F: drivers/net/ethernet/cisco/enic/
CISCO VIC LOW LATENCY NIC DRIVER
-M: Upinder Malhi <umalhi@cisco.com>
+M: Christian Benvenuti <benve@cisco.com>
+M: Dave Goodell <dgoodell@cisco.com>
S: Supported
-F: drivers/infiniband/hw/usnic
+F: drivers/infiniband/hw/usnic/
CIRRUS LOGIC EP93XX ETHERNET DRIVER
M: Hartley Sweeten <hsweeten@visionengravers.com>
W: http://www.dialog-semiconductor.com/products
S: Supported
F: Documentation/hwmon/da90??
+F: Documentation/devicetree/bindings/sound/da[79]*.txt
F: drivers/gpio/gpio-da90??.c
F: drivers/hwmon/da90??-hwmon.c
F: drivers/iio/adc/da91??-*.c
F: drivers/gpu/drm/drm_panel.c
F: drivers/gpu/drm/panel/
F: include/drm/drm_panel.h
-F: Documentation/devicetree/bindings/panel/
+F: Documentation/devicetree/bindings/display/panel/
INTEL DRM DRIVERS (excluding Poulsbo, Moorestown and derivative chipsets)
M: Daniel Vetter <daniel.vetter@intel.com>
L: dri-devel@lists.freedesktop.org
S: Supported
F: drivers/gpu/drm/fsl-dcu/
-F: Documentation/devicetree/bindings/video/fsl,dcu.txt
-F: Documentation/devicetree/bindings/panel/nec,nl4827hc19_05b.txt
+F: Documentation/devicetree/bindings/display/fsl,dcu.txt
+F: Documentation/devicetree/bindings/display/panel/nec,nl4827hc19_05b.txt
DRM DRIVERS FOR FREESCALE IMX
M: Philipp Zabel <p.zabel@pengutronix.de>
L: dri-devel@lists.freedesktop.org
S: Maintained
F: drivers/gpu/drm/imx/
-F: Documentation/devicetree/bindings/drm/imx/
+F: Documentation/devicetree/bindings/display/imx/
DRM DRIVERS FOR GMA500 (Poulsbo, Moorestown and derivative chipsets)
M: Patrik Jakobsson <patrik.r.jakobsson@gmail.com>
F: drivers/gpu/host1x/
F: include/linux/host1x.h
F: include/uapi/drm/tegra_drm.h
-F: Documentation/devicetree/bindings/gpu/nvidia,tegra20-host1x.txt
+F: Documentation/devicetree/bindings/display/tegra/nvidia,tegra20-host1x.txt
DRM DRIVERS FOR RENESAS
M: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
L: dri-devel@lists.freedesktop.org
S: Maintained
F: drivers/gpu/drm/rockchip/
-F: Documentation/devicetree/bindings/video/rockchip*
+F: Documentation/devicetree/bindings/display/rockchip*
DRM DRIVERS FOR STI
M: Benjamin Gaignard <benjamin.gaignard@linaro.org>
T: git http://git.linaro.org/people/benjamin.gaignard/kernel.git
S: Maintained
F: drivers/gpu/drm/sti
-F: Documentation/devicetree/bindings/gpu/st,stih4xx.txt
+F: Documentation/devicetree/bindings/display/st,stih4xx.txt
DSBR100 USB FM RADIO DRIVER
M: Alexey Klimov <klimov.linux@gmail.com>
T: git git://git.kernel.org/pub/scm/linux/kernel/git/chanwoo/extcon.git
S: Maintained
F: drivers/extcon/
+ F: include/linux/extcon/
+ F: include/linux/extcon.h
F: Documentation/extcon/
+ F: Documentation/devicetree/bindings/extcon/
EXYNOS DP DRIVER
M: Jingoo Han <jingoohan1@gmail.com>
T: git git://git.kernel.org/pub/scm/linux/kernel/git/plagnioj/linux-fbdev.git
S: Maintained
F: Documentation/fb/
-F: Documentation/devicetree/bindings/fb/
F: drivers/video/
F: include/video/
F: include/linux/fb.h
F: arch/metag/
F: Documentation/metag/
F: Documentation/devicetree/bindings/metag/
+F: Documentation/devicetree/bindings/interrupt-controller/img,*
F: drivers/clocksource/metag_generic.c
F: drivers/irqchip/irq-metag.c
F: drivers/irqchip/irq-metag-ext.c
F: Documentation/filesystems/nilfs2.txt
F: fs/nilfs2/
F: include/linux/nilfs2_fs.h
+ F: include/trace/events/nilfs2.h
NINJA SCSI-3 / NINJA SCSI-32Bi (16bit/CardBus) PCMCIA SCSI HOST ADAPTER DRIVER
M: YOKOTA Hiroshi <yokota@netlab.is.tsukuba.ac.jp>
F: arch/x86/pci/
F: arch/x86/kernel/quirks.c
+PCI DRIVER FOR ALTERA PCIE IP
+M: Ley Foon Tan <lftan@altera.com>
+L: rfi@lists.rocketboards.org (moderated for non-subscribers)
+L: linux-pci@vger.kernel.org
+S: Supported
+F: Documentation/devicetree/bindings/pci/altera-pcie.txt
+F: drivers/pci/host/pcie-altera.c
+
PCI DRIVER FOR ARM VERSATILE PLATFORM
M: Rob Herring <robh@kernel.org>
L: linux-pci@vger.kernel.org
S: Maintained
F: drivers/pci/host/*spear*
+PCI MSI DRIVER FOR ALTERA MSI IP
+M: Ley Foon Tan <lftan@altera.com>
+L: rfi@lists.rocketboards.org (moderated for non-subscribers)
+L: linux-pci@vger.kernel.org
+S: Supported
+F: Documentation/devicetree/bindings/pci/altera-pcie-msi.txt
+F: drivers/pci/host/pcie-altera-msi.c
+
PCI MSI DRIVER FOR APPLIEDMICRO XGENE
M: Duc Dang <dhdang@apm.com>
L: linux-pci@vger.kernel.org
F: Documentation/devicetree/bindings/pci/xgene-pci-msi.txt
F: drivers/pci/host/pci-xgene-msi.c
+PCIE DRIVER FOR HISILICON
+M: Zhou Wang <wangzhou1@hisilicon.com>
+L: linux-pci@vger.kernel.org
+S: Maintained
+F: Documentation/devicetree/bindings/pci/hisilicon-pcie.txt
+F: drivers/pci/host/pcie-hisi.c
+
PCMCIA SUBSYSTEM
P: Linux PCMCIA Team
L: linux-pcmcia@lists.infradead.org
M: Hans de Goede <hdegoede@redhat.com>
L: linux-fbdev@vger.kernel.org
S: Maintained
-F: Documentation/devicetree/bindings/video/simple-framebuffer.txt
+F: Documentation/devicetree/bindings/display/simple-framebuffer.txt
F: drivers/video/fbdev/simplefb.c
F: include/linux/platform_data/simplefb.h
S: Supported
F: arch/arc/
F: Documentation/devicetree/bindings/arc/*
+F: Documentation/devicetree/bindings/interrupt-controller/snps,arc*
F: drivers/tty/serial/arc_uart.c
T: git git://git.kernel.org/pub/scm/linux/kernel/git/vgupta/arc.git
F: Documentation/fb/uvesafb.txt
F: drivers/video/fbdev/uvesafb.*
+VF610 NAND DRIVER
+M: Stefan Agner <stefan@agner.ch>
+L: linux-mtd@lists.infradead.org
+S: Supported
+F: drivers/mtd/nand/vf610_nfc.c
+
VFAT/FAT/MSDOS FILESYSTEM
M: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp>
S: Maintained
F: drivers/media/v4l2-core/videobuf2-*
F: include/media/videobuf2-*
+VIRTUAL SERIO DEVICE DRIVER
+M: Stephen Chandler Paul <thatslyude@gmail.com>
+S: Maintained
+F: drivers/input/serio/userio.c
+F: include/uapi/linux/userio.h
+
VIRTIO CONSOLE DRIVER
M: Amit Shah <amit.shah@redhat.com>
L: virtualization@lists.linux-foundation.org
#include <linux/string.h>
#include <linux/drbd.h>
#include <linux/slab.h>
-#include <asm/kmap_types.h>
+#include <linux/highmem.h>
#include "drbd_int.h"
bm_set_page_unchanged(b->bm_pages[page_nr]);
if (ctx->flags & BM_AIO_COPY_PAGES) {
- page = mempool_alloc(drbd_md_io_page_pool, __GFP_HIGHMEM|__GFP_WAIT);
+ page = mempool_alloc(drbd_md_io_page_pool, __GFP_HIGHMEM|__GFP_RECLAIM);
copy_highpage(page, b->bm_pages[page_nr]);
bm_store_page_idx(page, page_nr);
} else
int ret = 0;
rq = blk_get_request(q, (cgc->data_direction == CGC_DATA_WRITE) ?
- WRITE : READ, __GFP_WAIT);
+ WRITE : READ, __GFP_RECLAIM);
if (IS_ERR(rq))
return PTR_ERR(rq);
blk_rq_set_block_pc(rq);
if (cgc->buflen) {
ret = blk_rq_map_kern(q, rq, cgc->buffer, cgc->buflen,
- __GFP_WAIT);
+ __GFP_RECLAIM);
if (ret)
goto out;
}
out_mem2:
put_disk(disk);
out_mem:
- if (pd->rb_pool)
- mempool_destroy(pd->rb_pool);
+ mempool_destroy(pd->rb_pool);
kfree(pd);
out_mutex:
mutex_unlock(&ctl_mutex);
force_grh = rdma_cap_eth_ah(device, port_num);
if (rec->hop_limit > 1 || force_grh) {
+ struct net_device *ndev = ib_get_ndev_from_path(rec);
+
ah_attr->ah_flags = IB_AH_GRH;
ah_attr->grh.dgid = rec->dgid;
- ret = ib_find_cached_gid(device, &rec->sgid, &port_num,
+ ret = ib_find_cached_gid(device, &rec->sgid, ndev, &port_num,
&gid_index);
- if (ret)
+ if (ret) {
+ if (ndev)
+ dev_put(ndev);
return ret;
+ }
ah_attr->grh.sgid_index = gid_index;
ah_attr->grh.flow_label = be32_to_cpu(rec->flow_label);
ah_attr->grh.hop_limit = rec->hop_limit;
ah_attr->grh.traffic_class = rec->traffic_class;
+ if (ndev)
+ dev_put(ndev);
}
if (force_grh) {
memcpy(ah_attr->dmac, rec->dmac, ETH_ALEN);
- ah_attr->vlan_id = rec->vlan_id;
- } else {
- ah_attr->vlan_id = 0xffff;
}
-
return 0;
}
EXPORT_SYMBOL(ib_init_ah_from_path);
static int send_mad(struct ib_sa_query *query, int timeout_ms, gfp_t gfp_mask)
{
- bool preload = !!(gfp_mask & __GFP_WAIT);
+ bool preload = gfpflags_allow_blocking(gfp_mask);
unsigned long flags;
int ret, id;
ib_unpack(path_rec_table, ARRAY_SIZE(path_rec_table),
mad->data, &rec);
- rec.vlan_id = 0xffff;
+ rec.net = NULL;
+ rec.ifindex = 0;
memset(rec.dmac, 0, ETH_ALEN);
- memset(rec.smac, 0, ETH_ALEN);
query->callback(status, &rec, query->context);
} else
query->callback(status, NULL, query->context);
struct mtd_notifier *not;
int i, error;
+ /*
+ * May occur, for instance, on buggy drivers which call
+ * mtd_device_parse_register() multiple times on the same master MTD,
+ * especially with CONFIG_MTD_PARTITIONED_MASTER=y.
+ */
+ if (WARN_ONCE(mtd->backing_dev_info, "MTD already registered\n"))
+ return -EEXIST;
+
mtd->backing_dev_info = &mtd_bdi;
BUG_ON(mtd->writesize == 0);
mtd->erasesize_mask = (1 << mtd->erasesize_shift) - 1;
mtd->writesize_mask = (1 << mtd->writesize_shift) - 1;
+ if (mtd->dev.parent) {
+ if (!mtd->owner && mtd->dev.parent->driver)
+ mtd->owner = mtd->dev.parent->driver->owner;
+ if (!mtd->name)
+ mtd->name = dev_name(mtd->dev.parent);
+ } else {
+ pr_debug("mtd device won't show a device symlink in sysfs\n");
+ }
+
/* Some chips always power up locked. Unlock them now */
if ((mtd->flags & MTD_WRITEABLE) && (mtd->flags & MTD_POWERUP_LOCK)) {
error = mtd_unlock(mtd, 0, mtd->size);
}
/* Caller should have set dev.parent to match the
- * physical device.
+ * physical device, if appropriate.
*/
mtd->dev.type = &mtd_devtype;
mtd->dev.class = &mtd_class;
else
ret = nr_parts;
}
+ /* Didn't come up with either parsed OR fallback partitions */
+ if (ret < 0) {
+ pr_info("mtd: failed to find partitions; one or more parsers reports errors (%d)\n",
+ ret);
+ /* Don't abort on errors; we can still use unpartitioned MTD */
+ ret = 0;
+ }
- if (ret >= 0)
- ret = mtd_add_device_partitions(mtd, real_parts, ret);
+ ret = mtd_add_device_partitions(mtd, real_parts, ret);
+ if (ret)
+ goto out;
/*
* FIXME: some drivers unfortunately call this function more than once.
* does cause problems with parse_mtd_partitions() above (e.g.,
* cmdlineparts will register partitions more than once).
*/
+ WARN_ONCE(mtd->_reboot && mtd->reboot_notifier.notifier_call,
+ "MTD already registered\n");
if (mtd->_reboot && !mtd->reboot_notifier.notifier_call) {
mtd->reboot_notifier.notifier_call = mtd_reboot_notifier;
register_reboot_notifier(&mtd->reboot_notifier);
}
+out:
kfree(real_parts);
return ret;
}
*/
void *mtd_kmalloc_up_to(const struct mtd_info *mtd, size_t *size)
{
- gfp_t flags = __GFP_NOWARN | __GFP_WAIT |
- __GFP_NORETRY | __GFP_NO_KSWAPD;
+ gfp_t flags = __GFP_NOWARN | __GFP_DIRECT_RECLAIM | __GFP_NORETRY;
size_t min_alloc = max_t(size_t, mtd->writesize, PAGE_SIZE);
void *kbuf;
remove_proc_entry("mtd", NULL);
class_unregister(&mtd_class);
bdi_destroy(&mtd_bdi);
+ idr_destroy(&mtd_idr);
}
module_init(init_mtd);
#include <linux/types.h>
#include <linux/pr.h>
#include <scsi/sg.h>
-#include <asm-generic/io-64-nonatomic-lo-hi.h>
+#include <linux/io-64-nonatomic-lo-hi.h>
#include <asm/unaligned.h>
#include <uapi/linux/nvme_ioctl.h>
req->special = (void *)0;
if (buffer && bufflen) {
- ret = blk_rq_map_kern(q, req, buffer, bufflen, __GFP_WAIT);
+ ret = blk_rq_map_kern(q, req, buffer, bufflen,
+ __GFP_DIRECT_RECLAIM);
if (ret)
goto out;
} else if (ubuffer && bufflen) {
- ret = blk_rq_map_user(q, req, NULL, ubuffer, bufflen, __GFP_WAIT);
+ ret = blk_rq_map_user(q, req, NULL, ubuffer, bufflen,
+ __GFP_DIRECT_RECLAIM);
if (ret)
goto out;
bio = req->bio;
goto next;
}
- page = __page_cache_alloc(mapping_gfp_mask(mapping) &
- ~__GFP_FS);
+ page = __page_cache_alloc(mapping_gfp_constraint(mapping,
+ ~__GFP_FS));
if (!page)
break;
- if (add_to_page_cache_lru(page, mapping, pg_index,
- GFP_NOFS)) {
+ if (add_to_page_cache_lru(page, mapping, pg_index, GFP_NOFS)) {
page_cache_release(page);
goto next;
}
return ret;
}
-static struct list_head comp_idle_workspace[BTRFS_COMPRESS_TYPES];
-static spinlock_t comp_workspace_lock[BTRFS_COMPRESS_TYPES];
-static int comp_num_workspace[BTRFS_COMPRESS_TYPES];
-static atomic_t comp_alloc_workspace[BTRFS_COMPRESS_TYPES];
-static wait_queue_head_t comp_workspace_wait[BTRFS_COMPRESS_TYPES];
+static struct {
+ struct list_head idle_ws;
+ spinlock_t ws_lock;
+ int num_ws;
+ atomic_t alloc_ws;
+ wait_queue_head_t ws_wait;
+} btrfs_comp_ws[BTRFS_COMPRESS_TYPES];
static const struct btrfs_compress_op * const btrfs_compress_op[] = {
&btrfs_zlib_compress,
int i;
for (i = 0; i < BTRFS_COMPRESS_TYPES; i++) {
- INIT_LIST_HEAD(&comp_idle_workspace[i]);
- spin_lock_init(&comp_workspace_lock[i]);
- atomic_set(&comp_alloc_workspace[i], 0);
- init_waitqueue_head(&comp_workspace_wait[i]);
+ INIT_LIST_HEAD(&btrfs_comp_ws[i].idle_ws);
+ spin_lock_init(&btrfs_comp_ws[i].ws_lock);
+ atomic_set(&btrfs_comp_ws[i].alloc_ws, 0);
+ init_waitqueue_head(&btrfs_comp_ws[i].ws_wait);
}
}
int cpus = num_online_cpus();
int idx = type - 1;
- struct list_head *idle_workspace = &comp_idle_workspace[idx];
- spinlock_t *workspace_lock = &comp_workspace_lock[idx];
- atomic_t *alloc_workspace = &comp_alloc_workspace[idx];
- wait_queue_head_t *workspace_wait = &comp_workspace_wait[idx];
- int *num_workspace = &comp_num_workspace[idx];
+ struct list_head *idle_ws = &btrfs_comp_ws[idx].idle_ws;
+ spinlock_t *ws_lock = &btrfs_comp_ws[idx].ws_lock;
+ atomic_t *alloc_ws = &btrfs_comp_ws[idx].alloc_ws;
+ wait_queue_head_t *ws_wait = &btrfs_comp_ws[idx].ws_wait;
+ int *num_ws = &btrfs_comp_ws[idx].num_ws;
again:
- spin_lock(workspace_lock);
- if (!list_empty(idle_workspace)) {
- workspace = idle_workspace->next;
+ spin_lock(ws_lock);
+ if (!list_empty(idle_ws)) {
+ workspace = idle_ws->next;
list_del(workspace);
- (*num_workspace)--;
- spin_unlock(workspace_lock);
+ (*num_ws)--;
+ spin_unlock(ws_lock);
return workspace;
}
- if (atomic_read(alloc_workspace) > cpus) {
+ if (atomic_read(alloc_ws) > cpus) {
DEFINE_WAIT(wait);
- spin_unlock(workspace_lock);
- prepare_to_wait(workspace_wait, &wait, TASK_UNINTERRUPTIBLE);
- if (atomic_read(alloc_workspace) > cpus && !*num_workspace)
+ spin_unlock(ws_lock);
+ prepare_to_wait(ws_wait, &wait, TASK_UNINTERRUPTIBLE);
+ if (atomic_read(alloc_ws) > cpus && !*num_ws)
schedule();
- finish_wait(workspace_wait, &wait);
+ finish_wait(ws_wait, &wait);
goto again;
}
- atomic_inc(alloc_workspace);
- spin_unlock(workspace_lock);
+ atomic_inc(alloc_ws);
+ spin_unlock(ws_lock);
workspace = btrfs_compress_op[idx]->alloc_workspace();
if (IS_ERR(workspace)) {
- atomic_dec(alloc_workspace);
- wake_up(workspace_wait);
+ atomic_dec(alloc_ws);
+ wake_up(ws_wait);
}
return workspace;
}
static void free_workspace(int type, struct list_head *workspace)
{
int idx = type - 1;
- struct list_head *idle_workspace = &comp_idle_workspace[idx];
- spinlock_t *workspace_lock = &comp_workspace_lock[idx];
- atomic_t *alloc_workspace = &comp_alloc_workspace[idx];
- wait_queue_head_t *workspace_wait = &comp_workspace_wait[idx];
- int *num_workspace = &comp_num_workspace[idx];
-
- spin_lock(workspace_lock);
- if (*num_workspace < num_online_cpus()) {
- list_add(workspace, idle_workspace);
- (*num_workspace)++;
- spin_unlock(workspace_lock);
+ struct list_head *idle_ws = &btrfs_comp_ws[idx].idle_ws;
+ spinlock_t *ws_lock = &btrfs_comp_ws[idx].ws_lock;
+ atomic_t *alloc_ws = &btrfs_comp_ws[idx].alloc_ws;
+ wait_queue_head_t *ws_wait = &btrfs_comp_ws[idx].ws_wait;
+ int *num_ws = &btrfs_comp_ws[idx].num_ws;
+
+ spin_lock(ws_lock);
+ if (*num_ws < num_online_cpus()) {
+ list_add(workspace, idle_ws);
+ (*num_ws)++;
+ spin_unlock(ws_lock);
goto wake;
}
- spin_unlock(workspace_lock);
+ spin_unlock(ws_lock);
btrfs_compress_op[idx]->free_workspace(workspace);
- atomic_dec(alloc_workspace);
+ atomic_dec(alloc_ws);
wake:
+ /*
+ * Make sure counter is updated before we wake up waiters.
