From a7b930cdf8ec790c85f81416c87f7c066679d373 Mon Sep 17 00:00:00 2001 From: Harvey Harrison Date: Sun, 2 Nov 2008 13:32:43 -0800 Subject: PCI: annotate return value of pci_ioremap_bar with __iomem Was missing from the initial patch. Acked-by: Arjan van de Ven Signed-off-by: Harvey Harrison Signed-off-by: Jesse Barnes --- include/linux/pci.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index c75b82bda32..feb4657bb04 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1136,7 +1136,7 @@ static inline void pci_mmcfg_late_init(void) { } #endif #ifdef CONFIG_HAS_IOMEM -static inline void * pci_ioremap_bar(struct pci_dev *pdev, int bar) +static inline void __iomem *pci_ioremap_bar(struct pci_dev *pdev, int bar) { /* * Make sure the BAR is actually a memory resource, not an IO resource -- cgit v1.2.3 From 2d3854a37e8b767a51aba38ed6d22817b0631e33 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Wed, 5 Nov 2008 13:39:10 +1100 Subject: cpumask: introduce new API, without changing anything Impact: introduce new APIs We want to deprecate cpumasks on the stack, as we are headed for gynormous numbers of CPUs. Eventually, we want to head towards an undefined 'struct cpumask' so they can never be declared on stack. 1) New cpumask functions which take pointers instead of copies. (cpus_* -> cpumask_*) 2) Several new helpers to reduce requirements for temporary cpumasks (cpumask_first_and, cpumask_next_and, cpumask_any_and) 3) Helpers for declaring cpumasks on or offstack for large NR_CPUS (cpumask_var_t, alloc_cpumask_var and free_cpumask_var) 4) 'struct cpumask' for explicitness and to mark new-style code. 5) Make iterator functions stop at nr_cpu_ids (a runtime constant), not NR_CPUS for time efficiency and for smaller dynamic allocations in future. 6) cpumask_copy() so we can allocate less than a full cpumask eventually (for alloc_cpumask_var), and so we can eliminate the 'struct cpumask' definition eventually. 7) work_on_cpu() helper for doing task on a CPU, rather than saving old cpumask for current thread and manipulating it. 8) smp_call_function_many() which is smp_call_function_mask() except taking a cpumask pointer. Note that this patch simply introduces the new functions and leaves the obsolescent ones in place. This is to simplify the transition patches. Signed-off-by: Rusty Russell Signed-off-by: Ingo Molnar --- include/linux/cpumask.h | 502 +++++++++++++++++++++++++++++++++++++++++++++- include/linux/smp.h | 9 + include/linux/workqueue.h | 8 + 3 files changed, 517 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index d3219d73f8e..c8e66619097 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -5,6 +5,9 @@ * Cpumasks provide a bitmap suitable for representing the * set of CPU's in a system, one bit position per CPU number. * + * The new cpumask_ ops take a "struct cpumask *"; the old ones + * use cpumask_t. + * * See detailed comments in the file linux/bitmap.h describing the * data type on which these cpumasks are based. * @@ -31,7 +34,7 @@ * will span the entire range of NR_CPUS. * . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . * - * The available cpumask operations are: + * The obsolescent cpumask operations are: * * void cpu_set(cpu, mask) turn on bit 'cpu' in mask * void cpu_clear(cpu, mask) turn off bit 'cpu' in mask @@ -138,7 +141,7 @@ #include #include -typedef struct { DECLARE_BITMAP(bits, NR_CPUS); } cpumask_t; +typedef struct cpumask { DECLARE_BITMAP(bits, NR_CPUS); } cpumask_t; extern cpumask_t _unused_cpumask_arg_; #define cpu_set(cpu, dst) __cpu_set((cpu), &(dst)) @@ -527,4 +530,499 @@ extern cpumask_t cpu_active_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) +/* These are the new versions of the cpumask operators: passed by pointer. + * The older versions will be implemented in terms of these, then deleted. */ +#define cpumask_bits(maskp) ((maskp)->bits) + +#if NR_CPUS <= BITS_PER_LONG +#define CPU_BITS_ALL \ +{ \ + [BITS_TO_LONGS(NR_CPUS)-1] = CPU_MASK_LAST_WORD \ +} + +/* This produces more efficient code. */ +#define nr_cpumask_bits NR_CPUS + +#else /* NR_CPUS > BITS_PER_LONG */ + +#define CPU_BITS_ALL \ +{ \ + [0 ... BITS_TO_LONGS(NR_CPUS)-2] = ~0UL, \ + [BITS_TO_LONGS(NR_CPUS)-1] = CPU_MASK_LAST_WORD \ +} + +#define nr_cpumask_bits nr_cpu_ids +#endif /* NR_CPUS > BITS_PER_LONG */ + +/* verify cpu argument to cpumask_* operators */ +static inline unsigned int cpumask_check(unsigned int cpu) +{ +#ifdef CONFIG_DEBUG_PER_CPU_MAPS + WARN_ON_ONCE(cpu >= nr_cpumask_bits); +#endif /* CONFIG_DEBUG_PER_CPU_MAPS */ + return cpu; +} + +#if NR_CPUS == 1 +/* Uniprocesor. */ +#define