OpenCloudOS-Kernel/kernel/groups.c

253 lines
5.2 KiB
C
Raw Normal View History

/*
* Supplementary group IDs
*/
#include <linux/cred.h>
#include <linux/export.h>
#include <linux/slab.h>
#include <linux/security.h>
#include <linux/syscalls.h>
#include <linux/user_namespace.h>
cred: simpler, 1D supplementary groups Current supplementary groups code can massively overallocate memory and is implemented in a way so that access to individual gid is done via 2D array. If number of gids is <= 32, memory allocation is more or less tolerable (140/148 bytes). But if it is not, code allocates full page (!) regardless and, what's even more fun, doesn't reuse small 32-entry array. 2D array means dependent shifts, loads and LEAs without possibility to optimize them (gid is never known at compile time). All of the above is unnecessary. Switch to the usual trailing-zero-len-array scheme. Memory is allocated with kmalloc/vmalloc() and only as much as needed. Accesses become simpler (LEA 8(gi,idx,4) or even without displacement). Maximum number of gids is 65536 which translates to 256KB+8 bytes. I think kernel can handle such allocation. On my usual desktop system with whole 9 (nine) aux groups, struct group_info shrinks from 148 bytes to 44 bytes, yay! Nice side effects: - "gi->gid[i]" is shorter than "GROUP_AT(gi, i)", less typing, - fix little mess in net/ipv4/ping.c should have been using GROUP_AT macro but this point becomes moot, - aux group allocation is persistent and should be accounted as such. Link: http://lkml.kernel.org/r/20160817201927.GA2096@p183.telecom.by Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com> Cc: Vasily Kulikov <segoon@openwall.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-10-08 08:03:12 +08:00
#include <linux/vmalloc.h>
#include <linux/uaccess.h>
struct group_info *groups_alloc(int gidsetsize)
{
cred: simpler, 1D supplementary groups Current supplementary groups code can massively overallocate memory and is implemented in a way so that access to individual gid is done via 2D array. If number of gids is <= 32, memory allocation is more or less tolerable (140/148 bytes). But if it is not, code allocates full page (!) regardless and, what's even more fun, doesn't reuse small 32-entry array. 2D array means dependent shifts, loads and LEAs without possibility to optimize them (gid is never known at compile time). All of the above is unnecessary. Switch to the usual trailing-zero-len-array scheme. Memory is allocated with kmalloc/vmalloc() and only as much as needed. Accesses become simpler (LEA 8(gi,idx,4) or even without displacement). Maximum number of gids is 65536 which translates to 256KB+8 bytes. I think kernel can handle such allocation. On my usual desktop system with whole 9 (nine) aux groups, struct group_info shrinks from 148 bytes to 44 bytes, yay! Nice side effects: - "gi->gid[i]" is shorter than "GROUP_AT(gi, i)", less typing, - fix little mess in net/ipv4/ping.c should have been using GROUP_AT macro but this point becomes moot, - aux group allocation is persistent and should be accounted as such. Link: http://lkml.kernel.org/r/20160817201927.GA2096@p183.telecom.by Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com> Cc: Vasily Kulikov <segoon@openwall.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-10-08 08:03:12 +08:00
struct group_info *gi;
unsigned int len;
len = sizeof(struct group_info) + sizeof(kgid_t) * gidsetsize;
gi = kmalloc(len, GFP_KERNEL_ACCOUNT|__GFP_NOWARN|__GFP_NORETRY);
if (!gi)
gi = __vmalloc(len, GFP_KERNEL_ACCOUNT|__GFP_HIGHMEM, PAGE_KERNEL);
if (!gi)
return NULL;
cred: simpler, 1D supplementary groups Current supplementary groups code can massively overallocate memory and is implemented in a way so that access to individual gid is done via 2D array. If number of gids is <= 32, memory allocation is more or less tolerable (140/148 bytes). But if it is not, code allocates full page (!) regardless and, what's even more fun, doesn't reuse small 32-entry array. 