^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1) // SPDX-License-Identifier: GPL-2.0-only
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2) #include <linux/slab.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 3) #include <linux/stat.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 4) #include <linux/sched/xacct.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 5) #include <linux/fcntl.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 6) #include <linux/file.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 7) #include <linux/uio.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 8) #include <linux/fsnotify.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 9) #include <linux/security.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 10) #include <linux/export.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 11) #include <linux/syscalls.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 12) #include <linux/pagemap.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 13) #include <linux/splice.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 14) #include <linux/compat.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 15) #include <linux/mount.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 16) #include <linux/fs.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 17) #include "internal.h"
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 18)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 19) #include <linux/uaccess.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 20) #include <asm/unistd.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 21)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 22) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 23) * Performs necessary checks before doing a clone.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 24) *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 25) * Can adjust amount of bytes to clone via @req_count argument.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 26) * Returns appropriate error code that caller should return or
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 27) * zero in case the clone should be allowed.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 28) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 29) static int generic_remap_checks(struct file *file_in, loff_t pos_in,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 30) struct file *file_out, loff_t pos_out,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 31) loff_t *req_count, unsigned int remap_flags)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 32) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 33) struct inode *inode_in = file_in->f_mapping->host;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 34) struct inode *inode_out = file_out->f_mapping->host;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 35) uint64_t count = *req_count;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 36) uint64_t bcount;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 37) loff_t size_in, size_out;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 38) loff_t bs = inode_out->i_sb->s_blocksize;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 39) int ret;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 40)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 41) /* The start of both ranges must be aligned to an fs block. */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 42) if (!IS_ALIGNED(pos_in, bs) || !IS_ALIGNED(pos_out, bs))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 43) return -EINVAL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 44)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 45) /* Ensure offsets don't wrap. */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 46) if (pos_in + count < pos_in || pos_out + count < pos_out)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 47) return -EINVAL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 48)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 49) size_in = i_size_read(inode_in);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 50) size_out = i_size_read(inode_out);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 51)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 52) /* Dedupe requires both ranges to be within EOF. */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 53) if ((remap_flags & REMAP_FILE_DEDUP) &&
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 54) (pos_in >= size_in || pos_in + count > size_in ||
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 55) pos_out >= size_out || pos_out + count > size_out))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 56) return -EINVAL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 57)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 58) /* Ensure the infile range is within the infile. */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 59) if (pos_in >= size_in)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 60) return -EINVAL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 61) count = min(count, size_in - (uint64_t)pos_in);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 62)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 63) ret = generic_write_check_limits(file_out, pos_out, &count);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 64) if (ret)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 65) return ret;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 66)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 67) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 68) * If the user wanted us to link to the infile's EOF, round up to the
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 69) * next block boundary for this check.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 70) *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 71) * Otherwise, make sure the count is also block-aligned, having
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 72) * already confirmed the starting offsets' block alignment.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 73) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 74) if (pos_in + count == size_in) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 75) bcount = ALIGN(size_in, bs) - pos_in;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 76) } else {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 77) if (!IS_ALIGNED(count, bs))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 78) count = ALIGN_DOWN(count, bs);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 79) bcount = count;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 80) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 81)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 82) /* Don't allow overlapped cloning within the same file. */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 83) if (inode_in == inode_out &&
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 84) pos_out + bcount > pos_in &&
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 85) pos_out < pos_in + bcount)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 86) return -EINVAL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 87)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 88) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 89) * We shortened the request but the caller can't deal with that, so
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 90) * bounce the request back to userspace.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 91) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 92) if (*req_count != count && !(remap_flags & REMAP_FILE_CAN_SHORTEN))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 93) return -EINVAL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 94)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 95) *req_count = count;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 96) return 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 97) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 98)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 99) static int remap_verify_area(struct file *file, loff_t pos, loff_t len,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 100) bool write)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 101) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 102) struct inode *inode = file_inode(file);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 103)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 104) if (unlikely(pos < 0 || len < 0))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 105) return -EINVAL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 106)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 107) if (unlikely((loff_t) (pos + len) < 0))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 108) return -EINVAL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 109)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 110) if (unlikely(inode->i_flctx && mandatory_lock(inode))) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 111) loff_t end = len ? pos + len - 1 : OFFSET_MAX;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 112) int retval;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 113)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 114) retval = locks_mandatory_area(inode, file, pos, end,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 115) write ? F_WRLCK : F_RDLCK);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 116) if (retval < 0)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 117) return retval;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 118) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 119)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 120) return security_file_permission(file, write ? MAY_WRITE : MAY_READ);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 121) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 122)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 123) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 124) * Ensure that we don't remap a partial EOF block in the middle of something
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 125) * else. Assume that the offsets have already been checked for block
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 126) * alignment.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 127) *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 128) * For clone we only link a partial EOF block above or at the destination file's
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 129) * EOF. For deduplication we accept a partial EOF block only if it ends at the
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 130) * destination file's EOF (can not link it into the middle of a file).
