Merge tag 'for-linus-5.6-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip

Pull xen updates from Juergen Gross:

 - fix a bug introduced in 5.5 in the Xen gntdev driver

 - fix the Xen balloon driver when running on ancient Xen versions

 - allow Xen stubdoms to control interrupt enable flags of
   passed-through PCI cards

 - release resources in Xen backends under memory pressure

* tag 'for-linus-5.6-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip:
  xen/blkback: Consistently insert one empty line between functions
  xen/blkback: Remove unnecessary static variable name prefixes
  xen/blkback: Squeeze page pools if a memory pressure is detected
  xenbus/backend: Protect xenbus callback with lock
  xenbus/backend: Add memory pressure handler callback
  xen/gntdev: Do not use mm notifiers with autotranslating guests
  xen/balloon: Support xend-based toolstack take two
  xen-pciback: optionally allow interrupt enable flag writes

Author: torvalds

Documentation/ABI/testing/sysfs-driver-pciback

@@ -11,3 +11,16 @@ Description:
                 #echo 00:19.0-E0:2:FF > /sys/bus/pci/drivers/pciback/quirks
                 will allow the guest to read and write to the configuration
                 register 0x0E.
+
+What:           /sys/bus/pci/drivers/pciback/allow_interrupt_control
+Date:           Jan 2020
+KernelVersion:  5.6
+Contact:        [email protected]
+Description:
+                List of devices which can have interrupt control flag (INTx,
+                MSI, MSI-X) set by a connected guest. It is meant to be set
+                only when the guest is a stubdomain hosting device model (qemu)
+                and the actual device is assigned to a HVM. It is not safe
+                (similar to permissive attribute) to set for a devices assigned
+                to a PV guest. The device is automatically removed from this
+                list when the connected pcifront terminates.

Documentation/ABI/testing/sysfs-driver-xen-blkback

@@ -25,3 +25,13 @@ Description:
                 allocated without being in use. The time is in
                 seconds, 0 means indefinitely long.
                 The default is 60 seconds.
+
+What:           /sys/module/xen_blkback/parameters/buffer_squeeze_duration_ms
+Date:           December 2019
+KernelVersion:  5.6
+Contact:        SeongJae Park <[email protected]>
+Description:
+                When memory pressure is reported to blkback this option
+                controls the duration in milliseconds that blkback will not
+                cache any page not backed by a grant mapping.
+                The default is 10ms.

drivers/block/xen-blkback/blkback.c

@@ -62,8 +62,8 @@
  * IO workloads.
  */
 
-static int xen_blkif_max_buffer_pages = 1024;
-module_param_named(max_buffer_pages, xen_blkif_max_buffer_pages, int, 0644);
+static int max_buffer_pages = 1024;
+module_param_named(max_buffer_pages, max_buffer_pages, int, 0644);
 MODULE_PARM_DESC(max_buffer_pages,
 "Maximum number of free pages to keep in each block backend buffer");
 
@@ -78,8 +78,8 @@ MODULE_PARM_DESC(max_buffer_pages,
  * algorithm.
  */
 
-static int xen_blkif_max_pgrants = 1056;
-module_param_named(max_persistent_grants, xen_blkif_max_pgrants, int, 0644);
+static int max_pgrants = 1056;
+module_param_named(max_persistent_grants, max_pgrants, int, 0644);
 MODULE_PARM_DESC(max_persistent_grants,
                  "Maximum number of grants to map persistently");
 
@@ -88,8 +88,8 @@ MODULE_PARM_DESC(max_persistent_grants,
  * use. The time is in seconds, 0 means indefinitely long.
  */
 
