2009-10-07 02:31:10 +08:00
|
|
|
|
2010-04-07 06:14:15 +08:00
|
|
|
#include <linux/ceph/ceph_debug.h>
|
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h
percpu.h is included by sched.h and module.h and thus ends up being
included when building most .c files. percpu.h includes slab.h which
in turn includes gfp.h making everything defined by the two files
universally available and complicating inclusion dependencies.
percpu.h -> slab.h dependency is about to be removed. Prepare for
this change by updating users of gfp and slab facilities include those
headers directly instead of assuming availability. As this conversion
needs to touch large number of source files, the following script is
used as the basis of conversion.
http://userweb.kernel.org/~tj/misc/slabh-sweep.py
The script does the followings.
* Scan files for gfp and slab usages and update includes such that
only the necessary includes are there. ie. if only gfp is used,
gfp.h, if slab is used, slab.h.
* When the script inserts a new include, it looks at the include
blocks and try to put the new include such that its order conforms
to its surrounding. It's put in the include block which contains
core kernel includes, in the same order that the rest are ordered -
alphabetical, Christmas tree, rev-Xmas-tree or at the end if there
doesn't seem to be any matching order.
* If the script can't find a place to put a new include (mostly
because the file doesn't have fitting include block), it prints out
an error message indicating which .h file needs to be added to the
file.
The conversion was done in the following steps.
1. The initial automatic conversion of all .c files updated slightly
over 4000 files, deleting around 700 includes and adding ~480 gfp.h
and ~3000 slab.h inclusions. The script emitted errors for ~400
files.
2. Each error was manually checked. Some didn't need the inclusion,
some needed manual addition while adding it to implementation .h or
embedding .c file was more appropriate for others. This step added
inclusions to around 150 files.
3. The script was run again and the output was compared to the edits
from #2 to make sure no file was left behind.
4. Several build tests were done and a couple of problems were fixed.
e.g. lib/decompress_*.c used malloc/free() wrappers around slab
APIs requiring slab.h to be added manually.
5. The script was run on all .h files but without automatically
editing them as sprinkling gfp.h and slab.h inclusions around .h
files could easily lead to inclusion dependency hell. Most gfp.h
inclusion directives were ignored as stuff from gfp.h was usually
wildly available and often used in preprocessor macros. Each
slab.h inclusion directive was examined and added manually as
necessary.
6. percpu.h was updated not to include slab.h.
7. Build test were done on the following configurations and failures
were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my
distributed build env didn't work with gcov compiles) and a few
more options had to be turned off depending on archs to make things
build (like ipr on powerpc/64 which failed due to missing writeq).
* x86 and x86_64 UP and SMP allmodconfig and a custom test config.
* powerpc and powerpc64 SMP allmodconfig
* sparc and sparc64 SMP allmodconfig
* ia64 SMP allmodconfig
* s390 SMP allmodconfig
* alpha SMP allmodconfig
* um on x86_64 SMP allmodconfig
8. percpu.h modifications were reverted so that it could be applied as
a separate patch and serve as bisection point.
Given the fact that I had only a couple of failures from tests on step
6, I'm fairly confident about the coverage of this conversion patch.
If there is a breakage, it's likely to be something in one of the arch
headers which should be easily discoverable easily on most builds of
the specific arch.
Signed-off-by: Tejun Heo <tj@kernel.org>
Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
|
|
|
|
2010-04-07 06:14:15 +08:00
|
|
|
#include <linux/module.h>
|
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h
percpu.h is included by sched.h and module.h and thus ends up being
included when building most .c files. percpu.h includes slab.h which
in turn includes gfp.h making everything defined by the two files
universally available and complicating inclusion dependencies.
percpu.h -> slab.h dependency is about to be removed. Prepare for
this change by updating users of gfp and slab facilities include those
headers directly instead of assuming availability. As this conversion
needs to touch large number of source files, the following script is
used as the basis of conversion.
http://userweb.kernel.org/~tj/misc/slabh-sweep.py
The script does the followings.
* Scan files for gfp and slab usages and update includes such that
only the necessary includes are there. ie. if only gfp is used,
gfp.h, if slab is used, slab.h.
* When the script inserts a new include, it looks at the include
blocks and try to put the new include such that its order conforms
to its surrounding. It's put in the include block which contains
core kernel includes, in the same order that the rest are ordered -
alphabetical, Christmas tree, rev-Xmas-tree or at the end if there
doesn't seem to be any matching order.
* If the script can't find a place to put a new include (mostly
because the file doesn't have fitting include block), it prints out
an error message indicating which .h file needs to be added to the
file.
The conversion was done in the following steps.
1. The initial automatic conversion of all .c files updated slightly
over 4000 files, deleting around 700 includes and adding ~480 gfp.h
and ~3000 slab.h inclusions. The script emitted errors for ~400
files.
2. Each error was manually checked. Some didn't need the inclusion,
some needed manual addition while adding it to implementation .h or
embedding .c file was more appropriate for others. This step added
inclusions to around 150 files.
3. The script was run again and the output was compared to the edits
from #2 to make sure no file was left behind.
4. Several build tests were done and a couple of problems were fixed.
e.g. lib/decompress_*.c used malloc/free() wrappers around slab
APIs requiring slab.h to be added manually.
5. The script was run on all .h files but without automatically
editing them as sprinkling gfp.h and slab.h inclusions around .h
files could easily lead to inclusion dependency hell. Most gfp.h
inclusion directives were ignored as stuff from gfp.h was usually
wildly available and often used in preprocessor macros. Each
slab.h inclusion directive was examined and added manually as
necessary.
6. percpu.h was updated not to include slab.h.
7. Build test were done on the following configurations and failures
were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my
distributed build env didn't work with gcov compiles) and a few
more options had to be turned off depending on archs to make things
build (like ipr on powerpc/64 which failed due to missing writeq).
* x86 and x86_64 UP and SMP allmodconfig and a custom test config.
* powerpc and powerpc64 SMP allmodconfig
* sparc and sparc64 SMP allmodconfig
* ia64 SMP allmodconfig
* s390 SMP allmodconfig
* alpha SMP allmodconfig
* um on x86_64 SMP allmodconfig
8. percpu.h modifications were reverted so that it could be applied as
a separate patch and serve as bisection point.
Given the fact that I had only a couple of failures from tests on step
6, I'm fairly confident about the coverage of this conversion patch.
If there is a breakage, it's likely to be something in one of the arch
headers which should be easily discoverable easily on most builds of
the specific arch.
Signed-off-by: Tejun Heo <tj@kernel.org>
Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
|
|
|
#include <linux/slab.h>
|
2009-10-07 02:31:10 +08:00
|
|
|
#include <asm/div64.h>
|
|
|
|
|
2010-04-07 06:14:15 +08:00
|
|
|
#include <linux/ceph/libceph.h>
|
|
|
|
#include <linux/ceph/osdmap.h>
|
|
|
|
#include <linux/ceph/decode.h>
|
|
|
|
#include <linux/crush/hash.h>
|
|
|
|
#include <linux/crush/mapper.h>
|
2009-10-07 02:31:10 +08:00
|
|
|
|
|
|
|
char *ceph_osdmap_state_str(char *str, int len, int state)
|
|
|
|
{
|
|
|
|
int flag = 0;
|
|
|
|
|
|
|
|
if (!len)
|
|
|
|
goto done;
|
|
|
|
|
|
|
|
*str = '\0';
|
|
|
|
if (state) {
|
|
|
|
if (state & CEPH_OSD_EXISTS) {
|
|
|
|
snprintf(str, len, "exists");
|
|
|
|
flag = 1;
|
|
|
|
}
|
|
|
|
if (state & CEPH_OSD_UP) {
|
|
|
|
snprintf(str, len, "%s%s%s", str, (flag ? ", " : ""),
|
|
|
|
"up");
|
|
|
|
flag = 1;
|
|
|
|
}
|
|
|
|
} else {
|
|
|
|
snprintf(str, len, "doesn't exist");
|
|
|
|
}
|
|
|
|
done:
|
|
|
|
return str;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* maps */
|
|
|
|
|
|
|
|
static int calc_bits_of(unsigned t)
|
|
|
|
{
|
|
|
|
int b = 0;
|
|
|
|
while (t) {
|
|
|
|
t = t >> 1;
|
|
|
|
b++;
|
|
|
|
}
|
|
|
|
return b;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* the foo_mask is the smallest value 2^n-1 that is >= foo.
