This series unifies declarations of bitmap-related functions and aligns
return types with values that actually returned. Also, it moves one-liner
wrappers around cpumask functions into headers, so that compiler has a
chance to optimize better.
With this series, GCC 11.2 for ARM64 with kernel v5.19-rc4:
add/remove: 15/7 grow/shrink: 461/164 up/down: 14844/-4580 (10264)
This +10K didn't surprise me because modern compilers are more aggressive
in inlining, loop unrolling, and other techniques that increase size of
the image.
v1: https://lore.kernel.org/linux-mm/[email protected]/T/
v2: - Align whitespaces in headers;
- Make bitmap_weight() unsigned long consistently;
- Pick 2 patches from Ingo's sched/headers series [1] that split
linux/gfp.h, and drop my similar patch for it.
[1] https://git.kernel.org/pub/scm/linux/kernel/git/mingo/tip.git/log/?h=sched/headers
Ingo Molnar (2):
headers/deps: mm: Optimize <linux/gfp.h> header dependencies
headers/deps: mm: Split <linux/gfp_types.h> out of <linux/gfp.h>
Yury Norov (8):
arm: align find_bit declarations with generic kernel
lib/bitmap: change return types to bool where appropriate
lib/bitmap: change type of bitmap_weight to unsigned long
cpumask: change return types to bool where appropriate
lib/cpumask: change return types to unsigned where appropriate
lib/cpumask: move trivial wrappers around find_bit to the header
headers/deps: mm: align MANITAINERS and Docs with new gfp.h structure
lib/cpumask: move some one-line wrappers to header file
Documentation/core-api/mm-api.rst | 8 +-
MAINTAINERS | 1 +
arch/arm/include/asm/bitops.h | 18 +-
include/linux/bitmap.h | 13 +-
include/linux/cpumask.h | 125 +++++++++--
include/linux/gfp.h | 348 +-----------------------------
include/linux/gfp_types.h | 348 ++++++++++++++++++++++++++++++
lib/bitmap.c | 9 +-
lib/cpumask.c | 97 +--------
tools/include/linux/bitmap.h | 12 +-
tools/lib/bitmap.c | 6 +-
11 files changed, 494 insertions(+), 491 deletions(-)
create mode 100644 include/linux/gfp_types.h
--
2.34.1
Switch return types to unsigned int where return values cannot be negative.
Signed-off-by: Yury Norov <[email protected]>
---
include/linux/cpumask.h | 14 +++++++-------
lib/cpumask.c | 18 +++++++++---------
2 files changed, 16 insertions(+), 16 deletions(-)
diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index b54e27d9da6b..760022bcb925 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -176,12 +176,12 @@ static inline unsigned int cpumask_local_spread(unsigned int i, int node)
return 0;
}
-static inline int cpumask_any_and_distribute(const struct cpumask *src1p,
+static inline unsigned int cpumask_any_and_distribute(const struct cpumask *src1p,
const struct cpumask *src2p) {
return cpumask_first_and(src1p, src2p);
}
-static inline int cpumask_any_distribute(const struct cpumask *srcp)
+static inline unsigned int cpumask_any_distribute(const struct cpumask *srcp)
{
return cpumask_first(srcp);
}
@@ -258,12 +258,12 @@ static inline unsigned int cpumask_next_zero(int n, const struct cpumask *srcp)
return find_next_zero_bit(cpumask_bits(srcp), nr_cpumask_bits, n+1);
}
-int __pure cpumask_next_and(int n, const struct cpumask *, const struct cpumask *);
-int __pure cpumask_any_but(const struct cpumask *mask, unsigned int cpu);
+unsigned int __pure cpumask_next_and(int n, const struct cpumask *, const struct cpumask *);
+unsigned int __pure cpumask_any_but(const struct cpumask *mask, unsigned int cpu);
unsigned int cpumask_local_spread(unsigned int i, int node);
-int cpumask_any_and_distribute(const struct cpumask *src1p,
+unsigned int cpumask_any_and_distribute(const struct cpumask *src1p,
const struct cpumask *src2p);
-int cpumask_any_distribute(const struct cpumask *srcp);
+unsigned int cpumask_any_distribute(const struct cpumask *srcp);
/**
* for_each_cpu - iterate over every cpu in a mask
@@ -289,7 +289,7 @@ int cpumask_any_distribute(const struct cpumask *srcp);
(cpu) = cpumask_next_zero((cpu), (mask)), \
(cpu) < nr_cpu_ids;)
-extern int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap);
+unsigned int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap);
/**
* for_each_cpu_wrap - iterate over every cpu in a mask, starting at a specified location
diff --git a/lib/cpumask.c b/lib/cpumask.c
index a971a82d2f43..da68f6bbde44 100644
--- a/lib/cpumask.c
+++ b/lib/cpumask.c
@@ -31,7 +31,7 @@ EXPORT_SYMBOL(cpumask_next);
*
* Returns >= nr_cpu_ids if no further cpus set in both.
*/
-int cpumask_next_and(int n, const struct cpumask *src1p,
+unsigned int cpumask_next_and(int n, const struct cpumask *src1p,
const struct cpumask *src2p)
{
/* -1 is a legal arg here. */
@@ -50,7 +50,7 @@ EXPORT_SYMBOL(cpumask_next_and);
* Often used to find any cpu but smp_processor_id() in a mask.
* Returns >= nr_cpu_ids if no cpus set.
*/
-int cpumask_any_but(const struct cpumask *mask, unsigned int cpu)
+unsigned int cpumask_any_but(const struct cpumask *mask, unsigned int cpu)
{
unsigned int i;
@@ -74,9 +74,9 @@ EXPORT_SYMBOL(cpumask_any_but);
* Note: the @wrap argument is required for the start condition when
* we cannot assume @start is set in @mask.
*/
-int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap)
+unsigned int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap)
{
- int next;
+ unsigned int next;
again:
next = cpumask_next(n, mask);
@@ -205,7 +205,7 @@ void __init free_bootmem_cpumask_var(cpumask_var_t mask)
*/
unsigned int cpumask_local_spread(unsigned int i, int node)
{
- int cpu;
+ unsigned int cpu;
/* Wrap: we always want a cpu. */
i %= num_online_cpus();
@@ -243,10 +243,10 @@ static DEFINE_PER_CPU(int, distribute_cpu_mask_prev);
*
* Returns >= nr_cpu_ids if the intersection is empty.
*/
-int cpumask_any_and_distribute(const struct cpumask *src1p,
+unsigned int cpumask_any_and_distribute(const struct cpumask *src1p,
const struct cpumask *src2p)
{
- int next, prev;
+ unsigned int next, prev;
/* NOTE: our first selection will skip 0. */
prev = __this_cpu_read(distribute_cpu_mask_prev);
@@ -262,9 +262,9 @@ int cpumask_any_and_distribute(const struct cpumask *src1p,
}
EXPORT_SYMBOL(cpumask_any_and_distribute);
-int cpumask_any_distribute(const struct cpumask *srcp)
+unsigned int cpumask_any_distribute(const struct cpumask *srcp)
{
- int next, prev;
+ unsigned int next, prev;
/* NOTE: our first selection will skip 0. */
prev = __this_cpu_read(distribute_cpu_mask_prev);
--
2.34.1
After moving gfp flags to a separate header, it's possible to move some
cpumask allocators into headers, and avoid creating real functions.
Signed-off-by: Yury Norov <[email protected]>
---
include/linux/cpumask.h | 34 +++++++++++++++++++++++++++++++---
lib/cpumask.c | 28 ----------------------------
2 files changed, 31 insertions(+), 31 deletions(-)
diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index ea3de2c2c180..80627362c774 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -12,6 +12,8 @@
#include <linux/bitmap.h>
#include <linux/atomic.h>
#include <linux/bug.h>
+#include <linux/gfp_types.h>
+#include <linux/numa.h>
/* Don't assign or return these: may not be this big! */
typedef struct cpumask { DECLARE_BITMAP(bits, NR_CPUS); } cpumask_t;
@@ -794,9 +796,35 @@ typedef struct cpumask *cpumask_var_t;
#define __cpumask_var_read_mostly __read_mostly
bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node);
-bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags);
-bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node);
-bool zalloc_cpumask_var(cpumask_var_t *mask, gfp_t flags);
+
+static inline
+bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node)
+{
+ return alloc_cpumask_var_node(mask, flags | __GFP_ZERO, node);
+}
+
+/**
+ * alloc_cpumask_var - allocate a struct cpumask
+ * @mask: pointer to cpumask_var_t where the cpumask is returned
+ * @flags: GFP_ flags
+ *
+ * Only defined when CONFIG_CPUMASK_OFFSTACK=y, otherwise is
+ * a nop returning a constant 1 (in <linux/cpumask.h>).
+ *
+ * See alloc_cpumask_var_node.
+ */
+static inline
+bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags)
+{
+ return alloc_cpumask_var_node(mask, flags, NUMA_NO_NODE);
+}
+
+static inline
+bool zalloc_cpumask_var(cpumask_var_t *mask, gfp_t flags)
+{
+ return alloc_cpumask_var(mask, flags | __GFP_ZERO);
+}
+
void alloc_bootmem_cpumask_var(cpumask_var_t *mask);
void free_cpumask_var(cpumask_var_t mask);
void free_bootmem_cpumask_var(cpumask_var_t mask);
diff --git a/lib/cpumask.c b/lib/cpumask.c
index cb7262ff8633..f0ae119be8c4 100644
--- a/lib/cpumask.c
+++ b/lib/cpumask.c
@@ -70,34 +70,6 @@ bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node)
}
EXPORT_SYMBOL(alloc_cpumask_var_node);
-bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node)
-{
- return alloc_cpumask_var_node(mask, flags | __GFP_ZERO, node);
-}
-EXPORT_SYMBOL(zalloc_cpumask_var_node);
-
-/**
- * alloc_cpumask_var - allocate a struct cpumask
- * @mask: pointer to cpumask_var_t where the cpumask is returned
- * @flags: GFP_ flags
- *
- * Only defined when CONFIG_CPUMASK_OFFSTACK=y, otherwise is
- * a nop returning a constant 1 (in <linux/cpumask.h>).
- *
- * See alloc_cpumask_var_node.
- */
-bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags)
-{
- return alloc_cpumask_var_node(mask, flags, NUMA_NO_NODE);
-}
-EXPORT_SYMBOL(alloc_cpumask_var);
-
-bool zalloc_cpumask_var(cpumask_var_t *mask, gfp_t flags)
-{
- return alloc_cpumask_var(mask, flags | __GFP_ZERO);
-}
-EXPORT_SYMBOL(zalloc_cpumask_var);
-
/**
* alloc_bootmem_cpumask_var - allocate a struct cpumask from the bootmem arena.
* @mask: pointer to cpumask_var_t where the cpumask is returned
--
2.34.1
bitmap_weight() doesn't return negative values, so change it's type
to unsigned long. It may help compiler to generate better code and
catch bugs.
