All of lore.kernel.org
 help / color / mirror / Atom feed
From: Alex Sierra <alex.sierra@amd.com>
To: <jgg@nvidia.com>
Cc: <david@redhat.com>, <Felix.Kuehling@amd.com>,
	<linux-mm@kvack.org>, <rcampbell@nvidia.com>,
	<linux-ext4@vger.kernel.org>, <linux-xfs@vger.kernel.org>,
	<amd-gfx@lists.freedesktop.org>,
	<dri-devel@lists.freedesktop.org>, <hch@lst.de>,
	<jglisse@redhat.com>, <apopple@nvidia.com>, <willy@infradead.org>,
	<akpm@linux-foundation.org>
Subject: [PATCH v3 09/13] lib: add support for device coherent type in test_hmm
Date: Tue, 24 May 2022 14:06:28 -0500	[thread overview]
Message-ID: <20220524190632.3304-10-alex.sierra@amd.com> (raw)
In-Reply-To: <20220524190632.3304-1-alex.sierra@amd.com>

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

Private and coherent device mirror instances can be created in the same
probed. This is done by passing the module parameters spm_addr_dev0 &
spm_addr_dev1. In this case, it will create four instances of
device_mirror. The first two correspond to private device type, the
last two to coherent type. Then, they can be easily accessed from user
space through /dev/hmm_mirror<num_device>. Usually num_device 0 and 1
are for private, and 2 and 3 for coherent types. If no module
parameters are passed, two instances of private type device_mirror will
be created only.

Signed-off-by: Alex Sierra <alex.sierra@amd.com>
Acked-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Alistair Poppple <apopple@nvidia.com>
---
 lib/test_hmm.c      | 253 +++++++++++++++++++++++++++++++++-----------
 lib/test_hmm_uapi.h |  15 ++-
 2 files changed, 202 insertions(+), 66 deletions(-)

diff --git a/lib/test_hmm.c b/lib/test_hmm.c
index 15747f70c5bc..361a026c5d21 100644
--- a/lib/test_hmm.c
+++ b/lib/test_hmm.c
@@ -32,11 +32,22 @@
 
 #include "test_hmm_uapi.h"
 
-#define DMIRROR_NDEVICES		2
+#define DMIRROR_NDEVICES		4
 #define DMIRROR_RANGE_FAULT_TIMEOUT	1000
 #define DEVMEM_CHUNK_SIZE		(256 * 1024 * 1024U)
 #define DEVMEM_CHUNKS_RESERVE		16
 
+/*
+ * For device_private pages, dpage is just a dummy struct page
+ * representing a piece of device memory. dmirror_devmem_alloc_page
+ * allocates a real system memory page as backing storage to fake a
+ * real device. zone_device_data points to that backing page. But
+ * for device_coherent memory, the struct page represents real
+ * physical CPU-accessible memory that we can use directly.
+ */
+#define BACKING_PAGE(page) (is_device_private_page((page)) ? \
+			   (page)->zone_device_data : (page))
+
 static unsigned long spm_addr_dev0;
 module_param(spm_addr_dev0, long, 0644);
 MODULE_PARM_DESC(spm_addr_dev0,
@@ -125,6 +136,21 @@ static int dmirror_bounce_init(struct dmirror_bounce *bounce,
 	return 0;
 }
 
+static bool dmirror_is_private_zone(struct dmirror_device *mdevice)
+{
+	return (mdevice->zone_device_type ==
+		HMM_DMIRROR_MEMORY_DEVICE_PRIVATE) ? true : false;
+}
+
+static enum migrate_vma_direction
+dmirror_select_device(struct dmirror *dmirror)
+{
+	return (dmirror->mdevice->zone_device_type ==
+		HMM_DMIRROR_MEMORY_DEVICE_PRIVATE) ?
+		MIGRATE_VMA_SELECT_DEVICE_PRIVATE :
+		MIGRATE_VMA_SELECT_DEVICE_COHERENT;
+}
+
 static void dmirror_bounce_fini(struct dmirror_bounce *bounce)
 {
 	vfree(bounce->ptr);
@@ -575,16 +601,19 @@ static int dmirror_allocate_chunk(struct dmirror_device *mdevice,
 static struct page *dmirror_devmem_alloc_page(struct dmirror_device *mdevice)
 {
 	struct page *dpage = NULL;
-	struct page *rpage;
+	struct page *rpage = NULL;
 
