Merge tag 'block-6.15-20250515' of git://git.kernel.dk/linux

Pull block fixes from Jens Axboe:

- NVMe pull request via Christoph:
- fixes for atomic writes (Alan Adamson)
- fixes for polled CQs in nvmet-epf (Damien Le Moal)
- fix for polled CQs in nvme-pci (Keith Busch)
- fix compile on odd configs that need to be forced to inline
(Kees Cook)
- one more quirk (Ilya Guterman)

- Fix for missing allocation of an integrity buffer for some cases

- Fix for a regression with ublk command cancelation

* tag 'block-6.15-20250515' of git://git.kernel.dk/linux:
ublk: fix dead loop when canceling io command
nvme-pci: add NVME_QUIRK_NO_DEEPEST_PS quirk for SOLIDIGM P44 Pro
nvme: all namespaces in a subsystem must adhere to a common atomic write size
nvme: multipath: enable BLK_FEAT_ATOMIC_WRITES for multipathing
nvmet: pci-epf: remove NVMET_PCI_EPF_Q_IS_SQ
nvmet: pci-epf: improve debug message
nvmet: pci-epf: cleanup nvmet_pci_epf_raise_irq()
nvmet: pci-epf: do not fall back to using INTX if not supported
nvmet: pci-epf: clear completion queue IRQ flag on delete
nvme-pci: acquire cq_poll_lock in nvme_poll_irqdisable
nvme-pci: make nvme_pci_npages_prp() __always_inline
block: always allocate integrity buffer when required

block/bio-integrity-auto.c

···
  * not aware of PI.
  */
 #include <linux/blk-integrity.h>
+#include <linux/t10-pi.h>
 #include <linux/workqueue.h>
 #include "blk.h"
 
···
 	bio_endio(bio);
 }
 
+#define BIP_CHECK_FLAGS (BIP_CHECK_GUARD | BIP_CHECK_REFTAG | BIP_CHECK_APPTAG)
+static bool bip_should_check(struct bio_integrity_payload *bip)
+{
+	return bip->bip_flags & BIP_CHECK_FLAGS;
+}
+
+static bool bi_offload_capable(struct blk_integrity *bi)
+{
+	switch (bi->csum_type) {
+	case BLK_INTEGRITY_CSUM_CRC64:
+		return bi->tuple_size == sizeof(struct crc64_pi_tuple);
+	case BLK_INTEGRITY_CSUM_CRC:
+	case BLK_INTEGRITY_CSUM_IP:
+		return bi->tuple_size == sizeof(struct t10_pi_tuple);
+	default:
+		pr_warn_once("%s: unknown integrity checksum type:%d\n",
+			__func__, bi->csum_type);
+		fallthrough;
+	case BLK_INTEGRITY_CSUM_NONE:
+		return false;
+	}
+}
+
 /**
  * __bio_integrity_endio - Integrity I/O completion function
  * @bio:	Protected bio
···
  */
 bool __bio_integrity_endio(struct bio *bio)
 {
-	struct blk_integrity *bi = blk_get_integrity(bio->bi_bdev->bd_disk);
 	struct bio_integrity_payload *bip = bio_integrity(bio);
 	struct bio_integrity_data *bid =
 		container_of(bip, struct bio_integrity_data, bip);
 
-	if (bio_op(bio) == REQ_OP_READ && !bio->bi_status && bi->csum_type) {
+	if (bio_op(bio) == REQ_OP_READ && !bio->bi_status &&
+	    bip_should_check(bip)) {
 		INIT_WORK(&bid->work, bio_integrity_verify_fn);
 		queue_work(kintegrityd_wq, &bid->work);
 		return false;
···
 {
 	struct blk_integrity *bi = blk_get_integrity(bio->bi_bdev->bd_disk);
 	struct bio_integrity_data *bid;
+	bool set_flags = true;
 	gfp_t gfp = GFP_NOIO;
 	unsigned int len;
 	void *buf;
···
 