Signed-off-by: Yury Norov <[email protected]>
---
include/linux/bitmap.h | 5 +++--
lib/bitmap.c | 5 ++---
tools/include/linux/bitmap.h | 4 ++--
tools/lib/bitmap.c | 4 ++--
4 files changed, 9 insertions(+), 9 deletions(-)
diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h
index 85aace699b2b..a92149f415d2 100644
--- a/include/linux/bitmap.h
+++ b/include/linux/bitmap.h
@@ -163,7 +163,7 @@ bool __bitmap_intersects(const unsigned long *bitmap1,
const unsigned long *bitmap2, unsigned int nbits);
bool __bitmap_subset(const unsigned long *bitmap1,
const unsigned long *bitmap2, unsigned int nbits);
-int __bitmap_weight(const unsigned long *bitmap, unsigned int nbits);
+unsigned long __bitmap_weight(const unsigned long *bitmap, unsigned int nbits);
void __bitmap_set(unsigned long *map, unsigned int start, int len);
void __bitmap_clear(unsigned long *map, unsigned int start, int len);
@@ -419,7 +419,8 @@ static inline bool bitmap_full(const unsigned long *src, unsigned int nbits)
return find_first_zero_bit(src, nbits) == nbits;
}
-static __always_inline int bitmap_weight(const unsigned long *src, unsigned int nbits)
+static __always_inline
+unsigned long bitmap_weight(const unsigned long *src, unsigned int nbits)
{
if (small_const_nbits(nbits))
return hweight_long(*src & BITMAP_LAST_WORD_MASK(nbits));
diff --git a/lib/bitmap.c b/lib/bitmap.c
index 098fd9db2363..b580b381eca1 100644
--- a/lib/bitmap.c
+++ b/lib/bitmap.c
@@ -333,10 +333,9 @@ bool __bitmap_subset(const unsigned long *bitmap1,
}
EXPORT_SYMBOL(__bitmap_subset);
-int __bitmap_weight(const unsigned long *bitmap, unsigned int bits)
+unsigned long __bitmap_weight(const unsigned long *bitmap, unsigned int bits)
{
- unsigned int k, lim = bits/BITS_PER_LONG;
- int w = 0;
+ unsigned long k, w = 0, lim = bits/BITS_PER_LONG;
for (k = 0; k < lim; k++)
w += hweight_long(bitmap[k]);
diff --git a/tools/include/linux/bitmap.h b/tools/include/linux/bitmap.h
index 2ae7ab8ed7d1..ae1852e39142 100644
--- a/tools/include/linux/bitmap.h
+++ b/tools/include/linux/bitmap.h
@@ -11,7 +11,7 @@
#define DECLARE_BITMAP(name,bits) \
unsigned long name[BITS_TO_LONGS(bits)]
-int __bitmap_weight(const unsigned long *bitmap, int bits);
+unsigned long __bitmap_weight(const unsigned long *bitmap, unsigned int bits);
void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1,
const unsigned long *bitmap2, int bits);
bool __bitmap_and(unsigned long *dst, const unsigned long *bitmap1,
@@ -61,7 +61,7 @@ static inline bool bitmap_full(const unsigned long *src, unsigned int nbits)
return find_first_zero_bit(src, nbits) == nbits;
}
-static inline int bitmap_weight(const unsigned long *src, unsigned int nbits)
+static inline unsigned long bitmap_weight(const unsigned long *src, unsigned int nbits)
{
if (small_const_nbits(nbits))
return hweight_long(*src & BITMAP_LAST_WORD_MASK(nbits));
diff --git a/tools/lib/bitmap.c b/tools/lib/bitmap.c
index 2e351d63fdba..e1fafc131a49 100644
--- a/tools/lib/bitmap.c
+++ b/tools/lib/bitmap.c
@@ -5,9 +5,9 @@
*/
#include <linux/bitmap.h>
-int __bitmap_weight(const unsigned long *bitmap, int bits)
+unsigned long __bitmap_weight(const unsigned long *bitmap, unsigned int bits)
{
- int k, w = 0, lim = bits/BITS_PER_LONG;
+ unsigned long k, w = 0, lim = bits/BITS_PER_LONG;
for (k = 0; k < lim; k++)
w += hweight_long(bitmap[k]);
--
2.34.1
To avoid circular dependencies, cpumask keeps simple (almost) one-line
wrappers around find_bit() in a c-file.
Commit 47d8c15615c0a2 ("include: move find.h from asm_generic to linux")
moved find.h header out of asm_generic include path, and it helped to fix
many circular dependencies, including some in cpumask.h.
This patch moves those one-liners to header files.
Signed-off-by: Yury Norov <[email protected]>
---
include/linux/cpumask.h | 57 ++++++++++++++++++++++++++++++++++++++---
lib/cpumask.c | 55 ---------------------------------------
2 files changed, 54 insertions(+), 58 deletions(-)
diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index 760022bcb925..ea3de2c2c180 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -241,7 +241,21 @@ static inline unsigned int cpumask_last(const struct cpumask *srcp)
return find_last_bit(cpumask_bits(srcp), nr_cpumask_bits);
}
-unsigned int __pure cpumask_next(int n, const struct cpumask *srcp);
+/**
+ * cpumask_next - get the next cpu in a cpumask
+ * @n: the cpu prior to the place to search (ie. return will be > @n)
+ * @srcp: the cpumask pointer
+ *
+ * Returns >= nr_cpu_ids if no further cpus set.
+ */
+static inline
+unsigned int cpumask_next(int n, const struct cpumask *srcp)
+{
+ /* -1 is a legal arg here. */
+ if (n != -1)
+ cpumask_check(n);
+ return find_next_bit(cpumask_bits(srcp), nr_cpumask_bits, n + 1);
+}
/**
* cpumask_next_zero - get the next unset cpu in a cpumask
@@ -258,8 +272,25 @@ static inline unsigned int cpumask_next_zero(int n, const struct cpumask *srcp)
return find_next_zero_bit(cpumask_bits(srcp), nr_cpumask_bits, n+1);
}
-unsigned int __pure cpumask_next_and(int n, const struct cpumask *, const struct cpumask *);
-unsigned int __pure cpumask_any_but(const struct cpumask *mask, unsigned int cpu);
+/**
+ * cpumask_next_and - get the next cpu in *src1p & *src2p
+ * @n: the cpu prior to the place to search (ie. return will be > @n)
+ * @src1p: the first cpumask pointer
+ * @src2p: the second cpumask pointer
+ *
+ * Returns >= nr_cpu_ids if no further cpus set in both.
+ */
+static inline
+unsigned int cpumask_next_and(int n, const struct cpumask *src1p,
+ const struct cpumask *src2p)
+{
+ /* -1 is a legal arg here. */
+ if (n != -1)
+ cpumask_check(n);
+ return find_next_and_bit(cpumask_bits(src1p), cpumask_bits(src2p),
+ nr_cpumask_bits, n + 1);
+}
+
unsigned int cpumask_local_spread(unsigned int i, int node);
unsigned int cpumask_any_and_distribute(const struct cpumask *src1p,
const struct cpumask *src2p);
@@ -324,6 +355,26 @@ unsigned int cpumask_next_wrap(int n, const struct cpumask *mask, int start, boo
for ((cpu) = -1; \
(cpu) = cpumask_next_and((cpu), (mask1), (mask2)), \
(cpu) < nr_cpu_ids;)
+
+/**
+ * cpumask_any_but - return a "random" in a cpumask, but not this one.
+ * @mask: the cpumask to search
+ * @cpu: the cpu to ignore.
+ *
+ * Often used to find any cpu but smp_processor_id() in a mask.
+ * Returns >= nr_cpu_ids if no cpus set.
+ */
+static inline
+unsigned int cpumask_any_but(const struct cpumask *mask, unsigned int cpu)
+{
+ unsigned int i;
+
+ cpumask_check(cpu);
+ for_each_cpu(i, mask)
+ if (i != cpu)
+ break;
+ return i;
+}
#endif /* SMP */
#define CPU_BITS_NONE \
diff --git a/lib/cpumask.c b/lib/cpumask.c
index da68f6bbde44..cb7262ff8633 100644
--- a/lib/cpumask.c
+++ b/lib/cpumask.c
@@ -7,61 +7,6 @@
#include <linux/memblock.h>
#include <linux/numa.h>
-/**
- * cpumask_next - get the next cpu in a cpumask
- * @n: the cpu prior to the place to search (ie. return will be > @n)
- * @srcp: the cpumask pointer
- *
- * Returns >= nr_cpu_ids if no further cpus set.
- */
-unsigned int cpumask_next(int n, const struct cpumask *srcp)
-{
- /* -1 is a legal arg here. */
- if (n != -1)
- cpumask_check(n);
- return find_next_bit(cpumask_bits(srcp), nr_cpumask_bits, n + 1);
-}
-EXPORT_SYMBOL(cpumask_next);
-
-/**
- * cpumask_next_and - get the next cpu in *src1p & *src2p
- * @n: the cpu prior to the place to search (ie. return will be > @n)
- * @src1p: the first cpumask pointer
- * @src2p: the second cpumask pointer
- *
- * Returns >= nr_cpu_ids if no further cpus set in both.
- */
-unsigned int cpumask_next_and(int n, const struct cpumask *src1p,
- const struct cpumask *src2p)
-{
- /* -1 is a legal arg here. */
- if (n != -1)
- cpumask_check(n);
- return find_next_and_bit(cpumask_bits(src1p), cpumask_bits(src2p),
- nr_cpumask_bits, n + 1);
-}
-EXPORT_SYMBOL(cpumask_next_and);
-
-/**
- * cpumask_any_but - return a "random" in a cpumask, but not this one.
- * @mask: the cpumask to search
- * @cpu: the cpu to ignore.
- *
- * Often used to find any cpu but smp_processor_id() in a mask.
- * Returns >= nr_cpu_ids if no cpus set.
- */
-unsigned int cpumask_any_but(const struct cpumask *mask, unsigned int cpu)
-{
- unsigned int i;
-
- cpumask_check(cpu);
- for_each_cpu(i, mask)
- if (i != cpu)
- break;
- return i;
-}
-EXPORT_SYMBOL(cpumask_any_but);
-
/**
* cpumask_next_wrap - helper to implement for_each_cpu_wrap
* @n: the cpu prior to the place to search
--
2.34.1
Some cpumask functions have integer return types where return values
are naturally booleans.
Signed-off-by: Yury Norov <[email protected]>
---
include/linux/cpumask.h | 24 ++++++++++++------------
1 file changed, 12 insertions(+), 12 deletions(-)
diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index fe29ac7cc469..b54e27d9da6b 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -372,9 +372,9 @@ static __always_inline void __cpumask_clear_cpu(int cpu, struct cpumask *dstp)
* @cpu: cpu number (< nr_cpu_ids)
* @cpumask: the cpumask pointer
*
- * Returns 1 if @cpu is set in @cpumask, else returns 0
+ * Returns true if @cpu is set in @cpumask, else returns false
*/
-static __always_inline int cpumask_test_cpu(int cpu, const struct cpumask *cpumask)
+static __always_inline bool cpumask_test_cpu(int cpu, const struct cpumask *cpumask)
{
return test_bit(cpumask_check(cpu), cpumask_bits((cpumask)));
}
@@ -384,11 +384,11 @@ static __always_inline int cpumask_test_cpu(int cpu, const struct cpumask *cpuma
* @cpu: cpu number (< nr_cpu_ids)
* @cpumask: the cpumask pointer
*
- * Returns 1 if @cpu is set in old bitmap of @cpumask, else returns 0
+ * Returns true if @cpu is set in old bitmap of @cpumask, else returns false
*
* test_and_set_bit wrapper for cpumasks.
