linux_dsm_epyc7002/fs/dcookies.c

356 lines
7.0 KiB
C
Raw Normal View History

/*
* dcookies.c
*
* Copyright 2002 John Levon <levon@movementarian.org>
*
* Persistent cookie-path mappings. These are used by
* profilers to convert a per-task EIP value into something
* non-transitory that can be processed at a later date.
* This is done by locking the dentry/vfsmnt pair in the
* kernel until released by the tasks needing the persistent
* objects. The tag is simply an unsigned long that refers
* to the pair and can be looked up from userspace.
*/
#include <linux/syscalls.h>
#include <linux/export.h>
#include <linux/slab.h>
#include <linux/list.h>
#include <linux/mount.h>
#include <linux/capability.h>
#include <linux/dcache.h>
#include <linux/mm.h>
Remove fs.h from mm.h Remove fs.h from mm.h. For this, 1) Uninline vma_wants_writenotify(). It's pretty huge anyway. 2) Add back fs.h or less bloated headers (err.h) to files that need it. As result, on x86_64 allyesconfig, fs.h dependencies cut down from 3929 files rebuilt down to 3444 (-12.3%). Cross-compile tested without regressions on my two usual configs and (sigh): alpha arm-mx1ads mips-bigsur powerpc-ebony alpha-allnoconfig arm-neponset mips-capcella powerpc-g5 alpha-defconfig arm-netwinder mips-cobalt powerpc-holly alpha-up arm-netx mips-db1000 powerpc-iseries arm arm-ns9xxx mips-db1100 powerpc-linkstation arm-assabet arm-omap_h2_1610 mips-db1200 powerpc-lite5200 arm-at91rm9200dk arm-onearm mips-db1500 powerpc-maple arm-at91rm9200ek arm-picotux200 mips-db1550 powerpc-mpc7448_hpc2 arm-at91sam9260ek arm-pleb mips-ddb5477 powerpc-mpc8272_ads arm-at91sam9261ek arm-pnx4008 mips-decstation powerpc-mpc8313_rdb arm-at91sam9263ek arm-pxa255-idp mips-e55 powerpc-mpc832x_mds arm-at91sam9rlek arm-realview mips-emma2rh powerpc-mpc832x_rdb arm-ateb9200 arm-realview-smp mips-excite powerpc-mpc834x_itx arm-badge4 arm-rpc mips-fulong powerpc-mpc834x_itxgp arm-carmeva arm-s3c2410 mips-ip22 powerpc-mpc834x_mds arm-cerfcube arm-shannon mips-ip27 powerpc-mpc836x_mds arm-clps7500 arm-shark mips-ip32 powerpc-mpc8540_ads arm-collie arm-simpad mips-jazz powerpc-mpc8544_ds arm-corgi arm-spitz mips-jmr3927 powerpc-mpc8560_ads arm-csb337 arm-trizeps4 mips-malta powerpc-mpc8568mds arm-csb637 arm-versatile mips-mipssim powerpc-mpc85xx_cds arm-ebsa110 i386 mips-mpc30x powerpc-mpc8641_hpcn arm-edb7211 i386-allnoconfig mips-msp71xx powerpc-mpc866_ads arm-em_x270 i386-defconfig mips-ocelot powerpc-mpc885_ads arm-ep93xx i386-up mips-pb1100 powerpc-pasemi arm-footbridge ia64 mips-pb1500 powerpc-pmac32 arm-fortunet ia64-allnoconfig mips-pb1550 powerpc-ppc64 arm-h3600 ia64-bigsur mips-pnx8550-jbs powerpc-prpmc2800 arm-h7201 ia64-defconfig mips-pnx8550-stb810 powerpc-ps3 arm-h7202 ia64-gensparse mips-qemu powerpc-pseries arm-hackkit ia64-sim mips-rbhma4200 powerpc-up arm-integrator ia64-sn2 mips-rbhma4500 s390 arm-iop13xx ia64-tiger mips-rm200 s390-allnoconfig arm-iop32x ia64-up mips-sb1250-swarm s390-defconfig arm-iop33x ia64-zx1 mips-sead s390-up arm-ixp2000 m68k mips-tb0219 sparc arm-ixp23xx m68k-amiga mips-tb0226 sparc-allnoconfig arm-ixp4xx m68k-apollo mips-tb0287 sparc-defconfig arm-jornada720 m68k-atari mips-workpad sparc-up arm-kafa m68k-bvme6000 mips-wrppmc sparc64 arm-kb9202 m68k-hp300 mips-yosemite sparc64-allnoconfig arm-ks8695 m68k-mac parisc sparc64-defconfig arm-lart m68k-mvme147 parisc-allnoconfig sparc64-up arm-lpd270 m68k-mvme16x parisc-defconfig um-x86_64 arm-lpd7a400 m68k-q40 parisc-up x86_64 arm-lpd7a404 m68k-sun3 powerpc x86_64-allnoconfig arm-lubbock m68k-sun3x powerpc-cell x86_64-defconfig arm-lusl7200 mips powerpc-celleb x86_64-up arm-mainstone mips-atlas powerpc-chrp32 Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-30 05:36:13 +07:00
