On Mon, 22 Jan 2007 10:35:10 -0800 Andrew Vasquez <andrew.vasquez@xxxxxxxxxx> wrote:
> All,
>
> We've been trying to track down a nagging regression seen during some
> port-disable/enable testing. The problem occurs anywhere from
> 20 minutes to 120 minutes of testing under very minimal I/O load:
>
> [ 1143.890598] Unable to handle kernel NULL pointer dereference at 0000000000000028 RIP:
> [ 1143.896087] [<ffffffff802ed04f>] as_move_to_dispatch+0x11/0x135
> [ 1143.904574] PGD 120ba067 PUD 31e8c067 PMD 0
> [ 1143.908895] Oops: 0000 [1] SMP
> [ 1143.912065] CPU 1
> [ 1143.914092] Modules linked in: qla2xxx scsi_transport_fc
> [ 1143.919453] Pid: 8362, comm: dt Not tainted 2.6.19 #39
> [ 1143.924588] RIP: 0010:[<ffffffff802ed04f>] [<ffffffff802ed04f>] as_move_to_dispatch+0x11/0x135
> [ 1143.933300] RSP: 0018:ffff8100021f7cf0 EFLAGS: 00010046
> [ 1143.938610] RAX: 0000000000000000 RBX: ffff8100261392f0 RCX: 0000000000000000
> [ 1143.945736] RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff8100261392f0
> [ 1143.952865] RBP: 0000000000000000 R08: ffffffff804d0928 R09: ffff8100351a96e0
> [ 1143.959992] R10: ffff8100351a96e0 R11: 0000000000000000 R12: 0000000000000000
> [ 1143.967118] R13: 0000000000000000 R14: 0000000000000282 R15: 0000000000000001
> [ 1143.974248] FS: 0000000000000000(0000) GS:ffff8100021c5930(0000) knlGS:0000000000000000
> [ 1143.982327] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b
> [ 1143.988070] CR2: 0000000000000028 CR3: 000000003493b000 CR4: 00000000000006e0
> [ 1143.995198] Process dt (pid: 8362, threadinfo ffff8100207a2000, task ffff810023d86840)
> [ 1144.003103] Stack: 0000000000000000 ffff8100261392f0 0000000000000000 0000000000000001
> [ 1144.011183] 0000000000000000 ffffffff802ed591 0000000000000000 ffff810035795990
> [ 1144.018640] ffff81000f11b3f8 ffff810035795990 ffff810035795990 ffffffff802e53d6
> [ 1144.025906] Call Trace:
> [ 1144.028548] <IRQ> [<ffffffff802ed591>] as_dispatch_request+0x39d/0x3aa
> [ 1144.035274] [<ffffffff802e53d6>] elv_next_request+0x45/0x151
> [ 1144.041015] [<ffffffff8037b3cf>] scsi_request_fn+0x7a/0x375
> [ 1144.046667] [<ffffffff802e8fa0>] blk_run_queue+0x42/0x74
> [ 1144.052062] [<ffffffff8037b2bc>] scsi_next_command+0x2d/0x39
> [ 1144.057805] [<ffffffff8037b85b>] scsi_end_request+0xc0/0xce
> [ 1144.063460] [<ffffffff8037ba03>] scsi_io_completion+0x149/0x351
> [ 1144.069464] [<ffffffff8038aad6>] sd_rw_intr+0x247/0x256
> [ 1144.074770] [<ffffffff80376b92>] scsi_finish_command+0x88/0x8d
> [ 1144.080686] [<ffffffff8037c25e>] scsi_softirq_done+0xe7/0xef
> [ 1144.086429] [<ffffffff802e614c>] blk_done_softirq+0x63/0x71
> [ 1144.092082] [<ffffffff80226487>] __do_softirq+0x51/0xbd
> [ 1144.097394] [<ffffffff8020a88c>] call_softirq+0x1c/0x28
> [ 1144.102701] [<ffffffff8020bffa>] do_softirq+0x2e/0x94
> [ 1144.107836] [<ffffffff8020c10e>] do_IRQ+0xae/0xc8
> [ 1144.112625] [<ffffffff80209c81>] ret_from_intr+0x0/0xb
> [ 1144.117845] <EOI> [<ffffffff8027dfad>] __bio_add_page+0x1b8/0x1bf
> [ 1144.124135] [<ffffffff8027ecb6>] blkdev_direct_IO+0x2c9/0x420
> [ 1144.129964] [<ffffffff8021a1f4>] __activate_task+0x2d/0x3f