 	/*
-	 * 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 allocate
+	 * 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;
-
+	if (dmirror_is_private_zone(mdevice)) {
+		rpage = alloc_page(GFP_HIGHUSER);
+		if (!rpage)
+			return NULL;
+	}
 	spin_lock(&mdevice->lock);
 
 	if (mdevice->free_pages) {
@@ -603,7 +632,8 @@ static struct page *dmirror_devmem_alloc_page(struct dmirror_device *mdevice)
 	return dpage;
 
 error:
-	__free_page(rpage);
+	if (rpage)
+		__free_page(rpage);
 	return NULL;
 }
 
@@ -629,12 +659,16 @@ 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 (WARN(spage && is_zone_device_page(spage),
+		     "page already in device spage pfn: 0x%lx\n",
+		     page_to_pfn(spage)))
+			continue;
 
 		dpage = dmirror_devmem_alloc_page(mdevice);
 		if (!dpage)
 			continue;
 
-		rpage = dpage->zone_device_data;
+		rpage = BACKING_PAGE(dpage);
 		if (spage)
 			copy_highpage(rpage, spage);
 		else
@@ -648,6 +682,8 @@ static void dmirror_migrate_alloc_and_copy(struct migrate_vma *args,
 		 */
 		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));
 		if ((*src & MIGRATE_PFN_WRITE) ||
 		    (!spage && args->vma->vm_flags & VM_WRITE))
@@ -725,11 +761,7 @@ static int dmirror_migrate_finalize_and_map(struct migrate_vma *args,
 		if (!dpage)
 			continue;
 
-		/*
-		 * Store the page that holds the data so the page table
-		 * doesn't have to deal with ZONE_DEVICE private pages.
-		 */
-		entry = dpage->zone_device_data;
+		entry = BACKING_PAGE(dpage);
 		if (*dst & MIGRATE_PFN_WRITE)
 			entry = xa_tag_pointer(entry, DPT_XA_TAG_WRITE);
 		entry = xa_store(&dmirror->pt, pfn, entry, GFP_ATOMIC);
@@ -809,15 +841,126 @@ static int dmirror_exclusive(struct dmirror *dmirror,
 	return ret;
 }
 
