diff mbox

[PATCHv2] tcmu: Fix possbile memory leak when recalculating the cmd base size

Message ID 1499767183-17980-1-git-send-email-lixiubo@cmss.chinamobile.com
State New, archived
Headers show

Commit Message

Xiubo Li July 11, 2017, 9:59 a.m. UTC
From: Xiubo Li <lixiubo@cmss.chinamobile.com>

For all the entries allocated from the ring cmd area, the memory is
something like the stack memory, which will always reserve the old
data, so the entry->req.iov_bidi_cnt maybe none zero.

On some environments, the crash could be reporduce very easy and some
not. The following is the crash core trace:

[  240.143969] CPU: 0 PID: 1285 Comm: iscsi_trx Not tainted
4.12.0-rc1+ #3
[  240.150607] Hardware name: ASUS All Series/H87-PRO, BIOS 2104
10/28/2014
[  240.157331] task: ffff8807de4f5800 task.stack:
ffffc900047dc000
[  240.163270] RIP: 0010:memcpy_erms+0x6/0x10
[  240.167377] RSP: 0018:ffffc900047dfc68 EFLAGS: 00010202
[  240.172621] RAX: ffffc9065db85540 RBX: ffff8807f7980000 RCX:
0000000000000010
[  240.179771] RDX: 0000000000000010 RSI: ffff8807de574fe0 RDI:
ffffc9065db85540
[  240.186930] RBP: ffffc900047dfd30 R08: ffff8807de41b000 R09:
0000000000000000
[  240.194088] R10: 0000000000000040 R11: ffff8807e9b726f0 R12:
00000006565726b0
[  240.201246] R13: ffffc90007612ea0 R14: 000000065657d540 R15:
0000000000000000
[  240.208397] FS:  0000000000000000(0000)
GS:ffff88081fa00000(0000)
knlGS:0000000000000000
[  240.216510] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  240.222280] CR2: ffffc9065db85540 CR3: 0000000001c0f000 CR4:
00000000001406f0
[  240.229430] Call Trace:
[  240.231887]  ? tcmu_queue_cmd+0x83c/0xa80
[  240.235916]  ? target_check_reservation+0xcd/0x6f0
[  240.240725]  __target_execute_cmd+0x27/0xa0
[  240.244918]  target_execute_cmd+0x232/0x2c0
[  240.249124]  ? __local_bh_enable_ip+0x64/0xa0
[  240.253499]  iscsit_execute_cmd+0x20d/0x270
[  240.257693]  iscsit_sequence_cmd+0x110/0x190
[  240.261985]  iscsit_get_rx_pdu+0x360/0xc80
[  240.267565]  ? iscsi_target_rx_thread+0x54/0xd0
[  240.273571]  iscsi_target_rx_thread+0x9a/0xd0
[  240.279413]  kthread+0x113/0x150
[  240.284120]  ? iscsi_target_tx_thread+0x1e0/0x1e0
[  240.290297]  ? kthread_create_on_node+0x40/0x40
[  240.296297]  ret_from_fork+0x2e/0x40
[  240.301332] Code: 90 90 90 90 90 eb 1e 0f 1f 00 48 89 f8 48
89 d1 48
c1 e9 03 83 e2 07 f3 48 a5 89 d1 f3 a4 c3 66 0f 1f 44 00 00 48
89 f8 48
89 d1 <f3> a4 c3 0f 1f 80 00 00 00 00 48 89 f8 48 83 fa 20 72 7e
40 38
[  240.321751] RIP: memcpy_erms+0x6/0x10 RSP: ffffc900047dfc68
[  240.328838] CR2: ffffc9065db85540
[  240.333667] ---[ end trace b7e5354cfb54d08b ]---

To fix this, just memset all the entry memory before using it, and
also to be more readable we adjust the bidi code.

