From 52cf25d0ab7f78eeecc59ac652ed5090f69b619e Mon Sep 17 00:00:00 2001 From: Emese Revfy Date: Tue, 19 Jan 2010 02:58:23 +0100 Subject: Driver core: Constify struct sysfs_ops in struct kobj_type Constify struct sysfs_ops. This is part of the ops structure constification effort started by Arjan van de Ven et al. Benefits of this constification: * prevents modification of data that is shared (referenced) by many other structure instances at runtime * detects/prevents accidental (but not intentional) modification attempts on archs that enforce read-only kernel data at runtime * potentially better optimized code as the compiler can assume that the const data cannot be changed * the compiler/linker move const data into .rodata and therefore exclude them from false sharing Signed-off-by: Emese Revfy Acked-by: David Teigland Acked-by: Matt Domsch Acked-by: Maciej Sosnowski Acked-by: Hans J. Koch Acked-by: Pekka Enberg Acked-by: Jens Axboe Acked-by: Stephen Hemminger Signed-off-by: Greg Kroah-Hartman --- drivers/md/dm-sysfs.c | 2 +- drivers/md/md.c | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'drivers/md') diff --git a/drivers/md/dm-sysfs.c b/drivers/md/dm-sysfs.c index f91b40942e07..84d2b91e4efb 100644 --- a/drivers/md/dm-sysfs.c +++ b/drivers/md/dm-sysfs.c @@ -75,7 +75,7 @@ static struct attribute *dm_attrs[] = { NULL, }; -static struct sysfs_ops dm_sysfs_ops = { +static const struct sysfs_ops dm_sysfs_ops = { .show = dm_attr_show, }; diff --git a/drivers/md/md.c b/drivers/md/md.c index a20a71e5efd3..fdc1890b6ac5 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -2642,7 +2642,7 @@ static void rdev_free(struct kobject *ko) mdk_rdev_t *rdev = container_of(ko, mdk_rdev_t, kobj); kfree(rdev); } -static struct sysfs_ops rdev_sysfs_ops = { +static const struct sysfs_ops rdev_sysfs_ops = { .show = rdev_attr_show, .store = rdev_attr_store, }; @@ -4059,7 +4059,7 @@ static void md_free(struct kobject *ko) kfree(mddev); } -static struct sysfs_ops md_sysfs_ops = { +static const struct sysfs_ops md_sysfs_ops = { .show = md_attr_show, .store = md_attr_store, }; -- cgit v1.2.1 From 5a0e3ad6af8660be21ca98a971cd00f331318c05 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 24 Mar 2010 17:04:11 +0900 Subject: 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 Guess-its-ok-by: Christoph Lameter Cc: Ingo Molnar Cc: Lee Schermerhorn --- drivers/md/dm-log-userspace-base.c | 1 + drivers/md/dm-log-userspace-transfer.c | 1 + drivers/md/dm-region-hash.c | 1 + drivers/md/dm-service-time.c | 2 ++ drivers/md/dm-target.c | 1 - drivers/md/faulty.c | 1 + drivers/md/linear.c | 1 + drivers/md/md.c | 1 + drivers/md/multipath.c | 1 + drivers/md/raid0.c | 1 + drivers/md/raid1.c | 1 + drivers/md/raid10.c | 1 + drivers/md/raid5.c | 1 + drivers/md/raid6algos.c | 1 + 14 files changed, 14 insertions(+), 1 deletion(-) (limited to 'drivers/md') diff --git a/drivers/md/dm-log-userspace-base.c b/drivers/md/dm-log-userspace-base.c index 7ac2c1450d10..1ed0094f064b 100644 --- a/drivers/md/dm-log-userspace-base.c +++ b/drivers/md/dm-log-userspace-base.c @@ -5,6 +5,7 @@ */ #include +#include #include #include #include diff --git a/drivers/md/dm-log-userspace-transfer.c b/drivers/md/dm-log-userspace-transfer.c index f1c8cae70b4b..075cbcf8a9f5 100644 --- a/drivers/md/dm-log-userspace-transfer.c +++ b/drivers/md/dm-log-userspace-transfer.c @@ -6,6 +6,7 @@ #include #include +#include #include #include #include diff --git a/drivers/md/dm-region-hash.c b/drivers/md/dm-region-hash.c index 168bd38f5006..bd5c58b28868 100644 --- a/drivers/md/dm-region-hash.c +++ b/drivers/md/dm-region-hash.c @@ -11,6 +11,7 @@ #include #include #include +#include #include #include "dm.h" diff --git a/drivers/md/dm-service-time.c b/drivers/md/dm-service-time.c index cfa668f46c40..9c6c2e47ad62 100644 --- a/drivers/md/dm-service-time.c +++ b/drivers/md/dm-service-time.c @@ -11,6 +11,8 @@ #include "dm.h" #include "dm-path-selector.h" +#include + #define DM_MSG_PREFIX "multipath service-time" #define ST_MIN_IO 1 #define ST_MAX_RELATIVE_THROUGHPUT 100 diff --git a/drivers/md/dm-target.c b/drivers/md/dm-target.c index 04feccf2a997..11dea11dc0b6 100644 --- a/drivers/md/dm-target.c +++ b/drivers/md/dm-target.c @@ -10,7 +10,6 @@ #include #include #include -#include #define DM_MSG_PREFIX "target" diff --git a/drivers/md/faulty.c b/drivers/md/faulty.c index 713acd02ab39..8e3850b98cca 100644 --- a/drivers/md/faulty.c +++ b/drivers/md/faulty.c @@ -64,6 +64,7 @@ #define MaxFault 50 #include #include +#include #include "md.h" #include diff --git a/drivers/md/linear.c b/drivers/md/linear.c index bb2a23159b21..09437e958235 100644 --- a/drivers/md/linear.c +++ b/drivers/md/linear.c @@ -19,6 +19,7 @@ #include #include #include +#include #include "md.h" #include "linear.h" diff --git a/drivers/md/md.c b/drivers/md/md.c index fdc1890b6ac5..9712b2e97be4 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -49,6 +49,7 @@ #include #include #include +#include #include "md.h" #include "bitmap.h" diff --git a/drivers/md/multipath.c b/drivers/md/multipath.c index 5558ebc705c8..789bf535d29c 100644 --- a/drivers/md/multipath.c +++ b/drivers/md/multipath.c @@ -22,6 +22,7 @@ #include #include #include +#include #include "md.h" #include "multipath.h" diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index 377cf2a3c333..c3bec024612e 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -20,6 +20,7 @@ #include #include +#include #include "md.h" #include "raid0.h" diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index f741f77eeb2b..e59b10e66edb 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -31,6 +31,7 @@ * Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */ +#include #include #include #include diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index b4ba41ecbd20..e2766d8251a1 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -18,6 +18,7 @@ * Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */ +#include #include #include #include diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 70ffbd071b2e..e3e9a36ea3b7 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -50,6 +50,7 @@ #include #include #include +#include #include "md.h" #include "raid5.h" #include "bitmap.h" diff --git a/drivers/md/raid6algos.c b/drivers/md/raid6algos.c index bffc61bff5ab..1f8784bfd44d 100644 --- a/drivers/md/raid6algos.c +++ b/drivers/md/raid6algos.c @@ -17,6 +17,7 @@ */ #include +#include #ifndef __KERNEL__ #include #include -- cgit v1.2.1 From 35f2a591192d0a5d9f7fc696869c76f0b8e49c3d Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Tue, 20 Apr 2010 14:13:34 +1000 Subject: md/raid5: allow for more than 2^31 chunks. With many large drives and small chunk sizes it is possible to create a RAID5 with more than 2^31 chunks. Make sure this works. Reported-by: Brett King Signed-off-by: NeilBrown Cc: stable@kernel.org --- drivers/md/raid5.c | 19 +++++++------------ 1 file changed, 7 insertions(+), 12 deletions(-) (limited to 'drivers/md') diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index e3e9a36ea3b7..20e48401910e 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -1650,8 +1650,8 @@ static sector_t raid5_compute_sector(raid5_conf_t *conf, sector_t r_sector, int previous, int *dd_idx, struct stripe_head *sh) { - long stripe; - unsigned long chunk_number; + sector_t stripe; + sector_t