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

Pull virtio updates from Michael Tsirkin:

 - virtio-mem: paravirtualized memory hotplug

 - support doorbell mapping for vdpa

 - config interrupt support in ifc

 - fixes all over the place

* tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost: (40 commits)
  vhost/test: fix up after API change
  virtio_mem: convert device block size into 64bit
  virtio-mem: drop unnecessary initialization
  ifcvf: implement config interrupt in IFCVF
  vhost: replace -1 with VHOST_FILE_UNBIND in ioctls
  vhost_vdpa: Support config interrupt in vdpa
  ifcvf: ignore continuous setting same status value
  virtio-mem: Don't rely on implicit compiler padding for requests
  virtio-mem: Try to unplug the complete online memory block first
  virtio-mem: Use -ETXTBSY as error code if the device is busy
  virtio-mem: Unplug subblocks right-to-left
  virtio-mem: Drop manual check for already present memory
  virtio-mem: Add parent resource for all added "System RAM"
  virtio-mem: Better retry handling
  virtio-mem: Offline and remove completely unplugged memory blocks
  mm/memory_hotplug: Introduce offline_and_remove_memory()
  virtio-mem: Allow to offline partially unplugged memory blocks
  mm: Allow to offline unmovable PageOffline() pages via MEM_GOING_OFFLINE
  virtio-mem: Paravirtualized memory hotunplug part 2
  virtio-mem: Paravirtualized memory hotunplug part 1
  ...

8 files changed, 284 insertions, 13 deletions

diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index fee7fab5d706..375515803cd8 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -318,6 +318,7 @@ extern void try_offline_node(int nid);
 extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages);
 extern int remove_memory(int nid, u64 start, u64 size);
 extern void __remove_memory(int nid, u64 start, u64 size);
+extern int offline_and_remove_memory(int nid, u64 start, u64 size);
 
 #else
 static inline void try_offline_node(int nid) {}
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 222f6f7b2bb3..6be1aa559b1e 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -777,6 +777,16 @@ PAGE_TYPE_OPS(Buddy, buddy)
  * not onlined when onlining the section).
  * The content of these pages is effectively stale. Such pages should not
  * be touched (read/write/dump/save) except by their owner.
+ *
+ * If a driver wants to allow to offline unmovable PageOffline() pages without
+ * putting them back to the buddy, it can do so via the memory notifier by
+ * decrementing the reference count in MEM_GOING_OFFLINE and incrementing the
+ * reference count in MEM_CANCEL_OFFLINE. When offlining, the PageOffline()
+ * pages (now with a reference count of zero) are treated like free pages,
+ * allowing the containing memory block to get offlined. A driver that
+ * relies on this feature is aware that re-onlining the memory block will
+ * require to re-set the pages PageOffline() and not giving them to the
+ * buddy via online_page_callback_t.
  */
 PAGE_TYPE_OPS(Offline, offline)
 
diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h
index 5453af87a33e..239db794357c 100644
--- a/include/linux/vdpa.h
+++ b/include/linux/vdpa.h
@@ -18,6 +18,16 @@ struct vdpa_callback {
 };
 
 /**
+ * vDPA notification area
+ * @addr: base address of the notification area
+ * @size: size of the notification area
+ */
+struct vdpa_notification_area {
+	resource_size_t addr;
+	resource_size_t size;
+};
+
+/**
  * vDPA device - representation of a vDPA device
  * @dev: underlying device
  * @dma_dev: the actual device that is performing DMA
@@ -73,6 +83,10 @@ struct vdpa_device {
  *				@vdev: vdpa device
  *				@idx: virtqueue index
  *				Returns virtqueue state (last_avail_idx)
+ * @get_vq_notification: 	Get the notification area for a virtqueue
+ *				@vdev: vdpa device
+ *				@idx: virtqueue index
+ *				Returns the notifcation area
  * @get_vq_align:		Get the virtqueue align requirement
  *				for the device
  *				@vdev: vdpa device
@@ -162,6 +176,8 @@ struct vdpa_config_ops {
 	bool (*get_vq_ready)(struct vdpa_device *vdev, u16 idx);
 	int (*set_vq_state)(struct vdpa_device *vdev, u16 idx, u64 state);
 	u64 (*get_vq_state)(struct vdpa_device *vdev, u16 idx);
+	struct vdpa_notification_area
+	(*get_vq_notification)(struct vdpa_device *vdev, u16 idx);
 
