Merge tag 'for-6.2/block-2022-12-08' of git://git.kernel.dk/linux

Pull block updates from Jens Axboe:

 - NVMe pull requests via Christoph:
      - Support some passthrough commands without CAP_SYS_ADMIN (Kanchan
        Joshi)
      - Refactor PCIe probing and reset (Christoph Hellwig)
      - Various fabrics authentication fixes and improvements (Sagi
        Grimberg)
      - Avoid fallback to sequential scan due to transient issues (Uday
        Shankar)
      - Implement support for the DEAC bit in Write Zeroes (Christoph
        Hellwig)
      - Allow overriding the IEEE OUI and firmware revision in configfs
        for nvmet (Aleksandr Miloserdov)
      - Force reconnect when number of queue changes in nvmet (Daniel
        Wagner)
      - Minor fixes and improvements (Uros Bizjak, Joel Granados, Sagi
        Grimberg, Christoph Hellwig, Christophe JAILLET)
      - Fix and cleanup nvme-fc req allocation (Chaitanya Kulkarni)
      - Use the common tagset helpers in nvme-pci driver (Christoph
        Hellwig)
      - Cleanup the nvme-pci removal path (Christoph Hellwig)
      - Use kstrtobool() instead of strtobool (Christophe JAILLET)
      - Allow unprivileged passthrough of Identify Controller (Joel
        Granados)
      - Support io stats on the mpath device (Sagi Grimberg)
      - Minor nvmet cleanup (Sagi Grimberg)

 - MD pull requests via Song:
      - Code cleanups (Christoph)
      - Various fixes

 - Floppy pull request from Denis:
      - Fix a memory leak in the init error path (Yuan)

 - Series fixing some batch wakeup issues with sbitmap (Gabriel)

 - Removal of the pktcdvd driver that was deprecated more than 5 years
   ago, and subsequent removal of the devnode callback in struct
   block_device_operations as no users are now left (Greg)

 - Fix for partition read on an exclusively opened bdev (Jan)

 - Series of elevator API cleanups (Jinlong, Christoph)

 - Series of fixes and cleanups for blk-iocost (Kemeng)

 - Series of fixes and cleanups for blk-throttle (Kemeng)

 - Series adding concurrent support for sync queues in BFQ (Yu)

 - Series bringing drbd a bit closer to the out-of-tree maintained
   version (Christian, Joel, Lars, Philipp)

 - Misc drbd fixes (Wang)

 - blk-wbt fixes and tweaks for enable/disable (Yu)

 - Fixes for mq-deadline for zoned devices (Damien)

 - Add support for read-only and offline zones for null_blk
   (Shin'ichiro)

 - Series fixing the delayed holder tracking, as used by DM (Yu,
   Christoph)

 - Series enabling bio alloc caching for IRQ based IO (Pavel)

 - Series enabling userspace peer-to-peer DMA (Logan)

 - BFQ waker fixes (Khazhismel)

 - Series fixing elevator refcount issues (Christoph, Jinlong)

 - Series cleaning up references around queue destruction (Christoph)

 - Series doing quiesce by tagset, enabling cleanups in drivers
   (Christoph, Chao)

 - Series untangling the queue kobject and queue references (Christoph)

 - Misc fixes and cleanups (Bart, David, Dawei, Jinlong, Kemeng, Ye,
   Yang, Waiman, Shin'ichiro, Randy, Pankaj, Christoph)

* tag 'for-6.2/block-2022-12-08' of git://git.kernel.dk/linux: (247 commits)
  blktrace: Fix output non-blktrace event when blk_classic option enabled
  block: sed-opal: Don't include <linux/kernel.h>
  sed-opal: allow using IOC_OPAL_SAVE for locking too
  blk-cgroup: Fix typo in comment
  block: remove bio_set_op_attrs
  nvmet: don't open-code NVME_NS_ATTR_RO enumeration
  nvme-pci: use the tagset alloc/free helpers
  nvme: add the Apple shared tag workaround to nvme_alloc_io_tag_set
  nvme: only set reserved_tags in nvme_alloc_io_tag_set for fabrics controllers
  nvme: consolidate setting the tagset flags
  nvme: pass nr_maps explicitly to nvme_alloc_io_tag_set
  block: bio_copy_data_iter
  nvme-pci: split out a nvme_pci_ctrl_is_dead helper
  nvme-pci: return early on ctrl state mismatch in nvme_reset_work
  nvme-pci: rename nvme_disable_io_queues
  nvme-pci: cleanup nvme_suspend_queue
  nvme-pci: remove nvme_pci_disable
  nvme-pci: remove nvme_disable_admin_queue
  nvme: merge nvme_shutdown_ctrl into nvme_disable_ctrl
  nvme: use nvme_wait_ready in nvme_shutdown_ctrl
  ...

