Merge tag 'block-6.15-20250502' of git://git.kernel.dk/linux

Pull block fixes from Jens Axboe:

 - NVMe pull request via Christoph:
     - fix queue unquiesce check on PCI slot_reset (Keith Busch)
     - fix premature queue removal and I/O failover in nvme-tcp (Michael
       Liang)
     - don't restore null sk_state_change (Alistair Francis)
     - select CONFIG_TLS where needed (Alistair Francis)
     - always free derived key data (Hannes Reinecke)
     - more quirks (Wentao Guan)

 - ublk zero copy fix

 - ublk selftest fix for UBLK_F_NEED_GET_DATA

* tag 'block-6.15-20250502' of git://git.kernel.dk/linux:
  nvmet-auth: always free derived key data
  nvmet-tcp: don't restore null sk_state_change
  nvmet-tcp: select CONFIG_TLS from CONFIG_NVME_TARGET_TCP_TLS
  nvme-tcp: select CONFIG_TLS from CONFIG_NVME_TCP_TLS
  nvme-tcp: fix premature queue removal and I/O failover
  nvme-pci: add quirks for WDC Blue SN550 15b7:5009
  nvme-pci: add quirks for device 126f:1001
  nvme-pci: fix queue unquiesce check on slot_reset
  ublk: remove the check of ublk_need_req_ref() from __ublk_check_and_get_req
  ublk: enhance check for register/unregister io buffer command
  ublk: decouple zero copy from user copy
  selftests: ublk: fix UBLK_F_NEED_GET_DATA

12 files changed, 133 insertions, 36 deletions

diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c
index 40f971a66d3e..f9032076bc06 100644
--- a/drivers/block/ublk_drv.c
+++ b/drivers/block/ublk_drv.c
@@ -201,15 +201,10 @@ struct ublk_params_header {
 static void ublk_stop_dev_unlocked(struct ublk_device *ub);
 static void ublk_abort_queue(struct ublk_device *ub, struct ublk_queue *ubq);
 static inline struct request *__ublk_check_and_get_req(struct ublk_device *ub,
-		struct ublk_queue *ubq, int tag, size_t offset);
+		const struct ublk_queue *ubq, int tag, size_t offset);
 static inline unsigned int ublk_req_build_flags(struct request *req);
 static inline struct ublksrv_io_desc *ublk_get_iod(struct ublk_queue *ubq,
 						   int tag);
-static inline bool ublk_dev_is_user_copy(const struct ublk_device *ub)
-{
-	return ub->dev_info.flags & (UBLK_F_USER_COPY | UBLK_F_SUPPORT_ZERO_COPY);
-}
-
 static inline bool ublk_dev_is_zoned(const struct ublk_device *ub)
 {
 	return ub->dev_info.flags & UBLK_F_ZONED;
@@ -609,14 +604,19 @@ static void ublk_apply_params(struct ublk_device *ub)
 		ublk_dev_param_zoned_apply(ub);
 }
 
+static inline bool ublk_support_zero_copy(const struct ublk_queue *ubq)
+{
+	return ubq->flags & UBLK_F_SUPPORT_ZERO_COPY;
+}
+
 static inline bool ublk_support_user_copy(const struct ublk_queue *ubq)
 {
-	return ubq->flags & (UBLK_F_USER_COPY | UBLK_F_SUPPORT_ZERO_COPY);
+	return ubq->flags & UBLK_F_USER_COPY;
 }
 
 static inline bool ublk_need_map_io(const struct ublk_queue *ubq)
 {
-	return !ublk_support_user_copy(ubq);
+	return !ublk_support_user_copy(ubq) && !ublk_support_zero_copy(ubq);
 }
 
 static inline bool ublk_need_req_ref(const struct ublk_queue *ubq)
@@ -624,8 +624,11 @@ static inline bool ublk_need_req_ref(const struct ublk_queue *ubq)
 	/*
 	 * read()/write() is involved in user copy, so request reference
 	 * has to be grabbed
+	 *
+	 * for zero copy, request buffer need to be registered to io_uring
+	 * buffer table, so reference is needed
 	 */
-	return ublk_support_user_copy(ubq);
+	return ublk_support_user_copy(ubq) || ublk_support_zero_copy(ubq);
 }
 
