extractedLnx/linux-2.6.17/drivers/md/raid5.c_handle_stripe.c

static void handle_stripe(struct stripe_head *sh)
{
	raid5_conf_t *conf = sh->raid_conf;
	int disks = sh->disks;
	struct bio *return_bi= NULL;
	struct bio *bi;
	int i;
	int syncing, expanding, expanded;
	int locked=0, uptodate=0, to_read=0, to_write=0, failed=0, written=0;
	int non_overwrite = 0;
	int failed_num=0;
	struct r5dev *dev;

	PRINTK("handling stripe %llu, cnt=%d, pd_idx=%d\n",
		(unsigned long long)sh->sector, atomic_read(&sh->count),
		sh->pd_idx);

	spin_lock(&sh->lock);
	clear_bit(STRIPE_HANDLE, &sh->state);
	clear_bit(STRIPE_DELAYED, &sh->state);

	syncing = test_bit(STRIPE_SYNCING, &sh->state);
	expanding = test_bit(STRIPE_EXPAND_SOURCE, &sh->state);
	expanded = test_bit(STRIPE_EXPAND_READY, &sh->state);
	/* Now to look around and see what can be done */

	rcu_read_lock();
	for (i=disks; i--; ) {
		mdk_rdev_t *rdev;
		dev = &sh->dev[i];
		clear_bit(R5_Insync, &dev->flags);

		PRINTK("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;
			PRINTK("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 (--rbi->bi_phys_segments == 0) {
					rbi->bi_next = return_bi;
					return_bi = rbi;
				}
				spin_unlock_irq(&conf->device_lock);
				rbi = rbi2;
			}
		}

		/* now count some things */
		if (test_bit(R5_LOCKED, &dev->flags)) locked++;
		if (test_bit(R5_UPTODATE, &dev->flags)) uptodate++;

		
		if (dev->toread) to_read++;
		if (dev->towrite) {
			to_write++;
			if (!test_bit(R5_OVERWRITE, &dev->flags))
				non_overwrite++;
		}
		if (dev->written) written++;
		rdev = rcu_dereference(conf->disks[i].rdev);
		if (!rdev || !test_bit(In_sync, &rdev->flags)) {
			/* The ReadError flag will just be confusing now */
			clear_bit(R5_ReadError, &dev->flags);
			clear_bit(R5_ReWrite, &dev->flags);
		}
		if (!rdev || !test_bit(In_sync, &rdev->flags)
		    || test_bit(R5_ReadError, &dev->flags)) {
			failed++;
			failed_num = i;
		} else
			set_bit(R5_Insync, &dev->flags);
	}
	rcu_read_unlock();
	PRINTK("locked=%d uptodate=%d to_read=%d"
		" to_write=%d failed=%d failed_num=%d\n",
		locked, uptodate, to_read, to_write, failed, failed_num);
	/* check if the array has lost two devices and, if so, some requests might
	 * need to be failed
	 */
	if (failed > 1 && to_read+to_write+written) {
		for (i=disks; i--; ) {
			int bitmap_end = 0;

			if (test_bit(R5_ReadError, &sh->dev[i].flags)) {
				mdk_rdev_t *rdev;
				rcu_read_lock();
				rdev = rcu_dereference(conf->disks[i].rdev);
				if (rdev && test_bit(In_sync, &rdev->flags))
					/* multiple read failures in one stripe */
					md_error(conf->mddev, rdev);
				rcu_read_unlock();
			}

			spin_lock_irq(&conf->device_lock);
			/* fail all writes first */
			bi = sh->dev[i].towrite;
			sh->dev[i].towrite = NULL;
			if (bi) { to_write--; bitmap_end = 1; }

			if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags))
				wake_up(&conf->wait_for_overlap);

