Revision 95a49603707d982b25d17c5b70e220a05556a2f9 authored by Ming Lei on 22 March 2017, 02:14:43 UTC, committed by Jens Axboe on 22 March 2017, 14:03:35 UTC
When iterating busy requests in timeout handler, if the STARTED flag of one request isn't set, that means the request is being processed in block layer or driver, and isn't submitted to hardware yet. In current implementation of blk_mq_check_expired(), if the request queue becomes dying, un-started requests are handled as being completed/freed immediately. This way is wrong, and can cause rq corruption or double allocation[1][2], when doing I/O and removing&resetting NVMe device at the sametime. This patch fixes several issues reported by Yi Zhang. [1]. oops log 1 [ 581.789754] ------------[ cut here ]------------ [ 581.789758] kernel BUG at block/blk-mq.c:374! [ 581.789760] invalid opcode: 0000 [#1] SMP [ 581.789761] Modules linked in: vfat fat ipmi_ssif intel_rapl sb_edac edac_core x86_pkg_temp_thermal intel_powerclamp coretemp kvm_intel kvm nvme irqbypass crct10dif_pclmul nvme_core crc32_pclmul ghash_clmulni_intel intel_cstate ipmi_si mei_me ipmi_devintf intel_uncore sg ipmi_msghandler intel_rapl_perf iTCO_wdt mei iTCO_vendor_support mxm_wmi lpc_ich dcdbas shpchp pcspkr acpi_power_meter wmi nfsd auth_rpcgss nfs_acl lockd dm_multipath grace sunrpc ip_tables xfs libcrc32c sd_mod mgag200 i2c_algo_bit drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops ttm drm ahci libahci crc32c_intel tg3 libata megaraid_sas i2c_core ptp fjes pps_core dm_mirror dm_region_hash dm_log dm_mod [ 581.789796] CPU: 1 PID: 1617 Comm: kworker/1:1H Not tainted 4.10.0.bz1420297+ #4 [ 581.789797] Hardware name: Dell Inc. PowerEdge R730xd/072T6D, BIOS 2.2.5 09/06/2016 [ 581.789804] Workqueue: kblockd blk_mq_timeout_work [ 581.789806] task: ffff8804721c8000 task.stack: ffffc90006ee4000 [ 581.789809] RIP: 0010:blk_mq_end_request+0x58/0x70 [ 581.789810] RSP: 0018:ffffc90006ee7d50 EFLAGS: 00010202 [ 581.789811] RAX: 0000000000000001 RBX: ffff8802e4195340 RCX: ffff88028e2f4b88 [ 581.789812] RDX: 0000000000001000 RSI: 0000000000001000 RDI: 0000000000000000 [ 581.789813] RBP: ffffc90006ee7d60 R08: 0000000000000003 R09: ffff88028e2f4b00 [ 581.789814] R10: 0000000000001000 R11: 0000000000000001 R12: 00000000fffffffb [ 581.789815] R13: ffff88042abe5780 R14: 000000000000002d R15: ffff88046fbdff80 [ 581.789817] FS: 0000000000000000(0000) GS:ffff88047fc00000(0000) knlGS:0000000000000000 [ 581.789818] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 581.789819] CR2: 00007f64f403a008 CR3: 000000014d078000 CR4: 00000000001406e0 [ 581.789820] Call Trace: [ 581.789825] blk_mq_check_expired+0x76/0x80 [ 581.789828] bt_iter+0x45/0x50 [ 581.789830] blk_mq_queue_tag_busy_iter+0xdd/0x1f0 [ 581.789832] ? blk_mq_rq_timed_out+0x70/0x70 [ 581.789833] ? blk_mq_rq_timed_out+0x70/0x70 [ 581.789840] ? __switch_to+0x140/0x450 [ 581.789841] blk_mq_timeout_work+0x88/0x170 [ 581.789845] process_one_work+0x165/0x410 [ 581.789847] worker_thread+0x137/0x4c0 [ 581.789851] kthread+0x101/0x140 [ 581.789853] ? rescuer_thread+0x3b0/0x3b0 [ 581.789855] ? kthread_park+0x90/0x90 [ 581.789860] ret_from_fork+0x2c/0x40 [ 581.789861] Code: 48 85 c0 74 0d 44 89 e6 48 89 df ff d0 5b 41 5c 5d c3 48 8b bb 70 01 00 00 48 85 ff 75 0f 48 89 df e8 7d f0 ff ff 5b 41 5c 5d c3 <0f> 0b e8 71 f0 ff ff 90 eb e9 0f 1f 40 00 66 2e 0f 1f 84 00 00 [ 581.789882] RIP: blk_mq_end_request+0x58/0x70 RSP: ffffc90006ee7d50 [ 581.789889] ---[ end trace bcaf03d9a14a0a70 ]--- [2]. oops log2 [ 6984.857362] BUG: unable to handle kernel NULL pointer dereference at 0000000000000010 [ 6984.857372] IP: nvme_queue_rq+0x6e6/0x8cd [nvme] [ 6984.857373] PGD 0 [ 6984.857374] [ 6984.857376] Oops: 0000 [#1] SMP [ 6984.857379] Modules linked in: ipmi_ssif vfat fat intel_rapl sb_edac edac_core x86_pkg_temp_thermal intel_powerclamp coretemp kvm_intel kvm irqbypass crct10dif_pclmul crc32_pclmul ghash_clmulni_intel ipmi_si iTCO_wdt iTCO_vendor_support mxm_wmi ipmi_devintf intel_cstate sg dcdbas intel_uncore mei_me intel_rapl_perf mei pcspkr lpc_ich ipmi_msghandler shpchp acpi_power_meter wmi nfsd auth_rpcgss dm_multipath nfs_acl lockd grace sunrpc ip_tables xfs libcrc32c sd_mod mgag200 i2c_algo_bit drm_kms_helper syscopyarea sysfillrect crc32c_intel sysimgblt fb_sys_fops ttm nvme drm nvme_core ahci libahci i2c_core tg3 libata ptp megaraid_sas pps_core fjes dm_mirror dm_region_hash dm_log dm_mod [ 6984.857416] CPU: 7 PID: 1635 Comm: kworker/7:1H Not tainted 4.10.0-2.el7.bz1420297.x86_64 #1 [ 6984.857417] Hardware name: Dell Inc. PowerEdge R730xd/072T6D, BIOS 2.2.5 09/06/2016 [ 6984.857427] Workqueue: kblockd blk_mq_run_work_fn [ 6984.857429] task: ffff880476e3da00 task.stack: ffffc90002e90000 [ 6984.857432] RIP: 0010:nvme_queue_rq+0x6e6/0x8cd [nvme] [ 6984.857433] RSP: 0018:ffffc90002e93c50 EFLAGS: 00010246 [ 6984.857434] RAX: 0000000000000000 RBX: ffff880275646600 RCX: 0000000000001000 [ 6984.857435] RDX: 0000000000000fff RSI: 00000002fba2a000 RDI: ffff8804734e6950 [ 6984.857436] RBP: ffffc90002e93d30 R08: 0000000000002000 R09: 0000000000001000 [ 6984.857437] R10: 0000000000001000 R11: 0000000000000000 R12: ffff8804741d8000 [ 6984.857438] R13: 0000000000000040 R14: ffff880475649f80 R15: ffff8804734e6780 [ 6984.857439] FS: 0000000000000000(0000) GS:ffff88047fcc0000(0000) knlGS:0000000000000000 [ 6984.857440] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 6984.857442] CR2: 0000000000000010 CR3: 0000000001c09000 CR4: 00000000001406e0 [ 6984.857443] Call Trace: [ 6984.857451] ? mempool_free+0x2b/0x80 [ 6984.857455] ? bio_free+0x4e/0x60 [ 6984.857459] blk_mq_dispatch_rq_list+0xf5/0x230 [ 6984.857462] blk_mq_process_rq_list+0x133/0x170 [ 6984.857465] __blk_mq_run_hw_queue+0x8c/0xa0 [ 6984.857467] blk_mq_run_work_fn+0x12/0x20 [ 6984.857473] process_one_work+0x165/0x410 [ 6984.857475] worker_thread+0x137/0x4c0 [ 6984.857478] kthread+0x101/0x140 [ 6984.857480] ? rescuer_thread+0x3b0/0x3b0 [ 6984.857481] ? kthread_park+0x90/0x90 [ 