chunk_number; unsigned int chunk_offset; int pd_idx, qd_idx; int ddf_layout = 0; @@ -1671,17 +1671,12 @@ static sector_t raid5_compute_sector(raid5_conf_t *conf, sector_t r_sector, */ chunk_offset = sector_div(r_sector, sectors_per_chunk); chunk_number = r_sector; - BUG_ON(r_sector != chunk_number); /* * Compute the stripe number */ - stripe = chunk_number / data_disks; - - /* - * Compute the data disk and parity disk indexes inside the stripe - */ - *dd_idx = chunk_number % data_disks; + stripe = chunk_number; + *dd_idx = sector_div(stripe, data_disks); /* * Select the parity disk based on the user selected algorithm. @@ -1870,14 +1865,14 @@ static sector_t compute_blocknr(struct stripe_head *sh, int i, int previous) : conf->algorithm; sector_t stripe; int chunk_offset; - int chunk_number, dummy1, dd_idx = i; + sector_t chunk_number; + int dummy1, dd_idx = i; sector_t r_sector; struct stripe_head sh2; chunk_offset = sector_div(new_sector, sectors_per_chunk); stripe = new_sector; - BUG_ON(new_sector != stripe); if (i == sh->pd_idx) return 0; @@ -1970,7 +1965,7 @@ static sector_t compute_blocknr(struct stripe_head *sh, int i, int previous) } chunk_number = stripe * data_disks + i; - r_sector = (sector_t)chunk_number * sectors_per_chunk + chunk_offset; + r_sector = chunk_number * sectors_per_chunk + chunk_offset; check = raid5_compute_sector(conf, r_sector, previous, &dummy1, &sh2); -- cgit v1.2.1 From 6e3b96ed610e5a1838e62ddae9fa0c3463f235fa Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Fri, 23 Apr 2010 07:08:28 +1000 Subject: md/raid5: fix previous patch. Previous patch changes stripe and chunk_number to sector_t but mistakenly did not update all of the divisions to use sector_dev(). This patch changes all the those divisions (actually the '%' operator) to sector_div. Signed-off-by: NeilBrown Cc: stable@kernel.org Tested-by: Stefan Lippers-Hollmann --- drivers/md/raid5.c | 35 ++++++++++++++++++----------------- 1 file changed, 18 insertions(+), 17 deletions(-) (limited to 'drivers/md') diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 20e48401910e..58ea0ecae7c3 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -1650,7 +1650,7 @@ static sector_t raid5_compute_sector(raid5_conf_t *conf, sector_t r_sector, int previous, int *dd_idx, struct stripe_head *sh) { - sector_t stripe; + sector_t stripe, stripe2; sector_t chunk_number; unsigned int chunk_offset; int pd_idx, qd_idx; @@ -1677,7 +1677,7 @@ static sector_t raid5_compute_sector(raid5_conf_t *conf, sector_t r_sector, */ stripe = chunk_number; *dd_idx = sector_div(stripe, data_disks); - + stripe2 = stripe; /* * Select the parity disk based on the user selected algorithm. */ @@ -1689,21 +1689,21 @@ static sector_t raid5_compute_sector(raid5_conf_t *conf, sector_t r_sector, case 5: switch (algorithm) { case ALGORITHM_LEFT_ASYMMETRIC: - pd_idx = data_disks - stripe % raid_disks; + pd_idx = data_disks - sector_div(stripe2, raid_disks); if (*dd_idx >= pd_idx) (*dd_idx)++; break; case ALGORITHM_RIGHT_ASYMMETRIC: - pd_idx = stripe % raid_disks; + pd_idx = sector_div(stripe2, raid_disks); if (*dd_idx >= pd_idx) (*dd_idx)++; break; case ALGORITHM_LEFT_SYMMETRIC: - pd_idx = data_disks - stripe % raid_disks; + pd_idx = data_disks - sector_div(stripe2, raid_disks); *dd_idx = (pd_idx + 1 + *dd_idx) % raid_disks; break; case ALGORITHM_RIGHT_SYMMETRIC: - pd_idx = stripe % raid_disks; + pd_idx = sector_div(stripe2, raid_disks); *dd_idx = (pd_idx + 1 + *dd_idx) % raid_disks; break; case ALGORITHM_PARITY_0: @@ -1723,7 +1723,7 @@ static sector_t raid5_compute_sector(raid5_conf_t *conf, sector_t r_sector, switch (algorithm) { case ALGORITHM_LEFT_ASYMMETRIC: - pd_idx = raid_disks - 1 - (stripe % raid_disks); + pd_idx = raid_disks - 1 - sector_div(stripe2, raid_disks); qd_idx = pd_idx + 1; if (pd_idx == raid_disks-1) { (*dd_idx)++; /* Q D D D P */ @@ -1732,7 +1732,7 @@ static sector_t raid5_compute_sector(raid5_conf_t *conf, sector_t r_sector, (*dd_idx) += 2; /* D D P Q D */ break; case ALGORITHM_RIGHT_ASYMMETRIC: - pd_idx = stripe % raid_disks; + pd_idx = sector_div(stripe2, raid_disks); qd_idx = pd_idx + 1; if (pd_idx == raid_disks-1) { (*dd_idx)++; /* Q D D D P */ @@ -1741,12 +1741,12 @@ static sector_t raid5_compute_sector(raid5_conf_t *conf, sector_t r_sector, (*dd_idx) += 2; /* D D P Q D */ break; case ALGORITHM_LEFT_SYMMETRIC: - pd_idx = raid_disks - 1 - (stripe % raid_disks); + pd_idx = raid_disks - 1 - sector_div(stripe2, raid_disks); qd_idx = (pd_idx + 1) % raid_disks; *dd_idx = (pd_idx + 2 + *dd_idx) % raid_disks; break; case ALGORITHM_RIGHT_SYMMETRIC: - pd_idx = stripe % raid_disks; + pd_idx = sector_div(stripe2, raid_disks); qd_idx = (pd_idx + 1) % raid_disks; *dd_idx = (pd_idx + 2 + *dd_idx) % raid_disks; break; @@ -1765,7 +1765,7 @@ static sector_t raid5_compute_sector(raid5_conf_t *conf, sector_t r_sector, /* Exactly the same as RIGHT_ASYMMETRIC, but or * of blocks for computing Q is different. */ - pd_idx = stripe % raid_disks; + pd_idx = sector_div(stripe2, raid_disks); qd_idx = pd_idx + 1; if (pd_idx == raid_disks-1) { (*dd_idx)++; /* Q D D D P */ @@ -1780,7 +1780,8 @@ static sector_t raid5_compute_sector(raid5_conf_t *conf, sector_t r_sector, * D D D P Q rather than * Q D D D P */ - pd_idx = raid_disks - 1 - ((stripe + 1) % raid_disks); + stripe2 += 1; + pd_idx = raid_disks - 1 - sector_div(stripe2, raid_disks); qd_idx = pd_idx + 1; if (pd_idx == raid_disks-1) { (*dd_idx)++; /* Q D D D P */ @@ -1792,7 +1793,7 @@ static sector_t raid5_compute_sector(raid5_conf_t *conf, sector_t r_sector, case ALGORITHM_ROTATING_N_CONTINUE: /* Same as left_symmetric but Q is before P */ - pd_idx = raid_disks - 1 - (stripe % raid_disks); + pd_idx = raid_disks - 1 - sector_div(stripe2, raid_disks); qd_idx = (pd_idx + raid_disks - 1) % raid_disks; *dd_idx = (pd_idx + 1 + *dd_idx) % raid_disks; ddf_layout = 1; @@ -1800,27 +1801,27 @@ static sector_t raid5_compute_sector(raid5_conf_t *conf, sector_t r_sector, case ALGORITHM_LEFT_ASYMMETRIC_6: /* RAID5 left_asymmetric, with Q on last device */ - pd_idx = data_disks - stripe % (raid_disks-1); + pd_idx = data_disks - sector_div(stripe2, raid_disks-1); if (*dd_idx >= pd_idx) (*dd_idx)++; qd_idx = raid_disks - 1; break; case ALGORITHM_RIGHT_ASYMMETRIC_6: - pd_idx = stripe % (raid_disks-1); + pd_idx = sector_div(stripe2, raid_disks-1); if (*dd_idx >= pd_idx) (*dd_idx)++; qd_idx = raid_disks - 1; break; case ALGORITHM_LEFT_SYMMETRIC_6: - pd_idx = data_disks - stripe % (raid_disks-1); + pd_idx = data_disks - sector_div(stripe2, raid_disks-1); *dd_idx = (pd_idx + 1 + *dd_idx) % (raid_disks-1); qd_idx = raid_disks - 1; break; case ALGORITHM_RIGHT_SYMMETRIC_6: - pd_idx = stripe % (raid_disks-1); + pd_idx = sector_div(stripe2, raid_disks-1); *dd_idx = (pd_idx + 1 + *dd_idx) % (raid_disks-1); qd_idx = raid_disks - 1; break; -- cgit v1.2.1 From 87aa63000c484bfb9909989316f615240dfee018 Mon Sep 17 00:00:00 2001 From: "Gabriele A. Trombetti" Date: Wed, 28 Apr 2010 11:51:17 +1000 Subject: md/raid6: Fix raid-6 read-error correction in degraded state Fix: Raid-6 was not trying to correct a read-error when in singly-degraded state and was instead dropping one more device, going to doubly-degraded state. This patch fixes this behaviour. Tested-by: Janos Haar Signed-off-by: Gabriele A. Trombetti Reported-by: Janos Haar Signed-off-by: NeilBrown Cc: stable@kernel.org --- drivers/md/raid5.