November 2017 - Linux-stable-mirror

[Linux-stable-mirror] [patch 127/131] mm/page_ext.c: check if page_ext is not prepared

by akpm＠linux-foundation.org

From: Jaewon Kim <jaewon31.kim(a)samsung.com> Subject: mm/page_ext.c: check if page_ext is not prepared online_page_ext() and page_ext_init() allocate page_ext for each section, but they do not allocate if the first PFN is !pfn_present(pfn) or !pfn_valid(pfn). Then section->page_ext remains as NULL. lookup_page_ext checks NULL only if CONFIG_DEBUG_VM is enabled. For a valid PFN, __set_page_owner will try to get page_ext through lookup_page_ext. Without CONFIG_DEBUG_VM lookup_page_ext will misuse NULL pointer as value 0. This incurrs invalid address access. This is the panic example when PFN 0x100000 is not valid but PFN 0x13FC00 is being used for page_ext. section->page_ext is NULL, get_entry returned invalid page_ext address as 0x1DFA000 for a PFN 0x13FC00. To avoid this panic, CONFIG_DEBUG_VM should be removed so that page_ext will be checked at all times. <1>[ 11.618085] Unable to handle kernel paging request at virtual address 01dfa014 <1>[ 11.618140] pgd = ffffffc0c6dc9000 <1>[ 11.618174] [01dfa014] *pgd=0000000000000000, *pud=0000000000000000 <4>[ 11.618240] ------------[ cut here ]------------ <2>[ 11.618278] Kernel BUG at ffffff80082371e0 [verbose debug info unavailable] <0>[ 11.618338] Internal error: Oops: 96000045 [#1] PREEMPT SMP <4>[ 11.618381] Modules linked in: <4>[ 11.618524] task: ffffffc0c6ec9180 task.stack: ffffffc0c6f40000 <4>[ 11.618569] PC is at __set_page_owner+0x48/0x78 <4>[ 11.618607] LR is at __set_page_owner+0x44/0x78 <4>[ 11.626025] [<ffffff80082371e0>] __set_page_owner+0x48/0x78 <4>[ 11.626071] [<ffffff80081df9f0>] get_page_from_freelist+0x880/0x8e8 <4>[ 11.626118] [<ffffff80081e00a4>] __alloc_pages_nodemask+0x14c/0xc48 <4>[ 11.626165] [<ffffff80081e610c>] __do_page_cache_readahead+0xdc/0x264 <4>[ 11.626214] [<ffffff80081d8824>] filemap_fault+0x2ac/0x550 <4>[ 11.626259] [<ffffff80082e5cf8>] ext4_filemap_fault+0x3c/0x58 <4>[ 11.626305] [<ffffff800820a2f8>] __do_fault+0x80/0x120 <4>[ 11.626347] [<ffffff800820eb4c>] handle_mm_fault+0x704/0xbb0 <4>[ 11.626393] [<ffffff800809ba70>] do_page_fault+0x2e8/0x394 <4>[ 11.626437] [<ffffff8008080be4>] do_mem_abort+0x88/0x124 Pre-4.7 kernels also need f86e427197 ("mm: check the return value of lookup_page_ext for all call sites"). Link: http://lkml.kernel.org/r/20171107094131.14621-1-jaewon31.kim@samsung.com Fixes: eefa864b701d ("mm/page_ext: resurrect struct page extending code for debugging") Signed-off-by: Jaewon Kim <jaewon31.kim(a)samsung.com> Acked-by: Michal Hocko <mhocko(a)suse.com> Cc: Vlastimil Babka <vbabka(a)suse.cz> Cc: Minchan Kim <minchan(a)kernel.org> Cc: Joonsoo Kim <js1304(a)gmail.com> Cc: <stable(a)vger.kernel.org> [depends on f86e427197, see above] Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/page_ext.c | 4 ---- 1 file changed, 4 deletions(-) diff -puN mm/page_ext.c~mm-page_ext-check-if-page_ext-is-not-prepared mm/page_ext.c --- a/mm/page_ext.c~mm-page_ext-check-if-page_ext-is-not-prepared +++ a/mm/page_ext.c @@ -125,7 +125,6 @@ struct page_ext *lookup_page_ext(struct struct page_ext *base; base = NODE_DATA(page_to_nid(page))->node_page_ext; -#if defined(CONFIG_DEBUG_VM) /* * The sanity checks the page allocator does upon freeing a * page can reach here before the page_ext arrays are @@ -134,7 +133,6 @@ struct page_ext *lookup_page_ext(struct */ if (unlikely(!base)) return NULL; -#endif index = pfn - round_down(node_start_pfn(page_to_nid(page)), MAX_ORDER_NR_PAGES); return get_entry(base, index); @@ -199,7 +197,6 @@ struct page_ext *lookup_page_ext(struct { unsigned long pfn = page_to_pfn(page); struct mem_section *section = __pfn_to_section(pfn); -#if defined(CONFIG_DEBUG_VM) /* * The sanity checks the page allocator does upon freeing a * page can reach here before the page_ext arrays are @@ -208,7 +205,6 @@ struct page_ext *lookup_page_ext(struct */ if (!section->page_ext) return NULL; -#endif return get_entry(section->page_ext, pfn); } _

