_tid_stat(struct seq_file *m, struct pid_namespace *ns, diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c index b1675c4e66da..43d23948384a 100644 --- a/fs/proc/meminfo.c +++ b/fs/proc/meminfo.c @@ -73,6 +73,9 @@ static int meminfo_proc_show(struct seq_file *m, void *v) "HighFree: %8lu kB\n" "LowTotal: %8lu kB\n" "LowFree: %8lu kB\n" +#endif +#ifndef CONFIG_MMU + "MmapCopy: %8lu kB\n" #endif "SwapTotal: %8lu kB\n" "SwapFree: %8lu kB\n" @@ -115,6 +118,9 @@ static int meminfo_proc_show(struct seq_file *m, void *v) K(i.freehigh), K(i.totalram-i.totalhigh), K(i.freeram-i.freehigh), +#endif +#ifndef CONFIG_MMU + K((unsigned long) atomic_read(&mmap_pages_allocated)), #endif K(i.totalswap), K(i.freeswap), diff --git a/fs/proc/nommu.c b/fs/proc/nommu.c index 3f87d2632947..b446d7ad0b0d 100644 --- a/fs/proc/nommu.c +++ b/fs/proc/nommu.c @@ -33,33 +33,33 @@ #include "internal.h" /* - * display a single VMA to a sequenced file + * display a single region to a sequenced file */ -int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma) +static int nommu_region_show(struct seq_file *m, struct vm_region *region) { unsigned long ino = 0; struct file *file; dev_t dev = 0; int flags, len; - flags = vma->vm_flags; - file = vma->vm_file; + flags = region->vm_flags; + file = region->vm_file; if (file) { - struct inode *inode = vma->vm_file->f_path.dentry->d_inode; + struct inode *inode = region->vm_file->f_path.dentry->d_inode; dev = inode->i_sb->s_dev; ino = inode->i_ino; } seq_printf(m, "%08lx-%08lx %c%c%c%c %08llx %02x:%02x %lu %n", - vma->vm_start, - vma->vm_end, + region->vm_start, + region->vm_end, flags & VM_READ ? 'r' : '-', flags & VM_WRITE ? 'w' : '-', flags & VM_EXEC ? 'x' : '-', flags & VM_MAYSHARE ? flags & VM_SHARED ? 'S' : 's' : 'p', - ((loff_t)vma->vm_pgoff) << PAGE_SHIFT, + ((loff_t)region->vm_pgoff) << PAGE_SHIFT, MAJOR(dev), MINOR(dev), ino, &len); if (file) { @@ -75,61 +75,54 @@ int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma) } /* - * display a list of all the VMAs the kernel knows about + * display a list of all the REGIONs the kernel knows about * - nommu kernals have a single flat list */ -static int nommu_vma_list_show(struct seq_file *m, void *v) +static int nommu_region_list_show(struct seq_file *m, void *_p) { - struct vm_area_struct *vma; + struct rb_node *p = _p; - vma = rb_entry((struct rb_node *) v, struct vm_area_struct, vm_rb); - return nommu_vma_show(m, vma); + return nommu_region_show(m, rb_entry(p, struct vm_region, vm_rb)); } -static void *nommu_vma_list_start(struct seq_file *m, loff_t *_pos) +static void *nommu_region_list_start(struct seq_file *m, loff_t *_pos) { - struct rb_node *_rb; + struct rb_node *p; loff_t pos = *_pos; - void *next = NULL; - down_read(&nommu_vma_sem); + down_read(&nommu_region_sem); - for (_rb = rb_first(&nommu_vma_tree); _rb; _rb = rb_next(_rb)) { - if (pos == 0) { - next = _rb; - break; - } - pos--; - } - - return next; + for (p = rb_first(&nommu_region_tree); p; p = rb_next(p)) + if (pos-- == 0) + return p; + return NULL; } -static void nommu_vma_list_stop(struct seq_file *m, void *v) +static void nommu_region_list_stop(struct seq_file *m, void *v) { - up_read(&nommu_vma_sem); + up_read(&nommu_region_sem); } -static void *nommu_vma_list_next(struct seq_file *m, void *v, loff_t *pos) +static void *nommu_region_list_next(struct seq_file *m, void *v, loff_t *pos) { (*pos)++; return rb_next((struct rb_node *) v); } -static const struct seq_operations proc_nommu_vma_list_seqop = { - .start = nommu_vma_list_start, - .next = nommu_vma_list_next, - .stop = nommu_vma_list_stop, - .show = nommu_vma_list_show +static struct seq_operations proc_nommu_region_list_seqop = { + .start = nommu_region_list_start, + .next = nommu_region_list_next, + .stop = nommu_region_list_stop, + .show = nommu_region_list_show }; -static int proc_nommu_vma_list_open(struct inode *inode, struct file *file) +static int proc_nommu_region_list_open(struct inode *inode, struct file *file) { - return seq_open(file, &proc_nommu_vma_list_seqop); + return seq_open(file, &proc_nommu_region_list_seqop); } -static const struct file_operations proc_nommu_vma_list_operations = { - .open = proc_nommu_vma_list_open, +static const struct file_operations proc_nommu_region_list_operations = { + .open = proc_nommu_region_list_open, .read = seq_read, .llseek = seq_lseek, .release = seq_release, @@ -137,7 +130,7 @@ static const struct file_operations proc_nommu_vma_list_operations = { static int __init proc_nommu_init(void) { - proc_create("maps", S_IRUGO, NULL, &proc_nommu_vma_list_operations); + proc_create("maps", S_IRUGO, NULL, &proc_nommu_region_list_operations); return 0; } diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c index d4a8be32b902..ca4a48d0d311 100644 --- a/fs/proc/task_nommu.c +++ b/fs/proc/task_nommu.c @@ -15,25 +15,25 @@ */ void task_mem(struct seq_file *m, struct mm_struct *mm) { - struct vm_list_struct *vml; + struct vm_area_struct *vma; + struct rb_node *p; unsigned long bytes = 0, sbytes = 0, slack = 0; down_read(&mm->mmap_sem); - for (vml = mm->context.vmlist; vml; vml = vml->next) { - if (!vml->vma) - continue; + for (p = rb_first(&mm->mm_rb); p; p = rb_next(p)) { + vma = rb_entry(p, struct vm_area_struct, vm_rb); - bytes += kobjsize(vml); + bytes += kobjsize(vma); if (atomic_read(&mm->mm_count) > 1 || - atomic_read(&vml->vma->vm_usage) > 1 - ) { - sbytes += kobjsize((void *) vml->vma->vm_start); - sbytes += kobjsize(vml->vma); + vma->vm_region || + vma->vm_flags & VM_MAYSHARE) { + sbytes += kobjsize((void *) vma->vm_start); + if (vma->vm_region) + sbytes += kobjsize(vma->vm_region); } else { - bytes += kobjsize((void *) vml->vma->vm_start); - bytes += kobjsize(vml->vma); - slack += kobjsize((void *) vml->vma->vm_start) - - (vml->vma->vm_end - vml->vma->vm_start); + bytes += kobjsize((void *) vma->vm_start); + slack += kobjsize((void *) vma->vm_start) - + (vma->vm_end - vma->vm_start); } } @@ -70,13 +70,14 @@ void task_mem(struct seq_file *m, struct mm_struct *mm) unsigned long task_vsize(struct mm_struct *mm) { - struct vm_list_struct *tbp; + struct vm_area_struct *vma; + struct rb_node *p; unsigned long vsize = 0; down_read(&mm->mmap_sem); - for (tbp = mm->context.vmlist; tbp; tbp = tbp->next) { - if (tbp->vma) - vsize += kobjsize((void *) tbp->vma->vm_start); + for (p = rb_first(&mm->mm_rb); p; p = rb_next(p)) { + vma = rb_entry(p, struct vm_area_struct, vm_rb); + vsize += vma->vm_region->vm_end - vma->vm_region->vm_start; } up_read(&mm->mmap_sem); return vsize; @@ -85,16 +86,15 @@ unsigned long task_vsize(struct mm_struct *mm) int task_statm(struct mm_struct *mm, int *shared, int *text, int *data, int *resident) { - struct vm_list_struct *tbp; + struct vm_area_struct *vma; + struct rb_node *p; int size = kobjsize(mm); down_read(&mm->mmap_sem); - for (tbp = mm->context.vmlist; tbp; tbp = tbp->next) { - size += kobjsize(tbp); - if (tbp->vma) { - size += kobjsize(tbp->vma); - size += kobjsize((void *) tbp->vma->vm_start); - } + for (p = rb_first(&mm->mm_rb); p; p = rb_next(p)) { + vma = rb_entry(p, struct vm_area_struct, vm_rb); + size += kobjsize(vma); + size += kobjsize((void *) vma->vm_start); } size += (*text = mm->end_code - mm->start_code); @@ -104,21 +104,63 @@ int task_statm(struct mm_struct *mm, int *shared, int *text, return size; } +/* + * display a single VMA to a sequenced file + */ +static int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma) +{ + unsigned long ino = 0; + struct file *file; + dev_t dev = 0; + int flags, len; + + flags = vma->vm_flags; + file = vma->vm_file; + + if (file) { + struct inode *inode = vma->vm_file->f_path.dentry->d_inode; + dev = inode->i_sb->s_dev; + ino = inode->i_ino; + } + + seq_printf(m, + "%08lx-%08lx %c%c%c%c %08lx %02x:%02x %lu %n", + vma->vm_start, + vma->vm_end, + flags & VM_READ ? 'r' : '-', + flags & VM_WRITE ? 'w' : '-', + flags & VM_EXEC ? 'x' : '-', + flags & VM_MAYSHARE ? flags & VM_SHARED ? 'S' : 's' : 'p', + vma->vm_pgoff << PAGE_SHIFT, + MAJOR(dev), MINOR(dev), ino, &len); + + if (file) { + len = 25 + sizeof(void *) * 6 - len; + if (len < 1) + len = 1; + seq_printf(m, "%*c", len, ' '); + seq_path(m, &file->f_path, ""); + } + + seq_putc(m, '\n'); + return 0; +} + /* * display mapping lines for a particular process's /proc/pid/maps */ -static int show_map(struct seq_file *m, void *_vml) +static int show_map(struct seq_file *m, void *_p) { - struct vm_list_struct *vml = _vml; + struct rb_node *p = _p; - return nommu_vma_show(m, vml->vma); + return nommu_vma_show(m, rb_entry(p, struct vm_area_struct, vm_rb)); } static void *m_start(struct seq_file *m, loff_t *pos) { struct proc_maps_private *priv = m->private; - struct vm_list_struct *vml; struct mm_struct *mm; + struct rb_node *p; loff_t n = *pos; /* pin the task and mm whilst we play with them */ @@ -134,9 +176,9 @@ static void *m_start(struct seq_file *m, loff_t *pos) } /* start from the Nth VMA */ - for (vml = mm->context.vmlist; vml; vml = vml->next) + for (p = rb_first(&mm->mm_rb); p; p = rb_next(p)) if (n-- == 0) - return vml; + return p; return NULL; } @@ -152,12 +194,12 @@ static void m_stop(struct seq_file *m, void *_vml) } } -static void *m_next(struct seq_file *m, void *_vml, loff_t *pos) +static void *m_next(struct seq_file *m, void *_p, loff_t *pos) { - struct vm_list_struct *vml = _vml; + struct rb_node *p = _p; (*pos)++; - return vml ? vml->next : NULL; + return p ? rb_next(p) : NULL; } static const struct seq_operations proc_pid_maps_ops = { diff --git a/include/asm-frv/mmu.h b/include/asm-frv/mmu.h index 22c03714fb14..86ca0e86e7d2 100644 --- a/include/asm-frv/mmu.h +++ b/include/asm-frv/mmu.h @@ -22,7 +22,6 @@ typedef struct { unsigned long dtlb_ptd_mapping; /* [DAMR5] PTD mapping for dtlb cached PGE */ #else - struct vm_list_struct *vmlist; unsigned long end_brk; #endif diff --git a/include/asm-m32r/mmu.h b/include/asm-m32r/mmu.h index d9bd724479cf..150cb92bb666 100644 --- a/include/asm-m32r/mmu.h +++ b/include/asm-m32r/mmu.h @@ -4,7 +4,6 @@ #if !defined(CONFIG_MMU) typedef struct { - struct vm_list_struct *vmlist; unsigned long end_brk; } mm_context_t; diff --git a/include/linux/mm.h b/include/linux/mm.h index 4a3d28c86443..b91a73fd1bcc 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -56,19 +56,9 @@ extern unsigned long mmap_min_addr; extern struct kmem_cache *vm_area_cachep; -/* - * This struct defines the per-mm list of VMAs for uClinux. If CONFIG_MMU is - * disabled, then there's a single shared list of VMAs maintained by the - * system, and mm's subscribe to these individually - */ -struct vm_list_struct { - struct vm_list_struct *next; - struct vm_area_struct *vma; -}; - #ifndef CONFIG_MMU -extern struct rb_root nommu_vma_tree; -extern struct rw_semaphore nommu_vma_sem; +extern struct rb_root nommu_region_tree; +extern struct rw_semaphore nommu_region_sem; extern unsigned int kobjsize(const void *objp); #endif @@ -1061,6 +1051,7 @@ extern void memmap_init_zone(unsigned long, int, unsigned long, unsigned long, enum memmap_context); extern void setup_per_zone_pages_min(void); extern void mem_init(void); +extern void __init mmap_init(void); extern void show_mem(void); extern void si_meminfo(struct sysinfo * val); extern void si_meminfo_node(struct sysinfo *val, int nid); @@ -1072,6 +1063,9 @@ extern void setup_per_cpu_pageset(void); static inline void setup_per_cpu_pageset(void) {} #endif +/* nommu.c */ +extern atomic_t mmap_pages_allocated; + /* prio_tree.c */ void vma_prio_tree_add(struct vm_area_struct *, struct vm_area_struct *old); void vma_prio_tree_insert(struct vm_area_struct *, struct prio_tree_root *); diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 9cfc9b627fdd..1c1e0d3a1714 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -96,6 +96,22 @@ struct page { #endif /* WANT_PAGE_VIRTUAL */ }; +/* + * A region containing a mapping of a non-memory backed file under NOMMU + * conditions. These are held in a global tree and are pinned by the VMAs that + * map parts of them. + */ +struct vm_region { + struct rb_node vm_rb; /* link in global region tree */ + unsigned long vm_flags; /* VMA vm_flags */ + unsigned long vm_start; /* start address of region */ + unsigned long vm_end; /* region initialised to here */ + unsigned long vm_pgoff; /* the offset in vm_file corresponding to vm_start */ + struct file *vm_file; /* the backing file or NULL */ + + atomic_t vm_usage; /* region usage count */ +}; + /* * This struct defines a memory VMM memory area. There is one of these * per VM-area/task. A VM area is any part of the process virtual memory @@ -152,7 +168,7 @@ struct vm_area_struct { unsigned long vm_truncate_count;/* truncate_count or restart_addr */ #ifndef CONFIG_MMU - atomic_t vm_usage; /* refcount (VMAs shared if !MMU) */ + struct vm_region *vm_region; /* NOMMU mapping region */ #endif #ifdef CONFIG_NUMA struct mempolicy *vm_policy; /* NUMA policy for the VMA */ diff --git a/ipc/shm.c b/ipc/shm.c index b125b560240e..d0ab5527bf45 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -990,6 +990,7 @@ asmlinkage long sys_shmdt(char __user *shmaddr) */ vma = find_vma(mm, addr); +#ifdef CONFIG_MMU while (vma) { next = vma->vm_next; @@ -1034,6 +1035,17 @@ asmlinkage long sys_shmdt(char __user *shmaddr) vma = next; } +#else /* CONFIG_MMU */ + /* under NOMMU conditions, the exact address to be destroyed must be + * given */ + retval = -EINVAL; + if (vma->vm_start == addr && vma->vm_ops == &shm_vm_ops) { + do_munmap(mm, vma->vm_start, vma->vm_end - vma->vm_start); + retval = 0; + } + +#endif + up_write(&mm->mmap_sem); return retval; } diff --git a/kernel/fork.c b/kernel/fork.c index 7b8f2a78be3d..0bce4a43bb37 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1481,12 +1481,10 @@ void __init proc_caches_init(void) fs_cachep = kmem_cache_create("fs_cache", sizeof(struct fs_struct), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL); - vm_area_cachep = kmem_cache_create("vm_area_struct", - sizeof(struct vm_area_struct), 0, - SLAB_PANIC, NULL); mm_cachep = kmem_cache_create("mm_struct", sizeof(struct mm_struct), ARCH_MIN_MMSTRUCT_ALIGN, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL); + mmap_init(); } /* diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 2e75478e9c69..d0a32aab03ff 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -512,6 +512,13 @@ config DEBUG_VIRTUAL If unsure, say N. +config DEBUG_NOMMU_REGIONS + bool "Debug the global anon/private NOMMU mapping region tree" + depends on DEBUG_KERNEL && !MMU + help + This option causes the global tree of anonymous and private mapping + regions to be regularly checked for invalid topology. + config DEBUG_WRITECOUNT bool "Debug filesystem writers count" depends on DEBUG_KERNEL diff --git a/mm/mmap.c b/mm/mmap.c index a910c045cfd4..749623196cb9 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2472,3 +2472,13 @@ void mm_drop_all_locks(struct mm_struct *mm) mutex_unlock(&mm_all_locks_mutex); } + +/* + * initialise the VMA slab + */ +void __init mmap_init(void) +{ + vm_area_cachep = kmem_cache_create("vm_area_struct", + sizeof(struct vm_area_struct), 0, + SLAB_PANIC, NULL); +} diff --git a/mm/nommu.c b/mm/nommu.c index 23f355bbe262..0d363dfcf10e 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -6,7 +6,7 @@ * * See Documentation/nommu-mmap.txt * - * Copyright (c) 2004-2005 David Howells + * Copyright (c) 2004-2008 David Howells * Copyright (c) 2000-2003 David McCullough * Copyright (c) 2000-2001 D Jeff Dionne * Copyright (c) 2002 Greg Ungerer @@ -33,6 +33,28 @@ #include #include #include +#include "internal.h" + +static inline __attribute__((format(printf, 1, 2))) +void no_printk(const char *fmt, ...) +{ +} + +#if 0 +#define kenter(FMT, ...) \ + printk(KERN_DEBUG "==> %s("FMT")\n", __func__, ##__VA_ARGS__) +#define kleave(FMT, ...) \ + printk(KERN_DEBUG "<== %s()"FMT"\n", __func__, ##__VA_ARGS__) +#define kdebug(FMT, ...) \ + printk(KERN_DEBUG "xxx" FMT"yyy\n", ##__VA_ARGS__) +#else +#define kenter(FMT, ...) \ + no_printk(KERN_DEBUG "==> %s("FMT")\n", __func__, ##__VA_ARGS__) +#define kleave(FMT, ...) \ + no_printk(KERN_DEBUG "<== %s()"FMT"\n", __func__, ##__VA_ARGS__) +#define kdebug(FMT, ...) \ + no_printk(KERN_DEBUG FMT"\n", ##__VA_ARGS__) +#endif #include "internal.h" @@ -46,12 +68,15 @@ int sysctl_overcommit_ratio = 50; /* default is 50% */ int sysctl_max_map_count = DEFAULT_MAX_MAP_COUNT; int heap_stack_gap = 0; +atomic_t mmap_pages_allocated; + EXPORT_SYMBOL(mem_map); EXPORT_SYMBOL(num_physpages); -/* list of shareable VMAs */ -struct rb_root nommu_vma_tree = RB_ROOT; -DECLARE_RWSEM(nommu_vma_sem); +/* list of mapped, potentially shareable regions */ +static struct kmem_cache *vm_region_jar; +struct rb_root nommu_region_tree = RB_ROOT; +DECLARE_RWSEM(nommu_region_sem); struct vm_operations_struct generic_file_vm_ops = { }; @@ -400,129 +425,174 @@ asmlinkage unsigned long sys_brk(unsigned long brk) return mm->brk = brk; } -#ifdef DEBUG -static void show_process_blocks(void) +/* + * initialise the VMA and region record slabs + */ +void __init mmap_init(void) { - struct vm_list_struct *vml; - - printk("Process blocks %d:", current->pid); - - for (vml = ¤t->mm->context.vmlist; vml; vml = vml->next) { - printk(" %p: %p", vml, vml->vma); - if (vml->vma) - printk(" (%d @%lx #%d)", - kobjsize((void *) vml->vma->vm_start), - vml->vma->vm_start, - atomic_read(&vml->vma->vm_usage)); - printk(vml->next ? " ->" : ".