extractedLnx/linux-2.6.17/drivers/md/raid6main.c_handle_stripe.c

static void handle_stripe(struct stripe_head *sh, struct page *tmp_page)
{
	raid6_conf_t *conf = sh->raid_conf;
	int disks = conf->raid_disks;
	struct bio *return_bi= NULL;
	struct bio *bi;
	int i;
	int syncing;
	int locked=0, uptodate=0, to_read=0, to_write=0, failed=0, written=0;
	int non_overwrite = 0;
	int failed_num[2] = {0, 0};
	struct r5dev *dev, *pdev, *qdev;
	int pd_idx = sh->pd_idx;
	int qd_idx = raid6_next_disk(pd_idx, disks);
	int p_failed, q_failed;

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

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

	syncing = test_bit(STRIPE_SYNCING, &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)) {
			if ( failed < 2 )
				failed_num[failed] = i;
			failed++;
		} 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,%d\n",
	       locked, uptodate, to_read, to_write, failed,
	       failed_num[0], failed_num[1]);
	/* check if the array has lost >2 devices and, if so, some requests might
	 * need to be failed
	 */
	if (failed > 2 && 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 > 2 && 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 blocks
	 * are safe, or on a failed drive
	 */
	pdev = &sh->dev[pd_idx];
	p_failed = (failed >= 1 && failed_num[0] == pd_idx)
		|| (failed >= 2 && failed_num[1] == pd_idx);
	qdev = &sh->dev[qd_idx];
	q_failed = (failed >= 1 && failed_num[0] == qd_idx)
		|| (failed >= 2 && failed_num[1] == qd_idx);

	if ( written &&
	     ( p_failed || ((test_bit(R5_Insync, &pdev->flags)
			     && !test_bit(R5_LOCKED, &pdev->flags)
			     && test_bit(R5_UPTODATE, &pdev->flags))) ) &&
	     ( q_failed || ((test_bit(R5_Insync, &qdev->flags)
			     && !test_bit(R5_LOCKED, &qdev->flags)
			     && test_bit(R5_UPTODATE, &qdev->flags))) ) ) {
		/* 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 */
					int bitmap_end = 0;
					struct bio *wbi, *wbi2;
					PRINTK("Return write for stripe %llu disc %d\n",
					       (unsigned long long)sh->sector, 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 || (to_write && failed) || (syncing && (uptodate < disks))) {
		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 ||
			     (failed >= 1 && (sh->dev[failed_num[0]].toread || to_write)) ||
			     (failed >= 2 && (sh->dev[failed_num[1]].toread || to_write))
				    )
				) {
				/* we would like to get this block, possibly
				 * by computing it, but we might not be able to
				 */
				if (uptodate == disks-1) {
					PRINTK("Computing stripe %llu block %d\n",
					       (unsigned long long)sh->sector, i);
					compute_block_1(sh, i, 0);
					uptodate++;
				} else if ( uptodate == disks-2 && 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);
					PRINTK("Computing stripe %llu blocks %d,%d\n",
					       (unsigned long long)sh->sector, i, other);
					compute_block_2(sh, i, other);
					uptodate += 2;
				} 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 rcw=0, must_compute=0;
		for (i=disks ; i--;) {
			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)
#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 {
					PRINTK("raid6: must_compute: disk %d flags=%#lx\n", i, dev->flags);
					must_compute++;
				}
			}
		}
		PRINTK("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--;) {
				dev = &sh->dev[i];
				if (!test_bit(R5_OVERWRITE, &dev->flags)
				    && !(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))
					{
						PRINTK("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);
						locked++;
					} else {
						PRINTK("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 (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 ( failed ) {
				case 0:	BUG();
				case 1: compute_block_1(sh, failed_num[0], 0); break;
				case 2: compute_block_2(sh, failed_num[0], failed_num[1]); break;
				default: BUG();	/* This request should have been failed? */
				}
			}

			PRINTK("Computing parity for stripe %llu\n", (unsigned long long)sh->sector);
			compute_parity(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)) {
					PRINTK("Writing stripe %llu block %d\n",
					       (unsigned long long)sh->sector, i);
					locked++;
					set_bit(R5_Wantwrite, &sh->dev[i].flags);
				}
			/* 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);
			}
		}
	}

	/* 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)) {
		int update_p = 0, update_q = 0;
		struct r5dev *dev;

		set_bit(STRIPE_HANDLE, &sh->state);

		BUG_ON(failed>2);
		BUG_ON(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) {
			if (failed == q_failed) {
				/* 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;
				}
			}
			if (!q_failed && failed < 2) {
				/* 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_parity(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 (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;
			}

			/* now write out any block on a failed drive,
			 * or P or Q if they need it
			 */

			if (failed == 2) {
				dev = &sh->dev[failed_num[1]];
				locked++;
				set_bit(R5_LOCKED, &dev->flags);
				set_bit(R5_Wantwrite, &dev->flags);
			}
			if (failed >= 1) {
				dev = &sh->dev[failed_num[0]];
				locked++;
				set_bit(R5_LOCKED, &dev->flags);
				set_bit(R5_Wantwrite, &dev->flags);
			}

			if (update_p) {
				dev = &sh->dev[pd_idx];
				locked ++;
				set_bit(R5_LOCKED, &dev->flags);
				set_bit(R5_Wantwrite, &dev->flags);
			}
			if (update_q) {
				dev = &sh->dev[qd_idx];
				locked++;
				set_bit(R5_LOCKED, &dev->flags);
				set_bit(R5_Wantwrite, &dev->flags);
			}
			clear_bit(STRIPE_DEGRADED, &sh->state);

			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 drives are just a ReadError, then we might need
	 * to progress the repair/check process
	 */
	if (failed <= 2 && ! conf->mddev->ro)
		for (i=0; i<failed;i++) {
			dev = &sh->dev[failed_num[i]];
			if (test_bit(R5_ReadError, &dev->flags)
			    && !test_bit(R5_LOCKED, &dev->flags)
			    && test_bit(R5_UPTODATE, &dev->flags)
				) {
				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);
				} else {
					/* let's read it back */
					set_bit(R5_Wantread, &dev->flags);
					set_bit(R5_LOCKED, &dev->flags);
				}
			}
		}
	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 = raid6_end_write_request;
		else
			bi->bi_end_io = raid6_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)
				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);
		}
	}
}