OpenCloudOS-Kernel/lib/idr.c

493 lines
14 KiB
C
Raw Normal View History

#include <linux/bitmap.h>
#include <linux/export.h>
#include <linux/idr.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
DEFINE_PER_CPU(struct ida_bitmap *, ida_bitmap);
static DEFINE_SPINLOCK(simple_ida_lock);
int idr_alloc_cmn(struct idr *idr, void *ptr, unsigned long *index,
unsigned long start, unsigned long end, gfp_t gfp,
bool ext)
idr: implement idr_preload[_end]() and idr_alloc() The current idr interface is very cumbersome. * For all allocations, two function calls - idr_pre_get() and idr_get_new*() - should be made. * idr_pre_get() doesn't guarantee that the following idr_get_new*() will not fail from memory shortage. If idr_get_new*() returns -EAGAIN, the caller is expected to retry pre_get and allocation. * idr_get_new*() can't enforce upper limit. Upper limit can only be enforced by allocating and then freeing if above limit. * idr_layer buffer is unnecessarily per-idr. Each idr ends up keeping around MAX_IDR_FREE idr_layers. The memory consumed per idr is under two pages but it makes it difficult to make idr_layer larger. This patch implements the following new set of allocation functions. * idr_preload[_end]() - Similar to radix preload but doesn't fail. The first idr_alloc() inside preload section can be treated as if it were called with @gfp_mask used for idr_preload(). * idr_alloc() - Allocate an ID w/ lower and upper limits. Takes @gfp_flags and can be used w/o preloading. When used inside preloaded section, the allocation mask of preloading can be assumed. If idr_alloc() can be called from a context which allows sufficiently relaxed @gfp_mask, it can be used by itself. If, for example, idr_alloc() is called inside spinlock protected region, preloading can be used like the following. idr_preload(GFP_KERNEL); spin_lock(lock); id = idr_alloc(idr, ptr, start, end, GFP_NOWAIT); spin_unlock(lock); idr_preload_end(); if (id < 0) error; which is much simpler and less error-prone than idr_pre_get and idr_get_new*() loop. The new interface uses per-pcu idr_layer buffer and thus the number of idr's in the system doesn't affect the amount of memory used for preloading. idr_layer_alloc() is introduced to handle idr_layer allocations for both old and new ID allocation paths. This is a bit hairy now but the new interface is expected to replace the old and the internal implementation eventually will become simpler. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Rusty Russell <rusty@rustcorp.com.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-28 09:03:55 +08:00
{
struct radix_tree_iter iter;
void __rcu **slot;
idr: implement idr_preload[_end]() and idr_alloc() The current idr interface is very cumbersome. * For all allocations, two function calls - idr_pre_get() and idr_get_new*() - should be made. * idr_pre_get() doesn't guarantee that the following idr_get_new*() will not fail from memory shortage. If idr_get_new*() returns -EAGAIN, the caller is expected to retry pre_get and allocation. * idr_get_new*() can't enforce upper limit. Upper limit can only be enforced by allocating and then freeing if above limit. * idr_layer buffer is unnecessarily per-idr. Each idr ends up keeping around MAX_IDR_FREE idr_layers. The memory consumed per idr is under two pages but it makes it difficult to make idr_layer larger. This patch implements the following new set of allocation functions. * idr_preload[_end]() - Similar to radix preload but doesn't fail. The first idr_alloc() inside preload section can be treated as if it were called with @gfp_mask used for idr_preload(). * idr_alloc() - Allocate an ID w/ lower and upper limits. Takes @gfp_flags and can be used w/o preloading. When used inside preloaded section, the allocation mask of preloading can be assumed. If idr_alloc() can be called from a context which allows sufficiently relaxed @gfp_mask, it can be used by itself. If, for example, idr_alloc() is called inside spinlock protected region, preloading can be used like the following. idr_preload(GFP_KERNEL); spin_lock(lock); id = idr_alloc(idr, ptr, start, end, GFP_NOWAIT); spin_unlock(lock); idr_preload_end(); if (id < 0) error; which is much simpler and less error-prone than idr_pre_get and idr_get_new*() loop. The new interface uses per-pcu idr_layer buffer and thus the number of idr's in the system doesn't affect the amount of memory used for preloading. idr_layer_alloc() is introduced to handle idr_layer allocations for both old and new ID allocation paths. This is a bit hairy now but the new interface is expected to replace the old and the internal implementation eventually will become simpler. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Rusty Russell <rusty@rustcorp.com.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-28 09:03:55 +08:00
if (WARN_ON_ONCE(radix_tree_is_internal_node(ptr)))
return -EINVAL;
idr: implement idr_preload[_end]() and idr_alloc() The current idr interface is very cumbersome. * For all allocations, two function calls - idr_pre_get() and idr_get_new*() - should be made. * idr_pre_get() doesn't guarantee that the following idr_get_new*() will not fail from memory shortage. If idr_get_new*() returns -EAGAIN, the caller is expected to retry pre_get and allocation. * idr_get_new*() can't enforce upper limit. Upper limit can only be enforced by allocating and then freeing if above limit. * idr_layer buffer is unnecessarily per-idr. Each idr ends up keeping around MAX_IDR_FREE idr_layers. The memory consumed per idr is under two pages but it makes it difficult to make idr_layer larger. This patch implements the following new set of allocation functions. * idr_preload[_end]() - Similar to radix preload but doesn't fail. The first idr_alloc() inside preload section can be treated as if it were called with @gfp_mask used for idr_preload(). * idr_alloc() - Allocate an ID w/ lower and upper limits. Takes @gfp_flags and can be used w/o preloading. When used inside preloaded section, the allocation mask of preloading can be assumed. If idr_alloc() can be called from a context which allows sufficiently relaxed @gfp_mask, it can be used by itself. If, for example, idr_alloc() is called inside spinlock protected region, preloading can be used like the following. idr_preload(GFP_KERNEL); spin_lock(lock); id = idr_alloc(idr, ptr, start, end, GFP_NOWAIT); spin_unlock(lock); idr_preload_end(); if (id < 0) error; which is much simpler and less error-prone than idr_pre_get and idr_get_new*() loop. The new interface uses per-pcu idr_layer buffer and thus the number of idr's in the system doesn't affect the amount of memory used for preloading. idr_layer_alloc() is introduced to handle idr_layer allocations for both old and new ID allocation paths. This is a bit hairy now but the new interface is expected to replace the old and the internal implementation eventually will become simpler. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Rusty Russell <rusty@rustcorp.com.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-28 09:03:55 +08:00
radix_tree_iter_init(&iter, start);
if (ext)
slot = idr_get_free_ext(&idr->idr_rt, &iter, gfp, end);
else
slot = idr_get_free(&idr->idr_rt, &iter, gfp, end);