cpumask_first(src) ({ (void)(src); 0; }) +#define cpumask_next(n, src) ({ (void)(src); 1; }) +#define cpumask_next_zero(n, src) ({ (void)(src); 1; }) +#define cpumask_next_and(n, srcp, andp) ({ (void)(srcp), (void)(andp); 1; }) +#define cpumask_any_but(mask, cpu) ({ (void)(mask); (void)(cpu); 0; }) + +#define for_each_cpu(cpu, mask) \ + for ((cpu) = 0; (cpu) < 1; (cpu)++, (void)mask) +#define for_each_cpu_and(cpu, mask, and) \ + for ((cpu) = 0; (cpu) < 1; (cpu)++, (void)mask, (void)and) +#else +/** + * cpumask_first - get the first cpu in a cpumask + * @srcp: the cpumask pointer + * + * Returns >= nr_cpu_ids if no cpus set. + */ +static inline unsigned int cpumask_first(const struct cpumask *srcp) +{ + return find_first_bit(cpumask_bits(srcp), nr_cpumask_bits); +} + +/** + * 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 + * @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 unset. + */ +static inline unsigned int cpumask_next_zero(int n, const struct cpumask *srcp) +{ + /* -1 is a legal arg here. */ + if (n != -1) + cpumask_check(n); + return find_next_zero_bit(cpumask_bits(srcp), nr_cpumask_bits, n+1); +} + +int cpumask_next_and(int n, const struct cpumask *, const struct cpumask *); +int cpumask_any_but(const struct cpumask *mask, unsigned int cpu); + +#define for_each_cpu(cpu, mask) \ + for ((cpu) = -1; \ + (cpu) = cpumask_next((cpu), (mask)), \ + (cpu) < nr_cpu_ids;) +#define for_each_cpu_and(cpu, mask, and) \ + for ((cpu) = -1; \ + (cpu) = cpumask_next_and((cpu), (mask), (and)), \ + (cpu) < nr_cpu_ids;) +#endif /* SMP */ + +#define CPU_BITS_NONE \ +{ \ + [0 ... BITS_TO_LONGS(NR_CPUS)-1] = 0UL \ +} + +#define CPU_BITS_CPU0 \ +{ \ + [0] = 1UL \ +} + +/** + * cpumask_set_cpu - set a cpu in a cpumask + * @cpu: cpu number (< nr_cpu_ids) + * @dstp: the cpumask pointer + */ +static inline void cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp) +{ + set_bit(cpumask_check(cpu), cpumask_bits(dstp)); +} + +/** + * cpumask_clear_cpu - clear a cpu in a cpumask + * @cpu: cpu number (< nr_cpu_ids) + * @dstp: the cpumask pointer + */ +static inline void cpumask_clear_cpu(int cpu, struct cpumask *dstp) +{ + clear_bit(cpumask_check(cpu), cpumask_bits(dstp)); +} + +/** + * cpumask_test_cpu - test for a cpu in a cpumask + * @cpu: cpu number (< nr_cpu_ids) + * @cpumask: the cpumask pointer + * + * No static inline type checking - see Subtlety (1) above. + */ +#define cpumask_test_cpu(cpu, cpumask) \ + test_bit(cpumask_check(cpu), (cpumask)->bits) + +/** + * cpumask_test_and_set_cpu - atomically test and set a cpu in a cpumask + * @cpu: cpu number (< nr_cpu_ids) + * @cpumask: the cpumask pointer + * + * test_and_set_bit wrapper for cpumasks. + */ +static inline int cpumask_test_and_set_cpu(int cpu, struct cpumask *cpumask) +{ + return test_and_set_bit(cpumask_check(cpu), cpumask_bits(cpumask)); +} + +/** + * cpumask_setall - set all cpus (< nr_cpu_ids) in a cpumask + * @dstp: the cpumask pointer + */ +static inline void cpumask_setall(struct cpumask *dstp) +{ + bitmap_fill(cpumask_bits(dstp), nr_cpumask_bits); +} + +/** + * cpumask_clear - clear all cpus (< nr_cpu_ids) in a cpumask + * @dstp: the cpumask pointer + */ +static inline void cpumask_clear(struct cpumask *dstp) +{ + bitmap_zero(cpumask_bits(dstp), nr_cpumask_bits); +} + +/** + * cpumask_and - *dstp = *src1p & *src2p + * @dstp: the cpumask result + * @src1p: the first input + * @src2p: the second input + */ +static inline void cpumask_and(struct cpumask *dstp, + const struct cpumask *src1p, + const struct cpumask *src2p) +{ + bitmap_and(cpumask_bits(dstp), cpumask_bits(src1p), + cpumask_bits(src2p), nr_cpumask_bits); +} + +/** + * cpumask_or - *dstp = *src1p | *src2p + * @dstp: the cpumask result + * @src1p: the first input + * @src2p: the second input + */ +static inline void cpumask_or(struct cpumask *dstp, const struct cpumask *src1p, + const struct cpumask *src2p) +{ + bitmap_or(cpumask_bits(dstp), cpumask_bits(src1p), + cpumask_bits(src2p), nr_cpumask_bits); +} + +/** + * cpumask_xor - *dstp = *src1p ^ *src2p + * @dstp: the cpumask result + * @src1p: the first input + * @src2p: the second input + */ +static inline void cpumask_xor(struct cpumask *dstp, + const struct cpumask *src1p, + const struct cpumask *src2p) +{ + bitmap_xor(cpumask_bits(dstp), cpumask_bits(src1p), + cpumask_bits(src2p), nr_cpumask_bits); +} + +/** + * cpumask_andnot - *dstp = *src1p & ~*src2p + * @dstp: the cpumask result + * @src1p: the first input + * @src2p: the second input + */ +static inline void cpumask_andnot(struct cpumask *dstp, + const struct cpumask *src1p, + const struct cpumask *src2p) +{ + bitmap_andnot(cpumask_bits(dstp), cpumask_bits(src1p), + cpumask_bits(src2p), nr_cpumask_bits); +} + +/** + * cpumask_complement - *dstp = ~*srcp + * @dstp: the cpumask result + * @srcp: the input to invert + */ +static inline void cpumask_complement(struct cpumask *dstp, + const struct cpumask *srcp) +{ + bitmap_complement(cpumask_bits(dstp), cpumask_bits(srcp), + nr_cpumask_bits); +} + +/** + * cpumask_equal - *src1p == *src2p + * @src1p: the first input + * @src2p: the second input + */ +static inline bool cpumask_equal(const struct cpumask *src1p, + const struct cpumask *src2p) +{ + return bitmap_equal(cpumask_bits(src1p), cpumask_bits(src2p), + nr_cpumask_bits); +} + +/** + * cpumask_intersects - (*src1p & *src2p) != 0 + * @src1p: the first input + * @src2p: the second input + */ +static inline bool cpumask_intersects(const struct cpumask *src1p, + const struct cpumask *src2p) +{ + return bitmap_intersects(cpumask_bits(src1p), cpumask_bits(src2p), + nr_cpumask_bits); +} + +/** + * cpumask_subset - (*src1p & ~*src2p) == 0 + * @src1p: the first input + * @src2p: the second input + */ +static inline int cpumask_subset(const struct cpumask *src1p, + const struct cpumask *src2p) +{ + return bitmap_subset(cpumask_bits(src1p), cpumask_bits(src2p), + nr_cpumask_bits); +} + +/** + * cpumask_empty - *srcp == 0 + * @srcp: the cpumask to that all cpus < nr_cpu_ids are clear. + */ +static inline bool cpumask_empty(const struct cpumask *srcp) +{ + return bitmap_empty(cpumask_bits(srcp), nr_cpumask_bits); +} + +/** + * cpumask_full - *srcp == 0xFFFFFFFF... + * @srcp: the cpumask to that all cpus < nr_cpu_ids are set. + */ +static inline bool cpumask_full(const struct cpumask *srcp) +{ + return bitmap_full(cpumask_bits(srcp), nr_cpumask_bits); +} + +/** + * cpumask_weight - Count of bits in *srcp + * @srcp: the cpumask to count bits (< nr_cpu_ids) in. + */ +static inline unsigned int cpumask_weight(const struct cpumask *srcp) +{ + return bitmap_weight(cpumask_bits(srcp), nr_cpumask_bits); +} + +/** + * cpumask_shift_right - *dstp = *srcp >> n + * @dstp: the cpumask result + * @srcp: the input to shift + * @n: the number of bits to shift by + */ +static inline void cpumask_shift_right(struct cpumask *dstp, + const struct cpumask *srcp, int n) +{ + bitmap_shift_right(cpumask_bits(dstp), cpumask_bits(srcp), n, + nr_cpumask_bits); +} + +/** + * cpumask_shift_left - *dstp = *srcp << n + * @dstp: the cpumask result + * @srcp: the input to shift + * @n: the number of bits to shift by + */ +static inline void cpumask_shift_left(struct cpumask *dstp, + const struct cpumask *srcp, int n) +{ + bitmap_shift_left(cpumask_bits(dstp), cpumask_bits(srcp), n, + nr_cpumask_bits); +} + +/** + * cpumask_copy - *dstp = *srcp + * @dstp: the result + * @srcp: the input cpumask + */ +static inline void cpumask_copy(struct cpumask *dstp, + const struct cpumask *srcp) +{ + bitmap_copy(cpumask_bits(dstp), cpumask_bits(srcp), nr_cpumask_bits); +} + +/** + * cpumask_any - pick a "random" cpu from *srcp + * @srcp: the input cpumask + * + * Returns >= nr_cpu_ids if no cpus set. + */ +#define cpumask_any(srcp) cpumask_first(srcp) + +/** + * cpumask_first_and - return the first cpu from *srcp1 & *srcp2 + * @src1p: the first input + * @src2p: the second input + * + * Returns >= nr_cpu_ids if no cpus set in both. See also cpumask_next_and(). + */ +#define cpumask_first_and(src1p, src2p) cpumask_next_and(-1, (src1p), (src2p)) + +/** + * cpumask_any_and - pick a "random" cpu from *mask1 & *mask2 + * @mask1: the first input cpumask + * @mask2: the second input cpumask + * + * Returns >= nr_cpu_ids if no cpus set. + */ +#define cpumask_any_and(mask1, mask2) cpumask_first_and((mask1), (mask2)) + +/** + * to_cpumask - convert an NR_CPUS bitmap to a struct cpumask * + * @bitmap: the bitmap + * + * There are a few places where cpumask_var_t isn't appropriate and + * static cpumasks must be used (eg. very early boot), yet we don't + * expose the definition of 'struct cpumask'. + * + * This does the conversion, and can be used as a constant initializer. + */ +#define to_cpumask(bitmap) \ + ((struct cpumask *)(1 ? (bitmap) \ + : (void *)sizeof(__check_is_bitmap(bitmap)))) + +static inline int __check_is_bitmap(const unsigned long *bitmap) +{ + return 1; +} + +/** + * cpumask_size - size to allocate for a 'struct cpumask' in bytes + * + * This will eventually be a runtime variable, depending on nr_cpu_ids. + */ +static inline size_t cpumask_size(void) +{ + /* FIXME: Once all cpumask assignments are eliminated, this + * can be nr_cpumask_bits */ + return BITS_TO_LONGS(NR_CPUS) * sizeof(long); +} + +/* + * cpumask_var_t: struct cpumask for stack usage. + * + * Oh, the wicked games we play! In order to make kernel coding a + * little more difficult, we typedef cpumask_var_t to an array or a + * pointer: doing &mask on an array is a noop, so it still works. + * + * ie. + * cpumask_var_t tmpmask; + * if (!alloc_cpumask_var(&tmpmask, GFP_KERNEL)) + * return -ENOMEM; + * + * ... use 'tmpmask' like a normal struct cpumask * ... + * + * free_cpumask_var(tmpmask); + */ +#ifdef CONFIG_CPUMASK_OFFSTACK +typedef struct cpumask *cpumask_var_t; + +bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags); +void alloc_bootmem_cpumask_var(cpumask_var_t *mask); +void free_cpumask_var(cpumask_var_t mask); + +#else +typedef struct cpumask cpumask_var_t[1]; + +static inline bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) +{ + return true; +} + +static inline void alloc_bootmem_cpumask_var(cpumask_var_t *mask) +{ +} + +static inline void free_cpumask_var(cpumask_var_t mask) +{ +} +#endif /* CONFIG_CPUMASK_OFFSTACK */ + +/* The pointer versions of the maps, these will become the primary versions. */ +#define cpu_possible_mask ((const struct cpumask *)&cpu_possible_map) +#define cpu_online_mask ((const struct cpumask *)&cpu_online_map) +#define cpu_present_mask ((const struct cpumask *)&cpu_present_map) +#define cpu_active_mask ((const struct cpumask *)&cpu_active_map) + +/* It's common to want to use cpu_all_mask in struct member initializers, + * so it has to refer to an address rather than a pointer. */ +extern const DECLARE_BITMAP(cpu_all_bits, NR_CPUS); +#define cpu_all_mask to_cpumask(cpu_all_bits) + +/* First bits of cpu_bit_bitmap are in fact unset. */ +#define cpu_none_mask to_cpumask(cpu_bit_bitmap[0]) + +/* Wrappers for arch boot code to manipulate normally-constant masks */ +static inline void set_cpu_possible(unsigned int cpu, bool possible) +{ + if (possible) + cpumask_set_cpu(cpu, &cpu_possible_map); + else + cpumask_clear_cpu(cpu, &cpu_possible_map); +} + +static inline void set_cpu_present(unsigned int cpu, bool present) +{ + if (present) + cpumask_set_cpu(cpu, &cpu_present_map); + else + cpumask_clear_cpu(cpu, &cpu_present_map); +} + +static inline void set_cpu_online(unsigned int cpu, bool online) +{ + if (online) + cpumask_set_cpu(cpu, &cpu_online_map); + else + cpumask_clear_cpu(cpu, &cpu_online_map); +} + +static inline void set_cpu_active(unsigned int cpu, bool active) +{ + if (active) + cpumask_set_cpu(cpu, &cpu_active_map); + else + cpumask_clear_cpu(cpu, &cpu_active_map); +} + +static inline void init_cpu_present(const struct cpumask *src) +{ + cpumask_copy(&cpu_present_map, src); +} + +static inline void init_cpu_possible(const struct cpumask *src) +{ + cpumask_copy(&cpu_possible_map, src); +} + +static inline void init_cpu_online(const struct cpumask *src) +{ + cpumask_copy(&cpu_online_map, src); +} #endif /* __LINUX_CPUMASK_H */ diff --git a/include/linux/smp.h b/include/linux/smp.h index 2e4d58b26c0..3f9a60043a9 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -64,8 +64,17 @@ extern void smp_cpus_done(unsigned int max_cpus); * Call a function on all other processors */ int smp_call_function(void(*func)(void *info), void *info, int wait); +/* Deprecated: use smp_call_function_many() which uses a cpumask ptr. */ int smp_call_function_mask(cpumask_t mask, void(*func)(void *info), void *info, int wait); + +static inline void smp_call_function_many(const struct cpumask *mask, + void (*func)(void *info), void *info, + int wait) +{ + smp_call_function_mask(*mask, func, info, wait); +} + int smp_call_function_single(int cpuid, void (*func) (void *info), void *info, int wait); void __smp_call_function_single(int cpuid, struct call_single_data *data); diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 89a5a1231ff..b36291130f2 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -240,4 +240,12 @@ void cancel_rearming_delayed_work(struct delayed_work *work) cancel_delayed_work_sync(work); } +#ifndef CONFIG_SMP +static inline long work_on_cpu(unsigned int cpu, long (*fn)(void *), void *arg) +{ + return fn(arg); +} +#else +long work_on_cpu(unsigned int cpu, long (*fn)(void *), void *arg); +#endif /* CONFIG_SMP */ #endif -- cgit v1.2.3 From cd83e42c6b0413dcbb548c2ead799111ff7e6a13 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Fri, 7 Nov 2008 11:12:29 +1100 Subject: cpumask: new API, v2 - add cpumask_of() - add free_bootmem_cpumask_var() Signed-off-by: Rusty Russell Signed-off-by: Ingo Molnar --- include/linux/cpumask.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index c8e66619097..31caa1bc620 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -893,6 +893,12 @@ static inline void cpumask_copy(struct cpumask *dstp, */ #define cpumask_any_and(mask1, mask2) cpumask_first_and((mask1), (mask2)) +/** + * cpumask_of - the cpumask containing just a given cpu + * @cpu: the cpu (<= nr_cpu_ids) + */ +#define cpumask_of(cpu) (get_cpu_mask(cpu)) + /** * to_cpumask - convert an NR_CPUS bitmap to a struct cpumask * * @bitmap: the bitmap @@ -946,6 +952,7 @@ typedef struct cpumask *cpumask_var_t; bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags); 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); #else typedef struct cpumask cpumask_var_t[1]; @@ -962,6 +969,10 @@ static inline void alloc_bootmem_cpumask_var(cpumask_var_t *mask) static inline void free_cpumask_var(cpumask_var_t mask) { } + +static inline void free_bootmem_cpumask_var(cpumask_var_t mask) +{ +} #endif /* CONFIG_CPUMASK_OFFSTACK */ /* The pointer versions of the maps, these will become the primary versions. */ -- cgit v1.2.3 From 14800984706bf6936bbec5187f736e928be5c218 Mon Sep 17 00:00:00 2001 From: Mike Galbraith Date: Fri, 7 Nov 2008 15:26:50 +0100 Subject: sched: fine-tune SD_MC_INIT Tune SD_MC_INIT the same way as SD_CPU_INIT: unset SD_BALANCE_NEWIDLE, and set SD_WAKE_BALANCE. This improves vmark by 5%: vmark 132102 125968 125497 messages/sec avg 127855.66 .984 vmark 139404 131719 131272 messages/sec avg 134131.66 1.033 Signed-off-by: Mike Galbraith Acked-by: Peter Zijlstra Signed-off-by: Ingo Molnar # *DOCUMENTATION* --- include/linux/topology.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/topology.h b/include/linux/topology.h index 34a7ee0ebed..a8d840595b7 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -120,10 +120,10 @@ void arch_update_cpu_topology(void); .wake_idx = 1, \ .forkexec_idx = 1, \ .flags = SD_LOAD_BALANCE \ - | SD_BALANCE_NEWIDLE \ | SD_BALANCE_FORK \ | SD_BALANCE_EXEC \ | SD_WAKE_AFFINE \ + | SD_WAKE_BALANCE \ | SD_SHARE_PKG_RESOURCES\ | BALANCE_FOR_MC_POWER, \ .last_balance = jiffies, \ -- cgit v1.2.3 From 52c642f33b14bfa1b00ef2b68296effb34a573f3 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Fri, 7 Nov 2008 16:09:23 +0100 Subject: sched: fine-tune SD_SIBLING_INIT fine-tune the HT sched-domains parameters as well. On a HT capable box, this increases lat_ctx performance from 23.87 usecs to 1.49 usecs: # before $ ./lat_ctx -s 0 2 "size=0k ovr=1.89 2 23.87 # after $ ./lat_ctx -s 0 2 "size=0k ovr=1.84 2 1.49 Signed-off-by: Ingo Molnar --- include/linux/topology.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/topology.h b/include/linux/topology.h index a8d840595b7..117f1b7405c 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -99,7 +99,7 @@ void arch_update_cpu_topology(void); | SD_BALANCE_FORK \ | SD_BALANCE_EXEC \ | SD_WAKE_AFFINE \ - | SD_WAKE_IDLE \ + | SD_WAKE_BALANCE \ | SD_SHARE_CPUPOWER, \ .last_balance = jiffies, \ .balance_interval = 1, \ -- cgit v1.2.3 From d1b268630875a7713b5d468a0c03403c5b721c8e Mon Sep 17 00:00:00 2001 From: Kay Sievers Date: Sat, 8 Nov 2008 21:37:46 +0100 Subject: mmc: struct device - replace bus_id with dev_name(), dev_set_name() Acked-by: Greg Kroah-Hartman Signed-Off-By: Kay Sievers Signed-off-by: Pierre Ossman --- include/linux/mmc/card.h | 2 +- include/linux/mmc/host.h | 2 +- include/linux/mmc/sdio_func.h | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h index ee6e822d599..403aa505f27 100644 --- a/include/linux/mmc/card.h +++ b/include/linux/mmc/card.h @@ -130,7 +130,7 @@ struct mmc_card { #define mmc_card_set_blockaddr(c) ((c)->state |= MMC_STATE_BLOCKADDR) #define mmc_card_name(c) ((c)->cid.prod_name) -#define mmc_card_id(c) ((c)->dev.bus_id) +#define mmc_card_id(c) (dev_name(&(c)->dev)) #define mmc_list_to_card(l) container_of(l, struct mmc_card, node) #define mmc_get_drvdata(c) dev_get_drvdata(&(c)->dev) diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index bde891f6459..f842f234e44 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -176,7 +176,7 @@ static inline void *mmc_priv(struct mmc_host *host) #define mmc_dev(x) ((x)->parent) #define mmc_classdev(x) (&(x)->class_dev) -#define mmc_hostname(x) ((x)->class_dev.bus_id) +#define mmc_hostname(x) (dev_name(&(x)->class_dev)) extern int mmc_suspend_host(struct mmc_host *, pm_message_t); extern int mmc_resume_host(struct mmc_host *); diff --git a/include/linux/mmc/sdio_func.h b/include/linux/mmc/sdio_func.h index 07bee4a0d45..451bdfc8583 100644 --- a/include/linux/mmc/sdio_func.h +++ b/include/linux/mmc/sdio_func.h @@ -63,7 +63,7 @@ struct sdio_func { #define sdio_func_set_present(f) ((f)->state |= SDIO_STATE_PRESENT) -#define sdio_func_id(f) ((f)->dev.bus_id) +#define sdio_func_id(f) (dev_name(&(f)->dev)) #define sdio_get_drvdata(f) dev_get_drvdata(&(f)->dev) #define sdio_set_drvdata(f,d) dev_set_drvdata(&(f)->dev, d) -- cgit v1.2.3 From 058e3739f6b0753696db1952378de9e8d2a11735 Mon Sep 17 00:00:00 2001 From: Nicolas Pitre Date: Sun, 9 Nov 2008 00:27:53 -0500 Subject: clarify usage expectations for cnt32_to_63() Currently, all existing users of cnt32_to_63() are fine since the CPU architectures where it is used don't do read access reordering, and user mode preemption is disabled already. It is nevertheless a good idea to better elaborate usage requirements wrt preemption, and use an explicit memory barrier on SMP to avoid different CPUs accessing the counter value in the wrong order. On UP a simple compiler barrier is sufficient. Signed-off-by: Nicolas Pitre Acked-by: Mathieu Desnoyers Signed-off-by: Linus Torvalds --- include/linux/cnt32_to_63.h | 22 ++++++++++++++++------ 1 file changed, 16 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cnt32_to_63.h b/include/linux/cnt32_to_63.h index 8c0f9505b48..7605fdd1eb6 100644 --- a/include/linux/cnt32_to_63.h +++ b/include/linux/cnt32_to_63.h @@ -16,6 +16,7 @@ #include #include #include +#include /* this is used only to give gcc a clue about good code generation */ union cnt32_to_63 { @@ -53,11 +54,19 @@ union cnt32_to_63 { * needed increment. And any race in updating the value in memory is harmless * as the same value would simply be stored more than once. * - * The only restriction for the algorithm to work properly is that this - * code must be executed at least once per each half period of the 32-bit - * counter to properly update the state bit in memory. This is usually not a - * problem in practice, but if it is then a kernel timer could be scheduled - * to manage for this code to be executed often enough. + * The restrictions for the algorithm to work properly are: + * + * 1) this code must be called at least once per each half period of the + * 32-bit counter; + * + * 2) this code must not be preempted for a duration longer than the + * 32-bit counter half period minus the longest period between two + * calls to this code. + * + * Those requirements ensure proper update to the state bit in memory. + * This is usually not a problem in practice, but if it is then a kernel + * timer should be scheduled to manage for this code to be executed often + * enough. * * Note that the top bit (bit 63) in the returned value should be considered * as garbage. It is not cleared here because callers are likely to use a @@ -68,9 +77,10 @@ union cnt32_to_63 { */ #define cnt32_to_63(cnt_lo) \ ({ \ - static volatile u32 __m_cnt_hi; \ + static u32 __m_cnt_hi; \ union cnt32_to_63 __x; \ __x.hi = __m_cnt_hi; \ + smp_rmb(); \ __x.lo = (cnt_lo); \ if (unlikely((s32)(__x.hi ^ __x.lo) < 0)) \ __m_cnt_hi = __x.hi = (__x.hi ^ 0x80000000) + (__x.hi >> 31); \ -- cgit v1.2.3 From 984f2f377fdfd098f5ae58d09ee04d5e29e6112b Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Sat, 8 Nov 2008 20:24:19 +1100 Subject: cpumask: introduce new API, without changing anything, v3 Impact: cleanup Clean up based on feedback from Andrew Morton and others: - change to inline functions instead of macros - add __init to bootmem method - add a missing debug check Signed-off-by: Rusty Russell Signed-off-by: Ingo Molnar --- include/linux/cpumask.h | 58 ++++++++++++++++++++++++++++++++++++++++++++----- 1 file changed, 52 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 31caa1bc620..21e1dd43e52 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -564,12 +564,36 @@ static inline unsigned int cpumask_check(unsigned int cpu) } #if NR_CPUS == 1 -/* Uniprocesor. */ -#define cpumask_first(src) ({ (void)(src); 0; }) -#define cpumask_next(n, src) ({ (void)(src); 1; }) -#define cpumask_next_zero(n, src) ({ (void)(src); 1; }) -#define cpumask_next_and(n, srcp, andp) ({ (void)(srcp), (void)(andp); 1; }) -#define cpumask_any_but(mask, cpu) ({ (void)(mask); (void)(cpu); 0; }) +/* Uniprocessor. Assume all masks are "1". */ +static inline unsigned int cpumask_first(const struct cpumask *srcp) +{ + return 0; +} + +/* Valid inputs for n are -1 and 0. */ +static inline unsigned int cpumask_next(int n, const struct cpumask *srcp) +{ + return n+1; +} + +static inline unsigned int cpumask_next_zero(int n, const struct cpumask *srcp) +{ + return n+1; +} + +static inline unsigned int cpumask_next_and(int n, + const struct cpumask *srcp, + const struct cpumask *andp) +{ + return n+1; +} + +/* cpu must be a valid cpu, ie 0, so there's no other choice. */ +static inline unsigned int cpumask_any_but(const struct cpumask *mask, + unsigned int cpu) +{ + return 1; +} #define for_each_cpu(cpu, mask) \ for ((cpu) = 0; (cpu) < 1; (cpu)++, (void)mask) @@ -620,10 +644,32 @@ static inline unsigned int cpumask_next_zero(int n, const struct cpumask *srcp) int cpumask_next_and(int n, const struct cpumask *, const struct cpumask *); int cpumask_any_but(const struct cpumask *mask, unsigned int cpu); +/** + * for_each_cpu - iterate over every cpu in a mask + * @cpu: the (optionally unsigned) integer iterator + * @mask: the cpumask pointer + * + * After the loop, cpu is >= nr_cpu_ids. + */ #define for_each_cpu(cpu, mask) \ for ((cpu) = -1; \ (cpu) = cpumask_next((cpu), (mask)), \ (cpu) < nr_cpu_ids;) + +/** + * for_each_cpu_and - iterate over every cpu in both masks + * @cpu: the (optionally unsigned) integer iterator + * @mask: the first cpumask pointer + * @and: the second cpumask pointer + * + * This saves a temporary CPU mask in many places. It is equivalent to: + * struct cpumask tmp; + * cpumask_and(&tmp, &mask, &and); + * for_each_cpu(cpu, &tmp) + * ... + * + * After the loop, cpu is >= nr_cpu_ids. + */ #define for_each_cpu_and(cpu, mask, and) \ for ((cpu) = -1; \ (cpu) = cpumask_next_and((cpu), (mask), (and)), \ -- cgit v1.2.3 From 8a8bc22332ee6ea49137508467a76aa7f4367719 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 10 Nov 2008 14:48:21 +0900 Subject: libata: revert convert-to-block-tagging patches This patch reverts the following three commits which convert libata to use block layer tagging. 43a49cbdf31e812c0d8f553d433b09b421f5d52c e013e13bf605b9e6b702adffbe2853cfc60e7806 2fca5ccf97d2c28bcfce44f5b07d85e74e3cd18e Although using block layer tagging is the right direction, due to the tight coupling among tag number, data structure allocation and hardware command slot allocation, libata doesn't work correctly with the current conversion. The biggest problem is guaranteeing that tag 0 is always used for non-NCQ commands. Due to the way blk-tag is implemented and how SCSI starts and finishes requests, such guarantee can't be made. I'm not sure whether this would actually break any low level driver but it doesn't look like a good idea to break such assumption given the frailty of ATA controllers. So, for the time being, keep using the old dumb in-libata qc allocation. Signed-off-by: Tejun Heo Cc: Jens Axobe Cc: Jeff Garzik Signed-off-by: Linus Torvalds --- include/linux/libata.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index c7665a4134c..59b0f1c807b 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -698,6 +698,7 @@ struct ata_port { unsigned int cbl; /* cable type; ATA_CBL_xxx */ struct ata_queued_cmd qcmd[ATA_MAX_QUEUE]; + unsigned long qc_allocated; unsigned int qc_active; int nr_active_links; /* #links with active qcs */ -- cgit v1.2.3 From fd0fcf5c29dd0339c5f5d86eb2cbe9fdad5bcd73 Mon Sep 17 00:00:00 2001 From: Michael Buesch Date: Thu, 6 Nov 2008 10:49:21 +0000 Subject: ssb: Fix DMA-API compilation for non-PCI systems This fixes compilation of the SSB DMA-API code on non-PCI platforms. Signed-off-by: Michael Buesch Signed-off-by: David S. Miller --- include/linux/ssb/ssb.h | 42 +++++++++++++++++++++++++++++++++++------- 1 file changed, 35 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ssb/ssb.h b/include/linux/ssb/ssb.h index e530026eedf..17d9b58f637 100644 --- a/include/linux/ssb/ssb.h +++ b/include/linux/ssb/ssb.h @@ -427,12 +427,16 @@ static inline int ssb_dma_mapping_error(struct ssb_device *dev, dma_addr_t addr) { switch (dev->bus->bustype) { case SSB_BUSTYPE_PCI: +#ifdef CONFIG_SSB_PCIHOST return pci_dma_mapping_error(dev->bus->host_pci, addr); +#endif + break; case SSB_BUSTYPE_SSB: return dma_mapping_error(dev->dev, addr); default: - __ssb_dma_not_implemented(dev); + break; } + __ssb_dma_not_implemented(dev); return -ENOSYS; } @@ -441,12 +445,16 @@ static inline dma_addr_t ssb_dma_map_single(struct ssb_device *dev, void *p, { switch (dev->bus->bustype) { case SSB_BUSTYPE_PCI: +#ifdef CONFIG_SSB_PCIHOST return pci_map_single(dev->bus->host_pci, p, size, dir); +#endif + break; case SSB_BUSTYPE_SSB: return dma_map_single(dev->dev, p, size, dir); default: - __ssb_dma_not_implemented(dev); + break; } + __ssb_dma_not_implemented(dev); return 0; } @@ -455,14 +463,18 @@ static inline void ssb_dma_unmap_single(struct ssb_device *dev, dma_addr_t dma_a { switch (dev->bus->bustype) { case SSB_BUSTYPE_PCI: +#ifdef CONFIG_SSB_PCIHOST pci_unmap_single(dev->bus->host_pci, dma_addr, size, dir); return; +#endif + break; case SSB_BUSTYPE_SSB: dma_unmap_single(dev->dev, dma_addr, size, dir); return; default: - __ssb_dma_not_implemented(dev); + break; } + __ssb_dma_not_implemented(dev); } static inline void ssb_dma_sync_single_for_cpu(struct ssb_device *dev, @@ -472,15 +484,19 @@ static inline void ssb_dma_sync_single_for_cpu(struct ssb_device *dev, { switch (dev->bus->bustype) { case SSB_BUSTYPE_PCI: +#ifdef CONFIG_SSB_PCIHOST pci_dma_sync_single_for_cpu(dev->bus->host_pci, dma_addr, size, dir); return; +#endif + break; case SSB_BUSTYPE_SSB: dma_sync_single_for_cpu(dev->dev, dma_addr, size, dir); return; default: - __ssb_dma_not_implemented(dev); + break; } + __ssb_dma_not_implemented(dev); } static inline void ssb_dma_sync_single_for_device(struct ssb_device *dev, @@ -490,15 +506,19 @@ static inline void ssb_dma_sync_single_for_device(struct ssb_device *dev, { switch (dev->bus->bustype) { case SSB_BUSTYPE_PCI: +#ifdef CONFIG_SSB_PCIHOST pci_dma_sync_single_for_device(dev->bus->host_pci, dma_addr, size, dir); return; +#endif + break; case SSB_BUSTYPE_SSB: dma_sync_single_for_device(dev->dev, dma_addr, size, dir); return; default: - __ssb_dma_not_implemented(dev); + break; } + __ssb_dma_not_implemented(dev); } static inline void ssb_dma_sync_single_range_for_cpu(struct ssb_device *dev, @@ -509,17 +529,21 @@ static inline void ssb_dma_sync_single_range_for_cpu(struct ssb_device *dev, { switch (dev->bus->bustype) { case SSB_BUSTYPE_PCI: +#ifdef CONFIG_SSB_PCIHOST /* Just sync everything. That's all the PCI API can do. */ pci_dma_sync_single_for_cpu(dev->bus->host_pci, dma_addr, offset + size, dir); return; +#endif + break; case SSB_BUSTYPE_SSB: dma_sync_single_range_for_cpu(dev->dev, dma_addr, offset, size, dir); return; default: - __ssb_dma_not_implemented(dev); + break; } + __ssb_dma_not_implemented(dev); } static inline void ssb_dma_sync_single_range_for_device(struct ssb_device *dev, @@ -530,17 +554,21 @@ static inline void ssb_dma_sync_single_range_for_device(struct ssb_device *dev, { switch (dev->bus->bustype) { case SSB_BUSTYPE_PCI: +#ifdef CONFIG_SSB_PCIHOST /* Just sync everything. That's all the PCI API can do. */ pci_dma_sync_single_for_device(dev->bus->host_pci, dma_addr, offset + size, dir); return; +#endif + break; case SSB_BUSTYPE_SSB: dma_sync_single_range_for_device(dev->dev, dma_addr, offset, size, dir); return; default: - __ssb_dma_not_implemented(dev); + break; } + __ssb_dma_not_implemented(dev); } -- cgit v1.2.3 From ad474caca3e2a0550b7ce0706527ad5ab389a4d4 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Mon, 10 Nov 2008 15:39:30 +0100 Subject: fix for account_group_exec_runtime(), make sure ->signal can't be freed under rq->lock Impact: fix hang/crash on ia64 under high load This is ugly, but the simplest patch by far. Unlike other similar routines, account_group_exec_runtime() could be called "implicitly" from within scheduler after exit_notify(). This means we can race with the parent doing release_task(), we can't just check ->signal != NULL. Change __exit_signal() to do spin_unlock_wait(&task_rq(tsk)->lock) before __cleanup_signal() to make sure ->signal can't be freed under task_rq(tsk)->lock. Note that task_rq_unlock_wait() doesn't care about the case when tsk changes cpu/rq under us, this should be OK. Thanks to Ingo who nacked my previous buggy patch. Signed-off-by: Oleg Nesterov Acked-by: Peter Zijlstra Signed-off-by: Ingo Molnar Reported-by: Doug Chapman --- include/linux/sched.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 295b7c756ca..644ffbda17c 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -247,6 +247,7 @@ extern void init_idle(struct task_struct *idle, int cpu); extern void init_idle_bootup_task(struct task_struct *idle); extern int runqueue_is_locked(void); +extern void task_rq_unlock_wait(struct task_struct *p); extern cpumask_t nohz_cpu_mask; #if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ) -- cgit v1.2.3 From 0906dd9df2f79042cfa82d8388895be7cbe7a51b Mon Sep 17 00:00:00 2001 From: Alan Cox Date: Tue, 11 Nov 2008 14:51:23 +0000 Subject: telephony: trivial: fix up email address Signed-off-by: Alan Cox Signed-off-by: Linus Torvalds --- include/linux/telephony.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/telephony.h b/include/linux/telephony.h index 5b2b6261f19..f63afe330ad 100644 --- a/include/linux/telephony.h +++ b/include/linux/telephony.h @@ -14,7 +14,7 @@ * Authors: Ed Okerson, * Greg Herlein, * - * Contributors: Alan Cox, + * Contributors: Alan Cox, * David W. Erhart, * * IN NO EVENT SHALL QUICKNET TECHNOLOGIES, INC. BE LIABLE TO ANY PARTY FOR -- cgit v1.2.3