Received-SPF: pass (google.com: domain of linux-ext4-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
Received-SPF: Pass (protection.outlook.com: domain of amd.com designates
 165.204.84.17 as permitted sender) receiver=protection.outlook.com;
 client-ip=165.204.84.17; helo=SATLEXMB04.amd.com;
From:   Alex Sierra <alex.sierra@amd.com>
To:     <akpm@linux-foundation.org>, <Felix.Kuehling@amd.com>,
        <linux-mm@kvack.org>, <rcampbell@nvidia.com>,
        <linux-ext4@vger.kernel.org>, <linux-xfs@vger.kernel.org>
CC:     <amd-gfx@lists.freedesktop.org>, <dri-devel@lists.freedesktop.org>,
        <hch@lst.de>, <jgg@nvidia.com>, <jglisse@redhat.com>,
        <apopple@nvidia.com>
Subject: [PATCH v1 10/12] lib: add support for device coherent type in test_hmm
Date:   Tue, 12 Oct 2021 12:12:45 -0500
Message-ID: <20211012171247.2861-11-alex.sierra@amd.com>
In-Reply-To: <20211012171247.2861-1-alex.sierra@amd.com>
References: <20211012171247.2861-1-alex.sierra@amd.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Content-Type: text/plain
X-MS-Exchange-CrossTenant-OriginalArrivalTime: 12 Oct 2021 17:13:07.5301
 (UTC)
X-MS-Exchange-CrossTenant-Network-Message-Id: 9ea873c8-9c64-49bf-a066-08d98da38f8a
X-MS-Exchange-CrossTenant-Id: 3dd8961f-e488-4e60-8e11-a82d994e183d
X-MS-Exchange-CrossTenant-OriginalAttributedTenantConnectingIp: TenantId=3dd8961f-e488-4e60-8e11-a82d994e183d;Ip=[165.204.84.17];Helo=[SATLEXMB04.amd.com]
X-MS-Exchange-CrossTenant-AuthSource: CO1NAM11FT018.eop-nam11.prod.protection.outlook.com
X-MS-Exchange-CrossTenant-AuthAs: Anonymous
X-MS-Exchange-CrossTenant-FromEntityHeader: HybridOnPrem
X-MS-Exchange-Transport-CrossTenantHeadersStamped: DM6PR12MB2716
Precedence: bulk
List-ID: <linux-ext4.vger.kernel.org>
X-Mailing-List: linux-ext4@vger.kernel.org

Device Coherent type uses device memory that is coherently accesible by
the CPU. This could be shown as SP (special purpose) memory range
at the BIOS-e820 memory enumeration. If no SP memory is supported in
system, this could be faked by setting CONFIG_EFI_FAKE_MEMMAP.

Currently, test_hmm only supports two different SP ranges of at least
256MB size. This could be specified in the kernel parameter variable
efi_fake_mem. Ex. Two SP ranges of 1GB starting at 0x100000000 &
0x140000000 physical address. Ex.
efi_fake_mem=1G@0x100000000:0x40000,1G@0x140000000:0x40000

Signed-off-by: Alex Sierra <alex.sierra@amd.com>
---
 lib/test_hmm.c      | 195 ++++++++++++++++++++++++++++++++------------
 lib/test_hmm_uapi.h |  16 +++-
 2 files changed, 157 insertions(+), 54 deletions(-)

diff --git a/lib/test_hmm.c b/lib/test_hmm.c
index 70a9be0efa00..b349dd920f04 100644
--- a/lib/test_hmm.c
+++ b/lib/test_hmm.c
@@ -469,6 +469,7 @@ static int dmirror_allocate_chunk(struct dmirror_device *mdevice,
 	unsigned long pfn_first;
 	unsigned long pfn_last;
 	void *ptr;
+	int ret = -ENOMEM;
 
 	devmem = kzalloc(sizeof(*devmem), GFP_KERNEL);
 	if (!devmem)
@@ -551,7 +552,7 @@ static int dmirror_allocate_chunk(struct dmirror_device *mdevice,
 	}
 	spin_unlock(&mdevice->lock);
 
-	return true;
+	return 0;
 
 err_release:
 	mutex_unlock(&mdevice->devmem_lock);
@@ -560,7 +561,7 @@ static int dmirror_allocate_chunk(struct dmirror_device *mdevice,
 err_devmem:
 	kfree(devmem);
 
-	return false;
+	return ret;
 }
 
 static struct page *dmirror_devmem_alloc_page(struct dmirror_device *mdevice)
@@ -569,13 +570,14 @@ static struct page *dmirror_devmem_alloc_page(struct dmirror_device *mdevice)
 	struct page *rpage;
 