#include <linux/err.h>
#include <linux/errno.h>
#include <linux/dcookies.h>
#include <linux/mutex.h>
#include <linux/path.h>
#include <linux/compat.h>
#include <linux/uaccess.h>
/* The dcookies are allocated from a kmem_cache and
* hashed onto a small number of lists. None of the
* code here is particularly performance critical
*/
struct dcookie_struct {
struct path path;
struct list_head hash_list;
};
static LIST_HEAD(dcookie_users);
static DEFINE_MUTEX(dcookie_mutex);
static struct kmem_cache *dcookie_cache __read_mostly;
static struct list_head *dcookie_hashtable __read_mostly;
static size_t hash_size __read_mostly;
static inline int is_live(void)
{
return !(list_empty(&dcookie_users));
}
/* The dentry is locked, its address will do for the cookie */
static inline unsigned long dcookie_value(struct dcookie_struct * dcs)
{
return (unsigned long)dcs->path.dentry;
}
static size_t dcookie_hash(unsigned long dcookie)
{
return (dcookie >> L1_CACHE_SHIFT) & (hash_size - 1);
}
static struct dcookie_struct * find_dcookie(unsigned long dcookie)
{
struct dcookie_struct *found = NULL;
struct dcookie_struct * dcs;
struct list_head * pos;
struct list_head * list;
list = dcookie_hashtable + dcookie_hash(dcookie);
list_for_each(pos, list) {
dcs = list_entry(pos, struct dcookie_struct, hash_list);
if (dcookie_value(dcs) == dcookie) {
found = dcs;
break;
}
}
return found;
}
static void hash_dcookie(struct dcookie_struct * dcs)
{
struct list_head * list = dcookie_hashtable + dcookie_hash(dcookie_value(dcs));
list_add(&dcs->hash_list, list);
}
static struct dcookie_struct *alloc_dcookie(const struct path *path)
{
struct dcookie_struct *dcs = kmem_cache_alloc(dcookie_cache,
GFP_KERNEL);
shrink struct dentry struct dentry is one of the most critical structures in the kernel. So it's sad to see it going neglected. With CONFIG_PROFILING turned on (which is probably the common case at least for distros and kernel developers), sizeof(struct dcache) == 208 here (64-bit). This gives 19 objects per slab. I packed d_mounted into a hole, and took another 4 bytes off the inline name length to take the padding out from the end of the structure. This shinks it to 200 bytes. I could have gone the other way and increased the length to 40, but I'm aiming for a magic number, read on... I then got rid of the d_cookie pointer. This shrinks it to 192 bytes. Rant: why was this ever a good idea? The cookie system should increase its hash size or use a tree or something if lookups are a problem. Also the "fast dcookie lookups" in oprofile should be moved into the dcookie code -- how can oprofile possibly care about the dcookie_mutex? It gets dropped after get_dcookie() returns so it can't be providing any sort of protection. At 192 bytes, 21 objects fit into a 4K page, saving about 3MB on my system with ~140 000 entries allocated. 192 is also a multiple of 64, so we get nice cacheline alignment on 64 and 32 byte line systems -- any given dentry will now require 3 cachelines to touch all fields wheras previously it would require 4. I know the inline name size was chosen quite carefully, however with the reduction in cacheline footprint, it should actually be just about as fast to do a name lookup for a 36 character name as it was before the patch (and faster for other sizes). The memory footprint savings for names which are <= 32 or > 36 bytes long should more than make up for the memory cost for 33-36 byte names. Performance is a feature... Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2008-12-01 15:33:43 +07:00