*/
-static __always_inline int cpumask_test_and_set_cpu(int cpu, struct cpumask *cpumask)
+static __always_inline bool cpumask_test_and_set_cpu(int cpu, struct cpumask *cpumask)
{
return test_and_set_bit(cpumask_check(cpu), cpumask_bits(cpumask));
}
@@ -398,11 +398,11 @@ static __always_inline int cpumask_test_and_set_cpu(int cpu, struct cpumask *cpu
* @cpu: cpu number (< nr_cpu_ids)
* @cpumask: the cpumask pointer
*
- * Returns 1 if @cpu is set in old bitmap of @cpumask, else returns 0
+ * Returns true if @cpu is set in old bitmap of @cpumask, else returns false
*
* test_and_clear_bit wrapper for cpumasks.
*/
-static __always_inline int cpumask_test_and_clear_cpu(int cpu, struct cpumask *cpumask)
+static __always_inline bool cpumask_test_and_clear_cpu(int cpu, struct cpumask *cpumask)
{
return test_and_clear_bit(cpumask_check(cpu), cpumask_bits(cpumask));
}
@@ -431,9 +431,9 @@ static inline void cpumask_clear(struct cpumask *dstp)
* @src1p: the first input
* @src2p: the second input
*
- * If *@dstp is empty, returns 0, else returns 1
+ * If *@dstp is empty, returns false, else returns true
*/
-static inline int cpumask_and(struct cpumask *dstp,
+static inline bool cpumask_and(struct cpumask *dstp,
const struct cpumask *src1p,
const struct cpumask *src2p)
{
@@ -474,9 +474,9 @@ static inline void cpumask_xor(struct cpumask *dstp,
* @src1p: the first input
* @src2p: the second input
*
- * If *@dstp is empty, returns 0, else returns 1
+ * If *@dstp is empty, returns false, else returns true
*/
-static inline int cpumask_andnot(struct cpumask *dstp,
+static inline bool cpumask_andnot(struct cpumask *dstp,
const struct cpumask *src1p,
const struct cpumask *src2p)
{
@@ -539,9 +539,9 @@ static inline bool cpumask_intersects(const struct cpumask *src1p,
* @src1p: the first input
* @src2p: the second input
*
- * Returns 1 if *@src1p is a subset of *@src2p, else returns 0
+ * Returns true if *@src1p is a subset of *@src2p, else returns false
*/
-static inline int cpumask_subset(const struct cpumask *src1p,
+static inline bool cpumask_subset(const struct cpumask *src1p,
const struct cpumask *src2p)
{
return bitmap_subset(cpumask_bits(src1p), cpumask_bits(src2p),
--
2.34.1
From: Ingo Molnar <[email protected]>
There's a couple of superfluous inclusions here - remove them before
doing bigger changes.
Signed-off-by: Ingo Molnar <[email protected]>
Signed-off-by: Yury Norov <[email protected]>
---
include/linux/gfp.h | 3 ---
1 file changed, 3 deletions(-)
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 2d2ccae933c2..52f2c873a7d4 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -2,10 +2,7 @@
#ifndef __LINUX_GFP_H
#define __LINUX_GFP_H
-#include <linux/mmdebug.h>
#include <linux/mmzone.h>
-#include <linux/stddef.h>
-#include <linux/linkage.h>
#include <linux/topology.h>
/* The typedef is in types.h but we want the documentation here */
--
2.34.1
From: Ingo Molnar <[email protected]>
This is a much smaller header.
Signed-off-by: Ingo Molnar <[email protected]>
Signed-off-by: Yury Norov <[email protected]>
---
include/linux/gfp.h | 345 +------------------------------------
include/linux/gfp_types.h | 348 ++++++++++++++++++++++++++++++++++++++
2 files changed, 350 insertions(+), 343 deletions(-)
create mode 100644 include/linux/gfp_types.h
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 52f2c873a7d4..f314be58fa77 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -2,354 +2,13 @@
#ifndef __LINUX_GFP_H
#define __LINUX_GFP_H
+#include <linux/gfp_types.h>
+
#include <linux/mmzone.h>
#include <linux/topology.h>
-/* The typedef is in types.h but we want the documentation here */
-#if 0
-/**
- * typedef gfp_t - Memory allocation flags.
- *
- * GFP flags are commonly used throughout Linux to indicate how memory
- * should be allocated. The GFP acronym stands for get_free_pages(),
- * the underlying memory allocation function. Not every GFP flag is
- * supported by every function which may allocate memory. Most users
- * will want to use a plain ``GFP_KERNEL``.
- */
-typedef unsigned int __bitwise gfp_t;
-#endif
-
struct vm_area_struct;
-/*
- * In case of changes, please don't forget to update
- * include/trace/events/mmflags.h and tools/perf/builtin-kmem.c
- */
-
-/* Plain integer GFP bitmasks. Do not use this directly. */
-#define ___GFP_DMA 0x01u
-#define ___GFP_HIGHMEM 0x02u
-#define ___GFP_DMA32 0x04u
-#define ___GFP_MOVABLE 0x08u
-#define ___GFP_RECLAIMABLE 0x10u
-#define ___GFP_HIGH 0x20u
-#define ___GFP_IO 0x40u
-#define ___GFP_FS 0x80u
-#define ___GFP_ZERO 0x100u
-#define ___GFP_ATOMIC 0x200u
-#define ___GFP_DIRECT_RECLAIM 0x400u
-#define ___GFP_KSWAPD_RECLAIM 0x800u
-#define ___GFP_WRITE 0x1000u
-#define ___GFP_NOWARN 0x2000u
-#define ___GFP_RETRY_MAYFAIL 0x4000u
-#define ___GFP_NOFAIL 0x8000u
-#define ___GFP_NORETRY 0x10000u
-#define ___GFP_MEMALLOC 0x20000u
-#define ___GFP_COMP 0x40000u
-#define ___GFP_NOMEMALLOC 0x80000u
-#define ___GFP_HARDWALL 0x100000u
-#define ___GFP_THISNODE 0x200000u
-#define ___GFP_ACCOUNT 0x400000u
-#define ___GFP_ZEROTAGS 0x800000u
-#ifdef CONFIG_KASAN_HW_TAGS
-#define ___GFP_SKIP_ZERO 0x1000000u
-#define ___GFP_SKIP_KASAN_UNPOISON 0x2000000u
-#define ___GFP_SKIP_KASAN_POISON 0x4000000u
-#else
-#define ___GFP_SKIP_ZERO 0
-#define ___GFP_SKIP_KASAN_UNPOISON 0
-#define ___GFP_SKIP_KASAN_POISON 0
-#endif
-#ifdef CONFIG_LOCKDEP
-#define ___GFP_NOLOCKDEP 0x8000000u
-#else
-#define ___GFP_NOLOCKDEP 0
-#endif
-/* If the above are modified, __GFP_BITS_SHIFT may need updating */
-
-/*
- * Physical address zone modifiers (see linux/mmzone.h - low four bits)
- *
- * Do not put any conditional on these. If necessary modify the definitions
- * without the underscores and use them consistently. The definitions here may
- * be used in bit comparisons.
- */
-#define __GFP_DMA ((__force gfp_t)___GFP_DMA)
-#define __GFP_HIGHMEM ((__force gfp_t)___GFP_HIGHMEM)
-#define __GFP_DMA32 ((__force gfp_t)___GFP_DMA32)
-#define __GFP_MOVABLE ((__force gfp_t)___GFP_MOVABLE) /* ZONE_MOVABLE allowed */
-#define GFP_ZONEMASK (__GFP_DMA|__GFP_HIGHMEM|__GFP_DMA32|__GFP_MOVABLE)
-
-/**
- * DOC: Page mobility and placement hints
- *
- * Page mobility and placement hints
- * ---------------------------------
- *
- * These flags provide hints about how mobile the page is. Pages with similar
- * mobility are placed within the same pageblocks to minimise problems due
- * to external fragmentation.
- *
- * %__GFP_MOVABLE (also a zone modifier) indicates that the page can be
- * moved by page migration during memory compaction or can be reclaimed.
- *
- * %__GFP_RECLAIMABLE is used for slab allocations that specify
- * SLAB_RECLAIM_ACCOUNT and whose pages can be freed via shrinkers.
- *
- * %__GFP_WRITE indicates the caller intends to dirty the page. Where possible,
- * these pages will be spread between local zones to avoid all the dirty
- * pages being in one zone (fair zone allocation policy).
- *
- * %__GFP_HARDWALL enforces the cpuset memory allocation policy.
- *
- * %__GFP_THISNODE forces the allocation to be satisfied from the requested
- * node with no fallbacks or placement policy enforcements.
- *
- * %__GFP_ACCOUNT causes the allocation to be accounted to kmemcg.
- */
-#define __GFP_RECLAIMABLE ((__force gfp_t)___GFP_RECLAIMABLE)
-#define __GFP_WRITE ((__force gfp_t)___GFP_WRITE)
-#define __GFP_HARDWALL ((__force gfp_t)___GFP_HARDWALL)
-#define __GFP_THISNODE ((__force gfp_t)___GFP_THISNODE)
-#define __GFP_ACCOUNT ((__force gfp_t)___GFP_ACCOUNT)
-
-/**
- * DOC: Watermark modifiers
- *
- * Watermark modifiers -- controls access to emergency reserves
- * ------------------------------------------------------------
- *
- * %__GFP_HIGH indicates that the caller is high-priority and that granting
- * the request is necessary before the system can make forward progress.
- * For example, creating an IO context to clean pages.
- *
- * %__GFP_ATOMIC indicates that the caller cannot reclaim or sleep and is
- * high priority. Users are typically interrupt handlers. This may be
- * used in conjunction with %__GFP_HIGH
- *
- * %__GFP_MEMALLOC allows access to all memory. This should only be used when
- * the caller guarantees the allocation will allow more memory to be freed
- * very shortly e.g. process exiting or swapping. Users either should
- * be the MM or co-ordinating closely with the VM (e.g. swap over NFS).
- * Users of this flag have to be extremely careful to not deplete the reserve
- * completely and implement a throttling mechanism which controls the
- * consumption of the reserve based on the amount of freed memory.
- * Usage of a pre-allocated pool (e.g. mempool) should be always considered
- * before using this flag.
- *
- * %__GFP_NOMEMALLOC is used to explicitly forbid access to emergency reserves.
- * This takes precedence over the %__GFP_MEMALLOC flag if both are set.
- */
-#define __GFP_ATOMIC ((__force gfp_t)___GFP_ATOMIC)
-#define __GFP_HIGH ((__force gfp_t)___GFP_HIGH)
-#define __GFP_MEMALLOC ((__force gfp_t)___GFP_MEMALLOC)
-#define __GFP_NOMEMALLOC ((__force gfp_t)___GFP_NOMEMALLOC)
-
-/**
- * DOC: Reclaim modifiers
- *
- * Reclaim modifiers
- * -----------------
- * Please note that all the following flags are only applicable to sleepable
- * allocations (e.g. %GFP_NOWAIT and %GFP_ATOMIC will ignore them).