-static int dmirror_migrate(struct dmirror *dmirror,
-			   struct hmm_dmirror_cmd *cmd)
+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;
+
+		if (WARN_ON(!is_device_private_page(spage) &&
+			    !is_device_coherent_page(spage)))
+			continue;
+		spage = BACKING_PAGE(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));
+		if (*src & MIGRATE_PFN_WRITE)
+			*dst |= MIGRATE_PFN_WRITE;
+	}
+	return 0;
+}
+
+static unsigned long
+dmirror_successful_migrated_pages(struct migrate_vma *migrate)
+{
+	unsigned long cpages = 0;
+	unsigned long i;
+
+	for (i = 0; i < migrate->npages; i++) {
+		if (migrate->src[i] & MIGRATE_PFN_VALID &&
+		    migrate->src[i] & MIGRATE_PFN_MIGRATE)
+			cpages++;
+	}
+	return cpages;
+}
+
+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];
+	unsigned long src_pfns[64] = { 0 };
+	unsigned long dst_pfns[64] = { 0 };
+	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;
+
+	cmd->cpages = 0;
+	mmap_read_lock(mm);
+	for (addr = start; addr < end; addr = next) {
+		vma = vma_lookup(mm, addr);
+		if (!vma || !(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_select_device(dmirror);
+
+		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);
+		cmd->cpages += dmirror_successful_migrated_pages(&args);
+		migrate_vma_finalize(&args);
+	}
+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;
+	unsigned long size = cmd->npages << PAGE_SHIFT;
+	struct mm_struct *mm = dmirror->notifier.mm;
+	struct vm_area_struct *vma;
+	unsigned long src_pfns[64] = { 0 };
+	unsigned long dst_pfns[64] = { 0 };
 	struct dmirror_bounce bounce;
 	struct migrate_vma args;
 	unsigned long next;
@@ -854,6 +997,7 @@ 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);
@@ -862,7 +1006,10 @@ 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;
@@ -905,6 +1052,12 @@ static void dmirror_mkentry(struct dmirror *dmirror, struct hmm_range *range,
 			*perm = HMM_DMIRROR_PROT_DEV_PRIVATE_LOCAL;
 		else
 			*perm = HMM_DMIRROR_PROT_DEV_PRIVATE_REMOTE;
+	} else if (is_device_coherent_page(page)) {
+		/* Is the page migrated to this device or some other? */
+		if (dmirror->mdevice == dmirror_page_to_device(page))
+			*perm = HMM_DMIRROR_PROT_DEV_COHERENT_LOCAL;
+		else
+			*perm = HMM_DMIRROR_PROT_DEV_COHERENT_REMOTE;
 	} else if (is_zero_pfn(page_to_pfn(page)))
 		*perm = HMM_DMIRROR_PROT_ZERO;
 	else
@@ -1101,8 +1254,12 @@ 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_EXCLUSIVE:
@@ -1167,14 +1324,13 @@ static const struct file_operations dmirror_fops = {
 
 static void dmirror_devmem_free(struct page *page)
 {
-	struct page *rpage = page->zone_device_data;
+	struct page *rpage = BACKING_PAGE(page);
 	struct dmirror_device *mdevice;
 
-	if (rpage)
+	if (rpage != page)
 		__free_page(rpage);
 
 	mdevice = dmirror_page_to_device(page);
-
 	spin_lock(&mdevice->lock);
 	mdevice->cfree++;
 	page->zone_device_data = mdevice->free_pages;
@@ -1182,43 +1338,11 @@ 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));
-		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;
-	unsigned long src_pfns;
-	unsigned long dst_pfns;
+	unsigned long src_pfns = 0;
+	unsigned long dst_pfns = 0;
 	struct page *rpage;
 	struct dmirror *dmirror;
 	vm_fault_t ret;
@@ -1238,7 +1362,7 @@ static vm_fault_t dmirror_devmem_fault(struct vm_fault *vmf)
 	args.src = &src_pfns;
 	args.dst = &dst_pfns;
 	args.pgmap_owner = dmirror->mdevice;
-	args.flags = MIGRATE_VMA_SELECT_DEVICE_PRIVATE;
+	args.flags = dmirror_select_device(dmirror);
 
 	if (migrate_vma_setup(&args))
 		return VM_FAULT_SIGBUS;
@@ -1317,6 +1441,12 @@ static int __init hmm_dmirror_init(void)
 				HMM_DMIRROR_MEMORY_DEVICE_PRIVATE;
 	dmirror_devices[ndevices++].zone_device_type =
 				HMM_DMIRROR_MEMORY_DEVICE_PRIVATE;
+	if (spm_addr_dev0 && spm_addr_dev1) {
+		dmirror_devices[ndevices++].zone_device_type =
+					HMM_DMIRROR_MEMORY_DEVICE_COHERENT;
+		dmirror_devices[ndevices++].zone_device_type =
+					HMM_DMIRROR_MEMORY_DEVICE_COHERENT;
+	}
 	for (id = 0; id < ndevices; id++) {
 		ret = dmirror_device_init(dmirror_devices + id, id);
 		if (ret)
@@ -1339,7 +1469,8 @@ static void __exit hmm_dmirror_exit(void)
 	int id;
 
