* [PATCH v11 1/8] mm/gup: Introduce unpin_folio/unpin_folios helpers
2024-01-13 6:52 [PATCH v11 0/8] mm/gup: Introduce memfd_pin_folios() for pinning memfd folios Vivek Kasireddy
@ 2024-01-13 6:52 ` Vivek Kasireddy
2024-01-13 6:52 ` [PATCH v11 2/8] mm/gup: Introduce check_and_migrate_movable_folios() Vivek Kasireddy
` (6 subsequent siblings)
7 siblings, 0 replies; 9+ messages in thread
From: Vivek Kasireddy @ 2024-01-13 6:52 UTC (permalink / raw)
To: dri-devel, linux-mm
Cc: Vivek Kasireddy, David Hildenbrand, Matthew Wilcox,
Christoph Hellwig, Jason Gunthorpe, Peter Xu
These helpers are the folio versions of unpin_user_page/unpin_user_pages.
They are currently only useful for unpinning folios pinned by
memfd_pin_folios() or other associated routines. However, they could
find new uses in the future, when more and more folio-only helpers
are added to GUP.
Cc: David Hildenbrand <david@redhat.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Jason Gunthorpe <jgg@nvidia.com>
Cc: Peter Xu <peterx@redhat.com>
Suggested-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Vivek Kasireddy <vivek.kasireddy@intel.com>
---
include/linux/mm.h | 2 ++
mm/gup.c | 81 ++++++++++++++++++++++++++++++++++++++++------
2 files changed, 74 insertions(+), 9 deletions(-)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index da5219b48d52..a0321adaefad 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1585,11 +1585,13 @@ static inline void put_page(struct page *page)
#define GUP_PIN_COUNTING_BIAS (1U << 10)
void unpin_user_page(struct page *page);
+void unpin_folio(struct folio *folio);
void unpin_user_pages_dirty_lock(struct page **pages, unsigned long npages,
bool make_dirty);
void unpin_user_page_range_dirty_lock(struct page *page, unsigned long npages,
bool make_dirty);
void unpin_user_pages(struct page **pages, unsigned long npages);
+void unpin_folios(struct folio **folios, unsigned long nfolios);
static inline bool is_cow_mapping(vm_flags_t flags)
{
diff --git a/mm/gup.c b/mm/gup.c
index 231711efa390..4d7bc4453819 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -30,6 +30,23 @@ struct follow_page_context {
unsigned int page_mask;
};
+static inline void sanity_check_pinned_folios(struct folio **folios,
+ unsigned long nfolios)
+{
+ if (!IS_ENABLED(CONFIG_DEBUG_VM))
+ return;
+
+ for (; nfolios; nfolios--, folios++) {
+ struct folio *folio = *folios;
+
+ if (is_zero_folio(folio) ||
+ !folio_test_anon(folio))
+ continue;
+
+ VM_BUG_ON_FOLIO(!PageAnonExclusive(&folio->page), folio);
+ }
+}
+
static inline void sanity_check_pinned_pages(struct page **pages,
unsigned long npages)
{
@@ -52,15 +69,11 @@ static inline void sanity_check_pinned_pages(struct page **pages,
struct page *page = *pages;
struct folio *folio = page_folio(page);
- if (is_zero_page(page) ||
- !folio_test_anon(folio))
- continue;
- if (!folio_test_large(folio) || folio_test_hugetlb(folio))
- VM_BUG_ON_PAGE(!PageAnonExclusive(&folio->page), page);
- else
- /* Either a PTE-mapped or a PMD-mapped THP. */
- VM_BUG_ON_PAGE(!PageAnonExclusive(&folio->page) &&
- !PageAnonExclusive(page), page);
+ sanity_check_pinned_folios(&folio, 1);
+
+ /* Either a PTE-mapped or a PMD-mapped THP. */
+ if (folio_test_large(folio) && !folio_test_hugetlb(folio))
+ VM_BUG_ON_PAGE(!PageAnonExclusive(page), page);
}
}
@@ -276,6 +289,21 @@ void unpin_user_page(struct page *page)
}
EXPORT_SYMBOL(unpin_user_page);
+/**
+ * unpin_folio() - release a dma-pinned folio
+ * @folio: pointer to folio to be released
+ *
+ * Folios that were pinned via memfd_pin_folios() or other similar routines
+ * must be released either using unpin_folio() or unpin_folios(). This is so
+ * that such folios can be separately tracked and uniquely handled.
+ */
+void unpin_folio(struct folio *folio)
+{
+ sanity_check_pinned_folios(&folio, 1);
+ gup_put_folio(folio, 1, FOLL_PIN);
+}
+EXPORT_SYMBOL(unpin_folio);
+
/**
* folio_add_pin - Try to get an additional pin on a pinned folio
* @folio: The folio to be pinned
@@ -488,6 +516,41 @@ void unpin_user_pages(struct page **pages, unsigned long npages)
}
EXPORT_SYMBOL(unpin_user_pages);
+/**
+ * unpin_folios() - release an array of gup-pinned folios.
+ * @folios: array of folios to be marked dirty and released.
+ * @nfolios: number of folios in the @folios array.
+ *
+ * For each folio in the @folios array, release the folio using unpin_folio().
+ *
+ * Please see the unpin_folio() documentation for details.
+ */
+void unpin_folios(struct folio **folios, unsigned long nfolios)
+{
+ unsigned long i = 0, j;
+
+ /*
+ * If this WARN_ON() fires, then the system *might* be leaking folios
+ * (by leaving them pinned), but probably not. More likely, gup/pup
+ * returned a hard -ERRNO error to the caller, who erroneously passed
+ * it here.
+ */
+ if (WARN_ON(IS_ERR_VALUE(nfolios)))
+ return;
+
+ sanity_check_pinned_folios(folios, nfolios);
+ while (i < nfolios) {
+ for (j = i + 1; j < nfolios; j++)
+ if (folios[i] != folios[j])
+ break;
+
+ if (folios[i])
+ gup_put_folio(folios[i], j - i, FOLL_PIN);
+ i = j;
+ }
+}
+EXPORT_SYMBOL(unpin_folios);
+
/*
* Set the MMF_HAS_PINNED if not set yet; after set it'll be there for the mm's
* lifecycle. Avoid setting the bit unless necessary, or it might cause write
--
2.39.2
^ permalink raw reply related [flat|nested] 9+ messages in thread* [PATCH v11 2/8] mm/gup: Introduce check_and_migrate_movable_folios()
2024-01-13 6:52 [PATCH v11 0/8] mm/gup: Introduce memfd_pin_folios() for pinning memfd folios Vivek Kasireddy
2024-01-13 6:52 ` [PATCH v11 1/8] mm/gup: Introduce unpin_folio/unpin_folios helpers Vivek Kasireddy
@ 2024-01-13 6:52 ` Vivek Kasireddy
2024-01-13 6:52 ` [PATCH v11 3/8] mm/gup: Introduce memfd_pin_folios() for pinning memfd folios Vivek Kasireddy
` (5 subsequent siblings)
7 siblings, 0 replies; 9+ messages in thread
From: Vivek Kasireddy @ 2024-01-13 6:52 UTC (permalink / raw)
To: dri-devel, linux-mm
Cc: Vivek Kasireddy, David Hildenbrand, Matthew Wilcox,
Christoph Hellwig, Jason Gunthorpe, Peter Xu
This helper is the folio equivalent of check_and_migrate_movable_pages().
Therefore, all the rules that apply to check_and_migrate_movable_pages()
also apply to this one as well. Currently, this helper is only used by
memfd_pin_folios().
This patch also includes changes to rename and convert the internal
functions collect_longterm_unpinnable_pages() and
migrate_longterm_unpinnable_pages() to work on folios. Since they
are also used by check_and_migrate_movable_pages(), a temporary
array is used to collect and share the folios with these functions.
Cc: David Hildenbrand <david@redhat.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Jason Gunthorpe <jgg@nvidia.com>
Cc: Peter Xu <peterx@redhat.com>
Suggested-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Vivek Kasireddy <vivek.kasireddy@intel.com>
---
mm/gup.c | 129 +++++++++++++++++++++++++++++++++++++++----------------
1 file changed, 92 insertions(+), 37 deletions(-)
diff --git a/mm/gup.c b/mm/gup.c
index 4d7bc4453819..00b24a429ba8 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -2097,20 +2097,24 @@ struct page *get_dump_page(unsigned long addr)
#ifdef CONFIG_MIGRATION
/*
- * Returns the number of collected pages. Return value is always >= 0.
+ * Returns the number of collected folios. Return value is always >= 0.
