2017-11-08 05:30:10 +08:00
|
|
|
// SPDX-License-Identifier: GPL-2.0+
|
|
|
|
/*
|
|
|
|
* XArray implementation
|
2020-01-18 11:13:21 +08:00
|
|
|
* Copyright (c) 2017-2018 Microsoft Corporation
|
|
|
|
* Copyright (c) 2018-2020 Oracle
|
2017-11-08 05:30:10 +08:00
|
|
|
* Author: Matthew Wilcox <willy@infradead.org>
|
|
|
|
*/
|
|
|
|
|
2017-11-10 22:34:31 +08:00
|
|
|
#include <linux/bitmap.h>
|
2017-11-08 05:30:10 +08:00
|
|
|
#include <linux/export.h>
|
2017-11-11 04:15:08 +08:00
|
|
|
#include <linux/list.h>
|
|
|
|
#include <linux/slab.h>
|
2017-11-08 05:30:10 +08:00
|
|
|
#include <linux/xarray.h>
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Coding conventions in this file:
|
|
|
|
*
|
|
|
|
* @xa is used to refer to the entire xarray.
|
|
|
|
* @xas is the 'xarray operation state'. It may be either a pointer to
|
|
|
|
* an xa_state, or an xa_state stored on the stack. This is an unfortunate
|
|
|
|
* ambiguity.
|
|
|
|
* @index is the index of the entry being operated on
|
|
|
|
* @mark is an xa_mark_t; a small number indicating one of the mark bits.
|
|
|
|
* @node refers to an xa_node; usually the primary one being operated on by
|
|
|
|
* this function.
|
|
|
|
* @offset is the index into the slots array inside an xa_node.
|
|
|
|
* @parent refers to the @xa_node closer to the head than @node.
|
|
|
|
* @entry refers to something stored in a slot in the xarray
|
|
|
|
*/
|
|
|
|
|
2017-11-11 04:15:08 +08:00
|
|
|
static inline unsigned int xa_lock_type(const struct xarray *xa)
|
|
|
|
{
|
|
|
|
return (__force unsigned int)xa->xa_flags & 3;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void xas_lock_type(struct xa_state *xas, unsigned int lock_type)
|
|
|
|
{
|
|
|
|
if (lock_type == XA_LOCK_IRQ)
|
|
|
|
xas_lock_irq(xas);
|
|
|
|
else if (lock_type == XA_LOCK_BH)
|
|
|
|
xas_lock_bh(xas);
|
|
|
|
else
|
|
|
|
xas_lock(xas);
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void xas_unlock_type(struct xa_state *xas, unsigned int lock_type)
|
|
|
|
{
|
|
|
|
if (lock_type == XA_LOCK_IRQ)
|
|
|
|
xas_unlock_irq(xas);
|
|
|
|
else if (lock_type == XA_LOCK_BH)
|
|
|
|
xas_unlock_bh(xas);
|
|
|
|
else
|
|
|
|
xas_unlock(xas);
|
|
|
|
}
|
|
|
|
|
2018-07-04 22:50:12 +08:00
|
|
|
static inline bool xa_track_free(const struct xarray *xa)
|
|
|
|
{
|
|
|
|
return xa->xa_flags & XA_FLAGS_TRACK_FREE;
|
|
|
|
}
|
|
|
|
|
2018-10-27 02:43:22 +08:00
|
|
|
static inline bool xa_zero_busy(const struct xarray *xa)
|
|
|
|
{
|
|
|
|
return xa->xa_flags & XA_FLAGS_ZERO_BUSY;
|
|
|
|
}
|
|
|
|
|
2017-11-10 22:34:31 +08:00
|
|
|
static inline void xa_mark_set(struct xarray *xa, xa_mark_t mark)
|
|
|
|
{
|
|
|
|
if (!(xa->xa_flags & XA_FLAGS_MARK(mark)))
|
|
|
|
xa->xa_flags |= XA_FLAGS_MARK(mark);
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void xa_mark_clear(struct xarray *xa, xa_mark_t mark)
|
|
|
|
{
|
|
|
|
if (xa->xa_flags & XA_FLAGS_MARK(mark))
|
|
|
|
xa->xa_flags &= ~(XA_FLAGS_MARK(mark));
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline unsigned long *node_marks(struct xa_node *node, xa_mark_t mark)
|
|
|
|
{
|
|
|
|
return node->marks[(__force unsigned)mark];
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline bool node_get_mark(struct xa_node *node,
|
|
|
|
unsigned int offset, xa_mark_t mark)
|
|
|
|
{
|
|
|
|
return test_bit(offset, node_marks(node, mark));
|
|
|
|
}
|
|
|
|
|
|
|
|
/* returns true if the bit was set */
|
|
|
|
static inline bool node_set_mark(struct xa_node *node, unsigned int offset,
|
|
|
|
xa_mark_t mark)
|
|
|
|
{
|
|
|
|
return __test_and_set_bit(offset, node_marks(node, mark));
|
|
|
|
}
|
|
|
|
|
|
|
|
/* returns true if the bit was set */
|
|
|
|
static inline bool node_clear_mark(struct xa_node *node, unsigned int offset,
|
|
|
|
xa_mark_t mark)
|
|
|
|
{
|
|
|
|
return __test_and_clear_bit(offset, node_marks(node, mark));
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline bool node_any_mark(struct xa_node *node, xa_mark_t mark)
|
|
|
|
{
|
|
|
|
return !bitmap_empty(node_marks(node, mark), XA_CHUNK_SIZE);
|
|
|
|
}
|
|
|
|
|
2018-07-04 22:50:12 +08:00
|
|
|
static inline void node_mark_all(struct xa_node *node, xa_mark_t mark)
|
|
|
|
{
|
|
|
|
bitmap_fill(node_marks(node, mark), XA_CHUNK_SIZE);
|
|
|
|
}
|
|
|
|
|
2017-11-11 04:15:08 +08:00
|
|
|
#define mark_inc(mark) do { \
|
|
|
|
mark = (__force xa_mark_t)((__force unsigned)(mark) + 1); \
|
|
|
|
} while (0)
|
|
|
|
|
|
|
|
/*
|
|
|
|
* xas_squash_marks() - Merge all marks to the first entry
|
|
|
|
* @xas: Array operation state.
|
|
|
|
*
|
|
|
|
* Set a mark on the first entry if any entry has it set. Clear marks on
|
|
|
|
* all sibling entries.
|
|
|
|
*/
|
|
|
|
static void xas_squash_marks(const struct xa_state *xas)
|
|
|
|
{
|
|
|
|
unsigned int mark = 0;
|
|
|
|
unsigned int limit = xas->xa_offset + xas->xa_sibs + 1;
|
|
|
|
|
|
|
|
if (!xas->xa_sibs)
|
|
|
|
return;
|
|
|
|
|
|
|
|
do {
|
|
|
|
unsigned long *marks = xas->xa_node->marks[mark];
|
|
|
|
if (find_next_bit(marks, limit, xas->xa_offset + 1) == limit)
|
|
|
|
continue;
|
|
|
|
__set_bit(xas->xa_offset, marks);
|
|
|
|
bitmap_clear(marks, xas->xa_offset + 1, xas->xa_sibs);
|
|
|
|
} while (mark++ != (__force unsigned)XA_MARK_MAX);
|
|
|
|
}
|
|
|
|
|
2017-11-08 03:57:46 +08:00
|
|
|
/* extracts the offset within this node from the index */
|
|
|
|
static unsigned int get_offset(unsigned long index, struct xa_node *node)
|
|
|
|
{
|
|
|
|
return (index >> node->shift) & XA_CHUNK_MASK;
|
|
|
|
}
|
|
|
|
|
2017-11-14 21:30:11 +08:00
|
|
|
static void xas_set_offset(struct xa_state *xas)
|
|
|
|
{
|
|
|
|
xas->xa_offset = get_offset(xas->xa_index, xas->xa_node);
|
|
|
|
}
|
|
|
|
|
2017-11-08 03:57:46 +08:00
|
|
|
/* move the index either forwards (find) or backwards (sibling slot) */
|
|
|
|
static void xas_move_index(struct xa_state *xas, unsigned long offset)
|
|
|
|
{
|
|
|
|
unsigned int shift = xas->xa_node->shift;
|
|
|
|
xas->xa_index &= ~XA_CHUNK_MASK << shift;
|
|
|
|
xas->xa_index += offset << shift;
|
|
|
|
}
|
|
|
|
|
2017-11-14 21:30:11 +08:00
|
|
|
static void xas_advance(struct xa_state *xas)
|
|
|
|
{
|
|
|
|
xas->xa_offset++;
|
|
|
|
xas_move_index(xas, xas->xa_offset);
|
|
|
|
}
|
|
|
|
|
2017-11-08 03:57:46 +08:00
|
|
|
static void *set_bounds(struct xa_state *xas)
|
|
|
|
{
|
|
|
|
xas->xa_node = XAS_BOUNDS;
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Starts a walk. If the @xas is already valid, we assume that it's on
|
|
|
|
* the right path and just return where we've got to. If we're in an
|
|
|
|
* error state, return NULL. If the index is outside the current scope
|
|
|
|
* of the xarray, return NULL without changing @xas->xa_node. Otherwise
|
|
|
|
* set @xas->xa_node to NULL and return the current head of the array.
|
|
|
|
*/
|
|
|
|
static void *xas_start(struct xa_state *xas)
|
|
|
|
{
|
|
|
|
void *entry;
|
|
|
|
|
|
|
|
if (xas_valid(xas))
|
|
|
|
return xas_reload(xas);
|
|
|
|
if (xas_error(xas))
|
|
|
|
return NULL;
|
|
|
|
|
|
|
|
entry = xa_head(xas->xa);
|
|
|
|
if (!xa_is_node(entry)) {
|
|
|
|
if (xas->xa_index)
|
|
|
|
return set_bounds(xas);
|
|
|
|
} else {
|
|
|
|
if ((xas->xa_index >> xa_to_node(entry)->shift) > XA_CHUNK_MASK)
|
|
|
|
return set_bounds(xas);
|
|
|
|
}
|
|
|
|
|
|
|
|
xas->xa_node = NULL;
|
|
|
|
return entry;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void *xas_descend(struct xa_state *xas, struct xa_node *node)
|
|
|
|
{
|
|
|
|
unsigned int offset = get_offset(xas->xa_index, node);
|
|
|
|
void *entry = xa_entry(xas->xa, node, offset);
|
|
|
|
|
|
|
|
xas->xa_node = node;
|
|
|
|
if (xa_is_sibling(entry)) {
|
|
|
|
offset = xa_to_sibling(entry);
|
|
|
|
entry = xa_entry(xas->xa, node, offset);
|
|
|
|
}
|
|
|
|
|
|
|
|
xas->xa_offset = offset;
|
|
|
|
return entry;
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* xas_load() - Load an entry from the XArray (advanced).
|
|
|
|
* @xas: XArray operation state.
|
|
|
|
*
|
|
|
|
* Usually walks the @xas to the appropriate state to load the entry
|
|
|
|
* stored at xa_index. However, it will do nothing and return %NULL if
|
|
|
|
* @xas is in an error state. xas_load() will never expand the tree.
|
|
|
|
*
|
|
|
|
* If the xa_state is set up to operate on a multi-index entry, xas_load()
|
|
|
|
* may return %NULL or an internal entry, even if there are entries
|
|
|
|
* present within the range specified by @xas.
|
|
|
|
*
|
|
|
|
* Context: Any context. The caller should hold the xa_lock or the RCU lock.
|
|
|
|
* Return: Usually an entry in the XArray, but see description for exceptions.
|
|
|
|
*/
|
|
|
|
void *xas_load(struct xa_state *xas)
|
|
|
|
{
|
|
|
|
void *entry = xas_start(xas);
|
|
|
|
|
|
|
|
while (xa_is_node(entry)) {
|
|
|
|
struct xa_node *node = xa_to_node(entry);
|
|
|
|
|
|
|
|
if (xas->xa_shift > node->shift)
|
|
|
|
break;
|
|
|
|
entry = xas_descend(xas, node);
|
2018-12-29 12:20:44 +08:00
|
|
|
if (node->shift == 0)
|
|
|
|
break;
|
2017-11-08 03:57:46 +08:00
|
|
|
}
|
|
|
|
return entry;
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(xas_load);
|
|
|
|
|
2017-11-11 04:15:08 +08:00
|
|
|
/* Move the radix tree node cache here */
|
|
|
|
extern struct kmem_cache *radix_tree_node_cachep;
|
|
|
|
extern void radix_tree_node_rcu_free(struct rcu_head *head);
|
|
|
|
|
|
|
|
#define XA_RCU_FREE ((struct xarray *)1)
|
|
|
|
|
|
|
|
static void xa_node_free(struct xa_node *node)
|
|
|
|
{
|
|
|
|
XA_NODE_BUG_ON(node, !list_empty(&node->private_list));
|
|
|
|
node->array = XA_RCU_FREE;
|
|
|
|
call_rcu(&node->rcu_head, radix_tree_node_rcu_free);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* xas_destroy() - Free any resources allocated during the XArray operation.
|
|
|
|
* @xas: XArray operation state.
|
|
|
|
*
|
|
|
|
* This function is now internal-only.
|
|
|
|
*/
|
|
|
|
static void xas_destroy(struct xa_state *xas)
|
|
|
|
{
|
2020-10-16 11:05:16 +08:00
|
|
|
struct xa_node *next, *node = xas->xa_alloc;
|
2017-11-11 04:15:08 +08:00
|
|
|
|
2020-10-16 11:05:16 +08:00
|
|
|
while (node) {
|
|
|
|
XA_NODE_BUG_ON(node, !list_empty(&node->private_list));
|
|
|
|
next = rcu_dereference_raw(node->parent);
|
|
|
|
radix_tree_node_rcu_free(&node->rcu_head);
|
|
|
|
xas->xa_alloc = node = next;
|
|
|
|
}
|
2017-11-11 04:15:08 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* xas_nomem() - Allocate memory if needed.
|
|
|
|
* @xas: XArray operation state.
|
|
|
|
* @gfp: Memory allocation flags.
|
|
|
|
*
|
|
|
|
* If we need to add new nodes to the XArray, we try to allocate memory
|
|
|
|
* with GFP_NOWAIT while holding the lock, which will usually succeed.
|
|
|
|
* If it fails, @xas is flagged as needing memory to continue. The caller
|
|
|
|
* should drop the lock and call xas_nomem(). If xas_nomem() succeeds,
|
|
|
|
* the caller should retry the operation.
|
|
|
|
*
|
|
|
|
* Forward progress is guaranteed as one node is allocated here and
|
|
|
|
* stored in the xa_state where it will be found by xas_alloc(). More
|
|
|
|
* nodes will likely be found in the slab allocator, but we do not tie
|
|
|
|
* them up here.
|
|
|
|
*
|
|
|
|
* Return: true if memory was needed, and was successfully allocated.
|
|
|
|
*/
|
|
|
|
bool xas_nomem(struct xa_state *xas, gfp_t gfp)
|
|
|
|
{
|
|
|
|
if (xas->xa_node != XA_ERROR(-ENOMEM)) {
|
|
|
|
xas_destroy(xas);
|
|
|
|
return false;
|
|
|
|
}
|
mm: fix page cache convergence regression
Since a28334862993 ("page cache: Finish XArray conversion"), on most
major Linux distributions, the page cache doesn't correctly transition
when the hot data set is changing, and leaves the new pages thrashing
indefinitely instead of kicking out the cold ones.
