#include <linux/kthread.h>
#include <linux/raid/pq.h>
#include <linux/async_tx.h>
+#include <linux/async.h>
#include <linux/seq_file.h>
+#include <linux/cpu.h>
#include "md.h"
#include "raid5.h"
#include "bitmap.h"
static struct stripe_head *
get_active_stripe(raid5_conf_t *conf, sector_t sector,
- int previous, int noblock)
+ int previous, int noblock, int noquiesce)
{
struct stripe_head *sh;
do {
wait_event_lock_irq(conf->wait_for_stripe,
- conf->quiesce == 0,
+ conf->quiesce == 0 || noquiesce,
conf->device_lock, /* nothing */);
sh = __find_stripe(conf, sector, conf->generation - previous);
if (!sh) {
struct page *bio_page;
int i;
int page_offset;
+ struct async_submit_ctl submit;
+ enum async_tx_flags flags = 0;
if (bio->bi_sector >= sector)
page_offset = (signed)(bio->bi_sector - sector) * 512;
else
page_offset = (signed)(sector - bio->bi_sector) * -512;
+
+ if (frombio)
+ flags |= ASYNC_TX_FENCE;
+ init_async_submit(&submit, flags, tx, NULL, NULL, NULL);
+
bio_for_each_segment(bvl, bio, i) {
int len = bio_iovec_idx(bio, i)->bv_len;
int clen;
bio_page = bio_iovec_idx(bio, i)->bv_page;
if (frombio)
tx = async_memcpy(page, bio_page, page_offset,
- b_offset, clen,
- ASYNC_TX_DEP_ACK,
- tx, NULL, NULL);
+ b_offset, clen, &submit);
else
tx = async_memcpy(bio_page, page, b_offset,
- page_offset, clen,
- ASYNC_TX_DEP_ACK,
- tx, NULL, NULL);
+ page_offset, clen, &submit);
}
+ /* chain the operations */
+ submit.depend_tx = tx;
+
if (clen < len) /* hit end of page */
break;
page_offset += len;
{
struct dma_async_tx_descriptor *tx = NULL;
raid5_conf_t *conf = sh->raid_conf;
+ struct async_submit_ctl submit;
int i;
pr_debug("%s: stripe %llu\n", __func__,
}
atomic_inc(&sh->count);
- async_trigger_callback(ASYNC_TX_DEP_ACK | ASYNC_TX_ACK, tx,
- ops_complete_biofill, sh);
+ init_async_submit(&submit, ASYNC_TX_ACK, tx, ops_complete_biofill, sh, NULL);
+ async_trigger_callback(&submit);
}
-static void ops_complete_compute5(void *stripe_head_ref)
+static void mark_target_uptodate(struct stripe_head *sh, int target)
{
- struct stripe_head *sh = stripe_head_ref;
- int target = sh->ops.target;
- struct r5dev *tgt = &sh->dev[target];
+ struct r5dev *tgt;
- pr_debug("%s: stripe %llu\n", __func__,
- (unsigned long long)sh->sector);
+ if (target < 0)
+ return;
+ tgt = &sh->dev[target];
set_bit(R5_UPTODATE, &tgt->flags);
BUG_ON(!test_bit(R5_Wantcompute, &tgt->flags));
clear_bit(R5_Wantcompute, &tgt->flags);
+}
+
+static void ops_complete_compute(void *stripe_head_ref)
+{
+ struct stripe_head *sh = stripe_head_ref;
+
+ pr_debug("%s: stripe %llu\n", __func__,
+ (unsigned long long)sh->sector);
+
+ /* mark the computed target(s) as uptodate */
+ mark_target_uptodate(sh, sh->ops.target);
+ mark_target_uptodate(sh, sh->ops.target2);
+
clear_bit(STRIPE_COMPUTE_RUN, &sh->state);
if (sh->check_state == check_state_compute_run)
sh->check_state = check_state_compute_result;
release_stripe(sh);
}
-static struct dma_async_tx_descriptor *ops_run_compute5(struct stripe_head *sh)
+/* return a pointer to the address conversion region of the scribble buffer */
+static addr_conv_t *to_addr_conv(struct stripe_head *sh,
+ struct raid5_percpu *percpu)
+{
+ return percpu->scribble + sizeof(struct page *) * (sh->disks + 2);
+}
+
+static struct dma_async_tx_descriptor *
+ops_run_compute5(struct stripe_head *sh, struct raid5_percpu *percpu)
{
- /* kernel stack size limits the total number of disks */
int disks = sh->disks;
- struct page *xor_srcs[disks];
+ struct page **xor_srcs = percpu->scribble;
int target = sh->ops.target;
struct r5dev *tgt = &sh->dev[target];
struct page *xor_dest = tgt->page;
int count = 0;
struct dma_async_tx_descriptor *tx;
+ struct async_submit_ctl submit;
int i;
pr_debug("%s: stripe %llu block: %d\n",
atomic_inc(&sh->count);
+ init_async_submit(&submit, ASYNC_TX_FENCE|ASYNC_TX_XOR_ZERO_DST, NULL,
+ ops_complete_compute, sh, to_addr_conv(sh, percpu));
if (unlikely(count == 1))
- tx = async_memcpy(xor_dest, xor_srcs[0], 0, 0, STRIPE_SIZE,
- 0, NULL, ops_complete_compute5, sh);
+ tx = async_memcpy(xor_dest, xor_srcs[0], 0, 0, STRIPE_SIZE, &submit);
+ else
+ tx = async_xor(xor_dest, xor_srcs, 0, count, STRIPE_SIZE, &submit);
+
+ return tx;
+}
+
+/* set_syndrome_sources - populate source buffers for gen_syndrome
+ * @srcs - (struct page *) array of size sh->disks
+ * @sh - stripe_head to parse
+ *
+ * Populates srcs in proper layout order for the stripe and returns the
+ * 'count' of sources to be used in a call to async_gen_syndrome. The P
+ * destination buffer is recorded in srcs[count] and the Q destination
+ * is recorded in srcs[count+1]].
+ */
+static int set_syndrome_sources(struct page **srcs, struct stripe_head *sh)
+{
+ int disks = sh->disks;
+ int syndrome_disks = sh->ddf_layout ? disks : (disks - 2);
+ int d0_idx = raid6_d0(sh);
+ int count;
+ int i;
+
+ for (i = 0; i < disks; i++)
+ srcs[i] = (void *)raid6_empty_zero_page;
+
+ count = 0;
+ i = d0_idx;
+ do {
+ int slot = raid6_idx_to_slot(i, sh, &count, syndrome_disks);
+
+ srcs[slot] = sh->dev[i].page;
+ i = raid6_next_disk(i, disks);
+ } while (i != d0_idx);
+ BUG_ON(count != syndrome_disks);
+
+ return count;
+}
+
+static struct dma_async_tx_descriptor *
+ops_run_compute6_1(struct stripe_head *sh, struct raid5_percpu *percpu)
+{
+ int disks = sh->disks;
+ struct page **blocks = percpu->scribble;
+ int target;
+ int qd_idx = sh->qd_idx;
+ struct dma_async_tx_descriptor *tx;
+ struct async_submit_ctl submit;
+ struct r5dev *tgt;
+ struct page *dest;
+ int i;
+ int count;
+
+ if (sh->ops.target < 0)
+ target = sh->ops.target2;
+ else if (sh->ops.target2 < 0)
+ target = sh->ops.target;
else
- tx = async_xor(xor_dest, xor_srcs, 0, count, STRIPE_SIZE,
- ASYNC_TX_XOR_ZERO_DST, NULL,
- ops_complete_compute5, sh);
+ /* we should only have one valid target */
+ BUG();
+ BUG_ON(target < 0);
+ pr_debug("%s: stripe %llu block: %d\n",
+ __func__, (unsigned long long)sh->sector, target);
+
+ tgt = &sh->dev[target];
+ BUG_ON(!test_bit(R5_Wantcompute, &tgt->flags));
+ dest = tgt->page;
+
+ atomic_inc(&sh->count);
+
+ if (target == qd_idx) {
+ count = set_syndrome_sources(blocks, sh);
+ blocks[count] = NULL; /* regenerating p is not necessary */
+ BUG_ON(blocks[count+1] != dest); /* q should already be set */
+ init_async_submit(&submit, ASYNC_TX_FENCE, NULL,
+ ops_complete_compute, sh,
+ to_addr_conv(sh, percpu));
+ tx = async_gen_syndrome(blocks, 0, count+2, STRIPE_SIZE, &submit);
+ } else {
+ /* Compute any data- or p-drive using XOR */
+ count = 0;
+ for (i = disks; i-- ; ) {
+ if (i == target || i == qd_idx)
+ continue;
+ blocks[count++] = sh->dev[i].page;
+ }
+
+ init_async_submit(&submit, ASYNC_TX_FENCE|ASYNC_TX_XOR_ZERO_DST,
+ NULL, ops_complete_compute, sh,
+ to_addr_conv(sh, percpu));
+ tx = async_xor(dest, blocks, 0, count, STRIPE_SIZE, &submit);
+ }
return tx;
}
+static struct dma_async_tx_descriptor *
+ops_run_compute6_2(struct stripe_head *sh, struct raid5_percpu *percpu)
+{
+ int i, count, disks = sh->disks;
+ int syndrome_disks = sh->ddf_layout ? disks : disks-2;
+ int d0_idx = raid6_d0(sh);
+ int faila = -1, failb = -1;
+ int target = sh->ops.target;
+ int target2 = sh->ops.target2;
+ struct r5dev *tgt = &sh->dev[target];
+ struct r5dev *tgt2 = &sh->dev[target2];
+ struct dma_async_tx_descriptor *tx;
+ struct page **blocks = percpu->scribble;
+ struct async_submit_ctl submit;
+
+ pr_debug("%s: stripe %llu block1: %d block2: %d\n",
+ __func__, (unsigned long long)sh->sector, target, target2);
+ BUG_ON(target < 0 || target2 < 0);
+ BUG_ON(!test_bit(R5_Wantcompute, &tgt->flags));
+ BUG_ON(!test_bit(R5_Wantcompute, &tgt2->flags));
+
+ /* we need to open-code set_syndrome_sources to handle the
+ * slot number conversion for 'faila' and 'failb'
+ */
+ for (i = 0; i < disks ; i++)
+ blocks[i] = (void *)raid6_empty_zero_page;
+ count = 0;
+ i = d0_idx;
+ do {
+ int slot = raid6_idx_to_slot(i, sh, &count, syndrome_disks);
+
+ blocks[slot] = sh->dev[i].page;
+
+ if (i == target)
+ faila = slot;
+ if (i == target2)
+ failb = slot;
+ i = raid6_next_disk(i, disks);
+ } while (i != d0_idx);
+ BUG_ON(count != syndrome_disks);
+
+ BUG_ON(faila == failb);
+ if (failb < faila)
+ swap(faila, failb);
+ pr_debug("%s: stripe: %llu faila: %d failb: %d\n",
+ __func__, (unsigned long long)sh->sector, faila, failb);
+
+ atomic_inc(&sh->count);
+
+ if (failb == syndrome_disks+1) {
+ /* Q disk is one of the missing disks */
+ if (faila == syndrome_disks) {
+ /* Missing P+Q, just recompute */
+ init_async_submit(&submit, ASYNC_TX_FENCE, NULL,
+ ops_complete_compute, sh,
+ to_addr_conv(sh, percpu));
+ return async_gen_syndrome(blocks, 0, count+2,
+ STRIPE_SIZE, &submit);
+ } else {
+ struct page *dest;
+ int data_target;
+ int qd_idx = sh->qd_idx;
+
+ /* Missing D+Q: recompute D from P, then recompute Q */
+ if (target == qd_idx)
+ data_target = target2;
+ else
+ data_target = target;
+
+ count = 0;
+ for (i = disks; i-- ; ) {
+ if (i == data_target || i == qd_idx)
+ continue;
+ blocks[count++] = sh->dev[i].page;
+ }
+ dest = sh->dev[data_target].page;
+ init_async_submit(&submit,
+ ASYNC_TX_FENCE|ASYNC_TX_XOR_ZERO_DST,
+ NULL, NULL, NULL,
+ to_addr_conv(sh, percpu));
+ tx = async_xor(dest, blocks, 0, count, STRIPE_SIZE,
+ &submit);
+
+ count = set_syndrome_sources(blocks, sh);
+ init_async_submit(&submit, ASYNC_TX_FENCE, tx,
+ ops_complete_compute, sh,
+ to_addr_conv(sh, percpu));
+ return async_gen_syndrome(blocks, 0, count+2,
+ STRIPE_SIZE, &submit);
+ }
+ } else {
+ init_async_submit(&submit, ASYNC_TX_FENCE, NULL,
+ ops_complete_compute, sh,
+ to_addr_conv(sh, percpu));
+ if (failb == syndrome_disks) {
+ /* We're missing D+P. */
+ return async_raid6_datap_recov(syndrome_disks+2,
+ STRIPE_SIZE, faila,
+ blocks, &submit);
+ } else {
+ /* We're missing D+D. */
+ return async_raid6_2data_recov(syndrome_disks+2,
+ STRIPE_SIZE, faila, failb,
+ blocks, &submit);
+ }
+ }
+}
+
+
static void ops_complete_prexor(void *stripe_head_ref)
{
struct stripe_head *sh = stripe_head_ref;
}
static struct dma_async_tx_descriptor *
-ops_run_prexor(struct stripe_head *sh, struct dma_async_tx_descriptor *tx)
+ops_run_prexor(struct stripe_head *sh, struct raid5_percpu *percpu,
+ struct dma_async_tx_descriptor *tx)
{
- /* kernel stack size limits the total number of disks */
int disks = sh->disks;
- struct page *xor_srcs[disks];
+ struct page **xor_srcs = percpu->scribble;