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 131) *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 132) * Shorten the request if possible.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 133) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 134) static int generic_remap_check_len(struct inode *inode_in,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 135) struct inode *inode_out,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 136) loff_t pos_out,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 137) loff_t *len,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 138) unsigned int remap_flags)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 139) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 140) u64 blkmask = i_blocksize(inode_in) - 1;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 141) loff_t new_len = *len;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 142)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 143) if ((*len & blkmask) == 0)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 144) return 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 145)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 146) if (pos_out + *len < i_size_read(inode_out))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 147) new_len &= ~blkmask;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 148)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 149) if (new_len == *len)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 150) return 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 151)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 152) if (remap_flags & REMAP_FILE_CAN_SHORTEN) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 153) *len = new_len;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 154) return 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 155) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 156)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 157) return (remap_flags & REMAP_FILE_DEDUP) ? -EBADE : -EINVAL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 158) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 159)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 160) /* Read a page's worth of file data into the page cache. */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 161) static struct page *vfs_dedupe_get_page(struct inode *inode, loff_t offset)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 162) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 163) struct page *page;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 164)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 165) page = read_mapping_page(inode->i_mapping, offset >> PAGE_SHIFT, NULL);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 166) if (IS_ERR(page))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 167) return page;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 168) if (!PageUptodate(page)) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 169) put_page(page);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 170) return ERR_PTR(-EIO);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 171) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 172) return page;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 173) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 174)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 175) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 176) * Lock two pages, ensuring that we lock in offset order if the pages are from
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 177) * the same file.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 178) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 179) static void vfs_lock_two_pages(struct page *page1, struct page *page2)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 180) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 181) /* Always lock in order of increasing index. */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 182) if (page1->index > page2->index)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 183) swap(page1, page2);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 184)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 185) lock_page(page1);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 186) if (page1 != page2)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 187) lock_page(page2);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 188) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 189)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 190) /* Unlock two pages, being careful not to unlock the same page twice. */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 191) static void vfs_unlock_two_pages(struct page *page1, struct page *page2)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 192) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 193) unlock_page(page1);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 194) if (page1 != page2)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 195) unlock_page(page2);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 196) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 197)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 198) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 199) * Compare extents of two files to see if they are the same.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 200) * Caller must have locked both inodes to prevent write races.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 201) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 202) static int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 203) struct inode *dest, loff_t destoff,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 204) loff_t len, bool *is_same)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 205) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 206) loff_t src_poff;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 207) loff_t dest_poff;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 208) void *src_addr;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 209) void *dest_addr;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 210) struct page *src_page;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 211) struct page *dest_page;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 212) loff_t cmp_len;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 213) bool same;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 214) int error;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 215)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 216) error = -EINVAL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 217) same = true;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 218) while (len) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 219) src_poff = srcoff & (PAGE_SIZE - 1);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 220) dest_poff = destoff & (PAGE_SIZE - 1);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 221) cmp_len = min(PAGE_SIZE - src_poff,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 222) PAGE_SIZE - dest_poff);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 223) cmp_len = min(cmp_len, len);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 224) if (cmp_len <= 0)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 225) goto out_error;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 226)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 227) src_page = vfs_dedupe_get_page(src, srcoff);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 228) if (IS_ERR(src_page)) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 229) error = PTR_ERR(src_page);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 230) goto out_error;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 231) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 232) dest_page = vfs_dedupe_get_page(dest, destoff);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 233) if (IS_ERR(dest_page)) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 234) error = PTR_ERR(dest_page);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 235) put_page(src_page);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 236) goto out_error;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 237) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 238)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 239) vfs_lock_two_pages(src_page, dest_page);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 240)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 241) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 242) * Now that we've locked both pages, make sure they're still
