1 files changed, 142 insertions, 81 deletions

diff --git a/fs/exofs/ore_raid.c b/fs/exofs/ore_raid.c
index 29c47e5c4a8..7f20f25c232 100644
--- a/fs/exofs/ore_raid.c
+++ b/fs/exofs/ore_raid.c
@@ -21,12 +21,12 @@
 #undef ORE_DBGMSG2
 #define ORE_DBGMSG2 ORE_DBGMSG
 
-struct page *_raid_page_alloc(void)
+static struct page *_raid_page_alloc(void)
 {
 	return alloc_page(GFP_KERNEL);
 }
 
-void _raid_page_free(struct page *p)
+static void _raid_page_free(struct page *p)
 {
 	__free_page(p);
 }
@@ -144,26 +144,26 @@ static void _sp2d_reset(struct __stripe_pages_2d *sp2d,
 {
 	unsigned data_devs = sp2d->data_devs;
 	unsigned group_width = data_devs + sp2d->parity;
-	unsigned p;
+	int p, c;
 
 	if (!sp2d->needed)
 		return;
 
-	for (p = 0; p < sp2d->pages_in_unit; p++) {
-		struct __1_page_stripe *_1ps = &sp2d->_1p_stripes[p];
-
-		if (_1ps->write_count < group_width) {
-			unsigned c;
+	for (c = data_devs - 1; c >= 0; --c)
+		for (p = sp2d->pages_in_unit - 1; p >= 0; --p) {
+			struct __1_page_stripe *_1ps = &sp2d->_1p_stripes[p];
 
-			for (c = 0; c < data_devs; c++)
-				if (_1ps->page_is_read[c]) {
-					struct page *page = _1ps->pages[c];
+			if (_1ps->page_is_read[c]) {
+				struct page *page = _1ps->pages[c];
 
-					r4w->put_page(priv, page);
-					_1ps->page_is_read[c] = false;
-				}
+				r4w->put_page(priv, page);
+				_1ps->page_is_read[c] = false;
+			}
 		}
 
+	for (p = 0; p < sp2d->pages_in_unit; p++) {
+		struct __1_page_stripe *_1ps = &sp2d->_1p_stripes[p];
+
 		memset(_1ps->pages, 0, group_width * sizeof(*_1ps->pages));
 		_1ps->write_count = 0;
 		_1ps->tx = NULL;
@@ -203,7 +203,7 @@ static unsigned _sp2d_min_pg(struct __stripe_pages_2d *sp2d)
 
 static unsigned _sp2d_max_pg(struct __stripe_pages_2d *sp2d)
 {
-	unsigned p;
+	int p;
 
 	for (p = sp2d->pages_in_unit - 1; p >= 0; --p) {
 		struct __1_page_stripe *_1ps = &sp2d->_1p_stripes[p];
@@ -218,22 +218,28 @@ static unsigned _sp2d_max_pg(struct __stripe_pages_2d *sp2d)
 static void _gen_xor_unit(struct __stripe_pages_2d *sp2d)
 {
 	unsigned p;
+	unsigned tx_flags = ASYNC_TX_ACK;
+
+	if (sp2d->parity == 1)
+		tx_flags |= ASYNC_TX_XOR_ZERO_DST;
+
 	for (p = 0; p < sp2d->pages_in_unit; p++) {
 		struct __1_page_stripe *_1ps = &sp2d->_1p_stripes[p];
 
 		if (!_1ps->write_count)
 			continue;
 
-		init_async_submit(&_1ps->submit,
-			ASYNC_TX_XOR_ZERO_DST | ASYNC_TX_ACK,
-			NULL,
-			NULL, NULL,
-			(addr_conv_t *)_1ps->scribble);
-
-		/* TODO: raid6 */
-		_1ps->tx = async_xor(_1ps->pages[sp2d->data_devs], _1ps->pages,
-				     0, sp2d->data_devs, PAGE_SIZE,
-				     &_1ps->submit);
+		init_async_submit(&_1ps->submit, tx_flags,
+			NULL, NULL, NULL, (addr_conv_t *)_1ps->scribble);
+
+		if (sp2d->parity == 1)
+			_1ps->tx = async_xor(_1ps->pages[sp2d->data_devs],
+						_1ps->pages, 0, sp2d->data_devs,
+						PAGE_SIZE, &_1ps->submit);
+		else /* parity == 2 */
+			_1ps->tx = async_gen_syndrome(_1ps->pages, 0,
+						sp2d->data_devs + sp2d->parity,
+						PAGE_SIZE, &_1ps->submit);
 	}
 