Fixed: fe25cc34795(tcmu: Recalculate the tcmu_cmd size to save cmd area
		memories)
Reported-by: Bryant G. Ly <bryantly@linux.vnet.ibm.com>
Tested-by: Damien Le Moal <damien.lemoal@wdc.com>
Signed-off-by: Xiubo Li <lixiubo@cmss.chinamobile.com>
---
 drivers/target/target_core_user.c | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

Comments

Bryant G. Ly July 11, 2017, 3:55 p.m. UTC | #1
> From: Xiubo Li <lixiubo@cmss.chinamobile.com>
>
> For all the entries allocated from the ring cmd area, the memory is
> something like the stack memory, which will always reserve the old
> data, so the entry->req.iov_bidi_cnt maybe none zero.
>
> On some environments, the crash could be reporduce very easy and some
> not. The following is the crash core trace:
>
> [  240.143969] CPU: 0 PID: 1285 Comm: iscsi_trx Not tainted
> 4.12.0-rc1+ #3
> [  240.150607] Hardware name: ASUS All Series/H87-PRO, BIOS 2104
> 10/28/2014
> [  240.157331] task: ffff8807de4f5800 task.stack:
> ffffc900047dc000
> [  240.163270] RIP: 0010:memcpy_erms+0x6/0x10
> [  240.167377] RSP: 0018:ffffc900047dfc68 EFLAGS: 00010202
> [  240.172621] RAX: ffffc9065db85540 RBX: ffff8807f7980000 RCX:
> 0000000000000010
> [  240.179771] RDX: 0000000000000010 RSI: ffff8807de574fe0 RDI:
> ffffc9065db85540
> [  240.186930] RBP: ffffc900047dfd30 R08: ffff8807de41b000 R09:
> 0000000000000000
> [  240.194088] R10: 0000000000000040 R11: ffff8807e9b726f0 R12:
> 00000006565726b0
> [  240.201246] R13: ffffc90007612ea0 R14: 000000065657d540 R15:
> 0000000000000000
> [  240.208397] FS:  0000000000000000(0000)
> GS:ffff88081fa00000(0000)
> knlGS:0000000000000000
> [  240.216510] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
> [  240.222280] CR2: ffffc9065db85540 CR3: 0000000001c0f000 CR4:
> 00000000001406f0
> [  240.229430] Call Trace:
> [  240.231887]  ? tcmu_queue_cmd+0x83c/0xa80
> [  240.235916]  ? target_check_reservation+0xcd/0x6f0
> [  240.240725]  __target_execute_cmd+0x27/0xa0
> [  240.244918]  target_execute_cmd+0x232/0x2c0
> [  240.249124]  ? __local_bh_enable_ip+0x64/0xa0
> [  240.253499]  iscsit_execute_cmd+0x20d/0x270
> [  240.257693]  iscsit_sequence_cmd+0x110/0x190
> [  240.261985]  iscsit_get_rx_pdu+0x360/0xc80
> [  240.267565]  ? iscsi_target_rx_thread+0x54/0xd0
> [  240.273571]  iscsi_target_rx_thread+0x9a/0xd0
> [  240.279413]  kthread+0x113/0x150
> [  240.284120]  ? iscsi_target_tx_thread+0x1e0/0x1e0
> [  240.290297]  ? kthread_create_on_node+0x40/0x40
> [  240.296297]  ret_from_fork+0x2e/0x40
> [  240.301332] Code: 90 90 90 90 90 eb 1e 0f 1f 00 48 89 f8 48
> 89 d1 48
> c1 e9 03 83 e2 07 f3 48 a5 89 d1 f3 a4 c3 66 0f 1f 44 00 00 48
> 89 f8 48
> 89 d1 <f3> a4 c3 0f 1f 80 00 00 00 00 48 89 f8 48 83 fa 20 72 7e
> 40 38
> [  240.321751] RIP: memcpy_erms+0x6/0x10 RSP: ffffc900047dfc68
> [  240.328838] CR2: ffffc9065db85540
> [  240.333667] ---[ end trace b7e5354cfb54d08b ]---
>
> To fix this, just memset all the entry memory before using it, and
> also to be more readable we adjust the bidi code.
>
> Fixed: fe25cc34795(tcmu: Recalculate the tcmu_cmd size to save cmd area
> 		memories)
> Reported-by: Bryant G. Ly <bryantly@linux.vnet.ibm.com>
> Tested-by: Damien Le Moal <damien.lemoal@wdc.com>
> Signed-off-by: Xiubo Li <lixiubo@cmss.chinamobile.com>
> ---
>   drivers/target/target_core_user.c | 12 +++++-------
>   1 file changed, 5 insertions(+), 7 deletions(-)
>
> diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c
> index 2f1fa92..3b25ef3 100644
> --- a/drivers/target/target_core_user.c
> +++ b/drivers/target/target_core_user.c

Nice! This has fixed our long standing issue with not being able to boot with the global data area support on power.

