- 20 Oct, 2008 40 commits
-
-
KAMEZAWA Hiroyuki authored
Allocate all page_cgroup at boot and remove page_cgroup poitner from struct page. This patch adds an interface as struct page_cgroup *lookup_page_cgroup(struct page*) All FLATMEM/DISCONTIGMEM/SPARSEMEM and MEMORY_HOTPLUG is supported. Remove page_cgroup pointer reduces the amount of memory by - 4 bytes per PAGE_SIZE. - 8 bytes per PAGE_SIZE if memory controller is disabled. (even if configured.) On usual 8GB x86-32 server, this saves 8MB of NORMAL_ZONE memory. On my x86-64 server with 48GB of memory, this saves 96MB of memory. I think this reduction makes sense. By pre-allocation, kmalloc/kfree in charge/uncharge are removed. This means - we're not necessary to be afraid of kmalloc faiulre. (this can happen because of gfp_mask type.) - we can avoid calling kmalloc/kfree. - we can avoid allocating tons of small objects which can be fragmented. - we can know what amount of memory will be used for this extra-lru handling. I added printk message as "allocated %ld bytes of page_cgroup" "please try cgroup_disable=memory option if you don't want" maybe enough informative for users. Signed-off-by:KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Reviewed-by:
Balbir Singh <balbir@linux.vnet.ibm.com> Cc: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by:
Andrew Morton <akpm@linux-foundation.org> Signed-off-by:
Linus Torvalds <torvalds@linux-foundation.org>
-
KAMEZAWA Hiroyuki authored
This patch makes page_cgroup->flags to be atomic_ops and define functions (and macros) to access it. Before trying to modify memory resource controller, this atomic operation on flags is necessary. Most of flags in this patch is for LRU and modfied under mz->lru_lock but we'll add another flags which is not for LRU soon. For example, we'll place LOCK bit on flags field. We need atomic operation to modify LRU bit without LOCK. Signed-off-by:
-
KAMEZAWA Hiroyuki authored
Some obvious optimization to memcg. I found mem_cgroup_charge_statistics() is a little big (in object) and does unnecessary address calclation. This patch is for optimization to reduce the size of this function. And res_counter_charge() is 'likely' to succeed. Signed-off-by:
-
KAMEZAWA Hiroyuki authored
There are not-on-LRU pages which can be mapped and they are not worth to be accounted. (becasue we can't shrink them and need dirty codes to handle specical case) We'd like to make use of usual objrmap/radix-tree's protcol and don't want to account out-of-vm's control pages. When special_mapping_fault() is called, page->mapping is tend to be NULL and it's charged as Anonymous page. insert_page() also handles some special pages from drivers. This patch is for avoiding to account special pages. Signed-off-by:
-
KAMEZAWA Hiroyuki authored
This patch tries to make page->mapping to be NULL before mem_cgroup_uncharge_cache_page() is called. "page->mapping == NULL" is a good check for "whether the page is still radix-tree or not". This patch also adds BUG_ON() to mem_cgroup_uncharge_cache_page(); Signed-off-by:
Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Cc: Balbir Singh <balbir@linux.vnet.ibm.com> Signed-off-by:
-
KAMEZAWA Hiroyuki authored
While page-cache's charge/uncharge is done under page_lock(), swap-cache isn't. (anonymous page is charged when it's newly allocated.) This patch moves do_swap_page()'s charge() call under lock. I don't see any bad problem *now* but this fix will be good for future for avoiding unnecessary racy state. Signed-off-by:
-
Lai Jiangshan authored
Since we introduced rcu for read side, spin_lock is used only for update. But we always hold cgroup_lock() when update, so spin_lock() is not need. Additional cleanup: 1) include linux/rcupdate.h explicitly 2) remove unused variable cur_devcgroup in devcgroup_update_access() Signed-off-by:
Lai Jiangshan <laijs@cn.fujitsu.com> Acked-by:
"Serge E. Hallyn" <serue@us.ibm.com> Cc: Paul Menage <menage@google.com> Cc: James Morris <jmorris@namei.org> Signed-off-by:
-
Li Zefan authored
Signed-off-by:
Li Zefan <lizf@cn.fujitsu.com> Acked-by:
-
Li Zefan authored
This saves 40 bytes on my x86_32 box. Signed-off-by:
-
Paul Menage authored
The choice of real/dummy declaration for cgroup_mm_owner_callbacks() shouldn't be based on CONFIG_MM_OWNER, but on CONFIG_CGROUPS. Otherwise kernel/exit.c fails to compile when something other than a cgroups controller selects CONFIG_MM_OWNER Signed-off-by:
Paul Menage <menage@google.com> Acked-by:
Pekka Enberg <penberg@cs.helsinki.fi> Signed-off-by:
-
Paul Menage authored
Rather than pre-generating the entire text for the "tasks" file each time the file is opened, we instead just generate/update the array of process ids and use a seq_file to report these to userspace. All open file handles on the same "tasks" file can share a pid array, which may be updated any time that no thread is actively reading the array. By sharing the array, the potential for userspace to DoS the system by opening many handles on the same "tasks" file is removed. [Based on a patch by Lai Jiangshan, extended to use seq_file] Signed-off-by:
-
Lai Jiangshan authored
put_css_set_taskexit may be called when find_css_set is called on other cpu. And the race will occur: put_css_set_taskexit side find_css_set side | atomic_dec_and_test(&kref->refcount) | /* kref->refcount = 0 */ | .................................................................... | read_lock(&css_set_lock) | find_existing_css_set | get_css_set | read_unlock(&css_set_lock); .................................................................... __release_css_set | .................................................................... | /* use a released css_set */ | [put_css_set is the same. But in the current code, all put_css_set are put into cgroup mutex critical region as the same as find_css_set.] [akpm@linux-foundation.org: repair comments] [menage@google.com: eliminate race in css_set refcounting] Signed-off-by: -
Eric Sesterhenn authored
A corrupted extent for the extent file itself may try to get an impossible extent, causing a deadlock if I see it correctly. Check the inode number after the first_blocks checks and fail if it's the extent file, as according to the spec the extent file should have no extent for itself. Signed-off-by:
Eric Sesterhenn <snakebyte@gmx.de> Cc: Roman Zippel <zippel@linux-m68k.org> Signed-off-by:
-
Alan Cox authored
hfsplus: O_LARGEFILE checking is missing Addresses http://bugzilla.kernel.org/show_bug.cgi?id=8490 From: Alan Cox <alan@redhat.com> Reported-by:
didier <did447@gmail.com> Cc: Roman Zippel <zippel@linux-m68k.org> Signed-off-by:
-
Eric Sandeen authored
A very large directory with many read failures (either due to storage problems, or due to invalid size & blocks from corruption) will generate a printk storm as the filesystem continues to try to read all the blocks. This flood of messages can tie up the box until it is complete - which may be a very long time, especially for very large corrupted values. This is fixed by only reporting the corruption once each time we try to read the directory. Signed-off-by:
Eric Sandeen <sandeen@redhat.com> Signed-off-by:
"Theodore Ts'o" <tytso@mit.edu> Cc: Eugene Teo <eugeneteo@kernel.sg> Signed-off-by:
-
Aneesh Kumar K.V authored
For blocksize < pagesize we need to remove blocks that got allocated in block_write_begin() if we fail with ENOSPC for later blocks. block_write_begin() internally does this if it allocated page locally. This makes sure we don't have blocks outside inode.i_size during ENOSPC. Signed-off-by:
Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Signed-off-by:
-
Eugene Dashevsky authored
This fixes a bug where readdir() would return a directory entry twice if there was a hash collision in an hash tree indexed directory. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by:
Eugene Dashevsky <eugene@ibrix.com> Signed-off-by:
Mike Snitzer <msnitzer@ibrix.com> Signed-off-by:
-
Hidehiro Kawai authored
In ordered mode, if a file data buffer being dirtied exists in the committing transaction, we write the buffer to the disk, move it from the committing transaction to the running transaction, then dirty it. But we don't have to remove the buffer from the committing transaction when the buffer couldn't be written out, otherwise it would miss the error and the committing transaction would not abort. This patch adds an error check before removing the buffer from the committing transaction. Signed-off-by:
Hidehiro Kawai <hidehiro.kawai.ez@hitachi.com> Acked-by:
Jan Kara <jack@suse.cz> Signed-off-by:
-
Hidehiro Kawai authored
If the journal doesn't abort when it gets an IO error in file data blocks, the file data corruption will spread silently. Because most of applications and commands do buffered writes without fsync(), they don't notice the IO error. It's scary for mission critical systems. On the other hand, if the journal aborts whenever it gets an IO error in file data blocks, the system will easily become inoperable. So this patch introduces a filesystem option to determine whether it aborts the journal or just call printk() when it gets an IO error in file data. If you mount a ext3 fs with data_err=abort option, it aborts on file data write error. If you mount it with data_err=ignore, it doesn't abort, just call printk(). data_err=ignore is the default. Signed-off-by:
-
Mingming Cao authored