			while (bi && bi->bi_sector < sh->dev[i].sector + STRIPE_SECTORS){
				struct bio *nextbi = r5_next_bio(bi, sh->dev[i].sector);
				clear_bit(BIO_UPTODATE, &bi->bi_flags);
				if (--bi->bi_phys_segments == 0) {
					md_write_end(conf->mddev);
					bi->bi_next = return_bi;
					return_bi = bi;
				}
				bi = nextbi;
			}
			/* and fail all 'written' */
			bi = sh->dev[i].written;
			sh->dev[i].written = NULL;
			if (bi) bitmap_end = 1;
			while (bi && bi->bi_sector < sh->dev[i].sector + STRIPE_SECTORS) {
				struct bio *bi2 = r5_next_bio(bi, sh->dev[i].sector);
				clear_bit(BIO_UPTODATE, &bi->bi_flags);
				if (--bi->bi_phys_segments == 0) {
					md_write_end(conf->mddev);
					bi->bi_next = return_bi;
					return_bi = bi;
				}
				bi = bi2;
			}

			/* fail any reads if this device is non-operational */
			if (!test_bit(R5_Insync, &sh->dev[i].flags) ||
			    test_bit(R5_ReadError, &sh->dev[i].flags)) {
				bi = sh->dev[i].toread;
				sh->dev[i].toread = NULL;
				if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags))
					wake_up(&conf->wait_for_overlap);
				if (bi) to_read--;
				while (bi && bi->bi_sector < sh->dev[i].sector + STRIPE_SECTORS){
					struct bio *nextbi = r5_next_bio(bi, sh->dev[i].sector);
					clear_bit(BIO_UPTODATE, &bi->bi_flags);
					if (--bi->bi_phys_segments == 0) {
						bi->bi_next = return_bi;
						return_bi = bi;
					}
					bi = nextbi;
				}
			}
			spin_unlock_irq(&conf->device_lock);
			if (bitmap_end)
				bitmap_endwrite(conf->mddev->bitmap, sh->sector,
						STRIPE_SECTORS, 0, 0);
		}
	}
	if (failed > 1 && syncing) {
		md_done_sync(conf->mddev, STRIPE_SECTORS,0);
		clear_bit(STRIPE_SYNCING, &sh->state);
		syncing = 0;
	}

	/* might be able to return some write requests if the parity block
	 * is safe, or on a failed drive
	 */
	dev = &sh->dev[sh->pd_idx];
	if ( written &&
	     ( (test_bit(R5_Insync, &dev->flags) && !test_bit(R5_LOCKED, &dev->flags) &&
		test_bit(R5_UPTODATE, &dev->flags))
	       || (failed == 1 && failed_num == sh->pd_idx))
	    ) {
	    /* any written block on an uptodate or failed drive can be returned.
	     * Note that if we 'wrote' to a failed drive, it will be UPTODATE, but 
	     * never LOCKED, so we don't need to test 'failed' directly.
	     */
	    for (i=disks; i--; )
		if (sh->dev[i].written) {
		    dev = &sh->dev[i];
		    if (!test_bit(R5_LOCKED, &dev->flags) &&
			 test_bit(R5_UPTODATE, &dev->flags) ) {
			/* We can return any write requests */
			    struct bio *wbi, *wbi2;
			    int bitmap_end = 0;
			    PRINTK("Return write for disc %d\n", i);
			    spin_lock_irq(&conf->device_lock);
			    wbi = dev->written;
			    dev->written = NULL;
			    while (wbi && wbi->bi_sector < dev->sector + STRIPE_SECTORS) {
				    wbi2 = r5_next_bio(wbi, dev->sector);
				    if (--wbi->bi_phys_segments == 0) {
					    md_write_end(conf->mddev);
					    wbi->bi_next = return_bi;
					    return_bi = wbi;
				    }
				    wbi = wbi2;
			    }
			    if (dev->towrite == NULL)
				    bitmap_end = 1;
			    spin_unlock_irq(&conf->device_lock);
			    if (bitmap_end)
				    bitmap_endwrite(conf->mddev->bitmap, sh->sector,
						    STRIPE_SECTORS,
						    !test_bit(STRIPE_DEGRADED, &sh->state), 0);
		    }
		}
	}