 	for (p = 0; p < sp2d->pages_in_unit; p++) {
@@ -328,8 +334,8 @@ static int _alloc_read_4_write(struct ore_io_state *ios)
 /* @si contains info of the to-be-inserted page. Update of @si should be
  * maintained by caller. Specificaly si->dev, si->obj_offset, ...
  */
-static int _add_to_read_4_write(struct ore_io_state *ios,
-				struct ore_striping_info *si, struct page *page)
+static int _add_to_r4w(struct ore_io_state *ios, struct ore_striping_info *si,
+		       struct page *page, unsigned pg_len)
 {
 	struct request_queue *q;
 	struct ore_per_dev_state *per_dev;
@@ -366,17 +372,59 @@ static int _add_to_read_4_write(struct ore_io_state *ios,
 		_ore_add_sg_seg(per_dev, gap, true);
 	}
 	q = osd_request_queue(ore_comp_dev(read_ios->oc, per_dev->dev));
-	added_len = bio_add_pc_page(q, per_dev->bio, page, PAGE_SIZE, 0);
-	if (unlikely(added_len != PAGE_SIZE)) {
+	added_len = bio_add_pc_page(q, per_dev->bio, page, pg_len,
+				    si->obj_offset % PAGE_SIZE);
+	if (unlikely(added_len != pg_len)) {
 		ORE_DBGMSG("Failed to bio_add_pc_page bi_vcnt=%d\n",
 			      per_dev->bio->bi_vcnt);
 		return -ENOMEM;
 	}
 
-	per_dev->length += PAGE_SIZE;
+	per_dev->length += pg_len;
 	return 0;
 }
 
+/* read the beginning of an unaligned first page */
+static int _add_to_r4w_first_page(struct ore_io_state *ios, struct page *page)
+{
+	struct ore_striping_info si;
+	unsigned pg_len;
+
+	ore_calc_stripe_info(ios->layout, ios->offset, 0, &si);
+
+	pg_len = si.obj_offset % PAGE_SIZE;
+	si.obj_offset -= pg_len;
+
+	ORE_DBGMSG("offset=0x%llx len=0x%x index=0x%lx dev=%x\n",
+		   _LLU(si.obj_offset), pg_len, page->index, si.dev);
+
+	return _add_to_r4w(ios, &si, page, pg_len);
+}
+
+/* read the end of an incomplete last page */
+static int _add_to_r4w_last_page(struct ore_io_state *ios, u64 *offset)
+{
+	struct ore_striping_info si;
+	struct page *page;
+	unsigned pg_len, p, c;
+
+	ore_calc_stripe_info(ios->layout, *offset, 0, &si);
+
+	p = si.cur_pg;
+	c = si.cur_comp;
+	page = ios->sp2d->_1p_stripes[p].pages[c];
+
+	pg_len = PAGE_SIZE - (si.unit_off % PAGE_SIZE);
+	*offset += pg_len;
+
+	ORE_DBGMSG("p=%d, c=%d next-offset=0x%llx len=0x%x dev=%x par_dev=%d\n",
+		   p, c, _LLU(*offset), pg_len, si.dev, si.par_dev);
+
+	BUG_ON(!page);
+
+	return _add_to_r4w(ios, &si, page, pg_len);
+}
+
 static void _mark_read4write_pages_uptodate(struct ore_io_state *ios, int ret)
 {
 	struct bio_vec *bv;
@@ -389,7 +437,7 @@ static void _mark_read4write_pages_uptodate(struct ore_io_state *ios, int ret)
 		if (!bio)
 			continue;
 
-		__bio_for_each_segment(bv, bio, i, 0) {
+		bio_for_each_segment_all(bv, bio, i) {
 			struct page *page = bv->bv_page;
 
 			SetPageUptodate(page);
@@ -418,16 +466,12 @@ static void _mark_read4write_pages_uptodate(struct ore_io_state *ios, int ret)
  * ios->sp2d[p][*], xor is calculated the same way. These pages are
  * allocated/freed and don't go through cache
  */
-static int _read_4_write(struct ore_io_state *ios)
+static int _read_4_write_first_stripe(struct ore_io_state *ios)
 {
-	struct ore_io_state *ios_read;
 	struct ore_striping_info read_si;
 	struct __stripe_pages_2d *sp2d = ios->sp2d;
 	u64 offset = ios->si.first_stripe_start;
-	u64 last_stripe_end;
-	unsigned bytes_in_stripe = ios->si.bytes_in_stripe;
-	unsigned i, c, p, min_p = sp2d->pages_in_unit, max_p = -1;
-	int ret;
+	unsigned c, p, min_p = sp2d->pages_in_unit, max_p = -1;
 
 	if (offset == ios->offset) /* Go to start collect $200 */
 		goto read_last_stripe;
@@ -435,6 +479,9 @@ static int _read_4_write(struct ore_io_state *ios)
 	min_p = _sp2d_min_pg(sp2d);
 	max_p = _sp2d_max_pg(sp2d);
 