 	for (id = 0; id < DMIRROR_NDEVICES; id++)
-		dmirror_device_remove(dmirror_devices + id);
+		if (dmirror_devices[id].zone_device_type)
+			dmirror_device_remove(dmirror_devices + id);
 	unregister_chrdev_region(dmirror_dev, DMIRROR_NDEVICES);
 }
 
diff --git a/lib/test_hmm_uapi.h b/lib/test_hmm_uapi.h
index 625f3690d086..e190b2ab6f19 100644
--- a/lib/test_hmm_uapi.h
+++ b/lib/test_hmm_uapi.h
@@ -33,11 +33,12 @@ struct hmm_dmirror_cmd {
 /* 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_EXCLUSIVE		_IOWR('H', 0x04, struct hmm_dmirror_cmd)
-#define HMM_DMIRROR_CHECK_EXCLUSIVE	_IOWR('H', 0x05, struct hmm_dmirror_cmd)
-#define HMM_DMIRROR_GET_MEM_DEV_TYPE	_IOWR('H', 0x06, 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_EXCLUSIVE		_IOWR('H', 0x05, struct hmm_dmirror_cmd)
+#define HMM_DMIRROR_CHECK_EXCLUSIVE	_IOWR('H', 0x06, struct hmm_dmirror_cmd)
+#define HMM_DMIRROR_GET_MEM_DEV_TYPE	_IOWR('H', 0x07, struct hmm_dmirror_cmd)
 
 /*
  * Values returned in hmm_dmirror_cmd.ptr for HMM_DMIRROR_SNAPSHOT.
@@ -52,6 +53,8 @@ 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,
@@ -63,6 +66,8 @@ 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_LOCAL	= 0x40,
+	HMM_DMIRROR_PROT_DEV_COHERENT_REMOTE	= 0x50,
 };
 
 enum {
-- 
2.32.0


WARNING: multiple messages have this Message-ID (diff)
From: Alex Sierra <alex.sierra@amd.com>
To: <jgg@nvidia.com>
Cc: rcampbell@nvidia.com, willy@infradead.org, david@redhat.com,
	Felix.Kuehling@amd.com, apopple@nvidia.com,
	amd-gfx@lists.freedesktop.org, linux-xfs@vger.kernel.org,
	linux-mm@kvack.org, jglisse@redhat.com,
	dri-devel@lists.freedesktop.org, akpm@linux-foundation.org,
	linux-ext4@vger.kernel.org, hch@lst.de
Subject: [PATCH v3 09/13] lib: add support for device coherent type in test_hmm
Date: Tue, 24 May 2022 14:06:28 -0500	[thread overview]
Message-ID: <20220524190632.3304-10-alex.sierra@amd.com> (raw)
In-Reply-To: <20220524190632.3304-1-alex.sierra@amd.com>

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

Private and coherent device mirror instances can be created in the same
probed. This is done by passing the module parameters spm_addr_dev0 &
spm_addr_dev1. In this case, it will create four instances of
device_mirror. The first two correspond to private device type, the
last two to coherent type. Then, they can be easily accessed from user
space through /dev/hmm_mirror<num_device>. Usually num_device 0 and 1
are for private, and 2 and 3 for coherent types. If no module
parameters are passed, two instances of private type device_mirror will
be created only.