+ */
smp_mb();
- if (waitqueue_active(workspace_wait))
- wake_up(workspace_wait);
+ if (waitqueue_active(ws_wait))
+ wake_up(ws_wait);
}
/*
int i;
for (i = 0; i < BTRFS_COMPRESS_TYPES; i++) {
- while (!list_empty(&comp_idle_workspace[i])) {
- workspace = comp_idle_workspace[i].next;
+ while (!list_empty(&btrfs_comp_ws[i].idle_ws)) {
+ workspace = btrfs_comp_ws[i].idle_ws.next;
list_del(workspace);
btrfs_compress_op[i]->free_workspace(workspace);
- atomic_dec(&comp_alloc_workspace[i]);
+ atomic_dec(&btrfs_comp_ws[i].alloc_ws);
}
}
}
*/
__le64 profiles;
- /* usage filter */
- __le64 usage;
+ /*
+ * usage filter
+ * BTRFS_BALANCE_ARGS_USAGE with a single value means '0..N'
+ * BTRFS_BALANCE_ARGS_USAGE_RANGE - range syntax, min..max
+ */
+ union {
+ __le64 usage;
+ struct {
+ __le32 usage_min;
+ __le32 usage_max;
+ };
+ };
/* devid filter */
__le64 devid;
/* BTRFS_BALANCE_ARGS_* */
__le64 flags;
- /* BTRFS_BALANCE_ARGS_LIMIT value */
- __le64 limit;
+ /*
+ * BTRFS_BALANCE_ARGS_LIMIT with value 'limit'
+ * BTRFS_BALANCE_ARGS_LIMIT_RANGE - the extend version can use minimum
+ * and maximum
+ */
+ union {
+ __le64 limit;
+ struct {
+ __le32 limit_min;
+ __le32 limit_max;
+ };
+ };
- __le64 unused[7];
+ /*
+ * Process chunks that cross stripes_min..stripes_max devices,
+ * BTRFS_BALANCE_ARGS_STRIPES_RANGE
+ */
+ __le32 stripes_min;
+ __le32 stripes_max;
+
+ __le64 unused[6];
} __attribute__ ((__packed__));
/*
delalloc/allocations */
u64 bytes_readonly; /* total bytes that are read only */
+ u64 max_extent_size; /* This will hold the maximum extent size of
+ the space info if we had an ENOSPC in the
+ allocator. */
+
unsigned int full:1; /* indicates that we cannot allocate any more
chunks for this space */
unsigned int chunk_alloc:1; /* set if we are allocating a chunk */
/* first extent starting offset */
u64 window_start;
+ /* We did a full search and couldn't create a cluster */
+ bool fragmented;
+
struct btrfs_block_group_cache *block_group;
/*
* when a cluster is allocated from a block group, we put the
int send_in_progress;
struct btrfs_subvolume_writers *subv_writers;
atomic_t will_be_snapshoted;
+
+ /* For qgroup metadata space reserve */
+ atomic_t qgroup_meta_rsv;
};
struct btrfs_ioctl_defrag_range_args {
#define BTRFS_MOUNT_CHECK_INTEGRITY_INCLUDING_EXTENT_DATA (1 << 21)
#define BTRFS_MOUNT_PANIC_ON_FATAL_ERROR (1 << 22)
#define BTRFS_MOUNT_RESCAN_UUID_TREE (1 << 23)
+#define BTRFS_MOUNT_FRAGMENT_DATA (1 << 24)
+#define BTRFS_MOUNT_FRAGMENT_METADATA (1 << 25)
#define BTRFS_DEFAULT_COMMIT_INTERVAL (30)
#define BTRFS_DEFAULT_MAX_INLINE (8192)
btrfs_clear_opt(root->fs_info->mount_opt, opt); \
}
+#ifdef CONFIG_BTRFS_DEBUG
+static inline int
+btrfs_should_fragment_free_space(struct btrfs_root *root,
+ struct btrfs_block_group_cache *block_group)
+{
+ return (btrfs_test_opt(root, FRAGMENT_METADATA) &&
+ block_group->flags & BTRFS_BLOCK_GROUP_METADATA) ||
+ (btrfs_test_opt(root, FRAGMENT_DATA) &&
+ block_group->flags & BTRFS_BLOCK_GROUP_DATA);
+}
+#endif
+
/*
* Requests for changes that need to be done during transaction commit.
*
static inline gfp_t btrfs_alloc_write_mask(struct address_space *mapping)
{
- return mapping_gfp_mask(mapping) & ~__GFP_FS;
+ return mapping_gfp_constraint(mapping, ~__GFP_FS);
}
/* extent-tree.c */
int btrfs_alloc_reserved_file_extent(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
u64 root_objectid, u64 owner,
- u64 offset, struct btrfs_key *ins);
+ u64 offset, u64 ram_bytes,
+ struct btrfs_key *ins);
int btrfs_alloc_logged_file_extent(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
u64 root_objectid, u64 owner, u64 offset,
int btrfs_free_extent(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
u64 bytenr, u64 num_bytes, u64 parent, u64 root_objectid,
- u64 owner, u64 offset, int no_quota);
+ u64 owner, u64 offset);
int btrfs_free_reserved_extent(struct btrfs_root *root, u64 start, u64 len,
int delalloc);
int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
u64 bytenr, u64 num_bytes, u64 parent,
- u64 root_objectid, u64 owner, u64 offset, int no_quota);
+ u64 root_objectid, u64 owner, u64 offset);
int btrfs_start_dirty_block_groups(struct btrfs_trans_handle *trans,
struct btrfs_root *root);
BTRFS_RESERVE_FLUSH_ALL,
};
-int btrfs_check_data_free_space(struct inode *inode, u64 bytes, u64 write_bytes);
-void btrfs_free_reserved_data_space(struct inode *inode, u64 bytes);
+int btrfs_check_data_free_space(struct inode *inode, u64 start, u64 len);
+int btrfs_alloc_data_chunk_ondemand(struct inode *inode, u64 bytes);
+void btrfs_free_reserved_data_space(struct inode *inode, u64 start, u64 len);
+void btrfs_free_reserved_data_space_noquota(struct inode *inode, u64 start,
+ u64 len);
void btrfs_trans_release_metadata(struct btrfs_trans_handle *trans,
struct btrfs_root *root);
void btrfs_trans_release_chunk_metadata(struct btrfs_trans_handle *trans);
u64 qgroup_reserved);
int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes);
void btrfs_delalloc_release_metadata(struct inode *inode, u64 num_bytes);
-int btrfs_delalloc_reserve_space(struct inode *inode, u64 num_bytes);
-void btrfs_delalloc_release_space(struct inode *inode, u64 num_bytes);
+int btrfs_delalloc_reserve_space(struct inode *inode, u64 start, u64 len);
+void btrfs_delalloc_release_space(struct inode *inode, u64 start, u64 len);
void btrfs_init_block_rsv(struct btrfs_block_rsv *rsv, unsigned short type);
struct btrfs_block_rsv *btrfs_alloc_block_rsv(struct btrfs_root *root,
unsigned short type);
/* sysfs.c */
int btrfs_init_sysfs(void);
void btrfs_exit_sysfs(void);
-int btrfs_sysfs_add_one(struct btrfs_fs_info *fs_info);
-void btrfs_sysfs_remove_one(struct btrfs_fs_info *fs_info);
+int btrfs_sysfs_add_mounted(struct btrfs_fs_info *fs_info);
+void btrfs_sysfs_remove_mounted(struct btrfs_fs_info *fs_info);
/* xattr.c */
ssize_t btrfs_listxattr(struct dentry *dentry, char *buffer, size_t size);
#define btrfs_info(fs_info, fmt, args...) \
btrfs_printk(fs_info, KERN_INFO fmt, ##args)
+/*
+ * Wrappers that use printk_in_rcu
+ */
+#define btrfs_emerg_in_rcu(fs_info, fmt, args...) \
+ btrfs_printk_in_rcu(fs_info, KERN_EMERG fmt, ##args)
+#define btrfs_alert_in_rcu(fs_info, fmt, args...) \
+ btrfs_printk_in_rcu(fs_info, KERN_ALERT fmt, ##args)
+#define btrfs_crit_in_rcu(fs_info, fmt, args...) \
+ btrfs_printk_in_rcu(fs_info, KERN_CRIT fmt, ##args)
+#define btrfs_err_in_rcu(fs_info, fmt, args...) \
+ btrfs_printk_in_rcu(fs_info, KERN_ERR fmt, ##args)
+#define btrfs_warn_in_rcu(fs_info, fmt, args...) \
+ btrfs_printk_in_rcu(fs_info, KERN_WARNING fmt, ##args)
+#define btrfs_notice_in_rcu(fs_info, fmt, args...) \
+ btrfs_printk_in_rcu(fs_info, KERN_NOTICE fmt, ##args)
+#define btrfs_info_in_rcu(fs_info, fmt, args...) \
+ btrfs_printk_in_rcu(fs_info, KERN_INFO fmt, ##args)
+
+/*
+ * Wrappers that use a ratelimited printk_in_rcu
+ */
+#define btrfs_emerg_rl_in_rcu(fs_info, fmt, args...) \
+ btrfs_printk_rl_in_rcu(fs_info, KERN_EMERG fmt, ##args)
+#define btrfs_alert_rl_in_rcu(fs_info, fmt, args...) \
+ btrfs_printk_rl_in_rcu(fs_info, KERN_ALERT fmt, ##args)
+#define btrfs_crit_rl_in_rcu(fs_info, fmt, args...) \
+ btrfs_printk_rl_in_rcu(fs_info, KERN_CRIT fmt, ##args)
+#define btrfs_err_rl_in_rcu(fs_info, fmt, args...) \
+ btrfs_printk_rl_in_rcu(fs_info, KERN_ERR fmt, ##args)
+#define btrfs_warn_rl_in_rcu(fs_info, fmt, args...) \
+ btrfs_printk_rl_in_rcu(fs_info, KERN_WARNING fmt, ##args)
+#define btrfs_notice_rl_in_rcu(fs_info, fmt, args...) \
+ btrfs_printk_rl_in_rcu(fs_info, KERN_NOTICE fmt, ##args)
+#define btrfs_info_rl_in_rcu(fs_info, fmt, args...) \
+ btrfs_printk_rl_in_rcu(fs_info, KERN_INFO fmt, ##args)
+
+/*
+ * Wrappers that use a ratelimited printk
+ */
+#define btrfs_emerg_rl(fs_info, fmt, args...) \
+ btrfs_printk_ratelimited(fs_info, KERN_EMERG fmt, ##args)
+#define btrfs_alert_rl(fs_info, fmt, args...) \
+ btrfs_printk_ratelimited(fs_info, KERN_ALERT fmt, ##args)
+#define btrfs_crit_rl(fs_info, fmt, args...) \
+ btrfs_printk_ratelimited(fs_info, KERN_CRIT fmt, ##args)
+#define btrfs_err_rl(fs_info, fmt, args...) \
+ btrfs_printk_ratelimited(fs_info, KERN_ERR fmt, ##args)
+#define btrfs_warn_rl(fs_info, fmt, args...) \
+ btrfs_printk_ratelimited(fs_info, KERN_WARNING fmt, ##args)
+#define btrfs_notice_rl(fs_info, fmt, args...) \
+ btrfs_printk_ratelimited(fs_info, KERN_NOTICE fmt, ##args)
+#define btrfs_info_rl(fs_info, fmt, args...) \
+ btrfs_printk_ratelimited(fs_info, KERN_INFO fmt, ##args)
#ifdef DEBUG
#define btrfs_debug(fs_info, fmt, args...) \
btrfs_printk(fs_info, KERN_DEBUG fmt, ##args)
+#define btrfs_debug_in_rcu(fs_info, fmt, args...) \
+ btrfs_printk_in_rcu(fs_info, KERN_DEBUG fmt, ##args)
+#define btrfs_debug_rl_in_rcu(fs_info, fmt, args...) \
+ btrfs_printk_rl_in_rcu(fs_info, KERN_DEBUG fmt, ##args)
+#define btrfs_debug_rl(fs_info, fmt, args...) \
+ btrfs_printk_ratelimited(fs_info, KERN_DEBUG fmt, ##args)
#else
#define btrfs_debug(fs_info, fmt, args...) \
no_printk(KERN_DEBUG fmt, ##args)
+#define btrfs_debug_in_rcu(fs_info, fmt, args...) \
+ no_printk(KERN_DEBUG fmt, ##args)
+#define btrfs_debug_rl_in_rcu(fs_info, fmt, args...) \
+ no_printk(KERN_DEBUG fmt, ##args)
+#define btrfs_debug_rl(fs_info, fmt, args...) \
+ no_printk(KERN_DEBUG fmt, ##args)
#endif
+#define btrfs_printk_in_rcu(fs_info, fmt, args...) \
+do { \
+ rcu_read_lock(); \
+ btrfs_printk(fs_info, fmt, ##args); \
+ rcu_read_unlock(); \
+} while (0)
+
+#define btrfs_printk_ratelimited(fs_info, fmt, args...) \
+do { \
+ static DEFINE_RATELIMIT_STATE(_rs, \
+ DEFAULT_RATELIMIT_INTERVAL, \
+ DEFAULT_RATELIMIT_BURST); \
+ if (__ratelimit(&_rs)) \
+ btrfs_printk(fs_info, fmt, ##args); \
+} while (0)
+
+#define btrfs_printk_rl_in_rcu(fs_info, fmt, args...) \
+do { \
+ rcu_read_lock(); \
+ btrfs_printk_ratelimited(fs_info, fmt, ##args); \
+ rcu_read_unlock(); \
+} while (0)
+
#ifdef CONFIG_BTRFS_ASSERT
__cold
__LINE__, (errno)); \
} while (0)
-#define btrfs_std_error(fs_info, errno) \
-do { \
- if ((errno)) \
- __btrfs_std_error((fs_info), __func__, \
- __LINE__, (errno), NULL); \
-} while (0)
-
-#define btrfs_error(fs_info, errno, fmt, args...) \
+#define btrfs_std_error(fs_info, errno, fmt, args...) \
do { \
__btrfs_std_error((fs_info), __func__, __LINE__, \
(errno), fmt, ##args); \
memcpy(&found, result, csum_size);
read_extent_buffer(buf, &val, 0, csum_size);
- printk_ratelimited(KERN_WARNING
- "BTRFS: %s checksum verify failed on %llu wanted %X found %X "
- "level %d\n",
+ btrfs_warn_rl(fs_info,
+ "%s checksum verify failed on %llu wanted %X found %X "
+ "level %d",
fs_info->sb->s_id, buf->start,
val, found, btrfs_header_level(buf));
if (result != (char *)&inline_result)
ret = 0;
goto out;
}
- printk_ratelimited(KERN_ERR
- "BTRFS (device %s): parent transid verify failed on %llu wanted %llu found %llu\n",
- eb->fs_info->sb->s_id, eb->start,
+ btrfs_err_rl(eb->fs_info,
+ "parent transid verify failed on %llu wanted %llu found %llu",
+ eb->start,
parent_transid, btrfs_header_generation(eb));
ret = 1;
found_start = btrfs_header_bytenr(eb);
if (found_start != eb->start) {
- printk_ratelimited(KERN_ERR "BTRFS (device %s): bad tree block start "
- "%llu %llu\n",
- eb->fs_info->sb->s_id, found_start, eb->start);
+ btrfs_err_rl(eb->fs_info, "bad tree block start %llu %llu",
+ found_start, eb->start);
ret = -EIO;
goto err;
}
if (check_tree_block_fsid(root->fs_info, eb)) {
- printk_ratelimited(KERN_ERR "BTRFS (device %s): bad fsid on block %llu\n",
- eb->fs_info->sb->s_id, eb->start);
+ btrfs_err_rl(eb->fs_info, "bad fsid on block %llu",
+ eb->start);
ret = -EIO;
goto err;
}
limit = btrfs_async_submit_limit(fs_info);
limit = limit * 2 / 3;
+ /*
+ * atomic_dec_return implies a barrier for waitqueue_active
+ */
if (atomic_dec_return(&fs_info->nr_async_submits) < limit &&
waitqueue_active(&fs_info->async_submit_wait))
wake_up(&fs_info->async_submit_wait);
atomic_set(&root->orphan_inodes, 0);
atomic_set(&root->refs, 1);
atomic_set(&root->will_be_snapshoted, 0);
+ atomic_set(&root->qgroup_meta_rsv, 0);
root->log_transid = 0;
root->log_transid_committed = -1;
root->last_log_commit = 0;
int again;
struct btrfs_trans_handle *trans;
+ set_freezable();
do {
again = 0;
u64 bytenr = btrfs_super_log_root(disk_super);
if (fs_devices->rw_devices == 0) {
- printk(KERN_WARNING "BTRFS: log replay required "
- "on RO media\n");
+ btrfs_warn(fs_info, "log replay required on RO media");
return -EIO;
}
log_tree_root->node = read_tree_block(tree_root, bytenr,
fs_info->generation + 1);
if (IS_ERR(log_tree_root->node)) {
- printk(KERN_ERR "BTRFS: failed to read log tree\n");
+ btrfs_warn(fs_info, "failed to read log tree");
ret = PTR_ERR(log_tree_root->node);
kfree(log_tree_root);
return ret;
} else if (!extent_buffer_uptodate(log_tree_root->node)) {
- printk(KERN_ERR "BTRFS: failed to read log tree\n");
+ btrfs_err(fs_info, "failed to read log tree");
free_extent_buffer(log_tree_root->node);
kfree(log_tree_root);
return -EIO;
/* returns with log_tree_root freed on success */
ret = btrfs_recover_log_trees(log_tree_root);
if (ret) {
- btrfs_error(tree_root->fs_info, ret,
+ btrfs_std_error(tree_root->fs_info, ret,
"Failed to recover log tree");
free_extent_buffer(log_tree_root->node);
kfree(log_tree_root);
fs_info->commit_interval = BTRFS_DEFAULT_COMMIT_INTERVAL;
fs_info->avg_delayed_ref_runtime = NSEC_PER_SEC >> 6; /* div by 64 */
/* readahead state */
- INIT_RADIX_TREE(&fs_info->reada_tree, GFP_NOFS & ~__GFP_WAIT);
+ INIT_RADIX_TREE(&fs_info->reada_tree, GFP_NOFS & ~__GFP_DIRECT_RECLAIM);
spin_lock_init(&fs_info->reada_lock);
fs_info->thread_pool_size = min_t(unsigned long,
* Read super block and check the signature bytes only
*/
bh = btrfs_read_dev_super(fs_devices->latest_bdev);
- if (!bh) {
- err = -EINVAL;
+ if (IS_ERR(bh)) {
+ err = PTR_ERR(bh);
goto fail_alloc;
}
goto fail_fsdev_sysfs;
}
- ret = btrfs_sysfs_add_one(fs_info);
+ ret = btrfs_sysfs_add_mounted(fs_info);
if (ret) {
pr_err("BTRFS: failed to init sysfs interface: %d\n", ret);
goto fail_fsdev_sysfs;
filemap_write_and_wait(fs_info->btree_inode->i_mapping);
fail_sysfs:
- btrfs_sysfs_remove_one(fs_info);
+ btrfs_sysfs_remove_mounted(fs_info);
fail_fsdev_sysfs:
btrfs_sysfs_remove_fsid(fs_info->fs_devices);
struct btrfs_device *device = (struct btrfs_device *)
bh->b_private;
- printk_ratelimited_in_rcu(KERN_WARNING "BTRFS: lost page write due to "
- "I/O error on %s\n",
+ btrfs_warn_rl_in_rcu(device->dev_root->fs_info,
+ "lost page write due to IO error on %s",
rcu_str_deref(device->name));
/* note, we dont' set_buffer_write_io_error because we have
* our own ways of dealing with the IO errors
put_bh(bh);
}
+int btrfs_read_dev_one_super(struct block_device *bdev, int copy_num,
+ struct buffer_head **bh_ret)
+{
+ struct buffer_head *bh;
+ struct btrfs_super_block *super;
+ u64 bytenr;
+
+ bytenr = btrfs_sb_offset(copy_num);
+ if (bytenr + BTRFS_SUPER_INFO_SIZE >= i_size_read(bdev->bd_inode))
+ return -EINVAL;
+
+ bh = __bread(bdev, bytenr / 4096, BTRFS_SUPER_INFO_SIZE);
+ /*
+ * If we fail to read from the underlying devices, as of now
+ * the best option we have is to mark it EIO.
