^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2) * linux/fs/nfs/blocklayout/blocklayout.c
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 3) *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 4) * Module for the NFSv4.1 pNFS block layout driver.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 5) *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 6) * Copyright (c) 2006 The Regents of the University of Michigan.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 7) * All rights reserved.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 8) *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 9) * Andy Adamson <andros@citi.umich.edu>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 10) * Fred Isaman <iisaman@umich.edu>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 11) *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 12) * permission is granted to use, copy, create derivative works and
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 13) * redistribute this software and such derivative works for any purpose,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 14) * so long as the name of the university of michigan is not used in
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 15) * any advertising or publicity pertaining to the use or distribution
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 16) * of this software without specific, written prior authorization. if
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 17) * the above copyright notice or any other identification of the
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 18) * university of michigan is included in any copy of any portion of
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 19) * this software, then the disclaimer below must also be included.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 20) *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 21) * this software is provided as is, without representation from the
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 22) * university of michigan as to its fitness for any purpose, and without
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 23) * warranty by the university of michigan of any kind, either express
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 24) * or implied, including without limitation the implied warranties of
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 25) * merchantability and fitness for a particular purpose. the regents
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 26) * of the university of michigan shall not be liable for any damages,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 27) * including special, indirect, incidental, or consequential damages,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 28) * with respect to any claim arising out or in connection with the use
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 29) * of the software, even if it has been or is hereafter advised of the
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 30) * possibility of such damages.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 31) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 32)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 33) #include <linux/module.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 34) #include <linux/init.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 35) #include <linux/mount.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 36) #include <linux/namei.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 37) #include <linux/bio.h> /* struct bio */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 38) #include <linux/prefetch.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 39) #include <linux/pagevec.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 40)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 41) #include "../pnfs.h"
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 42) #include "../nfs4session.h"
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 43) #include "../internal.h"
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 44) #include "blocklayout.h"
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 45)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 46) #define NFSDBG_FACILITY NFSDBG_PNFS_LD
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 47)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 48) MODULE_LICENSE("GPL");
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 49) MODULE_AUTHOR("Andy Adamson <andros@citi.umich.edu>");
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 50) MODULE_DESCRIPTION("The NFSv4.1 pNFS Block layout driver");
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 51)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 52) static bool is_hole(struct pnfs_block_extent *be)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 53) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 54) switch (be->be_state) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 55) case PNFS_BLOCK_NONE_DATA:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 56) return true;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 57) case PNFS_BLOCK_INVALID_DATA:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 58) return be->be_tag ? false : true;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 59) default:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 60) return false;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 61) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 62) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 63)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 64) /* The data we are handed might be spread across several bios. We need
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 65) * to track when the last one is finished.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 66) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 67) struct parallel_io {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 68) struct kref refcnt;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 69) void (*pnfs_callback) (void *data);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 70) void *data;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 71) };
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 72)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 73) static inline struct parallel_io *alloc_parallel(void *data)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 74) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 75) struct parallel_io *rv;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 76)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 77) rv = kmalloc(sizeof(*rv), GFP_NOFS);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 78) if (rv) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 79) rv->data = data;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 80) kref_init(&rv->refcnt);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 81) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 82) return rv;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 83) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 84)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 85) static inline void get_parallel(struct parallel_io *p)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 86) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 87) kref_get(&p->refcnt);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 88) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 89)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 90) static void destroy_parallel(struct kref *kref)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 91) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 92) struct parallel_io *p = container_of(kref, struct parallel_io, refcnt);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 93)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 94) dprintk("%s enter\n", __func__);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 95) p->pnfs_callback(p->data);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 96) kfree(p);
^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 inline void put_parallel(struct parallel_io *p)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 100) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 101) kref_put(&p->refcnt, destroy_parallel);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 102) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 103)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 104) static struct bio *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 105) bl_submit_bio(struct bio *bio)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 106) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 107) if (bio) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 108) get_parallel(bio->bi_private);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 109) dprintk("%s submitting %s bio %u@%llu\n", __func__,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 110) bio_op(bio) == READ ? "read" : "write",
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 111) bio->bi_iter.bi_size,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 112) (unsigned long long)bio->bi_iter.bi_sector);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 113) submit_bio(bio);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 114) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 115) return NULL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 116) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 117)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 118) static struct bio *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 119) bl_alloc_init_bio(int npg, struct block_device *bdev, sector_t disk_sector,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 120) bio_end_io_t end_io, struct parallel_io *par)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 121) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 122) struct bio *bio;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 123)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 124) npg = min(npg, BIO_MAX_PAGES);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 125) bio = bio_alloc(GFP_NOIO, npg);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 126) if (!bio && (current->flags & PF_MEMALLOC)) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 127) while (!bio && (npg /= 2))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 128) bio = bio_alloc(GFP_NOIO, npg);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 129) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 130)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 131) if (bio) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 132) bio->bi_iter.bi_sector = disk_sector;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 133) bio_set_dev(bio, bdev);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 134) bio->bi_end_io = end_io;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 135) bio->bi_private = par;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 136) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 137) return bio;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 138) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 139)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 140) static bool offset_in_map(u64 offset, struct pnfs_block_dev_map *map)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 141) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 142) return offset >= map->start && offset < map->start + map->len;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 143) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 144)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 145) static struct bio *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 146) do_add_page_to_bio(struct bio *bio, int npg, int rw, sector_t isect,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 147) struct page *page, struct pnfs_block_dev_map *map,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 148) struct pnfs_block_extent *be, bio_end_io_t end_io,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 149) struct parallel_io *par, unsigned int offset, int *len)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 150) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 151) struct pnfs_block_dev *dev =
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 152) container_of(be->be_device, struct pnfs_block_dev, node);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 153) u64 disk_addr, end;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 154)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 155) dprintk("%s: npg %d rw %d isect %llu offset %u len %d\n", __func__,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 156) npg, rw, (unsigned long long)isect, offset, *len);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 157)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 158) /* translate to device offset */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 159) isect += be->be_v_offset;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 160) isect -= be->be_f_offset;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 161)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 162) /* translate to physical disk offset */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 163) disk_addr = (u64)isect << SECTOR_SHIFT;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 164) if (!offset_in_map(disk_addr, map)) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 165) if (!dev->map(dev, disk_addr, map) || !offset_in_map(disk_addr, map))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 166) return ERR_PTR(-EIO);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 167) bio = bl_submit_bio(bio);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 168) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 169) disk_addr += map->disk_offset;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 170) disk_addr -= map->start;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 171)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 172) /* limit length to what the device mapping allows */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 173) end = disk_addr + *len;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 174) if (end >= map->start + map->len)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 175) *len = map->start + map->len - disk_addr;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 176)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 177) retry:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 178) if (!bio) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 179) bio = bl_alloc_init_bio(npg, map->bdev,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 180) disk_addr >> SECTOR_SHIFT, end_io, par);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 181) if (!bio)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 182) return ERR_PTR(-ENOMEM);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 183) bio_set_op_attrs(bio, rw, 0);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 184) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 185) if (bio_add_page(bio, page, *len, offset) < *len) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 186) bio = bl_submit_bio(bio);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 187) goto retry;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 188) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 189) return bio;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 190) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 191)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 192) static void bl_mark_devices_unavailable(struct nfs_pgio_header *header, bool rw)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 193) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 194) struct pnfs_block_layout *bl = BLK_LSEG2EXT(header->lseg);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 195) size_t bytes_left = header->args.count;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 196) sector_t isect, extent_length = 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 197) struct pnfs_block_extent be;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 198)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 199) isect = header->args.offset >> SECTOR_SHIFT;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 200) bytes_left += header->args.offset - (isect << SECTOR_SHIFT);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 201)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 202) while (bytes_left > 0) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 203) if (!ext_tree_lookup(bl, isect, &be, rw))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 204) return;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 205) extent_length = be.be_length - (isect - be.be_f_offset);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 206) nfs4_mark_deviceid_unavailable(be.be_device);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 207) isect += extent_length;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 208) if (bytes_left > extent_length << SECTOR_SHIFT)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 209) bytes_left -= extent_length << SECTOR_SHIFT;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 210) else
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 211) bytes_left = 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 212) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 213) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 214)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 215) static void bl_end_io_read(struct bio *bio)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 216) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 217) struct parallel_io *par = bio->bi_private;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 218)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 219) if (bio->bi_status) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 220) struct nfs_pgio_header *header = par->data;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 221)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 222) if (!header->pnfs_error)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 223) header->pnfs_error = -EIO;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 224) pnfs_set_lo_fail(header->lseg);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 225) bl_mark_devices_unavailable(header, false);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 226) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 227)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 228) bio_put(bio);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 229) put_parallel(par);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 230) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 231)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 232) static void bl_read_cleanup(struct work_struct *work)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 233) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 234) struct rpc_task *task;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 235) struct nfs_pgio_header *hdr;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 236) dprintk("%s enter\n", __func__);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 237) task = container_of(work, struct rpc_task, u.tk_work);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 238) hdr = container_of(task, struct nfs_pgio_header, task);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 239) pnfs_ld_read_done(hdr);
^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) static void
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 243) bl_end_par_io_read(void *data)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 244) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 245) struct nfs_pgio_header *hdr = data;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 246)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 247) hdr->task.tk_status = hdr->pnfs_error;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 248) INIT_WORK(&hdr->task.u.tk_work, bl_read_cleanup);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 249) schedule_work(&hdr->task.u.tk_work);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 250) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 251)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 252) static enum pnfs_try_status
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 253) bl_read_pagelist(struct nfs_pgio_header *header)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 254) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 255) struct pnfs_block_layout *bl = BLK_LSEG2EXT(header->lseg);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 256) struct pnfs_block_dev_map map = { .start = NFS4_MAX_UINT64 };
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 257) struct bio *bio = NULL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 258) struct pnfs_block_extent be;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 259) sector_t isect, extent_length = 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 260) struct parallel_io *par;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 261) loff_t f_offset = header->args.offset;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 262) size_t bytes_left = header->args.count;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 263) unsigned int pg_offset = header->args.pgbase, pg_len;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 264) struct page **pages = header->args.pages;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 265) int pg_index = header->args.pgbase >> PAGE_SHIFT;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 266) const bool is_dio = (header->dreq != NULL);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 267) struct blk_plug plug;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 268) int i;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 269)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 270) dprintk("%s enter nr_pages %u offset %lld count %u\n", __func__,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 271) header->page_array.npages, f_offset,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 272) (unsigned int)header->args.count);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 273)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 274) par = alloc_parallel(header);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 275) if (!par)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 276) return PNFS_NOT_ATTEMPTED;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 277) par->pnfs_callback = bl_end_par_io_read;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 278)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 279) blk_start_plug(&plug);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 280)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 281) isect = (sector_t) (f_offset >> SECTOR_SHIFT);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 282) /* Code assumes extents are page-aligned */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 283) for (i = pg_index; i < header->page_array.npages; i++) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 284) if (extent_length <= 0) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 285) /* We've used up the previous extent */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 286) bio = bl_submit_bio(bio);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 287)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 288) /* Get the next one */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 289) if (!ext_tree_lookup(bl, isect, &be, false)) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 290) header->pnfs_error = -EIO;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 291) goto out;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 292) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 293) extent_length = be.be_length - (isect - be.be_f_offset);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 294) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 295)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 296) if (is_dio) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 297) if (pg_offset + bytes_left > PAGE_SIZE)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 298) pg_len = PAGE_SIZE - pg_offset;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 299) else
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 300) pg_len = bytes_left;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 301) } else {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 302) BUG_ON(pg_offset != 0);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 303) pg_len = PAGE_SIZE;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 304) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 305)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 306) if (is_hole(&be)) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 307) bio = bl_submit_bio(bio);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 308) /* Fill hole w/ zeroes w/o accessing device */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 309) dprintk("%s Zeroing page for hole\n", __func__);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 310) zero_user_segment(pages[i], pg_offset, pg_len);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 311)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 312) /* invalidate map */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 313) map.start = NFS4_MAX_UINT64;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 314) } else {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 315) bio = do_add_page_to_bio(bio,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 316) header->page_array.npages - i,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 317) READ,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 318) isect, pages[i], &map, &be,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 319) bl_end_io_read, par,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 320) pg_offset, &pg_len);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 321) if (IS_ERR(bio)) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 322) header->pnfs_error = PTR_ERR(bio);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 323) bio = NULL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 324) goto out;
^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) isect += (pg_len >> SECTOR_SHIFT);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 328) extent_length -= (pg_len >> SECTOR_SHIFT);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 329) f_offset += pg_len;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 330) bytes_left -= pg_len;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 331) pg_offset = 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 332) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 333) if ((isect << SECTOR_SHIFT) >= header->inode->i_size) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 334) header->res.eof = 1;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 335) header->res.count = header->inode->i_size - header->args.offset;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 336) } else {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 337) header->res.count = (isect << SECTOR_SHIFT) - header->args.offset;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 338) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 339) out:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 340) bl_submit_bio(bio);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 341) blk_finish_plug(&plug);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 342) put_parallel(par);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 343) return PNFS_ATTEMPTED;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 344) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 345)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 346) static void bl_end_io_write(struct bio *bio)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 347) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 348) struct parallel_io *par = bio->bi_private;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 349) struct nfs_pgio_header *header = par->data;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 350)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 351) if (bio->bi_status) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 352) if (!header->pnfs_error)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 353) header->pnfs_error = -EIO;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 354) pnfs_set_lo_fail(header->lseg);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 355) bl_mark_devices_unavailable(header, true);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 356) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 357) bio_put(bio);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 358) put_parallel(par);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 359) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 360)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 361) /* Function scheduled for call during bl_end_par_io_write,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 362) * it marks sectors as written and extends the commitlist.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 363) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 364) static void bl_write_cleanup(struct work_struct *work)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 365) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 366) struct rpc_task *task = container_of(work, struct rpc_task, u.tk_work);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 367) struct nfs_pgio_header *hdr =
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 368) container_of(task, struct nfs_pgio_header, task);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 369)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 370) dprintk("%s enter\n", __func__);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 371)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 372) if (likely(!hdr->pnfs_error)) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 373) struct pnfs_block_layout *bl = BLK_LSEG2EXT(hdr->lseg);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 374) u64 start = hdr->args.offset & (loff_t)PAGE_MASK;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 375) u64 end = (hdr->args.offset + hdr->args.count +
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 376) PAGE_SIZE - 1) & (loff_t)PAGE_MASK;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 377) u64 lwb = hdr->args.offset + hdr->args.count;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 378)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 379) ext_tree_mark_written(bl, start >> SECTOR_SHIFT,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 380) (end - start) >> SECTOR_SHIFT, lwb);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 381) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 382)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 383) pnfs_ld_write_done(hdr);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 384) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 385)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 386) /* Called when last of bios associated with a bl_write_pagelist call finishes */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 387) static void bl_end_par_io_write(void *data)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 388) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 389) struct nfs_pgio_header *hdr = data;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 390)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 391) hdr->task.tk_status = hdr->pnfs_error;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 392) hdr->verf.committed = NFS_FILE_SYNC;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 393) INIT_WORK(&hdr->task.u.tk_work, bl_write_cleanup);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 394) schedule_work(&hdr->task.u.tk_work);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 395) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 396)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 397) static enum pnfs_try_status
