1 files changed, 261 insertions, 86 deletions

diff --git a/lib/test_hmm.c b/lib/test_hmm.c
index cfe632047839..e3965cafd27c 100644
--- a/lib/test_hmm.c
+++ b/lib/test_hmm.c
@@ -32,11 +32,32 @@
 
 #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,
+		"Specify start address for SPM (special purpose memory) used for device 0. By setting this Coherent device type will be used. Make sure spm_addr_dev1 is set too. Minimum SPM size should be DEVMEM_CHUNK_SIZE.");
+
+static unsigned long spm_addr_dev1;
+module_param(spm_addr_dev1, long, 0644);
+MODULE_PARM_DESC(spm_addr_dev1,
+		"Specify start address for SPM (special purpose memory) used for device 1. By setting this Coherent device type will be used. Make sure spm_addr_dev0 is set too. Minimum SPM size should be DEVMEM_CHUNK_SIZE.");
+
 static const struct dev_pagemap_ops dmirror_devmem_ops;
 static const struct mmu_interval_notifier_ops dmirror_min_ops;
 static dev_t dmirror_dev;
@@ -87,6 +108,7 @@ struct dmirror_chunk {
 struct dmirror_device {
 	struct cdev		cdevice;
 	struct hmm_devmem	*devmem;
+	unsigned int            zone_device_type;
 
 	unsigned int		devmem_capacity;
 	unsigned int		devmem_count;
@@ -114,6 +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);
@@ -454,28 +491,44 @@ fini:
 	return ret;
 }
 
-static bool dmirror_allocate_chunk(struct dmirror_device *mdevice,
+static int dmirror_allocate_chunk(struct dmirror_device *mdevice,
 				   struct page **ppage)
 {
 	struct dmirror_chunk *devmem;
-	struct resource *res;
+	struct resource *res = NULL;
 	unsigned long pfn;
 	unsigned long pfn_first;
 	unsigned long pfn_last;
 	void *ptr;
+	int ret = -ENOMEM;
 
 	devmem = kzalloc(sizeof(*devmem), GFP_KERNEL);
 	if (!devmem)
-		return false;
+		return ret;
 
-	res = request_free_mem_region(&iomem_resource, DEVMEM_CHUNK_SIZE,
-				      "hmm_dmirror");
-	if (IS_ERR(res))
+	switch (mdevice->zone_device_type) {
+	case HMM_DMIRROR_MEMORY_DEVICE_PRIVATE:
+		res = request_free_mem_region(&iomem_resource, DEVMEM_CHUNK_SIZE,
+					      "hmm_dmirror");
+		if (IS_ERR_OR_NULL(res))
+			goto err_devmem;
+		devmem->pagemap.range.start = res->start;
+		devmem->pagemap.range.end = res->end;
+		devmem->pagemap.type = MEMORY_DEVICE_PRIVATE;
+		break;
+	case HMM_DMIRROR_MEMORY_DEVICE_COHERENT:
+		devmem->pagemap.range.start = (MINOR(mdevice->cdevice.dev) - 2) ?
+							spm_addr_dev0 :
+							spm_addr_dev1;
+		devmem->pagemap.range.end = devmem->pagemap.range.start +
+					    DEVMEM_CHUNK_SIZE - 1;
+		devmem->pagemap.type = MEMORY_DEVICE_COHERENT;
+		break;
+	default:
+		ret = -EINVAL;
 		goto err_devmem;
+	}
 
-	devmem->pagemap.type = MEMORY_DEVICE_PRIVATE;
-	devmem->pagemap.range.start = res->start;
-	devmem->pagemap.range.end = res->end;
 	devmem->pagemap.nr_range = 1;
 	devmem->pagemap.ops = &dmirror_devmem_ops;
 	devmem->pagemap.owner = mdevice;
@@ -496,10 +549,14 @@ static bool dmirror_allocate_chunk(struct dmirror_device *mdevice,
 		mdevice->devmem_capacity = new_capacity;
 		mdevice->devmem_chunks = new_chunks;
 	}
-
 	ptr = memremap_pages(&devmem->pagemap, numa_node_id());
-	if (IS_ERR(ptr))
+	if (IS_ERR_OR_NULL(ptr)) {
+		if (ptr)
+			ret = PTR_ERR(ptr);
+		else
+			ret = -EFAULT;
 		goto err_release;
+	}
 
 	devmem->mdevice = mdevice;
 	pfn_first = devmem->pagemap.range.start >> PAGE_SHIFT;
@@ -528,30 +585,35 @@ static bool dmirror_allocate_chunk(struct dmirror_device *mdevice,
 	}
 	spin_unlock(&mdevice->lock);
 