On a freshly booted, freshly ssh'd into virtual machine with 1G RAM
running stock Arch Linux:
[root@ham ~]# ./reclaimtest.sh
+ dd of=workingset-a bs=1M count=0 seek=600
+ cat workingset-a
+ cat workingset-a
+ cat workingset-a
+ cat workingset-a
+ cat workingset-a
+ cat workingset-a
+ cat workingset-a
+ cat workingset-a
+ ./mincore workingset-a
153600/153600 workingset-a
+ dd of=workingset-b bs=1M count=0 seek=600
+ cat workingset-b
+ cat workingset-b
+ cat workingset-b
+ cat workingset-b
+ ./mincore workingset-a workingset-b
104029/153600 workingset-a
120086/153600 workingset-b
+ cat workingset-b
+ cat workingset-b
+ cat workingset-b
+ cat workingset-b
+ ./mincore workingset-a workingset-b
104029/153600 workingset-a
120268/153600 workingset-b
workingset-b is a 600M file on a 1G host that is otherwise entirely
idle. No matter how often it's being accessed, it won't get cached.
While investigating, I noticed that the non-resident information gets
aggressively reclaimed - /proc/vmstat::workingset_nodereclaim. This is
a problem because a workingset transition like this relies on the
non-resident information tracked in the page cache tree of evicted
file ranges: when the cache faults are refaults of recently evicted
cache, we challenge the existing active set, and that allows a new
workingset to establish itself.
Tracing the shrinker that maintains this memory revealed that all page
cache tree nodes were allocated to the root cgroup. This is a problem,
because 1) the shrinker sizes the amount of non-resident information
it keeps to the size of the cgroup's other memory and 2) on most major
Linux distributions, only kernel threads live in the root cgroup and
everything else gets put into services or session groups:
[root@ham ~]# cat /proc/self/cgroup
0::/user.slice/user-0.slice/session-c1.scope
As a result, we basically maintain no non-resident information for the
workloads running on the system, thus breaking the caching algorithm.
Looking through the code, I found the culprit in the above-mentioned
patch: when switching from the radix tree to xarray, it dropped the
__GFP_ACCOUNT flag from the tree node allocations - the flag that
makes sure the allocated memory gets charged to and tracked by the
cgroup of the calling process - in this case, the one doing the fault.
To fix this, allow xarray users to specify per-tree flag that makes
xarray allocate nodes using __GFP_ACCOUNT. Then restore the page cache
tree annotation to request such cgroup tracking for the cache nodes.
With this patch applied, the page cache correctly converges on new
workingsets again after just a few iterations:
[root@ham ~]# ./reclaimtest.sh
+ dd of=workingset-a bs=1M count=0 seek=600
+ cat workingset-a
+ cat workingset-a
+ cat workingset-a
+ cat workingset-a
+ cat workingset-a
+ cat workingset-a
+ cat workingset-a
+ cat workingset-a
+ ./mincore workingset-a
153600/153600 workingset-a
+ dd of=workingset-b bs=1M count=0 seek=600
+ cat workingset-b
+ ./mincore workingset-a workingset-b
124607/153600 workingset-a
87876/153600 workingset-b
+ cat workingset-b
+ ./mincore workingset-a workingset-b
81313/153600 workingset-a
133321/153600 workingset-b
+ cat workingset-b
+ ./mincore workingset-a workingset-b
63036/153600 workingset-a
153600/153600 workingset-b
Cc: stable@vger.kernel.org # 4.20+
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
2019-05-24 22:12:46 +08:00
|
|
|
if (xas->xa->xa_flags & XA_FLAGS_ACCOUNT)
|
|
|
|
gfp |= __GFP_ACCOUNT;
|
2017-11-11 04:15:08 +08:00
|
|
|
xas->xa_alloc = kmem_cache_alloc(radix_tree_node_cachep, gfp);
|
|
|
|
if (!xas->xa_alloc)
|
|
|
|
return false;
|
2020-10-16 11:05:16 +08:00
|
|
|
xas->xa_alloc->parent = NULL;
|
2017-11-11 04:15:08 +08:00
|
|
|
XA_NODE_BUG_ON(xas->xa_alloc, !list_empty(&xas->xa_alloc->private_list));
|
|
|
|
xas->xa_node = XAS_RESTART;
|
|
|
|
return true;
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(xas_nomem);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* __xas_nomem() - Drop locks and allocate memory if needed.
|
|
|
|
* @xas: XArray operation state.
|
|
|
|
* @gfp: Memory allocation flags.
|
|
|
|
*
|
|
|
|
* Internal variant of xas_nomem().
|
|
|
|
*
|
|
|
|
* Return: true if memory was needed, and was successfully allocated.
|
|
|
|
*/
|
|
|
|
static bool __xas_nomem(struct xa_state *xas, gfp_t gfp)
|
|
|
|
__must_hold(xas->xa->xa_lock)
|
|
|
|
{
|
|
|
|
unsigned int lock_type = xa_lock_type(xas->xa);
|
|
|
|
|
|
|
|
if (xas->xa_node != XA_ERROR(-ENOMEM)) {
|
|
|
|
xas_destroy(xas);
|
|
|
|
return false;
|
|
|
|
}
|
mm: fix page cache convergence regression
Since a28334862993 ("page cache: Finish XArray conversion"), on most
major Linux distributions, the page cache doesn't correctly transition
when the hot data set is changing, and leaves the new pages thrashing
indefinitely instead of kicking out the cold ones.
On a freshly booted, freshly ssh'd into virtual machine with 1G RAM
running stock Arch Linux:
[root@ham ~]# ./reclaimtest.sh
+ dd of=workingset-a bs=1M count=0 seek=600
+ cat workingset-a
+ cat workingset-a
+ cat workingset-a
+ cat workingset-a
+ cat workingset-a
+ cat workingset-a
+ cat workingset-a
+ cat workingset-a
+ ./mincore workingset-a
153600/153600 workingset-a
+ dd of=workingset-b bs=1M count=0 seek=600
+ cat workingset-b
+ cat workingset-b
+ cat workingset-b
+ cat workingset-b
+ ./mincore workingset-a workingset-b
104029/153600 workingset-a
120086/153600 workingset-b
+ cat workingset-b
+ cat workingset-b
+ cat workingset-b
+ cat workingset-b
+ ./mincore workingset-a workingset-b
104029/153600 workingset-a
120268/153600 workingset-b
workingset-b is a 600M file on a 1G host that is otherwise entirely
idle. No matter how often it's being accessed, it won't get cached.
While investigating, I noticed that the non-resident information gets
aggressively reclaimed - /proc/vmstat::workingset_nodereclaim. This is
a problem because a workingset transition like this relies on the
non-resident information tracked in the page cache tree of evicted
file ranges: when the cache faults are refaults of recently evicted
cache, we challenge the existing active set, and that allows a new
workingset to establish itself.
Tracing the shrinker that maintains this memory revealed that all page
cache tree nodes were allocated to the root cgroup. This is a problem,
because 1) the shrinker sizes the amount of non-resident information
it keeps to the size of the cgroup's other memory and 2) on most major
Linux distributions, only kernel threads live in the root cgroup and
everything else gets put into services or session groups:
[root@ham ~]# cat /proc/self/cgroup
0::/user.slice/user-0.slice/session-c1.scope
As a result, we basically maintain no non-resident information for the
workloads running on the system, thus breaking the caching algorithm.
Looking through the code, I found the culprit in the above-mentioned
patch: when switching from the radix tree to xarray, it dropped the
__GFP_ACCOUNT flag from the tree node allocations - the flag that
makes sure the allocated memory gets charged to and tracked by the
cgroup of the calling process - in this case, the one doing the fault.
To fix this, allow xarray users to specify per-tree flag that makes
xarray allocate nodes using __GFP_ACCOUNT. Then restore the page cache
tree annotation to request such cgroup tracking for the cache nodes.
With this patch applied, the page cache correctly converges on new
workingsets again after just a few iterations:
[root@ham ~]# ./reclaimtest.sh
+ dd of=workingset-a bs=1M count=0 seek=600
+ cat workingset-a
+ cat workingset-a
+ cat workingset-a
+ cat workingset-a
+ cat workingset-a
+ cat workingset-a
+ cat workingset-a
+ cat workingset-a
+ ./mincore workingset-a
153600/153600 workingset-a
+ dd of=workingset-b bs=1M count=0 seek=600
+ cat workingset-b
+ ./mincore workingset-a workingset-b
124607/153600 workingset-a
87876/153600 workingset-b
+ cat workingset-b
+ ./mincore workingset-a workingset-b
81313/153600 workingset-a
133321/153600 workingset-b
+ cat workingset-b
+ ./mincore workingset-a workingset-b
63036/153600 workingset-a
153600/153600 workingset-b
Cc: stable@vger.kernel.org # 4.20+
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
2019-05-24 22:12:46 +08:00
|
|
|
if (xas->xa->xa_flags & XA_FLAGS_ACCOUNT)
|
|
|
|
gfp |= __GFP_ACCOUNT;
|
2017-11-11 04:15:08 +08:00
|
|
|
if (gfpflags_allow_blocking(gfp)) {
|
|
|
|
xas_unlock_type(xas, lock_type);
|
|
|
|
xas->xa_alloc = kmem_cache_alloc(radix_tree_node_cachep, gfp);
|
|
|
|
xas_lock_type(xas, lock_type);
|
|
|
|
} else {
|
|
|
|
xas->xa_alloc = kmem_cache_alloc(radix_tree_node_cachep, gfp);
|
|
|
|
}
|
|
|
|
if (!xas->xa_alloc)
|
|
|
|
return false;
|
2020-10-16 11:05:16 +08:00
|
|
|
xas->xa_alloc->parent = NULL;
|
2017-11-11 04:15:08 +08:00
|
|
|
XA_NODE_BUG_ON(xas->xa_alloc, !list_empty(&xas->xa_alloc->private_list));
|
|
|
|
xas->xa_node = XAS_RESTART;
|
|
|
|
return true;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void xas_update(struct xa_state *xas, struct xa_node *node)
|
|
|
|
{
|
|
|
|
if (xas->xa_update)
|
|
|
|
xas->xa_update(node);
|
|
|
|
else
|
|
|
|
XA_NODE_BUG_ON(node, !list_empty(&node->private_list));
|
|
|
|
}
|
|
|
|
|
|
|
|
static void *xas_alloc(struct xa_state *xas, unsigned int shift)
|
|
|
|
{
|
|
|
|
struct xa_node *parent = xas->xa_node;
|
|
|
|
struct xa_node *node = xas->xa_alloc;
|
|
|
|
|
|
|
|
if (xas_invalid(xas))
|
|
|
|
return NULL;
|
|
|
|
|
|
|
|
if (node) {
|
|
|
|
xas->xa_alloc = NULL;
|
|
|
|
} else {
|
mm: fix page cache convergence regression
Since a28334862993 ("page cache: Finish XArray conversion"), on most
major Linux distributions, the page cache doesn't correctly transition
when the hot data set is changing, and leaves the new pages thrashing
indefinitely instead of kicking out the cold ones.
On a freshly booted, freshly ssh'd into virtual machine with 1G RAM
running stock Arch Linux:
[root@ham ~]# ./reclaimtest.sh
+ dd of=workingset-a bs=1M count=0 seek=600
+ cat workingset-a
+ cat workingset-a
+ cat workingset-a
+ cat workingset-a
+ cat workingset-a
+ cat workingset-a
+ cat workingset-a
+ cat workingset-a
+ ./mincore workingset-a
153600/153600 workingset-a
+ dd of=workingset-b bs=1M count=0 seek=600
+ cat workingset-b
+ cat workingset-b
+ cat workingset-b
+ cat workingset-b
+ ./mincore workingset-a workingset-b
104029/153600 workingset-a
120086/153600 workingset-b
+ cat workingset-b
+ cat workingset-b
+ cat workingset-b
+ cat workingset-b
+ ./mincore workingset-a workingset-b
104029/153600 workingset-a
120268/153600 workingset-b
workingset-b is a 600M file on a 1G host that is otherwise entirely
idle. No matter how often it's being accessed, it won't get cached.
While investigating, I noticed that the non-resident information gets
aggressively reclaimed - /proc/vmstat::workingset_nodereclaim. This is
a problem because a workingset transition like this relies on the
non-resident information tracked in the page cache tree of evicted
file ranges: when the cache faults are refaults of recently evicted
cache, we challenge the existing active set, and that allows a new
workingset to establish itself.
Tracing the shrinker that maintains this memory revealed that all page
cache tree nodes were allocated to the root cgroup. This is a problem,
because 1) the shrinker sizes the amount of non-resident information
it keeps to the size of the cgroup's other memory and 2) on most major
Linux distributions, only kernel threads live in the root cgroup and
everything else gets put into services or session groups:
[root@ham ~]# cat /proc/self/cgroup
0::/user.slice/user-0.slice/session-c1.scope
As a result, we basically maintain no non-resident information for the
workloads running on the system, thus breaking the caching algorithm.
Looking through the code, I found the culprit in the above-mentioned
patch: when switching from the radix tree to xarray, it dropped the
__GFP_ACCOUNT flag from the tree node allocations - the flag that
makes sure the allocated memory gets charged to and tracked by the
cgroup of the calling process - in this case, the one doing the fault.
To fix this, allow xarray users to specify per-tree flag that makes
xarray allocate nodes using __GFP_ACCOUNT. Then restore the page cache
tree annotation to request such cgroup tracking for the cache nodes.
With this patch applied, the page cache correctly converges on new
workingsets again after just a few iterations:
[root@ham ~]# ./reclaimtest.sh
+ dd of=workingset-a bs=1M count=0 seek=600
+ cat workingset-a
+ cat workingset-a
+ cat workingset-a
+ cat workingset-a
+ cat workingset-a
+ cat workingset-a
+ cat workingset-a
+ cat workingset-a
+ ./mincore workingset-a
153600/153600 workingset-a
+ dd of=workingset-b bs=1M count=0 seek=600
+ cat workingset-b
+ ./mincore workingset-a workingset-b
124607/153600 workingset-a
87876/153600 workingset-b
+ cat workingset-b
+ ./mincore workingset-a workingset-b
81313/153600 workingset-a
133321/153600 workingset-b
+ cat workingset-b
+ ./mincore workingset-a workingset-b
63036/153600 workingset-a
153600/153600 workingset-b
Cc: stable@vger.kernel.org # 4.20+
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
2019-05-24 22:12:46 +08:00
|
|
|
gfp_t gfp = GFP_NOWAIT | __GFP_NOWARN;
|
|
|
|
|
|
|
|
if (xas->xa->xa_flags & XA_FLAGS_ACCOUNT)
|
|
|
|
gfp |= __GFP_ACCOUNT;
|
|
|
|
|
|
|
|
node = kmem_cache_alloc(radix_tree_node_cachep, gfp);
|
2017-11-11 04:15:08 +08:00
|
|
|
if (!node) {
|
|
|
|
xas_set_err(xas, -ENOMEM);
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
if (parent) {
|
|
|
|
node->offset = xas->xa_offset;
|
|
|
|
parent->count++;
|
|
|
|
XA_NODE_BUG_ON(node, parent->count > XA_CHUNK_SIZE);
|
|
|
|
xas_update(xas, parent);
|
|
|
|
}
|
|
|
|
XA_NODE_BUG_ON(node, shift > BITS_PER_LONG);
|
|
|
|
XA_NODE_BUG_ON(node, !list_empty(&node->private_list));
|
|
|
|
node->shift = shift;
|
|
|
|
node->count = 0;
|
|
|
|
node->nr_values = 0;
|
|
|
|
RCU_INIT_POINTER(node->parent, xas->xa_node);
|
|
|
|
node->array = xas->xa;
|
|
|
|
|
|
|
|
return node;
|
|
|
|
}
|
|
|
|
|
2018-08-16 02:13:29 +08:00
|
|
|
#ifdef CONFIG_XARRAY_MULTI
|
|
|
|
/* Returns the number of indices covered by a given xa_state */
|
|
|
|
static unsigned long xas_size(const struct xa_state *xas)
|
|
|
|
{
|
|
|
|
return (xas->xa_sibs + 1UL) << xas->xa_shift;
|
|
|
|
}
|
|
|
|
#endif
|
|
|
|
|
2017-11-11 04:15:08 +08:00
|
|
|
/*
|
|
|
|
* Use this to calculate the maximum index that will need to be created
|
|
|
|
* in order to add the entry described by @xas. Because we cannot store a
|
2020-10-16 11:05:16 +08:00
|
|
|
* multi-index entry at index 0, the calculation is a little more complex
|
2017-11-11 04:15:08 +08:00
|
|
|
* than you might expect.