Tested-by: Bryant G. Ly <bryantly@linux.vnet.ibm.com>

-Bryant


--
To unsubscribe from this list: send the line "unsubscribe target-devel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Mike Christie July 11, 2017, 5:21 p.m. UTC | #2
On 07/11/2017 04:59 AM, lixiubo@cmss.chinamobile.com wrote:
> From: Xiubo Li <lixiubo@cmss.chinamobile.com>
> 
> For all the entries allocated from the ring cmd area, the memory is
> something like the stack memory, which will always reserve the old
> data, so the entry->req.iov_bidi_cnt maybe none zero.
> 
> On some environments, the crash could be reporduce very easy and some
> not. The following is the crash core trace:
> 
> [  240.143969] CPU: 0 PID: 1285 Comm: iscsi_trx Not tainted
> 4.12.0-rc1+ #3
> [  240.150607] Hardware name: ASUS All Series/H87-PRO, BIOS 2104
> 10/28/2014
> [  240.157331] task: ffff8807de4f5800 task.stack:
> ffffc900047dc000
> [  240.163270] RIP: 0010:memcpy_erms+0x6/0x10
> [  240.167377] RSP: 0018:ffffc900047dfc68 EFLAGS: 00010202
> [  240.172621] RAX: ffffc9065db85540 RBX: ffff8807f7980000 RCX:
> 0000000000000010
> [  240.179771] RDX: 0000000000000010 RSI: ffff8807de574fe0 RDI:
> ffffc9065db85540
> [  240.186930] RBP: ffffc900047dfd30 R08: ffff8807de41b000 R09:
> 0000000000000000
> [  240.194088] R10: 0000000000000040 R11: ffff8807e9b726f0 R12:
> 00000006565726b0
> [  240.201246] R13: ffffc90007612ea0 R14: 000000065657d540 R15:
> 0000000000000000
> [  240.208397] FS:  0000000000000000(0000)
> GS:ffff88081fa00000(0000)
> knlGS:0000000000000000
> [  240.216510] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
> [  240.222280] CR2: ffffc9065db85540 CR3: 0000000001c0f000 CR4:
> 00000000001406f0
> [  240.229430] Call Trace:
> [  240.231887]  ? tcmu_queue_cmd+0x83c/0xa80
> [  240.235916]  ? target_check_reservation+0xcd/0x6f0
> [  240.240725]  __target_execute_cmd+0x27/0xa0
> [  240.244918]  target_execute_cmd+0x232/0x2c0
> [  240.249124]  ? __local_bh_enable_ip+0x64/0xa0
> [  240.253499]  iscsit_execute_cmd+0x20d/0x270
> [  240.257693]  iscsit_sequence_cmd+0x110/0x190
> [  240.261985]  iscsit_get_rx_pdu+0x360/0xc80
> [  240.267565]  ? iscsi_target_rx_thread+0x54/0xd0
> [  240.273571]  iscsi_target_rx_thread+0x9a/0xd0
> [  240.279413]  kthread+0x113/0x150
> [  240.284120]  ? iscsi_target_tx_thread+0x1e0/0x1e0
> [  240.290297]  ? kthread_create_on_node+0x40/0x40
> [  240.296297]  ret_from_fork+0x2e/0x40
> [  240.301332] Code: 90 90 90 90 90 eb 1e 0f 1f 00 48 89 f8 48
> 89 d1 48
> c1 e9 03 83 e2 07 f3 48 a5 89 d1 f3 a4 c3 66 0f 1f 44 00 00 48
> 89 f8 48
> 89 d1 <f3> a4 c3 0f 1f 80 00 00 00 00 48 89 f8 48 83 fa 20 72 7e
> 40 38
> [  240.321751] RIP: memcpy_erms+0x6/0x10 RSP: ffffc900047dfc68
> [  240.328838] CR2: ffffc9065db85540
> [  240.333667] ---[ end trace b7e5354cfb54d08b ]---
> 
> To fix this, just memset all the entry memory before using it, and
> also to be more readable we adjust the bidi code.
> 
> Fixed: fe25cc34795(tcmu: Recalculate the tcmu_cmd size to save cmd area
> 		memories)
> Reported-by: Bryant G. Ly <bryantly@linux.vnet.ibm.com>
> Tested-by: Damien Le Moal <damien.lemoal@wdc.com>
> Signed-off-by: Xiubo Li <lixiubo@cmss.chinamobile.com>
> ---