|
|
|
|
*/
|
|
|
|
static void calc_pg_masks(struct ceph_pg_pool_info *pi)
|
|
|
|
{
|
|
|
|
pi->pg_num_mask = (1 << calc_bits_of(le32_to_cpu(pi->v.pg_num)-1)) - 1;
|
|
|
|
pi->pgp_num_mask =
|
|
|
|
(1 << calc_bits_of(le32_to_cpu(pi->v.pgp_num)-1)) - 1;
|
|
|
|
pi->lpg_num_mask =
|
|
|
|
(1 << calc_bits_of(le32_to_cpu(pi->v.lpg_num)-1)) - 1;
|
|
|
|
pi->lpgp_num_mask =
|
|
|
|
(1 << calc_bits_of(le32_to_cpu(pi->v.lpgp_num)-1)) - 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* decode crush map
|
|
|
|
*/
|
|
|
|
static int crush_decode_uniform_bucket(void **p, void *end,
|
|
|
|
struct crush_bucket_uniform *b)
|
|
|
|
{
|
|
|
|
dout("crush_decode_uniform_bucket %p to %p\n", *p, end);
|
|
|
|
ceph_decode_need(p, end, (1+b->h.size) * sizeof(u32), bad);
|
2009-10-15 00:59:09 +08:00
|
|
|
b->item_weight = ceph_decode_32(p);
|
2009-10-07 02:31:10 +08:00
|
|
|
return 0;
|
|
|
|
bad:
|
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int crush_decode_list_bucket(void **p, void *end,
|
|
|
|
struct crush_bucket_list *b)
|
|
|
|
{
|
|
|
|
int j;
|
|
|
|
dout("crush_decode_list_bucket %p to %p\n", *p, end);
|
|
|
|
b->item_weights = kcalloc(b->h.size, sizeof(u32), GFP_NOFS);
|
|
|
|
if (b->item_weights == NULL)
|
|
|
|
return -ENOMEM;
|
|
|
|
b->sum_weights = kcalloc(b->h.size, sizeof(u32), GFP_NOFS);
|
|
|
|
if (b->sum_weights == NULL)
|
|
|
|
return -ENOMEM;
|
|
|
|
ceph_decode_need(p, end, 2 * b->h.size * sizeof(u32), bad);
|
|
|
|
for (j = 0; j < b->h.size; j++) {
|
2009-10-15 00:59:09 +08:00
|
|
|
b->item_weights[j] = ceph_decode_32(p);
|
|
|
|
b->sum_weights[j] = ceph_decode_32(p);
|
2009-10-07 02:31:10 +08:00
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
bad:
|
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int crush_decode_tree_bucket(void **p, void *end,
|
|
|
|
struct crush_bucket_tree *b)
|
|
|
|
{
|
|
|
|
int j;
|
|
|
|
dout("crush_decode_tree_bucket %p to %p\n", *p, end);
|
|
|
|
ceph_decode_32_safe(p, end, b->num_nodes, bad);
|
|
|
|
b->node_weights = kcalloc(b->num_nodes, sizeof(u32), GFP_NOFS);
|
|
|
|
if (b->node_weights == NULL)
|
|
|
|
return -ENOMEM;
|
|
|
|
ceph_decode_need(p, end, b->num_nodes * sizeof(u32), bad);
|
|
|
|
for (j = 0; j < b->num_nodes; j++)
|
2009-10-15 00:59:09 +08:00
|
|
|
b->node_weights[j] = ceph_decode_32(p);
|
2009-10-07 02:31:10 +08:00
|
|
|
return 0;
|
|
|
|
bad:
|
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int crush_decode_straw_bucket(void **p, void *end,
|
|
|
|
struct crush_bucket_straw *b)
|
|
|
|
{
|
|
|
|
int j;
|
|
|
|
dout("crush_decode_straw_bucket %p to %p\n", *p, end);
|
|
|
|
b->item_weights = kcalloc(b->h.size, sizeof(u32), GFP_NOFS);
|
|
|
|
if (b->item_weights == NULL)
|
|
|
|
return -ENOMEM;
|
|
|
|
b->straws = kcalloc(b->h.size, sizeof(u32), GFP_NOFS);
|
|
|
|
if (b->straws == NULL)
|
|
|
|
return -ENOMEM;
|
|
|
|
ceph_decode_need(p, end, 2 * b->h.size * sizeof(u32), bad);
|
|
|
|
for (j = 0; j < b->h.size; j++) {
|
2009-10-15 00:59:09 +08:00
|
|
|
b->item_weights[j] = ceph_decode_32(p);
|
|
|
|
b->straws[j] = ceph_decode_32(p);
|
2009-10-07 02:31:10 +08:00
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
bad:
|
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
|
|
|
|
static struct crush_map *crush_decode(void *pbyval, void *end)
|
|
|
|
{
|
|
|
|
struct crush_map *c;
|
|
|
|
int err = -EINVAL;
|
|
|
|
int i, j;
|
|
|
|
void **p = &pbyval;
|
|
|
|
void *start = pbyval;
|
|
|
|
u32 magic;
|
|
|
|
|
|
|
|
dout("crush_decode %p to %p len %d\n", *p, end, (int)(end - *p));
|
|
|
|
|
|
|
|
c = kzalloc(sizeof(*c), GFP_NOFS);
|
|
|
|
if (c == NULL)
|
|
|
|
return ERR_PTR(-ENOMEM);
|
|
|
|
|
|
|
|
ceph_decode_need(p, end, 4*sizeof(u32), bad);
|
2009-10-15 00:59:09 +08:00
|
|
|
magic = ceph_decode_32(p);
|
2009-10-07 02:31:10 +08:00
|
|
|
if (magic != CRUSH_MAGIC) {
|
|
|
|
pr_err("crush_decode magic %x != current %x\n",
|
|
|
|
(unsigned)magic, (unsigned)CRUSH_MAGIC);
|
|
|
|
goto bad;
|
|
|
|
}
|
2009-10-15 00:59:09 +08:00
|
|
|
c->max_buckets = ceph_decode_32(p);
|
|
|
|
c->max_rules = ceph_decode_32(p);
|
|
|
|
c->max_devices = ceph_decode_32(p);
|
2009-10-07 02:31:10 +08:00
|
|
|
|
|
|
|
c->device_parents = kcalloc(c->max_devices, sizeof(u32), GFP_NOFS);
|
|
|
|
if (c->device_parents == NULL)
|
|
|
|
goto badmem;
|
|
|
|
c->bucket_parents = kcalloc(c->max_buckets, sizeof(u32), GFP_NOFS);
|
|
|
|
if (c->bucket_parents == NULL)
|
|
|
|
goto badmem;
|
|
|
|
|
|
|
|
c->buckets = kcalloc(c->max_buckets, sizeof(*c->buckets), GFP_NOFS);
|
|
|
|
if (c->buckets == NULL)
|
|
|
|
goto badmem;
|
|
|
|
c->rules = kcalloc(c->max_rules, sizeof(*c->rules), GFP_NOFS);
|
|
|
|
if (c->rules == NULL)
|
|
|
|
goto badmem;
|
|
|
|
|
|
|
|
/* buckets */
|
|
|
|
for (i = 0; i < c->max_buckets; i++) {
|
|
|
|
int size = 0;
|
|
|
|
u32 alg;
|
|
|
|
struct crush_bucket *b;
|
|
|
|
|
|
|
|
ceph_decode_32_safe(p, end, alg, bad);
|
|
|
|
if (alg == 0) {
|
|
|
|
c->buckets[i] = NULL;
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
dout("crush_decode bucket %d off %x %p to %p\n",
|
|
|
|
i, (int)(*p-start), *p, end);
|
|
|
|
|
|
|
|
switch (alg) {
|
|
|
|
case CRUSH_BUCKET_UNIFORM:
|
|
|
|
size = sizeof(struct crush_bucket_uniform);
|
|
|
|
break;
|
|
|
|
case CRUSH_BUCKET_LIST:
|
|
|
|
size = sizeof(struct crush_bucket_list);
|
|
|
|
break;
|
|
|
|
case CRUSH_BUCKET_TREE:
|
|
|
|
size = sizeof(struct crush_bucket_tree);
|
|
|
|
break;
|
|
|
|
case CRUSH_BUCKET_STRAW:
|
|
|
|
size = sizeof(struct crush_bucket_straw);
|
|
|
|
break;
|
|
|
|
default:
|
2009-12-22 06:49:37 +08:00
|
|
|
err = -EINVAL;
|
2009-10-07 02:31:10 +08:00
|
|
|
goto bad;
|
|
|
|
}
|
|
|
|
BUG_ON(size == 0);
|
|
|
|
b = c->buckets[i] = kzalloc(size, GFP_NOFS);