if (IS_ERR(slot))
return PTR_ERR(slot);
idr: implement idr_preload[_end]() and idr_alloc() The current idr interface is very cumbersome. * For all allocations, two function calls - idr_pre_get() and idr_get_new*() - should be made. * idr_pre_get() doesn't guarantee that the following idr_get_new*() will not fail from memory shortage. If idr_get_new*() returns -EAGAIN, the caller is expected to retry pre_get and allocation. * idr_get_new*() can't enforce upper limit. Upper limit can only be enforced by allocating and then freeing if above limit. * idr_layer buffer is unnecessarily per-idr. Each idr ends up keeping around MAX_IDR_FREE idr_layers. The memory consumed per idr is under two pages but it makes it difficult to make idr_layer larger. This patch implements the following new set of allocation functions. * idr_preload[_end]() - Similar to radix preload but doesn't fail. The first idr_alloc() inside preload section can be treated as if it were called with @gfp_mask used for idr_preload(). * idr_alloc() - Allocate an ID w/ lower and upper limits. Takes @gfp_flags and can be used w/o preloading. When used inside preloaded section, the allocation mask of preloading can be assumed. If idr_alloc() can be called from a context which allows sufficiently relaxed @gfp_mask, it can be used by itself. If, for example, idr_alloc() is called inside spinlock protected region, preloading can be used like the following. idr_preload(GFP_KERNEL); spin_lock(lock); id = idr_alloc(idr, ptr, start, end, GFP_NOWAIT); spin_unlock(lock); idr_preload_end(); if (id < 0) error; which is much simpler and less error-prone than idr_pre_get and idr_get_new*() loop. The new interface uses per-pcu idr_layer buffer and thus the number of idr's in the system doesn't affect the amount of memory used for preloading. idr_layer_alloc() is introduced to handle idr_layer allocations for both old and new ID allocation paths. This is a bit hairy now but the new interface is expected to replace the old and the internal implementation eventually will become simpler. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Rusty Russell <rusty@rustcorp.com.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-28 09:03:55 +08:00
radix_tree_iter_replace(&idr->idr_rt, &iter, slot, ptr);
radix_tree_iter_tag_clear(&idr->idr_rt, &iter, IDR_FREE);
if (index)
*index = iter.index;
return 0;
idr: implement idr_preload[_end]() and idr_alloc() The current idr interface is very cumbersome. * For all allocations, two function calls - idr_pre_get() and idr_get_new*() - should be made. * idr_pre_get() doesn't guarantee that the following idr_get_new*() will not fail from memory shortage. If idr_get_new*() returns -EAGAIN, the caller is expected to retry pre_get and allocation. * idr_get_new*() can't enforce upper limit. Upper limit can only be enforced by allocating and then freeing if above limit. * idr_layer buffer is unnecessarily per-idr. Each idr ends up keeping around MAX_IDR_FREE idr_layers. The memory consumed per idr is under two pages but it makes it difficult to make idr_layer larger. This patch implements the following new set of allocation functions. * idr_preload[_end]() - Similar to radix preload but doesn't fail. The first idr_alloc() inside preload section can be treated as if it were called with @gfp_mask used for idr_preload(). * idr_alloc() - Allocate an ID w/ lower and upper limits. Takes @gfp_flags and can be used w/o preloading. When used inside preloaded section, the allocation mask of preloading can be assumed. If idr_alloc() can be called from a context which allows sufficiently relaxed @gfp_mask, it can be used by itself. If, for example, idr_alloc() is called inside spinlock protected region, preloading can be used like the following. idr_preload(GFP_KERNEL); spin_lock(lock); id = idr_alloc(idr, ptr, start, end, GFP_NOWAIT); spin_unlock(lock); idr_preload_end(); if (id < 0) error; which is much simpler and less error-prone than idr_pre_get and idr_get_new*() loop. The new interface uses per-pcu idr_layer buffer and thus the number of idr's in the system doesn't affect the amount of memory used for preloading. idr_layer_alloc() is introduced to handle idr_layer allocations for both old and new ID allocation paths. This is a bit hairy now but the new interface is expected to replace the old and the internal implementation eventually will become simpler. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Rusty Russell <rusty@rustcorp.com.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-28 09:03:55 +08:00
}
EXPORT_SYMBOL_GPL(idr_alloc_cmn);
idr: implement idr_preload[_end]() and idr_alloc() The current idr interface is very cumbersome. * For all allocations, two function calls - idr_pre_get() and idr_get_new*() - should be made. * idr_pre_get() doesn't guarantee that the following idr_get_new*() will not fail from memory shortage. If idr_get_new*() returns -EAGAIN, the caller is expected to retry pre_get and allocation. * idr_get_new*() can't enforce upper limit. Upper limit can only be enforced by allocating and then freeing if above limit. * idr_layer buffer is unnecessarily per-idr. Each idr ends up keeping around MAX_IDR_FREE idr_layers. The memory consumed per idr is under two pages but it makes it difficult to make idr_layer larger. This patch implements the following new set of allocation functions. * idr_preload[_end]() - Similar to radix preload but doesn't fail. The first idr_alloc() inside preload section can be treated as if it were called with @gfp_mask used for idr_preload(). * idr_alloc() - Allocate an ID w/ lower and upper limits. Takes @gfp_flags and can be used w/o preloading. When used inside preloaded section, the allocation mask of preloading can be assumed. If idr_alloc() can be called from a context which allows sufficiently relaxed @gfp_mask, it can be used by itself. If, for example, idr_alloc() is called inside spinlock protected region, preloading can be used like the following. idr_preload(GFP_KERNEL); spin_lock(lock); id = idr_alloc(idr, ptr, start, end, GFP_NOWAIT); spin_unlock(lock); idr_preload_end(); if (id < 0) error; which is much simpler and less error-prone than idr_pre_get and idr_get_new*() loop. The new interface uses per-pcu idr_layer buffer and thus the number of idr's in the system doesn't affect the amount of memory used for preloading. idr_layer_alloc() is introduced to handle idr_layer allocations for both old and new ID allocation paths. This is a bit hairy now but the new interface is expected to replace the old and the internal implementation eventually will become simpler. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Rusty Russell <rusty@rustcorp.com.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-28 09:03:55 +08:00
