From: Balbir Singh <balbirs@nvidia.com>
To: linux-kernel@vger.kernel.org, dri-devel@lists.freedesktop.org,
linux-mm@kvack.org
Cc: akpm@linux-foundation.org, "Balbir Singh" <balbirs@nvidia.com>,
"David Hildenbrand" <david@redhat.com>, "Zi Yan" <ziy@nvidia.com>,
"Joshua Hahn" <joshua.hahnjy@gmail.com>,
"Rakie Kim" <rakie.kim@sk.com>,
"Byungchul Park" <byungchul@sk.com>,
"Gregory Price" <gourry@gourry.net>,
"Ying Huang" <ying.huang@linux.alibaba.com>,
"Alistair Popple" <apopple@nvidia.com>,
"Oscar Salvador" <osalvador@suse.de>,
"Lorenzo Stoakes" <lorenzo.stoakes@oracle.com>,
"Baolin Wang" <baolin.wang@linux.alibaba.com>,
"Liam R. Howlett" <Liam.Howlett@oracle.com>,
"Nico Pache" <npache@redhat.com>,
"Ryan Roberts" <ryan.roberts@arm.com>,
"Dev Jain" <dev.jain@arm.com>, "Barry Song" <baohua@kernel.org>,
"Lyude Paul" <lyude@redhat.com>,
"Danilo Krummrich" <dakr@kernel.org>,
"David Airlie" <airlied@gmail.com>,
"Simona Vetter" <simona@ffwll.ch>,
"Ralph Campbell" <rcampbell@nvidia.com>,
"Mika Penttilä" <mpenttil@redhat.com>,
"Matthew Brost" <matthew.brost@intel.com>,
"Francois Dugast" <francois.dugast@intel.com>
Subject: [v7 12/16] lib/test_hmm: add large page allocation failure testing
Date: Wed, 1 Oct 2025 16:57:03 +1000 [thread overview]
Message-ID: <20251001065707.920170-13-balbirs@nvidia.com> (raw)
In-Reply-To: <20251001065707.920170-1-balbirs@nvidia.com>
Add HMM_DMIRROR_FLAG_FAIL_ALLOC flag to simulate large page allocation
failures, enabling testing of split migration code paths.
This test flag allows validation of the fallback behavior when destination
device cannot allocate compound pages. This is useful for testing the
split migration functionality.
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: David Hildenbrand <david@redhat.com>
Cc: Zi Yan <ziy@nvidia.com>
Cc: Joshua Hahn <joshua.hahnjy@gmail.com>
Cc: Rakie Kim <rakie.kim@sk.com>
Cc: Byungchul Park <byungchul@sk.com>
Cc: Gregory Price <gourry@gourry.net>
Cc: Ying Huang <ying.huang@linux.alibaba.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: "Liam R. Howlett" <Liam.Howlett@oracle.com>
Cc: Nico Pache <npache@redhat.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Dev Jain <dev.jain@arm.com>
Cc: Barry Song <baohua@kernel.org>
Cc: Lyude Paul <lyude@redhat.com>
Cc: Danilo Krummrich <dakr@kernel.org>
Cc: David Airlie <airlied@gmail.com>
Cc: Simona Vetter <simona@ffwll.ch>
Cc: Ralph Campbell <rcampbell@nvidia.com>
Cc: Mika Penttilä <mpenttil@redhat.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: Francois Dugast <francois.dugast@intel.com>
Signed-off-by: Balbir Singh <balbirs@nvidia.com>
---
lib/test_hmm.c | 61 ++++++++++++++++++++++++++++++---------------
lib/test_hmm_uapi.h | 3 +++
2 files changed, 44 insertions(+), 20 deletions(-)
diff --git a/lib/test_hmm.c b/lib/test_hmm.c
index df429670633e..72a8b2f38d8a 100644
--- a/lib/test_hmm.c
+++ b/lib/test_hmm.c
@@ -92,6 +92,7 @@ struct dmirror {
struct xarray pt;
struct mmu_interval_notifier notifier;
struct mutex mutex;
+ __u64 flags;
};
/*
@@ -699,7 +700,12 @@ static void dmirror_migrate_alloc_and_copy(struct migrate_vma *args,
page_to_pfn(spage)))
goto next;
- dpage = dmirror_devmem_alloc_page(dmirror, is_large);
+ if (dmirror->flags & HMM_DMIRROR_FLAG_FAIL_ALLOC) {
+ dmirror->flags &= ~HMM_DMIRROR_FLAG_FAIL_ALLOC;
+ dpage = NULL;
+ } else
+ dpage = dmirror_devmem_alloc_page(dmirror, is_large);
+
if (!dpage) {
struct folio *folio;
unsigned long i;
@@ -959,44 +965,55 @@ static vm_fault_t dmirror_devmem_fault_alloc_and_copy(struct migrate_vma *args,
spage = BACKING_PAGE(spage);
order = folio_order(page_folio(spage));
-
if (order)
+ *dst = MIGRATE_PFN_COMPOUND;