\n"); - } + vm_region_jar = kmem_cache_create("vm_region_jar", + sizeof(struct vm_region), 0, + SLAB_PANIC, NULL); + vm_area_cachep = kmem_cache_create("vm_area_struct", + sizeof(struct vm_area_struct), 0, + SLAB_PANIC, NULL); } -#endif /* DEBUG */ /* - * add a VMA into a process's mm_struct in the appropriate place in the list - * - should be called with mm->mmap_sem held writelocked + * validate the region tree + * - the caller must hold the region lock */ -static void add_vma_to_mm(struct mm_struct *mm, struct vm_list_struct *vml) +#ifdef CONFIG_DEBUG_NOMMU_REGIONS +static noinline void validate_nommu_regions(void) { - struct vm_list_struct **ppv; + struct vm_region *region, *last; + struct rb_node *p, *lastp; - for (ppv = ¤t->mm->context.vmlist; *ppv; ppv = &(*ppv)->next) - if ((*ppv)->vma->vm_start > vml->vma->vm_start) - break; + lastp = rb_first(&nommu_region_tree); + if (!lastp) + return; + + last = rb_entry(lastp, struct vm_region, vm_rb); + if (unlikely(last->vm_end <= last->vm_start)) + BUG(); + + while ((p = rb_next(lastp))) { + region = rb_entry(p, struct vm_region, vm_rb); + last = rb_entry(lastp, struct vm_region, vm_rb); + + if (unlikely(region->vm_end <= region->vm_start)) + BUG(); + if (unlikely(region->vm_start < last->vm_end)) + BUG(); - vml->next = *ppv; - *ppv = vml; + lastp = p; + } } +#else +#define validate_nommu_regions() do {} while(0) +#endif /* - * look up the first VMA in which addr resides, NULL if none - * - should be called with mm->mmap_sem at least held readlocked + * add a region into the global tree */ -struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr) +static void add_nommu_region(struct vm_region *region) { - struct vm_list_struct *loop, *vml; + struct vm_region *pregion; + struct rb_node **p, *parent; - /* search the vm_start ordered list */ - vml = NULL; - for (loop = mm->context.vmlist; loop; loop = loop->next) { - if (loop->vma->vm_start > addr) - break; - vml = loop; + validate_nommu_regions(); + + BUG_ON(region->vm_start & ~PAGE_MASK); + + parent = NULL; + p = &nommu_region_tree.rb_node; + while (*p) { + parent = *p; + pregion = rb_entry(parent, struct vm_region, vm_rb); + if (region->vm_start < pregion->vm_start) + p = &(*p)->rb_left; + else if (region->vm_start > pregion->vm_start) + p = &(*p)->rb_right; + else if (pregion == region) + return; + else + BUG(); } - if (vml && vml->vma->vm_end > addr) - return vml->vma; + rb_link_node(®ion->vm_rb, parent, p); + rb_insert_color(®ion->vm_rb, &nommu_region_tree); - return NULL; + validate_nommu_regions(); } -EXPORT_SYMBOL(find_vma); /* - * find a VMA - * - we don't extend stack VMAs under NOMMU conditions + * delete a region from the global tree */ -struct vm_area_struct *find_extend_vma(struct mm_struct *mm, unsigned long addr) +static void delete_nommu_region(struct vm_region *region) { - return find_vma(mm, addr); -} + BUG_ON(!nommu_region_tree.rb_node); -int expand_stack(struct vm_area_struct *vma, unsigned long address) -{ - return -ENOMEM; + validate_nommu_regions(); + rb_erase(®ion->vm_rb, &nommu_region_tree); + validate_nommu_regions(); } /* - * look up the first VMA exactly that exactly matches addr - * - should be called with mm->mmap_sem at least held readlocked + * free a contiguous series of pages */ -static inline struct vm_area_struct *find_vma_exact(struct mm_struct *mm, - unsigned long addr) +static void free_page_series(unsigned long from, unsigned long to) { - struct vm_list_struct *vml; - - /* search the vm_start ordered list */ - for (vml = mm->context.vmlist; vml; vml = vml->next) { - if (vml->vma->vm_start == addr) - return vml->vma; - if (vml->vma->vm_start > addr) - break; + for (; from < to; from += PAGE_SIZE) { + struct page *page = virt_to_page(from); + + kdebug("- free %lx", from); + atomic_dec(&mmap_pages_allocated); + if (page_count(page) != 1) + kdebug("free page %p [%d]", page, page_count(page)); + put_page(page); } - - return NULL; } /* - * find a VMA in the global tree + * release a reference to a region + * - the caller must hold the region semaphore, which this releases + * - the region may not have been added to the tree yet, in which case vm_end + * will equal vm_start */ -static inline struct vm_area_struct *find_nommu_vma(unsigned long start) +static void __put_nommu_region(struct vm_region *region) + __releases(nommu_region_sem) { - struct vm_area_struct *vma; - struct rb_node *n = nommu_vma_tree.rb_node; + kenter("%p{%d}", region, atomic_read(®ion->vm_usage)); - while (n) { - vma = rb_entry(n, struct vm_area_struct, vm_rb); + BUG_ON(!nommu_region_tree.rb_node); - if (start < vma->vm_start) - n = n->rb_left; - else if (start > vma->vm_start) - n = n->rb_right; - else - return vma; + if (atomic_dec_and_test(®ion->vm_usage)) { + if (region->vm_end > region->vm_start) + delete_nommu_region(region); + up_write(&nommu_region_sem); + + if (region->vm_file) + fput(region->vm_file); + + /* IO memory and memory shared directly out of the pagecache + * from ramfs/tmpfs mustn't be released here */ + if (region->vm_flags & VM_MAPPED_COPY) { + kdebug("free series"); + free_page_series(region->vm_start, region->vm_end); + } + kmem_cache_free(vm_region_jar, region); + } else { + up_write(&nommu_region_sem); } +} - return NULL; +/* + * release a reference to a region + */ +static void put_nommu_region(struct vm_region *region) +{ + down_write(&nommu_region_sem); + __put_nommu_region(region); } /* - * add a VMA in the global tree + * add a VMA into a process's mm_struct in the appropriate place in the list + * and tree and add to the address space's page tree also if not an anonymous + * page + * - should be called with mm->mmap_sem held writelocked */ -static void add_nommu_vma(struct vm_area_struct *vma) +static void add_vma_to_mm(struct mm_struct *mm, struct vm_area_struct *vma) { - struct vm_area_struct *pvma; + struct vm_area_struct *pvma, **pp; struct address_space *mapping; - struct rb_node **p = &nommu_vma_tree.rb_node; - struct rb_node *parent = NULL; + struct rb_node **p, *parent; + + kenter(",%p", vma); + + BUG_ON(!vma->vm_region); + + mm->map_count++; + vma->vm_mm = mm; /* add the VMA to the mapping */ if (vma->vm_file) { @@ -533,42 +603,62 @@ static void add_nommu_vma(struct vm_area_struct *vma) flush_dcache_mmap_unlock(mapping); } - /* add the VMA to the master list */ + /* add the VMA to the tree */ + parent = NULL; + p = &mm->mm_rb.rb_node; while (*p) { parent = *p; pvma = rb_entry(parent, struct vm_area_struct, vm_rb); - if (vma->vm_start < pvma->vm_start) { + /* sort by: start addr, end addr, VMA struct addr in that order + * (the latter is necessary as we may get identical VMAs) */ + if (vma->vm_start < pvma->vm_start) p = &(*p)->rb_left; - } - else if (vma->vm_start > pvma->vm_start) { + else if (vma->vm_start > pvma->vm_start) p = &(*p)->rb_right; - } - else { - /* mappings are at the same address - this can only - * happen for shared-mem chardevs and shared file - * mappings backed by ramfs/tmpfs */ - BUG_ON(!(pvma->vm_flags & VM_SHARED)); - - if (vma < pvma) - p = &(*p)->rb_left; - else if (vma > pvma) - p = &(*p)->rb_right; - else - BUG(); - } + else if (vma->vm_end < pvma->vm_end) + p = &(*p)->rb_left; + else if (vma->vm_end > pvma->vm_end) + p = &(*p)->rb_right; + else if (vma < pvma) + p = &(*p)->rb_left; + else if (vma > pvma) + p = &(*p)->rb_right; + else + BUG(); } rb_link_node(&vma->vm_rb, parent, p); - rb_insert_color(&vma->vm_rb, &nommu_vma_tree); + rb_insert_color(&vma->vm_rb, &mm->mm_rb); + + /* add VMA to the VMA list also */ + for (pp = &mm->mmap; (pvma = *pp); pp = &(*pp)->vm_next) { + if (pvma->vm_start > vma->vm_start) + break; + if (pvma->vm_start < vma->vm_start) + continue; + if (pvma->vm_end < vma->vm_end) + break; + } + + vma->vm_next = *pp; + *pp = vma; } /* - * delete a VMA from the global list + * delete a VMA from its owning mm_struct and address space */ -static void delete_nommu_vma(struct vm_area_struct *vma) +static void delete_vma_from_mm(struct vm_area_struct *vma) { + struct vm_area_struct **pp; struct address_space *mapping; + struct mm_struct *mm = vma->vm_mm; + + kenter("%p", vma); + + mm->map_count--; + if (mm->mmap_cache == vma) + mm->mmap_cache = NULL; /* remove the VMA from the mapping */ if (vma->vm_file) { @@ -579,8 +669,115 @@ static void delete_nommu_vma(struct vm_area_struct *vma) flush_dcache_mmap_unlock(mapping); } - /* remove from the master list */ - rb_erase(&vma->vm_rb, &nommu_vma_tree); + /* remove from the MM's tree and list */ + rb_erase(&vma->vm_rb, &mm->mm_rb); + for (pp = &mm->mmap; *pp; pp = &(*pp)->vm_next) { + if (*pp == vma) { + *pp = vma->vm_next; + break; + } + } + + vma->vm_mm = NULL; +} + +/* + * destroy a VMA record + */ +static void delete_vma(struct mm_struct *mm, struct vm_area_struct *vma) +{ + kenter("%p", vma); + if (vma->vm_ops && vma->vm_ops->close) + vma->vm_ops->close(vma); + if (vma->vm_file) { + fput(vma->vm_file); + if (vma->vm_flags & VM_EXECUTABLE) + removed_exe_file_vma(mm); + } + put_nommu_region(vma->vm_region); + kmem_cache_free(vm_area_cachep, vma); +} + +/* + * look up the first VMA in which addr resides, NULL if none + * - should be called with mm->mmap_sem at least held readlocked + */ +struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr) +{ + struct vm_area_struct *vma; + struct rb_node *n = mm->mm_rb.rb_node; + + /* check the cache first */ + vma = mm->mmap_cache; + if (vma && vma->vm_start <= addr && vma->vm_end > addr) + return vma; + + /* trawl the tree (there may be multiple mappings in which addr + * resides) */ + for (n = rb_first(&mm->mm_rb); n; n = rb_next(n)) { + vma = rb_entry(n, struct vm_area_struct, vm_rb); + if (vma->vm_start > addr) + return NULL; + if (vma->vm_end > addr) { + mm->mmap_cache = vma; + return vma; + } + } + + return NULL; +} +EXPORT_SYMBOL(find_vma); + +/* + * find a VMA + * - we don't extend stack VMAs under NOMMU conditions + */ +struct vm_area_struct *find_extend_vma(struct mm_struct *mm, unsigned long addr) +{ + return find_vma(mm, addr); +} + +/* + * expand a stack to a given address + * - not supported under NOMMU conditions + */ +int expand_stack(struct vm_area_struct *vma, unsigned long address) +{ + return -ENOMEM; +} + +/* + * look up the first VMA exactly that exactly matches addr + * - should be called with mm->mmap_sem at least held readlocked + */ +static struct vm_area_struct *find_vma_exact(struct mm_struct *mm, + unsigned long addr, + unsigned long len) +{ + struct vm_area_struct *vma; + struct rb_node *n = mm->mm_rb.rb_node; + unsigned long end = addr + len; + + /* check the cache first */ + vma = mm->mmap_cache; + if (vma && vma->vm_start == addr && vma->vm_end == end) + return vma; + + /* trawl the tree (there may be multiple mappings in which addr + * resides) */ + for (n = rb_first(&mm->mm_rb); n; n = rb_next(n)) { + vma = rb_entry(n, struct vm_area_struct, vm_rb); + if (vma->vm_start < addr) + continue; + if (vma->vm_start > addr) + return NULL; + if (vma->vm_end == end) { + mm->mmap_cache = vma; + return vma; + } + } + + return NULL; } /* @@ -595,7 +792,7 @@ static int validate_mmap_request(struct file *file, unsigned long pgoff, unsigned long *_capabilities) { - unsigned long capabilities; + unsigned long capabilities, rlen; unsigned long reqprot = prot; int ret; @@ -615,12 +812,12 @@ static int validate_mmap_request(struct file *file, return -EINVAL; /* Careful about overflows.. */ - len = PAGE_ALIGN(len); - if (!len || len > TASK_SIZE) + rlen = PAGE_ALIGN(len); + if (!rlen || rlen > TASK_SIZE) return -ENOMEM; /* offset overflow? */ - if ((pgoff + (len >> PAGE_SHIFT)) < pgoff) + if ((pgoff + (rlen >> PAGE_SHIFT)) < pgoff) return -EOVERFLOW; if (file) { @@ -794,9 +991,10 @@ static unsigned long determine_vm_flags(struct file *file, } /* - * set up a shared mapping on a file + * set up a shared mapping on a file (the driver or filesystem provides and + * pins the storage) */ -static int do_mmap_shared_file(struct vm_area_struct *vma, unsigned long len) +static int do_mmap_shared_file(struct vm_area_struct *vma) { int ret; @@ -814,10 +1012,14 @@ static int do_mmap_shared_file(struct vm_area_struct *vma, unsigned long len) /* * set up a private mapping or an anonymous shared mapping */ -static int do_mmap_private(struct vm_area_struct *vma, unsigned long len) +static int do_mmap_private(struct vm_area_struct *vma, + struct vm_region *region, + unsigned long len) { + struct page *pages; + unsigned long total, point, n, rlen; void *base; - int ret; + int ret, order; /* invoke the file's mapping function so that it can keep track of * shared mappings on devices or memory @@ -836,23 +1038,46 @@ static int do_mmap_private(struct vm_area_struct *vma, unsigned long len) * make a private copy of the data and map that instead */ } + rlen = PAGE_ALIGN(len); + /* allocate some memory to hold the mapping * - note that this may not return a page-aligned address if the object * we're allocating is smaller than a page */ - base = kmalloc(len, GFP_KERNEL|__GFP_COMP); - if (!base) + order = get_order(rlen); + kdebug("alloc order %d for %lx", order, len); + + pages = alloc_pages(GFP_KERNEL, order); + if (!pages) goto enomem; - vma->vm_start = (unsigned long) base; - vma->vm_end = vma->vm_start + len; - vma->vm_flags |= VM_MAPPED_COPY; + /* we allocated a power-of-2 sized page set, so we need to trim off the + * excess */ + total = 1 << order; + atomic_add(total, &mmap_pages_allocated); + + point = rlen >> PAGE_SHIFT; + while (total > point) { + order = ilog2(total - point); + n = 1 << order; + kdebug("shave %lu/%lu @%lu", n, total - point, total); + atomic_sub(n, &mmap_pages_allocated); + total -= n; + set_page_refcounted(pages + total); + __free_pages(pages + total, order); + } + + total = rlen >> PAGE_SHIFT; + for (point = 1; point < total; point++) + set_page_refcounted(&pages[point]); -#ifdef WARN_ON_SLACK - if (len + WARN_ON_SLACK <= kobjsize(result)) - printk("Allocation of %lu bytes from process %d has %lu bytes of slack\n", - len, current->pid, kobjsize(result) - len); -#endif + base = page_address(pages); + region->vm_flags = vma->vm_flags |= VM_MAPPED_COPY; + region->vm_start = (unsigned long) base; + region->vm_end = region->vm_start + rlen; + + vma->vm_start = region->vm_start; + vma->vm_end = region->vm_start + len; if (vma->vm_file) { /* read the contents of a file into the copy */ @@ -864,26 +1089,27 @@ static int do_mmap_private(struct vm_area_struct *vma, unsigned long len) old_fs = get_fs(); set_fs(KERNEL_DS); - ret = vma->vm_file->f_op->read(vma->vm_file, base, len, &fpos); + ret = vma->vm_file->f_op->read(vma->vm_file, base, rlen, &fpos); set_fs(old_fs); if (ret < 0) goto error_free; /* clear the last little bit */ - if (ret < len) - memset(base + ret, 0, len - ret); + if (ret < rlen) + memset(base + ret, 0, rlen - ret); } else { /* if it's an anonymous mapping, then just clear it */ - memset(base, 0, len); + memset(base, 0, rlen); } return 0; error_free: - kfree(base); - vma->vm_start = 0; + free_page_series(region->vm_start, region->vm_end); + region->vm_start = vma->vm_start = 0; + region->vm_end = vma->vm_end = 0; return ret; enomem: @@ -903,13 +1129,14 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long flags, unsigned long pgoff) { - struct vm_list_struct *vml = NULL; - struct vm_area_struct *vma = NULL; + struct vm_area_struct *vma; + struct vm_region *region; struct rb_node *rb; - unsigned long capabilities, vm_flags; - void *result; + unsigned long capabilities, vm_flags, result; int ret; + kenter(",%lx,%lx,%lx,%lx,%lx", addr, len, prot, flags, pgoff); + if (!(flags & MAP_FIXED)) addr = round_hint_to_min(addr); @@ -917,73 +1144,120 @@ unsigned long do_mmap_pgoff(struct file *file, * mapping */ ret = validate_mmap_request(file, addr, len, prot, flags, pgoff, &capabilities); - if (ret < 0) + if (ret < 0) { + kleave(" = %d [val]", ret); return ret; + } /* we've determined that we can make the mapping, now translate what we * now know into VMA flags */ vm_flags = determine_vm_flags(file, prot, flags, capabilities); - /* we're going to need to record the mapping if it works */ - vml = kzalloc(sizeof(struct vm_list_struct), GFP_KERNEL); - if (!vml) - goto error_getting_vml; + /* we're going to need to record the mapping */ + region = kmem_cache_zalloc(vm_region_jar, GFP_KERNEL); + if (!region) + goto error_getting_region; + + vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL); + if (!vma) + goto error_getting_vma; + + atomic_set(®ion->vm_usage, 1); + region->vm_flags = vm_flags; + region->vm_pgoff = pgoff; - down_write(&nommu_vma_sem); + INIT_LIST_HEAD(&vma->anon_vma_node); + vma->vm_flags = vm_flags; + vma->vm_pgoff = pgoff; - /* if we want to share, we need to check for VMAs created by other + if (file) { + region->vm_file = file; + get_file(file); + vma->vm_file = file; + get_file(file); + if (vm_flags & VM_EXECUTABLE) { + added_exe_file_vma(current->mm); + vma->vm_mm = current->mm; + } + } + + down_write(&nommu_region_sem); + + /* if we want to share, we need to check for regions created by other * mmap() calls that overlap with our proposed mapping - * - we can only share with an exact match on most regular files + * - we can only share with a superset match on most regular files * - shared mappings on character devices and memory backed files are * permitted to overlap inexactly as far as we are concerned for in * these cases, sharing is handled in the driver or filesystem rather * than here */ if (vm_flags & VM_MAYSHARE) { - unsigned long pglen = (len + PAGE_SIZE - 1) >> PAGE_SHIFT; - unsigned long vmpglen; + struct vm_region *pregion; + unsigned long pglen, rpglen, pgend, rpgend, start; - /* suppress VMA sharing for shared regions */ - if (vm_flags & VM_SHARED && - capabilities & BDI_CAP_MAP_DIRECT) - goto dont_share_VMAs; + pglen = (len + PAGE_SIZE - 1) >> PAGE_SHIFT; + pgend = pgoff + pglen; - for (rb = rb_first(&nommu_vma_tree); rb; rb = rb_next(rb)) { - vma = rb_entry(rb, struct vm_area_struct, vm_rb); + for (rb = rb_first(&nommu_region_tree); rb; rb = rb_next(rb)) { + pregion = rb_entry(rb, struct vm_region, vm_rb); - if (!(vma->vm_flags & VM_MAYSHARE)) + if (!(pregion->vm_flags & VM_MAYSHARE)) continue; /* search for overlapping mappings on the same file */ - if (vma->vm_file->f_path.dentry->d_inode != file->f_path.dentry->d_inode) + if (pregion->vm_file->f_path.dentry->d_inode != + file->f_path.dentry->d_inode) continue; - if (vma->vm_pgoff >= pgoff + pglen) + if (pregion->vm_pgoff >= pgend) continue; - vmpglen = vma->vm_end - vma->vm_start + PAGE_SIZE - 1; - vmpglen >>= PAGE_SHIFT; - if (pgoff >= vma->vm_pgoff + vmpglen) + rpglen = pregion->vm_end - pregion->vm_start; + rpglen = (rpglen + PAGE_SIZE - 1) >> PAGE_SHIFT; + rpgend = pregion->vm_pgoff + rpglen; + if (pgoff >= rpgend) continue; - /* handle inexactly overlapping matches between mappings */ - if (vma->vm_pgoff != pgoff || vmpglen != pglen) { + /* handle inexactly overlapping matches between + * mappings */ + if ((pregion->vm_pgoff != pgoff || rpglen != pglen) && + !(pgoff >= pregion->vm_pgoff && pgend <= rpgend)) { + /* new mapping is not a subset of the region */ if (!(capabilities & BDI_CAP_MAP_DIRECT)) goto sharing_violation; continue; } - /* we've found a VMA we can share */ - atomic_inc(&vma->vm_usage); - - vml->vma = vma; - result = (void *) vma->vm_start; - goto shared; + /* we've found a region we can share */ + atomic_inc(&pregion->vm_usage); + vma->vm_region = pregion; + start = pregion->vm_start; + start += (pgoff - pregion->vm_pgoff) << PAGE_SHIFT; + vma->vm_start = start; + vma->vm_end = start + len; + + if (pregion->vm_flags & VM_MAPPED_COPY) { + kdebug("share copy"); + vma->vm_flags |= VM_MAPPED_COPY; + } else { + kdebug("share mmap"); + ret = do_mmap_shared_file(vma); + if (ret < 0) { + vma->vm_region = NULL; + vma->vm_start = 0; + vma->vm_end = 0; + atomic_dec(&pregion->vm_usage); + pregion = NULL; + goto error_just_free; + } + } + fput(region->vm_file); + kmem_cache_free(vm_region_jar, region); + region = pregion; + result = start; + goto share; } - dont_share_VMAs: - vma = NULL; - /* obtain the address at which to make a shared mapping * - this is the hook for quasi-memory character devices to * tell us the location of a shared mapping @@ -994,102 +1268,93 @@ unsigned long do_mmap_pgoff(struct file *file, if (IS_ERR((void *) addr)) { ret = addr; if (ret != (unsigned long) -ENOSYS) - goto error; + goto error_just_free; /* the driver refused to tell us where to site * the mapping so we'll have to attempt to copy * it */ ret = (unsigned long) -ENODEV; if (!