Am 2021-11-18 um 1:53 a.m. schrieb Alistair Popple:

On Tuesday, 16 November 2021 6:30:18 AM AEDT Alex Sierra wrote:

...

Device memory that is cache coherent from device and CPU point of view. This is used on platforms that have an advanced system bus (like CAPI or CXL). Any page of a process can be migrated to such memory. However, no one should be allowed to pin such memory so that it can always be evicted.

Signed-off-by: Alex Sierra alex.sierra@amd.com

include/linux/memremap.h | 8 ++++++++ include/linux/mm.h | 9 +++++++++ mm/memcontrol.c | 6 +++--- mm/memory-failure.c | 6 +++++- mm/memremap.c | 5 ++++- mm/migrate.c | 21 +++++++++++++-------- 6 files changed, 42 insertions(+), 13 deletions(-)

diff --git a/include/linux/memremap.h b/include/linux/memremap.h index c0e9d35889e8..ff4d398edf35 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -39,6 +39,13 @@ struct vmem_altmap {

• A more complete discussion of unaddressable memory may be found in
• include/linux/hmm.h and Documentation/vm/hmm.rst.

• • MEMORY_DEVICE_COHERENT:
• • Device memory that is cache coherent from device and CPU point of view. This
• • is used on platforms that have an advanced system bus (like CAPI or CXL). A
• • driver can hotplug the device memory using ZONE_DEVICE and with that memory
• • type. Any page of a process can be migrated to such memory. However no one
• • should be allowed to pin such memory so that it can always be evicted.
• • MEMORY_DEVICE_FS_DAX:
  • Host memory that has similar access semantics as System RAM i.e. DMA
  • coherent and supports page pinning. In support of coordinating page

@@ -59,6 +66,7 @@ struct vmem_altmap { enum memory_type { /* 0 is reserved to catch uninitialized type fields */ MEMORY_DEVICE_PRIVATE = 1,

• MEMORY_DEVICE_COHERENT, MEMORY_DEVICE_FS_DAX, MEMORY_DEVICE_GENERIC, MEMORY_DEVICE_PCI_P2PDMA,

diff --git a/include/linux/mm.h b/include/linux/mm.h index 73a52aba448f..d23b6ebd2177 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1162,6 +1162,7 @@ static inline bool page_is_devmap_managed(struct page *page) return false; switch (page->pgmap->type) { case MEMORY_DEVICE_PRIVATE:

• case MEMORY_DEVICE_COHERENT: case MEMORY_DEVICE_FS_DAX: return true; default:

@@ -1191,6 +1192,14 @@ static inline bool is_device_private_page(const struct page *page) page->pgmap->type == MEMORY_DEVICE_PRIVATE; }

+static inline bool is_device_page(const struct page *page) +{

• return IS_ENABLED(CONFIG_DEV_PAGEMAP_OPS) &&

• is_zone_device_page(page) &&
  

• (page->pgmap->type == MEMORY_DEVICE_PRIVATE ||
  

• page->pgmap->type == MEMORY_DEVICE_COHERENT);
  

+}

static inline bool is_pci_p2pdma_page(const struct page *page) { return IS_ENABLED(CONFIG_DEV_PAGEMAP_OPS) && diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 6da5020a8656..e0275ebe1198 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -5695,8 +5695,8 @@ static int mem_cgroup_move_account(struct page *page,

• 2(MC_TARGET_SWAP): if the swap entry corresponding to this pte is a

• target for charge migration. if @target is not NULL, the entry is stored
  

• in target->ent.
  

• • 3(MC_TARGET_DEVICE): like MC_TARGET_PAGE but page is MEMORY_DEVICE_PRIVATE

• • (so ZONE_DEVICE page and thus not on the lru).
    

• • 3(MC_TARGET_DEVICE): like MC_TARGET_PAGE but page is MEMORY_DEVICE_COHERENT

• • or MEMORY_DEVICE_PRIVATE (so ZONE_DEVICE page and thus not on the lru).
    

  • For now we such page is charge like a regular page would be as for all
    

  • intent and purposes it is just special memory taking the place of a
    

  • regular page.
    