struct dentry *d;
if (!dcs)
return NULL;
shrink struct dentry struct dentry is one of the most critical structures in the kernel. So it's sad to see it going neglected. With CONFIG_PROFILING turned on (which is probably the common case at least for distros and kernel developers), sizeof(struct dcache) == 208 here (64-bit). This gives 19 objects per slab. I packed d_mounted into a hole, and took another 4 bytes off the inline name length to take the padding out from the end of the structure. This shinks it to 200 bytes. I could have gone the other way and increased the length to 40, but I'm aiming for a magic number, read on... I then got rid of the d_cookie pointer. This shrinks it to 192 bytes. Rant: why was this ever a good idea? The cookie system should increase its hash size or use a tree or something if lookups are a problem. Also the "fast dcookie lookups" in oprofile should be moved into the dcookie code -- how can oprofile possibly care about the dcookie_mutex? It gets dropped after get_dcookie() returns so it can't be providing any sort of protection. At 192 bytes, 21 objects fit into a 4K page, saving about 3MB on my system with ~140 000 entries allocated. 192 is also a multiple of 64, so we get nice cacheline alignment on 64 and 32 byte line systems -- any given dentry will now require 3 cachelines to touch all fields wheras previously it would require 4. I know the inline name size was chosen quite carefully, however with the reduction in cacheline footprint, it should actually be just about as fast to do a name lookup for a 36 character name as it was before the patch (and faster for other sizes). The memory footprint savings for names which are <= 32 or > 36 bytes long should more than make up for the memory cost for 33-36 byte names. Performance is a feature... Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2008-12-01 15:33:43 +07:00
d = path->dentry;
spin_lock(&d->d_lock);
d->d_flags |= DCACHE_COOKIE;
spin_unlock(&d->d_lock);
dcs->path = *path;
path_get(path);
hash_dcookie(dcs);
return dcs;
}
/* This is the main kernel-side routine that retrieves the cookie
* value for a dentry/vfsmnt pair.
*/
int get_dcookie(const struct path *path, unsigned long *cookie)
{
int err = 0;
struct dcookie_struct * dcs;
mutex_lock(&dcookie_mutex);
if (!is_live()) {
err = -EINVAL;
goto out;
}
shrink struct dentry struct dentry is one of the most critical structures in the kernel. So it's sad to see it going neglected. With CONFIG_PROFILING turned on (which is probably the common case at least for distros and kernel developers), sizeof(struct dcache) == 208 here (64-bit). This gives 19 objects per slab. I packed d_mounted into a hole, and took another 4 bytes off the inline name length to take the padding out from the end of the structure. This shinks it to 200 bytes. I could have gone the other way and increased the length to 40, but I'm aiming for a magic number, read on... I then got rid of the d_cookie pointer. This shrinks it to 192 bytes. Rant: why was this ever a good idea? The cookie system should increase its hash size or use a tree or something if lookups are a problem. Also the "fast dcookie lookups" in oprofile should be moved into the dcookie code -- how can oprofile possibly care about the dcookie_mutex? It gets dropped after get_dcookie() returns so it can't be providing any sort of protection. At 192 bytes, 21 objects fit into a 4K page, saving about 3MB on my system with ~140 000 entries allocated. 