Merge tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost

Pull virtio updates from Michael Tsirkin:

 - in-order support in virtio core

 - multiple address space support in vduse

 - fixes, cleanups all over the place, notably dma alignment fixes for
   non-cache-coherent systems

* tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost: (59 commits)
  vduse: avoid adding implicit padding
  vhost: fix caching attributes of MMIO regions by setting them explicitly
  vdpa/mlx5: update MAC address handling in mlx5_vdpa_set_attr()
  vdpa/mlx5: reuse common function for MAC address updates
  vdpa/mlx5: update mlx_features with driver state check
  crypto: virtio: Replace package id with numa node id
  crypto: virtio: Remove duplicated virtqueue_kick in virtio_crypto_skcipher_crypt_req
  crypto: virtio: Add spinlock protection with virtqueue notification
  Documentation: Add documentation for VDUSE Address Space IDs
  vduse: bump version number
  vduse: add vq group asid support
  vduse: merge tree search logic of IOTLB_GET_FD and IOTLB_GET_INFO ioctls
  vduse: take out allocations from vduse_dev_alloc_coherent
  vduse: remove unused vaddr parameter of vduse_domain_free_coherent
  vduse: refactor vdpa_dev_add for goto err handling
  vhost: forbid change vq groups ASID if DRIVER_OK is set
  vdpa: document set_group_asid thread safety
  vduse: return internal vq group struct as map token
  vduse: add vq group support
  vduse: add v1 API definition
  ...

Author: torvalds

Documentation/core-api/dma-api-howto.rst

@@ -146,6 +146,58 @@ What about block I/O and networking buffers?  The block I/O and
 networking subsystems make sure that the buffers they use are valid
 for you to DMA from/to.
 
+__dma_from_device_group_begin/end annotations
+=============================================
+
+As explained previously, when a structure contains a DMA_FROM_DEVICE /
+DMA_BIDIRECTIONAL buffer (device writes to memory) alongside fields that the
+CPU writes to, cache line sharing between the DMA buffer and CPU-written fields
+can cause data corruption on CPUs with DMA-incoherent caches.
+
+The ``__dma_from_device_group_begin(GROUP)/__dma_from_device_group_end(GROUP)``
+macros ensure proper alignment to prevent this::
+
+	struct my_device {
+		spinlock_t lock1;
+		__dma_from_device_group_begin();
+		char dma_buffer1[16];
+		char dma_buffer2[16];
+		__dma_from_device_group_end();
+		spinlock_t lock2;
+	};
+
+To isolate a DMA buffer from adjacent fields, use
+``__dma_from_device_group_begin(GROUP)`` before the first DMA buffer
+field and ``__dma_from_device_group_end(GROUP)`` after the last DMA
+buffer field (with the same GROUP name). This protects both the head
+and tail of the buffer from cache line sharing.
+
+The GROUP parameter is an optional identifier that names the DMA buffer group
+(in case you have several in the same structure)::
+
+	struct my_device {
+		spinlock_t lock1;
+		__dma_from_device_group_begin(buffer1);
+		char dma_buffer1[16];
+		__dma_from_device_group_end(buffer1);
+		spinlock_t lock2;
+		__dma_from_device_group_begin(buffer2);
+		char dma_buffer2[16];
+		__dma_from_device_group_end(buffer2);
+	};
+
+On cache-coherent platforms these macros expand to zero-length array markers.
+On non-coherent platforms, they also ensure the minimal DMA alignment, which
+can be as large as 128 bytes.
+
+.. note::
+
+        It is allowed (though somewhat fragile) to include extra fields, not
+        intended for DMA from the device, within the group (in order to pack the
+        structure tightly) - but only as long as the CPU does not write these
+        fields while any fields in the group are mapped for DMA_FROM_DEVICE or
+        DMA_BIDIRECTIONAL.
+
 DMA addressing capabilities
 ===========================
 

Documentation/core-api/dma-attributes.rst

@@ -148,3 +148,12 @@ DMA_ATTR_MMIO is appropriate.
 For architectures that require cache flushing for DMA coherence
 DMA_ATTR_MMIO will not perform any cache flushing. The address
 provided must never be mapped cacheable into the CPU.
+
+DMA_ATTR_CPU_CACHE_CLEAN
+------------------------
+
+This attribute indicates the CPU will not dirty any cacheline overlapping this
+DMA_FROM_DEVICE/DMA_BIDIRECTIONAL buffer while it is mapped. This allows
+multiple small buffers to safely share a cacheline without risk of data
+corruption, suppressing DMA debug warnings about overlapping mappings.
+All mappings sharing a cacheline should have this attribute.

