mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-11-25 04:20:53 +07:00
ac15ee691f
Executed command: fsstress -d /mnt -n 600 -p 850 crash> bt PID: 7947 TASK: ffff880160546a70 CPU: 0 COMMAND: "fsstress" #0 [ffff8800dfc07d00] machine_kexec at ffffffff81030db9 #1 [ffff8800dfc07d70] crash_kexec at ffffffff810a7952 #2 [ffff8800dfc07e40] oops_end at ffffffff814aa7c8 #3 [ffff8800dfc07e70] die_nmi at ffffffff814aa969 #4 [ffff8800dfc07ea0] do_nmi_callback at ffffffff8102b07b #5 [ffff8800dfc07f10] do_nmi at ffffffff814aa514 #6 [ffff8800dfc07f50] nmi at ffffffff814a9d60 [exception RIP: __lookup_tag+100] RIP: ffffffff812274b4 RSP: ffff88016056b998 RFLAGS: 00000287 RAX: 0000000000000000 RBX: 0000000000000002 RCX: 0000000000000006 RDX: 000000000000001d RSI: ffff88016056bb18 RDI: ffff8800c85366e0 RBP: ffff88016056b9c8 R8: ffff88016056b9e8 R9: 0000000000000000 R10: 000000000000000e R11: ffff8800c8536908 R12: 0000000000000010 R13: 0000000000000040 R14: ffffffffffffffc0 R15: ffff8800c85366e0 ORIG_RAX: ffffffffffffffff CS: 0010 SS: 0018 <NMI exception stack> #7 [ffff88016056b998] __lookup_tag at ffffffff812274b4 #8 [ffff88016056b9d0] radix_tree_gang_lookup_tag_slot at ffffffff81227605 #9 [ffff88016056ba20] find_get_pages_tag at ffffffff810fc110 #10 [ffff88016056ba80] pagevec_lookup_tag at ffffffff81105e85 #11 [ffff88016056baa0] write_cache_pages at ffffffff81104c47 #12 [ffff88016056bbd0] generic_writepages at ffffffff81105014 #13 [ffff88016056bbe0] do_writepages at ffffffff81105055 #14 [ffff88016056bbf0] __filemap_fdatawrite_range at ffffffff810fb2cb #15 [ffff88016056bc40] filemap_write_and_wait_range at ffffffff810fb32a #16 [ffff88016056bc70] generic_file_direct_write at ffffffff810fb3dc #17 [ffff88016056bce0] __generic_file_aio_write at ffffffff810fcee5 #18 [ffff88016056bda0] generic_file_aio_write at ffffffff810fd085 #19 [ffff88016056bdf0] do_sync_write at ffffffff8114f9ea #20 [ffff88016056bf00] vfs_write at ffffffff8114fcf8 #21 [ffff88016056bf30] sys_write at ffffffff81150691 #22 [ffff88016056bf80] system_call_fastpath at ffffffff8100c0b2 I think this root cause is the following: radix_tree_range_tag_if_tagged() always tags the root tag with settag if the root tag is set with iftag even if there are no iftag tags in the specified range (Of course, there are some iftag tags outside the specified range). =============================================================================== [[[Detailed description]]] (1) Why cannot radix_tree_gang_lookup_tag_slot() return forever? __lookup_tag(): - Return with 0. - Return with the index which is not bigger than the old one as the input parameter. Therefore the following "while" repeats forever because the above conditions cause "ret" not to be updated and the cur_index cannot be changed into the bigger one. (So, radix_tree_gang_lookup_tag_slot() cannot return forever.) radix_tree_gang_lookup_tag_slot(): 1178 while (ret < max_items) { 1179 unsigned int slots_found; 1180 unsigned long next_index; /* Index of next search */ 1181 1182 if (cur_index > max_index) 1183 break; 1184 slots_found = __lookup_tag(node, results + ret, 1185 cur_index, max_items - ret, &next_index, tag); 1186 ret += slots_found; // cannot update ret because slots_found == 0. // so, this while loops forever. 