+ */
+ if (!bh)
+ return -EIO;
+
+ super = (struct btrfs_super_block *)bh->b_data;
+ if (btrfs_super_bytenr(super) != bytenr ||
+ btrfs_super_magic(super) != BTRFS_MAGIC) {
+ brelse(bh);
+ return -EINVAL;
+ }
+
+ *bh_ret = bh;
+ return 0;
+}
+
+
struct buffer_head *btrfs_read_dev_super(struct block_device *bdev)
{
struct buffer_head *bh;
struct btrfs_super_block *super;
int i;
u64 transid = 0;
- u64 bytenr;
+ int ret = -EINVAL;
/* we would like to check all the supers, but that would make
* a btrfs mount succeed after a mkfs from a different FS.
* later supers, using BTRFS_SUPER_MIRROR_MAX instead
*/
for (i = 0; i < 1; i++) {
- bytenr = btrfs_sb_offset(i);
- if (bytenr + BTRFS_SUPER_INFO_SIZE >=
- i_size_read(bdev->bd_inode))
- break;
- bh = __bread(bdev, bytenr / 4096,
- BTRFS_SUPER_INFO_SIZE);
- if (!bh)
+ ret = btrfs_read_dev_one_super(bdev, i, &bh);
+ if (ret)
continue;
super = (struct btrfs_super_block *)bh->b_data;
- if (btrfs_super_bytenr(super) != bytenr ||
- btrfs_super_magic(super) != BTRFS_MAGIC) {
- brelse(bh);
- continue;
- }
if (!latest || btrfs_super_generation(super) > transid) {
brelse(latest);
brelse(bh);
}
}
+
+ if (!latest)
+ return ERR_PTR(ret);
+
return latest;
}
bh = __getblk(device->bdev, bytenr / 4096,
BTRFS_SUPER_INFO_SIZE);
if (!bh) {
- printk(KERN_ERR "BTRFS: couldn't get super "
- "buffer head for bytenr %Lu\n", bytenr);
+ btrfs_err(device->dev_root->fs_info,
+ "couldn't get super buffer head for bytenr %llu",
+ bytenr);
errors++;
continue;
}
int btrfs_get_num_tolerated_disk_barrier_failures(u64 flags)
{
- if ((flags & (BTRFS_BLOCK_GROUP_DUP |
- BTRFS_BLOCK_GROUP_RAID0 |
- BTRFS_AVAIL_ALLOC_BIT_SINGLE)) ||
- ((flags & BTRFS_BLOCK_GROUP_PROFILE_MASK) == 0))
- return 0;
+ int raid_type;
+ int min_tolerated = INT_MAX;
- if (flags & (BTRFS_BLOCK_GROUP_RAID1 |
- BTRFS_BLOCK_GROUP_RAID5 |
- BTRFS_BLOCK_GROUP_RAID10))
- return 1;
+ if ((flags & BTRFS_BLOCK_GROUP_PROFILE_MASK) == 0 ||
+ (flags & BTRFS_AVAIL_ALLOC_BIT_SINGLE))
+ min_tolerated = min(min_tolerated,
+ btrfs_raid_array[BTRFS_RAID_SINGLE].
+ tolerated_failures);
- if (flags & BTRFS_BLOCK_GROUP_RAID6)
- return 2;
+ for (raid_type = 0; raid_type < BTRFS_NR_RAID_TYPES; raid_type++) {
+ if (raid_type == BTRFS_RAID_SINGLE)
+ continue;
+ if (!(flags & btrfs_raid_group[raid_type]))
+ continue;
+ min_tolerated = min(min_tolerated,
+ btrfs_raid_array[raid_type].
+ tolerated_failures);
+ }
- pr_warn("BTRFS: unknown raid type: %llu\n", flags);
- return 0;
+ if (min_tolerated == INT_MAX) {
+ pr_warn("BTRFS: unknown raid flag: %llu\n", flags);
+ min_tolerated = 0;
+ }
+
+ return min_tolerated;
}
int btrfs_calc_num_tolerated_disk_barrier_failures(
if (ret) {
mutex_unlock(
&root->fs_info->fs_devices->device_list_mutex);
- btrfs_error(root->fs_info, ret,
+ btrfs_std_error(root->fs_info, ret,
"errors while submitting device barriers.");
return ret;
}
mutex_unlock(&root->fs_info->fs_devices->device_list_mutex);
/* FUA is masked off if unsupported and can't be the reason */
- btrfs_error(root->fs_info, -EIO,
+ btrfs_std_error(root->fs_info, -EIO,
"%d errors while writing supers", total_errors);
return -EIO;
}
}
mutex_unlock(&root->fs_info->fs_devices->device_list_mutex);
if (total_errors > max_errors) {
- btrfs_error(root->fs_info, -EIO,
+ btrfs_std_error(root->fs_info, -EIO,
"%d errors while writing supers", total_errors);
return -EIO;
}
percpu_counter_sum(&fs_info->delalloc_bytes));
}
- btrfs_sysfs_remove_one(fs_info);
+ btrfs_sysfs_remove_mounted(fs_info);
btrfs_sysfs_remove_fsid(fs_info->fs_devices);
btrfs_free_fs_roots(fs_info);
return 0;
}
-static void btrfs_free_pending_ordered(struct btrfs_transaction *cur_trans,
- struct btrfs_fs_info *fs_info)
-{
- struct btrfs_ordered_extent *ordered;
-
- spin_lock(&fs_info->trans_lock);
- while (!list_empty(&cur_trans->pending_ordered)) {
- ordered = list_first_entry(&cur_trans->pending_ordered,
- struct btrfs_ordered_extent,
- trans_list);
- list_del_init(&ordered->trans_list);
- spin_unlock(&fs_info->trans_lock);
-
- btrfs_put_ordered_extent(ordered);
- spin_lock(&fs_info->trans_lock);
- }
- spin_unlock(&fs_info->trans_lock);
-}
-
void btrfs_cleanup_one_transaction(struct btrfs_transaction *cur_trans,
struct btrfs_root *root)
{
cur_trans->state = TRANS_STATE_UNBLOCKED;
wake_up(&root->fs_info->transaction_wait);
- btrfs_free_pending_ordered(cur_trans, root->fs_info);
btrfs_destroy_delayed_inodes(root);
btrfs_assert_delayed_root_empty(root);
inode = tree->mapping->host;
isize = i_size_read(inode);
if (end >= PAGE_SIZE && (end % 2) == 0 && end != isize - 1) {
- printk_ratelimited(KERN_DEBUG
- "BTRFS: %s: ino %llu isize %llu odd range [%llu,%llu]\n",
+ btrfs_debug_rl(BTRFS_I(inode)->root->fs_info,
+ "%s: ino %llu isize %llu odd range [%llu,%llu]",
caller, btrfs_ino(inode), isize, start, end);
}
}
unsigned int sync_io:1;
};
+static void add_extent_changeset(struct extent_state *state, unsigned bits,
+ struct extent_changeset *changeset,
+ int set)
+{
+ int ret;
+
+ if (!changeset)
+ return;
+ if (set && (state->state & bits) == bits)
+ return;
+ if (!set && (state->state & bits) == 0)
+ return;
+ changeset->bytes_changed += state->end - state->start + 1;
+ ret = ulist_add(changeset->range_changed, state->start, state->end,
+ GFP_ATOMIC);
+ /* ENOMEM */
+ BUG_ON(ret < 0);
+}
+
static noinline void flush_write_bio(void *data);
static inline struct btrfs_fs_info *
tree_fs_info(struct extent_io_tree *tree)
}
static void set_state_bits(struct extent_io_tree *tree,
- struct extent_state *state, unsigned *bits);
+ struct extent_state *state, unsigned *bits,
+ struct extent_changeset *changeset);
/*
* insert an extent_state struct into the tree. 'bits' are set on the
struct extent_state *state, u64 start, u64 end,
struct rb_node ***p,
struct rb_node **parent,
- unsigned *bits)
+ unsigned *bits, struct extent_changeset *changeset)
{
struct rb_node *node;
state->start = start;
state->end = end;
- set_state_bits(tree, state, bits);
+ set_state_bits(tree, state, bits, changeset);
node = tree_insert(&tree->state, NULL, end, &state->rb_node, p, parent);
if (node) {
*/
static struct extent_state *clear_state_bit(struct extent_io_tree *tree,
struct extent_state *state,
- unsigned *bits, int wake)
+ unsigned *bits, int wake,
+ struct extent_changeset *changeset)
{
struct extent_state *next;
unsigned bits_to_clear = *bits & ~EXTENT_CTLBITS;
tree->dirty_bytes -= range;
}
clear_state_cb(tree, state, bits);
+ add_extent_changeset(state, bits_to_clear, changeset, 0);
state->state &= ~bits_to_clear;
if (wake)
wake_up(&state->wq);
*
* This takes the tree lock, and returns 0 on success and < 0 on error.
*/
-int clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
- unsigned bits, int wake, int delete,
- struct extent_state **cached_state,
- gfp_t mask)
+static int __clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
+ unsigned bits, int wake, int delete,
+ struct extent_state **cached_state,
+ gfp_t mask, struct extent_changeset *changeset)
{
struct extent_state *state;
struct extent_state *cached;
if (bits & (EXTENT_IOBITS | EXTENT_BOUNDARY))
clear = 1;
again:
- if (!prealloc && (mask & __GFP_WAIT)) {
+ if (!prealloc && gfpflags_allow_blocking(mask)) {
/*
* Don't care for allocation failure here because we might end
* up not needing the pre-allocated extent state at all, which
if (err)
goto out;
if (state->end <= end) {
- state = clear_state_bit(tree, state, &bits, wake);
+ state = clear_state_bit(tree, state, &bits, wake,
+ changeset);
goto next;
}
goto search_again;
if (wake)
wake_up(&state->wq);
- clear_state_bit(tree, prealloc, &bits, wake);
+ clear_state_bit(tree, prealloc, &bits, wake, changeset);
prealloc = NULL;
goto out;
}
- state = clear_state_bit(tree, state, &bits, wake);
+ state = clear_state_bit(tree, state, &bits, wake, changeset);
next:
if (last_end == (u64)-1)
goto out;
if (start > end)
goto out;
spin_unlock(&tree->lock);
- if (mask & __GFP_WAIT)
+ if (gfpflags_allow_blocking(mask))
cond_resched();
goto again;
}
static void set_state_bits(struct extent_io_tree *tree,
struct extent_state *state,
- unsigned *bits)
+ unsigned *bits, struct extent_changeset *changeset)
{
unsigned bits_to_set = *bits & ~EXTENT_CTLBITS;
u64 range = state->end - state->start + 1;
tree->dirty_bytes += range;
}
+ add_extent_changeset(state, bits_to_set, changeset, 1);
state->state |= bits_to_set;
}
__set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
unsigned bits, unsigned exclusive_bits,
u64 *failed_start, struct extent_state **cached_state,
- gfp_t mask)
+ gfp_t mask, struct extent_changeset *changeset)
{
struct extent_state *state;
struct extent_state *prealloc = NULL;
bits |= EXTENT_FIRST_DELALLOC;
again:
- if (!prealloc && (mask & __GFP_WAIT)) {
+ if (!prealloc && gfpflags_allow_blocking(mask)) {
prealloc = alloc_extent_state(mask);
BUG_ON(!prealloc);
}
prealloc = alloc_extent_state_atomic(prealloc);
BUG_ON(!prealloc);
err = insert_state(tree, prealloc, start, end,
- &p, &parent, &bits);
+ &p, &parent, &bits, changeset);
if (err)
extent_io_tree_panic(tree, err);
goto out;
}
- set_state_bits(tree, state, &bits);
+ set_state_bits(tree, state, &bits, changeset);
cache_state(state, cached_state);
merge_state(tree, state);
if (last_end == (u64)-1)
if (err)
goto out;
if (state->end <= end) {
- set_state_bits(tree, state, &bits);
+ set_state_bits(tree, state, &bits, changeset);
cache_state(state, cached_state);
merge_state(tree, state);
if (last_end == (u64)-1)
* the later extent.
*/
err = insert_state(tree, prealloc, start, this_end,
- NULL, NULL, &bits);
+ NULL, NULL, &bits, changeset);
if (err)
extent_io_tree_panic(tree, err);
if (err)
extent_io_tree_panic(tree, err);
- set_state_bits(tree, prealloc, &bits);
+ set_state_bits(tree, prealloc, &bits, changeset);
cache_state(prealloc, cached_state);
merge_state(tree, prealloc);
prealloc = NULL;
if (start > end)
goto out;
spin_unlock(&tree->lock);
- if (mask & __GFP_WAIT)
+ if (gfpflags_allow_blocking(mask))
cond_resched();
goto again;
}
struct extent_state **cached_state, gfp_t mask)
{
return __set_extent_bit(tree, start, end, bits, 0, failed_start,
- cached_state, mask);
+ cached_state, mask, NULL);
}
btrfs_debug_check_extent_io_range(tree, start, end);
again:
- if (!prealloc && (mask & __GFP_WAIT)) {
+ if (!prealloc && gfpflags_allow_blocking(mask)) {
/*
* Best effort, don't worry if extent state allocation fails
* here for the first iteration. We might have a cached state
goto out;
}
err = insert_state(tree, prealloc, start, end,
- &p, &parent, &bits);
+ &p, &parent, &bits, NULL);
if (err)
extent_io_tree_panic(tree, err);
cache_state(prealloc, cached_state);
* Just lock what we found and keep going
*/
if (state->start == start && state->end <= end) {
- set_state_bits(tree, state, &bits);
+ set_state_bits(tree, state, &bits, NULL);
cache_state(state, cached_state);
- state = clear_state_bit(tree, state, &clear_bits, 0);
+ state = clear_state_bit(tree, state, &clear_bits, 0, NULL);
if (last_end == (u64)-1)
goto out;
start = last_end + 1;
if (err)
goto out;
if (state->end <= end) {
- set_state_bits(tree, state, &bits);
+ set_state_bits(tree, state, &bits, NULL);
cache_state(state, cached_state);
- state = clear_state_bit(tree, state, &clear_bits, 0);
+ state = clear_state_bit(tree, state, &clear_bits, 0,
+ NULL);
if (last_end == (u64)-1)
goto out;
start = last_end + 1;
* the later extent.
*/
err = insert_state(tree, prealloc, start, this_end,
- NULL, NULL, &bits);
+ NULL, NULL, &bits, NULL);
if (err)
extent_io_tree_panic(tree, err);
cache_state(prealloc, cached_state);
if (err)
extent_io_tree_panic(tree, err);
- set_state_bits(tree, prealloc, &bits);
+ set_state_bits(tree, prealloc, &bits, NULL);
cache_state(prealloc, cached_state);
- clear_state_bit(tree, prealloc, &clear_bits, 0);
+ clear_state_bit(tree, prealloc, &clear_bits, 0, NULL);
prealloc = NULL;
goto out;
}
if (start > end)
goto out;
spin_unlock(&tree->lock);
- if (mask & __GFP_WAIT)
+ if (gfpflags_allow_blocking(mask))
cond_resched();
first_iteration = false;
goto again;
NULL, mask);
}
+int set_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
+ unsigned bits, gfp_t mask,
+ struct extent_changeset *changeset)
+{
+ /*
+ * We don't support EXTENT_LOCKED yet, as current changeset will
+ * record any bits changed, so for EXTENT_LOCKED case, it will
+ * either fail with -EEXIST or changeset will record the whole
+ * range.
+ */
+ BUG_ON(bits & EXTENT_LOCKED);
+
+ return __set_extent_bit(tree, start, end, bits, 0, NULL, NULL, mask,
+ changeset);
+}
+
+int clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
+ unsigned bits, int wake, int delete,
+ struct extent_state **cached, gfp_t mask)
+{
+ return __clear_extent_bit(tree, start, end, bits, wake, delete,
+ cached, mask, NULL);
+}
+
int clear_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
unsigned bits, gfp_t mask)
{
return clear_extent_bit(tree, start, end, bits, wake, 0, NULL, mask);
}
+int clear_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
+ unsigned bits, gfp_t mask,
+ struct extent_changeset *changeset)
+{
+ /*
+ * Don't support EXTENT_LOCKED case, same reason as
+ * set_record_extent_bits().
