Merge tag 'for-linus-5.9-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip

Pull xen updates from Juergen Gross:

 - two trivial comment fixes

 - a small series for the Xen balloon driver fixing some issues

 - a series of the Xen privcmd driver targeting elimination of using
   get_user_pages*() in this driver

 - a series for the Xen swiotlb driver cleaning it up and adding support
   for letting the kernel run as dom0 on Rpi4

* tag 'for-linus-5.9-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip:
  xen/arm: call dma_to_phys on the dma_addr_t parameter of dma_cache_maint
  xen/arm: introduce phys/dma translations in xen_dma_sync_for_*
  swiotlb-xen: introduce phys_to_dma/dma_to_phys translations
  swiotlb-xen: remove XEN_PFN_PHYS
  swiotlb-xen: add struct device * parameter to is_xen_swiotlb_buffer
  swiotlb-xen: add struct device * parameter to xen_dma_sync_for_device
  swiotlb-xen: add struct device * parameter to xen_dma_sync_for_cpu
  swiotlb-xen: add struct device * parameter to xen_bus_to_phys
  swiotlb-xen: add struct device * parameter to xen_phys_to_bus
  swiotlb-xen: remove start_dma_addr
  swiotlb-xen: use vmalloc_to_page on vmalloc virt addresses
  Revert "xen/balloon: Fix crash when ballooning on x86 32 bit PAE"
  xen/balloon: make the balloon wait interruptible
  xen/balloon: fix accounting in alloc_xenballooned_pages error path
  xen: hypercall.h: fix duplicated word
  xen/gntdev: gntdev.h: drop a duplicated word
  xen/privcmd: Convert get_user_pages*() to pin_user_pages*()
  xen/privcmd: Mark pages as dirty
  xen/privcmd: Corrected error handling path

Author: torvalds

arch/arm/xen/mm.c

@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 #include <linux/cpu.h>
+#include <linux/dma-direct.h>
 #include <linux/dma-noncoherent.h>
 #include <linux/gfp.h>
 #include <linux/highmem.h>
@@ -42,15 +43,18 @@ unsigned long xen_get_swiotlb_free_pages(unsigned int order)
 static bool hypercall_cflush = false;
 
 /* buffers in highmem or foreign pages cannot cross page boundaries */
-static void dma_cache_maint(dma_addr_t handle, size_t size, u32 op)
+static void dma_cache_maint(struct device *dev, dma_addr_t handle,
+			    size_t size, u32 op)
 {
 	struct gnttab_cache_flush cflush;
 
-	cflush.a.dev_bus_addr = handle & XEN_PAGE_MASK;
 	cflush.offset = xen_offset_in_page(handle);
 	cflush.op = op;
+	handle &= XEN_PAGE_MASK;
 
 	do {
+		cflush.a.dev_bus_addr = dma_to_phys(dev, handle);
+
 		if (size + cflush.offset > XEN_PAGE_SIZE)
 			cflush.length = XEN_PAGE_SIZE - cflush.offset;
 		else
@@ -59,7 +63,7 @@ static void dma_cache_maint(dma_addr_t handle, size_t size, u32 op)
 		HYPERVISOR_grant_table_op(GNTTABOP_cache_flush, &cflush, 1);
 
 		cflush.offset = 0;
-		cflush.a.dev_bus_addr += cflush.length;
+		handle += cflush.length;
 		size -= cflush.length;
 	} while (size);
 }
@@ -71,32 +75,28 @@ static void dma_cache_maint(dma_addr_t handle, size_t size, u32 op)
  * pfn_valid returns true the pages is local and we can use the native
  * dma-direct functions, otherwise we call the Xen specific version.
  */
-void xen_dma_sync_for_cpu(dma_addr_t handle, phys_addr_t paddr, size_t size,
-		enum dma_data_direction dir)
+void xen_dma_sync_for_cpu(struct device *dev, dma_addr_t handle,
+			  size_t size, enum dma_data_direction dir)
 {
-	if (pfn_valid(PFN_DOWN(handle)))
-		arch_sync_dma_for_cpu(paddr, size, dir);
-	else if (dir != DMA_TO_DEVICE)
-		dma_cache_maint(handle, size, GNTTAB_CACHE_INVAL);
+	if (dir != DMA_TO_DEVICE)
+		dma_cache_maint(dev, handle, size, GNTTAB_CACHE_INVAL);
 }
 
-void xen_dma_sync_for_device(dma_addr_t handle, phys_addr_t paddr, size_t size,
-		enum dma_data_direction dir)
+void xen_dma_sync_for_device(struct device *dev, dma_addr_t handle,
+			     size_t size, enum dma_data_direction dir)
 {
-	if (pfn_valid(PFN_DOWN(handle)))
-		arch_sync_dma_for_device(paddr, size, dir);
-	else if (dir == DMA_FROM_DEVICE)
-		dma_cache_maint(handle, size, GNTTAB_CACHE_INVAL);
+	if (dir == DMA_FROM_DEVICE)
+		dma_cache_maint(dev, handle, size, GNTTAB_CACHE_INVAL);
 	else
-		dma_cache_maint(handle, size, GNTTAB_CACHE_CLEAN);
+		dma_cache_maint(dev, handle, size, GNTTAB_CACHE_CLEAN);
 }
 
 bool xen_arch_need_swiotlb(struct device *dev,
 			   phys_addr_t phys,
 			   dma_addr_t dev_addr)
 {
 	unsigned int xen_pfn = XEN_PFN_DOWN(phys);
-	unsigned int bfn = XEN_PFN_DOWN(dev_addr);
+	unsigned int bfn = XEN_PFN_DOWN(dma_to_phys(dev, dev_addr));
 