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 398) bl_write_pagelist(struct nfs_pgio_header *header, int sync)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 399) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 400) struct pnfs_block_layout *bl = BLK_LSEG2EXT(header->lseg);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 401) struct pnfs_block_dev_map map = { .start = NFS4_MAX_UINT64 };
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 402) struct bio *bio = NULL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 403) struct pnfs_block_extent be;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 404) sector_t isect, extent_length = 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 405) struct parallel_io *par = NULL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 406) loff_t offset = header->args.offset;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 407) size_t count = header->args.count;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 408) struct page **pages = header->args.pages;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 409) int pg_index = header->args.pgbase >> PAGE_SHIFT;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 410) unsigned int pg_len;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 411) struct blk_plug plug;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 412) int i;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 413)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 414) dprintk("%s enter, %zu@%lld\n", __func__, count, offset);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 415)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 416) /* At this point, header->page_aray is a (sequential) list of nfs_pages.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 417) * We want to write each, and if there is an error set pnfs_error
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 418) * to have it redone using nfs.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 419) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 420) par = alloc_parallel(header);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 421) if (!par)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 422) return PNFS_NOT_ATTEMPTED;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 423) par->pnfs_callback = bl_end_par_io_write;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 424)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 425) blk_start_plug(&plug);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 426)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 427) /* we always write out the whole page */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 428) offset = offset & (loff_t)PAGE_MASK;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 429) isect = offset >> SECTOR_SHIFT;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 430)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 431) for (i = pg_index; i < header->page_array.npages; i++) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 432) if (extent_length <= 0) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 433) /* We've used up the previous extent */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 434) bio = bl_submit_bio(bio);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 435) /* Get the next one */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 436) if (!ext_tree_lookup(bl, isect, &be, true)) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 437) header->pnfs_error = -EINVAL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 438) goto out;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 439) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 440)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 441) extent_length = be.be_length - (isect - be.be_f_offset);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 442) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 443)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 444) pg_len = PAGE_SIZE;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 445) bio = do_add_page_to_bio(bio, header->page_array.npages - i,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 446) WRITE, isect, pages[i], &map, &be,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 447) bl_end_io_write, par,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 448) 0, &pg_len);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 449) if (IS_ERR(bio)) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 450) header->pnfs_error = PTR_ERR(bio);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 451) bio = NULL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 452) goto out;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 453) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 454)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 455) offset += pg_len;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 456) count -= pg_len;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 457) isect += (pg_len >> SECTOR_SHIFT);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 458) extent_length -= (pg_len >> SECTOR_SHIFT);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 459) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 460)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 461) header->res.count = header->args.count;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 462) out:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 463) bl_submit_bio(bio);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 464) blk_finish_plug(&plug);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 465) put_parallel(par);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 466) return PNFS_ATTEMPTED;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 467) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 468)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 469) static void bl_free_layout_hdr(struct pnfs_layout_hdr *lo)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 470) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 471) struct pnfs_block_layout *bl = BLK_LO2EXT(lo);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 472) int err;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 473)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 474) dprintk("%s enter\n", __func__);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 475)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 476) err = ext_tree_remove(bl, true, 0, LLONG_MAX);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 477) WARN_ON(err);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 478)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 479) kfree_rcu(bl, bl_layout.plh_rcu);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 480) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 481)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 482) static struct pnfs_layout_hdr *__bl_alloc_layout_hdr(struct inode *inode,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 483) gfp_t gfp_flags, bool is_scsi_layout)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 484) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 485) struct pnfs_block_layout *bl;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 486)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 487) dprintk("%s enter\n", __func__);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 488) bl = kzalloc(sizeof(*bl), gfp_flags);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 489) if (!bl)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 490) return NULL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 491)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 492) bl->bl_ext_rw = RB_ROOT;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 493) bl->bl_ext_ro = RB_ROOT;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 494) spin_lock_init(&bl->bl_ext_lock);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 495)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 496) bl->bl_scsi_layout = is_scsi_layout;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 497) return &bl->bl_layout;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 498) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 499)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 500) static struct pnfs_layout_hdr *bl_alloc_layout_hdr(struct inode *inode,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 501) gfp_t gfp_flags)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 502) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 503) return __bl_alloc_layout_hdr(inode, gfp_flags, false);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 504) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 505)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 506) static struct pnfs_layout_hdr *sl_alloc_layout_hdr(struct inode *inode,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 507) gfp_t gfp_flags)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 508) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 509) return __bl_alloc_layout_hdr(inode, gfp_flags, true);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 510) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 511)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 512) static void bl_free_lseg(struct pnfs_layout_segment *lseg)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 513) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 514) dprintk("%s enter\n", __func__);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 515) kfree(lseg);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 516) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 517)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 518) /* Tracks info needed to ensure extents in layout obey constraints of spec */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 519) struct layout_verification {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 520) u32 mode; /* R or RW */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 521) u64 start; /* Expected start of next non-COW extent */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 522) u64 inval; /* Start of INVAL coverage */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 523) u64 cowread; /* End of COW read coverage */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 524) };