- *
- * %__GFP_IO can start physical IO.
- *
- * %__GFP_FS can call down to the low-level FS. Clearing the flag avoids the
- * allocator recursing into the filesystem which might already be holding
- * locks.
- *
- * %__GFP_DIRECT_RECLAIM indicates that the caller may enter direct reclaim.
- * This flag can be cleared to avoid unnecessary delays when a fallback
- * option is available.
- *
- * %__GFP_KSWAPD_RECLAIM indicates that the caller wants to wake kswapd when
- * the low watermark is reached and have it reclaim pages until the high
- * watermark is reached. A caller may wish to clear this flag when fallback
- * options are available and the reclaim is likely to disrupt the system. The
- * canonical example is THP allocation where a fallback is cheap but
- * reclaim/compaction may cause indirect stalls.
- *
- * %__GFP_RECLAIM is shorthand to allow/forbid both direct and kswapd reclaim.
- *
- * The default allocator behavior depends on the request size. We have a concept
- * of so called costly allocations (with order > %PAGE_ALLOC_COSTLY_ORDER).
- * !costly allocations are too essential to fail so they are implicitly
- * non-failing by default (with some exceptions like OOM victims might fail so
- * the caller still has to check for failures) while costly requests try to be
- * not disruptive and back off even without invoking the OOM killer.
- * The following three modifiers might be used to override some of these
- * implicit rules
- *
- * %__GFP_NORETRY: The VM implementation will try only very lightweight
- * memory direct reclaim to get some memory under memory pressure (thus
- * it can sleep). It will avoid disruptive actions like OOM killer. The
- * caller must handle the failure which is quite likely to happen under
- * heavy memory pressure. The flag is suitable when failure can easily be
- * handled at small cost, such as reduced throughput
- *
- * %__GFP_RETRY_MAYFAIL: The VM implementation will retry memory reclaim
- * procedures that have previously failed if there is some indication
- * that progress has been made else where. It can wait for other
- * tasks to attempt high level approaches to freeing memory such as
- * compaction (which removes fragmentation) and page-out.
- * There is still a definite limit to the number of retries, but it is
- * a larger limit than with %__GFP_NORETRY.
- * Allocations with this flag may fail, but only when there is
- * genuinely little unused memory. While these allocations do not
- * directly trigger the OOM killer, their failure indicates that
- * the system is likely to need to use the OOM killer soon. The
- * caller must handle failure, but can reasonably do so by failing
- * a higher-level request, or completing it only in a much less
- * efficient manner.
- * If the allocation does fail, and the caller is in a position to
- * free some non-essential memory, doing so could benefit the system
- * as a whole.
- *
- * %__GFP_NOFAIL: The VM implementation _must_ retry infinitely: the caller
- * cannot handle allocation failures. The allocation could block
- * indefinitely but will never return with failure. Testing for
- * failure is pointless.
- * New users should be evaluated carefully (and the flag should be
- * used only when there is no reasonable failure policy) but it is
- * definitely preferable to use the flag rather than opencode endless
- * loop around allocator.
- * Using this flag for costly allocations is _highly_ discouraged.
- */
-#define __GFP_IO ((__force gfp_t)___GFP_IO)
-#define __GFP_FS ((__force gfp_t)___GFP_FS)
-#define __GFP_DIRECT_RECLAIM ((__force gfp_t)___GFP_DIRECT_RECLAIM) /* Caller can reclaim */
-#define __GFP_KSWAPD_RECLAIM ((__force gfp_t)___GFP_KSWAPD_RECLAIM) /* kswapd can wake */
-#define __GFP_RECLAIM ((__force gfp_t)(___GFP_DIRECT_RECLAIM|___GFP_KSWAPD_RECLAIM))
-#define __GFP_RETRY_MAYFAIL ((__force gfp_t)___GFP_RETRY_MAYFAIL)
-#define __GFP_NOFAIL ((__force gfp_t)___GFP_NOFAIL)
-#define __GFP_NORETRY ((__force gfp_t)___GFP_NORETRY)
-
-/**
- * DOC: Action modifiers
- *
- * Action modifiers
- * ----------------
- *
- * %__GFP_NOWARN suppresses allocation failure reports.
- *
- * %__GFP_COMP address compound page metadata.
- *
- * %__GFP_ZERO returns a zeroed page on success.
- *
- * %__GFP_ZEROTAGS zeroes memory tags at allocation time if the memory itself
- * is being zeroed (either via __GFP_ZERO or via init_on_alloc, provided that
- * __GFP_SKIP_ZERO is not set). This flag is intended for optimization: setting
- * memory tags at the same time as zeroing memory has minimal additional
- * performace impact.
- *
- * %__GFP_SKIP_KASAN_UNPOISON makes KASAN skip unpoisoning on page allocation.
- * Only effective in HW_TAGS mode.
- *
- * %__GFP_SKIP_KASAN_POISON makes KASAN skip poisoning on page deallocation.
- * Typically, used for userspace pages. Only effective in HW_TAGS mode.
- */
-#define __GFP_NOWARN ((__force gfp_t)___GFP_NOWARN)
-#define __GFP_COMP ((__force gfp_t)___GFP_COMP)
-#define __GFP_ZERO ((__force gfp_t)___GFP_ZERO)
-#define __GFP_ZEROTAGS ((__force gfp_t)___GFP_ZEROTAGS)
-#define __GFP_SKIP_ZERO ((__force gfp_t)___GFP_SKIP_ZERO)
-#define __GFP_SKIP_KASAN_UNPOISON ((__force gfp_t)___GFP_SKIP_KASAN_UNPOISON)
-#define __GFP_SKIP_KASAN_POISON ((__force gfp_t)___GFP_SKIP_KASAN_POISON)
-
-/* Disable lockdep for GFP context tracking */
-#define __GFP_NOLOCKDEP ((__force gfp_t)___GFP_NOLOCKDEP)
-
-/* Room for N __GFP_FOO bits */
-#define __GFP_BITS_SHIFT (27 + IS_ENABLED(CONFIG_LOCKDEP))
-#define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1))
-
-/**
- * DOC: Useful GFP flag combinations
- *
- * Useful GFP flag combinations
- * ----------------------------
- *
- * Useful GFP flag combinations that are commonly used. It is recommended
- * that subsystems start with one of these combinations and then set/clear
- * %__GFP_FOO flags as necessary.
- *
- * %GFP_ATOMIC users can not sleep and need the allocation to succeed. A lower
- * watermark is applied to allow access to "atomic reserves".
- * The current implementation doesn't support NMI and few other strict
- * non-preemptive contexts (e.g. raw_spin_lock). The same applies to %GFP_NOWAIT.
- *
- * %GFP_KERNEL is typical for kernel-internal allocations. The caller requires
- * %ZONE_NORMAL or a lower zone for direct access but can direct reclaim.
- *
- * %GFP_KERNEL_ACCOUNT is the same as GFP_KERNEL, except the allocation is
- * accounted to kmemcg.
- *
- * %GFP_NOWAIT is for kernel allocations that should not stall for direct
- * reclaim, start physical IO or use any filesystem callback.
- *
- * %GFP_NOIO will use direct reclaim to discard clean pages or slab pages
- * that do not require the starting of any physical IO.
- * Please try to avoid using this flag directly and instead use
- * memalloc_noio_{save,restore} to mark the whole scope which cannot
- * perform any IO with a short explanation why. All allocation requests
- * will inherit GFP_NOIO implicitly.
- *
- * %GFP_NOFS will use direct reclaim but will not use any filesystem interfaces.
- * Please try to avoid using this flag directly and instead use
- * memalloc_nofs_{save,restore} to mark the whole scope which cannot/shouldn't
- * recurse into the FS layer with a short explanation why. All allocation
- * requests will inherit GFP_NOFS implicitly.
- *
- * %GFP_USER is for userspace allocations that also need to be directly
- * accessibly by the kernel or hardware. It is typically used by hardware
- * for buffers that are mapped to userspace (e.g. graphics) that hardware
- * still must DMA to. cpuset limits are enforced for these allocations.
- *
- * %GFP_DMA exists for historical reasons and should be avoided where possible.
- * The flags indicates that the caller requires that the lowest zone be
- * used (%ZONE_DMA or 16M on x86-64). Ideally, this would be removed but
- * it would require careful auditing as some users really require it and
- * others use the flag to avoid lowmem reserves in %ZONE_DMA and treat the
- * lowest zone as a type of emergency reserve.
- *
- * %GFP_DMA32 is similar to %GFP_DMA except that the caller requires a 32-bit
- * address. Note that kmalloc(..., GFP_DMA32) does not return DMA32 memory
- * because the DMA32 kmalloc cache array is not implemented.
- * (Reason: there is no such user in kernel).
- *
- * %GFP_HIGHUSER is for userspace allocations that may be mapped to userspace,
- * do not need to be directly accessible by the kernel but that cannot
- * move once in use. An example may be a hardware allocation that maps
- * data directly into userspace but has no addressing limitations.
- *
- * %GFP_HIGHUSER_MOVABLE is for userspace allocations that the kernel does not
- * need direct access to but can use kmap() when access is required. They
- * are expected to be movable via page reclaim or page migration. Typically,
- * pages on the LRU would also be allocated with %GFP_HIGHUSER_MOVABLE.
- *
- * %GFP_TRANSHUGE and %GFP_TRANSHUGE_LIGHT are used for THP allocations. They
- * are compound allocations that will generally fail quickly if memory is not
- * available and will not wake kswapd/kcompactd on failure. The _LIGHT
- * version does not attempt reclaim/compaction at all and is by default used
- * in page fault path, while the non-light is used by khugepaged.
- */
-#define GFP_ATOMIC (__GFP_HIGH|__GFP_ATOMIC|__GFP_KSWAPD_RECLAIM)
-#define GFP_KERNEL (__GFP_RECLAIM | __GFP_IO | __GFP_FS)
-#define GFP_KERNEL_ACCOUNT (GFP_KERNEL | __GFP_ACCOUNT)
-#define GFP_NOWAIT (__GFP_KSWAPD_RECLAIM)
-#define GFP_NOIO (__GFP_RECLAIM)
-#define GFP_NOFS (__GFP_RECLAIM | __GFP_IO)
-#define GFP_USER (__GFP_RECLAIM | __GFP_IO | __GFP_FS | __GFP_HARDWALL)
-#define GFP_DMA __GFP_DMA
-#define GFP_DMA32 __GFP_DMA32
-#define GFP_HIGHUSER (GFP_USER | __GFP_HIGHMEM)
-#define GFP_HIGHUSER_MOVABLE (GFP_HIGHUSER | __GFP_MOVABLE | \
- __GFP_SKIP_KASAN_POISON)
-#define GFP_TRANSHUGE_LIGHT ((GFP_HIGHUSER_MOVABLE | __GFP_COMP | \
- __GFP_NOMEMALLOC | __GFP_NOWARN) & ~__GFP_RECLAIM)
-#define GFP_TRANSHUGE (GFP_TRANSHUGE_LIGHT | __GFP_DIRECT_RECLAIM)
-
/* Convert GFP flags to their corresponding migrate type */
#define GFP_MOVABLE_MASK (__GFP_RECLAIMABLE|__GFP_MOVABLE)
#define GFP_MOVABLE_SHIFT 3
diff --git a/include/linux/gfp_types.h b/include/linux/gfp_types.h
new file mode 100644
index 000000000000..06fc85cee23f
--- /dev/null
+++ b/include/linux/gfp_types.h
@@ -0,0 +1,348 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __LINUX_GFP_TYPES_H
+#define __LINUX_GFP_TYPES_H
+
+/* The typedef is in types.h but we want the documentation here */
+#if 0
+/**
+ * typedef gfp_t - Memory allocation flags.