+ if (*src & MIGRATE_PFN_WRITE)
+ *dst |= MIGRATE_PFN_WRITE;
+
+ if (dmirror->flags & HMM_DMIRROR_FLAG_FAIL_ALLOC) {
+ dmirror->flags &= ~HMM_DMIRROR_FLAG_FAIL_ALLOC;
+ *dst &= ~MIGRATE_PFN_COMPOUND;
+ dpage = NULL;
+ } else if (order) {
dpage = folio_page(vma_alloc_folio(GFP_HIGHUSER_MOVABLE,
order, args->vma, addr), 0);
- else
- dpage = alloc_page_vma(GFP_HIGHUSER_MOVABLE, args->vma, addr);
-
- /* Try with smaller pages if large allocation fails */
- if (!dpage && order) {
+ } else {
dpage = alloc_page_vma(GFP_HIGHUSER_MOVABLE, args->vma, addr);
- if (!dpage)
- return VM_FAULT_OOM;
- order = 0;
}
+ if (!dpage && !order)
+ return VM_FAULT_OOM;
+
pr_debug("migrating from sys to dev 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;
- if (order)
- *dst |= MIGRATE_PFN_COMPOUND;
+
+ if (dpage) {
+ lock_page(dpage);
+ *dst |= migrate_pfn(page_to_pfn(dpage));
+ }
for (i = 0; i < (1 << order); i++) {
struct page *src_page;
struct page *dst_page;
+ /* Try with smaller pages if large allocation fails */
+ if (!dpage && order) {
+ dpage = alloc_page_vma(GFP_HIGHUSER_MOVABLE, args->vma, addr);
+ lock_page(dpage);
+ dst[i] = migrate_pfn(page_to_pfn(dpage));
+ dst_page = pfn_to_page(page_to_pfn(dpage));
+ dpage = NULL; /* For the next iteration */
+ } else {
+ dst_page = pfn_to_page(page_to_pfn(dpage) + i);
+ }
+
src_page = pfn_to_page(page_to_pfn(spage) + i);
- dst_page = pfn_to_page(page_to_pfn(dpage) + i);
xa_erase(&dmirror->pt, addr >> PAGE_SHIFT);
+ addr += PAGE_SIZE;
copy_highpage(dst_page, src_page);
}
next:
- addr += PAGE_SIZE << order;
src += 1 << order;
dst += 1 << order;
}
@@ -1514,6 +1531,10 @@ static long dmirror_fops_unlocked_ioctl(struct file *filp,
dmirror_device_remove_chunks(dmirror->mdevice);
ret = 0;
break;
+ case HMM_DMIRROR_FLAGS:
+ dmirror->flags = cmd.npages;
+ ret = 0;
+ break;
default:
return -EINVAL;
diff --git a/lib/test_hmm_uapi.h b/lib/test_hmm_uapi.h
index 8c818a2cf4f6..f94c6d457338 100644
--- a/lib/test_hmm_uapi.h
+++ b/lib/test_hmm_uapi.h
@@ -37,6 +37,9 @@ 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_RELEASE _IOWR('H', 0x07, struct hmm_dmirror_cmd)
+#define HMM_DMIRROR_FLAGS _IOWR('H', 0x08, struct hmm_dmirror_cmd)
+
+#define HMM_DMIRROR_FLAG_FAIL_ALLOC (1ULL << 0)
/*
* Values returned in hmm_dmirror_cmd.ptr for HMM_DMIRROR_SNAPSHOT.
--
2.51.0
next prev parent reply other threads:[~2025-10-01 7:00 UTC|newest]
Thread overview: 75+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-10-01 6:56 [v7 00/16] mm: support device-private THP Balbir Singh
2025-10-01 6:56 ` [v7 01/16] mm/zone_device: support large zone device private folios Balbir Singh
2025-10-12 6:10 ` Lance Yang
2025-10-12 22:54 ` Balbir Singh
2025-10-01 6:56 ` [v7 02/16] mm/zone_device: Rename page_free callback to folio_free Balbir Singh
2025-10-01 6:56 ` [v7 03/16] mm/huge_memory: add device-private THP support to PMD operations Balbir Singh
2025-10-12 15:46 ` Lance Yang
2025-10-13 0:01 ` Balbir Singh
2025-10-13 1:48 ` Lance Yang
2025-10-17 14:49 ` linux-next: KVM/s390x regression (was: [v7 03/16] mm/huge_memory: add device-private THP support to PMD operations) Christian Borntraeger
2025-10-17 14:54 ` linux-next: KVM/s390x regression David Hildenbrand
2025-10-17 15:01 ` Christian Borntraeger
2025-10-17 15:07 ` David Hildenbrand
2025-10-17 15:20 ` Christian Borntraeger
2025-10-17 17:07 ` David Hildenbrand
2025-10-17 21:56 ` Balbir Singh
2025-10-17 22:15 ` David Hildenbrand
2025-10-17 22:41 ` David Hildenbrand
2025-10-20 7:01 ` Christian Borntraeger
2025-10-20 7:00 ` Christian Borntraeger
2025-10-20 8:41 ` David Hildenbrand
2025-10-20 9:04 ` Claudio Imbrenda
2025-10-27 16:47 ` Claudio Imbrenda
2025-10-27 16:59 ` David Hildenbrand