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 525)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 526) /* Verify the extent meets the layout requirements of the pnfs-block draft,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 527) * section 2.3.1.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 528) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 529) static int verify_extent(struct pnfs_block_extent *be,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 530) struct layout_verification *lv)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 531) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 532) if (lv->mode == IOMODE_READ) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 533) if (be->be_state == PNFS_BLOCK_READWRITE_DATA ||
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 534) be->be_state == PNFS_BLOCK_INVALID_DATA)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 535) return -EIO;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 536) if (be->be_f_offset != lv->start)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 537) return -EIO;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 538) lv->start += be->be_length;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 539) return 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 540) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 541) /* lv->mode == IOMODE_RW */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 542) if (be->be_state == PNFS_BLOCK_READWRITE_DATA) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 543) if (be->be_f_offset != lv->start)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 544) return -EIO;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 545) if (lv->cowread > lv->start)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 546) return -EIO;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 547) lv->start += be->be_length;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 548) lv->inval = lv->start;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 549) return 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 550) } else if (be->be_state == PNFS_BLOCK_INVALID_DATA) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 551) if (be->be_f_offset != lv->start)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 552) return -EIO;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 553) lv->start += be->be_length;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 554) return 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 555) } else if (be->be_state == PNFS_BLOCK_READ_DATA) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 556) if (be->be_f_offset > lv->start)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 557) return -EIO;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 558) if (be->be_f_offset < lv->inval)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 559) return -EIO;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 560) if (be->be_f_offset < lv->cowread)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 561) return -EIO;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 562) /* It looks like you might want to min this with lv->start,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 563) * but you really don't.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 564) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 565) lv->inval = lv->inval + be->be_length;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 566) lv->cowread = be->be_f_offset + be->be_length;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 567) return 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 568) } else
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 569) return -EIO;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 570) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 571)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 572) static int decode_sector_number(__be32 **rp, sector_t *sp)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 573) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 574) uint64_t s;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 575)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 576) *rp = xdr_decode_hyper(*rp, &s);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 577) if (s & 0x1ff) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 578) printk(KERN_WARNING "NFS: %s: sector not aligned\n", __func__);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 579) return -1;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 580) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 581) *sp = s >> SECTOR_SHIFT;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 582) return 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 583) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 584)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 585) static struct nfs4_deviceid_node *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 586) bl_find_get_deviceid(struct nfs_server *server,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 587) const struct nfs4_deviceid *id, const struct cred *cred,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 588) gfp_t gfp_mask)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 589) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 590) struct nfs4_deviceid_node *node;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 591) unsigned long start, end;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 592)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 593) retry:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 594) node = nfs4_find_get_deviceid(server, id, cred, gfp_mask);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 595) if (!node)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 596) return ERR_PTR(-ENODEV);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 597)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 598) if (test_bit(NFS_DEVICEID_UNAVAILABLE, &node->flags) == 0)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 599) return node;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 600)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 601) end = jiffies;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 602) start = end - PNFS_DEVICE_RETRY_TIMEOUT;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 603) if (!time_in_range(node->timestamp_unavailable, start, end)) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 604) nfs4_delete_deviceid(node->ld, node->nfs_client, id);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 605) goto retry;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 606) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 607) return ERR_PTR(-ENODEV);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 608) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 609)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 610) static int
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 611) bl_alloc_extent(struct xdr_stream *xdr, struct pnfs_layout_hdr *lo,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 612) struct layout_verification *lv, struct list_head *extents,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 613) gfp_t gfp_mask)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 614) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 615) struct pnfs_block_extent *be;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 616) struct nfs4_deviceid id;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 617) int error;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 618) __be32 *p;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 619)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 620) p = xdr_inline_decode(xdr, 28 + NFS4_DEVICEID4_SIZE);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 621) if (!p)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 622) return -EIO;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 623)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 624) be = kzalloc(sizeof(*be), GFP_NOFS);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 625) if (!be)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 626) return -ENOMEM;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 627)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 628) memcpy(&id, p, NFS4_DEVICEID4_SIZE);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 629) p += XDR_QUADLEN(NFS4_DEVICEID4_SIZE);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 630)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 631) be->be_device = bl_find_get_deviceid(NFS_SERVER(lo->plh_inode), &id,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 632) lo->plh_lc_cred, gfp_mask);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 633) if (IS_ERR(be->be_device)) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 634) error = PTR_ERR(be->be_device);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 635) goto out_free_be;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 636) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 637)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 638) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 639) * The next three values are read in as bytes, but stored in the