 	/* Device ops */
 	u32 (*get_vq_align)(struct vdpa_device *vdev);
diff --git a/include/linux/vringh.h b/include/linux/vringh.h
index 9e2763d7c159..59bd50f99291 100644
--- a/include/linux/vringh.h
+++ b/include/linux/vringh.h
@@ -105,9 +105,9 @@ struct vringh_kiov {
 /* Helpers for userspace vrings. */
 int vringh_init_user(struct vringh *vrh, u64 features,
 		     unsigned int num, bool weak_barriers,
-		     struct vring_desc __user *desc,
-		     struct vring_avail __user *avail,
-		     struct vring_used __user *used);
+		     vring_desc_t __user *desc,
+		     vring_avail_t __user *avail,
+		     vring_used_t __user *used);
 
 static inline void vringh_iov_init(struct vringh_iov *iov,
 				   struct iovec *iovec, unsigned num)
diff --git a/include/uapi/linux/vhost.h b/include/uapi/linux/vhost.h
index 9fe72e4b1373..0c2349612e77 100644
--- a/include/uapi/linux/vhost.h
+++ b/include/uapi/linux/vhost.h
@@ -15,6 +15,8 @@
 #include <linux/types.h>
 #include <linux/ioctl.h>
 
+#define VHOST_FILE_UNBIND -1
+
 /* ioctls */
 
 #define VHOST_VIRTIO 0xAF
@@ -140,4 +142,6 @@
 /* Get the max ring size. */
 #define VHOST_VDPA_GET_VRING_NUM	_IOR(VHOST_VIRTIO, 0x76, __u16)
 