2D array means dependent shifts, loads and LEAs without possibility to optimize them (gid is never known at compile time). All of the above is unnecessary. Switch to the usual trailing-zero-len-array scheme. Memory is allocated with kmalloc/vmalloc() and only as much as needed. Accesses become simpler (LEA 8(gi,idx,4) or even without displacement). Maximum number of gids is 65536 which translates to 256KB+8 bytes. I think kernel can handle such allocation. On my usual desktop system with whole 9 (nine) aux groups, struct group_info shrinks from 148 bytes to 44 bytes, yay! Nice side effects: - "gi->gid[i]" is shorter than "GROUP_AT(gi, i)", less typing, - fix little mess in net/ipv4/ping.c should have been using GROUP_AT macro but this point becomes moot, - aux group allocation is persistent and should be accounted as such. Link: http://lkml.kernel.org/r/20160817201927.GA2096@p183.telecom.by Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com> Cc: Vasily Kulikov <segoon@openwall.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-10-08 08:03:12 +08:00
atomic_set(&gi->usage, 1);
gi->ngroups = gidsetsize;
return gi;
}
EXPORT_SYMBOL(groups_alloc);
void groups_free(struct group_info *group_info)
{
cred: simpler, 1D supplementary groups Current supplementary groups code can massively overallocate memory and is implemented in a way so that access to individual gid is done via 2D array. If number of gids is <= 32, memory allocation is more or less tolerable (140/148 bytes). But if it is not, code allocates full page (!) regardless and, what's even more fun, doesn't reuse small 32-entry array. 2D array means dependent shifts, loads and LEAs without possibility to optimize them (gid is never known at compile time). All of the above is unnecessary. Switch to the usual trailing-zero-len-array scheme. Memory is allocated with kmalloc/vmalloc() and only as much as needed. Accesses become simpler (LEA 8(gi,idx,4) or even without displacement). Maximum number of gids is 65536 which translates to 256KB+8 bytes. I think kernel can handle such allocation. On my usual desktop system with whole 9 (nine) aux groups, struct group_info shrinks from 148 bytes to 44 bytes, yay! Nice side effects: - "gi->gid[i]" is shorter than "GROUP_AT(gi, i)", less typing, - fix little mess in net/ipv4/ping.c should have been using GROUP_AT macro but this point becomes moot, - aux group allocation is persistent and should be accounted as such. Link: http://lkml.kernel.org/r/20160817201927.GA2096@p183.telecom.by Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com> Cc: Vasily Kulikov <segoon@openwall.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-10-08 08:03:12 +08:00
kvfree(group_info);
}
EXPORT_SYMBOL(groups_free);
/* export the group_info to a user-space array */
static int groups_to_user(gid_t __user *grouplist,
const struct group_info *group_info)
{
struct user_namespace *user_ns = current_user_ns();
int i;
unsigned int count = group_info->ngroups;
for (i = 0; i < count; i++) {
gid_t gid;
cred: simpler, 1D supplementary groups Current supplementary groups code can massively overallocate memory and is implemented in a way so that access to individual gid is done via 2D array. If number of gids is <= 32, memory allocation is more or less tolerable (140/148 bytes). But if it is not, code allocates full page (!) regardless and, what's even more fun, doesn't reuse small 32-entry array. 2D array means dependent shifts, loads and LEAs without possibility to optimize them (gid is never known at compile time). All of the above is unnecessary. Switch to the usual trailing-zero-len-array scheme. Memory is allocated with kmalloc/vmalloc() and only as much as needed. Accesses become simpler (LEA 8(gi,idx,4) or even without displacement). Maximum number of gids is 65536 which translates to 256KB+8 bytes. I think kernel can handle such allocation. On my usual desktop system with whole 9 (nine) aux groups, struct group_info shrinks from 148 bytes to 44 bytes, yay! Nice side effects: - "gi->gid[i]" is shorter than "GROUP_AT(gi, i)", less typing, - fix little mess in net/ipv4/ping.c should have been using GROUP_AT macro but this point becomes moot, - aux group allocation is persistent and should be accounted as such. Link: http://lkml.kernel.org/r/20160817201927.GA2096@p183.telecom.by Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com> Cc: Vasily Kulikov <segoon@openwall.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-10-08 08:03:12 +08:00
gid = from_kgid_munged(user_ns, group_info->gid[i]);
