diff --git a/Documentation/trace/user_events.rst b/Documentation/trace/user_events.rst index c180936f49fc..9f181f342a70 100644 --- a/Documentation/trace/user_events.rst +++ b/Documentation/trace/user_events.rst @@ -20,14 +20,14 @@ dynamic_events is the same as the ioctl with the u: prefix applied. Typically programs will register a set of events that they wish to expose to tools that can read trace_events (such as ftrace and perf). The registration -process gives back two ints to the program for each event. The first int is the -status index. This index describes which byte in the +process gives back two ints to the program for each event. The first int is +the status bit. This describes which bit in little-endian format in the /sys/kernel/debug/tracing/user_events_status file represents this event. The -second int is the write index. This index describes the data when a write() or +second int is the write index which describes the data when a write() or writev() is called on the /sys/kernel/debug/tracing/user_events_data file. -The structures referenced in this document are contained with the -/include/uap/linux/user_events.h file in the source tree. +The structures referenced in this document are contained within the +/include/uapi/linux/user_events.h file in the source tree. **NOTE:** *Both user_events_status and user_events_data are under the tracefs filesystem and may be mounted at different paths than above.* @@ -38,18 +38,18 @@ Registering within a user process is done via ioctl() out to the /sys/kernel/debug/tracing/user_events_data file. The command to issue is DIAG_IOCSREG. -This command takes a struct user_reg as an argument:: +This command takes a packed struct user_reg as an argument:: struct user_reg { u32 size; u64 name_args; - u32 status_index; + u32 status_bit; u32 write_index; }; The struct user_reg requires two inputs, the first is the size of the structure to ensure forward and backward compatibility. The second is the command string -to issue for registering. Upon success two outputs are set, the status index +to issue for registering. Upon success two outputs are set, the status bit and the write index. User based events show up under tracefs like any other event under the @@ -111,15 +111,56 @@ in realtime. This allows user programs to only incur the cost of the write() or writev() calls when something is actively attached to the event. User programs call mmap() on /sys/kernel/debug/tracing/user_events_status to -check the status for each event that is registered. The byte to check in the -file is given back after the register ioctl() via user_reg.status_index. +check the status for each event that is registered. The bit to check in the +file is given back after the register ioctl() via user_reg.status_bit. The bit +is always in little-endian format. Programs can check if the bit is set either +using a byte-wise index with a mask or a long-wise index with a little-endian +mask. + Currently the size of user_events_status is a single page, however, custom kernel configurations can change this size to allow more user based events. In all cases the size of the file is a multiple of a page size. -For example, if the register ioctl() gives back a status_index of 3 you would -check byte 3 of the returned mmap data to see if anything is attached to that -event. +For example, if the register ioctl() gives back a status_bit of 3 you would +check byte 0 (3 / 8) of the returned mmap data and then AND the result with 8 +(1 << (3 % 8)) to see if anything is attached to that event. + +A byte-wise index check is performed as follows:: + + int index, mask; + char *status_page; + + index = status_bit / 8; + mask = 1 << (status_bit % 8); + + ... + + if (status_page[index] & mask) { + /* Enabled */ + } + +A long-wise index check is performed as follows:: + + #include + #include + + #if __BITS_PER_LONG == 64 + #define endian_swap(x) htole64(x) + #else + #define endian_swap(x) htole32(x) + #endif + + long index, mask, *status_page; + + index = status_bit / __BITS_PER_LONG; + mask = 1L << (status_bit % __BITS_PER_LONG); + mask = endian_swap(mask); + + ... + + if (status_page[index] & mask) { + /* Enabled */ + } Administrators can easily check the status of all registered events by reading the user_events_status file directly via a terminal. The output is as follows:: @@ -137,7 +178,7 @@ For example, on a system that has a single event the output looks like this:: Active: 1 Busy: 0 - Max: 4096 + Max: 32768 If a user enables the user event via ftrace, the output would change to this:: @@ -145,21 +186,10 @@ If a user enables the user event via ftrace, the output would change to this:: Active: 1 Busy: 1 - Max: 4096 + Max: 32768 -**NOTE:** *A status index of 0 will never be returned. This allows user -programs to have an index that can be used on error cases.* - -Status Bits -^^^^^^^^^^^ -The byte being checked will be non-zero if anything is attached. Programs can -check specific bits in the byte to see what mechanism has been attached. - -The following values are defined to aid in checking what has been attached: - -**EVENT_STATUS_FTRACE** - Bit set if ftrace has been attached (Bit 0). - -**EVENT_STATUS_PERF** - Bit set if perf has been attached (Bit 1). +**NOTE:** *A status bit of 0 will never be returned. This allows user programs +to have a bit that can be used on error cases.* Writing Data ------------ diff --git a/MAINTAINERS b/MAINTAINERS index 5379e31541b7..19215863fcdb 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -8433,6 +8433,19 @@ L: platform-driver-x86@vger.kernel.org S: Maintained F: drivers/platform/x86/fujitsu-tablet.c +FUNCTION HOOKS (FTRACE) +M: Steven Rostedt +M: Masami Hiramatsu +R: Mark Rutland +S: Maintained +T: git git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace.git +F: Documentation/trace/ftrace* +F: kernel/trace/ftrace* +F: kernel/trace/fgraph.c +F: arch/*/*/*/*ftrace* +F: arch/*/*/*ftrace* +F: include/*/ftrace.h + FUNGIBLE ETHERNET DRIVERS M: Dimitris Michailidis L: netdev@vger.kernel.org @@ -11429,7 +11442,7 @@ M: Anil S Keshavamurthy M: "David S. Miller" M: Masami Hiramatsu S: Maintained -T: git git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace.git F: Documentation/trace/kprobes.rst F: include/asm-generic/kprobes.h F: include/linux/kprobes.h @@ -20778,14 +20791,11 @@ F: drivers/hwmon/pmbus/tps546d24.c TRACING M: Steven Rostedt -M: Ingo Molnar +M: Masami Hiramatsu S: Maintained -T: git git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace.git -F: Documentation/trace/ftrace.rst -F: arch/*/*/*/*ftrace* -F: arch/*/*/*ftrace* +T: git git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace.git +F: Documentation/trace/* F: fs/tracefs/ -F: include/*/ftrace.h F: include/linux/trace*.h F: include/trace/ F: kernel/trace/ @@ -20794,7 +20804,7 @@ F: tools/testing/selftests/ftrace/ TRACING MMIO ACCESSES (MMIOTRACE) M: Steven Rostedt -M: Ingo Molnar +M: Masami Hiramatsu R: Karol Herbst R: Pekka Paalanen L: linux-kernel@vger.kernel.org diff --git a/arch/loongarch/kernel/setup.c b/arch/loongarch/kernel/setup.c index 6ca5a0dcbb1c..5b49c78c23f4 100644 --- a/arch/loongarch/kernel/setup.c +++ b/arch/loongarch/kernel/setup.c @@ -336,7 +336,7 @@ static void __init prefill_possible_map(void) for (; i < NR_CPUS; i++) set_cpu_possible(i, false); - nr_cpu_ids = possible; + set_nr_cpu_ids(possible); } #endif diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c index 39c79f67c7a3..f1c88f8a1dc5 100644 --- a/arch/mips/kernel/setup.c +++ b/arch/mips/kernel/setup.c @@ -751,7 +751,7 @@ static void __init prefill_possible_map(void) for (; i < NR_CPUS; i++) set_cpu_possible(i, false); - nr_cpu_ids = possible; + set_nr_cpu_ids(possible); } #else static inline void prefill_possible_map(void) {} diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S index cfc09a96a420..dedcc6fe2263 100644 --- a/arch/powerpc/kernel/head_64.S +++ b/arch/powerpc/kernel/head_64.S @@ -393,8 +393,12 @@ generic_secondary_common_init: #else LOAD_REG_ADDR(r8, paca_ptrs) /* Load paca_ptrs pointe */ ld r8,0(r8) /* Get base vaddr of array */ +#if (NR_CPUS == 1) || defined(CONFIG_FORCE_NR_CPUS) + LOAD_REG_IMMEDIATE(r7, NR_CPUS) +#else LOAD_REG_ADDR(r7, nr_cpu_ids) /* Load nr_cpu_ids address */ lwz r7,0(r7) /* also the max paca allocated */ +#endif li r5,0 /* logical cpu id */ 1: sldi r9,r5,3 /* get paca_ptrs[] index from cpu id */ diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h index b5ef474be858..908d99b127d3 100644 --- a/arch/x86/include/asm/ftrace.h +++ b/arch/x86/include/asm/ftrace.h @@ -23,7 +23,6 @@ #define HAVE_FUNCTION_GRAPH_RET_ADDR_PTR #ifndef __ASSEMBLY__ -extern atomic_t modifying_ftrace_code; extern void __fentry__(void); static inline unsigned long ftrace_call_adjust(unsigned long addr) diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h index 71ea2eab43d5..a2e9317aad49 100644 --- a/arch/x86/include/asm/kprobes.h +++ b/arch/x86/include/asm/kprobes.h @@ -50,8 +50,6 @@ extern const int kretprobe_blacklist_size; void arch_remove_kprobe(struct kprobe *p); -extern void arch_kprobe_override_function(struct pt_regs *regs); - /* Architecture specific copy of original instruction*/ struct arch_specific_insn { /* copy of the original instruction */ diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 4c3c27b6aea3..eb8bc82846b9 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -59,8 +59,6 @@ DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL; DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk); -#define stack_addr(regs) ((unsigned long *)regs->sp) - #define W(row, b0, b1, b2, b3, b4, b5, b6, b7, b8, b9, ba, bb, bc, bd, be, bf)\ (((b0##UL << 0x0)|(b1##UL << 0x1)|(b2##UL << 0x2)|(b3##UL << 0x3) | \ (b4##UL << 0x4)|(b5##UL << 0x5)|(b6##UL << 0x6)|(b7##UL << 0x7) | \ diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index f24227bc3220..3f3ea0287f69 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -1316,7 +1316,7 @@ static void __init smp_sanity_check(void) nr++; } - nr_cpu_ids = 8; + set_nr_cpu_ids(8); } #endif @@ -1569,7 +1569,7 @@ __init void prefill_possible_map(void) possible = i; } - nr_cpu_ids = possible; + set_nr_cpu_ids(possible); pr_info("Allowing %d CPUs, %d hotplug CPUs\n", possible, max_t(int, possible - num_processors, 0)); diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c index ba7af2eca755..480be82e9b7b 100644 --- a/arch/x86/xen/smp_pv.c +++ b/arch/x86/xen/smp_pv.c @@ -179,7 +179,7 @@ static void __init _get_smp_config(unsigned int early) * hypercall to expand the max number of VCPUs an already * running guest has. So cap it up to X. */ if (subtract) - nr_cpu_ids = nr_cpu_ids - subtract; + set_nr_cpu_ids(nr_cpu_ids - subtract); #endif } diff --git a/fs/ntfs3/bitmap.c b/fs/ntfs3/bitmap.c index 5d44ceac855b..e92bbd754365 100644 --- a/fs/ntfs3/bitmap.c +++ b/fs/ntfs3/bitmap.c @@ -560,7 +560,7 @@ static int wnd_rescan(struct wnd_bitmap *wnd) buf = (ulong *)bh->b_data; - used = __bitmap_weight(buf, wbits); + used = bitmap_weight(buf, wbits); if (used < wbits) { frb = wbits - used; wnd->free_bits[iw] = frb; @@ -1364,7 +1364,7 @@ int wnd_extend(struct wnd_bitmap *wnd, size_t new_bits) buf = (ulong *)bh->b_data; __bitmap_clear(buf, b0, blocksize * 8 - b0); - frb = wbits - __bitmap_weight(buf, wbits); + frb = wbits - bitmap_weight(buf, wbits); wnd->total_zeroes += frb - wnd->free_bits[iw]; wnd->free_bits[iw] = frb; diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index 021e83fe831f..48f2d60bd78a 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -28,13 +28,6 @@ static const struct inode_operations proc_sys_inode_operations; static const struct file_operations proc_sys_dir_file_operations; static const struct inode_operations proc_sys_dir_operations; -/* shared constants to be used in various sysctls */ -const int sysctl_vals[] = { 0, 1, 2, 3, 4, 100, 200, 1000, 3000, INT_MAX, 65535, -1 }; -EXPORT_SYMBOL(sysctl_vals); - -const unsigned long sysctl_long_vals[] = { 0, 1, LONG_MAX }; -EXPORT_SYMBOL_GPL(sysctl_long_vals); - /* Support for permanently empty directories */ struct ctl_table sysctl_mount_point[] = { @@ -1246,7 +1239,7 @@ static bool get_links(struct ctl_dir *dir, static int insert_links(struct ctl_table_header *head) { struct ctl_table_set *root_set = &sysctl_table_root.default_set; - struct ctl_dir *core_parent = NULL; + struct ctl_dir *core_parent; struct ctl_table_header *links; int err; diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index f65410a49fda..7d6d73b78147 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -51,6 +51,7 @@ struct device; * bitmap_empty(src, nbits) Are all bits zero in *src? * bitmap_full(src, nbits) Are all bits set in *src? * bitmap_weight(src, nbits) Hamming Weight: number set bits + * bitmap_weight_and(src1, src2, nbits) Hamming Weight of and'ed bitmap * bitmap_set(dst, pos, nbits) Set specified bit area * bitmap_clear(dst, pos, nbits) Clear specified bit area * bitmap_find_next_zero_area(buf, len, pos, n, mask) Find bit free area @@ -164,6 +165,8 @@ bool __bitmap_intersects(const unsigned long *bitmap1, bool __bitmap_subset(const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int nbits); unsigned int __bitmap_weight(const unsigned long *bitmap, unsigned int nbits); +unsigned int __bitmap_weight_and(const unsigned long *bitmap1, + const unsigned long *bitmap2, 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); @@ -222,7 +225,6 @@ void bitmap_copy_le(unsigned long *dst, const unsigned long *src, unsigned int n #else #define bitmap_copy_le bitmap_copy #endif -unsigned int bitmap_ord_to_pos(const unsigned long *bitmap, unsigned int ord, unsigned int nbits); int bitmap_print_to_pagebuf(bool list, char *buf, const unsigned long *maskp, int nmaskbits); @@ -439,6 +441,15 @@ unsigned int bitmap_weight(const unsigned long *src, unsigned int nbits) return __bitmap_weight(src, nbits); } +static __always_inline +unsigned long bitmap_weight_and(const unsigned long *src1, + const unsigned long *src2, unsigned int nbits) +{ + if (small_const_nbits(nbits)) + return hweight_long(*src1 & *src2 & BITMAP_LAST_WORD_MASK(nbits)); + return __bitmap_weight_and(src1, src2, nbits); +} + static __always_inline void bitmap_set(unsigned long *map, unsigned int start, unsigned int nbits) { diff --git a/include/linux/bitops.h b/include/linux/bitops.h index 3b89c64bcfd8..d7dd83fafeba 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -247,6 +247,25 @@ static inline unsigned long __ffs64(u64 word) return __ffs((unsigned long)word); } +/** + * fns - find N'th set bit in a word + * @word: The word to search + * @n: Bit to find + */ +static inline unsigned