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 243) * mapped to the file data we're interested in. If not,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 244) * someone is invalidating pages on us and we lose.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 245) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 246) if (!PageUptodate(src_page) || !PageUptodate(dest_page) ||
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 247) src_page->mapping != src->i_mapping ||
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 248) dest_page->mapping != dest->i_mapping) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 249) same = false;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 250) goto unlock;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 251) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 252)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 253) src_addr = kmap_atomic(src_page);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 254) dest_addr = kmap_atomic(dest_page);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 255)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 256) flush_dcache_page(src_page);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 257) flush_dcache_page(dest_page);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 258)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 259) if (memcmp(src_addr + src_poff, dest_addr + dest_poff, cmp_len))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 260) same = false;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 261)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 262) kunmap_atomic(dest_addr);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 263) kunmap_atomic(src_addr);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 264) unlock:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 265) vfs_unlock_two_pages(src_page, dest_page);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 266) put_page(dest_page);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 267) put_page(src_page);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 268)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 269) if (!same)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 270) break;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 271)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 272) srcoff += cmp_len;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 273) destoff += cmp_len;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 274) len -= cmp_len;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 275) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 276)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 277) *is_same = same;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 278) return 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 279)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 280) out_error:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 281) return error;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 282) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 283)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 284) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 285) * Check that the two inodes are eligible for cloning, the ranges make
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 286) * sense, and then flush all dirty data. Caller must ensure that the
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 287) * inodes have been locked against any other modifications.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 288) *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 289) * If there's an error, then the usual negative error code is returned.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 290) * Otherwise returns 0 with *len set to the request length.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 291) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 292) int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 293) struct file *file_out, loff_t pos_out,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 294) loff_t *len, unsigned int remap_flags)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 295) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 296) struct inode *inode_in = file_inode(file_in);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 297) struct inode *inode_out = file_inode(file_out);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 298) bool same_inode = (inode_in == inode_out);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 299) int ret;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 300)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 301) /* Don't touch certain kinds of inodes */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 302) if (IS_IMMUTABLE(inode_out))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 303) return -EPERM;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 304)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 305) if (IS_SWAPFILE(inode_in) || IS_SWAPFILE(inode_out))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 306) return -ETXTBSY;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 307)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 308) /* Don't reflink dirs, pipes, sockets... */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 309) if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 310) return -EISDIR;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 311) if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 312) return -EINVAL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 313)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 314) /* Zero length dedupe exits immediately; reflink goes to EOF. */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 315) if (*len == 0) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 316) loff_t isize = i_size_read(inode_in);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 317)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 318) if ((remap_flags & REMAP_FILE_DEDUP) || pos_in == isize)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 319) return 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 320) if (pos_in > isize)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 321) return -EINVAL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 322) *len = isize - pos_in;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 323) if (*len == 0)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 324) return 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 325) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 326)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 327) /* Check that we don't violate system file offset limits. */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 328) ret = generic_remap_checks(file_in, pos_in, file_out, pos_out, len,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 329) remap_flags);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 330) if (ret)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 331) return ret;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 332)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 333) /* Wait for the completion of any pending IOs on both files */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 334) inode_dio_wait(inode_in);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 335) if (!same_inode)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 336) inode_dio_wait(inode_out);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 337)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 338) ret = filemap_write_and_wait_range(inode_in->i_mapping,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 339) pos_in, pos_in + *len - 1);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 340) if (ret)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 341) return ret;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 342)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 343) ret = filemap_write_and_wait_range(inode_out->i_mapping,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 344) pos_out, pos_out + *len - 1);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 345) if (ret)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 346) return ret;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 347)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 348) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 349) * Check that the extents are the same.