Skip to contentSkip to conversation

nvme: fix multipath crash caused by flush request when blktrace is enabled

PATCH New Sasha Levin 1 participant 4 messages Jan 3, 2023

Subsystems (3)
lore
Share & tools
lore

Sasha Levin

author maintainer
#0 lore raw

PATCH 1/4 nvme: fix multipath crash caused by flush request when blktrace is enabled

From: Yanjun Zhang <[email protected]>

[ Upstream commit 3659fb5ac29a5e6102bebe494ac789fd47fb78f4 ]

The flush request initialized by blk_kick_flush has NULL bio, and it may be dealt with nvme_end_req during io completion. When blktrace is enabled, nvme_trace_bio_complete with multipath activated trying to access NULL pointer bio from flush request results in the following crash:

[ 2517.831677] BUG: kernel NULL pointer dereference, address: 000000000000001a
[ 2517.835213] #PF: supervisor read access in kernel mode
[ 2517.838724] #PF: error_code(0x0000) - not-present page
[ 2517.842222] PGD 7b2d51067 P4D 0
[ 2517.845684] Oops: 0000 [#1] SMP NOPTI
[ 2517.849125] CPU: 2 PID: 732 Comm: kworker/2:1H Kdump: loaded Tainted: G S                5.15.67-0.cl9.x86_64 #1
[ 2517.852723] Hardware name: XFUSION 2288H V6/BC13MBSBC, BIOS 1.13 07/27/2022
[ 2517.856358] Workqueue: nvme_tcp_wq nvme_tcp_io_work [nvme_tcp]
[ 2517.859993] RIP: 0010:blk_add_trace_bio_complete+0x6/0x30
[ 2517.863628] Code: 1f 44 00 00 48 8b 46 08 31 c9 ba 04 00 10 00 48 8b 80 50 03 00 00 48 8b 78 50 e9 e5 fe ff ff 0f 1f 44 00 00 41 54 49 89 f4 55 <0f> b6 7a 1a 48 89 d5 e8 3e 1c 2b 00 48 89 ee 4c 89 e7 5d 89 c1 ba
[ 2517.871269] RSP: 0018:ff7f6a008d9dbcd0 EFLAGS: 00010286
[ 2517.875081] RAX: ff3d5b4be00b1d50 RBX: 0000000002040002 RCX: ff3d5b0a270f2000
[ 2517.878966] RDX: 0000000000000000 RSI: ff3d5b0b021fb9f8 RDI: 0000000000000000
[ 2517.882849] RBP: ff3d5b0b96a6fa00 R08: 0000000000000001 R09: 0000000000000000
[ 2517.886718] R10: 000000000000000c R11: 000000000000000c R12: ff3d5b0b021fb9f8
[ 2517.890575] R13: 0000000002000000 R14: ff3d5b0b021fb1b0 R15: 0000000000000018
[ 2517.894434] FS:  0000000000000000(0000) GS:ff3d5b42bfc80000(0000) knlGS:0000000000000000
[ 2517.898299] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 2517.902157] CR2: 000000000000001a CR3: 00000004f023e005 CR4: 0000000000771ee0
[ 2517.906053] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[ 2517.909930] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[ 2517.913761] PKRU: 55555554
[ 2517.917558] Call Trace:
[ 2517.921294]  <TASK>
[ 2517.924982]  nvme_complete_rq+0x1c3/0x1e0 [nvme_core]
[ 2517.928715]  nvme_tcp_recv_pdu+0x4d7/0x540 [nvme_tcp]
[ 2517.932442]  nvme_tcp_recv_skb+0x4f/0x240 [nvme_tcp]
[ 2517.936137]  ? nvme_tcp_recv_pdu+0x540/0x540 [nvme_tcp]
[ 2517.939830]  tcp_read_sock+0x9c/0x260
[ 2517.943486]  nvme_tcp_try_recv+0x65/0xa0 [nvme_tcp]
[ 2517.947173]  nvme_tcp_io_work+0x64/0x90 [nvme_tcp]
[ 2517.950834]  process_one_work+0x1e8/0x390
[ 2517.954473]  worker_thread+0x53/0x3c0
[ 2517.958069]  ? process_one_work+0x390/0x390
[ 2517.961655]  kthread+0x10c/0x130
[ 2517.965211]  ? set_kthread_struct+0x40/0x40
[ 2517.968760]  ret_from_fork+0x1f/0x30
[ 2517.972285]  </TASK>

To avoid this situation, add a NULL check for req->bio before calling trace_block_bio_complete.