|
|
|
|
if (b == NULL)
|
|
|
|
goto badmem;
|
|
|
|
|
|
|
|
ceph_decode_need(p, end, 4*sizeof(u32), bad);
|
2009-10-15 00:59:09 +08:00
|
|
|
b->id = ceph_decode_32(p);
|
|
|
|
b->type = ceph_decode_16(p);
|
2009-11-08 12:18:22 +08:00
|
|
|
b->alg = ceph_decode_8(p);
|
|
|
|
b->hash = ceph_decode_8(p);
|
2009-10-15 00:59:09 +08:00
|
|
|
b->weight = ceph_decode_32(p);
|
|
|
|
b->size = ceph_decode_32(p);
|
2009-10-07 02:31:10 +08:00
|
|
|
|
|
|
|
dout("crush_decode bucket size %d off %x %p to %p\n",
|
|
|
|
b->size, (int)(*p-start), *p, end);
|
|
|
|
|
|
|
|
b->items = kcalloc(b->size, sizeof(__s32), GFP_NOFS);
|
|
|
|
if (b->items == NULL)
|
|
|
|
goto badmem;
|
|
|
|
b->perm = kcalloc(b->size, sizeof(u32), GFP_NOFS);
|
|
|
|
if (b->perm == NULL)
|
|
|
|
goto badmem;
|
|
|
|
b->perm_n = 0;
|
|
|
|
|
|
|
|
ceph_decode_need(p, end, b->size*sizeof(u32), bad);
|
|
|
|
for (j = 0; j < b->size; j++)
|
2009-10-15 00:59:09 +08:00
|
|
|
b->items[j] = ceph_decode_32(p);
|
2009-10-07 02:31:10 +08:00
|
|
|
|
|
|
|
switch (b->alg) {
|
|
|
|
case CRUSH_BUCKET_UNIFORM:
|
|
|
|
err = crush_decode_uniform_bucket(p, end,
|
|
|
|
(struct crush_bucket_uniform *)b);
|
|
|
|
if (err < 0)
|
|
|
|
goto bad;
|
|
|
|
break;
|
|
|
|
case CRUSH_BUCKET_LIST:
|
|
|
|
err = crush_decode_list_bucket(p, end,
|
|
|
|
(struct crush_bucket_list *)b);
|
|
|
|
if (err < 0)
|
|
|
|
goto bad;
|
|
|
|
break;
|
|
|
|
case CRUSH_BUCKET_TREE:
|
|
|
|
err = crush_decode_tree_bucket(p, end,
|
|
|
|
(struct crush_bucket_tree *)b);
|
|
|
|
if (err < 0)
|
|
|
|
goto bad;
|
|
|
|
break;
|
|
|
|
case CRUSH_BUCKET_STRAW:
|
|
|
|
err = crush_decode_straw_bucket(p, end,
|
|
|
|
(struct crush_bucket_straw *)b);
|
|
|
|
if (err < 0)
|
|
|
|
goto bad;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/* rules */
|
|
|
|
dout("rule vec is %p\n", c->rules);
|
|
|
|
for (i = 0; i < c->max_rules; i++) {
|
|
|
|
u32 yes;
|
|
|
|
struct crush_rule *r;
|
|
|
|
|
|
|
|
ceph_decode_32_safe(p, end, yes, bad);
|
|
|
|
if (!yes) {
|
|
|
|
dout("crush_decode NO rule %d off %x %p to %p\n",
|
|
|
|
i, (int)(*p-start), *p, end);
|
|
|
|
c->rules[i] = NULL;
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
|
|
|
|
dout("crush_decode rule %d off %x %p to %p\n",
|
|
|
|
i, (int)(*p-start), *p, end);
|
|
|
|
|
|
|
|
/* len */
|
|
|
|
ceph_decode_32_safe(p, end, yes, bad);
|
|
|
|
#if BITS_PER_LONG == 32
|
2009-12-22 06:49:37 +08:00
|
|
|
err = -EINVAL;
|
2009-10-07 02:31:10 +08:00
|
|
|
if (yes > ULONG_MAX / sizeof(struct crush_rule_step))
|
|
|
|
goto bad;
|
|
|
|
#endif
|
|
|
|
r = c->rules[i] = kmalloc(sizeof(*r) +
|
|
|
|
yes*sizeof(struct crush_rule_step),
|
|
|
|
GFP_NOFS);
|
|
|
|
if (r == NULL)
|
|
|
|
goto badmem;
|
|
|
|
dout(" rule %d is at %p\n", i, r);
|
|
|
|
r->len = yes;
|
|
|
|
ceph_decode_copy_safe(p, end, &r->mask, 4, bad); /* 4 u8's */
|
|
|
|
ceph_decode_need(p, end, r->len*3*sizeof(u32), bad);
|
|
|
|
for (j = 0; j < r->len; j++) {
|
2009-10-15 00:59:09 +08:00
|
|
|
r->steps[j].op = ceph_decode_32(p);
|
|
|
|
r->steps[j].arg1 = ceph_decode_32(p);
|
|
|
|
r->steps[j].arg2 = ceph_decode_32(p);
|
2009-10-07 02:31:10 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/* ignore trailing name maps. */
|
|
|
|
|
|
|
|
dout("crush_decode success\n");
|
|
|
|
return c;
|
|
|
|
|
|
|
|
badmem:
|
|
|
|
err = -ENOMEM;
|
|
|
|
bad:
|
|
|
|
dout("crush_decode fail %d\n", err);
|
|
|
|
crush_destroy(c);
|
|
|
|
return ERR_PTR(err);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
2010-02-17 07:53:32 +08:00
|
|
|
* rbtree of pg_mapping for handling pg_temp (explicit mapping of pgid
|
|
|
|
* to a set of osds)
|
2009-10-07 02:31:10 +08:00
|
|
|
*/
|
2009-11-05 03:39:12 +08:00
|
|
|
static int pgid_cmp(struct ceph_pg l, struct ceph_pg r)
|
|
|
|
{
|
|
|
|
u64 a = *(u64 *)&l;
|
|
|
|
u64 b = *(u64 *)&r;
|
|
|
|
|
|
|
|
if (a < b)
|
|
|
|
return -1;
|
|
|
|
if (a > b)
|
|
|
|
return 1;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2009-10-09 13:22:37 +08:00
|
|
|
static int __insert_pg_mapping(struct ceph_pg_mapping *new,
|
|
|
|
struct rb_root *root)
|
2009-10-07 02:31:10 +08:00
|
|
|
{
|
|
|
|
struct rb_node **p = &root->rb_node;
|
|
|
|
struct rb_node *parent = NULL;
|
|
|
|
struct ceph_pg_mapping *pg = NULL;
|
2009-11-05 03:39:12 +08:00
|
|
|
int c;
|
2009-10-07 02:31:10 +08:00
|
|
|
|
|
|
|
while (*p) {
|
|
|
|
parent = *p;
|
|
|
|
pg = rb_entry(parent, struct ceph_pg_mapping, node);
|
2009-11-05 03:39:12 +08:00
|
|
|
c = pgid_cmp(new->pgid, pg->pgid);
|
|
|
|
if (c < 0)
|
2009-10-07 02:31:10 +08:00
|
|
|
p = &(*p)->rb_left;
|
2009-11-05 03:39:12 +08:00
|
|
|
else if (c > 0)
|
2009-10-07 02:31:10 +08:00
|
|
|
p = &(*p)->rb_right;
|
|
|
|
else
|
2009-10-09 13:22:37 +08:00
|
|
|
return -EEXIST;
|
2009-10-07 02:31:10 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
rb_link_node(&new->node, parent, p);
|
|
|
|
rb_insert_color(&new->node, root);
|
2009-10-09 13:22:37 +08:00
|
|
|
return 0;
|
2009-10-07 02:31:10 +08:00
|
|
|
}
|
|
|
|
|
2010-02-17 07:53:32 +08:00
|
|
|
static struct ceph_pg_mapping *__lookup_pg_mapping(struct rb_root *root,
|
|
|
|
struct ceph_pg pgid)
|
|
|
|
{
|
|
|
|
struct rb_node *n = root->rb_node;
|
|
|
|
struct ceph_pg_mapping *pg;
|
|
|
|
int c;
|
|
|
|
|
|
|
|
while (n) {
|
|
|
|
pg = rb_entry(n, struct ceph_pg_mapping, node);
|
|
|
|
c = pgid_cmp(pgid, pg->pgid);
|
|
|
|
if (c < 0)
|
|
|
|
n = n->rb_left;
|
|
|
|
else if (c > 0)
|
|
|
|
n = n->rb_right;
|
|
|
|
else
|
|
|
|
return pg;
|
|
|
|
}
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
2010-02-17 07:55:03 +08:00
|
|
|
/*
|
|
|
|
* rbtree of pg pool info
|
|
|
|
*/
|
|
|
|
static int __insert_pg_pool(struct rb_root *root, struct ceph_pg_pool_info *new)
|
|
|
|
