Merge branch 'for-linus' of git://git.open-osd.org/linux-open-osd

Pull exofs and ore fixes from Boaz Harrosh:
 "The main fix here, the first patch, is also destined for -stable.  The
  rest is small trivia and cosmetics.  The ORE patches effect both exofs
  and pnfs-objects very reproducible bugs"

[ ORE is "object raid engine", used by exofs and pnfs  - Linus ]

* 'for-linus' of git://git.open-osd.org/linux-open-osd:
  exofs: Print less in r4w
  exofs: Allow corrupted directory entry to be empty file
  exofs: Allow O_DIRECT open
  ore: Don't crash on NULL bio in _clear_bio
  ore: Fix wrong math in allocation of per device BIO

diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c
index a52a5d23c30bcfac672df7197c51b966cc087787..ee4317faccb1951852b483d825a5ccec7efa8a24 100644 (file)
--- a/fs/exofs/inode.c
+++ b/fs/exofs/inode.c
@@ -577,7 +577,7 @@ static struct page *__r4w_get_page(void *priv, u64 offset, bool *uptodate)
 
                if (offset >= i_size) {
                        *uptodate = true;
-                       EXOFS_DBGMSG("offset >= i_size index=0x%lx\n", index);
+                       EXOFS_DBGMSG2("offset >= i_size index=0x%lx\n", index);
                        return ZERO_PAGE(0);
                }
 
@@ -596,10 +596,10 @@ static struct page *__r4w_get_page(void *priv, u64 offset, bool *uptodate)
                        *uptodate = true;
                else
                        *uptodate = PageUptodate(page);
-               EXOFS_DBGMSG("index=0x%lx uptodate=%d\n", index, *uptodate);
+               EXOFS_DBGMSG2("index=0x%lx uptodate=%d\n", index, *uptodate);
                return page;
        } else {
-               EXOFS_DBGMSG("YES that_locked_page index=0x%lx\n",
+               EXOFS_DBGMSG2("YES that_locked_page index=0x%lx\n",
                             pcol->that_locked_page->index);
                *uptodate = true;
                return pcol->that_locked_page;
@@ -611,11 +611,11 @@ static void __r4w_put_page(void *priv, struct page *page)
        struct page_collect *pcol = priv;
 
        if ((pcol->that_locked_page != page) && (ZERO_PAGE(0) != page)) {
-               EXOFS_DBGMSG("index=0x%lx\n", page->index);
+               EXOFS_DBGMSG2("index=0x%lx\n", page->index);
                page_cache_release(page);
                return;
        }
-       EXOFS_DBGMSG("that_locked_page index=0x%lx\n",
+       EXOFS_DBGMSG2("that_locked_page index=0x%lx\n",
                     ZERO_PAGE(0) == page ? -1 : page->index);
 }
 
@@ -961,6 +961,14 @@ static void exofs_invalidatepage(struct page *page, unsigned int offset,
        WARN_ON(1);
 }
 
+
+ /* TODO: Should be easy enough to do proprly */
+static ssize_t exofs_direct_IO(int rw, struct kiocb *iocb,
+               const struct iovec *iov, loff_t offset, unsigned long nr_segs)
+{
+       return 0;
+}
+
 const struct address_space_operations exofs_aops = {
        .readpage       = exofs_readpage,
        .readpages      = exofs_readpages,
@@ -974,7 +982,7 @@ const struct address_space_operations exofs_aops = {
 
        /* Not implemented Yet */
        .bmap           = NULL, /* TODO: use osd's OSD_ACT_READ_MAP */
-       .direct_IO      = NULL, /* TODO: Should be trivial to do */
+       .direct_IO      = exofs_direct_IO,
 
        /* With these NULL has special meaning or default is not exported */
        .get_xip_mem    = NULL,
@@ -1010,7 +1018,7 @@ static int _do_truncate(struct inode *inode, loff_t newsize)
        if (likely(!ret))
                truncate_setsize(inode, newsize);
 