idr: introduce idr_alloc_cyclic() As Tejun points out, there are several users of the IDR facility that attempt to use it in a cyclic fashion. These users are likely to see -ENOSPC errors after the counter wraps one or more times however. This patchset adds a new idr_alloc_cyclic routine and converts several of these users to it. Many of these users are in obscure parts of the kernel, and I don't have a good way to test some of them. The change is pretty straightforward though, so hopefully it won't be an issue. There is one other cyclic user of idr_alloc that I didn't touch in ipc/util.c. That one is doing some strange stuff that I didn't quite understand, but it looks like it should probably be converted later somehow. This patch: Thus spake Tejun Heo: Ooh, BTW, the cyclic allocation is broken. It's prone to -ENOSPC after the first wraparound. There are several cyclic users in the kernel and I think it probably would be best to implement cyclic support in idr. This patch does that by adding new idr_alloc_cyclic function that such users in the kernel can use. With this, there's no need for a caller to keep track of the last value used as that's now tracked internally. This should prevent the ENOSPC problems that can hit when the "last allocated" counter exceeds INT_MAX. Later patches will convert existing cyclic users to the new interface. Signed-off-by: Jeff Layton <jlayton@redhat.com> Reviewed-by: Tejun Heo <tj@kernel.org> Cc: "David S. Miller" <davem@davemloft.net> Cc: "J. Bruce Fields" <bfields@fieldses.org> Cc: Eric Paris <eparis@parisplace.org> Cc: Jack Morgenstein <jackm@dev.mellanox.co.il> Cc: John McCutchan <john@johnmccutchan.com> Cc: Neil Horman <nhorman@tuxdriver.com> Cc: Or Gerlitz <ogerlitz@mellanox.com> Cc: Robert Love <rlove@rlove.org> Cc: Roland Dreier <roland@purestorage.com> Cc: Sridhar Samudrala <sri@us.ibm.com> Cc: Steve Wise <swise@opengridcomputing.com> Cc: Tom Tucker <tom@opengridcomputing.com> Cc: Vlad Yasevich <vyasevich@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-04-30 07:21:16 +08:00
/**
* idr_alloc_cyclic - allocate new idr entry in a cyclical fashion
* @idr: idr handle
idr: introduce idr_alloc_cyclic() As Tejun points out, there are several users of the IDR facility that attempt to use it in a cyclic fashion. These users are likely to see -ENOSPC errors after the counter wraps one or more times however. This patchset adds a new idr_alloc_cyclic routine and converts several of these users to it. Many of these users are in obscure parts of the kernel, and I don't have a good way to test some of them. The change is pretty straightforward though, so hopefully it won't be an issue. There is one other cyclic user of idr_alloc that I didn't touch in ipc/util.c. That one is doing some strange stuff that I didn't quite understand, but it looks like it should probably be converted later somehow. This patch: Thus spake Tejun Heo: Ooh, BTW, the cyclic allocation is broken. It's prone to -ENOSPC after the first wraparound. There are several cyclic users in the kernel and I think it probably would be best to implement cyclic support in idr. This patch does that by adding new idr_alloc_cyclic function that such users in the kernel can use. With this, there's no need for a caller to keep track of the last value used as that's now tracked internally. This should prevent the ENOSPC problems that can hit when the "last allocated" counter exceeds INT_MAX. Later patches will convert existing cyclic users to the new interface. Signed-off-by: Jeff Layton <jlayton@redhat.com> Reviewed-by: Tejun Heo <tj@kernel.org> Cc: "David S. Miller" <davem@davemloft.net> Cc: "J. Bruce Fields" <bfields@fieldses.org> Cc: Eric Paris <eparis@parisplace.org> Cc: Jack Morgenstein <jackm@dev.mellanox.co.il> Cc: John McCutchan <john@johnmccutchan.com> Cc: Neil Horman <nhorman@tuxdriver.com> Cc: Or Gerlitz <ogerlitz@mellanox.com> Cc: Robert Love <rlove@rlove.org> Cc: Roland Dreier <roland@purestorage.com> Cc: Sridhar Samudrala <sri@us.ibm.com> Cc: Steve Wise <swise@opengridcomputing.com> Cc: Tom Tucker <tom@opengridcomputing.com> Cc: Vlad Yasevich <vyasevich@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-04-30 07:21:16 +08:00
* @ptr: pointer to be associated with the new id
* @start: the minimum id (inclusive)
* @end: the maximum id (exclusive)
* @gfp: memory allocation flags
*
* Allocates an ID larger than the last ID allocated if one is available.
* If not, it will attempt to allocate the smallest ID that is larger or
* equal to @start.
*/
int idr_alloc_cyclic(struct idr *idr, void *ptr, int start, int end, gfp_t gfp)
{
int id, curr = idr->idr_next;
if (curr < start)
curr = start;
idr: remove MAX_IDR_MASK and move left MAX_IDR_* into idr.c MAX_IDR_MASK is another weirdness in the idr interface. As idr covers whole positive integer range, it's defined as 0x7fffffff or INT_MAX. Its usage in idr_find(), idr_replace() and idr_remove() is bizarre. They basically mask off the sign bit and operate on the rest, so if the caller, by accident, passes in a negative number, the sign bit will be masked off and the remaining part will be used as if that was the input, which is worse than crashing. The constant is visible in idr.h and there are several users in the kernel. * drivers/i2c/i2c-core.c:i2c_add_numbered_adapter() Basically used to test if adap->nr is a negative number which isn't -1 and returns -EINVAL if so. idr_alloc() already has negative @start checking (w/ WARN_ON_ONCE), so this can go away. * drivers/infiniband/core/cm.c:cm_alloc_id() drivers/infiniband/hw/mlx4/cm.c:id_map_alloc() Used to wrap cyclic @start. Can be replaced with max(next, 0). Note that this type of cyclic allocation using idr is buggy. These are prone to spurious -ENOSPC failure after the first wraparound. * fs/super.c:get_anon_bdev() The ID allocated from ida is masked off before being tested whether it's inside valid range. ida allocated ID can never be a negative number and the masking is unnecessary. Update idr_*() functions to fail with -EINVAL when negative @id is specified and update other MAX_IDR_MASK users as described above. This leaves MAX_IDR_MASK without any user, remove it and relocate other MAX_IDR_* constants to lib/idr.c. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Jean Delvare <khali@linux-fr.org> Cc: Roland Dreier <roland@kernel.org> Cc: Sean Hefty <sean.hefty@intel.com> Cc: Hal Rosenstock <hal.rosenstock@gmail.com> Cc: "Marciniszyn, Mike" <mike.marciniszyn@intel.com> Cc: Jack Morgenstein <jackm@dev.mellanox.co.il> Cc: Or Gerlitz <ogerlitz@mellanox.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Acked-by: Wolfram Sang <wolfram@the-dreams.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-28 09:05:04 +08:00
id = idr_alloc(idr, ptr, curr, end, gfp);
if ((id == -ENOSPC) && (curr > start))
id = idr_alloc(idr, ptr, start, curr, gfp);
if (id >= 0)
idr->idr_next = id + 1U;
return id;
}
EXPORT_SYMBOL(idr_alloc_cyclic);
/**
* idr_for_each - iterate through all stored pointers
* @idr: idr handle
* @fn: function to be called for each pointer
* @data: data passed to callback function
*
* The callback function will be called for each entry in @idr, passing
* the id, the pointer and the data pointer passed to this function.
*
* If @fn returns anything other than %0, the iteration stops and that
* value is returned from this function.
*
* idr_for_each() can be called concurrently with idr_alloc() and
* idr_remove() if protected by RCU. Newly added entries may not be
* seen and deleted entries may be seen, but adding and removing entries
* will not cause other entries to be skipped, nor spurious ones to be seen.
