Merge tag 'block-6.2-2022-12-29' of git://git.kernel.dk/linux

Pull block fixes from Jens Axboe:
 "Mostly just NVMe, but also a single fixup for BFQ for a regression
  that happened during the merge window. In detail:

   - NVMe pull requests via Christoph:
      - Fix doorbell buffer value endianness (Klaus Jensen)
      - Fix Linux vs NVMe page size mismatch (Keith Busch)
      - Fix a potential use memory access beyong the allocation limit
        (Keith Busch)
      - Fix a multipath vs blktrace NULL pointer dereference (Yanjun
        Zhang)
      - Fix various problems in handling the Command Supported and
        Effects log (Christoph Hellwig)
      - Don't allow unprivileged passthrough of commands that don't
        transfer data but modify logical block content (Christoph
        Hellwig)
      - Add a features and quirks policy document (Christoph Hellwig)
      - Fix some really nasty code that was correct but made smatch
        complain (Sagi Grimberg)

   - Use-after-free regression in BFQ from this merge window (Yu)"

* tag 'block-6.2-2022-12-29' of git://git.kernel.dk/linux:
  nvme-auth: fix smatch warning complaints
  nvme: consult the CSE log page for unprivileged passthrough
  nvme: also return I/O command effects from nvme_command_effects
  nvmet: don't defer passthrough commands with trivial effects to the workqueue
  nvmet: set the LBCC bit for commands that modify data
  nvmet: use NVME_CMD_EFFECTS_CSUPP instead of open coding it
  nvme: fix the NVME_CMD_EFFECTS_CSE_MASK definition
  docs, nvme: add a feature and quirk policy document
  nvme-pci: update sqsize when adjusting the queue depth
  nvme: fix setting the queue depth in nvme_alloc_io_tag_set
  block, bfq: fix uaf for bfqq in bfq_exit_icq_bfqq
  nvme: fix multipath crash caused by flush request when blktrace is enabled
  nvme-pci: fix page size checks
  nvme-pci: fix mempool alloc size
  nvme-pci: fix doorbell buffer value endianness

7 files changed, 103 insertions, 57 deletions

diff --git a/drivers/nvme/host/auth.c b/drivers/nvme/host/auth.c
index bb0abbe4491c..4424f53a8a0a 100644
--- a/drivers/nvme/host/auth.c
+++ b/drivers/nvme/host/auth.c
@@ -953,7 +953,7 @@ int nvme_auth_init_ctrl(struct nvme_ctrl *ctrl)
 		goto err_free_dhchap_secret;
 
 	if (!ctrl->opts->dhchap_secret && !ctrl->opts->dhchap_ctrl_secret)
-		return ret;
+		return 0;
 
 	ctrl->dhchap_ctxs = kvcalloc(ctrl_max_dhchaps(ctrl),
 				sizeof(*chap), GFP_KERNEL);
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 95c488ea91c3..7be562a4e1aa 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -1074,6 +1074,18 @@ 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;
@@ -1081,16 +1093,24 @@ 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;
 }
@@ -4926,7 +4946,7 @@ int nvme_alloc_io_tag_set(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set,
 
 	memset(set, 0, sizeof(*set));
 	set->ops = ops;
-	set->queue_depth = ctrl->sqsize + 1;
+	set->queue_depth = min_t(unsigned, ctrl->sqsize, BLK_MQ_MAX_DEPTH - 1);
 	/*
 	 * Some Apple controllers requires tags to be unique across admin and
 	 * the (only) I/O queue, so reserve the first 32 tags of the I/O queue.
diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c
index 9ddda571f046..a8639919237e 100644
--- a/drivers/nvme/host/ioctl.c
+++ b/drivers/nvme/host/ioctl.c
@@ -11,6 +11,8 @@
 static bool nvme_cmd_allowed(struct nvme_ns *ns, struct nvme_command *c,
 		fmode_t mode)
 {
+	u32 effects;
+
 	if (capable(CAP_SYS_ADMIN))
 		return true;
 
@@ -43,11 +45,29 @@ static bool nvme_cmd_allowed(struct nvme_ns *ns, struct nvme_command *c,
 	}
 