-	return true;
+	return 0;
 
 err_release:
 	mutex_unlock(&mdevice->devmem_lock);
-	release_mem_region(devmem->pagemap.range.start, range_len(&devmem->pagemap.range));
+	if (res && devmem->pagemap.type == MEMORY_DEVICE_PRIVATE)
+		release_mem_region(devmem->pagemap.range.start,
+				   range_len(&devmem->pagemap.range));
 err_devmem:
 	kfree(devmem);
 
-	return false;
+	return ret;
 }
 
 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) {
@@ -561,7 +623,7 @@ static struct page *dmirror_devmem_alloc_page(struct dmirror_device *mdevice)
 		spin_unlock(&mdevice->lock);
 	} else {
 		spin_unlock(&mdevice->lock);
-		if (!dmirror_allocate_chunk(mdevice, &dpage))
+		if (dmirror_allocate_chunk(mdevice, &dpage))
 			goto error;
 	}
 
@@ -570,7 +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;
 }
 
@@ -596,12 +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
@@ -615,6 +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))
@@ -692,11 +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);
@@ -732,7 +797,7 @@ static int dmirror_exclusive(struct dmirror *dmirror,
 
 	mmap_read_lock(mm);
 	for (addr = start; addr < end; addr = next) {
-		unsigned long mapped;
+		unsigned long mapped = 0;
 		int i;
 
 		if (end < addr + (ARRAY_SIZE(pages) << PAGE_SHIFT))
@@ -741,7 +806,13 @@ static int dmirror_exclusive(struct dmirror *dmirror,
 			next = addr + (ARRAY_SIZE(pages) << PAGE_SHIFT);
 
 		ret = make_device_exclusive_range(mm, addr, next, pages, NULL);
-		mapped = dmirror_atomic_map(addr, next, pages, dmirror);
+		/*
+		 * Do dmirror_atomic_map() iff all pages are marked for
+		 * exclusive access to avoid accessing uninitialized
+		 * fields of pages.
+		 */
+		if (ret == (next - addr) >> PAGE_SHIFT)
+			mapped = dmirror_atomic_map(addr, next, pages, dmirror);
 		for (i = 0; i < ret; i++) {
 			if (pages[i]) {
 				unlock_page(pages[i]);
@@ -776,15 +847,126 @@ 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;
@@ -821,6 +1003,7 @@ 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);
@@ -829,7 +1012,10 @@ 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;
@@ -872,6 +1058,12 @@ 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
@@ -1059,8 +1251,12 @@ 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:
@@ -1122,14 +1318,13 @@ 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;
@@ -1137,43 +1332,11 @@ 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;
@@ -1193,7 +1356,7 @@ 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;
@@ -1231,10 +1394,8 @@ static int dmirror_device_init(struct dmirror_device *mdevice, int id)
 	if (ret)
 		return ret;
 
-	/* Build a list of free ZONE_DEVICE private struct pages */
-	dmirror_allocate_chunk(mdevice, NULL);
-
-	return 0;
+	/* Build a list of free ZONE_DEVICE struct pages */
+	return dmirror_allocate_chunk(mdevice, NULL);
 }
 
 static void dmirror_device_remove(struct dmirror_device *mdevice)
@@ -1247,8 +1408,9 @@ static void dmirror_device_remove(struct dmirror_device *mdevice)
 				mdevice->devmem_chunks[i];
 
 			memunmap_pages(&devmem->pagemap);
-			release_mem_region(devmem->pagemap.range.start,
-					   range_len(&devmem->pagemap.range));
+			if (devmem->pagemap.type == MEMORY_DEVICE_PRIVATE)
+				release_mem_region(devmem->pagemap.range.start,
+						   range_len(&devmem->pagemap.range));
 			kfree(devmem);
 		}
 		kfree(mdevice->devmem_chunks);
@@ -1260,14 +1422,26 @@ static void dmirror_device_remove(struct dmirror_device *mdevice)
 static int __init hmm_dmirror_init(void)
 {
 	int ret;
-	int id;
+	int id = 0;
+	int ndevices = 0;
 
 	ret = alloc_chrdev_region(&dmirror_dev, 0, DMIRROR_NDEVICES,
 				  "HMM_DMIRROR");
 	if (ret)
 		goto err_unreg;
 
-	for (id = 0; id < DMIRROR_NDEVICES; id++) {
+	memset(dmirror_devices, 0, DMIRROR_NDEVICES * sizeof(dmirror_devices[0]));
+	dmirror_devices[ndevices++].zone_device_type =
+				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)
 			goto err_chrdev;
@@ -1289,7 +1463,8 @@ 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);
 }