7 years, 1 month

1
0
0 0

[Linux-stable-mirror] [patch 120/131] mm/page_alloc.c: broken deferred calculation

by akpm＠linux-foundation.org

From: Pavel Tatashin <pasha.tatashin(a)oracle.com> Subject: mm/page_alloc.c: broken deferred calculation In reset_deferred_meminit() we determine number of pages that must not be deferred. We initialize pages for at least 2G of memory, but also pages for reserved memory in this node. The reserved memory is determined in this function: memblock_reserved_memory_within(), which operates over physical addresses, and returns size in bytes. However, reset_deferred_meminit() assumes that that this function operates with pfns, and returns page count. The result is that in the best case machine boots slower than expected due to initializing more pages than needed in single thread, and in the worst case panics because fewer than needed pages are initialized early. Link: http://lkml.kernel.org/r/20171021011707.15191-1-pasha.tatashin@oracle.com Fixes: 864b9a393dcb ("mm: consider memblock reservations for deferred memory initialization sizing") Signed-off-by: Pavel Tatashin <pasha.tatashin(a)oracle.com> Acked-by: Michal Hocko <mhocko(a)suse.com> Cc: Mel Gorman <mgorman(a)techsingularity.net> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- include/linux/mmzone.h | 3 ++- mm/page_alloc.c | 27 ++++++++++++++++++--------- 2 files changed, 20 insertions(+), 10 deletions(-) diff -puN include/linux/mmzone.h~mm-broken-deferred-calculation include/linux/mmzone.h --- a/include/linux/mmzone.h~mm-broken-deferred-calculation +++ a/include/linux/mmzone.h @@ -700,7 +700,8 @@ typedef struct pglist_data { * is the first PFN that needs to be initialised. */ unsigned long first_deferred_pfn; - unsigned long static_init_size; + /* Number of non-deferred pages */ + unsigned long static_init_pgcnt; #endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */ #ifdef CONFIG_TRANSPARENT_HUGEPAGE diff -puN mm/page_alloc.c~mm-broken-deferred-calculation mm/page_alloc.c --- a/mm/page_alloc.c~mm-broken-deferred-calculation +++ a/mm/page_alloc.c @@ -291,28 +291,37 @@ EXPORT_SYMBOL(nr_online_nodes); int page_group_by_mobility_disabled __read_mostly; #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT + +/* + * Determine how many pages need to be initialized durig early boot + * (non-deferred initialization). + * The value of first_deferred_pfn will be set later, once non-deferred pages + * are initialized, but for now set it ULONG_MAX. + */ static inline void reset_deferred_meminit(pg_data_t *pgdat) { - unsigned long max_initialise; - unsigned long reserved_lowmem; + phys_addr_t start_addr, end_addr; + unsigned long max_pgcnt; + unsigned long reserved; /* * Initialise at least 2G of a node but also take into account that * two large system hashes that can take up 1GB for 0.25TB/node. */ - max_initialise = max(2UL << (30 - PAGE_SHIFT), - (pgdat->node_spanned_pages >> 8)); + max_pgcnt = max(2UL << (30 - PAGE_SHIFT), + (pgdat->node_spanned_pages >> 8)); /* * Compensate the all the memblock reservations (e.g. crash kernel) * from the initial estimation to make sure we will initialize enough * memory to boot. */ - reserved_lowmem = memblock_reserved_memory_within(pgdat->node_start_pfn, - pgdat->node_start_pfn + max_initialise); - max_initialise += reserved_lowmem; + start_addr = PFN_PHYS(pgdat->node_start_pfn); + end_addr = PFN_PHYS(pgdat->node_start_pfn + max_pgcnt); + reserved = memblock_reserved_memory_within(start_addr, end_addr); + max_pgcnt += PHYS_PFN(reserved); - pgdat->static_init_size = min(max_initialise, pgdat->node_spanned_pages); + pgdat->static_init_pgcnt = min(max_pgcnt, pgdat->node_spanned_pages); pgdat->first_deferred_pfn = ULONG_MAX; } @@ -339,7 +348,7 @@ static inline bool update_defer_init(pg_ if (zone_end < pgdat_end_pfn(pgdat)) return true; (*nr_initialised)++; - if ((*nr_initialised > pgdat->static_init_size) && + if ((*nr_initialised > pgdat->static_init_pgcnt) && (pfn & (PAGES_PER_SECTION - 1)) == 0) { pgdat->first_deferred_pfn = pfn; return false; _