|
|
|
|
*/
|
|
|
|
static unsigned long xas_max(struct xa_state *xas)
|
|
|
|
{
|
|
|
|
unsigned long max = xas->xa_index;
|
|
|
|
|
|
|
|
#ifdef CONFIG_XARRAY_MULTI
|
|
|
|
if (xas->xa_shift || xas->xa_sibs) {
|
2018-08-16 02:13:29 +08:00
|
|
|
unsigned long mask = xas_size(xas) - 1;
|
2017-11-11 04:15:08 +08:00
|
|
|
max |= mask;
|
|
|
|
if (mask == max)
|
|
|
|
max++;
|
|
|
|
}
|
|
|
|
#endif
|
|
|
|
|
|
|
|
return max;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* The maximum index that can be contained in the array without expanding it */
|
|
|
|
static unsigned long max_index(void *entry)
|
|
|
|
{
|
|
|
|
if (!xa_is_node(entry))
|
|
|
|
return 0;
|
|
|
|
return (XA_CHUNK_SIZE << xa_to_node(entry)->shift) - 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void xas_shrink(struct xa_state *xas)
|
|
|
|
{
|
|
|
|
struct xarray *xa = xas->xa;
|
|
|
|
struct xa_node *node = xas->xa_node;
|
|
|
|
|
|
|
|
for (;;) {
|
|
|
|
void *entry;
|
|
|
|
|
|
|
|
XA_NODE_BUG_ON(node, node->count > XA_CHUNK_SIZE);
|
|
|
|
if (node->count != 1)
|
|
|
|
break;
|
|
|
|
entry = xa_entry_locked(xa, node, 0);
|
|
|
|
if (!entry)
|
|
|
|
break;
|
|
|
|
if (!xa_is_node(entry) && node->shift)
|
|
|
|
break;
|
2018-10-27 02:43:22 +08:00
|
|
|
if (xa_is_zero(entry) && xa_zero_busy(xa))
|
|
|
|
entry = NULL;
|
2017-11-11 04:15:08 +08:00
|
|
|
xas->xa_node = XAS_BOUNDS;
|
|
|
|
|
|
|
|
RCU_INIT_POINTER(xa->xa_head, entry);
|
2018-07-04 22:50:12 +08:00
|
|
|
if (xa_track_free(xa) && !node_get_mark(node, 0, XA_FREE_MARK))
|
|
|
|
xa_mark_clear(xa, XA_FREE_MARK);
|
2017-11-11 04:15:08 +08:00
|
|
|
|
|
|
|
node->count = 0;
|
|
|
|
node->nr_values = 0;
|
|
|
|
if (!xa_is_node(entry))
|
|
|
|
RCU_INIT_POINTER(node->slots[0], XA_RETRY_ENTRY);
|
|
|
|
xas_update(xas, node);
|
|
|
|
xa_node_free(node);
|
|
|
|
if (!xa_is_node(entry))
|
|
|
|
break;
|
|
|
|
node = xa_to_node(entry);
|
|
|
|
node->parent = NULL;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* xas_delete_node() - Attempt to delete an xa_node
|
|
|
|
* @xas: Array operation state.
|
|
|
|
*
|
|
|
|
* Attempts to delete the @xas->xa_node. This will fail if xa->node has
|
|
|
|
* a non-zero reference count.
|
|
|
|
*/
|
|
|
|
static void xas_delete_node(struct xa_state *xas)
|
|
|
|
{
|
|
|
|
struct xa_node *node = xas->xa_node;
|
|
|
|
|
|
|
|
for (;;) {
|
|
|
|
struct xa_node *parent;
|
|
|
|
|
|
|
|
XA_NODE_BUG_ON(node, node->count > XA_CHUNK_SIZE);
|
|
|
|
if (node->count)
|
|
|
|
break;
|
|
|
|
|
|
|
|
parent = xa_parent_locked(xas->xa, node);
|
|
|
|
xas->xa_node = parent;
|
|
|
|
xas->xa_offset = node->offset;
|
|
|
|
xa_node_free(node);
|
|
|
|
|
|
|
|
if (!parent) {
|
|
|
|
xas->xa->xa_head = NULL;
|
|
|
|
xas->xa_node = XAS_BOUNDS;
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
|
|
|
parent->slots[xas->xa_offset] = NULL;
|
|
|
|
parent->count--;
|
|
|
|
XA_NODE_BUG_ON(parent, parent->count > XA_CHUNK_SIZE);
|
|
|
|
node = parent;
|
|
|
|
xas_update(xas, node);
|
|
|
|
}
|
|
|
|
|
|
|
|
if (!node->parent)
|
|
|
|
xas_shrink(xas);
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* xas_free_nodes() - Free this node and all nodes that it references
|
|
|
|
* @xas: Array operation state.
|
|
|
|
* @top: Node to free
|
|
|
|
*
|
|
|
|
* This node has been removed from the tree. We must now free it and all
|
|
|
|
* of its subnodes. There may be RCU walkers with references into the tree,
|
|
|
|
* so we must replace all entries with retry markers.
|
|
|
|
*/
|
|
|
|
static void xas_free_nodes(struct xa_state *xas, struct xa_node *top)
|
|
|
|
{
|
|
|
|
unsigned int offset = 0;
|
|
|
|
struct xa_node *node = top;
|
|
|
|
|
|
|
|
for (;;) {
|
|
|
|
void *entry = xa_entry_locked(xas->xa, node, offset);
|
|
|
|
|
2018-12-29 12:20:44 +08:00
|
|
|
if (node->shift && xa_is_node(entry)) {
|
2017-11-11 04:15:08 +08:00
|
|
|
node = xa_to_node(entry);
|
|
|
|
offset = 0;
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
if (entry)
|
|
|
|
RCU_INIT_POINTER(node->slots[offset], XA_RETRY_ENTRY);
|
|
|
|
offset++;
|
|
|
|
while (offset == XA_CHUNK_SIZE) {
|
|
|
|
struct xa_node *parent;
|
|
|
|
|
|
|
|
parent = xa_parent_locked(xas->xa, node);
|
|
|
|
offset = node->offset + 1;
|
|
|
|
node->count = 0;
|
|
|
|
node->nr_values = 0;
|
|
|
|
xas_update(xas, node);
|
|
|
|
xa_node_free(node);
|
|
|
|
if (node == top)
|
|
|
|
return;
|
|
|
|
node = parent;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* xas_expand adds nodes to the head of the tree until it has reached
|
|
|
|
* sufficient height to be able to contain @xas->xa_index
|
|
|
|
*/
|
|
|
|
static int xas_expand(struct xa_state *xas, void *head)
|
|
|
|
{
|
|
|
|
struct xarray *xa = xas->xa;
|
|
|
|
struct xa_node *node = NULL;
|
|
|
|
unsigned int shift = 0;
|
|
|
|
unsigned long max = xas_max(xas);
|
|
|
|
|
|
|
|
if (!head) {
|
|
|
|
if (max == 0)
|
|
|
|
return 0;
|
|
|
|
while ((max >> shift) >= XA_CHUNK_SIZE)
|
|
|
|
shift += XA_CHUNK_SHIFT;
|
|
|
|
return shift + XA_CHUNK_SHIFT;
|
|
|
|
} else if (xa_is_node(head)) {
|
|
|
|
node = xa_to_node(head);
|
|
|
|
shift = node->shift + XA_CHUNK_SHIFT;
|
|
|
|
}
|
|
|
|
xas->xa_node = NULL;
|
|
|
|
|
|
|
|
while (max > max_index(head)) {
|
|
|
|
xa_mark_t mark = 0;
|
|
|
|
|
|
|
|
XA_NODE_BUG_ON(node, shift > BITS_PER_LONG);
|
|
|
|
node = xas_alloc(xas, shift);
|
|
|
|
if (!node)
|
|
|
|
return -ENOMEM;
|
|
|
|
|
|
|
|
node->count = 1;
|
|
|
|
if (xa_is_value(head))
|
|
|
|
node->nr_values = 1;
|
|
|
|
RCU_INIT_POINTER(node->slots[0], head);
|
|
|
|
|
|
|
|
/* Propagate the aggregated mark info to the new child */
|
|
|
|
for (;;) {
|
2018-07-04 22:50:12 +08:00
|
|
|
if (xa_track_free(xa) && mark == XA_FREE_MARK) {
|
|
|
|
node_mark_all(node, XA_FREE_MARK);
|
|
|
|
if (!xa_marked(xa, XA_FREE_MARK)) {
|
|
|
|
node_clear_mark(node, 0, XA_FREE_MARK);
|
|
|
|
xa_mark_set(xa, XA_FREE_MARK);
|
|
|
|
}
|
|
|
|
} else if (xa_marked(xa, mark)) {
|
2017-11-11 04:15:08 +08:00
|
|
|
node_set_mark(node, 0, mark);
|
2018-07-04 22:50:12 +08:00
|
|
|
}
|
2017-11-11 04:15:08 +08:00
|
|
|
if (mark == XA_MARK_MAX)
|
|
|
|
break;
|
|
|
|
mark_inc(mark);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Now that the new node is fully initialised, we can add
|
|
|
|
* it to the tree
|
|
|
|
*/
|
|
|
|
if (xa_is_node(head)) {
|
|
|
|
xa_to_node(head)->offset = 0;
|
|
|
|
rcu_assign_pointer(xa_to_node(head)->parent, node);
|
|
|
|
}
|
|
|
|
head = xa_mk_node(node);
|
|
|
|
rcu_assign_pointer(xa->xa_head, head);
|
|
|
|
xas_update(xas, node);
|
|
|
|
|
|
|
|
shift += XA_CHUNK_SHIFT;
|
|
|
|
}
|
|
|
|
|
|
|
|
xas->xa_node = node;
|
|
|
|
return shift;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* xas_create() - Create a slot to store an entry in.
|
|
|
|
* @xas: XArray operation state.
|
2018-12-29 12:20:44 +08:00
|
|
|
* @allow_root: %true if we can store the entry in the root directly
|
2017-11-11 04:15:08 +08:00
|
|
|
*
|
|
|
|
* Most users will not need to call this function directly, as it is called
|
|
|
|
* by xas_store(). It is useful for doing conditional store operations
|
|
|
|
* (see the xa_cmpxchg() implementation for an example).
|
|
|
|
*
|
|
|
|
* Return: If the slot already existed, returns the contents of this slot.
|
2018-11-06 05:37:15 +08:00
|
|
|
* If the slot was newly created, returns %NULL. If it failed to create the
|
|
|
|
* slot, returns %NULL and indicates the error in @xas.
|
2017-11-11 04:15:08 +08:00
|
|
|
*/
|
2018-12-29 12:20:44 +08:00
|
|
|
static void *xas_create(struct xa_state *xas, bool allow_root)
|
2017-11-11 04:15:08 +08:00
|
|
|
{
|
|
|
|
struct xarray *xa = xas->xa;
|
|
|
|
void *entry;
|
|
|
|
void __rcu **slot;
|
|
|
|
struct xa_node *node = xas->xa_node;
|
|
|
|
int shift;
|
|
|
|
unsigned int order = xas->xa_shift;
|
|
|
|
|
|
|
|
if (xas_top(node)) {
|
|
|
|
entry = xa_head_locked(xa);
|
|
|
|
xas->xa_node = NULL;
|
2018-10-27 02:43:22 +08:00
|
|
|
if (!entry && xa_zero_busy(xa))
|
|
|
|
entry = XA_ZERO_ENTRY;
|
2017-11-11 04:15:08 +08:00
|
|
|
shift = xas_expand(xas, entry);
|
|
|
|
if (shift < 0)
|
|
|
|
return NULL;
|
2018-12-29 12:20:44 +08:00
|
|
|
if (!shift && !allow_root)
|
|
|
|
shift = XA_CHUNK_SHIFT;
|
2017-11-11 04:15:08 +08:00
|
|
|
entry = xa_head_locked(xa);
|
|
|
|
slot = &xa->xa_head;
|
|
|
|
} else if (xas_error(xas)) {
|
|
|
|
return NULL;
|
|
|
|
} else if (node) {
|
|
|
|
unsigned int offset = xas->xa_offset;
|
|
|
|
|
|
|
|
shift = node->shift;
|
|
|
|
entry = xa_entry_locked(xa, node, offset);
|
|
|
|
slot = &node->slots[offset];
|
|
|
|
} else {
|
|
|
|
shift = 0;
|
|
|
|
entry = xa_head_locked(xa);
|
|
|
|
slot = &xa->xa_head;
|
|
|
|
}
|
|
|
|
|
|
|
|
while (shift > order) {
|
|
|
|
shift -= XA_CHUNK_SHIFT;
|
|
|
|
if (!entry) {
|
|
|
|
node = xas_alloc(xas, shift);
|
|
|
|
if (!node)
|
|
|
|
break;
|
2018-07-04 22:50:12 +08:00
|
|
|
if (xa_track_free(xa))
|
|
|
|
node_mark_all(node, XA_FREE_MARK);
|
2017-11-11 04:15:08 +08:00
|
|
|
rcu_assign_pointer(*slot, xa_mk_node(node));
|
|
|
|
} else if (xa_is_node(entry)) {
|
|
|
|
node = xa_to_node(entry);
|
|
|
|
} else {
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
entry = xas_descend(xas, node);
|
|
|
|
slot = &node->slots[xas->xa_offset];
|
|
|
|
}
|
|
|
|
|
|
|
|
return entry;
|
|
|
|
}
|
|
|
|
|
2017-12-04 13:11:48 +08:00
|
|
|
/**
|
|
|
|
* xas_create_range() - Ensure that stores to this range will succeed
|
|
|
|
* @xas: XArray operation state.
|
|
|
|
*
|
|
|
|
* Creates all of the slots in the range covered by @xas. Sets @xas to
|
|
|
|
* create single-index entries and positions it at the beginning of the
|
|
|
|
* range. This is for the benefit of users which have not yet been
|
|
|
|
* converted to use multi-index entries.
|
|
|
|
*/
|
|
|
|
void xas_create_range(struct xa_state *xas)
|
|
|
|
{
|
|
|
|
unsigned long index = xas->xa_index;
|
|
|
|
unsigned char shift = xas->xa_shift;
|
|
|
|
unsigned char sibs = xas->xa_sibs;
|
|
|
|
|
2020-10-13 20:46:29 +08:00
|
|
|
xas->xa_index |= ((sibs + 1UL) << shift) - 1;
|
2017-12-04 13:11:48 +08:00
|
|
|
if (xas_is_node(xas) && xas->xa_node->shift == xas->xa_shift)
|
|
|
|
xas->xa_offset |= sibs;
|
|
|
|
xas->xa_shift = 0;
|
|
|
|
xas->xa_sibs = 0;
|
|
|
|
|
|
|
|
for (;;) {
|
2018-12-29 12:20:44 +08:00
|
|
|
xas_create(xas, true);
|
2017-12-04 13:11:48 +08:00
|
|
|
if (xas_error(xas))
|
|
|
|
goto restore;
|
|
|
|
if (xas->xa_index <= (index | XA_CHUNK_MASK))
|
|
|
|
goto success;
|
|
|
|
xas->xa_index -= XA_CHUNK_SIZE;
|
|
|
|
|
|
|
|
for (;;) {
|
|
|
|
struct xa_node *node = xas->xa_node;
|
|
|
|
xas->xa_node = xa_parent_locked(xas->xa, node);
|
|
|
|
xas->xa_offset = node->offset - 1;
|
|
|
|
if (node->offset != 0)
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
restore:
|
|
|
|
xas->xa_shift = shift;
|
|
|
|
xas->xa_sibs = sibs;
|
|
|
|
xas->xa_index = index;
|
|
|
|
return;
|
|
|
|
success:
|
|
|
|
xas->xa_index = index;
|
|
|
|
if (xas->xa_node)
|
|
|
|
xas_set_offset(xas);
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(xas_create_range);
|
|
|
|
|
2017-11-11 04:15:08 +08:00
|
|
|
static void update_node(struct xa_state *xas, struct xa_node *node,
|
|
|
|
int count, int values)
|
|
|
|
{
|
|
|
|
if (!node || (!count && !values))
|
|
|
|
return;
|
|
|
|
|
|
|
|
node->count += count;
|
|
|
|
node->nr_values += values;
|
|
|
|
XA_NODE_BUG_ON(node, node->count > XA_CHUNK_SIZE);
|
|
|
|
XA_NODE_BUG_ON(node, node->nr_values > XA_CHUNK_SIZE);
|
|
|
|
xas_update(xas, node);
|
|
|
|
if (count < 0)
|
|
|
|
xas_delete_node(xas);
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* xas_store() - Store this entry in the XArray.