Documentation/userspace-api/vduse.rst

@@ -230,4 +230,57 @@ able to start the dataplane processing as follows:
 5. Inject an interrupt for specific virtqueue with the VDUSE_INJECT_VQ_IRQ ioctl
    after the used ring is filled.
 
+Enabling ASID (API version 1)
+------------------------------
+
+VDUSE supports per-address-space identifiers (ASIDs) starting with API
+version 1. Set it up with ioctl(VDUSE_SET_API_VERSION) on `/dev/vduse/control`
+and pass `VDUSE_API_VERSION_1` before creating a new VDUSE instance with
+ioctl(VDUSE_CREATE_DEV).
+
+Afterwards, you can use the member asid of ioctl(VDUSE_VQ_SETUP) argument to
+select the address space of the IOTLB you are querying.  The driver could
+change the address space of any virtqueue group by using the
+VDUSE_SET_VQ_GROUP_ASID VDUSE message type, and the VDUSE instance needs to
+reply with VDUSE_REQ_RESULT_OK if it was possible to change it.
+
+Similarly, you can use ioctl(VDUSE_IOTLB_GET_FD2) to obtain the file descriptor
+describing an IOVA region of a specific ASID. Example usage:
+
+.. code-block:: c
+
+	static void *iova_to_va(int dev_fd, uint32_t asid, uint64_t iova,
+	                        uint64_t *len)
+	{
+		int fd;
+		void *addr;
+		size_t size;
+		struct vduse_iotlb_entry_v2 entry = { 0 };
+
+		entry.v1.start = iova;
+		entry.v1.last = iova;
+		entry.asid = asid;
+
+		fd = ioctl(dev_fd, VDUSE_IOTLB_GET_FD2, &entry);
+		if (fd < 0)
+			return NULL;
+
+		size = entry.v1.last - entry.v1.start + 1;
+		*len = entry.v1.last - iova + 1;
+		addr = mmap(0, size, perm_to_prot(entry.v1.perm), MAP_SHARED,
+			    fd, entry.v1.offset);
+		close(fd);
+		if (addr == MAP_FAILED)
+			return NULL;
+
+		/*
+		 * Using some data structures such as linked list to store
+		 * the iotlb mapping. The munmap(2) should be called for the
+		 * cached mapping when the corresponding VDUSE_UPDATE_IOTLB
+		 * message is received or the device is reset.
+		 */
+
+		return addr + iova - entry.v1.start;
+	}
+
 For more details on the uAPI, please see include/uapi/linux/vduse.h.

drivers/char/hw_random/virtio-rng.c

@@ -11,6 +11,7 @@
 #include <linux/spinlock.h>
 #include <linux/virtio.h>
 #include <linux/virtio_rng.h>
+#include <linux/dma-mapping.h>
 #include <linux/module.h>
 #include <linux/slab.h>
 
@@ -28,11 +29,13 @@ struct virtrng_info {
 	unsigned int data_avail;
 	unsigned int data_idx;
 	/* minimal size returned by rng_buffer_size() */
+	__dma_from_device_group_begin();
 #if SMP_CACHE_BYTES < 32
 	u8 data[32];
 #else
 	u8 data[SMP_CACHE_BYTES];
 #endif
+	__dma_from_device_group_end();
 };
 
 static void random_recv_done(struct virtqueue *vq)