-       EXOFS_DBGMSG("(0x%lx) size=0x%llx ret=>%d\n",
+       EXOFS_DBGMSG2("(0x%lx) size=0x%llx ret=>%d\n",
                     inode->i_ino, newsize, ret);
        return ret;
 }
@@ -1094,14 +1102,13 @@ static int exofs_get_inode(struct super_block *sb, struct exofs_i_info *oi,
                /* If object is lost on target we might as well enable it's
                 * delete.
                 */
-               if ((ret == -ENOENT) || (ret == -EINVAL))
-                       ret = 0;
+               ret = 0;
                goto out;
        }
 
        ret = extract_attr_from_ios(ios, &attrs[0]);
        if (ret) {
-               EXOFS_ERR("%s: extract_attr of inode_data failed\n", __func__);
+               EXOFS_ERR("%s: extract_attr 0 of inode failed\n", __func__);
                goto out;
        }
        WARN_ON(attrs[0].len != EXOFS_INO_ATTR_SIZE);
@@ -1109,7 +1116,7 @@ static int exofs_get_inode(struct super_block *sb, struct exofs_i_info *oi,
 
        ret = extract_attr_from_ios(ios, &attrs[1]);
        if (ret) {
-               EXOFS_ERR("%s: extract_attr of inode_data failed\n", __func__);
+               EXOFS_ERR("%s: extract_attr 1 of inode failed\n", __func__);
                goto out;
        }
        if (attrs[1].len) {
@@ -1124,7 +1131,7 @@ static int exofs_get_inode(struct super_block *sb, struct exofs_i_info *oi,
 
        ret = extract_attr_from_ios(ios, &attrs[2]);
        if (ret) {
-               EXOFS_ERR("%s: extract_attr of inode_data failed\n", __func__);
+               EXOFS_ERR("%s: extract_attr 2 of inode failed\n", __func__);
                goto out;
        }
        if (attrs[2].len) {

diff --git a/fs/exofs/ore.c b/fs/exofs/ore.c
index b744228886043d522fa15a32ff98cc80d29db3c9..dae884694bd99cd82643a5427c4981ea05c9639b 100644 (file)
--- a/fs/exofs/ore.c
+++ b/fs/exofs/ore.c
@@ -103,7 +103,7 @@ int ore_verify_layout(unsigned total_comps, struct ore_layout *layout)
 
        layout->max_io_length =
                (BIO_MAX_PAGES_KMALLOC * PAGE_SIZE - layout->stripe_unit) *
-                                                       layout->group_width;
+                                       (layout->group_width - layout->parity);
        if (layout->parity) {
                unsigned stripe_length =
                                (layout->group_width - layout->parity) *
@@ -286,7 +286,8 @@ int  ore_get_rw_state(struct ore_layout *layout, struct ore_components *oc,
        if (length) {
                ore_calc_stripe_info(layout, offset, length, &ios->si);
                ios->length = ios->si.length;
-               ios->nr_pages = (ios->length + PAGE_SIZE - 1) / PAGE_SIZE;
+               ios->nr_pages = ((ios->offset & (PAGE_SIZE - 1)) +
+                                ios->length + PAGE_SIZE - 1) / PAGE_SIZE;
                if (layout->parity)
                        _ore_post_alloc_raid_stuff(ios);
        }
@@ -430,8 +431,12 @@ int ore_check_io(struct ore_io_state *ios, ore_on_dev_error on_dev_error)
                if (likely(!ret))
                        continue;
 
-               if (OSD_ERR_PRI_CLEAR_PAGES == osi.osd_err_pri) {
-                       /* start read offset passed endof file */
+               if ((OSD_ERR_PRI_CLEAR_PAGES == osi.osd_err_pri) &&
+                   per_dev->bio) {
+                       /* start read offset passed endof file.
+                        * Note: if we do not have bio it means read-attributes
+                        * In this case we should return error to caller.
+                        */
                        _clear_bio(per_dev->bio);
                        ORE_DBGMSG("start read offset passed end of file "
                                "offset=0x%llx, length=0x%llx\n",
@@ -536,6 +541,7 @@ void ore_calc_stripe_info(struct ore_layout *layout, u64 file_offset,
        u64     H = LmodS - G * T;
 
        u32     N = div_u64(H, U);
+       u32     Nlast;
 