+ */
+ BUG_ON(bits & EXTENT_LOCKED);
+
+ return __clear_extent_bit(tree, start, end, bits, 0, 0, NULL, mask,
+ changeset);
+}
+
int set_extent_delalloc(struct extent_io_tree *tree, u64 start, u64 end,
struct extent_state **cached_state, gfp_t mask)
{
while (1) {
err = __set_extent_bit(tree, start, end, EXTENT_LOCKED | bits,
EXTENT_LOCKED, &failed_start,
- cached_state, GFP_NOFS);
+ cached_state, GFP_NOFS, NULL);
if (err == -EEXIST) {
wait_extent_bit(tree, failed_start, end, EXTENT_LOCKED);
start = failed_start;
u64 failed_start;
err = __set_extent_bit(tree, start, end, EXTENT_LOCKED, EXTENT_LOCKED,
- &failed_start, NULL, GFP_NOFS);
+ &failed_start, NULL, GFP_NOFS, NULL);
if (err == -EEXIST) {
if (failed_start > start)
clear_extent_bit(tree, start, failed_start - 1,
return -EIO;
}
- printk_ratelimited_in_rcu(KERN_INFO
- "BTRFS: read error corrected: ino %llu off %llu (dev %s sector %llu)\n",
+ btrfs_info_rl_in_rcu(fs_info,
+ "read error corrected: ino %llu off %llu (dev %s sector %llu)",
btrfs_ino(inode), start,
rcu_str_deref(dev->name), sector);
bio_put(bio);
set_extent_uptodate(tree, cur, cur + iosize - 1,
&cached, GFP_NOFS);
- unlock_extent_cached(tree, cur, cur + iosize - 1,
- &cached, GFP_NOFS);
+ if (parent_locked)
+ free_extent_state(cached);
+ else
+ unlock_extent_cached(tree, cur,
+ cur + iosize - 1,
+ &cached, GFP_NOFS);
cur = cur + iosize;
pg_offset += iosize;
continue;
u64 start = page_offset(page);
u64 end = start + PAGE_CACHE_SIZE - 1;
- if ((mask & __GFP_WAIT) &&
+ if (gfpflags_allow_blocking(mask) &&
page->mapping->host->i_size > 16 * 1024 * 1024) {
u64 len;
while (start <= end) {
unsigned long src_i;
if (src_offset + len > dst->len) {
- printk(KERN_ERR "BTRFS: memmove bogus src_offset %lu move "
- "len %lu dst len %lu\n", src_offset, len, dst->len);
+ btrfs_err(dst->fs_info,
+ "memmove bogus src_offset %lu move "
+ "len %lu dst len %lu", src_offset, len, dst->len);
BUG_ON(1);
}
if (dst_offset + len > dst->len) {
- printk(KERN_ERR "BTRFS: memmove bogus dst_offset %lu move "
- "len %lu dst len %lu\n", dst_offset, len, dst->len);
+ btrfs_err(dst->fs_info,
+ "memmove bogus dst_offset %lu move "
+ "len %lu dst len %lu", dst_offset, len, dst->len);
BUG_ON(1);
}
unsigned long src_i;
if (src_offset + len > dst->len) {
- printk(KERN_ERR "BTRFS: memmove bogus src_offset %lu move "
- "len %lu len %lu\n", src_offset, len, dst->len);
+ btrfs_err(dst->fs_info, "memmove bogus src_offset %lu move "
+ "len %lu len %lu", src_offset, len, dst->len);
BUG_ON(1);
}
if (dst_offset + len > dst->len) {
- printk(KERN_ERR "BTRFS: memmove bogus dst_offset %lu move "
- "len %lu len %lu\n", dst_offset, len, dst->len);
+ btrfs_err(dst->fs_info, "memmove bogus dst_offset %lu move "
+ "len %lu len %lu", dst_offset, len, dst->len);
BUG_ON(1);
}
if (dst_offset < src_offset) {
}
mapping_set_gfp_mask(inode->i_mapping,
- mapping_gfp_mask(inode->i_mapping) &
- ~(__GFP_FS | __GFP_HIGHMEM));
+ mapping_gfp_constraint(inode->i_mapping,
+ ~(__GFP_FS | __GFP_HIGHMEM)));
return inode;
}
gen = io_ctl->cur;
if (le64_to_cpu(*gen) != generation) {
- printk_ratelimited(KERN_ERR "BTRFS: space cache generation "
- "(%Lu) does not match inode (%Lu)\n", *gen,
- generation);
+ btrfs_err_rl(io_ctl->root->fs_info,
+ "space cache generation (%llu) does not match inode (%llu)",
+ *gen, generation);
io_ctl_unmap_page(io_ctl);
return -EIO;
}
PAGE_CACHE_SIZE - offset);
btrfs_csum_final(crc, (char *)&crc);
if (val != crc) {
- printk_ratelimited(KERN_ERR "BTRFS: csum mismatch on free "
- "space cache\n");
+ btrfs_err_rl(io_ctl->root->fs_info,
+ "csum mismatch on free space cache");
io_ctl_unmap_page(io_ctl);
return -EIO;
}
* @offset - the offset for the key we'll insert
*
* This function writes out a free space cache struct to disk for quick recovery
- * on mount. This will return 0 if it was successfull in writing the cache out,
+ * on mount. This will return 0 if it was successful in writing the cache out,
* or an errno if it was not.
*/
static int __btrfs_write_out_cache(struct btrfs_root *root, struct inode *inode,
*/
static int search_bitmap(struct btrfs_free_space_ctl *ctl,
struct btrfs_free_space *bitmap_info, u64 *offset,
- u64 *bytes)
+ u64 *bytes, bool for_alloc)
{
unsigned long found_bits = 0;
unsigned long max_bits = 0;
unsigned long next_zero;
unsigned long extent_bits;
+ /*
+ * Skip searching the bitmap if we don't have a contiguous section that
+ * is large enough for this allocation.
+ */
+ if (for_alloc &&
+ bitmap_info->max_extent_size &&
+ bitmap_info->max_extent_size < *bytes) {
+ *bytes = bitmap_info->max_extent_size;
+ return -1;
+ }
+
i = offset_to_bit(bitmap_info->offset, ctl->unit,
max_t(u64, *offset, bitmap_info->offset));
bits = bytes_to_bits(*bytes, ctl->unit);
for_each_set_bit_from(i, bitmap_info->bitmap, BITS_PER_BITMAP) {
+ if (for_alloc && bits == 1) {
+ found_bits = 1;
+ break;
+ }
next_zero = find_next_zero_bit(bitmap_info->bitmap,
BITS_PER_BITMAP, i);
extent_bits = next_zero - i;
}
*bytes = (u64)(max_bits) * ctl->unit;
+ bitmap_info->max_extent_size = *bytes;
return -1;
}
if (entry->bitmap) {
u64 size = *bytes;
- ret = search_bitmap(ctl, entry, &tmp, &size);
+ ret = search_bitmap(ctl, entry, &tmp, &size, true);
if (!ret) {
*offset = tmp;
*bytes = size;
search_start = *offset;
search_bytes = ctl->unit;
search_bytes = min(search_bytes, end - search_start + 1);
- ret = search_bitmap(ctl, bitmap_info, &search_start, &search_bytes);
+ ret = search_bitmap(ctl, bitmap_info, &search_start, &search_bytes,
+ false);
if (ret < 0 || search_start != *offset)
return -EINVAL;
search_start = *offset;
search_bytes = ctl->unit;
ret = search_bitmap(ctl, bitmap_info, &search_start,
- &search_bytes);
+ &search_bytes, false);
if (ret < 0 || search_start != *offset)
return -EAGAIN;
bitmap_set_bits(ctl, info, offset, bytes_to_set);
+ /*
+ * We set some bytes, we have no idea what the max extent size is
+ * anymore.
+ */
+ info->max_extent_size = 0;
+
return bytes_to_set;
}
struct btrfs_free_space *info)
{
struct btrfs_block_group_cache *block_group = ctl->private;
+ bool forced = false;
+
+#ifdef CONFIG_BTRFS_DEBUG
+ if (btrfs_should_fragment_free_space(block_group->fs_info->extent_root,
+ block_group))
+ forced = true;
+#endif
/*
* If we are below the extents threshold then we can add this as an
* extent, and don't have to deal with the bitmap
*/
- if (ctl->free_extents < ctl->extents_thresh) {
+ if (!forced && ctl->free_extents < ctl->extents_thresh) {
/*
* If this block group has some small extents we don't want to
* use up all of our free slots in the cache with them, we want
search_start = min_start;
search_bytes = bytes;
- err = search_bitmap(ctl, entry, &search_start, &search_bytes);
+ err = search_bitmap(ctl, entry, &search_start, &search_bytes, true);
if (err) {
if (search_bytes > *max_extent_size)
*max_extent_size = search_bytes;
unsigned long want_bits;
unsigned long min_bits;
unsigned long found_bits;
+ unsigned long max_bits = 0;
unsigned long start = 0;
unsigned long total_found = 0;
int ret;
want_bits = bytes_to_bits(bytes, ctl->unit);
min_bits = bytes_to_bits(min_bytes, ctl->unit);
+ /*
+ * Don't bother looking for a cluster in this bitmap if it's heavily
+ * fragmented.
+ */
+ if (entry->max_extent_size &&
+ entry->max_extent_size < cont1_bytes)
+ return -ENOSPC;
again:
found_bits = 0;
for_each_set_bit_from(i, entry->bitmap, BITS_PER_BITMAP) {
BITS_PER_BITMAP, i);
if (next_zero - i >= min_bits) {
found_bits = next_zero - i;
+ if (found_bits > max_bits)
+ max_bits = found_bits;
break;
}
+ if (next_zero - i > max_bits)
+ max_bits = next_zero - i;
i = next_zero;
}
- if (!found_bits)
+ if (!found_bits) {
+ entry->max_extent_size = (u64)max_bits * ctl->unit;
return -ENOSPC;
+ }
if (!total_found) {
start = i;
spin_lock_init(&cluster->refill_lock);
cluster->root = RB_ROOT;
cluster->max_size = 0;
+ cluster->fragmented = false;
INIT_LIST_HEAD(&cluster->block_group_list);
cluster->block_group = NULL;
}
}
bytes = minlen;
- ret2 = search_bitmap(ctl, entry, &start, &bytes);
+ ret2 = search_bitmap(ctl, entry, &start, &bytes, false);
if (ret2 || start >= end) {
spin_unlock(&ctl->tree_lock);
mutex_unlock(&ctl->cache_writeout_mutex);
u64 count = 1;
int ret;
- ret = search_bitmap(ctl, entry, &offset, &count);
+ ret = search_bitmap(ctl, entry, &offset, &count, true);
/* Logic error; Should be empty if it can't find anything */
ASSERT(!ret);
spin_lock(&ctl->tree_lock);
info->offset = offset;
info->bytes = bytes;
+ info->max_extent_size = 0;
ret = link_free_space(ctl, info);
spin_unlock(&ctl->tree_lock);
if (ret)
}
bytes_added = add_bytes_to_bitmap(ctl, bitmap_info, offset, bytes);
+
bytes -= bytes_added;
offset += bytes_added;
spin_unlock(&ctl->tree_lock);
bit_off = offset;
bit_bytes = ctl->unit;
- ret = search_bitmap(ctl, info, &bit_off, &bit_bytes);
+ ret = search_bitmap(ctl, info, &bit_off, &bit_bytes, false);
if (!ret) {
if (bit_off == offset) {
ret = 1;
#include "dev-replace.h"
#include "sysfs.h"
+const struct btrfs_raid_attr btrfs_raid_array[BTRFS_NR_RAID_TYPES] = {
+ [BTRFS_RAID_RAID10] = {
+ .sub_stripes = 2,
+ .dev_stripes = 1,
+ .devs_max = 0, /* 0 == as many as possible */
+ .devs_min = 4,
+ .tolerated_failures = 1,
+ .devs_increment = 2,
+ .ncopies = 2,
+ },
+ [BTRFS_RAID_RAID1] = {
+ .sub_stripes = 1,
+ .dev_stripes = 1,
+ .devs_max = 2,
+ .devs_min = 2,
+ .tolerated_failures = 1,
+ .devs_increment = 2,
+ .ncopies = 2,
+ },
+ [BTRFS_RAID_DUP] = {
+ .sub_stripes = 1,
+ .dev_stripes = 2,
+ .devs_max = 1,
+ .devs_min = 1,
+ .tolerated_failures = 0,
+ .devs_increment = 1,
+ .ncopies = 2,
+ },
+ [BTRFS_RAID_RAID0] = {
+ .sub_stripes = 1,
+ .dev_stripes = 1,
+ .devs_max = 0,
+ .devs_min = 2,
+ .tolerated_failures = 0,
+ .devs_increment = 1,
+ .ncopies = 1,
+ },
+ [BTRFS_RAID_SINGLE] = {
+ .sub_stripes = 1,
+ .dev_stripes = 1,
+ .devs_max = 1,
+ .devs_min = 1,
+ .tolerated_failures = 0,
+ .devs_increment = 1,
+ .ncopies = 1,
+ },
+ [BTRFS_RAID_RAID5] = {
+ .sub_stripes = 1,
+ .dev_stripes = 1,
+ .devs_max = 0,
+ .devs_min = 2,
+ .tolerated_failures = 1,
+ .devs_increment = 1,
+ .ncopies = 2,
+ },
+ [BTRFS_RAID_RAID6] = {
+ .sub_stripes = 1,
+ .dev_stripes = 1,
+ .devs_max = 0,
+ .devs_min = 3,
+ .tolerated_failures = 2,
+ .devs_increment = 1,
+ .ncopies = 3,
+ },
+};
+
+const u64 const btrfs_raid_group[BTRFS_NR_RAID_TYPES] = {
+ [BTRFS_RAID_RAID10] = BTRFS_BLOCK_GROUP_RAID10,
+ [BTRFS_RAID_RAID1] = BTRFS_BLOCK_GROUP_RAID1,
+ [BTRFS_RAID_DUP] = BTRFS_BLOCK_GROUP_DUP,
+ [BTRFS_RAID_RAID0] = BTRFS_BLOCK_GROUP_RAID0,
+ [BTRFS_RAID_SINGLE] = 0,
+ [BTRFS_RAID_RAID5] = BTRFS_BLOCK_GROUP_RAID5,
+ [BTRFS_RAID_RAID6] = BTRFS_BLOCK_GROUP_RAID6,
+};
+
static int init_first_rw_device(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
struct btrfs_device *device);
spin_lock_init(&dev->reada_lock);
atomic_set(&dev->reada_in_flight, 0);
atomic_set(&dev->dev_stats_ccnt, 0);
- INIT_RADIX_TREE(&dev->reada_zones, GFP_NOFS & ~__GFP_WAIT);
- INIT_RADIX_TREE(&dev->reada_extents, GFP_NOFS & ~__GFP_WAIT);
+ INIT_RADIX_TREE(&dev->reada_zones, GFP_NOFS & ~__GFP_DIRECT_RECLAIM);
+ INIT_RADIX_TREE(&dev->reada_extents, GFP_NOFS & ~__GFP_DIRECT_RECLAIM);
return dev;
}
if (IS_ERR(*bdev)) {
ret = PTR_ERR(*bdev);
- printk(KERN_INFO "BTRFS: open %s failed\n", device_path);
goto error;
}
}
invalidate_bdev(*bdev);
*bh = btrfs_read_dev_super(*bdev);
- if (!*bh) {
- ret = -EINVAL;
+ if (IS_ERR(*bh)) {
+ ret = PTR_ERR(*bh);
blkdev_put(*bdev, flags);
goto error;
}
pending = pending->bi_next;
cur->bi_next = NULL;
+ /*
+ * atomic_dec_return implies a barrier for waitqueue_active
+ */
if (atomic_dec_return(&fs_info->nr_async_bios) < limit &&
waitqueue_active(&fs_info->async_submit_wait))
wake_up(&fs_info->async_submit_wait);
mutex_lock(&fs_devices->device_list_mutex);
list_for_each_entry_safe(device, tmp, &fs_devices->devices, dev_list) {
- struct btrfs_device *new_device;
- struct rcu_string *name;
-
- if (device->bdev)
- fs_devices->open_devices--;
-
- if (device->writeable &&
- device->devid != BTRFS_DEV_REPLACE_DEVID) {
- list_del_init(&device->dev_alloc_list);
- fs_devices->rw_devices--;
- }
-
- if (device->missing)
- fs_devices->missing_devices--;
-
- new_device = btrfs_alloc_device(NULL, &device->devid,
- device->uuid);
- BUG_ON(IS_ERR(new_device)); /* -ENOMEM */
-
- /* Safe because we are under uuid_mutex */
- if (device->name) {
- name = rcu_string_strdup(device->name->str, GFP_NOFS);
- BUG_ON(!name); /* -ENOMEM */
- rcu_assign_pointer(new_device->name, name);
- }
-
- list_replace_rcu(&device->dev_list, &new_device->dev_list);
- new_device->fs_devices = device->fs_devices;
-
- call_rcu(&device->rcu, free_device);
+ btrfs_close_one_device(device);
}
mutex_unlock(&fs_devices->device_list_mutex);
extent = btrfs_item_ptr(leaf, path->slots[0],
struct btrfs_dev_extent);
} else {
- btrfs_error(root->fs_info, ret, "Slot search failed");
+ btrfs_std_error(root->fs_info, ret, "Slot search failed");
goto out;
}
ret = btrfs_del_item(trans, root, path);
if (ret) {
- btrfs_error(root->fs_info, ret,
+ btrfs_std_error(root->fs_info, ret,
"Failed to remove dev extent item");
} else {
- trans->transaction->have_free_bgs = 1;
+ set_bit(BTRFS_TRANS_HAVE_FREE_BGS, &trans->transaction->flags);
}
out:
btrfs_free_path(path);
if (device->bdev) {
device->fs_devices->open_devices--;
/* remove sysfs entry */
- btrfs_kobj_rm_device(root->fs_info->fs_devices, device);
+ btrfs_sysfs_rm_device_link(root->fs_info->fs_devices, device);
}
call_rcu(&device->rcu, free_device);
if (srcdev->writeable) {
fs_devices->rw_devices--;
/* zero out the old super if it is writable */
- btrfs_scratch_superblock(srcdev);
+ btrfs_scratch_superblocks(srcdev->bdev,
+ rcu_str_deref(srcdev->name));
}
if (srcdev->bdev)
WARN_ON(!tgtdev);
mutex_lock(&fs_info->fs_devices->device_list_mutex);
- btrfs_kobj_rm_device(fs_info->fs_devices, tgtdev);
+ btrfs_sysfs_rm_device_link(fs_info->fs_devices, tgtdev);
if (tgtdev->bdev) {
- btrfs_scratch_superblock(tgtdev);
+ btrfs_scratch_superblocks(tgtdev->bdev,
+ rcu_str_deref(tgtdev->name));
fs_info->fs_devices->open_devices--;
}
fs_info->fs_devices->num_devices--;
}
}
- if (!*device) {
- btrfs_err(root->fs_info, "no missing device found");
- return -ENOENT;
- }
+ if (!*device)
+ return BTRFS_ERROR_DEV_MISSING_NOT_FOUND;
return 0;
} else {
tmp + 1);
/* add sysfs device entry */
- btrfs_kobj_add_device(root->fs_info->fs_devices, device);
+ btrfs_sysfs_add_device_link(root->fs_info->fs_devices, device);
/*
* we've got more storage, clear any full flags on the space
*/
snprintf(fsid_buf, BTRFS_UUID_UNPARSED_SIZE, "%pU",
root->fs_info->fsid);
- if (kobject_rename(&root->fs_info->fs_devices->super_kobj,
+ if (kobject_rename(&root->fs_info->fs_devices->fsid_kobj,
fsid_buf))
- pr_warn("BTRFS: sysfs: failed to create fsid for sprout\n");
+ btrfs_warn(root->fs_info,
+ "sysfs: failed to create fsid for sprout");
}
root->fs_info->num_tolerated_disk_barrier_failures =
ret = btrfs_relocate_sys_chunks(root);
if (ret < 0)
- btrfs_error(root->fs_info, ret,
+ btrfs_std_error(root->fs_info, ret,
"Failed to relocate sys chunks after "
"device initialization. This can be fixed "
"using the \"btrfs balance\" command.");
error_trans:
btrfs_end_transaction(trans, root);
rcu_string_free(device->name);
- btrfs_kobj_rm_device(root->fs_info->fs_devices, device);
+ btrfs_sysfs_rm_device_link(root->fs_info->fs_devices, device);
kfree(device);
error:
blkdev_put(bdev, FMODE_EXCL);
if (ret < 0)
goto out;
else if (ret > 0) { /* Logic error or corruption */
- btrfs_error(root->fs_info, -ENOENT,
+ btrfs_std_error(root->fs_info, -ENOENT,
"Failed lookup while freeing chunk.");
ret = -ENOENT;
goto out;
ret = btrfs_del_item(trans, root, path);
if (ret < 0)
- btrfs_error(root->fs_info, ret,
+ btrfs_std_error(root->fs_info, ret,
"Failed to delete chunk item.");
out:
btrfs_free_path(path);
trans = btrfs_start_transaction(root, 0);
if (IS_ERR(trans)) {
ret = PTR_ERR(trans);
- btrfs_std_error(root->fs_info, ret);
+ btrfs_std_error(root->fs_info, ret, NULL);
return ret;
}
* (albeit full) chunks.