-static unsigned int xen_blkif_pgrant_timeout = 60;
-module_param_named(persistent_grant_unused_seconds, xen_blkif_pgrant_timeout,
+static unsigned int pgrant_timeout = 60;
+module_param_named(persistent_grant_unused_seconds, pgrant_timeout,
 		   uint, 0644);
 MODULE_PARM_DESC(persistent_grant_unused_seconds,
 		 "Time in seconds an unused persistent grant is allowed to "
@@ -137,9 +137,8 @@ module_param(log_stats, int, 0644);
 
 static inline bool persistent_gnt_timeout(struct persistent_gnt *persistent_gnt)
 {
-	return xen_blkif_pgrant_timeout &&
-	       (jiffies - persistent_gnt->last_used >=
-		HZ * xen_blkif_pgrant_timeout);
+	return pgrant_timeout && (jiffies - persistent_gnt->last_used >=
+			HZ * pgrant_timeout);
 }
 
 static inline int get_free_page(struct xen_blkif_ring *ring, struct page **page)
@@ -234,7 +233,7 @@ static int add_persistent_gnt(struct xen_blkif_ring *ring,
 	struct persistent_gnt *this;
 	struct xen_blkif *blkif = ring->blkif;
 
-	if (ring->persistent_gnt_c >= xen_blkif_max_pgrants) {
+	if (ring->persistent_gnt_c >= max_pgrants) {
 		if (!blkif->vbd.overflow_max_grants)
 			blkif->vbd.overflow_max_grants = 1;
 		return -EBUSY;
@@ -397,14 +396,13 @@ static void purge_persistent_gnt(struct xen_blkif_ring *ring)
 		goto out;
 	}
 
-	if (ring->persistent_gnt_c < xen_blkif_max_pgrants ||
-	    (ring->persistent_gnt_c == xen_blkif_max_pgrants &&
+	if (ring->persistent_gnt_c < max_pgrants ||
+	    (ring->persistent_gnt_c == max_pgrants &&
 	    !ring->blkif->vbd.overflow_max_grants)) {
 		num_clean = 0;
 	} else {
-		num_clean = (xen_blkif_max_pgrants / 100) * LRU_PERCENT_CLEAN;
-		num_clean = ring->persistent_gnt_c - xen_blkif_max_pgrants +
-			    num_clean;
+		num_clean = (max_pgrants / 100) * LRU_PERCENT_CLEAN;
+		num_clean = ring->persistent_gnt_c - max_pgrants + num_clean;
 		num_clean = min(ring->persistent_gnt_c, num_clean);
 		pr_debug("Going to purge at least %u persistent grants\n",
 			 num_clean);
@@ -599,8 +597,7 @@ static void print_stats(struct xen_blkif_ring *ring)
 		 current->comm, ring->st_oo_req,
 		 ring->st_rd_req, ring->st_wr_req,
 		 ring->st_f_req, ring->st_ds_req,
-		 ring->persistent_gnt_c,
-		 xen_blkif_max_pgrants);
+		 ring->persistent_gnt_c, max_pgrants);
 	ring->st_print = jiffies + msecs_to_jiffies(10 * 1000);
 	ring->st_rd_req = 0;
 	ring->st_wr_req = 0;
@@ -656,8 +653,11 @@ int xen_blkif_schedule(void *arg)
 			ring->next_lru = jiffies + msecs_to_jiffies(LRU_INTERVAL);
 		}
 
-		/* Shrink if we have more than xen_blkif_max_buffer_pages */
-		shrink_free_pagepool(ring, xen_blkif_max_buffer_pages);
+		/* Shrink the free pages pool if it is too large. */
+		if (time_before(jiffies, blkif->buffer_squeeze_end))
+			shrink_free_pagepool(ring, 0);
+		else
+			shrink_free_pagepool(ring, max_buffer_pages);
 
 		if (log_stats && time_after(jiffies, ring->st_print))
 			print_stats(ring);
@@ -884,7 +884,7 @@ static int xen_blkbk_map(struct xen_blkif_ring *ring,
 			continue;
 		}
 		if (use_persistent_gnts &&
-		    ring->persistent_gnt_c < xen_blkif_max_pgrants) {
+		    ring->persistent_gnt_c < max_pgrants) {
 			/*
 			 * We are using persistent grants, the grant is
 			 * not mapped but we might have room for it.
@@ -911,7 +911,7 @@ static int xen_blkbk_map(struct xen_blkif_ring *ring,
 			pages[seg_idx]->persistent_gnt = persistent_gnt;
 			pr_debug("grant %u added to the tree of persistent grants, using %u/%u\n",
 				 persistent_gnt->gnt, ring->persistent_gnt_c,
-				 xen_blkif_max_pgrants);
+				 max_pgrants);
 			goto next;
 		}
 		if (use_persistent_gnts && !blkif->vbd.overflow_max_grants) {