*/
-static unsigned long collect_longterm_unpinnable_pages(
- struct list_head *movable_page_list,
- unsigned long nr_pages,
+static unsigned long collect_longterm_unpinnable_folios(
+ struct list_head *movable_folio_list,
+ unsigned long nr_folios,
+ struct folio **folios,
struct page **pages)
{
unsigned long i, collected = 0;
struct folio *prev_folio = NULL;
bool drain_allow = true;
+ struct folio *folio;
- for (i = 0; i < nr_pages; i++) {
- struct folio *folio = page_folio(pages[i]);
+ for (i = 0; i < nr_folios; i++) {
+ if (pages)
+ folios[i] = page_folio(pages[i]);
+ folio = folios[i];
if (folio == prev_folio)
continue;
prev_folio = folio;
@@ -2124,7 +2128,7 @@ static unsigned long collect_longterm_unpinnable_pages(
continue;
if (folio_test_hugetlb(folio)) {
- isolate_hugetlb(folio, movable_page_list);
+ isolate_hugetlb(folio, movable_folio_list);
continue;
}
@@ -2136,7 +2140,7 @@ static unsigned long collect_longterm_unpinnable_pages(
if (!folio_isolate_lru(folio))
continue;
- list_add_tail(&folio->lru, movable_page_list);
+ list_add_tail(&folio->lru, movable_folio_list);
node_stat_mod_folio(folio,
NR_ISOLATED_ANON + folio_is_file_lru(folio),
folio_nr_pages(folio));
@@ -2146,27 +2150,28 @@ static unsigned long collect_longterm_unpinnable_pages(
}
/*
- * Unpins all pages and migrates device coherent pages and movable_page_list.
- * Returns -EAGAIN if all pages were successfully migrated or -errno for failure
- * (or partial success).
+ * Unpins all folios and migrates device coherent folios and movable_folio_list.
+ * Returns -EAGAIN if all folios were successfully migrated or -errno for
+ * failure (or partial success).
*/
-static int migrate_longterm_unpinnable_pages(
- struct list_head *movable_page_list,
- unsigned long nr_pages,
- struct page **pages)
+static int migrate_longterm_unpinnable_folios(
+ struct list_head *movable_folio_list,
+ unsigned long nr_folios,
+ struct folio **folios)
{
int ret;
unsigned long i;
- for (i = 0; i < nr_pages; i++) {
- struct folio *folio = page_folio(pages[i]);
+ for (i = 0; i < nr_folios; i++) {
+ struct folio *folio = folios[i];
if (folio_is_device_coherent(folio)) {
/*
- * Migration will fail if the page is pinned, so convert
- * the pin on the source page to a normal reference.
+ * Migration will fail if the folio is pinned, so
+ * convert the pin on the source folio to a normal
+ * reference.
*/
- pages[i] = NULL;
+ folios[i] = NULL;
folio_get(folio);
gup_put_folio(folio, 1, FOLL_PIN);
@@ -2179,23 +2184,23 @@ static int migrate_longterm_unpinnable_pages(
}
/*
- * We can't migrate pages with unexpected references, so drop
+ * We can't migrate folios with unexpected references, so drop
* the reference obtained by __get_user_pages_locked().
- * Migrating pages have been added to movable_page_list after
+ * Migrating folios have been added to movable_folio_list after
* calling folio_isolate_lru() which takes a reference so the
- * page won't be freed if it's migrating.
+ * folio won't be freed if it's migrating.
*/
- unpin_user_page(pages[i]);
- pages[i] = NULL;
+ unpin_folio(folios[i]);
+ folios[i] = NULL;
}
- if (!list_empty(movable_page_list)) {
+ if (!list_empty(movable_folio_list)) {
struct migration_target_control mtc = {
.nid = NUMA_NO_NODE,
.gfp_mask = GFP_USER | __GFP_NOWARN,
};
- if (migrate_pages(movable_page_list, alloc_migration_target,
+ if (migrate_pages(movable_folio_list, alloc_migration_target,
NULL, (unsigned long)&mtc, MIGRATE_SYNC,
MR_LONGTERM_PIN, NULL)) {
ret = -ENOMEM;
@@ -2203,15 +2208,15 @@ static int migrate_longterm_unpinnable_pages(
}
}
- putback_movable_pages(movable_page_list);
+ putback_movable_pages(movable_folio_list);
return -EAGAIN;
err:
- for (i = 0; i < nr_pages; i++)
- if (pages[i])
- unpin_user_page(pages[i]);
- putback_movable_pages(movable_page_list);
+ for (i = 0; i < nr_folios; i++)
+ if (folios[i])
+ unpin_folio(folios[i]);
+ putback_movable_pages(movable_folio_list);
return ret;
}
@@ -2235,16 +2240,60 @@ static int migrate_longterm_unpinnable_pages(
static long check_and_migrate_movable_pages(unsigned long nr_pages,
struct page **pages)
{
+ unsigned long nr_folios = nr_pages;
unsigned long collected;
- LIST_HEAD(movable_page_list);
+ LIST_HEAD(movable_folio_list);
+ struct folio **folios;
+ long ret;
- collected = collect_longterm_unpinnable_pages(&movable_page_list,
- nr_pages, pages);
+ folios = kmalloc_array(nr_folios, sizeof(*folios), GFP_KERNEL);
+ if (!folios)
+ return -ENOMEM;
+
+ collected = collect_longterm_unpinnable_folios(&movable_folio_list,
+ nr_folios, folios,
+ pages);
+ if (!collected) {
+ kfree(folios);
+ return 0;
+ }
+
+ ret = migrate_longterm_unpinnable_folios(&movable_folio_list,
+ nr_folios, folios);
+ kfree(folios);
+ return ret;
+}
+
+/*
+ * Check whether all folios are *allowed* to be pinned. Rather confusingly, all
+ * folios in the range are required to be pinned via FOLL_PIN, before calling
+ * this routine.
+ *
+ * If any folios in the range are not allowed to be pinned, then this routine
+ * will migrate those folios away, unpin all the folios in the range and return
+ * -EAGAIN. The caller should re-pin the entire range with FOLL_PIN and then
+ * call this routine again.
+ *
+ * If an error other than -EAGAIN occurs, this indicates a migration failure.
+ * The caller should give up, and propagate the error back up the call stack.
+ *
+ * If everything is OK and all folios in the range are allowed to be pinned,
+ * then this routine leaves all folios pinned and returns zero for success.
+ */
+static long check_and_migrate_movable_folios(unsigned long nr_folios,
+ struct folio **folios)
+{
+ unsigned long collected;
+ LIST_HEAD(movable_folio_list);
+
+ collected = collect_longterm_unpinnable_folios(&movable_folio_list,
+ nr_folios, folios,
+ NULL);
if (!collected)
return 0;
- return migrate_longterm_unpinnable_pages(&movable_page_list, nr_pages,
- pages);
+ return migrate_longterm_unpinnable_folios(&movable_folio_list,
+ nr_folios, folios);
}
#else
static long check_and_migrate_movable_pages(unsigned long nr_pages,
@@ -2252,6 +2301,12 @@ static long check_and_migrate_movable_pages(unsigned long nr_pages,
{
return 0;
}
+
+static long check_and_migrate_movable_folios(unsigned long nr_folios,
+ struct folio **folios)
+{
+ return 0;
+}
#endif /* CONFIG_MIGRATION */
/*
--
2.39.2
^ permalink raw reply related [flat|nested] 9+ messages in thread* [PATCH v11 3/8] mm/gup: Introduce memfd_pin_folios() for pinning memfd folios
2024-01-13 6:52 [PATCH v11 0/8] mm/gup: Introduce memfd_pin_folios() for pinning memfd folios Vivek Kasireddy
2024-01-13 6:52 ` [PATCH v11 1/8] mm/gup: Introduce unpin_folio/unpin_folios helpers Vivek Kasireddy
2024-01-13 6:52 ` [PATCH v11 2/8] mm/gup: Introduce check_and_migrate_movable_folios() Vivek Kasireddy
@ 2024-01-13 6:52 ` Vivek Kasireddy
2024-01-13 6:52 ` [PATCH v11 4/8] udmabuf: Use vmf_insert_pfn and VM_PFNMAP for handling mmap Vivek Kasireddy
` (4 subsequent siblings)
7 siblings, 0 replies; 9+ messages in thread
From: Vivek Kasireddy @ 2024-01-13 6:52 UTC (permalink / raw)
To: dri-devel, linux-mm
Cc: Vivek Kasireddy, David Hildenbrand, Matthew Wilcox,
Christoph Hellwig, Daniel Vetter, Mike Kravetz, Hugh Dickins,
Peter Xu, Gerd Hoffmann, Dongwon Kim, Junxiao Chang,
Jason Gunthorpe, Christoph Hellwig
For drivers that would like to longterm-pin the folios associated
with a memfd, the memfd_pin_folios() API provides an option to
not only pin the folios via FOLL_PIN but also to check and migrate
them if they reside in movable zone or CMA block. This API
currently works with memfds but it should work with any files
that belong to either shmemfs or hugetlbfs. Files belonging to
other filesystems are rejected for now.
The folios need to be located first before pinning them via FOLL_PIN.
If they are found in the page cache, they can be immediately pinned.
Otherwise, they need to be allocated using the filesystem specific
APIs and then pinned.