 	/*
-	 * Only allow I/O commands that transfer data to the controller if the
-	 * special file is open for writing, but always allow I/O commands that
-	 * transfer data from the controller.
+	 * Check if the controller provides a Commands Supported and Effects log
+	 * and marks this command as supported.  If not reject unprivileged
+	 * passthrough.
+	 */
+	effects = nvme_command_effects(ns->ctrl, ns, c->common.opcode);
+	if (!(effects & NVME_CMD_EFFECTS_CSUPP))
+		return false;
+
+	/*
+	 * Don't allow passthrough for command that have intrusive (or unknown)
+	 * effects.
+	 */
+	if (effects & ~(NVME_CMD_EFFECTS_CSUPP | NVME_CMD_EFFECTS_LBCC |
+			NVME_CMD_EFFECTS_UUID_SEL |
+			NVME_CMD_EFFECTS_SCOPE_MASK))
+		return false;
+
+	/*
+	 * Only allow I/O commands that transfer data to the controller or that
+	 * change the logical block contents if the file descriptor is open for
+	 * writing.
 	 */
-	if (nvme_is_write(c))
+	if (nvme_is_write(c) || (effects & NVME_CMD_EFFECTS_LBCC))
 		return mode & FMODE_WRITE;
 	return true;
 }
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 6bbb73ef8b25..424c8a467a0c 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -893,7 +893,7 @@ 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);
 }
 
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index f0f8027644bb..b13baccedb4a 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -36,7 +36,7 @@
 #define SQ_SIZE(q)	((q)->q_depth << (q)->sqes)
 #define CQ_SIZE(q)	((q)->q_depth * sizeof(struct nvme_completion))
 
-#define SGES_PER_PAGE	(PAGE_SIZE / sizeof(struct nvme_sgl_desc))
+#define SGES_PER_PAGE	(NVME_CTRL_PAGE_SIZE / sizeof(struct nvme_sgl_desc))
 
 /*
  * These can be higher, but we need to ensure that any command doesn't
@@ -144,9 +144,9 @@ struct nvme_dev {
 	mempool_t *iod_mempool;
 
 	/* shadow doorbell buffer support: */
-	u32 *dbbuf_dbs;
+	__le32 *dbbuf_dbs;
 	dma_addr_t dbbuf_dbs_dma_addr;
-	u32 *dbbuf_eis;
+	__le32 *dbbuf_eis;
 	dma_addr_t dbbuf_eis_dma_addr;
 
 	/* host memory buffer support: */
@@ -208,10 +208,10 @@ struct nvme_queue {
 #define NVMEQ_SQ_CMB		1
 #define NVMEQ_DELETE_ERROR	2
 #define NVMEQ_POLLED		3
-	u32 *dbbuf_sq_db;
-	u32 *dbbuf_cq_db;
-	u32 *dbbuf_sq_ei;
-	u32 *dbbuf_cq_ei;
+	__le32 *dbbuf_sq_db;
+	__le32 *dbbuf_cq_db;
+	__le32 *dbbuf_sq_ei;
+	__le32 *dbbuf_cq_ei;
 	struct completion delete_done;
 };
 
@@ -343,11 +343,11 @@ static inline int nvme_dbbuf_need_event(u16 event_idx, u16 new_idx, u16 old)
 }
 
 /* Update dbbuf and return true if an MMIO is required */
-static bool nvme_dbbuf_update_and_check_event(u16 value, u32 *dbbuf_db,
-					      volatile u32 *dbbuf_ei)
+static bool nvme_dbbuf_update_and_check_event(u16 value, __le32 *dbbuf_db,
+					      volatile __le32 *dbbuf_ei)
 {
 	if (dbbuf_db) {
-		u16 old_value;
+		u16 old_value, event_idx;
 
 		/*
 		 * Ensure that the queue is written before updating
@@ -355,8 +355,8 @@ static bool nvme_dbbuf_update_and_check_event(u16 value, u32 *dbbuf_db,
 		 */
 		wmb();
 
-		old_value = *dbbuf_db;
-		*dbbuf_db = value;
+		old_value = le32_to_cpu(*dbbuf_db);
+		*dbbuf_db = cpu_to_le32(value);
 
 		/*
 		 * Ensure that the doorbell is updated before reading the event
@@ -366,7 +366,8 @@ static bool nvme_dbbuf_update_and_check_event(u16 value, u32 *dbbuf_db,
 		 */
 		mb();
 
-		if (!nvme_dbbuf_need_event(*dbbuf_ei, value, old_value))
+		event_idx = le32_to_cpu(*dbbuf_ei);
+		if (!nvme_dbbuf_need_event(event_idx, value, old_value))
 			return false;
 	}
 
@@ -380,9 +381,9 @@ static bool nvme_dbbuf_update_and_check_event(u16 value, u32 *dbbuf_db,
  */
 static int nvme_pci_npages_prp(void)
 {
-	unsigned nprps = DIV_ROUND_UP(NVME_MAX_KB_SZ + NVME_CTRL_PAGE_SIZE,
-				      NVME_CTRL_PAGE_SIZE);
-	return DIV_ROUND_UP(8 * nprps, PAGE_SIZE - 8);
+	unsigned max_bytes = (NVME_MAX_KB_SZ * 1024) + NVME_CTRL_PAGE_SIZE;
+	unsigned nprps = DIV_ROUND_UP(max_bytes, NVME_CTRL_PAGE_SIZE);
+	return DIV_ROUND_UP(8 * nprps, NVME_CTRL_PAGE_SIZE - 8);
 }
 