(capabilities & BDI_CAP_MAP_COPY)) - goto error; + goto error_just_free; capabilities &= ~BDI_CAP_MAP_DIRECT; + } else { + vma->vm_start = region->vm_start = addr; + vma->vm_end = region->vm_end = addr + len; } } } - /* we're going to need a VMA struct as well */ - vma = kzalloc(sizeof(struct vm_area_struct), GFP_KERNEL); - if (!vma) - goto error_getting_vma; - - INIT_LIST_HEAD(&vma->anon_vma_node); - atomic_set(&vma->vm_usage, 1); - if (file) { - get_file(file); - if (vm_flags & VM_EXECUTABLE) { - added_exe_file_vma(current->mm); - vma->vm_mm = current->mm; - } - } - vma->vm_file = file; - vma->vm_flags = vm_flags; - vma->vm_start = addr; - vma->vm_end = addr + len; - vma->vm_pgoff = pgoff; - - vml->vma = vma; + vma->vm_region = region; /* set up the mapping */ if (file && vma->vm_flags & VM_SHARED) - ret = do_mmap_shared_file(vma, len); + ret = do_mmap_shared_file(vma); else - ret = do_mmap_private(vma, len); + ret = do_mmap_private(vma, region, len); if (ret < 0) - goto error; + goto error_put_region; + + add_nommu_region(region); /* okay... we have a mapping; now we have to register it */ - result = (void *) vma->vm_start; + result = vma->vm_start; current->mm->total_vm += len >> PAGE_SHIFT; - add_nommu_vma(vma); +share: + add_vma_to_mm(current->mm, vma); - shared: - add_vma_to_mm(current->mm, vml); - - up_write(&nommu_vma_sem); + up_write(&nommu_region_sem); if (prot & PROT_EXEC) - flush_icache_range((unsigned long) result, - (unsigned long) result + len); + flush_icache_range(result, result + len); -#ifdef DEBUG - printk("do_mmap:\n"); - show_process_blocks(); -#endif + kleave(" = %lx", result); + return result; - return (unsigned long) result; - - error: - up_write(&nommu_vma_sem); - kfree(vml); +error_put_region: + __put_nommu_region(region); if (vma) { if (vma->vm_file) { fput(vma->vm_file); if (vma->vm_flags & VM_EXECUTABLE) removed_exe_file_vma(vma->vm_mm); } - kfree(vma); + kmem_cache_free(vm_area_cachep, vma); } + kleave(" = %d [pr]", ret); return ret; - sharing_violation: - up_write(&nommu_vma_sem); - printk("Attempt to share mismatched mappings\n"); - kfree(vml); - return -EINVAL; +error_just_free: + up_write(&nommu_region_sem); +error: + fput(region->vm_file); + kmem_cache_free(vm_region_jar, region); + fput(vma->vm_file); + if (vma->vm_flags & VM_EXECUTABLE) + removed_exe_file_vma(vma->vm_mm); + kmem_cache_free(vm_area_cachep, vma); + kleave(" = %d", ret); + return ret; + +sharing_violation: + up_write(&nommu_region_sem); + printk(KERN_WARNING "Attempt to share mismatched mappings\n"); + ret = -EINVAL; + goto error; - error_getting_vma: - up_write(&nommu_vma_sem); - kfree(vml); - printk("Allocation of vma for %lu byte allocation from process %d failed\n", +error_getting_vma: + kmem_cache_free(vm_region_jar, region); + printk(KERN_WARNING "Allocation of vma for %lu byte allocation" + " from process %d failed\n", len, current->pid); show_free_areas(); return -ENOMEM; - error_getting_vml: - printk("Allocation of vml for %lu byte allocation from process %d failed\n", +error_getting_region: + printk(KERN_WARNING "Allocation of vm region for %lu byte allocation" + " from process %d failed\n", len, current->pid); show_free_areas(); return -ENOMEM; @@ -1097,77 +1362,180 @@ unsigned long do_mmap_pgoff(struct file *file, EXPORT_SYMBOL(do_mmap_pgoff); /* - * handle mapping disposal for uClinux + * split a vma into two pieces at address 'addr', a new vma is allocated either + * for the first part or the tail. */ -static void put_vma(struct mm_struct *mm, struct vm_area_struct *vma) +int split_vma(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long addr, int new_below) { - if (vma) { - down_write(&nommu_vma_sem); + struct vm_area_struct *new; + struct vm_region *region; + unsigned long npages; - if (atomic_dec_and_test(&vma->vm_usage)) { - delete_nommu_vma(vma); + kenter(""); - if (vma->vm_ops && vma->vm_ops->close) - vma->vm_ops->close(vma); + /* we're only permitted to split anonymous regions that have a single + * owner */ + if (vma->vm_file || + atomic_read(&vma->vm_region->vm_usage) != 1) + return -ENOMEM; - /* IO memory and memory shared directly out of the pagecache from - * ramfs/tmpfs mustn't be released here */ - if (vma->vm_flags & VM_MAPPED_COPY) - kfree((void *) vma->vm_start); + if (mm->map_count >= sysctl_max_map_count) + return -ENOMEM; - if (vma->vm_file) { - fput(vma->vm_file); - if (vma->vm_flags & VM_EXECUTABLE) - removed_exe_file_vma(mm); - } - kfree(vma); - } + region = kmem_cache_alloc(vm_region_jar, GFP_KERNEL); + if (!region) + return -ENOMEM; + + new = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL); + if (!new) { + kmem_cache_free(vm_region_jar, region); + return -ENOMEM; + } + + /* most fields are the same, copy all, and then fixup */ + *new = *vma; + *region = *vma->vm_region; + new->vm_region = region; + + npages = (addr - vma->vm_start) >> PAGE_SHIFT; + + if (new_below) { + region->vm_end = new->vm_end = addr; + } else { + region->vm_start = new->vm_start = addr; + region->vm_pgoff = new->vm_pgoff += npages; + } - up_write(&nommu_vma_sem); + if (new->vm_ops && new->vm_ops->open) + new->vm_ops->open(new); + + delete_vma_from_mm(vma); + down_write(&nommu_region_sem); + delete_nommu_region(vma->vm_region); + if (new_below) { + vma->vm_region->vm_start = vma->vm_start = addr; + vma->vm_region->vm_pgoff = vma->vm_pgoff += npages; + } else { + vma->vm_region->vm_end = vma->vm_end = addr; } + add_nommu_region(vma->vm_region); + add_nommu_region(new->vm_region); + up_write(&nommu_region_sem); + add_vma_to_mm(mm, vma); + add_vma_to_mm(mm, new); + return 0; } /* - * release a mapping - * - under NOMMU conditions the parameters must match exactly to the mapping to - * be removed + * shrink a VMA by removing the specified chunk from either the beginning or + * the end */ -int do_munmap(struct mm_struct *mm, unsigned long addr, size_t len) +static int shrink_vma(struct mm_struct *mm, + struct vm_area_struct *vma, + unsigned long from, unsigned long to) { - struct vm_list_struct *vml, **parent; - unsigned long end = addr + len; + struct vm_region *region; -#ifdef DEBUG - printk("do_munmap:\n"); -#endif + kenter(""); - for (parent = &mm->context.vmlist; *parent; parent = &(*parent)->next) { - if ((*parent)->vma->vm_start > addr) - break; - if ((*parent)->vma->vm_start == addr && - ((len == 0) || ((*parent)->vma->vm_end == end))) - goto found; - } + /* adjust the VMA's pointers, which may reposition it in the MM's tree + * and list */ + delete_vma_from_mm(vma); + if (from > vma->vm_start) + vma->vm_end = from; + else + vma->vm_start = to; + add_vma_to_mm(mm, vma); - printk("munmap of non-mmaped memory by process %d (%s): %p\n", - current->pid, current->comm, (void *) addr); - return -EINVAL; + /* cut the backing region down to size */ + region = vma->vm_region; + BUG_ON(atomic_read(®ion->vm_usage) != 1); - found: - vml = *parent; + down_write(&nommu_region_sem); + delete_nommu_region(region); + if (from > region->vm_start) + region->vm_end = from; + else + region->vm_start = to; + add_nommu_region(region); + up_write(&nommu_region_sem); - put_vma(mm, vml->vma); + free_page_series(from, to); + return 0; +} - *parent = vml->next; - kfree(vml); +/* + * release a mapping + * - under NOMMU conditions the chunk to be unmapped must be backed by a single + * VMA, though it need not cover the whole VMA + */ +int do_munmap(struct mm_struct *mm, unsigned long start, size_t len) +{ + struct vm_area_struct *vma; + struct rb_node *rb; + unsigned long end = start + len; + int ret; - update_hiwater_vm(mm); - mm->total_vm -= len >> PAGE_SHIFT; + kenter(",%lx,%zx", start, len); -#ifdef DEBUG - show_process_blocks(); -#endif + if (len == 0) + return -EINVAL; + + /* find the first potentially overlapping VMA */ + vma = find_vma(mm, start); + if (!vma) { + printk(KERN_WARNING + "munmap of memory not mmapped by process %d (%s):" + " 0x%lx-0x%lx\n", + current->pid, current->comm, start, start + len - 1); + return -EINVAL; + } + /* we're allowed to split an anonymous VMA but not a file-backed one */ + if (vma->vm_file) { + do { + if (start > vma->vm_start) { + kleave(" = -EINVAL [miss]"); + return -EINVAL; + } + if (end == vma->vm_end) + goto erase_whole_vma; + rb = rb_next(&vma->vm_rb); + vma = rb_entry(rb, struct vm_area_struct, vm_rb); + } while (rb); + kleave(" = -EINVAL [split file]"); + return -EINVAL; + } else { + /* the chunk must be a subset of the VMA found */ + if (start == vma->vm_start && end == vma->vm_end) + goto erase_whole_vma; + if (start < vma->vm_start || end > vma->vm_end) { + kleave(" = -EINVAL [superset]"); + return -EINVAL; + } + if (start & ~PAGE_MASK) { + kleave(" = -EINVAL [unaligned start]"); + return -EINVAL; + } + if (end != vma->vm_end && end & ~PAGE_MASK) { + kleave(" = -EINVAL [unaligned split]"); + return -EINVAL; + } + if (start != vma->vm_start && end != vma->vm_end) { + ret = split_vma(mm, vma, start, 1); + if (ret < 0) { + kleave(" = %d [split]", ret); + return ret; + } + } + return shrink_vma(mm, vma, start, end); + } + +erase_whole_vma: + delete_vma_from_mm(vma); + delete_vma(mm, vma); + kleave(" = 0"); return 0; } EXPORT_SYMBOL(do_munmap); @@ -1184,29 +1552,26 @@ asmlinkage long sys_munmap(unsigned long addr, size_t len) } /* - * Release all mappings + * release all the mappings made in a process's VM space */ -void exit_mmap(struct mm_struct * mm) +void exit_mmap(struct mm_struct *mm) { - struct vm_list_struct *tmp; + struct vm_area_struct *vma; - if (mm) { -#ifdef DEBUG - printk("Exit_mmap:\n"); -#endif + if (!mm) + return; - mm->total_vm = 0; + kenter(""); - while ((tmp = mm->context.vmlist)) { - mm->context.vmlist = tmp->next; - put_vma(mm, tmp->vma); - kfree(tmp); - } + mm->total_vm = 0; -#ifdef DEBUG - show_process_blocks(); -#endif + while ((vma = mm->mmap)) { + mm->mmap = vma->vm_next; + delete_vma_from_mm(vma); + delete_vma(mm, vma); } + + kleave(""); } unsigned long do_brk(unsigned long addr, unsigned long len) @@ -1219,8 +1584,8 @@ unsigned long do_brk(unsigned long addr, unsigned long len) * time (controlled by the MREMAP_MAYMOVE flag and available VM space) * * under NOMMU conditions, we only permit changing a mapping's size, and only - * as long as it stays within the hole allocated by the kmalloc() call in - * do_mmap_pgoff() and the block is not shareable + * as long as it stays within the region allocated by do_mmap_private() and the + * block is not shareable * * MREMAP_FIXED is not supported under NOMMU conditions */ @@ -1231,13 +1596,16 @@ unsigned long do_mremap(unsigned long addr, struct vm_area_struct *vma; /* insanity checks first */ - if (new_len == 0) + if (old_len == 0 || new_len == 0) return (unsigned long) -EINVAL; + if (addr & ~PAGE_MASK) + return -EINVAL; + if (flags & MREMAP_FIXED && new_addr != addr) return (unsigned long) -EINVAL; - vma = find_vma_exact(current->mm, addr); + vma = find_vma_exact(current->mm, addr, old_len); if (!vma) return (unsigned long) -EINVAL; @@ -1247,19 +1615,19 @@ unsigned long do_mremap(unsigned long addr, if (vma->vm_flags & VM_MAYSHARE) return (unsigned long) -EPERM; - if (new_len > kobjsize((void *) addr)) + if (new_len > vma->vm_region->vm_end - vma->vm_region->vm_start) return (unsigned long) -ENOMEM; /* all checks complete - do it */ vma->vm_end = vma->vm_start + new_len; - return vma->vm_start; } EXPORT_SYMBOL(do_mremap); -asmlinkage unsigned long sys_mremap(unsigned long addr, - unsigned long old_len, unsigned long new_len, - unsigned long flags, unsigned long new_addr) +asmlinkage +unsigned long sys_mremap(unsigned long addr, + unsigned long old_len, unsigned long new_len, + unsigned long flags, unsigned long new_addr) { unsigned long ret; -- cgit v1.2.3 From dd8632a12e500a684478fea0951f380478d56fed Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Thu, 8 Jan 2009 12:04:47 +0000 Subject: NOMMU: Make mmap allocation page trimming behaviour configurable. NOMMU mmap allocates a piece of memory for an mmap that's rounded up in size to the nearest power-of-2 number of pages. Currently it then discards the excess pages back to the page allocator, making that memory available for use by other things. This can, however, cause greater amount of fragmentation. To counter this, a sysctl is added in order to fine-tune the trimming behaviour. The default behaviour remains to trim pages aggressively, while this can either be disabled completely or set to a higher page-granular watermark in order to have finer-grained control. vm region vm_top bits taken from an earlier patch by David Howells. Signed-off-by: Paul Mundt Signed-off-by: David Howells Tested-by: Mike Frysinger --- Documentation/nommu-mmap.txt | 15 ++++++++++ Documentation/sysctl/vm.txt | 18 ++++++++++++ include/linux/mm_types.h | 1 + kernel/sysctl.c | 14 ++++++++++ mm/nommu.c | 65 ++++++++++++++++++++++++++++---------------- 5 files changed, 90 insertions(+), 23 deletions(-) (limited to 'kernel') diff --git a/Documentation/nommu-mmap.txt b/Documentation/nommu-mmap.txt index 02b89dcf38ac..b565e8279d13 100644 --- a/Documentation/nommu-mmap.txt +++ b/Documentation/nommu-mmap.txt @@ -248,3 +248,18 @@ PROVIDING SHAREABLE BLOCK DEVICE SUPPORT Provision of shared mappings on block device files is exactly the same as for character devices. If there isn't a real device underneath, then the driver should allocate sufficient contiguous memory to honour any supported mapping. + + +================================= +ADJUSTING PAGE TRIMMING BEHAVIOUR +================================= + +NOMMU mmap automatically rounds up to the nearest power-of-2 number of pages +when performing an allocation. This can have adverse effects on memory +fragmentation, and as such, is left configurable. The default behaviour is to +aggressively trim allocations and discard any excess pages back in to the page +allocator. In order to retain finer-grained control over fragmentation, this +behaviour can either be disabled completely, or bumped up to a higher page +watermark where trimming begins. + +Page trimming behaviour is configurable via the sysctl `vm.nr_trim_pages'. diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt index cd05994a49e6..a3415070bcac 100644 --- a/Documentation/sysctl/vm.txt +++ b/Documentation/sysctl/vm.txt @@ -38,6 +38,7 @@ Currently, these files are in /proc/sys/vm: - numa_zonelist_order - nr_hugepages - nr_overcommit_hugepages +- nr_trim_pages (only if CONFIG_MMU=n) ============================================================== @@ -348,3 +349,20 @@ Change the maximum size of the hugepage pool. The maximum is nr_hugepages + nr_overcommit_hugepages. See Documentation/vm/hugetlbpage.txt + +============================================================== + +nr_trim_pages + +This is available only on NOMMU kernels. + +This value adjusts the excess page trimming behaviour of power-of-2 aligned +NOMMU mmap allocations. + +A value of 0 disables trimming of allocations entirely, while a value of 1 +trims excess pages aggressively. Any value >= 1 acts as the watermark where +trimming of allocations is initiated. + +The default value is 1. + +See Documentation/nommu-mmap.txt for more information. diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 1c1e0d3a1714..92915e81443f 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -106,6 +106,7 @@ struct vm_region { unsigned long vm_flags; /* VMA vm_flags */ unsigned long vm_start; /* start address of region */ unsigned long vm_end; /* region initialised to here */ + unsigned long vm_top; /* region allocated to here */ unsigned long vm_pgoff; /* the offset in vm_file corresponding to vm_start */ struct file *vm_file; /* the backing file or NULL */ diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 92f6e5bc3c24..89d74436318c 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -82,6 +82,9 @@ extern int percpu_pagelist_fraction; extern int compat_log; extern int latencytop_enabled; extern int sysctl_nr_open_min, sysctl_nr_open_max; +#ifndef CONFIG_MMU +extern int sysctl_nr_trim_pages; +#endif #ifdef CONFIG_RCU_TORTURE_TEST extern int rcutorture_runnable; #endif /* #ifdef CONFIG_RCU_TORTURE_TEST */ @@ -1102,6 +1105,17 @@ static struct ctl_table vm_table[] = { .mode = 0644, .proc_handler = &proc_dointvec }, +#else + { + .ctl_name = CTL_UNNUMBERED, + .procname = "nr_trim_pages", + .data = &sysctl_nr_trim_pages, + .maxlen = sizeof(sysctl_nr_trim_pages), + .mode = 0644, + .proc_handler = &proc_dointvec_minmax, + .strategy = &sysctl_intvec, + .extra1 = &zero, + }, #endif { .ctl_name = VM_LAPTOP_MODE, diff --git a/mm/nommu.c b/mm/nommu.c index 0d363dfcf10e..a6e8ccfbd400 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -10,7 +10,7 @@ * Copyright (c) 2000-2003 David McCullough * Copyright (c) 2000-2001 D Jeff Dionne * Copyright (c) 2002 Greg Ungerer - * Copyright (c) 2007 Paul Mundt + * Copyright (c) 2007-2008 Paul Mundt */ #include @@ -66,6 +66,7 @@ atomic_long_t vm_committed_space = ATOMIC_LONG_INIT(0); int sysctl_overcommit_memory = OVERCOMMIT_GUESS; /* heuristic overcommit */ int sysctl_overcommit_ratio = 50; /* default is 50% */ int sysctl_max_map_count = DEFAULT_MAX_MAP_COUNT; +int sysctl_nr_trim_pages = 1; /* page trimming behaviour */ int heap_stack_gap = 0; atomic_t mmap_pages_allocated; @@ -455,6 +456,8 @@ static noinline void validate_nommu_regions(void) last = rb_entry(lastp, struct vm_region, vm_rb); if (unlikely(last->vm_end <= last->vm_start)) BUG(); + if (unlikely(last->vm_top < last->vm_end)) + BUG(); while ((p = rb_next(lastp))) { region = rb_entry(p, struct vm_region, vm_rb); @@ -462,7 +465,9 @@ static noinline void validate_nommu_regions(void) if (unlikely(region->vm_end <= region->vm_start)) BUG(); - if (unlikely(region->vm_start < last->vm_end)) + if (unlikely(region->vm_top < region->vm_end)) + BUG(); + if (unlikely(region->vm_start < last->vm_top)) BUG(); lastp = p; @@ -536,7 +541,7 @@ static void free_page_series(unsigned long from, unsigned long to) /* * release a reference to a region * - the caller must hold the region semaphore, which this releases - * - the region may not have been added to the tree yet, in which case vm_end + * - the region may not have been added to the tree yet, in which case vm_top * will equal vm_start */ static void __put_nommu_region(struct vm_region *region) @@ -547,7 +552,7 @@ static void __put_nommu_region(struct vm_region *region) BUG_ON(!nommu_region_tree.rb_node); if (atomic_dec_and_test(®ion->vm_usage)) { - if (region->vm_end > region->vm_start) + if (region->vm_top > region->vm_start) delete_nommu_region(region); up_write(&nommu_region_sem); @@ -558,7 +563,7 @@ static void __put_nommu_region(struct vm_region *region) * from ramfs/tmpfs mustn't be released here */ if (region->vm_flags & VM_MAPPED_COPY) { kdebug("free series"); - free_page_series(region->vm_start, region->vm_end); + free_page_series(region->vm_start, region->vm_top); } kmem_cache_free(vm_region_jar, region); } else { @@ -999,6 +1004,10 @@ static int do_mmap_shared_file(struct vm_area_struct *vma) int ret; ret = vma->vm_file->f_op->mmap(vma->vm_file, vma); + if (ret == 0) { + vma->vm_region->vm_top = vma->vm_region->vm_end; + return ret; + } if (ret != -ENOSYS) return ret; @@ -1027,11 +1036,14 @@ static int do_mmap_private(struct vm_area_struct *vma, */ if (vma->vm_file) { ret = vma->vm_file->f_op->mmap(vma->vm_file, vma); - if (ret != -ENOSYS) { + if (ret == 0) { /* shouldn't return success if we're not sharing */ - BUG_ON(ret == 0 && !