 static inline void ublk_init_req_ref(const struct ublk_queue *ubq,
@@ -1946,13 +1949,20 @@ static void ublk_io_release(void *priv)
 }
 
 static int ublk_register_io_buf(struct io_uring_cmd *cmd,
-				struct ublk_queue *ubq, unsigned int tag,
+				const struct ublk_queue *ubq, unsigned int tag,
 				unsigned int index, unsigned int issue_flags)
 {
 	struct ublk_device *ub = cmd->file->private_data;
+	const struct ublk_io *io = &ubq->ios[tag];
 	struct request *req;
 	int ret;
 
+	if (!ublk_support_zero_copy(ubq))
+		return -EINVAL;
+
+	if (!(io->flags & UBLK_IO_FLAG_OWNED_BY_SRV))
+		return -EINVAL;
+
 	req = __ublk_check_and_get_req(ub, ubq, tag, 0);
 	if (!req)
 		return -EINVAL;
@@ -1968,8 +1978,17 @@ static int ublk_register_io_buf(struct io_uring_cmd *cmd,
 }
 
 static int ublk_unregister_io_buf(struct io_uring_cmd *cmd,
+				  const struct ublk_queue *ubq, unsigned int tag,
 				  unsigned int index, unsigned int issue_flags)
 {
+	const struct ublk_io *io = &ubq->ios[tag];
+
+	if (!ublk_support_zero_copy(ubq))
+		return -EINVAL;
+
+	if (!(io->flags & UBLK_IO_FLAG_OWNED_BY_SRV))
+		return -EINVAL;
+
 	return io_buffer_unregister_bvec(cmd, index, issue_flags);
 }
 
@@ -2073,7 +2092,7 @@ static int __ublk_ch_uring_cmd(struct io_uring_cmd *cmd,
 	case UBLK_IO_REGISTER_IO_BUF:
 		return ublk_register_io_buf(cmd, ubq, tag, ub_cmd->addr, issue_flags);
 	case UBLK_IO_UNREGISTER_IO_BUF:
-		return ublk_unregister_io_buf(cmd, ub_cmd->addr, issue_flags);
+		return ublk_unregister_io_buf(cmd, ubq, tag, ub_cmd->addr, issue_flags);
 	case UBLK_IO_FETCH_REQ:
 		ret = ublk_fetch(cmd, ubq, io, ub_cmd->addr);
 		if (ret)
@@ -2125,13 +2144,10 @@ static int __ublk_ch_uring_cmd(struct io_uring_cmd *cmd,
 }
 
 static inline struct request *__ublk_check_and_get_req(struct ublk_device *ub,
-		struct ublk_queue *ubq, int tag, size_t offset)
+		const struct ublk_queue *ubq, int tag, size_t offset)
 {
 	struct request *req;
 
-	if (!ublk_need_req_ref(ubq))
-		return NULL;
-
 	req = blk_mq_tag_to_rq(ub->tag_set.tags[ubq->q_id], tag);
 	if (!req)
 		return NULL;
@@ -2245,6 +2261,9 @@ static struct request *ublk_check_and_get_req(struct kiocb *iocb,
 	if (!ubq)
 		return ERR_PTR(-EINVAL);
 
+	if (!ublk_support_user_copy(ubq))
+		return ERR_PTR(-EACCES);
+
 	if (tag >= ubq->q_depth)
 		return ERR_PTR(-EINVAL);
 
@@ -2783,13 +2802,18 @@ static int ublk_ctrl_add_dev(const struct ublksrv_ctrl_cmd *header)
 	ub->dev_info.flags |= UBLK_F_CMD_IOCTL_ENCODE |
 		UBLK_F_URING_CMD_COMP_IN_TASK;
 
-	/* GET_DATA isn't needed any more with USER_COPY */
-	if (ublk_dev_is_user_copy(ub))
+	/* GET_DATA isn't needed any more with USER_COPY or ZERO COPY */
+	if (ub->dev_info.flags & (UBLK_F_USER_COPY | UBLK_F_SUPPORT_ZERO_COPY))
 		ub->dev_info.flags &= ~UBLK_F_NEED_GET_DATA;
 