Signed-off-by: Alex Sierra <alex.sierra@amd.com>
Acked-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Alistair Poppple <apopple@nvidia.com>
---
 lib/test_hmm.c      | 253 +++++++++++++++++++++++++++++++++-----------
 lib/test_hmm_uapi.h |  15 ++-
 2 files changed, 202 insertions(+), 66 deletions(-)

diff --git a/lib/test_hmm.c b/lib/test_hmm.c
index 15747f70c5bc..361a026c5d21 100644
--- a/lib/test_hmm.c
+++ b/lib/test_hmm.c
@@ -32,11 +32,22 @@
 
 #include "test_hmm_uapi.h"
 
-#define DMIRROR_NDEVICES		2
+#define DMIRROR_NDEVICES		4
 #define DMIRROR_RANGE_FAULT_TIMEOUT	1000
 #define DEVMEM_CHUNK_SIZE		(256 * 1024 * 1024U)
 #define DEVMEM_CHUNKS_RESERVE		16
 
+/*
+ * For device_private pages, dpage is just a dummy struct page
+ * representing a piece of device memory. dmirror_devmem_alloc_page
+ * allocates a real system memory page as backing storage to fake a
+ * real device. zone_device_data points to that backing page. But
+ * for device_coherent memory, the struct page represents real
+ * physical CPU-accessible memory that we can use directly.
+ */
+#define BACKING_PAGE(page) (is_device_private_page((page)) ? \
+			   (page)->zone_device_data : (page))
+
 static unsigned long spm_addr_dev0;
 module_param(spm_addr_dev0, long, 0644);
 MODULE_PARM_DESC(spm_addr_dev0,
@@ -125,6 +136,21 @@ static int dmirror_bounce_init(struct dmirror_bounce *bounce,
 	return 0;
 }
 
+static bool dmirror_is_private_zone(struct dmirror_device *mdevice)
+{
+	return (mdevice->zone_device_type ==
+		HMM_DMIRROR_MEMORY_DEVICE_PRIVATE) ? true : false;
+}
+
+static enum migrate_vma_direction
+dmirror_select_device(struct dmirror *dmirror)
+{
+	return (dmirror->mdevice->zone_device_type ==
+		HMM_DMIRROR_MEMORY_DEVICE_PRIVATE) ?
+		MIGRATE_VMA_SELECT_DEVICE_PRIVATE :
+		MIGRATE_VMA_SELECT_DEVICE_COHERENT;
+}
+
 static void dmirror_bounce_fini(struct dmirror_bounce *bounce)
 {
 	vfree(bounce->ptr);
@@ -575,16 +601,19 @@ static int dmirror_allocate_chunk(struct dmirror_device *mdevice,
 static struct page *dmirror_devmem_alloc_page(struct dmirror_device *mdevice)
 {
 	struct page *dpage = NULL;
-	struct page *rpage;
+	struct page *rpage = NULL;
 
 	/*
-	 * 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 allocate
+	 * 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;
-
+	if (dmirror_is_private_zone(mdevice)) {
+		rpage = alloc_page(GFP_HIGHUSER);
+		if (!rpage)
+			return NULL;
+	}
 	spin_lock(&mdevice->lock);
 
 	if (mdevice->free_pages) {
@@ -603,7 +632,8 @@ static struct page *dmirror_devmem_alloc_page(struct dmirror_device *mdevice)
 	return dpage;
 
 error:
-	__free_page(rpage);
+	if (rpage)
+		__free_page(rpage);
 	return NULL;
 }
 
@@ -629,12 +659,16 @@ 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 (WARN(spage && is_zone_device_page(spage),
+		     "page already in device spage pfn: 0x%lx\n",
+		     page_to_pfn(spage)))
+			continue;
 
 		dpage = dmirror_devmem_alloc_page(mdevice);
 		if (!dpage)
 			continue;
 
-		rpage = dpage->zone_device_data;
+		rpage = BACKING_PAGE(dpage);
 		if (spage)
 			copy_highpage(rpage, spage);
 		else
@@ -648,6 +682,8 @@ static void dmirror_migrate_alloc_and_copy(struct migrate_vma *args,
 		 */
 		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));
 		if ((*src & MIGRATE_PFN_WRITE) ||
 		    (!spage && args->vma->vm_flags & VM_WRITE))
@@ -725,11 +761,7 @@ static int dmirror_migrate_finalize_and_map(struct migrate_vma *args,
 		if (!dpage)
 			continue;
 