(vma->vm_flags & VM_MAYSHARE)); - return ret; /* success or a real error */ + BUG_ON(!(vma->vm_flags & VM_MAYSHARE)); + vma->vm_region->vm_top = vma->vm_region->vm_end; + return ret; } + if (ret != -ENOSYS) + return ret; /* getting an ENOSYS error indicates that direct mmap isn't * possible (as opposed to tried but failed) so we'll try to @@ -1051,23 +1063,25 @@ static int do_mmap_private(struct vm_area_struct *vma, if (!pages) goto enomem; - /* we allocated a power-of-2 sized page set, so we need to trim off the - * excess */ total = 1 << order; atomic_add(total, &mmap_pages_allocated); point = rlen >> PAGE_SHIFT; - while (total > point) { - order = ilog2(total - point); - n = 1 << order; - kdebug("shave %lu/%lu @%lu", n, total - point, total); - atomic_sub(n, &mmap_pages_allocated); - total -= n; - set_page_refcounted(pages + total); - __free_pages(pages + total, order); + + /* we allocated a power-of-2 sized page set, so we may want to trim off + * the excess */ + if (sysctl_nr_trim_pages && total - point >= sysctl_nr_trim_pages) { + while (total > point) { + order = ilog2(total - point); + n = 1 << order; + kdebug("shave %lu/%lu @%lu", n, total - point, total); + atomic_sub(n, &mmap_pages_allocated); + total -= n; + set_page_refcounted(pages + total); + __free_pages(pages + total, order); + } } - total = rlen >> PAGE_SHIFT; for (point = 1; point < total; point++) set_page_refcounted(&pages[point]); @@ -1075,6 +1089,7 @@ static int do_mmap_private(struct vm_area_struct *vma, region->vm_flags = vma->vm_flags |= VM_MAPPED_COPY; region->vm_start = (unsigned long) base; region->vm_end = region->vm_start + rlen; + region->vm_top = region->vm_start + (total << PAGE_SHIFT); vma->vm_start = region->vm_start; vma->vm_end = region->vm_start + len; @@ -1110,6 +1125,7 @@ error_free: free_page_series(region->vm_start, region->vm_end); region->vm_start = vma->vm_start = 0; region->vm_end = vma->vm_end = 0; + region->vm_top = 0; return ret; enomem: @@ -1401,7 +1417,7 @@ int split_vma(struct mm_struct *mm, struct vm_area_struct *vma, npages = (addr - vma->vm_start) >> PAGE_SHIFT; if (new_below) { - region->vm_end = new->vm_end = addr; + region->vm_top = region->vm_end = new->vm_end = addr; } else { region->vm_start = new->vm_start = addr; region->vm_pgoff = new->vm_pgoff += npages; @@ -1418,6 +1434,7 @@ int split_vma(struct mm_struct *mm, struct vm_area_struct *vma, vma->vm_region->vm_pgoff = vma->vm_pgoff += npages; } else { vma->vm_region->vm_end = vma->vm_end = addr; + vma->vm_region->vm_top = addr; } add_nommu_region(vma->vm_region); add_nommu_region(new->vm_region); @@ -1454,10 +1471,12 @@ static int shrink_vma(struct mm_struct *mm, down_write(&nommu_region_sem); delete_nommu_region(region); - if (from > region->vm_start) - region->vm_end = from; - else + if (from > region->vm_start) { + to = region->vm_top; + region->vm_top = region->vm_end = from; + } else { region->vm_start = to; + } add_nommu_region(region); up_write(&nommu_region_sem); -- cgit v1.2.3 From b9456371a73871d001e67b5f4eac118c2c278e1c Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 8 Jan 2009 11:18:31 +0000 Subject: CRED: Fix commit_creds() on a process that has no mm Fix commit_creds()'s handling of a process that has no mm (such as one that is calling or has called daemonize()). commit_creds() should check to see if task->mm is not NULL before calling set_dumpable() on it. Reported-by: Jiri Slaby Signed-off-by: David Howells Signed-off-by: James Morris --- kernel/cred.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/cred.c b/kernel/cred.c index ff7bc071991c..480a61aec805 100644 --- a/kernel/cred.c +++ b/kernel/cred.c @@ -372,7 +372,8 @@ int commit_creds(struct cred *new) old->fsuid != new->fsuid || old->fsgid != new->fsgid || !cap_issubset(new->cap_permitted, old->cap_permitted)) { - set_dumpable(task->mm, suid_dumpable); + if (task->mm) + set_dumpable(task->mm, suid_dumpable); task->pdeath_signal = 0; smp_wmb(); } -- cgit v1.2.3 From 75139b8274c3e30354daea623f14b43a482a0bb5 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Wed, 7 Jan 2009 18:07:33 -0800 Subject: cgroups: remove some redundant NULL checks - In cgroup_clone(), if vfs_mkdir() returns successfully, dentry->d_fsdata will be the pointer to the newly created cgroup and won't be NULL. - a cgroup file's dentry->d_fsdata won't be NULL, guaranteed by cgroup_add_file(). - When walking through the subsystems of a cgroup_fs (using for_each_subsys), cgrp->subsys[ss->subsys_id] won't be NULL, guaranteed by cgroup_create(). (Also remove 2 unused variables in cgroup_rmdir(). Signed-off-by: Li Zefan Cc: Paul Menage Cc: KAMEZAWA Hiroyuki Cc: Balbir Singh Cc: Pavel Emelyanov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/cgroup.c | 29 +++++++---------------------- 1 file changed, 7 insertions(+), 22 deletions(-) (limited to 'kernel') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index f221446aa02d..220e0fd659fa 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -586,7 +586,7 @@ static void cgroup_call_pre_destroy(struct cgroup *cgrp) { struct cgroup_subsys *ss; for_each_subsys(cgrp->root, ss) - if (ss->pre_destroy && cgrp->subsys[ss->subsys_id]) + if (ss->pre_destroy) ss->pre_destroy(ss, cgrp); return; } @@ -610,10 +610,8 @@ static void cgroup_diput(struct dentry *dentry, struct inode *inode) /* * Release the subsystem state objects. */ - for_each_subsys(cgrp->root, ss) { - if (cgrp->subsys[ss->subsys_id]) - ss->destroy(ss, cgrp); - } + for_each_subsys(cgrp->root, ss) + ss->destroy(ss, cgrp); cgrp->root->number_of_cgroups--; mutex_unlock(&cgroup_mutex); @@ -1445,7 +1443,7 @@ static ssize_t cgroup_file_write(struct file *file, const char __user *buf, struct cftype *cft = __d_cft(file->f_dentry); struct cgroup *cgrp = __d_cgrp(file->f_dentry->d_parent); - if (!cft || cgroup_is_removed(cgrp)) + if (cgroup_is_removed(cgrp)) return -ENODEV; if (cft->write) return cft->write(cgrp, cft, file, buf, nbytes, ppos); @@ -1490,7 +1488,7 @@ static ssize_t cgroup_file_read(struct file *file, char __user *buf, struct cftype *cft = __d_cft(file->f_dentry); struct cgroup *cgrp = __d_cgrp(file->f_dentry->d_parent); - if (!cft || cgroup_is_removed(cgrp)) + if (cgroup_is_removed(cgrp)) return -ENODEV; if (cft->read) @@ -1554,10 +1552,8 @@ static int cgroup_file_open(struct inode *inode, struct file *file) err = generic_file_open(inode, file); if (err) return err; - cft = __d_cft(file->f_dentry); - if (!cft) - return -ENODEV; + if (cft->read_map || cft->read_seq_string) { struct cgroup_seqfile_state *state = kzalloc(sizeof(*state), GFP_USER); @@ -2463,8 +2459,6 @@ static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry) struct cgroup *cgrp = dentry->d_fsdata; struct dentry *d; struct cgroup *parent; - struct super_block *sb; - struct cgroupfs_root *root; /* the vfs holds both inode->i_mutex already */ @@ -2487,8 +2481,6 @@ static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry) mutex_lock(&cgroup_mutex); parent = cgrp->parent; - root = cgrp->root; - sb = root->sb; if (atomic_read(&cgrp->count) || !list_empty(&cgrp->children) @@ -2937,7 +2929,7 @@ int cgroup_clone(struct task_struct *tsk, struct cgroup_subsys *subsys, } /* Create the cgroup directory, which also creates the cgroup */ - ret = vfs_mkdir(inode, dentry, S_IFDIR | 0755); + ret = vfs_mkdir(inode, dentry, 0755); child = __d_cgrp(dentry); dput(dentry); if (ret) { @@ -2947,13 +2939,6 @@ int cgroup_clone(struct task_struct *tsk, struct cgroup_subsys *subsys, goto out_release; } - if (!child) { - printk(KERN_INFO - "Couldn't find new cgroup %s\n", nodename); - ret = -ENOMEM; - goto out_release; - } - /* The cgroup now exists. Retake cgroup_mutex and check * that we're still in the same state that we thought we * were. */ -- cgit v1.2.3 From cae7a366f77ea5c9f54ae98c5fc65056877a89ed Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Wed, 7 Jan 2009 18:07:34 -0800 Subject: ns_cgroup: remove unused spinlock I happened to find the spinlock in struct ns_cgroup is never used. Signed-off-by: Li Zefan Cc: Paul Menage Cc: KAMEZAWA Hiroyuki Cc: Balbir Singh Cc: Pavel Emelyanov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/ns_cgroup.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'kernel') diff --git a/kernel/ns_cgroup.c b/kernel/ns_cgroup.c index 43c2111cd54d..78bc3fdac0d2 100644 --- a/kernel/ns_cgroup.c +++ b/kernel/ns_cgroup.c @@ -13,7 +13,6 @@ struct ns_cgroup { struct cgroup_subsys_state css; - spinlock_t lock; }; struct cgroup_subsys ns_subsys; @@ -84,7 +83,6 @@ static struct cgroup_subsys_state *ns_create(struct cgroup_subsys *ss, ns_cgroup = kzalloc(sizeof(*ns_cgroup), GFP_KERNEL); if (!ns_cgroup) return ERR_PTR(-ENOMEM); - spin_lock_init(&ns_cgroup->lock); return &ns_cgroup->css; } -- cgit v1.2.3 From b12b533fa523e94e0cc9dc23274ae4f9439f1313 Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Wed, 7 Jan 2009 18:07:36 -0800 Subject: cgroups: add lock for child->cgroups in cgroup_post_fork() When cgroup_post_fork() is called, child is seen by find_task_by_vpid(), so child->cgroups maybe be changed, It'll incorrect. child->cgroups's refcnt is decreased child->cgroups's refcnt is increased but child->cg_list is added to child->cgroups's list. Signed-off-by: Lai Jiangshan Reviewed-by: Paul Menage Cc: KAMEZAWA Hiroyuki Cc: Pavel Emelyanov Cc: Balbir Singh Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/cgroup.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'kernel') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 220e0fd659fa..d7ab4ffd8fd9 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -2792,8 +2792,10 @@ void cgroup_post_fork(struct task_struct *child) { if (use_task_css_set_links) { write_lock(&css_set_lock); + task_lock(child); if (list_empty(&child->cg_list)) list_add(&child->cg_list, &child->cgroups->tasks); + task_unlock(child); write_unlock(&css_set_lock); } } -- cgit v1.2.3 From 2019f634ce5904c19eba4e86f51b1a119a53a9f1 Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Wed, 7 Jan 2009 18:07:36 -0800 Subject: cgroups: fix cgroup_iter_next() bug We access res->cgroups without the task_lock(), so res->cgroups may be changed. it's unreliable, and "if (l == &res->cgroups->tasks)" may be false forever. We don't need add any lock for fixing this bug. we just access to struct css_set by struct cg_cgroup_link, not by struct task_struct. Since we hold css_set_lock, struct cg_cgroup_link is reliable. Signed-off-by: Lai Jiangshan Reviewed-by: Paul Menage Cc: KAMEZAWA Hiroyuki Cc: Pavel Emelyanov Cc: Balbir Singh Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/cgroup.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index d7ab4ffd8fd9..a391ab3bdfc6 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -1808,6 +1808,7 @@ struct task_struct *cgroup_iter_next(struct cgroup *cgrp, { struct task_struct *res; struct list_head *l = it->task; + struct cg_cgroup_link *link; /* If the iterator cg is NULL, we have no tasks */ if (!it->cg_link) @@ -1815,7 +1816,8 @@ struct task_struct *cgroup_iter_next(struct cgroup *cgrp, res = list_entry(l, struct task_struct, cg_list); /* Advance iterator to find next entry */ l = l->next; - if (l == &res->cgroups->tasks) { + link = list_entry(it->cg_link, struct cg_cgroup_link, cgrp_link_list); + if (l == &link->cg->tasks) { /* We reached the end of this task list - move on to * the next cg_cgroup_link */ cgroup_advance_iter(cgrp, it); -- cgit v1.2.3 From b2aa30f7bb381e04c93eed106089ba55553955f1 Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Wed, 7 Jan 2009 18:07:37 -0800 Subject: cgroups: don't put struct cgroupfs_root protected by RCU We don't access struct cgroupfs_root in fast path, so we should not put struct cgroupfs_root protected by RCU But the comment in struct cgroup_subsys.root confuse us. struct cgroup_subsys.root is used in these places: 1 find_css_set(): if (ss->root->subsys_list.next == &ss->sibling) 2 rebind_subsystems(): if (ss->root != &rootnode) rcu_assign_pointer(ss->root, root); rcu_assign_pointer(subsys[i]->root, &rootnode); 3 cgroup_has_css_refs(): if (ss->root != cgrp->root) 4 cgroup_init_subsys(): ss->root = &rootnode; 5 proc_cgroupstats_show(): ss->name, ss->root->subsys_bits, ss->root->number_of_cgroups, !ss->disabled); 6 cgroup_clone(): root = subsys->root; if ((root != subsys->root) || All these place we have held cgroup_lock() or we don't dereference to struct cgroupfs_root. It's means wo don't need RCU when use struct cgroup_subsys.root, and we should not put struct cgroupfs_root protected by RCU. Signed-off-by: Lai Jiangshan Reviewed-by: Paul Menage Cc: KAMEZAWA Hiroyuki Cc: Pavel Emelyanov Cc: Balbir Singh Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cgroup.h | 1 - kernel/cgroup.c | 4 ++-- 2 files changed, 2 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 08b78c09b09a..f68dfd8dd53a 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -337,7 +337,6 @@ struct cgroup_subsys { #define MAX_CGROUP_TYPE_NAMELEN 32 const char *name; - /* Protected by RCU */ struct cgroupfs_root *root; struct list_head sibling; diff --git a/kernel/cgroup.c b/kernel/cgroup.c index a391ab3bdfc6..a288da176e46 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -713,7 +713,7 @@ static int rebind_subsystems(struct cgroupfs_root *root, cgrp->subsys[i] = dummytop->subsys[i]; cgrp->subsys[i]->cgroup = cgrp; list_add(&ss->sibling, &root->subsys_list); - rcu_assign_pointer(ss->root, root); + ss->root = root; if (ss->bind) ss->bind(ss, cgrp); @@ -725,7 +725,7 @@ static int rebind_subsystems(struct cgroupfs_root *root, ss->bind(ss, dummytop); dummytop->subsys[i]->cgroup = dummytop; cgrp->subsys[i] = NULL; - rcu_assign_pointer(subsys[i]->root, &rootnode); + subsys[i]->root = &rootnode; list_del(&ss->sibling); } else if (bit & final_bits) { /* Subsystem state should already exist */ -- cgit v1.2.3 From 104cbd55377029e70fc2cee01089e84b9c36e5dc Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Wed, 7 Jan 2009 18:07:38 -0800 Subject: cgroups: use task_lock() for access tsk->cgroups safe in cgroup_clone() Use task_lock() protect tsk->cgroups and get_css_set(tsk->cgroups). Signed-off-by: Lai Jiangshan Acked-by: Paul Menage Cc: KAMEZAWA Hiroyuki Cc: Pavel Emelyanov Cc: Balbir Singh Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/cgroup.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'kernel') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index a288da176e46..00d5136d38c2 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -2903,6 +2903,7 @@ int cgroup_clone(struct task_struct *tsk, struct cgroup_subsys *subsys, mutex_unlock(&cgroup_mutex); return 0; } + task_lock(tsk); cg = tsk->cgroups; parent = task_cgroup(tsk, subsys->subsys_id); @@ -2915,6 +2916,7 @@ int cgroup_clone(struct task_struct *tsk, struct cgroup_subsys *subsys, /* Keep the cgroup alive */ get_css_set(cg); + task_unlock(tsk); mutex_unlock(&cgroup_mutex); /* Now do the VFS work to create a cgroup */ -- cgit v1.2.3 From 77efecd9e0526327548152df715ab8644ecb5ba0 Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Wed, 7 Jan 2009 18:07:39 -0800 Subject: cgroups: call find_css_set() safely in cgroup_attach_task() In cgroup_attach_task(), tsk maybe exit when we call find_css_set(). and find_css_set() will access to invalid css_set. This patch increases the count before get_css_set(), and decreases it after find_css_set(). NOTE: css_set's refcount is also taskcount, after this patch applied, taskcount may be off-by-one WHEN cgroup_lock() is not held. but I reviewed other code which use taskcount, they are still correct. No regression found by reviewing and simply testing. So I do not use two counters in css_set. (one counter for taskcount, the other for refcount. like struct mm_struct) If this fix cause regression, we will use two counters in css_set. Signed-off-by: Lai Jiangshan Cc: Paul Menage Cc: KAMEZAWA Hiroyuki Cc: Pavel Emelyanov Cc: Balbir Singh Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/cgroup.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 00d5136d38c2..61e92c5867ea 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -1214,7 +1214,7 @@ int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk) int retval = 0; struct cgroup_subsys *ss; struct cgroup *oldcgrp; - struct css_set *cg = tsk->cgroups; + struct css_set *cg; struct css_set *newcg; struct cgroupfs_root *root = cgrp->root; int subsys_id; @@ -1234,11 +1234,16 @@ int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk) } } + task_lock(tsk); + cg = tsk->cgroups; + get_css_set(cg); + task_unlock(tsk); /* * Locate or allocate a new css_set for this task, * based on its final set of cgroups */ newcg = find_css_set(cg, cgrp); + put_css_set(cg); if (!newcg) return -ENOMEM; -- cgit v1.2.3 From 7534432dcc3c654a8671b6b0cdffd1dbdbc73074 Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Wed, 7 Jan 2009 18:07:40 -0800 Subject: cgroups: remove rcu_read_lock() in cgroupstats_build() cgroup_iter_* do not need rcu_read_lock(). In cgroup_enable_task_cg_lists(), do_each_thread() and while_each_thread() are protected by RCU, it's OK, for write_lock(&css_set_lock) implies rcu_read_lock() in non-RT kernel. If we need explicit rcu_read_lock(), we should add rcu_read_lock() in cgroup_enable_task_cg_lists(), not cgroup_iter_*. Signed-off-by: Lai Jiangshan Acked-by: Paul Menage Cc: KAMEZAWA Hiroyuki Cc: Pavel Emelyanov Cc: Balbir Singh Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/cgroup.