+ *
+ * GFP flags are commonly used throughout Linux to indicate how memory
+ * should be allocated. The GFP acronym stands for get_free_pages(),
+ * the underlying memory allocation function. Not every GFP flag is
+ * supported by every function which may allocate memory. Most users
+ * will want to use a plain ``GFP_KERNEL``.
+ */
+typedef unsigned int __bitwise gfp_t;
+#endif
+
+/*
+ * In case of changes, please don't forget to update
+ * include/trace/events/mmflags.h and tools/perf/builtin-kmem.c
+ */
+
+/* Plain integer GFP bitmasks. Do not use this directly. */
+#define ___GFP_DMA 0x01u
+#define ___GFP_HIGHMEM 0x02u
+#define ___GFP_DMA32 0x04u
+#define ___GFP_MOVABLE 0x08u
+#define ___GFP_RECLAIMABLE 0x10u
+#define ___GFP_HIGH 0x20u
+#define ___GFP_IO 0x40u
+#define ___GFP_FS 0x80u
+#define ___GFP_ZERO 0x100u
+#define ___GFP_ATOMIC 0x200u
+#define ___GFP_DIRECT_RECLAIM 0x400u
+#define ___GFP_KSWAPD_RECLAIM 0x800u
+#define ___GFP_WRITE 0x1000u
+#define ___GFP_NOWARN 0x2000u
+#define ___GFP_RETRY_MAYFAIL 0x4000u
+#define ___GFP_NOFAIL 0x8000u
+#define ___GFP_NORETRY 0x10000u
+#define ___GFP_MEMALLOC 0x20000u
+#define ___GFP_COMP 0x40000u
+#define ___GFP_NOMEMALLOC 0x80000u
+#define ___GFP_HARDWALL 0x100000u
+#define ___GFP_THISNODE 0x200000u
+#define ___GFP_ACCOUNT 0x400000u
+#define ___GFP_ZEROTAGS 0x800000u
+#ifdef CONFIG_KASAN_HW_TAGS
+#define ___GFP_SKIP_ZERO 0x1000000u
+#define ___GFP_SKIP_KASAN_UNPOISON 0x2000000u
+#define ___GFP_SKIP_KASAN_POISON 0x4000000u
+#else
+#define ___GFP_SKIP_ZERO 0
+#define ___GFP_SKIP_KASAN_UNPOISON 0
+#define ___GFP_SKIP_KASAN_POISON 0
+#endif
+#ifdef CONFIG_LOCKDEP
+#define ___GFP_NOLOCKDEP 0x8000000u
+#else
+#define ___GFP_NOLOCKDEP 0
+#endif
+/* If the above are modified, __GFP_BITS_SHIFT may need updating */
+
+/*
+ * Physical address zone modifiers (see linux/mmzone.h - low four bits)
+ *
+ * Do not put any conditional on these. If necessary modify the definitions
+ * without the underscores and use them consistently. The definitions here may
+ * be used in bit comparisons.
+ */
+#define __GFP_DMA ((__force gfp_t)___GFP_DMA)
+#define __GFP_HIGHMEM ((__force gfp_t)___GFP_HIGHMEM)
+#define __GFP_DMA32 ((__force gfp_t)___GFP_DMA32)
+#define __GFP_MOVABLE ((__force gfp_t)___GFP_MOVABLE) /* ZONE_MOVABLE allowed */
+#define GFP_ZONEMASK (__GFP_DMA|__GFP_HIGHMEM|__GFP_DMA32|__GFP_MOVABLE)
+
+/**
+ * DOC: Page mobility and placement hints
+ *
+ * Page mobility and placement hints
+ * ---------------------------------
+ *
+ * These flags provide hints about how mobile the page is. Pages with similar
+ * mobility are placed within the same pageblocks to minimise problems due
+ * to external fragmentation.
+ *
+ * %__GFP_MOVABLE (also a zone modifier) indicates that the page can be
+ * moved by page migration during memory compaction or can be reclaimed.
+ *
+ * %__GFP_RECLAIMABLE is used for slab allocations that specify
+ * SLAB_RECLAIM_ACCOUNT and whose pages can be freed via shrinkers.
+ *
+ * %__GFP_WRITE indicates the caller intends to dirty the page. Where possible,
+ * these pages will be spread between local zones to avoid all the dirty
+ * pages being in one zone (fair zone allocation policy).
+ *
+ * %__GFP_HARDWALL enforces the cpuset memory allocation policy.
+ *
+ * %__GFP_THISNODE forces the allocation to be satisfied from the requested
+ * node with no fallbacks or placement policy enforcements.
+ *
+ * %__GFP_ACCOUNT causes the allocation to be accounted to kmemcg.
+ */
+#define __GFP_RECLAIMABLE ((__force gfp_t)___GFP_RECLAIMABLE)
+#define __GFP_WRITE ((__force gfp_t)___GFP_WRITE)
+#define __GFP_HARDWALL ((__force gfp_t)___GFP_HARDWALL)
+#define __GFP_THISNODE ((__force gfp_t)___GFP_THISNODE)
+#define __GFP_ACCOUNT ((__force gfp_t)___GFP_ACCOUNT)
+
+/**
+ * DOC: Watermark modifiers
+ *
+ * Watermark modifiers -- controls access to emergency reserves
+ * ------------------------------------------------------------
+ *
+ * %__GFP_HIGH indicates that the caller is high-priority and that granting
+ * the request is necessary before the system can make forward progress.
+ * For example, creating an IO context to clean pages.
+ *
+ * %__GFP_ATOMIC indicates that the caller cannot reclaim or sleep and is
+ * high priority. Users are typically interrupt handlers. This may be
+ * used in conjunction with %__GFP_HIGH
+ *
+ * %__GFP_MEMALLOC allows access to all memory. This should only be used when
+ * the caller guarantees the allocation will allow more memory to be freed
+ * very shortly e.g. process exiting or swapping. Users either should
+ * be the MM or co-ordinating closely with the VM (e.g. swap over NFS).
+ * Users of this flag have to be extremely careful to not deplete the reserve
+ * completely and implement a throttling mechanism which controls the
+ * consumption of the reserve based on the amount of freed memory.
+ * Usage of a pre-allocated pool (e.g. mempool) should be always considered
+ * before using this flag.
+ *
+ * %__GFP_NOMEMALLOC is used to explicitly forbid access to emergency reserves.
+ * This takes precedence over the %__GFP_MEMALLOC flag if both are set.
+ */
+#define __GFP_ATOMIC ((__force gfp_t)___GFP_ATOMIC)
+#define __GFP_HIGH ((__force gfp_t)___GFP_HIGH)
+#define __GFP_MEMALLOC ((__force gfp_t)___GFP_MEMALLOC)
+#define __GFP_NOMEMALLOC ((__force gfp_t)___GFP_NOMEMALLOC)
+
+/**
+ * DOC: Reclaim modifiers
+ *
+ * Reclaim modifiers
+ * -----------------
+ * Please note that all the following flags are only applicable to sleepable
+ * allocations (e.g. %GFP_NOWAIT and %GFP_ATOMIC will ignore them).
+ *
+ * %__GFP_IO can start physical IO.
+ *
+ * %__GFP_FS can call down to the low-level FS. Clearing the flag avoids the
+ * allocator recursing into the filesystem which might already be holding
+ * locks.
+ *
+ * %__GFP_DIRECT_RECLAIM indicates that the caller may enter direct reclaim.
+ * This flag can be cleared to avoid unnecessary delays when a fallback
+ * option is available.
+ *
+ * %__GFP_KSWAPD_RECLAIM indicates that the caller wants to wake kswapd when
+ * the low watermark is reached and have it reclaim pages until the high
+ * watermark is reached. A caller may wish to clear this flag when fallback
+ * options are available and the reclaim is likely to disrupt the system. The
+ * canonical example is THP allocation where a fallback is cheap but
+ * reclaim/compaction may cause indirect stalls.
+ *
+ * %__GFP_RECLAIM is shorthand to allow/forbid both direct and kswapd reclaim.
+ *
+ * The default allocator behavior depends on the request size. We have a concept
+ * of so called costly allocations (with order > %PAGE_ALLOC_COSTLY_ORDER).
+ * !costly allocations are too essential to fail so they are implicitly
+ * non-failing by default (with some exceptions like OOM victims might fail so
+ * the caller still has to check for failures) while costly requests try to be
+ * not disruptive and back off even without invoking the OOM killer.
+ * The following three modifiers might be used to override some of these
+ * implicit rules
+ *
+ * %__GFP_NORETRY: The VM implementation will try only very lightweight
+ * memory direct reclaim to get some memory under memory pressure (thus
+ * it can sleep). It will avoid disruptive actions like OOM killer. The
+ * caller must handle the failure which is quite likely to happen under
+ * heavy memory pressure. The flag is suitable when failure can easily be
+ * handled at small cost, such as reduced throughput
+ *
+ * %__GFP_RETRY_MAYFAIL: The VM implementation will retry memory reclaim
+ * procedures that have previously failed if there is some indication
+ * that progress has been made else where. It can wait for other
+ * tasks to attempt high level approaches to freeing memory such as
+ * compaction (which removes fragmentation) and page-out.
+ * There is still a definite limit to the number of retries, but it is
+ * a larger limit than with %__GFP_NORETRY.
+ * Allocations with this flag may fail, but only when there is
+ * genuinely little unused memory. While these allocations do not
+ * directly trigger the OOM killer, their failure indicates that
+ * the system is likely to need to use the OOM killer soon. The
+ * caller must handle failure, but can reasonably do so by failing
+ * a higher-level request, or completing it only in a much less
+ * efficient manner.
+ * If the allocation does fail, and the caller is in a position to
+ * free some non-essential memory, doing so could benefit the system
+ * as a whole.
+ *
+ * %__GFP_NOFAIL: The VM implementation _must_ retry infinitely: the caller
+ * cannot handle allocation failures. The allocation could block
+ * indefinitely but will never return with failure. Testing for
+ * failure is pointless.
+ * New users should be evaluated carefully (and the flag should be
+ * used only when there is no reasonable failure policy) but it is
+ * definitely preferable to use the flag rather than opencode endless
+ * loop around allocator.
+ * Using this flag for costly allocations is _highly_ discouraged.