{
|
|
|
|
struct rb_node **p = &root->rb_node;
|
|
|
|
struct rb_node *parent = NULL;
|
|
|
|
struct ceph_pg_pool_info *pi = NULL;
|
|
|
|
|
|
|
|
while (*p) {
|
|
|
|
parent = *p;
|
|
|
|
pi = rb_entry(parent, struct ceph_pg_pool_info, node);
|
|
|
|
if (new->id < pi->id)
|
|
|
|
p = &(*p)->rb_left;
|
|
|
|
else if (new->id > pi->id)
|
|
|
|
p = &(*p)->rb_right;
|
|
|
|
else
|
|
|
|
return -EEXIST;
|
|
|
|
}
|
|
|
|
|
|
|
|
rb_link_node(&new->node, parent, p);
|
|
|
|
rb_insert_color(&new->node, root);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static struct ceph_pg_pool_info *__lookup_pg_pool(struct rb_root *root, int id)
|
|
|
|
{
|
|
|
|
struct ceph_pg_pool_info *pi;
|
|
|
|
struct rb_node *n = root->rb_node;
|
|
|
|
|
|
|
|
while (n) {
|
|
|
|
pi = rb_entry(n, struct ceph_pg_pool_info, node);
|
|
|
|
if (id < pi->id)
|
|
|
|
n = n->rb_left;
|
|
|
|
else if (id > pi->id)
|
|
|
|
n = n->rb_right;
|
|
|
|
else
|
|
|
|
return pi;
|
|
|
|
}
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
2010-05-18 03:31:35 +08:00
|
|
|
int ceph_pg_poolid_by_name(struct ceph_osdmap *map, const char *name)
|
|
|
|
{
|
|
|
|
struct rb_node *rbp;
|
|
|
|
|
|
|
|
for (rbp = rb_first(&map->pg_pools); rbp; rbp = rb_next(rbp)) {
|
|
|
|
struct ceph_pg_pool_info *pi =
|
|
|
|
rb_entry(rbp, struct ceph_pg_pool_info, node);
|
|
|
|
if (pi->name && strcmp(pi->name, name) == 0)
|
|
|
|
return pi->id;
|
|
|
|
}
|
|
|
|
return -ENOENT;
|
|
|
|
}
|
2010-04-07 06:14:15 +08:00
|
|
|
EXPORT_SYMBOL(ceph_pg_poolid_by_name);
|
2010-05-18 03:31:35 +08:00
|
|
|
|
2010-04-10 06:46:42 +08:00
|
|
|
static void __remove_pg_pool(struct rb_root *root, struct ceph_pg_pool_info *pi)
|
|
|
|
{
|
|
|
|
rb_erase(&pi->node, root);
|
|
|
|
kfree(pi->name);
|
|
|
|
kfree(pi);
|
|
|
|
}
|
|
|
|
|
2010-08-03 02:00:55 +08:00
|
|
|
static int __decode_pool(void **p, void *end, struct ceph_pg_pool_info *pi)
|
2010-03-18 01:05:28 +08:00
|
|
|
{
|
2010-08-03 02:00:55 +08:00
|
|
|
unsigned n, m;
|
|
|
|
|
2010-03-18 01:05:28 +08:00
|
|
|
ceph_decode_copy(p, &pi->v, sizeof(pi->v));
|
|
|
|
calc_pg_masks(pi);
|
2010-08-03 02:00:55 +08:00
|
|
|
|
|
|
|
/* num_snaps * snap_info_t */
|
|
|
|
n = le32_to_cpu(pi->v.num_snaps);
|
|
|
|
while (n--) {
|
|
|
|
ceph_decode_need(p, end, sizeof(u64) + 1 + sizeof(u64) +
|
|
|
|
sizeof(struct ceph_timespec), bad);
|
|
|
|
*p += sizeof(u64) + /* key */
|
|
|
|
1 + sizeof(u64) + /* u8, snapid */
|
|
|
|
sizeof(struct ceph_timespec);
|
|
|
|
m = ceph_decode_32(p); /* snap name */
|
|
|
|
*p += m;
|
|
|
|
}
|
|
|
|
|
2010-03-18 01:05:28 +08:00
|
|
|
*p += le32_to_cpu(pi->v.num_removed_snap_intervals) * sizeof(u64) * 2;
|
2010-08-03 02:00:55 +08:00
|
|
|
return 0;
|
|
|
|
|
|
|
|
bad:
|
|
|
|
return -EINVAL;
|
2010-03-18 01:05:28 +08:00
|
|
|
}
|
|
|
|
|
2010-04-10 06:46:42 +08:00
|
|
|
static int __decode_pool_names(void **p, void *end, struct ceph_osdmap *map)
|
|
|
|
{
|
|
|
|
struct ceph_pg_pool_info *pi;
|
|
|
|
u32 num, len, pool;
|
|
|
|
|
|
|
|
ceph_decode_32_safe(p, end, num, bad);
|
|
|
|
dout(" %d pool names\n", num);
|
|
|
|
while (num--) {
|
|
|
|
ceph_decode_32_safe(p, end, pool, bad);
|
|
|
|
ceph_decode_32_safe(p, end, len, bad);
|
|
|
|
dout(" pool %d len %d\n", pool, len);
|
|
|
|
pi = __lookup_pg_pool(&map->pg_pools, pool);
|
|
|
|
if (pi) {
|
|
|
|
kfree(pi->name);
|
|
|
|
pi->name = kmalloc(len + 1, GFP_NOFS);
|
|
|
|
if (pi->name) {
|
|
|
|
memcpy(pi->name, *p, len);
|
|
|
|
pi->name[len] = '\0';
|
|
|
|
dout(" name is %s\n", pi->name);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
*p += len;
|
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
bad:
|
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* osd map
|
|
|
|
*/
|
|
|
|
void ceph_osdmap_destroy(struct ceph_osdmap *map)
|
|
|
|
{
|
|
|
|
dout("osdmap_destroy %p\n", map);
|
|
|
|
if (map->crush)
|
|
|
|
crush_destroy(map->crush);
|
|
|
|
while (!RB_EMPTY_ROOT(&map->pg_temp)) {
|
|
|
|
struct ceph_pg_mapping *pg =
|
|
|
|
rb_entry(rb_first(&map->pg_temp),
|
|
|
|
struct ceph_pg_mapping, node);
|
|
|
|
rb_erase(&pg->node, &map->pg_temp);
|
|
|
|
kfree(pg);
|
|
|
|
}
|
|
|
|
while (!RB_EMPTY_ROOT(&map->pg_pools)) {
|
|
|
|
struct ceph_pg_pool_info *pi =
|
|
|
|
rb_entry(rb_first(&map->pg_pools),
|
|
|
|
struct ceph_pg_pool_info, node);
|
|
|
|
__remove_pg_pool(&map->pg_pools, pi);
|
|
|
|
}
|
|
|
|
kfree(map->osd_state);
|
|
|
|
kfree(map->osd_weight);
|
|
|
|
kfree(map->osd_addr);
|
|
|
|
kfree(map);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* adjust max osd value. reallocate arrays.
|
|
|
|
*/
|
|
|
|
static int osdmap_set_max_osd(struct ceph_osdmap *map, int max)
|
|
|
|
{
|
|
|
|
u8 *state;
|
|
|
|
struct ceph_entity_addr *addr;
|
|
|
|
u32 *weight;
|
|
|
|
|
|
|
|
state = kcalloc(max, sizeof(*state), GFP_NOFS);
|
|
|
|
addr = kcalloc(max, sizeof(*addr), GFP_NOFS);
|
|
|
|
weight = kcalloc(max, sizeof(*weight), GFP_NOFS);
|
|
|
|
if (state == NULL || addr == NULL || weight == NULL) {
|
|
|
|
kfree(state);
|
|
|
|
kfree(addr);
|
|
|
|
kfree(weight);
|
|
|
|
return -ENOMEM;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* copy old? */
|
|
|
|
if (map->osd_state) {
|
|
|
|
memcpy(state, map->osd_state, map->max_osd*sizeof(*state));
|
|
|
|
memcpy(addr, map->osd_addr, map->max_osd*sizeof(*addr));
|
|
|
|
memcpy(weight, map->osd_weight, map->max_osd*sizeof(*weight));
|
|
|
|
kfree(map->osd_state);
|
|
|
|
kfree(map->osd_addr);
|
|
|
|
kfree(map->osd_weight);
|
|
|
|
}
|
|
|
|
|
|
|
|
map->osd_state = state;
|
|
|
|
map->osd_weight = weight;
|
|
|
|
map->osd_addr = addr;
|
|
|
|
map->max_osd = max;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2009-10-07 02:31:10 +08:00
|
|
|
/*
|
|
|
|
* decode a full map.
