| Age | Commit message (Collapse) | Author |
|---|
|
To be in line with all the other osdmap decode helpers.
Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
Reviewed-by: Alex Elder <elder@linaro.org>
|
|
Sum up sizeof(...) results instead of (incorrectly) hard-coding the
number of bytes, expressed in ints and longs.
Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
Reviewed-by: Alex Elder <elder@linaro.org>
|
|
Only version 6 of osdmap encoding is supported, anything other than
version 6 results in an error and halts the decoding process. Checking
if version is >= 5 is therefore bogus.
Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
Reviewed-by: Alex Elder <elder@linaro.org>
|
|
The existing error handling scheme requires resetting err to -EINVAL
prior to calling any ceph_decode_* macro. This is ugly and fragile,
and there already are a few places where we would return 0 on error,
due to a missing reset. Follow osdmap_decode() and fix this by adding
a special e_inval label to be used by all ceph_decode_* macros.
Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
Reviewed-by: Alex Elder <elder@linaro.org>
|
|
The size of the memory area feeded to crush_decode() should be limited
not only by osdmap end, but also by the crush map length. Also, drop
unnecessary dout() (dout() in crush_decode() conveys the same info) and
step past crush map only if it is decoded successfully.
Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
Reviewed-by: Alex Elder <elder@linaro.org>
|
|
Check length of osd_state, osd_weight and osd_addr arrays. They
should all have exactly max_osd elements after the call to
osdmap_set_max_osd().
Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
Reviewed-by: Alex Elder <elder@linaro.org>
|
|
max_osd value is not covered by any ceph_decode_need(). Use a safe
version of ceph_decode_* macro to decode it.
Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
Reviewed-by: Alex Elder <elder@linaro.org>
|
|
The existing error handling scheme requires resetting err to -EINVAL
prior to calling any ceph_decode_* macro. This is ugly and fragile,
and there already are a few places where we would return 0 on error,
due to a missing reset. Fix this by adding a special e_inval label to
be used by all ceph_decode_* macros.
Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
Reviewed-by: Alex Elder <elder@linaro.org>
|
|
Split osdmap allocation and initialization into a separate function,
ceph_osdmap_decode().
Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
Reviewed-by: Alex Elder <elder@linaro.org>
|
|
Dump osdmap in hex on both full and incremental decode errors, to make
it easier to match the contents with error offset. dout() map epoch
and max_osd value on success.
Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
Reviewed-by: Alex Elder <elder@linaro.org>
|
|
Dump pg_temp mappings to /sys/kernel/debug/ceph/<client>/osdmap,
one 'pg_temp <pgid> [<osd>, ..., <osd>]' per line, e.g:
pg_temp 2.6 [2,3,4]
Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
Reviewed-by: Alex Elder <elder@linaro.org>
|
|
To save screen space in anticipation of more fields (e.g. primary
affinity).
Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
Reviewed-by: Alex Elder <elder@linaro.org>
|
|
To make it more readable and save screen space.
Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
Reviewed-by: Alex Elder <elder@linaro.org>
|
|
Add TUNABLES3 feature (chooseleaf_vary_r tunable) to a set of features
supported by default.
Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
|
|
This lets you adjust the vary_r tunable on a per-rule basis.
Reflects ceph.git commit f944ccc20aee60a7d8da7e405ec75ad1cd449fac.
Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
|
|
The current crush_choose_firstn code will re-use the same 'r' value for
the recursive call. That means that if we are hitting a collision or
rejection for some reason (say, an OSD that is marked out) and need to
retry, we will keep making the same (bad) choice in that recursive
selection.
Introduce a tunable that fixes that behavior by incorporating the parent
'r' value into the recursive starting point, so that a different path
will be taken in subsequent placement attempts.
Note that this was done from the get-go for the new crush_choose_indep
algorithm.
This was exposed by a user who was seeing PGs stuck in active+remapped
after reweight-by-utilization because the up set mapped to a single OSD.
Reflects ceph.git commit a8e6c9fbf88bad056dd05d3eb790e98a5e43451a.
Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
|
|
These two fields are misnomers; they are *retry* counts.
Reflects ceph.git commit f17caba8ae0cad7b6f8f35e53e5f73b444696835.
Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
|
|
Back in 27f4d1f6bc32c2ed7b2c5080cbd58b14df622607 we refactored the CRUSH
code to allow adjustment of the retry counts on a per-pool basis. That
commit had an off-by-one bug: the previous "tries" counter was a *retry*
count, not a *try* count, but the new code was passing in 1 meaning
there should be no retries.
Fix the ftotal vs tries comparison to use < instead of <= to fix the
problem. Note that the original code used <= here, which means the
global "choose_total_tries" tunable is actually counting retries.