192 is also a multiple of 64, so we get nice cacheline alignment on 64 and 32 byte line systems -- any given dentry will now require 3 cachelines to touch all fields wheras previously it would require 4. I know the inline name size was chosen quite carefully, however with the reduction in cacheline footprint, it should actually be just about as fast to do a name lookup for a 36 character name as it was before the patch (and faster for other sizes). The memory footprint savings for names which are <= 32 or > 36 bytes long should more than make up for the memory cost for 33-36 byte names. Performance is a feature... Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2008-12-01 15:33:43 +07:00
if (path->dentry->d_flags & DCACHE_COOKIE) {
dcs = find_dcookie((unsigned long)path->dentry);
} else {
dcs = alloc_dcookie(path);
shrink struct dentry struct dentry is one of the most critical structures in the kernel. So it's sad to see it going neglected. With CONFIG_PROFILING turned on (which is probably the common case at least for distros and kernel developers), sizeof(struct dcache) == 208 here (64-bit). This gives 19 objects per slab. I packed d_mounted into a hole, and took another 4 bytes off the inline name length to take the padding out from the end of the structure. This shinks it to 200 bytes. I could have gone the other way and increased the length to 40, but I'm aiming for a magic number, read on... I then got rid of the d_cookie pointer. This shrinks it to 192 bytes. Rant: why was this ever a good idea? The cookie system should increase its hash size or use a tree or something if lookups are a problem. Also the "fast dcookie lookups" in oprofile should be moved into the dcookie code -- how can oprofile possibly care about the dcookie_mutex? It gets dropped after get_dcookie() returns so it can't be providing any sort of protection. At 192 bytes, 21 objects fit into a 4K page, saving about 3MB on my system with ~140 000 entries allocated. 192 is also a multiple of 64, so we get nice cacheline alignment on 64 and 32 byte line systems -- any given dentry will now require 3 cachelines to touch all fields wheras previously it would require 4. I know the inline name size was chosen quite carefully, however with the reduction in cacheline footprint, it should actually be just about as fast to do a name lookup for a 36 character name as it was before the patch (and faster for other sizes). The memory footprint savings for names which are <= 32 or > 36 bytes long should more than make up for the memory cost for 33-36 byte names. Performance is a feature... Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2008-12-01 15:33:43 +07:00
if (!dcs) {
err = -ENOMEM;
goto out;
}
}
*cookie = dcookie_value(dcs);
out:
mutex_unlock(&dcookie_mutex);
return err;
}
/* And here is where the userspace process can look up the cookie value
* to retrieve the path.
*/
static int do_lookup_dcookie(u64 cookie64, char __user *buf, size_t len)