drivers/gpio/gpio-virtio.c

@@ -10,6 +10,7 @@
  */
 
 #include <linux/completion.h>
+#include <linux/dma-mapping.h>
 #include <linux/err.h>
 #include <linux/gpio/driver.h>
 #include <linux/io.h>
@@ -24,9 +25,13 @@
 struct virtio_gpio_line {
 	struct mutex lock; /* Protects line operation */
 	struct completion completion;
-	struct virtio_gpio_request req ____cacheline_aligned;
-	struct virtio_gpio_response res ____cacheline_aligned;
+
 	unsigned int rxlen;
+
+	__dma_from_device_group_begin();
+	struct virtio_gpio_request req;
+	struct virtio_gpio_response res;
+	__dma_from_device_group_end();
 };
 
 struct vgpio_irq_line {
@@ -37,8 +42,10 @@ struct vgpio_irq_line {
 	bool update_pending;
 	bool queue_pending;
 
-	struct virtio_gpio_irq_request ireq ____cacheline_aligned;
-	struct virtio_gpio_irq_response ires ____cacheline_aligned;
+	__dma_from_device_group_begin();
+	struct virtio_gpio_irq_request ireq;
+	struct virtio_gpio_irq_response ires;
+	__dma_from_device_group_end();
 };
 
 struct virtio_gpio {

drivers/scsi/virtio_scsi.c

@@ -29,6 +29,7 @@
 #include <scsi/scsi_tcq.h>
 #include <scsi/scsi_devinfo.h>
 #include <linux/seqlock.h>
+#include <linux/dma-mapping.h>
 
 #include "sd.h"
 
@@ -61,7 +62,7 @@ struct virtio_scsi_cmd {
 
 struct virtio_scsi_event_node {
 	struct virtio_scsi *vscsi;
-	struct virtio_scsi_event event;
+	struct virtio_scsi_event *event;
 	struct work_struct work;
 };
 
@@ -89,6 +90,11 @@ struct virtio_scsi {
 
 	struct virtio_scsi_vq ctrl_vq;
 	struct virtio_scsi_vq event_vq;
+
+	__dma_from_device_group_begin();
+	struct virtio_scsi_event events[VIRTIO_SCSI_EVENT_LEN];
+	__dma_from_device_group_end();
+
 	struct virtio_scsi_vq req_vqs[];
 };
 
@@ -237,12 +243,12 @@ static int virtscsi_kick_event(struct virtio_scsi *vscsi,
 	unsigned long flags;
 
 	INIT_WORK(&event_node->work, virtscsi_handle_event);
-	sg_init_one(&sg, &event_node->event, sizeof(struct virtio_scsi_event));
+	sg_init_one(&sg, event_node->event, sizeof(struct virtio_scsi_event));
 
 	spin_lock_irqsave(&vscsi->event_vq.vq_lock, flags);
 
-	err = virtqueue_add_inbuf(vscsi->event_vq.vq, &sg, 1, event_node,
-				  GFP_ATOMIC);
+	err = virtqueue_add_inbuf_cache_clean(vscsi->event_vq.vq, &sg, 1, event_node,
+					      GFP_ATOMIC);
 	if (!err)
 		virtqueue_kick(vscsi->event_vq.vq);
 
@@ -257,6 +263,7 @@ static int virtscsi_kick_event_all(struct virtio_scsi *vscsi)
 
 	for (i = 0; i < VIRTIO_SCSI_EVENT_LEN; i++) {
 		vscsi->event_list[i].vscsi = vscsi;
+		vscsi->event_list[i].event = &vscsi->events[i];
 		virtscsi_kick_event(vscsi, &vscsi->event_list[i]);
 	}
 
@@ -380,7 +387,7 @@ static void virtscsi_handle_event(struct work_struct *work)
 	struct virtio_scsi_event_node *event_node =
 		container_of(work, struct virtio_scsi_event_node, work);
 	struct virtio_scsi *vscsi = event_node->vscsi;
-	struct virtio_scsi_event *event = &event_node->event;
+	struct virtio_scsi_event *event = event_node->event;
 
 	if (event->event &
 	    cpu_to_virtio32(vscsi->vdev, VIRTIO_SCSI_T_EVENTS_MISSED)) {