Compensate for that by adding 1 in crush_do_rule when we pull the tunable
into the local variable.
This was noticed looking at output from a user provided osdmap.
Unfortunately the map doesn't illustrate the change in mapping behavior
and I haven't managed to construct one yet that does. Inspection of the
crush debug output now aligns with prior versions, though.
Reflects ceph.git commit 795704fd615f0b008dcc81aa088a859b2d075138.
Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
|
|
This avoids 'cp -a' modifying layout of new files/directories.
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
|
|
If buffer size is zero, return the size of layout vxattr. If buffer
size is not zero, check if it is large enough for layout vxattr.
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
|
|
send_mds_reconnect() may call discard_cap_releases() after all
release messages have been dropped by cleanup_cap_releases()
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
Reviewed-by: Sage Weil <sage@inktank.com>
|
|
When there is no more data, ceph_msg_data_{pages,pagelist}_advance()
should not move on to the next page.
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
|
|
Remove unsupported symlink operations.
Signed-off-by: Fabian Frederick <fabf@skynet.be>
Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
|
|
When adjusting caps client wants, MDS does not record caps that are
not allowed. For non-auth MDS, it does not record WR caps. So when
a MDS reply changes a non-auth cap to auth cap, client needs to set
cap's mds_wanted according to the reply.
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
|
|
flock and posix lock should use fl->fl_file instead of process ID
as owner identifier. (posix lock uses fl->fl_owner. fl->fl_owner
is usually equal to fl->fl_file, but it also can be a customized
value). The process ID of who holds the lock is just for F_GETLK
fcntl(2).
The fix is rename the 'pid' fields of struct ceph_mds_request_args
and struct ceph_filelock to 'owner', rename 'pid_namespace' fields
to 'pid'. Assign fl->fl_file to the 'owner' field of lock messages.
We also set the most significant bit of the 'owner' field. MDS can
use that bit to distinguish between old and new clients.
The MDS counterpart of this patch modifies the flock code to not
take the 'pid_namespace' into consideration when checking conflict
locks.
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
Reviewed-by: Sage Weil <sage@inktank.com>
|
|
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
|
|
VFS does not directly pass flock's operation code to filesystem's
flock callback. It translates the operation code to the form how
posix lock's parameters are presented.
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
|
|
handle following sequence of events:
- client releases a inode with i_max_size > 0. The release message
is queued. (is not sent to the auth MDS)
- a 'lookup' request reply from non-auth MDS returns the same inode.
- client opens the inode in write mode. The version of inode trace
in 'open' request reply is equal to the cached inode's version.
- client requests new max size. The MDS ignores the request because
it does not affect client's write range
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
Reviewed-by: Sage Weil <sage@inktank.com>
|
|
Only auth MDS can issue write caps to clients, so don't consider
write caps registered with non-auth MDS as valid.
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
|
|
Signed-off-by: Richard Kuo <rkuo@codeaurora.org>
|
|
The SP/r29 macro wasn't used anywhere else and was causing conflicts
with another module, so just remove it.
Signed-off-by: Richard Kuo <rkuo@codeaurora.org>
|
|
Signed-off-by: Richard Kuo <rkuo@codeaurora.org>
|
|
Signed-off-by: Richard Kuo <rkuo@codeaurora.org>
|
|
Normal writes in our our architecture don't invalidate lock
reservations.
Signed-off-by: Richard Kuo <rkuo@codeaurora.org>
|
|
Signed-off-by: Richard Kuo <rkuo@codeaurora.org>
|
|
swapper_pg_dir is an array of pgd_t, not pgd_t*. This has no actual
effect since sizeof(pgd_t) == sizeof(pgd_t*), but unconfuses tools that
check types.
Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
Signed-off-by: Richard Kuo <rkuo@codeaurora.org>
|
|
Commit 9a46ad6d6df3b54 "smp: make smp_call_function_many() use logic
similar to smp_call_function_single()" has unified the way to handle
single and multiple cross-CPU function calls. Now only one intterupt
is needed for architecture specific code to support generic SMP function
call interfaces, so kill the redundant single function call interrupt.