 	switch (bio_op(bio)) {
 	case REQ_OP_READ:
-		if (bi->flags & BLK_INTEGRITY_NOVERIFY)
-			return true;
+		if (bi->flags & BLK_INTEGRITY_NOVERIFY) {
+			if (bi_offload_capable(bi))
+				return true;
+			set_flags = false;
+		}
 		break;
 	case REQ_OP_WRITE:
-		if (bi->flags & BLK_INTEGRITY_NOGENERATE)
-			return true;
-
 		/*
 		 * Zero the memory allocated to not leak uninitialized kernel
 		 * memory to disk for non-integrity metadata where nothing else
 		 * initializes the memory.
 		 */
-		if (bi->csum_type == BLK_INTEGRITY_CSUM_NONE)
+		if (bi->flags & BLK_INTEGRITY_NOGENERATE) {
+			if (bi_offload_capable(bi))
+				return true;
+			set_flags = false;
+			gfp |= __GFP_ZERO;
+		} else if (bi->csum_type == BLK_INTEGRITY_CSUM_NONE)
 			gfp |= __GFP_ZERO;
 		break;
 	default:
···
 	bid->bip.bip_flags |= BIP_BLOCK_INTEGRITY;
 	bip_set_seed(&bid->bip, bio->bi_iter.bi_sector);
 
-	if (bi->csum_type == BLK_INTEGRITY_CSUM_IP)
-		bid->bip.bip_flags |= BIP_IP_CHECKSUM;
-	if (bi->csum_type)
-		bid->bip.bip_flags |= BIP_CHECK_GUARD;
-	if (bi->flags & BLK_INTEGRITY_REF_TAG)
-		bid->bip.bip_flags |= BIP_CHECK_REFTAG;
+	if (set_flags) {
+		if (bi->csum_type == BLK_INTEGRITY_CSUM_IP)
+			bid->bip.bip_flags |= BIP_IP_CHECKSUM;
+		if (bi->csum_type)
+			bid->bip.bip_flags |= BIP_CHECK_GUARD;
+		if (bi->flags & BLK_INTEGRITY_REF_TAG)
+			bid->bip.bip_flags |= BIP_CHECK_REFTAG;
+	}
 
 	if (bio_integrity_add_page(bio, virt_to_page(buf), len,
 			offset_in_page(buf)) < len)
 		goto err_end_io;
 
 	/* Auto-generate integrity metadata if this is a write */
-	if (bio_data_dir(bio) == WRITE)
+	if (bio_data_dir(bio) == WRITE && bip_should_check(&bid->bip))
 		blk_integrity_generate(bio);
 	else
 		bid->saved_bio_iter = bio->bi_iter;

drivers/block/ublk_drv.c

···
 	 * that ublk_dispatch_req() is always called
 	 */
 	req = blk_mq_tag_to_rq(ub->tag_set.tags[ubq->q_id], tag);
-	if (req && blk_mq_request_started(req))
+	if (req && blk_mq_request_started(req) && req->tag == tag)
 		return;
 
 	spin_lock(&ubq->cancel_lock);

drivers/nvme/host/core.c

···
 		if (id->nsfeat & NVME_NS_FEAT_ATOMICS && id->nawupf)
 			atomic_bs = (1 + le16_to_cpu(id->nawupf)) * bs;
 		else
-			atomic_bs = (1 + ns->ctrl->subsys->awupf) * bs;
+			atomic_bs = (1 + ns->ctrl->awupf) * bs;
+
+		/*
+		 * Set subsystem atomic bs.
+		 */
+		if (ns->ctrl->subsys->atomic_bs) {
+			if (atomic_bs != ns->ctrl->subsys->atomic_bs) {
+				dev_err_ratelimited(ns->ctrl->device,
+					"%s: Inconsistent Atomic Write Size, Namespace will not be added: Subsystem=%d bytes, Controller/Namespace=%d bytes\n",
+					ns->disk ? ns->disk->disk_name : "?",
+					ns->ctrl->subsys->atomic_bs,
+					atomic_bs);
+			}
+		} else
+			ns->ctrl->subsys->atomic_bs = atomic_bs;
 
 		nvme_update_atomic_write_disk_info(ns, id, lim, bs, atomic_bs);
 	}
···
 	nvme_set_chunk_sectors(ns, id, &lim);
 	if (!nvme_update_disk_info(ns, id, &lim))
 		capacity = 0;
+
+	/*
+	 * Validate the max atomic write size fits within the subsystem's
+	 * atomic write capabilities.
+	 */
+	if (lim.atomic_write_hw_max > ns->ctrl->subsys->atomic_bs) {
+		blk_mq_unfreeze_queue(ns->disk->queue, memflags);
+		ret = -ENXIO;
+		goto out;
+	}
+
 	nvme_config_discard(ns, &lim);
 	if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) &&
 	    ns->head->ids.csi == NVME_CSI_ZNS)
···
 		kfree(subsys);
 		return -EINVAL;
 	}
-	subsys->awupf = le16_to_cpu(id->awupf);
 	nvme_mpath_default_iopolicy(subsys);
 