int count = 0, pd_idx = sh->pd_idx, i;
+ struct async_submit_ctl submit;
/* existing parity data subtracted */
struct page *xor_dest = xor_srcs[count++] = sh->dev[pd_idx].page;
xor_srcs[count++] = dev->page;
}
- tx = async_xor(xor_dest, xor_srcs, 0, count, STRIPE_SIZE,
- ASYNC_TX_DEP_ACK | ASYNC_TX_XOR_DROP_DST, tx,
- ops_complete_prexor, sh);
+ init_async_submit(&submit, ASYNC_TX_FENCE|ASYNC_TX_XOR_DROP_DST, tx,
+ ops_complete_prexor, sh, to_addr_conv(sh, percpu));
+ tx = async_xor(xor_dest, xor_srcs, 0, count, STRIPE_SIZE, &submit);
return tx;
}
return tx;
}
-static void ops_complete_postxor(void *stripe_head_ref)
+static void ops_complete_reconstruct(void *stripe_head_ref)
{
struct stripe_head *sh = stripe_head_ref;
- int disks = sh->disks, i, pd_idx = sh->pd_idx;
+ int disks = sh->disks;
+ int pd_idx = sh->pd_idx;
+ int qd_idx = sh->qd_idx;
+ int i;
pr_debug("%s: stripe %llu\n", __func__,
(unsigned long long)sh->sector);
for (i = disks; i--; ) {
struct r5dev *dev = &sh->dev[i];
- if (dev->written || i == pd_idx)
+
+ if (dev->written || i == pd_idx || i == qd_idx)
set_bit(R5_UPTODATE, &dev->flags);
}
}
static void
-ops_run_postxor(struct stripe_head *sh, struct dma_async_tx_descriptor *tx)
+ops_run_reconstruct5(struct stripe_head *sh, struct raid5_percpu *percpu,
+ struct dma_async_tx_descriptor *tx)
{
- /* kernel stack size limits the total number of disks */
int disks = sh->disks;
- struct page *xor_srcs[disks];
-
+ struct page **xor_srcs = percpu->scribble;
+ struct async_submit_ctl submit;
int count = 0, pd_idx = sh->pd_idx, i;
struct page *xor_dest;
int prexor = 0;
* set ASYNC_TX_XOR_DROP_DST and ASYNC_TX_XOR_ZERO_DST
* for the synchronous xor case
*/
- flags = ASYNC_TX_DEP_ACK | ASYNC_TX_ACK |
+ flags = ASYNC_TX_ACK |
(prexor ? ASYNC_TX_XOR_DROP_DST : ASYNC_TX_XOR_ZERO_DST);
atomic_inc(&sh->count);
- if (unlikely(count == 1)) {
- flags &= ~(ASYNC_TX_XOR_DROP_DST | ASYNC_TX_XOR_ZERO_DST);
- tx = async_memcpy(xor_dest, xor_srcs[0], 0, 0, STRIPE_SIZE,
- flags, tx, ops_complete_postxor, sh);
- } else
- tx = async_xor(xor_dest, xor_srcs, 0, count, STRIPE_SIZE,
- flags, tx, ops_complete_postxor, sh);
+ init_async_submit(&submit, flags, tx, ops_complete_reconstruct, sh,
+ to_addr_conv(sh, percpu));
+ if (unlikely(count == 1))
+ tx = async_memcpy(xor_dest, xor_srcs[0], 0, 0, STRIPE_SIZE, &submit);
+ else
+ tx = async_xor(xor_dest, xor_srcs, 0, count, STRIPE_SIZE, &submit);
+}
+
+static void
+ops_run_reconstruct6(struct stripe_head *sh, struct raid5_percpu *percpu,
+ struct dma_async_tx_descriptor *tx)
+{
+ struct async_submit_ctl submit;
+ struct page **blocks = percpu->scribble;
+ int count;
+
+ pr_debug("%s: stripe %llu\n", __func__, (unsigned long long)sh->sector);
+
+ count = set_syndrome_sources(blocks, sh);
+
+ atomic_inc(&sh->count);
+
+ init_async_submit(&submit, ASYNC_TX_ACK, tx, ops_complete_reconstruct,
+ sh, to_addr_conv(sh, percpu));
+ async_gen_syndrome(blocks, 0, count+2, STRIPE_SIZE, &submit);
}
static void ops_complete_check(void *stripe_head_ref)
release_stripe(sh);
}
-static void ops_run_check(struct stripe_head *sh)
+static void ops_run_check_p(struct stripe_head *sh, struct raid5_percpu *percpu)
{
- /* kernel stack size limits the total number of disks */
int disks = sh->disks;
- struct page *xor_srcs[disks];
+ int pd_idx = sh->pd_idx;
+ int qd_idx = sh->qd_idx;
+ struct page *xor_dest;
+ struct page **xor_srcs = percpu->scribble;
struct dma_async_tx_descriptor *tx;
-
- int count = 0, pd_idx = sh->pd_idx, i;
- struct page *xor_dest = xor_srcs[count++] = sh->dev[pd_idx].page;
+ struct async_submit_ctl submit;
+ int count;
+ int i;
pr_debug("%s: stripe %llu\n", __func__,
(unsigned long long)sh->sector);
+ count = 0;
+ xor_dest = sh->dev[pd_idx].page;
+ xor_srcs[count++] = xor_dest;
for (i = disks; i--; ) {
- struct r5dev *dev = &sh->dev[i];
- if (i != pd_idx)
- xor_srcs[count++] = dev->page;
+ if (i == pd_idx || i == qd_idx)
+ continue;
+ xor_srcs[count++] = sh->dev[i].page;
}
- tx = async_xor_zero_sum(xor_dest, xor_srcs, 0, count, STRIPE_SIZE,
- &sh->ops.zero_sum_result, 0, NULL, NULL, NULL);
+ init_async_submit(&submit, 0, NULL, NULL, NULL,
+ to_addr_conv(sh, percpu));
+ tx = async_xor_val(xor_dest, xor_srcs, 0, count, STRIPE_SIZE,
+ &sh->ops.zero_sum_result, &submit);
atomic_inc(&sh->count);
- tx = async_trigger_callback(ASYNC_TX_DEP_ACK | ASYNC_TX_ACK, tx,
- ops_complete_check, sh);
+ init_async_submit(&submit, ASYNC_TX_ACK, tx, ops_complete_check, sh, NULL);
+ tx = async_trigger_callback(&submit);
}
-static void raid5_run_ops(struct stripe_head *sh, unsigned long ops_request)
+static void ops_run_check_pq(struct stripe_head *sh, struct raid5_percpu *percpu, int checkp)
+{
+ struct page **srcs = percpu->scribble;
+ struct async_submit_ctl submit;
+ int count;
+
+ pr_debug("%s: stripe %llu checkp: %d\n", __func__,
+ (unsigned long long)sh->sector, checkp);
+
+ count = set_syndrome_sources(srcs, sh);
+ if (!checkp)
+ srcs[count] = NULL;
+
+ atomic_inc(&sh->count);
+ init_async_submit(&submit, ASYNC_TX_ACK, NULL, ops_complete_check,
+ sh, to_addr_conv(sh, percpu));
+ async_syndrome_val(srcs, 0, count+2, STRIPE_SIZE,
+ &sh->ops.zero_sum_result, percpu->spare_page, &submit);
+}
+
+static void raid_run_ops(struct stripe_head *sh, unsigned long ops_request)
{
int overlap_clear = 0, i, disks = sh->disks;
struct dma_async_tx_descriptor *tx = NULL;
+ raid5_conf_t *conf = sh->raid_conf;
+ int level = conf->level;
+ struct raid5_percpu *percpu;
+ unsigned long cpu;
+ cpu = get_cpu();
+ percpu = per_cpu_ptr(conf->percpu, cpu);
if (test_bit(STRIPE_OP_BIOFILL, &ops_request)) {
ops_run_biofill(sh);
overlap_clear++;
}
if (test_bit(STRIPE_OP_COMPUTE_BLK, &ops_request)) {
- tx = ops_run_compute5(sh);
- /* terminate the chain if postxor is not set to be run */
- if (tx && !test_bit(STRIPE_OP_POSTXOR, &ops_request))
+ if (level < 6)
+ tx = ops_run_compute5(sh, percpu);
+ else {
+ if (sh->ops.target2 < 0 || sh->ops.target < 0)
+ tx = ops_run_compute6_1(sh, percpu);
+ else
+ tx = ops_run_compute6_2(sh, percpu);
+ }
+ /* terminate the chain if reconstruct is not set to be run */
+ if (tx && !test_bit(STRIPE_OP_RECONSTRUCT, &ops_request))
async_tx_ack(tx);
}
if (test_bit(STRIPE_OP_PREXOR, &ops_request))
- tx = ops_run_prexor(sh, tx);
+ tx = ops_run_prexor(sh, percpu, tx);
if (test_bit(STRIPE_OP_BIODRAIN, &ops_request)) {
tx = ops_run_biodrain(sh, tx);
overlap_clear++;
}
- if (test_bit(STRIPE_OP_POSTXOR, &ops_request))
- ops_run_postxor(sh, tx);
+ if (test_bit(STRIPE_OP_RECONSTRUCT, &ops_request)) {
+ if (level < 6)
+ ops_run_reconstruct5(sh, percpu, tx);
+ else
+ ops_run_reconstruct6(sh, percpu, tx);
+ }
- if (test_bit(STRIPE_OP_CHECK, &ops_request))
- ops_run_check(sh);
+ if (test_bit(STRIPE_OP_CHECK, &ops_request)) {
+ if (sh->check_state == check_state_run)
+ ops_run_check_p(sh, percpu);
+ else if (sh->check_state == check_state_run_q)
+ ops_run_check_pq(sh, percpu, 0);
+ else if (sh->check_state == check_state_run_pq)
+ ops_run_check_pq(sh, percpu, 1);
+ else
+ BUG();
+ }
if (overlap_clear)
for (i = disks; i--; ) {
if (test_and_clear_bit(R5_Overlap, &dev->flags))
wake_up(&sh->raid_conf->wait_for_overlap);
}
+ put_cpu();
}
static int grow_one_stripe(raid5_conf_t *conf)
return 0;
}
-#ifdef CONFIG_MD_RAID5_RESHAPE
+/**
+ * scribble_len - return the required size of the scribble region
+ * @num - total number of disks in the array
+ *
+ * The size must be enough to contain:
+ * 1/ a struct page pointer for each device in the array +2
+ * 2/ room to convert each entry in (1) to its corresponding dma
+ * (dma_map_page()) or page (page_address()) address.
+ *
+ * Note: the +2 is for the destination buffers of the ddf/raid6 case where we
+ * calculate over all devices (not just the data blocks), using zeros in place
+ * of the P and Q blocks.
+ */
+static size_t scribble_len(int num)
+{
+ size_t len;
+
+ len = sizeof(struct page *) * (num+2) + sizeof(addr_conv_t) * (num+2);
+
+ return len;
+}
+
static int resize_stripes(raid5_conf_t *conf, int newsize)
{
/* Make all the stripes able to hold 'newsize' devices.
struct stripe_head *osh, *nsh;
LIST_HEAD(newstripes);
struct disk_info *ndisks;
+ unsigned long cpu;
int err;
struct kmem_cache *sc;
int i;
/* Step 3.
* At this point, we are holding all the stripes so the array
* is completely stalled, so now is a good time to resize
- * conf->disks.
+ * conf->disks and the scribble region
*/
ndisks = kzalloc(newsize * sizeof(struct disk_info), GFP_NOIO);
if (ndisks) {
} else
err = -ENOMEM;
+ get_online_cpus();
+ conf->scribble_len = scribble_len(newsize);
+ for_each_present_cpu(cpu) {
+ struct raid5_percpu *percpu;
+ void *scribble;
+
+ percpu = per_cpu_ptr(conf->percpu, cpu);
+ scribble = kmalloc(conf->scribble_len, GFP_NOIO);
+
+ if (scribble) {
+ kfree(percpu->scribble);
+ percpu->scribble = scribble;
+ } else {
+ err = -ENOMEM;
+ break;
+ }
+ }
+ put_online_cpus();
+
/* Step 4, return new stripes to service */
while(!list_empty(&newstripes)) {
nsh = list_entry(newstripes.next, struct stripe_head, lru);
list_del_init(&nsh->lru);
+
for (i=conf->raid_disks; i < newsize; i++)
if (nsh->dev[i].page == NULL) {
struct page *p = alloc_page(GFP_NOIO);
conf->pool_size = newsize;
return err;
}
-#endif
static int drop_one_stripe(raid5_conf_t *conf)
{
sector_t new_sector;
int algorithm = previous ? conf->prev_algo
: conf->algorithm;
- int sectors_per_chunk = previous ? (conf->prev_chunk >> 9)
- : (conf->chunk_size >> 9);
+ int sectors_per_chunk = previous ? conf->prev_chunk_sectors
+ : conf->chunk_sectors;
int raid_disks = previous ? conf->previous_raid_disks
: conf->raid_disks;
int data_disks = raid_disks - conf->max_degraded;
int raid_disks = sh->disks;
int data_disks = raid_disks - conf->max_degraded;
sector_t new_sector = sh->sector, check;
- int sectors_per_chunk = previous ? (conf->prev_chunk >> 9)
- : (conf->chunk_size >> 9);
+ int sectors_per_chunk = previous ? conf->prev_chunk_sectors
+ : conf->chunk_sectors;
int algorithm = previous ? conf->prev_algo
: conf->algorithm;
sector_t stripe;
}
-
-/*
- * Copy data between a page in the stripe cache, and one or more bion
- * The page could align with the middle of the bio, or there could be
- * several bion, each with several bio_vecs, which cover part of the page
- * Multiple bion are linked together on bi_next. There may be extras
- * at the end of this list. We ignore them.