7 years, 1 month

1
0
0 0

[Linux-stable-mirror] [patch 033/131] mm, swap: fix false error message in __swp_swapcount()

by akpm＠linux-foundation.org

From: Huang Ying <huang.ying.caritas(a)gmail.com> Subject: mm, swap: fix false error message in __swp_swapcount() When a page fault occurs for a swap entry, the physical swap readahead (not the VMA base swap readahead) may readahead several swap entries after the fault swap entry. The readahead algorithm calculates some of the swap entries to readahead via increasing the offset of the fault swap entry without checking whether they are beyond the end of the swap device and it relys on the __swp_swapcount() and swapcache_prepare() to check it. Although __swp_swapcount() checks for the swap entry passed in, it will complain with the error message as follow for the expected invalid swap entry. This may make the end users confused. swap_info_get: Bad swap offset entry 0200f8a7 To fix the false error message, the swap entry checking is added in swapin_readahead() to avoid to pass the out-of-bound swap entries and the swap entry reserved for the swap header to __swp_swapcount() and swapcache_prepare(). Link: http://lkml.kernel.org/r/20171102054225.22897-1-ying.huang@intel.com Fixes: e8c26ab60598 ("mm/swap: skip readahead for unreferenced swap slots") Signed-off-by: "Huang, Ying" <ying.huang(a)intel.com> Reported-by: Christian Kujau <lists(a)nerdbynature.de> Acked-by: Minchan Kim <minchan(a)kernel.org> Suggested-by: Minchan Kim <minchan(a)kernel.org> Cc: Tim Chen <tim.c.chen(a)linux.intel.com> Cc: Michal Hocko <mhocko(a)suse.com> Cc: Hugh Dickins <hughd(a)google.com> Cc: <stable(a)vger.kernel.org> [4.11+] Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/swap_state.c | 3 +++ 1 file changed, 3 insertions(+) diff -puN mm/swap_state.c~mm-swap-fix-false-error-message-in-__swp_swapcount mm/swap_state.c --- a/mm/swap_state.c~mm-swap-fix-false-error-message-in-__swp_swapcount +++ a/mm/swap_state.c @@ -559,6 +559,7 @@ struct page *swapin_readahead(swp_entry_ unsigned long offset = entry_offset; unsigned long start_offset, end_offset; unsigned long mask; + struct swap_info_struct *si = swp_swap_info(entry); struct blk_plug plug; bool do_poll = true, page_allocated; @@ -572,6 +573,8 @@ struct page *swapin_readahead(swp_entry_ end_offset = offset | mask; if (!start_offset) /* First page is swap header. */ start_offset++; + if (end_offset >= si->max) + end_offset = si->max - 1; blk_start_plug(&plug); for (offset = start_offset; offset <= end_offset ; offset++) { _

7 years, 1 month

1
0
0 0

[Linux-stable-mirror] [patch 008/131] ocfs2: should wait dio before inode lock in ocfs2_setattr()

by akpm＠linux-foundation.org

From: alex chen <alex.chen(a)huawei.com> Subject: ocfs2: should wait dio before inode lock in ocfs2_setattr() we should wait dio requests to finish before inode lock in ocfs2_setattr(), otherwise the following deadlock will happen: process 1 process 2 process 3 truncate file 'A' end_io of writing file 'A' receiving the bast messages ocfs2_setattr ocfs2_inode_lock_tracker ocfs2_inode_lock_full inode_dio_wait __inode_dio_wait -->waiting for all dio requests finish dlm_proxy_ast_handler dlm_do_local_bast ocfs2_blocking_ast ocfs2_generic_handle_bast set OCFS2_LOCK_BLOCKED flag dio_end_io dio_bio_end_aio dio_complete ocfs2_dio_end_io ocfs2_dio_end_io_write ocfs2_inode_lock __ocfs2_cluster_lock ocfs2_wait_for_mask -->waiting for OCFS2_LOCK_BLOCKED flag to be cleared, that is waiting for 'process 1' unlocking the inode lock inode_dio_end -->here dec the i_dio_count, but will never be called, so a deadlock happened. Link: http://lkml.kernel.org/r/59F81636.70508@huawei.com Signed-off-by: Alex Chen <alex.chen(a)huawei.com> Reviewed-by: Jun Piao <piaojun(a)huawei.com> Reviewed-by: Joseph Qi <jiangqi903(a)gmail.com> Acked-by: Changwei Ge <ge.changwei(a)h3c.com> Cc: Mark Fasheh <mfasheh(a)versity.com> Cc: Joel Becker <jlbec(a)evilplan.org> Cc: Junxiao Bi <junxiao.bi(a)oracle.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- fs/ocfs2/file.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff -puN fs/ocfs2/file.c~ocfs2-should-wait-dio-before-inode-lock-in-ocfs2_setattr fs/ocfs2/file.c --- a/fs/ocfs2/file.c~ocfs2-should-wait-dio-before-inode-lock-in-ocfs2_setattr +++ a/fs/ocfs2/file.c @@ -1161,6 +1161,13 @@ int ocfs2_setattr(struct dentry *dentry, } size_change = S_ISREG(inode->i_mode) && attr->ia_valid & ATTR_SIZE; if (size_change) { + /* + * Here we should wait dio to finish before inode lock + * to avoid a deadlock between ocfs2_setattr() and + * ocfs2_dio_end_io_write() + */ + inode_dio_wait(inode); + status = ocfs2_rw_lock(inode, 1); if (status < 0) { mlog_errno(status); @@ -1200,8 +1207,6 @@ int ocfs2_setattr(struct dentry *dentry, if (status) goto bail_unlock; - inode_dio_wait(inode); - if (i_size_read(inode) >= attr->ia_size) { if (ocfs2_should_order_data(inode)) { status = ocfs2_begin_ordered_truncate(inode, _