drivers/block/xen-blkback/common.h

@@ -319,6 +319,7 @@ struct xen_blkif {
 	/* All rings for this device. */
 	struct xen_blkif_ring	*rings;
 	unsigned int		nr_rings;
+	unsigned long		buffer_squeeze_end;
 };
 
 struct seg_buf {

drivers/block/xen-blkback/xenbus.c

@@ -467,7 +467,6 @@ static void xenvbd_sysfs_delif(struct xenbus_device *dev)
 	device_remove_file(&dev->dev, &dev_attr_physical_device);
 }
 
-
 static void xen_vbd_free(struct xen_vbd *vbd)
 {
 	if (vbd->bdev)
@@ -524,6 +523,7 @@ static int xen_vbd_create(struct xen_blkif *blkif, blkif_vdev_t handle,
 		handle, blkif->domid);
 	return 0;
 }
+
 static int xen_blkbk_remove(struct xenbus_device *dev)
 {
 	struct backend_info *be = dev_get_drvdata(&dev->dev);
@@ -607,6 +607,7 @@ static void xen_blkbk_discard(struct xenbus_transaction xbt, struct backend_info
 	if (err)
 		dev_warn(&dev->dev, "writing feature-discard (%d)", err);
 }
+
 int xen_blkbk_barrier(struct xenbus_transaction xbt,
 		      struct backend_info *be, int state)
 {
@@ -691,7 +692,6 @@ static int xen_blkbk_probe(struct xenbus_device *dev,
 	return err;
 }
 
-
 /*
  * Callback received when the hotplug scripts have placed the physical-device
  * node.  Read it and the mode node, and create a vbd.  If the frontend is
@@ -783,7 +783,6 @@ static void backend_changed(struct xenbus_watch *watch,
 	}
 }
 
-
 /*
  * Callback received when the frontend's state changes.
  */
@@ -858,9 +857,27 @@ static void frontend_changed(struct xenbus_device *dev,
 	}
 }
 
+/* Once a memory pressure is detected, squeeze free page pools for a while. */
+static unsigned int buffer_squeeze_duration_ms = 10;
+module_param_named(buffer_squeeze_duration_ms,
+		buffer_squeeze_duration_ms, int, 0644);
+MODULE_PARM_DESC(buffer_squeeze_duration_ms,
+"Duration in ms to squeeze pages buffer when a memory pressure is detected");
 
-/* ** Connection ** */
+/*
+ * Callback received when the memory pressure is detected.
+ */
+static void reclaim_memory(struct xenbus_device *dev)
+{
+	struct backend_info *be = dev_get_drvdata(&dev->dev);
 
+	if (!be)
+		return;
+	be->blkif->buffer_squeeze_end = jiffies +
+		msecs_to_jiffies(buffer_squeeze_duration_ms);
+}
+
+/* ** Connection ** */
 
 /*
  * Write the physical details regarding the block device to the store, and
@@ -1152,6 +1169,7 @@ static struct xenbus_driver xen_blkbk_driver = {
 	.remove = xen_blkbk_remove,
 	.otherend_changed = frontend_changed,
 	.allow_rebind = true,
+	.reclaim_memory = reclaim_memory,
 };
 
 int xen_blkif_xenbus_init(void)

drivers/xen/gntdev.c

@@ -1006,19 +1006,19 @@ static int gntdev_mmap(struct file *flip, struct vm_area_struct *vma)
 	}
 	mutex_unlock(&priv->lock);
 