long fns(unsigned long word, unsigned int n) +{ + unsigned int bit; + + while (word) { + bit = __ffs(word); + if (n-- == 0) + return bit; + __clear_bit(bit, &word); + } + + return BITS_PER_LONG; +} + /** * assign_bit - Assign value to a bit in memory * @nr: the bit to set diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index e8ad12b5b9d2..2f065ad97541 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -35,19 +35,23 @@ typedef struct cpumask { DECLARE_BITMAP(bits, NR_CPUS); } cpumask_t; */ #define cpumask_pr_args(maskp) nr_cpu_ids, cpumask_bits(maskp) -#if NR_CPUS == 1 -#define nr_cpu_ids 1U +#if (NR_CPUS == 1) || defined(CONFIG_FORCE_NR_CPUS) +#define nr_cpu_ids ((unsigned int)NR_CPUS) #else extern unsigned int nr_cpu_ids; #endif -#ifdef CONFIG_CPUMASK_OFFSTACK -/* Assuming NR_CPUS is huge, a runtime limit is more efficient. Also, - * not all bits may be allocated. */ -#define nr_cpumask_bits nr_cpu_ids +static inline void set_nr_cpu_ids(unsigned int nr) +{ +#if (NR_CPUS == 1) || defined(CONFIG_FORCE_NR_CPUS) + WARN_ON(nr != nr_cpu_ids); #else -#define nr_cpumask_bits ((unsigned int)NR_CPUS) + nr_cpu_ids = nr; #endif +} + +/* Deprecated. Always use nr_cpu_ids. */ +#define nr_cpumask_bits nr_cpu_ids /* * The following particular system cpumasks and operations manage @@ -67,10 +71,6 @@ extern unsigned int nr_cpu_ids; * cpu_online_mask is the dynamic subset of cpu_present_mask, * indicating those CPUs available for scheduling. * - * If HOTPLUG is enabled, then cpu_possible_mask is forced to have - * all NR_CPUS bits set, otherwise it is just the set of CPUs that - * ACPI reports present at boot. - * * If HOTPLUG is enabled, then cpu_present_mask varies dynamically, * depending on what ACPI reports as currently plugged in, otherwise * cpu_present_mask is just a copy of cpu_possible_mask. @@ -174,9 +174,8 @@ static inline unsigned int cpumask_last(const struct cpumask *srcp) static inline unsigned int cpumask_next(int n, const struct cpumask *srcp) { - /* -1 is a legal arg here. */ - if (n != -1) - cpumask_check(n); + /* n is a prior cpu */ + cpumask_check(n + 1); return find_next_bit(cpumask_bits(srcp), nr_cpumask_bits, n + 1); } @@ -189,9 +188,8 @@ unsigned int cpumask_next(int n, const struct cpumask *srcp) */ 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); + /* n is a prior cpu */ + cpumask_check(n + 1); return find_next_zero_bit(cpumask_bits(srcp), nr_cpumask_bits, n+1); } @@ -231,9 +229,8 @@ 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); + /* n is a prior cpu */ + cpumask_check(n + 1); return find_next_and_bit(cpumask_bits(src1p), cpumask_bits(src2p), nr_cpumask_bits, n + 1); } @@ -246,9 +243,7 @@ unsigned int cpumask_next_and(int n, const struct cpumask *src1p, * 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_set_bit(cpu, cpumask_bits(mask), nr_cpumask_bits) /** * for_each_cpu_not - iterate over every cpu in a complemented mask @@ -258,17 +253,15 @@ unsigned int cpumask_next_and(int n, const struct cpumask *src1p, * After the loop, cpu is >= nr_cpu_ids. */ #define for_each_cpu_not(cpu, mask) \ - for ((cpu) = -1; \ - (cpu) = cpumask_next_zero((cpu), (mask)), \ - (cpu) < nr_cpu_ids;) + for_each_clear_bit(cpu, cpumask_bits(mask), nr_cpumask_bits) #if NR_CPUS == 1 static inline unsigned int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap) { cpumask_check(start); - if (n != -1) - cpumask_check(n); + /* n is a prior cpu */ + cpumask_check(n + 1); /* * Return the first available CPU when wrapping, or when starting before cpu0, @@ -293,10 +286,8 @@ unsigned int __pure cpumask_next_wrap(int n, const struct cpumask *mask, int sta * * After the loop, cpu is >= nr_cpu_ids. */ -#define for_each_cpu_wrap(cpu, mask, start) \ - for ((cpu) = cpumask_next_wrap((start)-1, (mask), (start), false); \ - (cpu) < nr_cpumask_bits; \ - (cpu) = cpumask_next_wrap((cpu), (mask), (start), true)) +#define for_each_cpu_wrap(cpu, mask, start) \ + for_each_set_bit_wrap(cpu, cpumask_bits(mask), nr_cpumask_bits, start) /** * for_each_cpu_and - iterate over every cpu in both masks @@ -313,9 +304,25 @@ unsigned int __pure cpumask_next_wrap(int n, const struct cpumask *mask, int sta * After the loop, cpu is >= nr_cpu_ids. */ #define for_each_cpu_and(cpu, mask1, mask2) \ - for ((cpu) = -1; \ - (cpu) = cpumask_next_and((cpu), (mask1), (mask2)), \ - (cpu) < nr_cpu_ids;) + for_each_and_bit(cpu, cpumask_bits(mask1), cpumask_bits(mask2), nr_cpumask_bits) + +/** + * for_each_cpu_andnot - iterate over every cpu present in one mask, excluding + * those present in another. + * @cpu: the (optionally unsigned) integer iterator + * @mask1: the first cpumask pointer + * @mask2: the second cpumask pointer + * + * This saves a temporary CPU mask in many places. It is equivalent to: + * struct cpumask tmp; + * cpumask_andnot(&tmp, &mask1, &mask2); + * for_each_cpu(cpu, &tmp) + * ... + * + * After the loop, cpu is >= nr_cpu_ids. + */ +#define for_each_cpu_andnot(cpu, mask1, mask2) \ + for_each_andnot_bit(cpu, cpumask_bits(mask1), cpumask_bits(mask2), nr_cpumask_bits) /** * cpumask_any_but - return a "random" in a cpumask, but not this one. @@ -337,6 +344,50 @@ unsigned int cpumask_any_but(const struct cpumask *mask, unsigned int cpu) return i; } +/** + * cpumask_nth - get the first cpu in a cpumask + * @srcp: the cpumask pointer + * @cpu: the N'th cpu to find, starting from 0 + * + * Returns >= nr_cpu_ids if such cpu doesn't exist. + */ +static inline unsigned int cpumask_nth(unsigned int cpu, const struct cpumask *srcp) +{ + return find_nth_bit(cpumask_bits(srcp), nr_cpumask_bits, cpumask_check(cpu)); +} + +/** + * cpumask_nth_and - get the first cpu in 2 cpumasks + * @srcp1: the cpumask pointer + * @srcp2: the cpumask pointer + * @cpu: the N'th cpu to find, starting from 0 + * + * Returns >= nr_cpu_ids if such cpu doesn't exist. + */ +static inline +unsigned int cpumask_nth_and(unsigned int cpu, const struct cpumask *srcp1, + const struct cpumask *srcp2) +{ + return find_nth_and_bit(cpumask_bits(srcp1), cpumask_bits(srcp2), + nr_cpumask_bits, cpumask_check(cpu)); +} + +/** + * cpumask_nth_andnot - get the first cpu set in 1st cpumask, and clear in 2nd. + * @srcp1: the cpumask pointer + * @srcp2: the cpumask pointer + * @cpu: the N'th cpu to find, starting from 0 + * + * Returns >= nr_cpu_ids if such cpu doesn't exist. + */ +static inline +unsigned int cpumask_nth_andnot(unsigned int cpu, const struct cpumask *srcp1, + const struct cpumask *srcp2) +{ + return find_nth_andnot_bit(cpumask_bits(srcp1), cpumask_bits(srcp2), + nr_cpumask_bits, cpumask_check(cpu)); +} + #define CPU_BITS_NONE \ { \ [0 ... BITS_TO_LONGS(NR_CPUS)-1] = 0UL \ @@ -586,6 +637,17 @@ static inline unsigned int cpumask_weight(const struct cpumask *srcp) return bitmap_weight(cpumask_bits(srcp), nr_cpumask_bits); } +/** + * cpumask_weight_and - Count of bits in (*srcp1 & *srcp2) + * @srcp1: the cpumask to count bits (< nr_cpu_ids) in. + * @srcp2: the cpumask to count bits (< nr_cpu_ids) in. + */ +static inline unsigned int cpumask_weight_and(const struct cpumask *srcp1, + const struct cpumask *srcp2) +{ + return bitmap_weight_and(cpumask_bits(srcp1), cpumask_bits(srcp2), nr_cpumask_bits); +} + /** * cpumask_shift_right - *dstp = *srcp >> n * @dstp: the cpumask result diff --git a/include/linux/find.h b/include/linux/find.h