-		/*
-		 * Store the page that holds the data so the page table
-		 * doesn't have to deal with ZONE_DEVICE private pages.
-		 */
-		entry = dpage->zone_device_data;
+		entry = BACKING_PAGE(dpage);
 		if (*dst & MIGRATE_PFN_WRITE)
 			entry = xa_tag_pointer(entry, DPT_XA_TAG_WRITE);
 		entry = xa_store(&dmirror->pt, pfn, entry, GFP_ATOMIC);
@@ -809,15 +841,126 @@ static int dmirror_exclusive(struct dmirror *dmirror,
 	return ret;
 }
 
-static int dmirror_migrate(struct dmirror *dmirror,
-			   struct hmm_dmirror_cmd *cmd)
+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;
+
+		if (WARN_ON(!is_device_private_page(spage) &&
+			    !is_device_coherent_page(spage)))
+			continue;
+		spage = BACKING_PAGE(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));
+		if (*src & MIGRATE_PFN_WRITE)
+			*dst |= MIGRATE_PFN_WRITE;
+	}
+	return 0;
+}
+
+static unsigned long
+dmirror_successful_migrated_pages(struct migrate_vma *migrate)
+{
+	unsigned long cpages = 0;
+	unsigned long i;
+
+	for (i = 0; i < migrate->npages; i++) {
+		if (migrate->src[i] & MIGRATE_PFN_VALID &&
+		    migrate->src[i] & MIGRATE_PFN_MIGRATE)
+			cpages++;
+	}
+	return cpages;
+}
+
+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];
+	unsigned long src_pfns[64] = { 0 };
+	unsigned long dst_pfns[64] = { 0 };
+	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;
+
+	cmd->cpages = 0;
+	mmap_read_lock(mm);
+	for (addr = start; addr < end; addr = next) {
+		vma = vma_lookup(mm, addr);
+		if (!vma || !(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_select_device(dmirror);
+
+		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);
+		cmd->cpages += dmirror_successful_migrated_pages(&args);
+		migrate_vma_finalize(&args);
+	}
+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;
+	unsigned long size = cmd->npages << PAGE_SHIFT;
+	struct mm_struct *mm = dmirror->notifier.mm;
+	struct vm_area_struct *vma;
+	unsigned long src_pfns[64] = { 0 };
+	unsigned long dst_pfns[64] = { 0 };
 	struct dmirror_bounce bounce;
 	struct migrate_vma args;
 	unsigned long next;
@@ -854,6 +997,7 @@ 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);
@@ -862,7 +1006,10 @@ 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;
@@ -905,6 +1052,12 @@ static void dmirror_mkentry(struct dmirror *dmirror, struct hmm_range *range,
 			*perm = HMM_DMIRROR_PROT_DEV_PRIVATE_LOCAL;
 		else
 			*perm = HMM_DMIRROR_PROT_DEV_PRIVATE_REMOTE;
+	} else if (is_device_coherent_page(page)) {
+		/* Is the page migrated to this device or some other? */
+		if (dmirror->mdevice == dmirror_page_to_device(page))
+			*perm = HMM_DMIRROR_PROT_DEV_COHERENT_LOCAL;
+		else
+			*perm = HMM_DMIRROR_PROT_DEV_COHERENT_REMOTE;
 	} else if (is_zero_pfn(page_to_pfn(page)))
 		*perm = HMM_DMIRROR_PROT_ZERO;
 	else
@@ -1101,8 +1254,12 @@ 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_EXCLUSIVE:
@@ -1167,14 +1324,13 @@ static const struct file_operations dmirror_fops = {
 
 static void dmirror_devmem_free(struct page *page)
 {
-	struct page *rpage = page->zone_device_data;
+	struct page *rpage = BACKING_PAGE(page);
 	struct dmirror_device *mdevice;
 