7 years, 1 month

1
0
0 0

[Linux-stable-mirror] [patch 006/131] ocfs2: fix cluster hang after a node dies

by akpm＠linux-foundation.org

From: Changwei Ge <ge.changwei(a)h3c.com> Subject: ocfs2: fix cluster hang after a node dies When a node dies, other live nodes have to choose a new master for an existed lock resource mastered by the dead node. As for ocfs2/dlm implementation, this is done by function - dlm_move_lockres_to_recovery_list which marks those lock rsources as DLM_LOCK_RES_RECOVERING and manages them via a list from which DLM changes lock resource's master later. So without invoking dlm_move_lockres_to_recovery_list, no master will be choosed after dlm recovery accomplishment since no lock resource can be found through ::resource list. What's worse is that if DLM_LOCK_RES_RECOVERING is not marked for lock resources mastered a dead node, it will break up synchronization among nodes. So invoke dlm_move_lockres_to_recovery_list again. Fixs: 'commit ee8f7fcbe638 ("ocfs2/dlm: continue to purge recovery lockres when recovery master goes down")' Link: http://lkml.kernel.org/r/63ADC13FD55D6546B7DECE290D39E373CED6E0F9@H3CMLB14-… Signed-off-by: Changwei Ge <ge.changwei(a)h3c.com> Reported-by: Vitaly Mayatskih <v.mayatskih(a)gmail.com> Tested-by: Vitaly Mayatskikh <v.mayatskih(a)gmail.com> Cc: Mark Fasheh <mfasheh(a)versity.com> Cc: Joel Becker <jlbec(a)evilplan.org> Cc: Junxiao Bi <junxiao.bi(a)oracle.com> Cc: Joseph Qi <jiangqi903(a)gmail.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- fs/ocfs2/dlm/dlmrecovery.c | 1 + 1 file changed, 1 insertion(+) diff -puN fs/ocfs2/dlm/dlmrecovery.c~ocfs2-fix-cluster-hang-after-a-node-dies fs/ocfs2/dlm/dlmrecovery.c --- a/fs/ocfs2/dlm/dlmrecovery.c~ocfs2-fix-cluster-hang-after-a-node-dies +++ a/fs/ocfs2/dlm/dlmrecovery.c @@ -2419,6 +2419,7 @@ static void dlm_do_local_recovery_cleanu dlm_lockres_put(res); continue; } + dlm_move_lockres_to_recovery_list(dlm, res); } else if (res->owner == dlm->node_num) { dlm_free_dead_locks(dlm, res, dead_node); __dlm_lockres_calc_usage(dlm, res); _

7 years, 1 month

1
0
0 0

[Linux-stable-mirror] [stable] sctp: do not peel off an assoc from one netns to another one

by Ben Hutchings

Please can you queue up the following for stable: df80cd9b28b9 sctp: do not peel off an assoc from one netns to another one Ben. -- Ben Hutchings Software Developer, Codethink Ltd.

7 years, 1 month

2
1
0 0

[Linux-stable-mirror] [folded-merged] mm-swap-skip-swapcache-for-swapin-of-synchronous-device-fix.patch removed from -mm tree