index 424ef67d4a42..ccaf61a0f5fd 100644 --- a/include/linux/find.h +++ b/include/linux/find.h @@ -8,15 +8,33 @@ #include -extern unsigned long _find_next_bit(const unsigned long *addr1, - const unsigned long *addr2, unsigned long nbits, - unsigned long start, unsigned long invert, unsigned long le); +unsigned long _find_next_bit(const unsigned long *addr1, unsigned long nbits, + unsigned long start); +unsigned long _find_next_and_bit(const unsigned long *addr1, const unsigned long *addr2, + unsigned long nbits, unsigned long start); +unsigned long _find_next_andnot_bit(const unsigned long *addr1, const unsigned long *addr2, + unsigned long nbits, unsigned long start); +unsigned long _find_next_zero_bit(const unsigned long *addr, unsigned long nbits, + unsigned long start); extern unsigned long _find_first_bit(const unsigned long *addr, unsigned long size); +unsigned long __find_nth_bit(const unsigned long *addr, unsigned long size, unsigned long n); +unsigned long __find_nth_and_bit(const unsigned long *addr1, const unsigned long *addr2, + unsigned long size, unsigned long n); +unsigned long __find_nth_andnot_bit(const unsigned long *addr1, const unsigned long *addr2, + unsigned long size, unsigned long n); extern unsigned long _find_first_and_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size); extern unsigned long _find_first_zero_bit(const unsigned long *addr, unsigned long size); extern unsigned long _find_last_bit(const unsigned long *addr, unsigned long size); +#ifdef __BIG_ENDIAN +unsigned long _find_first_zero_bit_le(const unsigned long *addr, unsigned long size); +unsigned long _find_next_zero_bit_le(const unsigned long *addr, unsigned + long size, unsigned long offset); +unsigned long _find_next_bit_le(const unsigned long *addr, unsigned + long size, unsigned long offset); +#endif + #ifndef find_next_bit /** * find_next_bit - find the next set bit in a memory region @@ -41,7 +59,7 @@ unsigned long find_next_bit(const unsigned long *addr, unsigned long size, return val ? __ffs(val) : size; } - return _find_next_bit(addr, NULL, size, offset, 0UL, 0); + return _find_next_bit(addr, size, offset); } #endif @@ -71,7 +89,38 @@ unsigned long find_next_and_bit(const unsigned long *addr1, return val ? __ffs(val) : size; } - return _find_next_bit(addr1, addr2, size, offset, 0UL, 0); + return _find_next_and_bit(addr1, addr2, size, offset); +} +#endif + +#ifndef find_next_andnot_bit +/** + * find_next_andnot_bit - find the next set bit in *addr1 excluding all the bits + * in *addr2 + * @addr1: The first address to base the search on + * @addr2: The second address to base the search on + * @size: The bitmap size in bits + * @offset: The bitnumber to start searching at + * + * Returns the bit number for the next set bit + * If no bits are set, returns @size. + */ +static inline +unsigned long find_next_andnot_bit(const unsigned long *addr1, + const unsigned long *addr2, unsigned long size, + unsigned long offset) +{ + if (small_const_nbits(size)) { + unsigned long val; + + if (unlikely(offset >= size)) + return size; + + val = *addr1 & ~*addr2 & GENMASK(size - 1, offset); + return val ? __ffs(val) : size; + } + + return _find_next_andnot_bit(addr1, addr2, size, offset); } #endif @@ -99,7 +148,7 @@ unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size, return val == ~0UL ? size : ffz(val); } - return _find_next_bit(addr, NULL, size, offset, ~0UL, 0); + return _find_next_zero_bit(addr, size, offset); } #endif @@ -125,6 +174,87 @@ unsigned long find_first_bit(const unsigned long *addr, unsigned long size) } #endif +/** + * find_nth_bit - find N'th set bit in a memory region + * @addr: The address to start the search at + * @size: The maximum number of bits to search + * @n: The number of set bit, which position is needed, counting from 0 + * + * The following is semantically equivalent: + * idx = find_nth_bit(addr, size, 0); + * idx = find_first_bit(addr, size); + * + * Returns the bit number of the N'th set bit. + * If no such, returns @size. + */ +static inline +unsigned long find_nth_bit(const unsigned long *addr, unsigned long size, unsigned long n) +{ + if (n >= size) + return size; + + if (small_const_nbits(size)) { + unsigned long val = *addr & GENMASK(size - 1, 0); + + return val ? fns(val, n) : size; + } + + return __find_nth_bit(addr, size, n); +} + +/** + * find_nth_and_bit - find N'th set bit in 2 memory regions + * @addr1: The 1st address to start the search at + * @addr2: The 2nd address to start the search at + * @size: The maximum number of bits to search + * @n: The number of set bit, which position is needed, counting from 0 + * + * Returns the bit number of the N'th set bit. + * If no such, returns @size. + */ +static inline +unsigned long find_nth_and_bit(const unsigned long *addr1, const unsigned long *addr2, + unsigned long size, unsigned long n) +{ + if (n >= size) + return size; + + if (small_const_nbits(size)) { + unsigned long val = *addr1 & *addr2 & GENMASK(size - 1, 0); + + return val ? fns(val, n) : size; + } + + return __find_nth_and_bit(addr1, addr2, size, n); +} + +/** + * find_nth_andnot_bit - find N'th set bit in 2 memory regions, + * flipping bits in 2nd region + * @addr1: The 1st address to start the search at + * @addr2: The 2nd address to start the search at + * @size: The maximum number of bits to search + * @n: The number of set bit, which position is needed, counting from 0 + * + * Returns the bit number of the N'th set bit. + * If no such, returns @size. + */ +static inline +unsigned long find_nth_andnot_bit(const unsigned long *addr1, const unsigned long *addr2, + unsigned long size, unsigned long n) +{ + if (n >= size) + return size; + + if (small_const_nbits(size)) { + unsigned long val = *addr1 & (~*addr2) & GENMASK(size - 1, 0); + + return val ? fns(val, n) : size; + } + + return __find_nth_andnot_bit(addr1, addr2, size, n); +} + #ifndef find_first_and_bit /** * find_first_and_bit - find the first set bit in both memory regions @@ -193,6 +323,78 @@ unsigned long find_last_bit(const unsigned long *addr, unsigned long size) } #endif +/** + * find_next_and_bit_wrap - find the next set bit in both memory regions + * @addr1: The first address to base the search on + * @addr2: The second address to base the search on + * @size: The bitmap size in bits + * @offset: The bitnumber to start searching at + * + * Returns the bit number for the next set bit, or first set bit up to @offset + * If no bits are set, returns @size. + */ +static inline +unsigned long find_next_and_bit_wrap(const unsigned long *addr1, + const unsigned long *addr2, + unsigned long size, unsigned long offset) +{ + unsigned long bit = find_next_and_bit(addr1, addr2, size, offset); + + if (bit < size) + return bit; + + bit = find_first_and_bit(addr1, addr2, offset); + return bit < offset ? bit : size; +} + +/** + * find_next_bit_wrap - find the next set bit in both memory regions + * @addr: The first address to base the search on + * @size: The bitmap size in bits + * @offset: The bitnumber to start searching at + * + * Returns the bit number for the next set bit, or first set bit up to @offset + * If no bits are set, returns @size. + */ +static inline +unsigned long find_next_bit_wrap(const unsigned long *addr, + unsigned long size, unsigned long