{
unsigned long cookie = (unsigned long)cookie64;
int err = -EINVAL;
char * kbuf;
char * path;
size_t pathlen;
struct dcookie_struct * dcs;
/* we could leak path information to users
* without dir read permission without this
*/
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
mutex_lock(&dcookie_mutex);
if (!is_live()) {
err = -EINVAL;
goto out;
}
if (!(dcs = find_dcookie(cookie)))
goto out;
err = -ENOMEM;
kbuf = kmalloc(PAGE_SIZE, GFP_KERNEL);
if (!kbuf)
goto out;
/* FIXME: (deleted) ? */
path = d_path(&dcs->path, kbuf, PAGE_SIZE);
oprofile, dcookies: Fix possible circular locking dependency The lockdep warning below detects a possible A->B/B->A locking dependency of mm->mmap_sem and dcookie_mutex. The order in sync_buffer() is mm->mmap_sem/dcookie_mutex, while in sys_lookup_dcookie() it is vice versa. Fixing it in sys_lookup_dcookie() by unlocking dcookie_mutex before copy_to_user(). oprofiled/4432 is trying to acquire lock: (&mm->mmap_sem){++++++}, at: [<ffffffff810b444b>] might_fault+0x53/0xa3 but task is already holding lock: (dcookie_mutex){+.+.+.}, at: [<ffffffff81124d28>] sys_lookup_dcookie+0x45/0x149 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (dcookie_mutex){+.+.+.}: [<ffffffff8106557f>] lock_acquire+0xf8/0x11e [<ffffffff814634f0>] mutex_lock_nested+0x63/0x309 [<ffffffff81124e5c>] get_dcookie+0x30/0x144 [<ffffffffa0000fba>] sync_buffer+0x196/0x3ec [oprofile] [<ffffffffa0001226>] task_exit_notify+0x16/0x1a [oprofile] [<ffffffff81467b96>] notifier_call_chain+0x37/0x63 [<ffffffff8105803d>] __blocking_notifier_call_chain+0x50/0x67 [<ffffffff81058068>] blocking_notifier_call_chain+0x14/0x16 [<ffffffff8105a718>] profile_task_exit+0x1a/0x1c [<ffffffff81039e8f>] do_exit+0x2a/0x6fc [<ffffffff8103a5e4>] do_group_exit+0x83/0xae [<ffffffff8103a626>] sys_exit_group+0x17/0x1b [<ffffffff8146ad4b>] system_call_fastpath+0x16/0x1b -> #0 (&mm->mmap_sem){++++++}: [<ffffffff81064dfb>] __lock_acquire+0x1085/0x1711 [<ffffffff8106557f>] lock_acquire+0xf8/0x11e [<ffffffff810b4478>] might_fault+0x80/0xa3 [<ffffffff81124de7>] sys_lookup_dcookie+0x104/0x149 [<ffffffff8146ad4b>] system_call_fastpath+0x16/0x1b other info that might help us debug this: 1 lock held by oprofiled/4432: #0: (dcookie_mutex){+.+.+.}, at: [<ffffffff81124d28>] sys_lookup_dcookie+0x45/0x149 stack backtrace: Pid: 4432, comm: oprofiled Not tainted 2.6.39-00008-ge5a450d #9 Call Trace: [<ffffffff81063193>] print_circular_bug+0xae/0xbc [<ffffffff81064dfb>] __lock_acquire+0x1085/0x1711 [<ffffffff8102ef13>] ? get_parent_ip+0x11/0x42 [<ffffffff810b444b>] ? might_fault+0x53/0xa3 [<ffffffff8106557f>] lock_acquire+0xf8/0x11e [<ffffffff810b444b>] ? might_fault+0x53/0xa3 [<ffffffff810d7d54>] ? path_put+0x22/0x27 [<ffffffff810b4478>] might_fault+0x80/0xa3 [<ffffffff810b444b>] ? might_fault+0x53/0xa3 [<ffffffff81124de7>] sys_lookup_dcookie+0x104/0x149 [<ffffffff8146ad4b>] system_call_fastpath+0x16/0x1b References: https://bugzilla.kernel.org/show_bug.cgi?id=13809 Cc: <stable@kernel.org> # .27+ Signed-off-by: Robert Richter <robert.richter@amd.com>
2011-05-31 17:35:41 +07:00
mutex_unlock(&dcookie_mutex);
if (IS_ERR(path)) {
err = PTR_ERR(path);
goto out_free;
}
err = -ERANGE;
pathlen = kbuf + PAGE_SIZE - path;
if (pathlen <= len) {
err = pathlen;
if (copy_to_user(buf, path, pathlen))
err = -EFAULT;
}
out_free:
kfree(kbuf);