- */
-static void copy_data(int frombio, struct bio *bio,
- struct page *page,
- sector_t sector)
-{
- char *pa = page_address(page);
- struct bio_vec *bvl;
- int i;
- int page_offset;
-
- if (bio->bi_sector >= sector)
- page_offset = (signed)(bio->bi_sector - sector) * 512;
- else
- page_offset = (signed)(sector - bio->bi_sector) * -512;
- bio_for_each_segment(bvl, bio, i) {
- int len = bio_iovec_idx(bio,i)->bv_len;
- int clen;
- int b_offset = 0;
-
- if (page_offset < 0) {
- b_offset = -page_offset;
- page_offset += b_offset;
- len -= b_offset;
- }
-
- if (len > 0 && page_offset + len > STRIPE_SIZE)
- clen = STRIPE_SIZE - page_offset;
- else clen = len;
-
- if (clen > 0) {
- char *ba = __bio_kmap_atomic(bio, i, KM_USER0);
- if (frombio)
- memcpy(pa+page_offset, ba+b_offset, clen);
- else
- memcpy(ba+b_offset, pa+page_offset, clen);
- __bio_kunmap_atomic(ba, KM_USER0);
- }
- if (clen < len) /* hit end of page */
- break;
- page_offset += len;
- }
-}
-
-#define check_xor() do { \
- if (count == MAX_XOR_BLOCKS) { \
- xor_blocks(count, STRIPE_SIZE, dest, ptr);\
- count = 0; \
- } \
- } while(0)
-
-static void compute_parity6(struct stripe_head *sh, int method)
-{
- raid5_conf_t *conf = sh->raid_conf;
- int i, pd_idx, qd_idx, d0_idx, disks = sh->disks, count;
- int syndrome_disks = sh->ddf_layout ? disks : (disks - 2);
- struct bio *chosen;
- /**** FIX THIS: This could be very bad if disks is close to 256 ****/
- void *ptrs[syndrome_disks+2];
-
- pd_idx = sh->pd_idx;
- qd_idx = sh->qd_idx;
- d0_idx = raid6_d0(sh);
-
- pr_debug("compute_parity, stripe %llu, method %d\n",
- (unsigned long long)sh->sector, method);
-
- switch(method) {
- case READ_MODIFY_WRITE:
- BUG(); /* READ_MODIFY_WRITE N/A for RAID-6 */
- case RECONSTRUCT_WRITE:
- for (i= disks; i-- ;)
- if ( i != pd_idx && i != qd_idx && sh->dev[i].towrite ) {
- chosen = sh->dev[i].towrite;
- sh->dev[i].towrite = NULL;
-
- if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags))
- wake_up(&conf->wait_for_overlap);
-
- BUG_ON(sh->dev[i].written);
- sh->dev[i].written = chosen;
- }
- break;
- case CHECK_PARITY:
- BUG(); /* Not implemented yet */
- }
-
- for (i = disks; i--;)
- if (sh->dev[i].written) {
- sector_t sector = sh->dev[i].sector;
- struct bio *wbi = sh->dev[i].written;
- while (wbi && wbi->bi_sector < sector + STRIPE_SECTORS) {
- copy_data(1, wbi, sh->dev[i].page, sector);
- wbi = r5_next_bio(wbi, sector);
- }
-
- set_bit(R5_LOCKED, &sh->dev[i].flags);
- set_bit(R5_UPTODATE, &sh->dev[i].flags);
- }
-
- /* Note that unlike RAID-5, the ordering of the disks matters greatly.*/
-
- for (i = 0; i < disks; i++)
- ptrs[i] = (void *)raid6_empty_zero_page;
-
- count = 0;
- i = d0_idx;
- do {
- int slot = raid6_idx_to_slot(i, sh, &count, syndrome_disks);
-
- ptrs[slot] = page_address(sh->dev[i].page);
- if (slot < syndrome_disks &&
- !test_bit(R5_UPTODATE, &sh->dev[i].flags)) {
- printk(KERN_ERR "block %d/%d not uptodate "
- "on parity calc\n", i, count);
- BUG();
- }
-
- i = raid6_next_disk(i, disks);
- } while (i != d0_idx);
- BUG_ON(count != syndrome_disks);
-
- raid6_call.gen_syndrome(syndrome_disks+2, STRIPE_SIZE, ptrs);
-
- switch(method) {
- case RECONSTRUCT_WRITE:
- set_bit(R5_UPTODATE, &sh->dev[pd_idx].flags);
- set_bit(R5_UPTODATE, &sh->dev[qd_idx].flags);
- set_bit(R5_LOCKED, &sh->dev[pd_idx].flags);
- set_bit(R5_LOCKED, &sh->dev[qd_idx].flags);
- break;
- case UPDATE_PARITY:
- set_bit(R5_UPTODATE, &sh->dev[pd_idx].flags);
- set_bit(R5_UPTODATE, &sh->dev[qd_idx].flags);
- break;
- }
-}
-
-
-/* Compute one missing block */
-static void compute_block_1(struct stripe_head *sh, int dd_idx, int nozero)
-{
- int i, count, disks = sh->disks;
- void *ptr[MAX_XOR_BLOCKS], *dest, *p;
- int qd_idx = sh->qd_idx;
-
- pr_debug("compute_block_1, stripe %llu, idx %d\n",
- (unsigned long long)sh->sector, dd_idx);
-
- if ( dd_idx == qd_idx ) {
- /* We're actually computing the Q drive */
- compute_parity6(sh, UPDATE_PARITY);
- } else {
- dest = page_address(sh->dev[dd_idx].page);
- if (!nozero) memset(dest, 0, STRIPE_SIZE);
- count = 0;
- for (i = disks ; i--; ) {
- if (i == dd_idx || i == qd_idx)
- continue;
- p = page_address(sh->dev[i].page);
- if (test_bit(R5_UPTODATE, &sh->dev[i].flags))
- ptr[count++] = p;
- else
- printk("compute_block() %d, stripe %llu, %d"
- " not present\n", dd_idx,
- (unsigned long long)sh->sector, i);
-
- check_xor();
- }
- if (count)
- xor_blocks(count, STRIPE_SIZE, dest, ptr);
- if (!nozero) set_bit(R5_UPTODATE, &sh->dev[dd_idx].flags);
- else clear_bit(R5_UPTODATE, &sh->dev[dd_idx].flags);
- }
-}
-
-/* Compute two missing blocks */
-static void compute_block_2(struct stripe_head *sh, int dd_idx1, int dd_idx2)
-{
- int i, count, disks = sh->disks;
- int syndrome_disks = sh->ddf_layout ? disks : disks-2;
- int d0_idx = raid6_d0(sh);
- int faila = -1, failb = -1;
- /**** FIX THIS: This could be very bad if disks is close to 256 ****/
- void *ptrs[syndrome_disks+2];
-
- for (i = 0; i < disks ; i++)
- ptrs[i] = (void *)raid6_empty_zero_page;
- count = 0;
- i = d0_idx;
- do {
- int slot = raid6_idx_to_slot(i, sh, &count, syndrome_disks);
-
- ptrs[slot] = page_address(sh->dev[i].page);
-
- if (i == dd_idx1)
- faila = slot;
- if (i == dd_idx2)
- failb = slot;
- i = raid6_next_disk(i, disks);
- } while (i != d0_idx);
- BUG_ON(count != syndrome_disks);
-
- BUG_ON(faila == failb);
- if ( failb < faila ) { int tmp = faila; faila = failb; failb = tmp; }
-
- pr_debug("compute_block_2, stripe %llu, idx %d,%d (%d,%d)\n",
- (unsigned long long)sh->sector, dd_idx1, dd_idx2,
- faila, failb);
-
- if (failb == syndrome_disks+1) {
- /* Q disk is one of the missing disks */
- if (faila == syndrome_disks) {
- /* Missing P+Q, just recompute */
- compute_parity6(sh, UPDATE_PARITY);
- return;
- } else {
- /* We're missing D+Q; recompute D from P */
- compute_block_1(sh, ((dd_idx1 == sh->qd_idx) ?
- dd_idx2 : dd_idx1),
- 0);
- compute_parity6(sh, UPDATE_PARITY); /* Is this necessary? */
- return;
- }
- }
-
- /* We're missing D+P or D+D; */
- if (failb == syndrome_disks) {
- /* We're missing D+P. */
- raid6_datap_recov(syndrome_disks+2, STRIPE_SIZE, faila, ptrs);
- } else {
- /* We're missing D+D. */
- raid6_2data_recov(syndrome_disks+2, STRIPE_SIZE, faila, failb,
- ptrs);
- }
-
- /* Both the above update both missing blocks */
- set_bit(R5_UPTODATE, &sh->dev[dd_idx1].flags);
- set_bit(R5_UPTODATE, &sh->dev[dd_idx2].flags);
-}
-
static void
-schedule_reconstruction5(struct stripe_head *sh, struct stripe_head_state *s,
+schedule_reconstruction(struct stripe_head *sh, struct stripe_head_state *s,
int rcw, int expand)
{
int i, pd_idx = sh->pd_idx, disks = sh->disks;
+ raid5_conf_t *conf = sh->raid_conf;
+ int level = conf->level;
if (rcw) {
/* if we are not expanding this is a proper write request, and
} else
sh->reconstruct_state = reconstruct_state_run;
- set_bit(STRIPE_OP_POSTXOR, &s->ops_request);
+ set_bit(STRIPE_OP_RECONSTRUCT, &s->ops_request);
for (i = disks; i--; ) {
struct r5dev *dev = &sh->dev[i];
s->locked++;
}
}
- if (s->locked + 1 == disks)
+ if (s->locked + conf->max_degraded == disks)
if (!test_and_set_bit(STRIPE_FULL_WRITE, &sh->state))
- atomic_inc(&sh->raid_conf->pending_full_writes);
+ atomic_inc(&conf->pending_full_writes);
} else {
+ BUG_ON(level == 6);
BUG_ON(!(test_bit(R5_UPTODATE, &sh->dev[pd_idx].flags) ||
test_bit(R5_Wantcompute, &sh->dev[pd_idx].flags)));
sh->reconstruct_state = reconstruct_state_prexor_drain_run;
set_bit(STRIPE_OP_PREXOR, &s->ops_request);
set_bit(STRIPE_OP_BIODRAIN, &s->ops_request);
- set_bit(STRIPE_OP_POSTXOR, &s->ops_request);
+ set_bit(STRIPE_OP_RECONSTRUCT, &s->ops_request);
for (i = disks; i--; ) {
struct r5dev *dev = &sh->dev[i];
}
}
- /* keep the parity disk locked while asynchronous operations
+ /* keep the parity disk(s) locked while asynchronous operations
* are in flight
*/
set_bit(R5_LOCKED, &sh->dev[pd_idx].flags);
clear_bit(R5_UPTODATE, &sh->dev[pd_idx].flags);
s->locked++;
+ if (level == 6) {
+ int qd_idx = sh->qd_idx;
+ struct r5dev *dev = &sh->dev[qd_idx];
+
+ set_bit(R5_LOCKED, &dev->flags);
+ clear_bit(R5_UPTODATE, &dev->flags);
+ s->locked++;
+ }
+
pr_debug("%s: stripe %llu locked: %d ops_request: %lx\n",
__func__, (unsigned long long)sh->sector,
s->locked, s->ops_request);
static void end_reshape(raid5_conf_t *conf);
-static int page_is_zero(struct page *p)
-{
- char *a = page_address(p);
- return ((*(u32*)a) == 0 &&
- memcmp(a, a+4, STRIPE_SIZE-4)==0);
-}
-
static void stripe_set_idx(sector_t stripe, raid5_conf_t *conf, int previous,
struct stripe_head *sh)
{
int sectors_per_chunk =
- previous ? (conf->prev_chunk >> 9)
- : (conf->chunk_size >> 9);
+ previous ? conf->prev_chunk_sectors : conf->chunk_sectors;
int dd_idx;
int chunk_offset = sector_div(stripe, sectors_per_chunk);
int disks = previous ? conf->previous_raid_disks : conf->raid_disks;
set_bit(STRIPE_OP_COMPUTE_BLK, &s->ops_request);
set_bit(R5_Wantcompute, &dev->flags);
sh->ops.target = disk_idx;
+ sh->ops.target2 = -1;
s->req_compute = 1;
/* Careful: from this point on 'uptodate' is in the eye
- * of raid5_run_ops which services 'compute' operations
+ * of raid_run_ops which services 'compute' operations
* before writes. R5_Wantcompute flags a block that will
* be R5_UPTODATE by the time it is needed for a
* subsequent operation.
set_bit(STRIPE_HANDLE, &sh->state);
}
-static void handle_stripe_fill6(struct stripe_head *sh,
- struct stripe_head_state *s, struct r6_state *r6s,
- int disks)
+/* fetch_block6 - checks the given member device to see if its data needs
+ * to be read or computed to satisfy a request.
+ *
+ * Returns 1 when no more member devices need to be checked, otherwise returns
+ * 0 to tell the loop in handle_stripe_fill6 to continue
+ */
+static int fetch_block6(struct stripe_head *sh, struct stripe_head_state *s,
+ struct r6_state *r6s, int disk_idx, int disks)
{
- int i;
- for (i = disks; i--; ) {
- struct r5dev *dev = &sh->dev[i];
- if (!test_bit(R5_LOCKED, &dev->flags) &&
- !test_bit(R5_UPTODATE, &dev->flags) &&
- (dev->toread || (dev->towrite &&
- !test_bit(R5_OVERWRITE, &dev->flags)) ||
- s->syncing || s->expanding ||
- (s->failed >= 1 &&
- (sh->dev[r6s->failed_num[0]].toread ||
- s->to_write)) ||
- (s->failed >= 2 &&
- (sh->dev[r6s->failed_num[1]].toread ||
- s->to_write)))) {
- /* we would like to get this block, possibly
- * by computing it, but we might not be able to
+ struct r5dev *dev = &sh->dev[disk_idx];
+ struct r5dev *fdev[2] = { &sh->dev[r6s->failed_num[0]],
+ &sh->dev[r6s->failed_num[1]] };
+
+ if (!test_bit(R5_LOCKED, &dev->flags) &&
+ !test_bit(R5_UPTODATE, &dev->flags) &&
+ (dev->toread ||
+ (dev->towrite && !test_bit(R5_OVERWRITE, &dev->flags)) ||
+ s->syncing || s->expanding ||
+ (s->failed >= 1 &&
+ (fdev[0]->toread || s->to_write)) ||
+ (s->failed >= 2 &&
+ (fdev[1]->toread || s->to_write)))) {
+ /* we would like to get this block, possibly by computing it,
+ * otherwise read it if the backing disk is insync
+ */
+ BUG_ON(test_bit(R5_Wantcompute, &dev->flags));
+ BUG_ON(test_bit(R5_Wantread, &dev->flags));
+ if ((s->uptodate == disks - 1) &&
+ (s->failed && (disk_idx == r6s->failed_num[0] ||
+ disk_idx == r6s->failed_num[1]))) {
+ /* have disk failed, and we're requested to fetch it;
+ * do compute it
*/
- if ((s->uptodate == disks - 1) &&
- (s->failed && (i == r6s->failed_num[0] ||
- i == r6s->failed_num[1]))) {
- pr_debug("Computing stripe %llu block %d\n",
- (unsigned long long)sh->sector, i);
- compute_block_1(sh, i, 0);
- s->uptodate++;
- } else if ( s->uptodate == disks-2 && s->failed >= 2 ) {
- /* Computing 2-failure is *very* expensive; only
- * do it if failed >= 2
- */
- int other;
- for (other = disks; other--; ) {
- if (other == i)
- continue;
- if (!test_bit(R5_UPTODATE,
- &sh->dev[other].flags))
- break;
- }
- BUG_ON(other < 0);
- pr_debug("Computing stripe %llu blocks %d,%d\n",
- (unsigned long long)sh->sector,
- i, other);
- compute_block_2(sh, i, other);
- s->uptodate += 2;
- } else if (test_bit(R5_Insync, &dev->flags)) {
- set_bit(R5_LOCKED, &dev->flags);
- set_bit(R5_Wantread, &dev->flags);
- s->locked++;
- pr_debug("Reading block %d (sync=%d)\n",
- i, s->syncing);
+ pr_debug("Computing stripe %llu block %d\n",
+ (unsigned long long)sh->sector, disk_idx);
+ set_bit(STRIPE_COMPUTE_RUN, &sh->state);
+ set_bit(STRIPE_OP_COMPUTE_BLK, &s->ops_request);
+ set_bit(R5_Wantcompute, &dev->flags);
+ sh->ops.target = disk_idx;
+ sh->ops.target2 = -1; /* no 2nd target */
+ s->req_compute = 1;
+ s->uptodate++;
+ return 1;
+ } else if (s->uptodate == disks-2 && s->failed >= 2) {
+ /* Computing 2-failure is *very* expensive; only
+ * do it if failed >= 2
+ */
+ int other;
+ for (other = disks; other--; ) {
+ if (other == disk_idx)
+ continue;
+ if (!test_bit(R5_UPTODATE,
+ &sh->dev[other].flags))
+ break;
}
+ BUG_ON(other < 0);
+ pr_debug("Computing stripe %llu blocks %d,%d\n",
+ (unsigned long long)sh->sector,
+ disk_idx, other);
+ set_bit(STRIPE_COMPUTE_RUN, &sh->state);
+ set_bit(STRIPE_OP_COMPUTE_BLK, &s->ops_request);
+ set_bit(R5_Wantcompute, &sh->dev[disk_idx].flags);
+ set_bit(R5_Wantcompute, &sh->dev[other].flags);
+ sh->ops.target = disk_idx;
+ sh->ops.target2 = other;
+ s->uptodate += 2;
+ s->req_compute = 1;
+ return 1;
+ } else if (test_bit(R5_Insync, &dev->flags)) {
+ set_bit(R5_LOCKED, &dev->flags);
+ set_bit(R5_Wantread, &dev->flags);
+ s->locked++;
+ pr_debug("Reading block %d (sync=%d)\n",
+ disk_idx, s->syncing);
}
}
+
+ return 0;
+}
+
+/**
+ * handle_stripe_fill6 - read or compute data to satisfy pending requests.