Nice. Thanks.

Reviewed-by: Mike Christie <mchristi@redhat.com>

--
To unsubscribe from this list: send the line "unsubscribe target-devel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Nicholas A. Bellinger July 11, 2017, 5:49 p.m. UTC | #3
On Tue, 2017-07-11 at 17:59 +0800, lixiubo@cmss.chinamobile.com wrote:
> From: Xiubo Li <lixiubo@cmss.chinamobile.com>
> 
> For all the entries allocated from the ring cmd area, the memory is
> something like the stack memory, which will always reserve the old
> data, so the entry->req.iov_bidi_cnt maybe none zero.
> 
> On some environments, the crash could be reporduce very easy and some
> not. The following is the crash core trace:
> 
> [  240.143969] CPU: 0 PID: 1285 Comm: iscsi_trx Not tainted
> 4.12.0-rc1+ #3
> [  240.150607] Hardware name: ASUS All Series/H87-PRO, BIOS 2104
> 10/28/2014
> [  240.157331] task: ffff8807de4f5800 task.stack:
> ffffc900047dc000
> [  240.163270] RIP: 0010:memcpy_erms+0x6/0x10
> [  240.167377] RSP: 0018:ffffc900047dfc68 EFLAGS: 00010202
> [  240.172621] RAX: ffffc9065db85540 RBX: ffff8807f7980000 RCX:
> 0000000000000010
> [  240.179771] RDX: 0000000000000010 RSI: ffff8807de574fe0 RDI:
> ffffc9065db85540
> [  240.186930] RBP: ffffc900047dfd30 R08: ffff8807de41b000 R09:
> 0000000000000000
> [  240.194088] R10: 0000000000000040 R11: ffff8807e9b726f0 R12:
> 00000006565726b0
> [  240.201246] R13: ffffc90007612ea0 R14: 000000065657d540 R15:
> 0000000000000000
> [  240.208397] FS:  0000000000000000(0000)
> GS:ffff88081fa00000(0000)
> knlGS:0000000000000000
> [  240.216510] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
> [  240.222280] CR2: ffffc9065db85540 CR3: 0000000001c0f000 CR4:
> 00000000001406f0
> [  240.229430] Call Trace:
> [  240.231887]  ? tcmu_queue_cmd+0x83c/0xa80
> [  240.235916]  ? target_check_reservation+0xcd/0x6f0
> [  240.240725]  __target_execute_cmd+0x27/0xa0
> [  240.244918]  target_execute_cmd+0x232/0x2c0
> [  240.249124]  ? __local_bh_enable_ip+0x64/0xa0
> [  240.253499]  iscsit_execute_cmd+0x20d/0x270
> [  240.257693]  iscsit_sequence_cmd+0x110/0x190
> [  240.261985]  iscsit_get_rx_pdu+0x360/0xc80
> [  240.267565]  ? iscsi_target_rx_thread+0x54/0xd0
> [  240.273571]  iscsi_target_rx_thread+0x9a/0xd0
> [  240.279413]  kthread+0x113/0x150
> [  240.284120]  ? iscsi_target_tx_thread+0x1e0/0x1e0
> [  240.290297]  ? kthread_create_on_node+0x40/0x40
> [  240.296297]  ret_from_fork+0x2e/0x40
> [  240.301332] Code: 90 90 90 90 90 eb 1e 0f 1f 00 48 89 f8 48
> 89 d1 48
> c1 e9 03 83 e2 07 f3 48 a5 89 d1 f3 a4 c3 66 0f 1f 44 00 00 48
> 89 f8 48
> 89 d1 <f3> a4 c3 0f 1f 80 00 00 00 00 48 89 f8 48 83 fa 20 72 7e
> 40 38
> [  240.321751] RIP: memcpy_erms+0x6/0x10 RSP: ffffc900047dfc68
> [  240.328838] CR2: ffffc9065db85540
> [  240.333667] ---[ end trace b7e5354cfb54d08b ]---
> 
> To fix this, just memset all the entry memory before using it, and
> also to be more readable we adjust the bidi code.
> 
> Fixed: fe25cc34795(tcmu: Recalculate the tcmu_cmd size to save cmd area
> 		memories)
> Reported-by: Bryant G. Ly <bryantly@linux.vnet.ibm.com>
> Tested-by: Damien Le Moal <damien.lemoal@wdc.com>
> Signed-off-by: Xiubo Li <lixiubo@cmss.chinamobile.com>
> ---
>  drivers/target/target_core_user.c | 12 +++++-------
>  1 file changed, 5 insertions(+), 7 deletions(-)
> 