Cc: David Hildenbrand <david@redhat.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Gerd Hoffmann <kraxel@redhat.com>
Cc: Dongwon Kim <dongwon.kim@intel.com>
Cc: Junxiao Chang <junxiao.chang@intel.com>
Suggested-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com> (v2)
Reviewed-by: David Hildenbrand <david@redhat.com> (v3)
Reviewed-by: Christoph Hellwig <hch@lst.de> (v6)
Signed-off-by: Vivek Kasireddy <vivek.kasireddy@intel.com>
---
include/linux/memfd.h | 5 ++
include/linux/mm.h | 3 +
mm/gup.c | 136 ++++++++++++++++++++++++++++++++++++++++++
mm/memfd.c | 34 +++++++++++
4 files changed, 178 insertions(+)
diff --git a/include/linux/memfd.h b/include/linux/memfd.h
index e7abf6fa4c52..3f2cf339ceaf 100644
--- a/include/linux/memfd.h
+++ b/include/linux/memfd.h
@@ -6,11 +6,16 @@
#ifdef CONFIG_MEMFD_CREATE
extern long memfd_fcntl(struct file *file, unsigned int cmd, unsigned int arg);
+struct folio *memfd_alloc_folio(struct file *memfd, pgoff_t idx);
#else
static inline long memfd_fcntl(struct file *f, unsigned int c, unsigned int a)
{
return -EINVAL;
}
+static inline struct folio *memfd_alloc_folio(struct file *memfd, pgoff_t idx)
+{
+ return ERR_PTR(-EINVAL);
+}
#endif
#endif /* __LINUX_MEMFD_H */
diff --git a/include/linux/mm.h b/include/linux/mm.h
index a0321adaefad..33ec267afc63 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2474,6 +2474,9 @@ long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages,
struct page **pages, unsigned int gup_flags);
long pin_user_pages_unlocked(unsigned long start, unsigned long nr_pages,
struct page **pages, unsigned int gup_flags);
+long memfd_pin_folios(struct file *memfd, loff_t start, loff_t end,
+ struct folio **folios, unsigned int max_folios,
+ pgoff_t *offset);
int get_user_pages_fast(unsigned long start, int nr_pages,
unsigned int gup_flags, struct page **pages);
diff --git a/mm/gup.c b/mm/gup.c
index 00b24a429ba8..5b2b55d87998 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -5,6 +5,7 @@
#include <linux/spinlock.h>
#include <linux/mm.h>
+#include <linux/memfd.h>
#include <linux/memremap.h>
#include <linux/pagemap.h>
#include <linux/rmap.h>
@@ -17,6 +18,7 @@
#include <linux/hugetlb.h>
#include <linux/migrate.h>
#include <linux/mm_inline.h>
+#include <linux/pagevec.h>
#include <linux/sched/mm.h>
#include <linux/shmem_fs.h>
@@ -3528,3 +3530,137 @@ long pin_user_pages_unlocked(unsigned long start, unsigned long nr_pages,
&locked, gup_flags);
}
EXPORT_SYMBOL(pin_user_pages_unlocked);
+
+/**
+ * memfd_pin_folios() - pin folios associated with a memfd
+ * @memfd: the memfd whose folios are to be pinned
+ * @start: the first memfd offset
+ * @end: the last memfd offset (inclusive)
+ * @folios: array that receives pointers to the folios pinned
+ * @max_folios: maximum number of entries in @folios
+ * @offset: the offset into the first folio
+ *
+ * Attempt to pin folios associated with a memfd in the contiguous range
+ * [start, end]. Given that a memfd is either backed by shmem or hugetlb,
+ * the folios can either be found in the page cache or need to be allocated
+ * if necessary. Once the folios are located, they are all pinned via
+ * FOLL_PIN and @offset is populatedwith the offset into the first folio.
+ * And, eventually, these pinned folios must be released either using
+ * unpin_folios() or unpin_folio().
+ *
+ * It must be noted that the folios may be pinned for an indefinite amount
+ * of time. And, in most cases, the duration of time they may stay pinned
+ * would be controlled by the userspace. This behavior is effectively the
+ * same as using FOLL_LONGTERM with other GUP APIs.
+ *
+ * Returns number of folios pinned, which could be less than @max_folios
+ * as it depends on the folio sizes that cover the range [start, end].
+ * If no folios were pinned, it returns -errno.
+ */
+long memfd_pin_folios(struct file *memfd, loff_t start, loff_t end,
+ struct folio **folios, unsigned int max_folios,
+ pgoff_t *offset)
+{
+ unsigned int flags, nr_folios, nr_found;
+ unsigned int i, pgshift = PAGE_SHIFT;
+ pgoff_t start_idx, end_idx, next_idx;
+ struct folio *folio = NULL;
+ struct folio_batch fbatch;
+ struct hstate *h;
+ long ret;
+
+ if (start > end || !max_folios)
+ return -EINVAL;
+
+ if (!memfd)
+ return -EINVAL;
+
+ if (!shmem_file(memfd) && !is_file_hugepages(memfd))
+ return -EINVAL;
+
+ if (is_file_hugepages(memfd)) {
+ h = hstate_file(memfd);
+ pgshift = huge_page_shift(h);
+ }
+
+ flags = memalloc_pin_save();
+ do {
+ nr_folios = 0;
+ start_idx = start >> pgshift;
+ end_idx = end >> pgshift;
+ if (is_file_hugepages(memfd)) {
+ start_idx <<= huge_page_order(h);
+ end_idx <<= huge_page_order(h);
+ }
+
+ folio_batch_init(&fbatch);
+ while (start_idx <= end_idx && nr_folios < max_folios) {
+ /*
+ * In most cases, we should be able to find the folios
+ * in the page cache. If we cannot find them for some
+ * reason, we try to allocate them and add them to the
+ * page cache.
+ */
+ nr_found = filemap_get_folios_contig(memfd->f_mapping,
+ &start_idx,
+ end_idx,
+ &fbatch);
+ if (folio) {
+ folio_put(folio);
+ folio = NULL;
+ }
+
+ next_idx = 0;
+ for (i = 0; i < nr_found; i++) {
+ /*
+ * As there can be multiple entries for a
+ * given folio in the batch returned by
+ * filemap_get_folios_contig(), the below
+ * check is to ensure that we pin and return a
+ * unique set of folios between start and end.
+ */
+ if (next_idx &&
+ next_idx != folio_index(fbatch.folios[i]))
+ continue;
+
+ folio = try_grab_folio(&fbatch.folios[i]->page,
+ 1, FOLL_PIN);
+ if (!folio) {
+ folio_batch_release(&fbatch);
+ goto err;
+ }
+
+ if (nr_folios == 0)
+ *offset = offset_in_folio(folio, start);
+
+ folios[nr_folios] = folio;
+ next_idx = folio_next_index(folio);
+ if (++nr_folios == max_folios)
+ break;
+ }
+
+ folio = NULL;
+ folio_batch_release(&fbatch);
+ if (!nr_found) {
+ folio = memfd_alloc_folio(memfd, start_idx);
+ if (IS_ERR(folio)) {
+ ret = PTR_ERR(folio);
+ if (ret != -EEXIST)
+ goto err;
+ }
+ }
+ }
+
+ ret = check_and_migrate_movable_folios(nr_folios, folios);
+ } while (ret == -EAGAIN);
+
+ memalloc_pin_restore(flags);
+ return ret ? ret : nr_folios;
+err:
+ memalloc_pin_restore(flags);
+ unpin_folios(folios, nr_folios);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(memfd_pin_folios);
+
diff --git a/mm/memfd.c b/mm/memfd.c
index d3a1ba4208c9..36a75e8249f8 100644
--- a/mm/memfd.c
+++ b/mm/memfd.c
@@ -63,6 +63,40 @@ static void memfd_tag_pins(struct xa_state *xas)
xas_unlock_irq(xas);
}
+/*
+ * This is a helper function used by memfd_pin_user_pages() in GUP (gup.c).
+ * It is mainly called to allocate a page in a memfd when the caller
+ * (memfd_pin_user_pages()) cannot find a page in the page cache at a given
+ * index in the mapping.
+ */
+struct folio *memfd_alloc_folio(struct file *memfd, pgoff_t idx)
+{
+#ifdef CONFIG_HUGETLB_PAGE
+ struct folio *folio;
+ int err;
+
+ if (is_file_hugepages(memfd)) {
+ folio = alloc_hugetlb_folio_nodemask(hstate_file(memfd),
+ NUMA_NO_NODE,
+ NULL,
+ GFP_USER);
+ if (folio && folio_try_get(folio)) {
+ err = hugetlb_add_to_page_cache(folio,
+ memfd->f_mapping,
+ idx);
+ if (err) {
+ folio_put(folio);
+ free_huge_folio(folio);
+ return ERR_PTR(err);
+ }
+ return folio;
+ }
+ return ERR_PTR(-ENOMEM);
+ }
+#endif
+ return shmem_read_folio(memfd->f_mapping, idx);
+}
+
/*
* Setting SEAL_WRITE requires us to verify there's no pending writer. However,
* via get_user_pages(), drivers might have some pending I/O without any active
--
2.39.2
^ permalink raw reply related [flat|nested] 9+ messages in thread* [PATCH v11 4/8] udmabuf: Use vmf_insert_pfn and VM_PFNMAP for handling mmap
2024-01-13 6:52 [PATCH v11 0/8] mm/gup: Introduce memfd_pin_folios() for pinning memfd folios Vivek Kasireddy
` (2 preceding siblings ...)