+ */
+static void handle_stripe_fill6(struct stripe_head *sh,
+ struct stripe_head_state *s, struct r6_state *r6s,
+ int disks)
+{
+ int i;
+
+ /* look for blocks to read/compute, skip this if a compute
+ * is already in flight, or if the stripe contents are in the
+ * midst of changing due to a write
+ */
+ if (!test_bit(STRIPE_COMPUTE_RUN, &sh->state) && !sh->check_state &&
+ !sh->reconstruct_state)
+ for (i = disks; i--; )
+ if (fetch_block6(sh, s, r6s, i, disks))
+ break;
set_bit(STRIPE_HANDLE, &sh->state);
}
*/
/* since handle_stripe can be called at any time we need to handle the
* case where a compute block operation has been submitted and then a
- * subsequent call wants to start a write request. raid5_run_ops only
- * handles the case where compute block and postxor are requested
+ * subsequent call wants to start a write request. raid_run_ops only
+ * handles the case where compute block and reconstruct are requested
* simultaneously. If this is not the case then new writes need to be
* held off until the compute completes.
*/
if ((s->req_compute || !test_bit(STRIPE_COMPUTE_RUN, &sh->state)) &&
(s->locked == 0 && (rcw == 0 || rmw == 0) &&
!test_bit(STRIPE_BIT_DELAY, &sh->state)))
- schedule_reconstruction5(sh, s, rcw == 0, 0);
+ schedule_reconstruction(sh, s, rcw == 0, 0);
}
static void handle_stripe_dirtying6(raid5_conf_t *conf,
struct stripe_head *sh, struct stripe_head_state *s,
struct r6_state *r6s, int disks)
{
- int rcw = 0, must_compute = 0, pd_idx = sh->pd_idx, i;
+ int rcw = 0, pd_idx = sh->pd_idx, i;
int qd_idx = sh->qd_idx;
+
+ set_bit(STRIPE_HANDLE, &sh->state);
for (i = disks; i--; ) {
struct r5dev *dev = &sh->dev[i];
- /* Would I have to read this buffer for reconstruct_write */
- if (!test_bit(R5_OVERWRITE, &dev->flags)
- && i != pd_idx && i != qd_idx
- && (!test_bit(R5_LOCKED, &dev->flags)
- ) &&
- !test_bit(R5_UPTODATE, &dev->flags)) {
- if (test_bit(R5_Insync, &dev->flags)) rcw++;
- else {
- pr_debug("raid6: must_compute: "
- "disk %d flags=%#lx\n", i, dev->flags);
- must_compute++;
+ /* check if we haven't enough data */
+ if (!test_bit(R5_OVERWRITE, &dev->flags) &&
+ i != pd_idx && i != qd_idx &&
+ !test_bit(R5_LOCKED, &dev->flags) &&
+ !(test_bit(R5_UPTODATE, &dev->flags) ||
+ test_bit(R5_Wantcompute, &dev->flags))) {
+ rcw++;
+ if (!test_bit(R5_Insync, &dev->flags))
+ continue; /* it's a failed drive */
+
+ if (
+ test_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) {
+ pr_debug("Read_old stripe %llu "
+ "block %d for Reconstruct\n",
+ (unsigned long long)sh->sector, i);
+ set_bit(R5_LOCKED, &dev->flags);
+ set_bit(R5_Wantread, &dev->flags);
+ s->locked++;
+ } else {
+ pr_debug("Request delayed stripe %llu "
+ "block %d for Reconstruct\n",
+ (unsigned long long)sh->sector, i);
+ set_bit(STRIPE_DELAYED, &sh->state);
+ set_bit(STRIPE_HANDLE, &sh->state);
}
}
}
- pr_debug("for sector %llu, rcw=%d, must_compute=%d\n",
- (unsigned long long)sh->sector, rcw, must_compute);
- set_bit(STRIPE_HANDLE, &sh->state);
-
- if (rcw > 0)
- /* want reconstruct write, but need to get some data */
- for (i = disks; i--; ) {
- struct r5dev *dev = &sh->dev[i];
- if (!test_bit(R5_OVERWRITE, &dev->flags)
- && !(s->failed == 0 && (i == pd_idx || i == qd_idx))
- && !test_bit(R5_LOCKED, &dev->flags) &&
- !test_bit(R5_UPTODATE, &dev->flags) &&
- test_bit(R5_Insync, &dev->flags)) {
- if (
- test_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) {
- pr_debug("Read_old stripe %llu "
- "block %d for Reconstruct\n",
- (unsigned long long)sh->sector, i);
- set_bit(R5_LOCKED, &dev->flags);
- set_bit(R5_Wantread, &dev->flags);
- s->locked++;
- } else {
- pr_debug("Request delayed stripe %llu "
- "block %d for Reconstruct\n",
- (unsigned long long)sh->sector, i);
- set_bit(STRIPE_DELAYED, &sh->state);
- set_bit(STRIPE_HANDLE, &sh->state);
- }
- }
- }
/* now if nothing is locked, and if we have enough data, we can start a
* write request
*/
- if (s->locked == 0 && rcw == 0 &&
+ if ((s->req_compute || !test_bit(STRIPE_COMPUTE_RUN, &sh->state)) &&
+ s->locked == 0 && rcw == 0 &&
!test_bit(STRIPE_BIT_DELAY, &sh->state)) {
- if (must_compute > 0) {
- /* We have failed blocks and need to compute them */
- switch (s->failed) {
- case 0:
- BUG();
- case 1:
- compute_block_1(sh, r6s->failed_num[0], 0);
- break;
- case 2:
- compute_block_2(sh, r6s->failed_num[0],
- r6s->failed_num[1]);
- break;
- default: /* This request should have been failed? */
- BUG();
- }
- }
-
- pr_debug("Computing parity for stripe %llu\n",
- (unsigned long long)sh->sector);
- compute_parity6(sh, RECONSTRUCT_WRITE);
- /* now every locked buffer is ready to be written */
- for (i = disks; i--; )
- if (test_bit(R5_LOCKED, &sh->dev[i].flags)) {
- pr_debug("Writing stripe %llu block %d\n",
- (unsigned long long)sh->sector, i);
- s->locked++;
- set_bit(R5_Wantwrite, &sh->dev[i].flags);
- }
- if (s->locked == disks)
- if (!test_and_set_bit(STRIPE_FULL_WRITE, &sh->state))
- atomic_inc(&conf->pending_full_writes);
- /* after a RECONSTRUCT_WRITE, the stripe MUST be in-sync */
- set_bit(STRIPE_INSYNC, &sh->state);
-
- if (test_and_clear_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) {
- atomic_dec(&conf->preread_active_stripes);
- if (atomic_read(&conf->preread_active_stripes) <
- IO_THRESHOLD)
- md_wakeup_thread(conf->mddev->thread);
- }
+ schedule_reconstruction(sh, s, 1, 0);
}
}
* we are done. Otherwise update the mismatch count and repair
* parity if !MD_RECOVERY_CHECK
*/
- if (sh->ops.zero_sum_result == 0)
+ if ((sh->ops.zero_sum_result & SUM_CHECK_P_RESULT) == 0)
/* parity is correct (on disc,
* not in buffer any more)
*/
set_bit(R5_Wantcompute,
&sh->dev[sh->pd_idx].flags);
sh->ops.target = sh->pd_idx;
+ sh->ops.target2 = -1;
s->uptodate++;
}
}
static void handle_parity_checks6(raid5_conf_t *conf, struct stripe_head *sh,
- struct stripe_head_state *s,
- struct r6_state *r6s, struct page *tmp_page,
- int disks)
+ struct stripe_head_state *s,
+ struct r6_state *r6s, int disks)
{
- int update_p = 0, update_q = 0;
- struct r5dev *dev;
int pd_idx = sh->pd_idx;
int qd_idx = sh->qd_idx;
+ struct r5dev *dev;
set_bit(STRIPE_HANDLE, &sh->state);
BUG_ON(s->failed > 2);
- BUG_ON(s->uptodate < disks);
+
/* Want to check and possibly repair P and Q.
* However there could be one 'failed' device, in which
* case we can only check one of them, possibly using the
* other to generate missing data
*/
- /* If !tmp_page, we cannot do the calculations,
- * but as we have set STRIPE_HANDLE, we will soon be called
- * by stripe_handle with a tmp_page - just wait until then.
- */
- if (tmp_page) {
+ switch (sh->check_state) {
+ case check_state_idle:
+ /* start a new check operation if there are < 2 failures */
if (s->failed == r6s->q_failed) {
- /* The only possible failed device holds 'Q', so it
+ /* The only possible failed device holds Q, so it
* makes sense to check P (If anything else were failed,
* we would have used P to recreate it).
*/
- compute_block_1(sh, pd_idx, 1);
- if (!page_is_zero(sh->dev[pd_idx].page)) {
- compute_block_1(sh, pd_idx, 0);
- update_p = 1;
- }
+ sh->check_state = check_state_run;
}
if (!r6s->q_failed && s->failed < 2) {
- /* q is not failed, and we didn't use it to generate
+ /* Q is not failed, and we didn't use it to generate
* anything, so it makes sense to check it
*/
- memcpy(page_address(tmp_page),
- page_address(sh->dev[qd_idx].page),
- STRIPE_SIZE);
- compute_parity6(sh, UPDATE_PARITY);
- if (memcmp(page_address(tmp_page),
- page_address(sh->dev[qd_idx].page),
- STRIPE_SIZE) != 0) {
- clear_bit(STRIPE_INSYNC, &sh->state);
- update_q = 1;
- }
+ if (sh->check_state == check_state_run)
+ sh->check_state = check_state_run_pq;
+ else
+ sh->check_state = check_state_run_q;
}
- if (update_p || update_q) {
- conf->mddev->resync_mismatches += STRIPE_SECTORS;
- if (test_bit(MD_RECOVERY_CHECK, &conf->mddev->recovery))
- /* don't try to repair!! */
- update_p = update_q = 0;
+
+ /* discard potentially stale zero_sum_result */
+ sh->ops.zero_sum_result = 0;
+
+ if (sh->check_state == check_state_run) {
+ /* async_xor_zero_sum destroys the contents of P */
+ clear_bit(R5_UPTODATE, &sh->dev[pd_idx].flags);
+ s->uptodate--;
+ }
+ if (sh->check_state >= check_state_run &&
+ sh->check_state <= check_state_run_pq) {
+ /* async_syndrome_zero_sum preserves P and Q, so
+ * no need to mark them !uptodate here
+ */
+ set_bit(STRIPE_OP_CHECK, &s->ops_request);
+ break;
}
+ /* we have 2-disk failure */
+ BUG_ON(s->failed != 2);
+ /* fall through */
+ case check_state_compute_result:
+ sh->check_state = check_state_idle;
+
+ /* check that a write has not made the stripe insync */
+ if (test_bit(STRIPE_INSYNC, &sh->state))
+ break;
+
/* now write out any block on a failed drive,
- * or P or Q if they need it
+ * or P or Q if they were recomputed
*/
-
+ BUG_ON(s->uptodate < disks - 1); /* We don't need Q to recover */
if (s->failed == 2) {
dev = &sh->dev[r6s->failed_num[1]];
s->locked++;
set_bit(R5_LOCKED, &dev->flags);
set_bit(R5_Wantwrite, &dev->flags);
}
-
- if (update_p) {
+ if (sh->ops.zero_sum_result & SUM_CHECK_P_RESULT) {
dev = &sh->dev[pd_idx];
s->locked++;
set_bit(R5_LOCKED, &dev->flags);
set_bit(R5_Wantwrite, &dev->flags);
}
- if (update_q) {
+ if (sh->ops.zero_sum_result & SUM_CHECK_Q_RESULT) {
dev = &sh->dev[qd_idx];
s->locked++;
set_bit(R5_LOCKED, &dev->flags);
clear_bit(STRIPE_DEGRADED, &sh->state);
set_bit(STRIPE_INSYNC, &sh->state);
+ break;
+ case check_state_run:
+ case check_state_run_q:
+ case check_state_run_pq:
+ break; /* we will be called again upon completion */
+ case check_state_check_result:
+ sh->check_state = check_state_idle;
+
+ /* handle a successful check operation, if parity is correct
+ * we are done. Otherwise update the mismatch count and repair
+ * parity if !MD_RECOVERY_CHECK
+ */
+ if (sh->ops.zero_sum_result == 0) {
+ /* both parities are correct */
+ if (!s->failed)
+ set_bit(STRIPE_INSYNC, &sh->state);
+ else {
+ /* in contrast to the raid5 case we can validate
+ * parity, but still have a failure to write
+ * back
+ */
+ sh->check_state = check_state_compute_result;
+ /* Returning at this point means that we may go
+ * off and bring p and/or q uptodate again so
+ * we make sure to check zero_sum_result again
+ * to verify if p or q need writeback
+ */
+ }
+ } else {
+ conf->mddev->resync_mismatches += STRIPE_SECTORS;
+ if (test_bit(MD_RECOVERY_CHECK, &conf->mddev->recovery))
+ /* don't try to repair!! */
+ set_bit(STRIPE_INSYNC, &sh->state);
+ else {
+ int *target = &sh->ops.target;
+
+ sh->ops.target = -1;
+ sh->ops.target2 = -1;
+ sh->check_state = check_state_compute_run;
+ set_bit(STRIPE_COMPUTE_RUN, &sh->state);
+ set_bit(STRIPE_OP_COMPUTE_BLK, &s->ops_request);
+ if (sh->ops.zero_sum_result & SUM_CHECK_P_RESULT) {
+ set_bit(R5_Wantcompute,
+ &sh->dev[pd_idx].flags);
+ *target = pd_idx;
+ target = &sh->ops.target2;
+ s->uptodate++;
+ }
+ if (sh->ops.zero_sum_result & SUM_CHECK_Q_RESULT) {
+ set_bit(R5_Wantcompute,
+ &sh->dev[qd_idx].flags);
+ *target = qd_idx;
+ s->uptodate++;
+ }
+ }
+ }
+ break;
+ case check_state_compute_run:
+ break;
+ default:
+ printk(KERN_ERR "%s: unknown check_state: %d sector: %llu\n",
+ __func__, sh->check_state,
+ (unsigned long long) sh->sector);
+ BUG();
}
}
if (i != sh->pd_idx && i != sh->qd_idx) {
int dd_idx, j;
struct stripe_head *sh2;
+ struct async_submit_ctl submit;
sector_t bn = compute_blocknr(sh, i, 1);
sector_t s = raid5_compute_sector(conf, bn, 0,
&dd_idx, NULL);
- sh2 = get_active_stripe(conf, s, 0, 1);
+ sh2 = get_active_stripe(conf, s, 0, 1, 1);
if (sh2 == NULL)
/* so far only the early blocks of this stripe
* have been requested. When later blocks
}
/* place all the copies on one channel */
+ init_async_submit(&submit, 0, tx, NULL, NULL, NULL);
tx = async_memcpy(sh2->dev[dd_idx].page,
- sh->dev[i].page, 0, 0, STRIPE_SIZE,
- ASYNC_TX_DEP_ACK, tx, NULL, NULL);
+ sh->dev[i].page, 0, 0, STRIPE_SIZE,
+ &submit);
set_bit(R5_Expanded, &sh2->dev[dd_idx].flags);
set_bit(R5_UPTODATE, &sh2->dev[dd_idx].flags);
rcu_read_lock();
for (i=disks; i--; ) {
mdk_rdev_t *rdev;
- struct r5dev *dev = &sh->dev[i];
+
+ dev = &sh->dev[i];
clear_bit(R5_Insync, &dev->flags);
pr_debug("check %d: state 0x%lx toread %p read %p write %p "
/* Finish reconstruct operations initiated by the expansion process */
if (sh->reconstruct_state == reconstruct_state_result) {
struct stripe_head *sh2
- = get_active_stripe(conf, sh->sector, 1, 1);
+ = get_active_stripe(conf, sh->sector, 1, 1, 1);
if (sh2 && test_bit(STRIPE_EXPAND_SOURCE, &sh2->state)) {
/* sh cannot be written until sh2 has been read.