Applied, with a CC' to v4.12.y and slightly updated patch subject.

Thanks Xiubo, Bryant, Damien and MNC!

--
To unsubscribe from this list: send the line "unsubscribe target-devel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
diff mbox

Patch

diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c
index 2f1fa92..3b25ef3 100644
--- a/drivers/target/target_core_user.c
+++ b/drivers/target/target_core_user.c
@@ -563,7 +563,7 @@  static int scatter_data_area(struct tcmu_dev *udev,
 			to_offset = get_block_offset_user(udev, dbi,
 					block_remaining);
 			offset = DATA_BLOCK_SIZE - block_remaining;
-			to = (void *)(unsigned long)to + offset;
+			to += offset;
 
 			if (*iov_cnt != 0 &&
 			    to_offset == iov_tail(udev, *iov)) {
@@ -636,7 +636,7 @@  static void gather_data_area(struct tcmu_dev *udev, struct tcmu_cmd *cmd,
 			copy_bytes = min_t(size_t, sg_remaining,
 					block_remaining);
 			offset = DATA_BLOCK_SIZE - block_remaining;
-			from = (void *)(unsigned long)from + offset;
+			from += offset;
 			tcmu_flush_dcache_range(from, copy_bytes);
 			memcpy(to + sg->length - sg_remaining, from,
 					copy_bytes);
@@ -840,10 +840,9 @@  static inline size_t tcmu_cmd_get_cmd_size(struct tcmu_cmd *tcmu_cmd,
 	}
 
 	entry = (void *) mb + CMDR_OFF + cmd_head;
+	memset(entry, 0, command_size);
 	tcmu_hdr_set_op(&entry->hdr.len_op, TCMU_OP_CMD);
 	entry->hdr.cmd_id = tcmu_cmd->cmd_id;
-	entry->hdr.kflags = 0;
-	entry->hdr.uflags = 0;
 
 	/* Handle allocating space from the data area */
 	tcmu_cmd_reset_dbi_cur(tcmu_cmd);
@@ -862,11 +861,10 @@  static inline size_t tcmu_cmd_get_cmd_size(struct tcmu_cmd *tcmu_cmd,
 		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 	}
 	entry->req.iov_cnt = iov_cnt;
-	entry->req.iov_dif_cnt = 0;
 
 	/* Handle BIDI commands */
+	iov_cnt = 0;
 	if (se_cmd->se_cmd_flags & SCF_BIDI) {
-		iov_cnt = 0;
 		iov++;
 		ret = scatter_data_area(udev, tcmu_cmd,
 					se_cmd->t_bidi_data_sg,
@@ -879,8 +877,8 @@  static inline size_t tcmu_cmd_get_cmd_size(struct tcmu_cmd *tcmu_cmd,
 			pr_err("tcmu: alloc and scatter bidi data failed\n");
 			return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 		}
-		entry->req.iov_bidi_cnt = iov_cnt;
 	}
+	entry->req.iov_bidi_cnt = iov_cnt;
 
 	/*
 	 * Recalaulate the command's base size and size according