by akpm＠linux-foundation.org

The patch titled Subject: mm, swap: fix false error message in __swp_swapcount() has been removed from the -mm tree. Its filename was mm-swap-skip-swapcache-for-swapin-of-synchronous-device-fix.patch This patch was dropped because it was folded into mm-swap-skip-swapcache-for-swapin-of-synchronous-device.patch ------------------------------------------------------ From: Huang Ying <huang.ying.caritas(a)gmail.com> Subject: mm, swap: fix false error message in __swp_swapcount() When a page fault occurs for a swap entry, the physical swap readahead (not the VMA base swap readahead) may readahead several swap entries after the fault swap entry. The readahead algorithm calculates some of the swap entries to readahead via increasing the offset of the fault swap entry without checking whether they are beyond the end of the swap device and it relys on the __swp_swapcount() and swapcache_prepare() to check it. Although __swp_swapcount() checks for the swap entry passed in, it will complain with the error message as follow for the expected invalid swap entry. This may make the end users confused. swap_info_get: Bad swap offset entry 0200f8a7 To fix the false error message, the swap entry checking is added in swapin_readahead() to avoid to pass the out-of-bound swap entries and the swap entry reserved for the swap header to __swp_swapcount() and swapcache_prepare(). Link: http://lkml.kernel.org/r/20171102054225.22897-1-ying.huang@intel.com Fixes: e8c26ab60598 ("mm/swap: skip readahead for unreferenced swap slots") Signed-off-by: "Huang, Ying" <ying.huang(a)intel.com> Reported-by: Christian Kujau <lists(a)nerdbynature.de> Acked-by: Minchan Kim <minchan(a)kernel.org> Suggested-by: Minchan Kim <minchan(a)kernel.org> Cc: Tim Chen <tim.c.chen(a)linux.intel.com> Cc: Michal Hocko <mhocko(a)suse.com> Cc: Hugh Dickins <hughd(a)google.com> Cc: <stable(a)vger.kernel.org> [4.11+] Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/swap_state.c | 3 +++ 1 file changed, 3 insertions(+) diff -puN mm/swap_state.c~mm-swap-skip-swapcache-for-swapin-of-synchronous-device-fix mm/swap_state.c --- a/mm/swap_state.c~mm-swap-skip-swapcache-for-swapin-of-synchronous-device-fix +++ a/mm/swap_state.c @@ -559,6 +559,7 @@ struct page *swapin_readahead(swp_entry_ unsigned long offset = entry_offset; unsigned long start_offset, end_offset; unsigned long mask; + struct swap_info_struct *si = swp_swap_info(entry); struct blk_plug plug; bool do_poll = true, page_allocated; @@ -572,6 +573,8 @@ struct page *swapin_readahead(swp_entry_ end_offset = offset | mask; if (!start_offset) /* First page is swap header. */ start_offset++; + if (end_offset >= si->max) + end_offset = si->max - 1; blk_start_plug(&plug); for (offset = start_offset; offset <= end_offset ; offset++) { _ Patches currently in -mm which might be from huang.ying.caritas(a)gmail.com are mm-swap-skip-swapcache-for-swapin-of-synchronous-device.patch

7 years, 1 month

1
0
0 0

Re: [Linux-stable-mirror] [PATCH] ALSA: usb-audio: Fix out-of-bound error

by Takashi Iwai

On Wed, 15 Nov 2017 09:57:56 +0100, Jaejoong Kim wrote: > > diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c > index e630813..5a83c2c 100644 > --- a/sound/usb/mixer.c > +++ b/sound/usb/mixer.c > @@ -204,7 +204,8 @@ static int snd_usb_copy_string_desc(struct mixer_build > *state, > int index, char *buf, int maxlen) > { > int len = usb_string(state->chip->dev, index, buf, maxlen - 1); > - buf[len] = 0; > + if (len > 0) > + buf[len] = 0; > return len; I'd rather put an explicit error bail-out, i.e. diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c index 91bc8f18791e..296a63a9d09c 100644 --- a/sound/usb/mixer.c +++ b/sound/usb/mixer.c @@ -204,6 +204,10 @@ static int snd_usb_copy_string_desc(struct mixer_build *state, int index, char *buf, int maxlen) { int len = usb_string(state->chip->dev, index, buf, maxlen - 1); + + if (len < 0) + return len; + buf[len] = 0; return len; } thanks, Takashi

7 years, 1 month

2
1
0 0

[Linux-stable-mirror] [PATCH] dm bufio: fix integer overflow when limiting maximum cache size