* so arrange for sh to be delayed a little
/* Need to write out all blocks after computing parity */
sh->disks = conf->raid_disks;
stripe_set_idx(sh->sector, conf, 0, sh);
- schedule_reconstruction5(sh, &s, 1, 1);
+ schedule_reconstruction(sh, &s, 1, 1);
} else if (s.expanded && !sh->reconstruct_state && s.locked == 0) {
clear_bit(STRIPE_EXPAND_READY, &sh->state);
atomic_dec(&conf->reshape_stripes);
md_wait_for_blocked_rdev(blocked_rdev, conf->mddev);
if (s.ops_request)
- raid5_run_ops(sh, s.ops_request);
+ raid_run_ops(sh, s.ops_request);
ops_run_io(sh, &s);
return blocked_rdev == NULL;
}
-static bool handle_stripe6(struct stripe_head *sh, struct page *tmp_page)
+static bool handle_stripe6(struct stripe_head *sh)
{
raid5_conf_t *conf = sh->raid_conf;
int disks = sh->disks;
mdk_rdev_t *blocked_rdev = NULL;
pr_debug("handling stripe %llu, state=%#lx cnt=%d, "
- "pd_idx=%d, qd_idx=%d\n",
+ "pd_idx=%d, qd_idx=%d\n, check:%d, reconstruct:%d\n",
(unsigned long long)sh->sector, sh->state,
- atomic_read(&sh->count), pd_idx, qd_idx);
+ atomic_read(&sh->count), pd_idx, qd_idx,
+ sh->check_state, sh->reconstruct_state);
memset(&s, 0, sizeof(s));
spin_lock(&sh->lock);
pr_debug("check %d: state 0x%lx read %p write %p written %p\n",
i, dev->flags, dev->toread, dev->towrite, dev->written);
- /* maybe we can reply to a read */
- if (test_bit(R5_UPTODATE, &dev->flags) && dev->toread) {
- struct bio *rbi, *rbi2;
- pr_debug("Return read for disc %d\n", i);
- spin_lock_irq(&conf->device_lock);
- rbi = dev->toread;
- dev->toread = NULL;
- if (test_and_clear_bit(R5_Overlap, &dev->flags))
- wake_up(&conf->wait_for_overlap);
- spin_unlock_irq(&conf->device_lock);
- while (rbi && rbi->bi_sector < dev->sector + STRIPE_SECTORS) {
- copy_data(0, rbi, dev->page, dev->sector);
- rbi2 = r5_next_bio(rbi, dev->sector);
- spin_lock_irq(&conf->device_lock);
- if (!raid5_dec_bi_phys_segments(rbi)) {
- rbi->bi_next = return_bi;
- return_bi = rbi;
- }
- spin_unlock_irq(&conf->device_lock);
- rbi = rbi2;
- }
- }
+ /* maybe we can reply to a read
+ *
+ * new wantfill requests are only permitted while
+ * ops_complete_biofill is guaranteed to be inactive
+ */
+ if (test_bit(R5_UPTODATE, &dev->flags) && dev->toread &&
+ !test_bit(STRIPE_BIOFILL_RUN, &sh->state))
+ set_bit(R5_Wantfill, &dev->flags);
/* now count some things */
if (test_bit(R5_LOCKED, &dev->flags)) s.locked++;
if (test_bit(R5_UPTODATE, &dev->flags)) s.uptodate++;
+ if (test_bit(R5_Wantcompute, &dev->flags)) {
+ s.compute++;
+ BUG_ON(s.compute > 2);
+ }
-
- if (dev->toread)
+ if (test_bit(R5_Wantfill, &dev->flags)) {
+ s.to_fill++;
+ } else if (dev->toread)
s.to_read++;
if (dev->towrite) {
s.to_write++;
blocked_rdev = NULL;
}
+ if (s.to_fill && !test_bit(STRIPE_BIOFILL_RUN, &sh->state)) {
+ set_bit(STRIPE_OP_BIOFILL, &s.ops_request);
+ set_bit(STRIPE_BIOFILL_RUN, &sh->state);
+ }
+
pr_debug("locked=%d uptodate=%d to_read=%d"
" to_write=%d failed=%d failed_num=%d,%d\n",
s.locked, s.uptodate, s.to_read, s.to_write, s.failed,
* or to load a block that is being partially written.
*/
if (s.to_read || s.non_overwrite || (s.to_write && s.failed) ||
- (s.syncing && (s.uptodate < disks)) || s.expanding)
+ (s.syncing && (s.uptodate + s.compute < disks)) || s.expanding)
handle_stripe_fill6(sh, &s, &r6s, disks);
- /* now to consider writing and what else, if anything should be read */
- if (s.to_write)
+ /* Now we check to see if any write operations have recently
+ * completed
+ */
+ if (sh->reconstruct_state == reconstruct_state_drain_result) {
+ int qd_idx = sh->qd_idx;
+
+ sh->reconstruct_state = reconstruct_state_idle;
+ /* All the 'written' buffers and the parity blocks are ready to
+ * be written back to disk
+ */
+ BUG_ON(!test_bit(R5_UPTODATE, &sh->dev[sh->pd_idx].flags));
+ BUG_ON(!test_bit(R5_UPTODATE, &sh->dev[qd_idx].flags));
+ for (i = disks; i--; ) {
+ dev = &sh->dev[i];
+ if (test_bit(R5_LOCKED, &dev->flags) &&
+ (i == sh->pd_idx || i == qd_idx ||
+ dev->written)) {
+ pr_debug("Writing block %d\n", i);
+ BUG_ON(!test_bit(R5_UPTODATE, &dev->flags));
+ set_bit(R5_Wantwrite, &dev->flags);
+ if (!test_bit(R5_Insync, &dev->flags) ||
+ ((i == sh->pd_idx || i == qd_idx) &&
+ s.failed == 0))
+ set_bit(STRIPE_INSYNC, &sh->state);
+ }
+ }
+ if (test_and_clear_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) {
+ atomic_dec(&conf->preread_active_stripes);
+ if (atomic_read(&conf->preread_active_stripes) <
+ IO_THRESHOLD)
+ md_wakeup_thread(conf->mddev->thread);
+ }
+ }
+
+ /* Now to consider new write requests and what else, if anything
+ * should be read. We do not handle new writes when:
+ * 1/ A 'write' operation (copy+gen_syndrome) is already in flight.
+ * 2/ A 'check' operation is in flight, as it may clobber the parity
+ * block.
+ */
+ if (s.to_write && !sh->reconstruct_state && !sh->check_state)
handle_stripe_dirtying6(conf, sh, &s, &r6s, disks);
/* maybe we need to check and possibly fix the parity for this stripe
* Any reads will already have been scheduled, so we just see if enough
- * data is available
+ * data is available. The parity check is held off while parity
+ * dependent operations are in flight.
*/
- if (s.syncing && s.locked == 0 && !test_bit(STRIPE_INSYNC, &sh->state))
- handle_parity_checks6(conf, sh, &s, &r6s, tmp_page, disks);
+ if (sh->check_state ||
+ (s.syncing && s.locked == 0 &&
+ !test_bit(STRIPE_COMPUTE_RUN, &sh->state) &&
+ !test_bit(STRIPE_INSYNC, &sh->state)))
+ handle_parity_checks6(conf, sh, &s, &r6s, disks);
if (s.syncing && s.locked == 0 && test_bit(STRIPE_INSYNC, &sh->state)) {
md_done_sync(conf->mddev, STRIPE_SECTORS,1);
set_bit(R5_Wantwrite, &dev->flags);
set_bit(R5_ReWrite, &dev->flags);
set_bit(R5_LOCKED, &dev->flags);
+ s.locked++;
} else {
/* let's read it back */
set_bit(R5_Wantread, &dev->flags);
set_bit(R5_LOCKED, &dev->flags);
+ s.locked++;
}
}
}
- if (s.expanded && test_bit(STRIPE_EXPANDING, &sh->state)) {
+ /* Finish reconstruct operations initiated by the expansion process */
+ if (sh->reconstruct_state == reconstruct_state_result) {
+ sh->reconstruct_state = reconstruct_state_idle;
+ clear_bit(STRIPE_EXPANDING, &sh->state);
+ for (i = conf->raid_disks; i--; ) {
+ set_bit(R5_Wantwrite, &sh->dev[i].flags);
+ set_bit(R5_LOCKED, &sh->dev[i].flags);
+ s.locked++;
+ }
+ }
+
+ if (s.expanded && test_bit(STRIPE_EXPANDING, &sh->state) &&
+ !sh->reconstruct_state) {
struct stripe_head *sh2
- = get_active_stripe(conf, sh->sector, 1, 1);
+ = get_active_stripe(conf, sh->sector, 1, 1, 1);
if (sh2 && test_bit(STRIPE_EXPAND_SOURCE, &sh2->state)) {
/* sh cannot be written until sh2 has been read.