*/
if (!(bctl->data.flags & BTRFS_BALANCE_ARGS_USAGE) &&
+ !(bctl->data.flags & BTRFS_BALANCE_ARGS_USAGE_RANGE) &&
!(bctl->data.flags & BTRFS_BALANCE_ARGS_CONVERT)) {
bctl->data.flags |= BTRFS_BALANCE_ARGS_USAGE;
bctl->data.usage = 90;
}
if (!(bctl->sys.flags & BTRFS_BALANCE_ARGS_USAGE) &&
+ !(bctl->sys.flags & BTRFS_BALANCE_ARGS_USAGE_RANGE) &&
!(bctl->sys.flags & BTRFS_BALANCE_ARGS_CONVERT)) {
bctl->sys.flags |= BTRFS_BALANCE_ARGS_USAGE;
bctl->sys.usage = 90;
}
if (!(bctl->meta.flags & BTRFS_BALANCE_ARGS_USAGE) &&
+ !(bctl->meta.flags & BTRFS_BALANCE_ARGS_USAGE_RANGE) &&
!(bctl->meta.flags & BTRFS_BALANCE_ARGS_CONVERT)) {
bctl->meta.flags |= BTRFS_BALANCE_ARGS_USAGE;
bctl->meta.usage = 90;
static int chunk_usage_filter(struct btrfs_fs_info *fs_info, u64 chunk_offset,
struct btrfs_balance_args *bargs)
+{
+ struct btrfs_block_group_cache *cache;
+ u64 chunk_used;
+ u64 user_thresh_min;
+ u64 user_thresh_max;
+ int ret = 1;
+
+ cache = btrfs_lookup_block_group(fs_info, chunk_offset);
+ chunk_used = btrfs_block_group_used(&cache->item);
+
+ if (bargs->usage_min == 0)
+ user_thresh_min = 0;
+ else
+ user_thresh_min = div_factor_fine(cache->key.offset,
+ bargs->usage_min);
+
+ if (bargs->usage_max == 0)
+ user_thresh_max = 1;
+ else if (bargs->usage_max > 100)
+ user_thresh_max = cache->key.offset;
+ else
+ user_thresh_max = div_factor_fine(cache->key.offset,
+ bargs->usage_max);
+
+ if (user_thresh_min <= chunk_used && chunk_used < user_thresh_max)
+ ret = 0;
+
+ btrfs_put_block_group(cache);
+ return ret;
+}
+
+static int chunk_usage_range_filter(struct btrfs_fs_info *fs_info,
+ u64 chunk_offset, struct btrfs_balance_args *bargs)
{
struct btrfs_block_group_cache *cache;
u64 chunk_used, user_thresh;
cache = btrfs_lookup_block_group(fs_info, chunk_offset);
chunk_used = btrfs_block_group_used(&cache->item);
- if (bargs->usage == 0)
+ if (bargs->usage_min == 0)
user_thresh = 1;
else if (bargs->usage > 100)
user_thresh = cache->key.offset;
return 1;
}
+static int chunk_stripes_range_filter(struct extent_buffer *leaf,
+ struct btrfs_chunk *chunk,
+ struct btrfs_balance_args *bargs)
+{
+ int num_stripes = btrfs_chunk_num_stripes(leaf, chunk);
+
+ if (bargs->stripes_min <= num_stripes
+ && num_stripes <= bargs->stripes_max)
+ return 0;
+
+ return 1;
+}
+
static int chunk_soft_convert_filter(u64 chunk_type,
struct btrfs_balance_args *bargs)
{
if ((bargs->flags & BTRFS_BALANCE_ARGS_USAGE) &&
chunk_usage_filter(bctl->fs_info, chunk_offset, bargs)) {
return 0;
+ } else if ((bargs->flags & BTRFS_BALANCE_ARGS_USAGE_RANGE) &&
+ chunk_usage_range_filter(bctl->fs_info, chunk_offset, bargs)) {
+ return 0;
}
/* devid filter */
return 0;
}
+ /* stripes filter */
+ if ((bargs->flags & BTRFS_BALANCE_ARGS_STRIPES_RANGE) &&
+ chunk_stripes_range_filter(leaf, chunk, bargs)) {
+ return 0;
+ }
+
/* soft profile changing mode */
if ((bargs->flags & BTRFS_BALANCE_ARGS_SOFT) &&
chunk_soft_convert_filter(chunk_type, bargs)) {
return 0;
else
bargs->limit--;
+ } else if ((bargs->flags & BTRFS_BALANCE_ARGS_LIMIT_RANGE)) {
+ /*
+ * Same logic as the 'limit' filter; the minimum cannot be
+ * determined here because we do not have the global informatoin
+ * about the count of all chunks that satisfy the filters.
+ */
+ if (bargs->limit_max == 0)
+ return 0;
+ else
+ bargs->limit_max--;
}
return 1;
struct btrfs_device *device;
u64 old_size;
u64 size_to_free;
+ u64 chunk_type;
struct btrfs_chunk *chunk;
struct btrfs_path *path;
struct btrfs_key key;
int ret;
int enospc_errors = 0;
bool counting = true;
+ /* The single value limit and min/max limits use the same bytes in the */
u64 limit_data = bctl->data.limit;
u64 limit_meta = bctl->meta.limit;
u64 limit_sys = bctl->sys.limit;
+ u32 count_data = 0;
+ u32 count_meta = 0;
+ u32 count_sys = 0;
/* step one make some room on all the devices */
devices = &fs_info->fs_devices->devices;
spin_unlock(&fs_info->balance_lock);
again:
if (!counting) {
+ /*
+ * The single value limit and min/max limits use the same bytes
+ * in the
+ */
bctl->data.limit = limit_data;
bctl->meta.limit = limit_meta;
bctl->sys.limit = limit_sys;
}
chunk = btrfs_item_ptr(leaf, slot, struct btrfs_chunk);
+ chunk_type = btrfs_chunk_type(leaf, chunk);
if (!counting) {
spin_lock(&fs_info->balance_lock);
spin_lock(&fs_info->balance_lock);
bctl->stat.expected++;
spin_unlock(&fs_info->balance_lock);
+
+ if (chunk_type & BTRFS_BLOCK_GROUP_DATA)
+ count_data++;
+ else if (chunk_type & BTRFS_BLOCK_GROUP_SYSTEM)
+ count_sys++;
+ else if (chunk_type & BTRFS_BLOCK_GROUP_METADATA)
+ count_meta++;
+
+ goto loop;
+ }
+
+ /*
+ * Apply limit_min filter, no need to check if the LIMITS
+ * filter is used, limit_min is 0 by default
+ */
+ if (((chunk_type & BTRFS_BLOCK_GROUP_DATA) &&
+ count_data < bctl->data.limit_min)
+ || ((chunk_type & BTRFS_BLOCK_GROUP_METADATA) &&
+ count_meta < bctl->meta.limit_min)
+ || ((chunk_type & BTRFS_BLOCK_GROUP_SYSTEM) &&
+ count_sys < bctl->sys.limit_min)) {
+ mutex_unlock(&fs_info->delete_unused_bgs_mutex);
goto loop;
}
unset_balance_control(fs_info);
ret = del_balance_item(fs_info->tree_root);
if (ret)
- btrfs_std_error(fs_info, ret);
+ btrfs_std_error(fs_info, ret, NULL);
atomic_set(&fs_info->mutually_exclusive_operation_running, 0);
}
+/* Non-zero return value signifies invalidity */
+static inline int validate_convert_profile(struct btrfs_balance_args *bctl_arg,
+ u64 allowed)
+{
+ return ((bctl_arg->flags & BTRFS_BALANCE_ARGS_CONVERT) &&
+ (!alloc_profile_is_valid(bctl_arg->target, 1) ||
+ (bctl_arg->target & ~allowed)));
+}
+
/*
* Should be called with both balance and volume mutexes held
*/
if (num_devices > 3)
allowed |= (BTRFS_BLOCK_GROUP_RAID10 |
BTRFS_BLOCK_GROUP_RAID6);
- if ((bctl->data.flags & BTRFS_BALANCE_ARGS_CONVERT) &&
- (!alloc_profile_is_valid(bctl->data.target, 1) ||
- (bctl->data.target & ~allowed))) {
+ if (validate_convert_profile(&bctl->data, allowed)) {
btrfs_err(fs_info, "unable to start balance with target "
"data profile %llu",
bctl->data.target);
ret = -EINVAL;
goto out;
}
- if ((bctl->meta.flags & BTRFS_BALANCE_ARGS_CONVERT) &&
- (!alloc_profile_is_valid(bctl->meta.target, 1) ||
- (bctl->meta.target & ~allowed))) {
+ if (validate_convert_profile(&bctl->meta, allowed)) {
btrfs_err(fs_info,
"unable to start balance with target metadata profile %llu",
bctl->meta.target);
ret = -EINVAL;
goto out;
}
- if ((bctl->sys.flags & BTRFS_BALANCE_ARGS_CONVERT) &&
- (!alloc_profile_is_valid(bctl->sys.target, 1) ||
- (bctl->sys.target & ~allowed))) {
+ if (validate_convert_profile(&bctl->sys, allowed)) {
btrfs_err(fs_info,
"unable to start balance with target system profile %llu",
bctl->sys.target);
return 0;
}
-static const struct btrfs_raid_attr btrfs_raid_array[BTRFS_NR_RAID_TYPES] = {
- [BTRFS_RAID_RAID10] = {
- .sub_stripes = 2,
- .dev_stripes = 1,
- .devs_max = 0, /* 0 == as many as possible */
- .devs_min = 4,
- .devs_increment = 2,
- .ncopies = 2,
- },
- [BTRFS_RAID_RAID1] = {
- .sub_stripes = 1,
- .dev_stripes = 1,
- .devs_max = 2,
- .devs_min = 2,
- .devs_increment = 2,
- .ncopies = 2,
- },
- [BTRFS_RAID_DUP] = {
- .sub_stripes = 1,
- .dev_stripes = 2,
- .devs_max = 1,
- .devs_min = 1,
- .devs_increment = 1,
- .ncopies = 2,
- },
- [BTRFS_RAID_RAID0] = {
- .sub_stripes = 1,
- .dev_stripes = 1,
- .devs_max = 0,
- .devs_min = 2,
- .devs_increment = 1,
- .ncopies = 1,
- },
- [BTRFS_RAID_SINGLE] = {
- .sub_stripes = 1,
- .dev_stripes = 1,
- .devs_max = 1,
- .devs_min = 1,
- .devs_increment = 1,
- .ncopies = 1,
- },
- [BTRFS_RAID_RAID5] = {
- .sub_stripes = 1,
- .dev_stripes = 1,
- .devs_max = 0,
- .devs_min = 2,
- .devs_increment = 1,
- .ncopies = 2,
- },
- [BTRFS_RAID_RAID6] = {
- .sub_stripes = 1,
- .dev_stripes = 1,
- .devs_max = 0,
- .devs_min = 3,
- .devs_increment = 1,
- .ncopies = 3,
- },
-};
-
static u32 find_raid56_stripe_len(u32 data_devices, u32 dev_stripe_target)
{
/* TODO allow them to set a preferred stripe size */
BUG_ON(!path);
ret = btrfs_search_slot(trans, dev_root, &key, path, -1, 1);
if (ret < 0) {
- printk_in_rcu(KERN_WARNING "BTRFS: "
- "error %d while searching for dev_stats item for device %s!\n",
+ btrfs_warn_in_rcu(dev_root->fs_info,
+ "error %d while searching for dev_stats item for device %s",
ret, rcu_str_deref(device->name));
goto out;
}
/* need to delete old one and insert a new one */
ret = btrfs_del_item(trans, dev_root, path);
if (ret != 0) {
- printk_in_rcu(KERN_WARNING "BTRFS: "
- "delete too small dev_stats item for device %s failed %d!\n",
+ btrfs_warn_in_rcu(dev_root->fs_info,
+ "delete too small dev_stats item for device %s failed %d",
rcu_str_deref(device->name), ret);
goto out;
}
ret = btrfs_insert_empty_item(trans, dev_root, path,
&key, sizeof(*ptr));
if (ret < 0) {
- printk_in_rcu(KERN_WARNING "BTRFS: "
- "insert dev_stats item for device %s failed %d!\n",
- rcu_str_deref(device->name), ret);
+ btrfs_warn_in_rcu(dev_root->fs_info,
+ "insert dev_stats item for device %s failed %d",
+ rcu_str_deref(device->name), ret);
goto out;
}
}
{
if (!dev->dev_stats_valid)
return;
- printk_ratelimited_in_rcu(KERN_ERR "BTRFS: "
- "bdev %s errs: wr %u, rd %u, flush %u, corrupt %u, gen %u\n",
+ btrfs_err_rl_in_rcu(dev->dev_root->fs_info,
+ "bdev %s errs: wr %u, rd %u, flush %u, corrupt %u, gen %u",
rcu_str_deref(dev->name),
btrfs_dev_stat_read(dev, BTRFS_DEV_STAT_WRITE_ERRS),
btrfs_dev_stat_read(dev, BTRFS_DEV_STAT_READ_ERRS),
if (i == BTRFS_DEV_STAT_VALUES_MAX)
return; /* all values == 0, suppress message */
- printk_in_rcu(KERN_INFO "BTRFS: "
- "bdev %s errs: wr %u, rd %u, flush %u, corrupt %u, gen %u\n",
+ btrfs_info_in_rcu(dev->dev_root->fs_info,
+ "bdev %s errs: wr %u, rd %u, flush %u, corrupt %u, gen %u",
rcu_str_deref(dev->name),
btrfs_dev_stat_read(dev, BTRFS_DEV_STAT_WRITE_ERRS),
btrfs_dev_stat_read(dev, BTRFS_DEV_STAT_READ_ERRS),
return 0;
}
-int btrfs_scratch_superblock(struct btrfs_device *device)
+void btrfs_scratch_superblocks(struct block_device *bdev, char *device_path)
{
struct buffer_head *bh;
struct btrfs_super_block *disk_super;
+ int copy_num;
- bh = btrfs_read_dev_super(device->bdev);
- if (!bh)
- return -EINVAL;
- disk_super = (struct btrfs_super_block *)bh->b_data;
+ if (!bdev)
+ return;
- memset(&disk_super->magic, 0, sizeof(disk_super->magic));
- set_buffer_dirty(bh);
- sync_dirty_buffer(bh);
- brelse(bh);
+ for (copy_num = 0; copy_num < BTRFS_SUPER_MIRROR_MAX;
+ copy_num++) {
- return 0;
+ if (btrfs_read_dev_one_super(bdev, copy_num, &bh))
+ continue;
+
+ disk_super = (struct btrfs_super_block *)bh->b_data;
+
+ memset(&disk_super->magic, 0, sizeof(disk_super->magic));
+ set_buffer_dirty(bh);
+ sync_dirty_buffer(bh);
+ brelse(bh);
+ }
+
+ /* Notify udev that device has changed */
+ btrfs_kobject_uevent(bdev, KOBJ_CHANGE);
+
+ /* Update ctime/mtime for device path for libblkid */
+ update_dev_time(device_path);
}
/*
fs_devices = fs_devices->seed;
}
}
+
+void btrfs_close_one_device(struct btrfs_device *device)
+{
+ struct btrfs_fs_devices *fs_devices = device->fs_devices;
+ struct btrfs_device *new_device;
+ struct rcu_string *name;
+
+ if (device->bdev)
+ fs_devices->open_devices--;
+
+ if (device->writeable &&
+ device->devid != BTRFS_DEV_REPLACE_DEVID) {
+ list_del_init(&device->dev_alloc_list);
+ fs_devices->rw_devices--;
+ }
+
+ if (device->missing)
+ fs_devices->missing_devices--;
+
+ new_device = btrfs_alloc_device(NULL, &device->devid,
+ device->uuid);
+ BUG_ON(IS_ERR(new_device)); /* -ENOMEM */
+
+ /* Safe because we are under uuid_mutex */
+ if (device->name) {
+ name = rcu_string_strdup(device->name->str, GFP_NOFS);
+ BUG_ON(!name); /* -ENOMEM */
+ rcu_assign_pointer(new_device->name, name);
+ }
+
+ list_replace_rcu(&device->dev_list, &new_device->dev_list);
+ new_device->fs_devices = device->fs_devices;
+
+ call_rcu(&device->rcu, free_device);
+}
"lblock %lu mapped to illegal pblock "
"(length %d)", (unsigned long) map->m_lblk,
map->m_len);
- return -EIO;
+ return -EFSCORRUPTED;
}
return 0;
}
/* We can handle the block number less than EXT_MAX_BLOCKS */
if (unlikely(map->m_lblk >= EXT_MAX_BLOCKS))
- return -EIO;
+ return -EFSCORRUPTED;
/* Lookup extent status tree firstly */
if (ext4_es_lookup_extent(inode, map->m_lblk, &es)) {
if (unlikely(err))
page_zero_new_buffers(page, from, to);
else if (decrypt)
- err = ext4_decrypt_one(inode, page);
+ err = ext4_decrypt(page);
return err;
}
#endif
return ret ? ret : copied;
}
+/*
+ * This is a private version of page_zero_new_buffers() which doesn't
+ * set the buffer to be dirty, since in data=journalled mode we need
+ * to call ext4_handle_dirty_metadata() instead.
+ */
+static void zero_new_buffers(struct page *page, unsigned from, unsigned to)
+{
+ unsigned int block_start = 0, block_end;
+ struct buffer_head *head, *bh;
+
+ bh = head = page_buffers(page);
+ do {
+ block_end = block_start + bh->b_size;
+ if (buffer_new(bh)) {
+ if (block_end > from && block_start < to) {
+ if (!PageUptodate(page)) {
+ unsigned start, size;
+
+ start = max(from, block_start);
+ size = min(to, block_end) - start;
+
+ zero_user(page, start, size);
+ set_buffer_uptodate(bh);
+ }
+ clear_buffer_new(bh);
+ }
+ }
+ block_start = block_end;
+ bh = bh->b_this_page;
+ } while (bh != head);
+}
+
static int ext4_journalled_write_end(struct file *file,
struct address_space *mapping,
loff_t pos, unsigned len, unsigned copied,
if (copied < len) {
if (!PageUptodate(page))
copied = 0;
- page_zero_new_buffers(page, from+copied, to);
+ zero_new_buffers(page, from+copied, to);
}
ret = ext4_walk_page_buffers(handle, page_buffers(page), from,
* the page. But we may reach here when we do a journal commit via
* journal_submit_inode_data_buffers() and in that case we must write
* allocated buffers to achieve data=ordered mode guarantees.