offset) +{ + unsigned long bit = find_next_bit(addr, size, offset); + + if (bit < size) + return bit; + + bit = find_first_bit(addr, offset); + return bit < offset ? bit : size; +} + +/* + * Helper for for_each_set_bit_wrap(). Make sure you're doing right thing + * before using it alone. + */ +static inline +unsigned long __for_each_wrap(const unsigned long *bitmap, unsigned long size, + unsigned long start, unsigned long n) +{ + unsigned long bit; + + /* If not wrapped around */ + if (n > start) { + /* and have a bit, just return it. */ + bit = find_next_bit(bitmap, size, n); + if (bit < size) + return bit; + + /* Otherwise, wrap around and ... */ + n = 0; + } + + /* Search the other part. */ + bit = find_next_bit(bitmap, start, n); + return bit < start ? bit : size; +} + /** * find_next_clump8 - find next 8-bit clump with set bits in a memory region * @clump: location to store copy of found clump @@ -247,7 +449,21 @@ unsigned long find_next_zero_bit_le(const void *addr, unsigned return val == ~0UL ? size : ffz(val); } - return _find_next_bit(addr, NULL, size, offset, ~0UL, 1); + return _find_next_zero_bit_le(addr, size, offset); +} +#endif + +#ifndef find_first_zero_bit_le +static inline +unsigned long find_first_zero_bit_le(const void *addr, unsigned long size) +{ + if (small_const_nbits(size)) { + unsigned long val = swab(*(const unsigned long *)addr) | ~GENMASK(size - 1, 0); + + return val == ~0UL ? size : ffz(val); + } + + return _find_first_zero_bit_le(addr, size); } #endif @@ -266,40 +482,39 @@ unsigned long find_next_bit_le(const void *addr, unsigned return val ? __ffs(val) : size; } - return _find_next_bit(addr, NULL, size, offset, 0UL, 1); + return _find_next_bit_le(addr, size, offset); } #endif -#ifndef find_first_zero_bit_le -#define find_first_zero_bit_le(addr, size) \ - find_next_zero_bit_le((addr), (size), 0) -#endif - #else #error "Please fix " #endif #define for_each_set_bit(bit, addr, size) \ - for ((bit) = find_next_bit((addr), (size), 0); \ - (bit) < (size); \ - (bit) = find_next_bit((addr), (size), (bit) + 1)) + for ((bit) = 0; (bit) = find_next_bit((addr), (size), (bit)), (bit) < (size); (bit)++) + +#define for_each_and_bit(bit, addr1, addr2, size) \ + for ((bit) = 0; \ + (bit) = find_next_and_bit((addr1), (addr2), (size), (bit)), (bit) < (size);\ + (bit)++) + +#define for_each_andnot_bit(bit, addr1, addr2, size) \ + for ((bit) = 0; \ + (bit) = find_next_andnot_bit((addr1), (addr2), (size), (bit)), (bit) < (size);\ + (bit)++) /* same as for_each_set_bit() but use bit as value to start with */ #define for_each_set_bit_from(bit, addr, size) \ - for ((bit) = find_next_bit((addr), (size), (bit)); \ - (bit) < (size); \ - (bit) = find_next_bit((addr), (size), (bit) + 1)) + for (; (bit) = find_next_bit((addr), (size), (bit)), (bit) < (size); (bit)++) #define for_each_clear_bit(bit, addr, size) \ - for ((bit) = find_next_zero_bit((addr), (size), 0); \ - (bit) < (size); \ - (bit) = find_next_zero_bit((addr), (size), (bit) + 1)) + for ((bit) = 0; \ + (bit) = find_next_zero_bit((addr), (size), (bit)), (bit) < (size); \ + (bit)++) /* same as for_each_clear_bit() but use bit as value to start with */ #define for_each_clear_bit_from(bit, addr, size) \ - for ((bit) = find_next_zero_bit((addr), (size), (bit)); \ - (bit) < (size); \ - (bit) = find_next_zero_bit((addr), (size), (bit) + 1)) + for (; (bit) = find_next_zero_bit((addr), (size), (bit)), (bit) < (size); (bit)++) /** * for_each_set_bitrange - iterate over all set bit ranges [b; e) @@ -309,11 +524,11 @@ unsigned long find_next_bit_le(const void *addr, unsigned * @size: bitmap size in number of bits */ #define for_each_set_bitrange(b, e, addr, size) \ - for ((b) = find_next_bit((addr), (size), 0), \ - (e) = find_next_zero_bit((addr), (size), (b) + 1); \ + for ((b) = 0; \ + (b) = find_next_bit((addr), (size), b), \ + (e) = find_next_zero_bit((addr), (size), (b) + 1), \ (b) < (size); \ - (b) = find_next_bit((addr), (size), (e) + 1), \ - (e) = find_next_zero_bit((addr), (size), (b) + 1)) + (b) = (e) + 1) /** * for_each_set_bitrange_from - iterate over all set bit ranges [b; e) @@ -323,11 +538,11 @@ unsigned long find_next_bit_le(const void *addr, unsigned * @size: bitmap size in number of bits */ #define for_each_set_bitrange_from(b, e, addr, size) \ - for ((b) = find_next_bit((addr), (size), (b)), \ - (e) = find_next_zero_bit((addr), (size), (b) + 1); \ + for (; \ + (b) = find_next_bit((addr), (size), (b)), \ + (e) = find_next_zero_bit((addr), (size), (b) + 1), \ (b) < (size); \ - (b) = find_next_bit((addr), (size), (e) + 1), \ - (e) = find_next_zero_bit((addr), (size), (b) + 1)) + (b) = (e) + 1) /** * for_each_clear_bitrange - iterate over all unset bit ranges [b; e) @@ -337,11 +552,11 @@ unsigned long find_next_bit_le(const void *addr, unsigned * @size: bitmap size in number of bits */ #define for_each_clear_bitrange(b, e, addr, size) \ - for ((b) = find_next_zero_bit((addr), (size), 0), \ - (e) = find_next_bit((addr), (size), (b) + 1); \ + for ((b) = 0; \ + (b) = find_next_zero_bit((addr), (size), (b)), \ + (e) = find_next_bit((addr), (size), (b) + 1), \ (b) < (size); \ - (b) = find_next_zero_bit((addr), (size), (e) + 1), \ - (e) = find_next_bit((addr), (size), (b) + 1)) + (b) = (e) + 1) /** * for_each_clear_bitrange_from - iterate over all unset bit ranges [b; e) @@ -351,11 +566,24 @@ unsigned long find_next_bit_le(const void *addr, unsigned * @size: bitmap size in number of bits */ #define for_each_clear_bitrange_from(b, e, addr, size) \ - for ((b) = find_next_zero_bit((addr), (size), (b)), \ - (e) = find_next_bit((addr), (size), (b) + 1); \ + for (; \ + (b) = find_next_zero_bit((addr), (size), (b)), \ + (e) = find_next_bit((addr), (size), (b) + 1), \ (b) < (size); \ - (b) = find_next_zero_bit((addr), (size), (e) + 1), \ - (e) = find_next_bit((addr), (size), (b) + 1)) + (b) = (e) + 1) + +/** + * for_each_set_bit_wrap - iterate over all set bits starting from @start, and + * wrapping around the end of bitmap. + * @bit: offset for current iteration + * @addr: bitmap address to base the search on + * @size: bitmap size in number of bits + * @start: Starting bit for bitmap traversing, wrapping around the bitmap end + */ +#define for_each_set_bit_wrap(bit, addr, size, start) \ + for ((bit) = find_next_bit_wrap((addr), (size), (start)); \ + (bit) < (size); \ + (bit) = __for_each_wrap((addr), (size), (start), (bit) + 1)) /** * for_each_set_clump8 - iterate over bitmap for each 8-bit clump with set bits diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 0b61371e287b..62557d4bffc2 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -1122,47 +1122,6 @@ static inline void unpause_graph_tracing(void) { } #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ #ifdef CONFIG_TRACING - -/* flags for current->trace */ -enum { - TSK_TRACE_FL_TRACE_BIT = 0, - TSK_TRACE_FL_GRAPH_BIT = 1, -}; -enum { - TSK_TRACE_FL_TRACE = 1 << TSK_TRACE_FL_TRACE_BIT, - TSK_TRACE_FL_GRAPH = 1 << TSK_TRACE_FL_GRAPH_BIT, -}; - -static inline void set_tsk_trace_trace(struct task_struct *tsk) -{ - set_bit(TSK_TRACE_FL_TRACE_BIT, &tsk->trace); -} - -static inline void clear_tsk_trace_trace(struct task_struct *tsk) -{ - clear_bit(TSK_TRACE_FL_TRACE_BIT, &tsk->trace); -} - -static inline int test_tsk_trace_trace(struct task_struct *tsk) -{ - return