X-Git-Url: https://err.no/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=mm%2Fmadvise.c;h=4454936f87d1b6fb2fde25e1570a2748ea4a16b0;hb=0dd7f883a9e21c5f2ff5e8f1cbb0e78cdc044d8a;hp=944b5e52d812f051fb2bffaed33a4288ba4c920e;hpb=1da177e4c3f41524e886b7f1b8a0c1fc7321cac2;p=linux-2.6 diff --git a/mm/madvise.c b/mm/madvise.c index 944b5e52d8..4454936f87 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -8,17 +8,47 @@ #include #include #include +#include #include /* * We can potentially split a vm area into separate * areas, each area with its own behavior. */ -static long madvise_behavior(struct vm_area_struct * vma, unsigned long start, - unsigned long end, int behavior) +static long madvise_behavior(struct vm_area_struct * vma, + struct vm_area_struct **prev, + unsigned long start, unsigned long end, int behavior) { struct mm_struct * mm = vma->vm_mm; int error = 0; + pgoff_t pgoff; + int new_flags = vma->vm_flags & ~VM_READHINTMASK; + + switch (behavior) { + case MADV_SEQUENTIAL: + new_flags |= VM_SEQ_READ; + break; + case MADV_RANDOM: + new_flags |= VM_RAND_READ; + break; + default: + break; + } + + if (new_flags == vma->vm_flags) { + *prev = vma; + goto out; + } + + pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT); + *prev = vma_merge(mm, *prev, start, end, new_flags, vma->anon_vma, + vma->vm_file, pgoff, vma_policy(vma)); + if (*prev) { + vma = *prev; + goto success; + } + + *prev = vma; if (start != vma->vm_start) { error = split_vma(mm, vma, start, 1); @@ -32,21 +62,11 @@ static long madvise_behavior(struct vm_area_struct * vma, unsigned long start, goto out; } +success: /* * vm_flags is protected by the mmap_sem held in write mode. */ - VM_ClearReadHint(vma); - - switch (behavior) { - case MADV_SEQUENTIAL: - vma->vm_flags |= VM_SEQ_READ; - break; - case MADV_RANDOM: - vma->vm_flags |= VM_RAND_READ; - break; - default: - break; - } + vma->vm_flags = new_flags; out: if (error == -ENOMEM) @@ -58,13 +78,17 @@ out: * Schedule all required I/O operations. Do not wait for completion. */ static long madvise_willneed(struct vm_area_struct * vma, + struct vm_area_struct ** prev, unsigned long start, unsigned long end) { struct file *file = vma->vm_file; - if (!file) - return -EBADF; + if (file->f_mapping->a_ops->get_xip_page) { + /* no bad return value, but ignore advice */ + return 0; + } + *prev = vma; start = ((start - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff; if (end > vma->vm_end) end = vma->vm_end; @@ -95,8 +119,10 @@ static long madvise_willneed(struct vm_area_struct * vma, * dirty pages is already available as msync(MS_INVALIDATE). */ static long madvise_dontneed(struct vm_area_struct * vma, + struct vm_area_struct ** prev, unsigned long start, unsigned long end) { + *prev = vma; if ((vma->vm_flags & VM_LOCKED) || is_vm_hugetlb_page(vma)) return -EINVAL; @@ -111,24 +137,29 @@ static long madvise_dontneed(struct vm_area_struct * vma, return 0; } -static long madvise_vma(struct vm_area_struct * vma, unsigned long start, - unsigned long end, int behavior) +static long +madvise_vma(struct vm_area_struct *vma, struct vm_area_struct **prev, + unsigned long start, unsigned long end, int behavior) { + struct file *filp = vma->vm_file; long error = -EBADF; + if (!filp) + goto out; + switch (behavior) { case MADV_NORMAL: case MADV_SEQUENTIAL: case MADV_RANDOM: - error = madvise_behavior(vma, start, end, behavior); + error = madvise_behavior(vma, prev, start, end, behavior); break; case MADV_WILLNEED: - error = madvise_willneed(vma, start, end); + error = madvise_willneed(vma, prev, start, end); break; case MADV_DONTNEED: - error = madvise_dontneed(vma, start, end); + error = madvise_dontneed(vma, prev, start, end); break; default: @@ -136,6 +167,7 @@ static long madvise_vma(struct vm_area_struct * vma, unsigned long start, break; } +out: return error; } @@ -175,8 +207,8 @@ static long madvise_vma(struct vm_area_struct * vma, unsigned long start, */ asmlinkage long sys_madvise(unsigned long start, size_t len_in, int behavior) { - unsigned long end; - struct vm_area_struct * vma; + unsigned long end, tmp; + struct vm_area_struct * vma, *prev; int unmapped_error = 0; int error = -EINVAL; size_t len; @@ -202,40 +234,43 @@ asmlinkage long sys_madvise(unsigned long start, size_t len_in, int behavior) /* * If the interval [start,end) covers some unmapped address * ranges, just ignore them, but return -ENOMEM at the end. + * - different from the way of handling in mlock etc. */ - vma = find_vma(current->mm, start); + vma = find_vma_prev(current->mm, start, &prev); + if (vma && start > vma->vm_start) + prev = vma; + for (;;) { /* Still start < end. */ error = -ENOMEM; if (!vma) goto out; - /* Here start < vma->vm_end. */ + /* Here start < (end|vma->vm_end). */ if (start < vma->vm_start) { unmapped_error = -ENOMEM; start = vma->vm_start; + if (start >= end) + goto out; } - /* Here vma->vm_start <= start < vma->vm_end. */ - if (end <= vma->vm_end) { - if (start < end) { - error = madvise_vma(vma, start, end, - behavior); - if (error) - goto out; - } - error = unmapped_error; - goto out; - } + /* Here vma->vm_start <= start < (end|vma->vm_end) */ + tmp = vma->vm_end; + if (end < tmp) + tmp = end; - /* Here vma->vm_start <= start < vma->vm_end < end. */ - error = madvise_vma(vma, start, vma->vm_end, behavior); + /* Here vma->vm_start <= start < tmp <= (end|vma->vm_end). */ + error = madvise_vma(vma, &prev, start, tmp, behavior); if (error) goto out; - start = vma->vm_end; - vma = vma->vm_next; + start = tmp; + if (start < prev->vm_end) + start = prev->vm_end; + error = unmapped_error; + if (start >= end) + goto out; + vma = prev->vm_next; } - out: up_write(¤t->mm->mmap_sem); return error;