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/md') diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 58ea0ecae7c3..15348c393b5d 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -1527,7 +1527,7 @@ static void raid5_end_read_request(struct bio * bi, int error) clear_bit(R5_UPTODATE, &sh->dev[i].flags); atomic_inc(&rdev->read_errors); - if (conf->mddev->degraded) + if (conf->mddev->degraded >= conf->max_degraded) printk_rl(KERN_WARNING "raid5:%s: read error not correctable " "(sector %llu on %s).\n", -- cgit v1.2.1 From 1176568de7e066c0be9e46c37503b9fd4730edcf Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Fri, 7 May 2010 19:44:26 +1000 Subject: md: restore ability of spare drives to spin down. Some time ago we stopped the clean/active metadata updates from being written to a 'spare' device in most cases so that it could spin down and say spun down. Device failure/removal etc are still recorded on spares. However commit 51d5668cb2e3fd1827a55 broke this 50% of the time, depending on whether the event count is even or odd. The change log entry said: This means that the alignment between 'odd/even' and 'clean/dirty' might take a little longer to attain, how ever the code makes no attempt to create that alignment, so it could take arbitrarily long. So when we find that clean/dirty is not aligned with odd/even, force a second metadata-update immediately. There are already cases where a second metadata-update is needed immediately (e.g. when a device fails during the metadata update). We just piggy-back on that. Reported-by: Joe Bryant Signed-off-by: NeilBrown Cc: stable@kernel.org --- drivers/md/md.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'drivers/md') diff --git a/drivers/md/md.c b/drivers/md/md.c index 9712b2e97be4..cefd63daff31 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -2109,12 +2109,18 @@ repeat: if (!mddev->in_sync || mddev->recovery_cp != MaxSector) { /* not clean */ /* .. if the array isn't clean, an 'even' event must also go * to spares. */ - if ((mddev->events&1)==0) + if ((mddev->events&1)==0) { nospares = 0; + sync_req = 2; /* force a second update to get the + * even/odd in sync */ + } } else { /* otherwise an 'odd' event must go to spares */ - if ((mddev->events&1)) + if ((mddev->events&1)) { nospares = 0; + sync_req = 2; /* force a second update to get the + * even/odd in sync */ + } } } -- cgit v1.2.1 From 3ff195b011d7decf501a4d55aeed312731094796 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 30 Mar 2010 11:31:26 -0700 Subject: sysfs: Implement sysfs tagged directory support. The problem. When implementing a network namespace I need to be able to have multiple network devices with the same name. Currently this is a problem for /sys/class/net/*, /sys/devices/virtual/net/*, and potentially a few other directories of the form /sys/ ... /net/*. What this patch does is to add an additional tag field to the sysfs dirent structure. For directories that should show different contents depending on the context such as /sys/class/net/, and /sys/devices/virtual/net/ this tag field is used to specify the context in which those directories should be visible. Effectively this is the same as creating multiple distinct directories with the same name but internally to sysfs the result is nicer. I am calling the concept of a single directory that looks like multiple directories all at the same path in the filesystem tagged directories. For the networking namespace the set of directories whose contents I need to filter with tags can depend on the presence or absence of hotplug hardware or which modules are