2025-10-27 17:06 ` Christian Borntraeger
2025-10-28 9:24 ` Balbir Singh
2025-10-28 13:01 ` [PATCH v1 0/1] KVM: s390: Fix missing present bit for gmap puds Claudio Imbrenda
2025-10-28 13:01 ` [PATCH v1 1/1] " Claudio Imbrenda
2025-10-28 21:23 ` Balbir Singh
2025-10-29 10:00 ` David Hildenbrand
2025-10-29 10:20 ` Claudio Imbrenda
2025-10-28 22:53 ` [PATCH v1 0/1] " Andrew Morton
2025-10-01 6:56 ` [v7 04/16] mm/rmap: extend rmap and migration support device-private entries Balbir Singh
2025-10-22 11:54 ` Lance Yang
2025-10-01 6:56 ` [v7 05/16] mm/huge_memory: implement device-private THP splitting Balbir Singh
2025-10-01 6:56 ` [v7 06/16] mm/migrate_device: handle partially mapped folios during collection Balbir Singh
2025-10-01 6:56 ` [v7 07/16] mm/migrate_device: implement THP migration of zone device pages Balbir Singh
2025-10-01 6:56 ` [v7 08/16] mm/memory/fault: add THP fault handling for zone device private pages Balbir Singh
2025-10-01 6:57 ` [v7 09/16] lib/test_hmm: add zone device private THP test infrastructure Balbir Singh
2025-10-01 6:57 ` [v7 10/16] mm/memremap: add driver callback support for folio splitting Balbir Singh
2025-10-01 6:57 ` [v7 11/16] mm/migrate_device: add THP splitting during migration Balbir Singh
2025-10-13 21:17 ` Zi Yan
2025-10-13 21:33 ` Balbir Singh
2025-10-13 21:55 ` Zi Yan
2025-10-13 22:50 ` Balbir Singh
2025-10-19 8:19 ` Wei Yang
2025-10-19 22:49 ` Balbir Singh
2025-10-19 22:59 ` Zi Yan
2025-10-21 21:34 ` Balbir Singh
2025-10-22 2:59 ` Zi Yan
2025-10-22 7:16 ` Balbir Singh
2025-10-22 15:26 ` Zi Yan
2025-10-28 9:32 ` Balbir Singh
2025-10-01 6:57 ` Balbir Singh [this message]
2025-10-01 6:57 ` [v7 13/16] selftests/mm/hmm-tests: new tests for zone device THP migration Balbir Singh
2025-10-01 6:57 ` [v7 14/16] selftests/mm/hmm-tests: partial unmap, mremap and anon_write tests Balbir Singh
2025-10-01 6:57 ` [v7 15/16] selftests/mm/hmm-tests: new throughput tests including THP Balbir Singh
2025-10-01 6:57 ` [v7 16/16] gpu/drm/nouveau: enable THP support for GPU memory migration Balbir Singh
2025-10-09 3:17 ` [v7 00/16] mm: support device-private THP Andrew Morton
2025-10-09 3:26 ` Balbir Singh
2025-10-09 10:33 ` Matthew Brost
2025-10-13 22:51 ` Balbir Singh
2025-11-11 23:43 ` Andrew Morton
2025-11-11 23:52 ` Balbir Singh
2025-11-12 0:24 ` Andrew Morton
2025-11-12 0:36 ` Balbir Singh
2025-11-20 2:40 ` Matthew Brost
2025-11-20 2:50 ` Balbir Singh
2025-11-20 2:59 ` Balbir Singh
2025-11-20 3:15 ` Matthew Brost
2025-11-20 3:58 ` Balbir Singh
2025-11-20 5:46 ` Balbir Singh
2025-11-20 5:53 ` Matthew Brost
2025-11-20 6:03 ` Balbir Singh
2025-11-20 17:27 ` Matthew Brost
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=20251001065707.920170-13-balbirs@nvidia.com \
--to=balbirs@nvidia.com \
--cc=Liam.Howlett@oracle.com \
--cc=airlied@gmail.com \
--cc=akpm@linux-foundation.org \
--cc=apopple@nvidia.com \
--cc=baohua@kernel.org \
--cc=baolin.wang@linux.alibaba.com \
--cc=byungchul@sk.com \
--cc=dakr@kernel.org \
--cc=david@redhat.com \
--cc=dev.jain@arm.com \
--cc=dri-devel@lists.freedesktop.org \
--cc=francois.dugast@intel.com \
--cc=gourry@gourry.net \
--cc=joshua.hahnjy@gmail.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=lorenzo.stoakes@oracle.com \
--cc=lyude@redhat.com \
--cc=matthew.brost@intel.com \
--cc=mpenttil@redhat.com \
--cc=npache@redhat.com \
--cc=osalvador@suse.de \
--cc=rakie.kim@sk.com \
--cc=rcampbell@nvidia.com \
--cc=ryan.roberts@arm.com \
--cc=simona@ffwll.ch \
--cc=ying.huang@linux.alibaba.com \
--cc=ziy@nvidia.com \
/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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox