From 41df0d61c266998b8049df7fec119cd518a43aa1 Mon Sep 17 00:00:00 2001 From: Mike Travis Date: Mon, 12 May 2008 21:21:13 +0200 Subject: x86: Add performance variants of cpumask operators * Increase performance for systems with large count NR_CPUS by limiting the range of the cpumask operators that loop over the bits in a cpumask_t variable. This removes a large amount of wasted cpu cycles. * Add performance variants of the cpumask operators: int cpus_weight_nr(mask) Same using nr_cpu_ids instead of NR_CPUS int first_cpu_nr(mask) Number lowest set bit, or nr_cpu_ids int next_cpu_nr(cpu, mask) Next cpu past 'cpu', or nr_cpu_ids for_each_cpu_mask_nr(cpu, mask) for-loop cpu over mask using nr_cpu_ids * Modify following to use performance variants: #define num_online_cpus() cpus_weight_nr(cpu_online_map) #define num_possible_cpus() cpus_weight_nr(cpu_possible_map) #define num_present_cpus() cpus_weight_nr(cpu_present_map) #define for_each_possible_cpu(cpu) for_each_cpu_mask_nr((cpu), ...) #define for_each_online_cpu(cpu) for_each_cpu_mask_nr((cpu), ...) #define for_each_present_cpu(cpu) for_each_cpu_mask_nr((cpu), ...) * Comment added to include/linux/cpumask.h: Note: The alternate operations with the suffix "_nr" are used to limit the range of the loop to nr_cpu_ids instead of NR_CPUS when NR_CPUS > 64 for performance reasons. If NR_CPUS is <= 64 then most assembler bitmask operators execute faster with a constant range, so the operator will continue to use NR_CPUS. Another consideration is that nr_cpu_ids is initialized to NR_CPUS and isn't lowered until the possible cpus are discovered (including any disabled cpus). So early uses will span the entire range of NR_CPUS. (The net effect is that for systems with 64 or less CPU's there are no functional changes.) For inclusion into sched-devel/latest tree. Based on: git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6.git + sched-devel/latest .../mingo/linux-2.6-sched-devel.git Cc: Paul Jackson Cc: Christoph Lameter Reviewed-by: Paul Jackson Reviewed-by: Christoph Lameter Signed-off-by: Mike Travis Signed-off-by: Ingo Molnar --- include/linux/cpumask.h | 92 +++++++++++++++++++++++++++++++++---------------- 1 file changed, 62 insertions(+), 30 deletions(-) (limited to 'include') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 5df3db58fcc6..b49472d1af84 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -17,6 +17,20 @@ * For details of cpus_onto(), see bitmap_onto in lib/bitmap.c. * For details of cpus_fold(), see bitmap_fold in lib/bitmap.c. * + * . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . + * Note: The alternate operations with the suffix "_nr" are used + * to limit the range of the loop to nr_cpu_ids instead of + * NR_CPUS when NR_CPUS > 64 for performance reasons. + * If NR_CPUS is <= 64 then most assembler bitmask + * operators execute faster with a constant range, so + * the operator will continue to use NR_CPUS. + * + * Another consideration is that nr_cpu_ids is initialized + * to NR_CPUS and isn't lowered until the possible cpus are + * discovered (including any disabled cpus). So early uses + * will span the entire range of NR_CPUS. + * . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . + * * The available cpumask operations are: * * void cpu_set(cpu, mask) turn on bit 'cpu' in mask @@ -38,12 +52,14 @@ * int cpus_empty(mask) Is mask empty (no bits sets)? * int cpus_full(mask) Is mask full (all bits sets)? * int cpus_weight(mask) Hamming weigh - number of set bits + * int cpus_weight_nr(mask) Same using nr_cpu_ids instead of NR_CPUS * * void cpus_shift_right(dst, src, n) Shift right * void cpus_shift_left(dst, src, n) Shift left * * int first_cpu(mask) Number lowest set bit, or NR_CPUS * int next_cpu(cpu, mask) Next cpu past 'cpu', or NR_CPUS + * int next_cpu_nr(cpu, mask) Next cpu past 'cpu', or nr_cpu_ids * * cpumask_t cpumask_of_cpu(cpu) Return cpumask with bit 'cpu' set * CPU_MASK_ALL Initializer - all bits set @@ -59,7 +75,8 @@ * void cpus_onto(dst, orig, relmap) *dst = orig relative to relmap * void cpus_fold(dst, orig, sz) dst bits = orig bits mod sz * - * for_each_cpu_mask(cpu, mask) for-loop cpu over mask + * for_each_cpu_mask(cpu, mask) for-loop cpu over mask using NR_CPUS + * for_each_cpu_mask_nr(cpu, mask) for-loop cpu over mask using nr_cpu_ids * * int num_online_cpus() Number of online CPUs * int num_possible_cpus() Number of all possible CPUs @@ -216,15 +233,6 @@ static inline void __cpus_shift_left(cpumask_t *dstp, bitmap_shift_left(dstp->bits, srcp->bits, n, nbits); } -#ifdef CONFIG_SMP -int __first_cpu(const cpumask_t *srcp); -#define first_cpu(src) __first_cpu(&(src)) -int __next_cpu(int n, const cpumask_t *srcp); -#define next_cpu(n, src) __next_cpu((n), &(src)) -#else -#define first_cpu(src) ({ (void)(src); 0; }) -#define next_cpu(n, src) ({ (void)(src); 1; }) -#endif #ifdef CONFIG_HAVE_CPUMASK_OF_CPU_MAP extern cpumask_t *cpumask_of_cpu_map; @@ -343,15 +351,48 @@ static inline void __cpus_fold(cpumask_t *dstp, const cpumask_t *origp, bitmap_fold(dstp->bits, origp->bits, sz, nbits); } -#if NR_CPUS > 1 +#if NR_CPUS == 1 + +#define nr_cpu_ids 1 +#define first_cpu(src) ({ (void)(src); 0; }) +#define next_cpu(n, src) ({ (void)(src); 1; }) +#define any_online_cpu(mask) 0 +#define for_each_cpu_mask(cpu, mask) \ + for ((cpu) = 0; (cpu) < 1; (cpu)++, (void)mask) + +#else /* NR_CPUS > 1 */ + +extern int nr_cpu_ids; +int __first_cpu(const cpumask_t *srcp); +int __next_cpu(int n, const cpumask_t *srcp); +int __any_online_cpu(const cpumask_t *mask); + +#define first_cpu(src) __first_cpu(&(src)) +#define next_cpu(n, src) __next_cpu((n), &(src)) +#define any_online_cpu(mask) __any_online_cpu(&(mask)) #define for_each_cpu_mask(cpu, mask) \ for ((cpu) = first_cpu(mask); \ (cpu) < NR_CPUS; \ (cpu) = next_cpu((cpu), (mask))) -#else /* NR_CPUS == 1 */ -#define for_each_cpu_mask(cpu, mask) \ - for ((cpu) = 0; (cpu) < 1; (cpu)++, (void)mask) -#endif /* NR_CPUS */ +#endif + +#if NR_CPUS <= 64 + +#define next_cpu_nr(n, src) next_cpu(n, src) +#define cpus_weight_nr(cpumask) cpus_weight(cpumask) +#define for_each_cpu_mask_nr(cpu, mask) for_each_cpu_mask(cpu, mask) + +#else /* NR_CPUS > 64 */ + +int __next_cpu_nr(int n, const cpumask_t *srcp); +#define next_cpu_nr(n, src) __next_cpu_nr((n), &(src)) +#define cpus_weight_nr(cpumask) __cpus_weight(&(cpumask), nr_cpu_ids) +#define for_each_cpu_mask_nr(cpu, mask) \ + for ((cpu) = first_cpu(mask); \ + (cpu) < nr_cpu_ids; \ + (cpu) = next_cpu_nr((cpu), (mask))) + +#endif /* NR_CPUS > 64 */ /* * The following particular system cpumasks and operations manage @@ -414,9 +455,9 @@ extern cpumask_t cpu_online_map; extern cpumask_t cpu_present_map; #if NR_CPUS > 1 -#define num_online_cpus() cpus_weight(cpu_online_map) -#define num_possible_cpus() cpus_weight(cpu_possible_map) -#define num_present_cpus() cpus_weight(cpu_present_map) +#define num_online_cpus() cpus_weight_nr(cpu_online_map) +#define num_possible_cpus() cpus_weight_nr(cpu_possible_map) +#define num_present_cpus() cpus_weight_nr(cpu_present_map) #define cpu_online(cpu) cpu_isset((cpu), cpu_online_map) #define cpu_possible(cpu) cpu_isset((cpu), cpu_possible_map) #define cpu_present(cpu) cpu_isset((cpu), cpu_present_map) @@ -431,17 +472,8 @@ extern cpumask_t cpu_present_map; #define cpu_is_offline(cpu) unlikely(!cpu_online(cpu)) -#ifdef CONFIG_SMP -extern int nr_cpu_ids; -#define any_online_cpu(mask) __any_online_cpu(&(mask)) -int __any_online_cpu(const cpumask_t *mask); -#else -#define nr_cpu_ids 1 -#define any_online_cpu(mask) 0 -#endif - -#define for_each_possible_cpu(cpu) for_each_cpu_mask((cpu), cpu_possible_map) -#define for_each_online_cpu(cpu) for_each_cpu_mask((cpu), cpu_online_map) -#define for_each_present_cpu(cpu) for_each_cpu_mask((cpu), cpu_present_map) +#define for_each_possible_cpu(cpu) for_each_cpu_mask_nr((cpu), cpu_possible_map) +#define for_each_online_cpu(cpu) for_each_cpu_mask_nr((cpu), cpu_online_map) +#define for_each_present_cpu(cpu) for_each_cpu_mask_nr((cpu), cpu_present_map) #endif /* __LINUX_CPUMASK_H */ -- cgit v1.2.3 From 334ef7a7ab8f80b689a2be95d5e62d2167900865 Mon Sep 17 00:00:00 2001 From: Mike Travis Date: Mon, 12 May 2008 21:21:13 +0200 Subject: x86: use performance variant for_each_cpu_mask_nr Change references from for_each_cpu_mask to for_each_cpu_mask_nr where appropriate Reviewed-by: Paul Jackson Reviewed-by: Christoph Lameter Signed-off-by: Mike Travis Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner commit 2d474871e2fb092eb46a0930aba5442e10eb96cc Author: Mike Travis Date: Mon May 12 21:21:13 2008 +0200 --- include/asm-x86/ipi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/asm-x86/ipi.h b/include/asm-x86/ipi.h index ecc80f341f37..5f7310aa3efd 100644 --- a/include/asm-x86/ipi.h +++ b/include/asm-x86/ipi.h @@ -121,7 +121,7 @@ static inline void send_IPI_mask_sequence(cpumask_t mask, int vector) * - mbligh */ local_irq_save(flags); - for_each_cpu_mask(query_cpu, mask) { + for_each_cpu_mask_nr(query_cpu, mask) { __send_IPI_dest_field(per_cpu(x86_cpu_to_apicid, query_cpu), vector, APIC_DEST_PHYSICAL); } -- cgit v1.2.3 From 7baac8b91f9871ba8cb09af84de4ae1d86d07812 Mon Sep 17 00:00:00 2001 From: Alexander van Heukelum Date: Tue, 13 May 2008 11:28:21 +0200 Subject: cpumask: make for_each_cpu_mask a bit smaller The for_each_cpu_mask loop is used quite often in the kernel. It makes use of two functions: first_cpu and next_cpu. This patch changes for_each_cpu_mask to use only the latter. Because next_cpu finds the next eligible cpu _after_ the given one, the iteration variable has to be initialized to -1 and next_cpu has to be called with this value before the first iteration. An x86_64 defconfig kernel (from sched/latest) is about 2500 bytes smaller with this patch applied: text data bss dec hex filename 6222517 917952 749932 7890401 7865e1 vmlinux.orig 6219922 917952 749932 7887806 785bbe vmlinux The same size reduction is seen for defconfig+MAXSMP text data bss dec hex filename 6241772 2563968 1492716 10298456 9d2458 vmlinux.orig 6239211 2563968 1492716 10295895 9d1a57 vmlinux Signed-off-by: Alexander van Heukelum Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/linux/cpumask.h | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index b49472d1af84..80226e776143 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -370,10 +370,10 @@ int __any_online_cpu(const cpumask_t *mask); #define first_cpu(src) __first_cpu(&(src)) #define next_cpu(n, src) __next_cpu((n), &(src)) #define any_online_cpu(mask) __any_online_cpu(&(mask)) -#define for_each_cpu_mask(cpu, mask) \ - for ((cpu) = first_cpu(mask); \ - (cpu) < NR_CPUS; \ - (cpu) = next_cpu((cpu), (mask))) +#define for_each_cpu_mask(cpu, mask) \ + for ((cpu) = -1; \ + (cpu) = next_cpu((cpu), (mask)), \ + (cpu) < NR_CPUS; ) #endif #if NR_CPUS <= 64 @@ -387,10 +387,10 @@ int __any_online_cpu(const cpumask_t *mask); int __next_cpu_nr(int n, const cpumask_t *srcp); #define next_cpu_nr(n, src) __next_cpu_nr((n), &(src)) #define cpus_weight_nr(cpumask) __cpus_weight(&(cpumask), nr_cpu_ids) -#define for_each_cpu_mask_nr(cpu, mask) \ - for ((cpu) = first_cpu(mask); \ - (cpu) < nr_cpu_ids; \ - (cpu) = next_cpu_nr((cpu), (mask))) +#define for_each_cpu_mask_nr(cpu, mask) \ + for ((cpu) = -1; \ + (cpu) = next_cpu_nr((cpu), (mask)), \ + (cpu) < nr_cpu_ids; ) #endif /* NR_CPUS > 64 */ -- cgit v1.2.3 From 9982fbface82893e77d211fbabfbd229da6bdde6 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Sun, 6 Jul 2008 14:24:08 +0200 Subject: Revert "cpumask: introduce new APIs" This reverts commit acb7669c125676e63cf96582455509216c39745e. the wrappers are not needed anymore. Signed-off-by: Ingo Molnar --- include/linux/cpumask.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 47418b1b4103..80226e776143 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -394,10 +394,6 @@ int __next_cpu_nr(int n, const cpumask_t *srcp); #endif /* NR_CPUS > 64 */ -#define next_cpu_nr(n, src) next_cpu(n, src) -#define cpus_weight_nr(cpumask) cpus_weight(cpumask) -#define for_each_cpu_mask_nr(cpu, mask) for_each_cpu_mask(cpu, mask) - /* * The following particular system cpumasks and operations manage * possible, present and online cpus. Each of them is a fixed size -- cgit v1.2.3 From 65c011845316d3c1381f478ca0d8265c43b3b039 Mon Sep 17 00:00:00 2001 From: Mike Travis Date: Tue, 15 Jul 2008 14:14:30 -0700 Subject: cpumask: Replace cpumask_of_cpu with cpumask_of_cpu_ptr * This patch replaces the dangerous lvalue version of cpumask_of_cpu with new cpumask_of_cpu_ptr macros. These are patterned after the node_to_cpumask_ptr macros. In general terms, if there is a cpumask_of_cpu_map[] then a pointer to the cpumask_of_cpu_map[cpu] entry is used. The cpumask_of_cpu_map is provided when there is a large NR_CPUS count, reducing greatly the amount of code generated and stack space used for cpumask_of_cpu(). The pointer to the cpumask_t value is needed for calling set_cpus_allowed_ptr() to reduce the amount of stack space needed to pass the cpumask_t value. If there isn't a cpumask_of_cpu_map[], then a temporary variable is declared and filled in with value from cpumask_of_cpu(cpu) as well as a pointer variable pointing to this temporary variable. Afterwards, the pointer is used to reference the cpumask value. The compiler will optimize out the extra dereference through the pointer as well as the stack space used for the pointer, resulting in identical code. A good example of the orthogonal usages is in net/sunrpc/svc.c: case SVC_POOL_PERCPU: { unsigned int cpu = m->pool_to[pidx]; cpumask_of_cpu_ptr(cpumask, cpu); *oldmask = current->cpus_allowed; set_cpus_allowed_ptr(current, cpumask); return 1; } case SVC_POOL_PERNODE: { unsigned int node = m->pool_to[pidx]; node_to_cpumask_ptr(nodecpumask, node); *oldmask = current->cpus_allowed; set_cpus_allowed_ptr(current, nodecpumask); return 1; } Signed-off-by: Mike Travis Signed-off-by: Ingo Molnar --- include/linux/cpumask.h | 32 +++++++++++++++++++++++++++----- 1 file changed, 27 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 80226e776143..2dbd9a287e77 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -62,6 +62,15 @@ * int next_cpu_nr(cpu, mask) Next cpu past 'cpu', or nr_cpu_ids * * cpumask_t cpumask_of_cpu(cpu) Return cpumask with bit 'cpu' set + *ifdef CONFIG_HAS_CPUMASK_OF_CPU + * cpumask_of_cpu_ptr_declare(v) Declares cpumask_t *v + * cpumask_of_cpu_ptr_next(v, cpu) Sets v = &cpumask_of_cpu_map[cpu] + * cpumask_of_cpu_ptr(v, cpu) Combines above two operations + *else + * cpumask_of_cpu_ptr_declare(v) Declares cpumask_t _v and *v = &_v + * cpumask_of_cpu_ptr_next(v, cpu) Sets _v = cpumask_of_cpu(cpu) + * cpumask_of_cpu_ptr(v, cpu) Combines above two operations + *endif * CPU_MASK_ALL Initializer - all bits set * CPU_MASK_NONE Initializer - no bits set * unsigned long *cpus_addr(mask) Array of unsigned long's in mask @@ -236,11 +245,16 @@ static inline void __cpus_shift_left(cpumask_t *dstp, #ifdef CONFIG_HAVE_CPUMASK_OF_CPU_MAP extern cpumask_t *cpumask_of_cpu_map; -#define cpumask_of_cpu(cpu) (cpumask_of_cpu_map[cpu]) - +#define cpumask_of_cpu(cpu) (cpumask_of_cpu_map[cpu]) +#define cpumask_of_cpu_ptr(v, cpu) \ + const cpumask_t *v = &cpumask_of_cpu(cpu) +#define cpumask_of_cpu_ptr_declare(v) \ + const cpumask_t *v +#define cpumask_of_cpu_ptr_next(v, cpu) \ + v = &cpumask_of_cpu(cpu) #else #define cpumask_of_cpu(cpu) \ -(*({ \ +({ \ typeof(_unused_cpumask_arg_) m; \ if (sizeof(m) == sizeof(unsigned long)) { \ m.bits[0] = 1UL<<(cpu); \ @@ -248,8 +262,16 @@ extern cpumask_t *cpumask_of_cpu_map; cpus_clear(m); \ cpu_set((cpu), m); \ } \ - &m; \ -})) + m; \ +}) +#define cpumask_of_cpu_ptr(v, cpu) \ + cpumask_t _##v = cpumask_of_cpu(cpu); \ + const cpumask_t *v = &_##v +#define cpumask_of_cpu_ptr_declare(v) \ + cpumask_t _##v; \ + const cpumask_t *v = &_##v +#define cpumask_of_cpu_ptr_next(v, cpu) \ + _##v = cpumask_of_cpu(cpu) #endif #define CPU_MASK_LAST_WORD BITMAP_LAST_WORD_MASK(NR_CPUS) -- cgit v1.2.3 From 77586c2bdad0798cb24e35de5a878e7c6b200574 Mon Sep 17 00:00:00 2001 From: Mike Travis Date: Tue, 15 Jul 2008 14:14:36 -0700 Subject: cpumask: Provide a generic set of CPUMASK_ALLOC macros * Provide a generic set of CPUMASK_ALLOC macros patterned after the SCHED_CPUMASK_ALLOC macros. This is used where multiple cpumask_t variables are declared on the stack to reduce the amount of stack space required. Signed-off-by: Mike Travis Signed-off-by: Ingo Molnar --- include/linux/cpumask.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'include') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 2dbd9a287e77..72f9c32c12b0 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -75,6 +75,17 @@ * CPU_MASK_NONE Initializer - no bits set * unsigned long *cpus_addr(mask) Array of unsigned long's in mask * + *if NR_CPUS > BITS_PER_LONG + * CPUMASK_ALLOC(m) Declares and allocates struct m *m = + * (struct m *)kmalloc(sizeof(*m), ...) + * CPUMASK_FREE(m) Macro for kfree(v) + *else + * CPUMASK_ALLOC(m) Declares struct m _m, *m = &_m + * CPUMASK_FREE(m) Nop + *endif + * CPUMASK_VAR(v, m) Declares cpumask_t *v = + * m + offset(struct m, v) + * * int cpumask_scnprintf(buf, len, mask) Format cpumask for printing * int cpumask_parse_user(ubuf, ulen, mask) Parse ascii string as cpumask * int cpulist_scnprintf(buf, len, mask) Format cpumask as list for printing @@ -311,6 +322,16 @@ extern cpumask_t cpu_mask_all; #define cpus_addr(src) ((src).bits) +#if NR_CPUS > BITS_PER_LONG +#define CPUMASK_ALLOC(m) struct m *m = kmalloc(sizeof(*m), GFP_KERNEL) +#define CPUMASK_FREE(m) kfree(m) +#else +#define CPUMASK_ALLOC(m) struct allmasks _m, *m = &_m +#define CPUMASK_FREE(m) +#endif +#define CPUMASK_VAR(v, m) cpumask_t *v = (cpumask_t *) \ + ((unsigned long)(m) + offsetof(struct m, v)) + #define cpumask_scnprintf(buf, len, src) \ __cpumask_scnprintf((buf), (len), &(src), NR_CPUS) static inline int __cpumask_scnprintf(char *buf, int len, -- cgit v1.2.3 From 94a1e869c7b96a9d30e260084866383a145fd8ae Mon Sep 17 00:00:00 2001 From: Mike Travis Date: Fri, 18 Jul 2008 18:11:31 -0700 Subject: NR_CPUS: Replace per_cpu(..., smp_processor_id()) with __get_cpu_var * Slight optimization when getting one's own cpu_info percpu data. Signed-off-by: Mike Travis Signed-off-by: Ingo Molnar --- include/asm-x86/processor.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/asm-x86/processor.h b/include/asm-x86/processor.h index 55402d2ab938..f92315ed68e1 100644 --- a/include/asm-x86/processor.h +++ b/include/asm-x86/processor.h @@ -134,7 +134,7 @@ extern __u32 cleared_cpu_caps[NCAPINTS]; #ifdef CONFIG_SMP DECLARE_PER_CPU(struct cpuinfo_x86, cpu_info); #define cpu_data(cpu) per_cpu(cpu_info, cpu) -#define current_cpu_data cpu_data(smp_processor_id()) +#define current_cpu_data __get_cpu_var(cpu_info) #else #define cpu_data(cpu) boot_cpu_data #define current_cpu_data boot_cpu_data -- cgit v1.2.3 From 80422d3431cc990b967da129f9eb8e3e9989f841 Mon Sep 17 00:00:00 2001 From: Mike Travis Date: Fri, 18 Jul 2008 18:11:33 -0700 Subject: cpumask: Provide a generic set of CPUMASK_ALLOC macros, FIXUP * Rename CPUMASK_VAR --> CPUMASK_PTR (and simplify) * Fix a semantic error in CPUMASK_ALLOC * Add a bit of commentry to cpumask.h Signed-off-by: Mike Travis Signed-off-by: Ingo Molnar --- include/linux/cpumask.h | 33 ++++++++++++++++++++++++++------- 1 file changed, 26 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 72f9c32c12b0..30d59d1d0626 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -75,16 +75,36 @@ * CPU_MASK_NONE Initializer - no bits set * unsigned long *cpus_addr(mask) Array of unsigned long's in mask * + * CPUMASK_ALLOC kmalloc's a structure that is a composite of many cpumask_t + * variables, and CPUMASK_PTR provides pointers to each field. + * + * The structure should be defined something like this: + * struct my_cpumasks { + * cpumask_t mask1; + * cpumask_t mask2; + * }; + * + * Usage is then: + * CPUMASK_ALLOC(my_cpumasks); + * CPUMASK_PTR(mask1, my_cpumasks); + * CPUMASK_PTR(mask2, my_cpumasks); + * + * --- DO NOT reference cpumask_t pointers until this check --- + * if (my_cpumasks == NULL) + * "kmalloc failed"... + * + * References are now pointers to the cpumask_t variables (*mask1, ...) + * *if NR_CPUS > BITS_PER_LONG * CPUMASK_ALLOC(m) Declares and allocates struct m *m = - * (struct m *)kmalloc(sizeof(*m), ...) - * CPUMASK_FREE(m) Macro for kfree(v) + * kmalloc(sizeof(*m), GFP_KERNEL) + * CPUMASK_FREE(m) Macro for kfree(m) *else * CPUMASK_ALLOC(m) Declares struct m _m, *m = &_m * CPUMASK_FREE(m) Nop *endif - * CPUMASK_VAR(v, m) Declares cpumask_t *v = - * m + offset(struct m, v) + * CPUMASK_PTR(v, m) Declares cpumask_t *v = &(m->v) + * ------------------------------------------------------------------------ * * int cpumask_scnprintf(buf, len, mask) Format cpumask for printing * int cpumask_parse_user(ubuf, ulen, mask) Parse ascii string as cpumask @@ -326,11 +346,10 @@ extern cpumask_t cpu_mask_all; #define CPUMASK_ALLOC(m) struct m *m = kmalloc(sizeof(*m), GFP_KERNEL) #define CPUMASK_FREE(m) kfree(m) #else -#define CPUMASK_ALLOC(m) struct allmasks _m, *m = &_m +#define CPUMASK_ALLOC(m) struct m _m, *m = &_m #define CPUMASK_FREE(m) #endif -#define CPUMASK_VAR(v, m) cpumask_t *v = (cpumask_t *) \ - ((unsigned long)(m) + offsetof(struct m, v)) +#define CPUMASK_PTR(v, m) cpumask_t *v = &(m->v) #define cpumask_scnprintf(buf, len, src) \ __cpumask_scnprintf((buf), (len), &(src), NR_CPUS) -- cgit v1.2.3