|
|
|
|
* @xas: XArray operation state.
|
|
|
|
* @entry: New entry.
|
|
|
|
*
|
|
|
|
* If @xas is operating on a multi-index entry, the entry returned by this
|
|
|
|
* function is essentially meaningless (it may be an internal entry or it
|
|
|
|
* may be %NULL, even if there are non-NULL entries at some of the indices
|
|
|
|
* covered by the range). This is not a problem for any current users,
|
|
|
|
* and can be changed if needed.
|
|
|
|
*
|
|
|
|
* Return: The old entry at this index.
|
|
|
|
*/
|
|
|
|
void *xas_store(struct xa_state *xas, void *entry)
|
|
|
|
{
|
|
|
|
struct xa_node *node;
|
|
|
|
void __rcu **slot = &xas->xa->xa_head;
|
|
|
|
unsigned int offset, max;
|
|
|
|
int count = 0;
|
|
|
|
int values = 0;
|
|
|
|
void *first, *next;
|
|
|
|
bool value = xa_is_value(entry);
|
|
|
|
|
2019-02-22 06:54:44 +08:00
|
|
|
if (entry) {
|
|
|
|
bool allow_root = !xa_is_node(entry) && !xa_is_zero(entry);
|
|
|
|
first = xas_create(xas, allow_root);
|
|
|
|
} else {
|
2017-11-11 04:15:08 +08:00
|
|
|
first = xas_load(xas);
|
2019-02-22 06:54:44 +08:00
|
|
|
}
|
2017-11-11 04:15:08 +08:00
|
|
|
|
|
|
|
if (xas_invalid(xas))
|
|
|
|
return first;
|
|
|
|
node = xas->xa_node;
|
|
|
|
if (node && (xas->xa_shift < node->shift))
|
|
|
|
xas->xa_sibs = 0;
|
|
|
|
if ((first == entry) && !xas->xa_sibs)
|
|
|
|
return first;
|
|
|
|
|
|
|
|
next = first;
|
|
|
|
offset = xas->xa_offset;
|
|
|
|
max = xas->xa_offset + xas->xa_sibs;
|
|
|
|
if (node) {
|
|
|
|
slot = &node->slots[offset];
|
|
|
|
if (xas->xa_sibs)
|
|
|
|
xas_squash_marks(xas);
|
|
|
|
}
|
|
|
|
if (!entry)
|
|
|
|
xas_init_marks(xas);
|
|
|
|
|
|
|
|
for (;;) {
|
|
|
|
/*
|
|
|
|
* Must clear the marks before setting the entry to NULL,
|
|
|
|
* otherwise xas_for_each_marked may find a NULL entry and
|
|
|
|
* stop early. rcu_assign_pointer contains a release barrier
|
|
|
|
* so the mark clearing will appear to happen before the
|
|
|
|
* entry is set to NULL.
|
|
|
|
*/
|
|
|
|
rcu_assign_pointer(*slot, entry);
|
2019-02-22 06:36:45 +08:00
|
|
|
if (xa_is_node(next) && (!node || node->shift))
|
2017-11-11 04:15:08 +08:00
|
|
|
xas_free_nodes(xas, xa_to_node(next));
|
|
|
|
if (!node)
|
|
|
|
break;
|
|
|
|
count += !next - !entry;
|
|
|
|
values += !xa_is_value(first) - !value;
|
|
|
|
if (entry) {
|
|
|
|
if (offset == max)
|
|
|
|
break;
|
|
|
|
if (!xa_is_sibling(entry))
|
|
|
|
entry = xa_mk_sibling(xas->xa_offset);
|
|
|
|
} else {
|
|
|
|
if (offset == XA_CHUNK_MASK)
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
next = xa_entry_locked(xas->xa, node, ++offset);
|
|
|
|
if (!xa_is_sibling(next)) {
|
|
|
|
if (!entry && (offset > max))
|
|
|
|
break;
|
|
|
|
first = next;
|
|
|
|
}
|
|
|
|
slot++;
|
|
|
|
}
|
|
|
|
|
|
|
|
update_node(xas, node, count, values);
|
|
|
|
return first;
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(xas_store);
|
|
|
|
|
2017-11-10 22:34:31 +08:00
|
|
|
/**
|
|
|
|
* xas_get_mark() - Returns the state of this mark.
|
|
|
|
* @xas: XArray operation state.
|
|
|
|
* @mark: Mark number.
|
|
|
|
*
|
|
|
|
* Return: true if the mark is set, false if the mark is clear or @xas
|
|
|
|
* is in an error state.
|
|
|
|
*/
|
|
|
|
bool xas_get_mark(const struct xa_state *xas, xa_mark_t mark)
|
|
|
|
{
|
|
|
|
if (xas_invalid(xas))
|
|
|
|
return false;
|
|
|
|
if (!xas->xa_node)
|
|
|
|
return xa_marked(xas->xa, mark);
|
|
|
|
return node_get_mark(xas->xa_node, xas->xa_offset, mark);
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(xas_get_mark);
|
|
|
|
|
|
|
|
/**
|
|
|
|
* xas_set_mark() - Sets the mark on this entry and its parents.
|
|
|
|
* @xas: XArray operation state.
|
|
|
|
* @mark: Mark number.
|
|
|
|
*
|
|
|
|
* Sets the specified mark on this entry, and walks up the tree setting it
|
|
|
|
* on all the ancestor entries. Does nothing if @xas has not been walked to
|
|
|
|
* an entry, or is in an error state.
|
|
|
|
*/
|
|
|
|
void xas_set_mark(const struct xa_state *xas, xa_mark_t mark)
|
|
|
|
{
|
|
|
|
struct xa_node *node = xas->xa_node;
|
|
|
|
unsigned int offset = xas->xa_offset;
|
|
|
|
|
|
|
|
if (xas_invalid(xas))
|
|
|
|
return;
|
|
|
|
|
|
|
|
while (node) {
|
|
|
|
if (node_set_mark(node, offset, mark))
|
|
|
|
return;
|
|
|
|
offset = node->offset;
|
|
|
|
node = xa_parent_locked(xas->xa, node);
|
|
|
|
}
|
|
|
|
|
|
|
|
if (!xa_marked(xas->xa, mark))
|
|
|
|
xa_mark_set(xas->xa, mark);
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(xas_set_mark);
|
|
|
|
|
|
|
|
/**
|
|
|
|
* xas_clear_mark() - Clears the mark on this entry and its parents.
|
|
|
|
* @xas: XArray operation state.
|
|
|
|
* @mark: Mark number.
|
|
|
|
*
|
|
|
|
* Clears the specified mark on this entry, and walks back to the head
|
|
|
|
* attempting to clear it on all the ancestor entries. Does nothing if
|
|
|
|
* @xas has not been walked to an entry, or is in an error state.
|
|
|
|
*/
|
|
|
|
void xas_clear_mark(const struct xa_state *xas, xa_mark_t mark)
|
|
|
|
{
|
|
|
|
struct xa_node *node = xas->xa_node;
|
|
|
|
unsigned int offset = xas->xa_offset;
|
|
|
|
|
|
|
|
if (xas_invalid(xas))
|
|
|
|
return;
|
|
|
|
|
|
|
|
while (node) {
|
|
|
|
if (!node_clear_mark(node, offset, mark))
|
|
|
|
return;
|
|
|
|
if (node_any_mark(node, mark))
|
|
|
|
return;
|
|
|
|
|
|
|
|
offset = node->offset;
|
|
|
|
node = xa_parent_locked(xas->xa, node);
|
|
|
|
}
|
|
|
|
|
|
|
|
if (xa_marked(xas->xa, mark))
|
|
|
|
xa_mark_clear(xas->xa, mark);
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(xas_clear_mark);
|
|
|
|
|
2017-11-11 04:15:08 +08:00
|
|
|
/**
|
|
|
|
* xas_init_marks() - Initialise all marks for the entry
|
|
|
|
* @xas: Array operations state.
|
|
|
|
*
|
|
|
|
* Initialise all marks for the entry specified by @xas. If we're tracking
|
|
|
|
* free entries with a mark, we need to set it on all entries. All other
|
|
|
|
* marks are cleared.
|
|
|
|
*
|
|
|
|
* This implementation is not as efficient as it could be; we may walk
|
|
|
|
* up the tree multiple times.
|
|
|
|
*/
|
|
|
|
void xas_init_marks(const struct xa_state *xas)
|
|
|
|
{
|
|
|
|
xa_mark_t mark = 0;
|
|
|
|
|
|
|
|
for (;;) {
|
2018-07-04 22:50:12 +08:00
|
|
|
if (xa_track_free(xas->xa) && mark == XA_FREE_MARK)
|
|
|
|
xas_set_mark(xas, mark);
|
|
|
|
else
|
|
|
|
xas_clear_mark(xas, mark);
|
2017-11-11 04:15:08 +08:00
|
|
|
if (mark == XA_MARK_MAX)
|
|
|
|
break;
|
|
|
|
mark_inc(mark);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(xas_init_marks);
|
|
|
|
|
2020-10-16 11:05:16 +08:00
|
|
|
#ifdef CONFIG_XARRAY_MULTI
|
|
|
|
static unsigned int node_get_marks(struct xa_node *node, unsigned int offset)
|
|
|
|
{
|
|
|
|
unsigned int marks = 0;
|
|
|
|
xa_mark_t mark = XA_MARK_0;
|
|
|
|
|
|
|
|
for (;;) {
|
|
|
|
if (node_get_mark(node, offset, mark))
|
|
|
|
marks |= 1 << (__force unsigned int)mark;
|
|
|
|
if (mark == XA_MARK_MAX)
|
|
|
|
break;
|
|
|
|
mark_inc(mark);
|
|
|
|
}
|
|
|
|
|
|
|
|
return marks;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void node_set_marks(struct xa_node *node, unsigned int offset,
|
|
|
|
struct xa_node *child, unsigned int marks)
|
|
|
|
{
|
|
|
|
xa_mark_t mark = XA_MARK_0;
|
|
|
|
|
|
|
|
for (;;) {
|
|
|
|
if (marks & (1 << (__force unsigned int)mark)) {
|
|
|
|
node_set_mark(node, offset, mark);
|
|
|
|
if (child)
|
|
|
|
node_mark_all(child, mark);
|
|
|
|
}
|
|
|
|
if (mark == XA_MARK_MAX)
|
|
|
|
break;
|
|
|
|
mark_inc(mark);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* xas_split_alloc() - Allocate memory for splitting an entry.
|
|
|
|
* @xas: XArray operation state.
|
|
|
|
* @entry: New entry which will be stored in the array.
|
2020-10-10 23:17:44 +08:00
|
|
|
* @order: Current entry order.
|
2020-10-16 11:05:16 +08:00
|
|
|
* @gfp: Memory allocation flags.
|
|
|
|
*
|
|
|
|
* This function should be called before calling xas_split().
|
|
|
|
* If necessary, it will allocate new nodes (and fill them with @entry)
|
|
|
|
* to prepare for the upcoming split of an entry of @order size into
|
|
|
|
* entries of the order stored in the @xas.
|
|
|
|
*
|
|
|
|
* Context: May sleep if @gfp flags permit.
|
|
|
|
*/
|
|
|
|
void xas_split_alloc(struct xa_state *xas, void *entry, unsigned int order,
|
|
|
|
gfp_t gfp)
|
|
|
|
{
|
|
|
|
unsigned int sibs = (1 << (order % XA_CHUNK_SHIFT)) - 1;
|
|
|
|
unsigned int mask = xas->xa_sibs;
|
|
|
|
|
|
|
|
/* XXX: no support for splitting really large entries yet */
|
|
|
|
if (WARN_ON(xas->xa_shift + 2 * XA_CHUNK_SHIFT < order))
|
|
|
|
goto nomem;
|
|
|
|
if (xas->xa_shift + XA_CHUNK_SHIFT > order)
|
|
|
|
return;
|
|
|
|
|
|
|
|
do {
|
|
|
|
unsigned int i;
|
2020-11-19 21:32:31 +08:00
|
|
|
void *sibling = NULL;
|
2020-10-16 11:05:16 +08:00
|
|
|
struct xa_node *node;
|
|
|
|
|
|
|
|
node = kmem_cache_alloc(radix_tree_node_cachep, gfp);
|
|
|
|
if (!node)
|
|
|
|
goto nomem;
|
|
|
|
node->array = xas->xa;
|
|
|
|
for (i = 0; i < XA_CHUNK_SIZE; i++) {
|
|
|
|
if ((i & mask) == 0) {
|
|
|
|
RCU_INIT_POINTER(node->slots[i], entry);
|
2020-11-19 21:32:31 +08:00
|
|
|
sibling = xa_mk_sibling(i);
|
2020-10-16 11:05:16 +08:00
|
|
|
} else {
|
|
|
|
RCU_INIT_POINTER(node->slots[i], sibling);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
RCU_INIT_POINTER(node->parent, xas->xa_alloc);
|
|
|
|
xas->xa_alloc = node;
|
|
|
|
} while (sibs-- > 0);
|
|
|
|
|
|
|
|
return;
|
|
|
|
nomem:
|
|
|
|
xas_destroy(xas);
|
|
|
|
xas_set_err(xas, -ENOMEM);
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(xas_split_alloc);
|
|
|
|
|
|
|
|
/**
|
|
|
|
* xas_split() - Split a multi-index entry into smaller entries.
|
|
|
|
* @xas: XArray operation state.
|
|
|
|
* @entry: New entry to store in the array.
|
2020-10-10 23:17:44 +08:00
|
|
|
* @order: Current entry order.
|
2020-10-16 11:05:16 +08:00
|
|
|
*
|
2020-10-10 23:17:44 +08:00
|
|
|
* The size of the new entries is set in @xas. The value in @entry is
|
|
|
|
* copied to all the replacement entries.
|
2020-10-16 11:05:16 +08:00
|
|
|
*
|
|
|
|
* Context: Any context. The caller should hold the xa_lock.
|
|
|
|
*/
|
|
|
|
void xas_split(struct xa_state *xas, void *entry, unsigned int order)
|
|
|
|
{
|
|
|
|
unsigned int sibs = (1 << (order % XA_CHUNK_SHIFT)) - 1;
|
|
|
|
unsigned int offset, marks;
|
|
|
|
struct xa_node *node;
|
|
|
|
void *curr = xas_load(xas);
|
|
|
|
int values = 0;
|
|
|
|
|
|
|
|
node = xas->xa_node;
|
|
|
|
if (xas_top(node))
|
|
|
|
return;
|
|
|
|
|
|
|
|
marks = node_get_marks(node, xas->xa_offset);
|
|
|
|
|
|
|
|
offset = xas->xa_offset + sibs;
|
|
|
|
do {
|
|
|
|
if (xas->xa_shift < node->shift) {
|
|
|
|
struct xa_node *child = xas->xa_alloc;
|
|
|
|
|
|
|
|
xas->xa_alloc = rcu_dereference_raw(child->parent);
|
|
|
|
child->shift = node->shift - XA_CHUNK_SHIFT;
|
|
|
|
child->offset = offset;
|
|
|
|
child->count = XA_CHUNK_SIZE;
|
|
|
|
child->nr_values = xa_is_value(entry) ?