@@ -5730,7 +5730,7 @@ static enum mc_target_type get_mctgt_type(struct vm_area_struct *vma, */ if (page_memcg(page) == mc.from) { ret = MC_TARGET_PAGE;

• 	if (is_device_private_page(page))
  

• 	if (is_device_page(page))
  	ret = MC_TARGET_DEVICE;
  if (target)
  	target->page = page;
  

diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 3e6449f2102a..51b55fc5172c 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1554,12 +1554,16 @@ static int memory_failure_dev_pagemap(unsigned long pfn, int flags, goto unlock; }

• if (pgmap->type == MEMORY_DEVICE_PRIVATE) {

• switch (pgmap->type) {

• case MEMORY_DEVICE_PRIVATE:

• case MEMORY_DEVICE_COHERENT: /*

  • TODO: Handle HMM pages which may need coordination
  • with device-side memory.

  */ goto unlock;

• default:

• break;
  

  }

  /*

diff --git a/mm/memremap.c b/mm/memremap.c index ed593bf87109..94d6a1e01d42 100644 --- a/mm/memremap.c +++ b/mm/memremap.c @@ -44,6 +44,7 @@ EXPORT_SYMBOL(devmap_managed_key); static void devmap_managed_enable_put(struct dev_pagemap *pgmap) { if (pgmap->type == MEMORY_DEVICE_PRIVATE ||

•    pgmap->type == MEMORY_DEVICE_COHERENT ||
   pgmap->type == MEMORY_DEVICE_FS_DAX)
  

  static_branch_dec(&devmap_managed_key);

} @@ -51,6 +52,7 @@ static void devmap_managed_enable_put(struct dev_pagemap *pgmap) static void devmap_managed_enable_get(struct dev_pagemap *pgmap) { if (pgmap->type == MEMORY_DEVICE_PRIVATE ||

•    pgmap->type == MEMORY_DEVICE_COHERENT ||
   pgmap->type == MEMORY_DEVICE_FS_DAX)
  

  static_branch_inc(&devmap_managed_key);

} @@ -328,6 +330,7 @@ void *memremap_pages(struct dev_pagemap *pgmap, int nid)

switch (pgmap->type) { case MEMORY_DEVICE_PRIVATE:

• case MEMORY_DEVICE_COHERENT: if (!IS_ENABLED(CONFIG_DEVICE_PRIVATE)) { WARN(1, "Device private memory not supported\n"); return ERR_PTR(-EINVAL);

@@ -498,7 +501,7 @@ EXPORT_SYMBOL_GPL(get_dev_pagemap); void free_devmap_managed_page(struct page *page) { /* notify page idle for dax */

• if (!is_device_private_page(page)) {

• if (!is_device_page(page)) { wake_up_var(&page->_refcount); return; }

diff --git a/mm/migrate.c b/mm/migrate.c index 1852d787e6ab..f74422a42192 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -362,7 +362,7 @@ static int expected_page_refs(struct address_space *mapping, struct page *page) * Device private pages have an extra refcount as they are * ZONE_DEVICE pages. */

• expected_count += is_device_private_page(page);

• expected_count += is_device_page(page); if (mapping) expected_count += thp_nr_pages(page) + page_has_private(page);

@@ -2503,7 +2503,7 @@ static bool migrate_vma_check_page(struct page *page) * FIXME proper solution is to rework migration_entry_wait() so * it does not need to take a reference on page. */

Note that I have posted a patch to fix this - see https://lore.kernel.org/all/20211118020754.954425-1-apopple@nvidia.com/ This looks ok for now assuming coherent pages can never be pinned.

However that raises a question - what happens when something calls get_user_pages() on a pfn pointing to a coherent device page? I can't see anything in this series that prevents pinning of coherent device pages, so we can't just assume they aren't pinned.

I agree. I think we need to depend on your patch to go in first.

I'm also wondering if we need to do something to prevent get_user_pages from pinning device pages. And by "pin", I think migrate_vma_check_page is not talking about FOLL_PIN, but any get_user_pages call. As far as I can tell, there should be nothing fundamentally wrong with pinning device pages for a short time. But I think we'll want to avoid FOLL_LONGTERM because that would affect our memory manager's ability to evict device memory.

In the case of device-private pages this is enforced by the fact they never have present pte's, so any attempt to GUP them results in a fault. But if I'm understanding this series correctly that won't be the case for coherent device pages right?

Right.

Regards,   Felix

...

• return is_device_private_page(page);
  

• return is_device_page(page);
  

  }

  /* For file back page */

@@ -2791,7 +2791,7 @@ EXPORT_SYMBOL(migrate_vma_setup);

• handle_pte_fault()
  

•   do_anonymous_page()
  

• to map in an anonymous zero page but the struct page will be a ZONE_DEVICE

• • private page.