+ */
+#define __GFP_IO ((__force gfp_t)___GFP_IO)
+#define __GFP_FS ((__force gfp_t)___GFP_FS)
+#define __GFP_DIRECT_RECLAIM ((__force gfp_t)___GFP_DIRECT_RECLAIM) /* Caller can reclaim */
+#define __GFP_KSWAPD_RECLAIM ((__force gfp_t)___GFP_KSWAPD_RECLAIM) /* kswapd can wake */
+#define __GFP_RECLAIM ((__force gfp_t)(___GFP_DIRECT_RECLAIM|___GFP_KSWAPD_RECLAIM))
+#define __GFP_RETRY_MAYFAIL ((__force gfp_t)___GFP_RETRY_MAYFAIL)
+#define __GFP_NOFAIL ((__force gfp_t)___GFP_NOFAIL)
+#define __GFP_NORETRY ((__force gfp_t)___GFP_NORETRY)
+
+/**
+ * DOC: Action modifiers
+ *
+ * Action modifiers
+ * ----------------
+ *
+ * %__GFP_NOWARN suppresses allocation failure reports.
+ *
+ * %__GFP_COMP address compound page metadata.
+ *
+ * %__GFP_ZERO returns a zeroed page on success.
+ *
+ * %__GFP_ZEROTAGS zeroes memory tags at allocation time if the memory itself
+ * is being zeroed (either via __GFP_ZERO or via init_on_alloc, provided that
+ * __GFP_SKIP_ZERO is not set). This flag is intended for optimization: setting
+ * memory tags at the same time as zeroing memory has minimal additional
+ * performace impact.
+ *
+ * %__GFP_SKIP_KASAN_UNPOISON makes KASAN skip unpoisoning on page allocation.
+ * Only effective in HW_TAGS mode.
+ *
+ * %__GFP_SKIP_KASAN_POISON makes KASAN skip poisoning on page deallocation.
+ * Typically, used for userspace pages. Only effective in HW_TAGS mode.
+ */
+#define __GFP_NOWARN ((__force gfp_t)___GFP_NOWARN)
+#define __GFP_COMP ((__force gfp_t)___GFP_COMP)
+#define __GFP_ZERO ((__force gfp_t)___GFP_ZERO)
+#define __GFP_ZEROTAGS ((__force gfp_t)___GFP_ZEROTAGS)
+#define __GFP_SKIP_ZERO ((__force gfp_t)___GFP_SKIP_ZERO)
+#define __GFP_SKIP_KASAN_UNPOISON ((__force gfp_t)___GFP_SKIP_KASAN_UNPOISON)
+#define __GFP_SKIP_KASAN_POISON ((__force gfp_t)___GFP_SKIP_KASAN_POISON)
+
+/* Disable lockdep for GFP context tracking */
+#define __GFP_NOLOCKDEP ((__force gfp_t)___GFP_NOLOCKDEP)
+
+/* Room for N __GFP_FOO bits */
+#define __GFP_BITS_SHIFT (27 + IS_ENABLED(CONFIG_LOCKDEP))
+#define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1))
+
+/**
+ * DOC: Useful GFP flag combinations
+ *
+ * Useful GFP flag combinations
+ * ----------------------------
+ *
+ * Useful GFP flag combinations that are commonly used. It is recommended
+ * that subsystems start with one of these combinations and then set/clear
+ * %__GFP_FOO flags as necessary.
+ *
+ * %GFP_ATOMIC users can not sleep and need the allocation to succeed. A lower
+ * watermark is applied to allow access to "atomic reserves".
+ * The current implementation doesn't support NMI and few other strict
+ * non-preemptive contexts (e.g. raw_spin_lock). The same applies to %GFP_NOWAIT.
+ *
+ * %GFP_KERNEL is typical for kernel-internal allocations. The caller requires
+ * %ZONE_NORMAL or a lower zone for direct access but can direct reclaim.
+ *
+ * %GFP_KERNEL_ACCOUNT is the same as GFP_KERNEL, except the allocation is
+ * accounted to kmemcg.
+ *
+ * %GFP_NOWAIT is for kernel allocations that should not stall for direct
+ * reclaim, start physical IO or use any filesystem callback.
+ *
+ * %GFP_NOIO will use direct reclaim to discard clean pages or slab pages
+ * that do not require the starting of any physical IO.
+ * Please try to avoid using this flag directly and instead use
+ * memalloc_noio_{save,restore} to mark the whole scope which cannot
+ * perform any IO with a short explanation why. All allocation requests
+ * will inherit GFP_NOIO implicitly.
+ *
+ * %GFP_NOFS will use direct reclaim but will not use any filesystem interfaces.
+ * Please try to avoid using this flag directly and instead use
+ * memalloc_nofs_{save,restore} to mark the whole scope which cannot/shouldn't
+ * recurse into the FS layer with a short explanation why. All allocation
+ * requests will inherit GFP_NOFS implicitly.
+ *
+ * %GFP_USER is for userspace allocations that also need to be directly
+ * accessibly by the kernel or hardware. It is typically used by hardware
+ * for buffers that are mapped to userspace (e.g. graphics) that hardware
+ * still must DMA to. cpuset limits are enforced for these allocations.
+ *
+ * %GFP_DMA exists for historical reasons and should be avoided where possible.
+ * The flags indicates that the caller requires that the lowest zone be
+ * used (%ZONE_DMA or 16M on x86-64). Ideally, this would be removed but
+ * it would require careful auditing as some users really require it and
+ * others use the flag to avoid lowmem reserves in %ZONE_DMA and treat the
+ * lowest zone as a type of emergency reserve.
+ *
+ * %GFP_DMA32 is similar to %GFP_DMA except that the caller requires a 32-bit
+ * address. Note that kmalloc(..., GFP_DMA32) does not return DMA32 memory
+ * because the DMA32 kmalloc cache array is not implemented.
+ * (Reason: there is no such user in kernel).
+ *
+ * %GFP_HIGHUSER is for userspace allocations that may be mapped to userspace,
+ * do not need to be directly accessible by the kernel but that cannot
+ * move once in use. An example may be a hardware allocation that maps
+ * data directly into userspace but has no addressing limitations.
+ *
+ * %GFP_HIGHUSER_MOVABLE is for userspace allocations that the kernel does not
+ * need direct access to but can use kmap() when access is required. They
+ * are expected to be movable via page reclaim or page migration. Typically,
+ * pages on the LRU would also be allocated with %GFP_HIGHUSER_MOVABLE.
+ *
+ * %GFP_TRANSHUGE and %GFP_TRANSHUGE_LIGHT are used for THP allocations. They
+ * are compound allocations that will generally fail quickly if memory is not
+ * available and will not wake kswapd/kcompactd on failure. The _LIGHT
+ * version does not attempt reclaim/compaction at all and is by default used
+ * in page fault path, while the non-light is used by khugepaged.
+ */
+#define GFP_ATOMIC (__GFP_HIGH|__GFP_ATOMIC|__GFP_KSWAPD_RECLAIM)
+#define GFP_KERNEL (__GFP_RECLAIM | __GFP_IO | __GFP_FS)
+#define GFP_KERNEL_ACCOUNT (GFP_KERNEL | __GFP_ACCOUNT)
+#define GFP_NOWAIT (__GFP_KSWAPD_RECLAIM)
+#define GFP_NOIO (__GFP_RECLAIM)
+#define GFP_NOFS (__GFP_RECLAIM | __GFP_IO)
+#define GFP_USER (__GFP_RECLAIM | __GFP_IO | __GFP_FS | __GFP_HARDWALL)
+#define GFP_DMA __GFP_DMA
+#define GFP_DMA32 __GFP_DMA32
+#define GFP_HIGHUSER (GFP_USER | __GFP_HIGHMEM)
+#define GFP_HIGHUSER_MOVABLE (GFP_HIGHUSER | __GFP_MOVABLE | \
+ __GFP_SKIP_KASAN_POISON)
+#define GFP_TRANSHUGE_LIGHT ((GFP_HIGHUSER_MOVABLE | __GFP_COMP | \
+ __GFP_NOMEMALLOC | __GFP_NOWARN) & ~__GFP_RECLAIM)
+#define GFP_TRANSHUGE (GFP_TRANSHUGE_LIGHT | __GFP_DIRECT_RECLAIM)
+
+#endif /* __LINUX_GFP_TYPES_H */
--
2.34.1
Some bitmap functions return boolean results in int variables. Fix it
by changing return types to bool.