|
|
|
|
XA_CHUNK_SIZE : 0;
|
|
|
|
RCU_INIT_POINTER(child->parent, node);
|
|
|
|
node_set_marks(node, offset, child, marks);
|
|
|
|
rcu_assign_pointer(node->slots[offset],
|
|
|
|
xa_mk_node(child));
|
|
|
|
if (xa_is_value(curr))
|
|
|
|
values--;
|
|
|
|
} else {
|
|
|
|
unsigned int canon = offset - xas->xa_sibs;
|
|
|
|
|
|
|
|
node_set_marks(node, canon, NULL, marks);
|
|
|
|
rcu_assign_pointer(node->slots[canon], entry);
|
|
|
|
while (offset > canon)
|
|
|
|
rcu_assign_pointer(node->slots[offset--],
|
|
|
|
xa_mk_sibling(canon));
|
|
|
|
values += (xa_is_value(entry) - xa_is_value(curr)) *
|
|
|
|
(xas->xa_sibs + 1);
|
|
|
|
}
|
|
|
|
} while (offset-- > xas->xa_offset);
|
|
|
|
|
|
|
|
node->nr_values += values;
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(xas_split);
|
|
|
|
#endif
|
|
|
|
|
2017-11-14 21:30:11 +08:00
|
|
|
/**
|
|
|
|
* xas_pause() - Pause a walk to drop a lock.
|
|
|
|
* @xas: XArray operation state.
|
|
|
|
*
|
|
|
|
* Some users need to pause a walk and drop the lock they're holding in
|
|
|
|
* order to yield to a higher priority thread or carry out an operation
|
|
|
|
* on an entry. Those users should call this function before they drop
|
|
|
|
* the lock. It resets the @xas to be suitable for the next iteration
|
|
|
|
* of the loop after the user has reacquired the lock. If most entries
|
|
|
|
* found during a walk require you to call xas_pause(), the xa_for_each()
|
|
|
|
* iterator may be more appropriate.
|
|
|
|
*
|
|
|
|
* Note that xas_pause() only works for forward iteration. If a user needs
|
|
|
|
* to pause a reverse iteration, we will need a xas_pause_rev().
|
|
|
|
*/
|
|
|
|
void xas_pause(struct xa_state *xas)
|
|
|
|
{
|
|
|
|
struct xa_node *node = xas->xa_node;
|
|
|
|
|
|
|
|
if (xas_invalid(xas))
|
|
|
|
return;
|
|
|
|
|
2019-11-08 11:49:11 +08:00
|
|
|
xas->xa_node = XAS_RESTART;
|
2017-11-14 21:30:11 +08:00
|
|
|
if (node) {
|
2020-01-31 19:17:09 +08:00
|
|
|
unsigned long offset = xas->xa_offset;
|
2017-11-14 21:30:11 +08:00
|
|
|
while (++offset < XA_CHUNK_SIZE) {
|
|
|
|
if (!xa_is_sibling(xa_entry(xas->xa, node, offset)))
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
xas->xa_index += (offset - xas->xa_offset) << node->shift;
|
2019-11-08 11:49:11 +08:00
|
|
|
if (xas->xa_index == 0)
|
|
|
|
xas->xa_node = XAS_BOUNDS;
|
2017-11-14 21:30:11 +08:00
|
|
|
} else {
|
|
|
|
xas->xa_index++;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(xas_pause);
|
|
|
|
|
2017-12-01 13:06:52 +08:00
|
|
|
/*
|
|
|
|
* __xas_prev() - Find the previous entry in the XArray.
|
|
|
|
* @xas: XArray operation state.
|
|
|
|
*
|
|
|
|
* Helper function for xas_prev() which handles all the complex cases
|
|
|
|
* out of line.
|
|
|
|
*/
|
|
|
|
void *__xas_prev(struct xa_state *xas)
|
|
|
|
{
|
|
|
|
void *entry;
|
|
|
|
|
|
|
|
if (!xas_frozen(xas->xa_node))
|
|
|
|
xas->xa_index--;
|
2019-07-02 05:03:29 +08:00
|
|
|
if (!xas->xa_node)
|
|
|
|
return set_bounds(xas);
|
2017-12-01 13:06:52 +08:00
|
|
|
if (xas_not_node(xas->xa_node))
|
|
|
|
return xas_load(xas);
|
|
|
|
|
|
|
|
if (xas->xa_offset != get_offset(xas->xa_index, xas->xa_node))
|
|
|
|
xas->xa_offset--;
|
|
|
|
|
|
|
|
while (xas->xa_offset == 255) {
|
|
|
|
xas->xa_offset = xas->xa_node->offset - 1;
|
|
|
|
xas->xa_node = xa_parent(xas->xa, xas->xa_node);
|
|
|
|
if (!xas->xa_node)
|
|
|
|
return set_bounds(xas);
|
|
|
|
}
|
|
|
|
|
|
|
|
for (;;) {
|
|
|
|
entry = xa_entry(xas->xa, xas->xa_node, xas->xa_offset);
|
|
|
|
if (!xa_is_node(entry))
|
|
|
|
return entry;
|
|
|
|
|
|
|
|
xas->xa_node = xa_to_node(entry);
|
|
|
|
xas_set_offset(xas);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(__xas_prev);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* __xas_next() - Find the next entry in the XArray.
|
|
|
|
* @xas: XArray operation state.
|
|
|
|
*
|
|
|
|
* Helper function for xas_next() which handles all the complex cases
|
|
|
|
* out of line.
|
|
|
|
*/
|
|
|
|
void *__xas_next(struct xa_state *xas)
|
|
|
|
{
|
|
|
|
void *entry;
|
|
|
|
|
|
|
|
if (!xas_frozen(xas->xa_node))
|
|
|
|
xas->xa_index++;
|
2019-07-02 05:03:29 +08:00
|
|
|
if (!xas->xa_node)
|
|
|
|
return set_bounds(xas);
|
2017-12-01 13:06:52 +08:00
|
|
|
if (xas_not_node(xas->xa_node))
|
|
|
|
return xas_load(xas);
|
|
|
|
|
|
|
|
if (xas->xa_offset != get_offset(xas->xa_index, xas->xa_node))
|
|
|
|
xas->xa_offset++;
|
|
|
|
|
|
|
|
while (xas->xa_offset == XA_CHUNK_SIZE) {
|
|
|
|
xas->xa_offset = xas->xa_node->offset + 1;
|
|
|
|
xas->xa_node = xa_parent(xas->xa, xas->xa_node);
|
|
|
|
if (!xas->xa_node)
|
|
|
|
return set_bounds(xas);
|
|
|
|
}
|
|
|
|
|
|
|
|
for (;;) {
|
|
|
|
entry = xa_entry(xas->xa, xas->xa_node, xas->xa_offset);
|
|
|
|
if (!xa_is_node(entry))
|
|
|
|
return entry;
|
|
|
|
|
|
|
|
xas->xa_node = xa_to_node(entry);
|
|
|
|
xas_set_offset(xas);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(__xas_next);
|
|
|
|
|
2017-11-14 21:30:11 +08:00
|
|
|
/**
|
|
|
|
* xas_find() - Find the next present entry in the XArray.
|
|
|
|
* @xas: XArray operation state.
|
|
|
|
* @max: Highest index to return.
|
|
|
|
*
|
|
|
|
* If the @xas has not yet been walked to an entry, return the entry
|
|
|
|
* which has an index >= xas.xa_index. If it has been walked, the entry
|
|
|
|
* currently being pointed at has been processed, and so we move to the
|
|
|
|
* next entry.
|
|
|
|
*
|
|
|
|
* If no entry is found and the array is smaller than @max, the iterator
|
|
|
|
* is set to the smallest index not yet in the array. This allows @xas
|
|
|
|
* to be immediately passed to xas_store().
|
|
|
|
*
|
|
|
|
* Return: The entry, if found, otherwise %NULL.
|
|
|
|
*/
|
|
|
|
void *xas_find(struct xa_state *xas, unsigned long max)
|
|
|
|
{
|
|
|
|
void *entry;
|
|
|
|
|
2019-11-08 11:49:11 +08:00
|
|
|
if (xas_error(xas) || xas->xa_node == XAS_BOUNDS)
|
2017-11-14 21:30:11 +08:00
|
|
|
return NULL;
|
2020-01-18 11:13:21 +08:00
|
|
|
if (xas->xa_index > max)
|
|
|
|
return set_bounds(xas);
|
2017-11-14 21:30:11 +08:00
|
|
|
|
|
|
|
if (!xas->xa_node) {
|
|
|
|
xas->xa_index = 1;
|
|
|
|
return set_bounds(xas);
|
2019-11-08 11:49:11 +08:00
|
|
|
} else if (xas->xa_node == XAS_RESTART) {
|
2017-11-14 21:30:11 +08:00
|
|
|
entry = xas_load(xas);
|
|
|
|
if (entry || xas_not_node(xas->xa_node))
|
|
|
|
return entry;
|
|
|
|
} else if (!xas->xa_node->shift &&
|
|
|
|
xas->xa_offset != (xas->xa_index & XA_CHUNK_MASK)) {
|
|
|
|
xas->xa_offset = ((xas->xa_index - 1) & XA_CHUNK_MASK) + 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
xas_advance(xas);
|
|
|
|
|
|
|
|
while (xas->xa_node && (xas->xa_index <= max)) {
|
|
|
|
if (unlikely(xas->xa_offset == XA_CHUNK_SIZE)) {
|
|
|
|
xas->xa_offset = xas->xa_node->offset + 1;
|
|
|
|
xas->xa_node = xa_parent(xas->xa, xas->xa_node);
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
|
|
|
|
entry = xa_entry(xas->xa, xas->xa_node, xas->xa_offset);
|
|
|
|
if (xa_is_node(entry)) {
|
|
|
|
xas->xa_node = xa_to_node(entry);
|
|
|
|
xas->xa_offset = 0;
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
if (entry && !xa_is_sibling(entry))
|
|
|
|
return entry;
|
|
|
|
|
|
|
|
xas_advance(xas);
|
|
|
|
}
|
|
|
|
|
|
|
|
if (!xas->xa_node)
|
|
|
|
xas->xa_node = XAS_BOUNDS;
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(xas_find);
|
|
|
|
|
|
|
|
/**
|
|
|
|
* xas_find_marked() - Find the next marked entry in the XArray.
|
|
|
|
* @xas: XArray operation state.
|
|
|
|
* @max: Highest index to return.
|
|
|
|
* @mark: Mark number to search for.
|
|
|
|
*
|
|
|
|
* If the @xas has not yet been walked to an entry, return the marked entry
|
|
|
|
* which has an index >= xas.xa_index. If it has been walked, the entry
|
|
|
|
* currently being pointed at has been processed, and so we return the
|
|
|
|
* first marked entry with an index > xas.xa_index.
|
|
|
|
*
|
|
|
|
* If no marked entry is found and the array is smaller than @max, @xas is
|
|
|
|
* set to the bounds state and xas->xa_index is set to the smallest index
|
|
|
|
* not yet in the array. This allows @xas to be immediately passed to
|
|
|
|
* xas_store().
|
|
|
|
*
|
|
|
|
* If no entry is found before @max is reached, @xas is set to the restart
|
|
|
|
* state.
|
|
|
|
*
|
|
|
|
* Return: The entry, if found, otherwise %NULL.
|
|
|
|
*/
|
|
|
|
void *xas_find_marked(struct xa_state *xas, unsigned long max, xa_mark_t mark)
|
|
|
|
{
|
|
|
|
bool advance = true;
|
|
|
|
unsigned int offset;
|
|
|
|
void *entry;
|
|
|
|
|
|
|
|
if (xas_error(xas))
|
|
|
|
return NULL;
|
2020-01-18 11:13:21 +08:00
|
|
|
if (xas->xa_index > max)
|
|
|
|
goto max;
|
2017-11-14 21:30:11 +08:00
|
|
|
|
|
|
|
if (!xas->xa_node) {
|
|
|
|
xas->xa_index = 1;
|
|
|
|
goto out;
|
|
|
|
} else if (xas_top(xas->xa_node)) {
|
|
|
|
advance = false;
|
|
|
|
entry = xa_head(xas->xa);
|
|
|
|
xas->xa_node = NULL;
|
|
|
|
if (xas->xa_index > max_index(entry))
|
2018-12-14 02:57:42 +08:00
|
|
|
goto out;
|
2017-11-14 21:30:11 +08:00
|
|
|
if (!xa_is_node(entry)) {
|
|
|
|
if (xa_marked(xas->xa, mark))
|
|
|
|
return entry;
|
|
|
|
xas->xa_index = 1;
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
xas->xa_node = xa_to_node(entry);
|
|
|
|
xas->xa_offset = xas->xa_index >> xas->xa_node->shift;
|
|
|
|
}
|
|
|
|
|
|
|
|
while (xas->xa_index <= max) {
|
|
|
|
if (unlikely(xas->xa_offset == XA_CHUNK_SIZE)) {
|
|
|
|
xas->xa_offset = xas->xa_node->offset + 1;
|
|
|
|
xas->xa_node = xa_parent(xas->xa, xas->xa_node);
|
|
|
|
if (!xas->xa_node)
|
|
|
|
break;
|
|
|
|
advance = false;
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (!advance) {
|
|
|
|
entry = xa_entry(xas->xa, xas->xa_node, xas->xa_offset);
|
|
|
|
if (xa_is_sibling(entry)) {
|
|
|
|
xas->xa_offset = xa_to_sibling(entry);
|
|
|
|
xas_move_index(xas, xas->xa_offset);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
offset = xas_find_chunk(xas, advance, mark);
|
|
|
|
if (offset > xas->xa_offset) {
|
|
|
|
advance = false;
|
|
|
|
xas_move_index(xas, offset);
|
|
|
|
/* Mind the wrap */
|
|
|
|
if ((xas->xa_index - 1) >= max)
|
|
|
|
goto max;
|
|
|
|
xas->xa_offset = offset;
|
|
|
|
if (offset == XA_CHUNK_SIZE)
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
|
|
|
|
entry = xa_entry(xas->xa, xas->xa_node, xas->xa_offset);
|
2020-03-13 05:29:11 +08:00
|
|
|
if (!entry && !(xa_track_free(xas->xa) && mark == XA_FREE_MARK))
|
|
|
|
continue;
|
2017-11-14 21:30:11 +08:00
|
|
|
if (!xa_is_node(entry))
|
|
|
|
return entry;
|
|
|
|
xas->xa_node = xa_to_node(entry);
|
|
|
|
xas_set_offset(xas);
|
|
|
|
}
|
|
|
|
|
|
|
|
out:
|
2018-12-14 02:57:42 +08:00
|
|
|
if (xas->xa_index > max)
|
2017-11-14 21:30:11 +08:00
|
|
|
goto max;
|
2018-12-14 02:57:42 +08:00
|
|
|
return set_bounds(xas);
|
2017-11-14 21:30:11 +08:00
|
|
|
max:
|
|
|
|
xas->xa_node = XAS_RESTART;
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(xas_find_marked);
|
|
|
|
|
2018-06-02 10:46:02 +08:00
|
|
|
/**
|
|
|
|
* xas_find_conflict() - Find the next present entry in a range.
|
|
|
|
* @xas: XArray operation state.
|
|
|
|
*
|
|
|
|
* The @xas describes both a range and a position within that range.
|
|
|
|
*
|
|
|
|
* Context: Any context. Expects xa_lock to be held.
|
|
|
|
* Return: The next entry in the range covered by @xas or %NULL.
