From 590d356aa433074ece2b0d02faa5f959b26d54d6 Mon Sep 17 00:00:00 2001 From: Lorenzo Stoakes Date: Thu, 22 Jan 2026 16:06:17 +0000 Subject: mm: update shmem_[kernel]_file_*() functions to use vma_flags_t In order to be able to use only vma_flags_t in vm_area_desc we must adjust shmem file setup functions to operate in terms of vma_flags_t rather than vm_flags_t. This patch makes this change and updates all callers to use the new functions. No functional changes intended. [akpm@linux-foundation.org: comment fixes, per Baolin] Link: https://lkml.kernel.org/r/736febd280eb484d79cef5cf55b8a6f79ad832d2.1769097829.git.lorenzo.stoakes@oracle.com Signed-off-by: Lorenzo Stoakes Reviewed-by: Baolin Wang Reviewed-by: Jarkko Sakkinen Reviewed-by: Liam R. Howlett Cc: Barry Song Cc: David Hildenbrand Cc: Dev Jain Cc: Jason Gunthorpe Cc: Suren Baghdasaryan Cc: Vlastimil Babka Cc: Zi Yan Cc: "Darrick J. Wong" Cc: Damien Le Moal Cc: Yury Norov Cc: Chris Mason Cc: Pedro Falcato Signed-off-by: Andrew Morton --- arch/x86/kernel/cpu/sgx/ioctl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/kernel/cpu/sgx/ioctl.c b/arch/x86/kernel/cpu/sgx/ioctl.c index 9322a9287dc7..0bc36957979d 100644 --- a/arch/x86/kernel/cpu/sgx/ioctl.c +++ b/arch/x86/kernel/cpu/sgx/ioctl.c @@ -83,7 +83,7 @@ static int sgx_encl_create(struct sgx_encl *encl, struct sgx_secs *secs) encl_size = secs->size + PAGE_SIZE; backing = shmem_file_setup("SGX backing", encl_size + (encl_size >> 5), - VM_NORESERVE); + mk_vma_flags(VMA_NORESERVE_BIT)); if (IS_ERR(backing)) { ret = PTR_ERR(backing); goto err_out_shrink; -- cgit v1.2.3 From 67d59bddfc26a2f7d5740d4d7ce9ff45274322d5 Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Mon, 9 Feb 2026 22:07:25 +0800 Subject: arm64: mm: factor out the address and ptep alignment into a new helper Factor out the contpte block's address and ptep alignment into a new helper, and will be reused in the following patch. No functional changes. Link: https://lkml.kernel.org/r/8076d12cb244b2d9e91119b44dc6d5e4ad9c00af.1770645603.git.baolin.wang@linux.alibaba.com Signed-off-by: Baolin Wang Reviewed-by: David Hildenbrand (Arm) Reviewed-by: Ryan Roberts Cc: Barry Song Cc: Catalin Marinas Cc: Harry Yoo Cc: Jann Horn Cc: Liam Howlett Cc: Lorenzo Stoakes Cc: Matthew Wilcox (Oracle) Cc: Michal Hocko Cc: Mike Rapoport Cc: Rik van Riel Cc: Suren Baghdasaryan Cc: Vlastimil Babka Cc: Will Deacon Signed-off-by: Andrew Morton --- arch/arm64/mm/contpte.c | 29 +++++++++++++++++++++-------- 1 file changed, 21 insertions(+), 8 deletions(-) (limited to 'arch') diff --git a/arch/arm64/mm/contpte.c b/arch/arm64/mm/contpte.c index 589bcf878938..e4ddeb46f25d 100644 --- a/arch/arm64/mm/contpte.c +++ b/arch/arm64/mm/contpte.c @@ -26,6 +26,26 @@ static inline pte_t *contpte_align_down(pte_t *ptep) return PTR_ALIGN_DOWN(ptep, sizeof(*ptep) * CONT_PTES); } +static inline pte_t *contpte_align_addr_ptep(unsigned long *start, + unsigned long *end, pte_t *ptep, + unsigned int nr) +{ + /* + * Note: caller must ensure these nr PTEs are consecutive (present) + * PTEs that map consecutive pages of the same large folio within a + * single VMA and a single page table. + */ + if (pte_cont(__ptep_get(ptep + nr - 1))) + *end = ALIGN(*end, CONT_PTE_SIZE); + + if (pte_cont(__ptep_get(ptep))) { + *start = ALIGN_DOWN(*start, CONT_PTE_SIZE); + ptep = contpte_align_down(ptep); + } + + return ptep; +} + static void contpte_try_unfold_partial(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned int nr) { @@ -569,14 +589,7 @@ void contpte_clear_young_dirty_ptes(struct vm_area_struct *vma, unsigned long start = addr; unsigned long end = start + nr * PAGE_SIZE; - if (pte_cont(__ptep_get(ptep + nr - 1))) - end = ALIGN(end, CONT_PTE_SIZE); - - if (pte_cont(__ptep_get(ptep))) { - start = ALIGN_DOWN(start, CONT_PTE_SIZE); - ptep = contpte_align_down(ptep); - } - + ptep = contpte_align_addr_ptep(&start, &end, ptep, nr); __clear_young_dirty_ptes(vma, start, ptep, (end - start) / PAGE_SIZE, flags); } EXPORT_SYMBOL_GPL(contpte_clear_young_dirty_ptes); -- cgit v1.2.3 From 6f0e1142173a54b8a18c59fc3cbae3b31ee423d9 Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Mon, 9 Feb 2026 22:07:26 +0800 Subject: arm64: mm: support batch clearing of the young flag for large folios Currently, contpte_ptep_test_and_clear_young() and contpte_ptep_clear_flush_young() only clear the young flag and flush TLBs for PTEs within the contiguous range. To support batch PTE operations for other sized large folios in the following patches, adding a new parameter to specify the number of PTEs that map consecutive pages of the same large folio in a single VMA and a single page table. While we are at it, rename the functions to maintain consistency with other contpte_*() functions. Link: https://lkml.kernel.org/r/5644250dcc0417278c266ad37118d27f541fd052.1770645603.git.baolin.wang@linux.alibaba.com Signed-off-by: Baolin Wang Reviewed-by: Ryan Roberts Reviewed-by: David Hildenbrand (Arm) Cc: Barry Song Cc: Catalin Marinas Cc: Harry Yoo Cc: Jann Horn Cc: Liam Howlett Cc: Lorenzo Stoakes Cc: Matthew Wilcox (Oracle) Cc: Michal Hocko Cc: Mike Rapoport Cc: Rik van Riel Cc: Suren Baghdasaryan Cc: Vlastimil Babka Cc: Will Deacon Signed-off-by: Andrew Morton --- arch/arm64/include/asm/pgtable.h | 12 ++++++------ arch/arm64/mm/contpte.c | 33 +++++++++++++++++++-------------- 2 files changed, 25 insertions(+), 20 deletions(-) (limited to 'arch') diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index d94445b4f3df..3dabf5ea17fa 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -1648,10 +1648,10 @@ extern void contpte_clear_full_ptes(struct mm_struct *mm, unsigned long addr, extern pte_t contpte_get_and_clear_full_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned int nr, int full); -extern int contpte_ptep_test_and_clear_young(struct vm_area_struct *vma, - unsigned long addr, pte_t *ptep); -extern int contpte_ptep_clear_flush_young(struct vm_area_struct *vma, - unsigned long addr, pte_t *ptep); +int contpte_test_and_clear_young_ptes(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, unsigned int nr); +int contpte_clear_flush_young_ptes(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, unsigned int nr); extern void contpte_wrprotect_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned int nr); extern int contpte_ptep_set_access_flags(struct vm_area_struct *vma, @@ -1823,7 +1823,7 @@ static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, if (likely(!pte_valid_cont(orig_pte))) return __ptep_test_and_clear_young(vma, addr, ptep); - return contpte_ptep_test_and_clear_young(vma, addr, ptep); + return contpte_test_and_clear_young_ptes(vma, addr, ptep, 1); } #define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH @@ -1835,7 +1835,7 @@ static inline int ptep_clear_flush_young(struct vm_area_struct *vma, if (likely(!pte_valid_cont(orig_pte))) return __ptep_clear_flush_young(vma, addr, ptep); - return contpte_ptep_clear_flush_young(vma, addr, ptep); + return contpte_clear_flush_young_ptes(vma, addr, ptep, 1); } #define wrprotect_ptes wrprotect_ptes diff --git a/arch/arm64/mm/contpte.c b/arch/arm64/mm/contpte.c index e4ddeb46f25d..b929a455103f 100644 --- a/arch/arm64/mm/contpte.c +++ b/arch/arm64/mm/contpte.c @@ -508,8 +508,9 @@ pte_t contpte_get_and_clear_full_ptes(struct mm_struct *mm, } EXPORT_SYMBOL_GPL(contpte_get_and_clear_full_ptes); -int contpte_ptep_test_and_clear_young(struct vm_area_struct *vma, - unsigned long addr, pte_t *ptep) +int contpte_test_and_clear_young_ptes(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + unsigned int nr) { /* * ptep_clear_flush_young() technically requires us to clear the access @@ -518,41 +519,45 @@ int contpte_ptep_test_and_clear_young(struct vm_area_struct *vma, * contig range when the range is covered by a single folio, we can get * away with