 	/*
-	 * This is a fake device so we alloc real system memory to store
-	 * our device memory.
+	 * For ZONE_DEVICE private type, this is a fake device so we alloc real
+	 * system memory to store our device memory.
+	 * For ZONE_DEVICE coherent type we use the actual dpage to store the data
+	 * and ignore rpage.
 	 */
 	rpage = alloc_page(GFP_HIGHUSER);
 	if (!rpage)
 		return NULL;
-
 	spin_lock(&mdevice->lock);
 
 	if (mdevice->free_pages) {
@@ -603,7 +605,7 @@ static void dmirror_migrate_alloc_and_copy(struct migrate_vma *args,
 					   struct dmirror *dmirror)
 {
 	struct dmirror_device *mdevice = dmirror->mdevice;
-	const unsigned long *src = args->src;
+	unsigned long *src = args->src;
 	unsigned long *dst = args->dst;
 	unsigned long addr;
 
@@ -621,12 +623,17 @@ static void dmirror_migrate_alloc_and_copy(struct migrate_vma *args,
 		 * unallocated pte_none() or read-only zero page.
 		 */
 		spage = migrate_pfn_to_page(*src);
+		if (spage && is_zone_device_page(spage))
+			pr_err("page already in device spage pfn: 0x%lx\n",
+				  page_to_pfn(spage));
+		BUG_ON(spage && is_zone_device_page(spage));
 
 		dpage = dmirror_devmem_alloc_page(mdevice);
 		if (!dpage)
 			continue;
 
-		rpage = dpage->zone_device_data;
+		rpage = is_device_private_page(dpage) ? dpage->zone_device_data :
+							dpage;
 		if (spage)
 			copy_highpage(rpage, spage);
 		else
@@ -638,8 +645,10 @@ static void dmirror_migrate_alloc_and_copy(struct migrate_vma *args,
 		 * the simulated device memory and that page holds the pointer
 		 * to the mirror.
 		 */
+		rpage = dpage->zone_device_data;
 		rpage->zone_device_data = dmirror;
-
+		pr_debug("migrating from sys to dev pfn src: 0x%lx pfn dst: 0x%lx\n",
+			 page_to_pfn(spage), page_to_pfn(dpage));
 		*dst = migrate_pfn(page_to_pfn(dpage)) |
 			    MIGRATE_PFN_LOCKED;
 		if ((*src & MIGRATE_PFN_WRITE) ||
@@ -673,10 +682,13 @@ static int dmirror_migrate_finalize_and_map(struct migrate_vma *args,
 			continue;
 
 		/*
-		 * Store the page that holds the data so the page table
-		 * doesn't have to deal with ZONE_DEVICE private pages.
+		 * For ZONE_DEVICE private pages we store the page that
+		 * holds the data so the page table doesn't have to deal it.
+		 * For ZONE_DEVICE coherent pages we store the actual page, since
+		 * the CPU has coherent access to the page.
 		 */
-		entry = dpage->zone_device_data;
+		entry = is_device_private_page(dpage) ? dpage->zone_device_data :
+							dpage;
 		if (*dst & MIGRATE_PFN_WRITE)
 			entry = xa_tag_pointer(entry, DPT_XA_TAG_WRITE);
 		entry = xa_store(&dmirror->pt, pfn, entry, GFP_ATOMIC);
@@ -690,7 +702,110 @@ static int dmirror_migrate_finalize_and_map(struct migrate_vma *args,
 	return 0;
 }
 
