mm/gup: Introduce memfd_pin_folios() for pinning memfd folios
Subsystems (7)
Vivek Kasireddy
maintainerv13 cover mm/gup: Introduce memfd_pin_folios() for pinning memfd folios
Currently, some drivers (e.g, Udmabuf) that want to longterm-pin the pages/folios associated with a memfd, do so by simply taking a reference on them. This is not desirable because the pages/folios may reside in Movable zone or CMA block.
Therefore, having drivers use memfd_pin_folios() API ensures that the folios are appropriately pinned via FOLL_PIN for longterm DMA.
This patchset also introduces a few helpers and converts the Udmabuf driver to use folios and memfd_pin_folios() API to longterm-pin the folios for DMA. Two new Udmabuf selftests are also included to test the driver and the new API.
---
Patchset overview:
Patch 1-2: GUP helpers to migrate and unpin one or more folios Patch 3: Introduce memfd_pin_folios() API Patch 4-5: Udmabuf driver bug fixes for Qemu + hugetlb=on, blob=true case Patch 6-8: Convert Udmabuf to use memfd_pin_folios() and add sefltests
This series is tested using the following methods:
- Run the subtests added in Patch 8
- Run Qemu (master) with the following options and a few additional patches to Spice:
qemu-system-x86_64 -m 4096m....
-device virtio-gpu-pci,max_outputs=1,blob=true,xres=1920,yres=1080 -spice port=3001,gl=on,disable-ticketing=on,preferred-codec=gstreamer:h264 -object memory-backend-memfd,hugetlb=on,id=mem1,size=4096M -machine memory-backend=mem1
- Run source ./run_vmtests.sh -t gup_test -a to check GUP regressions
Changelog:
v12 -> v13: (suggestions from David)
- Drop the sanity checks in unpin_folio()/unpin_folios() due to unavailability of per folio anon-exclusive flag
- Export unpin_folio()/unpin_folios() using EXPORT_SYMBOL_GPL instead of EXPORT_SYMBOL
- Have check_and_migrate_movable_pages() just call check_and_migrate_movable_folios() instead of calling other helpers
- Slightly improve the comments and commit messages
v11 -> v12:
- Rebased and tested on mm-unstable
v10 -> v11:
- Remove the version string from the patch subject (Andrew)
- Move the changelog from the patches into the cover letter
- Rearrange the patchset to have GUP patches at the beginning
v9 -> v10:
- Introduce and use unpin_folio(), unpin_folios() and check_and_migrate_movable_folios() helpers
- Use a list to track the folios that need to be unpinned in udmabuf
v8 -> v9: (suggestions from Matthew)
- Drop the extern while declaring memfd_alloc_folio()
- Fix memfd_alloc_folio() declaration to have it return struct folio * instead of struct page * when CONFIG_MEMFD_CREATE is not defined
- Use folio_pfn() on the folio instead of page_to_pfn() on head page in udmabuf
- Don't split the arguments to shmem_read_folio() on multiple lines in udmabuf
v7 -> v8: (suggestions from David)
- Have caller pass [start, end], max_folios instead of start, nr_pages
- Replace offsets array with just offset into the first page
- Add comments explaning the need for next_idx
- Pin (and return) the folio (via FOLL_PIN) only once
v6 -> v7:
- Rename this API to memfd_pin_folios() and make it return folios and offsets instead of pages (David)
- Don't continue processing the folios in the batch returned by filemap_get_folios_contig() if they do not have correct next_idx
- Add the R-b tag from Christoph
v5 -> v6: (suggestions from Christoph)
- Rename this API to memfd_pin_user_pages() to make it clear that it is intended for memfds
- Move the memfd page allocation helper from gup.c to memfd.c
- Fix indentation errors in memfd_pin_user_pages()
- For contiguous ranges of folios, use a helper such as filemap_get_folios_contig() to lookup the page cache in batches
- Split the processing of hugetlb or shmem pages into helpers to simplify the code in udmabuf_create()
v4 -> v5: (suggestions from David)
- For hugetlb case, ensure that we only obtain head pages from the mapping by using __filemap_get_folio() instead of find_get_page_flags()
- Handle -EEXIST when two or more potential users try to simultaneously add a huge page to the mapping by forcing them to retry on failure
v3 -> v4:
- Remove the local variable "page" and instead use 3 return statements in alloc_file_page() (David)
- Add the R-b tag from David
v2 -> v3: (suggestions from David)
- Enclose the huge page allocation code with #ifdef CONFIG_HUGETLB_PAGE (Build error reported by kernel test robot <[email protected]>)
- Don't forget memalloc_pin_restore() on non-migration related errors
- Improve the readability of the cleanup code associated with non-migration related errors