*/
int idr_for_each(const struct idr *idr,
int (*fn)(int id, void *p, void *data), void *data)
{
struct radix_tree_iter iter;
void __rcu **slot;
radix_tree_for_each_slot(slot, &idr->idr_rt, &iter, 0) {
int ret = fn(iter.index, rcu_dereference_raw(*slot), data);
if (ret)
return ret;
}
return 0;
}
EXPORT_SYMBOL(idr_for_each);
cgroup: CSS ID support Patch for Per-CSS(Cgroup Subsys State) ID and private hierarchy code. This patch attaches unique ID to each css and provides following. - css_lookup(subsys, id) returns pointer to struct cgroup_subysys_state of id. - css_get_next(subsys, id, rootid, depth, foundid) returns the next css under "root" by scanning When cgroup_subsys->use_id is set, an id for css is maintained. The cgroup framework only parepares - css_id of root css for subsys - id is automatically attached at creation of css. - id is *not* freed automatically. Because the cgroup framework don't know lifetime of cgroup_subsys_state. free_css_id() function is provided. This must be called by subsys. There are several reasons to develop this. - Saving space .... For example, memcg's swap_cgroup is array of pointers to cgroup. But it is not necessary to be very fast. By replacing pointers(8bytes per ent) to ID (2byes per ent), we can reduce much amount of memory usage. - Scanning without lock. CSS_ID provides "scan id under this ROOT" function. By this, scanning css under root can be written without locks. ex) do { rcu_read_lock(); next = cgroup_get_next(subsys, id, root, &found); /* check sanity of next here */ css_tryget(); rcu_read_unlock(); id = found + 1 } while(...) Characteristics: - Each css has unique ID under subsys. - Lifetime of ID is controlled by subsys. - css ID contains "ID" and "Depth in hierarchy" and stack of hierarchy - Allowed ID is 1-65535, ID 0 is UNUSED ID. Design Choices: - scan-by-ID v.s. scan-by-tree-walk. As /proc's pid scan does, scan-by-ID is robust when scanning is done by following kind of routine. scan -> rest a while(release a lock) -> conitunue from interrupted memcg's hierarchical reclaim does this. - When subsys->use_id is set, # of css in the system is limited to 65535. [bharata@linux.vnet.ibm.com: remove rcu_read_lock() from css_get_next()] Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Acked-by: Paul Menage <menage@google.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Balbir Singh <balbir@in.ibm.com> Cc: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: Bharata B Rao <bharata@linux.vnet.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-03 07:57:25 +08:00
/**
* idr_get_next - Find next populated entry
* @idr: idr handle
* @nextid: Pointer to lowest possible ID to return
*
* Returns the next populated entry in the tree with an ID greater than
* or equal to the value pointed to by @nextid. On exit, @nextid is updated
* to the ID of the found value. To use in a loop, the value pointed to by
* nextid must be incremented by the user.
cgroup: CSS ID support Patch for Per-CSS(Cgroup Subsys State) ID and private hierarchy code. This patch attaches unique ID to each css and provides following. - css_lookup(subsys, id) returns pointer to struct cgroup_subysys_state of id. - css_get_next(subsys, id, rootid, depth, foundid) returns the next css under "root" by scanning When cgroup_subsys->use_id is set, an id for css is maintained. The cgroup framework only parepares - css_id of root css for subsys - id is automatically attached at creation of css. - id is *not* freed automatically. Because the cgroup framework don't know lifetime of cgroup_subsys_state. free_css_id() function is provided. This must be called by subsys. There are several reasons to develop this. - Saving space .... For example, memcg's swap_cgroup is array of pointers to cgroup. But it is not necessary to be very fast. By replacing pointers(8bytes per ent) to ID (2byes per ent), we can reduce much amount of memory usage. - Scanning without lock. CSS_ID provides "scan id under this ROOT" function. By this, scanning css under root can be written without locks. ex) do { rcu_read_lock(); next = cgroup_get_next(subsys, id, root, &found); /* check sanity of next here */ css_tryget(); rcu_read_unlock(); id = found + 1 } while(...) Characteristics: - Each css has unique ID under subsys. - Lifetime of ID is controlled by subsys. - css ID contains "ID" and "Depth in hierarchy" and stack of hierarchy - Allowed ID is 1-65535, ID 0 is UNUSED ID. Design Choices: - scan-by-ID v.s. scan-by-tree-walk. As /proc's pid scan does, scan-by-ID is robust when scanning is done by following kind of routine. scan -> rest a while(release a lock) -> conitunue from interrupted memcg's hierarchical reclaim does this. - When subsys->use_id is set, # of css in the system is limited to 65535. [bharata@linux.vnet.ibm.com: remove rcu_read_lock() from css_get_next()] Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Acked-by: Paul Menage <menage@google.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Balbir Singh <balbir@in.ibm.com> Cc: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: Bharata B Rao <bharata@linux.vnet.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-03 07:57:25 +08:00
*/
void *idr_get_next(struct idr *idr, int *nextid)
cgroup: CSS ID support Patch for Per-CSS(Cgroup Subsys State) ID and private hierarchy code. This patch attaches unique ID to each css and provides following. - css_lookup(subsys, id) returns pointer to struct cgroup_subysys_state of id. - css_get_next(subsys, id, rootid, depth, foundid) returns the next css under "root" by scanning When cgroup_subsys->use_id is set, an id for css is maintained. The cgroup framework only parepares - css_id of root css for subsys - id is automatically attached at creation of css. - id is *not* freed automatically. Because the cgroup framework don't know lifetime of cgroup_subsys_state. free_css_id() function is provided. This must be called by subsys. There are several reasons to develop this. - Saving space .... For example, memcg's swap_cgroup is array of pointers to cgroup. But it is not necessary to be very fast. By replacing pointers(8bytes per ent) to ID (2byes per ent), we can reduce much amount of memory usage. - Scanning without lock. CSS_ID provides "scan id under this ROOT" function. By this, scanning css under root can be written without locks. ex) do { rcu_read_lock(); next = cgroup_get_next(subsys, id, root, &found); /* check sanity of next here */ css_tryget(); rcu_read_unlock(); id = found + 1 } while(...) Characteristics: - Each css has unique ID under subsys. - Lifetime of ID is controlled by subsys. - css ID contains "ID" and "Depth in hierarchy" and stack of hierarchy - Allowed ID is 1-65535, ID 0 is UNUSED ID. Design Choices: - scan-by-ID v.s. scan-by-tree-walk. As /proc's pid scan does, scan-by-ID is robust when scanning is done by following kind of routine. scan -> rest a while(release a lock) -> conitunue from interrupted memcg's hierarchical reclaim does this. - When subsys->use_id is set, # of css in the system is limited to 65535. [bharata@linux.vnet.ibm.com: remove rcu_read_lock() from css_get_next()] Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Acked-by: Paul Menage <menage@google.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Balbir Singh <balbir@in.ibm.com> Cc: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: Bharata B Rao <bharata@linux.vnet.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-03 07:57:25 +08:00