clearing young for the whole contig range here, so we avoid * having to unfold. + * + * The 'nr' means consecutive (present) PTEs that map consecutive pages + * of the same large folio in a single VMA and a single page table. */ + unsigned long end = addr + nr * PAGE_SIZE; int young = 0; - int i; - ptep = contpte_align_down(ptep); - addr = ALIGN_DOWN(addr, CONT_PTE_SIZE); - - for (i = 0; i < CONT_PTES; i++, ptep++, addr += PAGE_SIZE) + ptep = contpte_align_addr_ptep(&addr, &end, ptep, nr); + for (; addr != end; ptep++, addr += PAGE_SIZE) young |= __ptep_test_and_clear_young(vma, addr, ptep); return young; } -EXPORT_SYMBOL_GPL(contpte_ptep_test_and_clear_young); +EXPORT_SYMBOL_GPL(contpte_test_and_clear_young_ptes); -int contpte_ptep_clear_flush_young(struct vm_area_struct *vma, - unsigned long addr, pte_t *ptep) +int contpte_clear_flush_young_ptes(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + unsigned int nr) { int young; - young = contpte_ptep_test_and_clear_young(vma, addr, ptep); + young = contpte_test_and_clear_young_ptes(vma, addr, ptep, nr); if (young) { + unsigned long end = addr + nr * PAGE_SIZE; + + contpte_align_addr_ptep(&addr, &end, ptep, nr); /* * See comment in __ptep_clear_flush_young(); same rationale for * eliding the trailing DSB applies here. */ - addr = ALIGN_DOWN(addr, CONT_PTE_SIZE); - __flush_tlb_range_nosync(vma->vm_mm, addr, addr + CONT_PTE_SIZE, + __flush_tlb_range_nosync(vma->vm_mm, addr, end, PAGE_SIZE, true, 3); } return young; } -EXPORT_SYMBOL_GPL(contpte_ptep_clear_flush_young); +EXPORT_SYMBOL_GPL(contpte_clear_flush_young_ptes); void contpte_wrprotect_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned int nr) -- cgit v1.2.3 From 07f440c23a197616f7b7607b98b9427da23f9f6f Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Mon, 9 Feb 2026 22:07:27 +0800 Subject: arm64: mm: implement the architecture-specific clear_flush_young_ptes() Implement the Arm64 architecture-specific clear_flush_young_ptes() to enable batched checking of young flags and TLB flushing, improving performance during large folio reclamation. Performance testing: Allocate 10G clean file-backed folios by mmap() in a memory cgroup, and try to reclaim 8G file-backed folios via the memory.reclaim interface. I can observe 33% performance improvement on my Arm64 32-core server (and 10%+ improvement on my X86 machine). Meanwhile, the hotspot folio_check_references() dropped from approximately 35% to around 5%. W/o patchset: real 0m1.518s user 0m0.000s sys 0m1.518s W/ patchset: real 0m1.018s user 0m0.000s sys 0m1.018s Link: https://lkml.kernel.org/r/ce749fbae3e900e733fa104a16fcb3ca9fe4f9bd.1770645603.git.baolin.wang@linux.alibaba.com Signed-off-by: Baolin Wang Reviewed-by: Ryan Roberts Reviewed-by: David Hildenbrand (Arm) Cc: Barry Song Cc: Catalin Marinas Cc: Harry Yoo Cc: Jann Horn Cc: Liam Howlett Cc: Lorenzo Stoakes Cc: Matthew Wilcox (Oracle) Cc: Michal Hocko Cc: Mike Rapoport Cc: Rik van Riel Cc: Suren Baghdasaryan Cc: Vlastimil Babka Cc: Will Deacon Signed-off-by: Andrew Morton --- arch/arm64/include/asm/pgtable.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'arch') diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 3dabf5ea17fa..a17eb8a76788 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -1838,6 +1838,17 @@ static inline int ptep_clear_flush_young(struct vm_area_struct *vma, return contpte_clear_flush_young_ptes(vma, addr, ptep, 1); } +#define clear_flush_young_ptes clear_flush_young_ptes +static inline int clear_flush_young_ptes(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + unsigned int nr) +{ + if (likely(nr == 1 && !pte_cont(__ptep_get(ptep)))) + return __ptep_clear_flush_young(vma, addr, ptep); + + return contpte_clear_flush_young_ptes(vma, addr, ptep, nr); +} + #define wrprotect_ptes wrprotect_ptes static __always_inline void wrprotect_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned int nr) -- cgit v1.2.3