-static int dmirror_migrate(struct dmirror *dmirror,
+static vm_fault_t dmirror_devmem_fault_alloc_and_copy(struct migrate_vma *args,
+						      struct dmirror *dmirror)
+{
+	unsigned long *src = args->src;
+	unsigned long *dst = args->dst;
+	unsigned long start = args->start;
+	unsigned long end = args->end;
+	unsigned long addr;
+
+	for (addr = start; addr < end; addr += PAGE_SIZE,
+				       src++, dst++) {
+		struct page *dpage, *spage;
+
+		spage = migrate_pfn_to_page(*src);
+		if (!spage || !(*src & MIGRATE_PFN_MIGRATE))
+			continue;
+
+		BUG_ON(!is_device_page(spage));
+		spage = is_device_private_page(spage) ? spage->zone_device_data:
+							spage;
+		dpage = alloc_page_vma(GFP_HIGHUSER_MOVABLE, args->vma, addr);
+		if (!dpage)
+			continue;
+		pr_debug("migrating from dev to sys pfn src: 0x%lx pfn dst: 0x%lx\n",
+			 page_to_pfn(spage), page_to_pfn(dpage));
+
+		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)
+			*dst |= MIGRATE_PFN_WRITE;
+	}
+	return 0;
+}
+
+static int dmirror_migrate_to_system(struct dmirror *dmirror,
+			   struct hmm_dmirror_cmd *cmd)
+{
+	unsigned long start, end, addr;
+	unsigned long size = cmd->npages << PAGE_SHIFT;
+	struct mm_struct *mm = dmirror->notifier.mm;
+	struct vm_area_struct *vma;
+	unsigned long src_pfns[64];
+	unsigned long dst_pfns[64];
+	struct migrate_vma args;
+	unsigned long next;
+	int ret;
+
+	start = cmd->addr;
+	end = start + size;
+	if (end < start)
+		return -EINVAL;
+
+	/* Since the mm is for the mirrored process, get a reference first. */
+	if (!mmget_not_zero(mm))
+		return -EINVAL;
+
+	mmap_read_lock(mm);
+	for (addr = start; addr < end; addr = next) {
+		vma = find_vma(mm, addr);
+		if (!vma || addr < vma->vm_start ||
+		    !(vma->vm_flags & VM_READ)) {
+			ret = -EINVAL;
+			goto out;
+		}
+		next = min(end, addr + (ARRAY_SIZE(src_pfns) << PAGE_SHIFT));
+		if (next > vma->vm_end)
+			next = vma->vm_end;
+
+		args.vma = vma;
+		args.src = src_pfns;
+		args.dst = dst_pfns;
+		args.start = addr;
+		args.end = next;
+		args.pgmap_owner = dmirror->mdevice;
+		args.flags = (dmirror->mdevice->zone_device_type ==
+			     HMM_DMIRROR_MEMORY_DEVICE_PRIVATE) ?
+			     MIGRATE_VMA_SELECT_DEVICE_PRIVATE :
+			     MIGRATE_VMA_SELECT_DEVICE_COHERENT;
+
+		ret = migrate_vma_setup(&args);
+		if (ret)
+			goto out;
+
+		pr_debug("Migrating from device mem to sys mem\n");
+		dmirror_devmem_fault_alloc_and_copy(&args, dmirror);
+
+		migrate_vma_pages(&args);
+		migrate_vma_finalize(&args);
+	}
+	mmap_read_unlock(mm);
+	mmput(mm);
+
+	return ret;
+
+out:
+	mmap_read_unlock(mm);
+	mmput(mm);
+	return ret;
+}
+
+
+static int dmirror_migrate_to_device(struct dmirror *dmirror,
 			   struct hmm_dmirror_cmd *cmd)
 {
 	unsigned long start, end, addr;
@@ -736,6 +851,7 @@ static int dmirror_migrate(struct dmirror *dmirror,
 		if (ret)
 			goto out;
 
+		pr_debug("Migrating from sys mem to device mem\n");
 		dmirror_migrate_alloc_and_copy(&args, dmirror);
 		migrate_vma_pages(&args);
 		dmirror_migrate_finalize_and_map(&args, dmirror);
@@ -744,7 +860,7 @@ static int dmirror_migrate(struct dmirror *dmirror,
 	mmap_read_unlock(mm);
 	mmput(mm);
 
-	/* Return the migrated data for verification. */
+	/* Return the migrated data for verification. only for pages in device zone */
 	ret = dmirror_bounce_init(&bounce, start, size);
 	if (ret)
 		return ret;
@@ -758,6 +874,7 @@ static int dmirror_migrate(struct dmirror *dmirror,
 	}
 	cmd->cpages = bounce.cpages;
 	dmirror_bounce_fini(&bounce);
+
 	return ret;
 
 out:
@@ -781,9 +898,15 @@ static void dmirror_mkentry(struct dmirror *dmirror, struct hmm_range *range,
 	}
 
 	page = hmm_pfn_to_page(entry);
-	if (is_device_private_page(page)) {
-		/* Is the page migrated to this device or some other? */
-		if (dmirror->mdevice == dmirror_page_to_device(page))
+	if (is_device_page(page)) {
+		/* Is page ZONE_DEVICE coherent? */
+		if (!is_device_private_page(page))
+			*perm = HMM_DMIRROR_PROT_DEV_COHERENT;
+		/*
+		 * Is page ZONE_DEVICE private migrated to
+		 * this device or some other?
+		 */
+		else if (dmirror->mdevice == dmirror_page_to_device(page))
 			*perm = HMM_DMIRROR_PROT_DEV_PRIVATE_LOCAL;
 		else
 			*perm = HMM_DMIRROR_PROT_DEV_PRIVATE_REMOTE;
@@ -983,8 +1106,12 @@ static long dmirror_fops_unlocked_ioctl(struct file *filp,
 		ret = dmirror_write(dmirror, &cmd);
 		break;
 