-	/* Zoned storage support requires user copy feature */
+	/*
+	 * Zoned storage support requires reuse `ublksrv_io_cmd->addr` for
+	 * returning write_append_lba, which is only allowed in case of
+	 * user copy or zero copy
+	 */
 	if (ublk_dev_is_zoned(ub) &&
-	    (!IS_ENABLED(CONFIG_BLK_DEV_ZONED) || !ublk_dev_is_user_copy(ub))) {
+	    (!IS_ENABLED(CONFIG_BLK_DEV_ZONED) || !(ub->dev_info.flags &
+	     (UBLK_F_USER_COPY | UBLK_F_SUPPORT_ZERO_COPY)))) {
 		ret = -EINVAL;
 		goto out_free_dev_number;
 	}
diff --git a/drivers/nvme/host/Kconfig b/drivers/nvme/host/Kconfig
index d47dfa80fb95..4d64b6935bb9 100644
--- a/drivers/nvme/host/Kconfig
+++ b/drivers/nvme/host/Kconfig
@@ -102,6 +102,7 @@ config NVME_TCP_TLS
 	depends on NVME_TCP
 	select NET_HANDSHAKE
 	select KEYS
+	select TLS
 	help
 	  Enables TLS encryption for NVMe TCP using the netlink handshake API.
 
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index b178d52eac1b..2e30e9be7408 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -3575,7 +3575,7 @@ static pci_ers_result_t nvme_slot_reset(struct pci_dev *pdev)
 
 	dev_info(dev->ctrl.device, "restart after slot reset\n");
 	pci_restore_state(pdev);
-	if (!nvme_try_sched_reset(&dev->ctrl))
+	if (nvme_try_sched_reset(&dev->ctrl))
 		nvme_unquiesce_io_queues(&dev->ctrl);
 	return PCI_ERS_RESULT_RECOVERED;
 }
@@ -3623,6 +3623,9 @@ static const struct pci_device_id nvme_id_table[] = {
 		.driver_data = NVME_QUIRK_BOGUS_NID, },
 	{ PCI_DEVICE(0x1217, 0x8760), /* O2 Micro 64GB Steam Deck */
 		.driver_data = NVME_QUIRK_DMAPOOL_ALIGN_512, },
+	{ PCI_DEVICE(0x126f, 0x1001),	/* Silicon Motion generic */
+		.driver_data = NVME_QUIRK_NO_DEEPEST_PS |
+				NVME_QUIRK_IGNORE_DEV_SUBNQN, },
 	{ PCI_DEVICE(0x126f, 0x2262),	/* Silicon Motion generic */
 		.driver_data = NVME_QUIRK_NO_DEEPEST_PS |
 				NVME_QUIRK_BOGUS_NID, },
@@ -3646,6 +3649,9 @@ static const struct pci_device_id nvme_id_table[] = {
 				NVME_QUIRK_IGNORE_DEV_SUBNQN, },
 	{ PCI_DEVICE(0x15b7, 0x5008),   /* Sandisk SN530 */
 		.driver_data = NVME_QUIRK_BROKEN_MSI },
+	{ PCI_DEVICE(0x15b7, 0x5009),   /* Sandisk SN550 */
+		.driver_data = NVME_QUIRK_BROKEN_MSI |
+				NVME_QUIRK_NO_DEEPEST_PS },
 	{ PCI_DEVICE(0x1987, 0x5012),	/* Phison E12 */
 		.driver_data = NVME_QUIRK_BOGUS_NID, },
 	{ PCI_DEVICE(0x1987, 0x5016),	/* Phison E16 */
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 72d260201d8c..aba365f97cf6 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -1946,7 +1946,7 @@ static void __nvme_tcp_stop_queue(struct nvme_tcp_queue *queue)
 	cancel_work_sync(&queue->io_work);
 }
 