oprofile, dcookies: Fix possible circular locking dependency The lockdep warning below detects a possible A->B/B->A locking dependency of mm->mmap_sem and dcookie_mutex. The order in sync_buffer() is mm->mmap_sem/dcookie_mutex, while in sys_lookup_dcookie() it is vice versa. Fixing it in sys_lookup_dcookie() by unlocking dcookie_mutex before copy_to_user(). oprofiled/4432 is trying to acquire lock: (&mm->mmap_sem){++++++}, at: [<ffffffff810b444b>] might_fault+0x53/0xa3 but task is already holding lock: (dcookie_mutex){+.+.+.}, at: [<ffffffff81124d28>] sys_lookup_dcookie+0x45/0x149 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (dcookie_mutex){+.+.+.}: [<ffffffff8106557f>] lock_acquire+0xf8/0x11e [<ffffffff814634f0>] mutex_lock_nested+0x63/0x309 [<ffffffff81124e5c>] get_dcookie+0x30/0x144 [<ffffffffa0000fba>] sync_buffer+0x196/0x3ec [oprofile] [<ffffffffa0001226>] task_exit_notify+0x16/0x1a [oprofile] [<ffffffff81467b96>] notifier_call_chain+0x37/0x63 [<ffffffff8105803d>] __blocking_notifier_call_chain+0x50/0x67 [<ffffffff81058068>] blocking_notifier_call_chain+0x14/0x16 [<ffffffff8105a718>] profile_task_exit+0x1a/0x1c [<ffffffff81039e8f>] do_exit+0x2a/0x6fc [<ffffffff8103a5e4>] do_group_exit+0x83/0xae [<ffffffff8103a626>] sys_exit_group+0x17/0x1b [<ffffffff8146ad4b>] system_call_fastpath+0x16/0x1b -> #0 (&mm->mmap_sem){++++++}: [<ffffffff81064dfb>] __lock_acquire+0x1085/0x1711 [<ffffffff8106557f>] lock_acquire+0xf8/0x11e [<ffffffff810b4478>] might_fault+0x80/0xa3 [<ffffffff81124de7>] sys_lookup_dcookie+0x104/0x149 [<ffffffff8146ad4b>] system_call_fastpath+0x16/0x1b other info that might help us debug this: 1 lock held by oprofiled/4432: #0: (dcookie_mutex){+.+.+.}, at: [<ffffffff81124d28>] sys_lookup_dcookie+0x45/0x149 stack backtrace: Pid: 4432, comm: oprofiled Not tainted 2.6.39-00008-ge5a450d #9 Call Trace: [<ffffffff81063193>] print_circular_bug+0xae/0xbc [<ffffffff81064dfb>] __lock_acquire+0x1085/0x1711 [<ffffffff8102ef13>] ? get_parent_ip+0x11/0x42 [<ffffffff810b444b>] ? might_fault+0x53/0xa3 [<ffffffff8106557f>] lock_acquire+0xf8/0x11e [<ffffffff810b444b>] ? might_fault+0x53/0xa3 [<ffffffff810d7d54>] ? path_put+0x22/0x27 [<ffffffff810b4478>] might_fault+0x80/0xa3 [<ffffffff810b444b>] ? might_fault+0x53/0xa3 [<ffffffff81124de7>] sys_lookup_dcookie+0x104/0x149 [<ffffffff8146ad4b>] system_call_fastpath+0x16/0x1b References: https://bugzilla.kernel.org/show_bug.cgi?id=13809 Cc: <stable@kernel.org> # .27+ Signed-off-by: Robert Richter <robert.richter@amd.com>
2011-05-31 17:35:41 +07:00
return err;
out:
mutex_unlock(&dcookie_mutex);
return err;
}
SYSCALL_DEFINE3(lookup_dcookie, u64, cookie64, char __user *, buf, size_t, len)
{
return do_lookup_dcookie(cookie64, buf, len);
}
#ifdef CONFIG_COMPAT
COMPAT_SYSCALL_DEFINE4(lookup_dcookie, u32, w0, u32, w1, char __user *, buf, compat_size_t, len)
{
#ifdef __BIG_ENDIAN
return do_lookup_dcookie(((u64)w0 << 32) | w1, buf, len);
#else
return do_lookup_dcookie(((u64)w1 << 32) | w0, buf, len);
#endif
}
#endif
static int dcookie_init(void)
{
struct list_head * d;
unsigned int i, hash_bits;
int err = -ENOMEM;
dcookie_cache = kmem_cache_create("dcookie_cache",
sizeof(struct dcookie_struct),
0, 0, NULL);
if (!dcookie_cache)
goto out;
dcookie_hashtable = kmalloc(PAGE_SIZE, GFP_KERNEL);
if (!dcookie_hashtable)
goto out_kmem;
err = 0;
/*
* Find the power-of-two list-heads that can fit into the allocation..
* We don't guarantee that "sizeof(struct list_head)" is necessarily
* a power-of-two.