by Eric Biggers

The default max_cache_size_bytes for dm-bufio is meant to be the lesser of 25% of the size of the vmalloc area and 2% of the size of lowmem. However, on 32-bit systems the intermediate result in the expression (VMALLOC_END - VMALLOC_START) * DM_BUFIO_VMALLOC_PERCENT / 100 overflows, causing the wrong result to be computed. For example, on a 32-bit system where the vmalloc area is 520093696 bytes, the result is 1174405 rather than the expected 130023424, which makes the maximum cache size much too small (far less than 2% of lowmem). This causes severe performance problems for dm-verity users on affected systems. Fix this by using mult_frac() to correctly multiply by a percentage. Do this for all places in dm-bufio that multiply by a percentage. Also replace (VMALLOC_END - VMALLOC_START) with VMALLOC_TOTAL, which contrary to the comment is now defined in include/linux/vmalloc.h. Fixes: 95d402f057f2 ("dm: add bufio") Cc: <stable(a)vger.kernel.org> # v3.2+ Signed-off-by: Eric Biggers <ebiggers(a)google.com> --- drivers/md/dm-bufio.c | 15 ++++++--------- 1 file changed, 6 insertions(+), 9 deletions(-) diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c index 33bb074d6941..b8ac591aaaa7 100644 --- a/drivers/md/dm-bufio.c +++ b/drivers/md/dm-bufio.c @@ -974,7 +974,8 @@ static void __get_memory_limit(struct dm_bufio_client *c, buffers = c->minimum_buffers; *limit_buffers = buffers; - *threshold_buffers = buffers * DM_BUFIO_WRITEBACK_PERCENT / 100; + *threshold_buffers = mult_frac(buffers, + DM_BUFIO_WRITEBACK_PERCENT, 100); } /* @@ -1910,19 +1911,15 @@ static int __init dm_bufio_init(void) memset(&dm_bufio_caches, 0, sizeof dm_bufio_caches); memset(&dm_bufio_cache_names, 0, sizeof dm_bufio_cache_names); - mem = (__u64)((totalram_pages - totalhigh_pages) * - DM_BUFIO_MEMORY_PERCENT / 100) << PAGE_SHIFT; + mem = (__u64)mult_frac(totalram_pages - totalhigh_pages, + DM_BUFIO_MEMORY_PERCENT, 100) << PAGE_SHIFT; if (mem > ULONG_MAX) mem = ULONG_MAX; #ifdef CONFIG_MMU - /* - * Get the size of vmalloc space the same way as VMALLOC_TOTAL - * in fs/proc/internal.h - */ - if (mem > (VMALLOC_END - VMALLOC_START) * DM_BUFIO_VMALLOC_PERCENT / 100) - mem = (VMALLOC_END - VMALLOC_START) * DM_BUFIO_VMALLOC_PERCENT / 100; + if (mem > mult_frac(VMALLOC_TOTAL, DM_BUFIO_VMALLOC_PERCENT, 100)) + mem = mult_frac(VMALLOC_TOTAL, DM_BUFIO_VMALLOC_PERCENT, 100); #endif dm_bufio_default_cache_size = mem; -- 2.15.0.448.gf294e3d99a-goog

7 years, 1 month

1
0
0 0

[Linux-stable-mirror] [PATCH 4.9.y] netfilter: nat: Revert "netfilter: nat: convert nat bysrc hash to rhashtable"