6984.857489] ret_from_fork+0x2c/0x40 [ 6984.857490] Code: 8b bd 70 ff ff ff 89 95 50 ff ff ff 89 8d 58 ff ff ff 44 89 95 60 ff ff ff e8 b7 dd 12 e1 8b 95 50 ff ff ff 48 89 85 68 ff ff ff <4c> 8b 48 10 44 8b 58 18 8b 8d 58 ff ff ff 44 8b 95 60 ff ff ff [ 6984.857511] RIP: nvme_queue_rq+0x6e6/0x8cd [nvme] RSP: ffffc90002e93c50 [ 6984.857512] CR2: 0000000000000010 [ 6984.895359] ---[ end trace 2d7ceb528432bf83 ]--- Cc: stable@vger.kernel.org Reported-by: Yi Zhang <yizhan@redhat.com> Tested-by: Yi Zhang <yizhan@redhat.com> Reviewed-by: Bart Van Assche <bart.vanassche@sandisk.com> Reviewed-by: Hannes Reinecke <hare@suse.com> Signed-off-by: Ming Lei <tom.leiming@gmail.com> Signed-off-by: Jens Axboe <axboe@fb.com>
1 parent a457d08
percpu-vm.c
/*
* mm/percpu-vm.c - vmalloc area based chunk allocation
*
* Copyright (C) 2010 SUSE Linux Products GmbH
* Copyright (C) 2010 Tejun Heo <tj@kernel.org>
*
* This file is released under the GPLv2.
*
* Chunks are mapped into vmalloc areas and populated page by page.
* This is the default chunk allocator.
*/
static struct page *pcpu_chunk_page(struct pcpu_chunk *chunk,
unsigned int cpu, int page_idx)
{
/* must not be used on pre-mapped chunk */
WARN_ON(chunk->immutable);
return vmalloc_to_page((void *)pcpu_chunk_addr(chunk, cpu, page_idx));
}
/**
* pcpu_get_pages - get temp pages array
*
* Returns pointer to array of pointers to struct page which can be indexed
* with pcpu_page_idx(). Note that there is only one array and accesses
* should be serialized by pcpu_alloc_mutex.
*
* RETURNS:
* Pointer to temp pages array on success.
*/
static struct page **pcpu_get_pages(void)
{
static struct page **pages;
size_t pages_size = pcpu_nr_units * pcpu_unit_pages * sizeof(pages[0]);
lockdep_assert_held(&pcpu_alloc_mutex);
if (!pages)
pages = pcpu_mem_zalloc(pages_size);
return pages;
}
/**
* pcpu_free_pages - free pages which were allocated for @chunk
* @chunk: chunk pages were allocated for
* @pages: array of pages to be freed, indexed by pcpu_page_idx()
* @page_start: page index of the first page to be freed
* @page_end: page index of the last page to be freed + 1
*
* Free pages [@page_start and @page_end) in @pages for all units.
* The pages were allocated for @chunk.
*/
static void pcpu_free_pages(struct pcpu_chunk *chunk,
struct page **pages, int page_start, int page_end)
{
unsigned int cpu;
int i;
for_each_possible_cpu(cpu) {
for (i = page_start; i < page_end; i++) {
struct page *page = pages[pcpu_page_idx(cpu, i)];
if (page)
__free_page(page);
}
}
}
/**
* pcpu_alloc_pages - allocates pages for @chunk
* @chunk: target chunk
* @pages: array to put the allocated pages into, indexed by pcpu_page_idx()
* @page_start: page index of the first page to be allocated
* @page_end: page index of the last page to be allocated + 1
*
* Allocate pages [@page_start,@page_end) into @pages for all units.
* The allocation is for @chunk. Percpu core doesn't care about the
* content of @pages and will pass it verbatim to pcpu_map_pages().