-static void nvme_tcp_stop_queue(struct nvme_ctrl *nctrl, int qid)
+static void nvme_tcp_stop_queue_nowait(struct nvme_ctrl *nctrl, int qid)
 {
 	struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(nctrl);
 	struct nvme_tcp_queue *queue = &ctrl->queues[qid];
@@ -1965,6 +1965,31 @@ static void nvme_tcp_stop_queue(struct nvme_ctrl *nctrl, int qid)
 	mutex_unlock(&queue->queue_lock);
 }
 
+static void nvme_tcp_wait_queue(struct nvme_ctrl *nctrl, int qid)
+{
+	struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(nctrl);
+	struct nvme_tcp_queue *queue = &ctrl->queues[qid];
+	int timeout = 100;
+
+	while (timeout > 0) {
+		if (!test_bit(NVME_TCP_Q_ALLOCATED, &queue->flags) ||
+		    !sk_wmem_alloc_get(queue->sock->sk))
+			return;
+		msleep(2);
+		timeout -= 2;
+	}
+	dev_warn(nctrl->device,
+		 "qid %d: timeout draining sock wmem allocation expired\n",
+		 qid);
+}
+
+static void nvme_tcp_stop_queue(struct nvme_ctrl *nctrl, int qid)
+{
+	nvme_tcp_stop_queue_nowait(nctrl, qid);
+	nvme_tcp_wait_queue(nctrl, qid);
+}
+
+
 static void nvme_tcp_setup_sock_ops(struct nvme_tcp_queue *queue)
 {
 	write_lock_bh(&queue->sock->sk->sk_callback_lock);
@@ -2032,7 +2057,9 @@ static void nvme_tcp_stop_io_queues(struct nvme_ctrl *ctrl)
 	int i;
 
 	for (i = 1; i < ctrl->queue_count; i++)
-		nvme_tcp_stop_queue(ctrl, i);
+		nvme_tcp_stop_queue_nowait(ctrl, i);
+	for (i = 1; i < ctrl->queue_count; i++)
+		nvme_tcp_wait_queue(ctrl, i);
 }
 
 static int nvme_tcp_start_io_queues(struct nvme_ctrl *ctrl,
diff --git a/drivers/nvme/target/Kconfig b/drivers/nvme/target/Kconfig
index fb7446d6d682..4c253b433bf7 100644
--- a/drivers/nvme/target/Kconfig
+++ b/drivers/nvme/target/Kconfig
@@ -98,6 +98,7 @@ config NVME_TARGET_TCP_TLS
 	bool "NVMe over Fabrics TCP target TLS encryption support"
 	depends on NVME_TARGET_TCP
 	select NET_HANDSHAKE
+	select TLS
 	help
 	  Enables TLS encryption for the NVMe TCP target using the netlink handshake API.
 
diff --git a/drivers/nvme/target/auth.c b/drivers/nvme/target/auth.c
index cef8d77f477b..9429b8218408 100644
--- a/drivers/nvme/target/auth.c
+++ b/drivers/nvme/target/auth.c
@@ -600,13 +600,12 @@ void nvmet_auth_insert_psk(struct nvmet_sq *sq)
 		pr_warn("%s: ctrl %d qid %d failed to refresh key, error %ld\n",
 			__func__, sq->ctrl->cntlid, sq->qid, PTR_ERR(tls_key));
 		tls_key = NULL;
-		kfree_sensitive(tls_psk);
 	}
 	if (sq->ctrl->tls_key)
 		key_put(sq->ctrl->tls_key);
 	sq->ctrl->tls_key = tls_key;
 #endif
-
+	kfree_sensitive(tls_psk);
 out_free_digest:
 	kfree_sensitive(digest);
 out_free_psk:
diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c
index f2d0c920269b..12a5cb8641ca 100644
--- a/drivers/nvme/target/tcp.c
+++ b/drivers/nvme/target/tcp.c
@@ -1560,6 +1560,9 @@ static void nvmet_tcp_restore_socket_callbacks(struct nvmet_tcp_queue *queue)
 {
 	struct socket *sock = queue->sock;
 