• • private or coherent page.
  */

static void migrate_vma_insert_page(struct migrate_vma *migrate, unsigned long addr, @@ -2867,10 +2867,15 @@ static void migrate_vma_insert_page(struct migrate_vma *migrate, swp_entry = make_readable_device_private_entry( page_to_pfn(page)); entry = swp_entry_to_pte(swp_entry);

• } else if (is_device_page(page)) {
  

How about adding an explicit `is_device_coherent_page()` helper? It would make the test more explicit that this is expected to handle just coherent pages and I bet there will be future changes that need to differentiate between private and coherent pages anyway.

...

• 	entry = pte_mkold(mk_pte(page,
  

• 				 READ_ONCE(vma->vm_page_prot)));
  

• 	if (vma->vm_flags & VM_WRITE)
  

• 		entry = pte_mkwrite(pte_mkdirty(entry));
  

  } else { /*

• 	 * For now we only support migrating to un-addressable
  

• 	 * device memory.
  

• 	 * We support migrating to private and coherent types
  

• 	 * for device zone memory.
   */
  pr_warn_once("Unsupported ZONE_DEVICE page type.\n");
  goto abort;
  

@@ -2976,10 +2981,10 @@ void migrate_vma_pages(struct migrate_vma *migrate) mapping = page_mapping(page);

if (is_zone_device_page(newpage)) {

• 	if (is_device_private_page(newpage)) {
  

• 	if (is_device_page(newpage)) {
  	/*
  

• 		 * For now only support private anonymous when
  

• 		 * migrating to un-addressable device memory.
  

• 		 * For now only support private and coherent
  

• 		 * anonymous when migrating to device memory.
  	 */
  	if (mapping) {
  		migrate->src[i] &= ~MIGRATE_PFN_MIGRATE;
  
  

Am 2021-11-21 um 9:40 p.m. schrieb Alistair Popple:

...

...

...

diff --git a/mm/migrate.c b/mm/migrate.c index 1852d787e6ab..f74422a42192 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -362,7 +362,7 @@ static int expected_page_refs(struct address_space *mapping, struct page *page) * Device private pages have an extra refcount as they are * ZONE_DEVICE pages. */

• expected_count += is_device_private_page(page);

• expected_count += is_device_page(page); if (mapping) expected_count += thp_nr_pages(page) + page_has_private(page);

@@ -2503,7 +2503,7 @@ static bool migrate_vma_check_page(struct page *page) * FIXME proper solution is to rework migration_entry_wait() so * it does not need to take a reference on page. */

Note that I have posted a patch to fix this - see https://lore.kernel.org/all/20211118020754.954425-1-apopple@nvidia.com/ This looks ok for now assuming coherent pages can never be pinned.

However that raises a question - what happens when something calls get_user_pages() on a pfn pointing to a coherent device page? I can't see anything in this series that prevents pinning of coherent device pages, so we can't just assume they aren't pinned.

I agree. I think we need to depend on your patch to go in first.

I'm also wondering if we need to do something to prevent get_user_pages from pinning device pages. And by "pin", I think migrate_vma_check_page is not talking about FOLL_PIN, but any get_user_pages call. As far as I can tell, there should be nothing fundamentally wrong with pinning device pages for a short time. But I think we'll want to avoid FOLL_LONGTERM because that would affect our memory manager's ability to evict device memory.

Right, so long as my fix goes in I don't think there is anything wrong with pinning device public pages. Agree that we should avoid FOLL_LONGTERM pins for device memory though. I think the way to do that is update is_pinnable_page() so we treat device pages the same as other unpinnable pages ie. long-term pins will migrate the page.

I'm trying to understand check_and_migrate_movable_pages in gup.c. It doesn't look like the right way to migrate device pages. We may have to do something different there as well. So instead of changing is_pinnable_page, it maybe better to explicitly check for is_device_page or is_device_coherent_page in check_and_migrate_movable_pages to migrate it correctly, or just fail outright.

Thanks,   Felix

...

...

In the case of device-private pages this is enforced by the fact they never have present pte's, so any attempt to GUP them results in a fault. But if I'm understanding this series correctly that won't be the case for coherent device pages right?

Right.

Regards, Felix

...

...