-	/*
-	 * gntdev takes the address of the PTE in find_grant_ptes() and passes
-	 * it to the hypervisor in gntdev_map_grant_pages(). The purpose of
-	 * the notifier is to prevent the hypervisor pointer to the PTE from
-	 * going stale.
-	 *
-	 * Since this vma's mappings can't be touched without the mmap_sem,
-	 * and we are holding it now, there is no need for the notifier_range
-	 * locking pattern.
-	 */
-	mmu_interval_read_begin(&map->notifier);
-
 	if (use_ptemod) {
+		/*
+		 * gntdev takes the address of the PTE in find_grant_ptes() and
+		 * passes it to the hypervisor in gntdev_map_grant_pages(). The
+		 * purpose of the notifier is to prevent the hypervisor pointer
+		 * to the PTE from going stale.
+		 *
+		 * Since this vma's mappings can't be touched without the
+		 * mmap_sem, and we are holding it now, there is no need for
+		 * the notifier_range locking pattern.
+		 */
+		mmu_interval_read_begin(&map->notifier);
+
 		map->pages_vm_start = vma->vm_start;
 		err = apply_to_page_range(vma->vm_mm, vma->vm_start,
 					  vma->vm_end - vma->vm_start,

drivers/xen/xen-balloon.c

@@ -94,7 +94,7 @@ static void watch_target(struct xenbus_watch *watch,
 				  "%llu", &static_max) == 1))
 			static_max >>= PAGE_SHIFT - 10;
 		else
-			static_max = new_target;
+			static_max = balloon_stats.current_pages;
 
 		target_diff = (xen_pv_domain() || xen_initial_domain()) ? 0
 				: static_max - balloon_stats.target_pages;

drivers/xen/xen-pciback/conf_space.c

@@ -286,6 +286,43 @@ int xen_pcibk_config_write(struct pci_dev *dev, int offset, int size, u32 value)
 	return xen_pcibios_err_to_errno(err);
 }
 
+int xen_pcibk_get_interrupt_type(struct pci_dev *dev)
+{
+	int err;
+	u16 val;
+	int ret = 0;
+
+	err = pci_read_config_word(dev, PCI_COMMAND, &val);
+	if (err)
+		return err;
+	if (!(val & PCI_COMMAND_INTX_DISABLE))
+		ret |= INTERRUPT_TYPE_INTX;
+
+	/*
+	 * Do not trust dev->msi(x)_enabled here, as enabling could be done
+	 * bypassing the pci_*msi* functions, by the qemu.
+	 */
+	if (dev->msi_cap) {
+		err = pci_read_config_word(dev,
+				dev->msi_cap + PCI_MSI_FLAGS,
+				&val);
+		if (err)
+			return err;
+		if (val & PCI_MSI_FLAGS_ENABLE)
+			ret |= INTERRUPT_TYPE_MSI;
+	}
+	if (dev->msix_cap) {
+		err = pci_read_config_word(dev,
+				dev->msix_cap + PCI_MSIX_FLAGS,
+				&val);
+		if (err)
+			return err;
+		if (val & PCI_MSIX_FLAGS_ENABLE)
+			ret |= INTERRUPT_TYPE_MSIX;
+	}
+	return ret;
+}
+
 void xen_pcibk_config_free_dyn_fields(struct pci_dev *dev)
 {
 	struct xen_pcibk_dev_data *dev_data = pci_get_drvdata(dev);

drivers/xen/xen-pciback/conf_space.h

@@ -65,6 +65,11 @@ struct config_field_entry {
 	void *data;
 };
 
+#define INTERRUPT_TYPE_NONE (1<<0)
+#define INTERRUPT_TYPE_INTX (1<<1)
+#define INTERRUPT_TYPE_MSI  (1<<2)
+#define INTERRUPT_TYPE_MSIX (1<<3)
+
 extern bool xen_pcibk_permissive;
 
 #define OFFSET(cfg_entry) ((cfg_entry)->base_offset+(cfg_entry)->field->offset)
@@ -126,4 +131,6 @@ int xen_pcibk_config_capability_init(void);
 int xen_pcibk_config_header_add_fields(struct pci_dev *dev);
 int xen_pcibk_config_capability_add_fields(struct pci_dev *dev);
 
+int xen_pcibk_get_interrupt_type(struct pci_dev *dev);
+
 #endif				/* __XEN_PCIBACK_CONF_SPACE_H__ */