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 640) * extent structure in 512-byte granularity.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 641) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 642) error = -EIO;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 643) if (decode_sector_number(&p, &be->be_f_offset) < 0)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 644) goto out_put_deviceid;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 645) if (decode_sector_number(&p, &be->be_length) < 0)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 646) goto out_put_deviceid;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 647) if (decode_sector_number(&p, &be->be_v_offset) < 0)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 648) goto out_put_deviceid;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 649) be->be_state = be32_to_cpup(p++);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 650)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 651) error = verify_extent(be, lv);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 652) if (error) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 653) dprintk("%s: extent verification failed\n", __func__);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 654) goto out_put_deviceid;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 655) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 656)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 657) list_add_tail(&be->be_list, extents);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 658) return 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 659)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 660) out_put_deviceid:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 661) nfs4_put_deviceid_node(be->be_device);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 662) out_free_be:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 663) kfree(be);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 664) return error;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 665) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 666)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 667) static struct pnfs_layout_segment *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 668) bl_alloc_lseg(struct pnfs_layout_hdr *lo, struct nfs4_layoutget_res *lgr,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 669) gfp_t gfp_mask)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 670) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 671) struct layout_verification lv = {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 672) .mode = lgr->range.iomode,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 673) .start = lgr->range.offset >> SECTOR_SHIFT,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 674) .inval = lgr->range.offset >> SECTOR_SHIFT,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 675) .cowread = lgr->range.offset >> SECTOR_SHIFT,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 676) };
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 677) struct pnfs_block_layout *bl = BLK_LO2EXT(lo);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 678) struct pnfs_layout_segment *lseg;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 679) struct xdr_buf buf;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 680) struct xdr_stream xdr;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 681) struct page *scratch;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 682) int status, i;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 683) uint32_t count;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 684) __be32 *p;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 685) LIST_HEAD(extents);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 686)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 687) dprintk("---> %s\n", __func__);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 688)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 689) lseg = kzalloc(sizeof(*lseg), gfp_mask);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 690) if (!lseg)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 691) return ERR_PTR(-ENOMEM);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 692)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 693) status = -ENOMEM;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 694) scratch = alloc_page(gfp_mask);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 695) if (!scratch)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 696) goto out;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 697)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 698) xdr_init_decode_pages(&xdr, &buf,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 699) lgr->layoutp->pages, lgr->layoutp->len);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 700) xdr_set_scratch_buffer(&xdr, page_address(scratch), PAGE_SIZE);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 701)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 702) status = -EIO;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 703) p = xdr_inline_decode(&xdr, 4);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 704) if (unlikely(!p))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 705) goto out_free_scratch;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 706)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 707) count = be32_to_cpup(p++);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 708) dprintk("%s: number of extents %d\n", __func__, count);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 709)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 710) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 711) * Decode individual extents, putting them in temporary staging area
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 712) * until whole layout is decoded to make error recovery easier.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 713) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 714) for (i = 0; i < count; i++) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 715) status = bl_alloc_extent(&xdr, lo, &lv, &extents, gfp_mask);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 716) if (status)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 717) goto process_extents;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 718) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 719)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 720) if (lgr->range.offset + lgr->range.length !=
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 721) lv.start << SECTOR_SHIFT) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 722) dprintk("%s Final length mismatch\n", __func__);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 723) status = -EIO;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 724) goto process_extents;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 725) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 726)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 727) if (lv.start < lv.cowread) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 728) dprintk("%s Final uncovered COW extent\n", __func__);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 729) status = -EIO;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 730) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 731)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 732) process_extents:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 733) while (!list_empty(&extents)) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 734) struct pnfs_block_extent *be =
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 735) list_first_entry(&extents, struct pnfs_block_extent,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 736) be_list);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 737) list_del(&be->be_list);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 738)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 739) if (!status)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 740) status = ext_tree_insert(bl, be);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 741)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 742) if (status) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 743) nfs4_put_deviceid_node(be->be_device);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 744) kfree(be);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 745) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 746) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 747)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 748) out_free_scratch:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 749) __free_page(scratch);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 750) out:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 751) dprintk("%s returns %d\n", __func__, status);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 752) switch (status) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 753) case -ENODEV:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 754) /* Our extent block devices are unavailable */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 755) set_bit(NFS_LSEG_UNAVAILABLE, &lseg->pls_flags);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 756) fallthrough;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 757) case 0:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 758) return lseg;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 759) default:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 760) kfree(lseg);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 761) return ERR_PTR(status);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 762) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 763) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 764)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 765) static void
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 766) bl_return_range(struct pnfs_layout_hdr *lo,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 767) struct pnfs_layout_range *range)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 768) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 769) struct pnfs_block_layout *bl = BLK_LO2EXT(lo);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 770) sector_t offset = range->offset >> SECTOR_SHIFT, end;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 771)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 772) if (range->offset % 8) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 773) dprintk("%s: offset %lld not block size aligned\n",
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 774) __func__, range->offset);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 775) return;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 776) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 777)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 778) if (range->length != NFS4_MAX_UINT64) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 779) if (range->length % 8) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 780) dprintk("%s: length %lld not block size aligned\n",
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 781) __func__, range->length);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 782) return;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 783) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 784)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 785) end = offset + (range->length >> SECTOR_SHIFT);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 786) } else {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 787) end = round_down(NFS4_MAX_UINT64, PAGE_SIZE);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 788) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 789)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 790) ext_tree_remove(bl, range->iomode & IOMODE_RW, offset, end);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 791) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 792)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 793) static int