*/
hash_size = PAGE_SIZE / sizeof(struct list_head);
hash_bits = 0;
do {
hash_bits++;
} while ((hash_size >> hash_bits) != 0);
hash_bits--;
/*
* Re-calculate the actual number of entries and the mask
* from the number of bits we can fit.
*/
hash_size = 1UL << hash_bits;
/* And initialize the newly allocated array */
d = dcookie_hashtable;
i = hash_size;
do {
INIT_LIST_HEAD(d);
d++;
i--;
} while (i);
out:
return err;
out_kmem:
kmem_cache_destroy(dcookie_cache);
goto out;
}
static void free_dcookie(struct dcookie_struct * dcs)
{
shrink struct dentry struct dentry is one of the most critical structures in the kernel. So it's sad to see it going neglected. With CONFIG_PROFILING turned on (which is probably the common case at least for distros and kernel developers), sizeof(struct dcache) == 208 here (64-bit). This gives 19 objects per slab. I packed d_mounted into a hole, and took another 4 bytes off the inline name length to take the padding out from the end of the structure. This shinks it to 200 bytes. I could have gone the other way and increased the length to 40, but I'm aiming for a magic number, read on... I then got rid of the d_cookie pointer. This shrinks it to 192 bytes. Rant: why was this ever a good idea? The cookie system should increase its hash size or use a tree or something if lookups are a problem. Also the "fast dcookie lookups" in oprofile should be moved into the dcookie code -- how can oprofile possibly care about the dcookie_mutex? It gets dropped after get_dcookie() returns so it can't be providing any sort of protection. At 192 bytes, 21 objects fit into a 4K page, saving about 3MB on my system with ~140 000 entries allocated. 192 is also a multiple of 64, so we get nice cacheline alignment on 64 and 32 byte line systems -- any given dentry will now require 3 cachelines to touch all fields wheras previously it would require 4. I know the inline name size was chosen quite carefully, however with the reduction in cacheline footprint, it should actually be just about as fast to do a name lookup for a 36 character name as it was before the patch (and faster for other sizes). The memory footprint savings for names which are <= 32 or > 36 bytes long should more than make up for the memory cost for 33-36 byte names. Performance is a feature... Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2008-12-01 15:33:43 +07:00
struct dentry *d = dcs->path.dentry;
spin_lock(&d->d_lock);
d->d_flags &= ~DCACHE_COOKIE;
spin_unlock(&d->d_lock);
path_put(&dcs->path);
kmem_cache_free(dcookie_cache, dcs);
}
static void dcookie_exit(void)
{
struct list_head * list;
struct list_head * pos;
struct list_head * pos2;
struct dcookie_struct * dcs;
size_t i;
for (i = 0; i < hash_size; ++i) {
list = dcookie_hashtable + i;
list_for_each_safe(pos, pos2, list) {
dcs = list_entry(pos, struct dcookie_struct, hash_list);
list_del(&dcs->hash_list);
free_dcookie(dcs);
}
}
kfree(dcookie_hashtable);
kmem_cache_destroy(dcookie_cache);
}
struct dcookie_user {
struct list_head next;
};
struct dcookie_user * dcookie_register(void)
{
struct dcookie_user * user;
mutex_lock(&dcookie_mutex);
user = kmalloc(sizeof(struct dcookie_user), GFP_KERNEL);
if (!user)
goto out;
if (!is_live() && dcookie_init())
goto out_free;
list_add(&user->next, &dcookie_users);
out:
mutex_unlock(&dcookie_mutex);
return user;
out_free:
kfree(user);
user = NULL;
goto out;
}
void dcookie_unregister(struct dcookie_user * user)
{
mutex_lock(&dcookie_mutex);
list_del(&user->next);
kfree(user);
if (!is_live())
dcookie_exit();
mutex_unlock(&dcookie_mutex);
}
EXPORT_SYMBOL_GPL(dcookie_register);
EXPORT_SYMBOL_GPL(dcookie_unregister);
EXPORT_SYMBOL_GPL(get_dcookie);