md: handle_stripe5 - add request/completion logic for async write ops

After handle_stripe5 decides whether it wants to perform a
read-modify-write, or a reconstruct write it calls
handle_write_operations5.  A read-modify-write operation will perform an
xor subtraction of the blocks marked with the R5_Wantprexor flag, copy the
new data into the stripe (biodrain) and perform a postxor operation across
all up-to-date blocks to generate the new parity.  A reconstruct write is run
when all blocks are already up-to-date in the cache so all that is needed
is a biodrain and postxor.

On the completion path STRIPE_OP_PREXOR will be set if the operation was a
read-modify-write.  The STRIPE_OP_BIODRAIN flag is used in the completion
path to differentiate write-initiated postxor operations versus
expansion-initiated postxor operations.  Completion of a write triggers i/o
to the drives.

Changelog:
* make the 'rcw' parameter to handle_write_operations5 a simple flag, Neil Brown
* remove test_and_set/test_and_clear BUG_ONs, Neil Brown

Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Acked-By: NeilBrown <neilb@suse.de>

1 files changed, 138 insertions, 23 deletions

diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index d89a25e7c17b..d9521aa69461 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -1822,7 +1822,79 @@ static void compute_block_2(struct stripe_head *sh, int dd_idx1, int dd_idx2)
         }
 }
 
+static int
+handle_write_operations5(struct stripe_head *sh, int rcw, int expand)
+{
+        int i, pd_idx = sh->pd_idx, disks = sh->disks;
+        int locked = 0;
+
+        if (rcw) {
+                /* if we are not expanding this is a proper write request, and
+                 * there will be bios with new data to be drained into the
+                 * stripe cache
+                 */
+                if (!expand) {
+                        set_bit(STRIPE_OP_BIODRAIN, &sh->ops.pending);
+                        sh->ops.count++;
+                }
+
+                set_bit(STRIPE_OP_POSTXOR, &sh->ops.pending);
+                sh->ops.count++;
+
+                for (i = disks; i--; ) {
+                        struct r5dev *dev = &sh->dev[i];
+
+                        if (dev->towrite) {
+                                set_bit(R5_LOCKED, &dev->flags);
+                                if (!expand)
+                                        clear_bit(R5_UPTODATE, &dev->flags);
+                                locked++;
+                        }
+                }
+        } else {
+                BUG_ON(!(test_bit(R5_UPTODATE, &sh->dev[pd_idx].flags) ||
+                        test_bit(R5_Wantcompute, &sh->dev[pd_idx].flags)));
+
+                set_bit(STRIPE_OP_PREXOR, &sh->ops.pending);
+                set_bit(STRIPE_OP_BIODRAIN, &sh->ops.pending);
+                set_bit(STRIPE_OP_POSTXOR, &sh->ops.pending);
+
+                sh->ops.count += 3;
+
+                for (i = disks; i--; ) {
+                        struct r5dev *dev = &sh->dev[i];
+                        if (i == pd_idx)
+                                continue;
+
+                        /* For a read-modify write there may be blocks that are
+                         * locked for reading while others are ready to be
+                         * written so we distinguish these blocks by the
+                         * R5_Wantprexor bit
+                         */
+                        if (dev->towrite &&
+                            (test_bit(R5_UPTODATE, &dev->flags) ||
+                            test_bit(R5_Wantcompute, &dev->flags))) {
+                                set_bit(R5_Wantprexor, &dev->flags);
+                                set_bit(R5_LOCKED, &dev->flags);
+                                clear_bit(R5_UPTODATE, &dev->flags);
+                                locked++;
+                        }
+                }
+        }
+
+        /* keep the parity disk 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);
+        locked++;
 
+        pr_debug("%s: stripe %llu locked: %d pending: %lx\n",
+                __FUNCTION__, (unsigned long long)sh->sector,
+                locked, sh->ops.pending);
+
+        return locked;
+}
 