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 794) bl_prepare_layoutcommit(struct nfs4_layoutcommit_args *arg)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 795) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 796) return ext_tree_prepare_commit(arg);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 797) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 798)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 799) static void
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 800) bl_cleanup_layoutcommit(struct nfs4_layoutcommit_data *lcdata)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 801) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 802) ext_tree_mark_committed(&lcdata->args, lcdata->res.status);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 803) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 804)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 805) static int
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 806) bl_set_layoutdriver(struct nfs_server *server, const struct nfs_fh *fh)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 807) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 808) dprintk("%s enter\n", __func__);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 809)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 810) if (server->pnfs_blksize == 0) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 811) dprintk("%s Server did not return blksize\n", __func__);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 812) return -EINVAL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 813) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 814) if (server->pnfs_blksize > PAGE_SIZE) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 815) printk(KERN_ERR "%s: pNFS blksize %d not supported.\n",
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 816) __func__, server->pnfs_blksize);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 817) return -EINVAL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 818) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 819)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 820) return 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 821) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 822)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 823) static bool
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 824) is_aligned_req(struct nfs_pageio_descriptor *pgio,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 825) struct nfs_page *req, unsigned int alignment, bool is_write)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 826) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 827) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 828) * Always accept buffered writes, higher layers take care of the
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 829) * right alignment.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 830) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 831) if (pgio->pg_dreq == NULL)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 832) return true;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 833)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 834) if (!IS_ALIGNED(req->wb_offset, alignment))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 835) return false;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 836)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 837) if (IS_ALIGNED(req->wb_bytes, alignment))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 838) return true;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 839)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 840) if (is_write &&
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 841) (req_offset(req) + req->wb_bytes == i_size_read(pgio->pg_inode))) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 842) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 843) * If the write goes up to the inode size, just write
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 844) * the full page. Data past the inode size is
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 845) * guaranteed to be zeroed by the higher level client
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 846) * code, and this behaviour is mandated by RFC 5663
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 847) * section 2.3.2.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 848) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 849) return true;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 850) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 851)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 852) return false;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 853) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 854)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 855) static void
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 856) bl_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 857) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 858) if (!is_aligned_req(pgio, req, SECTOR_SIZE, false)) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 859) nfs_pageio_reset_read_mds(pgio);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 860) return;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 861) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 862)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 863) pnfs_generic_pg_init_read(pgio, req);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 864)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 865) if (pgio->pg_lseg &&
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 866) test_bit(NFS_LSEG_UNAVAILABLE, &pgio->pg_lseg->pls_flags)) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 867) pnfs_error_mark_layout_for_return(pgio->pg_inode, pgio->pg_lseg);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 868) pnfs_set_lo_fail(pgio->pg_lseg);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 869) nfs_pageio_reset_read_mds(pgio);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 870) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 871) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 872)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 873) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 874) * Return 0 if @req cannot be coalesced into @pgio, otherwise return the number
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 875) * of bytes (maximum @req->wb_bytes) that can be coalesced.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 876) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 877) static size_t
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 878) bl_pg_test_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 879) struct nfs_page *req)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 880) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 881) if (!is_aligned_req(pgio, req, SECTOR_SIZE, false))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 882) return 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 883) return pnfs_generic_pg_test(pgio, prev, req);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 884) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 885)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 886) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 887) * Return the number of contiguous bytes for a given inode
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 888) * starting at page frame idx.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 889) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 890) static u64 pnfs_num_cont_bytes(struct inode *inode, pgoff_t idx)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 891) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 892) struct address_space *mapping = inode->i_mapping;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 893) pgoff_t end;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 894)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 895) /* Optimize common case that writes from 0 to end of file */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 896) end = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 897) if (end != inode->i_mapping->nrpages) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 898) rcu_read_lock();
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 899) end = page_cache_next_miss(mapping, idx + 1, ULONG_MAX);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 900) rcu_read_unlock();
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 901) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 902)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 903) if (!end)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 904) return i_size_read(inode) - (idx << PAGE_SHIFT);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 905) else
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 906) return (end - idx) << PAGE_SHIFT;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 907) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 908)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 909) static void
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 910) bl_pg_init_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 911) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 912) u64 wb_size;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 913)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 914) if (!is_aligned_req(pgio, req, PAGE_SIZE, true)) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 915) nfs_pageio_reset_write_mds(pgio);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 916) return;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 917) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 918)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 919) if (pgio->pg_dreq == NULL)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 920) wb_size = pnfs_num_cont_bytes(pgio->pg_inode,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 921) req->wb_index);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 922) else
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 923) wb_size = nfs_dreq_bytes_left(pgio->pg_dreq);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 924)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 925) pnfs_generic_pg_init_write(pgio, req, wb_size);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 926)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 927) if (pgio->pg_lseg &&