 	/*
 	 * The swiotlb buffer should be used if

arch/x86/include/asm/xen/hypercall.h

@@ -82,7 +82,7 @@ struct xen_dm_op_buf;
  *     - clobber the rest
  *
  * The result certainly isn't pretty, and it really shows up cpp's
- * weakness as as macro language.  Sorry.  (But let's just give thanks
+ * weakness as a macro language.  Sorry.  (But let's just give thanks
  * there aren't more than 5 arguments...)
  */
 

drivers/xen/balloon.c

@@ -266,20 +266,6 @@ static struct resource *additional_memory_resource(phys_addr_t size)
 		return NULL;
 	}
 
-#ifdef CONFIG_SPARSEMEM
-	{
-		unsigned long limit = 1UL << (MAX_PHYSMEM_BITS - PAGE_SHIFT);
-		unsigned long pfn = res->start >> PAGE_SHIFT;
-
-		if (pfn > limit) {
-			pr_err("New System RAM resource outside addressable RAM (%lu > %lu)\n",
-			       pfn, limit);
-			release_memory_resource(res);
-			return NULL;
-		}
-	}
-#endif
-
 	return res;
 }
 
@@ -568,11 +554,13 @@ static int add_ballooned_pages(int nr_pages)
 	if (xen_hotplug_unpopulated) {
 		st = reserve_additional_memory();
 		if (st != BP_ECANCELED) {
+			int rc;
+
 			mutex_unlock(&balloon_mutex);
-			wait_event(balloon_wq,
+			rc = wait_event_interruptible(balloon_wq,
 				   !list_empty(&ballooned_pages));
 			mutex_lock(&balloon_mutex);
-			return 0;
+			return rc ? -ENOMEM : 0;
 		}
 	}
 
@@ -630,6 +618,12 @@ int alloc_xenballooned_pages(int nr_pages, struct page **pages)
  out_undo:
 	mutex_unlock(&balloon_mutex);
 	free_xenballooned_pages(pgno, pages);
+	/*
+	 * NB: free_xenballooned_pages will only subtract pgno pages, but since
+	 * target_unpopulated is incremented with nr_pages at the start we need
+	 * to remove the remaining ones also, or accounting will be screwed.
+	 */
+	balloon_stats.target_unpopulated -= nr_pages - pgno;
 	return ret;
 }
 EXPORT_SYMBOL(alloc_xenballooned_pages);

drivers/xen/privcmd.c

@@ -580,44 +580,37 @@ static long privcmd_ioctl_mmap_batch(
 
 static int lock_pages(
 	struct privcmd_dm_op_buf kbufs[], unsigned int num,
-	struct page *pages[], unsigned int nr_pages)
+	struct page *pages[], unsigned int nr_pages, unsigned int *pinned)
 {
 	unsigned int i;
 
 	for (i = 0; i < num; i++) {
 		unsigned int requested;
-		int pinned;
+		int page_count;
 
 		requested = DIV_ROUND_UP(
 			offset_in_page(kbufs[i].uptr) + kbufs[i].size,
 			PAGE_SIZE);
 		if (requested > nr_pages)
 			return -ENOSPC;
 
-		pinned = get_user_pages_fast(
+		page_count = pin_user_pages_fast(
 			(unsigned long) kbufs[i].uptr,
 			requested, FOLL_WRITE, pages);
-		if (pinned < 0)
-			return pinned;
+		if (page_count < 0)
+			return page_count;
 
-		nr_pages -= pinned;
-		pages += pinned;
+		*pinned += page_count;
+		nr_pages -= page_count;
+		pages += page_count;
 	}
 
 	return 0;
 }
 
 static void unlock_pages(struct page *pages[], unsigned int nr_pages)
 {
-	unsigned int i;
-
-	if (!pages)
-		return;
-
-	for (i = 0; i < nr_pages; i++) {
-		if (pages[i])
-			put_page(pages[i]);
-	}
+	unpin_user_pages_dirty_lock(pages, nr_pages, true);
 }
 
 static long privcmd_ioctl_dm_op(struct file *file, void __user *udata)
@@ -630,6 +623,7 @@ static long privcmd_ioctl_dm_op(struct file *file, void __user *udata)
 	struct xen_dm_op_buf *xbufs = NULL;
 	unsigned int i;
 	long rc;
+	unsigned int pinned = 0;
 
 	if (copy_from_user(&kdata, udata, sizeof(kdata)))
 		return -EFAULT;
@@ -683,9 +677,11 @@ static long privcmd_ioctl_dm_op(struct file *file, void __user *udata)
 		goto out;
 	}
 
-	rc = lock_pages(kbufs, kdata.num, pages, nr_pages);
-	if (rc)
+	rc = lock_pages(kbufs, kdata.num, pages, nr_pages, &pinned);
+	if (rc < 0) {
+		nr_pages = pinned;
 		goto out;
+	}
 
 	for (i = 0; i < kdata.num; i++) {
 		set_xen_guest_handle(xbufs[i].h, kbufs[i].uptr);