1187 if (next_index == 0) 1188 break; 1189 cur_index = next_index; 1190 } (2) Why does __lookup_tag() return with 0 and doesn't update the index? Assuming the following: - the one of the slot in radix_tree_node is NULL. - the one of the tag which corresponds to the slot sets with PAGECACHE_TAG_TOWRITE or other. - In a certain height(!=0), the corresponding index is 0. a) __lookup_tag() notices that the tag is set. 1005 static unsigned int 1006 __lookup_tag(struct radix_tree_node *slot, void ***results, unsigned long index, 1007 unsigned int max_items, unsigned long *next_index, unsigned int tag) 1008 { 1009 unsigned int nr_found = 0; 1010 unsigned int shift, height; 1011 1012 height = slot->height; 1013 if (height == 0) 1014 goto out; 1015 shift = (height-1) * RADIX_TREE_MAP_SHIFT; 1016 1017 while (height > 0) { 1018 unsigned long i = (index >> shift) & RADIX_TREE_MAP_MASK ; 1019 1020 for (;;) { 1021 if (tag_get(slot, tag, i)) 1022 break; ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ * the index is not updated yet. b) __lookup_tag() notices that the slot is NULL. 1023 index &= ~((1UL << shift) - 1); 1024 index += 1UL << shift; 1025 if (index == 0) 1026 goto out; /* 32-bit wraparound */ 1027 i++; 1028 if (i == RADIX_TREE_MAP_SIZE) 1029 goto out; 1030 } 1031 height--; 1032 if (height == 0) { /* Bottom level: grab some items */ ... 1055 } 1056 shift -= RADIX_TREE_MAP_SHIFT; 1057 slot = rcu_dereference_raw(slot->slots[i]); 1058 if (slot == NULL) 1059 break; ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ c) __lookup_tag() doesn't update the index and return with 0. 1060 } 1061 out: 1062 *next_index = index; ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ 1063 return nr_found; 1064 } (3) Why is the slot NULL even if the tag is set? Because radix_tree_range_tag_if_tagged() always sets the root tag with PAGECACHE_TAG_TOWRITE if the root tag is set with PAGECACHE_TAG_DIRTY, even if there is no tag which can be set with PAGECACHE_TAG_TOWRITE in the specified range (from *first_indexp to last_index). Of course, some PAGECACHE_TAG_DIRTY nodes must exist outside the specified range. (radix_tree_range_tag_if_tagged() is called only from tag_pages_for_writeback()) 640 unsigned long radix_tree_range_tag_if_tagged(struct radix_tree_root *root, 641 unsigned long *first_indexp, unsigned long last_index, 642 unsigned long nr_to_tag, 643 unsigned int iftag, unsigned int settag) 644 { 645 unsigned int height = root->height; 646 struct radix_tree_path path[height]; 647 struct radix_tree_path *pathp = path; 648 struct radix_tree_node *slot; 649 unsigned int shift; 650 unsigned long tagged = 0; 651 unsigned long index = *first_indexp; 652 653 last_index = min(last_index, radix_tree_maxindex(height)); 654 if (index > last_index) 655 return 0; 656 if (!nr_to_tag) 657 return 0; 658 if (!root_tag_get(root, iftag)) { 659 *first_indexp = last_index + 1; 660 return 0; 661 } 662 if (height == 0) { 663 *first_indexp = last_index + 1; 664 root_tag_set(root, settag); 665 return 1; 666 } ... 