* so arrange for sh to be delayed a little
/* Need to write out all blocks after computing P&Q */
sh->disks = conf->raid_disks;
stripe_set_idx(sh->sector, conf, 0, sh);
- compute_parity6(sh, RECONSTRUCT_WRITE);
- for (i = conf->raid_disks ; i-- ; ) {
- set_bit(R5_LOCKED, &sh->dev[i].flags);
- s.locked++;
- set_bit(R5_Wantwrite, &sh->dev[i].flags);
- }
- clear_bit(STRIPE_EXPANDING, &sh->state);
- } else if (s.expanded) {
+ schedule_reconstruction(sh, &s, 1, 1);
+ } else if (s.expanded && !sh->reconstruct_state && s.locked == 0) {
clear_bit(STRIPE_EXPAND_READY, &sh->state);
atomic_dec(&conf->reshape_stripes);
wake_up(&conf->wait_for_overlap);
if (unlikely(blocked_rdev))
md_wait_for_blocked_rdev(blocked_rdev, conf->mddev);
+ if (s.ops_request)
+ raid_run_ops(sh, s.ops_request);
+
ops_run_io(sh, &s);
return_io(return_bi);
}
/* returns true if the stripe was handled */
-static bool handle_stripe(struct stripe_head *sh, struct page *tmp_page)
+static bool handle_stripe(struct stripe_head *sh)
{
if (sh->raid_conf->level == 6)
- return handle_stripe6(sh, tmp_page);
+ return handle_stripe6(sh);
else
return handle_stripe5(sh);
}
-
-
static void raid5_activate_delayed(raid5_conf_t *conf)
{
if (atomic_read(&conf->preread_active_stripes) < IO_THRESHOLD) {
static void unplug_slaves(mddev_t *mddev)
{
- raid5_conf_t *conf = mddev_to_conf(mddev);
+ raid5_conf_t *conf = mddev->private;
int i;
rcu_read_lock();
- for (i=0; i<mddev->raid_disks; i++) {
+ for (i = 0; i < conf->raid_disks; i++) {
mdk_rdev_t *rdev = rcu_dereference(conf->disks[i].rdev);
if (rdev && !test_bit(Faulty, &rdev->flags) && atomic_read(&rdev->nr_pending)) {
struct request_queue *r_queue = bdev_get_queue(rdev->bdev);
static void raid5_unplug_device(struct request_queue *q)
{
mddev_t *mddev = q->queuedata;
- raid5_conf_t *conf = mddev_to_conf(mddev);
+ raid5_conf_t *conf = mddev->private;
unsigned long flags;
spin_lock_irqsave(&conf->device_lock, flags);
static int raid5_congested(void *data, int bits)
{
mddev_t *mddev = data;
- raid5_conf_t *conf = mddev_to_conf(mddev);
+ raid5_conf_t *conf = mddev->private;
/* No difference between reads and writes. Just check
* how busy the stripe_cache is
*/
+
+ if (mddev_congested(mddev, bits))
+ return 1;
if (conf->inactive_blocked)
return 1;
if (conf->quiesce)
mddev_t *mddev = q->queuedata;
sector_t sector = bvm->bi_sector + get_start_sect(bvm->bi_bdev);
int max;
- unsigned int chunk_sectors = mddev->chunk_size >> 9;
+ unsigned int chunk_sectors = mddev->chunk_sectors;
unsigned int bio_sectors = bvm->bi_size >> 9;
if ((bvm->bi_rw & 1) == WRITE)
return biovec->bv_len; /* always allow writes to be mergeable */
- if (mddev->new_chunk < mddev->chunk_size)
- chunk_sectors = mddev->new_chunk >> 9;
+ if (mddev->new_chunk_sectors < mddev->chunk_sectors)
+ chunk_sectors = mddev->new_chunk_sectors;
max = (chunk_sectors - ((sector & (chunk_sectors - 1)) + bio_sectors)) << 9;
if (max < 0) max = 0;
if (max <= biovec->bv_len && bio_sectors == 0)
static int in_chunk_boundary(mddev_t *mddev, struct bio *bio)
{
sector_t sector = bio->bi_sector + get_start_sect(bio->bi_bdev);
- unsigned int chunk_sectors = mddev->chunk_size >> 9;
+ unsigned int chunk_sectors = mddev->chunk_sectors;
unsigned int bio_sectors = bio->bi_size >> 9;
- if (mddev->new_chunk < mddev->chunk_size)
- chunk_sectors = mddev->new_chunk >> 9;
+ if (mddev->new_chunk_sectors < mddev->chunk_sectors)
+ chunk_sectors = mddev->new_chunk_sectors;
return chunk_sectors >=
((sector & (chunk_sectors - 1)) + bio_sectors);
}
bio_put(bi);
mddev = raid_bi->bi_bdev->bd_disk->queue->queuedata;
- conf = mddev_to_conf(mddev);
+ conf = mddev->private;
rdev = (void*)raid_bi->bi_next;
raid_bi->bi_next = NULL;
{
struct request_queue *q = bdev_get_queue(bi->bi_bdev);
- if ((bi->bi_size>>9) > q->max_sectors)
+ if ((bi->bi_size>>9) > queue_max_sectors(q))
return 0;
blk_recount_segments(q, bi);
- if (bi->bi_phys_segments > q->max_phys_segments)
+ if (bi->bi_phys_segments > queue_max_phys_segments(q))
return 0;
if (q->merge_bvec_fn)
static int chunk_aligned_read(struct request_queue *q, struct bio * raid_bio)
{
mddev_t *mddev = q->queuedata;
- raid5_conf_t *conf = mddev_to_conf(mddev);
+ raid5_conf_t *conf = mddev->private;
unsigned int dd_idx;
struct bio* align_bi;
mdk_rdev_t *rdev;
static int make_request(struct request_queue *q, struct bio * bi)
{
mddev_t *mddev = q->queuedata;
- raid5_conf_t *conf = mddev_to_conf(mddev);
+ raid5_conf_t *conf = mddev->private;
int dd_idx;
sector_t new_sector;
sector_t logical_sector, last_sector;
const int rw = bio_data_dir(bi);
int cpu, remaining;
- if (unlikely(bio_barrier(bi))) {
+ if (unlikely(bio_rw_flagged(bi, BIO_RW_BARRIER))) {
bio_endio(bi, -EOPNOTSUPP);
return 0;
}
retry:
previous = 0;
+ disks = conf->raid_disks;
prepare_to_wait(&conf->wait_for_overlap, &w, TASK_UNINTERRUPTIBLE);
- if (likely(conf->reshape_progress == MaxSector))
- disks = conf->raid_disks;
- else {
+ if (unlikely(conf->reshape_progress != MaxSector)) {
/* spinlock is needed as reshape_progress may be
* 64bit on a 32bit platform, and so it might be
* possible to see a half-updated value
* to check again.
*/
spin_lock_irq(&conf->device_lock);
- disks = conf->raid_disks;
if (mddev->delta_disks < 0
? logical_sector < conf->reshape_progress
: logical_sector >= conf->reshape_progress) {
(unsigned long long)logical_sector);
sh = get_active_stripe(conf, new_sector, previous,
- (bi->bi_rw&RWA_MASK));
+ (bi->bi_rw&RWA_MASK), 0);
if (sh) {
- if (unlikely(conf->reshape_progress != MaxSector)) {
+ if (unlikely(previous)) {
/* expansion might have moved on while waiting for a
* stripe, so we must do the range check again.
* Expansion could still move past after this
*/
int must_retry = 0;
spin_lock_irq(&conf->device_lock);
- if ((mddev->delta_disks < 0
- ? logical_sector >= conf->reshape_progress
- : logical_sector < conf->reshape_progress)
- && previous)
+ if (mddev->delta_disks < 0
+ ? logical_sector >= conf->reshape_progress
+ : logical_sector < conf->reshape_progress)
/* mismatch, need to try again */
must_retry = 1;
spin_unlock_irq(&conf->device_lock);
if (must_retry) {
release_stripe(sh);
+ schedule();
goto retry;
}
}
- /* FIXME what if we get a false positive because these
- * are being updated.
- */
- if (logical_sector >= mddev->suspend_lo &&
+
+ if (bio_data_dir(bi) == WRITE &&
+ logical_sector >= mddev->suspend_lo &&
logical_sector < mddev->suspend_hi) {
release_stripe(sh);
- schedule();
+ /* As the suspend_* range is controlled by
+ * userspace, we want an interruptible
+ * wait.
+ */
+ flush_signals(current);
+ prepare_to_wait(&conf->wait_for_overlap,
+ &w, TASK_INTERRUPTIBLE);
+ if (logical_sector >= mddev->suspend_lo &&
+ logical_sector < mddev->suspend_hi)
+ schedule();
goto retry;
}
int new_data_disks = conf->raid_disks - conf->max_degraded;
int i;
int dd_idx;
- sector_t writepos, safepos, gap;
+ sector_t writepos, readpos, safepos;
sector_t stripe_addr;
int reshape_sectors;
struct list_head stripes;
conf->reshape_progress < raid5_size(mddev, 0, 0)) {
sector_nr = raid5_size(mddev, 0, 0)
- conf->reshape_progress;
- } else if (mddev->delta_disks > 0 &&
+ } else if (mddev->delta_disks >= 0 &&
conf->reshape_progress > 0)
sector_nr = conf->reshape_progress;
sector_div(sector_nr, new_data_disks);
* If old and new chunk sizes differ, we need to process the
* largest of these
*/
- if (mddev->new_chunk > mddev->chunk_size)
- reshape_sectors = mddev->new_chunk / 512;
+ if (mddev->new_chunk_sectors > mddev->chunk_sectors)
+ reshape_sectors = mddev->new_chunk_sectors;
else
- reshape_sectors = mddev->chunk_size / 512;
+ reshape_sectors = mddev->chunk_sectors;
/* we update the metadata when there is more than 3Meg
* in the block range (that is rather arbitrary, should
*/
writepos = conf->reshape_progress;
sector_div(writepos, new_data_disks);
+ readpos = conf->reshape_progress;
+ sector_div(readpos, data_disks);
safepos = conf->reshape_safe;
sector_div(safepos, data_disks);
if (mddev->delta_disks < 0) {
- writepos -= reshape_sectors;
+ writepos -= min_t(sector_t, reshape_sectors, writepos);
+ readpos += reshape_sectors;
safepos += reshape_sectors;
- gap = conf->reshape_safe - conf->reshape_progress;
} else {
writepos += reshape_sectors;
- safepos -= reshape_sectors;
- gap = conf->reshape_progress - conf->reshape_safe;
+ readpos -= min_t(sector_t, reshape_sectors, readpos);
+ safepos -= min_t(sector_t, reshape_sectors, safepos);
}
+ /* 'writepos' is the most advanced device address we might write.
+ * 'readpos' is the least advanced device address we might read.
+ * 'safepos' is the least address recorded in the metadata as having
+ * been reshaped.
+ * If 'readpos' is behind 'writepos', then there is no way that we can
+ * ensure safety in the face of a crash - that must be done by userspace
+ * making a backup of the data. So in that case there is no particular
+ * rush to update metadata.
+ * Otherwise if 'safepos' is behind 'writepos', then we really need to
+ * update the metadata to advance 'safepos' to match 'readpos' so that
+ * we can be safe in the event of a crash.
+ * So we insist on updating metadata if safepos is behind writepos and
+ * readpos is beyond writepos.
+ * In any case, update the metadata every 10 seconds.
+ * Maybe that number should be configurable, but I'm not sure it is
+ * worth it.... maybe it could be a multiple of safemode_delay???
+ */
if ((mddev->delta_disks < 0
- ? writepos < safepos
- : writepos > safepos) ||
- gap > (new_data_disks)*3000*2 /*3Meg*/) {
+ ? (safepos > writepos && readpos < writepos)
+ : (safepos < writepos && readpos > writepos)) ||
+ time_after(jiffies, conf->reshape_checkpoint + 10*HZ)) {
/* Cannot proceed until we've updated the superblock... */
wait_event(conf->wait_for_overlap,
atomic_read(&conf->reshape_stripes)==0);
mddev->reshape_position = conf->reshape_progress;
+ mddev->curr_resync_completed = mddev->curr_resync;
+ conf->reshape_checkpoint = jiffies;
set_bit(MD_CHANGE_DEVS, &mddev->flags);
md_wakeup_thread(mddev->thread);
wait_event(mddev->sb_wait, mddev->flags == 0 ||
conf->reshape_safe = mddev->reshape_position;
spin_unlock_irq(&conf->device_lock);
wake_up(&conf->wait_for_overlap);
+ sysfs_notify(&mddev->kobj, NULL, "sync_completed");
}
if (mddev->delta_disks < 0) {
INIT_LIST_HEAD(&stripes);
for (i = 0; i < reshape_sectors; i += STRIPE_SECTORS) {
int j;
- int skipped = 0;
- sh = get_active_stripe(conf, stripe_addr+i, 0, 0);
+ int skipped_disk = 0;
+ sh = get_active_stripe(conf, stripe_addr+i, 0, 0, 1);
set_bit(STRIPE_EXPANDING, &sh->state);
atomic_inc(&conf->reshape_stripes);
/* If any of this stripe is beyond the end of the old
continue;
s = compute_blocknr(sh, j, 0);
if (s < raid5_size(mddev, 0, 0)) {
- skipped = 1;
+ skipped_disk = 1;
continue;
}
memset(page_address(sh->dev[j].page), 0, STRIPE_SIZE);
set_bit(R5_Expanded, &sh->dev[j].flags);
set_bit(R5_UPTODATE, &sh->dev[j].flags);
}
- if (!skipped) {
+ if (!skipped_disk) {
set_bit(STRIPE_EXPAND_READY, &sh->state);
set_bit(STRIPE_HANDLE, &sh->state);
}
raid5_compute_sector(conf, stripe_addr*(new_data_disks),
1, &dd_idx, NULL);
last_sector =
- raid5_compute_sector(conf, ((stripe_addr+conf->chunk_size/512)
- *(new_data_disks) - 1),
+ raid5_compute_sector(conf, ((stripe_addr+reshape_sectors)
+ * new_data_disks - 1),
1, &dd_idx, NULL);
if (last_sector >= mddev->dev_sectors)
last_sector = mddev->dev_sectors - 1;
while (first_sector <= last_sector) {
- sh = get_active_stripe(conf, first_sector, 1, 0);
+ sh = get_active_stripe(conf, first_sector, 1, 0, 1);
set_bit(STRIPE_EXPAND_SOURCE, &sh->state);
set_bit(STRIPE_HANDLE, &sh->state);
release_stripe(sh);
* then we need to write out the superblock.
*/
sector_nr += reshape_sectors;
- if (sector_nr >= mddev->resync_max) {
+ if ((sector_nr - mddev->curr_resync_completed) * 2
+ >= mddev->resync_max - mddev->curr_resync_completed) {
/* Cannot proceed until we've updated the superblock... */
wait_event(conf->wait_for_overlap,
atomic_read(&conf->reshape_stripes) == 0);
mddev->reshape_position = conf->reshape_progress;
+ mddev->curr_resync_completed = mddev->curr_resync + reshape_sectors;
+ conf->reshape_checkpoint = jiffies;
set_bit(MD_CHANGE_DEVS, &mddev->flags);
md_wakeup_thread(mddev->thread);
wait_event(mddev->sb_wait,
conf->reshape_safe = mddev->reshape_position;
spin_unlock_irq(&conf->device_lock);
wake_up(&conf->wait_for_overlap);
+ sysfs_notify(&mddev->kobj, NULL, "sync_completed");
}
return reshape_sectors;
}
return 0;
}
+ /* Allow raid5_quiesce to complete */
+ wait_event(conf->wait_for_overlap, conf->quiesce != 2);
+
if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery))
return reshape_request(mddev, sector_nr, skipped);
bitmap_cond_end_sync(mddev->bitmap, sector_nr);
- sh = get_active_stripe(conf, sector_nr, 0, 1);
+ sh = get_active_stripe(conf, sector_nr, 0, 1, 0);
if (sh == NULL) {
- sh = get_active_stripe(conf, sector_nr, 0, 0);
+ sh = get_active_stripe(conf, sector_nr, 0, 0, 0);
/* make sure we don't swamp the stripe cache if someone else
* is trying to get access
*/
* We don't need to check the 'failed' flag as when that gets set,
* recovery aborts.