Signed-off-by: Yury Norov <[email protected]>
---
include/linux/bitmap.h | 8 ++++----
lib/bitmap.c | 4 ++--
tools/include/linux/bitmap.h | 8 ++++----
tools/lib/bitmap.c | 2 +-
4 files changed, 11 insertions(+), 11 deletions(-)
diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h
index 2e6cd5681040..85aace699b2b 100644
--- a/include/linux/bitmap.h
+++ b/include/linux/bitmap.h
@@ -148,13 +148,13 @@ void __bitmap_shift_left(unsigned long *dst, const unsigned long *src,
unsigned int shift, unsigned int nbits);
void bitmap_cut(unsigned long *dst, const unsigned long *src,
unsigned int first, unsigned int cut, unsigned int nbits);
-int __bitmap_and(unsigned long *dst, const unsigned long *bitmap1,
+bool __bitmap_and(unsigned long *dst, const unsigned long *bitmap1,
const unsigned long *bitmap2, unsigned int nbits);
void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1,
const unsigned long *bitmap2, unsigned int nbits);
void __bitmap_xor(unsigned long *dst, const unsigned long *bitmap1,
const unsigned long *bitmap2, unsigned int nbits);
-int __bitmap_andnot(unsigned long *dst, const unsigned long *bitmap1,
+bool __bitmap_andnot(unsigned long *dst, const unsigned long *bitmap1,
const unsigned long *bitmap2, unsigned int nbits);
void __bitmap_replace(unsigned long *dst,
const unsigned long *old, const unsigned long *new,
@@ -303,7 +303,7 @@ void bitmap_to_arr64(u64 *buf, const unsigned long *bitmap, unsigned int nbits);
bitmap_copy_clear_tail((unsigned long *)(buf), (const unsigned long *)(bitmap), (nbits))
#endif
-static inline int bitmap_and(unsigned long *dst, const unsigned long *src1,
+static inline bool bitmap_and(unsigned long *dst, const unsigned long *src1,
const unsigned long *src2, unsigned int nbits)
{
if (small_const_nbits(nbits))
@@ -329,7 +329,7 @@ static inline void bitmap_xor(unsigned long *dst, const unsigned long *src1,
__bitmap_xor(dst, src1, src2, nbits);
}
-static inline int bitmap_andnot(unsigned long *dst, const unsigned long *src1,
+static inline bool bitmap_andnot(unsigned long *dst, const unsigned long *src1,
const unsigned long *src2, unsigned int nbits)
{
if (small_const_nbits(nbits))
diff --git a/lib/bitmap.c b/lib/bitmap.c
index b18e31ea6e66..098fd9db2363 100644
--- a/lib/bitmap.c
+++ b/lib/bitmap.c
@@ -237,7 +237,7 @@ void bitmap_cut(unsigned long *dst, const unsigned long *src,
}
EXPORT_SYMBOL(bitmap_cut);
-int __bitmap_and(unsigned long *dst, const unsigned long *bitmap1,
+bool __bitmap_and(unsigned long *dst, const unsigned long *bitmap1,
const unsigned long *bitmap2, unsigned int bits)
{
unsigned int k;
@@ -275,7 +275,7 @@ void __bitmap_xor(unsigned long *dst, const unsigned long *bitmap1,
}
EXPORT_SYMBOL(__bitmap_xor);
-int __bitmap_andnot(unsigned long *dst, const unsigned long *bitmap1,
+bool __bitmap_andnot(unsigned long *dst, const unsigned long *bitmap1,
const unsigned long *bitmap2, unsigned int bits)
{
unsigned int k;
diff --git a/tools/include/linux/bitmap.h b/tools/include/linux/bitmap.h
index afdf93bebaaf..2ae7ab8ed7d1 100644
--- a/tools/include/linux/bitmap.h
+++ b/tools/include/linux/bitmap.h
@@ -14,7 +14,7 @@
int __bitmap_weight(const unsigned long *bitmap, int bits);
void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1,
const unsigned long *bitmap2, int bits);
-int __bitmap_and(unsigned long *dst, const unsigned long *bitmap1,
+bool __bitmap_and(unsigned long *dst, const unsigned long *bitmap1,
const unsigned long *bitmap2, unsigned int bits);
bool __bitmap_equal(const unsigned long *bitmap1,
const unsigned long *bitmap2, unsigned int bits);
@@ -45,7 +45,7 @@ static inline void bitmap_fill(unsigned long *dst, unsigned int nbits)
dst[nlongs - 1] = BITMAP_LAST_WORD_MASK(nbits);
}
-static inline int bitmap_empty(const unsigned long *src, unsigned nbits)
+static inline bool bitmap_empty(const unsigned long *src, unsigned int nbits)
{
if (small_const_nbits(nbits))
return ! (*src & BITMAP_LAST_WORD_MASK(nbits));
@@ -53,7 +53,7 @@ static inline int bitmap_empty(const unsigned long *src, unsigned nbits)
return find_first_bit(src, nbits) == nbits;
}
-static inline int bitmap_full(const unsigned long *src, unsigned int nbits)
+static inline bool bitmap_full(const unsigned long *src, unsigned int nbits)
{
if (small_const_nbits(nbits))
return ! (~(*src) & BITMAP_LAST_WORD_MASK(nbits));
@@ -146,7 +146,7 @@ size_t bitmap_scnprintf(unsigned long *bitmap, unsigned int nbits,
* @src2: operand 2
* @nbits: size of bitmap
*/
-static inline int bitmap_and(unsigned long *dst, const unsigned long *src1,
+static inline bool bitmap_and(unsigned long *dst, const unsigned long *src1,
const unsigned long *src2, unsigned int nbits)
{
if (small_const_nbits(nbits))
diff --git a/tools/lib/bitmap.c b/tools/lib/bitmap.c
index 354f8cdc0880..2e351d63fdba 100644
--- a/tools/lib/bitmap.c
+++ b/tools/lib/bitmap.c
@@ -57,7 +57,7 @@ size_t bitmap_scnprintf(unsigned long *bitmap, unsigned int nbits,
return ret;
}
-int __bitmap_and(unsigned long *dst, const unsigned long *bitmap1,
+bool __bitmap_and(unsigned long *dst, const unsigned long *bitmap1,
const unsigned long *bitmap2, unsigned int bits)
{
unsigned int k;
--
2.34.1
After moving gfp types out of gfp.h, we have to align MAINTAINERS
and Docs, to avoid warnings like this:
>> include/linux/gfp.h:1: warning: 'Page mobility and placement hints' not found
>> include/linux/gfp.h:1: warning: 'Watermark modifiers' not found
>> include/linux/gfp.h:1: warning: 'Reclaim modifiers' not found
>> include/linux/gfp.h:1: warning: 'Useful GFP flag combinations' not found
Signed-off-by: Yury Norov <[email protected]>
---
Documentation/core-api/mm-api.rst | 8 ++++----
MAINTAINERS | 1 +
2 files changed, 5 insertions(+), 4 deletions(-)
diff --git a/Documentation/core-api/mm-api.rst b/Documentation/core-api/mm-api.rst
index f5b2f92822c8..1ebcc6c3fafe 100644
--- a/Documentation/core-api/mm-api.rst
+++ b/Documentation/core-api/mm-api.rst
@@ -22,16 +22,16 @@ Memory Allocation Controls
.. kernel-doc:: include/linux/gfp.h
:internal:
-.. kernel-doc:: include/linux/gfp.h
+.. kernel-doc:: include/linux/gfp_types.h
:doc: Page mobility and placement hints
-.. kernel-doc:: include/linux/gfp.h
+.. kernel-doc:: include/linux/gfp_types.h
:doc: Watermark modifiers
-.. kernel-doc:: include/linux/gfp.h
+.. kernel-doc:: include/linux/gfp_types.h
:doc: Reclaim modifiers
-.. kernel-doc:: include/linux/gfp.h
+.. kernel-doc:: include/linux/gfp_types.h
:doc: Useful GFP flag combinations
The Slab Cache
diff --git a/MAINTAINERS b/MAINTAINERS
index 3cf9842d9233..7c0b8f28aa25 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -12850,6 +12850,7 @@ T: quilt https://ozlabs.org/~akpm/mmotm/
T: quilt https://ozlabs.org/~akpm/mmots/
T: git git://github.com/hnaz/linux-mm.git
F: include/linux/gfp.h
+F: include/linux/gfp_types.h
F: include/linux/memory_hotplug.h
F: include/linux/mm.h
F: include/linux/mmzone.h
--
2.34.1
ARM has their own implementation for find_bit functions, and function
declarations are different with those in generic headers. Fix it.
Signed-off-by: Yury Norov <[email protected]>
---
arch/arm/include/asm/bitops.h | 18 ++++++++++--------
1 file changed, 10 insertions(+), 8 deletions(-)
diff --git a/arch/arm/include/asm/bitops.h b/arch/arm/include/asm/bitops.h
index 8e94fe7ab5eb..714440fa2fc6 100644
--- a/arch/arm/include/asm/bitops.h
+++ b/arch/arm/include/asm/bitops.h
@@ -160,18 +160,20 @@ extern int _test_and_change_bit(int nr, volatile unsigned long * p);
/*
* Little endian assembly bitops. nr = 0 -> byte 0 bit 0.
*/
-extern int _find_first_zero_bit_le(const unsigned long *p, unsigned size);
-extern int _find_next_zero_bit_le(const unsigned long *p, int size, int offset);
-extern int _find_first_bit_le(const unsigned long *p, unsigned size);
-extern int _find_next_bit_le(const unsigned long *p, int size, int offset);
+unsigned long _find_first_zero_bit_le(const unsigned long *p, unsigned long size);
+unsigned long _find_next_zero_bit_le(const unsigned long *p,
+ unsigned long size, unsigned long offset);
+unsigned long _find_first_bit_le(const unsigned long *p, unsigned long size);
+unsigned long _find_next_bit_le(const unsigned long *p, unsigned long size, unsigned long offset);
/*
* Big endian assembly bitops. nr = 0 -> byte 3 bit 0.
*/
-extern int _find_first_zero_bit_be(const unsigned long *p, unsigned size);
-extern int _find_next_zero_bit_be(const unsigned long *p, int size, int offset);
-extern int _find_first_bit_be(const unsigned long *p, unsigned size);
-extern int _find_next_bit_be(const unsigned long *p, int size, int offset);
+unsigned long _find_first_zero_bit_be(const unsigned long *p, unsigned long size);
+unsigned long _find_next_zero_bit_be(const unsigned long *p,
+ unsigned long size, unsigned long offset);
+unsigned long _find_first_bit_be(const unsigned long *p, unsigned long size);
+unsigned long _find_next_bit_be(const unsigned long *p, unsigned long size, unsigned long offset);
#ifndef CONFIG_SMP
/*
--
2.34.1
On Wed, Jul 6, 2022 at 10:42 AM Yury Norov <[email protected]> wrote:
>
> This series unifies declarations of bitmap-related functions and aligns
> return types with values that actually returned. Also, it moves one-liner
> wrappers around cpumask functions into headers, so that compiler has a
> chance to optimize better.
>
> With this series, GCC 11.2 for ARM64 with kernel v5.19-rc4:
> add/remove: 15/7 grow/shrink: 461/164 up/down: 14844/-4580 (10264)
>
> This +10K didn't surprise me because modern compilers are more aggressive
> in inlining, loop unrolling, and other techniques that increase size of
> the image.
>
> v1: https://lore.kernel.org/linux-mm/[email protected]/T/
> v2: - Align whitespaces in headers;
> - Make bitmap_weight() unsigned long consistently;
> - Pick 2 patches from Ingo's sched/headers series [1] that split
> linux/gfp.h, and drop my similar patch for it.
Ping?
On Tue, Jul 12, 2022 at 09:28:21AM -0700, Yury Norov wrote:
> On Wed, Jul 6, 2022 at 10:42 AM Yury Norov <[email protected]> wrote:
> >
> > This series unifies declarations of bitmap-related functions and aligns
> > return types with values that actually returned. Also, it moves one-liner
> > wrappers around cpumask functions into headers, so that compiler has a
> > chance to optimize better.
> >
> > With this series, GCC 11.2 for ARM64 with kernel v5.19-rc4:
> > add/remove: 15/7 grow/shrink: 461/164 up/down: 14844/-4580 (10264)
> >
> > This +10K didn't surprise me because modern compilers are more aggressive
> > in inlining, loop unrolling, and other techniques that increase size of
> > the image.
> >
> > v1: https://lore.kernel.org/linux-mm/[email protected]/T/
> > v2: - Align whitespaces in headers;
> > - Make bitmap_weight() unsigned long consistently;
> > - Pick 2 patches from Ingo's sched/headers series [1] that split
> > linux/gfp.h, and drop my similar patch for it.
>
> Ping?
OK, I realize that it's not the very entertaining thing to review a
headers cleanup.
Adding this into -next because there's no negative feedback (he-he).
Hi Yury,
On Wed, 2022-07-06 at 10:42 -0700, Yury Norov wrote:
> To avoid circular dependencies, cpumask keeps simple (almost) one-line
> wrappers around find_bit() in a c-file.
>
> Commit 47d8c15615c0a2 ("include: move find.h from asm_generic to linux")
> moved find.h header out of asm_generic include path, and it helped to fix
> many circular dependencies, including some in cpumask.h.
>
> This patch moves those one-liners to header files.
>
> Signed-off-by: Yury Norov <[email protected]>
> ---
> include/linux/cpumask.h | 57 ++++++++++++++++++++++++++++++++++++++---
> lib/cpumask.c | 55 ---------------------------------------
> 2 files changed, 54 insertions(+), 58 deletions(-)
>
> diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
> index 760022bcb925..ea3de2c2c180 100644
> --- a/include/linux/cpumask.h
> +++ b/include/linux/cpumask.h
> @@ -241,7 +241,21 @@ static inline unsigned int cpumask_last(const struct
> cpumask *srcp)
> return find_last_bit(cpumask_bits(srcp), nr_cpumask_bits);
> }
>
> -unsigned int __pure cpumask_next(int n, const struct cpumask *srcp);
> +/**
> + * cpumask_next - get the next cpu in a cpumask
> + * @n: the cpu prior to the place to search (ie. return will be > @n)
> + * @srcp: the cpumask pointer
> + *
> + * Returns >= nr_cpu_ids if no further cpus set.