	/* Now we might consider reading some blocks, either to check/generate
	 * parity, or to satisfy requests
	 * or to load a block that is being partially written.
	 */
	if (to_read || non_overwrite || (syncing && (uptodate < disks)) || expanding) {
		for (i=disks; i--;) {
			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)) ||
			     syncing ||
			     expanding ||
			     (failed && (sh->dev[failed_num].toread ||
					 (sh->dev[failed_num].towrite && !test_bit(R5_OVERWRITE, &sh->dev[failed_num].flags))))
				    )
				) {
				/* we would like to get this block, possibly
				 * by computing it, but we might not be able to
				 */
				if (uptodate == disks-1) {
					PRINTK("Computing block %d\n", i);
					compute_block(sh, i);
					uptodate++;
				} else if (test_bit(R5_Insync, &dev->flags)) {
					set_bit(R5_LOCKED, &dev->flags);
					set_bit(R5_Wantread, &dev->flags);
#if 0
					/* if I am just reading this block and we don't have
					   a failed drive, or any pending writes then sidestep the cache */
					if (sh->bh_read[i] && !sh->bh_read[i]->b_reqnext &&
					    ! syncing && !failed && !to_write) {
						sh->bh_cache[i]->b_page =  sh->bh_read[i]->b_page;
						sh->bh_cache[i]->b_data =  sh->bh_read[i]->b_data;
					}
#endif
					locked++;
					PRINTK("Reading block %d (sync=%d)\n", 
						i, syncing);
				}
			}
		}
		set_bit(STRIPE_HANDLE, &sh->state);
	}

	/* now to consider writing and what else, if anything should be read */
	if (to_write) {
		int rmw=0, rcw=0;
		for (i=disks ; i--;) {
			/* would I have to read this buffer for read_modify_write */
			dev = &sh->dev[i];
			if ((dev->towrite || i == sh->pd_idx) &&
			    (!test_bit(R5_LOCKED, &dev->flags) 
#if 0
|| sh->bh_page[i]!=bh->b_page
#endif
				    ) &&
			    !test_bit(R5_UPTODATE, &dev->flags)) {
				if (test_bit(R5_Insync, &dev->flags)
/*				    && !(!mddev->insync && i == sh->pd_idx) */
					)
					rmw++;
				else rmw += 2*disks;  /* cannot read it */
			}
			/* Would I have to read this buffer for reconstruct_write */
			if (!test_bit(R5_OVERWRITE, &dev->flags) && i != sh->pd_idx &&
			    (!test_bit(R5_LOCKED, &dev->flags) 
#if 0
|| sh->bh_page[i] != bh->b_page
#endif
				    ) &&
			    !test_bit(R5_UPTODATE, &dev->flags)) {
				if (test_bit(R5_Insync, &dev->flags)) rcw++;
				else rcw += 2*disks;
			}
		}
		PRINTK("for sector %llu, rmw=%d rcw=%d\n", 
			(unsigned long long)sh->sector, rmw, rcw);
		set_bit(STRIPE_HANDLE, &sh->state);
		if (rmw < rcw && rmw > 0)
			/* prefer read-modify-write, but need to get some data */
			for (i=disks; i--;) {
				dev = &sh->dev[i];
				if ((dev->towrite || i == sh->pd_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))
					{
						PRINTK("Read_old block %d for r-m-w\n", i);
						set_bit(R5_LOCKED, &dev->flags);
						set_bit(R5_Wantread, &dev->flags);
						locked++;
					} else {
						set_bit(STRIPE_DELAYED, &sh->state);
						set_bit(STRIPE_HANDLE, &sh->state);
					}
				}
			}
		if (rcw <= rmw && rcw > 0)
			/* want reconstruct write, but need to get some data */
			for (i=disks; i--;) {
				dev = &sh->dev[i];
				if (!test_bit(R5_OVERWRITE, &dev->flags) && i != sh->pd_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))
					{
						PRINTK("Read_old block %d for Reconstruct\n", i);
						set_bit(R5_LOCKED, &dev->flags);
						set_bit(R5_Wantread, &dev->flags);
						locked++;
					} else {
						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 (locked == 0 && (rcw == 0 ||rmw == 0) &&
		    !test_bit(STRIPE_BIT_DELAY, &sh->state)) {
			PRINTK("Computing parity...\n");
			compute_parity(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)) {
					PRINTK("Writing block %d\n", i);
					locked++;
					set_bit(R5_Wantwrite, &sh->dev[i].flags);
					if (!test_bit(R5_Insync, &sh->dev[i].flags)
					    || (i==sh->pd_idx && 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);
			}
		}
	}