• return is_device_private_page(page);
  

• return is_device_page(page);
  

  }

  /* For file back page */

@@ -2791,7 +2791,7 @@ EXPORT_SYMBOL(migrate_vma_setup);

• handle_pte_fault()
  

•   do_anonymous_page()
  

• to map in an anonymous zero page but the struct page will be a ZONE_DEVICE

• • private page.

• • private or coherent page.
  */

static void migrate_vma_insert_page(struct migrate_vma *migrate, unsigned long addr, @@ -2867,10 +2867,15 @@ static void migrate_vma_insert_page(struct migrate_vma *migrate, swp_entry = make_readable_device_private_entry( page_to_pfn(page)); entry = swp_entry_to_pte(swp_entry);

• } else if (is_device_page(page)) {
  

How about adding an explicit `is_device_coherent_page()` helper? It would make the test more explicit that this is expected to handle just coherent pages and I bet there will be future changes that need to differentiate between private and coherent pages anyway.

...

• 	entry = pte_mkold(mk_pte(page,
  

• 				 READ_ONCE(vma->vm_page_prot)));
  

• 	if (vma->vm_flags & VM_WRITE)
  

• 		entry = pte_mkwrite(pte_mkdirty(entry));
  

  } else { /*

• 	 * For now we only support migrating to un-addressable
  

• 	 * device memory.
  

• 	 * We support migrating to private and coherent types
  

• 	 * for device zone memory.
   */
  pr_warn_once("Unsupported ZONE_DEVICE page type.\n");
  goto abort;
  

@@ -2976,10 +2981,10 @@ void migrate_vma_pages(struct migrate_vma *migrate) mapping = page_mapping(page);

if (is_zone_device_page(newpage)) {

• 	if (is_device_private_page(newpage)) {
  

• 	if (is_device_page(newpage)) {
  	/*
  

• 		 * For now only support private anonymous when
  

• 		 * migrating to un-addressable device memory.
  

• 		 * For now only support private and coherent
  

• 		 * anonymous when migrating to device memory.
  	 */
  	if (mapping) {
  		migrate->src[i] &= ~MIGRATE_PFN_MIGRATE;
  
  

On Tuesday, 16 November 2021 6:30:23 AM AEDT Alex Sierra wrote:

In order to configure device coherent in test_hmm, two module parameters should be passed, which correspond to the SP start address of each device (2) spm_addr_dev0 & spm_addr_dev1. If no parameters are passed, private device type is configured.

Thanks for taking the time to add proper tests for this, as previously mentioned I don't like the need for module parameters but understand why these are more difficult to avoid.

However as also mentioned previously the restriction of being able to test only private *or* coherent device pages is unnecessary and makes testing both types harder, especially if we need to test migration between device private and coherent pages.

<snip>

• res = request_free_mem_region(&iomem_resource, DEVMEM_CHUNK_SIZE,

• 		      "hmm_dmirror");
  

• if (IS_ERR(res))

• goto err_devmem;
  

• if (!spm_addr_dev0 && !spm_addr_dev1) {

• 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;
  

• mdevice->zone_device_type = HMM_DMIRROR_MEMORY_DEVICE_PRIVATE;
  

• } else if (spm_addr_dev0 && spm_addr_dev1) {

• devmem->pagemap.range.start = MINOR(mdevice->cdevice.dev) ?
  

• 					spm_addr_dev0 :
  

• 					spm_addr_dev1;
  

It seems like it would be fairly straight forward to address this concern by adding extra minor character devices for the coherent devices. Would it be possible for you to try that?

• devmem->pagemap.range.end = devmem->pagemap.range.start +
  

• 			    DEVMEM_CHUNK_SIZE - 1;
  

• devmem->pagemap.type = MEMORY_DEVICE_COHERENT;
  

• mdevice->zone_device_type = HMM_DMIRROR_MEMORY_DEVICE_COHERENT;
  

• } else {

• pr_err("Both spm_addr_dev parameters should be set\n");
  

• }

• mdevice->zone_device_type = HMM_DMIRROR_MEMORY_DEVICE_PRIVATE;
• 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;

@@ -495,10 +517,14 @@ 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;

@@ -531,7 +557,8 @@ static bool dmirror_allocate_chunk(struct dmirror_device *mdevice,

err_release: mutex_unlock(&mdevice->devmem_lock);