2024-01-13 6:52 ` [PATCH v11 3/8] mm/gup: Introduce memfd_pin_folios() for pinning memfd folios Vivek Kasireddy
@ 2024-01-13 6:52 ` Vivek Kasireddy
2024-01-13 6:52 ` [PATCH v11 5/8] udmabuf: Add back support for mapping hugetlb pages Vivek Kasireddy
` (3 subsequent siblings)
7 siblings, 0 replies; 9+ messages in thread
From: Vivek Kasireddy @ 2024-01-13 6:52 UTC (permalink / raw)
To: dri-devel, linux-mm
Cc: Vivek Kasireddy, David Hildenbrand, Daniel Vetter, Mike Kravetz,
Hugh Dickins, Peter Xu, Jason Gunthorpe, Gerd Hoffmann,
Dongwon Kim, Junxiao Chang
Add VM_PFNMAP to vm_flags in the mmap handler to ensure that
the mappings would be managed without using struct page.
And, in the vm_fault handler, use vmf_insert_pfn to share the
page's pfn to userspace instead of directly sharing the page
(via struct page *).
Cc: David Hildenbrand <david@redhat.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Jason Gunthorpe <jgg@nvidia.com>
Cc: Gerd Hoffmann <kraxel@redhat.com>
Cc: Dongwon Kim <dongwon.kim@intel.com>
Cc: Junxiao Chang <junxiao.chang@intel.com>
Suggested-by: David Hildenbrand <david@redhat.com>
Acked-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Vivek Kasireddy <vivek.kasireddy@intel.com>
---
drivers/dma-buf/udmabuf.c | 8 +++++---
1 file changed, 5 insertions(+), 3 deletions(-)
diff --git a/drivers/dma-buf/udmabuf.c b/drivers/dma-buf/udmabuf.c
index c40645999648..820c993c8659 100644
--- a/drivers/dma-buf/udmabuf.c
+++ b/drivers/dma-buf/udmabuf.c
@@ -35,12 +35,13 @@ static vm_fault_t udmabuf_vm_fault(struct vm_fault *vmf)
struct vm_area_struct *vma = vmf->vma;
struct udmabuf *ubuf = vma->vm_private_data;
pgoff_t pgoff = vmf->pgoff;
+ unsigned long pfn;
if (pgoff >= ubuf->pagecount)
return VM_FAULT_SIGBUS;
- vmf->page = ubuf->pages[pgoff];
- get_page(vmf->page);
- return 0;
+
+ pfn = page_to_pfn(ubuf->pages[pgoff]);
+ return vmf_insert_pfn(vma, vmf->address, pfn);
}
static const struct vm_operations_struct udmabuf_vm_ops = {
@@ -56,6 +57,7 @@ static int mmap_udmabuf(struct dma_buf *buf, struct vm_area_struct *vma)
vma->vm_ops = &udmabuf_vm_ops;
vma->vm_private_data = ubuf;
+ vm_flags_set(vma, VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP);
return 0;
}
--
2.39.2
^ permalink raw reply related [flat|nested] 9+ messages in thread* [PATCH v11 5/8] udmabuf: Add back support for mapping hugetlb pages
2024-01-13 6:52 [PATCH v11 0/8] mm/gup: Introduce memfd_pin_folios() for pinning memfd folios Vivek Kasireddy
` (3 preceding siblings ...)
2024-01-13 6:52 ` [PATCH v11 4/8] udmabuf: Use vmf_insert_pfn and VM_PFNMAP for handling mmap Vivek Kasireddy
@ 2024-01-13 6:52 ` Vivek Kasireddy
2024-01-13 6:52 ` [PATCH v11 6/8] udmabuf: Convert udmabuf driver to use folios Vivek Kasireddy
` (2 subsequent siblings)
7 siblings, 0 replies; 9+ messages in thread
From: Vivek Kasireddy @ 2024-01-13 6:52 UTC (permalink / raw)
To: dri-devel, linux-mm
Cc: Vivek Kasireddy, David Hildenbrand, Daniel Vetter, Mike Kravetz,
Hugh Dickins, Peter Xu, Jason Gunthorpe, Gerd Hoffmann,
Dongwon Kim, Junxiao Chang
A user or admin can configure a VMM (Qemu) Guest's memory to be
backed by hugetlb pages for various reasons. However, a Guest OS
would still allocate (and pin) buffers that are backed by regular
4k sized pages. In order to map these buffers and create dma-bufs
for them on the Host, we first need to find the hugetlb pages where
the buffer allocations are located and then determine the offsets
of individual chunks (within those pages) and use this information
to eventually populate a scatterlist.
Testcase: default_hugepagesz=2M hugepagesz=2M hugepages=2500 options
were passed to the Host kernel and Qemu was launched with these
relevant options: qemu-system-x86_64 -m 4096m....
-device virtio-gpu-pci,max_outputs=1,blob=true,xres=1920,yres=1080
-display gtk,gl=on
-object memory-backend-memfd,hugetlb=on,id=mem1,size=4096M
-machine memory-backend=mem1
Replacing -display gtk,gl=on with -display gtk,gl=off above would
exercise the mmap handler.
Cc: David Hildenbrand <david@redhat.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Jason Gunthorpe <jgg@nvidia.com>
Cc: Gerd Hoffmann <kraxel@redhat.com>
Cc: Dongwon Kim <dongwon.kim@intel.com>
Cc: Junxiao Chang <junxiao.chang@intel.com>
Acked-by: Mike Kravetz <mike.kravetz@oracle.com> (v2)
Signed-off-by: Vivek Kasireddy <vivek.kasireddy@intel.com>
---
drivers/dma-buf/udmabuf.c | 122 +++++++++++++++++++++++++++++++-------
1 file changed, 101 insertions(+), 21 deletions(-)
diff --git a/drivers/dma-buf/udmabuf.c b/drivers/dma-buf/udmabuf.c
index 820c993c8659..274defd3fa3e 100644
--- a/drivers/dma-buf/udmabuf.c
+++ b/drivers/dma-buf/udmabuf.c
@@ -10,6 +10,7 @@
#include <linux/miscdevice.h>
#include <linux/module.h>
#include <linux/shmem_fs.h>
+#include <linux/hugetlb.h>
#include <linux/slab.h>
#include <linux/udmabuf.h>
#include <linux/vmalloc.h>
@@ -28,6 +29,7 @@ struct udmabuf {
struct page **pages;
struct sg_table *sg;
struct miscdevice *device;
+ pgoff_t *offsets;
};
static vm_fault_t udmabuf_vm_fault(struct vm_fault *vmf)
@@ -41,6 +43,8 @@ static vm_fault_t udmabuf_vm_fault(struct vm_fault *vmf)
return VM_FAULT_SIGBUS;
pfn = page_to_pfn(ubuf->pages[pgoff]);
+ pfn += ubuf->offsets[pgoff] >> PAGE_SHIFT;
+
return vmf_insert_pfn(vma, vmf->address, pfn);
}
@@ -90,23 +94,29 @@ static struct sg_table *get_sg_table(struct device *dev, struct dma_buf *buf,
{
struct udmabuf *ubuf = buf->priv;
struct sg_table *sg;
+ struct scatterlist *sgl;
+ unsigned int i = 0;
int ret;
sg = kzalloc(sizeof(*sg), GFP_KERNEL);
if (!sg)
return ERR_PTR(-ENOMEM);
- ret = sg_alloc_table_from_pages(sg, ubuf->pages, ubuf->pagecount,