if (put_user(gid, grouplist+i))
return -EFAULT;
}
return 0;
}
/* fill a group_info from a user-space array - it must be allocated already */
static int groups_from_user(struct group_info *group_info,
gid_t __user *grouplist)
{
struct user_namespace *user_ns = current_user_ns();
int i;
unsigned int count = group_info->ngroups;
for (i = 0; i < count; i++) {
gid_t gid;
kgid_t kgid;
if (get_user(gid, grouplist+i))
return -EFAULT;
kgid = make_kgid(user_ns, gid);
if (!gid_valid(kgid))
return -EINVAL;
cred: simpler, 1D supplementary groups Current supplementary groups code can massively overallocate memory and is implemented in a way so that access to individual gid is done via 2D array. If number of gids is <= 32, memory allocation is more or less tolerable (140/148 bytes). But if it is not, code allocates full page (!) regardless and, what's even more fun, doesn't reuse small 32-entry array. 2D array means dependent shifts, loads and LEAs without possibility to optimize them (gid is never known at compile time). All of the above is unnecessary. Switch to the usual trailing-zero-len-array scheme. Memory is allocated with kmalloc/vmalloc() and only as much as needed. Accesses become simpler (LEA 8(gi,idx,4) or even without displacement). Maximum number of gids is 65536 which translates to 256KB+8 bytes. I think kernel can handle such allocation. On my usual desktop system with whole 9 (nine) aux groups, struct group_info shrinks from 148 bytes to 44 bytes, yay! Nice side effects: - "gi->gid[i]" is shorter than "GROUP_AT(gi, i)", less typing, - fix little mess in net/ipv4/ping.c should have been using GROUP_AT macro but this point becomes moot, - aux group allocation is persistent and should be accounted as such. Link: http://lkml.kernel.org/r/20160817201927.GA2096@p183.telecom.by Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com> Cc: Vasily Kulikov <segoon@openwall.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-10-08 08:03:12 +08:00
group_info->gid[i] = kgid;
}
return 0;
}
/* a simple Shell sort */
static void groups_sort(struct group_info *group_info)
{
int base, max, stride;
int gidsetsize = group_info->ngroups;
for (stride = 1; stride < gidsetsize; stride = 3 * stride + 1)
; /* nothing */
stride /= 3;
while (stride) {
max = gidsetsize - stride;
for (base = 0; base < max; base++) {
int left = base;
int right = left + stride;
cred: simpler, 1D supplementary groups Current supplementary groups code can massively overallocate memory and is implemented in a way so that access to individual gid is done via 2D array. If number of gids is <= 32, memory allocation is more or less tolerable (140/148 bytes). But if it is not, code allocates full page (!) regardless and, what's even more fun, doesn't reuse small 32-entry array. 2D array means dependent shifts, loads and LEAs without possibility to optimize them (gid is never known at compile time). All of the above is unnecessary. Switch to the usual trailing-zero-len-array scheme. Memory is allocated with kmalloc/vmalloc() and only as much as needed. Accesses become simpler (LEA 8(gi,idx,4) or even without displacement). Maximum number of gids is 65536 which translates to 256KB+8 bytes. I think kernel can handle such allocation. On my usual desktop system with whole 9 (nine) aux groups, struct group_info shrinks from 148 bytes to 44 bytes, yay! Nice side effects: - "gi->gid[i]" is shorter than "GROUP_AT(gi, i)", less typing, - fix little mess in net/ipv4/ping.c should have been using GROUP_AT macro but this point becomes moot, - aux group allocation is persistent and should be accounted as such. Link: http://lkml.kernel.org/r/20160817201927.GA2096@p183.telecom.by Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com> Cc: Vasily Kulikov <segoon@openwall.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-10-08 08:03:12 +08:00
kgid_t tmp = group_info->gid[right];