by Florian Westphal

commit e1bf1687740ce1a3598a1c5e452b852ff2190682 upstream. This reverts commit 870190a9ec9075205c0fa795a09fa931694a3ff1. It was not a good idea. The custom hash table was a much better fit for this purpose. A fast lookup is not essential, in fact for most cases there is no lookup at all because original tuple is not taken and can be used as-is. What needs to be fast is insertion and deletion. rhlist removal however requires a rhlist walk. We can have thousands of entries in such a list if source port/addresses are reused for multiple flows, if this happens removal requests are so expensive that deletions of a few thousand flows can take several seconds(!). The advantages that we got from rhashtable are: 1) table auto-sizing 2) multiple locks 1) would be nice to have, but it is not essential as we have at most one lookup per new flow, so even a million flows in the bysource table are not a problem compared to current deletion cost. 2) is easy to add to custom hash table. I tried to add hlist_node to rhlist to speed up rhltable_remove but this isn't doable without changing semantics. rhltable_remove_fast will check that the to-be-deleted object is part of the table and that requires a list walk that we want to avoid. Furthermore, using hlist_node increases size of struct rhlist_head, which in turn increases nf_conn size. Link: https://bugzilla.kernel.org/show_bug.cgi?id=196821 Reported-by: Ivan Babrou <ibobrik(a)gmail.com> Signed-off-by: Florian Westphal <fw(a)strlen.de> Signed-off-by: Pablo Neira Ayuso <pablo(a)netfilter.org> --- Hi Greg, this is a 4.9.y backport of the same revert that already went into 4.13.y; please consider applying this. I briefly tested this in kvm, at very least it doesn't break nat redirect in obvious ways... include/net/netfilter/nf_conntrack.h | 3 +- include/net/netfilter/nf_nat.h | 1 - net/netfilter/nf_nat_core.c | 133 +++++++++++++++-------------------- 3 files changed, 57 insertions(+), 80 deletions(-) diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index d9d52c020a70..9ae819e27940 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -17,7 +17,6 @@ #include <linux/bitops.h> #include <linux/compiler.h> #include <linux/atomic.h> -#include <linux/rhashtable.h> #include <linux/netfilter/nf_conntrack_tcp.h> #include <linux/netfilter/nf_conntrack_dccp.h> @@ -101,7 +100,7 @@ struct nf_conn { possible_net_t ct_net; #if IS_ENABLED(CONFIG_NF_NAT) - struct rhlist_head nat_bysource; + struct hlist_node nat_bysource; #endif /* all members below initialized via memset */ u8 __nfct_init_offset[0]; diff --git a/include/net/netfilter/nf_nat.h b/include/net/netfilter/nf_nat.h index c327a431a6f3..02515f7ed4cc 100644 --- a/include/net/netfilter/nf_nat.h +++ b/include/net/netfilter/nf_nat.h @@ -1,6 +1,5 @@ #ifndef _NF_NAT_H #define _NF_NAT_H -#include <linux/rhashtable.h> #include <linux/netfilter_ipv4.h> #include <linux/netfilter/nf_nat.h> #include <net/netfilter/nf_conntrack_tuple.h> diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index 2916f4815c9c..87d67e714dc4 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -30,19 +30,17 @@ #include <net/netfilter/nf_conntrack_zones.h> #include <linux/netfilter/nf_nat.h> +static DEFINE_SPINLOCK(nf_nat_lock); + static DEFINE_MUTEX(nf_nat_proto_mutex); static const struct nf_nat_l3proto __rcu *nf_nat_l3protos[NFPROTO_NUMPROTO] __read_mostly; static const struct nf_nat_l4proto __rcu **nf_nat_l4protos[NFPROTO_NUMPROTO] __read_mostly; -struct nf_nat_conn_key { - const struct net *net; - const struct nf_conntrack_tuple *tuple; - const struct nf_conntrack_zone *zone; -}; - -static struct rhltable nf_nat_bysource_table; +static struct hlist_head *nf_nat_bysource __read_mostly; +static unsigned int nf_nat_htable_size __read_mostly; +static unsigned int nf_nat_hash_rnd __read_mostly; inline const struct nf_nat_l3proto * __nf_nat_l3proto_find(u8 family) @@ -121,17 +119,19 @@ int nf_xfrm_me_harder(struct net *net, struct sk_buff *skb, unsigned int family) EXPORT_SYMBOL(nf_xfrm_me_harder); #endif /* CONFIG_XFRM */ -static u32 nf_nat_bysource_hash(const void *data, u32 len, u32 seed) +/* We keep an extra hash for each conntrack, for fast searching. */ +static inline unsigned int +hash_by_src(const struct net *n, const struct nf_conntrack_tuple *tuple) { - const struct nf_conntrack_tuple *t; - const struct nf_conn *ct = data; + unsigned int hash; + + get_random_once(&nf_nat_hash_rnd, sizeof(nf_nat_hash_rnd)); - t = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple; /* Original src, to ensure we map it consistently if poss. */ + hash = jhash2((u32 *)&tuple->src, sizeof(tuple->src) / sizeof(u32), + tuple->dst.protonum ^ nf_nat_hash_rnd ^ net_hash_mix(n)); - seed ^= net_hash_mix(nf_ct_net(ct)); - return jhash2((const u32 *)&t->src, sizeof(t->src) / sizeof(u32), - t->dst.protonum ^ seed); + return reciprocal_scale(hash, nf_nat_htable_size); } /* Is this tuple already taken? (not