- 0, ubuf->pagecount << PAGE_SHIFT,
- GFP_KERNEL);
+
+ ret = sg_alloc_table(sg, ubuf->pagecount, GFP_KERNEL);
if (ret < 0)
- goto err;
+ goto err_alloc;
+
+ for_each_sg(sg->sgl, sgl, ubuf->pagecount, i)
+ sg_set_page(sgl, ubuf->pages[i], PAGE_SIZE, ubuf->offsets[i]);
+
ret = dma_map_sgtable(dev, sg, direction, 0);
if (ret < 0)
- goto err;
+ goto err_map;
return sg;
-err:
+err_map:
sg_free_table(sg);
+err_alloc:
kfree(sg);
return ERR_PTR(ret);
}
@@ -143,6 +153,7 @@ static void release_udmabuf(struct dma_buf *buf)
for (pg = 0; pg < ubuf->pagecount; pg++)
put_page(ubuf->pages[pg]);
+ kfree(ubuf->offsets);
kfree(ubuf->pages);
kfree(ubuf);
}
@@ -196,17 +207,77 @@ static const struct dma_buf_ops udmabuf_ops = {
#define SEALS_WANTED (F_SEAL_SHRINK)
#define SEALS_DENIED (F_SEAL_WRITE)
+static int handle_hugetlb_pages(struct udmabuf *ubuf, struct file *memfd,
+ pgoff_t offset, pgoff_t pgcnt,
+ pgoff_t *pgbuf)
+{
+ struct hstate *hpstate = hstate_file(memfd);
+ pgoff_t mapidx = offset >> huge_page_shift(hpstate);
+ pgoff_t subpgoff = (offset & ~huge_page_mask(hpstate)) >> PAGE_SHIFT;
+ pgoff_t maxsubpgs = huge_page_size(hpstate) >> PAGE_SHIFT;
+ struct page *hpage = NULL;
+ struct folio *folio;
+ pgoff_t pgidx;
+
+ mapidx <<= huge_page_order(hpstate);
+ for (pgidx = 0; pgidx < pgcnt; pgidx++) {
+ if (!hpage) {
+ folio = __filemap_get_folio(memfd->f_mapping,
+ mapidx,
+ FGP_ACCESSED, 0);
+ if (IS_ERR(folio))
+ return PTR_ERR(folio);
+
+ hpage = &folio->page;
+ }
+
+ get_page(hpage);
+ ubuf->pages[*pgbuf] = hpage;
+ ubuf->offsets[*pgbuf] = subpgoff << PAGE_SHIFT;
+ (*pgbuf)++;
+ if (++subpgoff == maxsubpgs) {
+ put_page(hpage);
+ hpage = NULL;
+ subpgoff = 0;
+ mapidx += pages_per_huge_page(hpstate);
+ }
+ }
+
+ if (hpage)
+ put_page(hpage);
+
+ return 0;
+}
+
+static int handle_shmem_pages(struct udmabuf *ubuf, struct file *memfd,
+ pgoff_t offset, pgoff_t pgcnt,
+ pgoff_t *pgbuf)
+{
+ pgoff_t pgidx, pgoff = offset >> PAGE_SHIFT;
+ struct page *page;
+
+ for (pgidx = 0; pgidx < pgcnt; pgidx++) {
+ page = shmem_read_mapping_page(memfd->f_mapping,
+ pgoff + pgidx);
+ if (IS_ERR(page))
+ return PTR_ERR(page);
+
+ ubuf->pages[*pgbuf] = page;
+ (*pgbuf)++;
+ }
+
+ return 0;
+}
+
static long udmabuf_create(struct miscdevice *device,
struct udmabuf_create_list *head,
struct udmabuf_create_item *list)
{
DEFINE_DMA_BUF_EXPORT_INFO(exp_info);
struct file *memfd = NULL;
- struct address_space *mapping = NULL;
struct udmabuf *ubuf;
struct dma_buf *buf;
- pgoff_t pgoff, pgcnt, pgidx, pgbuf = 0, pglimit;
- struct page *page;
+ pgoff_t pgcnt, pgbuf = 0, pglimit;
int seals, ret = -EINVAL;
u32 i, flags;
@@ -234,6 +305,12 @@ static long udmabuf_create(struct miscdevice *device,
ret = -ENOMEM;
goto err;
}
+ ubuf->offsets = kcalloc(ubuf->pagecount, sizeof(*ubuf->offsets),
+ GFP_KERNEL);
+ if (!ubuf->offsets) {
+ ret = -ENOMEM;
+ goto err;
+ }
pgbuf = 0;
for (i = 0; i < head->count; i++) {
@@ -241,8 +318,7 @@ static long udmabuf_create(struct miscdevice *device,
memfd = fget(list[i].memfd);
if (!memfd)
goto err;
- mapping = memfd->f_mapping;
- if (!shmem_mapping(mapping))
+ if (!shmem_file(memfd) && !is_file_hugepages(memfd))
goto err;
seals = memfd_fcntl(memfd, F_GET_SEALS, 0);
if (seals == -EINVAL)
@@ -251,16 +327,19 @@ static long udmabuf_create(struct miscdevice *device,
if ((seals & SEALS_WANTED) != SEALS_WANTED ||
(seals & SEALS_DENIED) != 0)
goto err;
- pgoff = list[i].offset >> PAGE_SHIFT;
- pgcnt = list[i].size >> PAGE_SHIFT;
- for (pgidx = 0; pgidx < pgcnt; pgidx++) {
- page = shmem_read_mapping_page(mapping, pgoff + pgidx);
- if (IS_ERR(page)) {
- ret = PTR_ERR(page);
- goto err;
- }
- ubuf->pages[pgbuf++] = page;
- }
+
+ pgcnt = list[i].size >> PAGE_SHIFT;
+ if (is_file_hugepages(memfd))
+ ret = handle_hugetlb_pages(ubuf, memfd,
+ list[i].offset,
+ pgcnt, &pgbuf);
+ else
+ ret = handle_shmem_pages(ubuf, memfd,
+ list[i].offset,
+ pgcnt, &pgbuf);
+ if (ret < 0)
+ goto err;
+
fput(memfd);
memfd = NULL;
}
@@ -287,6 +366,7 @@ static long udmabuf_create(struct miscdevice *device,
put_page(ubuf->pages[--pgbuf]);
if (memfd)
fput(memfd);
+ kfree(ubuf->offsets);
kfree(ubuf->pages);
kfree(ubuf);
return ret;
--
2.39.2
^ permalink raw reply related [flat|nested] 9+ messages in thread* [PATCH v11 6/8] udmabuf: Convert udmabuf driver to use folios
2024-01-13 6:52 [PATCH v11 0/8] mm/gup: Introduce memfd_pin_folios() for pinning memfd folios Vivek Kasireddy
` (4 preceding siblings ...)
2024-01-13 6:52 ` [PATCH v11 5/8] udmabuf: Add back support for mapping hugetlb pages Vivek Kasireddy
@ 2024-01-13 6:52 ` Vivek Kasireddy
2024-01-13 6:52 ` [PATCH v11 7/8] udmabuf: Pin the pages using memfd_pin_folios() API Vivek Kasireddy
2024-01-13 6:52 ` [PATCH v11 8/8] selftests/udmabuf: Add tests to verify data after page migration Vivek Kasireddy
7 siblings, 0 replies; 9+ messages in thread
From: Vivek Kasireddy @ 2024-01-13 6:52 UTC (permalink / raw)
To: dri-devel, linux-mm
Cc: Vivek Kasireddy, David Hildenbrand, Matthew Wilcox,
Daniel Vetter, Mike Kravetz, Hugh Dickins, Peter Xu,
Jason Gunthorpe, Gerd Hoffmann, Dongwon Kim, Junxiao Chang
This is mainly a preparatory patch to use memfd_pin_folios() API
for pinning folios. Using folios instead of pages makes sense as
the udmabuf driver needs to handle both shmem and hugetlb cases.
However, the function vmap_udmabuf() still needs a list of pages;
so, we collect all the head pages into a local array in this case.
Other changes in this patch include the addition of helpers for
checking the memfd seals and exporting dmabuf. Moving code from
udmabuf_create() into these helpers improves readability given
that udmabuf_create() is a bit long.