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 350) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 351) if (remap_flags & REMAP_FILE_DEDUP) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 352) bool is_same = false;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 353)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 354) ret = vfs_dedupe_file_range_compare(inode_in, pos_in,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 355) inode_out, pos_out, *len, &is_same);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 356) if (ret)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 357) return ret;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 358) if (!is_same)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 359) return -EBADE;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 360) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 361)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 362) ret = generic_remap_check_len(inode_in, inode_out, pos_out, len,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 363) remap_flags);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 364) if (ret)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 365) return ret;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 366)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 367) /* If can't alter the file contents, we're done. */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 368) if (!(remap_flags & REMAP_FILE_DEDUP))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 369) ret = file_modified(file_out);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 370)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 371) return ret;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 372) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 373) EXPORT_SYMBOL(generic_remap_file_range_prep);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 374)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 375) loff_t do_clone_file_range(struct file *file_in, loff_t pos_in,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 376) struct file *file_out, loff_t pos_out,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 377) loff_t len, unsigned int remap_flags)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 378) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 379) loff_t ret;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 380)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 381) WARN_ON_ONCE(remap_flags & REMAP_FILE_DEDUP);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 382)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 383) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 384) * FICLONE/FICLONERANGE ioctls enforce that src and dest files are on
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 385) * the same mount. Practically, they only need to be on the same file
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 386) * system.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 387) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 388) if (file_inode(file_in)->i_sb != file_inode(file_out)->i_sb)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 389) return -EXDEV;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 390)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 391) ret = generic_file_rw_checks(file_in, file_out);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 392) if (ret < 0)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 393) return ret;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 394)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 395) if (!file_in->f_op->remap_file_range)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 396) return -EOPNOTSUPP;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 397)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 398) ret = remap_verify_area(file_in, pos_in, len, false);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 399) if (ret)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 400) return ret;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 401)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 402) ret = remap_verify_area(file_out, pos_out, len, true);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 403) if (ret)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 404) return ret;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 405)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 406) ret = file_in->f_op->remap_file_range(file_in, pos_in,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 407) file_out, pos_out, len, remap_flags);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 408) if (ret < 0)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 409) return ret;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 410)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 411) fsnotify_access(file_in);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 412) fsnotify_modify(file_out);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 413) return ret;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 414) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 415) EXPORT_SYMBOL(do_clone_file_range);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 416)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 417) loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 418) struct file *file_out, loff_t pos_out,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 419) loff_t len, unsigned int remap_flags)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 420) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 421) loff_t ret;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 422)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 423) file_start_write(file_out);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 424) ret = do_clone_file_range(file_in, pos_in, file_out, pos_out, len,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 425) remap_flags);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 426) file_end_write(file_out);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 427)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 428) return ret;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 429) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 430) EXPORT_SYMBOL(vfs_clone_file_range);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 431)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 432) /* Check whether we are allowed to dedupe the destination file */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 433) static bool allow_file_dedupe(struct file *file)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 434) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 435) if (capable(CAP_SYS_ADMIN))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 436) return true;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 437) if (file->f_mode & FMODE_WRITE)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 438) return true;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 439) if (uid_eq(current_fsuid(), file_inode(file)->i_uid))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 440) return true;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 441) if (!inode_permission(file_inode(file), MAY_WRITE))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 442) return true;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 443) return false;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 444) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 445)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 446) loff_t vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 447) struct file *dst_file, loff_t dst_pos,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 448) loff_t len, unsigned int remap_flags)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 449) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 450) loff_t ret;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 451)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 452) WARN_ON_ONCE(remap_flags & ~(REMAP_FILE_DEDUP |
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 453) REMAP_FILE_CAN_SHORTEN));