|
|
|
|
*/
|
|
|
|
struct ceph_osdmap *osdmap_decode(void **p, void *end)
|
|
|
|
{
|
|
|
|
struct ceph_osdmap *map;
|
|
|
|
u16 version;
|
|
|
|
u32 len, max, i;
|
2010-01-26 08:03:02 +08:00
|
|
|
u8 ev;
|
2009-10-07 02:31:10 +08:00
|
|
|
int err = -EINVAL;
|
|
|
|
void *start = *p;
|
2010-02-17 07:55:03 +08:00
|
|
|
struct ceph_pg_pool_info *pi;
|
2009-10-07 02:31:10 +08:00
|
|
|
|
|
|
|
dout("osdmap_decode %p to %p len %d\n", *p, end, (int)(end - *p));
|
|
|
|
|
|
|
|
map = kzalloc(sizeof(*map), GFP_NOFS);
|
|
|
|
if (map == NULL)
|
|
|
|
return ERR_PTR(-ENOMEM);
|
|
|
|
map->pg_temp = RB_ROOT;
|
|
|
|
|
|
|
|
ceph_decode_16_safe(p, end, version, bad);
|
2010-02-05 08:18:10 +08:00
|
|
|
if (version > CEPH_OSDMAP_VERSION) {
|
|
|
|
pr_warning("got unknown v %d > %d of osdmap\n", version,
|
|
|
|
CEPH_OSDMAP_VERSION);
|
|
|
|
goto bad;
|
|
|
|
}
|
2009-10-07 02:31:10 +08:00
|
|
|
|
|
|
|
ceph_decode_need(p, end, 2*sizeof(u64)+6*sizeof(u32), bad);
|
|
|
|
ceph_decode_copy(p, &map->fsid, sizeof(map->fsid));
|
2009-10-15 00:59:09 +08:00
|
|
|
map->epoch = ceph_decode_32(p);
|
2009-10-07 02:31:10 +08:00
|
|
|
ceph_decode_copy(p, &map->created, sizeof(map->created));
|
|
|
|
ceph_decode_copy(p, &map->modified, sizeof(map->modified));
|
|
|
|
|
|
|
|
ceph_decode_32_safe(p, end, max, bad);
|
|
|
|
while (max--) {
|
2010-02-17 07:55:03 +08:00
|
|
|
ceph_decode_need(p, end, 4 + 1 + sizeof(pi->v), bad);
|
2010-04-10 06:46:42 +08:00
|
|
|
pi = kzalloc(sizeof(*pi), GFP_NOFS);
|
2010-02-17 07:55:03 +08:00
|
|
|
if (!pi)
|
2009-10-07 02:31:10 +08:00
|
|
|
goto bad;
|
2010-02-17 07:55:03 +08:00
|
|
|
pi->id = ceph_decode_32(p);
|
2010-01-26 08:03:02 +08:00
|
|
|
ev = ceph_decode_8(p); /* encoding version */
|
2010-02-05 08:18:10 +08:00
|
|
|
if (ev > CEPH_PG_POOL_VERSION) {
|
|
|
|
pr_warning("got unknown v %d > %d of ceph_pg_pool\n",
|
|
|
|
ev, CEPH_PG_POOL_VERSION);
|
2010-07-08 20:49:38 +08:00
|
|
|
kfree(pi);
|
2010-02-05 08:18:10 +08:00
|
|
|
goto bad;
|
|
|
|
}
|
2010-08-03 02:00:55 +08:00
|
|
|
err = __decode_pool(p, end, pi);
|
2010-12-25 06:01:12 +08:00
|
|
|
if (err < 0) {
|
|
|
|
kfree(pi);
|
2010-08-03 02:00:55 +08:00
|
|
|
goto bad;
|
2010-12-25 06:01:12 +08:00
|
|
|
}
|
2010-02-17 07:55:03 +08:00
|
|
|
__insert_pg_pool(&map->pg_pools, pi);
|
2009-10-07 02:31:10 +08:00
|
|
|
}
|
2010-04-10 06:46:42 +08:00
|
|
|
|
|
|
|
if (version >= 5 && __decode_pool_names(p, end, map) < 0)
|
|
|
|
goto bad;
|
|
|
|
|
2010-02-17 07:55:03 +08:00
|
|
|
ceph_decode_32_safe(p, end, map->pool_max, bad);
|
2009-10-07 02:31:10 +08:00
|
|
|
|
|
|
|
ceph_decode_32_safe(p, end, map->flags, bad);
|
|
|
|
|
2009-10-15 00:59:09 +08:00
|
|
|
max = ceph_decode_32(p);
|
2009-10-07 02:31:10 +08:00
|
|
|
|
|
|
|
/* (re)alloc osd arrays */
|
|
|
|
err = osdmap_set_max_osd(map, max);
|
|
|
|
if (err < 0)
|
|
|
|
goto bad;
|
|
|
|
dout("osdmap_decode max_osd = %d\n", map->max_osd);
|
|
|
|
|
|
|
|
/* osds */
|
|
|
|
err = -EINVAL;
|
|
|
|
ceph_decode_need(p, end, 3*sizeof(u32) +
|
|
|
|
map->max_osd*(1 + sizeof(*map->osd_weight) +
|
|
|
|
sizeof(*map->osd_addr)), bad);
|
|
|
|
*p += 4; /* skip length field (should match max) */
|
|
|
|
ceph_decode_copy(p, map->osd_state, map->max_osd);
|
|
|
|
|
|
|
|
*p += 4; /* skip length field (should match max) */
|
|
|
|
for (i = 0; i < map->max_osd; i++)
|
2009-10-15 00:59:09 +08:00
|
|
|
map->osd_weight[i] = ceph_decode_32(p);
|
2009-10-07 02:31:10 +08:00
|
|
|
|
|
|
|
*p += 4; /* skip length field (should match max) */
|
|
|
|
ceph_decode_copy(p, map->osd_addr, map->max_osd*sizeof(*map->osd_addr));
|
2009-11-04 07:17:56 +08:00
|
|
|
for (i = 0; i < map->max_osd; i++)
|
|
|
|
ceph_decode_addr(&map->osd_addr[i]);
|
2009-10-07 02:31:10 +08:00
|
|
|
|
|
|
|
/* pg_temp */
|
|
|
|
ceph_decode_32_safe(p, end, len, bad);
|
|
|
|
for (i = 0; i < len; i++) {
|
|
|
|
int n, j;
|
2009-11-05 03:39:12 +08:00
|
|
|
struct ceph_pg pgid;
|
2009-10-07 02:31:10 +08:00
|
|
|
struct ceph_pg_mapping *pg;
|
|
|
|
|
|
|
|
ceph_decode_need(p, end, sizeof(u32) + sizeof(u64), bad);
|
2009-11-05 03:39:12 +08:00
|
|
|
ceph_decode_copy(p, &pgid, sizeof(pgid));
|
2009-10-15 00:59:09 +08:00
|
|
|
n = ceph_decode_32(p);
|
2009-10-07 02:31:10 +08:00
|
|
|
ceph_decode_need(p, end, n * sizeof(u32), bad);
|
2009-12-22 06:49:37 +08:00
|
|
|
err = -ENOMEM;
|
2009-10-07 02:31:10 +08:00
|
|
|
pg = kmalloc(sizeof(*pg) + n*sizeof(u32), GFP_NOFS);
|
2009-12-22 06:49:37 +08:00
|
|
|
if (!pg)
|
2009-10-07 02:31:10 +08:00
|
|
|
goto bad;
|
|
|
|
pg->pgid = pgid;
|
|
|
|
pg->len = n;
|
|
|
|
for (j = 0; j < n; j++)
|
2009-10-15 00:59:09 +08:00
|
|
|
pg->osds[j] = ceph_decode_32(p);
|
2009-10-07 02:31:10 +08:00
|
|
|
|
2009-10-09 13:22:37 +08:00
|
|
|
err = __insert_pg_mapping(pg, &map->pg_temp);
|
|
|
|
if (err)
|
|
|
|
goto bad;
|
2009-11-05 03:39:12 +08:00
|
|
|
dout(" added pg_temp %llx len %d\n", *(u64 *)&pgid, len);
|
2009-10-07 02:31:10 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
/* crush */
|
|
|
|
ceph_decode_32_safe(p, end, len, bad);
|
|
|
|
dout("osdmap_decode crush len %d from off 0x%x\n", len,
|
|
|
|
(int)(*p - start));
|
|
|
|
ceph_decode_need(p, end, len, bad);
|
|
|
|
map->crush = crush_decode(*p, end);
|
|
|
|
*p += len;
|
|
|
|
if (IS_ERR(map->crush)) {
|
|
|
|
err = PTR_ERR(map->crush);
|
|
|
|
map->crush = NULL;
|
|
|
|
goto bad;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* ignore the rest of the map */
|
|
|
|
*p = end;
|
|
|
|
|
|
|
|
dout("osdmap_decode done %p %p\n", *p, end);
|
|
|
|
return map;
|
|
|
|
|
|
|
|
bad:
|
|
|
|
dout("osdmap_decode fail\n");
|
|
|
|
ceph_osdmap_destroy(map);
|
|
|
|
return ERR_PTR(err);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* decode and apply an incremental map update.