733 root_tag_set(root, settag); ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ 734 *first_indexp = index; 735 736 return tagged; 737 } As the result, there is no radix_tree_node which is set with PAGECACHE_TAG_TOWRITE but the root tag(radix_tree_root) is set with PAGECACHE_TAG_TOWRITE. [figure: inside radix_tree] (Please see the figure with typewriter font) =========================================== [roottag = DIRTY] | tag=0:NOTHING tag[0 0 0 1] 1:DIRTY [x x x +] 2:WRITEBACK | 3:DIRTY,WRITEBACK p 4:TOWRITE <---> 5:DIRTY,TOWRITE ... specified range (index: 0 to 2) * There is no DIRTY tag within the specified range. (But there is a DIRTY tag outside that range.) | | | | | | | | | after calling tag_pages_for_writeback() | | | | | | | | | v v v v v v v v v [roottag = DIRTY,TOWRITE] | p is "page". tag[0 0 0 1] x is NULL. [x x x +] +- is a pointer to "page". | p * But TOWRITE tag is set on the root tag. ============================================ After that, radix_tree_extend() via radix_tree_insert() is called when the page is added. This function sets the new radix_tree_node with PAGECACHE_TAG_TOWRITE to succeed the status of the root tag. 246 static int radix_tree_extend(struct radix_tree_root *root, unsigned long index) 247 { 248 struct radix_tree_node *node; 249 unsigned int height; 250 int tag; 251 252 /* Figure out what the height should be. */ 253 height = root->height + 1; 254 while (index > radix_tree_maxindex(height)) 255 height++; 256 257 if (root->rnode == NULL) { 258 root->height = height; 259 goto out; 260 } 261 262 do { 263 unsigned int newheight; 264 if (!(node = radix_tree_node_alloc(root))) 265 return -ENOMEM; 266 267 /* Increase the height. */ 268 node->slots[0] = radix_tree_indirect_to_ptr(root->rnode); 269 270 /* Propagate the aggregated tag info into the new root */ 271 for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++) { 272 if (root_tag_get(root, tag)) 273 tag_set(node, tag, 0); ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ 274 } =========================================== [roottag = DIRTY,TOWRITE] | : tag[0 0 0 1] [0 0 0 0] [x x x +] [+ x x x] | | p p (new page) | | | | | | | | | after calling radix_tree_insert | | | | | | | | | v v v v v v v v v [roottag = DIRTY,TOWRITE] | tag [5 0 0 0] * DIRTY and TOWRITE tags are [+ + x x] succeeded to the new node. | | tag [0 0 0 1] [0 0 0 0] [x x x +] [+ x x x] | | p p ============================================ After that, the index 3 page is released by remove_from_page_cache(). Then we can make the situation that the tag is set with PAGECACHE_TAG_TOWRITE and that the slot which corresponds to the tag is NULL. =========================================== [roottag = DIRTY,TOWRITE] | tag [5 0 0 0] [+ + x x] | | tag [0 0 0 1] [0 0 0 0] [x x x +] [+ x x x] | | p p (remove) | | | | | | | | | after calling remove_page_cache | | | | | | | | | v v v v v v v v v [roottag = DIRTY,TOWRITE] | tag [4 0 0 0] * Only DIRTY tag is cleared [x + x x] because no TOWRITE tag is existed | in the bottom node. [0 0 0 0] [+ x x x] | p ============================================ To solve this problem Change to that radix_tree_tag_if_tagged() doesn't tag the root tag if it doesn't set any tags within the specified range. Like this. ============================================ 640 unsigned long radix_tree_range_tag_if_tagged(struct radix_tree_root *root, 641 unsigned long *first_indexp, unsigned long last_index, 642 unsigned long nr_to_tag, 643 unsigned int iftag, unsigned int settag) 644 { 650 unsigned long tagged = 0; ... 