+	if (!queue->state_change)
+		return;
+
 	write_lock_bh(&sock->sk->sk_callback_lock);
 	sock->sk->sk_data_ready =  queue->data_ready;
 	sock->sk->sk_state_change = queue->state_change;
diff --git a/tools/testing/selftests/ublk/Makefile b/tools/testing/selftests/ublk/Makefile
index ec4624a283bc..f34ac0bac696 100644
--- a/tools/testing/selftests/ublk/Makefile
+++ b/tools/testing/selftests/ublk/Makefile
@@ -9,6 +9,7 @@ TEST_PROGS += test_generic_03.sh
 TEST_PROGS += test_generic_04.sh
 TEST_PROGS += test_generic_05.sh
 TEST_PROGS += test_generic_06.sh
+TEST_PROGS += test_generic_07.sh
 
 TEST_PROGS += test_null_01.sh
 TEST_PROGS += test_null_02.sh
diff --git a/tools/testing/selftests/ublk/kublk.c b/tools/testing/selftests/ublk/kublk.c
index e57a1486bb48..842b40736a9b 100644
--- a/tools/testing/selftests/ublk/kublk.c
+++ b/tools/testing/selftests/ublk/kublk.c
@@ -536,12 +536,17 @@ int ublk_queue_io_cmd(struct ublk_queue *q, struct ublk_io *io, unsigned tag)
 	if (!(io->flags & UBLKSRV_IO_FREE))
 		return 0;
 
-	/* we issue because we need either fetching or committing */
+	/*
+	 * we issue because we need either fetching or committing or
+	 * getting data
+	 */
 	if (!(io->flags &
-		(UBLKSRV_NEED_FETCH_RQ | UBLKSRV_NEED_COMMIT_RQ_COMP)))
+		(UBLKSRV_NEED_FETCH_RQ | UBLKSRV_NEED_COMMIT_RQ_COMP | UBLKSRV_NEED_GET_DATA)))
 		return 0;
 
-	if (io->flags & UBLKSRV_NEED_COMMIT_RQ_COMP)
+	if (io->flags & UBLKSRV_NEED_GET_DATA)
+		cmd_op = UBLK_U_IO_NEED_GET_DATA;
+	else if (io->flags & UBLKSRV_NEED_COMMIT_RQ_COMP)
 		cmd_op = UBLK_U_IO_COMMIT_AND_FETCH_REQ;
 	else if (io->flags & UBLKSRV_NEED_FETCH_RQ)
 		cmd_op = UBLK_U_IO_FETCH_REQ;
@@ -658,6 +663,9 @@ static void ublk_handle_cqe(struct io_uring *r,
 		assert(tag < q->q_depth);
 		if (q->tgt_ops->queue_io)
 			q->tgt_ops->queue_io(q, tag);
+	} else if (cqe->res == UBLK_IO_RES_NEED_GET_DATA) {
+		io->flags |= UBLKSRV_NEED_GET_DATA | UBLKSRV_IO_FREE;
+		ublk_queue_io_cmd(q, io, tag);
 	} else {
 		/*
 		 * COMMIT_REQ will be completed immediately since no fetching
@@ -1237,7 +1245,7 @@ static void __cmd_create_help(char *exe, bool recovery)
 
 	printf("%s %s -t [null|loop|stripe|fault_inject] [-q nr_queues] [-d depth] [-n dev_id]\n",
 			exe, recovery ? "recover" : "add");
-	printf("\t[--foreground] [--quiet] [-z] [--debug_mask mask] [-r 0|1 ] [-g 0|1]\n");
+	printf("\t[--foreground] [--quiet] [-z] [--debug_mask mask] [-r 0|1 ] [-g]\n");
 	printf("\t[-e 0|1 ] [-i 0|1]\n");
 	printf("\t[target options] [backfile1] [backfile2] ...\n");
 	printf("\tdefault: nr_queues=2(max 32), depth=128(max 1024), dev_id=-1(auto allocation)\n");
@@ -1313,7 +1321,7 @@ int main(int argc, char *argv[])
 