{
struct radix_tree_iter iter;
void __rcu **slot;
cgroup: CSS ID support Patch for Per-CSS(Cgroup Subsys State) ID and private hierarchy code. This patch attaches unique ID to each css and provides following. - css_lookup(subsys, id) returns pointer to struct cgroup_subysys_state of id. - css_get_next(subsys, id, rootid, depth, foundid) returns the next css under "root" by scanning When cgroup_subsys->use_id is set, an id for css is maintained. The cgroup framework only parepares - css_id of root css for subsys - id is automatically attached at creation of css. - id is *not* freed automatically. Because the cgroup framework don't know lifetime of cgroup_subsys_state. free_css_id() function is provided. This must be called by subsys. There are several reasons to develop this. - Saving space .... For example, memcg's swap_cgroup is array of pointers to cgroup. But it is not necessary to be very fast. By replacing pointers(8bytes per ent) to ID (2byes per ent), we can reduce much amount of memory usage. - Scanning without lock. CSS_ID provides "scan id under this ROOT" function. By this, scanning css under root can be written without locks. ex) do { rcu_read_lock(); next = cgroup_get_next(subsys, id, root, &found); /* check sanity of next here */ css_tryget(); rcu_read_unlock(); id = found + 1 } while(...) Characteristics: - Each css has unique ID under subsys. - Lifetime of ID is controlled by subsys. - css ID contains "ID" and "Depth in hierarchy" and stack of hierarchy - Allowed ID is 1-65535, ID 0 is UNUSED ID. Design Choices: - scan-by-ID v.s. scan-by-tree-walk. As /proc's pid scan does, scan-by-ID is robust when scanning is done by following kind of routine. scan -> rest a while(release a lock) -> conitunue from interrupted memcg's hierarchical reclaim does this. - When subsys->use_id is set, # of css in the system is limited to 65535. [bharata@linux.vnet.ibm.com: remove rcu_read_lock() from css_get_next()] Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Acked-by: Paul Menage <menage@google.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Balbir Singh <balbir@in.ibm.com> Cc: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: Bharata B Rao <bharata@linux.vnet.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-03 07:57:25 +08:00
slot = radix_tree_iter_find(&idr->idr_rt, &iter, *nextid);
if (!slot)
cgroup: CSS ID support Patch for Per-CSS(Cgroup Subsys State) ID and private hierarchy code. This patch attaches unique ID to each css and provides following. - css_lookup(subsys, id) returns pointer to struct cgroup_subysys_state of id. - css_get_next(subsys, id, rootid, depth, foundid) returns the next css under "root" by scanning When cgroup_subsys->use_id is set, an id for css is maintained. The cgroup framework only parepares - css_id of root css for subsys - id is automatically attached at creation of css. - id is *not* freed automatically. Because the cgroup framework don't know lifetime of cgroup_subsys_state. free_css_id() function is provided. This must be called by subsys. There are several reasons to develop this. - Saving space .... For example, memcg's swap_cgroup is array of pointers to cgroup. But it is not necessary to be very fast. By replacing pointers(8bytes per ent) to ID (2byes per ent), we can reduce much amount of memory usage. - Scanning without lock. CSS_ID provides "scan id under this ROOT" function. By this, scanning css under root can be written without locks. ex) do { rcu_read_lock(); next = cgroup_get_next(subsys, id, root, &found); /* check sanity of next here */ css_tryget(); rcu_read_unlock(); id = found + 1 } while(...) Characteristics: - Each css has unique ID under subsys. - Lifetime of ID is controlled by subsys. - css ID contains "ID" and "Depth in hierarchy" and stack of hierarchy - Allowed ID is 1-65535, ID 0 is UNUSED ID. Design Choices: - scan-by-ID v.s. scan-by-tree-walk. As /proc's pid scan does, scan-by-ID is robust when scanning is done by following kind of routine. scan -> rest a while(release a lock) -> conitunue from interrupted memcg's hierarchical reclaim does this. - When subsys->use_id is set, # of css in the system is limited to 65535. [bharata@linux.vnet.ibm.com: remove rcu_read_lock() from css_get_next()] Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Acked-by: Paul Menage <menage@google.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Balbir Singh <balbir@in.ibm.com> Cc: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: Bharata B Rao <bharata@linux.vnet.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-03 07:57:25 +08:00
return NULL;
*nextid = iter.index;
return rcu_dereference_raw(*slot);
cgroup: CSS ID support Patch for Per-CSS(Cgroup Subsys State) ID and private hierarchy code. This patch attaches unique ID to each css and provides following. - css_lookup(subsys, id) returns pointer to struct cgroup_subysys_state of id. - css_get_next(subsys, id, rootid, depth, foundid) returns the next css under "root" by scanning When cgroup_subsys->use_id is set, an id for css is maintained. The cgroup framework only parepares - css_id of root css for subsys - id is automatically attached at creation of css. - id is *not* freed automatically. Because the cgroup framework don't know lifetime of cgroup_subsys_state. free_css_id() function is provided. This must be called by subsys. There are several reasons to develop this. - Saving space .... For example, memcg's swap_cgroup is array of pointers to cgroup. But it is not necessary to be very fast. By replacing pointers(8bytes per ent) to ID (2byes per ent), we can reduce much amount of memory usage. - Scanning without lock. CSS_ID provides "scan id under this ROOT" function. By this, scanning css under root can be written without locks. ex) do { rcu_read_lock(); next = cgroup_get_next(subsys, id, root, &found); /* check sanity of next here */ css_tryget(); rcu_read_unlock(); id = found + 1 } while(...) Characteristics: - Each css has unique ID under subsys. - Lifetime of ID is controlled by subsys. - css ID contains "ID" and "Depth in hierarchy" and stack of hierarchy - Allowed ID is 1-65535, ID 0 is UNUSED ID. Design Choices: - scan-by-ID v.s. scan-by-tree-walk. As /proc's pid scan does, scan-by-ID is robust when scanning is done by following kind of routine. scan -> rest a while(release a lock) -> conitunue from interrupted memcg's hierarchical reclaim does this. - When subsys->use_id is set, # of css in the system is limited to 65535. [bharata@linux.vnet.ibm.com: remove rcu_read_lock() from css_get_next()] Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Acked-by: Paul Menage <menage@google.