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 928) test_bit(NFS_LSEG_UNAVAILABLE, &pgio->pg_lseg->pls_flags)) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 929)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 930) pnfs_error_mark_layout_for_return(pgio->pg_inode, pgio->pg_lseg);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 931) pnfs_set_lo_fail(pgio->pg_lseg);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 932) nfs_pageio_reset_write_mds(pgio);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 933) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 934) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 935)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 936) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 937) * Return 0 if @req cannot be coalesced into @pgio, otherwise return the number
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 938) * of bytes (maximum @req->wb_bytes) that can be coalesced.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 939) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 940) static size_t
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 941) bl_pg_test_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 942) struct nfs_page *req)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 943) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 944) if (!is_aligned_req(pgio, req, PAGE_SIZE, true))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 945) return 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 946) return pnfs_generic_pg_test(pgio, prev, req);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 947) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 948)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 949) static const struct nfs_pageio_ops bl_pg_read_ops = {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 950) .pg_init = bl_pg_init_read,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 951) .pg_test = bl_pg_test_read,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 952) .pg_doio = pnfs_generic_pg_readpages,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 953) .pg_cleanup = pnfs_generic_pg_cleanup,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 954) };
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 955)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 956) static const struct nfs_pageio_ops bl_pg_write_ops = {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 957) .pg_init = bl_pg_init_write,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 958) .pg_test = bl_pg_test_write,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 959) .pg_doio = pnfs_generic_pg_writepages,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 960) .pg_cleanup = pnfs_generic_pg_cleanup,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 961) };
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 962)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 963) static struct pnfs_layoutdriver_type blocklayout_type = {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 964) .id = LAYOUT_BLOCK_VOLUME,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 965) .name = "LAYOUT_BLOCK_VOLUME",
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 966) .owner = THIS_MODULE,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 967) .flags = PNFS_LAYOUTRET_ON_SETATTR |
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 968) PNFS_LAYOUTRET_ON_ERROR |
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 969) PNFS_READ_WHOLE_PAGE,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 970) .read_pagelist = bl_read_pagelist,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 971) .write_pagelist = bl_write_pagelist,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 972) .alloc_layout_hdr = bl_alloc_layout_hdr,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 973) .free_layout_hdr = bl_free_layout_hdr,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 974) .alloc_lseg = bl_alloc_lseg,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 975) .free_lseg = bl_free_lseg,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 976) .return_range = bl_return_range,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 977) .prepare_layoutcommit = bl_prepare_layoutcommit,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 978) .cleanup_layoutcommit = bl_cleanup_layoutcommit,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 979) .set_layoutdriver = bl_set_layoutdriver,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 980) .alloc_deviceid_node = bl_alloc_deviceid_node,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 981) .free_deviceid_node = bl_free_deviceid_node,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 982) .pg_read_ops = &bl_pg_read_ops,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 983) .pg_write_ops = &bl_pg_write_ops,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 984) .sync = pnfs_generic_sync,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 985) };
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 986)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 987) static struct pnfs_layoutdriver_type scsilayout_type = {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 988) .id = LAYOUT_SCSI,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 989) .name = "LAYOUT_SCSI",
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 990) .owner = THIS_MODULE,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 991) .flags = PNFS_LAYOUTRET_ON_SETATTR |
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 992) PNFS_LAYOUTRET_ON_ERROR |
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 993) PNFS_READ_WHOLE_PAGE,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 994) .read_pagelist = bl_read_pagelist,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 995) .write_pagelist = bl_write_pagelist,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 996) .alloc_layout_hdr = sl_alloc_layout_hdr,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 997) .free_layout_hdr = bl_free_layout_hdr,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 998) .alloc_lseg = bl_alloc_lseg,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 999) .free_lseg = bl_free_lseg,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1000) .return_range = bl_return_range,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1001) .prepare_layoutcommit = bl_prepare_layoutcommit,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1002) .cleanup_layoutcommit = bl_cleanup_layoutcommit,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1003) .set_layoutdriver = bl_set_layoutdriver,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1004) .alloc_deviceid_node = bl_alloc_deviceid_node,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1005) .free_deviceid_node = bl_free_deviceid_node,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1006) .pg_read_ops = &bl_pg_read_ops,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1007) .pg_write_ops = &bl_pg_write_ops,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1008) .sync = pnfs_generic_sync,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1009) };
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1010)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1011)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1012) static int __init nfs4blocklayout_init(void)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1013) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1014) int ret;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1015)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1016) dprintk("%s: NFSv4 Block Layout Driver Registering...\n", __func__);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1017)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1018) ret = bl_init_pipefs();
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1019) if (ret)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1020) goto out;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1021)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1022) ret = pnfs_register_layoutdriver(&blocklayout_type);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1023) if (ret)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1024) goto out_cleanup_pipe;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1025)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1026) ret = pnfs_register_layoutdriver(&scsilayout_type);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1027) if (ret)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1028) goto out_unregister_block;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1029) return 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1030)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1031) out_unregister_block:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1032) pnfs_unregister_layoutdriver(&blocklayout_type);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1033) out_cleanup_pipe:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1034) bl_cleanup_pipefs();
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1035) out:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1036) return ret;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1037) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1038)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1039) static void __exit nfs4blocklayout_exit(void)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1040) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1041) dprintk("%s: NFSv4 Block Layout Driver Unregistering...\n",
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1042) __func__);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1043)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1044) pnfs_unregister_layoutdriver(&scsilayout_type);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1045) pnfs_unregister_layoutdriver(&blocklayout_type);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1046) bl_cleanup_pipefs();
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1047) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1048)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1049) MODULE_ALIAS("nfs-layouttype4-3");
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1050) MODULE_ALIAS("nfs-layouttype4-5");
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1051)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1052) module_init(nfs4blocklayout_init);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1053) module_exit(nfs4blocklayout_exit);
Orange Pi5 kernel
Deprecated Linux kernel 5.10.110 for OrangePi 5/5B/5+ boards
3 Commits
0 Branches
0 Tags