*/
- for (i=0; i<mddev->raid_disks; i++)
+ for (i = 0; i < conf->raid_disks; i++)
if (conf->disks[i].rdev == NULL)
still_degraded = 1;
spin_unlock(&sh->lock);
/* wait for any blocked device to be handled */
- while(unlikely(!handle_stripe(sh, NULL)))
+ while (unlikely(!handle_stripe(sh)))
;
release_stripe(sh);
/* already done this stripe */
continue;
- sh = get_active_stripe(conf, sector, 0, 1);
+ sh = get_active_stripe(conf, sector, 0, 1, 0);
if (!sh) {
/* failed to get a stripe - must wait */
return handled;
}
- handle_stripe(sh, NULL);
+ handle_stripe(sh);
release_stripe(sh);
handled++;
}
return handled;
}
+#ifdef CONFIG_MULTICORE_RAID456
+static void __process_stripe(void *param, async_cookie_t cookie)
+{
+ struct stripe_head *sh = param;
+
+ handle_stripe(sh);
+ release_stripe(sh);
+}
+
+static void process_stripe(struct stripe_head *sh, struct list_head *domain)
+{
+ async_schedule_domain(__process_stripe, sh, domain);
+}
+
+static void synchronize_stripe_processing(struct list_head *domain)
+{
+ async_synchronize_full_domain(domain);
+}
+#else
+static void process_stripe(struct stripe_head *sh, struct list_head *domain)
+{
+ handle_stripe(sh);
+ release_stripe(sh);
+ cond_resched();
+}
+
+static void synchronize_stripe_processing(struct list_head *domain)
+{
+}
+#endif
/*
static void raid5d(mddev_t *mddev)
{
struct stripe_head *sh;
- raid5_conf_t *conf = mddev_to_conf(mddev);
+ raid5_conf_t *conf = mddev->private;
int handled;
+ LIST_HEAD(raid_domain);
pr_debug("+++ raid5d active\n");
spin_unlock_irq(&conf->device_lock);
handled++;
- handle_stripe(sh, conf->spare_page);
- release_stripe(sh);
+ process_stripe(sh, &raid_domain);
spin_lock_irq(&conf->device_lock);
}
spin_unlock_irq(&conf->device_lock);
+ synchronize_stripe_processing(&raid_domain);
async_tx_issue_pending_all();
unplug_slaves(mddev);
static ssize_t
raid5_show_stripe_cache_size(mddev_t *mddev, char *page)
{
- raid5_conf_t *conf = mddev_to_conf(mddev);
+ raid5_conf_t *conf = mddev->private;
if (conf)
return sprintf(page, "%d\n", conf->max_nr_stripes);
else
static ssize_t
raid5_store_stripe_cache_size(mddev_t *mddev, const char *page, size_t len)
{
- raid5_conf_t *conf = mddev_to_conf(mddev);
+ raid5_conf_t *conf = mddev->private;
unsigned long new;
int err;
static ssize_t
raid5_show_preread_threshold(mddev_t *mddev, char *page)
{
- raid5_conf_t *conf = mddev_to_conf(mddev);
+ raid5_conf_t *conf = mddev->private;
if (conf)
return sprintf(page, "%d\n", conf->bypass_threshold);
else
static ssize_t
raid5_store_preread_threshold(mddev_t *mddev, const char *page, size_t len)
{
- raid5_conf_t *conf = mddev_to_conf(mddev);
+ raid5_conf_t *conf = mddev->private;
unsigned long new;
if (len >= PAGE_SIZE)
return -EINVAL;
static ssize_t
stripe_cache_active_show(mddev_t *mddev, char *page)
{
- raid5_conf_t *conf = mddev_to_conf(mddev);
+ raid5_conf_t *conf = mddev->private;
if (conf)
return sprintf(page, "%d\n", atomic_read(&conf->active_stripes));
else
static sector_t
raid5_size(mddev_t *mddev, sector_t sectors, int raid_disks)
{
- raid5_conf_t *conf = mddev_to_conf(mddev);
+ raid5_conf_t *conf = mddev->private;
if (!sectors)
sectors = mddev->dev_sectors;
raid_disks = conf->previous_raid_disks;
}
- sectors &= ~((sector_t)mddev->chunk_size/512 - 1);
- sectors &= ~((sector_t)mddev->new_chunk/512 - 1);
+ sectors &= ~((sector_t)mddev->chunk_sectors - 1);
+ sectors &= ~((sector_t)mddev->new_chunk_sectors - 1);
return sectors * (raid_disks - conf->max_degraded);
}
+static void raid5_free_percpu(raid5_conf_t *conf)
+{
+ struct raid5_percpu *percpu;
+ unsigned long cpu;
+
+ if (!conf->percpu)
+ return;
+
+ get_online_cpus();
+ for_each_possible_cpu(cpu) {
+ percpu = per_cpu_ptr(conf->percpu, cpu);
+ safe_put_page(percpu->spare_page);
+ kfree(percpu->scribble);
+ }
+#ifdef CONFIG_HOTPLUG_CPU
+ unregister_cpu_notifier(&conf->cpu_notify);
+#endif
+ put_online_cpus();
+
+ free_percpu(conf->percpu);
+}
+
+static void free_conf(raid5_conf_t *conf)
+{
+ shrink_stripes(conf);
+ raid5_free_percpu(conf);
+ kfree(conf->disks);
+ kfree(conf->stripe_hashtbl);
+ kfree(conf);
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+static int raid456_cpu_notify(struct notifier_block *nfb, unsigned long action,
+ void *hcpu)
+{
+ raid5_conf_t *conf = container_of(nfb, raid5_conf_t, cpu_notify);
+ long cpu = (long)hcpu;
+ struct raid5_percpu *percpu = per_cpu_ptr(conf->percpu, cpu);
+
+ switch (action) {
+ case CPU_UP_PREPARE:
+ case CPU_UP_PREPARE_FROZEN:
+ if (conf->level == 6 && !percpu->spare_page)
+ percpu->spare_page = alloc_page(GFP_KERNEL);
+ if (!percpu->scribble)
+ percpu->scribble = kmalloc(conf->scribble_len, GFP_KERNEL);
+
+ if (!percpu->scribble ||
+ (conf->level == 6 && !percpu->spare_page)) {
+ safe_put_page(percpu->spare_page);
+ kfree(percpu->scribble);
+ pr_err("%s: failed memory allocation for cpu%ld\n",
+ __func__, cpu);
+ return NOTIFY_BAD;
+ }
+ break;
+ case CPU_DEAD:
+ case CPU_DEAD_FROZEN:
+ safe_put_page(percpu->spare_page);
+ kfree(percpu->scribble);
+ percpu->spare_page = NULL;
+ percpu->scribble = NULL;
+ break;
+ default:
+ break;
+ }
+ return NOTIFY_OK;
+}
+#endif
+
+static int raid5_alloc_percpu(raid5_conf_t *conf)
+{
+ unsigned long cpu;
+ struct page *spare_page;
+ struct raid5_percpu *allcpus;
+ void *scribble;
+ int err;
+
+ allcpus = alloc_percpu(struct raid5_percpu);
+ if (!allcpus)
+ return -ENOMEM;
+ conf->percpu = allcpus;
+
+ get_online_cpus();
+ err = 0;
+ for_each_present_cpu(cpu) {
+ if (conf->level == 6) {
+ spare_page = alloc_page(GFP_KERNEL);
+ if (!spare_page) {
+ err = -ENOMEM;
+ break;
+ }
+ per_cpu_ptr(conf->percpu, cpu)->spare_page = spare_page;
+ }
+ scribble = kmalloc(scribble_len(conf->raid_disks), GFP_KERNEL);
+ if (!scribble) {
+ err = -ENOMEM;
+ break;
+ }
+ per_cpu_ptr(conf->percpu, cpu)->scribble = scribble;
+ }
+#ifdef CONFIG_HOTPLUG_CPU
+ conf->cpu_notify.notifier_call = raid456_cpu_notify;
+ conf->cpu_notify.priority = 0;
+ if (err == 0)
+ err = register_cpu_notifier(&conf->cpu_notify);
+#endif
+ put_online_cpus();
+
+ return err;
+}
+
static raid5_conf_t *setup_conf(mddev_t *mddev)
{
raid5_conf_t *conf;
return ERR_PTR(-EINVAL);
}
- if (!mddev->new_chunk || mddev->new_chunk % PAGE_SIZE) {
+ if (!mddev->new_chunk_sectors ||
+ (mddev->new_chunk_sectors << 9) % PAGE_SIZE ||
+ !is_power_of_2(mddev->new_chunk_sectors)) {
printk(KERN_ERR "raid5: invalid chunk size %d for %s\n",
- mddev->new_chunk, mdname(mddev));
+ mddev->new_chunk_sectors << 9, mdname(mddev));
return ERR_PTR(-EINVAL);
}
goto abort;
conf->raid_disks = mddev->raid_disks;
+ conf->scribble_len = scribble_len(conf->raid_disks);
if (mddev->reshape_position == MaxSector)
conf->previous_raid_disks = mddev->raid_disks;
else
if ((conf->stripe_hashtbl = kzalloc(PAGE_SIZE, GFP_KERNEL)) == NULL)
goto abort;
- if (mddev->new_level == 6) {
- conf->spare_page = alloc_page(GFP_KERNEL);
- if (!conf->spare_page)
- goto abort;
- }
+ conf->level = mddev->new_level;
+ if (raid5_alloc_percpu(conf) != 0)
+ goto abort;
+
spin_lock_init(&conf->device_lock);
init_waitqueue_head(&conf->wait_for_stripe);
init_waitqueue_head(&conf->wait_for_overlap);
conf->fullsync = 1;
}
- conf->chunk_size = mddev->new_chunk;
+ conf->chunk_sectors = mddev->new_chunk_sectors;
conf->level = mddev->new_level;
if (conf->level == 6)
conf->max_degraded = 2;
conf->max_nr_stripes = NR_STRIPES;
conf->reshape_progress = mddev->reshape_position;
if (conf->reshape_progress != MaxSector) {
- conf->prev_chunk = mddev->chunk_size;
+ conf->prev_chunk_sectors = mddev->chunk_sectors;
conf->prev_algo = mddev->layout;
}
printk(KERN_INFO "raid5: allocated %dkB for %s\n",
memory, mdname(mddev));
- conf->thread = md_register_thread(raid5d, mddev, "%s_raid5");
+ conf->thread = md_register_thread(raid5d, mddev, NULL);
if (!conf->thread) {
printk(KERN_ERR
"raid5: couldn't allocate thread for %s\n",
abort:
if (conf) {
- shrink_stripes(conf);
- safe_put_page(conf->spare_page);
- kfree(conf->disks);
- kfree(conf->stripe_hashtbl);
- kfree(conf);
+ free_conf(conf);
return ERR_PTR(-EIO);
} else
return ERR_PTR(-ENOMEM);
static int run(mddev_t *mddev)
{
raid5_conf_t *conf;
- int working_disks = 0;
+ int working_disks = 0, chunk_size;
mdk_rdev_t *rdev;
+ if (mddev->recovery_cp != MaxSector)
+ printk(KERN_NOTICE "raid5: %s is not clean"
+ " -- starting background reconstruction\n",
+ mdname(mddev));
if (mddev->reshape_position != MaxSector) {
/* Check that we can continue the reshape.
* Currently only disks can change, it must
* geometry.
*/
here_new = mddev->reshape_position;
- if (sector_div(here_new, (mddev->new_chunk>>9)*
+ if (sector_div(here_new, mddev->new_chunk_sectors *
(mddev->raid_disks - max_degraded))) {
printk(KERN_ERR "raid5: reshape_position not "
"on a stripe boundary\n");
}
/* here_new is the stripe we will write to */
here_old = mddev->reshape_position;
- sector_div(here_old, (mddev->chunk_size>>9)*
+ sector_div(here_old, mddev->chunk_sectors *
(old_disks-max_degraded));
/* here_old is the first stripe that we might need to read
* from */
- if (here_new >= here_old) {
+ if (mddev->delta_disks == 0) {
+ /* We cannot be sure it is safe to start an in-place
+ * reshape. It is only safe if user-space if monitoring
+ * and taking constant backups.
+ * mdadm always starts a situation like this in
+ * readonly mode so it can take control before
+ * allowing any writes. So just check for that.
+ */
+ if ((here_new * mddev->new_chunk_sectors !=
+ here_old * mddev->chunk_sectors) ||
+ mddev->ro == 0) {
+ printk(KERN_ERR "raid5: in-place reshape must be started"
+ " in read-only mode - aborting\n");
+ return -EINVAL;
+ }
+ } else if (mddev->delta_disks < 0
+ ? (here_new * mddev->new_chunk_sectors <=
+ here_old * mddev->chunk_sectors)
+ : (here_new * mddev->new_chunk_sectors >=
+ here_old * mddev->chunk_sectors)) {
/* Reading from the same stripe as writing to - bad */
printk(KERN_ERR "raid5: reshape_position too early for "
"auto-recovery - aborting.\n");
} else {
BUG_ON(mddev->level != mddev->new_level);
BUG_ON(mddev->layout != mddev->new_layout);
- BUG_ON(mddev->chunk_size != mddev->new_chunk);
+ BUG_ON(mddev->chunk_sectors != mddev->new_chunk_sectors);
BUG_ON(mddev->delta_disks != 0);
}
}
/* device size must be a multiple of chunk size */
- mddev->dev_sectors &= ~(mddev->chunk_size / 512 - 1);
+ mddev->dev_sectors &= ~(mddev->chunk_sectors - 1);
mddev->resync_max_sectors = mddev->dev_sectors;
if (mddev->degraded > 0 &&
set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
set_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
mddev->sync_thread = md_register_thread(md_do_sync, mddev,
- "%s_reshape");
+ "reshape");
}
/* read-ahead size must cover two whole stripes, which is
{
int data_disks = conf->previous_raid_disks - conf->max_degraded;
int stripe = data_disks *
- (mddev->chunk_size / PAGE_SIZE);
+ ((mddev->chunk_sectors << 9) / PAGE_SIZE);
if (mddev->queue->backing_dev_info.ra_pages < 2 * stripe)
mddev->queue->backing_dev_info.ra_pages = 2 * stripe;
}
md_set_array_sectors(mddev, raid5_size(mddev, 0, 0));
blk_queue_merge_bvec(mddev->queue, raid5_mergeable_bvec);
+ chunk_size = mddev->chunk_sectors << 9;
+ blk_queue_io_min(mddev->queue, chunk_size);
+ blk_queue_io_opt(mddev->queue, chunk_size *
+ (conf->raid_disks - conf->max_degraded));
+
+ list_for_each_entry(rdev, &mddev->disks, same_set)
+ disk_stack_limits(mddev->gendisk, rdev->bdev,
+ rdev->data_offset << 9);
return 0;
abort:
md_unregister_thread(mddev->thread);
mddev->thread = NULL;
if (conf) {
- shrink_stripes(conf);
print_raid5_conf(conf);
- safe_put_page(conf->spare_page);
- kfree(conf->disks);
- kfree(conf->stripe_hashtbl);
- kfree(conf);
+ free_conf(conf);
}
mddev->private = NULL;
printk(KERN_ALERT "raid5: failed to run raid set %s\n", mdname(mddev));
md_unregister_thread(mddev->thread);
mddev->thread = NULL;
- shrink_stripes(conf);
- kfree(conf->stripe_hashtbl);
mddev->queue->backing_dev_info.congested_fn = NULL;
blk_sync_queue(mddev->queue); /* the unplug fn references 'conf'*/
sysfs_remove_group(&mddev->kobj, &raid5_attrs_group);
- kfree(conf->disks);
- kfree(conf);
+ free_conf(conf);
mddev->private = NULL;
return 0;
}
raid5_conf_t *conf = (raid5_conf_t *) mddev->private;
int i;
- seq_printf (seq, " level %d, %dk chunk, algorithm %d", mddev->level, mddev->chunk_size >> 10, mddev->layout);
+ seq_printf(seq, " level %d, %dk chunk, algorithm %d", mddev->level,
+ mddev->chunk_sectors / 2, mddev->layout);
seq_printf (seq, " [%d/%d] [", conf->raid_disks, conf->raid_disks - mddev->degraded);
for (i = 0; i < conf->raid_disks; i++)
seq_printf (seq, "%s",
* any io in the removed space completes, but it hardly seems
* worth it.