---
 drivers/nvme/host/nvme.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/nvme/host/nvme.h +1 -1
index 7f52b2b179b8..39ca48babbe8 100644
@@ -799,7 +799,7 @@ static inline void nvme_trace_bio_complete(struct request *req)
 {
 	struct nvme_ns *ns = req->q->queuedata;
 
-	if (req->cmd_flags & REQ_NVME_MPATH)
+	if ((req->cmd_flags & REQ_NVME_MPATH) && req->bio)
 		trace_block_bio_complete(ns->head->disk->queue, req->bio);
 }
 
Signature · 1 line
2.35.1
author maintainer
#1 lore raw

PATCH 2/4 io_uring: check for valid register opcode earlier

From: Jens Axboe <[email protected]>

[ Upstream commit 343190841a1f22b96996d9f8cfab902a4d1bfd0e ]

We only check the register opcode value inside the restricted ring section, move it into the main io_uring_register() function instead and check it up front.

---
 io_uring/io_uring.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)
io_uring/io_uring.c +3 -2
index eebbe8a6da0c..52a08632326a 100644
@@ -10895,8 +10895,6 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode,
 		return -ENXIO;
 
 	if (ctx->restricted) {
-		if (opcode >= IORING_REGISTER_LAST)
-			return -EINVAL;
 		opcode = array_index_nospec(opcode, IORING_REGISTER_LAST);
 		if (!test_bit(opcode, ctx->restrictions.register_op))
 			return -EACCES;
@@ -11028,6 +11026,9 @@ SYSCALL_DEFINE4(io_uring_register, unsigned int, fd, unsigned int, opcode,
 	long ret = -EBADF;
 	struct fd f;
 
+	if (opcode >= IORING_REGISTER_LAST)
+		return -EINVAL;
+
 	f = fdget(fd);
 	if (!f.file)
 		return -EBADF;
Signature · 1 line
2.35.1
author maintainer
#3 lore raw

PATCH 4/4 nvme: also return I/O command effects from nvme_command_effects

In reply to Sasha Levin

From: Christoph Hellwig <[email protected]>

[ Upstream commit 831ed60c2aca2d7c517b2da22897a90224a97d27 ]

To be able to use the Commands Supported and Effects Log for allowing unprivileged passtrough, it needs to be corretly reported for I/O commands as well. Return the I/O command effects from nvme_command_effects, and also add a default list of effects for the NVM command set. For other command sets, the Commands Supported and Effects log is required to be present already.

---
 drivers/nvme/host/core.c | 32 ++++++++++++++++++++++++++------
 1 file changed, 26 insertions(+), 6 deletions(-)
drivers/nvme/host/core.c +26 -6
index 2d5b5e0fb66a..672f53d5651a 100644
@@ -1113,6 +1113,18 @@ static u32 nvme_known_admin_effects(u8 opcode)
 	return 0;
 }
 
+static u32 nvme_known_nvm_effects(u8 opcode)
+{
+	switch (opcode) {
+	case nvme_cmd_write:
+	case nvme_cmd_write_zeroes:
+	case nvme_cmd_write_uncor:
+		 return NVME_CMD_EFFECTS_LBCC;
+	default:
+		return 0;
+	}
+}
+
 u32 nvme_command_effects(struct nvme_ctrl *ctrl, struct nvme_ns *ns, u8 opcode)
 {
 	u32 effects = 0;
@@ -1120,16 +1132,24 @@ u32 nvme_command_effects(struct nvme_ctrl *ctrl, struct nvme_ns *ns, u8 opcode)
 	if (ns) {
 		if (ns->head->effects)
 			effects = le32_to_cpu(ns->head->effects->iocs[opcode]);
+		if (ns->head->ids.csi == NVME_CAP_CSS_NVM)
+			effects |= nvme_known_nvm_effects(opcode);
 		if (effects & ~(NVME_CMD_EFFECTS_CSUPP | NVME_CMD_EFFECTS_LBCC))
 			dev_warn_once(ctrl->device,
-				"IO command:%02x has unhandled effects:%08x\n",
+				"IO command:%02x has unusual effects:%08x\n",
 				opcode, effects);
-		return 0;
-	}
 