-	if (rpage)
+	if (rpage != page)
 		__free_page(rpage);
 
 	mdevice = dmirror_page_to_device(page);
-
 	spin_lock(&mdevice->lock);
 	mdevice->cfree++;
 	page->zone_device_data = mdevice->free_pages;
@@ -1182,43 +1338,11 @@ 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));
-		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;
-	unsigned long src_pfns;
-	unsigned long dst_pfns;
+	unsigned long src_pfns = 0;
+	unsigned long dst_pfns = 0;
 	struct page *rpage;
 	struct dmirror *dmirror;
 	vm_fault_t ret;
@@ -1238,7 +1362,7 @@ static vm_fault_t dmirror_devmem_fault(struct vm_fault *vmf)
 	args.src = &src_pfns;
 	args.dst = &dst_pfns;
 	args.pgmap_owner = dmirror->mdevice;
-	args.flags = MIGRATE_VMA_SELECT_DEVICE_PRIVATE;
+	args.flags = dmirror_select_device(dmirror);
 
 	if (migrate_vma_setup(&args))
 		return VM_FAULT_SIGBUS;
@@ -1317,6 +1441,12 @@ static int __init hmm_dmirror_init(void)
 				HMM_DMIRROR_MEMORY_DEVICE_PRIVATE;
 	dmirror_devices[ndevices++].zone_device_type =
 				HMM_DMIRROR_MEMORY_DEVICE_PRIVATE;
+	if (spm_addr_dev0 && spm_addr_dev1) {
+		dmirror_devices[ndevices++].zone_device_type =
+					HMM_DMIRROR_MEMORY_DEVICE_COHERENT;
+		dmirror_devices[ndevices++].zone_device_type =
+					HMM_DMIRROR_MEMORY_DEVICE_COHERENT;
+	}
 	for (id = 0; id < ndevices; id++) {
 		ret = dmirror_device_init(dmirror_devices + id, id);
 		if (ret)
@@ -1339,7 +1469,8 @@ static void __exit hmm_dmirror_exit(void)
 	int id;
 
 	for (id = 0; id < DMIRROR_NDEVICES; id++)
-		dmirror_device_remove(dmirror_devices + id);
+		if (dmirror_devices[id].zone_device_type)
+			dmirror_device_remove(dmirror_devices + id);
 	unregister_chrdev_region(dmirror_dev, DMIRROR_NDEVICES);
 }
 
diff --git a/lib/test_hmm_uapi.h b/lib/test_hmm_uapi.h
index 625f3690d086..e190b2ab6f19 100644
--- a/lib/test_hmm_uapi.h
+++ b/lib/test_hmm_uapi.h
@@ -33,11 +33,12 @@ struct hmm_dmirror_cmd {
 /* 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_EXCLUSIVE		_IOWR('H', 0x04, struct hmm_dmirror_cmd)
-#define HMM_DMIRROR_CHECK_EXCLUSIVE	_IOWR('H', 0x05, struct hmm_dmirror_cmd)
-#define HMM_DMIRROR_GET_MEM_DEV_TYPE	_IOWR('H', 0x06, 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_EXCLUSIVE		_IOWR('H', 0x05, struct hmm_dmirror_cmd)
+#define HMM_DMIRROR_CHECK_EXCLUSIVE	_IOWR('H', 0x06, struct hmm_dmirror_cmd)
+#define HMM_DMIRROR_GET_MEM_DEV_TYPE	_IOWR('H', 0x07, struct hmm_dmirror_cmd)
 
 /*
  * Values returned in hmm_dmirror_cmd.ptr for HMM_DMIRROR_SNAPSHOT.
@@ -52,6 +53,8 @@ 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,
@@ -63,6 +66,8 @@ 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_LOCAL	= 0x40,
+	HMM_DMIRROR_PROT_DEV_COHERENT_REMOTE	= 0x50,
 };
 
 enum {
-- 
2.32.0


  parent reply	other threads:[~2022-05-24 19:08 UTC|newest]