 	opterr = 0;
 	optind = 2;
-	while ((opt = getopt_long(argc, argv, "t:n:d:q:r:e:i:az",
+	while ((opt = getopt_long(argc, argv, "t:n:d:q:r:e:i:gaz",
 				  longopts, &option_idx)) != -1) {
 		switch (opt) {
 		case 'a':
@@ -1351,9 +1359,7 @@ int main(int argc, char *argv[])
 				ctx.flags |= UBLK_F_USER_RECOVERY | UBLK_F_USER_RECOVERY_REISSUE;
 			break;
 		case 'g':
-			value = strtol(optarg, NULL, 10);
-			if (value)
-				ctx.flags |= UBLK_F_NEED_GET_DATA;
+			ctx.flags |= UBLK_F_NEED_GET_DATA;
 			break;
 		case 0:
 			if (!strcmp(longopts[option_idx].name, "debug_mask"))
diff --git a/tools/testing/selftests/ublk/kublk.h b/tools/testing/selftests/ublk/kublk.h
index 918db5cd633f..44ee1e4ac55b 100644
--- a/tools/testing/selftests/ublk/kublk.h
+++ b/tools/testing/selftests/ublk/kublk.h
@@ -115,6 +115,7 @@ struct ublk_io {
 #define UBLKSRV_NEED_FETCH_RQ		(1UL << 0)
 #define UBLKSRV_NEED_COMMIT_RQ_COMP	(1UL << 1)
 #define UBLKSRV_IO_FREE			(1UL << 2)
+#define UBLKSRV_NEED_GET_DATA           (1UL << 3)
 	unsigned short flags;
 	unsigned short refs;		/* used by target code only */
 
diff --git a/tools/testing/selftests/ublk/test_generic_07.sh b/tools/testing/selftests/ublk/test_generic_07.sh
new file mode 100755
index 000000000000..cba86451fa5e
--- /dev/null
+++ b/tools/testing/selftests/ublk/test_generic_07.sh
@@ -0,0 +1,28 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+. "$(cd "$(dirname "$0")" && pwd)"/test_common.sh
+
+TID="generic_07"
+ERR_CODE=0
+
+if ! _have_program fio; then
+	exit "$UBLK_SKIP_CODE"
+fi
+
+_prep_test "generic" "test UBLK_F_NEED_GET_DATA"
+
+_create_backfile 0 256M
+dev_id=$(_add_ublk_dev -t loop -q 2 -g "${UBLK_BACKFILES[0]}")
+_check_add_dev $TID $?
+
+# run fio over the ublk disk
+_run_fio_verify_io --filename=/dev/ublkb"${dev_id}" --size=256M
+ERR_CODE=$?
+if [ "$ERR_CODE" -eq 0 ]; then
+	_mkfs_mount_test /dev/ublkb"${dev_id}"
+	ERR_CODE=$?
+fi
+
+_cleanup_test "generic"
+_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_stress_05.sh b/tools/testing/selftests/ublk/test_stress_05.sh
index a7071b10224d..88601b48f1cd 100755
--- a/tools/testing/selftests/ublk/test_stress_05.sh
+++ b/tools/testing/selftests/ublk/test_stress_05.sh
@@ -47,15 +47,15 @@ _create_backfile 0 256M
 _create_backfile 1 256M
 
 for reissue in $(seq 0 1); do
-	ublk_io_and_remove 8G -t null -q 4 -g 1 -r 1 -i "$reissue" &
-	ublk_io_and_remove 256M -t loop -q 4 -g 1 -r 1 -i "$reissue" "${UBLK_BACKFILES[0]}" &
+	ublk_io_and_remove 8G -t null -q 4 -g -r 1 -i "$reissue" &
+	ublk_io_and_remove 256M -t loop -q 4 -g -r 1 -i "$reissue" "${UBLK_BACKFILES[0]}" &
 	wait
 done
 
 if _have_feature "ZERO_COPY"; then
 	for reissue in $(seq 0 1); do
-		ublk_io_and_remove 8G -t null -q 4 -g 1 -z -r 1 -i "$reissue" &
-		ublk_io_and_remove 256M -t loop -q 4 -g 1 -z -r 1 -i "$reissue" "${UBLK_BACKFILES[1]}" &
+		ublk_io_and_remove 8G -t null -q 4 -g -z -r 1 -i "$reissue" &
+		ublk_io_and_remove 256M -t loop -q 4 -g -z -r 1 -i "$reissue" "${UBLK_BACKFILES[1]}" &
 		wait
 	done
 fi