tsk->trace & TSK_TRACE_FL_TRACE; -} - -static inline void set_tsk_trace_graph(struct task_struct *tsk) -{ - set_bit(TSK_TRACE_FL_GRAPH_BIT, &tsk->trace); -} - -static inline void clear_tsk_trace_graph(struct task_struct *tsk) -{ - clear_bit(TSK_TRACE_FL_GRAPH_BIT, &tsk->trace); -} - -static inline int test_tsk_trace_graph(struct task_struct *tsk) -{ - return tsk->trace & TSK_TRACE_FL_GRAPH; -} - enum ftrace_dump_mode; extern enum ftrace_dump_mode ftrace_dump_on_oops; diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index eddf8ee270e7..a36edb0ec199 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3663,9 +3663,8 @@ static inline bool netif_attr_test_online(unsigned long j, static inline unsigned int netif_attrmask_next(int n, const unsigned long *srcp, unsigned int nr_bits) { - /* -1 is a legal arg here. */ - if (n != -1) - cpu_max_bits_warn(n, nr_bits); + /* n is a prior cpu */ + cpu_max_bits_warn(n + 1, nr_bits); if (srcp) return find_next_bit(srcp, nr_bits, n + 1); @@ -3686,9 +3685,8 @@ static inline int netif_attrmask_next_and(int n, const unsigned long *src1p, const unsigned long *src2p, unsigned int nr_bits) { - /* -1 is a legal arg here. */ - if (n != -1) - cpu_max_bits_warn(n, nr_bits); + /* n is a prior cpu */ + cpu_max_bits_warn(n + 1, nr_bits); if (src1p && src2p) return find_next_and_bit(src1p, src2p, nr_bits, n + 1); diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h index 4b71a96190a8..0c45fb066caa 100644 --- a/include/linux/nodemask.h +++ b/include/linux/nodemask.h @@ -508,8 +508,7 @@ static inline int node_random(const nodemask_t *maskp) w = nodes_weight(*maskp); if (w) - bit = bitmap_ord_to_pos(maskp->bits, - get_random_int() % w, MAX_NUMNODES); + bit = find_nth_bit(maskp->bits, MAX_NUMNODES, get_random_int() % w); return bit; #else return 0; diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index dac53fd3afea..2504df9a0453 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -101,7 +101,7 @@ __ring_buffer_alloc(unsigned long size, unsigned flags, struct lock_class_key *k int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full); __poll_t ring_buffer_poll_wait(struct trace_buffer *buffer, int cpu, struct file *filp, poll_table *poll_table); - +void ring_buffer_wake_waiters(struct trace_buffer *buffer, int cpu); #define RING_BUFFER_ALL_CPUS -1 diff --git a/include/linux/sched.h b/include/linux/sched.h index 12cc87aa4bfb..7a769122fcd2 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1398,9 +1398,6 @@ struct task_struct { #endif #ifdef CONFIG_TRACING - /* State flags for use by tracers: */ - unsigned long trace; - /* Bitmask and counter of trace recursion: */ unsigned long trace_recursion; #endif /* CONFIG_TRACING */ diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 8401dec93c15..20749bd9db71 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -92,6 +92,7 @@ struct trace_iterator { unsigned int temp_size; char *fmt; /* modified format holder */ unsigned int fmt_size; + long wait_index; /* trace_seq for __print_flags() and __print_symbolic() etc. */ struct trace_seq tmp_seq; diff --git a/include/linux/user_events.h b/include/linux/user_events.h index 736e05603463..592a3fbed98e 100644 --- a/include/linux/user_events.h +++ b/include/linux/user_events.h @@ -20,15 +20,6 @@ #define USER_EVENTS_SYSTEM "user_events" #define USER_EVENTS_PREFIX "u:" -/* Bits 0-6 are for known probe types, Bit 7 is for unknown probes */ -#define EVENT_BIT_FTRACE 0 -#define EVENT_BIT_PERF 1 -#define EVENT_BIT_OTHER 7 - -#define EVENT_STATUS_FTRACE (1 << EVENT_BIT_FTRACE) -#define EVENT_STATUS_PERF (1 << EVENT_BIT_PERF) -#define EVENT_STATUS_OTHER (1 << EVENT_BIT_OTHER) - /* Create dynamic location entry within a 32-bit value */ #define DYN_LOC(offset, size) ((size) << 16 | (offset)) @@ -45,12 +36,12 @@ struct user_reg { /* Input: Pointer to string with event name, description and flags */ __u64 name_args; - /* Output: Byte index of the event within the status page */ - __u32 status_index; + /* Output: Bitwise index of the event within the status page */ + __u32 status_bit; /* Output: Index of the event to use when writing data */ __u32 write_index; -}; +} __attribute__((__packed__)); #define DIAG_IOC_MAGIC '*' diff --git a/kernel/module/decompress.c b/kernel/module/decompress.c index 4d0bcb3d9e44..c033572d83f0 100644 --- a/kernel/module/decompress.c +++ b/kernel/module/decompress.c @@ -256,7 +256,7 @@ void module_decompress_cleanup(struct load_info *info) static ssize_t compression_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { - return sysfs_emit(buf, "%s\n", __stringify(MODULE_COMPRESSION)); + return sysfs_emit(buf, __stringify(MODULE_COMPRESSION) "\n"); } static struct kobj_attribute module_compression_attr = __ATTR_RO(compression); diff --git a/kernel/module/tracking.c b/kernel/module/tracking.c index 7f8133044d09..26d812e07615 100644 --- a/kernel/module/tracking.c +++ b/kernel/module/tracking.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include "internal.h" @@ -21,6 +22,9 @@ int try_add_tainted_module(struct module *mod) module_assert_mutex_or_preempt(); + if (!mod->taints) + goto out; + list_for_each_entry_rcu(mod_taint, &unloaded_tainted_modules, list, lockdep_is_held(&module_mutex)) { if (!strcmp(mod_taint->name, mod->name) && @@ -59,3 +63,70 @@ void print_unloaded_tainted_modules(void) } } } + +#ifdef CONFIG_DEBUG_FS +static void *unloaded_tainted_modules_seq_start(struct seq_file *m, loff_t *pos) + __acquires(rcu) +{ + rcu_read_lock(); + return seq_list_start_rcu(&unloaded_tainted_modules, *pos); +} + +static void *unloaded_tainted_modules_seq_next(struct seq_file *m, void *p, loff_t *pos) +{ + return seq_list_next_rcu(p, &unloaded_tainted_modules, pos); +} + +static void unloaded_tainted_modules_seq_stop(struct seq_file *m, void *p) + __releases(rcu) +{ + rcu_read_unlock(); +} + +static int unloaded_tainted_modules_seq_show(struct seq_file *m, void *p) +{ + struct mod_unload_taint *mod_taint; + char buf[MODULE_FLAGS_BUF_SIZE]; + size_t l; + + mod_taint = list_entry(p, struct mod_unload_taint, list); + l = module_flags_taint(mod_taint->taints, buf); + buf[l++] = '\0'; + + seq_printf(m, "%s (%s) %llu", mod_taint->name, buf, mod_taint->count); + seq_puts(m, "\n"); + + return 0; +} + +static const struct seq_operations unloaded_tainted_modules_seq_ops = { + .start = unloaded_tainted_modules_seq_start, + .next = unloaded_tainted_modules_seq_next, + .stop = unloaded_tainted_modules_seq_stop, + .show = unloaded_tainted_modules_seq_show, +}; + +static int unloaded_tainted_modules_open(struct inode *inode, struct file *file) +{ + return seq_open(file, &unloaded_tainted_modules_seq_ops); +} + +static const struct file_operations unloaded_tainted_modules_fops = { + .open = unloaded_tainted_modules_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + +static int __init unloaded_tainted_modules_init(void) +{ + struct dentry *dir; + + dir = debugfs_create_dir("modules", NULL); + debugfs_create_file("unloaded_tainted", 0444, dir, NULL, + &unloaded_tainted_modules_fops); + + return 0; +} +module_init(unloaded_tainted_modules_init); +#endif /* CONFIG_DEBUG_FS */ diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 5b44ae0e6e46..ce0387826eda 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -363,10 +363,7 @@ static void __sched_core_flip(bool enabled) /* * Toggle the offline CPUs. */ - cpumask_copy(&sched_core_mask, cpu_possible_mask); - cpumask_andnot(&sched_core_mask, &sched_core_mask, cpu_online_mask); - - for_each_cpu(cpu, &sched_core_mask) + for_each_cpu_andnot(cpu, cpu_possible_mask, cpu_online_mask) cpu_rq(cpu)->core_enabled = enabled; cpus_read_unlock(); diff --git a/kernel/smp.c b/kernel/smp.c index e8cdc025a046..06a413987a14 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -1069,7 +1069,7 @@ static int __init nrcpus(char *str) int nr_cpus; if (get_option(&str, &nr_cpus) && nr_cpus > 0 && nr_cpus < nr_cpu_ids) - nr_cpu_ids = nr_cpus; + set_nr_cpu_ids(nr_cpus); return 0; } @@ -1087,14 +1087,16 @@ static int __init maxcpus(char *str) early_param("maxcpus", maxcpus); +#if (NR_CPUS > 1) && !defined(CONFIG_FORCE_NR_CPUS) /* Setup number of possible processor ids */ unsigned int nr_cpu_ids __read_mostly = NR_CPUS; EXPORT_SYMBOL(nr_cpu_ids); +#endif /* An arch may set nr_cpu_ids earlier if needed, so this would be redundant */ void __init setup_nr_cpu_ids(void) { - nr_cpu_ids = find_last_bit(cpumask_bits(cpu_possible_mask),NR_CPUS) + 1; + set_nr_cpu_ids(find_last_bit(cpumask_bits(cpu_possible_mask), NR_CPUS) + 1); } /* Called by boot processor to activate the rest. */ diff --git a/kernel/sysctl-test.c b/kernel/sysctl-test.c index 664ded05dd7a..6ef887c19c48 100644 --- a/kernel/sysctl-test.c +++ b/kernel/sysctl-test.c @@ -9,9 +9,6 @@ #define KUNIT_PROC_READ 0 #define KUNIT_PROC_WRITE 1 -static int i_zero; -static int i_one_hundred = 100; - /* * Test that proc_dointvec will not try to use a NULL .data field even when the * length is non-zero. @@ -29,8 +26,8 @@ static void sysctl_test_api_dointvec_null_tbl_data(struct kunit *test) .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, - .extra1 = &i_zero, - .extra2 = &i_one_hundred, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE_HUNDRED, }; /* * proc_dointvec expects a buffer in user space, so we allocate one. We @@ -79,8 +76,8 @@ static void sysctl_test_api_dointvec_table_maxlen_unset(struct kunit *test) .maxlen = 0, .mode = 0644, .proc_handler = proc_dointvec, - .extra1 = &i_zero, - .extra2 = &i_one_hundred, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE_HUNDRED, }; void __user *buffer = (void __user *)kunit_kzalloc(test, sizeof(int), GFP_USER); @@ -122,8 +119,8 @@ static void sysctl_test_api_dointvec_table_len_is_zero(struct kunit *test) .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, - .extra1 = &i_zero, - .extra2 = &i_one_hundred, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE_HUNDRED, }; void __user *buffer = (void __user *)kunit_kzalloc(test, sizeof(int), GFP_USER); @@ -156,8 +153,8 @@ static void sysctl_test_api_dointvec_table_read_but_position_set( .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, - .extra1 = &i_zero, - .extra2 = &i_one_hundred, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE_HUNDRED, }; void __user *buffer = (void __user *)kunit_kzalloc(test, sizeof(int), GFP_USER); @@ -191,8 +188,8 @@ static void sysctl_test_dointvec_read_happy_single_positive(struct kunit *test) .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, - .extra1 = &i_zero, - .extra2 = &i_one_hundred, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE_HUNDRED, }; size_t len = 4; loff_t pos = 0; @@ -222,8 +219,8 @@ static void sysctl_test_dointvec_read_happy_single_negative(struct kunit *test) .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, - .extra1 = &i_zero, - .extra2 = &i_one_hundred, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE_HUNDRED, }; size_t len = 5; loff_t pos = 0; @@ -251,8 +248,8 @@ static void sysctl_test_dointvec_write_happy_single_positive(struct kunit *test) .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, - .extra1 = &i_zero, - .extra2 = &i_one_hundred, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE_HUNDRED, }; char input[] = "9"; size_t len = sizeof(input) - 1; @@ -281,8 +278,8 @@ static void sysctl_test_dointvec_write_happy_single_negative(struct kunit *test) .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, - .extra1 = &i_zero, - .extra2 = &i_one_hundred, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE_HUNDRED, }; char input[] = "-9"; size_t len = sizeof(input) - 1; @@ -313,8 +310,8 @@ static void sysctl_test_api_dointvec_write_single_less_int_min( .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, - .extra1 = &i_zero, - .extra2 = &i_one_hundred, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE_HUNDRED, }; size_t max_len = 32, len = max_len; loff_t pos = 0; @@ -351,8 +348,8 @@ static void sysctl_test_api_dointvec_write_single_greater_int_max( .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, - .extra1 = &i_zero, - .extra2 = &i_one_hundred, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE_HUNDRED, }; size_t max_len = 32, len = max_len; loff_t pos = 0; diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 205d605cacc5..82ab288758f5 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -82,9 +82,16 @@ #include #endif +/* shared constants to be used in various sysctls */ +const int sysctl_vals[] = { 0, 1, 2, 3, 4, 100, 200, 1000, 3000, INT_MAX, 65535, -1 }; +EXPORT_SYMBOL(sysctl_vals); + +const unsigned long sysctl_long_vals[] = { 0, 1, LONG_MAX }; +EXPORT_SYMBOL_GPL(sysctl_long_vals); + #if defined(CONFIG_SYSCTL) -/* Constants used for minimum and maximum */ +/* Constants used for minimum and maximum */ #ifdef CONFIG_PERF_EVENTS static const int six_hundred_forty_kb = 640 * 1024; @@ -129,11 +136,6 @@ static enum sysctl_writes_mode sysctl_writes_strict = SYSCTL_WRITES_STRICT; int sysctl_legacy_va_layout; #endif -#ifdef CONFIG_COMPACTION -/* min_extfrag_threshold is SYSCTL_ZERO */; -static const int max_extfrag_threshold = 1000; -#endif - #endif /* CONFIG_SYSCTL */ /* @@ -1052,9 +1054,9 @@ static int __do_proc_doulongvec_minmax(void *data, struct ctl_table *table, return 0; } - i = (unsigned long *) data; - min = (unsigned long *) table->extra1; - max = (unsigned long *) table->extra2; + i = data; + min = table->extra1; + max = table->extra2; vleft = table->maxlen / sizeof(unsigned long); left = *lenp; @@ -2216,7 +2218,7 @@ static struct ctl_table vm_table[] = { .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, - .extra2 = (void *)&max_extfrag_threshold, + .extra2 = SYSCTL_ONE_THOUSAND, }, { .procname = "compact_unevictable_allowed", diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 447d2e2a8549..02e18c436439 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1644,6 +1644,18 @@ ftrace_find_tramp_ops_any_other(struct dyn_ftrace *rec, struct ftrace_ops *op_ex static struct ftrace_ops * ftrace_find_tramp_ops_next(struct dyn_ftrace *rec, struct ftrace_ops *ops); +static bool skip_record(struct dyn_ftrace *rec) +{ + /* + * At boot up, weak functions are set to disable. Function tracing + * can be enabled before they are, and they still need to be disabled now. + * If the record is disabled, still continue if it is marked as already + * enabled (this is needed to keep the accounting working). + */ + return rec->flags & FTRACE_FL_DISABLED && + !