        /* "H - (N * U)" is just "H % U" so it's bound to u32 */
        u32     C = (u32)(H - (N * U)) / stripe_unit + G * group_width;
@@ -568,6 +574,10 @@ void ore_calc_stripe_info(struct ore_layout *layout, u64 file_offset,
        si->length = T - H;
        if (si->length > length)
                si->length = length;
+
+       Nlast = div_u64(H + si->length + U - 1, U);
+       si->maxdevUnits = Nlast - N;
+
        si->M = M;
 }
 EXPORT_SYMBOL(ore_calc_stripe_info);
@@ -583,13 +593,16 @@ int _ore_add_stripe_unit(struct ore_io_state *ios,  unsigned *cur_pg,
        int ret;
 
        if (per_dev->bio == NULL) {
-               unsigned pages_in_stripe = ios->layout->group_width *
-                                       (ios->layout->stripe_unit / PAGE_SIZE);
-               unsigned nr_pages = ios->nr_pages * ios->layout->group_width /
-                                       (ios->layout->group_width -
-                                        ios->layout->parity);
-               unsigned bio_size = (nr_pages + pages_in_stripe) /
-                                       ios->layout->group_width;
+               unsigned bio_size;
+
+               if (!ios->reading) {
+                       bio_size = ios->si.maxdevUnits;
+               } else {
+                       bio_size = (ios->si.maxdevUnits + 1) *
+                            (ios->layout->group_width - ios->layout->parity) /
+                            ios->layout->group_width;
+               }
+               bio_size *= (ios->layout->stripe_unit / PAGE_SIZE);
 
                per_dev->bio = bio_kmalloc(GFP_KERNEL, bio_size);
                if (unlikely(!per_dev->bio)) {
@@ -609,8 +622,12 @@ int _ore_add_stripe_unit(struct ore_io_state *ios,  unsigned *cur_pg,
                added_len = bio_add_pc_page(q, per_dev->bio, pages[pg],
                                            pglen, pgbase);
                if (unlikely(pglen != added_len)) {
-                       ORE_DBGMSG("Failed bio_add_pc_page bi_vcnt=%u\n",
-                                  per_dev->bio->bi_vcnt);
+                       /* If bi_vcnt == bi_max then this is a SW BUG */
+                       ORE_DBGMSG("Failed bio_add_pc_page bi_vcnt=0x%x "
+                                  "bi_max=0x%x BIO_MAX=0x%x cur_len=0x%x\n",
+                                  per_dev->bio->bi_vcnt,
+                                  per_dev->bio->bi_max_vecs,
+                                  BIO_MAX_PAGES_KMALLOC, cur_len);
                        ret = -ENOMEM;
                        goto out;
                }
@@ -1098,7 +1115,7 @@ int ore_truncate(struct ore_layout *layout, struct ore_components *oc,
                size_attr->attr = g_attr_logical_length;
                size_attr->attr.val_ptr = &size_attr->newsize;
 
-               ORE_DBGMSG("trunc(0x%llx) obj_offset=0x%llx dev=%d\n",
+               ORE_DBGMSG2("trunc(0x%llx) obj_offset=0x%llx dev=%d\n",
                             _LLU(oc->comps->obj.id), _LLU(obj_size), i);
                ret = _truncate_mirrors(ios, i * ios->layout->mirrors_p1,
                                        &size_attr->attr);

diff --git a/include/scsi/osd_ore.h b/include/scsi/osd_ore.h
index a5f9b960dfc8f0ca329c1fc510956f379e817fdd..6ca3265a4dcacaff704e32a329f546a421c2971e 100644 (file)
--- a/include/scsi/osd_ore.h
+++ b/include/scsi/osd_ore.h
@@ -102,6 +102,7 @@ struct ore_striping_info {
        unsigned unit_off;
        unsigned cur_pg;
        unsigned cur_comp;
+       unsigned maxdevUnits;
 };
 
 struct ore_io_state;