 	subsys->dev.class = &nvme_subsys_class;
···
 		dev_pm_qos_expose_latency_tolerance(ctrl->device);
 	else if (!ctrl->apst_enabled && prev_apst_enabled)
 		dev_pm_qos_hide_latency_tolerance(ctrl->device);
-
+	ctrl->awupf = le16_to_cpu(id->awupf);
 out_free:
 	kfree(id);
 	return ret;

drivers/nvme/host/multipath.c

···
 
 	blk_set_stacking_limits(&lim);
 	lim.dma_alignment = 3;
-	lim.features |= BLK_FEAT_IO_STAT | BLK_FEAT_NOWAIT | BLK_FEAT_POLL;
+	lim.features |= BLK_FEAT_IO_STAT | BLK_FEAT_NOWAIT |
+		BLK_FEAT_POLL | BLK_FEAT_ATOMIC_WRITES;
 	if (head->ids.csi == NVME_CSI_ZNS)
 		lim.features |= BLK_FEAT_ZONED;
 

drivers/nvme/host/nvme.h

···
 
 	enum nvme_ctrl_type cntrltype;
 	enum nvme_dctype dctype;
+	u16 awupf; /* 0's based value. */
 };
 
 static inline enum nvme_ctrl_state nvme_ctrl_state(struct nvme_ctrl *ctrl)
···
 	u8			cmic;
 	enum nvme_subsys_type	subtype;
 	u16			vendor_id;
-	u16			awupf;	/* 0's based awupf value. */
 	struct ida		ns_ida;
 #ifdef CONFIG_NVME_MULTIPATH
 	enum nvme_iopolicy	iopolicy;
 #endif
+	u32			atomic_bs;
 };
 
 /*

drivers/nvme/host/pci.c

···
  * as it only leads to a small amount of wasted memory for the lifetime of
  * the I/O.
  */
-static int nvme_pci_npages_prp(void)
+static __always_inline int nvme_pci_npages_prp(void)
 {
 	unsigned max_bytes = (NVME_MAX_KB_SZ * 1024) + NVME_CTRL_PAGE_SIZE;
 	unsigned nprps = DIV_ROUND_UP(max_bytes, NVME_CTRL_PAGE_SIZE);
···
 	WARN_ON_ONCE(test_bit(NVMEQ_POLLED, &nvmeq->flags));
 
 	disable_irq(pci_irq_vector(pdev, nvmeq->cq_vector));
+	spin_lock(&nvmeq->cq_poll_lock);
 	nvme_poll_cq(nvmeq, NULL);
+	spin_unlock(&nvmeq->cq_poll_lock);
 	enable_irq(pci_irq_vector(pdev, nvmeq->cq_vector));
 }
 
···
 	{ PCI_DEVICE(0x1e49, 0x0021),   /* ZHITAI TiPro5000 NVMe SSD */
 		.driver_data = NVME_QUIRK_NO_DEEPEST_PS, },
 	{ PCI_DEVICE(0x1e49, 0x0041),   /* ZHITAI TiPro7000 NVMe SSD */
+		.driver_data = NVME_QUIRK_NO_DEEPEST_PS, },
+	{ PCI_DEVICE(0x025e, 0xf1ac),   /* SOLIDIGM  P44 pro SSDPFKKW020X7  */
 		.driver_data = NVME_QUIRK_NO_DEEPEST_PS, },
 	{ PCI_DEVICE(0xc0a9, 0x540a),   /* Crucial P2 */
 		.driver_data = NVME_QUIRK_BOGUS_NID, },

drivers/nvme/target/pci-epf.c

···
 #define NVMET_PCI_EPF_CQ_RETRY_INTERVAL	msecs_to_jiffies(1)
 
 enum nvmet_pci_epf_queue_flags {
-	NVMET_PCI_EPF_Q_IS_SQ = 0,	/* The queue is a submission queue */
-	NVMET_PCI_EPF_Q_LIVE,		/* The queue is live */
+	NVMET_PCI_EPF_Q_LIVE = 0,	/* The queue is live */
 	NVMET_PCI_EPF_Q_IRQ_ENABLED,	/* IRQ is enabled for this queue */
 };
 