1 files changed, 124 insertions, 0 deletions

diff --git a/drivers/pci/p2pdma.c b/drivers/pci/p2pdma.c
index 5565f67d6537..86812d2073ea 100644
--- a/drivers/pci/p2pdma.c
+++ b/drivers/pci/p2pdma.c
@@ -89,6 +89,90 @@ static ssize_t published_show(struct device *dev, struct device_attribute *attr,
 }
 static DEVICE_ATTR_RO(published);
 
+static int p2pmem_alloc_mmap(struct file *filp, struct kobject *kobj,
+		struct bin_attribute *attr, struct vm_area_struct *vma)
+{
+	struct pci_dev *pdev = to_pci_dev(kobj_to_dev(kobj));
+	size_t len = vma->vm_end - vma->vm_start;
+	struct pci_p2pdma *p2pdma;
+	struct percpu_ref *ref;
+	unsigned long vaddr;
+	void *kaddr;
+	int ret;
+
+	/* prevent private mappings from being established */
+	if ((vma->vm_flags & VM_MAYSHARE) != VM_MAYSHARE) {
+		pci_info_ratelimited(pdev,
+				     "%s: fail, attempted private mapping\n",
+				     current->comm);
+		return -EINVAL;
+	}
+
+	if (vma->vm_pgoff) {
+		pci_info_ratelimited(pdev,
+				     "%s: fail, attempted mapping with non-zero offset\n",
+				     current->comm);
+		return -EINVAL;
+	}
+
+	rcu_read_lock();
+	p2pdma = rcu_dereference(pdev->p2pdma);
+	if (!p2pdma) {
+		ret = -ENODEV;
+		goto out;
+	}
+
+	kaddr = (void *)gen_pool_alloc_owner(p2pdma->pool, len, (void **)&ref);
+	if (!kaddr) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	/*
+	 * vm_insert_page() can sleep, so a reference is taken to mapping
+	 * such that rcu_read_unlock() can be done before inserting the
+	 * pages
+	 */
+	if (unlikely(!percpu_ref_tryget_live_rcu(ref))) {
+		ret = -ENODEV;
+		goto out_free_mem;
+	}
+	rcu_read_unlock();
+
+	for (vaddr = vma->vm_start; vaddr < vma->vm_end; vaddr += PAGE_SIZE) {
+		ret = vm_insert_page(vma, vaddr, virt_to_page(kaddr));
+		if (ret) {
+			gen_pool_free(p2pdma->pool, (uintptr_t)kaddr, len);
+			return ret;
+		}
+		percpu_ref_get(ref);
+		put_page(virt_to_page(kaddr));
+		kaddr += PAGE_SIZE;
+		len -= PAGE_SIZE;
+	}
+
+	percpu_ref_put(ref);
+
+	return 0;
+out_free_mem:
+	gen_pool_free(p2pdma->pool, (uintptr_t)kaddr, len);
+out:
+	rcu_read_unlock();
+	return ret;
+}
+
+static struct bin_attribute p2pmem_alloc_attr = {
+	.attr = { .name = "allocate", .mode = 0660 },
+	.mmap = p2pmem_alloc_mmap,
+	/*
+	 * Some places where we want to call mmap (ie. python) will check
+	 * that the file size is greater than the mmap size before allowing
+	 * the mmap to continue. To work around this, just set the size
+	 * to be very large.
+	 */
+	.size = SZ_1T,
+};
+
 static struct attribute *p2pmem_attrs[] = {
 	&dev_attr_size.attr,
 	&dev_attr_available.attr,
@@ -96,11 +180,32 @@ static struct attribute *p2pmem_attrs[] = {
 	NULL,
 };
 
+static struct bin_attribute *p2pmem_bin_attrs[] = {
+	&p2pmem_alloc_attr,
+	NULL,
+};
+
 static const struct attribute_group p2pmem_group = {
 	.attrs = p2pmem_attrs,
+	.bin_attrs = p2pmem_bin_attrs,
 	.name = "p2pmem",
 };
 
+static void p2pdma_page_free(struct page *page)
+{
+	struct pci_p2pdma_pagemap *pgmap = to_p2p_pgmap(page->pgmap);
+	struct percpu_ref *ref;
+
+	gen_pool_free_owner(pgmap->provider->p2pdma->pool,
+			    (uintptr_t)page_to_virt(page), PAGE_SIZE,
+			    (void **)&ref);
+	percpu_ref_put(ref);
+}
+
+static const struct dev_pagemap_ops p2pdma_pgmap_ops = {
+	.page_free = p2pdma_page_free,
+};
+
 static void pci_p2pdma_release(void *data)
 {
 	struct pci_dev *pdev = data;
@@ -152,6 +257,19 @@ out:
 	return error;
 }
 
+static void pci_p2pdma_unmap_mappings(void *data)
+{
+	struct pci_dev *pdev = data;
+
+	/*
+	 * Removing the alloc attribute from sysfs will call
+	 * unmap_mapping_range() on the inode, teardown any existing userspace
+	 * mappings and prevent new ones from being created.
+	 */
+	sysfs_remove_file_from_group(&pdev->dev.kobj, &p2pmem_alloc_attr.attr,
+				     p2pmem_group.name);
+}
+
 /**
  * pci_p2pdma_add_resource - add memory for use as p2p memory
  * @pdev: the device to add the memory to
@@ -198,6 +316,7 @@ int pci_p2pdma_add_resource(struct pci_dev *pdev, int bar, size_t size,
 	pgmap->range.end = pgmap->range.start + size - 1;
 	pgmap->nr_range = 1;
 	pgmap->type = MEMORY_DEVICE_PCI_P2PDMA;
+	pgmap->ops = &p2pdma_pgmap_ops;
 
 	p2p_pgmap->provider = pdev;
 	p2p_pgmap->bus_offset = pci_bus_address(pdev, bar) -
@@ -209,6 +328,11 @@ int pci_p2pdma_add_resource(struct pci_dev *pdev, int bar, size_t size,
 		goto pgmap_free;
 	}
 
+	error = devm_add_action_or_reset(&pdev->dev, pci_p2pdma_unmap_mappings,
+					 pdev);
+	if (error)
+		goto pages_free;
+
 	p2pdma = rcu_dereference_protected(pdev->p2pdma, 1);
 	error = gen_pool_add_owner(p2pdma->pool, (unsigned long)addr,
 			pci_bus_address(pdev, bar) + offset,