+ *
+ * Also, if there is only one buffer per page (the fs block
+ * size == the page size), if one buffer needs block
+ * allocation or needs to modify the extent tree to clear the
+ * unwritten flag, we know that the page can't be written at
+ * all, so we might as well refuse the write immediately.
+ * Unfortunately if the block size != page size, we can't as
+ * easily detect this case using ext4_walk_page_buffers(), but
+ * for the extremely common case, this is an optimization that
+ * skips a useless round trip through ext4_bio_write_page().
*/
if (ext4_walk_page_buffers(NULL, page_bufs, 0, len, NULL,
ext4_bh_delay_or_unwritten)) {
redirty_page_for_writepage(wbc, page);
- if (current->flags & PF_MEMALLOC) {
+ if ((current->flags & PF_MEMALLOC) ||
+ (inode->i_sb->s_blocksize == PAGE_CACHE_SIZE)) {
/*
* For memory cleaning there's no point in writing only
* some buffers. So just bail out. Warn if we came here
/* We always reserve for an inode update; the superblock could be there too */
static int ext4_da_write_credits(struct inode *inode, loff_t pos, unsigned len)
{
- if (likely(EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
- EXT4_FEATURE_RO_COMPAT_LARGE_FILE)))
+ if (likely(ext4_has_feature_large_file(inode->i_sb)))
return 1;
if (pos + len <= 0x7fffffffULL)
int err = 0;
page = find_or_create_page(mapping, from >> PAGE_CACHE_SHIFT,
- mapping_gfp_mask(mapping) & ~__GFP_FS);
+ mapping_gfp_constraint(mapping, ~__GFP_FS));
if (!page)
return -ENOMEM;
/* We expect the key to be set. */
BUG_ON(!ext4_has_encryption_key(inode));
BUG_ON(blocksize != PAGE_CACHE_SIZE);
- WARN_ON_ONCE(ext4_decrypt_one(inode, page));
+ WARN_ON_ONCE(ext4_decrypt(page));
}
}
if (ext4_should_journal_data(inode)) {
iloc->bh = NULL;
if (!ext4_valid_inum(sb, inode->i_ino))
- return -EIO;
+ return -EFSCORRUPTED;
iloc->block_group = (inode->i_ino - 1) / EXT4_INODES_PER_GROUP(sb);
gdp = ext4_get_group_desc(sb, iloc->block_group, NULL);
struct inode *inode = &(ei->vfs_inode);
struct super_block *sb = inode->i_sb;
- if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
- EXT4_FEATURE_RO_COMPAT_HUGE_FILE)) {
+ if (ext4_has_feature_huge_file(sb)) {
/* we are using combined 48 bit field */
i_blocks = ((u64)le16_to_cpu(raw_inode->i_blocks_high)) << 32 |
le32_to_cpu(raw_inode->i_blocks_lo);
EXT4_ERROR_INODE(inode, "bad extra_isize (%u != %u)",
EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize,
EXT4_INODE_SIZE(inode->i_sb));
- ret = -EIO;
+ ret = -EFSCORRUPTED;
goto bad_inode;
}
} else
if (!ext4_inode_csum_verify(inode, raw_inode, ei)) {
EXT4_ERROR_INODE(inode, "checksum invalid");
- ret = -EIO;
+ ret = -EFSBADCRC;
goto bad_inode;
}
ei->i_flags = le32_to_cpu(raw_inode->i_flags);
inode->i_blocks = ext4_inode_blocks(raw_inode, ei);
ei->i_file_acl = le32_to_cpu(raw_inode->i_file_acl_lo);
- if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_64BIT))
+ if (ext4_has_feature_64bit(sb))
ei->i_file_acl |=
((__u64)le16_to_cpu(raw_inode->i_file_acl_high)) << 32;
inode->i_size = ext4_isize(raw_inode);
!ext4_data_block_valid(EXT4_SB(sb), ei->i_file_acl, 1)) {
EXT4_ERROR_INODE(inode, "bad extended attribute block %llu",
ei->i_file_acl);
- ret = -EIO;
+ ret = -EFSCORRUPTED;
goto bad_inode;
} else if (!ext4_has_inline_data(inode)) {
if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
} else if (ino == EXT4_BOOT_LOADER_INO) {
make_bad_inode(inode);
} else {
- ret = -EIO;
+ ret = -EFSCORRUPTED;
EXT4_ERROR_INODE(inode, "bogus i_mode (%o)", inode->i_mode);
goto bad_inode;
}
struct inode *ext4_iget_normal(struct super_block *sb, unsigned long ino)
{
if (ino < EXT4_FIRST_INO(sb) && ino != EXT4_ROOT_INO)
- return ERR_PTR(-EIO);
+ return ERR_PTR(-EFSCORRUPTED);
return ext4_iget(sb, ino);
}
ext4_clear_inode_flag(inode, EXT4_INODE_HUGE_FILE);
return 0;
}
- if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_HUGE_FILE))
+ if (!ext4_has_feature_huge_file(sb))
return -EFBIG;
if (i_blocks <= 0xffffffffffffULL) {
need_datasync = 1;
}
if (ei->i_disksize > 0x7fffffffULL) {
- if (!EXT4_HAS_RO_COMPAT_FEATURE(sb,
- EXT4_FEATURE_RO_COMPAT_LARGE_FILE) ||
+ if (!ext4_has_feature_large_file(sb) ||
EXT4_SB(sb)->s_es->s_rev_level ==
cpu_to_le32(EXT4_GOOD_OLD_REV))
set_large_file = 1;
if (err)
goto out_brelse;
ext4_update_dynamic_rev(sb);
- EXT4_SET_RO_COMPAT_FEATURE(sb,
- EXT4_FEATURE_RO_COMPAT_LARGE_FILE);
+ ext4_set_feature_large_file(sb);
ext4_handle_sync(handle);
err = ext4_handle_dirty_super(handle, sb);
}
bio_for_each_segment_all(bv, bio, i) {
struct page *page = bv->bv_page;
- int ret = ext4_decrypt(ctx, page);
+ int ret = ext4_decrypt(page);
if (ret) {
WARN_ON_ONCE(1);
SetPageError(page);
page = list_entry(pages->prev, struct page, lru);
list_del(&page->lru);
if (add_to_page_cache_lru(page, mapping, page->index,
- GFP_KERNEL & mapping_gfp_mask(mapping)))
+ mapping_gfp_constraint(mapping, GFP_KERNEL)))
goto next_page;
}
#include <linux/namei.h>
#include <linux/quotaops.h>
#include <linux/seq_file.h>
-#include <linux/proc_fs.h>
#include <linux/ctype.h>
#include <linux/log2.h>
#include <linux/crc16.h>
#define CREATE_TRACE_POINTS
#include <trace/events/ext4.h>
-static struct proc_dir_entry *ext4_proc_root;
-static struct kset *ext4_kset;
static struct ext4_lazy_init *ext4_li_info;
static struct mutex ext4_li_mtx;
-static struct ext4_features *ext4_feat;
static int ext4_mballoc_ready;
static struct ratelimit_state ext4_mount_msg_ratelimit;
static void ext4_destroy_lazyinit_thread(void);
static void ext4_unregister_li_request(struct super_block *sb);
static void ext4_clear_request_list(void);
-static int ext4_reserve_clusters(struct ext4_sb_info *, ext4_fsblk_t);
#if !defined(CONFIG_EXT2_FS) && !defined(CONFIG_EXT2_FS_MODULE) && defined(CONFIG_EXT4_USE_FOR_EXT2)
static struct file_system_type ext2_fs_type = {
static int ext4_verify_csum_type(struct super_block *sb,
struct ext4_super_block *es)
{
- if (!EXT4_HAS_RO_COMPAT_FEATURE(sb,
- EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+ if (!ext4_has_feature_metadata_csum(sb))
return 1;
return es->s_checksum_type == EXT4_CRC32C_CHKSUM;
smp_wmb();
sb->s_flags |= MS_RDONLY;
}
- if (test_opt(sb, ERRORS_PANIC))
+ if (test_opt(sb, ERRORS_PANIC)) {
+ if (EXT4_SB(sb)->s_journal &&
+ !(EXT4_SB(sb)->s_journal->j_flags & JBD2_REC_ERR))
+ return;
panic("EXT4-fs (device %s): panic forced after error\n",
sb->s_id);
+ }
}
#define ext4_error_ratelimit(sb) \
char *errstr = NULL;
switch (errno) {
+ case -EFSCORRUPTED:
+ errstr = "Corrupt filesystem";
+ break;
+ case -EFSBADCRC:
+ errstr = "Filesystem failed CRC";
+ break;
case -EIO:
errstr = "IO failure";
break;
jbd2_journal_abort(EXT4_SB(sb)->s_journal, -EIO);
save_error_info(sb, function, line);
}
- if (test_opt(sb, ERRORS_PANIC))
+ if (test_opt(sb, ERRORS_PANIC)) {
+ if (EXT4_SB(sb)->s_journal &&
+ !(EXT4_SB(sb)->s_journal->j_flags & JBD2_REC_ERR))
+ return;
panic("EXT4-fs panic from previous error\n");
+ }
}
void __ext4_msg(struct super_block *sb,
ext4_abort(sb, "Couldn't clean up the journal");
}
+ ext4_unregister_sysfs(sb);
ext4_es_unregister_shrinker(sbi);
del_timer_sync(&sbi->s_err_report);
ext4_release_system_zone(sb);
ext4_xattr_put_super(sb);
if (!(sb->s_flags & MS_RDONLY)) {
- EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
+ ext4_clear_feature_journal_needs_recovery(sb);
es->s_state = cpu_to_le16(sbi->s_mount_state);
}
if (!(sb->s_flags & MS_RDONLY))
ext4_commit_super(sb, 1);
- if (sbi->s_proc) {
- remove_proc_entry("options", sbi->s_proc);
- remove_proc_entry(sb->s_id, ext4_proc_root);
- }
- kobject_del(&sbi->s_kobj);
-
for (i = 0; i < sbi->s_gdb_count; i++)
brelse(sbi->s_group_desc[i]);
kvfree(sbi->s_group_desc);
return 0;
if (journal)
return jbd2_journal_try_to_free_buffers(journal, page,
- wait & ~__GFP_WAIT);
+ wait & ~__GFP_DIRECT_RECLAIM);
return try_to_free_buffers(page);
}
"quota options when quota turned on");
return -1;
}
- if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA)) {
+ if (ext4_has_feature_quota(sb)) {
ext4_msg(sb, KERN_ERR, "Cannot set journaled quota options "
"when QUOTA feature is enabled");
return -1;
{Opt_nojournal_checksum, EXT4_MOUNT_JOURNAL_CHECKSUM,
MOPT_EXT4_ONLY | MOPT_CLEAR},
{Opt_journal_checksum, EXT4_MOUNT_JOURNAL_CHECKSUM,
- MOPT_EXT4_ONLY | MOPT_SET},
+ MOPT_EXT4_ONLY | MOPT_SET | MOPT_EXPLICIT},
{Opt_journal_async_commit, (EXT4_MOUNT_JOURNAL_ASYNC_COMMIT |
EXT4_MOUNT_JOURNAL_CHECKSUM),
- MOPT_EXT4_ONLY | MOPT_SET},
+ MOPT_EXT4_ONLY | MOPT_SET | MOPT_EXPLICIT},
{Opt_noload, EXT4_MOUNT_NOLOAD, MOPT_NO_EXT2 | MOPT_SET},
{Opt_err_panic, EXT4_MOUNT_ERRORS_PANIC, MOPT_SET | MOPT_CLEAR_ERR},
{Opt_err_ro, EXT4_MOUNT_ERRORS_RO, MOPT_SET | MOPT_CLEAR_ERR},
return -1;
if (args->from && (m->flags & MOPT_GTE0) && (arg < 0))
return -1;
- if (m->flags & MOPT_EXPLICIT)
- set_opt2(sb, EXPLICIT_DELALLOC);
+ if (m->flags & MOPT_EXPLICIT) {
+ if (m->mount_opt & EXT4_MOUNT_DELALLOC) {
+ set_opt2(sb, EXPLICIT_DELALLOC);
+ } else if (m->mount_opt & EXT4_MOUNT_JOURNAL_CHECKSUM) {
+ set_opt2(sb, EXPLICIT_JOURNAL_CHECKSUM);
+ } else
+ return -1;
+ }
if (m->flags & MOPT_CLEAR_ERR)
clear_opt(sb, ERRORS_MASK);
if (token == Opt_noquota && sb_any_quota_loaded(sb)) {
"quota options when quota turned on");
return -1;
}
- if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
- EXT4_FEATURE_RO_COMPAT_QUOTA)) {
+ if (ext4_has_feature_quota(sb)) {
ext4_msg(sb, KERN_ERR,
"Cannot set journaled quota options "
"when QUOTA feature is enabled");
return 0;
}
#ifdef CONFIG_QUOTA
- if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA) &&
+ if (ext4_has_feature_quota(sb) &&
(test_opt(sb, USRQUOTA) || test_opt(sb, GRPQUOTA))) {
ext4_msg(sb, KERN_ERR, "Cannot set quota options when QUOTA "
"feature is enabled");
return _ext4_show_options(seq, root->d_sb, 0);
}
-static int options_seq_show(struct seq_file *seq, void *offset)
+int ext4_seq_options_show(struct seq_file *seq, void *offset)
{
struct super_block *sb = seq->private;
int rc;
return rc;
}
-static int options_open_fs(struct inode *inode, struct file *file)
-{
- return single_open(file, options_seq_show, PDE_DATA(inode));
-}
-
-static const struct file_operations ext4_seq_options_fops = {
- .owner = THIS_MODULE,
- .open = options_open_fs,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es,
int read_only)
{
es->s_mtime = cpu_to_le32(get_seconds());
ext4_update_dynamic_rev(sb);
if (sbi->s_journal)
- EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
+ ext4_set_feature_journal_needs_recovery(sb);
ext4_commit_super(sb, 1);
done:
return 0;
}
-static __le16 ext4_group_desc_csum(struct ext4_sb_info *sbi, __u32 block_group,
+static __le16 ext4_group_desc_csum(struct super_block *sb, __u32 block_group,
struct ext4_group_desc *gdp)
{
int offset;
__u16 crc = 0;
__le32 le_group = cpu_to_le32(block_group);
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
if (ext4_has_metadata_csum(sbi->s_sb)) {
/* Use new metadata_csum algorithm */
}
/* old crc16 code */
- if (!(sbi->s_es->s_feature_ro_compat &
- cpu_to_le32(EXT4_FEATURE_RO_COMPAT_GDT_CSUM)))
+ if (!ext4_has_feature_gdt_csum(sb))
return 0;
offset = offsetof(struct ext4_group_desc, bg_checksum);
crc = crc16(crc, (__u8 *)gdp, offset);
offset += sizeof(gdp->bg_checksum); /* skip checksum */
/* for checksum of struct ext4_group_desc do the rest...*/
- if ((sbi->s_es->s_feature_incompat &
- cpu_to_le32(EXT4_FEATURE_INCOMPAT_64BIT)) &&
+ if (ext4_has_feature_64bit(sb) &&
offset < le16_to_cpu(sbi->s_es->s_desc_size))
crc = crc16(crc, (__u8 *)gdp + offset,
le16_to_cpu(sbi->s_es->s_desc_size) -
struct ext4_group_desc *gdp)
{
if (ext4_has_group_desc_csum(sb) &&
- (gdp->bg_checksum != ext4_group_desc_csum(EXT4_SB(sb),
- block_group, gdp)))
+ (gdp->bg_checksum != ext4_group_desc_csum(sb, block_group, gdp)))
return 0;
return 1;
{
if (!ext4_has_group_desc_csum(sb))
return;
- gdp->bg_checksum = ext4_group_desc_csum(EXT4_SB(sb), block_group, gdp);
+ gdp->bg_checksum = ext4_group_desc_csum(sb, block_group, gdp);
}
/* Called at mount-time, super-block is locked */
int flexbg_flag = 0;
ext4_group_t i, grp = sbi->s_groups_count;
- if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG))
+ if (ext4_has_feature_flex_bg(sb))
flexbg_flag = 1;
ext4_debug("Checking group descriptors");
if (!ext4_group_desc_csum_verify(sb, i, gdp)) {
ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
"Checksum for group %u failed (%u!=%u)",
- i, le16_to_cpu(ext4_group_desc_csum(sbi, i,
+ i, le16_to_cpu(ext4_group_desc_csum(sb, i,
gdp)), le16_to_cpu(gdp->bg_checksum));
if (!(sb->s_flags & MS_RDONLY)) {
ext4_unlock_group(sb, i);
first_meta_bg = le32_to_cpu(sbi->s_es->s_first_meta_bg);
- if (!EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_META_BG) ||
- nr < first_meta_bg)
+ if (!ext4_has_feature_meta_bg(sb) || nr < first_meta_bg)
return logical_sb_block + nr + 1;
bg = sbi->s_desc_per_block * nr;
if (ext4_bg_has_super(sb, bg))
return ret;
}
-/* sysfs supprt */
-
-struct ext4_attr {
- struct attribute attr;
- ssize_t (*show)(struct ext4_attr *, struct ext4_sb_info *, char *);
- ssize_t (*store)(struct ext4_attr *, struct ext4_sb_info *,
- const char *, size_t);
- union {
- int offset;
- int deprecated_val;
- } u;
-};
-
-static int parse_strtoull(const char *buf,
- unsigned long long max, unsigned long long *value)
-{
- int ret;
-
- ret = kstrtoull(skip_spaces(buf), 0, value);
- if (!ret && *value > max)
- ret = -EINVAL;
- return ret;
-}
-
-static ssize_t delayed_allocation_blocks_show(struct ext4_attr *a,
- struct ext4_sb_info *sbi,
- char *buf)
-{
- return snprintf(buf, PAGE_SIZE, "%llu\n",
- (s64) EXT4_C2B(sbi,
- percpu_counter_sum(&sbi->s_dirtyclusters_counter)));
-}
-
-static ssize_t session_write_kbytes_show(struct ext4_attr *a,
- struct ext4_sb_info *sbi, char *buf)
-{
- struct super_block *sb = sbi->s_buddy_cache->i_sb;
-
- if (!sb->s_bdev->bd_part)
- return snprintf(buf, PAGE_SIZE, "0\n");
- return snprintf(buf, PAGE_SIZE, "%lu\n",
- (part_stat_read(sb->s_bdev->bd_part, sectors[1]) -
- sbi->s_sectors_written_start) >> 1);
-}
-
-static ssize_t lifetime_write_kbytes_show(struct ext4_attr *a,
- struct ext4_sb_info *sbi, char *buf)
-{
- struct super_block *sb = sbi->s_buddy_cache->i_sb;
-
- if (!sb->s_bdev->bd_part)
- return snprintf(buf, PAGE_SIZE, "0\n");
- return snprintf(buf, PAGE_SIZE, "%llu\n",
- (unsigned long long)(sbi->s_kbytes_written +
- ((part_stat_read(sb->s_bdev->bd_part, sectors[1]) -
- EXT4_SB(sb)->s_sectors_written_start) >> 1)));
-}
-
-static ssize_t inode_readahead_blks_store(struct ext4_attr *a,
- struct ext4_sb_info *sbi,
- const char *buf, size_t count)
-{
- unsigned long t;
- int ret;
-
- ret = kstrtoul(skip_spaces(buf), 0, &t);
- if (ret)
- return ret;
-
- if (t && (!is_power_of_2(t) || t > 0x40000000))
- return -EINVAL;
-
- sbi->s_inode_readahead_blks = t;
- return count;
-}
-
-static ssize_t sbi_ui_show(struct ext4_attr *a,
- struct ext4_sb_info *sbi, char *buf)
-{
- unsigned int *ui = (unsigned int *) (((char *) sbi) + a->u.offset);
-
- return snprintf(buf, PAGE_SIZE, "%u\n", *ui);
-}
-
-static ssize_t sbi_ui_store(struct ext4_attr *a,
- struct ext4_sb_info *sbi,
- const char *buf, size_t count)
-{
- unsigned int *ui = (unsigned int *) (((char *) sbi) + a->u.offset);
- unsigned long t;
- int ret;
-
- ret = kstrtoul(skip_spaces(buf), 0, &t);
- if (ret)
- return ret;
- *ui = t;
- return count;
-}
-
