From d6bbbd29b1de2da807753be8a3a992a72aef42de Mon Sep 17 00:00:00 2001 From: Raymond Jennings Date: Wed, 11 Sep 2013 14:20:16 -0700 Subject: swap: warn when a swap area overflows the maximum size It is possible to swapon a swap area that is too big for the pte width to handle. Presently this failure happens silently. Instead, emit a diagnostic to warn the user. Testing results, root prompt commands and kernel log messages: # lvresize /dev/system/swap --size 16G # mkswap /dev/system/swap # swapon /dev/system/swap Jul 7 04:27:22 warfang kernel: Adding 16777212k swap on /dev/mapper/system-swap. Priority:-1 extents:1 across:16777212k # lvresize /dev/system/swap --size 64G # mkswap /dev/system/swap # swapon /dev/system/swap Jul 7 04:27:22 warfang kernel: Truncating oversized swap area, only using 33554432k out of 67108860k Jul 7 04:27:22 warfang kernel: Adding 33554428k swap on /dev/mapper/system-swap. Priority:-1 extents:1 across:33554428k [akpm@linux-foundation.org: fix warning] Signed-off-by: Raymond Jennings Acked-by: Valdis Kletnieks Reviewed-by: Rik van Riel Cc: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/swapfile.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) (limited to 'mm/swapfile.c') diff --git a/mm/swapfile.c b/mm/swapfile.c index 6cf2e60983b7..b5212eea6c3c 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -1926,6 +1926,7 @@ static unsigned long read_swap_header(struct swap_info_struct *p, int i; unsigned long maxpages; unsigned long swapfilepages; + unsigned long last_page; if (memcmp("SWAPSPACE2", swap_header->magic.magic, 10)) { printk(KERN_ERR "Unable to find swap-space signature\n"); @@ -1968,8 +1969,15 @@ static unsigned long read_swap_header(struct swap_info_struct *p, */ maxpages = swp_offset(pte_to_swp_entry( swp_entry_to_pte(swp_entry(0, ~0UL)))) + 1; - if (maxpages > swap_header->info.last_page) { - maxpages = swap_header->info.last_page + 1; + last_page = swap_header->info.last_page; + if (last_page > maxpages) { + printk(KERN_WARNING + "Truncating oversized swap area, only using %luk out of %luk\n", + maxpages << (PAGE_SHIFT - 10), + last_page << (PAGE_SHIFT - 10)); + } + if (maxpages > last_page) { + maxpages = last_page + 1; /* p->max is an unsigned int: don't overflow it */ if ((unsigned int)maxpages == 0) maxpages = UINT_MAX; -- cgit v1.2.2 From 465c47fd8dc44302fed6c4eab8927464744ce08c Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Wed, 11 Sep 2013 14:20:17 -0700 Subject: mm/swapfile.c: convert to pr_foo() A few 80-col gymnastics were cleaned up as a result. Cc: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/swapfile.c | 30 +++++++++++++----------------- 1 file changed, 13 insertions(+), 17 deletions(-) (limited to 'mm/swapfile.c') diff --git a/mm/swapfile.c b/mm/swapfile.c index b5212eea6c3c..6ef2d15c5fe3 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -527,16 +527,16 @@ static struct swap_info_struct *swap_info_get(swp_entry_t entry) return p; bad_free: - printk(KERN_ERR "swap_free: %s%08lx\n", Unused_offset, entry.val); + pr_err("swap_free: %s%08lx\n", Unused_offset, entry.val); goto out; bad_offset: - printk(KERN_ERR "swap_free: %s%08lx\n", Bad_offset, entry.val); + pr_err("swap_free: %s%08lx\n", Bad_offset, entry.val); goto out; bad_device: - printk(KERN_ERR "swap_free: %s%08lx\n", Unused_file, entry.val); + pr_err("swap_free: %s%08lx\n", Unused_file, entry.val); goto out; bad_nofile: - printk(KERN_ERR "swap_free: %s%08lx\n", Bad_file, entry.val); + pr_err("swap_free: %s%08lx\n", Bad_file, entry.val); out: return NULL; } @@ -1929,7 +1929,7 @@ static unsigned long read_swap_header(struct swap_info_struct *p, unsigned long last_page; if (memcmp("SWAPSPACE2", swap_header->magic.magic, 10)) { - printk(KERN_ERR "Unable to find swap-space signature\n"); + pr_err("Unable to find swap-space signature\n"); return 0; } @@ -1943,9 +1943,8 @@ static unsigned long read_swap_header(struct swap_info_struct *p, } /* Check the swap header's sub-version */ if (swap_header->info.version != 1) { - printk(KERN_WARNING - "Unable to handle swap header version %d\n", - swap_header->info.version); + pr_warn("Unable to handle swap header version %d\n", + swap_header->info.version); return 0; } @@ -1971,8 +1970,7 @@ static unsigned long read_swap_header(struct swap_info_struct *p, swp_entry_to_pte(swp_entry(0, ~0UL)))) + 1; last_page = swap_header->info.last_page; if (last_page > maxpages) { - printk(KERN_WARNING - "Truncating oversized swap area, only using %luk out of %luk\n", + pr_warn("Truncating oversized swap area, only using %luk out of %luk\n", maxpages << (PAGE_SHIFT - 10), last_page << (PAGE_SHIFT - 10)); } @@ -1988,8 +1986,7 @@ static unsigned long read_swap_header(struct swap_info_struct *p, return 0; swapfilepages = i_size_read(inode) >> PAGE_SHIFT; if (swapfilepages && maxpages > swapfilepages) { - printk(KERN_WARNING - "Swap area shorter than signature indicates\n"); + pr_warn("Swap area shorter than signature indicates\n"); return 0; } if (swap_header->info.nr_badpages && S_ISREG(inode->i_mode)) @@ -2032,7 +2029,7 @@ static int setup_swap_map_and_extents(struct swap_info_struct *p, nr_good_pages = p->pages; } if (!nr_good_pages) { - printk(KERN_WARNING "Empty swap-file\n"); + pr_warn("Empty swap-file\n"); return -EINVAL; } @@ -2186,8 +2183,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) if (p->flags & SWP_AREA_DISCARD) { int err = discard_swap(p); if (unlikely(err)) - printk(KERN_ERR - "swapon: discard_swap(%p): %d\n", + pr_err("swapon: discard_swap(%p): %d\n", p, err); } } @@ -2200,7 +2196,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) (swap_flags & SWAP_FLAG_PRIO_MASK) >> SWAP_FLAG_PRIO_SHIFT; enable_swap_info(p, prio, swap_map, frontswap_map); - printk(KERN_INFO "Adding %uk swap on %s. " + pr_info("Adding %uk swap on %s. " "Priority:%d extents:%d across:%lluk %s%s%s%s%s\n", p->pages<<(PAGE_SHIFT-10), name->name, p->prio, nr_extents, (unsigned long long)span<<(PAGE_SHIFT-10), @@ -2334,7 +2330,7 @@ out: return err; bad_file: - printk(KERN_ERR "swap_dup: %s%08lx\n", Bad_file, entry.val); + pr_err("swap_dup: %s%08lx\n", Bad_file, entry.val); goto out; } -- cgit v1.2.2 From 2a8f9449343260373398d59228a62a4332ea513a Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Wed, 11 Sep 2013 14:20:28 -0700 Subject: swap: change block allocation algorithm for SSD I'm using a fast SSD to do swap. scan_swap_map() sometimes uses up to 20~30% CPU time (when cluster is hard to find, the CPU time can be up to 80%), which becomes a bottleneck. scan_swap_map() scans a byte array to search a 256 page cluster, which is very slow. Here I introduced a simple algorithm to search cluster. Since we only care about 256 pages cluster, we can just use a counter to track if a cluster is free. Every 256 pages use one int to store the counter. If the counter of a cluster is 0, the cluster is free. All free clusters will be added to a list, so searching cluster is very efficient. With this, scap_swap_map() overhead disappears. This might help low end SD card swap too. Because if the cluster is aligned, SD firmware can do flash erase more efficiently. We only enable the algorithm for SSD. Hard disk swap isn't fast enough and has downside with the algorithm which might introduce regression (see below). The patch slightly changes which cluster is choosen. It always adds free cluster to list tail. This can help wear leveling for low end SSD too. And if no cluster found, the scan_swap_map() will do search from the end of last cluster. So if no cluster found, the scan_swap_map() will do search from the end of last free cluster, which is random. For SSD, this isn't a problem at all. Another downside is the cluster must be aligned to 256 pages, which will reduce the chance to find a cluster. I would expect this isn't a big problem for SSD because of the non-seek penality. (And this is the reason I only enable the algorithm for SSD). Signed-off-by: Shaohua Li Cc: Rik van Riel Cc: Minchan Kim Cc: Kyungmin Park Cc: Hugh Dickins Cc: Rafael Aquini Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/swapfile.c | 288 ++++++++++++++++++++++++++++++++++++++++++++++++++-------- 1 file changed, 250 insertions(+), 38 deletions(-) (limited to 'mm/swapfile.c') diff --git a/mm/swapfile.c b/mm/swapfile.c index 6ef2d15c5fe3..d1fbeb486de5 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -184,6 +184,134 @@ static int wait_for_discard(void *word) #define SWAPFILE_CLUSTER 256 #define LATENCY_LIMIT 256 +static inline void cluster_set_flag(struct swap_cluster_info *info, + unsigned int flag) +{ + info->flags = flag; +} + +static inline unsigned int cluster_count(struct swap_cluster_info *info) +{ + return info->data; +} + +static inline void cluster_set_count(struct swap_cluster_info *info, + unsigned int c) +{ + info->data = c; +} + +static inline void cluster_set_count_flag(struct swap_cluster_info *info, + unsigned int c, unsigned int f) +{ + info->flags = f; + info->data = c; +} + +static inline unsigned int cluster_next(struct swap_cluster_info *info) +{ + return info->data; +} + +static inline void cluster_set_next(struct swap_cluster_info *info, + unsigned int n) +{ + info->data = n; +} + +static inline void cluster_set_next_flag(struct swap_cluster_info *info, + unsigned int n, unsigned int f) +{ + info->flags = f; + info->data = n; +} + +static inline bool cluster_is_free(struct swap_cluster_info *info) +{ + return info->flags & CLUSTER_FLAG_FREE; +} + +static inline bool cluster_is_null(struct swap_cluster_info *info) +{ + return info->flags & CLUSTER_FLAG_NEXT_NULL; +} + +static inline void cluster_set_null(struct swap_cluster_info *info) +{ + info->flags = CLUSTER_FLAG_NEXT_NULL; + info->data = 0; +} + +/* + * The cluster corresponding to page_nr will be used. The cluster will be + * removed from free cluster list and its usage counter will be increased. + */ +static void inc_cluster_info_page(struct swap_info_struct *p, + struct swap_cluster_info *cluster_info, unsigned long page_nr) +{ + unsigned long idx = page_nr / SWAPFILE_CLUSTER; + + if (!cluster_info) + return; + if (cluster_is_free(&cluster_info[idx])) { + VM_BUG_ON(cluster_next(&p->free_cluster_head) != idx); + cluster_set_next_flag(&p->free_cluster_head, + cluster_next(&cluster_info[idx]), 0); + if (cluster_next(&p->free_cluster_tail) == idx) { + cluster_set_null(&p->free_cluster_tail); + cluster_set_null(&p->free_cluster_head); + } + cluster_set_count_flag(&cluster_info[idx], 0, 0); + } + + VM_BUG_ON(cluster_count(&cluster_info[idx]) >= SWAPFILE_CLUSTER); + cluster_set_count(&cluster_info[idx], + cluster_count(&cluster_info[idx]) + 1); +} + +/* + * The cluster corresponding to page_nr decreases one usage. If the usage + * counter becomes 0, which means no page in the cluster is in using, we can + * optionally discard the cluster and add it to free cluster list. + */ +static void dec_cluster_info_page(struct swap_info_struct *p, + struct swap_cluster_info *cluster_info, unsigned long page_nr) +{ + unsigned long idx = page_nr / SWAPFILE_CLUSTER; + + if (!cluster_info) + return; + + VM_BUG_ON(cluster_count(&cluster_info[idx]) == 0); + cluster_set_count(&cluster_info[idx], + cluster_count(&cluster_info[idx]) - 1); + + if (cluster_count(&cluster_info[idx]) == 0) { + cluster_set_flag(&cluster_info[idx], CLUSTER_FLAG_FREE); + if (cluster_is_null(&p->free_cluster_head)) { + cluster_set_next_flag(&p->free_cluster_head, idx, 0); + cluster_set_next_flag(&p->free_cluster_tail, idx, 0); + } else { + unsigned int tail = cluster_next(&p->free_cluster_tail); + cluster_set_next(&cluster_info[tail], idx); + cluster_set_next_flag(&p->free_cluster_tail, idx, 0); + } + } +} + +/* + * It's possible scan_swap_map() uses a free cluster in the middle of free + * cluster list. Avoiding such abuse to avoid list corruption. + */ +static inline bool scan_swap_map_recheck_cluster(struct swap_info_struct *si, + unsigned long offset) +{ + offset /= SWAPFILE_CLUSTER; + return !cluster_is_null(&si->free_cluster_head) && + offset != cluster_next(&si->free_cluster_head) && + cluster_is_free(&si->cluster_info[offset]); +} + static unsigned long scan_swap_map(struct swap_info_struct *si, unsigned char usage) { @@ -225,6 +353,25 @@ static unsigned long scan_swap_map(struct swap_info_struct *si, si->lowest_alloc = si->max; si->highest_alloc = 0; } +check_cluster: + if (!cluster_is_null(&si->free_cluster_head)) { + offset = cluster_next(&si->free_cluster_head) * + SWAPFILE_CLUSTER; + last_in_cluster = offset + SWAPFILE_CLUSTER - 1; + si->cluster_next = offset; + si->cluster_nr = SWAPFILE_CLUSTER - 1; + found_free_cluster = 1; + goto checks; + } else if (si->cluster_info) { + /* + * Checking free cluster is fast enough, we can do the + * check every time + */ + si->cluster_nr = 0; + si->lowest_alloc = 0; + goto checks; + } + spin_unlock(&si->lock); /* @@ -285,6 +432,8 @@ static unsigned long scan_swap_map(struct swap_info_struct *si, } checks: + if (scan_swap_map_recheck_cluster(si, offset)) + goto check_cluster; if (!(si->flags & SWP_WRITEOK)) goto no_page; if (!si->highest_bit) @@ -317,6 +466,7 @@ checks: si->highest_bit = 0; } si->swap_map[offset] = usage; + inc_cluster_info_page(si, si->cluster_info, offset); si->cluster_next = offset + 1; si->flags -= SWP_SCANNING; @@ -600,6 +750,7 @@ static unsigned char swap_entry_free(struct swap_info_struct *p, /* free if no reference */ if (!usage) { + dec_cluster_info_page(p, p->cluster_info, offset); if (offset < p->lowest_bit) p->lowest_bit = offset; if (offset > p->highest_bit) @@ -1524,7 +1675,8 @@ static int setup_swap_extents(struct swap_info_struct *sis, sector_t *span) } static void _enable_swap_info(struct swap_info_struct *p, int prio, - unsigned char *swap_map) + unsigned char *swap_map, + struct swap_cluster_info *cluster_info) { int i, prev; @@ -1533,6 +1685,7 @@ static void _enable_swap_info(struct swap_info_struct *p, int prio, else p->prio = --least_priority; p->swap_map = swap_map; + p->cluster_info = cluster_info; p->flags |= SWP_WRITEOK; atomic_long_add(p->pages, &nr_swap_pages); total_swap_pages += p->pages; @@ -1553,12 +1706,13 @@ static void _enable_swap_info(struct swap_info_struct *p, int prio, static void enable_swap_info(struct swap_info_struct *p, int prio, unsigned char *swap_map, + struct swap_cluster_info *cluster_info, unsigned long *frontswap_map) { frontswap_init(p->type, frontswap_map); spin_lock(&swap_lock); spin_lock(&p->lock); - _enable_swap_info(p, prio, swap_map); + _enable_swap_info(p, prio, swap_map, cluster_info); spin_unlock(&p->lock); spin_unlock(&swap_lock); } @@ -1567,7 +1721,7 @@ static void reinsert_swap_info(struct swap_info_struct *p) { spin_lock(&swap_lock); spin_lock(&p->lock); - _enable_swap_info(p, p->prio, p->swap_map); + _enable_swap_info(p, p->prio, p->swap_map, p->cluster_info); spin_unlock(&p->lock); spin_unlock(&swap_lock); } @@ -1576,6 +1730,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) { struct swap_info_struct *p = NULL; unsigned char *swap_map; + struct swap_cluster_info *cluster_info; unsigned long *frontswap_map; struct file *swap_file, *victim; struct address_space *mapping; @@ -1675,6 +1830,8 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) p->max = 0; swap_map = p->swap_map; p->swap_map = NULL; + cluster_info = p->cluster_info; + p->cluster_info = NULL; p->flags = 0; frontswap_map = frontswap_map_get(p); frontswap_map_set(p, NULL); @@ -1683,6 +1840,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) frontswap_invalidate_area(type); mutex_unlock(&swapon_mutex); vfree(swap_map); + vfree(cluster_info); vfree(frontswap_map); /* Destroy swap account informatin */ swap_cgroup_swapoff(type); @@ -2000,15 +2158,21 @@ static unsigned long read_swap_header(struct swap_info_struct *p, static int setup_swap_map_and_extents(struct swap_info_struct *p, union swap_header *swap_header, unsigned char *swap_map, + struct swap_cluster_info *cluster_info, unsigned long maxpages, sector_t *span) { int i; unsigned int nr_good_pages; int nr_extents; + unsigned long nr_clusters = DIV_ROUND_UP(maxpages, SWAPFILE_CLUSTER); + unsigned long idx = p->cluster_next / SWAPFILE_CLUSTER; nr_good_pages = maxpages - 1; /* omit header page */ + cluster_set_null(&p->free_cluster_head); + cluster_set_null(&p->free_cluster_tail); + for (i = 0; i < swap_header->info.nr_badpages; i++) { unsigned int page_nr = swap_header->info.badpages[i]; if (page_nr == 0 || page_nr > swap_header->info.last_page) @@ -2016,11 +2180,25 @@ static int setup_swap_map_and_extents(struct swap_info_struct *p, if (page_nr < maxpages) { swap_map[page_nr] = SWAP_MAP_BAD; nr_good_pages--; + /* + * Haven't marked the cluster free yet, no list + * operation involved + */ + inc_cluster_info_page(p, cluster_info, page_nr); } } + /* Haven't marked the cluster free yet, no list operation involved */ + for (i = maxpages; i < round_up(maxpages, SWAPFILE_CLUSTER); i++) + inc_cluster_info_page(p, cluster_info, i); + if (nr_good_pages) { swap_map[0] = SWAP_MAP_BAD; + /* + * Not mark the cluster free yet, no list + * operation involved + */ + inc_cluster_info_page(p, cluster_info, 0); p->max = maxpages; p->pages = nr_good_pages; nr_extents = setup_swap_extents(p, span); @@ -2033,6 +2211,30 @@ static int setup_swap_map_and_extents(struct swap_info_struct *p, return -EINVAL; } + if (!cluster_info) + return nr_extents; + + for (i = 0; i < nr_clusters; i++) { + if (!cluster_count(&cluster_info[idx])) { + cluster_set_flag(&cluster_info[idx], CLUSTER_FLAG_FREE); + if (cluster_is_null(&p->free_cluster_head)) { + cluster_set_next_flag(&p->free_cluster_head, + idx, 0); + cluster_set_next_flag(&p->free_cluster_tail, + idx, 0); + } else { + unsigned int tail; + + tail = cluster_next(&p->free_cluster_tail); + cluster_set_next(&cluster_info[tail], idx); + cluster_set_next_flag(&p->free_cluster_tail, + idx, 0); + } + } + idx++; + if (idx == nr_clusters) + idx = 0; + } return nr_extents; } @@ -2064,6 +2266,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) sector_t span; unsigned long maxpages; unsigned char *swap_map = NULL; + struct swap_cluster_info *cluster_info = NULL; unsigned long *frontswap_map = NULL; struct page *page = NULL; struct inode *inode = NULL; @@ -2137,13 +2340,28 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) error = -ENOMEM; goto bad_swap; } + if (p->bdev && blk_queue_nonrot(bdev_get_queue(p->bdev))) { + p->flags |= SWP_SOLIDSTATE; + /* + * select a random position to start with to help wear leveling + * SSD + */ + p->cluster_next = 1 + (prandom_u32() % p->highest_bit); + + cluster_info = vzalloc(DIV_ROUND_UP(maxpages, + SWAPFILE_CLUSTER) * sizeof(*cluster_info)); + if (!cluster_info) { + error = -ENOMEM; + goto bad_swap; + } + } error = swap_cgroup_swapon(p->type, maxpages); if (error) goto bad_swap; nr_extents = setup_swap_map_and_extents(p, swap_header, swap_map, - maxpages, &span); + cluster_info, maxpages, &span); if (unlikely(nr_extents < 0)) { error = nr_extents; goto bad_swap; @@ -2152,40 +2370,33 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) if (frontswap_enabled) frontswap_map = vzalloc(BITS_TO_LONGS(maxpages) * sizeof(long)); - if (p->bdev) { - if (blk_queue_nonrot(bdev_get_queue(p->bdev))) { - p->flags |= SWP_SOLIDSTATE; - p->cluster_next = 1 + (prandom_u32() % p->highest_bit); - } - - if ((swap_flags & SWAP_FLAG_DISCARD) && swap_discardable(p)) { - /* - * When discard is enabled for swap with no particular - * policy flagged, we set all swap discard flags here in - * order to sustain backward compatibility with older - * swapon(8) releases. - */ - p->flags |= (SWP_DISCARDABLE | SWP_AREA_DISCARD | - SWP_PAGE_DISCARD); + if (p->bdev &&(swap_flags & SWAP_FLAG_DISCARD) && swap_discardable(p)) { + /* + * When discard is enabled for swap with no particular + * policy flagged, we set all swap discard flags here in + * order to sustain backward compatibility with older + * swapon(8) releases. + */ + p->flags |= (SWP_DISCARDABLE | SWP_AREA_DISCARD | + SWP_PAGE_DISCARD); - /* - * By flagging sys_swapon, a sysadmin can tell us to - * either do single-time area discards only, or to just - * perform discards for released swap page-clusters. - * Now it's time to adjust the p->flags accordingly. - */ - if (swap_flags & SWAP_FLAG_DISCARD_ONCE) - p->flags &= ~SWP_PAGE_DISCARD; - else if (swap_flags & SWAP_FLAG_DISCARD_PAGES) - p->flags &= ~SWP_AREA_DISCARD; - - /* issue a swapon-time discard if it's still required */ - if (p->flags & SWP_AREA_DISCARD) { - int err = discard_swap(p); - if (unlikely(err)) - pr_err("swapon: discard_swap(%p): %d\n", - p, err); - } + /* + * By flagging sys_swapon, a sysadmin can tell us to + * either do single-time area discards only, or to just + * perform discards for released swap page-clusters. + * Now it's time to adjust the p->flags accordingly. + */ + if (swap_flags & SWAP_FLAG_DISCARD_ONCE) + p->flags &= ~SWP_PAGE_DISCARD; + else if (swap_flags & SWAP_FLAG_DISCARD_PAGES) + p->flags &= ~SWP_AREA_DISCARD; + + /* issue a swapon-time discard if it's still required */ + if (p->flags & SWP_AREA_DISCARD) { + int err = discard_swap(p); + if (unlikely(err)) + pr_err("swapon: discard_swap(%p): %d\n", + p, err); } } @@ -2194,7 +2405,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) if (swap_flags & SWAP_FLAG_PREFER) prio = (swap_flags & SWAP_FLAG_PRIO_MASK) >> SWAP_FLAG_PRIO_SHIFT; - enable_swap_info(p, prio, swap_map, frontswap_map); + enable_swap_info(p, prio, swap_map, cluster_info, frontswap_map); pr_info("Adding %uk swap on %s. " "Priority:%d extents:%d across:%lluk %s%s%s%s%s\n", @@ -2226,6 +2437,7 @@ bad_swap: p->flags = 0; spin_unlock(&swap_lock); vfree(swap_map); + vfree(cluster_info); if (swap_file) { if (inode && S_ISREG(inode->i_mode)) { mutex_unlock(&inode->i_mutex); -- cgit v1.2.2 From 815c2c543d3aeb914a361f981440ece552778724 Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Wed, 11 Sep 2013 14:20:30 -0700 Subject: swap: make swap discard async swap can do cluster discard for SSD, which is good, but there are some problems here: 1. swap do the discard just before page reclaim gets a swap entry and writes the disk sectors. This is useless for high end SSD, because an overwrite to a sector implies a discard to original sector too. A discard + overwrite == overwrite. 2. the purpose of doing discard is to improve SSD firmware garbage collection. Idealy we should send discard as early as possible, so firmware can do something smart. Sending discard just after swap entry is freed is considered early compared to sending discard before write. Of course, if workload is already bound to gc speed, sending discard earlier or later doesn't make 3. block discard is a sync API, which will delay scan_swap_map() significantly. 4. Write and discard command can be executed parallel in PCIe SSD. Making swap discard async can make execution more efficiently. This patch makes swap discard async and moves discard to where swap entry is freed. Discard and write have no dependence now, so above issues can be avoided. Idealy we should do discard for any freed sectors, but some SSD discard is very slow. This patch still does discard for a whole cluster. My test does a several round of 'mmap, write, unmap', which will trigger a lot of swap discard. In a fusionio card, with this patch, the test runtime is reduced to 18% of the time without it, so around 5.5x faster. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Shaohua Li Cc: Rik van Riel Cc: Minchan Kim Cc: Kyungmin Park Cc: Hugh Dickins Cc: Rafael Aquini Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/swapfile.c | 192 ++++++++++++++++++++++++++++++++++------------------------ 1 file changed, 114 insertions(+), 78 deletions(-) (limited to 'mm/swapfile.c') diff --git a/mm/swapfile.c b/mm/swapfile.c index d1fbeb486de5..dac47c66055c 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -175,12 +175,6 @@ static void discard_swap_cluster(struct swap_info_struct *si, } } -static int wait_for_discard(void *word) -{ - schedule(); - return 0; -} - #define SWAPFILE_CLUSTER 256 #define LATENCY_LIMIT 256 @@ -242,6 +236,90 @@ static inline void cluster_set_null(struct swap_cluster_info *info) info->data = 0; } +/* Add a cluster to discard list and schedule it to do discard */ +static void swap_cluster_schedule_discard(struct swap_info_struct *si, + unsigned int idx) +{ + /* + * If scan_swap_map() can't find a free cluster, it will check + * si->swap_map directly. To make sure the discarding cluster isn't + * taken by scan_swap_map(), mark the swap entries bad (occupied). It + * will be cleared after discard + */ + memset(si->swap_map + idx * SWAPFILE_CLUSTER, + SWAP_MAP_BAD, SWAPFILE_CLUSTER); + + if (cluster_is_null(&si->discard_cluster_head)) { + cluster_set_next_flag(&si->discard_cluster_head, + idx, 0); + cluster_set_next_flag(&si->discard_cluster_tail, + idx, 0); + } else { + unsigned int tail = cluster_next(&si->discard_cluster_tail); + cluster_set_next(&si->cluster_info[tail], idx); + cluster_set_next_flag(&si->discard_cluster_tail, + idx, 0); + } + + schedule_work(&si->discard_work); +} + +/* + * Doing discard actually. After a cluster discard is finished, the cluster + * will be added to free cluster list. caller should hold si->lock. +*/ +static void swap_do_scheduled_discard(struct swap_info_struct *si) +{ + struct swap_cluster_info *info; + unsigned int idx; + + info = si->cluster_info; + + while (!cluster_is_null(&si->discard_cluster_head)) { + idx = cluster_next(&si->discard_cluster_head); + + cluster_set_next_flag(&si->discard_cluster_head, + cluster_next(&info[idx]), 0); + if (cluster_next(&si->discard_cluster_tail) == idx) { + cluster_set_null(&si->discard_cluster_head); + cluster_set_null(&si->discard_cluster_tail); + } + spin_unlock(&si->lock); + + discard_swap_cluster(si, idx * SWAPFILE_CLUSTER, + SWAPFILE_CLUSTER); + + spin_lock(&si->lock); + cluster_set_flag(&info[idx], CLUSTER_FLAG_FREE); + if (cluster_is_null(&si->free_cluster_head)) { + cluster_set_next_flag(&si->free_cluster_head, + idx, 0); + cluster_set_next_flag(&si->free_cluster_tail, + idx, 0); + } else { + unsigned int tail; + + tail = cluster_next(&si->free_cluster_tail); + cluster_set_next(&info[tail], idx); + cluster_set_next_flag(&si->free_cluster_tail, + idx, 0); + } + memset(si->swap_map + idx * SWAPFILE_CLUSTER, + 0, SWAPFILE_CLUSTER); + } +} + +static void swap_discard_work(struct work_struct *work) +{ + struct swap_info_struct *si; + + si = container_of(work, struct swap_info_struct, discard_work); + + spin_lock(&si->lock); + swap_do_scheduled_discard(si); + spin_unlock(&si->lock); +} + /* * The cluster corresponding to page_nr will be used. The cluster will be * removed from free cluster list and its usage counter will be increased. @@ -287,6 +365,16 @@ static void dec_cluster_info_page(struct swap_info_struct *p, cluster_count(&cluster_info[idx]) - 1); if (cluster_count(&cluster_info[idx]) == 0) { + /* + * If the swap is discardable, prepare discard the cluster + * instead of free it immediately. The cluster will be freed + * after discard. + */ + if (p->flags & SWP_PAGE_DISCARD) { + swap_cluster_schedule_discard(p, idx); + return; + } + cluster_set_flag(&cluster_info[idx], CLUSTER_FLAG_FREE); if (cluster_is_null(&p->free_cluster_head)) { cluster_set_next_flag(&p->free_cluster_head, idx, 0); @@ -319,7 +407,6 @@ static unsigned long scan_swap_map(struct swap_info_struct *si, unsigned long scan_base; unsigned long last_in_cluster = 0; int latency_ration = LATENCY_LIMIT; - int found_free_cluster = 0; /* * We try to cluster swap pages by allocating them sequentially @@ -340,19 +427,6 @@ static unsigned long scan_swap_map(struct swap_info_struct *si, si->cluster_nr = SWAPFILE_CLUSTER - 1; goto checks; } - if (si->flags & SWP_PAGE_DISCARD) { - /* - * Start range check on racing allocations, in case - * they overlap the cluster we eventually decide on - * (we scan without swap_lock to allow preemption). - * It's hardly conceivable that cluster_nr could be - * wrapped during our scan, but don't depend on it. - */ - if (si->lowest_alloc) - goto checks; - si->lowest_alloc = si->max; - si->highest_alloc = 0; - } check_cluster: if (!cluster_is_null(&si->free_cluster_head)) { offset = cluster_next(&si->free_cluster_head) * @@ -360,15 +434,27 @@ check_cluster: last_in_cluster = offset + SWAPFILE_CLUSTER - 1; si->cluster_next = offset; si->cluster_nr = SWAPFILE_CLUSTER - 1; - found_free_cluster = 1; goto checks; } else if (si->cluster_info) { + /* + * we don't have free cluster but have some clusters in + * discarding, do discard now and reclaim them + */ + if (!cluster_is_null(&si->discard_cluster_head)) { + si->cluster_nr = 0; + swap_do_scheduled_discard(si); + scan_base = offset = si->cluster_next; + if (!si->cluster_nr) + goto check_cluster; + si->cluster_nr--; + goto checks; + } + /* * Checking free cluster is fast enough, we can do the * check every time */ si->cluster_nr = 0; - si->lowest_alloc = 0; goto checks; } @@ -395,7 +481,6 @@ check_cluster: offset -= SWAPFILE_CLUSTER - 1; si->cluster_next = offset; si->cluster_nr = SWAPFILE_CLUSTER - 1; - found_free_cluster = 1; goto checks; } if (unlikely(--latency_ration < 0)) { @@ -416,7 +501,6 @@ check_cluster: offset -= SWAPFILE_CLUSTER - 1; si->cluster_next = offset; si->cluster_nr = SWAPFILE_CLUSTER - 1; - found_free_cluster = 1; goto checks; } if (unlikely(--latency_ration < 0)) { @@ -428,7 +512,6 @@ check_cluster: offset = scan_base; spin_lock(&si->lock); si->cluster_nr = SWAPFILE_CLUSTER - 1; - si->lowest_alloc = 0; } checks: @@ -470,59 +553,6 @@ checks: si->cluster_next = offset + 1; si->flags -= SWP_SCANNING; - if (si->lowest_alloc) { - /* - * Only set when SWP_PAGE_DISCARD, and there's a scan - * for a free cluster in progress or just completed. - */ - if (found_free_cluster) { - /* - * To optimize wear-levelling, discard the - * old data of the cluster, taking care not to - * discard any of its pages that have already - * been allocated by racing tasks (offset has - * already stepped over any at the beginning). - */ - if (offset < si->highest_alloc && - si->lowest_alloc <= last_in_cluster) - last_in_cluster = si->lowest_alloc - 1; - si->flags |= SWP_DISCARDING; - spin_unlock(&si->lock); - - if (offset < last_in_cluster) - discard_swap_cluster(si, offset, - last_in_cluster - offset + 1); - - spin_lock(&si->lock); - si->lowest_alloc = 0; - si->flags &= ~SWP_DISCARDING; - - smp_mb(); /* wake_up_bit advises this */ - wake_up_bit(&si->flags, ilog2(SWP_DISCARDING)); - - } else if (si->flags & SWP_DISCARDING) { - /* - * Delay using pages allocated by racing tasks - * until the whole discard has been issued. We - * could defer that delay until swap_writepage, - * but it's easier to keep this self-contained. - */ - spin_unlock(&si->lock); - wait_on_bit(&si->flags, ilog2(SWP_DISCARDING), - wait_for_discard, TASK_UNINTERRUPTIBLE); - spin_lock(&si->lock); - } else { - /* - * Note pages allocated by racing tasks while - * scan for a free cluster is in progress, so - * that its final discard can exclude them. - */ - if (offset < si->lowest_alloc) - si->lowest_alloc = offset; - if (offset > si->highest_alloc) - si->highest_alloc = offset; - } - } return offset; scan: @@ -1806,6 +1836,8 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) goto out_dput; } + flush_work(&p->discard_work); + destroy_swap_extents(p); if (p->flags & SWP_CONTINUED) free_swap_count_continuations(p); @@ -2172,6 +2204,8 @@ static int setup_swap_map_and_extents(struct swap_info_struct *p, cluster_set_null(&p->free_cluster_head); cluster_set_null(&p->free_cluster_tail); + cluster_set_null(&p->discard_cluster_head); + cluster_set_null(&p->discard_cluster_tail); for (i = 0; i < swap_header->info.nr_badpages; i++) { unsigned int page_nr = swap_header->info.badpages[i]; @@ -2281,6 +2315,8 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) if (IS_ERR(p)) return PTR_ERR(p); + INIT_WORK(&p->discard_work, swap_discard_work); + name = getname(specialfile); if (IS_ERR(name)) { error = PTR_ERR(name); -- cgit v1.2.2 From edfe23dac3e2981277087b05bec7fec7790d1835 Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Wed, 11 Sep 2013 14:20:31 -0700 Subject: swap: fix races exposed by swap discard The previous patch can expose races, according to Hugh: swapoff was sometimes failing with "Cannot allocate memory", coming from try_to_unuse()'s -ENOMEM: it needs to allow for swap_duplicate() failing on a free entry temporarily SWAP_MAP_BAD while being discarded. We should use ACCESS_ONCE() there, and whenever accessing swap_map locklessly; but rather than peppering it throughout try_to_unuse(), just declare *swap_map with volatile. try_to_unuse() is accustomed to *swap_map going down racily, but not necessarily to it jumping up from 0 to SWAP_MAP_BAD: we'll be safer to prevent that transition once SWP_WRITEOK is switched off, when it's a waste of time to issue discards anyway (swapon can do a whole discard). Another issue is: In swapin_readahead(), read_swap_cache_async() can read a bad swap entry, because we don't check if readahead swap entry is bad. This doesn't break anything but such swapin page is wasteful and can only be freed at page reclaim. We should avoid read such swap entry. And in discard, we mark swap entry SWAP_MAP_BAD and then switch it to normal when discard is finished. If readahead reads such swap entry, we have the same issue, so we much check if swap entry is bad too. Thanks Hugh to inspire