We could run into ENOSPC error on ext3, even when there is free blocks on the filesystem. The problem is triggered in the case the goal block group has 0 free blocks , and the rest block groups are skipped due to the check of "free_blocks < windowsz/2". Current code could fall back to non reservation allocation to prevent early ENOSPC after examing all the block groups with reservation on , but this code was bypassed if the reservation window is turned off already, which is true in this case. This patch fixed two issues: 1) We don't need to turn off block reservation if the goal block group has 0 free blocks left and continue search for the rest of block groups. Current code the intention is to turn off the block reservation if the goal allocation group has a few (some) free blocks left (not enough for make the desired reservation window),to try to allocation in the goal block group, to get better locality. But if the goal blocks have 0 free blocks, it should leave the block reservation on, and continues search for the next block groups,rather than turn off block reservation completely. 2) we don't need to check the window size if the block reservation is off. The problem was originally found and fixed in ext4. Signed-off-by:
Mingming Cao <cmm@us.ibm.com> Cc: Theodore Ts'o <tytso@mit.edu> Signed-off-by:
-
Josef Bacik authored
When trying to resize a ext3 fs and you run out of reserved gdt blocks, you get an error that doesn't actually tell you what went wrong, it just says that the gdb it picked is not correct, which is the case since you don't have any reserved gdt blocks left. This patch adds a check to make sure you have reserved gdt blocks to use, and if not prints out a more relevant error. Signed-off-by:
Josef Bacik <jbacik@redhat.com> Cc: <linux-ext4@vger.kernel.org> Cc: Andreas Dilger <adilger@sun.com> Signed-off-by:
-
Hidehiro Kawai authored
Currently, original metadata buffers are dirtied when they are unfiled whether the journal has aborted or not. Eventually these buffers will be written-back to the filesystem by pdflush. This means some metadata buffers are written to the filesystem without journaling if the journal aborts. So if both journal abort and system crash happen at the same time, the filesystem would become inconsistent state. Additionally, replaying journaled metadata can overwrite the latest metadata on the filesystem partly. Because, if the journal aborts, journaled metadata are preserved and replayed during the next mount not to lose uncheckpointed metadata. This would also break the consistency of the filesystem. This patch prevents original metadata buffers from being dirtied on abort by clearing BH_JBDDirty flag from those buffers. Thus, no metadata buffers are written to the filesystem without journaling. Signed-off-by:
-
Hidehiro Kawai authored
If we failed to write metadata buffers to the journal space and succeeded to write the commit record, stale data can be written back to the filesystem as metadata in the recovery phase. To avoid this, when we failed to write out metadata buffers, abort the journal before writing the commit record. Signed-off-by:
-
Richard Holden authored
The phone_device array is covered by the phone_lock mutex in all cases and request_module no longer needs the BKL so we can remove the only remaining instance of the BKL from phonedev. Signed-off-by:
Richard Holden <aciddeath@gmail.com> Signed-off-by:
-
Krzysztof Helt authored
Change lock_kernel()/unlock_kernel() to local fb mutex. Each frame buffer instance has its own mutex. The one line try_to_load() function is unrolled to request_module() in two places for readability. [righi.andrea@gmail.com: fb: fix NULL pointer BUG dereference in fb_open()] Signed-off-by:
Krzysztof Helt <krzysztof.h1@wp.pl> Signed-off-by:
Andrea Righi <righi.andrea@gmail.com> Signed-off-by:
-
Alan Cox authored
Framebuffer is heavily BKL dependant at the moment so just wrap the ioctl handler in the driver as we push down. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by:
Alan Cox <alan@redhat.com> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Cc: "Antonino A. Daplas" <adaplas@pol.net> Signed-off-by:
-
David Brownell authored
We can get the following oops from gpio_get_value_cansleep() when a GPIO controller doesn't provide a get() callback: Unable to handle kernel paging request for instruction fetch Faulting instruction address: 0x00000000 Oops: Kernel access of bad area, sig: 11 [#1] [...] NIP [00000000] 0x0 LR [c0182fb0] gpio_get_value_cansleep+0x40/0x50 Call Trace: [c7b79e80] [c0183f28] gpio_value_show+0x5c/0x94 [c7b79ea0] [c01a584c] dev_attr_show+0x30/0x7c [c7b79eb0] [c00d6b48] fill_read_buffer+0x68/0xe0 [c7b79ed0] [c00d6c54] sysfs_read_file+0x94/0xbc [c7b79ef0] [c008f24c] vfs_read+0xb4/0x16c [c7b79f10] [c008f580] sys_read+0x4c/0x90 [c7b79f40] [c0013a14] ret_from_syscall+0x0/0x38 It's OK to request the value of *any* GPIO; most GPIOs are bidirectional, so configuring them as outputs just enables an output driver and doesn't disable the input logic. So the problem is that gpio_get_value_cansleep() isn't making the same sanity check that gpio_get_value() does: making sure this GPIO isn't one of the atypical "no input logic" cases. Reported-by:
Anton Vorontsov <avorontsov@ru.mvista.com> Signed-off-by:
David Brownell <dbrownell@users.sourceforge.net> Cc: <stable@kernel.org> [2.6.27.x, 2.6.26.x, 2.6.25.x] Signed-off-by:
-
Steven A. Falco authored
gpiolib can export GPIOs to userspace via sysfs. This patch modifies the gpio_value_show() so that any non-zero value is explicitly printed as "1", rather than whatever numerical value the lower-level driver returns. Signed-off-by:
Steve Falco <sfalco@harris.com> Signed-off-by:
-
David Brownell authored
Teach rtc-cmos about the second bank of registers found on most modern x86 systems, giving access to 128 bytes more NVRAM. This version only sees that extra NVRAM when both register banks are provided as part of *one* PNP resource. Since BIOS on some systems presents them using two IO resources, and nothing merges them, this can't always show all the NVRAM. (We're supposed to be able to use PNP id PNP0b01 too, but BIOS tables doesn't often seem to use that particular option.) Signed-off-by:
-
roel kluin authored
In function sn_sal_switch_to_asynch(): drivers/serial/sn_console.c:713: HZ * SN_SAL_UART_FIFO_DEPTH / SN_SAL_UART_FIFO_SPEED_CPS; After preprocessing (see defines in patch) this becomes HZ * 16 / 9600 / 10 (associativity from left to right), not equivalent to HZ * 16 / 960. Looks-obviously-right-to: Tony Luck <tony.luck@intel.com> Cc: Jes Sorensen <jes@sgi.com> Acked-by:
Pat Gefre <pfg@sgi.com> Signed-off-by:
-
Adrian Bunk authored
This patch makes the needlessly global probe_serial_gsc() static. Signed-off-by:
Adrian Bunk <bunk@kernel.org> Signed-off-by:
-
Jiri Slaby authored
readl/writel are not expected to accept iomap return value. Replace bogus mapping by standard ioremap. Signed-off-by:
Jiri Slaby <jirislaby@gmail.com> Cc: <R.E.Wolff@BitWizard.nl> Acked-by:
Alan Cox <alan@lxorguk.ukuu.org.uk> Signed-off-by:
-
Henrik Rydberg authored
The read fail ratio is sensitive to the delay between the first byte written and the first byte read; apparently the sensors cannot be rushed. Increasing the minimum wait time, without changing the total wait time, improves the fail ratio from a 8% chance that any of the sensors fails in one read, down to 0.4%, on a Macbook Air. On a Macbook Pro 3,1, the effect is even more apparent. By reducing the number of status polls, the ratio is further improved to below 0.1%. Finally, increasing the total wait time brings the fail ratio down to virtually zero. Signed-off-by:
Henrik Rydberg <rydberg@euromail.se> Tested-by:
Bob McElrath <bob@mcelrath.org> Cc: Nicolas Boichat <nicolas@boichat.ch> Cc: "Mark M. Hoffman" <mhoffman@lightlink.com> Cc: Jean Delvare <khali@linux-fr.org> Signed-off-by:
-
Henrik Rydberg authored
Add temperature sensor support for Macbook Pro 3. Signed-off-by:
-
Henrik Rydberg authored
Adds temperature sensor support for the Macbook Pro 4. Signed-off-by:
-
Andrew Morton authored
dmi_system_id.driver_data is already void*. Cc: Henrik Rydberg <rydberg@euromail.se> Cc: Nicolas Boichat <nicolas@boichat.ch> Cc: Riki Oktarianto <rkoktarianto@gmail.com> Cc: Mark M. Hoffman <mhoffman@lightlink.com> Cc: Jean Delvare <khali@linux-fr.org> Signed-off-by:
-
Henrik Rydberg authored
This patch adds accelerometer, backlight and temperature sensor support for the Macbook Air. Signed-off-by:
-
Henrik Rydberg authored
On some recent Macbooks, the package length for the light sensors ALV0 and ALV1 has changed from 6 to 10. This patch allows for a variable package length encompassing both variants. Signed-off-by:
-
Henrik Rydberg authored
The time to wait for a status change while reading or writing to the SMC ports is a balance between read reliability and system performance. The current setting yields rougly three errors in a thousand when simultaneously reading three different temperature values on a Macbook Air. This patch increases the setting to a value yielding roughly one error in ten thousand, with no noticable system performance degradation. Signed-off-by:
-
Henrik Rydberg authored
On many Macbooks since mid 2007, the Pro, C2D and Air models, applesmc fails to read some or all SMC ports. This problem has various effects, such as flooded logfiles, malfunctioning temperature sensors, accelerometers failing to initialize, and difficulties getting backlight functionality to work properly. The root of the problem seems to be the command protocol. The current code sends out a command byte, then repeatedly polls for an ack before continuing to send or recieve data. From experiments leading to this patch, it seems the command protocol never quite worked or changed so that one now sends a command byte, waits a little bit, polls for an ack, and if it fails, repeats the whole thing by sending the command byte again. This patch implements a send_command function according to the new interpretation of the protocol, and should work also for earlier models. Signed-off-by:
-