···
 	struct nvmet_pci_epf_irq_vector *iv = cq->iv;
 	bool ret;
 
-	if (!test_bit(NVMET_PCI_EPF_Q_IRQ_ENABLED, &cq->flags))
-		return false;
-
 	/* IRQ coalescing for the admin queue is not allowed. */
 	if (!cq->qid)
 		return true;
···
 	struct pci_epf *epf = nvme_epf->epf;
 	int ret = 0;
 
-	if (!test_bit(NVMET_PCI_EPF_Q_LIVE, &cq->flags))
+	if (!test_bit(NVMET_PCI_EPF_Q_LIVE, &cq->flags) ||
+	    !test_bit(NVMET_PCI_EPF_Q_IRQ_ENABLED, &cq->flags))
 		return;
 
 	mutex_lock(&ctrl->irq_lock);
···
 	switch (nvme_epf->irq_type) {
 	case PCI_IRQ_MSIX:
 	case PCI_IRQ_MSI:
+		/*
+		 * If we fail to raise an MSI or MSI-X interrupt, it is likely
+		 * because the host is using legacy INTX IRQs (e.g. BIOS,
+		 * grub), but we can fallback to the INTX type only if the
+		 * endpoint controller supports this type.
+		 */
 		ret = pci_epc_raise_irq(epf->epc, epf->func_no, epf->vfunc_no,
 					nvme_epf->irq_type, cq->vector + 1);
-		if (!ret)
+		if (!ret || !nvme_epf->epc_features->intx_capable)
 			break;
-		/*
-		 * If we got an error, it is likely because the host is using
-		 * legacy IRQs (e.g. BIOS, grub).
-		 */
 		fallthrough;
 	case PCI_IRQ_INTX:
 		ret = pci_epc_raise_irq(epf->epc, epf->func_no, epf->vfunc_no,
···
 	}
 
 	if (ret)
-		dev_err(ctrl->dev, "Failed to raise IRQ (err=%d)\n", ret);
+		dev_err_ratelimited(ctrl->dev,
+				    "CQ[%u]: Failed to raise IRQ (err=%d)\n",
+				    cq->qid, ret);
 
 unlock:
 	mutex_unlock(&ctrl->irq_lock);
···
 
 	set_bit(NVMET_PCI_EPF_Q_LIVE, &cq->flags);
 
-	dev_dbg(ctrl->dev, "CQ[%u]: %u entries of %zu B, IRQ vector %u\n",
-		cqid, qsize, cq->qes, cq->vector);
+	if (test_bit(NVMET_PCI_EPF_Q_IRQ_ENABLED, &cq->flags))
+		dev_dbg(ctrl->dev,
+			"CQ[%u]: %u entries of %zu B, IRQ vector %u\n",
+			cqid, qsize, cq->qes, cq->vector);
+	else
+		dev_dbg(ctrl->dev,
+			"CQ[%u]: %u entries of %zu B, IRQ disabled\n",
+			cqid, qsize, cq->qes);
 
 	return NVME_SC_SUCCESS;
 
···
 
 	cancel_delayed_work_sync(&cq->work);
 	nvmet_pci_epf_drain_queue(cq);
-	nvmet_pci_epf_remove_irq_vector(ctrl, cq->vector);
+	if (test_and_clear_bit(NVMET_PCI_EPF_Q_IRQ_ENABLED, &cq->flags))
+		nvmet_pci_epf_remove_irq_vector(ctrl, cq->vector);
 	nvmet_pci_epf_mem_unmap(ctrl->nvme_epf, &cq->pci_map);
 
 	return NVME_SC_SUCCESS;
···
 
 	if (sq) {
 		queue = &ctrl->sq[qid];
-		set_bit(NVMET_PCI_EPF_Q_IS_SQ, &queue->flags);
 	} else {
 		queue = &ctrl->cq[qid];
 		INIT_DELAYED_WORK(&queue->work, nvmet_pci_epf_cq_work);