*/
- sectors &= ~((sector_t)mddev->chunk_size/512 - 1);
+ sectors &= ~((sector_t)mddev->chunk_sectors - 1);
md_set_array_sectors(mddev, raid5_size(mddev, sectors,
mddev->raid_disks));
if (mddev->array_sectors >
return -EINVAL;
set_capacity(mddev->gendisk, mddev->array_sectors);
mddev->changed = 1;
+ revalidate_disk(mddev->gendisk);
if (sectors > mddev->dev_sectors && mddev->recovery_cp == MaxSector) {
mddev->recovery_cp = mddev->dev_sectors;
set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
return 0;
}
-#ifdef CONFIG_MD_RAID5_RESHAPE
-static int raid5_check_reshape(mddev_t *mddev)
+static int check_stripe_cache(mddev_t *mddev)
+{
+ /* Can only proceed if there are plenty of stripe_heads.
+ * We need a minimum of one full stripe,, and for sensible progress
+ * it is best to have about 4 times that.
+ * If we require 4 times, then the default 256 4K stripe_heads will
+ * allow for chunk sizes up to 256K, which is probably OK.
+ * If the chunk size is greater, user-space should request more
+ * stripe_heads first.
+ */
+ raid5_conf_t *conf = mddev->private;
+ if (((mddev->chunk_sectors << 9) / STRIPE_SIZE) * 4
+ > conf->max_nr_stripes ||
+ ((mddev->new_chunk_sectors << 9) / STRIPE_SIZE) * 4
+ > conf->max_nr_stripes) {
+ printk(KERN_WARNING "raid5: reshape: not enough stripes. Needed %lu\n",
+ ((max(mddev->chunk_sectors, mddev->new_chunk_sectors) << 9)
+ / STRIPE_SIZE)*4);
+ return 0;
+ }
+ return 1;
+}
+
+static int check_reshape(mddev_t *mddev)
{
- raid5_conf_t *conf = mddev_to_conf(mddev);
+ raid5_conf_t *conf = mddev->private;
if (mddev->delta_disks == 0 &&
mddev->new_layout == mddev->layout &&
- mddev->new_chunk == mddev->chunk_size)
- return -EINVAL; /* nothing to do */
+ mddev->new_chunk_sectors == mddev->chunk_sectors)
+ return 0; /* nothing to do */
if (mddev->bitmap)
/* Cannot grow a bitmap yet */
return -EBUSY;
return -EINVAL;
}
- /* Can only proceed if there are plenty of stripe_heads.
- * We need a minimum of one full stripe,, and for sensible progress
- * it is best to have about 4 times that.
- * If we require 4 times, then the default 256 4K stripe_heads will
- * allow for chunk sizes up to 256K, which is probably OK.
- * If the chunk size is greater, user-space should request more
- * stripe_heads first.
- */
- if ((mddev->chunk_size / STRIPE_SIZE) * 4 > conf->max_nr_stripes ||
- (mddev->new_chunk / STRIPE_SIZE) * 4 > conf->max_nr_stripes) {
- printk(KERN_WARNING "raid5: reshape: not enough stripes. Needed %lu\n",
- (max(mddev->chunk_size, mddev->new_chunk)
- / STRIPE_SIZE)*4);
+ if (!check_stripe_cache(mddev))
return -ENOSPC;
- }
return resize_stripes(conf, conf->raid_disks + mddev->delta_disks);
}
static int raid5_start_reshape(mddev_t *mddev)
{
- raid5_conf_t *conf = mddev_to_conf(mddev);
+ raid5_conf_t *conf = mddev->private;
mdk_rdev_t *rdev;
int spares = 0;
int added_devices = 0;
if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
return -EBUSY;
+ if (!check_stripe_cache(mddev))
+ return -ENOSPC;
+
list_for_each_entry(rdev, &mddev->disks, same_set)
if (rdev->raid_disk < 0 &&
!test_bit(Faulty, &rdev->flags))
spin_lock_irq(&conf->device_lock);
conf->previous_raid_disks = conf->raid_disks;
conf->raid_disks += mddev->delta_disks;
- conf->prev_chunk = conf->chunk_size;
- conf->chunk_size = mddev->new_chunk;
+ conf->prev_chunk_sectors = conf->chunk_sectors;
+ conf->chunk_sectors = mddev->new_chunk_sectors;
conf->prev_algo = conf->algorithm;
conf->algorithm = mddev->new_layout;
if (mddev->delta_disks < 0)
spin_unlock_irqrestore(&conf->device_lock, flags);
}
mddev->raid_disks = conf->raid_disks;
- mddev->reshape_position = 0;
+ mddev->reshape_position = conf->reshape_progress;
set_bit(MD_CHANGE_DEVS, &mddev->flags);
clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
set_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
mddev->sync_thread = md_register_thread(md_do_sync, mddev,
- "%s_reshape");
+ "reshape");
if (!mddev->sync_thread) {
mddev->recovery = 0;
spin_lock_irq(&conf->device_lock);
spin_unlock_irq(&conf->device_lock);
return -EAGAIN;
}
+ conf->reshape_checkpoint = jiffies;
md_wakeup_thread(mddev->sync_thread);
md_new_event(mddev);
return 0;
}
-#endif
/* This is called from the reshape thread and should make any
* changes needed in 'conf'
conf->previous_raid_disks = conf->raid_disks;
conf->reshape_progress = MaxSector;
spin_unlock_irq(&conf->device_lock);
+ wake_up(&conf->wait_for_overlap);
/* read-ahead size must cover two whole stripes, which is
* 2 * (datadisks) * chunksize where 'n' is the number of raid devices
*/
{
int data_disks = conf->raid_disks - conf->max_degraded;
- int stripe = data_disks * (conf->chunk_size
+ int stripe = data_disks * ((conf->chunk_sectors << 9)
/ PAGE_SIZE);
if (conf->mddev->queue->backing_dev_info.ra_pages < 2 * stripe)
conf->mddev->queue->backing_dev_info.ra_pages = 2 * stripe;
*/
static void raid5_finish_reshape(mddev_t *mddev)
{
- struct block_device *bdev;
- raid5_conf_t *conf = mddev_to_conf(mddev);
+ raid5_conf_t *conf = mddev->private;
if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery)) {
md_set_array_sectors(mddev, raid5_size(mddev, 0, 0));
set_capacity(mddev->gendisk, mddev->array_sectors);
mddev->changed = 1;
-
- bdev = bdget_disk(mddev->gendisk, 0);
- if (bdev) {
- mutex_lock(&bdev->bd_inode->i_mutex);
- i_size_write(bdev->bd_inode,
- (loff_t)mddev->array_sectors << 9);
- mutex_unlock(&bdev->bd_inode->i_mutex);
- bdput(bdev);
- }
+ revalidate_disk(mddev->gendisk);
} else {
int d;
mddev->degraded = conf->raid_disks;
mddev->degraded--;
for (d = conf->raid_disks ;
d < conf->raid_disks - mddev->delta_disks;
- d++)
- raid5_remove_disk(mddev, d);
+ d++) {
+ mdk_rdev_t *rdev = conf->disks[d].rdev;
+ if (rdev && raid5_remove_disk(mddev, d) == 0) {
+ char nm[20];
+ sprintf(nm, "rd%d", rdev->raid_disk);
+ sysfs_remove_link(&mddev->kobj, nm);
+ rdev->raid_disk = -1;
+ }
+ }
}
mddev->layout = conf->algorithm;
- mddev->chunk_size = conf->chunk_size;
+ mddev->chunk_sectors = conf->chunk_sectors;
mddev->reshape_position = MaxSector;
mddev->delta_disks = 0;
}
static void raid5_quiesce(mddev_t *mddev, int state)
{
- raid5_conf_t *conf = mddev_to_conf(mddev);
+ raid5_conf_t *conf = mddev->private;
switch(state) {
case 2: /* resume for a suspend */
case 1: /* stop all writes */
spin_lock_irq(&conf->device_lock);
- conf->quiesce = 1;
+ /* '2' tells resync/reshape to pause so that all
+ * active stripes can drain
+ */
+ conf->quiesce = 2;
wait_event_lock_irq(conf->wait_for_stripe,
atomic_read(&conf->active_stripes) == 0 &&
atomic_read(&conf->active_aligned_reads) == 0,
conf->device_lock, /* nothing */);
+ conf->quiesce = 1;
spin_unlock_irq(&conf->device_lock);
+ /* allow reshape to continue */
+ wake_up(&conf->wait_for_overlap);
break;
case 0: /* re-enable writes */
mddev->new_level = 5;
mddev->new_layout = ALGORITHM_LEFT_SYMMETRIC;
- mddev->new_chunk = chunksect << 9;
+ mddev->new_chunk_sectors = chunksect;
return setup_conf(mddev);
}
}
-static int raid5_reconfig(mddev_t *mddev, int new_layout, int new_chunk)
+static int raid5_check_reshape(mddev_t *mddev)
{
/* For a 2-drive array, the layout and chunk size can be changed
* immediately as not restriping is needed.
* For larger arrays we record the new value - after validation
* to be used by a reshape pass.
*/
- raid5_conf_t *conf = mddev_to_conf(mddev);
+ raid5_conf_t *conf = mddev->private;
+ int new_chunk = mddev->new_chunk_sectors;
- if (new_layout >= 0 && !algorithm_valid_raid5(new_layout))
+ if (mddev->new_layout >= 0 && !algorithm_valid_raid5(mddev->new_layout))
return -EINVAL;
if (new_chunk > 0) {
- if (new_chunk & (new_chunk-1))
- /* not a power of 2 */
+ if (!is_power_of_2(new_chunk))
return -EINVAL;
- if (new_chunk < PAGE_SIZE)
+ if (new_chunk < (PAGE_SIZE>>9))
return -EINVAL;
- if (mddev->array_sectors & ((new_chunk>>9)-1))
+ if (mddev->array_sectors & (new_chunk-1))
/* not factor of array size */
return -EINVAL;
}
/* They look valid */
if (mddev->raid_disks == 2) {
-
- if (new_layout >= 0) {
- conf->algorithm = new_layout;
- mddev->layout = mddev->new_layout = new_layout;
+ /* can make the change immediately */
+ if (mddev->new_layout >= 0) {
+ conf->algorithm = mddev->new_layout;
+ mddev->layout = mddev->new_layout;
}
if (new_chunk > 0) {
- conf->chunk_size = new_chunk;
- mddev->chunk_size = mddev->new_chunk = new_chunk;
+ conf->chunk_sectors = new_chunk ;
+ mddev->chunk_sectors = new_chunk;
}
set_bit(MD_CHANGE_DEVS, &mddev->flags);
md_wakeup_thread(mddev->thread);
- } else {
- if (new_layout >= 0)
- mddev->new_layout = new_layout;
- if (new_chunk > 0)
- mddev->new_chunk = new_chunk;
}
- return 0;
+ return check_reshape(mddev);
}
-static int raid6_reconfig(mddev_t *mddev, int new_layout, int new_chunk)
+static int raid6_check_reshape(mddev_t *mddev)
{
- if (new_layout >= 0 && !algorithm_valid_raid6(new_layout))
+ int new_chunk = mddev->new_chunk_sectors;
+
+ if (mddev->new_layout >= 0 && !algorithm_valid_raid6(mddev->new_layout))
return -EINVAL;
if (new_chunk > 0) {
- if (new_chunk & (new_chunk-1))
- /* not a power of 2 */
+ if (!is_power_of_2(new_chunk))
return -EINVAL;
- if (new_chunk < PAGE_SIZE)
+ if (new_chunk < (PAGE_SIZE >> 9))
return -EINVAL;
- if (mddev->array_sectors & ((new_chunk>>9)-1))
+ if (mddev->array_sectors & (new_chunk-1))
/* not factor of array size */
return -EINVAL;
}
/* They look valid */
-
- if (new_layout >= 0)
- mddev->new_layout = new_layout;
- if (new_chunk > 0)
- mddev->new_chunk = new_chunk;
-
- return 0;
+ return check_reshape(mddev);
}
static void *raid5_takeover(mddev_t *mddev)
* raid1 - if there are two drives. We need to know the chunk size
* raid4 - trivial - just use a raid4 layout.
* raid6 - Providing it is a *_6 layout
- *
- * For now, just do raid1
*/
if (mddev->level == 1)
.sync_request = sync_request,
.resize = raid5_resize,
.size = raid5_size,
-#ifdef CONFIG_MD_RAID5_RESHAPE
- .check_reshape = raid5_check_reshape,
+ .check_reshape = raid6_check_reshape,
.start_reshape = raid5_start_reshape,
.finish_reshape = raid5_finish_reshape,
-#endif
.quiesce = raid5_quiesce,
.takeover = raid6_takeover,
- .reconfig = raid6_reconfig,
};
static struct mdk_personality raid5_personality =
{
.sync_request = sync_request,
.resize = raid5_resize,
.size = raid5_size,
-#ifdef CONFIG_MD_RAID5_RESHAPE
.check_reshape = raid5_check_reshape,
.start_reshape = raid5_start_reshape,
.finish_reshape = raid5_finish_reshape,
-#endif
.quiesce = raid5_quiesce,
.takeover = raid5_takeover,
- .reconfig = raid5_reconfig,
};
static struct mdk_personality raid4_personality =
.sync_request = sync_request,
.resize = raid5_resize,
.size = raid5_size,
-#ifdef CONFIG_MD_RAID5_RESHAPE
.check_reshape = raid5_check_reshape,
.start_reshape = raid5_start_reshape,
.finish_reshape = raid5_finish_reshape,
-#endif
.quiesce = raid5_quiesce,
};
Code Review / linux-2.6.git / blobdiff