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'kernel') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 61e92c5867ea..f55af3daffc2 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -2055,7 +2055,6 @@ int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry) ret = 0; cgrp = dentry->d_fsdata; - rcu_read_lock(); cgroup_iter_start(cgrp, &it); while ((tsk = cgroup_iter_next(cgrp, &it))) { @@ -2080,7 +2079,6 @@ int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry) } cgroup_iter_end(cgrp, &it); - rcu_read_unlock(); err: return ret; } -- cgit v1.2.3 From e5f6a8609bab0c2d7543ab1505105e011832afd7 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Wed, 7 Jan 2009 18:07:41 -0800 Subject: cgroups: make root_list contains active hierarchies only Don't link rootnode to the root list, so root_list contains active hierarchies only as the comment indicates. And rename for_each_root() to for_each_active_root(). Also remove redundant check in cgroup_kill_sb(). Signed-off-by: Li Zefan Cc: Paul Menage Cc: KAMEZAWA Hiroyuki Cc: Balbir Singh Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/cgroup.c | 19 +++++++------------ 1 file changed, 7 insertions(+), 12 deletions(-) (limited to 'kernel') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index f55af3daffc2..fd572d057691 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -84,7 +84,7 @@ struct cgroupfs_root { /* Tracks how many cgroups are currently defined in hierarchy.*/ int number_of_cgroups; - /* A list running through the mounted hierarchies */ + /* A list running through the active hierarchies */ struct list_head root_list; /* Hierarchy-specific flags */ @@ -148,8 +148,8 @@ static int notify_on_release(const struct cgroup *cgrp) #define for_each_subsys(_root, _ss) \ list_for_each_entry(_ss, &_root->subsys_list, sibling) -/* for_each_root() allows you to iterate across the active hierarchies */ -#define for_each_root(_root) \ +/* for_each_active_root() allows you to iterate across the active hierarchies */ +#define for_each_active_root(_root) \ list_for_each_entry(_root, &roots, root_list) /* the list of cgroups eligible for automatic release. Protected by @@ -1111,10 +1111,9 @@ static void cgroup_kill_sb(struct super_block *sb) { } write_unlock(&css_set_lock); - if (!list_empty(&root->root_list)) { - list_del(&root->root_list); - root_count--; - } + list_del(&root->root_list); + root_count--; + mutex_unlock(&cgroup_mutex); kfree(root); @@ -2559,7 +2558,6 @@ int __init cgroup_init_early(void) INIT_HLIST_NODE(&init_css_set.hlist); css_set_count = 1; init_cgroup_root(&rootnode); - list_add(&rootnode.root_list, &roots); root_count = 1; init_task.cgroups = &init_css_set; @@ -2666,15 +2664,12 @@ static int proc_cgroup_show(struct seq_file *m, void *v) mutex_lock(&cgroup_mutex); - for_each_root(root) { + for_each_active_root(root) { struct cgroup_subsys *ss; struct cgroup *cgrp; int subsys_id; int count = 0; - /* Skip this hierarchy if it has no active subsystems */ - if (!root->actual_subsys_bits) - continue; seq_printf(m, "%lu:", root->subsys_bits); for_each_subsys(root, ss) seq_printf(m, "%s%s", count++ ? "," : "", ss->name); -- cgit v1.2.3 From 33a68ac1c1b695216e873ee12e819adbe73e4d9f Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Wed, 7 Jan 2009 18:07:42 -0800 Subject: cgroups: add inactive subsystems to rootnode.subsys_list Though for an inactive hierarchy, we have subsys->root == &rootnode, but rootnode's subsys_list is always empty. This conflicts with the code in find_css_set(): for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) { ... if (ss->root->subsys_list.next == &ss->sibling) { ... } } if (list_empty(&rootnode.subsys_list)) { ... } The above code assumes rootnode.subsys_list links all inactive hierarchies. Signed-off-by: Li Zefan Cc: Paul Menage Cc: KAMEZAWA Hiroyuki Cc: Balbir Singh Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/cgroup.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index fd572d057691..abf7248f501a 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -712,7 +712,7 @@ static int rebind_subsystems(struct cgroupfs_root *root, BUG_ON(dummytop->subsys[i]->cgroup != dummytop); cgrp->subsys[i] = dummytop->subsys[i]; cgrp->subsys[i]->cgroup = cgrp; - list_add(&ss->sibling, &root->subsys_list); + list_move(&ss->sibling, &root->subsys_list); ss->root = root; if (ss->bind) ss->bind(ss, cgrp); @@ -726,7 +726,7 @@ static int rebind_subsystems(struct cgroupfs_root *root, dummytop->subsys[i]->cgroup = dummytop; cgrp->subsys[i] = NULL; subsys[i]->root = &rootnode; - list_del(&ss->sibling); + list_move(&ss->sibling, &rootnode.subsys_list); } else if (bit & final_bits) { /* Subsystem state should already exist */ BUG_ON(!cgrp->subsys[i]); @@ -2521,6 +2521,7 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss) printk(KERN_INFO "Initializing cgroup subsys %s\n", ss->name); /* Create the top cgroup state for this subsystem */ + list_add(&ss->sibling, &rootnode.subsys_list); ss->root = &rootnode; css = ss->create(ss, dummytop); /* We don't handle early failures gracefully */ -- cgit v1.2.3 From c12f65d4396e05c51ce3af7f159ead98574a587c Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Wed, 7 Jan 2009 18:07:42 -0800 Subject: cgroups: introduce link_css_set() to remove duplicate code Add a common function link_css_set() to link a css_set to a cgroup. Signed-off-by: Li Zefan Cc: Paul Menage Cc: KAMEZAWA Hiroyuki Cc: Balbir Singh Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/cgroup.c | 68 +++++++++++++++++++++++++-------------------------------- 1 file changed, 30 insertions(+), 38 deletions(-) (limited to 'kernel') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index abf7248f501a..4c475ce4e222 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -384,6 +384,25 @@ static int allocate_cg_links(int count, struct list_head *tmp) return 0; } +/** + * link_css_set - a helper function to link a css_set to a cgroup + * @tmp_cg_links: cg_cgroup_link objects allocated by allocate_cg_links() + * @cg: the css_set to be linked + * @cgrp: the destination cgroup + */ +static void link_css_set(struct list_head *tmp_cg_links, + struct css_set *cg, struct cgroup *cgrp) +{ + struct cg_cgroup_link *link; + + BUG_ON(list_empty(tmp_cg_links)); + link = list_first_entry(tmp_cg_links, struct cg_cgroup_link, + cgrp_link_list); + link->cg = cg; + list_move(&link->cgrp_link_list, &cgrp->css_sets); + list_add(&link->cg_link_list, &cg->cg_links); +} + /* * find_css_set() takes an existing cgroup group and a * cgroup object, and returns a css_set object that's @@ -399,7 +418,6 @@ static struct css_set *find_css_set( int i; struct list_head tmp_cg_links; - struct cg_cgroup_link *link; struct hlist_head *hhead; @@ -444,26 +462,11 @@ static struct css_set *find_css_set( * only do it for the first subsystem in each * hierarchy */ - if (ss->root->subsys_list.next == &ss->sibling) { - BUG_ON(list_empty(&tmp_cg_links)); - link = list_entry(tmp_cg_links.next, - struct cg_cgroup_link, - cgrp_link_list); - list_del(&link->cgrp_link_list); - list_add(&link->cgrp_link_list, &cgrp->css_sets); - link->cg = res; - list_add(&link->cg_link_list, &res->cg_links); - } - } - if (list_empty(&rootnode.subsys_list)) { - link = list_entry(tmp_cg_links.next, - struct cg_cgroup_link, - cgrp_link_list); - list_del(&link->cgrp_link_list); - list_add(&link->cgrp_link_list, &dummytop->css_sets); - link->cg = res; - list_add(&link->cg_link_list, &res->cg_links); + if (ss->root->subsys_list.next == &ss->sibling) + link_css_set(&tmp_cg_links, res, cgrp); } + if (list_empty(&rootnode.subsys_list)) + link_css_set(&tmp_cg_links, res, dummytop); BUG_ON(!list_empty(&tmp_cg_links)); @@ -988,7 +991,7 @@ static int cgroup_get_sb(struct file_system_type *fs_type, root = NULL; } else { /* New superblock */ - struct cgroup *cgrp = &root->top_cgroup; + struct cgroup *root_cgrp = &root->top_cgroup; struct inode *inode; int i; @@ -1029,7 +1032,7 @@ static int cgroup_get_sb(struct file_system_type *fs_type, list_add(&root->root_list, &roots); root_count++; - sb->s_root->d_fsdata = &root->top_cgroup; + sb->s_root->d_fsdata = root_cgrp; root->top_cgroup.dentry = sb->s_root; /* Link the top cgroup in this hierarchy into all @@ -1040,29 +1043,18 @@ static int cgroup_get_sb(struct file_system_type *fs_type, struct hlist_node *node; struct css_set *cg; - hlist_for_each_entry(cg, node, hhead, hlist) { - struct cg_cgroup_link *link; - - BUG_ON(list_empty(&tmp_cg_links)); - link = list_entry(tmp_cg_links.next, - struct cg_cgroup_link, - cgrp_link_list); - list_del(&link->cgrp_link_list); - link->cg = cg; - list_add(&link->cgrp_link_list, - &root->top_cgroup.css_sets); - list_add(&link->cg_link_list, &cg->cg_links); - } + hlist_for_each_entry(cg, node, hhead, hlist) + link_css_set(&tmp_cg_links, cg, root_cgrp); } write_unlock(&css_set_lock); free_cg_links(&tmp_cg_links); - BUG_ON(!list_empty(&cgrp->sibling)); - BUG_ON(!list_empty(&cgrp->children)); + BUG_ON(!list_empty(&root_cgrp->sibling)); + BUG_ON(!list_empty(&root_cgrp->children)); BUG_ON(root->number_of_cgroups != 1); - cgroup_populate_dir(cgrp); + cgroup_populate_dir(root_cgrp); mutex_unlock(&inode->i_mutex); mutex_unlock(&cgroup_mutex); } -- cgit v1.2.3 From e7b80bb695a5b64c92e314838e083b2f3bdf29b2 Mon Sep 17 00:00:00 2001 From: Gowrishankar M Date: Wed, 7 Jan 2009 18:07:43 -0800 Subject: cgroups: skip processes from other namespaces when listing a cgroup Once tasks are populated from system namespace inside cgroup, container replaces other namespace task with 0 while listing tasks, inside container. Though this is expected behaviour from container end, there is no use of showing unwanted 0s. In this patch, we check if a process is in same namespace before loading into pid array. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Gowrishankar M Acked-by: Paul Menage Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/cgroup.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 4c475ce4e222..cb7c72b91f46 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -2007,14 +2007,16 @@ int cgroup_scan_tasks(struct cgroup_scanner *scan) */ static int pid_array_load(pid_t *pidarray, int npids, struct cgroup *cgrp) { - int n = 0; + int n = 0, pid; struct cgroup_iter it; struct task_struct *tsk; cgroup_iter_start(cgrp, &it); while ((tsk = cgroup_iter_next(cgrp, &it))) { if (unlikely(n == npids)) break; - pidarray[n++] = task_pid_vnr(tsk); + pid = task_pid_vnr(tsk); + if (pid > 0) + pidarray[n++] = pid; } cgroup_iter_end(cgrp, &it); return n; -- cgit v1.2.3 From a47295e6bc42ad35f9c15ac66f598aa24debd4e2 Mon Sep 17 00:00:00 2001 From: Paul Menage Date: Wed, 7 Jan 2009 18:07:44 -0800 Subject: cgroups: make cgroup_path() RCU-safe Fix races between /proc/sched_debug by freeing cgroup objects via an RCU callback. Thus any cgroup reference obtained from an RCU-safe source will remain valid during the RCU section. Since dentries are also RCU-safe, this allows us to traverse up the tree safely. Additionally, make cgroup_path() check for a NULL cgrp->dentry to avoid trying to report a path for a partially-created cgroup. [lizf@cn.fujitsu.com: call deactive_super() in cgroup_diput()] Signed-off-by: Paul Menage Reviewed-by: Li Zefan Tested-by: Li Zefan Cc: Peter Zijlstra Signed-off-by: Li Zefan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cgroup.h | 5 ++++- kernel/cgroup.c | 30 +++++++++++++++++++++--------- 2 files changed, 25 insertions(+), 10 deletions(-) (limited to 'kernel') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index f68dfd8dd53a..73d1c730c3c4 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -116,7 +116,7 @@ struct cgroup { struct list_head children; /* my children */ struct cgroup *parent; /* my parent */ - struct dentry *dentry; /* cgroup fs entry */ + struct dentry *dentry; /* cgroup fs entry, RCU protected */ /* Private pointers for each registered subsystem */ struct cgroup_subsys_state *subsys[CGROUP_SUBSYS_COUNT]; @@ -145,6 +145,9 @@ struct cgroup { int pids_use_count; /* Length of the current tasks_pids array */ int pids_length; + + /* For RCU-protected deletion */ + struct rcu_head rcu_head; }; /* A css_set is a structure holding pointers to a set of diff --git a/kernel/cgroup.c b/kernel/cgroup.c index cb7c72b91f46..83ea4f524be5 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -271,7 +271,7 @@ static void __put_css_set(struct css_set *cg, int taskexit) rcu_read_lock(); for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) { - struct cgroup *cgrp = cg->subsys[i]->cgroup; + struct cgroup *cgrp = rcu_dereference(cg->subsys[i]->cgroup); if (atomic_dec_and_test(&cgrp->count) && notify_on_release(cgrp)) { if (taskexit) @@ -594,6 +594,13 @@ static void cgroup_call_pre_destroy(struct cgroup *cgrp) return; } +static void free_cgroup_rcu(struct rcu_head *obj) +{ + struct cgroup *cgrp = container_of(obj, struct cgroup, rcu_head); + + kfree(cgrp); +} + static void cgroup_diput(struct dentry *dentry, struct inode *inode) { /* is dentry a directory ? if so, kfree() associated cgroup */ @@ -619,11 +626,13 @@ static void cgroup_diput(struct dentry *dentry, struct inode *inode) cgrp->root->number_of_cgroups--; mutex_unlock(&cgroup_mutex); - /* Drop the active superblock reference that we took when we - * created the cgroup */ + /* + * Drop the active superblock reference that we took when we + * created the cgroup + */ deactivate_super(cgrp->root->sb); - kfree(cgrp); + call_rcu(&cgrp->rcu_head, free_cgroup_rcu); } iput(inode); } @@ -1134,14 +1143,16 @@ static inline struct cftype *__d_cft(struct dentry *dentry) * @buf: the buffer to write the path into * @buflen: the length of the buffer * - * Called with cgroup_mutex held. Writes path of cgroup into buf. - * Returns 0 on success, -errno on error. + * Called with cgroup_mutex held or else with an RCU-protected cgroup + * reference. Writes path of cgroup into buf. Returns 0 on success, + * -errno on error. */ int cgroup_path(const struct cgroup *cgrp, char *buf, int buflen) { char *start; + struct dentry *dentry = rcu_dereference(cgrp->dentry); - if (cgrp == dummytop) { + if (!dentry || cgrp == dummytop) { /* * Inactive subsystems have no dentry for their root * cgroup @@ -1154,13 +1165,14 @@ int cgroup_path(const struct cgroup *cgrp, char *buf, int buflen) *--start = '\0'; for (;;) { - int len = cgrp->dentry->d_name.len; + int len = dentry->d_name.len; if ((start -= len) < buf) return -ENAMETOOLONG; memcpy(start, cgrp->dentry->d_name.name, len); cgrp = cgrp->parent; if (!cgrp) break; + dentry = rcu_dereference(cgrp->dentry); if (!cgrp->parent) continue; if (--start < buf) @@ -1663,7 +1675,7 @@ static int cgroup_create_dir(struct cgroup *cgrp, struct dentry *dentry, if (!error) { dentry->d_fsdata = cgrp; inc_nlink(parent->d_inode); - cgrp->dentry = dentry; + rcu_assign_pointer(cgrp->dentry, dentry); dget(dentry); } dput(dentry); -- cgit v1.2.3 From 28dbc4b6a01fb579a9441c7b81e3d3413dc452df Mon Sep 17 00:00:00 2001 From: Balbir Singh Date: Wed, 7 Jan 2009 18:08:05 -0800 Subject: memcg: memory cgroup resource counters for hierarchy Add support for building hierarchies in resource counters. Cgroups allows us to build a deep hierarchy, but we currently don't link the resource counters belonging to the memory controller control groups, in the same fashion as the corresponding cgroup entries in the cgroup hierarchy. This patch provides the infrastructure for resource counters that have the same hiearchy as their cgroup counter parts. These set of patches are based on the resource counter hiearchy patches posted by Pavel Emelianov. NOTE: Building hiearchies is expensive, deeper hierarchies imply charging the all the way up to the root. It is known that hiearchies are expensive, so the user needs to be careful and aware of the trade-offs before creating very deep ones. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Balbir Singh Cc: YAMAMOTO Takashi Cc: Paul Menage Cc: Li Zefan Cc: David Rientjes Cc: Pavel Emelianov Cc: Dhaval Giani Cc: KAMEZAWA Hiroyuki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/res_counter.h | 8 ++++++-- kernel/res_counter.c | 44 +++++++++++++++++++++++++++++++++++--------- mm/memcontrol.c | 20 +++++++++++++------- 3 files changed, 54 insertions(+), 18 deletions(-) (limited to 'kernel') diff --git a/include/linux/res_counter.h b/include/linux/res_counter.h index 271c1c2c9f6f..dede0a2cfc45 100644 --- a/include/linux/res_counter.h +++ b/include/linux/res_counter.h @@ -43,6 +43,10 @@ struct res_counter { * the routines below consider this to be IRQ-safe */ spinlock_t lock; + /* + * Parent counter, used for hierarchial resource accounting + */ + struct res_counter *parent; }; /** @@ -87,7 +91,7 @@ enum { * helpers for accounting */ -void res_counter_init(struct res_counter *counter); +void res_counter_init(struct res_counter *counter, struct res_counter *parent); /* * charge - try to consume more resource. @@ -103,7 +107,7 @@ void res_counter_init(struct res_counter *counter); int __must_check res_counter_charge_locked(struct res_counter *counter, unsigned long val); int __must_check res_counter_charge(struct res_counter *counter, - unsigned long val); + unsigned long val, struct res_counter **limit_fail_at); /* * uncharge - tell that some portion of the resource is released diff --git a/kernel/res_counter.c b/kernel/res_counter.c index f275c8eca772..bf8e7534c803 100644 --- a/kernel/res_counter.c +++ b/kernel/res_counter.c @@ -15,10 +15,11 @@ #include #include -void res_counter_init(struct res_counter *counter) +void res_counter_init(struct res_counter *counter, struct res_counter *parent) { spin_lock_init(&counter->lock); counter->limit = (unsigned long long)LLONG_MAX; + counter->parent = parent; } int res_counter_charge_locked(struct res_counter *counter, unsigned long val) @@ -34,14 +35,34 @@ int res_counter_charge_locked(struct res_counter *counter, unsigned long val) return 0; } -int res_counter_charge(struct res_counter *counter, unsigned long val) +int res_counter_charge(struct res_counter *counter, unsigned long val, + struct res_counter **limit_fail_at) { int ret; unsigned long flags; - - spin_lock_irqsave(&counter->lock, flags); - ret = res_counter_charge_locked(counter, val); - spin_unlock_irqrestore(&counter->lock, flags); + struct res_counter *c, *u; + + *limit_fail_at = NULL; + local_irq_save(flags); + for (c = counter; c != NULL; c = c->parent) { + spin_lock(&c->lock); + ret = res_counter_charge_locked(c, val); + spin_unlock(&c->lock); + if (ret < 0) { + *limit_fail_at = c; + goto undo; + } + } + ret = 0; + goto done; +undo: + for (u = counter; u != c; u = u->parent) { + spin_lock(&u->lock); + res_counter_uncharge_locked(u, val); + spin_unlock(&u->lock); + } +done: + local_irq_restore(flags); return ret; } @@ -56,10 +77,15 @@ void res_counter_uncharge_locked(struct res_counter *counter, unsigned long val) void res_counter_uncharge(struct res_counter *counter, unsigned long val) { unsigned long flags; + struct res_counter *c; - spin_lock_irqsave(&counter->lock, flags); - res_counter_uncharge_locked(counter, val); - spin_unlock_irqrestore(&counter->lock, flags); + local_irq_save(flags); + for (c = counter; c != NULL; c = c->parent) { + spin_lock(&c->lock); + res_counter_uncharge_locked(c, val); + spin_unlock(&c->lock); + } + local_irq_restore(flags); } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 9846f617115d..e72fb2b4a7d8 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -471,6 +471,7 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm, { struct mem_cgroup *mem; int nr_retries = MEM_CGROUP_RECLAIM_RETRIES; + struct res_counter *fail_res; /* * We always charge the cgroup the mm_struct belongs to. * The mm_struct's mem_cgroup changes on task migration if the @@ -499,11 +500,12 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm, int ret; bool noswap = false; - ret = res_counter_charge(&mem->res, PAGE_SIZE); + ret = res_counter_charge(&mem->res, PAGE_SIZE, &fail_res); if (likely(!ret)) { if (!do_swap_account) break; - ret = res_counter_charge(&mem->memsw, PAGE_SIZE); + ret = res_counter_charge(&mem->memsw, PAGE_SIZE, + &fail_res); if (likely(!ret)) break; /* mem+swap counter fails */ @@ -1709,22 +1711,26 @@ static void __init enable_swap_cgroup(void) static struct cgroup_subsys_state * mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont) { - struct mem_cgroup *mem; + struct mem_cgroup *mem, *parent; int node; mem = mem_cgroup_alloc(); if (!mem) return ERR_PTR(-ENOMEM); - res_counter_init(&mem->res); - res_counter_init(&mem->memsw); - for_each_node_state(node, N_POSSIBLE) if (alloc_mem_cgroup_per_zone_info(mem, node)) goto free_out; /* root ? */ - if (cont->parent == NULL) + if (cont->parent == NULL) { enable_swap_cgroup(); + parent = NULL; + } else + parent = mem_cgroup_from_cont(cont->parent); + + res_counter_init(&mem->res, parent ? &parent->res : NULL); + res_counter_init(&mem->memsw, parent ? &parent->memsw : NULL); + return &mem->css; free_out: -- cgit v1.2.3 From 999cd8a450f8f93701669a61cac4d3b19eca07e8 Mon Sep 17 00:00:00 2001 From: Paul Menage Date: Wed, 7 Jan 2009 18:08:36 -0800 Subject: cgroups: add a per-subsystem hierarchy_mutex These patches introduce new locking/refcount support for cgroups to reduce the need for subsystems to call cgroup_lock(). This will ultimately allow the atomicity of cgroup_rmdir() (which was removed recently) to be restored. These three patches give: 1/3 - introduce a per-subsystem hierarchy_mutex which a subsystem can use to prevent changes to its own cgroup tree 2/3 - use hierarchy_mutex in place of calling cgroup_lock() in the memory controller 3/3 - introduce a css_tryget() function similar to the one recently proposed by Kamezawa, but avoiding spurious refcount failures in the event of a race between a css_tryget() and an unsuccessful cgroup_rmdir() Future patches will likely involve: - using hierarchy mutex in place of cgroup_lock() in more subsystems where appropriate - restoring the atomicity of cgroup_rmdir() with respect to cgroup_create() This patch: Add a hierarchy_mutex to the cgroup_subsys object that protects changes to the hierarchy observed by that subsystem. It is taken by the cgroup subsystem (in addition to cgroup_mutex) for the following operations: - linking a cgroup into that subsystem's cgroup tree - unlinking a cgroup from that subsystem's cgroup tree - moving the subsystem to/from a hierarchy (including across the bind() callback) Thus if the subsystem holds its own hierarchy_mutex, it can safely traverse its own hierarchy. Signed-off-by: Paul Menage Tested-by: KAMEZAWA Hiroyuki Cc: Li Zefan Cc: Balbir Singh Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/cgroups/cgroups.txt | 2 +- include/linux/cgroup.h | 17 ++++++++++++++++- kernel/cgroup.c | 37 +++++++++++++++++++++++++++++++++++-- 3 files changed, 52 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/Documentation/cgroups/cgroups.txt b/Documentation/cgroups/cgroups.txt index 60287e9e9d27..e33ee74eee77 100644 --- a/Documentation/cgroups/cgroups.txt +++ b/Documentation/cgroups/cgroups.txt @@ -528,7 +528,7 @@ example in cpusets, no task may attach before 'cpus' and 'mems' are set up. void bind(struct cgroup_subsys *ss, struct cgroup *root) -(cgroup_mutex held by caller) +(cgroup_mutex and ss->hierarchy_mutex held by caller) Called when a cgroup subsystem is rebound to a different hierarchy and root cgroup. Currently this will only involve movement between diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 73d1c730c3c4..ce1c1f34c30c 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -340,8 +340,23 @@ struct cgroup_subsys { #define MAX_CGROUP_TYPE_NAMELEN 32 const char *name; - struct cgroupfs_root *root; + /* + * Protects sibling/children links of cgroups in this + * hierarchy, plus protects which hierarchy (or none) the + * subsystem is a part of (i.e. root/sibling). To avoid + * potential deadlocks, the following operations should not be + * undertaken while holding any hierarchy_mutex: + * + * - allocating memory + * - initiating hotplug events + */ + struct mutex hierarchy_mutex; + /* + * Link to parent, and list entry in parent's children. + * Protected by this->hierarchy_mutex and cgroup_lock() + */ + struct cgroupfs_root *root; struct list_head sibling; }; diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 83ea4f524be5..8b6379cdf637 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -722,23 +722,26 @@ static int rebind_subsystems(struct cgroupfs_root *root, BUG_ON(cgrp->subsys[i]); BUG_ON(!dummytop->subsys[i]); BUG_ON(dummytop->subsys[i]->cgroup != dummytop); + mutex_lock(&ss->hierarchy_mutex); cgrp->subsys[i] = dummytop->subsys[i]; cgrp->subsys[i]->cgroup = cgrp; list_move(&ss->sibling, &root->subsys_list); ss->root = root; if (ss->bind) ss->bind(ss, cgrp); - + mutex_unlock(&ss->hierarchy_mutex); } else if (bit & removed_bits) { /* We're removing this subsystem */ BUG_ON(cgrp->subsys[i] != dummytop->subsys[i]); BUG_ON(cgrp->subsys[i]->cgroup != cgrp); + mutex_lock(&ss->hierarchy_mutex); if (ss->bind) ss->bind(ss, dummytop); dummytop->subsys[i]->cgroup = dummytop; cgrp->subsys[i] = NULL; subsys[i]->root = &rootnode; list_move(&ss->sibling, &rootnode.subsys_list); + mutex_unlock(&ss->hierarchy_mutex); } else if (bit & final_bits) { /* Subsystem state should already exist */ BUG_ON(!cgrp->subsys[i]); @@ -2338,6 +2341,29 @@ static void init_cgroup_css(struct cgroup_subsys_state *css, cgrp->subsys[ss->subsys_id] = css; } +static void cgroup_lock_hierarchy(struct cgroupfs_root *root) +{ + /* We need to take each hierarchy_mutex in a consistent order */ + int i; + + for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) { + struct cgroup_subsys *ss = subsys[i]; + if (ss->root == root) + mutex_lock_nested(&ss->hierarchy_mutex, i); + } +} + +static void cgroup_unlock_hierarchy(struct cgroupfs_root *root) +{ + int i; + + for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) { + struct cgroup_subsys *ss = subsys[i]; + if (ss->root == root) + mutex_unlock(&ss->hierarchy_mutex); + } +} + /* * cgroup_create - create a cgroup * @parent: cgroup that will be parent of the new cgroup @@ -2386,7 +2412,9 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry, init_cgroup_css(css, ss, cgrp); } + cgroup_lock_hierarchy(root); list_add(&cgrp->sibling, &cgrp->parent->children); + cgroup_unlock_hierarchy(root); root->number_of_cgroups++; err = cgroup_create_dir(cgrp, dentry, mode); @@ -2504,8 +2532,12 @@ static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry) if (!list_empty(&cgrp->release_list)) list_del(&cgrp->release_list); spin_unlock(&release_list_lock); - /* delete my sibling from parent->children */ + + cgroup_lock_hierarchy(cgrp->root); + /* delete this cgroup from parent->children */ list_del(&cgrp->sibling); + cgroup_unlock_hierarchy(cgrp->root); + spin_lock(&cgrp->dentry->d_lock); d = dget(cgrp->dentry); spin_unlock(&d->d_lock); @@ -2547,6 +2579,7 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss) * need to invoke fork callbacks here. */ BUG_ON(!list_empty(&init_task.tasks)); + mutex_init(&ss->hierarchy_mutex); ss->active = 1; } -- cgit v1.2.3 From e7c5ec9193d32b9559a3bb8893ceedbda85201ff Mon Sep 17 00:00:00 2001 From: Paul Menage Date: Wed, 7 Jan 2009 18:08:38 -0800 Subject: cgroups: add css_tryget() Add css_tryget(), that obtains a counted reference on a CSS. It is used in situations where the caller has a "weak" reference to the CSS, i.e. one that does not protect the cgroup from removal via a reference count, but would instead be cleaned up by a destroy() callback. css_tryget() will return true on success, or false if the cgroup is being removed. This is similar to Kamezawa Hiroyuki's patch from a week or two ago, but with the difference that in the event of css_tryget() racing with a cgroup_rmdir(), css_tryget() will only return false if the cgroup really does get removed. This implementation is done by biasing css->refcnt, so that a refcnt of 1 means "releasable" and 0 means "released or releasing". In the event of a race, css_tryget() distinguishes between "released" and "releasing" by checking for the CSS_REMOVED flag in css->flags. Signed-off-by: Paul Menage Tested-by: KAMEZAWA Hiroyuki Cc: Li Zefan Cc: Balbir Singh Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cgroup.h | 38 ++++++++++++++++++++++++++----- kernel/cgroup.c | 61 +++++++++++++++++++++++++++++++++++++++++++++----- 2 files changed, 88 insertions(+), 11 deletions(-) (limited to 'kernel') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index ce1c1f34c30c..e267e62827bb 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -52,9 +52,9 @@ struct cgroup_subsys_state { * hierarchy structure */ struct cgroup *cgroup; - /* State maintained by the cgroup system to allow - * subsystems to be "busy". Should be accessed via css_get() - * and css_put() */ + /* State maintained by the cgroup system to allow subsystems + * to be "busy". Should be accessed via css_get(), + * css_tryget() and and css_put(). */ atomic_t refcnt; @@ -64,11 +64,14 @@ struct cgroup_subsys_state { /* bits in struct cgroup_subsys_state flags field */ enum { CSS_ROOT, /* This CSS is the root of the subsystem */ + CSS_REMOVED, /* This CSS is dead */ }; /* - * Call css_get() to hold a reference on the cgroup; - * + * Call css_get() to hold a reference on the css; it can be used + * for a reference obtained via: + * - an existing ref-counted reference to the css + * - task->cgroups for a locked task */ static inline void css_get(struct cgroup_subsys_state *css) @@ -77,9 +80,32 @@ static inline void css_get(struct cgroup_subsys_state *css) if (!test_bit(CSS_ROOT, &css->flags)) atomic_inc(&css->refcnt); } + +static inline bool css_is_removed(struct cgroup_subsys_state *css) +{ + return test_bit(CSS_REMOVED, &css->flags); +} + +/* + * Call css_tryget() to take a reference on a css if your existing + * (known-valid) reference isn't already ref-counted. Returns false if + * the css has been destroyed. + */ + +static inline bool css_tryget(struct cgroup_subsys_state *css) +{ + if (test_bit(CSS_ROOT, &css->flags)) + return true; + while (!atomic_inc_not_zero(&css->refcnt)) { + if (test_bit(CSS_REMOVED, &css->flags)) + return false; + } + return true; +} + /* * css_put() should be called to release a reference taken by - * css_get() + * css_get() or css_tryget() */ extern void __css_put(struct cgroup_subsys_state *css); diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 8b6379cdf637..c29831076e7a 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -2333,7 +2333,7 @@ static void init_cgroup_css(struct cgroup_subsys_state *css, struct cgroup *cgrp) { css->cgroup = cgrp; - atomic_set(&css->refcnt, 0); + atomic_set(&css->refcnt, 1); css->flags = 0; if (cgrp == dummytop) set_bit(CSS_ROOT, &css->flags); @@ -2465,7 +2465,7 @@ static int cgroup_has_css_refs(struct cgroup *cgrp) { /* Check the reference count on each subsystem. Since we * already established that there are no tasks in the - * cgroup, if the css refcount is also 0, then there should + * cgroup, if the css refcount is also 1, then there should * be no outstanding references, so the subsystem is safe to * destroy. We scan across all subsystems rather than using * the per-hierarchy linked list of mounted subsystems since @@ -2486,12 +2486,62 @@ static int cgroup_has_css_refs(struct cgroup *cgrp) * matter, since it can only happen if the cgroup * has been deleted and hence no longer needs the * release agent to be called anyway. */ - if (css && atomic_read(&css->refcnt)) + if (css && (atomic_read(&css->refcnt) > 1)) return 1; } return 0; } +/* + * Atomically mark all (or else none) of the cgroup's CSS objects as + * CSS_REMOVED. Return true on success, or false if the cgroup has + * busy subsystems. Call with cgroup_mutex held + */ + +static int cgroup_clear_css_refs(struct cgroup *cgrp) +{ + struct cgroup_subsys *ss; + unsigned long flags; + bool failed = false; + local_irq_save(flags); + for_each_subsys(cgrp->root, ss) { + struct cgroup_subsys_state *css = cgrp->subsys[ss->subsys_id]; + int refcnt; + do { + /* We can only remove a CSS with a refcnt==1 */ + refcnt = atomic_read(&css->refcnt); + if (refcnt > 1) { + failed = true; + goto done; + } + BUG_ON(!refcnt); + /* + * Drop the refcnt to 0 while we check other + * subsystems. This will cause any racing + * css_tryget() to spin until we set the + * CSS_REMOVED bits or abort + */ + } while (atomic_cmpxchg(&css->refcnt, refcnt, 0) != refcnt); + } + done: + for_each_subsys(cgrp->root, ss) { + struct cgroup_subsys_state *css = cgrp->subsys[ss->subsys_id]; + if (failed) { + /* + * Restore old refcnt if we previously managed + * to clear it from 1 to 0 + */ + if (!atomic_read(&css->refcnt)) + atomic_set(&css->refcnt, 1); + } else { + /* Commit the fact that the CSS is removed */ + set_bit(CSS_REMOVED, &css->flags); + } + } + local_irq_restore(flags); + return !failed; +} + static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry) { struct cgroup *cgrp = dentry->d_fsdata; @@ -2522,7 +2572,7 @@ static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry) if (atomic_read(&cgrp->count) || !list_empty(&cgrp->children) - || cgroup_has_css_refs(cgrp)) { + || !cgroup_clear_css_refs(cgrp)) { mutex_unlock(&cgroup_mutex); return -EBUSY; } @@ -3078,7 +3128,8 @@ void __css_put(struct cgroup_subsys_state *css) { struct cgroup *cgrp = css->cgroup; rcu_read_lock(); - if (atomic_dec_and_test(&css->refcnt) && notify_on_release(cgrp)) { + if ((atomic_dec_return(&css->refcnt) == 1) && + notify_on_release(cgrp)) { set_bit(CGRP_RELEASABLE, &cgrp->flags); check_for_release(cgrp); } -- cgit v1.2.3 From 13337714f3b0307dc7f75ef5d83ecf0db2abbd65 Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Wed, 7 Jan 2009 18:08:39 -0800 Subject: cpuset: rcu_read_lock() to protect task_cs() task_cs() calls task_subsys_state(). We must use rcu_read_lock() to protect cgroup_subsys_state(). It's correct that top_cpuset is never freed, but cgroup_subsys_state() accesses css_set, this css_set maybe freed when task_cs() called. We use use rcu_read_lock() to protect it. Signed-off-by: Lai Jiangshan Acked-by: Paul Menage Cc: KAMEZAWA Hiroyuki Cc: Pavel Emelyanov Cc: Balbir Singh Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/cpuset.c | 11 +++-------- 1 file changed, 3 insertions(+), 8 deletions(-) (limited to 'kernel') diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 345ace5117de..a841b5c01ef9 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -375,14 +375,9 @@ void cpuset_update_task_memory_state(void) struct task_struct *tsk = current; struct cpuset *cs; - if (task_cs(tsk) == &top_cpuset) { - /* Don't need rcu for top_cpuset. It's never freed. */ - my_cpusets_mem_gen = top_cpuset.mems_generation; - } else { - rcu_read_lock(); - my_cpusets_mem_gen = task_cs(tsk)->mems_generation; - rcu_read_unlock(); - } + rcu_read_lock(); + my_cpusets_mem_gen = task_cs(tsk)->mems_generation; + rcu_read_unlock(); if (my_cpusets_mem_gen != tsk->cpuset_mems_generation) { mutex_lock(&callback_mutex); -- cgit v1.2.3 From f5813d94279a18ff5936d675e24b44b44a571197 Mon Sep 17 00:00:00 2001 From: Miao Xie Date: Wed, 7 Jan 2009 18:08:40 -0800 Subject: cpusets: set task's cpu_allowed to cpu_possible_map when attaching it into top cpuset I found a bug on my dual-cpu box. I created a sub cpuset in top cpuset and assign 1 to its cpus. And then we attach some tasks into this sub cpuset. After this, we offline CPU1. Now, the tasks in this new cpuset are moved into top cpuset automatically because there is no cpu in sub cpuset. Then we online CPU1, we find all the tasks which doesn't belong to top cpuset originally just run on CPU0. We fix this bug by setting task's cpu_allowed to cpu_possible_map when attaching it into top cpuset. This method needn't modify the current behavior of cpusets on CPU hotplug, and all of tasks in top cpuset use cpu_possible_map to initialize their cpu_allowed. Signed-off-by: Miao Xie Cc: Paul Menage Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/cpuset.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/cpuset.c b/kernel/cpuset.c index a841b5c01ef9..6012e326e856 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -1338,10 +1338,14 @@ static void cpuset_attach(struct cgroup_subsys *ss, struct cpuset *oldcs = cgroup_cs(oldcont); int err; - mutex_lock(&callback_mutex); - guarantee_online_cpus(cs, &cpus); + if (cs == &top_cpuset) { + cpus = cpu_possible_map; + } else { + mutex_lock(&callback_mutex); + guarantee_online_cpus(cs, &cpus); + mutex_unlock(&callback_mutex); + } err = set_cpus_allowed_ptr(tsk, &cpus); - mutex_unlock(&callback_mutex); if (err) return; -- cgit v1.2.3 From 5a7625df725a486ad600b0036b6111dbd6321c41 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Wed, 7 Jan 2009 18:08:41 -0800 Subject: cpuset: remove on stack cpumask_t in cpuset_sprintf_cpulist() This patchset converts cpuset to use new cpumask API, and thus remove on stack cpumask_t to reduce stack usage. Before: # cat kernel/cpuset.c include/linux/cpuset.h | grep -c cpumask_t 21 After: # cat kernel/cpuset.c include/linux/cpuset.h | grep -c cpumask_t 0 This patch: Impact: reduce stack usage It's safe to call cpulist_scnprintf inside callback_mutex, and thus we can just remove the cpumask_t and no need to allocate a cpumask_var_t. Signed-off-by: Li Zefan Cc: Ingo Molnar Cc: Rusty Russell Acked-by: Mike Travis Cc: Paul Menage Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/cpuset.