Cc: David Hildenbrand <david@redhat.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Jason Gunthorpe <jgg@nvidia.com>
Cc: Gerd Hoffmann <kraxel@redhat.com>
Cc: Dongwon Kim <dongwon.kim@intel.com>
Cc: Junxiao Chang <junxiao.chang@intel.com>
Signed-off-by: Vivek Kasireddy <vivek.kasireddy@intel.com>
---
drivers/dma-buf/udmabuf.c | 140 ++++++++++++++++++++++----------------
1 file changed, 83 insertions(+), 57 deletions(-)
diff --git a/drivers/dma-buf/udmabuf.c b/drivers/dma-buf/udmabuf.c
index 274defd3fa3e..a8f3af61f7f2 100644
--- a/drivers/dma-buf/udmabuf.c
+++ b/drivers/dma-buf/udmabuf.c
@@ -26,7 +26,7 @@ MODULE_PARM_DESC(size_limit_mb, "Max size of a dmabuf, in megabytes. Default is
struct udmabuf {
pgoff_t pagecount;
- struct page **pages;
+ struct folio **folios;
struct sg_table *sg;
struct miscdevice *device;
pgoff_t *offsets;
@@ -42,7 +42,7 @@ static vm_fault_t udmabuf_vm_fault(struct vm_fault *vmf)
if (pgoff >= ubuf->pagecount)
return VM_FAULT_SIGBUS;
- pfn = page_to_pfn(ubuf->pages[pgoff]);
+ pfn = folio_pfn(ubuf->folios[pgoff]);
pfn += ubuf->offsets[pgoff] >> PAGE_SHIFT;
return vmf_insert_pfn(vma, vmf->address, pfn);
@@ -68,11 +68,21 @@ static int mmap_udmabuf(struct dma_buf *buf, struct vm_area_struct *vma)
static int vmap_udmabuf(struct dma_buf *buf, struct iosys_map *map)
{
struct udmabuf *ubuf = buf->priv;
+ struct page **pages;
void *vaddr;
+ pgoff_t pg;
dma_resv_assert_held(buf->resv);
- vaddr = vm_map_ram(ubuf->pages, ubuf->pagecount, -1);
+ pages = kmalloc_array(ubuf->pagecount, sizeof(*pages), GFP_KERNEL);
+ if (!pages)
+ return -ENOMEM;
+
+ for (pg = 0; pg < ubuf->pagecount; pg++)
+ pages[pg] = &ubuf->folios[pg]->page;
+
+ vaddr = vm_map_ram(pages, ubuf->pagecount, -1);
+ kfree(pages);
if (!vaddr)
return -EINVAL;
@@ -107,7 +117,8 @@ static struct sg_table *get_sg_table(struct device *dev, struct dma_buf *buf,
goto err_alloc;
for_each_sg(sg->sgl, sgl, ubuf->pagecount, i)
- sg_set_page(sgl, ubuf->pages[i], PAGE_SIZE, ubuf->offsets[i]);
+ sg_set_folio(sgl, ubuf->folios[i], PAGE_SIZE,
+ ubuf->offsets[i]);
ret = dma_map_sgtable(dev, sg, direction, 0);
if (ret < 0)
@@ -152,9 +163,9 @@ static void release_udmabuf(struct dma_buf *buf)
put_sg_table(dev, ubuf->sg, DMA_BIDIRECTIONAL);
for (pg = 0; pg < ubuf->pagecount; pg++)
- put_page(ubuf->pages[pg]);
+ folio_put(ubuf->folios[pg]);
kfree(ubuf->offsets);
- kfree(ubuf->pages);
+ kfree(ubuf->folios);
kfree(ubuf);
}
@@ -215,36 +226,33 @@ static int handle_hugetlb_pages(struct udmabuf *ubuf, struct file *memfd,
pgoff_t mapidx = offset >> huge_page_shift(hpstate);
pgoff_t subpgoff = (offset & ~huge_page_mask(hpstate)) >> PAGE_SHIFT;
pgoff_t maxsubpgs = huge_page_size(hpstate) >> PAGE_SHIFT;
- struct page *hpage = NULL;
- struct folio *folio;
+ struct folio *folio = NULL;
pgoff_t pgidx;
mapidx <<= huge_page_order(hpstate);
for (pgidx = 0; pgidx < pgcnt; pgidx++) {
- if (!hpage) {
+ if (!folio) {
folio = __filemap_get_folio(memfd->f_mapping,
mapidx,
FGP_ACCESSED, 0);
if (IS_ERR(folio))
return PTR_ERR(folio);
-
- hpage = &folio->page;
}
- get_page(hpage);
- ubuf->pages[*pgbuf] = hpage;
+ folio_get(folio);
+ ubuf->folios[*pgbuf] = folio;
ubuf->offsets[*pgbuf] = subpgoff << PAGE_SHIFT;
(*pgbuf)++;
if (++subpgoff == maxsubpgs) {
- put_page(hpage);
- hpage = NULL;
+ folio_put(folio);
+ folio = NULL;
subpgoff = 0;
mapidx += pages_per_huge_page(hpstate);
}
}
- if (hpage)
- put_page(hpage);
+ if (folio)
+ folio_put(folio);
return 0;
}
@@ -254,31 +262,69 @@ static int handle_shmem_pages(struct udmabuf *ubuf, struct file *memfd,
pgoff_t *pgbuf)
{
pgoff_t pgidx, pgoff = offset >> PAGE_SHIFT;
- struct page *page;
+ struct folio *folio = NULL;
for (pgidx = 0; pgidx < pgcnt; pgidx++) {
- page = shmem_read_mapping_page(memfd->f_mapping,
- pgoff + pgidx);
- if (IS_ERR(page))
- return PTR_ERR(page);
+ folio = shmem_read_folio(memfd->f_mapping, pgoff + pgidx);
+ if (IS_ERR(folio))
+ return PTR_ERR(folio);
- ubuf->pages[*pgbuf] = page;
+ ubuf->folios[*pgbuf] = folio;
(*pgbuf)++;
}
return 0;
}
+static int check_memfd_seals(struct file *memfd)
+{
+ int seals;
+
+ if (!memfd)
+ return -EBADFD;
+
+ if (!shmem_file(memfd) && !is_file_hugepages(memfd))
+ return -EBADFD;
+
+ seals = memfd_fcntl(memfd, F_GET_SEALS, 0);
+ if (seals == -EINVAL)
+ return -EBADFD;
+
+ if ((seals & SEALS_WANTED) != SEALS_WANTED ||
+ (seals & SEALS_DENIED) != 0)
+ return -EINVAL;
+
+ return 0;
+}
+
+static int export_udmabuf(struct udmabuf *ubuf,
+ struct miscdevice *device,
+ u32 flags)
+{
+ DEFINE_DMA_BUF_EXPORT_INFO(exp_info);
+ struct dma_buf *buf;
+
+ ubuf->device = device;
+ exp_info.ops = &udmabuf_ops;
+ exp_info.size = ubuf->pagecount << PAGE_SHIFT;
+ exp_info.priv = ubuf;
+ exp_info.flags = O_RDWR;
+
+ buf = dma_buf_export(&exp_info);
+ if (IS_ERR(buf))
+ return PTR_ERR(buf);
+
+ return dma_buf_fd(buf, flags);
+}
+
static long udmabuf_create(struct miscdevice *device,
struct udmabuf_create_list *head,
struct udmabuf_create_item *list)
{
- DEFINE_DMA_BUF_EXPORT_INFO(exp_info);
+ pgoff_t pgcnt, pgbuf = 0, pglimit;
struct file *memfd = NULL;
struct udmabuf *ubuf;
- struct dma_buf *buf;
- pgoff_t pgcnt, pgbuf = 0, pglimit;
- int seals, ret = -EINVAL;
+ int ret = -EINVAL;
u32 i, flags;
ubuf = kzalloc(sizeof(*ubuf), GFP_KERNEL);
@@ -299,9 +345,9 @@ static long udmabuf_create(struct miscdevice *device,
if (!ubuf->pagecount)
goto err;
- ubuf->pages = kmalloc_array(ubuf->pagecount, sizeof(*ubuf->pages),
+ ubuf->folios = kmalloc_array(ubuf->pagecount, sizeof(*ubuf->folios),
GFP_KERNEL);
- if (!ubuf->pages) {
+ if (!ubuf->folios) {
ret = -ENOMEM;
goto err;
}
@@ -314,18 +360,9 @@ static long udmabuf_create(struct miscdevice *device,
pgbuf = 0;
for (i = 0; i < head->count; i++) {
- ret = -EBADFD;
memfd = fget(list[i].memfd);
- if (!memfd)
- goto err;
- if (!shmem_file(memfd) && !is_file_hugepages(memfd))
- goto err;
- seals = memfd_fcntl(memfd, F_GET_SEALS, 0);
- if (seals == -EINVAL)
- goto err;
- ret = -EINVAL;
- if ((seals & SEALS_WANTED) != SEALS_WANTED ||
- (seals & SEALS_DENIED) != 0)
+ ret = check_memfd_seals(memfd);
+ if (ret < 0)
goto err;
pgcnt = list[i].size >> PAGE_SHIFT;
@@ -341,33 +378,22 @@ static long udmabuf_create(struct miscdevice *device,
goto err;
fput(memfd);
- memfd = NULL;
}
- exp_info.ops = &udmabuf_ops;
- exp_info.size = ubuf->pagecount << PAGE_SHIFT;
- exp_info.priv = ubuf;
- exp_info.flags = O_RDWR;
-
- ubuf->device = device;
- buf = dma_buf_export(&exp_info);
- if (IS_ERR(buf)) {
- ret = PTR_ERR(buf);
+ flags = head->flags & UDMABUF_FLAGS_CLOEXEC ? O_CLOEXEC : 0;
+ ret = export_udmabuf(ubuf, device, flags);
+ if (ret < 0)
goto err;
- }
- flags = 0;
- if (head->flags & UDMABUF_FLAGS_CLOEXEC)
- flags |= O_CLOEXEC;
- return dma_buf_fd(buf, flags);
+ return ret;
err:
while (pgbuf > 0)
- put_page(ubuf->pages[--pgbuf]);
+ folio_put(ubuf->folios[--pgbuf]);
if (memfd)
fput(memfd);
kfree(ubuf->offsets);
- kfree(ubuf->pages);
+ kfree(ubuf->folios);
kfree(ubuf);
return ret;
}
--
2.39.2
^ permalink raw reply related [flat|nested] 9+ messages in thread* [PATCH v11 7/8] udmabuf: Pin the pages using memfd_pin_folios() API
2024-01-13 6:52 [PATCH v11 0/8] mm/gup: Introduce memfd_pin_folios() for pinning memfd folios Vivek Kasireddy
` (5 preceding siblings ...)
2024-01-13 6:52 ` [PATCH v11 6/8] udmabuf: Convert udmabuf driver to use folios Vivek Kasireddy
@ 2024-01-13 6:52 ` Vivek Kasireddy
2024-01-13 6:52 ` [PATCH v11 8/8] selftests/udmabuf: Add tests to verify data after page migration Vivek Kasireddy
7 siblings, 0 replies; 9+ messages in thread
From: Vivek Kasireddy @ 2024-01-13 6:52 UTC (permalink / raw)
To: dri-devel, linux-mm
Cc: Vivek Kasireddy, David Hildenbrand, Matthew Wilcox,
Daniel Vetter, Mike Kravetz, Hugh Dickins, Peter Xu,
Jason Gunthorpe, Gerd Hoffmann, Dongwon Kim, Junxiao Chang
Using memfd_pin_folios() will ensure that the pages are pinned
correctly using FOLL_PIN. And, this also ensures that we don't
accidentally break features such as memory hotunplug as it would
not allow pinning pages in the movable zone.