swapin_readahead could use bad swap entry. [include Hugh's patch 'swap: fix swapoff ENOMEMs from discard'] Signed-off-by: Shaohua Li Signed-off-by: Hugh Dickins Cc: Rik van Riel Cc: Minchan Kim Cc: Kyungmin Park Cc: Rafael Aquini Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/swapfile.c | 31 +++++++++++++++++++++++++++---- 1 file changed, 27 insertions(+), 4 deletions(-) (limited to 'mm/swapfile.c') diff --git a/mm/swapfile.c b/mm/swapfile.c index dac47c66055c..98e52e373bd8 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -370,7 +370,8 @@ static void dec_cluster_info_page(struct swap_info_struct *p, * instead of free it immediately. The cluster will be freed * after discard. */ - if (p->flags & SWP_PAGE_DISCARD) { + if ((p->flags & (SWP_WRITEOK | SWP_PAGE_DISCARD)) == + (SWP_WRITEOK | SWP_PAGE_DISCARD)) { swap_cluster_schedule_discard(p, idx); return; } @@ -1288,7 +1289,7 @@ static unsigned int find_next_to_unuse(struct swap_info_struct *si, else continue; } - count = si->swap_map[i]; + count = ACCESS_ONCE(si->swap_map[i]); if (count && swap_count(count) != SWAP_MAP_BAD) break; } @@ -1308,7 +1309,11 @@ int try_to_unuse(unsigned int type, bool frontswap, { struct swap_info_struct *si = swap_info[type]; struct mm_struct *start_mm; - unsigned char *swap_map; + volatile unsigned char *swap_map; /* swap_map is accessed without + * locking. Mark it as volatile + * to prevent compiler doing + * something odd. + */ unsigned char swcount; struct page *page; swp_entry_t entry; @@ -1359,7 +1364,15 @@ int try_to_unuse(unsigned int type, bool frontswap, * reused since sys_swapoff() already disabled * allocation from here, or alloc_page() failed. */ - if (!*swap_map) + swcount = *swap_map; + /* + * We don't hold lock here, so the swap entry could be + * SWAP_MAP_BAD (when the cluster is discarding). + * Instead of fail out, We can just skip the swap + * entry because swapoff will wait for discarding + * finish anyway. + */ + if (!swcount || swcount == SWAP_MAP_BAD) continue; retval = -ENOMEM; break; @@ -2543,6 +2556,16 @@ static int __swap_duplicate(swp_entry_t entry, unsigned char usage) goto unlock_out; count = p->swap_map[offset]; + + /* + * swapin_readahead() doesn't check if a swap entry is valid, so the + * swap entry could be SWAP_MAP_BAD. Check here with lock held. + */ + if (unlikely(swap_count(count) == SWAP_MAP_BAD)) { + err = -ENOENT; + goto unlock_out; + } + has_cache = count & SWAP_HAS_CACHE; count &= ~SWAP_HAS_CACHE; err = 0; -- cgit v1.2.2 From ebc2a1a69111eadfeda8487e577f1a5d42ef0dae Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Wed, 11 Sep 2013 14:20:32 -0700 Subject: swap: make cluster allocation per-cpu swap cluster allocation is to get better request merge to improve performance. But the cluster is shared globally, if multiple tasks are doing swap, this will cause interleave disk access. While multiple tasks swap is quite common, for example, each numa node has a kswapd thread doing swap and multiple threads/processes doing direct page reclaim. ioscheduler can't help too much here, because tasks don't send swapout IO down to block layer in the meantime. Block layer does merge some IOs, but a lot not, depending on how many tasks are doing swapout concurrently. In practice, I've seen a lot of small size IO in swapout workloads. We makes the cluster allocation per-cpu here. The interleave disk access issue goes away. All tasks swapout to their own cluster, so swapout will become sequential, which can be easily merged to big size IO. If one CPU can't get its per-cpu cluster (for example, there is no free cluster anymore in the swap), it will fallback to scan swap_map. The CPU can still continue swap. We don't need recycle free swap entries of other CPUs. In my test (swap to a 2-disk raid0 partition), this improves around 10% swapout throughput, and request size is increased significantly. How does this impact swap readahead is uncertain though. On one side, page reclaim always isolates and swaps several adjancent pages, this will make page reclaim write the pages sequentially and benefit readahead. On the other side, several CPU write pages interleave means the pages don't live _sequentially_ but relatively _near_. In the per-cpu allocation case, if adjancent pages are written by different cpus, they will live relatively _far_. So how this impacts swap readahead depends on how many pages page reclaim isolates and swaps one time. If the number is big, this patch will benefit swap readahead. Of course, this is about sequential access pattern. The patch has no impact for random access pattern, because the new cluster allocation algorithm is just for SSD. Alternative solution is organizing swap layout to be per-mm instead of this per-cpu approach. In the per-mm layout, we allocate a disk range for each mm, so pages of one mm live in swap disk adjacently. per-mm layout has potential issues of lock contention if multiple reclaimers are swap pages from one mm. For a sequential workload, per-mm layout is better to implement swap readahead, because pages from the mm are adjacent in disk. But per-cpu layout isn't very bad in this workload, as page reclaim always isolates and swaps several pages one time, such pages will still live in disk sequentially and readahead can utilize this. For a random workload, per-mm layout isn't beneficial of request merge, because it's quite possible pages from different mm are swapout in the meantime and IO can't be merged in per-mm layout. while with per-cpu layout we can merge requests from any mm. Considering random workload is more popular in workloads with swap (and per-cpu approach isn't too bad for sequential workload too), I'm choosing per-cpu layout. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Shaohua Li Cc: Rik van Riel Cc: Minchan Kim Cc: Kyungmin Park Cc: Hugh Dickins Cc: Rafael Aquini Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/swapfile.c | 125 ++++++++++++++++++++++++++++++++++++++++++---------------- 1 file changed, 91 insertions(+), 34 deletions(-) (limited to 'mm/swapfile.c') diff --git a/mm/swapfile.c b/mm/swapfile.c index 98e52e373bd8..3963fc24fcc1 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -392,13 +392,78 @@ static void dec_cluster_info_page(struct swap_info_struct *p, * It's possible scan_swap_map() uses a free cluster in the middle of free * cluster list. Avoiding such abuse to avoid list corruption. */ -static inline bool scan_swap_map_recheck_cluster(struct swap_info_struct *si, +static bool +scan_swap_map_ssd_cluster_conflict(struct swap_info_struct *si, unsigned long offset) { + struct percpu_cluster *percpu_cluster; + bool conflict; + offset /= SWAPFILE_CLUSTER; - return !cluster_is_null(&si->free_cluster_head) && + conflict = !cluster_is_null(&si->free_cluster_head) && offset != cluster_next(&si->free_cluster_head) && cluster_is_free(&si->cluster_info[offset]); + + if (!conflict) + return false; + + percpu_cluster = this_cpu_ptr(si->percpu_cluster); + cluster_set_null(&percpu_cluster->index); + return true; +} + +/* + * Try to get a swap entry from current cpu's swap entry pool (a cluster). This + * might involve allocating a new cluster for current CPU too. + */ +static void scan_swap_map_try_ssd_cluster(struct swap_info_struct *si, + unsigned long *offset, unsigned long *scan_base) +{ + struct percpu_cluster *cluster; + bool found_free; + unsigned long tmp; + +new_cluster: + cluster = this_cpu_ptr(si->percpu_cluster); + if (cluster_is_null(&cluster->index)) { + if (!cluster_is_null(&si->free_cluster_head)) { + cluster->index = si->free_cluster_head; + cluster->next = cluster_next(&cluster->index) * + SWAPFILE_CLUSTER; + } else if (!cluster_is_null(&si->discard_cluster_head)) { + /* + * we don't have free cluster but have some clusters in + * discarding, do discard now and reclaim them + */ + swap_do_scheduled_discard(si); + *scan_base = *offset = si->cluster_next; + goto new_cluster; + } else + return; + } + + found_free = false; + + /* + * Other CPUs can use our cluster if they can't find a free cluster, + * check if there is still free entry in the cluster + */ + tmp = cluster->next; + while (tmp < si->max && tmp < (cluster_next(&cluster->index) + 1) * + SWAPFILE_CLUSTER) { + if (!si->swap_map[tmp]) { + found_free = true; + break; + } + tmp++; + } + if (!found_free) { + cluster_set_null(&cluster->index); + goto new_cluster; + } + cluster->next = tmp + 1; + *offset = tmp; + *scan_base = tmp; } static unsigned long scan_swap_map(struct swap_info_struct *si, @@ -423,41 +488,17 @@ static unsigned long scan_swap_map(struct swap_info_struct *si, si->flags += SWP_SCANNING; scan_base = offset = si->cluster_next; + /* SSD algorithm */ + if (si->cluster_info) { + scan_swap_map_try_ssd_cluster(si, &offset, &scan_base); + goto checks; + } + if (unlikely(!si->cluster_nr--)) { if (si->pages - si->inuse_pages < SWAPFILE_CLUSTER) { si->cluster_nr = SWAPFILE_CLUSTER - 1; goto checks; } -check_cluster: - if (!cluster_is_null(&si->free_cluster_head)) { - offset = cluster_next(&si->free_cluster_head) * - SWAPFILE_CLUSTER; - last_in_cluster = offset + SWAPFILE_CLUSTER - 1; - si->cluster_next = offset; - si->cluster_nr = SWAPFILE_CLUSTER - 1; - goto checks; - } else if (si->cluster_info) { - /* - * we don't have free cluster but have some clusters in - * discarding, do discard now and reclaim them - */ - if (!cluster_is_null(&si->discard_cluster_head)) { - si->cluster_nr = 0; - swap_do_scheduled_discard(si); - scan_base = offset = si->cluster_next; - if (!si->cluster_nr) - goto check_cluster; - si->cluster_nr--; - goto checks; - } - - /* - * Checking free cluster is fast enough, we can do the - * check every time - */ - si->cluster_nr = 0; - goto checks; - } spin_unlock(&si->lock); @@ -516,8 +557,10 @@ check_cluster: } checks: - if (scan_swap_map_recheck_cluster(si, offset)) - goto check_cluster; + if (si->cluster_info) { + while (scan_swap_map_ssd_cluster_conflict(si, offset)) + scan_swap_map_try_ssd_cluster(si, &offset, &scan_base); + } if (!(si->flags & SWP_WRITEOK)) goto no_page; if (!si->highest_bit) @@ -1884,6 +1927,8 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) spin_unlock(&swap_lock); frontswap_invalidate_area(type); mutex_unlock(&swapon_mutex); + free_percpu(p->percpu_cluster); + p->percpu_cluster = NULL; vfree(swap_map); vfree(cluster_info); vfree(frontswap_map); @@ -2403,6 +2448,16 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) error = -ENOMEM; goto bad_swap; } + p->percpu_cluster = alloc_percpu(struct percpu_cluster); + if (!p->percpu_cluster) { + error = -ENOMEM; + goto bad_swap; + } + for_each_possible_cpu(i) { + struct percpu_cluster *cluster; + cluster = per_cpu_ptr(p->percpu_cluster, i); + cluster_set_null(&cluster->index); + } } error = swap_cgroup_swapon(p->type, maxpages); @@ -2475,6 +2530,8 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) error = 0; goto out; bad_swap: + free_percpu(p->percpu_cluster); + p->percpu_cluster = NULL; if (inode && S_ISBLK(inode->i_mode) && p->bdev) { set_blocksize(p->bdev, p->old_block_size); blkdev_put(p->bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL); -- cgit v1.2.2