 /*
@@ -392,7 +393,7 @@ static int nvme_pci_npages_prp(void)
 static int nvme_pci_npages_sgl(void)
 {
 	return DIV_ROUND_UP(NVME_MAX_SEGS * sizeof(struct nvme_sgl_desc),
-			PAGE_SIZE);
+			NVME_CTRL_PAGE_SIZE);
 }
 
 static int nvme_admin_init_hctx(struct blk_mq_hw_ctx *hctx, void *data,
@@ -708,7 +709,7 @@ static void nvme_pci_sgl_set_seg(struct nvme_sgl_desc *sge,
 		sge->length = cpu_to_le32(entries * sizeof(*sge));
 		sge->type = NVME_SGL_FMT_LAST_SEG_DESC << 4;
 	} else {
-		sge->length = cpu_to_le32(PAGE_SIZE);
+		sge->length = cpu_to_le32(NVME_CTRL_PAGE_SIZE);
 		sge->type = NVME_SGL_FMT_SEG_DESC << 4;
 	}
 }
@@ -2332,10 +2333,12 @@ static int nvme_setup_io_queues(struct nvme_dev *dev)
 	if (dev->cmb_use_sqes) {
 		result = nvme_cmb_qdepth(dev, nr_io_queues,
 				sizeof(struct nvme_command));
-		if (result > 0)
+		if (result > 0) {
 			dev->q_depth = result;
-		else
+			dev->ctrl.sqsize = result - 1;
+		} else {
 			dev->cmb_use_sqes = false;
+		}
 	}
 
 	do {
@@ -2536,7 +2539,6 @@ static int nvme_pci_enable(struct nvme_dev *dev)
 
 	dev->q_depth = min_t(u32, NVME_CAP_MQES(dev->ctrl.cap) + 1,
 				io_queue_depth);
-	dev->ctrl.sqsize = dev->q_depth - 1; /* 0's based queue depth */
 	dev->db_stride = 1 << NVME_CAP_STRIDE(dev->ctrl.cap);
 	dev->dbs = dev->bar + 4096;
 
@@ -2577,7 +2579,7 @@ static int nvme_pci_enable(struct nvme_dev *dev)
 		dev_warn(dev->ctrl.device, "IO queue depth clamped to %d\n",
 			 dev->q_depth);
 	}
-
+	dev->ctrl.sqsize = dev->q_depth - 1; /* 0's based queue depth */
 
 	nvme_map_cmb(dev);
 
diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c
index 53a004ea320c..6a54ed6fb121 100644
--- a/drivers/nvme/target/admin-cmd.c
+++ b/drivers/nvme/target/admin-cmd.c
@@ -164,26 +164,31 @@ out:
 
 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_flush] =
+	log->iocs[nvme_cmd_dsm]	=
+		cpu_to_le32(NVME_CMD_EFFECTS_CSUPP);
+	log->iocs[nvme_cmd_write] =
+	log->iocs[nvme_cmd_write_zeroes] =
+		cpu_to_le32(NVME_CMD_EFFECTS_CSUPP | NVME_CMD_EFFECTS_LBCC);
 }
 
 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] =
+		cpu_to_le32(NVME_CMD_EFFECTS_CSUPP | NVME_CMD_EFFECTS_LBCC);
+	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)
diff --git a/drivers/nvme/target/passthru.c b/drivers/nvme/target/passthru.c
index 79af5140af8b..adc0958755d6 100644
--- a/drivers/nvme/target/passthru.c
+++ b/drivers/nvme/target/passthru.c
@@ -334,14 +334,13 @@ static void nvmet_passthru_execute_cmd(struct nvmet_req *req)
 	}
 
 	/*
-	 * If there are effects for the command we are about to execute, or
-	 * an end_req function we need to use nvme_execute_passthru_rq()
-	 * synchronously in a work item seeing the end_req function and
-	 * nvme_passthru_end() can't be called in the request done callback
-	 * which is typically in interrupt context.
+	 * If a command needs post-execution fixups, or there are any
+	 * non-trivial effects, make sure to execute the command synchronously
+	 * in a workqueue so that nvme_passthru_end gets called.
 	 */
 	effects = nvme_command_effects(ctrl, ns, req->cmd->common.opcode);
-	if (req->p.use_workqueue || effects) {
+	if (req->p.use_workqueue ||
+	    (effects & ~(NVME_CMD_EFFECTS_CSUPP | NVME_CMD_EFFECTS_LBCC))) {
 		INIT_WORK(&req->p.work, nvmet_passthru_execute_cmd_work);
 		req->p.rq = rq;
 		queue_work(nvmet_wq, &req->p.work);