[PATCH v2 5/5] mm/hmm/test: use the new migration invalidation

From: Ralph Campbell <rcampbell@nvidia.com>
To: <linux-rdma@vger.kernel.org>, <linux-mm@kvack.org>,
	<nouveau@lists.freedesktop.org>, <kvm-ppc@vger.kernel.org>,
	<linux-kselftest@vger.kernel.org>, <linux-kernel@vger.kernel.org>
Cc: Jerome Glisse <jglisse@redhat.com>,
	John Hubbard <jhubbard@nvidia.com>,
	Christoph Hellwig <hch@lst.de>,
	Jason Gunthorpe <jgg@mellanox.com>,
	"Andrew Morton" <akpm@linux-foundation.org>,
	Shuah Khan <shuah@kernel.org>, "Ben Skeggs" <bskeggs@redhat.com>,
	Bharata B Rao <bharata@linux.ibm.com>,
	"Ralph Campbell" <rcampbell@nvidia.com>
Subject: [PATCH v2 5/5] mm/hmm/test: use the new migration invalidation
Date: Mon, 13 Jul 2020 10:21:49 -0700	[thread overview]
Message-ID: <20200713172149.2310-6-rcampbell@nvidia.com> (raw)
In-Reply-To: <20200713172149.2310-1-rcampbell@nvidia.com>

Use the new MMU_NOTIFY_MIGRATE event to skip MMU invalidations of device
private memory and handle the invalidation in the driver as part of
migrating device private memory.

Signed-off-by: Ralph Campbell <rcampbell@nvidia.com>
---
 lib/test_hmm.c | 31 ++++++++++++++++++-------------
 1 file changed, 18 insertions(+), 13 deletions(-)

diff --git a/lib/test_hmm.c b/lib/test_hmm.c
index 1bd60cfb5a25..77875fc4e7c1 100644
--- a/lib/test_hmm.c
+++ b/lib/test_hmm.c
@@ -214,6 +214,14 @@ static bool dmirror_interval_invalidate(struct mmu_interval_notifier *mni,
 {
 	struct dmirror *dmirror = container_of(mni, struct dmirror, notifier);
 
+	/*
+	 * Ignore invalidation callbacks for device private pages since
+	 * the invalidation is handled as part of the migration process.
+	 */
+	if (range->event == MMU_NOTIFY_MIGRATE &&
+	    range->migrate_pgmap_owner == dmirror->mdevice)
+		return true;
+
 	if (mmu_notifier_range_blockable(range))
 		mutex_lock(&dmirror->mutex);
 	else if (!mutex_trylock(&dmirror->mutex))
@@ -702,7 +710,7 @@ static int dmirror_migrate(struct dmirror *dmirror,
 		args.dst = dst_pfns;
 		args.start = addr;
 		args.end = next;
-		args.src_owner = NULL;
+		args.src_owner = dmirror->mdevice;
 		args.dir = MIGRATE_VMA_FROM_SYSTEM;
 		ret = migrate_vma_setup(&args);
 		if (ret)
@@ -992,7 +1000,7 @@ static void dmirror_devmem_free(struct page *page)
 }
 
 static vm_fault_t dmirror_devmem_fault_alloc_and_copy(struct migrate_vma *args,
-						struct dmirror_device *mdevice)
+						      struct dmirror *dmirror)
 {
 	const unsigned long *src = args->src;
 	unsigned long *dst = args->dst;
@@ -1014,6 +1022,7 @@ static vm_fault_t dmirror_devmem_fault_alloc_and_copy(struct migrate_vma *args,
 			continue;
 
 		lock_page(dpage);
+		xa_erase(&dmirror->pt, addr >> PAGE_SHIFT);
 		copy_highpage(dpage, spage);
 		*dst = migrate_pfn(page_to_pfn(dpage)) | MIGRATE_PFN_LOCKED;
 		if (*src & MIGRATE_PFN_WRITE)
@@ -1022,15 +1031,6 @@ static vm_fault_t dmirror_devmem_fault_alloc_and_copy(struct migrate_vma *args,
 	return 0;
 }
 
-static void dmirror_devmem_fault_finalize_and_map(struct migrate_vma *args,
-						  struct dmirror *dmirror)
-{
-	/* Invalidate the device's page table mapping. */
-	mutex_lock(&dmirror->mutex);
-	dmirror_do_update(dmirror, args->start, args->end);
-	mutex_unlock(&dmirror->mutex);
-}
-
 static vm_fault_t dmirror_devmem_fault(struct vm_fault *vmf)
 {
 	struct migrate_vma args;
@@ -1060,11 +1060,16 @@ static vm_fault_t dmirror_devmem_fault(struct vm_fault *vmf)
 	if (migrate_vma_setup(&args))
 		return VM_FAULT_SIGBUS;
 
-	ret = dmirror_devmem_fault_alloc_and_copy(&args, dmirror->mdevice);
+	ret = dmirror_devmem_fault_alloc_and_copy(&args, dmirror);
 	if (ret)
 		return ret;
 	migrate_vma_pages(&args);
-	dmirror_devmem_fault_finalize_and_map(&args, dmirror);
+	/*
+	 * No device finalize step is needed since
+	 * dmirror_devmem_fault_alloc_and_copy() will have already
+	 * invalidated the device page table. We could reinstate device MMU
+	 * entries for pages that didn't migrate but that should be rare.
+	 */
 	migrate_vma_finalize(&args);
 	return 0;
 }
-- 
2.20.1