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Shaohua Li <shli@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Jiri Kosina <trivial@kernel.org>
Cc: Richard Kuo <rkuo@codeaurora.org>
Cc: linux-hexagon@vger.kernel.org
Signed-off-by: Jiang Liu <liuj97@gmail.com>
Signed-off-by: Richard Kuo <rkuo@codeaurora.org>
|
|
Need dumy mmiowb(), or can not pass compiling, the related error with
allmodconfig:
CC [M] drivers/mmc/host/sdhci.o
drivers/mmc/host/sdhci.c: In function 'sdhci_request':
drivers/mmc/host/sdhci.c:1409:2: error: implicit declaration of function 'mmiowb' [-Werror=implicit-function-declaration]
Signed-off-by: Chen Gang <gang.chen.5i5j@gmail.com>
Signed-off-by: Richard Kuo <rkuo@codeaurora.org>
|
|
modules need
Need export all related functions and symbols for various modules with
allmodconfig. The related errors:
MODPOST 2879 modules
ERROR: "__vmyield" [sound/sound_firmware.ko] undefined!
ERROR: "__phys_offset" [sound/drivers/snd-dummy.ko] undefined!
ERROR: "ioremap_nocache" [drivers/char/ipmi/ipmi_si.ko] undefined!
ERROR: "__iounmap" [drivers/char/ipmi/ipmi_si.ko] undefined!
...
For including files, need "linux/*" first, then "asm/*". All related
included files and symbols need be sorted by alphabetical order.
Signed-off-by: Chen Gang <gang.chen.5i5j@gmail.com>
Signed-off-by: Richard Kuo <rkuo@codeaurora.org>
|
|
pm_power_off and export it
'pm_power_off' is a function pointer, not a function, so need change
its type, and also need export it, or can not pass compiling with
allmodconfig. The related error:
MODPOST 2879 modules
ERROR: "pm_power_off" [drivers/char/ipmi/ipmi_poweroff.ko] undefined!
Signed-off-by: Chen Gang <gang.chen.5i5j@gmail.com>
Signed-off-by: Richard Kuo <rkuo@codeaurora.org>
|
|
Need include generic "vga.h", or can not pass compiling with
allmodconfig, the related error:
CC [M] drivers/gpu/drm/drm_irq.o
In file included from include/linux/vgaarb.h:34:0,
from drivers/gpu/drm/drm_irq.c:42:
include/video/vga.h:22:21: fatal error: asm/vga.h: No such file or directory
Also move "preempt.h" upper to match sort order.
Signed-off-by: Chen Gang <gang.chen.5i5j@gmail.com>
Signed-off-by: Richard Kuo <rkuo@codeaurora.org>
|
|
Add "serial.h" in Kbuild, or can not pass compiling with allmodconfig,
the related error:
CC [M] drivers/staging/speakup/speakup_acntpc.o
In file included from drivers/staging/speakup/speakup_acntpc.c:33:0:
drivers/staging/speakup/serialio.h:7:24: fatal error: asm/serial.h: No such file or directory
Signed-off-by: Chen Gang <gang.chen.5i5j@gmail.com>
Signed-off-by: Richard Kuo <rkuo@codeaurora.org>
|
|
Define dummy '__init' instead of include "linux/init.h" if !__KERNEL__,
or can not pass checking. The related error (with allmodconfig under
hexagon):
CHECK include/asm (34 files)
usr/include/asm/setup.h:22: included file 'linux/init.h' is not exported
Signed-off-by: Chen Gang <gang.chen.5i5j@gmail.com>
Signed-off-by: Richard Kuo <rkuo@codeaurora.org>
|
|
"hexagon_vm.h"
Append "hvmc_" or "hvmi_" to all related enum members (which are too
common to make conflict with another sub-systems). The related error
with allmodconfig:
CC [M] drivers/md/raid1.o
drivers/md/raid1.c:1440:13: error: 'status' redeclared as different kind of symbol
arch/hexagon/include/asm/hexagon_vm.h:76:2: note: previous definition of 'status' was here
Also use 'affinity' instead of 'locdis' for __vmintop_affinity().
Signed-off-by: Chen Gang <gang.chen.5i5j@gmail.com>
Signed-off-by: Richard Kuo <rkuo@codeaurora.org>
|
|
"linux/dma-mapping.h" from "asm/dma-mapping.h"
When HAS_DMA, and also need use generic implementation, HAVE_DMA_ATTR
must be enabled, or can not pass compiling with allmodconfig, the
related error:
CC [M] drivers/ata/libata-core.o
drivers/ata/libata-core.c: In function 'ata_sg_clean':
drivers/ata/libata-core.c:4598:3: error: implicit declaration of function 'dma_unmap_sg' [-Werror=implicit-function-declaration]
drivers/ata/libata-core.c: In function 'ata_sg_setup':
drivers/ata/libata-core.c:4708:2: error: implicit declaration of function 'dma_map_sg' [-Werror=implicit-function-declaration]
"linux/dma-mapping.h" will include "asm/dma-mapping.h", so need remove
"linux/dma-mapping.h" from "asm/dma-mapping.h",
Signed-off-by: Chen Gang <gang.chen.5i5j@gmail.com>
Signed-off-by: Richard Kuo <rkuo@codeaurora.org>
|
|
Need add __delay() implementation, or can not pass allmodconfig in
next-20131118 tree.