|
|
|
|
*/
|
|
|
|
void *xas_find_conflict(struct xa_state *xas)
|
|
|
|
{
|
|
|
|
void *curr;
|
|
|
|
|
|
|
|
if (xas_error(xas))
|
|
|
|
return NULL;
|
|
|
|
|
|
|
|
if (!xas->xa_node)
|
|
|
|
return NULL;
|
|
|
|
|
|
|
|
if (xas_top(xas->xa_node)) {
|
|
|
|
curr = xas_start(xas);
|
|
|
|
if (!curr)
|
|
|
|
return NULL;
|
|
|
|
while (xa_is_node(curr)) {
|
|
|
|
struct xa_node *node = xa_to_node(curr);
|
|
|
|
curr = xas_descend(xas, node);
|
|
|
|
}
|
|
|
|
if (curr)
|
|
|
|
return curr;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (xas->xa_node->shift > xas->xa_shift)
|
|
|
|
return NULL;
|
|
|
|
|
|
|
|
for (;;) {
|
|
|
|
if (xas->xa_node->shift == xas->xa_shift) {
|
|
|
|
if ((xas->xa_offset & xas->xa_sibs) == xas->xa_sibs)
|
|
|
|
break;
|
|
|
|
} else if (xas->xa_offset == XA_CHUNK_MASK) {
|
|
|
|
xas->xa_offset = xas->xa_node->offset;
|
|
|
|
xas->xa_node = xa_parent_locked(xas->xa, xas->xa_node);
|
|
|
|
if (!xas->xa_node)
|
|
|
|
break;
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
curr = xa_entry_locked(xas->xa, xas->xa_node, ++xas->xa_offset);
|
|
|
|
if (xa_is_sibling(curr))
|
|
|
|
continue;
|
|
|
|
while (xa_is_node(curr)) {
|
|
|
|
xas->xa_node = xa_to_node(curr);
|
|
|
|
xas->xa_offset = 0;
|
|
|
|
curr = xa_entry_locked(xas->xa, xas->xa_node, 0);
|
|
|
|
}
|
|
|
|
if (curr)
|
|
|
|
return curr;
|
|
|
|
}
|
|
|
|
xas->xa_offset -= xas->xa_sibs;
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(xas_find_conflict);
|
|
|
|
|
2017-11-08 03:57:46 +08:00
|
|
|
/**
|
|
|
|
* xa_load() - Load an entry from an XArray.
|
|
|
|
* @xa: XArray.
|
|
|
|
* @index: index into array.
|
|
|
|
*
|
|
|
|
* Context: Any context. Takes and releases the RCU lock.
|
|
|
|
* Return: The entry at @index in @xa.
|
|
|
|
*/
|
|
|
|
void *xa_load(struct xarray *xa, unsigned long index)
|
|
|
|
{
|
|
|
|
XA_STATE(xas, xa, index);
|
|
|
|
void *entry;
|
|
|
|
|
|
|
|
rcu_read_lock();
|
|
|
|
do {
|
|
|
|
entry = xas_load(&xas);
|
2018-10-02 02:54:59 +08:00
|
|
|
if (xa_is_zero(entry))
|
|
|
|
entry = NULL;
|
2017-11-08 03:57:46 +08:00
|
|
|
} while (xas_retry(&xas, entry));
|
|
|
|
rcu_read_unlock();
|
|
|
|
|
|
|
|
return entry;
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL(xa_load);
|
|
|
|
|
2017-11-11 04:15:08 +08:00
|
|
|
static void *xas_result(struct xa_state *xas, void *curr)
|
|
|
|
{
|
2018-10-02 02:54:59 +08:00
|
|
|
if (xa_is_zero(curr))
|
|
|
|
return NULL;
|
2017-11-11 04:15:08 +08:00
|
|
|
if (xas_error(xas))
|
|
|
|
curr = xas->xa_node;
|
|
|
|
return curr;
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* __xa_erase() - Erase this entry from the XArray while locked.
|
|
|
|
* @xa: XArray.
|
|
|
|
* @index: Index into array.
|
|
|
|
*
|
2019-01-26 13:52:26 +08:00
|
|
|
* After this function returns, loading from @index will return %NULL.
|
|
|
|
* If the index is part of a multi-index entry, all indices will be erased
|
|
|
|
* and none of the entries will be part of a multi-index entry.
|
2017-11-11 04:15:08 +08:00
|
|
|
*
|
2019-01-26 13:52:26 +08:00
|
|
|
* Context: Any context. Expects xa_lock to be held on entry.
|
|
|
|
* Return: The entry which used to be at this index.
|
2017-11-11 04:15:08 +08:00
|
|
|
*/
|
|
|
|
void *__xa_erase(struct xarray *xa, unsigned long index)
|
|
|
|
{
|
|
|
|
XA_STATE(xas, xa, index);
|
|
|
|
return xas_result(&xas, xas_store(&xas, NULL));
|
|
|
|
}
|
2018-11-02 10:52:06 +08:00
|
|
|
EXPORT_SYMBOL(__xa_erase);
|
2017-11-11 04:15:08 +08:00
|
|
|
|
2018-11-06 04:48:49 +08:00
|
|
|
/**
|
|
|
|
* xa_erase() - Erase this entry from the XArray.
|
|
|
|
* @xa: XArray.
|
|
|
|
* @index: Index of entry.
|
|
|
|
*
|
2019-01-26 13:52:26 +08:00
|
|
|
* After this function returns, loading from @index will return %NULL.
|
|
|
|
* If the index is part of a multi-index entry, all indices will be erased
|
|
|
|
* and none of the entries will be part of a multi-index entry.
|
2018-11-06 04:48:49 +08:00
|
|
|
*
|
|
|
|
* Context: Any context. Takes and releases the xa_lock.
|
|
|
|
* Return: The entry which used to be at this index.
|
|
|
|
*/
|
|
|
|
void *xa_erase(struct xarray *xa, unsigned long index)
|
|
|
|
{
|
|
|
|
void *entry;
|
|
|
|
|
|
|
|
xa_lock(xa);
|
|
|
|
entry = __xa_erase(xa, index);
|
|
|
|
xa_unlock(xa);
|
|
|
|
|
|
|
|
return entry;
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL(xa_erase);
|
|
|
|
|
2017-11-11 04:15:08 +08:00
|
|
|
/**
|
2018-11-06 04:56:17 +08:00
|
|
|
* __xa_store() - Store this entry in the XArray.
|
2017-11-11 04:15:08 +08:00
|
|
|
* @xa: XArray.
|
|
|
|
* @index: Index into array.
|
|
|
|
* @entry: New entry.
|
|
|
|
* @gfp: Memory allocation flags.
|
|
|
|
*
|
2018-11-06 04:56:17 +08:00
|
|
|
* You must already be holding the xa_lock when calling this function.
|
|
|
|
* It will drop the lock if needed to allocate memory, and then reacquire
|
|
|
|
* it afterwards.
|
2017-11-11 04:15:08 +08:00
|
|
|
*
|
2018-11-06 04:56:17 +08:00
|
|
|
* Context: Any context. Expects xa_lock to be held on entry. May
|
|
|
|
* release and reacquire xa_lock if @gfp flags permit.
|
|
|
|
* Return: The old entry at this index or xa_err() if an error happened.
|
2017-11-11 04:15:08 +08:00
|
|
|
*/
|
2018-11-06 04:56:17 +08:00
|
|
|
void *__xa_store(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp)
|
2017-11-11 04:15:08 +08:00
|
|
|
{
|
|
|
|
XA_STATE(xas, xa, index);
|
|
|
|
void *curr;
|
|
|
|
|
2018-12-29 12:20:44 +08:00
|
|
|
if (WARN_ON_ONCE(xa_is_advanced(entry)))
|
2017-11-11 04:15:08 +08:00
|
|
|
return XA_ERROR(-EINVAL);
|
2018-11-06 05:15:56 +08:00
|
|
|
if (xa_track_free(xa) && !entry)
|
|
|
|
entry = XA_ZERO_ENTRY;
|
2017-11-11 04:15:08 +08:00
|
|
|
|
|
|
|
do {
|
|
|
|
curr = xas_store(&xas, entry);
|
2018-11-06 05:15:56 +08:00
|
|
|
if (xa_track_free(xa))
|
2018-07-04 22:50:12 +08:00
|
|
|
xas_clear_mark(&xas, XA_FREE_MARK);
|
2018-11-06 04:56:17 +08:00
|
|
|
} while (__xas_nomem(&xas, gfp));
|
2017-11-11 04:15:08 +08:00
|
|
|
|
|
|
|
return xas_result(&xas, curr);
|
|
|
|
}
|
2018-11-06 04:56:17 +08:00
|
|
|
EXPORT_SYMBOL(__xa_store);
|
2017-11-11 04:15:08 +08:00
|
|
|
|
|
|
|
/**
|
2018-11-06 04:56:17 +08:00
|
|
|
* xa_store() - Store this entry in the XArray.
|
2017-11-11 04:15:08 +08:00
|
|
|
* @xa: XArray.
|
|
|
|
* @index: Index into array.
|
|
|
|
* @entry: New entry.
|
|
|
|
* @gfp: Memory allocation flags.
|
|
|
|
*
|
2018-11-06 04:56:17 +08:00
|
|
|
* After this function returns, loads from this index will return @entry.
|
2020-10-16 11:05:16 +08:00
|
|
|
* Storing into an existing multi-index entry updates the entry of every index.
|
2018-11-06 04:56:17 +08:00
|
|
|
* The marks associated with @index are unaffected unless @entry is %NULL.
|
2017-11-11 04:15:08 +08:00
|
|
|
*
|
2018-11-06 04:56:17 +08:00
|
|
|
* Context: Any context. Takes and releases the xa_lock.
|
|
|
|
* May sleep if the @gfp flags permit.
|
|
|
|
* Return: The old entry at this index on success, xa_err(-EINVAL) if @entry
|
|
|
|
* cannot be stored in an XArray, or xa_err(-ENOMEM) if memory allocation
|
|
|
|
* failed.
|
2017-11-11 04:15:08 +08:00
|
|
|
*/
|
2018-11-06 04:56:17 +08:00
|
|
|
void *xa_store(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp)
|
2017-11-11 04:15:08 +08:00
|
|
|
{
|
|
|
|
void *curr;
|
|
|
|
|
2018-11-06 04:56:17 +08:00
|
|
|
xa_lock(xa);
|
|
|
|
curr = __xa_store(xa, index, entry, gfp);
|
|
|
|
xa_unlock(xa);
|
2017-11-11 04:15:08 +08:00
|
|
|
|
2018-11-06 04:56:17 +08:00
|
|
|
return curr;
|
2017-11-11 04:15:08 +08:00
|
|
|
}
|
2018-11-06 04:56:17 +08:00
|
|
|
EXPORT_SYMBOL(xa_store);
|
2017-11-11 04:15:08 +08:00
|
|
|
|
2017-11-11 04:34:55 +08:00
|
|
|
/**
|
|
|
|
* __xa_cmpxchg() - Store this entry in the XArray.
|
|
|
|
* @xa: XArray.
|
|
|
|
* @index: Index into array.
|
|
|
|
* @old: Old value to test against.
|
|
|
|
* @entry: New entry.
|
|
|
|
* @gfp: Memory allocation flags.
|
|
|
|
*
|
|
|
|
* You must already be holding the xa_lock when calling this function.
|
|
|
|
* It will drop the lock if needed to allocate memory, and then reacquire
|
|
|
|
* it afterwards.
|
|
|
|
*
|
|
|
|
* Context: Any context. Expects xa_lock to be held on entry. May
|
|
|
|
* release and reacquire xa_lock if @gfp flags permit.
|
|
|
|
* Return: The old entry at this index or xa_err() if an error happened.
|
|
|
|
*/
|
|
|
|
void *__xa_cmpxchg(struct xarray *xa, unsigned long index,
|
|
|
|
void *old, void *entry, gfp_t gfp)
|
|
|
|
{
|
|
|
|
XA_STATE(xas, xa, index);
|
|
|
|
void *curr;
|
|
|
|
|
2018-12-29 12:20:44 +08:00
|
|
|
if (WARN_ON_ONCE(xa_is_advanced(entry)))
|
2017-11-11 04:34:55 +08:00
|
|
|
return XA_ERROR(-EINVAL);
|
|
|
|
|
|
|
|
do {
|
|
|
|
curr = xas_load(&xas);
|
2018-07-04 22:50:12 +08:00
|
|
|
if (curr == old) {
|
2017-11-11 04:34:55 +08:00
|
|
|
xas_store(&xas, entry);
|
2019-02-21 00:30:49 +08:00
|
|
|
if (xa_track_free(xa) && entry && !curr)
|
2018-07-04 22:50:12 +08:00
|
|
|
xas_clear_mark(&xas, XA_FREE_MARK);
|
|
|
|
}
|
2017-11-11 04:34:55 +08:00
|
|
|
} while (__xas_nomem(&xas, gfp));
|
|
|
|
|
|
|
|
return xas_result(&xas, curr);
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL(__xa_cmpxchg);
|
|
|
|
|
2019-01-03 02:57:03 +08:00
|
|
|
/**
|
|
|
|
* __xa_insert() - Store this entry in the XArray if no entry is present.
|
|
|
|
* @xa: XArray.
|
|
|
|
* @index: Index into array.
|
|
|
|
* @entry: New entry.
|
|
|
|
* @gfp: Memory allocation flags.
|
|
|
|
*
|
|
|
|
* Inserting a NULL entry will store a reserved entry (like xa_reserve())
|
|
|
|
* if no entry is present. Inserting will fail if a reserved entry is
|
|
|
|
* present, even though loading from this index will return NULL.
|
|
|
|
*
|
|
|
|
* Context: Any context. Expects xa_lock to be held on entry. May
|
|
|
|
* release and reacquire xa_lock if @gfp flags permit.
|
2019-02-07 02:07:11 +08:00
|
|
|
* Return: 0 if the store succeeded. -EBUSY if another entry was present.
|
2019-01-03 02:57:03 +08:00
|
|
|
* -ENOMEM if memory could not be allocated.
|
|
|
|
*/
|
|
|
|
int __xa_insert(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp)
|
|
|
|
{
|
|
|
|
XA_STATE(xas, xa, index);
|
|
|
|
void *curr;
|
|
|
|
|
|
|
|
if (WARN_ON_ONCE(xa_is_advanced(entry)))
|
|
|
|
return -EINVAL;
|
|
|
|
if (!entry)
|
|
|
|
entry = XA_ZERO_ENTRY;
|
|
|
|
|
|
|
|
do {
|
|
|
|
curr = xas_load(&xas);
|
|
|
|
if (!curr) {
|
|
|
|
xas_store(&xas, entry);
|
|
|
|
if (xa_track_free(xa))
|
|
|
|
xas_clear_mark(&xas, XA_FREE_MARK);
|
|
|
|
} else {
|
2019-02-07 02:07:11 +08:00
|
|
|
xas_set_err(&xas, -EBUSY);
|
2019-01-03 02:57:03 +08:00
|
|
|
}
|
|
|
|
} while (__xas_nomem(&xas, gfp));
|
|
|
|
|
|
|
|
return xas_error(&xas);
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL(__xa_insert);
|
|
|
|
|
2018-08-16 02:13:29 +08:00
|
|
|
#ifdef CONFIG_XARRAY_MULTI
|
|
|
|
static void xas_set_range(struct xa_state *xas, unsigned long first,
|
|
|
|
unsigned long last)
|
|
|
|
{
|
|
|
|
unsigned int shift = 0;
|
|
|
|
unsigned long sibs = last - first;
|
|
|
|
unsigned int offset = XA_CHUNK_MASK;
|
|
|
|
|
|
|
|
xas_set(xas, first);
|
|
|
|
|
|
|
|
while ((first & XA_CHUNK_MASK) == 0) {
|
|
|
|
if (sibs < XA_CHUNK_MASK)
|
|
|
|
break;
|
|
|
|
if ((sibs == XA_CHUNK_MASK) && (offset < XA_CHUNK_MASK))
|
|
|
|
break;
|
|
|
|
shift += XA_CHUNK_SHIFT;
|
|
|
|
if (offset == XA_CHUNK_MASK)
|
|
|
|
offset = sibs & XA_CHUNK_MASK;
|
|
|
|
sibs >>= XA_CHUNK_SHIFT;
|
|
|
|
first >>= XA_CHUNK_SHIFT;
|
|
|
|
}
|
|
|
|
|
|
|
|
offset = first & XA_CHUNK_MASK;
|
|
|
|
if (offset + sibs > XA_CHUNK_MASK)
|
|
|
|
sibs = XA_CHUNK_MASK - offset;
|
|
|
|
if ((((first + sibs + 1) << shift) - 1) > last)
|
|
|
|
sibs -= 1;
|
|
|
|
|
|
|
|
xas->xa_shift = shift;
|
|
|
|
xas->xa_sibs = sibs;
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* xa_store_range() - Store this entry at a range of indices in the XArray.