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Balbir Singh <balbir@in.ibm.com> Cc: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: Bharata B Rao <bharata@linux.vnet.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-03 07:57:25 +08:00
}
EXPORT_SYMBOL(idr_get_next);
cgroup: CSS ID support Patch for Per-CSS(Cgroup Subsys State) ID and private hierarchy code. This patch attaches unique ID to each css and provides following. - css_lookup(subsys, id) returns pointer to struct cgroup_subysys_state of id. - css_get_next(subsys, id, rootid, depth, foundid) returns the next css under "root" by scanning When cgroup_subsys->use_id is set, an id for css is maintained. The cgroup framework only parepares - css_id of root css for subsys - id is automatically attached at creation of css. - id is *not* freed automatically. Because the cgroup framework don't know lifetime of cgroup_subsys_state. free_css_id() function is provided. This must be called by subsys. There are several reasons to develop this. - Saving space .... For example, memcg's swap_cgroup is array of pointers to cgroup. But it is not necessary to be very fast. By replacing pointers(8bytes per ent) to ID (2byes per ent), we can reduce much amount of memory usage. - Scanning without lock. CSS_ID provides "scan id under this ROOT" function. By this, scanning css under root can be written without locks. ex) do { rcu_read_lock(); next = cgroup_get_next(subsys, id, root, &found); /* check sanity of next here */ css_tryget(); rcu_read_unlock(); id = found + 1 } while(...) Characteristics: - Each css has unique ID under subsys. - Lifetime of ID is controlled by subsys. - css ID contains "ID" and "Depth in hierarchy" and stack of hierarchy - Allowed ID is 1-65535, ID 0 is UNUSED ID. Design Choices: - scan-by-ID v.s. scan-by-tree-walk. As /proc's pid scan does, scan-by-ID is robust when scanning is done by following kind of routine. scan -> rest a while(release a lock) -> conitunue from interrupted memcg's hierarchical reclaim does this. - When subsys->use_id is set, # of css in the system is limited to 65535. [bharata@linux.vnet.ibm.com: remove rcu_read_lock() from css_get_next()] Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Acked-by: Paul Menage <menage@google.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Balbir Singh <balbir@in.ibm.com> Cc: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: Bharata B Rao <bharata@linux.vnet.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-03 07:57:25 +08:00
void *idr_get_next_ext(struct idr *idr, unsigned long *nextid)
{
struct radix_tree_iter iter;
void __rcu **slot;
slot = radix_tree_iter_find(&idr->idr_rt, &iter, *nextid);
if (!slot)
return NULL;
*nextid = iter.index;
return rcu_dereference_raw(*slot);
}
EXPORT_SYMBOL(idr_get_next_ext);
/**
* idr_replace - replace pointer for given id
* @idr: idr handle
* @ptr: New pointer to associate with the ID
* @id: Lookup key
*
* Replace the pointer registered with an ID and return the old value.
* This function can be called under the RCU read lock concurrently with
* idr_alloc() and idr_remove() (as long as the ID being removed is not
* the one being replaced!).
*
* Returns: 0 on success. %-ENOENT indicates that @id was not found.
* %-EINVAL indicates that @id or @ptr were not valid.
*/
void *idr_replace(struct idr *idr, void *ptr, int id)
{
idr: remove WARN_ON_ONCE() when trying to replace negative ID IDR only supports non-negative IDs. There used to be a 'WARN_ON_ONCE(id < 0)' in idr_replace(), but it was intentionally removed by commit 2e1c9b286765 ("idr: remove WARN_ON_ONCE() on negative IDs"). Then it was added back by commit 0a835c4f090a ("Reimplement IDR and IDA using the radix tree"). However it seems that adding it back was a mistake, given that some users such as drm_gem_handle_delete() (DRM_IOCTL_GEM_CLOSE) pass in a value from userspace to idr_replace(), allowing the WARN_ON_ONCE to be triggered. drm_gem_handle_delete() actually just wants idr_replace() to return an error code if the ID is not allocated, including in the case where the ID is invalid (negative). So once again remove the bogus WARN_ON_ONCE(). This bug was found by syzkaller, which encountered the following warning: WARNING: CPU: 3 PID: 3008 at lib/idr.c:157 idr_replace+0x1d8/0x240 lib/idr.c:157 Kernel panic - not syncing: panic_on_warn set ... CPU: 3 PID: 3008 Comm: syzkaller218828 Not tainted 4.13.0-rc4-next-20170811 #2 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011 Call Trace: fixup_bug+0x40/0x90 arch/x86/kernel/traps.c:190 do_trap_no_signal arch/x86/kernel/traps.c:224 [inline] do_trap+0x260/0x390 arch/x86/kernel/traps.c:273 do_error_trap+0x120/0x390 arch/x86/kernel/traps.c:310 do_invalid_op+0x1b/0x20 arch/x86/kernel/traps.c:323 invalid_op+0x1e/0x30 arch/x86/entry/entry_64.S:930 RIP: 0010:idr_replace+0x1d8/0x240 lib/idr.c:157 RSP: 0018:ffff8800394bf9f8 EFLAGS: 00010297 RAX: ffff88003c6c60c0 RBX: 1ffff10007297f43 RCX: 0000000000000000 RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff8800394bfa78 RBP: ffff8800394bfae0 R08: ffffffff82856487 R09: 0000000000000000 R10: ffff8800394bf9a8 R11: ffff88006c8bae28 R12: ffffffffffffffff R13: ffff8800394bfab8 R14: dffffc0000000000 R15: ffff8800394bfbc8 drm_gem_handle_delete+0x33/0xa0 drivers/gpu/drm/drm_gem.c:297 drm_gem_close_ioctl+0xa1/0xe0 drivers/gpu/drm/drm_gem.c:671 drm_ioctl_kernel+0x1e7/0x2e0 drivers/gpu/drm/drm_ioctl.c:729 drm_ioctl+0x72e/0xa50 drivers/gpu/drm/drm_ioctl.c:825 vfs_ioctl fs/ioctl.c:45 [inline] do_vfs_ioctl+0x1b1/0x1520 fs/ioctl.c:685 SYSC_ioctl fs/ioctl.c:700 [inline] SyS_ioctl+0x8f/0xc0 fs/ioctl.c:691 entry_SYSCALL_64_fastpath+0x1f/0xbe Here is a C reproducer: #include <fcntl.h> #include <stddef.h> #include <stdint.h> #include <sys/ioctl.h> #include <drm/drm.h> int main(void) { int cardfd = open("/dev/dri/card0", O_RDONLY); ioctl(cardfd, DRM_IOCTL_GEM_CLOSE, &(struct drm_gem_close) { .handle = -1 } ); } Link: http://lkml.kernel.org/r/20170906235306.20534-1-ebiggers3@gmail.com Fixes: 0a835c4f090a ("Reimplement IDR and IDA using the radix tree") Signed-off-by: Eric Biggers <ebiggers@google.com> Acked-by: Tejun Heo <tj@kernel.org> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Matthew Wilcox <mawilcox@microsoft.com> Cc: <stable@vger.kernel.org> [v4.11+] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-14 07:28:11 +08:00