+/* Set event fd for config interrupt*/
+#define VHOST_VDPA_SET_CONFIG_CALL	_IOW(VHOST_VIRTIO, 0x77, int)
 #endif
diff --git a/include/uapi/linux/virtio_ids.h b/include/uapi/linux/virtio_ids.h
index ecc27a17401a..b052355ac7a3 100644
--- a/include/uapi/linux/virtio_ids.h
+++ b/include/uapi/linux/virtio_ids.h
@@ -44,6 +44,7 @@
 #define VIRTIO_ID_VSOCK        19 /* virtio vsock transport */
 #define VIRTIO_ID_CRYPTO       20 /* virtio crypto */
 #define VIRTIO_ID_IOMMU        23 /* virtio IOMMU */
+#define VIRTIO_ID_MEM          24 /* virtio mem */
 #define VIRTIO_ID_FS           26 /* virtio filesystem */
 #define VIRTIO_ID_PMEM         27 /* virtio pmem */
 #define VIRTIO_ID_MAC80211_HWSIM 29 /* virtio mac80211-hwsim */
diff --git a/include/uapi/linux/virtio_mem.h b/include/uapi/linux/virtio_mem.h
new file mode 100644
index 000000000000..a9ffe041843c
--- /dev/null
+++ b/include/uapi/linux/virtio_mem.h
@@ -0,0 +1,211 @@
+/* SPDX-License-Identifier: BSD-3-Clause */
+/*
+ * Virtio Mem Device
+ *
+ * Copyright Red Hat, Inc. 2020
+ *
+ * Authors:
+ *     David Hildenbrand <david@redhat.com>
+ *
+ * This header is BSD licensed so anyone can use the definitions
+ * to implement compatible drivers/servers:
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the name of IBM nor the names of its contributors
+ *    may be used to endorse or promote products derived from this software
+ *    without specific prior written permission.
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * ``AS IS'' AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+ * FOR A PARTICULAR PURPOSE ARE DISCLAIMED.  IN NO EVENT SHALL IBM OR
+ * CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF
+ * USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
+ * OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT
+ * OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE.
+ */
+
+#ifndef _LINUX_VIRTIO_MEM_H
+#define _LINUX_VIRTIO_MEM_H
+
+#include <linux/types.h>
+#include <linux/virtio_types.h>
+#include <linux/virtio_ids.h>
+#include <linux/virtio_config.h>
+
+/*
+ * Each virtio-mem device manages a dedicated region in physical address
+ * space. Each device can belong to a single NUMA node, multiple devices
+ * for a single NUMA node are possible. A virtio-mem device is like a
+ * "resizable DIMM" consisting of small memory blocks that can be plugged
+ * or unplugged. The device driver is responsible for (un)plugging memory
+ * blocks on demand.
+ *
+ * Virtio-mem devices can only operate on their assigned memory region in
+ * order to (un)plug memory. A device cannot (un)plug memory belonging to
+ * other devices.
+ *
+ * The "region_size" corresponds to the maximum amount of memory that can
+ * be provided by a device. The "size" corresponds to the amount of memory
+ * that is currently plugged. "requested_size" corresponds to a request
+ * from the device to the device driver to (un)plug blocks. The
+ * device driver should try to (un)plug blocks in order to reach the
+ * "requested_size". It is impossible to plug more memory than requested.
+ *
+ * The "usable_region_size" represents the memory region that can actually
+ * be used to (un)plug memory. It is always at least as big as the
+ * "requested_size" and will grow dynamically. It will only shrink when
+ * explicitly triggered (VIRTIO_MEM_REQ_UNPLUG).
+ *
+ * There are no guarantees what will happen if unplugged memory is
+ * read/written. Such memory should, in general, not be touched. E.g.,
+ * even writing might succeed, but the values will simply be discarded at
+ * random points in time.
+ *
+ * It can happen that the device cannot process a request, because it is
+ * busy. The device driver has to retry later.
+ *
+ * Usually, during system resets all memory will get unplugged, so the
+ * device driver can start with a clean state. However, in specific
+ * scenarios (if the device is busy) it can happen that the device still
+ * has memory plugged. The device driver can request to unplug all memory
+ * (VIRTIO_MEM_REQ_UNPLUG) - which might take a while to succeed if the
+ * device is busy.
+ */
+
+/* --- virtio-mem: feature bits --- */
+
+/* node_id is an ACPI PXM and is valid */
+#define VIRTIO_MEM_F_ACPI_PXM		0
+
+
+/* --- virtio-mem: guest -> host requests --- */
+
+/* request to plug memory blocks */
+#define VIRTIO_MEM_REQ_PLUG			0
+/* request to unplug memory blocks */
+#define VIRTIO_MEM_REQ_UNPLUG			1
+/* request to unplug all blocks and shrink the usable size */
+#define VIRTIO_MEM_REQ_UNPLUG_ALL		2
+/* request information about the plugged state of memory blocks */
+#define VIRTIO_MEM_REQ_STATE			3
+
+struct virtio_mem_req_plug {
+	__virtio64 addr;
+	__virtio16 nb_blocks;
+	__virtio16 padding[3];
+};
+
+struct virtio_mem_req_unplug {
+	__virtio64 addr;
+	__virtio16 nb_blocks;
+	__virtio16 padding[3];
+};
+
+struct virtio_mem_req_state {
+	__virtio64 addr;
+	__virtio16 nb_blocks;
+	__virtio16 padding[3];
+};
+
+struct virtio_mem_req {
+	__virtio16 type;
+	__virtio16 padding[3];
+
+	union {
+		struct virtio_mem_req_plug plug;
+		struct virtio_mem_req_unplug unplug;
+		struct virtio_mem_req_state state;
+	} u;
+};
+
+
+/* --- virtio-mem: host -> guest response --- */
+
+/*
+ * Request processed successfully, applicable for
+ * - VIRTIO_MEM_REQ_PLUG
+ * - VIRTIO_MEM_REQ_UNPLUG
+ * - VIRTIO_MEM_REQ_UNPLUG_ALL
+ * - VIRTIO_MEM_REQ_STATE
+ */
+#define VIRTIO_MEM_RESP_ACK			0
+/*
+ * Request denied - e.g. trying to plug more than requested, applicable for
+ * - VIRTIO_MEM_REQ_PLUG
+ */
+#define VIRTIO_MEM_RESP_NACK			1
+/*
+ * Request cannot be processed right now, try again later, applicable for
+ * - VIRTIO_MEM_REQ_PLUG
+ * - VIRTIO_MEM_REQ_UNPLUG
+ * - VIRTIO_MEM_REQ_UNPLUG_ALL
+ */
+#define VIRTIO_MEM_RESP_BUSY			2
+/*
+ * Error in request (e.g. addresses/alignment), applicable for
+ * - VIRTIO_MEM_REQ_PLUG
+ * - VIRTIO_MEM_REQ_UNPLUG
+ * - VIRTIO_MEM_REQ_STATE
+ */
+#define VIRTIO_MEM_RESP_ERROR			3
+
+
+/* State of memory blocks is "plugged" */
+#define VIRTIO_MEM_STATE_PLUGGED		0
+/* State of memory blocks is "unplugged" */
+#define VIRTIO_MEM_STATE_UNPLUGGED		1
+/* State of memory blocks is "mixed" */
+#define VIRTIO_MEM_STATE_MIXED			2
+
+struct virtio_mem_resp_state {
+	__virtio16 state;
+};
+
+struct virtio_mem_resp {
+	__virtio16 type;
+	__virtio16 padding[3];
+
+	union {
+		struct virtio_mem_resp_state state;
+	} u;
+};
+
+/* --- virtio-mem: configuration --- */
+
+struct virtio_mem_config {
+	/* Block size and alignment. Cannot change. */
+	__u64 block_size;
+	/* Valid with VIRTIO_MEM_F_ACPI_PXM. Cannot change. */
+	__u16 node_id;
+	__u8 padding[6];
+	/* Start address of the memory region. Cannot change. */
+	__u64 addr;
+	/* Region size (maximum). Cannot change. */
+	__u64 region_size;
+	/*
+	 * Currently usable region size. Can grow up to region_size. Can
+	 * shrink due to VIRTIO_MEM_REQ_UNPLUG_ALL (in which case no config
+	 * update will be sent).
+	 */
+	__u64 usable_region_size;
+	/*
+	 * Currently used size. Changes due to plug/unplug requests, but no
+	 * config updates will be sent.
+	 */
+	__u64 plugged_size;
+	/* Requested size. New plug requests cannot exceed it. Can change. */
+	__u64 requested_size;
+};
+
+#endif /* _LINUX_VIRTIO_MEM_H */
diff --git a/include/uapi/linux/virtio_ring.h b/include/uapi/linux/virtio_ring.h
index 559f42e73315..476d3e5c0fe7 100644
--- a/include/uapi/linux/virtio_ring.h
+++ b/include/uapi/linux/virtio_ring.h
@@ -86,6 +86,13 @@
  * at the end of the used ring. Guest should ignore the used->flags field. */
 #define VIRTIO_RING_F_EVENT_IDX		29
 