-	case HMM_DMIRROR_MIGRATE:
-		ret = dmirror_migrate(dmirror, &cmd);
+	case HMM_DMIRROR_MIGRATE_TO_DEV:
+		ret = dmirror_migrate_to_device(dmirror, &cmd);
+		break;
+
+	case HMM_DMIRROR_MIGRATE_TO_SYS:
+		ret = dmirror_migrate_to_system(dmirror, &cmd);
 		break;
 
 	case HMM_DMIRROR_SNAPSHOT:
@@ -1030,38 +1157,6 @@ static void dmirror_devmem_free(struct page *page)
 	spin_unlock(&mdevice->lock);
 }
 
-static vm_fault_t dmirror_devmem_fault_alloc_and_copy(struct migrate_vma *args,
-						      struct dmirror *dmirror)
-{
-	const unsigned long *src = args->src;
-	unsigned long *dst = args->dst;
-	unsigned long start = args->start;
-	unsigned long end = args->end;
-	unsigned long addr;
-
-	for (addr = start; addr < end; addr += PAGE_SIZE,
-				       src++, dst++) {
-		struct page *dpage, *spage;
-
-		spage = migrate_pfn_to_page(*src);
-		if (!spage || !(*src & MIGRATE_PFN_MIGRATE))
-			continue;
-		spage = spage->zone_device_data;
-
-		dpage = alloc_page_vma(GFP_HIGHUSER_MOVABLE, args->vma, addr);
-		if (!dpage)
-			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)
-			*dst |= MIGRATE_PFN_WRITE;
-	}
-	return 0;
-}
-
 static vm_fault_t dmirror_devmem_fault(struct vm_fault *vmf)
 {
 	struct migrate_vma args;
diff --git a/lib/test_hmm_uapi.h b/lib/test_hmm_uapi.h
index f86754be64fd..13cec485328d 100644
--- a/lib/test_hmm_uapi.h
+++ b/lib/test_hmm_uapi.h
@@ -17,8 +17,12 @@
  * @addr: (in) user address the device will read/write
  * @ptr: (in) user address where device data is copied to/from
  * @npages: (in) number of pages to read/write
+ * @alloc_to_devmem: (in) desired allocation destination during migration.
+ * True if allocation is to device memory.
+ * False if allocation is to system memory.
  * @cpages: (out) number of pages copied
  * @faults: (out) number of device page faults seen
+ * @zone_device_type: (out) zone device memory type
  */
 struct hmm_dmirror_cmd {
 	__u64		addr;
@@ -26,15 +30,16 @@ struct hmm_dmirror_cmd {
 	__u64		npages;
 	__u64		cpages;
 	__u64		faults;
-	__u64		zone_device_type;
+	__u32		zone_device_type;
 };
 
 /* Expose the address space of the calling process through hmm device file */
 #define HMM_DMIRROR_READ		_IOWR('H', 0x00, struct hmm_dmirror_cmd)
 #define HMM_DMIRROR_WRITE		_IOWR('H', 0x01, struct hmm_dmirror_cmd)
-#define HMM_DMIRROR_MIGRATE		_IOWR('H', 0x02, struct hmm_dmirror_cmd)
-#define HMM_DMIRROR_SNAPSHOT		_IOWR('H', 0x03, struct hmm_dmirror_cmd)
-#define HMM_DMIRROR_GET_MEM_DEV_TYPE	_IOWR('H', 0x04, struct hmm_dmirror_cmd)
+#define HMM_DMIRROR_MIGRATE_TO_DEV	_IOWR('H', 0x02, struct hmm_dmirror_cmd)
+#define HMM_DMIRROR_MIGRATE_TO_SYS	_IOWR('H', 0x03, struct hmm_dmirror_cmd)
+#define HMM_DMIRROR_SNAPSHOT		_IOWR('H', 0x04, struct hmm_dmirror_cmd)
+#define HMM_DMIRROR_GET_MEM_DEV_TYPE	_IOWR('H', 0x05, struct hmm_dmirror_cmd)
 
 /*
  * Values returned in hmm_dmirror_cmd.ptr for HMM_DMIRROR_SNAPSHOT.
@@ -49,6 +54,8 @@ struct hmm_dmirror_cmd {
  *					device the ioctl() is made
  * HMM_DMIRROR_PROT_DEV_PRIVATE_REMOTE: Migrated device private page on some
  *					other device
+ * HMM_DMIRROR_PROT_DEV_COHERENT: Migrate device coherent page on the device
+ *				 the ioctl() is made
  */
 enum {
 	HMM_DMIRROR_PROT_ERROR			= 0xFF,
@@ -60,6 +67,7 @@ enum {
 	HMM_DMIRROR_PROT_ZERO			= 0x10,
 	HMM_DMIRROR_PROT_DEV_PRIVATE_LOCAL	= 0x20,
 	HMM_DMIRROR_PROT_DEV_PRIVATE_REMOTE	= 0x30,
+	HMM_DMIRROR_PROT_DEV_COHERENT		= 0x40,
 };
 
 enum {
-- 
2.32.0