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 454)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 455) ret = mnt_want_write_file(dst_file);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 456) if (ret)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 457) return ret;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 458)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 459) ret = remap_verify_area(dst_file, dst_pos, len, true);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 460) if (ret < 0)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 461) goto out_drop_write;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 462)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 463) ret = -EPERM;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 464) if (!allow_file_dedupe(dst_file))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 465) goto out_drop_write;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 466)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 467) ret = -EXDEV;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 468) if (src_file->f_path.mnt != dst_file->f_path.mnt)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 469) goto out_drop_write;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 470)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 471) ret = -EISDIR;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 472) if (S_ISDIR(file_inode(dst_file)->i_mode))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 473) goto out_drop_write;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 474)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 475) ret = -EINVAL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 476) if (!dst_file->f_op->remap_file_range)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 477) goto out_drop_write;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 478)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 479) if (len == 0) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 480) ret = 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 481) goto out_drop_write;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 482) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 483)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 484) ret = dst_file->f_op->remap_file_range(src_file, src_pos, dst_file,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 485) dst_pos, len, remap_flags | REMAP_FILE_DEDUP);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 486) out_drop_write:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 487) mnt_drop_write_file(dst_file);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 488)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 489) return ret;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 490) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 491) EXPORT_SYMBOL(vfs_dedupe_file_range_one);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 492)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 493) int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 494) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 495) struct file_dedupe_range_info *info;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 496) struct inode *src = file_inode(file);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 497) u64 off;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 498) u64 len;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 499) int i;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 500) int ret;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 501) u16 count = same->dest_count;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 502) loff_t deduped;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 503)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 504) if (!(file->f_mode & FMODE_READ))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 505) return -EINVAL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 506)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 507) if (same->reserved1 || same->reserved2)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 508) return -EINVAL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 509)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 510) off = same->src_offset;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 511) len = same->src_length;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 512)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 513) if (S_ISDIR(src->i_mode))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 514) return -EISDIR;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 515)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 516) if (!S_ISREG(src->i_mode))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 517) return -EINVAL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 518)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 519) if (!file->f_op->remap_file_range)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 520) return -EOPNOTSUPP;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 521)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 522) ret = remap_verify_area(file, off, len, false);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 523) if (ret < 0)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 524) return ret;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 525) ret = 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 526)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 527) if (off + len > i_size_read(src))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 528) return -EINVAL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 529)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 530) /* Arbitrary 1G limit on a single dedupe request, can be raised. */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 531) len = min_t(u64, len, 1 << 30);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 532)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 533) /* pre-format output fields to sane values */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 534) for (i = 0; i < count; i++) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 535) same->info[i].bytes_deduped = 0ULL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 536) same->info[i].status = FILE_DEDUPE_RANGE_SAME;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 537) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 538)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 539) for (i = 0, info = same->info; i < count; i++, info++) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 540) struct fd dst_fd = fdget(info->dest_fd);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 541) struct file *dst_file = dst_fd.file;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 542)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 543) if (!dst_file) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 544) info->status = -EBADF;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 545) goto next_loop;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 546) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 547)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 548) if (info->reserved) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 549) info->status = -EINVAL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 550) goto next_fdput;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 551) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 552)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 553) deduped = vfs_dedupe_file_range_one(file, off, dst_file,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 554) info->dest_offset, len,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 555) REMAP_FILE_CAN_SHORTEN);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 556) if (deduped == -EBADE)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 557) info->status = FILE_DEDUPE_RANGE_DIFFERS;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 558) else if (deduped < 0)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 559) info->status = deduped;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 560) else
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 561) info->bytes_deduped = len;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 562)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 563) next_fdput:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 564) fdput(dst_fd);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 565) next_loop:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 566) if (fatal_signal_pending(current))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 567) break;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 568) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 569) return ret;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 570) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 571) EXPORT_SYMBOL(vfs_dedupe_file_range);