*/
static int pcpu_alloc_pages(struct pcpu_chunk *chunk,
struct page **pages, int page_start, int page_end)
{
const gfp_t gfp = GFP_KERNEL | __GFP_HIGHMEM | __GFP_COLD;
unsigned int cpu, tcpu;
int i;
for_each_possible_cpu(cpu) {
for (i = page_start; i < page_end; i++) {
struct page **pagep = &pages[pcpu_page_idx(cpu, i)];
*pagep = alloc_pages_node(cpu_to_node(cpu), gfp, 0);
if (!*pagep)
goto err;
}
}
return 0;
err:
while (--i >= page_start)
__free_page(pages[pcpu_page_idx(cpu, i)]);
for_each_possible_cpu(tcpu) {
if (tcpu == cpu)
break;
for (i = page_start; i < page_end; i++)
__free_page(pages[pcpu_page_idx(tcpu, i)]);
}
return -ENOMEM;
}
/**
* pcpu_pre_unmap_flush - flush cache prior to unmapping
* @chunk: chunk the regions to be flushed belongs to
* @page_start: page index of the first page to be flushed
* @page_end: page index of the last page to be flushed + 1
*
* Pages in [@page_start,@page_end) of @chunk are about to be
* unmapped. Flush cache. As each flushing trial can be very
* expensive, issue flush on the whole region at once rather than
* doing it for each cpu. This could be an overkill but is more
* scalable.
*/
static void pcpu_pre_unmap_flush(struct pcpu_chunk *chunk,
int page_start, int page_end)
{
flush_cache_vunmap(
pcpu_chunk_addr(chunk, pcpu_low_unit_cpu, page_start),
pcpu_chunk_addr(chunk, pcpu_high_unit_cpu, page_end));
}
static void __pcpu_unmap_pages(unsigned long addr, int nr_pages)
{
unmap_kernel_range_noflush(addr, nr_pages << PAGE_SHIFT);
}
/**
* pcpu_unmap_pages - unmap pages out of a pcpu_chunk
* @chunk: chunk of interest
* @pages: pages array which can be used to pass information to free
* @page_start: page index of the first page to unmap
* @page_end: page index of the last page to unmap + 1
*
* For each cpu, unmap pages [@page_start,@page_end) out of @chunk.
* Corresponding elements in @pages were cleared by the caller and can
* be used to carry information to pcpu_free_pages() which will be
* called after all unmaps are finished. The caller should call
* proper pre/post flush functions.
*/
static void pcpu_unmap_pages(struct pcpu_chunk *chunk,
struct page **pages, int page_start, int page_end)
{
unsigned int cpu;
int i;
for_each_possible_cpu(cpu) {
for (i = page_start; i < page_end; i++) {
struct page *page;
page = pcpu_chunk_page(chunk, cpu, i);
WARN_ON(!page);
pages[pcpu_page_idx(cpu, i)] = page;
}
__pcpu_unmap_pages(pcpu_chunk_addr(chunk, cpu, page_start),
page_end - page_start);
}
}
/**
* pcpu_post_unmap_tlb_flush - flush TLB after unmapping
* @chunk: pcpu_chunk the regions to be flushed belong to
* @page_start: page index of the first page to be flushed
* @page_end: page index of the last page to be flushed + 1
*
* Pages [@page_start,@page_end) of @chunk have been unmapped. Flush
* TLB for the regions. This can be skipped if the area is to be
* returned to vmalloc as vmalloc will handle TLB flushing lazily.
*
* As with pcpu_pre_unmap_flush(), TLB flushing also is done at once
* for the whole region.
*/
static void pcpu_post_unmap_tlb_flush(struct pcpu_chunk *chunk,
int page_start, int page_end)
{
flush_tlb_kernel_range(
pcpu_chunk_addr(chunk, pcpu_low_unit_cpu, page_start),
pcpu_chunk_addr(chunk, pcpu_high_unit_cpu, page_end));
}
static int __pcpu_map_pages(unsigned long addr, struct page **pages,
int nr_pages)
{
return map_kernel_range_noflush(addr, nr_pages << PAGE_SHIFT,
PAGE_KERNEL, pages);
}
/**
* pcpu_map_pages - map pages into a pcpu_chunk
* @chunk: chunk of interest
* @pages: pages array containing pages to be mapped
* @page_start: page index of the first page to map
* @page_end: page index of the last page to map + 1
*
* For each cpu, map pages [@page_start,@page_end) into @chunk. The
* caller is responsible for calling pcpu_post_map_flush() after all
* mappings are complete.
*
* This function is responsible for setting up whatever is necessary for
* reverse lookup (addr -> chunk).