The related error:
CC kernel/locking/spinlock_debug.o
kernel/locking/spinlock_debug.c: In function '__spin_lock_debug':
kernel/locking/spinlock_debug.c:114:3: error: implicit declaration of function '__delay' [-Werror=implicit-function-declaration]
Signed-off-by: Chen Gang <gang.chen.5i5j@gmail.com>
Signed-off-by: Richard Kuo <rkuo@codeaurora.org>
|
|
Need extend maximized number for "cs0/1", the related warning (with
allmodconfig for v4):
arch/hexagon/kernel/kgdb.c:79: warning: excess elements in array initializer
arch/hexagon/kernel/kgdb.c:79: warning: (near initialization for 'dbg_reg_def')
arch/hexagon/kernel/kgdb.c:80: warning: excess elements in array initializer
arch/hexagon/kernel/kgdb.c:80: warning: (near initialization for 'dbg_reg_def')
Signed-off-by: Chen Gang <gang.chen@asianux.com>
Signed-off-by: Richard Kuo <rkuo@codeaurora.org>
|
|
Need include related headers for pass compiling, the related error
(with allmodconfig for v4):
CC arch/hexagon/kernel/kgdb.o
arch/hexagon/kernel/kgdb.c:30: error: invalid use of undefined type 'struct pt_regs'
arch/hexagon/kernel/kgdb.c:31: error: invalid use of undefined type 'struct pt_regs'
...
arch/hexagon/kernel/kgdb.c:220: error: implicit declaration of function 'local_irq_save'
arch/hexagon/kernel/kgdb.c:222: error: implicit declaration of function 'local_irq_restore'
...
Signed-off-by: Chen Gang <gang.chen@asianux.com>
Signed-off-by: Richard Kuo <rkuo@codeaurora.org>
|
|
time_init_deferred() in "time.c"
Remove them, since they are useless. The related warnings (with
allmodconfig for v4):
CC arch/hexagon/kernel/time.o
arch/hexagon/kernel/time.c: In function 'time_init_deferred':
arch/hexagon/kernel/time.c:196: warning: unused variable 'err'
arch/hexagon/kernel/time.c:195: warning: unused variable 'r'
arch/hexagon/kernel/time.c:194: warning: unused variable 'dn'
Signed-off-by: Chen Gang <gang.chen@asianux.com>
Signed-off-by: Richard Kuo <rkuo@codeaurora.org>
|
|
get_user_pages(write=1, force=1) has always had odd behaviour on write-
protected shared mappings: although it demands FMODE_WRITE-access to the
underlying object (do_mmap_pgoff sets neither VM_SHARED nor VM_MAYWRITE
without that), it ends up with do_wp_page substituting private anonymous
Copied-On-Write pages for the shared file pages in the area.
That was long ago intentional, as a safety measure to prevent ptrace
setting a breakpoint (or POKETEXT or POKEDATA) from inadvertently
corrupting the underlying executable. Yet exec and dynamic loaders open
the file read-only, and use MAP_PRIVATE rather than MAP_SHARED.
The traditional odd behaviour still causes surprises and bugs in mm, and
is probably not what any caller wants - even the comment on the flag
says "You do not want this" (although it's undoubtedly necessary for
overriding userspace protections in some contexts, and good when !write).
Let's stop doing that. But it would be dangerous to remove the long-
standing safety at this stage, so just make get_user_pages(write,force)
fail with EFAULT when applied to a write-protected shared area.
Infiniband may in future want to force write through to underlying
object: we can add another FOLL_flag later to enable that if required.
Odd though the old behaviour was, there is no doubt that we may turn out
to break userspace with this change, and have to revert it quickly.
Issue a WARN_ON_ONCE to help debug the changed case (easily triggered by
userspace, so only once to prevent spamming the logs); and delay a few
associated cleanups until this change is proved.
get_user_pages callers who might see trouble from this change:
ptrace poking, or writing to /proc/<pid>/mem
drivers/infiniband/
drivers/media/v4l2-core/
drivers/gpu/drm/exynos/exynos_drm_gem.c
drivers/staging/tidspbridge/core/tiomap3430.c
if they ever apply get_user_pages to write-protected shared mappings
of an object which was opened for writing.
I went to apply the same change to mm/nommu.c, but retreated. NOMMU has
no place for COW, and its VM_flags conventions are not the same: I'd be
more likely to screw up NOMMU than make an improvement there.
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Hugh Dickins <hughd@google.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
|