currently loaded. Which means I need a simple race free way to setup those directories as tagged. To achieve a reace free design all tagged directories are created and managed by sysfs itself. Users of this interface: - define a type in the sysfs_tag_type enumeration. - call sysfs_register_ns_types with the type and it's operations - sysfs_exit_ns when an individual tag is no longer valid - Implement mount_ns() which returns the ns of the calling process so we can attach it to a sysfs superblock. - Implement ktype.namespace() which returns the ns of a syfs kobject. Everything else is left up to sysfs and the driver layer. For the network namespace mount_ns and namespace() are essentially one line functions, and look to remain that. Tags are currently represented a const void * pointers as that is both generic, prevides enough information for equality comparisons, and is trivial to create for current users, as it is just the existing namespace pointer. The work needed in sysfs is more extensive. At each directory or symlink creating I need to check if the directory it is being created in is a tagged directory and if so generate the appropriate tag to place on the sysfs_dirent. Likewise at each symlink or directory removal I need to check if the sysfs directory it is being removed from is a tagged directory and if so figure out which tag goes along with the name I am deleting. Currently only directories which hold kobjects, and symlinks are supported. There is not enough information in the current file attribute interfaces to give us anything to discriminate on which makes it useless, and there are no potential users which makes it an uninteresting problem to solve. Signed-off-by: Eric W. Biederman Signed-off-by: Benjamin Thery Signed-off-by: Greg Kroah-Hartman --- drivers/md/bitmap.c | 4 ++-- drivers/md/md.c | 6 +++--- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'drivers/md') diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c index 26ac8aad0b19..f084249295d9 100644 --- a/drivers/md/bitmap.c +++ b/drivers/md/bitmap.c @@ -1678,9 +1678,9 @@ int bitmap_create(mddev_t *mddev) bitmap->mddev = mddev; - bm = sysfs_get_dirent(mddev->kobj.sd, "bitmap"); + bm = sysfs_get_dirent(mddev->kobj.sd, NULL, "bitmap"); if (bm) { - bitmap->sysfs_can_clear = sysfs_get_dirent(bm, "can_clear"); + bitmap->sysfs_can_clear = sysfs_get_dirent(bm, NULL, "can_clear"); sysfs_put(bm); } else bitmap->sysfs_can_clear = NULL; diff --git a/drivers/md/md.c b/drivers/md/md.c index cefd63daff31..a9fd491796ac 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -1766,7 +1766,7 @@ static int bind_rdev_to_array(mdk_rdev_t * rdev, mddev_t * mddev) kobject_del(&rdev->kobj); goto fail; } - rdev->sysfs_state = sysfs_get_dirent(rdev->kobj.sd, "state"); + rdev->sysfs_state = sysfs_get_dirent(rdev->kobj.sd, NULL, "state"); list_add_rcu(&rdev->same_set, &mddev->disks); bd_claim_by_disk(rdev->bdev, rdev->bdev->bd_holder, mddev->gendisk); @@ -4189,7 +4189,7 @@ static int md_alloc(dev_t dev, char *name) mutex_unlock(&disks_mutex); if (!error) { kobject_uevent(&mddev->kobj, KOBJ_ADD); - mddev->sysfs_state = sysfs_get_dirent(mddev->kobj.sd, "array_state"); + mddev->sysfs_state = sysfs_get_dirent(mddev->kobj.sd, NULL, "array_state"); } mddev_put(mddev); return error; @@ -4398,7 +4398,7 @@ static int do_md_run(mddev_t * mddev) printk(KERN_WARNING "md: cannot register extra attributes for %s\n", mdname(mddev)); - mddev->sysfs_action = sysfs_get_dirent(mddev->kobj.sd, "sync_action"); + mddev->sysfs_action = sysfs_get_dirent(mddev->kobj.sd, NULL, "sync_action"); } else if (mddev->ro == 2) /* auto-readonly not meaningful */ mddev->ro = 0; -- cgit v1.2.1