 /*
  * Each stripe/dev can have one or more bion attached.
@@ -2217,27 +2289,8 @@ static void handle_issuing_new_write_requests5(raid5_conf_t *conf,
          * we can start a write request
          */
         if (s->locked == 0 && (rcw == 0 || rmw == 0) &&
-            !test_bit(STRIPE_BIT_DELAY, &sh->state)) {
-                pr_debug("Computing parity...\n");
-                compute_parity5(sh, rcw == 0 ?
-                        RECONSTRUCT_WRITE : READ_MODIFY_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 block %d\n", i);
-                                s->locked++;
-                                set_bit(R5_Wantwrite, &sh->dev[i].flags);
-                                if (!test_bit(R5_Insync, &sh->dev[i].flags)
-                                    || (i == sh->pd_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);
-                }
-        }
+            !test_bit(STRIPE_BIT_DELAY, &sh->state))
+                s->locked += handle_write_operations5(sh, rcw == 0, 0);
 }
 
 static void handle_issuing_new_write_requests6(raid5_conf_t *conf,
@@ -2656,8 +2709,70 @@ static void handle_stripe5(struct stripe_head *sh)
                 (s.syncing && (s.uptodate < disks)) || s.expanding)
                 handle_issuing_new_read_requests5(sh, &s, 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
+         */
+
+        /* leave prexor set until postxor is done, allows us to distinguish
+         * a rmw from a rcw during biodrain
+         */
+        if (test_bit(STRIPE_OP_PREXOR, &sh->ops.complete) &&
+                test_bit(STRIPE_OP_POSTXOR, &sh->ops.complete)) {
+
+                clear_bit(STRIPE_OP_PREXOR, &sh->ops.complete);
+                clear_bit(STRIPE_OP_PREXOR, &sh->ops.ack);
+                clear_bit(STRIPE_OP_PREXOR, &sh->ops.pending);
+
+                for (i = disks; i--; )
+                        clear_bit(R5_Wantprexor, &sh->dev[i].flags);
+        }
+
+        /* if only POSTXOR is set then this is an 'expand' postxor */
+        if (test_bit(STRIPE_OP_BIODRAIN, &sh->ops.complete) &&
+                test_bit(STRIPE_OP_POSTXOR, &sh->ops.complete)) {
+
+                clear_bit(STRIPE_OP_BIODRAIN, &sh->ops.complete);
+                clear_bit(STRIPE_OP_BIODRAIN, &sh->ops.ack);
+                clear_bit(STRIPE_OP_BIODRAIN, &sh->ops.pending);
+
+                clear_bit(STRIPE_OP_POSTXOR, &sh->ops.complete);
+                clear_bit(STRIPE_OP_POSTXOR, &sh->ops.ack);
+                clear_bit(STRIPE_OP_POSTXOR, &sh->ops.pending);
+
+                /* All the 'written' buffers and the parity block are ready to
+                 * be written back to disk
+                 */
+                BUG_ON(!test_bit(R5_UPTODATE, &sh->dev[sh->pd_idx].flags));
+                for (i = disks; i--; ) {
+                        dev = &sh->dev[i];
+                        if (test_bit(R5_LOCKED, &dev->flags) &&
+                                (i == sh->pd_idx || dev->written)) {
+                                pr_debug("Writing block %d\n", i);
+                                set_bit(R5_Wantwrite, &dev->flags);
+                                if (!test_and_set_bit(
+                                    STRIPE_OP_IO, &sh->ops.pending))
+                                        sh->ops.count++;
+                                if (!test_bit(R5_Insync, &dev->flags) ||
+                                    (i == sh->pd_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+xor) is already in flight.
+         * 2/ A 'check' operation is in flight, as it may clobber the parity
+         *    block.
+         */
+        if (s.to_write && !test_bit(STRIPE_OP_POSTXOR, &sh->ops.pending) &&
+                          !test_bit(STRIPE_OP_CHECK, &sh->ops.pending))
                 handle_issuing_new_write_requests5(conf, sh, &s, disks);
 
         /* maybe we need to check and possibly fix the parity for this stripe