+	ORE_DBGMSG("stripe_start=0x%llx ios->offset=0x%llx min_p=%d max_p=%d\n",
+		   offset, ios->offset, min_p, max_p);
+
 	for (c = 0; ; c++) {
 		ore_calc_stripe_info(ios->layout, offset, 0, &read_si);
 		read_si.obj_offset += min_p * PAGE_SIZE;
@@ -444,9 +491,13 @@ static int _read_4_write(struct ore_io_state *ios)
 			struct page **pp = &_1ps->pages[c];
 			bool uptodate;
 
-			if (*pp)
+			if (*pp) {
+				if (ios->offset % PAGE_SIZE)
+					/* Read the remainder of the page */
+					_add_to_r4w_first_page(ios, *pp);
 				/* to-be-written pages start here */
 				goto read_last_stripe;
+			}
 
 			*pp = ios->r4w->get_page(ios->private, offset,
 						 &uptodate);
@@ -454,7 +505,7 @@ static int _read_4_write(struct ore_io_state *ios)
 				return -ENOMEM;
 
 			if (!uptodate)
-				_add_to_read_4_write(ios, &read_si, *pp);
+				_add_to_r4w(ios, &read_si, *pp, PAGE_SIZE);
 
 			/* Mark read-pages to be cache_released */
 			_1ps->page_is_read[c] = true;
@@ -465,20 +516,31 @@ static int _read_4_write(struct ore_io_state *ios)
 	}
 
 read_last_stripe:
-	offset = ios->offset + (ios->length + PAGE_SIZE - 1) /
-				PAGE_SIZE * PAGE_SIZE;
+	return 0;
+}
+
+static int _read_4_write_last_stripe(struct ore_io_state *ios)
+{
+	struct ore_striping_info read_si;
+	struct __stripe_pages_2d *sp2d = ios->sp2d;
+	u64 offset;
+	u64 last_stripe_end;
+	unsigned bytes_in_stripe = ios->si.bytes_in_stripe;
+	unsigned c, p, min_p = sp2d->pages_in_unit, max_p = -1;
+
+	offset = ios->offset + ios->length;
+	if (offset % PAGE_SIZE)
+		_add_to_r4w_last_page(ios, &offset);
+		/* offset will be aligned to next page */
+
 	last_stripe_end = div_u64(offset + bytes_in_stripe - 1, bytes_in_stripe)
 				 * bytes_in_stripe;
 	if (offset == last_stripe_end) /* Optimize for the aligned case */
 		goto read_it;
 
 	ore_calc_stripe_info(ios->layout, offset, 0, &read_si);
-	p = read_si.unit_off / PAGE_SIZE;
-	c = _dev_order(ios->layout->group_width * ios->layout->mirrors_p1,
-		       ios->layout->mirrors_p1, read_si.par_dev, read_si.dev);
-
-	BUG_ON(ios->si.first_stripe_start + bytes_in_stripe != last_stripe_end);
-	/* unaligned IO must be within a single stripe */
+	p = read_si.cur_pg;
+	c = read_si.cur_comp;
 
 	if (min_p == sp2d->pages_in_unit) {
 		/* Didn't do it yet */
@@ -486,6 +548,9 @@ read_last_stripe:
 		max_p = _sp2d_max_pg(sp2d);
 	}
 
+	ORE_DBGMSG("offset=0x%llx stripe_end=0x%llx min_p=%d max_p=%d\n",
+		   offset, last_stripe_end, min_p, max_p);
+
 	while (offset < last_stripe_end) {
 		struct __1_page_stripe *_1ps = &sp2d->_1p_stripes[p];
 
@@ -503,7 +568,7 @@ read_last_stripe:
 			/* Mark read-pages to be cache_released */
 			_1ps->page_is_read[c] = true;
 			if (!uptodate)
-				_add_to_read_4_write(ios, &read_si, page);
+				_add_to_r4w(ios, &read_si, page, PAGE_SIZE);
 		}
 
 		offset += PAGE_SIZE;
@@ -518,6 +583,15 @@ read_last_stripe:
 	}
 
 read_it:
+	return 0;
+}
+
+static int _read_4_write_execute(struct ore_io_state *ios)
+{
+	struct ore_io_state *ios_read;
+	unsigned i;
+	int ret;
+
 	ios_read = ios->ios_read_4_write;
 	if (!ios_read)
 		return 0;
@@ -541,6 +615,8 @@ read_it:
 	}
 