> + */
> +static inline
> +unsigned int cpumask_next(int n, const struct cpumask *srcp)
This also drops the __pure speficier for these functions. Since I have a patch
that does the opposite for cpumask_next_wrap() [1], I was wondering what your
reasoning behind this is.
Since a cpumask like cpu_online_mask may change between subsequent calls, I'm
considering to drop my patch adding __pure, and to follow the changes you've
made here.
[1]
https://lore.kernel.org/all/06eebdc46cfb21eb437755a2a5a56d55c41400f5.1659077534.git.sander@svanheule.net/
Best,
Sander
> +{
> + /* -1 is a legal arg here. */
> + if (n != -1)
> + cpumask_check(n);
> + return find_next_bit(cpumask_bits(srcp), nr_cpumask_bits, n + 1);
> +}
>
> /**
> * cpumask_next_zero - get the next unset cpu in a cpumask
> @@ -258,8 +272,25 @@ static inline unsigned int cpumask_next_zero(int n, const
> struct cpumask *srcp)
> return find_next_zero_bit(cpumask_bits(srcp), nr_cpumask_bits, n+1);
> }
>
> -unsigned int __pure cpumask_next_and(int n, const struct cpumask *, const
> struct cpumask *);
> -unsigned int __pure cpumask_any_but(const struct cpumask *mask, unsigned int
> cpu);
> +/**
> + * cpumask_next_and - get the next cpu in *src1p & *src2p
> + * @n: the cpu prior to the place to search (ie. return will be > @n)
> + * @src1p: the first cpumask pointer
> + * @src2p: the second cpumask pointer
> + *
> + * Returns >= nr_cpu_ids if no further cpus set in both.
> + */
> +static inline
> +unsigned int cpumask_next_and(int n, const struct cpumask *src1p,
> + const struct cpumask *src2p)
> +{
> + /* -1 is a legal arg here. */
> + if (n != -1)
> + cpumask_check(n);
> + return find_next_and_bit(cpumask_bits(src1p), cpumask_bits(src2p),
> + nr_cpumask_bits, n + 1);
> +}
> +
> unsigned int cpumask_local_spread(unsigned int i, int node);
> unsigned int cpumask_any_and_distribute(const struct cpumask *src1p,
> const struct cpumask *src2p);
> @@ -324,6 +355,26 @@ unsigned int cpumask_next_wrap(int n, const struct
> cpumask *mask, int start, boo
> for ((cpu) = -1; \
> (cpu) = cpumask_next_and((cpu), (mask1), (mask2)), \
> (cpu) < nr_cpu_ids;)
> +
> +/**
> + * cpumask_any_but - return a "random" in a cpumask, but not this one.
> + * @mask: the cpumask to search
> + * @cpu: the cpu to ignore.
> + *
> + * Often used to find any cpu but smp_processor_id() in a mask.
> + * Returns >= nr_cpu_ids if no cpus set.
> + */
> +static inline
> +unsigned int cpumask_any_but(const struct cpumask *mask, unsigned int cpu)
> +{
> + unsigned int i;
> +
> + cpumask_check(cpu);
> + for_each_cpu(i, mask)
> + if (i != cpu)
> + break;
> + return i;
> +}
> #endif /* SMP */
>
> #define CPU_BITS_NONE \
> diff --git a/lib/cpumask.c b/lib/cpumask.c
> index da68f6bbde44..cb7262ff8633 100644
> --- a/lib/cpumask.c
> +++ b/lib/cpumask.c
> @@ -7,61 +7,6 @@
> #include <linux/memblock.h>
> #include <linux/numa.h>
>
> -/**
> - * cpumask_next - get the next cpu in a cpumask
> - * @n: the cpu prior to the place to search (ie. return will be > @n)
> - * @srcp: the cpumask pointer
> - *
> - * Returns >= nr_cpu_ids if no further cpus set.
> - */
> -unsigned int cpumask_next(int n, const struct cpumask *srcp)
> -{
> - /* -1 is a legal arg here. */
> - if (n != -1)
> - cpumask_check(n);
> - return find_next_bit(cpumask_bits(srcp), nr_cpumask_bits, n + 1);
> -}
> -EXPORT_SYMBOL(cpumask_next);
> -
> -/**
> - * cpumask_next_and - get the next cpu in *src1p & *src2p
> - * @n: the cpu prior to the place to search (ie. return will be > @n)
> - * @src1p: the first cpumask pointer
> - * @src2p: the second cpumask pointer
> - *
> - * Returns >= nr_cpu_ids if no further cpus set in both.
> - */
> -unsigned int cpumask_next_and(int n, const struct cpumask *src1p,
> - const struct cpumask *src2p)
> -{
> - /* -1 is a legal arg here. */
> - if (n != -1)
> - cpumask_check(n);
> - return find_next_and_bit(cpumask_bits(src1p), cpumask_bits(src2p),
> - nr_cpumask_bits, n + 1);
> -}
> -EXPORT_SYMBOL(cpumask_next_and);
> -
> -/**
> - * cpumask_any_but - return a "random" in a cpumask, but not this one.
> - * @mask: the cpumask to search
> - * @cpu: the cpu to ignore.
> - *
> - * Often used to find any cpu but smp_processor_id() in a mask.
> - * Returns >= nr_cpu_ids if no cpus set.
> - */
> -unsigned int cpumask_any_but(const struct cpumask *mask, unsigned int cpu)
> -{
> - unsigned int i;
> -
> - cpumask_check(cpu);
> - for_each_cpu(i, mask)
> - if (i != cpu)
> - break;
> - return i;
> -}
> -EXPORT_SYMBOL(cpumask_any_but);
> -
> /**
> * cpumask_next_wrap - helper to implement for_each_cpu_wrap
> * @n: the cpu prior to the place to search
On Sun, Jul 31, 2022 at 11:42:52AM +0200, Sander Vanheule wrote:
> Hi Yury,
>
> On Wed, 2022-07-06 at 10:42 -0700, Yury Norov wrote:
> > To avoid circular dependencies, cpumask keeps simple (almost) one-line
> > wrappers around find_bit() in a c-file.
> >
> > Commit 47d8c15615c0a2 ("include: move find.h from asm_generic to linux")
> > moved find.h header out of asm_generic include path, and it helped to fix
> > many circular dependencies, including some in cpumask.h.
> >
> > This patch moves those one-liners to header files.
> >
> > Signed-off-by: Yury Norov <[email protected]>
> > ---
> > ?include/linux/cpumask.h | 57 ++++++++++++++++++++++++++++++++++++++---
> > ?lib/cpumask.c?????????? | 55 ---------------------------------------
> > ?2 files changed, 54 insertions(+), 58 deletions(-)
> >
> > diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
> > index 760022bcb925..ea3de2c2c180 100644
> > --- a/include/linux/cpumask.h
> > +++ b/include/linux/cpumask.h
> > @@ -241,7 +241,21 @@ static inline unsigned int cpumask_last(const struct
> > cpumask *srcp)
> > ????????return find_last_bit(cpumask_bits(srcp), nr_cpumask_bits);
> > ?}
> > ?
> > -unsigned int __pure cpumask_next(int n, const struct cpumask *srcp);
> > +/**
> > + * cpumask_next - get the next cpu in a cpumask
> > + * @n: the cpu prior to the place to search (ie. return will be > @n)
> > + * @srcp: the cpumask pointer
> > + *
> > + * Returns >= nr_cpu_ids if no further cpus set.
> > + */
> > +static inline
> > +unsigned int cpumask_next(int n, const struct cpumask *srcp)
>
> This also drops the __pure speficier for these functions. Since I have a patch
> that does the opposite for cpumask_next_wrap() [1], I was wondering what your
> reasoning behind this is.
>
> Since a cpumask like cpu_online_mask may change between subsequent calls, I'm
> considering to drop my patch adding __pure, and to follow the changes you've
> made here.
>
> [1]
> https://lore.kernel.org/all/06eebdc46cfb21eb437755a2a5a56d55c41400f5.1659077534.git.sander@svanheule.net/
__pure is a promise to the compiler that the function will not modify
system state (i.e. will not write into the memory). Now that the
cpumask_next etc. became static inline, there's no reason for the hint
because the compiler inlines the code, and there's no a real function.
Maybe then it's worth to propagate the __pure to find_bit() helpers...
Would be great to get comments form compiler people. Rasmus?
Thanks,
Yury
On Wed, Jul 06, 2022 at 10:42:51AM -0700, Yury Norov wrote:
> From: Ingo Molnar <[email protected]>
>
> This is a much smaller header.
>
> Signed-off-by: Ingo Molnar <[email protected]>
> Signed-off-by: Yury Norov <[email protected]>
> ---
> include/linux/gfp.h | 345 +------------------------------------
> include/linux/gfp_types.h | 348 ++++++++++++++++++++++++++++++++++++++
> 2 files changed, 350 insertions(+), 343 deletions(-)
You move a lot of kernel-doc. Where do you change the rst files?
On Thu, Sep 01, 2022 at 09:43:13PM +0100, Matthew Wilcox wrote:
> On Wed, Jul 06, 2022 at 10:42:51AM -0700, Yury Norov wrote:
> > From: Ingo Molnar <[email protected]>
> >
> > This is a much smaller header.
> >
> > Signed-off-by: Ingo Molnar <[email protected]>
> > Signed-off-by: Yury Norov <[email protected]>
> > ---
> > include/linux/gfp.h | 345 +------------------------------------
> > include/linux/gfp_types.h | 348 ++++++++++++++++++++++++++++++++++++++
> > 2 files changed, 350 insertions(+), 343 deletions(-)
>
> You move a lot of kernel-doc. Where do you change the rst files?
Ingo - nowhere. So I did it in the next patch:
7343f2b0db4961d ("headers/deps: mm: align MANITAINERS and Docs with new
gfp.h structure")
On Thu, Sep 01, 2022 at 07:10:09PM -0700, Yury Norov wrote:
> On Thu, Sep 01, 2022 at 09:43:13PM +0100, Matthew Wilcox wrote:
> > On Wed, Jul 06, 2022 at 10:42:51AM -0700, Yury Norov wrote:
> > > From: Ingo Molnar <[email protected]>
> > >
> > > This is a much smaller header.
> > >
> > > Signed-off-by: Ingo Molnar <[email protected]>
> > > Signed-off-by: Yury Norov <[email protected]>
> > > ---
> > > include/linux/gfp.h | 345 +------------------------------------
> > > include/linux/gfp_types.h | 348 ++++++++++++++++++++++++++++++++++++++
> > > 2 files changed, 350 insertions(+), 343 deletions(-)
> >
> > You move a lot of kernel-doc. Where do you change the rst files?
>
> Ingo - nowhere. So I did it in the next patch:
>
> 7343f2b0db4961d ("headers/deps: mm: align MANITAINERS and Docs with new
> gfp.h structure")
That's not the right way to do it. Don't merge a patch with bugs and
then fix it up in the next patch. Just fix the patch. This is covered
in Documentation/process/.