cred: simpler, 1D supplementary groups Current supplementary groups code can massively overallocate memory and is implemented in a way so that access to individual gid is done via 2D array. If number of gids is <= 32, memory allocation is more or less tolerable (140/148 bytes). But if it is not, code allocates full page (!) regardless and, what's even more fun, doesn't reuse small 32-entry array. 2D array means dependent shifts, loads and LEAs without possibility to optimize them (gid is never known at compile time). All of the above is unnecessary. Switch to the usual trailing-zero-len-array scheme. Memory is allocated with kmalloc/vmalloc() and only as much as needed. Accesses become simpler (LEA 8(gi,idx,4) or even without displacement). Maximum number of gids is 65536 which translates to 256KB+8 bytes. I think kernel can handle such allocation. On my usual desktop system with whole 9 (nine) aux groups, struct group_info shrinks from 148 bytes to 44 bytes, yay! Nice side effects: - "gi->gid[i]" is shorter than "GROUP_AT(gi, i)", less typing, - fix little mess in net/ipv4/ping.c should have been using GROUP_AT macro but this point becomes moot, - aux group allocation is persistent and should be accounted as such. Link: http://lkml.kernel.org/r/20160817201927.GA2096@p183.telecom.by Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com> Cc: Vasily Kulikov <segoon@openwall.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-10-08 08:03:12 +08:00
while (left >= 0 && gid_gt(group_info->gid[left], tmp)) {
group_info->gid[right] = group_info->gid[left];
right = left;
left -= stride;
}
cred: simpler, 1D supplementary groups Current supplementary groups code can massively overallocate memory and is implemented in a way so that access to individual gid is done via 2D array. If number of gids is <= 32, memory allocation is more or less tolerable (140/148 bytes). But if it is not, code allocates full page (!) regardless and, what's even more fun, doesn't reuse small 32-entry array. 2D array means dependent shifts, loads and LEAs without possibility to optimize them (gid is never known at compile time). All of the above is unnecessary. Switch to the usual trailing-zero-len-array scheme. Memory is allocated with kmalloc/vmalloc() and only as much as needed. Accesses become simpler (LEA 8(gi,idx,4) or even without displacement). Maximum number of gids is 65536 which translates to 256KB+8 bytes. I think kernel can handle such allocation. On my usual desktop system with whole 9 (nine) aux groups, struct group_info shrinks from 148 bytes to 44 bytes, yay! Nice side effects: - "gi->gid[i]" is shorter than "GROUP_AT(gi, i)", less typing, - fix little mess in net/ipv4/ping.c should have been using GROUP_AT macro but this point becomes moot, - aux group allocation is persistent and should be accounted as such. Link: http://lkml.kernel.org/r/20160817201927.GA2096@p183.telecom.by Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com> Cc: Vasily Kulikov <segoon@openwall.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-10-08 08:03:12 +08:00
group_info->gid[right] = tmp;
}
stride /= 3;
}
}
/* a simple bsearch */
int groups_search(const struct group_info *group_info, kgid_t grp)
{
unsigned int left, right;
if (!group_info)
return 0;
left = 0;
right = group_info->ngroups;
while (left < right) {
unsigned int mid = (left+right)/2;
cred: simpler, 1D supplementary groups Current supplementary groups code can massively overallocate memory and is implemented in a way so that access to individual gid is done via 2D array. If number of gids is <= 32, memory allocation is more or less tolerable (140/148 bytes). But if it is not, code allocates full page (!) regardless and, what's even more fun, doesn't reuse small 32-entry array. 2D array means dependent shifts, loads and LEAs without possibility to optimize them (gid is never known at compile time). All of the above is unnecessary. Switch to the usual trailing-zero-len-array scheme. Memory is allocated with kmalloc/vmalloc() and only as much as needed. Accesses become simpler (LEA 8(gi,idx,4) or even without displacement). Maximum number of gids is 65536 which translates to 256KB+8 bytes. I think kernel can handle such allocation. On my usual desktop system with whole 9 (nine) aux groups, struct group_info shrinks from 148 bytes to 44 bytes, yay! Nice side effects: - "gi->gid[i]" is shorter than "GROUP_AT(gi, i)", less typing, - fix little mess in net/ipv4/ping.c should have been using GROUP_AT macro but this point becomes moot, - aux group allocation is persistent and should be accounted as such. Link: http://lkml.kernel.org/r/20160817201927.GA2096@p183.telecom.by Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com> Cc: Vasily Kulikov <segoon@openwall.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-10-08 08:03:12 +08:00