- Augment the comments by describing FOLL_LONGTERM like behavior
- Include the R-b tag from Jason
v1 -> v2:
- Drop gup_flags and improve comments and commit message (David)
- Allocate a page if we cannot find in page cache for the hugetlbfs case as well (David)
- Don't unpin pages if there is a migration related failure (David)
- Drop the unnecessary nr_pages <= 0 check (Jason)
- Have the caller of the API pass in file * instead of fd (Jason)
Vivek Kasireddy (8):
mm/gup: Introduce unpin_folio/unpin_folios helpers mm/gup: Introduce check_and_migrate_movable_folios() mm/gup: Introduce memfd_pin_folios() for pinning memfd folios
udmabuf: Use vmf_insert_pfn and VM_PFNMAP for handling mmap
udmabuf: Add back support for mapping hugetlb pages
udmabuf: Convert udmabuf driver to use folios
udmabuf: Pin the pages using memfd_pin_folios() API selftests/udmabuf: Add tests to verify data after page migration
drivers/dma-buf/udmabuf.c | 231 +++++++++---- include/linux/memfd.h | 5 + include/linux/mm.h | 5 + mm/gup.c | 305 +++++++++++++++--- mm/memfd.c | 35 ++ .../selftests/drivers/dma-buf/udmabuf.c | 151 ++++++++- 6 files changed, 627 insertions(+), 105 deletions(-)
Signature · 1 line
2.43.0
Vivek Kasireddy
maintainerPATCH v13 1/8 mm/gup: Introduce unpin_folio/unpin_folios helpers
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.
We should probably sanity check the folio as part of unpin similar to how it is done in unpin_user_page/unpin_user_pages but we cannot cleanly do that at the moment without also checking the subpage. Therefore, sanity checking needs to be added to these routines once we have a way to determine if any given folio is anon-exclusive (via a per folio AnonExclusive flag).
--- include/linux/mm.h | 2 ++ mm/gup.c | 47 ++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 49 insertions(+)
include/linux/mm.h +2 -0
@@ -1614,11 +1614,13 @@ 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) {
mm/gup.c +47 -0
59 lines not on this page · raw message
Signature · 1 line
2.43.0
Re: [PATCH v13 1/8] mm/gup: Introduce unpin_folio/unpin_folios helpers
Quoted 13 lines · Vivek Kasireddy
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.We should probably sanity check the folio as part of unpin similar to how it is done in unpin_user_page/unpin_user_pages but we cannot cleanly do that at the moment without also checking the subpage. Therefore, sanity checking needs to be added to these routines once we have a way to determine if any given folio is anon-exclusive (via a per folio AnonExclusive flag).
Quoted 8 lines
Cc David Hildenbrand <[email protected]>Cc Matthew Wilcox <[email protected]>Cc Christoph Hellwig <[email protected]>Cc Jason Gunthorpe <[email protected]>Cc Peter Xu <[email protected]>Suggested-by David Hildenbrand <[email protected]>Signed-off-by Vivek Kasireddy <[email protected]>---
Signature · 3 lines
Cheers, David / dhildenb
Vivek Kasireddy
maintainerPATCH v13 2/8 mm/gup: Introduce check_and_migrate_movable_folios()
In reply to Vivek KasireddyThis 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. As a result, check_and_migrate_movable_pages() is now a wrapper around check_and_migrate_movable_folios().
--- mm/gup.c | 122 ++++++++++++++++++++++++++++++++++++------------------- 1 file changed, 81 insertions(+), 41 deletions(-)
mm/gup.c +81 -41
@@ -2416,19 +2416,19 @@ 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, -struct page **pages) +static unsigned long collect_longterm_unpinnable_folios ( +struct list_head *movable_folio_list, +unsigned long nr_folios, +struct folio **folios) {unsigned long i, collected =0 ;struct folio *prev_folio =NULL ;bool drain_allow = true; -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 == prev_folio)continue ;
@@ -2443,7 +2443,7 @@ 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 ; }
@@ -2455,7 +2455,7 @@ 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));
@@ -2465,27 +2465,28 @@ 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 );
@@ -2498,24 +2499,24 @@ 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, .reason =MR_LONGTERM_PIN , }; -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 ;
@@ -2523,19 +2524,48 @@ 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); +unpin_folios (folios, nr_folios); +putback_movable_pages (movable_folio_list);return ret; } +/* +* Check whether all folios are *allowed* to be pinned indefinitely (longterm). +* 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); +if (!collected) +return 0 ; + +return migrate_longterm_unpinnable_folios (&movable_folio_list, + nr_folios, folios); +} +/* * Check whether all pages are *allowed* to be pinned. Rather confusingly, all * pages in the range are required to be pinned via FOLL_PIN, before calling