|
|
|
|
*/
|
|
|
|
struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end,
|
|
|
|
struct ceph_osdmap *map,
|
|
|
|
struct ceph_messenger *msgr)
|
|
|
|
{
|
|
|
|
struct crush_map *newcrush = NULL;
|
|
|
|
struct ceph_fsid fsid;
|
|
|
|
u32 epoch = 0;
|
|
|
|
struct ceph_timespec modified;
|
|
|
|
u32 len, pool;
|
2010-02-17 07:55:03 +08:00
|
|
|
__s32 new_pool_max, new_flags, max;
|
2009-10-07 02:31:10 +08:00
|
|
|
void *start = *p;
|
|
|
|
int err = -EINVAL;
|
|
|
|
u16 version;
|
|
|
|
struct rb_node *rbp;
|
|
|
|
|
|
|
|
ceph_decode_16_safe(p, end, version, bad);
|
2010-02-05 08:18:10 +08:00
|
|
|
if (version > CEPH_OSDMAP_INC_VERSION) {
|
|
|
|
pr_warning("got unknown v %d > %d of inc osdmap\n", version,
|
|
|
|
CEPH_OSDMAP_INC_VERSION);
|
|
|
|
goto bad;
|
|
|
|
}
|
2009-10-07 02:31:10 +08:00
|
|
|
|
|
|
|
ceph_decode_need(p, end, sizeof(fsid)+sizeof(modified)+2*sizeof(u32),
|
|
|
|
bad);
|
|
|
|
ceph_decode_copy(p, &fsid, sizeof(fsid));
|
2009-10-15 00:59:09 +08:00
|
|
|
epoch = ceph_decode_32(p);
|
2009-10-07 02:31:10 +08:00
|
|
|
BUG_ON(epoch != map->epoch+1);
|
|
|
|
ceph_decode_copy(p, &modified, sizeof(modified));
|
2010-02-17 07:55:03 +08:00
|
|
|
new_pool_max = ceph_decode_32(p);
|
2009-10-15 00:59:09 +08:00
|
|
|
new_flags = ceph_decode_32(p);
|
2009-10-07 02:31:10 +08:00
|
|
|
|
|
|
|
/* full map? */
|
|
|
|
ceph_decode_32_safe(p, end, len, bad);
|
|
|
|
if (len > 0) {
|
|
|
|
dout("apply_incremental full map len %d, %p to %p\n",
|
|
|
|
len, *p, end);
|
2009-12-22 06:49:37 +08:00
|
|
|
return osdmap_decode(p, min(*p+len, end));
|
2009-10-07 02:31:10 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
/* new crush? */
|
|
|
|
ceph_decode_32_safe(p, end, len, bad);
|
|
|
|
if (len > 0) {
|
|
|
|
dout("apply_incremental new crush map len %d, %p to %p\n",
|
|
|
|
len, *p, end);
|
|
|
|
newcrush = crush_decode(*p, min(*p+len, end));
|
|
|
|
if (IS_ERR(newcrush))
|
2010-05-22 18:01:14 +08:00
|
|
|
return ERR_CAST(newcrush);
|
2010-06-18 01:22:48 +08:00
|
|
|
*p += len;
|
2009-10-07 02:31:10 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
/* new flags? */
|
|
|
|
if (new_flags >= 0)
|
|
|
|
map->flags = new_flags;
|
2010-02-17 07:55:03 +08:00
|
|
|
if (new_pool_max >= 0)
|
|
|
|
map->pool_max = new_pool_max;
|
2009-10-07 02:31:10 +08:00
|
|
|
|
|
|
|
ceph_decode_need(p, end, 5*sizeof(u32), bad);
|
|
|
|
|
|
|
|
/* new max? */
|
2009-10-15 00:59:09 +08:00
|
|
|
max = ceph_decode_32(p);
|
2009-10-07 02:31:10 +08:00
|
|
|
if (max >= 0) {
|
|
|
|
err = osdmap_set_max_osd(map, max);
|
|
|
|
if (err < 0)
|
|
|
|
goto bad;
|
|
|
|
}
|
|
|
|
|
|
|
|
map->epoch++;
|
2011-05-13 06:18:43 +08:00
|
|
|
map->modified = modified;
|
2009-10-07 02:31:10 +08:00
|
|
|
if (newcrush) {
|
|
|
|
if (map->crush)
|
|
|
|
crush_destroy(map->crush);
|
|
|
|
map->crush = newcrush;
|
|
|
|
newcrush = NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* new_pool */
|
|
|
|
ceph_decode_32_safe(p, end, len, bad);
|
|
|
|
while (len--) {
|
2010-01-26 08:03:02 +08:00
|
|
|
__u8 ev;
|
2010-02-17 07:55:03 +08:00
|
|
|
struct ceph_pg_pool_info *pi;
|
2010-01-26 08:03:02 +08:00
|
|
|
|
2009-10-07 02:31:10 +08:00
|
|
|
ceph_decode_32_safe(p, end, pool, bad);
|
2010-02-17 07:55:03 +08:00
|
|
|
ceph_decode_need(p, end, 1 + sizeof(pi->v), bad);
|
2010-01-26 08:03:02 +08:00
|
|
|
ev = ceph_decode_8(p); /* encoding version */
|
2010-02-05 08:18:10 +08:00
|
|
|
if (ev > CEPH_PG_POOL_VERSION) {
|
|
|
|
pr_warning("got unknown v %d > %d of ceph_pg_pool\n",
|
|
|
|
ev, CEPH_PG_POOL_VERSION);
|
|
|
|
goto bad;
|
|
|
|
}
|
2010-02-17 07:55:03 +08:00
|
|
|
pi = __lookup_pg_pool(&map->pg_pools, pool);
|
|
|
|
if (!pi) {
|
2010-04-10 06:46:42 +08:00
|
|
|
pi = kzalloc(sizeof(*pi), GFP_NOFS);
|
2010-02-17 07:55:03 +08:00
|
|
|
if (!pi) {
|
|
|
|
err = -ENOMEM;
|
|
|
|
goto bad;
|
|
|
|
}
|
|
|
|
pi->id = pool;
|
|
|
|
__insert_pg_pool(&map->pg_pools, pi);
|
|
|
|
}
|
2010-08-03 02:00:55 +08:00
|
|
|
err = __decode_pool(p, end, pi);
|
|
|
|
if (err < 0)
|
|
|
|
goto bad;
|
2009-10-07 02:31:10 +08:00
|
|
|
}
|
2010-04-10 06:46:42 +08:00
|
|
|
if (version >= 5 && __decode_pool_names(p, end, map) < 0)
|
|
|
|
goto bad;
|
2009-10-07 02:31:10 +08:00
|
|
|
|
2010-02-17 07:55:03 +08:00
|
|
|
/* old_pool */
|
2009-10-07 02:31:10 +08:00
|
|
|
ceph_decode_32_safe(p, end, len, bad);
|
2010-02-17 07:55:03 +08:00
|
|
|
while (len--) {
|
|
|
|
struct ceph_pg_pool_info *pi;
|
|
|
|
|
|
|
|
ceph_decode_32_safe(p, end, pool, bad);
|
|
|
|
pi = __lookup_pg_pool(&map->pg_pools, pool);
|
2010-04-10 06:46:42 +08:00
|
|
|
if (pi)
|
|
|
|
__remove_pg_pool(&map->pg_pools, pi);
|
2010-02-17 07:55:03 +08:00
|
|
|
}
|
2009-10-07 02:31:10 +08:00
|
|
|
|
|
|
|
/* new_up */
|
|
|
|
err = -EINVAL;
|
|
|
|
ceph_decode_32_safe(p, end, len, bad);
|
|
|
|
while (len--) {
|
|
|
|
u32 osd;
|
|
|
|
struct ceph_entity_addr addr;
|
|
|
|
ceph_decode_32_safe(p, end, osd, bad);
|
|
|
|
ceph_decode_copy_safe(p, end, &addr, sizeof(addr), bad);
|
2009-11-04 07:17:56 +08:00
|
|
|
ceph_decode_addr(&addr);
|
2009-10-07 02:31:10 +08:00
|
|
|
pr_info("osd%d up\n", osd);
|
|
|
|
BUG_ON(osd >= map->max_osd);
|
|
|
|
map->osd_state[osd] |= CEPH_OSD_UP;
|
|
|
|
map->osd_addr[osd] = addr;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* new_down */
|
|
|
|
ceph_decode_32_safe(p, end, len, bad);
|
|
|
|
while (len--) {
|
|
|
|
u32 osd;
|
|
|
|
ceph_decode_32_safe(p, end, osd, bad);
|
|
|
|
(*p)++; /* clean flag */
|
2009-11-07 05:57:49 +08:00
|
|
|
pr_info("osd%d down\n", osd);
|
2009-10-07 02:31:10 +08:00
|
|
|