|
|
|
|
* @xa: XArray.
|
|
|
|
* @first: First index to affect.
|
|
|
|
* @last: Last index to affect.
|
|
|
|
* @entry: New entry.
|
|
|
|
* @gfp: Memory allocation flags.
|
|
|
|
*
|
|
|
|
* After this function returns, loads from any index between @first and @last,
|
|
|
|
* inclusive will return @entry.
|
2020-10-16 11:05:16 +08:00
|
|
|
* Storing into an existing multi-index entry updates the entry of every index.
|
2018-08-16 02:13:29 +08:00
|
|
|
* The marks associated with @index are unaffected unless @entry is %NULL.
|
|
|
|
*
|
|
|
|
* Context: Process context. Takes and releases the xa_lock. May sleep
|
|
|
|
* if the @gfp flags permit.
|
|
|
|
* Return: %NULL on success, xa_err(-EINVAL) if @entry cannot be stored in
|
|
|
|
* an XArray, or xa_err(-ENOMEM) if memory allocation failed.
|
|
|
|
*/
|
|
|
|
void *xa_store_range(struct xarray *xa, unsigned long first,
|
|
|
|
unsigned long last, void *entry, gfp_t gfp)
|
|
|
|
{
|
|
|
|
XA_STATE(xas, xa, 0);
|
|
|
|
|
|
|
|
if (WARN_ON_ONCE(xa_is_internal(entry)))
|
|
|
|
return XA_ERROR(-EINVAL);
|
|
|
|
if (last < first)
|
|
|
|
return XA_ERROR(-EINVAL);
|
|
|
|
|
|
|
|
do {
|
|
|
|
xas_lock(&xas);
|
|
|
|
if (entry) {
|
2018-11-05 23:53:09 +08:00
|
|
|
unsigned int order = BITS_PER_LONG;
|
|
|
|
if (last + 1)
|
|
|
|
order = __ffs(last + 1);
|
2018-08-16 02:13:29 +08:00
|
|
|
xas_set_order(&xas, last, order);
|
2018-12-29 12:20:44 +08:00
|
|
|
xas_create(&xas, true);
|
2018-08-16 02:13:29 +08:00
|
|
|
if (xas_error(&xas))
|
|
|
|
goto unlock;
|
|
|
|
}
|
|
|
|
do {
|
|
|
|
xas_set_range(&xas, first, last);
|
|
|
|
xas_store(&xas, entry);
|
|
|
|
if (xas_error(&xas))
|
|
|
|
goto unlock;
|
|
|
|
first += xas_size(&xas);
|
|
|
|
} while (first <= last);
|
|
|
|
unlock:
|
|
|
|
xas_unlock(&xas);
|
|
|
|
} while (xas_nomem(&xas, gfp));
|
|
|
|
|
|
|
|
return xas_result(&xas, NULL);
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL(xa_store_range);
|
2020-10-16 11:05:13 +08:00
|
|
|
|
|
|
|
/**
|
|
|
|
* xa_get_order() - Get the order of an entry.
|
|
|
|
* @xa: XArray.
|
|
|
|
* @index: Index of the entry.
|
|
|
|
*
|
|
|
|
* Return: A number between 0 and 63 indicating the order of the entry.
|
|
|
|
*/
|
|
|
|
int xa_get_order(struct xarray *xa, unsigned long index)
|
|
|
|
{
|
|
|
|
XA_STATE(xas, xa, index);
|
|
|
|
void *entry;
|
|
|
|
int order = 0;
|
|
|
|
|
|
|
|
rcu_read_lock();
|
|
|
|
entry = xas_load(&xas);
|
|
|
|
|
|
|
|
if (!entry)
|
|
|
|
goto unlock;
|
|
|
|
|
|
|
|
if (!xas.xa_node)
|
|
|
|
goto unlock;
|
|
|
|
|
|
|
|
for (;;) {
|
|
|
|
unsigned int slot = xas.xa_offset + (1 << order);
|
|
|
|
|
|
|
|
if (slot >= XA_CHUNK_SIZE)
|
|
|
|
break;
|
|
|
|
if (!xa_is_sibling(xas.xa_node->slots[slot]))
|
|
|
|
break;
|
|
|
|
order++;
|
|
|
|
}
|
|
|
|
|
|
|
|
order += xas.xa_node->shift;
|
|
|
|
unlock:
|
|
|
|
rcu_read_unlock();
|
|
|
|
|
|
|
|
return order;
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL(xa_get_order);
|
2018-08-16 02:13:29 +08:00
|
|
|
#endif /* CONFIG_XARRAY_MULTI */
|
|
|
|
|
2018-07-04 22:50:12 +08:00
|
|
|
/**
|
|
|
|
* __xa_alloc() - Find somewhere to store this entry in the XArray.
|
|
|
|
* @xa: XArray.
|
|
|
|
* @id: Pointer to ID.
|
2018-12-31 23:41:01 +08:00
|
|
|
* @limit: Range for allocated ID.
|
2018-07-04 22:50:12 +08:00
|
|
|
* @entry: New entry.
|
|
|
|
* @gfp: Memory allocation flags.
|
|
|
|
*
|
2018-12-31 23:41:01 +08:00
|
|
|
* Finds an empty entry in @xa between @limit.min and @limit.max,
|
|
|
|
* stores the index into the @id pointer, then stores the entry at
|
|
|
|
* that index. A concurrent lookup will not see an uninitialised @id.
|
2018-07-04 22:50:12 +08:00
|
|
|
*
|
|
|
|
* Context: Any context. Expects xa_lock to be held on entry. May
|
|
|
|
* release and reacquire xa_lock if @gfp flags permit.
|
2018-12-31 23:41:01 +08:00
|
|
|
* Return: 0 on success, -ENOMEM if memory could not be allocated or
|
|
|
|
* -EBUSY if there are no free entries in @limit.
|
2018-07-04 22:50:12 +08:00
|
|
|
*/
|
2018-12-31 23:41:01 +08:00
|
|
|
int __xa_alloc(struct xarray *xa, u32 *id, void *entry,
|
|
|
|
struct xa_limit limit, gfp_t gfp)
|
2018-07-04 22:50:12 +08:00
|
|
|
{
|
|
|
|
XA_STATE(xas, xa, 0);
|
|
|
|
|
2018-12-29 12:20:44 +08:00
|
|
|
if (WARN_ON_ONCE(xa_is_advanced(entry)))
|
2018-07-04 22:50:12 +08:00
|
|
|
return -EINVAL;
|
|
|
|
if (WARN_ON_ONCE(!xa_track_free(xa)))
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
if (!entry)
|
|
|
|
entry = XA_ZERO_ENTRY;
|
|
|
|
|
|
|
|
do {
|
2018-12-31 23:41:01 +08:00
|
|
|
xas.xa_index = limit.min;
|
|
|
|
xas_find_marked(&xas, limit.max, XA_FREE_MARK);
|
2018-07-04 22:50:12 +08:00
|
|
|
if (xas.xa_node == XAS_RESTART)
|
2018-12-31 23:41:01 +08:00
|
|
|
xas_set_err(&xas, -EBUSY);
|
|
|
|
else
|
|
|
|
*id = xas.xa_index;
|
2018-07-04 22:50:12 +08:00
|
|
|
xas_store(&xas, entry);
|
|
|
|
xas_clear_mark(&xas, XA_FREE_MARK);
|
|
|
|
} while (__xas_nomem(&xas, gfp));
|
|
|
|
|
2018-12-31 23:41:01 +08:00
|
|
|
return xas_error(&xas);
|
2018-07-04 22:50:12 +08:00
|
|
|
}
|
|
|
|
EXPORT_SYMBOL(__xa_alloc);
|
|
|
|
|
2018-11-07 03:13:35 +08:00
|
|
|
/**
|
|
|
|
* __xa_alloc_cyclic() - Find somewhere to store this entry in the XArray.
|
|
|
|
* @xa: XArray.
|
|
|
|
* @id: Pointer to ID.
|
|
|
|
* @entry: New entry.
|
|
|
|
* @limit: Range of allocated ID.
|
|
|
|
* @next: Pointer to next ID to allocate.
|
|
|
|
* @gfp: Memory allocation flags.
|
|
|
|
*
|
|
|
|
* Finds an empty entry in @xa between @limit.min and @limit.max,
|
|
|
|
* stores the index into the @id pointer, then stores the entry at
|
|
|
|
* that index. A concurrent lookup will not see an uninitialised @id.
|
|
|
|
* The search for an empty entry will start at @next and will wrap
|
|
|
|
* around if necessary.
|
|
|
|
*
|
|
|
|
* Context: Any context. Expects xa_lock to be held on entry. May
|
|
|
|
* release and reacquire xa_lock if @gfp flags permit.
|
|
|
|
* Return: 0 if the allocation succeeded without wrapping. 1 if the
|
|
|
|
* allocation succeeded after wrapping, -ENOMEM if memory could not be
|
|
|
|
* allocated or -EBUSY if there are no free entries in @limit.
|
|
|
|
*/
|
|
|
|
int __xa_alloc_cyclic(struct xarray *xa, u32 *id, void *entry,
|
|
|
|
struct xa_limit limit, u32 *next, gfp_t gfp)
|
|
|
|
{
|
|
|
|
u32 min = limit.min;
|
|
|
|
int ret;
|
|
|
|
|
|
|
|
limit.min = max(min, *next);
|
|
|
|
ret = __xa_alloc(xa, id, entry, limit, gfp);
|
|
|
|
if ((xa->xa_flags & XA_FLAGS_ALLOC_WRAPPED) && ret == 0) {
|
|
|
|
xa->xa_flags &= ~XA_FLAGS_ALLOC_WRAPPED;
|
|
|
|
ret = 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (ret < 0 && limit.min > min) {
|
|
|
|
limit.min = min;
|
|
|
|
ret = __xa_alloc(xa, id, entry, limit, gfp);
|
|
|
|
if (ret == 0)
|
|
|
|
ret = 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (ret >= 0) {
|
|
|
|
*next = *id + 1;
|
|
|
|
if (*next == 0)
|
|
|
|
xa->xa_flags |= XA_FLAGS_ALLOC_WRAPPED;
|
|
|
|
}
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL(__xa_alloc_cyclic);
|
|
|
|
|
2017-11-10 22:34:31 +08:00
|
|
|
/**
|
|
|
|
* __xa_set_mark() - Set this mark on this entry while locked.
|
|
|
|
* @xa: XArray.
|
|
|
|
* @index: Index of entry.
|
|
|
|
* @mark: Mark number.
|
|
|
|
*
|
2018-11-06 05:37:15 +08:00
|
|
|
* Attempting to set a mark on a %NULL entry does not succeed.
|
2017-11-10 22:34:31 +08:00
|
|
|
*
|
|
|
|
* Context: Any context. Expects xa_lock to be held on entry.
|
|
|
|
*/
|
|
|
|
void __xa_set_mark(struct xarray *xa, unsigned long index, xa_mark_t mark)
|
|
|
|
{
|
|
|
|
XA_STATE(xas, xa, index);
|
|
|
|
void *entry = xas_load(&xas);
|
|
|
|
|
|
|
|
if (entry)
|
|
|
|
xas_set_mark(&xas, mark);
|
|
|
|
}
|
2018-11-02 10:52:06 +08:00
|
|
|
EXPORT_SYMBOL(__xa_set_mark);
|
2017-11-10 22:34:31 +08:00
|
|
|
|
|
|
|
/**
|
|
|
|
* __xa_clear_mark() - Clear this mark on this entry while locked.
|
|
|
|
* @xa: XArray.
|
|
|
|
* @index: Index of entry.
|
|
|
|
* @mark: Mark number.
|
|
|
|
*
|
|
|
|
* Context: Any context. Expects xa_lock to be held on entry.
|
|
|
|
*/
|
|
|
|
void __xa_clear_mark(struct xarray *xa, unsigned long index, xa_mark_t mark)
|
|
|
|
{
|
|
|
|
XA_STATE(xas, xa, index);
|
|
|
|
void *entry = xas_load(&xas);
|
|
|
|
|
|
|
|
if (entry)
|
|
|
|
xas_clear_mark(&xas, mark);
|
|
|
|
}
|
2018-11-02 10:52:06 +08:00
|
|
|
EXPORT_SYMBOL(__xa_clear_mark);
|
2017-11-10 22:34:31 +08:00
|
|
|
|
|
|
|
/**
|
|
|
|
* xa_get_mark() - Inquire whether this mark is set on this entry.
|
|
|
|
* @xa: XArray.
|
|
|
|
* @index: Index of entry.
|
|
|
|
* @mark: Mark number.
|
|
|
|
*
|
|
|
|
* This function uses the RCU read lock, so the result may be out of date
|
|
|
|
* by the time it returns. If you need the result to be stable, use a lock.
|
|
|
|
*
|
|
|
|
* Context: Any context. Takes and releases the RCU lock.
|
|
|
|
* Return: True if the entry at @index has this mark set, false if it doesn't.
|
|
|
|
*/
|
|
|
|
bool xa_get_mark(struct xarray *xa, unsigned long index, xa_mark_t mark)
|
|
|
|
{
|
|
|
|
XA_STATE(xas, xa, index);
|
|
|
|
void *entry;
|
|
|
|
|
|
|
|
rcu_read_lock();
|
|
|
|
entry = xas_start(&xas);
|
|
|
|
while (xas_get_mark(&xas, mark)) {
|
|
|
|
if (!xa_is_node(entry))
|
|
|
|
goto found;
|
|
|
|
entry = xas_descend(&xas, xa_to_node(entry));
|
|
|
|
}
|
|
|
|
rcu_read_unlock();
|
|
|
|
return false;
|
|
|
|
found:
|
|
|
|
rcu_read_unlock();
|
|
|
|
return true;
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL(xa_get_mark);
|
|
|
|
|
|
|
|
/**
|
|
|
|
* xa_set_mark() - Set this mark on this entry.
|
|
|
|
* @xa: XArray.
|
|
|
|
* @index: Index of entry.
|
|
|
|
* @mark: Mark number.
|
|
|
|
*
|
2018-11-06 05:37:15 +08:00
|
|
|
* Attempting to set a mark on a %NULL entry does not succeed.
|
2017-11-10 22:34:31 +08:00
|
|
|
*
|
|
|
|
* Context: Process context. Takes and releases the xa_lock.
|
|
|
|
*/
|
|
|
|
void xa_set_mark(struct xarray *xa, unsigned long index, xa_mark_t mark)
|
|
|
|
{
|
|
|
|
xa_lock(xa);
|
|
|
|
__xa_set_mark(xa, index, mark);
|
|
|
|
xa_unlock(xa);
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL(xa_set_mark);
|
|
|
|
|
|
|
|
/**
|
|
|
|
* xa_clear_mark() - Clear this mark on this entry.
|
|
|
|
* @xa: XArray.
|
|
|
|
* @index: Index of entry.
|
|
|
|
* @mark: Mark number.
|
|
|
|
*
|
|
|
|
* Clearing a mark always succeeds.
|
|
|
|
*
|
|
|
|
* Context: Process context. Takes and releases the xa_lock.
|
|
|
|
*/
|
|
|
|
void xa_clear_mark(struct xarray *xa, unsigned long index, xa_mark_t mark)
|
|
|
|
{
|
|
|
|
xa_lock(xa);
|
|
|
|
__xa_clear_mark(xa, index, mark);
|
|
|
|
xa_unlock(xa);
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL(xa_clear_mark);
|
|
|
|
|
2017-11-14 21:30:11 +08:00
|
|
|
/**
|
|
|
|
* xa_find() - Search the XArray for an entry.
