+ lib-add-support-for-device-coherent-type-in-test_hmm.patch added to -mm tree

[Andrew Morton <akpm@linux-foundation.org>]

The patch titled
     Subject: lib: add support for device coherent type in test_hmm
has been added to the -mm tree.  Its filename is
     lib-add-support-for-device-coherent-type-in-test_hmm.patch

This patch should soon appear at
    https://ozlabs.org/~akpm/mmots/broken-out/lib-add-support-for-device-coherent-type-in-test_hmm.patch
and later at
    https://ozlabs.org/~akpm/mmotm/broken-out/lib-add-support-for-device-coherent-type-in-test_hmm.patch

Before you just go and hit "reply", please:
   a) Consider who else should be cc'ed
   b) Prefer to cc a suitable mailing list as well
   c) Ideally: find the original patch on the mailing list and do a
      reply-to-all to that, adding suitable additional cc's

*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***

The -mm tree is included into linux-next and is updated
there every 3-4 working days

------------------------------------------------------
From: Alex Sierra <alex.sierra@amd.com>
Subject: lib: add support for device coherent type in test_hmm

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.

Link: https://lkml.kernel.org/r/20220201154901.7921-9-alex.sierra@amd.com
Signed-off-by: Alex Sierra <alex.sierra@amd.com>
Acked-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Alistair Poppple <apopple@nvidia.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Jason Gunthorpe <jgg@nvidia.com>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Ralph Campbell <rcampbell@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 lib/test_hmm.c      |  260 +++++++++++++++++++++++++++++++-----------
 lib/test_hmm_uapi.h |   15 +-
 2 files changed, 205 insertions(+), 70 deletions(-)

--- a/lib/test_hmm.c~lib-add-support-for-device-coherent-type-in-test_hmm
+++ a/lib/test_hmm.c
@@ -29,11 +29,22 @@
 
 #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,
@@ -122,6 +133,21 @@ static int dmirror_bounce_init(struct dm
 	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);
@@ -572,16 +598,19 @@ err_devmem:
 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 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;
-
+	if (dmirror_is_private_zone(mdevice)) {
+		rpage = alloc_page(GFP_HIGHUSER);
+		if (!rpage)
+			return NULL;
+	}
 	spin_lock(&mdevice->lock);
 
 	if (mdevice->free_pages) {
@@ -601,7 +630,8 @@ static struct page *dmirror_devmem_alloc
 	return dpage;
 
 error:
-	__free_page(rpage);
+	if (rpage)
+		__free_page(rpage);
 	return NULL;
 }
 
@@ -627,12 +657,16 @@ static void dmirror_migrate_alloc_and_co
 		 * 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
@@ -646,6 +680,8 @@ static void dmirror_migrate_alloc_and_co
 		 */
 		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))
@@ -723,11 +759,7 @@ static int dmirror_migrate_finalize_and_
 		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);
@@ -807,15 +839,124 @@ static int dmirror_exclusive(struct dmir
 	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_dev_private_or_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] = { 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];
-	unsigned long dst_pfns[64];
+	unsigned long src_pfns[64] = { 0 };
+	unsigned long dst_pfns[64] = { 0 };
 	struct dmirror_bounce bounce;
 	struct migrate_vma args;
 	unsigned long next;
@@ -852,6 +993,7 @@ static int dmirror_migrate(struct dmirro
 		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);
@@ -860,7 +1002,7 @@ static int dmirror_migrate(struct dmirro
 	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;
@@ -897,12 +1039,22 @@ static void dmirror_mkentry(struct dmirr
 	}
 
 	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_dev_private_or_coherent_page(page)) {
+		/* Is page ZONE_DEVICE coherent? */
+		if (is_device_coherent_page(page)) {
+			if (dmirror->mdevice == dmirror_page_to_device(page))
+				*perm = HMM_DMIRROR_PROT_DEV_COHERENT_LOCAL;
+			else
+				*perm = HMM_DMIRROR_PROT_DEV_COHERENT_REMOTE;
+		/*
+		 * 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
+		} else {
 			*perm = HMM_DMIRROR_PROT_DEV_PRIVATE_REMOTE;
+		}
 	} else if (is_zero_pfn(page_to_pfn(page)))
 		*perm = HMM_DMIRROR_PROT_ZERO;
 	else
@@ -1099,8 +1251,12 @@ static long dmirror_fops_unlocked_ioctl(
 		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:
@@ -1165,14 +1321,13 @@ static const struct file_operations dmir
 
 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;
@@ -1180,43 +1335,11 @@ static void dmirror_devmem_free(struct p
 	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;
@@ -1236,7 +1359,7 @@ static vm_fault_t dmirror_devmem_fault(s
 	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;
@@ -1315,6 +1438,12 @@ 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)
@@ -1337,7 +1466,8 @@ 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);
 }
 
--- a/lib/test_hmm_uapi.h~lib-add-support-for-device-coherent-type-in-test_hmm
+++ a/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 {
_

Patches currently in -mm which might be from alex.sierra@amd.com are

mm-add-zone-device-coherent-type-memory-support.patch
mm-add-device-coherent-vma-selection-for-memory-migration.patch
mm-gup-fail-get_user_pages-for-longterm-dev-coherent-type.patch
drm-amdkfd-add-spm-support-for-svm.patch
drm-amdkfd-coherent-type-as-sys-mem-on-migration-to-ram.patch
lib-test_hmm-add-ioctl-to-get-zone-device-type.patch
lib-test_hmm-add-module-param-for-zone-device-type.patch
lib-add-support-for-device-coherent-type-in-test_hmm.patch
tools-update-hmm-test-to-support-device-coherent-type.patch
tools-update-test_hmm-script-to-support-sp-config.patch