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 6012e326e856..41c2343df975 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -1486,13 +1486,13 @@ static int cpuset_write_resmask(struct cgroup *cgrp, struct cftype *cft, static int cpuset_sprintf_cpulist(char *page, struct cpuset *cs) { - cpumask_t mask; + int ret; mutex_lock(&callback_mutex); - mask = cs->cpus_allowed; + ret = cpulist_scnprintf(page, PAGE_SIZE, &cs->cpus_allowed); mutex_unlock(&callback_mutex); - return cpulist_scnprintf(page, PAGE_SIZE, &mask); + return ret; } static int cpuset_sprintf_memlist(char *page, struct cpuset *cs) -- cgit v1.2.3 From 5771f0a2236df69683e9abea87f35f522c97ff94 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Wed, 7 Jan 2009 18:08:41 -0800 Subject: cpuset: remove on stack cpumask_t in cpuset_can_attach() Impact: reduce stack usage Just use cs->cpus_allowed, and no need to allocate a cpumask_var_t. Signed-off-by: Li Zefan Cc: Ingo Molnar Cc: Rusty Russell Acked-by: Mike Travis Cc: Paul Menage Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/cpuset.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) (limited to 'kernel') diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 41c2343df975..afa29cfc5bbb 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -1311,20 +1311,19 @@ static int cpuset_can_attach(struct cgroup_subsys *ss, struct cgroup *cont, struct task_struct *tsk) { struct cpuset *cs = cgroup_cs(cont); + int ret = 0; if (cpus_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed)) return -ENOSPC; - if (tsk->flags & PF_THREAD_BOUND) { - cpumask_t mask; + if (tsk->flags & PF_THREAD_BOUND) { mutex_lock(&callback_mutex); - mask = cs->cpus_allowed; + if (!cpus_equal(tsk->cpus_allowed, cs->cpus_allowed)) + ret = -EINVAL; mutex_unlock(&callback_mutex); - if (!cpus_equal(tsk->cpus_allowed, mask)) - return -EINVAL; } - return security_task_setscheduler(tsk, 0, NULL); + return ret < 0 ? ret : security_task_setscheduler(tsk, 0, NULL); } static void cpuset_attach(struct cgroup_subsys *ss, -- cgit v1.2.3 From 2341d1b6598c7146d64a5050b53a72a5a819617f Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Wed, 7 Jan 2009 18:08:42 -0800 Subject: cpuset: convert cpuset_attach() to use cpumask_var_t Impact: reduce stack usage Allocate a global cpumask_var_t at boot, and use it in cpuset_attach(), so we won't fail cpuset_attach(). Signed-off-by: Li Zefan Cc: Ingo Molnar Cc: Rusty Russell Acked-by: Mike Travis Cc: Paul Menage Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/cpuset.c | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) (limited to 'kernel') diff --git a/kernel/cpuset.c b/kernel/cpuset.c index afa29cfc5bbb..1e32e6b380af 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -1306,6 +1306,9 @@ static int fmeter_getrate(struct fmeter *fmp) return val; } +/* Protected by cgroup_lock */ +static cpumask_var_t cpus_attach; + /* Called by cgroups to determine if a cpuset is usable; cgroup_mutex held */ static int cpuset_can_attach(struct cgroup_subsys *ss, struct cgroup *cont, struct task_struct *tsk) @@ -1330,7 +1333,6 @@ static void cpuset_attach(struct cgroup_subsys *ss, struct cgroup *cont, struct cgroup *oldcont, struct task_struct *tsk) { - cpumask_t cpus; nodemask_t from, to; struct mm_struct *mm; struct cpuset *cs = cgroup_cs(cont); @@ -1338,13 +1340,13 @@ static void cpuset_attach(struct cgroup_subsys *ss, int err; if (cs == &top_cpuset) { - cpus = cpu_possible_map; + cpumask_copy(cpus_attach, cpu_possible_mask); } else { mutex_lock(&callback_mutex); - guarantee_online_cpus(cs, &cpus); + guarantee_online_cpus(cs, cpus_attach); mutex_unlock(&callback_mutex); } - err = set_cpus_allowed_ptr(tsk, &cpus); + err = set_cpus_allowed_ptr(tsk, cpus_attach); if (err) return; @@ -1357,7 +1359,6 @@ static void cpuset_attach(struct cgroup_subsys *ss, cpuset_migrate_mm(mm, &from, &to); mmput(mm); } - } /* The various types of files and directories in a cpuset file system */ @@ -1838,6 +1839,9 @@ int __init cpuset_init(void) if (err < 0) return err; + if (!alloc_cpumask_var(&cpus_attach, GFP_KERNEL)) + BUG(); + number_of_cpusets = 1; return 0; } -- cgit v1.2.3 From 645fcc9d2f6946f97a41c8d00edee38f8a6f0060 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Wed, 7 Jan 2009 18:08:43 -0800 Subject: cpuset: don't allocate trial cpuset on stack Impact: cleanups, reduce stack usage This patch prepares for the next patch. When we convert cpuset.cpus_allowed to cpumask_var_t, (trialcs = *cs) no longer works. Another result of this patch is reducing stack usage of trialcs. sizeof(*cs) can be as large as 148 bytes on x86_64, so it's really not good to have it on stack. Signed-off-by: Li Zefan Cc: Ingo Molnar Cc: Rusty Russell Acked-by: Mike Travis Cc: Paul Menage Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/cpuset.c | 93 +++++++++++++++++++++++++++++++++++++-------------------- 1 file changed, 60 insertions(+), 33 deletions(-) (limited to 'kernel') diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 1e32e6b380af..f66527bfd216 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -415,6 +415,24 @@ static int is_cpuset_subset(const struct cpuset *p, const struct cpuset *q) is_mem_exclusive(p) <= is_mem_exclusive(q); } +/** + * alloc_trial_cpuset - allocate a trial cpuset + * @cs: the cpuset that the trial cpuset duplicates + */ +static struct cpuset *alloc_trial_cpuset(const struct cpuset *cs) +{ + return kmemdup(cs, sizeof(*cs), GFP_KERNEL); +} + +/** + * free_trial_cpuset - free the trial cpuset + * @trial: the trial cpuset to be freed + */ +static void free_trial_cpuset(struct cpuset *trial) +{ + kfree(trial); +} + /* * validate_change() - Used to validate that any proposed cpuset change * follows the structural rules for cpusets. @@ -880,10 +898,10 @@ static void update_tasks_cpumask(struct cpuset *cs, struct ptr_heap *heap) * @cs: the cpuset to consider * @buf: buffer of cpu numbers written to this cpuset */ -static int update_cpumask(struct cpuset *cs, const char *buf) +static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs, + const char *buf) { struct ptr_heap heap; - struct cpuset trialcs; int retval; int is_load_balanced; @@ -891,8 +909,6 @@ static int update_cpumask(struct cpuset *cs, const char *buf) if (cs == &top_cpuset) return -EACCES; - trialcs = *cs; - /* * An empty cpus_allowed is ok only if the cpuset has no tasks. * Since cpulist_parse() fails on an empty mask, we special case @@ -900,31 +916,31 @@ static int update_cpumask(struct cpuset *cs, const char *buf) * with tasks have cpus. */ if (!*buf) { - cpus_clear(trialcs.cpus_allowed); + cpus_clear(trialcs->cpus_allowed); } else { - retval = cpulist_parse(buf, &trialcs.cpus_allowed); + retval = cpulist_parse(buf, &trialcs->cpus_allowed); if (retval < 0) return retval; - if (!cpus_subset(trialcs.cpus_allowed, cpu_online_map)) + if (!cpus_subset(trialcs->cpus_allowed, cpu_online_map)) return -EINVAL; } - retval = validate_change(cs, &trialcs); + retval = validate_change(cs, trialcs); if (retval < 0) return retval; /* Nothing to do if the cpus didn't change */ - if (cpus_equal(cs->cpus_allowed, trialcs.cpus_allowed)) + if (cpus_equal(cs->cpus_allowed, trialcs->cpus_allowed)) return 0; retval = heap_init(&heap, PAGE_SIZE, GFP_KERNEL, NULL); if (retval) return retval; - is_load_balanced = is_sched_load_balance(&trialcs); + is_load_balanced = is_sched_load_balance(trialcs); mutex_lock(&callback_mutex); - cs->cpus_allowed = trialcs.cpus_allowed; + cs->cpus_allowed = trialcs->cpus_allowed; mutex_unlock(&callback_mutex); /* @@ -1099,9 +1115,9 @@ done: * lock each such tasks mm->mmap_sem, scan its vma's and rebind * their mempolicies to the cpusets new mems_allowed. */ -static int update_nodemask(struct cpuset *cs, const char *buf) +static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs, + const char *buf) { - struct cpuset trialcs; nodemask_t oldmem; int retval; @@ -1112,8 +1128,6 @@ static int update_nodemask(struct cpuset *cs, const char *buf) if (cs == &top_cpuset) return -EACCES; - trialcs = *cs; - /* * An empty mems_allowed is ok iff there are no tasks in the cpuset. * Since nodelist_parse() fails on an empty mask, we special case @@ -1121,27 +1135,27 @@ static int update_nodemask(struct cpuset *cs, const char *buf) * with tasks have memory. */ if (!*buf) { - nodes_clear(trialcs.mems_allowed); + nodes_clear(trialcs->mems_allowed); } else { - retval = nodelist_parse(buf, trialcs.mems_allowed); + retval = nodelist_parse(buf, trialcs->mems_allowed); if (retval < 0) goto done; - if (!nodes_subset(trialcs.mems_allowed, + if (!nodes_subset(trialcs->mems_allowed, node_states[N_HIGH_MEMORY])) return -EINVAL; } oldmem = cs->mems_allowed; - if (nodes_equal(oldmem, trialcs.mems_allowed)) { + if (nodes_equal(oldmem, trialcs->mems_allowed)) { retval = 0; /* Too easy - nothing to do */ goto done; } - retval = validate_change(cs, &trialcs); + retval = validate_change(cs, trialcs); if (retval < 0) goto done; mutex_lock(&callback_mutex); - cs->mems_allowed = trialcs.mems_allowed; + cs->mems_allowed = trialcs->mems_allowed; cs->mems_generation = cpuset_mems_generation++; mutex_unlock(&callback_mutex); @@ -1181,31 +1195,36 @@ static int update_relax_domain_level(struct cpuset *cs, s64 val) static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs, int turning_on) { - struct cpuset trialcs; + struct cpuset *trialcs; int err; int balance_flag_changed; - trialcs = *cs; + trialcs = alloc_trial_cpuset(cs); + if (!trialcs) + return -ENOMEM; + if (turning_on) - set_bit(bit, &trialcs.flags); + set_bit(bit, &trialcs->flags); else - clear_bit(bit, &trialcs.flags); + clear_bit(bit, &trialcs->flags); - err = validate_change(cs, &trialcs); + err = validate_change(cs, trialcs); if (err < 0) - return err; + goto out; balance_flag_changed = (is_sched_load_balance(cs) != - is_sched_load_balance(&trialcs)); + is_sched_load_balance(trialcs)); mutex_lock(&callback_mutex); - cs->flags = trialcs.flags; + cs->flags = trialcs->flags; mutex_unlock(&callback_mutex); - if (!cpus_empty(trialcs.cpus_allowed) && balance_flag_changed) + if (!cpus_empty(trialcs->cpus_allowed) && balance_flag_changed) async_rebuild_sched_domains(); - return 0; +out: + free_trial_cpuset(trialcs); + return err; } /* @@ -1453,21 +1472,29 @@ static int cpuset_write_resmask(struct cgroup *cgrp, struct cftype *cft, const char *buf) { int retval = 0; + struct cpuset *cs = cgroup_cs(cgrp); + struct cpuset *trialcs; if (!cgroup_lock_live_group(cgrp)) return -ENODEV; + trialcs = alloc_trial_cpuset(cs); + if (!trialcs) + return -ENOMEM; + switch (cft->private) { case FILE_CPULIST: - retval = update_cpumask(cgroup_cs(cgrp), buf); + retval = update_cpumask(cs, trialcs, buf); break; case FILE_MEMLIST: - retval = update_nodemask(cgroup_cs(cgrp), buf); + retval = update_nodemask(cs, trialcs, buf); break; default: retval = -EINVAL; break; } + + free_trial_cpuset(trialcs); cgroup_unlock(); return retval; } -- cgit v1.2.3 From 300ed6cbb70718872cb4936d1d22ef295f9ba44d Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Wed, 7 Jan 2009 18:08:44 -0800 Subject: cpuset: convert cpuset->cpus_allowed to cpumask_var_t Impact: use new cpumask API This patch mainly does the following things: - change cs->cpus_allowed from cpumask_t to cpumask_var_t - call alloc_bootmem_cpumask_var() for top_cpuset in cpuset_init_early() - call alloc_cpumask_var() for other cpusets - replace cpus_xxx() to cpumask_xxx() Signed-off-by: Li Zefan Cc: Ingo Molnar Cc: Rusty Russell Acked-by: Mike Travis Cc: Paul Menage Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/cpuset.c | 100 +++++++++++++++++++++++++++++++++----------------------- 1 file changed, 60 insertions(+), 40 deletions(-) (limited to 'kernel') diff --git a/kernel/cpuset.c b/kernel/cpuset.c index f66527bfd216..fc294aa9a97a 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -84,7 +84,7 @@ struct cpuset { struct cgroup_subsys_state css; unsigned long flags; /* "unsigned long" so bitops work */ - cpumask_t cpus_allowed; /* CPUs allowed to tasks in cpuset */ + cpumask_var_t cpus_allowed; /* CPUs allowed to tasks in cpuset */ nodemask_t mems_allowed; /* Memory Nodes allowed to tasks */ struct cpuset *parent; /* my parent */ @@ -195,8 +195,6 @@ static int cpuset_mems_generation; static struct cpuset top_cpuset = { .flags = ((1 << CS_CPU_EXCLUSIVE) | (1 << CS_MEM_EXCLUSIVE)), - .cpus_allowed = CPU_MASK_ALL, - .mems_allowed = NODE_MASK_ALL, }; /* @@ -278,7 +276,7 @@ static struct file_system_type cpuset_fs_type = { }; /* - * Return in *pmask the portion of a cpusets's cpus_allowed that + * Return in pmask the portion of a cpusets's cpus_allowed that * are online. If none are online, walk up the cpuset hierarchy * until we find one that does have some online cpus. If we get * all the way to the top and still haven't found any online cpus, @@ -293,13 +291,13 @@ static struct file_system_type cpuset_fs_type = { static void guarantee_online_cpus(const struct cpuset *cs, cpumask_t *pmask) { - while (cs && !cpus_intersects(cs->cpus_allowed, cpu_online_map)) + while (cs && !cpumask_intersects(cs->cpus_allowed, cpu_online_mask)) cs = cs->parent; if (cs) - cpus_and(*pmask, cs->cpus_allowed, cpu_online_map); + cpumask_and(pmask, cs->cpus_allowed, cpu_online_mask); else - *pmask = cpu_online_map; - BUG_ON(!cpus_intersects(*pmask, cpu_online_map)); + cpumask_copy(pmask, cpu_online_mask); + BUG_ON(!cpumask_intersects(pmask, cpu_online_mask)); } /* @@ -409,7 +407,7 @@ void cpuset_update_task_memory_state(void) static int is_cpuset_subset(const struct cpuset *p, const struct cpuset *q) { - return cpus_subset(p->cpus_allowed, q->cpus_allowed) && + return cpumask_subset(p->cpus_allowed, q->cpus_allowed) && nodes_subset(p->mems_allowed, q->mems_allowed) && is_cpu_exclusive(p) <= is_cpu_exclusive(q) && is_mem_exclusive(p) <= is_mem_exclusive(q); @@ -421,7 +419,19 @@ static int is_cpuset_subset(const struct cpuset *p, const struct cpuset *q) */ static struct cpuset *alloc_trial_cpuset(const struct cpuset *cs) { - return kmemdup(cs, sizeof(*cs), GFP_KERNEL); + struct cpuset *trial; + + trial = kmemdup(cs, sizeof(*cs), GFP_KERNEL); + if (!trial) + return NULL; + + if (!alloc_cpumask_var(&trial->cpus_allowed, GFP_KERNEL)) { + kfree(trial); + return NULL; + } + cpumask_copy(trial->cpus_allowed, cs->cpus_allowed); + + return trial; } /** @@ -430,6 +440,7 @@ static struct cpuset *alloc_trial_cpuset(const struct cpuset *cs) */ static void free_trial_cpuset(struct cpuset *trial) { + free_cpumask_var(trial->cpus_allowed); kfree(trial); } @@ -482,7 +493,7 @@ static int validate_change(const struct cpuset *cur, const struct cpuset *trial) c = cgroup_cs(cont); if ((is_cpu_exclusive(trial) || is_cpu_exclusive(c)) && c != cur && - cpus_intersects(trial->cpus_allowed, c->cpus_allowed)) + cpumask_intersects(trial->cpus_allowed, c->cpus_allowed)) return -EINVAL; if ((is_mem_exclusive(trial) || is_mem_exclusive(c)) && c != cur && @@ -492,7 +503,7 @@ static int validate_change(const struct cpuset *cur, const struct cpuset *trial) /* Cpusets with tasks can't have empty cpus_allowed or mems_allowed */ if (cgroup_task_count(cur->css.cgroup)) { - if (cpus_empty(trial->cpus_allowed) || + if (cpumask_empty(trial->cpus_allowed) || nodes_empty(trial->mems_allowed)) { return -ENOSPC; } @@ -507,7 +518,7 @@ static int validate_change(const struct cpuset *cur, const struct cpuset *trial) */ static int cpusets_overlap(struct cpuset *a, struct cpuset *b) { - return cpus_intersects(a->cpus_allowed, b->cpus_allowed); + return cpumask_intersects(a->cpus_allowed, b->cpus_allowed); } static void @@ -532,7 +543,7 @@ update_domain_attr_tree(struct sched_domain_attr *dattr, struct cpuset *c) cp = list_first_entry(&q, struct cpuset, stack_list); list_del(q.next); - if (cpus_empty(cp->cpus_allowed)) + if (cpumask_empty(cp->cpus_allowed)) continue; if (is_sched_load_balance(cp)) @@ -627,7 +638,7 @@ static int generate_sched_domains(cpumask_t **domains, *dattr = SD_ATTR_INIT; update_domain_attr_tree(dattr, &top_cpuset); } - *doms = top_cpuset.cpus_allowed; + cpumask_copy(doms, top_cpuset.cpus_allowed); ndoms = 1; goto done; @@ -646,7 +657,7 @@ static int generate_sched_domains(cpumask_t **domains, cp = list_first_entry(&q, struct cpuset, stack_list); list_del(q.next); - if (cpus_empty(cp->cpus_allowed)) + if (cpumask_empty(cp->cpus_allowed)) continue; /* @@ -739,7 +750,7 @@ restart: struct cpuset *b = csa[j]; if (apn == b->pn) { - cpus_or(*dp, *dp, b->cpus_allowed); + cpumask_or(dp, dp, b->cpus_allowed); if (dattr) update_domain_attr_tree(dattr + nslot, b); @@ -848,7 +859,7 @@ void rebuild_sched_domains(void) static int cpuset_test_cpumask(struct task_struct *tsk, struct cgroup_scanner *scan) { - return !cpus_equal(tsk->cpus_allowed, + return !cpumask_equal(&tsk->cpus_allowed, (cgroup_cs(scan->cg))->cpus_allowed); } @@ -866,7 +877,7 @@ static int cpuset_test_cpumask(struct task_struct *tsk, static void cpuset_change_cpumask(struct task_struct *tsk, struct cgroup_scanner *scan) { - set_cpus_allowed_ptr(tsk, &((cgroup_cs(scan->cg))->cpus_allowed)); + set_cpus_allowed_ptr(tsk, ((cgroup_cs(scan->cg))->cpus_allowed)); } /** @@ -916,13 +927,13 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs, * with tasks have cpus. */ if (!