|
|
|
|
* @xa: XArray.
|
|
|
|
* @indexp: Pointer to an index.
|
|
|
|
* @max: Maximum index to search to.
|
|
|
|
* @filter: Selection criterion.
|
|
|
|
*
|
|
|
|
* Finds the entry in @xa which matches the @filter, and has the lowest
|
|
|
|
* index that is at least @indexp and no more than @max.
|
|
|
|
* If an entry is found, @indexp is updated to be the index of the entry.
|
|
|
|
* This function is protected by the RCU read lock, so it may not find
|
|
|
|
* entries which are being simultaneously added. It will not return an
|
|
|
|
* %XA_RETRY_ENTRY; if you need to see retry entries, use xas_find().
|
|
|
|
*
|
|
|
|
* Context: Any context. Takes and releases the RCU lock.
|
|
|
|
* Return: The entry, if found, otherwise %NULL.
|
|
|
|
*/
|
|
|
|
void *xa_find(struct xarray *xa, unsigned long *indexp,
|
|
|
|
unsigned long max, xa_mark_t filter)
|
|
|
|
{
|
|
|
|
XA_STATE(xas, xa, *indexp);
|
|
|
|
void *entry;
|
|
|
|
|
|
|
|
rcu_read_lock();
|
|
|
|
do {
|
|
|
|
if ((__force unsigned int)filter < XA_MAX_MARKS)
|
|
|
|
entry = xas_find_marked(&xas, max, filter);
|
|
|
|
else
|
|
|
|
entry = xas_find(&xas, max);
|
|
|
|
} while (xas_retry(&xas, entry));
|
|
|
|
rcu_read_unlock();
|
|
|
|
|
|
|
|
if (entry)
|
|
|
|
*indexp = xas.xa_index;
|
|
|
|
return entry;
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL(xa_find);
|
|
|
|
|
2020-01-18 11:00:41 +08:00
|
|
|
static bool xas_sibling(struct xa_state *xas)
|
|
|
|
{
|
|
|
|
struct xa_node *node = xas->xa_node;
|
|
|
|
unsigned long mask;
|
|
|
|
|
2020-02-27 20:37:40 +08:00
|
|
|
if (!IS_ENABLED(CONFIG_XARRAY_MULTI) || !node)
|
2020-01-18 11:00:41 +08:00
|
|
|
return false;
|
|
|
|
mask = (XA_CHUNK_SIZE << node->shift) - 1;
|
2020-01-31 18:07:55 +08:00
|
|
|
return (xas->xa_index & mask) >
|
|
|
|
((unsigned long)xas->xa_offset << node->shift);
|
2020-01-18 11:00:41 +08:00
|
|
|
}
|
|
|
|
|
2017-11-14 21:30:11 +08:00
|
|
|
/**
|
|
|
|
* xa_find_after() - Search the XArray for a present entry.
|
|
|
|
* @xa: XArray.
|
|
|
|
* @indexp: Pointer to an index.
|
|
|
|
* @max: Maximum index to search to.
|
|
|
|
* @filter: Selection criterion.
|
|
|
|
*
|
|
|
|
* Finds the entry in @xa which matches the @filter and has the lowest
|
|
|
|
* index that is above @indexp and no more than @max.
|
|
|
|
* If an entry is found, @indexp is updated to be the index of the entry.
|
|
|
|
* This function is protected by the RCU read lock, so it may miss entries
|
|
|
|
* which are being simultaneously added. It will not return an
|
|
|
|
* %XA_RETRY_ENTRY; if you need to see retry entries, use xas_find().
|
|
|
|
*
|
|
|
|
* Context: Any context. Takes and releases the RCU lock.
|
|
|
|
* Return: The pointer, if found, otherwise %NULL.
|
|
|
|
*/
|
|
|
|
void *xa_find_after(struct xarray *xa, unsigned long *indexp,
|
|
|
|
unsigned long max, xa_mark_t filter)
|
|
|
|
{
|
|
|
|
XA_STATE(xas, xa, *indexp + 1);
|
|
|
|
void *entry;
|
|
|
|
|
2020-01-18 06:45:12 +08:00
|
|
|
if (xas.xa_index == 0)
|
|
|
|
return NULL;
|
|
|
|
|
2017-11-14 21:30:11 +08:00
|
|
|
rcu_read_lock();
|
|
|
|
for (;;) {
|
|
|
|
if ((__force unsigned int)filter < XA_MAX_MARKS)
|
|
|
|
entry = xas_find_marked(&xas, max, filter);
|
|
|
|
else
|
|
|
|
entry = xas_find(&xas, max);
|
2020-01-18 11:13:21 +08:00
|
|
|
|
|
|
|
if (xas_invalid(&xas))
|
2018-11-02 04:55:19 +08:00
|
|
|
break;
|
2020-01-18 11:00:41 +08:00
|
|
|
if (xas_sibling(&xas))
|
|
|
|
continue;
|
2017-11-14 21:30:11 +08:00
|
|
|
if (!xas_retry(&xas, entry))
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
rcu_read_unlock();
|
|
|
|
|
|
|
|
if (entry)
|
|
|
|
*indexp = xas.xa_index;
|
|
|
|
return entry;
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL(xa_find_after);
|
|
|
|
|
2017-11-15 05:42:22 +08:00
|
|
|
static unsigned int xas_extract_present(struct xa_state *xas, void **dst,
|
|
|
|
unsigned long max, unsigned int n)
|
|
|
|
{
|
|
|
|
void *entry;
|
|
|
|
unsigned int i = 0;
|
|
|
|
|
|
|
|
rcu_read_lock();
|
|
|
|
xas_for_each(xas, entry, max) {
|
|
|
|
if (xas_retry(xas, entry))
|
|
|
|
continue;
|
|
|
|
dst[i++] = entry;
|
|
|
|
if (i == n)
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
rcu_read_unlock();
|
|
|
|
|
|
|
|
return i;
|
|
|
|
}
|
|
|
|
|
|
|
|
static unsigned int xas_extract_marked(struct xa_state *xas, void **dst,
|
|
|
|
unsigned long max, unsigned int n, xa_mark_t mark)
|
|
|
|
{
|
|
|
|
void *entry;
|
|
|
|
unsigned int i = 0;
|
|
|
|
|
|
|
|
rcu_read_lock();
|
|
|
|
xas_for_each_marked(xas, entry, max, mark) {
|
|
|
|
if (xas_retry(xas, entry))
|
|
|
|
continue;
|
|
|
|
dst[i++] = entry;
|
|
|
|
if (i == n)
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
rcu_read_unlock();
|
|
|
|
|
|
|
|
return i;
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* xa_extract() - Copy selected entries from the XArray into a normal array.
|
|
|
|
* @xa: The source XArray to copy from.
|
|
|
|
* @dst: The buffer to copy entries into.
|
|
|
|
* @start: The first index in the XArray eligible to be selected.
|
|
|
|
* @max: The last index in the XArray eligible to be selected.
|
|
|
|
* @n: The maximum number of entries to copy.
|
|
|
|
* @filter: Selection criterion.
|
|
|
|
*
|
|
|
|
* Copies up to @n entries that match @filter from the XArray. The
|
|
|
|
* copied entries will have indices between @start and @max, inclusive.
|
|
|
|
*
|
|
|
|
* The @filter may be an XArray mark value, in which case entries which are
|
|
|
|
* marked with that mark will be copied. It may also be %XA_PRESENT, in
|
2018-11-06 05:37:15 +08:00
|
|
|
* which case all entries which are not %NULL will be copied.
|
2017-11-15 05:42:22 +08:00
|
|
|
*
|
|
|
|
* The entries returned may not represent a snapshot of the XArray at a
|
|
|
|
* moment in time. For example, if another thread stores to index 5, then
|
|
|
|
* index 10, calling xa_extract() may return the old contents of index 5
|
|
|
|
* and the new contents of index 10. Indices not modified while this
|
|
|
|
* function is running will not be skipped.
|
|
|
|
*
|
|
|
|
* If you need stronger guarantees, holding the xa_lock across calls to this
|
|
|
|
* function will prevent concurrent modification.
|
|
|
|
*
|
|
|
|
* Context: Any context. Takes and releases the RCU lock.
|
|
|
|
* Return: The number of entries copied.
|
|
|
|
*/
|
|
|
|
unsigned int xa_extract(struct xarray *xa, void **dst, unsigned long start,
|
|
|
|
unsigned long max, unsigned int n, xa_mark_t filter)
|
|
|
|
{
|
|
|
|
XA_STATE(xas, xa, start);
|
|
|
|
|
|
|
|
if (!n)
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
if ((__force unsigned int)filter < XA_MAX_MARKS)
|
|
|
|
return xas_extract_marked(&xas, dst, max, n, filter);
|
|
|
|
return xas_extract_present(&xas, dst, max, n);
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL(xa_extract);
|
|
|
|
|
2020-08-18 21:05:56 +08:00
|
|
|
/**
|
|
|
|
* xa_delete_node() - Private interface for workingset code.
|
|
|
|
* @node: Node to be removed from the tree.
|
|
|
|
* @update: Function to call to update ancestor nodes.
|
|
|
|
*
|
|
|
|
* Context: xa_lock must be held on entry and will not be released.
|
|
|
|
*/
|
|
|
|
void xa_delete_node(struct xa_node *node, xa_update_node_t update)
|
|
|
|
{
|
|
|
|
struct xa_state xas = {
|
|
|
|
.xa = node->array,
|
|
|
|
.xa_index = (unsigned long)node->offset <<
|
|
|
|
(node->shift + XA_CHUNK_SHIFT),
|
|
|
|
.xa_shift = node->shift + XA_CHUNK_SHIFT,
|
|
|
|
.xa_offset = node->offset,
|
|
|
|
.xa_node = xa_parent_locked(node->array, node),
|
|
|
|
.xa_update = update,
|
|
|
|
};
|
|
|
|
|
|
|
|
xas_store(&xas, NULL);
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(xa_delete_node); /* For the benefit of the test suite */
|
|
|
|
|
2017-11-17 21:16:34 +08:00
|
|
|
/**
|
|
|
|
* xa_destroy() - Free all internal data structures.
|
|
|
|
* @xa: XArray.
|
|
|
|
*
|
|
|
|
* After calling this function, the XArray is empty and has freed all memory
|
|
|
|
* allocated for its internal data structures. You are responsible for
|
|
|
|
* freeing the objects referenced by the XArray.
|
|
|
|
*
|
|
|
|
* Context: Any context. Takes and releases the xa_lock, interrupt-safe.
|
|
|
|
*/
|
|
|
|
void xa_destroy(struct xarray *xa)
|
|
|
|
{
|
|
|
|
XA_STATE(xas, xa, 0);
|
|
|
|
unsigned long flags;
|
|
|
|
void *entry;
|
|
|
|
|
|
|
|
xas.xa_node = NULL;
|
|
|
|
xas_lock_irqsave(&xas, flags);
|
|
|
|
entry = xa_head_locked(xa);
|
|
|
|
RCU_INIT_POINTER(xa->xa_head, NULL);
|
|
|
|
xas_init_marks(&xas);
|
2018-10-27 02:43:22 +08:00
|
|
|
if (xa_zero_busy(xa))
|
|
|
|
xa_mark_clear(xa, XA_FREE_MARK);
|
2017-11-17 21:16:34 +08:00
|
|
|
/* lockdep checks we're still holding the lock in xas_free_nodes() */
|
|
|
|
if (xa_is_node(entry))
|
|
|
|
xas_free_nodes(&xas, xa_to_node(entry));
|
|
|
|
xas_unlock_irqrestore(&xas, flags);
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL(xa_destroy);
|
|
|
|
|
2017-11-08 03:57:46 +08:00
|
|
|
#ifdef XA_DEBUG
|
|
|
|
void xa_dump_node(const struct xa_node *node)
|
|
|
|
{
|
|
|
|
unsigned i, j;
|
|
|
|
|
|
|
|
if (!node)
|
|
|
|
return;
|
|
|
|
if ((unsigned long)node & 3) {
|
|
|
|
pr_cont("node %px\n", node);
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
|
|
|
pr_cont("node %px %s %d parent %px shift %d count %d values %d "
|
|
|
|
"array %px list %px %px marks",
|
|
|
|
node, node->parent ? "offset" : "max", node->offset,
|
|
|
|
node->parent, node->shift, node->count, node->nr_values,
|
|
|
|
node->array, node->private_list.prev, node->private_list.next);
|
|
|
|
for (i = 0; i < XA_MAX_MARKS; i++)
|
|
|
|
for (j = 0; j < XA_MARK_LONGS; j++)
|
|
|
|
pr_cont(" %lx", node->marks[i][j]);
|
|
|
|
pr_cont("\n");
|
|
|
|
}
|
|
|
|
|
|
|
|
void xa_dump_index(unsigned long index, unsigned int shift)
|
|
|
|
{
|
|
|
|
if (!shift)
|
|
|
|
pr_info("%lu: ", index);
|
|
|
|
else if (shift >= BITS_PER_LONG)
|
|
|
|
pr_info("0-%lu: ", ~0UL);
|
|
|
|
else
|
|
|
|
pr_info("%lu-%lu: ", index, index | ((1UL << shift) - 1));
|
|
|
|
}
|
|
|
|
|
|
|
|
void xa_dump_entry(const void *entry, unsigned long index, unsigned long shift)
|
|
|
|
{
|
|
|
|
if (!entry)
|
|
|
|
return;
|
|
|
|
|
|
|
|
xa_dump_index(index, shift);
|
|
|
|
|
|
|
|
if (xa_is_node(entry)) {
|
|
|
|
if (shift == 0) {
|
|
|
|
pr_cont("%px\n", entry);
|
|
|
|
} else {
|
|
|
|
unsigned long i;
|
|
|
|
struct xa_node *node = xa_to_node(entry);
|
|
|
|
xa_dump_node(node);
|
|
|
|
for (i = 0; i < XA_CHUNK_SIZE; i++)
|
|
|
|
xa_dump_entry(node->slots[i],
|
|
|
|
index + (i << node->shift), node->shift);
|
|
|
|
}
|
|
|
|
} else if (xa_is_value(entry))
|
|
|
|
pr_cont("value %ld (0x%lx) [%px]\n", xa_to_value(entry),
|
|
|
|
xa_to_value(entry), entry);
|
|
|
|
else if (!xa_is_internal(entry))
|
|
|
|
pr_cont("%px\n", entry);
|
|
|
|
else if (xa_is_retry(entry))
|
|
|
|
pr_cont("retry (%ld)\n", xa_to_internal(entry));
|
|
|
|
else if (xa_is_sibling(entry))
|
|
|
|
pr_cont("sibling (slot %ld)\n", xa_to_sibling(entry));
|
2018-10-02 02:54:59 +08:00
|
|
|
else if (xa_is_zero(entry))
|
|
|
|
pr_cont("zero (%ld)\n", xa_to_internal(entry));
|
2017-11-08 03:57:46 +08:00
|
|
|
else
|
|
|
|
pr_cont("UNKNOWN ENTRY (%px)\n", entry);
|
|
|
|
}
|
|
|
|
|
|
|
|
void xa_dump(const struct xarray *xa)
|
|
|
|
{
|
|
|
|
void *entry = xa->xa_head;
|
|
|
|
unsigned int shift = 0;
|
|
|
|
|
|
|
|
pr_info("xarray: %px head %px flags %x marks %d %d %d\n", xa, entry,
|
2017-11-10 22:34:31 +08:00
|
|
|
xa->xa_flags, xa_marked(xa, XA_MARK_0),
|
|
|
|
xa_marked(xa, XA_MARK_1), xa_marked(xa, XA_MARK_2));
|
2017-11-08 03:57:46 +08:00
|
|
|
if (xa_is_node(entry))
|
|
|
|
shift = xa_to_node(entry)->shift + XA_CHUNK_SHIFT;
|
|
|
|
xa_dump_entry(entry, 0, shift);
|
|
|
|
}
|
|
|
|
#endif
|