From 552546366a30d88bd1d6f5efe848b2ab50fd57e5 Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Sat, 30 Nov 2019 17:56:30 -0800 Subject: hugetlbfs: hugetlb_fault_mutex_hash() cleanup A new clang diagnostic (-Wsizeof-array-div) warns about the calculation to determine the number of u32's in an array of unsigned longs. Suppress warning by adding parentheses. While looking at the above issue, noticed that the 'address' parameter to hugetlb_fault_mutex_hash is no longer used. So, remove it from the definition and all callers. No functional change. Link: http://lkml.kernel.org/r/20190919011847.18400-1-mike.kravetz@oracle.com Signed-off-by: Mike Kravetz Reported-by: Nathan Chancellor Reviewed-by: Nathan Chancellor Reviewed-by: Davidlohr Bueso Reviewed-by: Andrew Morton Cc: Nick Desaulniers Cc: Ilie Halip Cc: David Bolvansky Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/userfaultfd.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'mm/userfaultfd.c') diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index c7ae74ce5ff3..640ff2bd9a69 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -269,7 +269,7 @@ retry: */ idx = linear_page_index(dst_vma, dst_addr); mapping = dst_vma->vm_file->f_mapping; - hash = hugetlb_fault_mutex_hash(h, mapping, idx, dst_addr); + hash = hugetlb_fault_mutex_hash(h, mapping, idx); mutex_lock(&hugetlb_fault_mutex_table[hash]); err = -ENOMEM; -- cgit v1.2.3 From 188b04a7d93860fd100b2671600b8ad81fb0a842 Mon Sep 17 00:00:00 2001 From: Wei Yang Date: Sat, 30 Nov 2019 17:57:02 -0800 Subject: hugetlb: remove unused hstate in hugetlb_fault_mutex_hash() The first parameter hstate in function hugetlb_fault_mutex_hash() is not used anymore. This patch removes it. [akpm@linux-foundation.org: various build fixes] [cai@lca.pw: fix a GCC compilation warning] Link: http://lkml.kernel.org/r/1570544108-32331-1-git-send-email-cai@lca.pw Link: http://lkml.kernel.org/r/20191005003302.785-1-richardw.yang@linux.intel.com Signed-off-by: Wei Yang Signed-off-by: Qian Cai Suggested-by: Andrew Morton Reviewed-by: Andrew Morton Cc: Mike Kravetz Cc: Hugh Dickins Cc: Andrea Arcangeli Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/hugetlbfs/inode.c | 4 ++-- include/linux/hugetlb.h | 3 +-- mm/hugetlb.c | 10 ++++------ mm/userfaultfd.c | 5 +---- 4 files changed, 8 insertions(+), 14 deletions(-) (limited to 'mm/userfaultfd.c') diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index c978061c3893..d5c2a3158610 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -440,7 +440,7 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart, u32 hash; index = page->index; - hash = hugetlb_fault_mutex_hash(h, mapping, index); + hash = hugetlb_fault_mutex_hash(mapping, index); mutex_lock(&hugetlb_fault_mutex_table[hash]); /* @@ -644,7 +644,7 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset, addr = index * hpage_size; /* mutex taken here, fault path and hole punch */ - hash = hugetlb_fault_mutex_hash(h, mapping, index); + hash = hugetlb_fault_mutex_hash(mapping, index); mutex_lock(&hugetlb_fault_mutex_table[hash]); /* See if already present in mapping to avoid alloc/free */ diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 159d2012cdb1..31d4920994b9 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -105,8 +105,7 @@ void move_hugetlb_state(struct page *oldpage, struct page *newpage, int reason); void free_huge_page(struct page *page); void hugetlb_fix_reserve_counts(struct inode *inode); extern struct mutex *hugetlb_fault_mutex_table; -u32 hugetlb_fault_mutex_hash(struct hstate *h, struct address_space *mapping, - pgoff_t idx); +u32 hugetlb_fault_mutex_hash(struct address_space *mapping, pgoff_t idx); pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index a8e43aa9c670..8624b7758abb 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -3796,7 +3796,7 @@ retry: * handling userfault. Reacquire after handling * fault to make calling code simpler. */ - hash = hugetlb_fault_mutex_hash(h, mapping, idx); + hash = hugetlb_fault_mutex_hash(mapping, idx); mutex_unlock(&hugetlb_fault_mutex_table[hash]); ret = handle_userfault(&vmf, VM_UFFD_MISSING); mutex_lock(&hugetlb_fault_mutex_table[hash]); @@ -3923,8 +3923,7 @@ backout_unlocked: } #ifdef CONFIG_SMP -u32 hugetlb_fault_mutex_hash(struct hstate *h, struct address_space *mapping, - pgoff_t idx) +u32 hugetlb_fault_mutex_hash(struct address_space *mapping, pgoff_t idx) { unsigned long key[2]; u32 hash; @@ -3941,8 +3940,7 @@ u32 hugetlb_fault_mutex_hash(struct hstate *h, struct address_space *mapping, * For uniprocesor systems we always use a single mutex, so just * return 0 and avoid the hashing overhead. */ -u32 hugetlb_fault_mutex_hash(struct hstate *h, struct address_space *mapping, - pgoff_t idx) +u32 hugetlb_fault_mutex_hash(struct address_space *mapping, pgoff_t idx) { return 0; } @@ -3986,7 +3984,7 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, * get spurious allocation failures if two CPUs race to instantiate * the same page in the page cache. */ - hash = hugetlb_fault_mutex_hash(h, mapping, idx); + hash = hugetlb_fault_mutex_hash(mapping, idx); mutex_lock(&hugetlb_fault_mutex_table[hash]); entry = huge_ptep_get(ptep); diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 640ff2bd9a69..6d152741bb26 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -184,7 +184,6 @@ static __always_inline ssize_t __mcopy_atomic_hugetlb(struct mm_struct *dst_mm, unsigned long src_addr, dst_addr; long copied; struct page *page; - struct hstate *h; unsigned long vma_hpagesize; pgoff_t idx; u32 hash; @@ -256,8 +255,6 @@ retry: goto out_unlock; } - h = hstate_vma(dst_vma); - while (src_addr < src_start + len) { pte_t dst_pteval; @@ -269,7 +266,7 @@ retry: */ idx = linear_page_index(dst_vma, dst_addr); mapping = dst_vma->vm_file->f_mapping; - hash = hugetlb_fault_mutex_hash(h, mapping, idx); + hash = hugetlb_fault_mutex_hash(mapping, idx); mutex_lock(&hugetlb_fault_mutex_table[hash]); err = -ENOMEM; -- cgit v1.2.3 From 4fb07ee6510280219403592e0a70c3b248b588c8 Mon Sep 17 00:00:00 2001 From: Wei Yang Date: Sat, 30 Nov 2019 17:57:49 -0800 Subject: userfaultfd: use vma_pagesize for all huge page size calculation In __mcopy_atomic_hugetlb() we use two variables to deal with huge page size: vma_hpagesize and huge_page_size. Since they are the same, it is not necessary to use two different mechanism. This patch makes it consistent by all using vma_hpagesize. Link: http://lkml.kernel.org/r/20190927070032.2129-1-richardw.yang@linux.intel.com Signed-off-by: Wei Yang Reviewed-by: Mike Kravetz Cc: Andrea Arcangeli Cc: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/userfaultfd.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'mm/userfaultfd.c') diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 6d152741bb26..c545ee84331d 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -259,7 +259,7 @@ retry: pte_t dst_pteval; BUG_ON(dst_addr >= dst_start + len); - VM_BUG_ON(dst_addr & ~huge_page_mask(h)); + VM_BUG_ON(dst_addr & (vma_hpagesize - 1)); /* * Serialize via hugetlb_fault_mutex @@ -270,7 +270,7 @@ retry: mutex_lock(&hugetlb_fault_mutex_table[hash]); err = -ENOMEM; - dst_pte = huge_pte_alloc(dst_mm, dst_addr, huge_page_size(h)); + dst_pte = huge_pte_alloc(dst_mm, dst_addr, vma_hpagesize); if (!dst_pte) { mutex_unlock(&hugetlb_fault_mutex_table[hash]); goto out_unlock; @@ -297,7 +297,8 @@ retry: err = copy_huge_page_from_user(page, (const void __user *)src_addr, - pages_per_huge_page(h), true); + vma_hpagesize / PAGE_SIZE, + true); if (unlikely(err)) { err = -EFAULT; goto out; -- cgit v1.2.3 From 53eaa14b62d27f3011feb97e12a80bf61a4b29ab Mon Sep 17 00:00:00 2001 From: Wei Yang Date: Sat, 30 Nov 2019 17:57:52 -0800 Subject: userfaultfd: remove unnecessary WARN_ON() in __mcopy_atomic_hugetlb() These warning here is to make sure address(dst_addr) and length(len - copied) are huge page size aligned. While this is ensured by: dst_start and len is huge page size aligned dst_addr equals to dst_start and increase huge page size each time copied increase huge page size each time This means these warnings will never be triggered. Link: http://lkml.kernel.org/r/20190927070032.2129-2-richardw.yang@linux.intel.com Signed-off-by: Wei Yang Reviewed-by: Mike Kravetz Cc: Andrea Arcangeli Cc: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/userfaultfd.c | 5 ----- 1 file changed, 5 deletions(-) (limited to 'mm/userfaultfd.c') diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index c545ee84331d..07f44555fd03 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -242,10 +242,6 @@ retry: vm_shared = dst_vma->vm_flags & VM_SHARED; } - if (WARN_ON(dst_addr & (vma_hpagesize - 1) || - (len - copied) & (vma_hpagesize - 1))) - goto out_unlock; - /* * If not shared, ensure the dst_vma has a anon_vma. */ @@ -259,7 +255,6 @@ retry: pte_t dst_pteval; BUG_ON(dst_addr >= dst_start + len); - VM_BUG_ON(dst_addr & (vma_hpagesize - 1)); /* * Serialize via hugetlb_fault_mutex -- cgit v1.2.3 From 643aa36eadebdcdcaeecf538f0549a619ad78ea0 Mon Sep 17 00:00:00 2001 From: Wei Yang Date: Sat, 30 Nov 2019 17:57:55 -0800 Subject: userfaultfd: wrap the common dst_vma check into an inlined function When doing UFFDIO_COPY, it is necessary to find the correct destination vma and make sure fault range is in it. Since there are two places need to do the same task, just wrap those common check into an inlined function. Link: http://lkml.kernel.org/r/20190927070032.2129-3-richardw.yang@linux.intel.com Signed-off-by: Wei Yang Reviewed-by: Mike Kravetz Cc: Andrea Arcangeli Cc: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/userfaultfd.c | 56 ++++++++++++++++++++++++++++++++------------------------ 1 file changed, 32 insertions(+), 24 deletions(-) (limited to 'mm/userfaultfd.c') diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 07f44555fd03..a10aa8563e41 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -18,6 +18,36 @@ #include #include "internal.h" +static __always_inline +struct vm_area_struct *find_dst_vma(struct mm_struct *dst_mm, + unsigned long dst_start, + unsigned long len) +{ + /* + * Make sure that the dst range is both valid and fully within a + * single existing vma. + */ + struct vm_area_struct *dst_vma; + + dst_vma = find_vma(dst_mm, dst_start); + if (!dst_vma) + return NULL; + + if (dst_start < dst_vma->vm_start || + dst_start + len > dst_vma->vm_end) + return NULL; + + /* + * Check the vma is registered in uffd, this is required to + * enforce the VM_MAYWRITE check done at uffd registration + * time. + */ + if (!dst_vma->vm_userfaultfd_ctx.ctx) + return NULL; + + return dst_vma; +} + static int mcopy_atomic_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd, struct vm_area_struct *dst_vma, @@ -220,20 +250,9 @@ retry: */ if (!dst_vma) { err = -ENOENT; - dst_vma = find_vma(dst_mm, dst_start); + dst_vma = find_dst_vma(dst_mm, dst_start, len); if (!dst_vma || !is_vm_hugetlb_page(dst_vma)) goto out_unlock; - /* - * Check the vma is registered in uffd, this is - * required to enforce the VM_MAYWRITE check done at - * uffd registration time. - */ - if (!dst_vma->vm_userfaultfd_ctx.ctx) - goto out_unlock; - - if (dst_start < dst_vma->vm_start || - dst_start + len > dst_vma->vm_end) - goto out_unlock; err = -EINVAL; if (vma_hpagesize != vma_kernel_pagesize(dst_vma)) @@ -468,20 +487,9 @@ retry: * both valid and fully within a single existing vma. */ err = -ENOENT; - dst_vma = find_vma(dst_mm, dst_start); + dst_vma = find_dst_vma(dst_mm, dst_start, len); if (!dst_vma) goto out_unlock; - /* - * Check the vma is registered in uffd, this is required to - * enforce the VM_MAYWRITE check done at uffd registration - * time. - */ - if (!dst_vma->vm_userfaultfd_ctx.ctx) - goto out_unlock; - - if (dst_start < dst_vma->vm_start || - dst_start + len > dst_vma->vm_end) - goto out_unlock; err = -EINVAL; /* -- cgit v1.2.3 From f4f5329d453704e2214011ecf00db73cd3196d06 Mon Sep 17 00:00:00 2001 From: Wei Yang Date: Sat, 30 Nov 2019 17:58:17 -0800 Subject: mm: fix typos in comments when calling __SetPageUptodate() There are several places emphasise the effect of __SetPageUptodate(), while the comment seems to have a typo in two places. Link: http://lkml.kernel.org/r/20190926023705.7226-1-richardw.yang@linux.intel.com Signed-off-by: Wei Yang Reviewed-by: Andrew Morton Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory.c | 2 +- mm/userfaultfd.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'mm/userfaultfd.c') diff --git a/mm/memory.c b/mm/memory.c index c3902201989f..513c3ecc76ee 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3105,7 +3105,7 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf) /* * The memory barrier inside __SetPageUptodate makes sure that - * preceeding stores to the page contents become visible before + * preceding stores to the page contents become visible before * the set_pte_at() write. */ __SetPageUptodate(page); diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index a10aa8563e41..1b0d7abad1d4 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -90,7 +90,7 @@ static int mcopy_atomic_pte(struct mm_struct *dst_mm, /* * The memory barrier inside __SetPageUptodate makes sure that - * preceeding stores to the page contents become visible before + * preceding stores to the page contents become visible before * the set_pte_at() write. */ __SetPageUptodate(page); -- cgit v1.2.3