	/* 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
	 */
	if (syncing && locked == 0 &&
	    !test_bit(STRIPE_INSYNC, &sh->state)) {
		set_bit(STRIPE_HANDLE, &sh->state);
		if (failed == 0) {
			char *pagea;
			BUG_ON(uptodate != disks);
			compute_parity(sh, CHECK_PARITY);
			uptodate--;
			pagea = page_address(sh->dev[sh->pd_idx].page);
			if ((*(u32*)pagea) == 0 &&
			    !memcmp(pagea, pagea+4, STRIPE_SIZE-4)) {
				/* parity is correct (on disc, not in buffer any more) */
				set_bit(STRIPE_INSYNC, &sh->state);
			} 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 {
					compute_block(sh, sh->pd_idx);
					uptodate++;
				}
			}
		}
		if (!test_bit(STRIPE_INSYNC, &sh->state)) {
			/* either failed parity check, or recovery is happening */
			if (failed==0)
				failed_num = sh->pd_idx;
			dev = &sh->dev[failed_num];
			BUG_ON(!test_bit(R5_UPTODATE, &dev->flags));
			BUG_ON(uptodate != disks);

			set_bit(R5_LOCKED, &dev->flags);
			set_bit(R5_Wantwrite, &dev->flags);
			clear_bit(STRIPE_DEGRADED, &sh->state);
			locked++;
			set_bit(STRIPE_INSYNC, &sh->state);
		}
	}
	if (syncing && locked == 0 && test_bit(STRIPE_INSYNC, &sh->state)) {
		md_done_sync(conf->mddev, STRIPE_SECTORS,1);
		clear_bit(STRIPE_SYNCING, &sh->state);
	}

	/* If the failed drive is just a ReadError, then we might need to progress
	 * the repair/check process
	 */
	if (failed == 1 && ! conf->mddev->ro &&
	    test_bit(R5_ReadError, &sh->dev[failed_num].flags)
	    && !test_bit(R5_LOCKED, &sh->dev[failed_num].flags)
	    && test_bit(R5_UPTODATE, &sh->dev[failed_num].flags)
		) {
		dev = &sh->dev[failed_num];
		if (!test_bit(R5_ReWrite, &dev->flags)) {
			set_bit(R5_Wantwrite, &dev->flags);
			set_bit(R5_ReWrite, &dev->flags);
			set_bit(R5_LOCKED, &dev->flags);
			locked++;
		} else {
			/* let's read it back */
			set_bit(R5_Wantread, &dev->flags);
			set_bit(R5_LOCKED, &dev->flags);
			locked++;
		}
	}

	if (expanded && test_bit(STRIPE_EXPANDING, &sh->state)) {
		/* Need to write out all blocks after computing parity */
		sh->disks = conf->raid_disks;
		sh->pd_idx = stripe_to_pdidx(sh->sector, conf, conf->raid_disks);
		compute_parity(sh, RECONSTRUCT_WRITE);
		for (i= conf->raid_disks; i--;) {
			set_bit(R5_LOCKED, &sh->dev[i].flags);
			locked++;
			set_bit(R5_Wantwrite, &sh->dev[i].flags);
		}
		clear_bit(STRIPE_EXPANDING, &sh->state);
	} else if (expanded) {
		clear_bit(STRIPE_EXPAND_READY, &sh->state);
		atomic_dec(&conf->reshape_stripes);
		wake_up(&conf->wait_for_overlap);
		md_done_sync(conf->mddev, STRIPE_SECTORS, 1);
	}

	if (expanding && locked == 0) {
		/* We have read all the blocks in this stripe and now we need to
		 * copy some of them into a target stripe for expand.
		 */
		clear_bit(STRIPE_EXPAND_SOURCE, &sh->state);
		for (i=0; i< sh->disks; i++)
			if (i != sh->pd_idx) {
				int dd_idx, pd_idx, j;
				struct stripe_head *sh2;