@@ -2555,16 +2585,20 @@ static int migrate_longterm_unpinnable_pages(static long check_and_migrate_movable_pages (unsigned long nr_pages,struct page **pages) { -unsigned long collected; -LIST_HEAD (movable_page_list); +struct folio **folios; +long i, ret; - collected =collect_longterm_unpinnable_pages (&movable_page_list, - nr_pages, pages); -if (!collected) -return 0 ; + folios =kmalloc_array (nr_pages,sizeof (*folios),GFP_KERNEL ); +if (!folios) +return -ENOMEM ; -return migrate_longterm_unpinnable_pages (&movable_page_list, nr_pages, - pages); +for (i =0 ; i < nr_pages; i++) + folios[i] =page_folio (pages[i]); + + ret =check_and_migrate_movable_folios (nr_pages, folios); + +kfree (folios); +return ret; }#else static long check_and_migrate_movable_pages(unsigned long nr_pages,
@@ -2572,6 +2606,12 @@ 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 */ /*
Signature · 1 line
2.43.0
Re: [PATCH v13 2/8] mm/gup: Introduce check_and_migrate_movable_folios()
Quoted 19 lines · Vivek Kasireddy
This helper is the folio equivalent of
check_and_migrate_movable_pages(). Therefore, all the rules that apply tocheck_and_migrate_movable_pages()also apply to this one as well. Currently, this helper is only used bymemfd_pin_folios().This patch also includes changes to rename and convert the internal functions
collect_longterm_unpinnable_pages()andmigrate_longterm_unpinnable_pages()to work on folios. As a result,check_and_migrate_movable_pages()is now a wrapper aroundcheck_and_migrate_movable_folios().Cc David Hildenbrand <[email protected]>Cc Matthew Wilcox <[email protected]>Cc Christoph Hellwig <[email protected]>Cc Jason Gunthorpe <[email protected]>Cc Peter Xu <[email protected]>Suggested-by David Hildenbrand <[email protected]>Signed-off-by Vivek Kasireddy <[email protected]>---
[...]
Quoted 24 lines
mm/gup.c +24
-0+/* +* Check whether all folios are *allowed* to be pinned indefinitely (longterm). +* 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);
mm/gup.c static int migrate_longterm_unpinnable_pages( · line 2571
Quoted 10 lines
mm/gup.c +7
-0+if (!collected) +return 0 ; + +return migrate_longterm_unpinnable_folios (&movable_folio_list, + nr_folios, folios); +} +/* * Check whether all pages are *allowed* to be pinned. Rather confusingly, all * pages in the range are required to be pinned via FOLL_PIN, before calling
Likely we should just drop that comment and refer to check_and_migrate_movable_folios() instead. No need to duplicate all that.
Quoted 11 lines
mm/gup.c +2
-4@@ -2555,16 +2585,20 @@ static int migrate_longterm_unpinnable_pages(static long check_and_migrate_movable_pages (unsigned long nr_pages,struct page **pages) { -unsigned long collected; -LIST_HEAD (movable_page_list); +struct folio **folios; +long i, ret; - collected =collect_longterm_unpinnable_pages (&movable_page_list, - nr_pages, pages);
mm/gup.c static int migrate_longterm_unpinnable_pages( · line 2596
Quoted 10 lines
mm/gup.c +5
-4-if (!collected) -return 0 ; + folios =kmalloc_array (nr_pages,sizeof (*folios),GFP_KERNEL ); +if (!folios) +return -ENOMEM ; -return migrate_longterm_unpinnable_pages (&movable_page_list, nr_pages, - pages); +for (i =0 ; i < nr_pages; i++) + folios[i] =page_folio (pages[i]);
I wonder if we have to handle pages[i] being NULL. Hopefully not :)
Looks straight forward now:
Signature · 3 lines
Cheers, David / dhildenb
Vivek Kasireddy
maintainerPATCH v13 3/8 mm/gup: Introduce memfd_pin_folios() for pinning memfd folios
In reply to Vivek KasireddyFor 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.
--- include/linux/memfd.h | 5 ++ include/linux/mm.h | 3 + mm/gup.c | 136 ++++++++++++++++++++++++++++++++++++++++++ mm/memfd.c | 35 +++++++++++ 4 files changed, 179 insertions(+)
include/linux/memfd.h +5 -0
@@ -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 */
include/linux/mm.h +3 -0
@@ -2533,6 +2533,9 @@ 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);
mm/gup.c +136 -0
151 lines not on this page · raw message
mm/memfd.c +35 -0
@@ -59,6 +59,41 @@ 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_folios()) 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 , + false); +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
Signature · 1 line
2.43.0
Vivek Kasireddy
maintainerPATCH v13 4/8 udmabuf: Use vmf_insert_pfn and VM_PFNMAP for handling mmap
In reply to Vivek KasireddyAdd 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 *).