if (osd < map->max_osd)
|
|
|
|
map->osd_state[osd] &= ~CEPH_OSD_UP;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* new_weight */
|
|
|
|
ceph_decode_32_safe(p, end, len, bad);
|
|
|
|
while (len--) {
|
|
|
|
u32 osd, off;
|
|
|
|
ceph_decode_need(p, end, sizeof(u32)*2, bad);
|
2009-10-15 00:59:09 +08:00
|
|
|
osd = ceph_decode_32(p);
|
|
|
|
off = ceph_decode_32(p);
|
2009-10-07 02:31:10 +08:00
|
|
|
pr_info("osd%d weight 0x%x %s\n", osd, off,
|
|
|
|
off == CEPH_OSD_IN ? "(in)" :
|
|
|
|
(off == CEPH_OSD_OUT ? "(out)" : ""));
|
|
|
|
if (osd < map->max_osd)
|
|
|
|
map->osd_weight[osd] = off;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* new_pg_temp */
|
|
|
|
rbp = rb_first(&map->pg_temp);
|
|
|
|
ceph_decode_32_safe(p, end, len, bad);
|
|
|
|
while (len--) {
|
|
|
|
struct ceph_pg_mapping *pg;
|
|
|
|
int j;
|
2009-11-05 03:39:12 +08:00
|
|
|
struct ceph_pg pgid;
|
2009-10-07 02:31:10 +08:00
|
|
|
u32 pglen;
|
|
|
|
ceph_decode_need(p, end, sizeof(u64) + sizeof(u32), bad);
|
2009-11-05 03:39:12 +08:00
|
|
|
ceph_decode_copy(p, &pgid, sizeof(pgid));
|
2009-10-15 00:59:09 +08:00
|
|
|
pglen = ceph_decode_32(p);
|
2009-10-07 02:31:10 +08:00
|
|
|
|
|
|
|
/* remove any? */
|
2009-11-05 03:39:12 +08:00
|
|
|
while (rbp && pgid_cmp(rb_entry(rbp, struct ceph_pg_mapping,
|
|
|
|
node)->pgid, pgid) <= 0) {
|
2010-07-21 07:19:56 +08:00
|
|
|
struct ceph_pg_mapping *cur =
|
|
|
|
rb_entry(rbp, struct ceph_pg_mapping, node);
|
2010-08-04 01:25:11 +08:00
|
|
|
|
2009-10-07 02:31:10 +08:00
|
|
|
rbp = rb_next(rbp);
|
2010-07-21 07:19:56 +08:00
|
|
|
dout(" removed pg_temp %llx\n", *(u64 *)&cur->pgid);
|
|
|
|
rb_erase(&cur->node, &map->pg_temp);
|
|
|
|
kfree(cur);
|
2009-10-07 02:31:10 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
if (pglen) {
|
|
|
|
/* insert */
|
|
|
|
ceph_decode_need(p, end, pglen*sizeof(u32), bad);
|
|
|
|
pg = kmalloc(sizeof(*pg) + sizeof(u32)*pglen, GFP_NOFS);
|
|
|
|
if (!pg) {
|
|
|
|
err = -ENOMEM;
|
|
|
|
goto bad;
|
|
|
|
}
|
|
|
|
pg->pgid = pgid;
|
|
|
|
pg->len = pglen;
|
2009-12-22 08:02:37 +08:00
|
|
|
for (j = 0; j < pglen; j++)
|
2009-10-15 00:59:09 +08:00
|
|
|
pg->osds[j] = ceph_decode_32(p);
|
2009-10-09 13:22:37 +08:00
|
|
|
err = __insert_pg_mapping(pg, &map->pg_temp);
|
2010-07-21 07:19:56 +08:00
|
|
|
if (err) {
|
|
|
|
kfree(pg);
|
2009-10-09 13:22:37 +08:00
|
|
|
goto bad;
|
2010-07-21 07:19:56 +08:00
|
|
|
}
|
2009-11-05 03:39:12 +08:00
|
|
|
dout(" added pg_temp %llx len %d\n", *(u64 *)&pgid,
|
|
|
|
pglen);
|
2009-10-07 02:31:10 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
while (rbp) {
|
2010-07-21 07:19:56 +08:00
|
|
|
struct ceph_pg_mapping *cur =
|
|
|
|
rb_entry(rbp, struct ceph_pg_mapping, node);
|
|
|
|
|
2009-10-07 02:31:10 +08:00
|
|
|
rbp = rb_next(rbp);
|
2010-07-21 07:19:56 +08:00
|
|
|
dout(" removed pg_temp %llx\n", *(u64 *)&cur->pgid);
|
|
|
|
rb_erase(&cur->node, &map->pg_temp);
|
|
|
|
kfree(cur);
|
2009-10-07 02:31:10 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
/* ignore the rest */
|
|
|
|
*p = end;
|
|
|
|
return map;
|
|
|
|
|
|
|
|
bad:
|
|
|
|
pr_err("corrupt inc osdmap epoch %d off %d (%p of %p-%p)\n",
|
|
|
|
epoch, (int)(*p - start), *p, start, end);
|
2009-12-15 07:13:47 +08:00
|
|
|
print_hex_dump(KERN_DEBUG, "osdmap: ",
|
|
|
|
DUMP_PREFIX_OFFSET, 16, 1,
|
|
|
|
start, end - start, true);
|
2009-10-07 02:31:10 +08:00
|
|
|
if (newcrush)
|
|
|
|
crush_destroy(newcrush);
|
|
|
|
return ERR_PTR(err);
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
* calculate file layout from given offset, length.
|
|
|
|
* fill in correct oid, logical length, and object extent
|
|
|
|
* offset, length.
|
|
|
|
*
|
|
|
|
* for now, we write only a single su, until we can
|
|
|
|
* pass a stride back to the caller.
|
|
|
|
*/
|
|
|
|
void ceph_calc_file_object_mapping(struct ceph_file_layout *layout,
|
|
|
|
u64 off, u64 *plen,
|
2009-10-29 06:15:05 +08:00
|
|
|
u64 *ono,
|
2009-10-07 02:31:10 +08:00
|
|
|
u64 *oxoff, u64 *oxlen)
|
|
|
|
{
|
|
|
|
u32 osize = le32_to_cpu(layout->fl_object_size);
|
|
|
|
u32 su = le32_to_cpu(layout->fl_stripe_unit);
|
|
|
|
u32 sc = le32_to_cpu(layout->fl_stripe_count);
|
|
|
|
u32 bl, stripeno, stripepos, objsetno;
|
|
|
|
u32 su_per_object;
|
2009-10-31 03:57:30 +08:00
|
|
|
u64 t, su_offset;
|
2009-10-07 02:31:10 +08:00
|
|
|
|
|
|
|
dout("mapping %llu~%llu osize %u fl_su %u\n", off, *plen,
|
|
|
|
osize, su);
|
2009-10-29 05:04:48 +08:00
|
|
|
su_per_object = osize / su;
|
2009-10-07 02:31:10 +08:00
|
|
|
dout("osize %u / su %u = su_per_object %u\n", osize, su,
|
|
|
|
su_per_object);
|
|
|
|
|
|
|
|
BUG_ON((su & ~PAGE_MASK) != 0);
|
|
|
|
/* bl = *off / su; */
|
|
|
|
t = off;
|
|
|
|
do_div(t, su);
|
|
|
|
bl = t;
|
|
|
|
dout("off %llu / su %u = bl %u\n", off, su, bl);
|
|
|
|
|
|
|
|
stripeno = bl / sc;
|
|
|
|
stripepos = bl % sc;
|
|
|
|
objsetno = stripeno / su_per_object;
|
|
|
|
|
2009-10-29 06:15:05 +08:00
|
|
|
*ono = objsetno * sc + stripepos;
|
|
|
|
dout("objset %u * sc %u = ono %u\n", objsetno, sc, (unsigned)*ono);
|
|
|
|
|
|
|
|
/* *oxoff = *off % layout->fl_stripe_unit; # offset in su */
|
2009-10-07 02:31:10 +08:00
|
|
|
t = off;
|
2009-10-31 03:57:30 +08:00
|
|
|
su_offset = do_div(t, su);
|
|
|
|
*oxoff = su_offset + (stripeno % su_per_object) * su;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Calculate the length of the extent being written to the selected
|
|
|
|
* object. This is the minimum of the full length requested (plen) or
|
|
|
|
* the remainder of the current stripe being written to.