-static ssize_t es_ui_show(struct ext4_attr *a,
- struct ext4_sb_info *sbi, char *buf)
-{
-
- unsigned int *ui = (unsigned int *) (((char *) sbi->s_es) +
- a->u.offset);
-
- return snprintf(buf, PAGE_SIZE, "%u\n", *ui);
-}
-
-static ssize_t reserved_clusters_show(struct ext4_attr *a,
- struct ext4_sb_info *sbi, char *buf)
-{
- return snprintf(buf, PAGE_SIZE, "%llu\n",
- (unsigned long long) atomic64_read(&sbi->s_resv_clusters));
-}
-
-static ssize_t reserved_clusters_store(struct ext4_attr *a,
- struct ext4_sb_info *sbi,
- const char *buf, size_t count)
-{
- unsigned long long val;
- int ret;
-
- if (parse_strtoull(buf, -1ULL, &val))
- return -EINVAL;
- ret = ext4_reserve_clusters(sbi, val);
-
- return ret ? ret : count;
-}
-
-static ssize_t trigger_test_error(struct ext4_attr *a,
- struct ext4_sb_info *sbi,
- const char *buf, size_t count)
-{
- int len = count;
-
- if (!capable(CAP_SYS_ADMIN))
- return -EPERM;
-
- if (len && buf[len-1] == '\n')
- len--;
-
- if (len)
- ext4_error(sbi->s_sb, "%.*s", len, buf);
- return count;
-}
-
-static ssize_t sbi_deprecated_show(struct ext4_attr *a,
- struct ext4_sb_info *sbi, char *buf)
-{
- return snprintf(buf, PAGE_SIZE, "%d\n", a->u.deprecated_val);
-}
-
-#define EXT4_ATTR_OFFSET(_name,_mode,_show,_store,_elname) \
-static struct ext4_attr ext4_attr_##_name = { \
- .attr = {.name = __stringify(_name), .mode = _mode }, \
- .show = _show, \
- .store = _store, \
- .u = { \
- .offset = offsetof(struct ext4_sb_info, _elname),\
- }, \
-}
-
-#define EXT4_ATTR_OFFSET_ES(_name,_mode,_show,_store,_elname) \
-static struct ext4_attr ext4_attr_##_name = { \
- .attr = {.name = __stringify(_name), .mode = _mode }, \
- .show = _show, \
- .store = _store, \
- .u = { \
- .offset = offsetof(struct ext4_super_block, _elname), \
- }, \
-}
-
-#define EXT4_ATTR(name, mode, show, store) \
-static struct ext4_attr ext4_attr_##name = __ATTR(name, mode, show, store)
-
-#define EXT4_INFO_ATTR(name) EXT4_ATTR(name, 0444, NULL, NULL)
-#define EXT4_RO_ATTR(name) EXT4_ATTR(name, 0444, name##_show, NULL)
-#define EXT4_RW_ATTR(name) EXT4_ATTR(name, 0644, name##_show, name##_store)
-
-#define EXT4_RO_ATTR_ES_UI(name, elname) \
- EXT4_ATTR_OFFSET_ES(name, 0444, es_ui_show, NULL, elname)
-#define EXT4_RW_ATTR_SBI_UI(name, elname) \
- EXT4_ATTR_OFFSET(name, 0644, sbi_ui_show, sbi_ui_store, elname)
-
-#define ATTR_LIST(name) &ext4_attr_##name.attr
-#define EXT4_DEPRECATED_ATTR(_name, _val) \
-static struct ext4_attr ext4_attr_##_name = { \
- .attr = {.name = __stringify(_name), .mode = 0444 }, \
- .show = sbi_deprecated_show, \
- .u = { \
- .deprecated_val = _val, \
- }, \
-}
-
-EXT4_RO_ATTR(delayed_allocation_blocks);
-EXT4_RO_ATTR(session_write_kbytes);
-EXT4_RO_ATTR(lifetime_write_kbytes);
-EXT4_RW_ATTR(reserved_clusters);
-EXT4_ATTR_OFFSET(inode_readahead_blks, 0644, sbi_ui_show,
- inode_readahead_blks_store, s_inode_readahead_blks);
-EXT4_RW_ATTR_SBI_UI(inode_goal, s_inode_goal);
-EXT4_RW_ATTR_SBI_UI(mb_stats, s_mb_stats);
-EXT4_RW_ATTR_SBI_UI(mb_max_to_scan, s_mb_max_to_scan);
-EXT4_RW_ATTR_SBI_UI(mb_min_to_scan, s_mb_min_to_scan);
-EXT4_RW_ATTR_SBI_UI(mb_order2_req, s_mb_order2_reqs);
-EXT4_RW_ATTR_SBI_UI(mb_stream_req, s_mb_stream_request);
-EXT4_RW_ATTR_SBI_UI(mb_group_prealloc, s_mb_group_prealloc);
-EXT4_DEPRECATED_ATTR(max_writeback_mb_bump, 128);
-EXT4_RW_ATTR_SBI_UI(extent_max_zeroout_kb, s_extent_max_zeroout_kb);
-EXT4_ATTR(trigger_fs_error, 0200, NULL, trigger_test_error);
-EXT4_RW_ATTR_SBI_UI(err_ratelimit_interval_ms, s_err_ratelimit_state.interval);
-EXT4_RW_ATTR_SBI_UI(err_ratelimit_burst, s_err_ratelimit_state.burst);
-EXT4_RW_ATTR_SBI_UI(warning_ratelimit_interval_ms, s_warning_ratelimit_state.interval);
-EXT4_RW_ATTR_SBI_UI(warning_ratelimit_burst, s_warning_ratelimit_state.burst);
-EXT4_RW_ATTR_SBI_UI(msg_ratelimit_interval_ms, s_msg_ratelimit_state.interval);
-EXT4_RW_ATTR_SBI_UI(msg_ratelimit_burst, s_msg_ratelimit_state.burst);
-EXT4_RO_ATTR_ES_UI(errors_count, s_error_count);
-EXT4_RO_ATTR_ES_UI(first_error_time, s_first_error_time);
-EXT4_RO_ATTR_ES_UI(last_error_time, s_last_error_time);
-
-static struct attribute *ext4_attrs[] = {
- ATTR_LIST(delayed_allocation_blocks),
- ATTR_LIST(session_write_kbytes),
- ATTR_LIST(lifetime_write_kbytes),
- ATTR_LIST(reserved_clusters),
- ATTR_LIST(inode_readahead_blks),
- ATTR_LIST(inode_goal),
- ATTR_LIST(mb_stats),
- ATTR_LIST(mb_max_to_scan),
- ATTR_LIST(mb_min_to_scan),
- ATTR_LIST(mb_order2_req),
- ATTR_LIST(mb_stream_req),
- ATTR_LIST(mb_group_prealloc),
- ATTR_LIST(max_writeback_mb_bump),
- ATTR_LIST(extent_max_zeroout_kb),
- ATTR_LIST(trigger_fs_error),
- ATTR_LIST(err_ratelimit_interval_ms),
- ATTR_LIST(err_ratelimit_burst),
- ATTR_LIST(warning_ratelimit_interval_ms),
- ATTR_LIST(warning_ratelimit_burst),
- ATTR_LIST(msg_ratelimit_interval_ms),
- ATTR_LIST(msg_ratelimit_burst),
- ATTR_LIST(errors_count),
- ATTR_LIST(first_error_time),
- ATTR_LIST(last_error_time),
- NULL,
-};
-
-/* Features this copy of ext4 supports */
-EXT4_INFO_ATTR(lazy_itable_init);
-EXT4_INFO_ATTR(batched_discard);
-EXT4_INFO_ATTR(meta_bg_resize);
-EXT4_INFO_ATTR(encryption);
-
-static struct attribute *ext4_feat_attrs[] = {
- ATTR_LIST(lazy_itable_init),
- ATTR_LIST(batched_discard),
- ATTR_LIST(meta_bg_resize),
- ATTR_LIST(encryption),
- NULL,
-};
-
-static ssize_t ext4_attr_show(struct kobject *kobj,
- struct attribute *attr, char *buf)
-{
- struct ext4_sb_info *sbi = container_of(kobj, struct ext4_sb_info,
- s_kobj);
- struct ext4_attr *a = container_of(attr, struct ext4_attr, attr);
-
- return a->show ? a->show(a, sbi, buf) : 0;
-}
-
-static ssize_t ext4_attr_store(struct kobject *kobj,
- struct attribute *attr,
- const char *buf, size_t len)
-{
- struct ext4_sb_info *sbi = container_of(kobj, struct ext4_sb_info,
- s_kobj);
- struct ext4_attr *a = container_of(attr, struct ext4_attr, attr);
-
- return a->store ? a->store(a, sbi, buf, len) : 0;
-}
-
-static void ext4_sb_release(struct kobject *kobj)
-{
- struct ext4_sb_info *sbi = container_of(kobj, struct ext4_sb_info,
- s_kobj);
- complete(&sbi->s_kobj_unregister);
-}
-
-static const struct sysfs_ops ext4_attr_ops = {
- .show = ext4_attr_show,
- .store = ext4_attr_store,
-};
-
-static struct kobj_type ext4_ktype = {
- .default_attrs = ext4_attrs,
- .sysfs_ops = &ext4_attr_ops,
- .release = ext4_sb_release,
-};
-
-static void ext4_feat_release(struct kobject *kobj)
-{
- complete(&ext4_feat->f_kobj_unregister);
-}
-
-static ssize_t ext4_feat_show(struct kobject *kobj,
- struct attribute *attr, char *buf)
-{
- return snprintf(buf, PAGE_SIZE, "supported\n");
-}
-
-/*
- * We can not use ext4_attr_show/store because it relies on the kobject
- * being embedded in the ext4_sb_info structure which is definitely not
- * true in this case.
- */
-static const struct sysfs_ops ext4_feat_ops = {
- .show = ext4_feat_show,
- .store = NULL,
-};
-
-static struct kobj_type ext4_feat_ktype = {
- .default_attrs = ext4_feat_attrs,
- .sysfs_ops = &ext4_feat_ops,
- .release = ext4_feat_release,
-};
-
/*
* Check whether this filesystem can be mounted based on
* the features present and the RDONLY/RDWR mount requested.
*/
static int ext4_feature_set_ok(struct super_block *sb, int readonly)
{
- if (EXT4_HAS_INCOMPAT_FEATURE(sb, ~EXT4_FEATURE_INCOMPAT_SUPP)) {
+ if (ext4_has_unknown_ext4_incompat_features(sb)) {
ext4_msg(sb, KERN_ERR,
"Couldn't mount because of "
"unsupported optional features (%x)",
if (readonly)
return 1;
- if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_READONLY)) {
+ if (ext4_has_feature_readonly(sb)) {
ext4_msg(sb, KERN_INFO, "filesystem is read-only");
sb->s_flags |= MS_RDONLY;
return 1;
}
/* Check that feature set is OK for a read-write mount */
- if (EXT4_HAS_RO_COMPAT_FEATURE(sb, ~EXT4_FEATURE_RO_COMPAT_SUPP)) {
+ if (ext4_has_unknown_ext4_ro_compat_features(sb)) {
ext4_msg(sb, KERN_ERR, "couldn't mount RDWR because of "
"unsupported optional features (%x)",
(le32_to_cpu(EXT4_SB(sb)->s_es->s_feature_ro_compat) &
* Large file size enabled file system can only be mounted
* read-write on 32-bit systems if kernel is built with CONFIG_LBDAF
*/
- if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_HUGE_FILE)) {
+ if (ext4_has_feature_huge_file(sb)) {
if (sizeof(blkcnt_t) < sizeof(u64)) {
ext4_msg(sb, KERN_ERR, "Filesystem with huge files "
"cannot be mounted RDWR without "
return 0;
}
}
- if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_BIGALLOC) &&
- !EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS)) {
+ if (ext4_has_feature_bigalloc(sb) && !ext4_has_feature_extents(sb)) {
ext4_msg(sb, KERN_ERR,
"Can't support bigalloc feature without "
"extents feature\n");
}
#ifndef CONFIG_QUOTA
- if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA) &&
- !readonly) {
+ if (ext4_has_feature_quota(sb) && !readonly) {
ext4_msg(sb, KERN_ERR,
"Filesystem with quota feature cannot be mounted RDWR "
"without CONFIG_QUOTA");
ext4_group_t i, ngroups = ext4_get_groups_count(sb);
int s, j, count = 0;
- if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_BIGALLOC))
+ if (!ext4_has_feature_bigalloc(sb))
return (ext4_bg_has_super(sb, grp) + ext4_bg_num_gdb(sb, grp) +
sbi->s_itb_per_group + 2);
return 0;
}
-
-static ext4_fsblk_t ext4_calculate_resv_clusters(struct super_block *sb)
+static void ext4_set_resv_clusters(struct super_block *sb)
{
ext4_fsblk_t resv_clusters;
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
/*
* There's no need to reserve anything when we aren't using extents.
* hole punching doesn't need new metadata... This is needed especially
* to keep ext2/3 backward compatibility.
*/
- if (!EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS))
- return 0;
+ if (!ext4_has_feature_extents(sb))
+ return;
/*
* By default we reserve 2% or 4096 clusters, whichever is smaller.
* This should cover the situations where we can not afford to run
* allocation would require 1, or 2 blocks, higher numbers are
* very rare.
*/
- resv_clusters = ext4_blocks_count(EXT4_SB(sb)->s_es) >>
- EXT4_SB(sb)->s_cluster_bits;
+ resv_clusters = (ext4_blocks_count(sbi->s_es) >>
+ sbi->s_cluster_bits);
do_div(resv_clusters, 50);
resv_clusters = min_t(ext4_fsblk_t, resv_clusters, 4096);
- return resv_clusters;
-}
-
-
-static int ext4_reserve_clusters(struct ext4_sb_info *sbi, ext4_fsblk_t count)
-{
- ext4_fsblk_t clusters = ext4_blocks_count(sbi->s_es) >>
- sbi->s_cluster_bits;
-
- if (count >= clusters)
- return -EINVAL;
-
- atomic64_set(&sbi->s_resv_clusters, count);
- return 0;
+ atomic64_set(&sbi->s_resv_clusters, resv_clusters);
}
static int ext4_fill_super(struct super_block *sb, void *data, int silent)
sbi->s_kbytes_written = le64_to_cpu(es->s_kbytes_written);
/* Warn if metadata_csum and gdt_csum are both set. */
- if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
- EXT4_FEATURE_RO_COMPAT_METADATA_CSUM) &&
- EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_GDT_CSUM))
+ if (ext4_has_feature_metadata_csum(sb) &&
+ ext4_has_feature_gdt_csum(sb))
ext4_warning(sb, "metadata_csum and uninit_bg are "
"redundant flags; please run fsck.");
}
/* Load the checksum driver */
- if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
- EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) {
+ if (ext4_has_feature_metadata_csum(sb)) {
sbi->s_chksum_driver = crypto_alloc_shash("crc32c", 0, 0);
if (IS_ERR(sbi->s_chksum_driver)) {
ext4_msg(sb, KERN_ERR, "Cannot load crc32c driver.");
ext4_msg(sb, KERN_ERR, "VFS: Found ext4 filesystem with "
"invalid superblock checksum. Run e2fsck?");
silent = 1;
+ ret = -EFSBADCRC;
goto cantfind_ext4;
}
/* Precompute checksum seed for all metadata */
- if (ext4_has_metadata_csum(sb))
+ if (ext4_has_feature_csum_seed(sb))
+ sbi->s_csum_seed = le32_to_cpu(es->s_checksum_seed);
+ else if (ext4_has_metadata_csum(sb))
sbi->s_csum_seed = ext4_chksum(sbi, ~0, es->s_uuid,
sizeof(es->s_uuid));
(test_opt(sb, POSIX_ACL) ? MS_POSIXACL : 0);
if (le32_to_cpu(es->s_rev_level) == EXT4_GOOD_OLD_REV &&
- (EXT4_HAS_COMPAT_FEATURE(sb, ~0U) ||
- EXT4_HAS_RO_COMPAT_FEATURE(sb, ~0U) ||
- EXT4_HAS_INCOMPAT_FEATURE(sb, ~0U)))
+ (ext4_has_compat_features(sb) ||
+ ext4_has_ro_compat_features(sb) ||
+ ext4_has_incompat_features(sb)))
ext4_msg(sb, KERN_WARNING,
"feature flags set on rev 0 fs, "
"running e2fsck is recommended");
if (es->s_creator_os == cpu_to_le32(EXT4_OS_HURD)) {
set_opt2(sb, HURD_COMPAT);
- if (EXT4_HAS_INCOMPAT_FEATURE(sb,
- EXT4_FEATURE_INCOMPAT_64BIT)) {
+ if (ext4_has_feature_64bit(sb)) {
ext4_msg(sb, KERN_ERR,
"The Hurd can't support 64-bit file systems");
goto failed_mount;
}
}
- if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_ENCRYPT) &&
- es->s_encryption_level) {
+ if (ext4_has_feature_encrypt(sb) && es->s_encryption_level) {
ext4_msg(sb, KERN_ERR, "Unsupported encryption level %d",
es->s_encryption_level);
goto failed_mount;
}
}
- has_huge_files = EXT4_HAS_RO_COMPAT_FEATURE(sb,
- EXT4_FEATURE_RO_COMPAT_HUGE_FILE);
+ has_huge_files = ext4_has_feature_huge_file(sb);
sbi->s_bitmap_maxbytes = ext4_max_bitmap_size(sb->s_blocksize_bits,
has_huge_files);
sb->s_maxbytes = ext4_max_size(sb->s_blocksize_bits, has_huge_files);
}
sbi->s_desc_size = le16_to_cpu(es->s_desc_size);
- if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_64BIT)) {
+ if (ext4_has_feature_64bit(sb)) {
if (sbi->s_desc_size < EXT4_MIN_DESC_SIZE_64BIT ||
sbi->s_desc_size > EXT4_MAX_DESC_SIZE ||
!is_power_of_2(sbi->s_desc_size)) {
for (i = 0; i < 4; i++)
sbi->s_hash_seed[i] = le32_to_cpu(es->s_hash_seed[i]);
sbi->s_def_hash_version = es->s_def_hash_version;
- if (EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_DIR_INDEX)) {
+ if (ext4_has_feature_dir_index(sb)) {
i = le32_to_cpu(es->s_flags);
if (i & EXT2_FLAGS_UNSIGNED_HASH)
sbi->s_hash_unsigned = 3;
/* Handle clustersize */
clustersize = BLOCK_SIZE << le32_to_cpu(es->s_log_cluster_size);
- has_bigalloc = EXT4_HAS_RO_COMPAT_FEATURE(sb,
- EXT4_FEATURE_RO_COMPAT_BIGALLOC);
+ has_bigalloc = ext4_has_feature_bigalloc(sb);
if (has_bigalloc) {
if (clustersize < blocksize) {
ext4_msg(sb, KERN_ERR,
goto failed_mount;
}
- if (ext4_proc_root)
- sbi->s_proc = proc_mkdir(sb->s_id, ext4_proc_root);
-
- if (sbi->s_proc)
- proc_create_data("options", S_IRUGO, sbi->s_proc,
- &ext4_seq_options_fops, sb);
-
bgl_lock_init(sbi->s_blockgroup_lock);
for (i = 0; i < db_count; i++) {
}
if (!ext4_check_descriptors(sb, &first_not_zeroed)) {
ext4_msg(sb, KERN_ERR, "group descriptors corrupted!");
+ ret = -EFSCORRUPTED;
goto failed_mount2;
}
sb->s_xattr = ext4_xattr_handlers;
#ifdef CONFIG_QUOTA
sb->dq_op = &ext4_quota_operations;
- if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA))
+ if (ext4_has_feature_quota(sb))
sb->s_qcop = &dquot_quotactl_sysfile_ops;
else
sb->s_qcop = &ext4_qctl_operations;
sb->s_root = NULL;
needs_recovery = (es->s_last_orphan != 0 ||
- EXT4_HAS_INCOMPAT_FEATURE(sb,
- EXT4_FEATURE_INCOMPAT_RECOVER));
+ ext4_has_feature_journal_needs_recovery(sb));
- if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_MMP) &&
- !(sb->s_flags & MS_RDONLY))
+ if (ext4_has_feature_mmp(sb) && !(sb->s_flags & MS_RDONLY))
if (ext4_multi_mount_protect(sb, le64_to_cpu(es->s_mmp_block)))
goto failed_mount3a;
* The first inode we look at is the journal inode. Don't try
* root first: it may be modified in the journal!