if (gid_gt(grp, group_info->gid[mid]))
left = mid + 1;
cred: simpler, 1D supplementary groups Current supplementary groups code can massively overallocate memory and is implemented in a way so that access to individual gid is done via 2D array. If number of gids is <= 32, memory allocation is more or less tolerable (140/148 bytes). But if it is not, code allocates full page (!) regardless and, what's even more fun, doesn't reuse small 32-entry array. 2D array means dependent shifts, loads and LEAs without possibility to optimize them (gid is never known at compile time). All of the above is unnecessary. Switch to the usual trailing-zero-len-array scheme. Memory is allocated with kmalloc/vmalloc() and only as much as needed. Accesses become simpler (LEA 8(gi,idx,4) or even without displacement). Maximum number of gids is 65536 which translates to 256KB+8 bytes. I think kernel can handle such allocation. On my usual desktop system with whole 9 (nine) aux groups, struct group_info shrinks from 148 bytes to 44 bytes, yay! Nice side effects: - "gi->gid[i]" is shorter than "GROUP_AT(gi, i)", less typing, - fix little mess in net/ipv4/ping.c should have been using GROUP_AT macro but this point becomes moot, - aux group allocation is persistent and should be accounted as such. Link: http://lkml.kernel.org/r/20160817201927.GA2096@p183.telecom.by Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com> Cc: Vasily Kulikov <segoon@openwall.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-10-08 08:03:12 +08:00
else if (gid_lt(grp, group_info->gid[mid]))
right = mid;
else
return 1;
}
return 0;
}
/**
* set_groups - Change a group subscription in a set of credentials
* @new: The newly prepared set of credentials to alter
* @group_info: The group list to install
*/
void set_groups(struct cred *new, struct group_info *group_info)
{
put_group_info(new->group_info);
groups_sort(group_info);
get_group_info(group_info);
new->group_info = group_info;
}
EXPORT_SYMBOL(set_groups);
/**
* set_current_groups - Change current's group subscription
* @group_info: The group list to impose
*
* Validate a group subscription and, if valid, impose it upon current's task
* security record.
*/
int set_current_groups(struct group_info *group_info)
{
struct cred *new;
new = prepare_creds();
if (!new)
return -ENOMEM;
set_groups(new, group_info);
return commit_creds(new);
}
EXPORT_SYMBOL(set_current_groups);
SYSCALL_DEFINE2(getgroups, int, gidsetsize, gid_t __user *, grouplist)
{
const struct cred *cred = current_cred();
int i;
if (gidsetsize < 0)
return -EINVAL;
/* no need to grab task_lock here; it cannot change */
i = cred->group_info->ngroups;
if (gidsetsize) {
if (i > gidsetsize) {
i = -EINVAL;
goto out;
}
if (groups_to_user(grouplist, cred->group_info)) {
i = -EFAULT;
goto out;
}
}
out:
return i;
}
bool may_setgroups(void)
{
struct user_namespace *user_ns = current_user_ns();
return ns_capable(user_ns, CAP_SETGID) &&
userns_may_setgroups(user_ns);
}
/*
* SMP: Our groups are copy-on-write. We can set them safely
* without another task interfering.
*/
SYSCALL_DEFINE2(setgroups, int, gidsetsize, gid_t __user *, grouplist)
{
struct group_info *group_info;
int retval;
if (!may_setgroups())
return -EPERM;
if ((unsigned)gidsetsize > NGROUPS_MAX)
return -EINVAL;
group_info = groups_alloc(gidsetsize);
if (!group_info)
return -ENOMEM;
retval = groups_from_user(group_info, grouplist);
if (retval) {
put_group_info(group_info);
return retval;
}
retval = set_current_groups(group_info);
put_group_info(group_info);
return retval;
}
/*
* Check whether we're fsgid/egid or in the supplemental group..
*/
int in_group_p(kgid_t grp)
{
const struct cred *cred = current_cred();
int retval = 1;
if (!gid_eq(grp, cred->fsgid))
retval = groups_search(cred->group_info, grp);
return retval;
}
EXPORT_SYMBOL(in_group_p);
int in_egroup_p(kgid_t grp)
{
const struct cred *cred = current_cred();
int retval = 1;
if (!gid_eq(grp, cred->egid))
retval = groups_search(cred->group_info, grp);
return retval;
}
EXPORT_SYMBOL(in_egroup_p);