> [ 1144.135537] [<ffffffff8040df0d>] _spin_unlock_irq+0x6/0x9
> [ 1144.141024] [<ffffffff80241d86>] generic_file_direct_IO+0xa6/0xe8
> [ 1144.147196] [<ffffffff80219efe>] __wake_up_common+0x42/0x6c
> [ 1144.152852] [<ffffffff80242515>] generic_file_aio_read+0xcc/0x19d
> [ 1144.159029] [<ffffffff8025d7cd>] do_sync_read+0xc8/0x10b
> [ 1144.164426] [<ffffffff8023343c>] autoremove_wake_function+0x0/0x2e
> [ 1144.170684] [<ffffffff8040df0d>] _spin_unlock_irq+0x6/0x9
> [ 1144.176166] [<ffffffff8025c516>] do_filp_open+0x2d/0x3d
> [ 1144.181480] [<ffffffff80259876>] poison_obj+0x35/0x44
> [ 1144.186620] [<ffffffff8025e1c0>] vfs_read+0xac/0x14f
> [ 1144.191668] [<ffffffff8025e322>] sys_read+0x45/0x6e
> [ 1144.196630] [<ffffffff8020976e>] system_call+0x7e/0x83
> [ 1144.201852]
>
> ...
>
> Basically what is happening from the FC side is the initiator executes
> a simple dt test:
>
> dt of=/dev/raw/raw1 procs=8 oncerr=abort bs=16k disable=stats limit=2m passes=1000000 pattern=iot dlimit=2048
>
> against a single lun (a very basic Windows target mode driver).
> During the test a port-enable, port-disable script is running agains
> the switch's port that is connected to the target (this occurs every
> sixty seconds (for a disabled duration of 2 seconds). Additionally,
> the target itself is set to LOGO (logout) or drop off the topology
> every 30 seconds.
I don't understand what effect the port-enable/port-disable has upon the
system. Will it cause I/O errors, or what?
> This test runs fine up to 2.6.19.
One thing we did in there was to give direct-io-against-blockdevs some
special-case bio-preparation code. Perhaps this is tickling a bug somehow.
We can revert that change like this:
diff -puN fs/block_dev.c~a fs/block_dev.c
--- a/fs/block_dev.c~a
+++ a/fs/block_dev.c
@@ -196,8 +196,47 @@ static void blk_unget_page(struct page *
pvec->page[--pvec->idx] = page;
}
+static int
+blkdev_get_blocks(struct inode *inode, sector_t iblock,
+ struct buffer_head *bh, int create)
+{
+ sector_t end_block = max_block(I_BDEV(inode));
+ unsigned long max_blocks = bh->b_size >> inode->i_blkbits;
+
+ if ((iblock + max_blocks) > end_block) {
+ max_blocks = end_block - iblock;
+ if ((long)max_blocks <= 0) {
+ if (create)
+ return -EIO; /* write fully beyond EOF */
+ /*
+ * It is a read which is fully beyond EOF. We return
+ * a !buffer_mapped buffer
+ */
+ max_blocks = 0;
+ }
+ }
+
+ bh->b_bdev = I_BDEV(inode);
+ bh->b_blocknr = iblock;
+ bh->b_size = max_blocks << inode->i_blkbits;
+ if (max_blocks)
+ set_buffer_mapped(bh);
+ return 0;
+}
+
static ssize_t
blkdev_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
+ loff_t offset, unsigned long nr_segs)
+{
+ struct file *file = iocb->ki_filp;
+ struct inode *inode = file->f_mapping->host;
+
+ return blockdev_direct_IO_no_locking(rw, iocb, inode, I_BDEV(inode),
+ iov, offset, nr_segs, blkdev_get_blocks, NULL);
+}
+
+static ssize_t
+xxblkdev_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
loff_t pos, unsigned long nr_segs)
{
struct inode *inode = iocb->ki_filp->f_mapping->host;
_
-
To unsubscribe from this list: send the line "unsubscribe linux-scsi" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