*/
- if (!test_opt(sb, NOLOAD) &&
- EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL)) {
+ if (!test_opt(sb, NOLOAD) && ext4_has_feature_journal(sb)) {
if (ext4_load_journal(sb, es, journal_devnum))
goto failed_mount3a;
} else if (test_opt(sb, NOLOAD) && !(sb->s_flags & MS_RDONLY) &&
- EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER)) {
+ ext4_has_feature_journal_needs_recovery(sb)) {
ext4_msg(sb, KERN_ERR, "required journal recovery "
"suppressed and not mounted read-only");
goto failed_mount_wq;
} else {
+ /* Nojournal mode, all journal mount options are illegal */
+ if (test_opt2(sb, EXPLICIT_JOURNAL_CHECKSUM)) {
+ ext4_msg(sb, KERN_ERR, "can't mount with "
+ "journal_checksum, fs mounted w/o journal");
+ goto failed_mount_wq;
+ }
+ if (test_opt(sb, JOURNAL_ASYNC_COMMIT)) {
+ ext4_msg(sb, KERN_ERR, "can't mount with "
+ "journal_async_commit, fs mounted w/o journal");
+ goto failed_mount_wq;
+ }
+ if (sbi->s_commit_interval != JBD2_DEFAULT_MAX_COMMIT_AGE*HZ) {
+ ext4_msg(sb, KERN_ERR, "can't mount with "
+ "commit=%lu, fs mounted w/o journal",
+ sbi->s_commit_interval / HZ);
+ goto failed_mount_wq;
+ }
+ if (EXT4_MOUNT_DATA_FLAGS &
+ (sbi->s_mount_opt ^ sbi->s_def_mount_opt)) {
+ ext4_msg(sb, KERN_ERR, "can't mount with "
+ "data=, fs mounted w/o journal");
+ goto failed_mount_wq;
+ }
+ sbi->s_def_mount_opt &= EXT4_MOUNT_JOURNAL_CHECKSUM;
+ clear_opt(sb, JOURNAL_CHECKSUM);
clear_opt(sb, DATA_FLAGS);
sbi->s_journal = NULL;
needs_recovery = 0;
goto no_journal;
}
- if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_64BIT) &&
+ if (ext4_has_feature_64bit(sb) &&
!jbd2_journal_set_features(EXT4_SB(sb)->s_journal, 0, 0,
JBD2_FEATURE_INCOMPAT_64BIT)) {
ext4_msg(sb, KERN_ERR, "Failed to set 64-bit journal feature");
}
}
- if ((DUMMY_ENCRYPTION_ENABLED(sbi) ||
- EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_ENCRYPT)) &&
+ if ((DUMMY_ENCRYPTION_ENABLED(sbi) || ext4_has_feature_encrypt(sb)) &&
(blocksize != PAGE_CACHE_SIZE)) {
ext4_msg(sb, KERN_ERR,
"Unsupported blocksize for fs encryption");
goto failed_mount_wq;
}
- if (DUMMY_ENCRYPTION_ENABLED(sbi) &&
- !(sb->s_flags & MS_RDONLY) &&
- !EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_ENCRYPT)) {
- EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_ENCRYPT);
+ if (DUMMY_ENCRYPTION_ENABLED(sbi) && !(sb->s_flags & MS_RDONLY) &&
+ !ext4_has_feature_encrypt(sb)) {
+ ext4_set_feature_encrypt(sb);
ext4_commit_super(sb, 1);
}
if (sbi->s_inode_size > EXT4_GOOD_OLD_INODE_SIZE) {
sbi->s_want_extra_isize = sizeof(struct ext4_inode) -
EXT4_GOOD_OLD_INODE_SIZE;
- if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
- EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE)) {
+ if (ext4_has_feature_extra_isize(sb)) {
if (sbi->s_want_extra_isize <
le16_to_cpu(es->s_want_extra_isize))
sbi->s_want_extra_isize =
"available");
}
- err = ext4_reserve_clusters(sbi, ext4_calculate_resv_clusters(sb));
- if (err) {
- ext4_msg(sb, KERN_ERR, "failed to reserve %llu clusters for "
- "reserved pool", ext4_calculate_resv_clusters(sb));
- goto failed_mount4a;
- }
+ ext4_set_resv_clusters(sb);
err = ext4_setup_system_zone(sb);
if (err) {
goto failed_mount6;
}
- if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG))
+ if (ext4_has_feature_flex_bg(sb))
if (!ext4_fill_flex_info(sb)) {
ext4_msg(sb, KERN_ERR,
"unable to initialize "
if (err)
goto failed_mount6;
- sbi->s_kobj.kset = ext4_kset;
- init_completion(&sbi->s_kobj_unregister);
- err = kobject_init_and_add(&sbi->s_kobj, &ext4_ktype, NULL,
- "%s", sb->s_id);
+ err = ext4_register_sysfs(sb);
if (err)
goto failed_mount7;
#ifdef CONFIG_QUOTA
/* Enable quota usage during mount. */
- if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA) &&
- !(sb->s_flags & MS_RDONLY)) {
+ if (ext4_has_feature_quota(sb) && !(sb->s_flags & MS_RDONLY)) {
err = ext4_enable_quotas(sb);
if (err)
goto failed_mount8;
#ifdef CONFIG_QUOTA
failed_mount8:
- kobject_del(&sbi->s_kobj);
+ ext4_unregister_sysfs(sb);
#endif
failed_mount7:
ext4_unregister_li_request(sb);
failed_mount:
if (sbi->s_chksum_driver)
crypto_free_shash(sbi->s_chksum_driver);
- if (sbi->s_proc) {
- remove_proc_entry("options", sbi->s_proc);
- remove_proc_entry(sb->s_id, ext4_proc_root);
- }
#ifdef CONFIG_QUOTA
for (i = 0; i < EXT4_MAXQUOTAS; i++)
kfree(sbi->s_qf_names[i]);
struct inode *journal_inode;
journal_t *journal;
- BUG_ON(!EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL));
+ BUG_ON(!ext4_has_feature_journal(sb));
/* First, test for the existence of a valid inode on disk. Bad
* things happen if we iget() an unused inode, as the subsequent
struct ext4_super_block *es;
struct block_device *bdev;
- BUG_ON(!EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL));
+ BUG_ON(!ext4_has_feature_journal(sb));
bdev = ext4_blkdev_get(j_dev, sb);
if (bdev == NULL)
int err = 0;
int really_read_only;
- BUG_ON(!EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL));
+ BUG_ON(!ext4_has_feature_journal(sb));
if (journal_devnum &&
journal_devnum != le32_to_cpu(es->s_journal_dev)) {
* crash? For recovery, we need to check in advance whether we
* can get read-write access to the device.
*/
- if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER)) {
+ if (ext4_has_feature_journal_needs_recovery(sb)) {
if (sb->s_flags & MS_RDONLY) {
ext4_msg(sb, KERN_INFO, "INFO: recovery "
"required on readonly filesystem");
if (!(journal->j_flags & JBD2_BARRIER))
ext4_msg(sb, KERN_INFO, "barriers disabled");
- if (!EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER))
+ if (!ext4_has_feature_journal_needs_recovery(sb))
err = jbd2_journal_wipe(journal, !really_read_only);
if (!err) {
char *save = kmalloc(EXT4_S_ERR_LEN, GFP_KERNEL);
{
journal_t *journal = EXT4_SB(sb)->s_journal;
- if (!EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL)) {
+ if (!ext4_has_feature_journal(sb)) {
BUG_ON(journal != NULL);
return;
}
if (jbd2_journal_flush(journal) < 0)
goto out;
- if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER) &&
+ if (ext4_has_feature_journal_needs_recovery(sb) &&
sb->s_flags & MS_RDONLY) {
- EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
+ ext4_clear_feature_journal_needs_recovery(sb);
ext4_commit_super(sb, 1);
}
int j_errno;
const char *errstr;
- BUG_ON(!EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL));
+ BUG_ON(!ext4_has_feature_journal(sb));
journal = EXT4_SB(sb)->s_journal;
goto out;
/* Journal blocked and flushed, clear needs_recovery flag. */
- EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
+ ext4_clear_feature_journal_needs_recovery(sb);
}
error = ext4_commit_super(sb, 1);
if (EXT4_SB(sb)->s_journal) {
/* Reset the needs_recovery flag before the fs is unlocked. */
- EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
+ ext4_set_feature_journal_needs_recovery(sb);
}
ext4_commit_super(sb, 1);
ext4_mark_recovery_complete(sb, es);
} else {
/* Make sure we can mount this feature set readwrite */
- if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
- EXT4_FEATURE_RO_COMPAT_READONLY) ||
+ if (ext4_has_feature_readonly(sb) ||
!ext4_feature_set_ok(sb, 0)) {
err = -EROFS;
goto restore_opts;
if (!ext4_group_desc_csum_verify(sb, g, gdp)) {
ext4_msg(sb, KERN_ERR,
"ext4_remount: Checksum for group %u failed (%u!=%u)",
- g, le16_to_cpu(ext4_group_desc_csum(sbi, g, gdp)),
+ g, le16_to_cpu(ext4_group_desc_csum(sb, g, gdp)),
le16_to_cpu(gdp->bg_checksum));
- err = -EINVAL;
+ err = -EFSBADCRC;
goto restore_opts;
}
}
sbi->s_mount_state = le16_to_cpu(es->s_state);
if (!ext4_setup_super(sb, es, 0))
sb->s_flags &= ~MS_RDONLY;
- if (EXT4_HAS_INCOMPAT_FEATURE(sb,
- EXT4_FEATURE_INCOMPAT_MMP))
+ if (ext4_has_feature_mmp(sb))
if (ext4_multi_mount_protect(sb,
le64_to_cpu(es->s_mmp_block))) {
err = -EROFS;
if (enable_quota) {
if (sb_any_quota_suspended(sb))
dquot_resume(sb, -1);
- else if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
- EXT4_FEATURE_RO_COMPAT_QUOTA)) {
+ else if (ext4_has_feature_quota(sb)) {
err = ext4_enable_quotas(sb);
if (err)
goto restore_opts;
struct ext4_sb_info *sbi = EXT4_SB(sb);
/* Are we journaling quotas? */
- if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA) ||
+ if (ext4_has_feature_quota(sb) ||
sbi->s_qf_names[USRQUOTA] || sbi->s_qf_names[GRPQUOTA]) {
dquot_mark_dquot_dirty(dquot);
return ext4_write_dquot(dquot);
le32_to_cpu(EXT4_SB(sb)->s_es->s_grp_quota_inum)
};
- BUG_ON(!EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA));
+ BUG_ON(!ext4_has_feature_quota(sb));
if (!qf_inums[type])
return -EPERM;
static inline int ext2_feature_set_ok(struct super_block *sb)
{
- if (EXT4_HAS_INCOMPAT_FEATURE(sb, ~EXT2_FEATURE_INCOMPAT_SUPP))
+ if (ext4_has_unknown_ext2_incompat_features(sb))
return 0;
if (sb->s_flags & MS_RDONLY)
return 1;
- if (EXT4_HAS_RO_COMPAT_FEATURE(sb, ~EXT2_FEATURE_RO_COMPAT_SUPP))
+ if (ext4_has_unknown_ext2_ro_compat_features(sb))
return 0;
return 1;
}
static inline int ext3_feature_set_ok(struct super_block *sb)
{
- if (EXT4_HAS_INCOMPAT_FEATURE(sb, ~EXT3_FEATURE_INCOMPAT_SUPP))
+ if (ext4_has_unknown_ext3_incompat_features(sb))
return 0;
- if (!EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL))
+ if (!ext4_has_feature_journal(sb))
return 0;
if (sb->s_flags & MS_RDONLY)
return 1;
- if (EXT4_HAS_RO_COMPAT_FEATURE(sb, ~EXT3_FEATURE_RO_COMPAT_SUPP))
+ if (ext4_has_unknown_ext3_ro_compat_features(sb))
return 0;
return 1;
}
};
MODULE_ALIAS_FS("ext4");
-static int __init ext4_init_feat_adverts(void)
-{
- struct ext4_features *ef;
- int ret = -ENOMEM;
-
- ef = kzalloc(sizeof(struct ext4_features), GFP_KERNEL);
- if (!ef)
- goto out;
-
- ef->f_kobj.kset = ext4_kset;
- init_completion(&ef->f_kobj_unregister);
- ret = kobject_init_and_add(&ef->f_kobj, &ext4_feat_ktype, NULL,
- "features");
- if (ret) {
- kfree(ef);
- goto out;
- }
-
- ext4_feat = ef;
- ret = 0;
-out:
- return ret;
-}
-
-static void ext4_exit_feat_adverts(void)
-{
- kobject_put(&ext4_feat->f_kobj);
- wait_for_completion(&ext4_feat->f_kobj_unregister);
- kfree(ext4_feat);
-}
-
/* Shared across all ext4 file systems */
wait_queue_head_t ext4__ioend_wq[EXT4_WQ_HASH_SZ];
struct mutex ext4__aio_mutex[EXT4_WQ_HASH_SZ];
err = ext4_init_pageio();
if (err)
- goto out7;
+ goto out5;
err = ext4_init_system_zone();
if (err)
- goto out6;
- ext4_kset = kset_create_and_add("ext4", NULL, fs_kobj);
- if (!ext4_kset) {
- err = -ENOMEM;
- goto out5;
- }
- ext4_proc_root = proc_mkdir("fs/ext4", NULL);
+ goto out4;
- err = ext4_init_feat_adverts();
+ err = ext4_init_sysfs();
if (err)
- goto out4;
+ goto out3;
err = ext4_init_mballoc();
if (err)
ext4_mballoc_ready = 0;
ext4_exit_mballoc();
out2:
- ext4_exit_feat_adverts();
-out4:
- if (ext4_proc_root)
- remove_proc_entry("fs/ext4", NULL);
- kset_unregister(ext4_kset);
-out5:
+ ext4_exit_sysfs();
+out3:
ext4_exit_system_zone();
-out6:
+out4:
ext4_exit_pageio();
-out7:
+out5:
ext4_exit_es();
return err;
unregister_filesystem(&ext4_fs_type);
destroy_inodecache();
ext4_exit_mballoc();
- ext4_exit_feat_adverts();
- remove_proc_entry("fs/ext4", NULL);
- kset_unregister(ext4_kset);
+ ext4_exit_sysfs();
ext4_exit_system_zone();
ext4_exit_pageio();
ext4_exit_es();
if ((c->flash_size % c->sector_size) != 0) {
c->flash_size = (c->flash_size / c->sector_size) * c->sector_size;
pr_warn("flash size adjusted to %dKiB\n", c->flash_size);
- };
+ }
c->wbuf_ofs = 0xFFFFFFFF;
c->wbuf = kmalloc(c->wbuf_pagesize, GFP_KERNEL);
#ifdef CONFIG_JFFS2_FS_WBUF_VERIFY
c->wbuf_verify = kmalloc(c->wbuf_pagesize, GFP_KERNEL);
if (!c->wbuf_verify) {
- kfree(c->oobbuf);
kfree(c->wbuf);
return -ENOMEM;
}
if (err) {
const char *s = get_link(nd);
- if (unlikely(IS_ERR(s)))
+ if (IS_ERR(s))
return PTR_ERR(s);
err = 0;
if (unlikely(!s)) {
return ERR_PTR(-ELOOP);
filename = getname_kernel(name);
- if (unlikely(IS_ERR(filename)))
+ if (IS_ERR(filename))
return ERR_CAST(filename);
set_nameidata(&nd, -1, filename);
int page_symlink(struct inode *inode, const char *symname, int len)
{
return __page_symlink(inode, symname, len,
- !(mapping_gfp_mask(inode->i_mapping) & __GFP_FS));
+ !mapping_gfp_constraint(inode->i_mapping, __GFP_FS));
}
EXPORT_SYMBOL(page_symlink);
for_each_populated_zone(zone)
nr_zones++;
- /* Make sure at least 2 hugepages are free for MIGRATE_RESERVE */
+ /* Ensure 2 pageblocks are free to assist fragmentation avoidance */
recommended_min = pageblock_nr_pages * nr_zones * 2;
/*
if (!khugepaged_thread)
khugepaged_thread = kthread_run(khugepaged, NULL,
"khugepaged");
- if (unlikely(IS_ERR(khugepaged_thread))) {
+ if (IS_ERR(khugepaged_thread)) {
pr_err("khugepaged: kthread_run(khugepaged) failed\n");
err = PTR_ERR(khugepaged_thread);
khugepaged_thread = NULL;
static inline gfp_t alloc_hugepage_gfpmask(int defrag, gfp_t extra_gfp)
{
- return (GFP_TRANSHUGE & ~(defrag ? 0 : __GFP_WAIT)) | extra_gfp;
+ return (GFP_TRANSHUGE & ~(defrag ? 0 : __GFP_RECLAIM)) | extra_gfp;
}
/* Caller must hold page table lock. */
(1L << PG_unevictable)));
page_tail->flags |= (1L << PG_dirty);
- /* clear PageTail before overwriting first_page */
- smp_wmb();
+ clear_compound_head(page_tail);
if (page_is_young(page))
set_page_young(page_tail);
static struct page *
khugepaged_alloc_page(struct page **hpage, gfp_t gfp, struct mm_struct *mm,
- struct vm_area_struct *vma, unsigned long address,
- int node)
+ unsigned long address, int node)
{
VM_BUG_ON_PAGE(*hpage, *hpage);
static struct page *
khugepaged_alloc_page(struct page **hpage, gfp_t gfp, struct mm_struct *mm,
- struct vm_area_struct *vma, unsigned long address,
- int node)
+ unsigned long address, int node)
{
up_read(&mm->mmap_sem);
VM_BUG_ON(!*hpage);
__GFP_THISNODE;
/* release the mmap_sem read lock. */
- new_page = khugepaged_alloc_page(hpage, gfp, mm, vma, address, node);
+ new_page = khugepaged_alloc_page(hpage, gfp, mm, address, node);
if (!new_page)
return;