by us) */ @@ -187,28 +187,6 @@ same_src(const struct nf_conn *ct, t->src.u.all == tuple->src.u.all); } -static int nf_nat_bysource_cmp(struct rhashtable_compare_arg *arg, - const void *obj) -{ - const struct nf_nat_conn_key *key = arg->key; - const struct nf_conn *ct = obj; - - if (!same_src(ct, key->tuple) || - !net_eq(nf_ct_net(ct), key->net) || - !nf_ct_zone_equal(ct, key->zone, IP_CT_DIR_ORIGINAL)) - return 1; - - return 0; -} - -static struct rhashtable_params nf_nat_bysource_params = { - .head_offset = offsetof(struct nf_conn, nat_bysource), - .obj_hashfn = nf_nat_bysource_hash, - .obj_cmpfn = nf_nat_bysource_cmp, - .nelem_hint = 256, - .min_size = 1024, -}; - /* Only called for SRC manip */ static int find_appropriate_src(struct net *net, @@ -219,26 +197,22 @@ find_appropriate_src(struct net *net, struct nf_conntrack_tuple *result, const struct nf_nat_range *range) { + unsigned int h = hash_by_src(net, tuple); const struct nf_conn *ct; - struct nf_nat_conn_key key = { - .net = net, - .tuple = tuple, - .zone = zone - }; - struct rhlist_head *hl, *h; - - hl = rhltable_lookup(&nf_nat_bysource_table, &key, - nf_nat_bysource_params); - rhl_for_each_entry_rcu(ct, h, hl, nat_bysource) { - nf_ct_invert_tuplepr(result, - &ct->tuplehash[IP_CT_DIR_REPLY].tuple); - result->dst = tuple->dst; - - if (in_range(l3proto, l4proto, result, range)) - return 1; + hlist_for_each_entry_rcu(ct, &nf_nat_bysource[h], nat_bysource) { + if (same_src(ct, tuple) && + net_eq(net, nf_ct_net(ct)) && + nf_ct_zone_equal(ct, zone, IP_CT_DIR_ORIGINAL)) { + /* Copy source part from reply tuple. */ + nf_ct_invert_tuplepr(result, + &ct->tuplehash[IP_CT_DIR_REPLY].tuple); + result->dst = tuple->dst; + + if (in_range(l3proto, l4proto, result, range)) + return 1; + } } - return 0; } @@ -411,6 +385,7 @@ nf_nat_setup_info(struct nf_conn *ct, const struct nf_nat_range *range, enum nf_nat_manip_type maniptype) { + struct net *net = nf_ct_net(ct); struct nf_conntrack_tuple curr_tuple, new_tuple; struct nf_conn_nat *nat; @@ -452,19 +427,16 @@ nf_nat_setup_info(struct nf_conn *ct, } if (maniptype == NF_NAT_MANIP_SRC) { - struct nf_nat_conn_key key = { - .net = nf_ct_net(ct), - .tuple = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple, - .zone = nf_ct_zone(ct), - }; - int err; - - err = rhltable_insert_key(&nf_nat_bysource_table, - &key, - &ct->nat_bysource, - nf_nat_bysource_params); - if (err) - return NF_DROP; + unsigned int srchash; + + srchash = hash_by_src(net, + &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); + spin_lock_bh(&nf_nat_lock); + /* nf_conntrack_alter_reply might re-allocate extension aera */ + nat = nfct_nat(ct); + hlist_add_head_rcu(&ct->nat_bysource, + &nf_nat_bysource[srchash]); + spin_unlock_bh(&nf_nat_lock); } /* It's done. */ @@ -578,9 +550,10 @@ static int nf_nat_proto_clean(struct nf_conn *ct, void *data) * Else, when the conntrack is destoyed, nf_nat_cleanup_conntrack() * will delete entry from already-freed table. */ + spin_lock_bh(&nf_nat_lock); + hlist_del_rcu(&ct->nat_bysource); ct->status &= ~IPS_NAT_DONE_MASK; - rhltable_remove(&nf_nat_bysource_table, &ct->nat_bysource, - nf_nat_bysource_params); + spin_unlock_bh(&nf_nat_lock); /* don't delete conntrack. Although that would make things a lot * simpler, we'd end up flushing all conntracks on nat rmmod. @@ -710,8 +683,11 @@ static void nf_nat_cleanup_conntrack(struct nf_conn *ct) if (!nat) return; - rhltable_remove(&nf_nat_bysource_table, &ct->nat_bysource, - nf_nat_bysource_params); + NF_CT_ASSERT(ct->status & IPS_SRC_NAT_DONE); + + spin_lock_bh(&nf_nat_lock); + hlist_del_rcu(&ct->nat_bysource); + spin_unlock_bh(&nf_nat_lock); } static struct nf_ct_ext_type nat_extend __read_mostly = { @@ -846,13 +822,16 @@ static int __init nf_nat_init(void) { int ret; - ret = rhltable_init(&nf_nat_bysource_table, &nf_nat_bysource_params); - if (ret) - return ret; + /* Leave them the same for the moment. */ + nf_nat_htable_size = nf_conntrack_htable_size; + + nf_nat_bysource = nf_ct_alloc_hashtable(&nf_nat_htable_size, 0); + if (!nf_nat_bysource) + return -ENOMEM; ret = nf_ct_extend_register(&nat_extend); if (ret < 0) { - rhltable_destroy(&nf_nat_bysource_table); + nf_ct_free_hashtable(nf_nat_bysource, nf_nat_htable_size); printk(KERN_ERR "nf_nat_core: Unable to register extension\n"); return ret; } @@ -876,7 +855,7 @@ static int __init nf_nat_init(void) return 0; cleanup_extend: - rhltable_destroy(&nf_nat_bysource_table); + nf_ct_free_hashtable(nf_nat_bysource, nf_nat_htable_size); nf_ct_extend_unregister(&nat_extend); return ret; } @@ -896,8 +875,8 @@ static void __exit nf_nat_cleanup(void) for (i = 0; i < NFPROTO_NUMPROTO; i++) kfree(nf_nat_l4protos[i]); - - rhltable_destroy(&nf_nat_bysource_table); + synchronize_net(); + nf_ct_free_hashtable(nf_nat_bysource, nf_nat_htable_size); } MODULE_LICENSE("GPL"); -- 2.13.6

7 years, 1 month

6
13
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror November 2017