				sector_t bn = compute_blocknr(sh, i);
				sector_t s = raid5_compute_sector(bn, conf->raid_disks,
								  conf->raid_disks-1,
								  &dd_idx, &pd_idx, conf);
				sh2 = get_active_stripe(conf, s, conf->raid_disks, pd_idx, 1);
				if (sh2 == NULL)
					/* so far only the early blocks of this stripe
					 * have been requested.  When later blocks
					 * get requested, we will try again
					 */
					continue;
				if(!test_bit(STRIPE_EXPANDING, &sh2->state) ||
				   test_bit(R5_Expanded, &sh2->dev[dd_idx].flags)) {
					/* must have already done this block */
					release_stripe(sh2);
					continue;
				}
				memcpy(page_address(sh2->dev[dd_idx].page),
				       page_address(sh->dev[i].page),
				       STRIPE_SIZE);
				set_bit(R5_Expanded, &sh2->dev[dd_idx].flags);
				set_bit(R5_UPTODATE, &sh2->dev[dd_idx].flags);
				for (j=0; j<conf->raid_disks; j++)
					if (j != sh2->pd_idx &&
					    !test_bit(R5_Expanded, &sh2->dev[j].flags))
						break;
				if (j == conf->raid_disks) {
					set_bit(STRIPE_EXPAND_READY, &sh2->state);
					set_bit(STRIPE_HANDLE, &sh2->state);
				}
				release_stripe(sh2);
			}
	}

	spin_unlock(&sh->lock);

	while ((bi=return_bi)) {
		int bytes = bi->bi_size;

		return_bi = bi->bi_next;
		bi->bi_next = NULL;
		bi->bi_size = 0;
		bi->bi_end_io(bi, bytes, 0);
	}
	for (i=disks; i-- ;) {
		int rw;
		struct bio *bi;
		mdk_rdev_t *rdev;
		if (test_and_clear_bit(R5_Wantwrite, &sh->dev[i].flags))
			rw = 1;
		else if (test_and_clear_bit(R5_Wantread, &sh->dev[i].flags))
			rw = 0;
		else
			continue;
 
		bi = &sh->dev[i].req;
 
		bi->bi_rw = rw;
		if (rw)
			bi->bi_end_io = raid5_end_write_request;
		else
			bi->bi_end_io = raid5_end_read_request;
 
		rcu_read_lock();
		rdev = rcu_dereference(conf->disks[i].rdev);
		if (rdev && test_bit(Faulty, &rdev->flags))
			rdev = NULL;
		if (rdev)
			atomic_inc(&rdev->nr_pending);
		rcu_read_unlock();
 
		if (rdev) {
			if (syncing || expanding || expanded)
				md_sync_acct(rdev->bdev, STRIPE_SECTORS);

			bi->bi_bdev = rdev->bdev;
			PRINTK("for %llu schedule op %ld on disc %d\n",
				(unsigned long long)sh->sector, bi->bi_rw, i);
			atomic_inc(&sh->count);
			bi->bi_sector = sh->sector + rdev->data_offset;
			bi->bi_flags = 1 << BIO_UPTODATE;
			bi->bi_vcnt = 1;	
			bi->bi_max_vecs = 1;
			bi->bi_idx = 0;
			bi->bi_io_vec = &sh->dev[i].vec;
			bi->bi_io_vec[0].bv_len = STRIPE_SIZE;
			bi->bi_io_vec[0].bv_offset = 0;
			bi->bi_size = STRIPE_SIZE;
			bi->bi_next = NULL;
			if (rw == WRITE &&
			    test_bit(R5_ReWrite, &sh->dev[i].flags))
				atomic_add(STRIPE_SECTORS, &rdev->corrected_errors);
			generic_make_request(bi);
		} else {
			if (rw == 1)
				set_bit(STRIPE_DEGRADED, &sh->state);
			PRINTK("skip op %ld on disc %d for sector %llu\n",
				bi->bi_rw, i, (unsigned long long)sh->sector);
			clear_bit(R5_LOCKED, &sh->dev[i].flags);
			set_bit(STRIPE_HANDLE, &sh->state);
		}
	}
}