pnfs: fix lockup caused by pnfs_generic_pg_test
end_offset and req_offset both return u64 - avoid casting to u32 until it's needed, when it's less than the (u32) size returned by nfs_generic_pg_test. Also, fix the comments in pnfs_generic_pg_test. Running the cthon04 special tests caused this lockup in the "write/read at 2GB, 4GB edges" test when running against a file layout server: BUG: soft lockup - CPU#0 stuck for 22s! [bigfile2:823] Modules linked in: nfs_layout_nfsv41_files rpcsec_gss_krb5 nfsv4 nfs fscache ip6t_REJECT nf_conntrack_ipv6 nf_defrag_ipv6 ip6table_mangle ip6table_filter ip6_tables iptable_nat nf_nat_ipv4 nf_nat iptable_mangle ppdev crc32c_intel aesni_intel aes_x86_64 glue_helper lrw gf128mul ablk_helper cryptd serio_raw e1000 shpchp i2c_piix4 i2c_core parport_pc parport nfsd auth_rpcgss oid_registry exportfs nfs_acl lockd sunrpc btrfs xor zlib_deflate raid6_pq mptspi scsi_transport_spi mptscsih mptbase ata_generic floppy autofs4 irq event stamp: 205958 hardirqs last enabled at (205957): [<ffffffff814a62dc>] restore_args+0x0/0x30 hardirqs last disabled at (205958): [<ffffffff814ad96a>] apic_timer_interrupt+0x6a/0x80 softirqs last enabled at (205956): [<ffffffff8103ffb2>] __do_softirq+0x1ea/0x2ab softirqs last disabled at (205951): [<ffffffff8104026d>] irq_exit+0x44/0x9a CPU: 0 PID: 823 Comm: bigfile2 Not tainted 3.15.0-rc1-branch-pgio_plus+ #3 Hardware name: VMware, Inc. VMware Virtual Platform/440BX Desktop Reference Platform, BIOS 6.00 07/31/2013 task: ffff8800792ec480 ti: ffff880078c4e000 task.ti: ffff880078c4e000 RIP: 0010:[<ffffffffa02ce51f>] [<ffffffffa02ce51f>] nfs_page_group_unlock+0x3e/0x4b [nfs] RSP: 0018:ffff880078c4fab0 EFLAGS: 00000202 RAX: 0000000000000fff RBX: ffff88006bf83300 RCX: 0000000000000000 RDX: 0000000000000001 RSI: 0000000000000000 RDI: ffff88006bf83300 RBP: ffff880078c4fab8 R08: 0000000000000001 R09: 0000000000000000 R10: ffffffff8249840c R11: 0000000000000000 R12: 0000000000000035 R13: ffff88007ffc72d8 R14: 0000000000000001 R15: 0000000000000000 FS: 00007f45f11b7740(0000) GS:ffff88007f200000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f3a8cb632d0 CR3: 000000007931c000 CR4: 00000000001407f0 Stack: ffff88006bf832c0 ffff880078c4fb00 ffffffffa02cec22 ffff880078c4fad8 00000fff810f9d99 ffff880078c4fca0 ffff88006bf832c0 ffff88006bf832c0 ffff880078c4fca0 ffff880078c4fd60 ffff880078c4fb28 ffffffffa02cee34 Call Trace: [<ffffffffa02cec22>] __nfs_pageio_add_request+0x298/0x34f [nfs] [<ffffffffa02cee34>] nfs_pageio_add_request+0x1f/0x42 [nfs] [<ffffffffa02d1722>] nfs_do_writepage+0x1b5/0x1e4 [nfs] [<ffffffffa02d1764>] nfs_writepages_callback+0x13/0x25 [nfs] [<ffffffffa02d1751>] ? nfs_do_writepage+0x1e4/0x1e4 [nfs] [<ffffffff810eb32d>] write_cache_pages+0x254/0x37f [<ffffffffa02d1751>] ? nfs_do_writepage+0x1e4/0x1e4 [nfs] [<ffffffff8149cf9e>] ? printk+0x54/0x56 [<ffffffff810eacca>] ? __set_page_dirty_nobuffers+0x22/0xe9 [<ffffffffa016d864>] ? put_rpccred+0x38/0x101 [sunrpc] [<ffffffffa02d1ae1>] nfs_writepages+0xb4/0xf8 [nfs] [<ffffffff810ec59c>] do_writepages+0x21/0x2f [<ffffffff810e36e8>] __filemap_fdatawrite_range+0x55/0x57 [<ffffffff810e374a>] filemap_write_and_wait_range+0x2d/0x5b [<ffffffffa030ba0a>] nfs4_file_fsync+0x3a/0x98 [nfsv4] [<ffffffff8114ee3c>] vfs_fsync_range+0x18/0x20 [<ffffffff810e40c2>] generic_file_aio_write+0xa7/0xbd [<ffffffffa02c5c6b>] nfs_file_write+0xf0/0x170 [nfs] [<ffffffff81129215>] do_sync_write+0x59/0x78 [<ffffffff8112956c>] vfs_write+0xab/0x107 [<ffffffff81129c8b>] SyS_write+0x49/0x7f [<ffffffff814acd12>] system_call_fastpath+0x16/0x1b Reported-by: Anna Schumaker <Anna.Schumaker@netapp.com> Signed-off-by: Weston Andros Adamson <dros@primarydata.com> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
This commit is contained in:
parent
f383b7e8fd
commit
c5e20cb700
|
@ -1433,33 +1433,37 @@ pnfs_generic_pg_test(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev,
|
|||
struct nfs_page *req)
|
||||
{
|
||||
unsigned int size;
|
||||
u64 end;
|
||||
u64 seg_end, req_start, seg_left;
|
||||
|
||||
size = nfs_generic_pg_test(pgio, prev, req);
|
||||
if (!size)
|
||||
return 0;
|
||||
|
||||
/*
|
||||
* Test if a nfs_page is fully contained in the pnfs_layout_range.
|
||||
* Note that this test makes several assumptions:
|
||||
* - that the previous nfs_page in the struct nfs_pageio_descriptor
|
||||
* is known to lie within the range.
|
||||
* - that the nfs_page being tested is known to be contiguous with the
|
||||
* previous nfs_page.
|
||||
* - Layout ranges are page aligned, so we only have to test the
|
||||
* start offset of the request.
|
||||
* 'size' contains the number of bytes left in the current page (up
|
||||
* to the original size asked for in @req->wb_bytes).
|
||||
*
|
||||
* Calculate how many bytes are left in the layout segment
|
||||
* and if there are less bytes than 'size', return that instead.
|
||||
*
|
||||
* Please also note that 'end_offset' is actually the offset of the
|
||||
* first byte that lies outside the pnfs_layout_range. FIXME?
|
||||
*
|
||||
*/
|
||||
if (pgio->pg_lseg) {
|
||||
end = end_offset(pgio->pg_lseg->pls_range.offset,
|
||||
pgio->pg_lseg->pls_range.length);
|
||||
WARN_ON_ONCE(req_offset(req) > end);
|
||||
if (req_offset(req) >= end)
|
||||
seg_end = end_offset(pgio->pg_lseg->pls_range.offset,
|
||||
pgio->pg_lseg->pls_range.length);
|
||||
req_start = req_offset(req);
|
||||
WARN_ON_ONCE(req_start > seg_end);
|
||||
/* start of request is past the last byte of this segment */
|
||||
if (req_start >= seg_end)
|
||||
return 0;
|
||||
size = min((unsigned int)(end - req_offset(req)), size);
|
||||
|
||||
/* adjust 'size' iff there are fewer bytes left in the
|
||||
* segment than what nfs_generic_pg_test returned */
|
||||
seg_left = seg_end - req_start;
|
||||
if (seg_left < size)
|
||||
size = (unsigned int)seg_left;
|
||||
}
|
||||
|
||||
return size;
|
||||
|
|
Loading…
Reference in New Issue