if (id < 0)
return ERR_PTR(-EINVAL);
return idr_replace_ext(idr, ptr, id);
}
EXPORT_SYMBOL(idr_replace);
void *idr_replace_ext(struct idr *idr, void *ptr, unsigned long id)
{
struct radix_tree_node *node;
void __rcu **slot = NULL;
void *entry;
if (WARN_ON_ONCE(radix_tree_is_internal_node(ptr)))
idr: remove MAX_IDR_MASK and move left MAX_IDR_* into idr.c MAX_IDR_MASK is another weirdness in the idr interface. As idr covers whole positive integer range, it's defined as 0x7fffffff or INT_MAX. Its usage in idr_find(), idr_replace() and idr_remove() is bizarre. They basically mask off the sign bit and operate on the rest, so if the caller, by accident, passes in a negative number, the sign bit will be masked off and the remaining part will be used as if that was the input, which is worse than crashing. The constant is visible in idr.h and there are several users in the kernel. * drivers/i2c/i2c-core.c:i2c_add_numbered_adapter() Basically used to test if adap->nr is a negative number which isn't -1 and returns -EINVAL if so. idr_alloc() already has negative @start checking (w/ WARN_ON_ONCE), so this can go away. * drivers/infiniband/core/cm.c:cm_alloc_id() drivers/infiniband/hw/mlx4/cm.c:id_map_alloc() Used to wrap cyclic @start. Can be replaced with max(next, 0). Note that this type of cyclic allocation using idr is buggy. These are prone to spurious -ENOSPC failure after the first wraparound. * fs/super.c:get_anon_bdev() The ID allocated from ida is masked off before being tested whether it's inside valid range. ida allocated ID can never be a negative number and the masking is unnecessary. Update idr_*() functions to fail with -EINVAL when negative @id is specified and update other MAX_IDR_MASK users as described above. This leaves MAX_IDR_MASK without any user, remove it and relocate other MAX_IDR_* constants to lib/idr.c. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Jean Delvare <khali@linux-fr.org> Cc: Roland Dreier <roland@kernel.org> Cc: Sean Hefty <sean.hefty@intel.com> Cc: Hal Rosenstock <hal.rosenstock@gmail.com> Cc: "Marciniszyn, Mike" <mike.marciniszyn@intel.com> Cc: Jack Morgenstein <jackm@dev.mellanox.co.il> Cc: Or Gerlitz <ogerlitz@mellanox.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Acked-by: Wolfram Sang <wolfram@the-dreams.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-28 09:05:04 +08:00
return ERR_PTR(-EINVAL);
entry = __radix_tree_lookup(&idr->idr_rt, id, &node, &slot);
if (!slot || radix_tree_tag_get(&idr->idr_rt, id, IDR_FREE))
return ERR_PTR(-ENOENT);
__radix_tree_replace(&idr->idr_rt, node, slot, ptr, NULL, NULL);
return entry;
}
EXPORT_SYMBOL(idr_replace_ext);
/**
* DOC: IDA description
*
* The IDA is an ID allocator which does not provide the ability to
* associate an ID with a pointer. As such, it only needs to store one
* bit per ID, and so is more space efficient than an IDR. To use an IDA,
* define it using DEFINE_IDA() (or embed a &struct ida in a data structure,
* then initialise it using ida_init()). To allocate a new ID, call
* ida_simple_get(). To free an ID, call ida_simple_remove().
*
* If you have more complex locking requirements, use a loop around
* ida_pre_get() and ida_get_new() to allocate a new ID. Then use
* ida_remove() to free an ID. You must make sure that ida_get_new() and
* ida_remove() cannot be called at the same time as each other for the
* same IDA.
*
* You can also use ida_get_new_above() if you need an ID to be allocated
* above a particular number. ida_destroy() can be used to dispose of an
* IDA without needing to free the individual IDs in it. You can use
* ida_is_empty() to find out whether the IDA has any IDs currently allocated.
*
* IDs are currently limited to the range [0-INT_MAX]. If this is an awkward
* limitation, it should be quite straightforward to raise the maximum.
*/
/*
* Developer's notes:
*
* The IDA uses the functionality provided by the IDR & radix tree to store
* bitmaps in each entry. The IDR_FREE tag means there is at least one bit
* free, unlike the IDR where it means at least one entry is free.
*
* I considered telling the radix tree that each slot is an order-10 node
* and storing the bit numbers in the radix tree, but the radix tree can't
* allow a single multiorder entry at index 0, which would significantly
* increase memory consumption for the IDA. So instead we divide the index
* by the number of bits in the leaf bitmap before doing a radix tree lookup.
*
* As an optimisation, if there are only a few low bits set in any given
* leaf, instead of allocating a 128-byte bitmap, we use the 'exceptional
* entry' functionality of the radix tree to store BITS_PER_LONG - 2 bits
* directly in the entry. By being really tricksy, we could store
* BITS_PER_LONG - 1 bits, but there're diminishing returns after optimising
* for 0-3 allocated IDs.
*
* We allow the radix tree 'exceptional' count to get out of date. Nothing
* in the IDA nor the radix tree code checks it. If it becomes important
* to maintain an accurate exceptional count, switch the rcu_assign_pointer()
* calls to radix_tree_iter_replace() which will correct the exceptional
* count.
*
* The IDA always requires a lock to alloc/free. If we add a 'test_bit'
* equivalent, it will still need locking. Going to RCU lookup would require
* using RCU to free bitmaps, and that's not trivial without embedding an
* RCU head in the bitmap, which adds a 2-pointer overhead to each 128-byte
* bitmap, which is excessive.
*/
#define IDA_MAX (0x80000000U / IDA_BITMAP_BITS)
/**
* ida_get_new_above - allocate new ID above or equal to a start id
* @ida: ida handle
* @start: id to start search at
* @id: pointer to the allocated handle
*
* Allocate new ID above or equal to @start. It should be called
* with any required locks to ensure that concurrent calls to
* ida_get_new_above() / ida_get_new() / ida_remove() are not allowed.
* Consider using ida_simple_get() if you do not have complex locking
* requirements.
*
* If memory is required, it will return %-EAGAIN, you should unlock
* and go back to the ida_pre_get() call. If the ida is full, it will
* return %-ENOSPC. On success, it will return 0.
*
* @id returns a value in the range @start ... %0x7fffffff.