• release_mem_region(devmem->pagemap.range.start, range_len(&devmem->pagemap.range));

• if (res)

• release_mem_region(devmem->pagemap.range.start, range_len(&devmem->pagemap.range));
  

err_devmem: kfree(devmem);

@@ -1219,10 +1246,8 @@ 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) @@ -1235,8 +1260,9 @@ 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);

diff --git a/lib/test_hmm_uapi.h b/lib/test_hmm_uapi.h index c42e57a6a71e..77f81e6314eb 100644 --- a/lib/test_hmm_uapi.h +++ b/lib/test_hmm_uapi.h @@ -67,6 +67,7 @@ enum { enum { /* 0 is reserved to catch uninitialized type fields */ HMM_DMIRROR_MEMORY_DEVICE_PRIVATE = 1,

• HMM_DMIRROR_MEMORY_DEVICE_COHERENT,

};

#endif /* _LIB_TEST_HMM_UAPI_H */

Am 2021-11-15 um 2:30 p.m. schrieb Alex Sierra:

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 | 191 +++++++++++++++++++++++++++++++++----------- lib/test_hmm_uapi.h | 15 ++-- 2 files changed, 153 insertions(+), 53 deletions(-)

diff --git a/lib/test_hmm.c b/lib/test_hmm.c index 45334df28d7b..9e2cc0cd4412 100644 --- a/lib/test_hmm.c +++ b/lib/test_hmm.c @@ -471,6 +471,7 @@ 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)

@@ -553,7 +554,7 @@ static int dmirror_allocate_chunk(struct dmirror_device *mdevice, } spin_unlock(&mdevice->lock);

• return true;

• return 0;

You're changing the meaning of the return value, but you're not updating the callers. I think at least dmirror_devmem_alloc_page will be broken by this change.

err_release: mutex_unlock(&mdevice->devmem_lock); @@ -562,7 +563,7 @@ 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) @@ -571,8 +572,10 @@ 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)

@@ -623,12 +626,17 @@ 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));
  

• WARN_ON(spage && is_zone_device_page(spage));
  

You can write WARN_ON inside the if-condition:

if (WARN_ON(spage && is_zone_device_page(spage)) ...

But I don't see why you need both pr_err and WARN_ON. You can add a custom message by using WARN instead of WARN_ON:

WARN(spage && is_zone_device_page(spage), "page already in device spage pfn: 0x%lx\n", page_to_pfn(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

@@ -640,8 +648,11 @@ 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) ||

@@ -721,10 +732,13 @@ 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.
  

  */

I find this explanation confusing. The comment in dmirror_devmem_alloc_page is much clearer. I think all we need here is that dpage->zone_device_data points to the backing page for device_private pages. Device_coherent struct pages don't have a backing page because they represent a real CPU-accessible page already.

• entry = dpage->zone_device_data;
  

• entry = is_device_private_page(dpage) ? dpage->zone_device_data :
  

• 					dpage;
  

I see this in a few places. Maybe better to wrap that in a helper function or macro. Something like this:

#define BACKING_PAGE(page) (is_device_private_page((page)) ? \ (page)->zone_device_data : (page))

if (*dst & MIGRATE_PFN_WRITE)
	entry = xa_tag_pointer(entry, DPT_XA_TAG_WRITE);
entry = xa_store(&dmirror->pt, pfn, entry, GFP_ATOMIC);

@@ -804,8 +818,110 @@ 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;
  

• WARN_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; unsigned long size = cmd->npages << PAGE_SHIFT; @@ -849,6 +965,7 @@ 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);

@@ -857,7 +974,7 @@ 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;

@@ -894,9 +1011,15 @@ 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;
  

Does it make sense to distinguish between DEV_COHERENT_LOCAL and DEV_COHERENT_REMOTE as well?

• /*
  

•  * 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;

@@ -1096,8 +1219,12 @@ 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:

@@ -1152,38 +1279,6 @@ 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 77f81e6314eb..af15c35a90f4 100644 --- a/lib/test_hmm_uapi.h +++ b/lib/test_hmm_uapi.h @@ -19,6 +19,7 @@

• @npages: (in) number of pages to read/write
• @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; @@ -32,11 +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.

@@ -51,6 +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, @@ -62,6 +66,7 @@ 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,

Does it make sense to distinguish between DEV_COHERENT_LOCAL and DEV_COHERENT_REMOTE as well?

Regards,   Felix

};

enum {