Using this new API also simplifies the code as we no longer have
to deal with extracting individual pages from their mappings or
handle shmem and hugetlb cases separately.
Cc: David Hildenbrand <david@redhat.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Jason Gunthorpe <jgg@nvidia.com>
Cc: Gerd Hoffmann <kraxel@redhat.com>
Cc: Dongwon Kim <dongwon.kim@intel.com>
Cc: Junxiao Chang <junxiao.chang@intel.com>
Signed-off-by: Vivek Kasireddy <vivek.kasireddy@intel.com>
---
drivers/dma-buf/udmabuf.c | 153 +++++++++++++++++++-------------------
1 file changed, 78 insertions(+), 75 deletions(-)
diff --git a/drivers/dma-buf/udmabuf.c b/drivers/dma-buf/udmabuf.c
index a8f3af61f7f2..afa8bfd2a2a9 100644
--- a/drivers/dma-buf/udmabuf.c
+++ b/drivers/dma-buf/udmabuf.c
@@ -30,6 +30,12 @@ struct udmabuf {
struct sg_table *sg;
struct miscdevice *device;
pgoff_t *offsets;
+ struct list_head unpin_list;
+};
+
+struct udmabuf_folio {
+ struct folio *folio;
+ struct list_head list;
};
static vm_fault_t udmabuf_vm_fault(struct vm_fault *vmf)
@@ -153,17 +159,43 @@ static void unmap_udmabuf(struct dma_buf_attachment *at,
return put_sg_table(at->dev, sg, direction);
}
+static void unpin_all_folios(struct list_head *unpin_list)
+{
+ struct udmabuf_folio *ubuf_folio;
+
+ while (!list_empty(unpin_list)) {
+ ubuf_folio = list_first_entry(unpin_list,
+ struct udmabuf_folio, list);
+ unpin_folio(ubuf_folio->folio);
+
+ list_del(&ubuf_folio->list);
+ kfree(ubuf_folio);
+ }
+}
+
+static int add_to_unpin_list(struct list_head *unpin_list,
+ struct folio *folio)
+{
+ struct udmabuf_folio *ubuf_folio;
+
+ ubuf_folio = kzalloc(sizeof(*ubuf_folio), GFP_KERNEL);
+ if (!ubuf_folio)
+ return -ENOMEM;
+
+ ubuf_folio->folio = folio;
+ list_add_tail(&ubuf_folio->list, unpin_list);
+ return 0;
+}
+
static void release_udmabuf(struct dma_buf *buf)
{
struct udmabuf *ubuf = buf->priv;
struct device *dev = ubuf->device->this_device;
- pgoff_t pg;
if (ubuf->sg)
put_sg_table(dev, ubuf->sg, DMA_BIDIRECTIONAL);
- for (pg = 0; pg < ubuf->pagecount; pg++)
- folio_put(ubuf->folios[pg]);
+ unpin_all_folios(&ubuf->unpin_list);
kfree(ubuf->offsets);
kfree(ubuf->folios);
kfree(ubuf);
@@ -218,64 +250,6 @@ static const struct dma_buf_ops udmabuf_ops = {
#define SEALS_WANTED (F_SEAL_SHRINK)
#define SEALS_DENIED (F_SEAL_WRITE)
-static int handle_hugetlb_pages(struct udmabuf *ubuf, struct file *memfd,
- pgoff_t offset, pgoff_t pgcnt,
- pgoff_t *pgbuf)
-{
- struct hstate *hpstate = hstate_file(memfd);
- pgoff_t mapidx = offset >> huge_page_shift(hpstate);
- pgoff_t subpgoff = (offset & ~huge_page_mask(hpstate)) >> PAGE_SHIFT;
- pgoff_t maxsubpgs = huge_page_size(hpstate) >> PAGE_SHIFT;
- struct folio *folio = NULL;
- pgoff_t pgidx;
-
- mapidx <<= huge_page_order(hpstate);
- for (pgidx = 0; pgidx < pgcnt; pgidx++) {
- if (!folio) {
- folio = __filemap_get_folio(memfd->f_mapping,
- mapidx,
- FGP_ACCESSED, 0);
- if (IS_ERR(folio))
- return PTR_ERR(folio);
- }
-
- folio_get(folio);
- ubuf->folios[*pgbuf] = folio;
- ubuf->offsets[*pgbuf] = subpgoff << PAGE_SHIFT;
- (*pgbuf)++;
- if (++subpgoff == maxsubpgs) {
- folio_put(folio);
- folio = NULL;
- subpgoff = 0;
- mapidx += pages_per_huge_page(hpstate);
- }
- }
-
- if (folio)
- folio_put(folio);
-
- return 0;
-}
-
-static int handle_shmem_pages(struct udmabuf *ubuf, struct file *memfd,
- pgoff_t offset, pgoff_t pgcnt,
- pgoff_t *pgbuf)
-{
- pgoff_t pgidx, pgoff = offset >> PAGE_SHIFT;
- struct folio *folio = NULL;
-
- for (pgidx = 0; pgidx < pgcnt; pgidx++) {
- folio = shmem_read_folio(memfd->f_mapping, pgoff + pgidx);
- if (IS_ERR(folio))
- return PTR_ERR(folio);
-
- ubuf->folios[*pgbuf] = folio;
- (*pgbuf)++;
- }
-
- return 0;
-}
-
static int check_memfd_seals(struct file *memfd)
{
int seals;
@@ -321,16 +295,19 @@ static long udmabuf_create(struct miscdevice *device,
struct udmabuf_create_list *head,
struct udmabuf_create_item *list)
{
- pgoff_t pgcnt, pgbuf = 0, pglimit;
+ pgoff_t pgoff, pgcnt, pglimit, pgbuf = 0;
+ long nr_folios, ret = -EINVAL;
struct file *memfd = NULL;
+ struct folio **folios;
struct udmabuf *ubuf;
- int ret = -EINVAL;
- u32 i, flags;
+ u32 i, j, k, flags;
+ loff_t end;
ubuf = kzalloc(sizeof(*ubuf), GFP_KERNEL);
if (!ubuf)
return -ENOMEM;
+ INIT_LIST_HEAD(&ubuf->unpin_list);
pglimit = (size_limit_mb * 1024 * 1024) >> PAGE_SHIFT;
for (i = 0; i < head->count; i++) {
if (!IS_ALIGNED(list[i].offset, PAGE_SIZE))
@@ -366,17 +343,44 @@ static long udmabuf_create(struct miscdevice *device,
goto err;
pgcnt = list[i].size >> PAGE_SHIFT;
- if (is_file_hugepages(memfd))
- ret = handle_hugetlb_pages(ubuf, memfd,
- list[i].offset,
- pgcnt, &pgbuf);
- else
- ret = handle_shmem_pages(ubuf, memfd,
- list[i].offset,
- pgcnt, &pgbuf);
- if (ret < 0)
+ folios = kmalloc_array(pgcnt, sizeof(*folios), GFP_KERNEL);
+ if (!folios) {
+ ret = -ENOMEM;
goto err;
+ }
+ end = list[i].offset + (pgcnt << PAGE_SHIFT) - 1;
+ ret = memfd_pin_folios(memfd, list[i].offset, end,
+ folios, pgcnt, &pgoff);
+ if (ret < 0) {
+ kfree(folios);
+ goto err;
+ }
+
+ nr_folios = ret;
+ pgoff >>= PAGE_SHIFT;
+ for (j = 0, k = 0; j < pgcnt; j++) {
+ ubuf->folios[pgbuf] = folios[k];
+ ubuf->offsets[pgbuf] = pgoff << PAGE_SHIFT;
+
+ if (j == 0 || ubuf->folios[pgbuf-1] != folios[k]) {
+ ret = add_to_unpin_list(&ubuf->unpin_list,
+ folios[k]);
+ if (ret < 0) {
+ kfree(folios);
+ goto err;
+ }
+ }
+
+ pgbuf++;
+ if (++pgoff == folio_nr_pages(folios[k])) {
+ pgoff = 0;
+ if (++k == nr_folios)
+ break;
+ }
+ }
+
+ kfree(folios);
fput(memfd);
}
@@ -388,10 +392,9 @@ static long udmabuf_create(struct miscdevice *device,
return ret;
err:
- while (pgbuf > 0)
- folio_put(ubuf->folios[--pgbuf]);
if (memfd)
fput(memfd);
+ unpin_all_folios(&ubuf->unpin_list);
kfree(ubuf->offsets);
kfree(ubuf->folios);
kfree(ubuf);
--
2.39.2
^ permalink raw reply related [flat|nested] 9+ messages in thread* [PATCH v11 8/8] selftests/udmabuf: Add tests to verify data after page migration
2024-01-13 6:52 [PATCH v11 0/8] mm/gup: Introduce memfd_pin_folios() for pinning memfd folios Vivek Kasireddy
` (6 preceding siblings ...)