*/
static int pcpu_map_pages(struct pcpu_chunk *chunk,
struct page **pages, int page_start, int page_end)
{
unsigned int cpu, tcpu;
int i, err;
for_each_possible_cpu(cpu) {
err = __pcpu_map_pages(pcpu_chunk_addr(chunk, cpu, page_start),
&pages[pcpu_page_idx(cpu, page_start)],
page_end - page_start);
if (err < 0)
goto err;
for (i = page_start; i < page_end; i++)
pcpu_set_page_chunk(pages[pcpu_page_idx(cpu, i)],
chunk);
}
return 0;
err:
for_each_possible_cpu(tcpu) {
if (tcpu == cpu)
break;
__pcpu_unmap_pages(pcpu_chunk_addr(chunk, tcpu, page_start),
page_end - page_start);
}
pcpu_post_unmap_tlb_flush(chunk, page_start, page_end);
return err;
}
/**
* pcpu_post_map_flush - flush cache after mapping
* @chunk: pcpu_chunk the regions to be flushed belong to
* @page_start: page index of the first page to be flushed
* @page_end: page index of the last page to be flushed + 1
*
* Pages [@page_start,@page_end) of @chunk have been mapped. Flush
* cache.
*
* As with pcpu_pre_unmap_flush(), TLB flushing also is done at once
* for the whole region.
*/
static void pcpu_post_map_flush(struct pcpu_chunk *chunk,
int page_start, int page_end)
{
flush_cache_vmap(
pcpu_chunk_addr(chunk, pcpu_low_unit_cpu, page_start),
pcpu_chunk_addr(chunk, pcpu_high_unit_cpu, page_end));
}
/**
* pcpu_populate_chunk - populate and map an area of a pcpu_chunk
* @chunk: chunk of interest
* @page_start: the start page
* @page_end: the end page
*
* For each cpu, populate and map pages [@page_start,@page_end) into
* @chunk.
*
* CONTEXT:
* pcpu_alloc_mutex, does GFP_KERNEL allocation.
*/
static int pcpu_populate_chunk(struct pcpu_chunk *chunk,
int page_start, int page_end)
{
struct page **pages;
pages = pcpu_get_pages();
if (!pages)
return -ENOMEM;
if (pcpu_alloc_pages(chunk, pages, page_start, page_end))
return -ENOMEM;
if (pcpu_map_pages(chunk, pages, page_start, page_end)) {
pcpu_free_pages(chunk, pages, page_start, page_end);
return -ENOMEM;
}
pcpu_post_map_flush(chunk, page_start, page_end);
return 0;
}
/**
* pcpu_depopulate_chunk - depopulate and unmap an area of a pcpu_chunk
* @chunk: chunk to depopulate
* @page_start: the start page
* @page_end: the end page
*
* For each cpu, depopulate and unmap pages [@page_start,@page_end)
* from @chunk.
*
* CONTEXT:
* pcpu_alloc_mutex.
*/
static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk,
int page_start, int page_end)
{
struct page **pages;
/*
* If control reaches here, there must have been at least one
* successful population attempt so the temp pages array must
* be available now.
*/
pages = pcpu_get_pages();
BUG_ON(!pages);
/* unmap and free */
pcpu_pre_unmap_flush(chunk, page_start, page_end);
pcpu_unmap_pages(chunk, pages, page_start, page_end);
/* no need to flush tlb, vmalloc will handle it lazily */
pcpu_free_pages(chunk, pages, page_start, page_end);
}
static struct pcpu_chunk *pcpu_create_chunk(void)
{
struct pcpu_chunk *chunk;
struct vm_struct **vms;
chunk = pcpu_alloc_chunk();
if (!chunk)
return NULL;
vms = pcpu_get_vm_areas(pcpu_group_offsets, pcpu_group_sizes,
pcpu_nr_groups, pcpu_atom_size);
if (!vms) {
pcpu_free_chunk(chunk);
return NULL;
}
chunk->data = vms;
chunk->base_addr = vms[0]->addr - pcpu_group_offsets[0];
return chunk;
}
static void pcpu_destroy_chunk(struct pcpu_chunk *chunk)
{
if (chunk && chunk->data)
pcpu_free_vm_areas(chunk->data, pcpu_nr_groups);
pcpu_free_chunk(chunk);
}
static struct page *pcpu_addr_to_page(void *addr)
{
return vmalloc_to_page(addr);
}
static int __init pcpu_verify_alloc_info(const struct pcpu_alloc_info *ai)
{
/* no extra restriction */
return 0;
}
![swh spinner](/static/img/swh-spinner.gif)
Computing file changes ...