+/* Alignment requirements for vring elements.
+ * When using pre-virtio 1.0 layout, these fall out naturally.
+ */
+#define VRING_AVAIL_ALIGN_SIZE 2
+#define VRING_USED_ALIGN_SIZE 4
+#define VRING_DESC_ALIGN_SIZE 16
+
 /* Virtio ring descriptors: 16 bytes.  These can chain together via "next". */
 struct vring_desc {
 	/* Address (guest-physical). */
@@ -112,28 +119,47 @@ struct vring_used_elem {
 	__virtio32 len;
 };
 
+typedef struct vring_used_elem __attribute__((aligned(VRING_USED_ALIGN_SIZE)))
+	vring_used_elem_t;
+
 struct vring_used {
 	__virtio16 flags;
 	__virtio16 idx;
-	struct vring_used_elem ring[];
+	vring_used_elem_t ring[];
 };
 
+/*
+ * The ring element addresses are passed between components with different
+ * alignments assumptions. Thus, we might need to decrease the compiler-selected
+ * alignment, and so must use a typedef to make sure the aligned attribute
+ * actually takes hold:
+ *
+ * https://gcc.gnu.org/onlinedocs//gcc/Common-Type-Attributes.html#Common-Type-Attributes
+ *
+ * When used on a struct, or struct member, the aligned attribute can only
+ * increase the alignment; in order to decrease it, the packed attribute must
+ * be specified as well. When used as part of a typedef, the aligned attribute
+ * can both increase and decrease alignment, and specifying the packed
+ * attribute generates a warning.
+ */
+typedef struct vring_desc __attribute__((aligned(VRING_DESC_ALIGN_SIZE)))
+	vring_desc_t;
+typedef struct vring_avail __attribute__((aligned(VRING_AVAIL_ALIGN_SIZE)))
+	vring_avail_t;
+typedef struct vring_used __attribute__((aligned(VRING_USED_ALIGN_SIZE)))
+	vring_used_t;
+
 struct vring {
 	unsigned int num;
 
-	struct vring_desc *desc;
+	vring_desc_t *desc;
 
-	struct vring_avail *avail;
+	vring_avail_t *avail;
 
-	struct vring_used *used;
+	vring_used_t *used;
 };
 
-/* Alignment requirements for vring elements.
- * When using pre-virtio 1.0 layout, these fall out naturally.
- */
-#define VRING_AVAIL_ALIGN_SIZE 2
-#define VRING_USED_ALIGN_SIZE 4
-#define VRING_DESC_ALIGN_SIZE 16
+#ifndef VIRTIO_RING_NO_LEGACY
 
 /* The standard layout for the ring is a continuous chunk of memory which looks
  * like this.  We assume num is a power of 2.
@@ -181,6 +207,8 @@ static inline unsigned vring_size(unsigned int num, unsigned long align)
 		+ sizeof(__virtio16) * 3 + sizeof(struct vring_used_elem) * num;
 }
 
+#endif /* VIRTIO_RING_NO_LEGACY */
+
 /* The following is used with USED_EVENT_IDX and AVAIL_EVENT_IDX */
 /* Assuming a given event_idx value from the other side, if
  * we have just incremented index from old to new_idx,