 	_mark_read4write_pages_uptodate(ios_read, ret);
+	ore_put_io_state(ios_read);
+	ios->ios_read_4_write = NULL; /* Might need a reuse at last stripe */
 	return 0;
 }
 
@@ -548,10 +624,14 @@ read_it:
 int _ore_add_parity_unit(struct ore_io_state *ios,
 			    struct ore_striping_info *si,
 			    struct ore_per_dev_state *per_dev,
-			    unsigned cur_len)
+			    unsigned cur_len, bool do_xor)
 {
 	if (ios->reading) {
-		BUG_ON(per_dev->cur_sg >= ios->sgs_per_dev);
+		if (per_dev->cur_sg >= ios->sgs_per_dev) {
+			ORE_DBGMSG("cur_sg(%d) >= sgs_per_dev(%d)\n" ,
+				per_dev->cur_sg, ios->sgs_per_dev);
+			return -ENOMEM;
+		}
 		_ore_add_sg_seg(per_dev, cur_len, true);
 	} else {
 		struct __stripe_pages_2d *sp2d = ios->sp2d;
@@ -564,16 +644,18 @@ int _ore_add_parity_unit(struct ore_io_state *ios,
 		si->cur_pg = _sp2d_min_pg(sp2d);
 		num_pages  = _sp2d_max_pg(sp2d) + 1 - si->cur_pg;
 
-		if (!cur_len) /* If last stripe operate on parity comp */
-			si->cur_comp = sp2d->data_devs;
-
 		if (!per_dev->length) {
 			per_dev->offset += si->cur_pg * PAGE_SIZE;
 			/* If first stripe, Read in all read4write pages
 			 * (if needed) before we calculate the first parity.
 			 */
-			_read_4_write(ios);
+			if (do_xor)
+				_read_4_write_first_stripe(ios);
 		}
+		if (!cur_len && do_xor)
+			/* If last stripe r4w pages of last stripe */
+			_read_4_write_last_stripe(ios);
+		_read_4_write_execute(ios);
 
 		for (i = 0; i < num_pages; i++) {
 			pages[i] = _raid_page_alloc();
@@ -583,7 +665,7 @@ int _ore_add_parity_unit(struct ore_io_state *ios,
 			++(ios->cur_par_page);
 		}
 
-		BUG_ON(si->cur_comp != sp2d->data_devs);
+		BUG_ON(si->cur_comp < sp2d->data_devs);
 		BUG_ON(si->cur_pg + num_pages > sp2d->pages_in_unit);
 
 		ret = _ore_add_stripe_unit(ios,  &array_start, 0, pages,
@@ -591,45 +673,24 @@ int _ore_add_parity_unit(struct ore_io_state *ios,
 		if (unlikely(ret))
 			return ret;
 
-		/* TODO: raid6 if (last_parity_dev) */
-		_gen_xor_unit(sp2d);
-		_sp2d_reset(sp2d, ios->r4w, ios->private);
+		if (do_xor) {
+			_gen_xor_unit(sp2d);
+			_sp2d_reset(sp2d, ios->r4w, ios->private);
+		}
 	}
 	return 0;
 }
 
 int _ore_post_alloc_raid_stuff(struct ore_io_state *ios)
 {
-	struct ore_layout *layout = ios->layout;
-
 	if (ios->parity_pages) {
+		struct ore_layout *layout = ios->layout;
 		unsigned pages_in_unit = layout->stripe_unit / PAGE_SIZE;
-		unsigned stripe_size = ios->si.bytes_in_stripe;
-		u64 last_stripe, first_stripe;
 
 		if (_sp2d_alloc(pages_in_unit, layout->group_width,
 				layout->parity, &ios->sp2d)) {
 			return -ENOMEM;
 		}
-
-		BUG_ON(ios->offset % PAGE_SIZE);
-
-		/* Round io down to last full strip */
-		first_stripe = div_u64(ios->offset, stripe_size);
-		last_stripe = div_u64(ios->offset + ios->length, stripe_size);
-
-		/* If an IO spans more then a single stripe it must end at
-		 * a stripe boundary. The reminder at the end is pushed into the
-		 * next IO.
-		 */
-		if (last_stripe != first_stripe) {
-			ios->length = last_stripe * stripe_size - ios->offset;
-
-			BUG_ON(!ios->length);
-			ios->nr_pages = (ios->length + PAGE_SIZE - 1) /
-					PAGE_SIZE;
-			ios->si.length = ios->length; /*make it consistent */
-		}
 	}
 	return 0;
 }