diff --git a/arch/alpha/include/uapi/asm/mman.h b/arch/alpha/include/uapi/asm/mman.h index 4aa996423b0d1666f0b9d3db6d9d457d00dacef5..763929e814e9a3faa76ee2a715494867210ca14e 100644 --- a/arch/alpha/include/uapi/asm/mman.h +++ b/arch/alpha/include/uapi/asm/mman.h @@ -76,6 +76,8 @@ #define MADV_DONTNEED_LOCKED 24 /* like DONTNEED, but drop locked pages too */ +#define MADV_COLLAPSE 25 /* Synchronous hugepage collapse */ + /* compatibility flags */ #define MAP_FILE 0 diff --git a/arch/mips/include/uapi/asm/mman.h b/arch/mips/include/uapi/asm/mman.h index 1be428663c102701e26a1516bb6ca8eb0a083a75..c6e1fc77c9968874feefc79b7c94a165d0ad89d2 100644 --- a/arch/mips/include/uapi/asm/mman.h +++ b/arch/mips/include/uapi/asm/mman.h @@ -103,6 +103,8 @@ #define MADV_DONTNEED_LOCKED 24 /* like DONTNEED, but drop locked pages too */ +#define MADV_COLLAPSE 25 /* Synchronous hugepage collapse */ + /* compatibility flags */ #define MAP_FILE 0 diff --git a/arch/parisc/include/uapi/asm/mman.h b/arch/parisc/include/uapi/asm/mman.h index a7ea3204a5faa0ed79e3a473ea915ec92aead4c1..22133a6a506efba842e7286deed19c4fe9c1e6ce 100644 --- a/arch/parisc/include/uapi/asm/mman.h +++ b/arch/parisc/include/uapi/asm/mman.h @@ -70,6 +70,8 @@ #define MADV_WIPEONFORK 71 /* Zero memory on fork, child only */ #define MADV_KEEPONFORK 72 /* Undo MADV_WIPEONFORK */ +#define MADV_COLLAPSE 73 /* Synchronous hugepage collapse */ + #define MADV_HWPOISON 100 /* poison a page for testing */ #define MADV_SOFT_OFFLINE 101 /* soft offline page for testing */ diff --git a/arch/xtensa/include/uapi/asm/mman.h b/arch/xtensa/include/uapi/asm/mman.h index 7966a58af472a18b726a1ecb2698ac6de17989d1..1ff0c858544fa81e7164cf602b3c2ef4f9f17df6 100644 --- a/arch/xtensa/include/uapi/asm/mman.h +++ b/arch/xtensa/include/uapi/asm/mman.h @@ -111,6 +111,8 @@ #define MADV_DONTNEED_LOCKED 24 /* like DONTNEED, but drop locked pages too */ +#define MADV_COLLAPSE 25 /* Synchronous hugepage collapse */ + /* compatibility flags */ #define MAP_FILE 0 diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index b0e80cc72b0cd3674e0b934b04b218dd167ec636..38265f9f782e9aede7b2b85c944c02fafad53b88 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -218,6 +218,9 @@ void __split_huge_pud(struct vm_area_struct *vma, pud_t *pud, int hugepage_madvise(struct vm_area_struct *vma, unsigned long *vm_flags, int advice); +int madvise_collapse(struct vm_area_struct *vma, + struct vm_area_struct **prev, + unsigned long start, unsigned long end); void vma_adjust_trans_huge(struct vm_area_struct *vma, unsigned long start, unsigned long end, long adjust_next); spinlock_t *__pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma); @@ -361,9 +364,16 @@ static inline void split_huge_pmd_address(struct vm_area_struct *vma, static inline int hugepage_madvise(struct vm_area_struct *vma, unsigned long *vm_flags, int advice) { - BUG(); - return 0; + return -EINVAL; } + +static inline int madvise_collapse(struct vm_area_struct *vma, + struct vm_area_struct **prev, + unsigned long start, unsigned long end) +{ + return -EINVAL; +} + static inline void vma_adjust_trans_huge(struct vm_area_struct *vma, unsigned long start, unsigned long end, diff --git a/include/uapi/asm-generic/mman-common.h b/include/uapi/asm-generic/mman-common.h index 6c1aa92a92e4411946335cbb9724b75d8efa987a..6ce1f1ceb432c64599f706b86e74a12581c2a54e 100644 --- a/include/uapi/asm-generic/mman-common.h +++ b/include/uapi/asm-generic/mman-common.h @@ -77,6 +77,8 @@ #define MADV_DONTNEED_LOCKED 24 /* like DONTNEED, but drop locked pages too */ +#define MADV_COLLAPSE 25 /* Synchronous hugepage collapse */ + /* compatibility flags */ #define MAP_FILE 0 diff --git a/mm/khugepaged.c b/mm/khugepaged.c index a6eb81722871c8dfc7678ccb253fc92d0671aadc..92bdd2b5aacf0a4b9cf4b3abf9abd88c42c1f156 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -982,7 +982,8 @@ static int alloc_charge_hpage(struct page **hpage, struct mm_struct *mm, struct collapse_control *cc) { /* Only allocate from the target node */ - gfp_t gfp = alloc_hugepage_khugepaged_gfpmask() | __GFP_THISNODE; + gfp_t gfp = (cc->is_khugepaged ? alloc_hugepage_khugepaged_gfpmask() : + GFP_TRANSHUGE) | __GFP_THISNODE; int node = khugepaged_find_target_node(cc); if (!khugepaged_alloc_page(hpage, gfp, node)) @@ -2362,3 +2363,119 @@ void khugepaged_min_free_kbytes_update(void) set_recommended_min_free_kbytes(); mutex_unlock(&khugepaged_mutex); } + +static int madvise_collapse_errno(enum scan_result r) +{ + /* + * MADV_COLLAPSE breaks from existing madvise(2) conventions to provide + * actionable feedback to caller, so they may take an appropriate + * fallback measure depending on the nature of the failure. + */ + switch (r) { + case SCAN_ALLOC_HUGE_PAGE_FAIL: + return -ENOMEM; + case SCAN_CGROUP_CHARGE_FAIL: + return -EBUSY; + /* Resource temporary unavailable - trying again might succeed */ + case SCAN_PAGE_LOCK: + case SCAN_PAGE_LRU: + return -EAGAIN; + /* + * Other: Trying again likely not to succeed / error intrinsic to + * specified memory range. khugepaged likely won't be able to collapse + * either. + */ + default: + return -EINVAL; + } +} + +int madvise_collapse(struct vm_area_struct *vma, struct vm_area_struct **prev, + unsigned long start, unsigned long end) +{ + struct collapse_control *cc; + struct mm_struct *mm = vma->vm_mm; + unsigned long hstart, hend, addr; + int thps = 0, last_fail = SCAN_FAIL; + bool mmap_locked = true; + + BUG_ON(vma->vm_start > start); + BUG_ON(vma->vm_end < end); + + *prev = vma; + + /* TODO: Support file/shmem */ + if (!vma->anon_vma || !vma_is_anonymous(vma)) + return -EINVAL; + + if (!hugepage_vma_check(vma, vma->vm_flags, false, false, false)) + return -EINVAL; + + cc = kmalloc(sizeof(*cc), GFP_KERNEL); + if (!cc) + return -ENOMEM; + cc->is_khugepaged = false; + cc->last_target_node = NUMA_NO_NODE; + + mmgrab(mm); + lru_add_drain_all(); + + hstart = (start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK; + hend = end & HPAGE_PMD_MASK; + + for (addr = hstart; addr < hend; addr += HPAGE_PMD_SIZE) { + int result = SCAN_FAIL; + + if (!mmap_locked) { + cond_resched(); + mmap_read_lock(mm); + mmap_locked = true; + result = hugepage_vma_revalidate(mm, addr, &vma, cc); + if (result != SCAN_SUCCEED) { + last_fail = result; + goto out_nolock; + } + } + mmap_assert_locked(mm); + memset(cc->node_load, 0, sizeof(cc->node_load)); + result = khugepaged_scan_pmd(mm, vma, addr, &mmap_locked, cc); + if (!mmap_locked) + *prev = NULL; /* Tell caller we dropped mmap_lock */ + + switch (result) { + case SCAN_SUCCEED: + case SCAN_PMD_MAPPED: + ++thps; + break; + /* Whitelisted set of results where continuing OK */ + case SCAN_PMD_NULL: + case SCAN_PTE_NON_PRESENT: + case SCAN_PTE_UFFD_WP: + case SCAN_PAGE_RO: + case SCAN_LACK_REFERENCED_PAGE: + case SCAN_PAGE_NULL: + case SCAN_PAGE_COUNT: + case SCAN_PAGE_LOCK: + case SCAN_PAGE_COMPOUND: + case SCAN_PAGE_LRU: + last_fail = result; + break; + default: + last_fail = result; + /* Other error, exit */ + goto out_maybelock; + } + } + +out_maybelock: + /* Caller expects us to hold mmap_lock on return */ + if (!mmap_locked) + mmap_read_lock(mm); +out_nolock: + mmap_assert_locked(mm); + mmdrop(mm); + kfree(cc); + + return thps == ((hend - hstart) >> HPAGE_PMD_SHIFT) ? 0 + : madvise_collapse_errno(last_fail); +} diff --git a/mm/madvise.c b/mm/madvise.c index 5f0f0948a50e4399a3115f6cd12ae8deae25f1bd..bf50a2d4ee4e26d2ced4f963901da0aca1732ca4 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -59,6 +59,7 @@ static int madvise_need_mmap_write(int behavior) case MADV_FREE: case MADV_POPULATE_READ: case MADV_POPULATE_WRITE: + case MADV_COLLAPSE: return 0; default: /* be safe, default to 1. list exceptions explicitly */ @@ -1057,6 +1058,8 @@ static int madvise_vma_behavior(struct vm_area_struct *vma, if (error) goto out; break; + case MADV_COLLAPSE: + return madvise_collapse(vma, prev, start, end); } anon_name = anon_vma_name(vma); @@ -1150,6 +1153,7 @@ madvise_behavior_valid(int behavior) #ifdef CONFIG_TRANSPARENT_HUGEPAGE case MADV_HUGEPAGE: case MADV_NOHUGEPAGE: + case MADV_COLLAPSE: #endif case MADV_DONTDUMP: case MADV_DODUMP: @@ -1339,6 +1343,7 @@ int madvise_set_anon_name(struct mm_struct *mm, unsigned long start, * MADV_NOHUGEPAGE - mark the given range as not worth being backed by * transparent huge pages so the existing pages will not be * coalesced into THP and new pages will not be allocated as THP. + * MADV_COLLAPSE - synchronously coalesce pages into new THP. * MADV_DONTDUMP - the application wants to prevent pages in the given range * from being included in its core dump. * MADV_DODUMP - cancel MADV_DONTDUMP: no longer exclude from core dump. diff --git a/tools/include/uapi/asm-generic/mman-common.h b/tools/include/uapi/asm-generic/mman-common.h index 6c1aa92a92e4411946335cbb9724b75d8efa987a..6ce1f1ceb432c64599f706b86e74a12581c2a54e 100644 --- a/tools/include/uapi/asm-generic/mman-common.h +++ b/tools/include/uapi/asm-generic/mman-common.h @@ -77,6 +77,8 @@ #define MADV_DONTNEED_LOCKED 24 /* like DONTNEED, but drop locked pages too */ +#define MADV_COLLAPSE 25 /* Synchronous hugepage collapse */ + /* compatibility flags */ #define MAP_FILE 0