Thread overview: 38+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-05-24 19:06 [PATCH v3 00/13] Add MEMORY_DEVICE_COHERENT for coherent device memory mapping Alex Sierra
2022-05-24 19:06 ` Alex Sierra
2022-05-24 19:06 ` [PATCH v3 01/13] mm: add zone device coherent type memory support Alex Sierra
2022-05-24 19:06   ` Alex Sierra
2022-05-24 19:06 ` [PATCH v3 02/13] mm: handling Non-LRU pages returned by vm_normal_pages Alex Sierra
2022-05-24 19:06   ` Alex Sierra
2022-05-25  4:11   ` Alistair Popple
2022-05-25  4:11     ` Alistair Popple
2022-05-26 16:07     ` Sierra Guiza, Alejandro (Alex)
2022-05-26 16:07       ` Sierra Guiza, Alejandro (Alex)
2022-05-27  1:28       ` Alistair Popple
2022-05-27  1:28         ` Alistair Popple
2022-05-27  6:28     ` Felix Kuehling
2022-05-27  6:28       ` Felix Kuehling
2022-05-27  8:02       ` Alistair Popple
2022-05-27  8:02         ` Alistair Popple
2022-05-24 19:06 ` [PATCH v3 03/13] mm: add device coherent vma selection for memory migration Alex Sierra
2022-05-24 19:06   ` Alex Sierra
2022-05-24 19:06 ` [PATCH v3 04/13] mm: remove the vma check in migrate_vma_setup() Alex Sierra
2022-05-24 19:06   ` Alex Sierra
2022-05-24 19:06 ` [PATCH v3 05/13] mm/gup: migrate device coherent pages when pinning instead of failing Alex Sierra
2022-05-24 19:06   ` Alex Sierra
2022-05-24 19:06 ` [PATCH v3 06/13] drm/amdkfd: add SPM support for SVM Alex Sierra
2022-05-24 19:06   ` Alex Sierra
2022-05-24 19:06 ` [PATCH v3 07/13] lib: test_hmm add ioctl to get zone device type Alex Sierra
2022-05-24 19:06   ` Alex Sierra
2022-05-24 19:06 ` [PATCH v3 08/13] lib: test_hmm add module param for " Alex Sierra
2022-05-24 19:06   ` Alex Sierra
2022-05-24 19:06 ` Alex Sierra [this message]
2022-05-24 19:06   ` [PATCH v3 09/13] lib: add support for device coherent type in test_hmm Alex Sierra
2022-05-24 19:06 ` [PATCH v3 10/13] tools: update hmm-test to support device coherent type Alex Sierra
2022-05-24 19:06   ` Alex Sierra
2022-05-24 19:06 ` [PATCH v3 11/13] tools: update test_hmm script to support SP config Alex Sierra
2022-05-24 19:06   ` Alex Sierra
2022-05-24 19:06 ` [PATCH v3 12/13] tools: add hmm gup tests for device coherent type Alex Sierra
2022-05-24 19:06   ` Alex Sierra
2022-05-24 19:06 ` [PATCH v3 13/13] tools: add selftests to hmm for COW in device memory Alex Sierra
2022-05-24 19:06   ` Alex Sierra

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20220524190632.3304-10-alex.sierra@amd.com \
    --to=alex.sierra@amd.com \
    --cc=Felix.Kuehling@amd.com \
    --cc=akpm@linux-foundation.org \
    --cc=amd-gfx@lists.freedesktop.org \
    --cc=apopple@nvidia.com \
    --cc=david@redhat.com \
    --cc=dri-devel@lists.freedesktop.org \
    --cc=hch@lst.de \
    --cc=jgg@nvidia.com \
    --cc=jglisse@redhat.com \
    --cc=linux-ext4@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=linux-xfs@vger.kernel.org \
    --cc=rcampbell@nvidia.com \
    --cc=willy@infradead.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.