*/
int ida_get_new_above(struct ida *ida, int start, int *id)
{
struct radix_tree_root *root = &ida->ida_rt;
void __rcu **slot;
struct radix_tree_iter iter;
struct ida_bitmap *bitmap;
unsigned long index;
unsigned bit, ebit;
int new;
index = start / IDA_BITMAP_BITS;
bit = start % IDA_BITMAP_BITS;
ebit = bit + RADIX_TREE_EXCEPTIONAL_SHIFT;
slot = radix_tree_iter_init(&iter, index);
for (;;) {
if (slot)
slot = radix_tree_next_slot(slot, &iter,
RADIX_TREE_ITER_TAGGED);
if (!slot) {
slot = idr_get_free(root, &iter, GFP_NOWAIT, IDA_MAX);
if (IS_ERR(slot)) {
if (slot == ERR_PTR(-ENOMEM))
return -EAGAIN;
return PTR_ERR(slot);
}
}
if (iter.index > index) {
bit = 0;
ebit = RADIX_TREE_EXCEPTIONAL_SHIFT;
}
new = iter.index * IDA_BITMAP_BITS;
bitmap = rcu_dereference_raw(*slot);
if (radix_tree_exception(bitmap)) {
unsigned long tmp = (unsigned long)bitmap;
ebit = find_next_zero_bit(&tmp, BITS_PER_LONG, ebit);
if (ebit < BITS_PER_LONG) {
tmp |= 1UL << ebit;
rcu_assign_pointer(*slot, (void *)tmp);
*id = new + ebit - RADIX_TREE_EXCEPTIONAL_SHIFT;
return 0;
}
bitmap = this_cpu_xchg(ida_bitmap, NULL);
if (!bitmap)
return -EAGAIN;
memset(bitmap, 0, sizeof(*bitmap));
bitmap->bitmap[0] = tmp >> RADIX_TREE_EXCEPTIONAL_SHIFT;
rcu_assign_pointer(*slot, bitmap);
}
if (bitmap) {
bit = find_next_zero_bit(bitmap->bitmap,
IDA_BITMAP_BITS, bit);
new += bit;
if (new < 0)
return -ENOSPC;
if (bit == IDA_BITMAP_BITS)
continue;
__set_bit(bit, bitmap->bitmap);
if (bitmap_full(bitmap->bitmap, IDA_BITMAP_BITS))
radix_tree_iter_tag_clear(root, &iter,
IDR_FREE);
} else {
new += bit;
if (new < 0)
return -ENOSPC;
if (ebit < BITS_PER_LONG) {
bitmap = (void *)((1UL << ebit) |
RADIX_TREE_EXCEPTIONAL_ENTRY);
radix_tree_iter_replace(root, &iter, slot,
bitmap);
*id = new;
return 0;
}
bitmap = this_cpu_xchg(ida_bitmap, NULL);
if (!bitmap)
return -EAGAIN;
memset(bitmap, 0, sizeof(*bitmap));
__set_bit(bit, bitmap->bitmap);
radix_tree_iter_replace(root, &iter, slot, bitmap);
}
*id = new;
return 0;
}
}
EXPORT_SYMBOL(ida_get_new_above);
/**
* ida_remove - Free the given ID
* @ida: ida handle
* @id: ID to free
*
* This function should not be called at the same time as ida_get_new_above().
*/
void ida_remove(struct ida *ida, int id)
{
unsigned long index = id / IDA_BITMAP_BITS;
unsigned offset = id % IDA_BITMAP_BITS;
struct ida_bitmap *bitmap;
unsigned long *btmp;
struct radix_tree_iter iter;
void __rcu **slot;
slot = radix_tree_iter_lookup(&ida->ida_rt, &iter, index);
if (!slot)
goto err;
bitmap = rcu_dereference_raw(*slot);
if (radix_tree_exception(bitmap)) {
btmp = (unsigned long *)slot;
offset += RADIX_TREE_EXCEPTIONAL_SHIFT;
if (offset >= BITS_PER_LONG)
goto err;
} else {
btmp = bitmap->bitmap;
}
if (!test_bit(offset, btmp))
goto err;
__clear_bit(offset, btmp);
radix_tree_iter_tag_set(&ida->ida_rt, &iter, IDR_FREE);
if (radix_tree_exception(bitmap)) {
if (rcu_dereference_raw(*slot) ==
(void *)RADIX_TREE_EXCEPTIONAL_ENTRY)
radix_tree_iter_delete(&ida->ida_rt, &iter, slot);
} else if (bitmap_empty(btmp, IDA_BITMAP_BITS)) {
kfree(bitmap);
radix_tree_iter_delete(&ida->ida_rt, &iter, slot);
}
return;
err:
WARN(1, "ida_remove called for id=%d which is not allocated.\n", id);
}
EXPORT_SYMBOL(ida_remove);
/**
* ida_destroy - Free the contents of an ida
* @ida: ida handle
*
* Calling this function releases all resources associated with an IDA. When
* this call returns, the IDA is empty and can be reused or freed. The caller
* should not allow ida_remove() or ida_get_new_above() to be called at the
* same time.
*/
void ida_destroy(struct ida *ida)
{
struct radix_tree_iter iter;
void __rcu **slot;
radix_tree_for_each_slot(slot, &ida->ida_rt, &iter, 0) {
struct ida_bitmap *bitmap = rcu_dereference_raw(*slot);
if (!radix_tree_exception(bitmap))
kfree(bitmap);
radix_tree_iter_delete(&ida->ida_rt, &iter, slot);
}
}
EXPORT_SYMBOL(ida_destroy);
/**
* ida_simple_get - get a new id.
* @ida: the (initialized) ida.
* @start: the minimum id (inclusive, < 0x8000000)
* @end: the maximum id (exclusive, < 0x8000000 or 0)
* @gfp_mask: memory allocation flags
*
* Allocates an id in the range start <= id < end, or returns -ENOSPC.
* On memory allocation failure, returns -ENOMEM.
*
* Compared to ida_get_new_above() this function does its own locking, and
* should be used unless there are special requirements.
*
* Use ida_simple_remove() to get rid of an id.
*/
int ida_simple_get(struct ida *ida, unsigned int start, unsigned int end,
gfp_t gfp_mask)
{
int ret, id;
unsigned int max;
unsigned long flags;
BUG_ON((int)start < 0);
BUG_ON((int)end < 0);
if (end == 0)
max = 0x80000000;
else {
BUG_ON(end < start);
max = end - 1;
}
again:
if (!ida_pre_get(ida, gfp_mask))
return -ENOMEM;
spin_lock_irqsave(&simple_ida_lock, flags);
ret = ida_get_new_above(ida, start, &id);
if (!ret) {
if (id > max) {
ida_remove(ida, id);
ret = -ENOSPC;
} else {
ret = id;
}
}
spin_unlock_irqrestore(&simple_ida_lock, flags);
if (unlikely(ret == -EAGAIN))
goto again;
return ret;
}
EXPORT_SYMBOL(ida_simple_get);
/**
* ida_simple_remove - remove an allocated id.
* @ida: the (initialized) ida.
* @id: the id returned by ida_simple_get.
*
* Use to release an id allocated with ida_simple_get().
*
* Compared to ida_remove() this function does its own locking, and should be
* used unless there are special requirements.
*/
void ida_simple_remove(struct ida *ida, unsigned int id)
{
unsigned long flags;
BUG_ON((int)id < 0);
spin_lock_irqsave(&simple_ida_lock, flags);
ida_remove(ida, id);
spin_unlock_irqrestore(&simple_ida_lock, flags);
}
EXPORT_SYMBOL(ida_simple_remove);