*buf) { - cpus_clear(trialcs->cpus_allowed); + cpumask_clear(trialcs->cpus_allowed); } else { - retval = cpulist_parse(buf, &trialcs->cpus_allowed); + retval = cpulist_parse(buf, trialcs->cpus_allowed); if (retval < 0) return retval; - if (!cpus_subset(trialcs->cpus_allowed, cpu_online_map)) + if (!cpumask_subset(trialcs->cpus_allowed, cpu_online_mask)) return -EINVAL; } retval = validate_change(cs, trialcs); @@ -930,7 +941,7 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs, return retval; /* Nothing to do if the cpus didn't change */ - if (cpus_equal(cs->cpus_allowed, trialcs->cpus_allowed)) + if (cpumask_equal(cs->cpus_allowed, trialcs->cpus_allowed)) return 0; retval = heap_init(&heap, PAGE_SIZE, GFP_KERNEL, NULL); @@ -940,7 +951,7 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs, is_load_balanced = is_sched_load_balance(trialcs); mutex_lock(&callback_mutex); - cs->cpus_allowed = trialcs->cpus_allowed; + cpumask_copy(cs->cpus_allowed, trialcs->cpus_allowed); mutex_unlock(&callback_mutex); /* @@ -1028,7 +1039,7 @@ static int update_tasks_nodemask(struct cpuset *cs, const nodemask_t *oldmem) cpuset_being_rebound = cs; /* causes mpol_dup() rebind */ fudge = 10; /* spare mmarray[] slots */ - fudge += cpus_weight(cs->cpus_allowed); /* imagine one fork-bomb/cpu */ + fudge += cpumask_weight(cs->cpus_allowed);/* imagine 1 fork-bomb/cpu */ retval = -ENOMEM; /* @@ -1176,7 +1187,8 @@ static int update_relax_domain_level(struct cpuset *cs, s64 val) if (val != cs->relax_domain_level) { cs->relax_domain_level = val; - if (!cpus_empty(cs->cpus_allowed) && is_sched_load_balance(cs)) + if (!cpumask_empty(cs->cpus_allowed) && + is_sched_load_balance(cs)) async_rebuild_sched_domains(); } @@ -1219,7 +1231,7 @@ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs, cs->flags = trialcs->flags; mutex_unlock(&callback_mutex); - if (!cpus_empty(trialcs->cpus_allowed) && balance_flag_changed) + if (!cpumask_empty(trialcs->cpus_allowed) && balance_flag_changed) async_rebuild_sched_domains(); out: @@ -1335,12 +1347,12 @@ static int cpuset_can_attach(struct cgroup_subsys *ss, struct cpuset *cs = cgroup_cs(cont); int ret = 0; - if (cpus_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed)) + if (cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed)) return -ENOSPC; if (tsk->flags & PF_THREAD_BOUND) { mutex_lock(&callback_mutex); - if (!cpus_equal(tsk->cpus_allowed, cs->cpus_allowed)) + if (!cpumask_equal(&tsk->cpus_allowed, cs->cpus_allowed)) ret = -EINVAL; mutex_unlock(&callback_mutex); } @@ -1516,7 +1528,7 @@ static int cpuset_sprintf_cpulist(char *page, struct cpuset *cs) int ret; mutex_lock(&callback_mutex); - ret = cpulist_scnprintf(page, PAGE_SIZE, &cs->cpus_allowed); + ret = cpulist_scnprintf(page, PAGE_SIZE, cs->cpus_allowed); mutex_unlock(&callback_mutex); return ret; @@ -1755,7 +1767,7 @@ static void cpuset_post_clone(struct cgroup_subsys *ss, parent_cs = cgroup_cs(parent); cs->mems_allowed = parent_cs->mems_allowed; - cs->cpus_allowed = parent_cs->cpus_allowed; + cpumask_copy(cs->cpus_allowed, parent_cs->cpus_allowed); return; } @@ -1781,6 +1793,10 @@ static struct cgroup_subsys_state *cpuset_create( cs = kmalloc(sizeof(*cs), GFP_KERNEL); if (!cs) return ERR_PTR(-ENOMEM); + if (!alloc_cpumask_var(&cs->cpus_allowed, GFP_KERNEL)) { + kfree(cs); + return ERR_PTR(-ENOMEM); + } cpuset_update_task_memory_state(); cs->flags = 0; @@ -1789,7 +1805,7 @@ static struct cgroup_subsys_state *cpuset_create( if (is_spread_slab(parent)) set_bit(CS_SPREAD_SLAB, &cs->flags); set_bit(CS_SCHED_LOAD_BALANCE, &cs->flags); - cpus_clear(cs->cpus_allowed); + cpumask_clear(cs->cpus_allowed); nodes_clear(cs->mems_allowed); cs->mems_generation = cpuset_mems_generation++; fmeter_init(&cs->fmeter); @@ -1816,6 +1832,7 @@ static void cpuset_destroy(struct cgroup_subsys *ss, struct cgroup *cont) update_flag(CS_SCHED_LOAD_BALANCE, cs, 0); number_of_cpusets--; + free_cpumask_var(cs->cpus_allowed); kfree(cs); } @@ -1839,6 +1856,8 @@ struct cgroup_subsys cpuset_subsys = { int __init cpuset_init_early(void) { + alloc_bootmem_cpumask_var(&top_cpuset.cpus_allowed); + top_cpuset.mems_generation = cpuset_mems_generation++; return 0; } @@ -1854,7 +1873,7 @@ int __init cpuset_init(void) { int err = 0; - cpus_setall(top_cpuset.cpus_allowed); + cpumask_setall(top_cpuset.cpus_allowed); nodes_setall(top_cpuset.mems_allowed); fmeter_init(&top_cpuset.fmeter); @@ -1943,7 +1962,7 @@ static void remove_tasks_in_empty_cpuset(struct cpuset *cs) * has online cpus, so can't be empty). */ parent = cs->parent; - while (cpus_empty(parent->cpus_allowed) || + while (cpumask_empty(parent->cpus_allowed) || nodes_empty(parent->mems_allowed)) parent = parent->parent; @@ -1984,7 +2003,7 @@ static void scan_for_empty_cpusets(struct cpuset *root) } /* Continue past cpusets with all cpus, mems online */ - if (cpus_subset(cp->cpus_allowed, cpu_online_map) && + if (cpumask_subset(cp->cpus_allowed, cpu_online_mask) && nodes_subset(cp->mems_allowed, node_states[N_HIGH_MEMORY])) continue; @@ -1992,13 +2011,14 @@ static void scan_for_empty_cpusets(struct cpuset *root) /* Remove offline cpus and mems from this cpuset. */ mutex_lock(&callback_mutex); - cpus_and(cp->cpus_allowed, cp->cpus_allowed, cpu_online_map); + cpumask_and(cp->cpus_allowed, cp->cpus_allowed, + cpu_online_mask); nodes_and(cp->mems_allowed, cp->mems_allowed, node_states[N_HIGH_MEMORY]); mutex_unlock(&callback_mutex); /* Move tasks from the empty cpuset to a parent */ - if (cpus_empty(cp->cpus_allowed) || + if (cpumask_empty(cp->cpus_allowed) || nodes_empty(cp->mems_allowed)) remove_tasks_in_empty_cpuset(cp); else { @@ -2039,7 +2059,7 @@ static int cpuset_track_online_cpus(struct notifier_block *unused_nb, } cgroup_lock(); - top_cpuset.cpus_allowed = cpu_online_map; + cpumask_copy(top_cpuset.cpus_allowed, cpu_online_mask); scan_for_empty_cpusets(&top_cpuset); ndoms = generate_sched_domains(&doms, &attr); cgroup_unlock(); @@ -2084,7 +2104,7 @@ static int cpuset_track_online_nodes(struct notifier_block *self, void __init cpuset_init_smp(void) { - top_cpuset.cpus_allowed = cpu_online_map; + cpumask_copy(top_cpuset.cpus_allowed, cpu_online_mask); top_cpuset.mems_allowed = node_states[N_HIGH_MEMORY]; hotcpu_notifier(cpuset_track_online_cpus, 0); @@ -2096,7 +2116,7 @@ void __init cpuset_init_smp(void) * @tsk: pointer to task_struct from which to obtain cpuset->cpus_allowed. * @pmask: pointer to cpumask_t variable to receive cpus_allowed set. * - * Description: Returns the cpumask_t cpus_allowed of the cpuset + * Description: Returns the cpumask_var_t cpus_allowed of the cpuset * attached to the specified @tsk. Guaranteed to return some non-empty * subset of cpu_online_map, even if this means going outside the * tasks cpuset. -- cgit v1.2.3 From 6af866af34a96fed24a55979a78b6f73bd4e8e87 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Wed, 7 Jan 2009 18:08:45 -0800 Subject: cpuset: remove remaining pointers to cpumask_t Impact: cleanups, use new cpumask API Final trivial cleanups: mainly s/cpumask_t/struct cpumask Note there is a FIXME in generate_sched_domains(). A future patch will change struct cpumask *doms to struct cpumask *doms[]. (I suppose Rusty will do this.) Signed-off-by: Li Zefan Cc: Ingo Molnar Cc: Rusty Russell Acked-by: Mike Travis Cc: Paul Menage Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cpuset.h | 10 ++++++---- kernel/cpuset.c | 28 +++++++++++++++------------- 2 files changed, 21 insertions(+), 17 deletions(-) (limited to 'kernel') diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index 51ea2bdea0f9..90c6074a36ca 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -20,8 +20,9 @@ extern int number_of_cpusets; /* How many cpusets are defined in system? */ extern int cpuset_init_early(void); extern int cpuset_init(void); extern void cpuset_init_smp(void); -extern void cpuset_cpus_allowed(struct task_struct *p, cpumask_t *mask); -extern void cpuset_cpus_allowed_locked(struct task_struct *p, cpumask_t *mask); +extern void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask); +extern void cpuset_cpus_allowed_locked(struct task_struct *p, + struct cpumask *mask); extern nodemask_t cpuset_mems_allowed(struct task_struct *p); #define cpuset_current_mems_allowed (current->mems_allowed) void cpuset_init_current_mems_allowed(void); @@ -86,12 +87,13 @@ static inline int cpuset_init_early(void) { return 0; } static inline int cpuset_init(void) { return 0; } static inline void cpuset_init_smp(void) {} -static inline void cpuset_cpus_allowed(struct task_struct *p, cpumask_t *mask) +static inline void cpuset_cpus_allowed(struct task_struct *p, + struct cpumask *mask) { *mask = cpu_possible_map; } static inline void cpuset_cpus_allowed_locked(struct task_struct *p, - cpumask_t *mask) + struct cpumask *mask) { *mask = cpu_possible_map; } diff --git a/kernel/cpuset.c b/kernel/cpuset.c index fc294aa9a97a..647c77a88fcb 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -289,7 +289,8 @@ static struct file_system_type cpuset_fs_type = { * Call with callback_mutex held. */ -static void guarantee_online_cpus(const struct cpuset *cs, cpumask_t *pmask) +static void guarantee_online_cpus(const struct cpuset *cs, + struct cpumask *pmask) { while (cs && !cpumask_intersects(cs->cpus_allowed, cpu_online_mask)) cs = cs->parent; @@ -610,7 +611,8 @@ update_domain_attr_tree(struct sched_domain_attr *dattr, struct cpuset *c) * element of the partition (one sched domain) to be passed to * partition_sched_domains(). */ -static int generate_sched_domains(cpumask_t **domains, +/* FIXME: see the FIXME in partition_sched_domains() */ +static int generate_sched_domains(struct cpumask **domains, struct sched_domain_attr **attributes) { LIST_HEAD(q); /* queue of cpusets to be scanned */ @@ -618,10 +620,10 @@ static int generate_sched_domains(cpumask_t **domains, struct cpuset **csa; /* array of all cpuset ptrs */ int csn; /* how many cpuset ptrs in csa so far */ int i, j, k; /* indices for partition finding loops */ - cpumask_t *doms; /* resulting partition; i.e. sched domains */ + struct cpumask *doms; /* resulting partition; i.e. sched domains */ struct sched_domain_attr *dattr; /* attributes for custom domains */ int ndoms = 0; /* number of sched domains in result */ - int nslot; /* next empty doms[] cpumask_t slot */ + int nslot; /* next empty doms[] struct cpumask slot */ doms = NULL; dattr = NULL; @@ -629,7 +631,7 @@ static int generate_sched_domains(cpumask_t **domains, /* Special case for the 99% of systems with one, full, sched domain */ if (is_sched_load_balance(&top_cpuset)) { - doms = kmalloc(sizeof(cpumask_t), GFP_KERNEL); + doms = kmalloc(cpumask_size(), GFP_KERNEL); if (!doms) goto done; @@ -708,7 +710,7 @@ restart: * Now we know how many domains to create. * Convert to and populate cpu masks. */ - doms = kmalloc(ndoms * sizeof(cpumask_t), GFP_KERNEL); + doms = kmalloc(ndoms * cpumask_size(), GFP_KERNEL); if (!doms) goto done; @@ -720,7 +722,7 @@ restart: for (nslot = 0, i = 0; i < csn; i++) { struct cpuset *a = csa[i]; - cpumask_t *dp; + struct cpumask *dp; int apn = a->pn; if (apn < 0) { @@ -743,7 +745,7 @@ restart: continue; } - cpus_clear(*dp); + cpumask_clear(dp); if (dattr) *(dattr + nslot) = SD_ATTR_INIT; for (j = i; j < csn; j++) { @@ -790,7 +792,7 @@ done: static void do_rebuild_sched_domains(struct work_struct *unused) { struct sched_domain_attr *attr; - cpumask_t *doms; + struct cpumask *doms; int ndoms; get_online_cpus(); @@ -2044,7 +2046,7 @@ static int cpuset_track_online_cpus(struct notifier_block *unused_nb, unsigned long phase, void *unused_cpu) { struct sched_domain_attr *attr; - cpumask_t *doms; + struct cpumask *doms; int ndoms; switch (phase) { @@ -2114,7 +2116,7 @@ void __init cpuset_init_smp(void) /** * cpuset_cpus_allowed - return cpus_allowed mask from a tasks cpuset. * @tsk: pointer to task_struct from which to obtain cpuset->cpus_allowed. - * @pmask: pointer to cpumask_t variable to receive cpus_allowed set. + * @pmask: pointer to struct cpumask variable to receive cpus_allowed set. * * Description: Returns the cpumask_var_t cpus_allowed of the cpuset * attached to the specified @tsk. Guaranteed to return some non-empty @@ -2122,7 +2124,7 @@ void __init cpuset_init_smp(void) * tasks cpuset. **/ -void cpuset_cpus_allowed(struct task_struct *tsk, cpumask_t *pmask) +void cpuset_cpus_allowed(struct task_struct *tsk, struct cpumask *pmask) { mutex_lock(&callback_mutex); cpuset_cpus_allowed_locked(tsk, pmask); @@ -2133,7 +2135,7 @@ void cpuset_cpus_allowed(struct task_struct *tsk, cpumask_t *pmask) * cpuset_cpus_allowed_locked - return cpus_allowed mask from a tasks cpuset. * Must be called with callback_mutex held. **/ -void cpuset_cpus_allowed_locked(struct task_struct *tsk, cpumask_t *pmask) +void cpuset_cpus_allowed_locked(struct task_struct *tsk, struct cpumask *pmask) { task_lock(tsk); guarantee_online_cpus(task_cs(tsk), pmask); -- cgit v1.2.3 From 61bce0f1371cfff497fe85594fd39d1a0b15ebe1 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 7 Jan 2009 18:08:49 -0800 Subject: pid: generalize task_active_pid_ns Currently task_active_pid_ns is not safe to call after a task becomes a zombie and exit_task_namespaces is called, as nsproxy becomes NULL. By reading the pid namespace from the pid of the task we can trivially solve this problem at the cost of one extra memory read in what should be the same cacheline as we read the namespace from. When moving things around I have made task_active_pid_ns out of line because keeping it in pid_namespace.h would require adding includes of pid.h and sched.h that I don't think we want. This change does make task_active_pid_ns unsafe to call during copy_process until we attach a pid on the task_struct which seems to be a reasonable trade off. Signed-off-by: Eric W. Biederman Signed-off-by: Sukadev Bhattiprolu Cc: Oleg Nesterov Cc: Roland McGrath Cc: Bastian Blank Cc: Pavel Emelyanov Cc: Nadia Derbey Acked-by: Serge Hallyn Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pid_namespace.h | 6 +----- kernel/fork.c | 4 ++-- kernel/pid.c | 6 ++++++ 3 files changed, 9 insertions(+), 7 deletions(-) (limited to 'kernel') diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h index d82fe825d62f..38d10326246a 100644 --- a/include/linux/pid_namespace.h +++ b/include/linux/pid_namespace.h @@ -79,11 +79,7 @@ static inline void zap_pid_ns_processes(struct pid_namespace *ns) } #endif /* CONFIG_PID_NS */ -static inline struct pid_namespace *task_active_pid_ns(struct task_struct *tsk) -{ - return tsk->nsproxy->pid_ns; -} - +extern struct pid_namespace *task_active_pid_ns(struct task_struct *tsk); void pidhash_init(void); void pidmap_init(void); diff --git a/kernel/fork.c b/kernel/fork.c index 7b8f2a78be3d..4018308048cf 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1126,12 +1126,12 @@ static struct task_struct *copy_process(unsigned long clone_flags, if (pid != &init_struct_pid) { retval = -ENOMEM; - pid = alloc_pid(task_active_pid_ns(p)); + pid = alloc_pid(p->nsproxy->pid_ns); if (!pid) goto bad_fork_cleanup_io; if (clone_flags & CLONE_NEWPID) { - retval = pid_ns_prepare_proc(task_active_pid_ns(p)); + retval = pid_ns_prepare_proc(p->nsproxy->pid_ns); if (retval < 0) goto bad_fork_free_pid; } diff --git a/kernel/pid.c b/kernel/pid.c index af9224cdd6c0..1b3586fe753a 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -474,6 +474,12 @@ pid_t task_session_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) } EXPORT_SYMBOL(task_session_nr_ns); +struct pid_namespace *task_active_pid_ns(struct task_struct *tsk) +{ + return ns_of_pid(task_pid(tsk)); +} +EXPORT_SYMBOL_GPL(task_active_pid_ns); + /* * Used by proc to find the first pid that is greater than or equal to nr. * -- cgit v1.2.3 From df4927bf6ccf6278a97a44bd107080c71b269cb5 Mon Sep 17 00:00:00 2001 From: Wu Fengguang Date: Wed, 7 Jan 2009 18:09:14 -0800 Subject: generic swap(): sched: remove local swap() macro Use the new generic implementation. Signed-off-by: Wu Fengguang Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/sched_fair.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'kernel') diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index e0c0b4bc3f08..8e1352c75557 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -1617,8 +1617,6 @@ static void task_tick_fair(struct rq *rq, struct task_struct *curr, int queued) } } -#define swap(a, b) do { typeof(a) tmp = (a); (a) = (b); (b) = tmp; } while (0) - /* * Share the fairness runtime between parent and child, thus the * total amount of pressure for CPU stays equal - new tasks -- cgit v1.2.3 From 33b04b9308959af7febc1c111c766fa3fd8b1934 Mon Sep 17 00:00:00 2001 From: Arjan van de Ven Date: Thu, 8 Jan 2009 12:35:11 -0800 Subject: async: make async_synchronize_full() more serializing turns out that there are real problems with allowing async tasks that are scheduled from async tasks to run after the async_synchronize_full() returns. This patch makes the _full more strict and a complete synchronization. Later I might need to add back a lighter form of synchronization for other uses.. but not right now. Signed-off-by: Arjan van de Ven Signed-off-by: Linus Torvalds --- kernel/async.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/async.c b/kernel/async.c index 97373380c9e7..64cc916299a5 100644 --- a/kernel/async.c +++ b/kernel/async.c @@ -206,7 +206,9 @@ EXPORT_SYMBOL_GPL(async_schedule_special); void async_synchronize_full(void) { - async_synchronize_cookie(next_cookie); + do { + async_synchronize_cookie(next_cookie); + } while (!list_empty(&async_running) || !list_empty(&async_pending)); } EXPORT_SYMBOL_GPL(async_synchronize_full); -- cgit v1.2.3 From 0de336814107358bc8c4173bf9ce2d42445173fe Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 9 Jan 2009 16:13:41 +0000 Subject: CRED: Missing put_cred() in prepare_kernel_cred() Missing put_cred() in the error handling path of prepare_kernel_cred(). Signed-off-by: David Howells Acked-by: Steve Dickson Signed-off-by: Linus Torvalds --- kernel/cred.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel') diff --git a/kernel/cred.c b/kernel/cred.c index ff7bc071991c..fc222e4acfb0 100644 --- a/kernel/cred.c +++ b/kernel/cred.c @@ -529,6 +529,7 @@ struct cred *prepare_kernel_cred(struct task_struct *daemon) error: put_cred(new); + put_cred(old); return NULL; } EXPORT_SYMBOL(prepare_kernel_cred); -- cgit v1.2.3 From 43529c97122f2c851126447963eedcb8cba74fbe Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 9 Jan 2009 16:13:46 +0000 Subject: CRED: Must initialise the new creds in prepare_kernel_cred() The newly allocated creds in prepare_kernel_cred() must be initialised before get_uid() and get_group_info() can access them. They should be copied from the old credentials. Reported-by: Steve Dickson Signed-off-by: David Howells Acked-by: Steve Dickson Signed-off-by: Linus Torvalds --- kernel/cred.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel') diff --git a/kernel/cred.c b/kernel/cred.c index fc222e4acfb0..043f78c133c4 100644 --- a/kernel/cred.c +++ b/kernel/cred.c @@ -506,6 +506,7 @@ struct cred *prepare_kernel_cred(struct task_struct *daemon) else old = get_cred(&init_cred); + *new = *old; get_uid(new->user); get_group_info(new->group_info); -- cgit v1.2.3 From cdb80f630be5cbc23d82331f24dc4704f75b64f4 Mon Sep 17 00:00:00 2001 From: Arjan van de Ven Date: Fri, 9 Jan 2009 13:23:45 -0800 Subject: async: make async a command line option for now ... and have it default off. This does allow people to work with it for testing. Signed-off-by: Arjan van de Ven --- kernel/async.c | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/async.c b/kernel/async.c index 64cc916299a5..f286e9f2b736 100644 --- a/kernel/async.c +++ b/kernel/async.c @@ -65,6 +65,8 @@ static LIST_HEAD(async_pending); static LIST_HEAD(async_running); static DEFINE_SPINLOCK(async_lock); +static int async_enabled = 0; + struct async_entry { struct list_head list; async_cookie_t cookie; @@ -169,7 +171,7 @@ static async_cookie_t __async_schedule(async_func_ptr *ptr, void *data, struct l * If we're out of memory or if there's too much work * pending already, we execute synchronously. */ - if (!entry || atomic_read(&entry_count) > MAX_WORK) { + if (!async_enabled || !entry || atomic_read(&entry_count) > MAX_WORK) { kfree(entry); spin_lock_irqsave(&async_lock, flags); newcookie = next_cookie++; @@ -316,8 +318,18 @@ static int async_manager_thread(void *unused) static int __init async_init(void) { - kthread_run(async_manager_thread, NULL, "async/mgr"); + if (async_enabled) + kthread_run(async_manager_thread, NULL, "async/mgr"); return 0; } +static int __init setup_async(char *str) +{ + async_enabled = 1; + return 1; +} + +__setup("fastboot", setup_async); + + core_initcall(async_init); -- cgit v1.2.3