--- drivers/dma-buf/udmabuf.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-)
drivers/dma-buf/udmabuf.c +5 -3
@@ -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 ; }
Signature · 1 line
2.43.0
Vivek Kasireddy
maintainerPATCH v13 5/8 udmabuf: Add back support for mapping hugetlb pages
In reply to Vivek KasireddyA 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.
--- drivers/dma-buf/udmabuf.c | 122 +++++++++++++++++++++++++++++++------- 1 file changed, 101 insertions(+), 21 deletions(-)
drivers/dma-buf/udmabuf.c +101 -21
@@ -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;
Signature · 1 line
2.43.0
Vivek Kasireddy
maintainerPATCH v13 6/8 udmabuf: Convert udmabuf driver to use folios
In reply to Vivek KasireddyThis 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.
--- drivers/dma-buf/udmabuf.c | 140 ++++++++++++++++++++++---------------- 1 file changed, 83 insertions(+), 57 deletions(-)
drivers/dma-buf/udmabuf.c +83 -57
@@ -26,7 +26,7 @@ MODULE_PARM_DESC(size_limit_mb, "Max size of a dmabuf, in megabytes. Default isstruct 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; }
Signature · 1 line
2.43.0
Vivek Kasireddy
maintainerPATCH v13 7/8 udmabuf: Pin the pages using memfd_pin_folios() API
In reply to Vivek KasireddyUsing 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.
--- drivers/dma-buf/udmabuf.c | 153 +++++++++++++++++++------------------- 1 file changed, 78 insertions(+), 75 deletions(-)
drivers/dma-buf/udmabuf.c +78 -75
@@ -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);
Signature · 1 line
2.43.0
Vivek Kasireddy
maintainerPATCH v13 8/8 selftests/udmabuf: Add tests to verify data after page migration
In reply to Vivek KasireddySince 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.
--- .../selftests/drivers/dma-buf/udmabuf.c | 151 +++++++++++++++++- 1 file changed, 147 insertions(+), 4 deletions(-)
tools/testing/selftests/drivers/dma-buf/udmabuf.c +147 -4
@@ -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);
Signature · 1 line
2.43.0
Shuah Khan
maintainerRe: [PATCH v13 8/8] selftests/udmabuf: Add tests to verify data after page migration
Quoted 6 lines · Vivek Kasireddy
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.
Quoted 6 lines
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.
Add Suggested-by for Mike Kravetz
Quoted 47 lines
Cc Shuah Khan <[email protected]>Cc David Hildenbrand <[email protected]>Cc Daniel Vetter <[email protected]>Cc Mike Kravetz <[email protected]>Cc Hugh Dickins <[email protected]>Cc Peter Xu <[email protected]>Cc Jason Gunthorpe <[email protected]>Cc Gerd Hoffmann <[email protected]>Cc Dongwon Kim <[email protected]>Cc Junxiao Chang <[email protected]>Signed-off-by Vivek Kasireddy <[email protected]>--- .../selftests/drivers/dma-buf/udmabuf.c | 151 +++++++++++++++++- 1 file changed, 147 insertions(+), 4 deletions(-)tools/testing/selftests/drivers/dma-buf/udmabuf.c +13
-1@@ -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 ;
tools/testing/selftests/drivers/dma-buf/udmabuf.c line 43
Quoted 10 lines
tools/testing/selftests/drivers/dma-buf/udmabuf.c +10
-0+ + 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 );
Use the kselftest skip code here. Also use kselftest_* functions to print results and exit messages for KTAP format.
tools/testing/selftests/drivers/dma-buf/udmabuf.c line 44
Quoted 1 line
tools/testing/selftests/drivers/dma-buf/udmabuf.c +1
-0+exit (77 );
This should be KSFT_SKIP
tools/testing/selftests/drivers/dma-buf/udmabuf.c line 50
Quoted 6 lines
tools/testing/selftests/drivers/dma-buf/udmabuf.c +6
-0+ } + + ret =ftruncate (memfd, size); +if (ret ==-1 ) { +printf ("%s: [FAIL,memfd-truncate]\n" ,TEST_PREFIX ); +exit (1 );
Use KSFT_FAIL
Quoted 20 lines
tools/testing/selftests/drivers/dma-buf/udmabuf.c +20
-0+ } + +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 );
tools/testing/selftests/drivers/dma-buf/udmabuf.c line 80
Quoted 10 lines
tools/testing/selftests/drivers/dma-buf/udmabuf.c +10
-0+ 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 );
Same as before.
Quoted 104 lines
tools/testing/selftests/drivers/dma-buf/udmabuf.c +80
-3+ } + +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);
tools/testing/selftests/drivers/dma-buf/udmabuf.c int main(int argc, char *argv[]) · line 246
Quoted 10 lines
tools/testing/selftests/drivers/dma-buf/udmabuf.c +7
-0+ 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);
CC linux0kselftest list when you send v2.
thanks,
-- Shuah