-	if (ctrl->effects)
-		effects = le32_to_cpu(ctrl->effects->acs[opcode]);
-	effects |= nvme_known_admin_effects(opcode);
+		/*
+		 * NVME_CMD_EFFECTS_CSE_MASK causes a freeze all I/O queues,
+		 * which would deadlock when done on an I/O command.  Note that
+		 * We already warn about an unusual effect above.
+		 */
+		effects &= ~NVME_CMD_EFFECTS_CSE_MASK;
+	} else {
+		if (ctrl->effects)
+			effects = le32_to_cpu(ctrl->effects->acs[opcode]);
+		effects |= nvme_known_admin_effects(opcode);
+	}
 
 	return effects;
 }
Signature · 1 line
2.35.1
author maintainer
#2 lore raw

PATCH 3/4 nvmet: use NVME_CMD_EFFECTS_CSUPP instead of open coding it

In reply to Sasha Levin

From: Christoph Hellwig <[email protected]>

[ Upstream commit 61f37154c599cf9f2f84dcbd9be842f8645a7099 ]

Use NVME_CMD_EFFECTS_CSUPP instead of open coding it and assign a single value to multiple array entries instead of repeated assignments.

---
 drivers/nvme/target/admin-cmd.c | 35 ++++++++++++++++++---------------
 1 file changed, 19 insertions(+), 16 deletions(-)
drivers/nvme/target/admin-cmd.c +19 -16
index 52bb262d267a..bf78c58ed41d 100644
@@ -164,26 +164,29 @@ static void nvmet_execute_get_log_page_smart(struct nvmet_req *req)
 
 static void nvmet_get_cmd_effects_nvm(struct nvme_effects_log *log)
 {
-	log->acs[nvme_admin_get_log_page]	= cpu_to_le32(1 << 0);
-	log->acs[nvme_admin_identify]		= cpu_to_le32(1 << 0);
-	log->acs[nvme_admin_abort_cmd]		= cpu_to_le32(1 << 0);
-	log->acs[nvme_admin_set_features]	= cpu_to_le32(1 << 0);
-	log->acs[nvme_admin_get_features]	= cpu_to_le32(1 << 0);
-	log->acs[nvme_admin_async_event]	= cpu_to_le32(1 << 0);
-	log->acs[nvme_admin_keep_alive]		= cpu_to_le32(1 << 0);
-
-	log->iocs[nvme_cmd_read]		= cpu_to_le32(1 << 0);
-	log->iocs[nvme_cmd_write]		= cpu_to_le32(1 << 0);
-	log->iocs[nvme_cmd_flush]		= cpu_to_le32(1 << 0);
-	log->iocs[nvme_cmd_dsm]			= cpu_to_le32(1 << 0);
-	log->iocs[nvme_cmd_write_zeroes]	= cpu_to_le32(1 << 0);
+	log->acs[nvme_admin_get_log_page] =
+	log->acs[nvme_admin_identify] =
+	log->acs[nvme_admin_abort_cmd] =
+	log->acs[nvme_admin_set_features] =
+	log->acs[nvme_admin_get_features] =
+	log->acs[nvme_admin_async_event] =
+	log->acs[nvme_admin_keep_alive] =
+		cpu_to_le32(NVME_CMD_EFFECTS_CSUPP);
+
+	log->iocs[nvme_cmd_read] =
+	log->iocs[nvme_cmd_write] =
+	log->iocs[nvme_cmd_flush] =
+	log->iocs[nvme_cmd_dsm]	=
+	log->iocs[nvme_cmd_write_zeroes] =
+		cpu_to_le32(NVME_CMD_EFFECTS_CSUPP);
 }
 
 static void nvmet_get_cmd_effects_zns(struct nvme_effects_log *log)
 {
-	log->iocs[nvme_cmd_zone_append]		= cpu_to_le32(1 << 0);
-	log->iocs[nvme_cmd_zone_mgmt_send]	= cpu_to_le32(1 << 0);
-	log->iocs[nvme_cmd_zone_mgmt_recv]	= cpu_to_le32(1 << 0);
+	log->iocs[nvme_cmd_zone_append] =
+	log->iocs[nvme_cmd_zone_mgmt_send] =
+	log->iocs[nvme_cmd_zone_mgmt_recv] =
+		cpu_to_le32(NVME_CMD_EFFECTS_CSUPP);
 }
 
 static void nvmet_execute_get_log_cmd_effects_ns(struct nvmet_req *req)
Signature · 1 line
2.35.1