733 if (tagged) ^^^^^^^^^^^^^^^^^^^^^^^^ 734 root_tag_set(root, settag); 735 *first_indexp = index; 736 737 return tagged; 738 } ============================================ Signed-off-by: Toshiyuki Okajima <toshi.okajima@jp.fujitsu.com> Acked-by: Jan Kara <jack@suse.cz> Cc: Dave Chinner <david@fromorbit.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> |
||
|---|---|---|
| .. | ||
| lzo | ||
| raid6 | ||
| reed_solomon | ||
| xz | ||
| zlib_deflate | ||
| zlib_inflate | ||
| .gitignore | ||
| argv_split.c | ||
| atomic64_test.c | ||
| atomic64.c | ||
| audit.c | ||
| average.c | ||
| bcd.c | ||
| bitmap.c | ||
| bitrev.c | ||
| btree.c | ||
| bug.c | ||
| bust_spinlocks.c | ||
| check_signature.c | ||
| checksum.c | ||
| cmdline.c | ||
| cpu-notifier-error-inject.c | ||
| cpumask.c | ||
| crc7.c | ||
| crc16.c | ||
| crc32.c | ||
| crc32defs.h | ||
| crc-ccitt.c | ||
| crc-itu-t.c | ||
| crc-t10dif.c | ||
| ctype.c | ||
| debug_locks.c | ||
| debugobjects.c | ||
| dec_and_lock.c | ||
| decompress_bunzip2.c | ||
| decompress_inflate.c | ||
| decompress_unlzma.c | ||
| decompress_unlzo.c | ||
| decompress_unxz.c | ||
| decompress.c | ||
| devres.c | ||
| div64.c | ||
| dma-debug.c | ||
| dump_stack.c | ||
| dynamic_debug.c | ||
| extable.c | ||
| fault-inject.c | ||
| find_last_bit.c | ||
| find_next_bit.c | ||
| flex_array.c | ||
| gcd.c | ||
| gen_crc32table.c | ||
| genalloc.c | ||
| halfmd4.c | ||
| hexdump.c | ||
| hweight.c | ||
| idr.c | ||
| inflate.c | ||
| int_sqrt.c | ||
| iomap_copy.c | ||
| iomap.c | ||
| iommu-helper.c | ||
| ioremap.c | ||
| irq_regs.c | ||
| is_single_threaded.c | ||
| kasprintf.c | ||
| Kconfig | ||
| Kconfig.debug | ||
| Kconfig.kgdb | ||
| Kconfig.kmemcheck | ||
| kernel_lock.c | ||
| klist.c | ||
| kobject_uevent.c | ||
| kobject.c | ||
| kref.c | ||
| lcm.c | ||
| libcrc32c.c | ||
| list_debug.c | ||
| list_sort.c | ||
| locking-selftest-hardirq.h | ||
| locking-selftest-mutex.h | ||
| locking-selftest-rlock-hardirq.h | ||
| locking-selftest-rlock-softirq.h | ||
| locking-selftest-rlock.h | ||
| locking-selftest-rsem.h | ||
| locking-selftest-softirq.h | ||
| locking-selftest-spin-hardirq.h | ||
| locking-selftest-spin-softirq.h | ||
| locking-selftest-spin.h | ||
| locking-selftest-wlock-hardirq.h | ||
| locking-selftest-wlock-softirq.h | ||
| locking-selftest-wlock.h | ||
| locking-selftest-wsem.h | ||
| locking-selftest.c | ||
| lru_cache.c | ||
| Makefile | ||
| nlattr.c | ||
| parser.c | ||
| percpu_counter.c | ||
| plist.c | ||
| prio_heap.c | ||
| prio_tree.c | ||
| proportions.c | ||
| radix-tree.c | ||
| random32.c | ||
| ratelimit.c | ||
| rational.c | ||
| rbtree.c | ||
| reciprocal_div.c | ||
| rwsem-spinlock.c | ||
| rwsem.c | ||
| scatterlist.c | ||
| sha1.c | ||
| show_mem.c | ||
| smp_processor_id.c | ||
| sort.c | ||
| spinlock_debug.c | ||
| string_helpers.c | ||
| string.c | ||
| swiotlb.c | ||
| syscall.c | ||
| textsearch.c | ||
| timerqueue.c | ||
| ts_bm.c | ||
| ts_fsm.c | ||
| ts_kmp.c | ||
| uuid.c | ||
| vsprintf.c | ||