2024-01-13 6:52 ` [PATCH v11 7/8] udmabuf: Pin the pages using memfd_pin_folios() API Vivek Kasireddy
@ 2024-01-13 6:52 ` Vivek Kasireddy
7 siblings, 0 replies; 9+ messages in thread
From: Vivek Kasireddy @ 2024-01-13 6:52 UTC (permalink / raw)
To: dri-devel, linux-mm
Cc: Vivek Kasireddy, Shuah Khan, David Hildenbrand, Daniel Vetter,
Mike Kravetz, Hugh Dickins, Peter Xu, Jason Gunthorpe,
Gerd Hoffmann, Dongwon Kim, Junxiao Chang
Since the memfd pages associated with a udmabuf may be migrated
as part of udmabuf create, we need to verify the data coherency
after successful migration. The new tests added in this patch try
to do just that using 4k sized pages and also 2 MB sized huge
pages for the memfd.
Successful completion of the tests would mean that there is no
disconnect between the memfd pages and the ones associated with
a udmabuf. And, these tests can also be augmented in the future
to test newer udmabuf features (such as handling memfd hole punch).
The idea for these tests comes from a patch by Mike Kravetz.
Cc: Shuah Khan <shuah@kernel.org>
Cc: David Hildenbrand <david@redhat.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Jason Gunthorpe <jgg@nvidia.com>
Cc: Gerd Hoffmann <kraxel@redhat.com>
Cc: Dongwon Kim <dongwon.kim@intel.com>
Cc: Junxiao Chang <junxiao.chang@intel.com>
Signed-off-by: Vivek Kasireddy <vivek.kasireddy@intel.com>
---
.../selftests/drivers/dma-buf/udmabuf.c | 151 +++++++++++++++++-
1 file changed, 147 insertions(+), 4 deletions(-)
diff --git a/tools/testing/selftests/drivers/dma-buf/udmabuf.c b/tools/testing/selftests/drivers/dma-buf/udmabuf.c
index c812080e304e..d76c813fe652 100644
--- a/tools/testing/selftests/drivers/dma-buf/udmabuf.c
+++ b/tools/testing/selftests/drivers/dma-buf/udmabuf.c
@@ -9,26 +9,132 @@
#include <errno.h>
#include <fcntl.h>
#include <malloc.h>
+#include <stdbool.h>
#include <sys/ioctl.h>
#include <sys/syscall.h>
+#include <sys/mman.h>
#include <linux/memfd.h>
#include <linux/udmabuf.h>
#define TEST_PREFIX "drivers/dma-buf/udmabuf"
#define NUM_PAGES 4
+#define NUM_ENTRIES 4
+#define MEMFD_SIZE 1024 /* in pages */
-static int memfd_create(const char *name, unsigned int flags)
+static unsigned int page_size;
+
+static int create_memfd_with_seals(off64_t size, bool hpage)
+{
+ int memfd, ret;
+ unsigned int flags = MFD_ALLOW_SEALING;
+
+ if (hpage)
+ flags |= MFD_HUGETLB;
+
+ memfd = memfd_create("udmabuf-test", flags);
+ if (memfd < 0) {
+ printf("%s: [skip,no-memfd]\n", TEST_PREFIX);
+ exit(77);
+ }
+
+ ret = fcntl(memfd, F_ADD_SEALS, F_SEAL_SHRINK);
+ if (ret < 0) {
+ printf("%s: [skip,fcntl-add-seals]\n", TEST_PREFIX);
+ exit(77);
+ }
+
+ ret = ftruncate(memfd, size);
+ if (ret == -1) {
+ printf("%s: [FAIL,memfd-truncate]\n", TEST_PREFIX);
+ exit(1);
+ }
+
+ return memfd;
+}
+
+static int create_udmabuf_list(int devfd, int memfd, off64_t memfd_size)
+{
+ struct udmabuf_create_list *list;
+ int ubuf_fd, i;
+
+ list = malloc(sizeof(struct udmabuf_create_list) +
+ sizeof(struct udmabuf_create_item) * NUM_ENTRIES);
+ if (!list) {
+ printf("%s: [FAIL, udmabuf-malloc]\n", TEST_PREFIX);
+ exit(1);
+ }
+
+ for (i = 0; i < NUM_ENTRIES; i++) {
+ list->list[i].memfd = memfd;
+ list->list[i].offset = i * (memfd_size / NUM_ENTRIES);
+ list->list[i].size = getpagesize() * NUM_PAGES;
+ }
+
+ list->count = NUM_ENTRIES;
+ list->flags = UDMABUF_FLAGS_CLOEXEC;
+ ubuf_fd = ioctl(devfd, UDMABUF_CREATE_LIST, list);
+ free(list);
+ if (ubuf_fd < 0) {
+ printf("%s: [FAIL, udmabuf-create]\n", TEST_PREFIX);
+ exit(1);
+ }
+
+ return ubuf_fd;
+}
+
+static void write_to_memfd(void *addr, off64_t size, char chr)
+{
+ int i;
+
+ for (i = 0; i < size / page_size; i++) {
+ *((char *)addr + (i * page_size)) = chr;
+ }
+}
+
+static void *mmap_fd(int fd, off64_t size)
{
- return syscall(__NR_memfd_create, name, flags);
+ void *addr;
+
+ addr = mmap(NULL, size, PROT_READ|PROT_WRITE, MAP_SHARED, fd, 0);
+ if (addr == MAP_FAILED) {
+ printf("%s: ubuf_fd mmap fail\n", TEST_PREFIX);
+ exit(1);
+ }
+
+ return addr;
+}
+
+static int compare_chunks(void *addr1, void *addr2, off64_t memfd_size)
+{
+ off64_t off;
+ int i = 0, j, k = 0, ret = 0;
+ char char1, char2;
+
+ while (i < NUM_ENTRIES) {
+ off = i * (memfd_size / NUM_ENTRIES);
+ for (j = 0; j < NUM_PAGES; j++, k++) {
+ char1 = *((char *)addr1 + off + (j * getpagesize()));
+ char2 = *((char *)addr2 + (k * getpagesize()));
+ if (char1 != char2) {
+ ret = -1;
+ goto err;
+ }
+ }
+ i++;
+ }
+err:
+ munmap(addr1, memfd_size);
+ munmap(addr2, NUM_ENTRIES * NUM_PAGES * getpagesize());
+ return ret;
}
int main(int argc, char *argv[])
{
struct udmabuf_create create;
int devfd, memfd, buf, ret;
- off_t size;
- void *mem;
+ off64_t size;
+ void *addr1, *addr2;
devfd = open("/dev/udmabuf", O_RDWR);
if (devfd < 0) {
@@ -90,6 +196,9 @@ int main(int argc, char *argv[])
}
/* should work */
+ page_size = getpagesize();
+ addr1 = mmap_fd(memfd, size);
+ write_to_memfd(addr1, size, 'a');
create.memfd = memfd;
create.offset = 0;
create.size = size;
@@ -98,6 +207,40 @@ int main(int argc, char *argv[])
printf("%s: [FAIL,test-4]\n", TEST_PREFIX);
exit(1);
}
+ munmap(addr1, size);
+ close(buf);
+ close(memfd);
+
+ /* should work (migration of 4k size pages)*/
+ size = MEMFD_SIZE * page_size;
+ memfd = create_memfd_with_seals(size, false);
+ addr1 = mmap_fd(memfd, size);
+ write_to_memfd(addr1, size, 'a');
+ buf = create_udmabuf_list(devfd, memfd, size);
+ addr2 = mmap_fd(buf, NUM_PAGES * NUM_ENTRIES * getpagesize());
+ write_to_memfd(addr1, size, 'b');
+ ret = compare_chunks(addr1, addr2, size);
+ if (ret < 0) {
+ printf("%s: [FAIL,test-5]\n", TEST_PREFIX);
+ exit(1);
+ }
+ close(buf);
+ close(memfd);
+
+ /* should work (migration of 2MB size huge pages)*/
+ page_size = getpagesize() * 512; /* 2 MB */
+ size = MEMFD_SIZE * page_size;
+ memfd = create_memfd_with_seals(size, true);
+ addr1 = mmap_fd(memfd, size);
+ write_to_memfd(addr1, size, 'a');
+ buf = create_udmabuf_list(devfd, memfd, size);
+ addr2 = mmap_fd(buf, NUM_PAGES * NUM_ENTRIES * getpagesize());
+ write_to_memfd(addr1, size, 'b');
+ ret = compare_chunks(addr1, addr2, size);
+ if (ret < 0) {
+ printf("%s: [FAIL,test-6]\n", TEST_PREFIX);
+ exit(1);
+ }
fprintf(stderr, "%s: ok\n", TEST_PREFIX);
close(buf);
--
2.39.2
^ permalink raw reply related [flat|nested] 9+ messages in thread