|
|
|
|
*/
|
|
|
|
*oxlen = min_t(u64, *plen, su - su_offset);
|
2009-10-07 02:31:10 +08:00
|
|
|
*plen = *oxlen;
|
|
|
|
|
|
|
|
dout(" obj extent %llu~%llu\n", *oxoff, *oxlen);
|
|
|
|
}
|
2010-04-07 06:14:15 +08:00
|
|
|
EXPORT_SYMBOL(ceph_calc_file_object_mapping);
|
2009-10-07 02:31:10 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* calculate an object layout (i.e. pgid) from an oid,
|
|
|
|
* file_layout, and osdmap
|
|
|
|
*/
|
|
|
|
int ceph_calc_object_layout(struct ceph_object_layout *ol,
|
|
|
|
const char *oid,
|
|
|
|
struct ceph_file_layout *fl,
|
|
|
|
struct ceph_osdmap *osdmap)
|
|
|
|
{
|
|
|
|
unsigned num, num_mask;
|
2009-11-05 03:39:12 +08:00
|
|
|
struct ceph_pg pgid;
|
2009-10-07 02:31:10 +08:00
|
|
|
s32 preferred = (s32)le32_to_cpu(fl->fl_pg_preferred);
|
|
|
|
int poolid = le32_to_cpu(fl->fl_pg_pool);
|
|
|
|
struct ceph_pg_pool_info *pool;
|
2009-11-05 03:39:12 +08:00
|
|
|
unsigned ps;
|
2009-10-07 02:31:10 +08:00
|
|
|
|
2009-12-22 06:49:37 +08:00
|
|
|
BUG_ON(!osdmap);
|
2009-10-07 02:31:10 +08:00
|
|
|
|
2010-02-17 07:55:03 +08:00
|
|
|
pool = __lookup_pg_pool(&osdmap->pg_pools, poolid);
|
|
|
|
if (!pool)
|
|
|
|
return -EIO;
|
2009-11-07 13:55:25 +08:00
|
|
|
ps = ceph_str_hash(pool->v.object_hash, oid, strlen(oid));
|
2009-10-07 02:31:10 +08:00
|
|
|
if (preferred >= 0) {
|
2009-11-05 03:39:12 +08:00
|
|
|
ps += preferred;
|
2009-10-07 02:31:10 +08:00
|
|
|
num = le32_to_cpu(pool->v.lpg_num);
|
|
|
|
num_mask = pool->lpg_num_mask;
|
|
|
|
} else {
|
|
|
|
num = le32_to_cpu(pool->v.pg_num);
|
|
|
|
num_mask = pool->pg_num_mask;
|
|
|
|
}
|
|
|
|
|
2009-11-05 03:39:12 +08:00
|
|
|
pgid.ps = cpu_to_le16(ps);
|
|
|
|
pgid.preferred = cpu_to_le16(preferred);
|
|
|
|
pgid.pool = fl->fl_pg_pool;
|
2009-10-07 02:31:10 +08:00
|
|
|
if (preferred >= 0)
|
2009-11-05 03:39:12 +08:00
|
|
|
dout("calc_object_layout '%s' pgid %d.%xp%d\n", oid, poolid, ps,
|
|
|
|
(int)preferred);
|
2009-10-07 02:31:10 +08:00
|
|
|
else
|
2009-11-05 03:39:12 +08:00
|
|
|
dout("calc_object_layout '%s' pgid %d.%x\n", oid, poolid, ps);
|
2009-10-07 02:31:10 +08:00
|
|
|
|
2009-11-05 03:39:12 +08:00
|
|
|
ol->ol_pgid = pgid;
|
2009-10-07 02:31:10 +08:00
|
|
|
ol->ol_stripe_unit = fl->fl_object_stripe_unit;
|
|
|
|
return 0;
|
|
|
|
}
|
2010-04-07 06:14:15 +08:00
|
|
|
EXPORT_SYMBOL(ceph_calc_object_layout);
|
2009-10-07 02:31:10 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Calculate raw osd vector for the given pgid. Return pointer to osd
|
|
|
|
* array, or NULL on failure.
|
|
|
|
*/
|
2009-11-05 03:39:12 +08:00
|
|
|
static int *calc_pg_raw(struct ceph_osdmap *osdmap, struct ceph_pg pgid,
|
2009-10-07 02:31:10 +08:00
|
|
|
int *osds, int *num)
|
|
|
|
{
|
|
|
|
struct ceph_pg_mapping *pg;
|
|
|
|
struct ceph_pg_pool_info *pool;
|
|
|
|
int ruleno;
|
2009-11-05 03:39:12 +08:00
|
|
|
unsigned poolid, ps, pps;
|
|
|
|
int preferred;
|
2009-10-07 02:31:10 +08:00
|
|
|
|
|
|
|
/* pg_temp? */
|
2010-02-17 07:53:32 +08:00
|
|
|
pg = __lookup_pg_mapping(&osdmap->pg_temp, pgid);
|
|
|
|
if (pg) {
|
|
|
|
*num = pg->len;
|
|
|
|
return pg->osds;
|
2009-10-07 02:31:10 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
/* crush */
|
2009-11-05 03:39:12 +08:00
|
|
|
poolid = le32_to_cpu(pgid.pool);
|
|
|
|
ps = le16_to_cpu(pgid.ps);
|
|
|
|
preferred = (s16)le16_to_cpu(pgid.preferred);
|
|
|
|
|
2009-12-10 04:34:01 +08:00
|
|
|
/* don't forcefeed bad device ids to crush */
|
|
|
|
if (preferred >= osdmap->max_osd ||
|
|
|
|
preferred >= osdmap->crush->max_devices)
|
|
|
|
preferred = -1;
|
|
|
|
|
2010-02-17 07:55:03 +08:00
|
|
|
pool = __lookup_pg_pool(&osdmap->pg_pools, poolid);
|
|
|
|
if (!pool)
|
2009-10-07 02:31:10 +08:00
|
|
|
return NULL;
|
|
|
|
ruleno = crush_find_rule(osdmap->crush, pool->v.crush_ruleset,
|
|
|
|
pool->v.type, pool->v.size);
|
|
|
|
if (ruleno < 0) {
|
2010-07-10 02:00:08 +08:00
|
|
|
pr_err("no crush rule pool %d ruleset %d type %d size %d\n",
|
|
|
|
poolid, pool->v.crush_ruleset, pool->v.type,
|
|
|
|
pool->v.size);
|
2009-10-07 02:31:10 +08:00
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
2009-11-05 03:39:12 +08:00
|
|
|
if (preferred >= 0)
|
|
|
|
pps = ceph_stable_mod(ps,
|
2009-10-07 02:31:10 +08:00
|
|
|
le32_to_cpu(pool->v.lpgp_num),
|
|
|
|
pool->lpgp_num_mask);
|
|
|
|
else
|
2009-11-05 03:39:12 +08:00
|
|
|
pps = ceph_stable_mod(ps,
|
2009-10-07 02:31:10 +08:00
|
|
|
le32_to_cpu(pool->v.pgp_num),
|
|
|
|
pool->pgp_num_mask);
|
2009-11-05 03:39:12 +08:00
|
|
|
pps += poolid;
|
2009-10-07 02:31:10 +08:00
|
|
|
*num = crush_do_rule(osdmap->crush, ruleno, pps, osds,
|
|
|
|
min_t(int, pool->v.size, *num),
|
2009-11-05 03:39:12 +08:00
|
|
|
preferred, osdmap->osd_weight);
|
2009-10-07 02:31:10 +08:00
|
|
|
return osds;
|
|
|
|
}
|
|
|
|
|
2010-05-11 01:24:48 +08:00
|
|
|
/*
|
|
|
|
* Return acting set for given pgid.
|
|
|
|
*/
|
|
|
|
int ceph_calc_pg_acting(struct ceph_osdmap *osdmap, struct ceph_pg pgid,
|
|
|
|
int *acting)
|
|
|
|
{
|
|
|
|
int rawosds[CEPH_PG_MAX_SIZE], *osds;
|
|
|
|
int i, o, num = CEPH_PG_MAX_SIZE;
|
|
|
|
|
|
|
|
osds = calc_pg_raw(osdmap, pgid, rawosds, &num);
|
|
|
|
if (!osds)
|
|
|
|
return -1;
|
|
|
|
|
|
|
|
/* primary is first up osd */
|
|
|
|
o = 0;
|
|
|
|
for (i = 0; i < num; i++)
|
|
|
|
if (ceph_osd_is_up(osdmap, osds[i]))
|
|
|
|
acting[o++] = osds[i];
|
|
|
|
return o;
|
|
|
|
}
|
|
|
|
|
2009-10-07 02:31:10 +08:00
|
|
|
/*
|
|
|
|
* Return primary osd for given pgid, or -1 if none.
|
|
|
|
*/
|
2009-11-05 03:39:12 +08:00
|
|
|
int ceph_calc_pg_primary(struct ceph_osdmap *osdmap, struct ceph_pg pgid)
|
2009-10-07 02:31:10 +08:00
|
|
|
{
|
2010-05-11 01:24:48 +08:00
|
|
|
int rawosds[CEPH_PG_MAX_SIZE], *osds;
|
|
|
|
int i, num = CEPH_PG_MAX_SIZE;
|
2009-10-07 02:31:10 +08:00
|
|
|
|
|
|
|
osds = calc_pg_raw(osdmap, pgid, rawosds, &num);
|
|
|
|
if (!osds)
|
|
|
|
return -1;
|
|
|
|
|
|
|
|
/* primary is first up osd */
|
|
|
|
for (i = 0; i < num; i++)
|
2010-05-11 01:24:48 +08:00
|
|
|
if (ceph_osd_is_up(osdmap, osds[i]))
|
2009-10-07 02:31:10 +08:00
|
|
|
return osds[i];
|
|
|
|
return -1;
|
|
|
|
}
|
2010-04-07 06:14:15 +08:00
|
|
|
EXPORT_SYMBOL(ceph_calc_pg_primary);
|