(rec->flags & FTRACE_FL_ENABLED); +} + static bool __ftrace_hash_rec_update(struct ftrace_ops *ops, int filter_hash, bool inc) @@ -1693,7 +1705,7 @@ static bool __ftrace_hash_rec_update(struct ftrace_ops *ops, int in_hash = 0; int match = 0; - if (rec->flags & FTRACE_FL_DISABLED) + if (skip_record(rec)) continue; if (all) { @@ -2126,7 +2138,7 @@ static int ftrace_check_record(struct dyn_ftrace *rec, bool enable, bool update) ftrace_bug_type = FTRACE_BUG_UNKNOWN; - if (rec->flags & FTRACE_FL_DISABLED) + if (skip_record(rec)) return FTRACE_UPDATE_IGNORE; /* @@ -2241,7 +2253,7 @@ static int ftrace_check_record(struct dyn_ftrace *rec, bool enable, bool update) if (update) { /* If there's no more users, clear all flags */ if (!ftrace_rec_count(rec)) - rec->flags = 0; + rec->flags &= FTRACE_FL_DISABLED; else /* * Just disable the record, but keep the ops TRAMP @@ -2634,7 +2646,7 @@ void __weak ftrace_replace_code(int mod_flags) do_for_each_ftrace_rec(pg, rec) { - if (rec->flags & FTRACE_FL_DISABLED) + if (skip_record(rec)) continue; failed = __ftrace_replace_code(rec, enable); @@ -5427,6 +5439,8 @@ static struct ftrace_ops stub_ops = { * it is safe to modify the ftrace record, where it should be * currently calling @old_addr directly, to call @new_addr. * + * This is called with direct_mutex locked. + * * Safety checks should be made to make sure that the code at * @rec->ip is currently calling @old_addr. And this must * also update entry->direct to @new_addr. @@ -5439,6 +5453,8 @@ int __weak ftrace_modify_direct_caller(struct ftrace_func_entry *entry, unsigned long ip = rec->ip; int ret; + lockdep_assert_held(&direct_mutex); + /* * The ftrace_lock was used to determine if the record * had more than one registered user to it. If it did, @@ -5461,7 +5477,7 @@ int __weak ftrace_modify_direct_caller(struct ftrace_func_entry *entry, if (ret) goto out_lock; - ret = register_ftrace_function(&stub_ops); + ret = register_ftrace_function_nolock(&stub_ops); if (ret) { ftrace_set_filter_ip(&stub_ops, ip, 1, 0); goto out_lock; @@ -6081,8 +6097,12 @@ int ftrace_regex_release(struct inode *inode, struct file *file) if (filter_hash) { orig_hash = &iter->ops->func_hash->filter_hash; - if (iter->tr && !list_empty(&iter->tr->mod_trace)) - iter->hash->flags |= FTRACE_HASH_FL_MOD; + if (iter->tr) { + if (list_empty(&iter->tr->mod_trace)) + iter->hash->flags &= ~FTRACE_HASH_FL_MOD; + else + iter->hash->flags |= FTRACE_HASH_FL_MOD; + } } else orig_hash = &iter->ops->func_hash->notrace_hash; diff --git a/kernel/trace/kprobe_event_gen_test.c b/kernel/trace/kprobe_event_gen_test.c index 18b0f1cbb947..80e04a1e1977 100644 --- a/kernel/trace/kprobe_event_gen_test.c +++ b/kernel/trace/kprobe_event_gen_test.c @@ -35,6 +35,45 @@ static struct trace_event_file *gen_kprobe_test; static struct trace_event_file *gen_kretprobe_test; +#define KPROBE_GEN_TEST_FUNC "do_sys_open" + +/* X86 */ +#if defined(CONFIG_X86_64) || defined(CONFIG_X86_32) +#define KPROBE_GEN_TEST_ARG0 "dfd=%ax" +#define KPROBE_GEN_TEST_ARG1 "filename=%dx" +#define KPROBE_GEN_TEST_ARG2 "flags=%cx" +#define KPROBE_GEN_TEST_ARG3 "mode=+4($stack)" + +/* ARM64 */ +#elif defined(CONFIG_ARM64) +#define KPROBE_GEN_TEST_ARG0 "dfd=%x0" +#define KPROBE_GEN_TEST_ARG1 "filename=%x1" +#define KPROBE_GEN_TEST_ARG2 "flags=%x2" +#define KPROBE_GEN_TEST_ARG3 "mode=%x3" + +/* ARM */ +#elif defined(CONFIG_ARM) +#define KPROBE_GEN_TEST_ARG0 "dfd=%r0" +#define KPROBE_GEN_TEST_ARG1 "filename=%r1" +#define KPROBE_GEN_TEST_ARG2 "flags=%r2" +#define KPROBE_GEN_TEST_ARG3 "mode=%r3" + +/* RISCV */ +#elif defined(CONFIG_RISCV) +#define KPROBE_GEN_TEST_ARG0 "dfd=%a0" +#define KPROBE_GEN_TEST_ARG1 "filename=%a1" +#define KPROBE_GEN_TEST_ARG2 "flags=%a2" +#define KPROBE_GEN_TEST_ARG3 "mode=%a3" + +/* others */ +#else +#define KPROBE_GEN_TEST_ARG0 NULL +#define KPROBE_GEN_TEST_ARG1 NULL +#define KPROBE_GEN_TEST_ARG2 NULL +#define KPROBE_GEN_TEST_ARG3 NULL +#endif + + /* * Test to make sure we can create a kprobe event, then add more * fields. @@ -58,14 +97,14 @@ static int __init test_gen_kprobe_cmd(void) * fields. */ ret = kprobe_event_gen_cmd_start(&cmd, "gen_kprobe_test", - "do_sys_open", - "dfd=%ax", "filename=%dx"); + KPROBE_GEN_TEST_FUNC, + KPROBE_GEN_TEST_ARG0, KPROBE_GEN_TEST_ARG1); if (ret) goto free; /* Use kprobe_event_add_fields to add the rest of the fields */ - ret = kprobe_event_add_fields(&cmd, "flags=%cx", "mode=+4($stack)"); + ret = kprobe_event_add_fields(&cmd, KPROBE_GEN_TEST_ARG2, KPROBE_GEN_TEST_ARG3); if (ret) goto free; @@ -128,7 +167,7 @@ static int __init test_gen_kretprobe_cmd(void) * Define the kretprobe event. */ ret = kretprobe_event_gen_cmd_start(&cmd, "gen_kretprobe_test", - "do_sys_open", + KPROBE_GEN_TEST_FUNC, "$retval"); if (ret) goto free; @@ -206,7 +245,7 @@ static void __exit kprobe_event_gen_test_exit(void) WARN_ON(kprobe_event_delete("gen_kprobe_test")); /* Disable the event or you can't remove it */ - WARN_ON(trace_array_set_clr_event(gen_kprobe_test->tr, + WARN_ON(trace_array_set_clr_event(gen_kretprobe_test->tr, "kprobes", "gen_kretprobe_test", false)); diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index d59b6a328b7f..c3f354cfc5ba 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -413,6 +413,7 @@ struct rb_irq_work { struct irq_work work; wait_queue_head_t waiters; wait_queue_head_t full_waiters; + long wait_index; bool waiters_pending; bool full_waiters_pending; bool wakeup_full; @@ -917,12 +918,44 @@ static void rb_wake_up_waiters(struct irq_work *work) struct rb_irq_work *rbwork = container_of(work, struct rb_irq_work, work); wake_up_all(&rbwork->waiters); - if (rbwork->wakeup_full) { + if (rbwork->full_waiters_pending || rbwork->wakeup_full) { rbwork->wakeup_full = false; + rbwork->full_waiters_pending = false; wake_up_all(&rbwork->full_waiters); } } +/** + * ring_buffer_wake_waiters - wake up any waiters on this ring buffer + * @buffer: The ring buffer to wake waiters on + * + * In the case of a file that represents a ring buffer is closing, + * it is prudent to wake up any waiters that are on this. + */ +void ring_buffer_wake_waiters(struct trace_buffer *buffer, int cpu) +{ + struct ring_buffer_per_cpu *cpu_buffer; + struct rb_irq_work *rbwork; + + if (cpu == RING_BUFFER_ALL_CPUS) { + + /* Wake up individual ones too. One level recursion */ + for_each_buffer_cpu(buffer, cpu) + ring_buffer_wake_waiters(buffer, cpu); + + rbwork = &buffer->irq_work; + } else { + cpu_buffer = buffer->buffers[cpu]; + rbwork = &cpu_buffer->irq_work; + } + + rbwork->wait_index++; + /* make sure the waiters see the new index */ + smp_wmb(); + + rb_wake_up_waiters(&rbwork->work); +} + /** * ring_buffer_wait - wait for input to the ring buffer * @buffer: buffer to wait on @@ -938,6 +971,7 @@ int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full) struct ring_buffer_per_cpu *cpu_buffer; DEFINE_WAIT(wait); struct rb_irq_work *work; + long wait_index; int ret = 0; /* @@ -956,6 +990,7 @@ int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full) work = &cpu_buffer->irq_work; } + wait_index = READ_ONCE(work->wait_index); while (true) { if (full) @@ -1011,7 +1046,7 @@ int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full) nr_pages = cpu_buffer->nr_pages; dirty = ring_buffer_nr_dirty_pages(buffer, cpu); if (!cpu_buffer->shortest_full || - cpu_buffer->shortest_full < full) + cpu_buffer->shortest_full > full) cpu_buffer->shortest_full = full; raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); if (!pagebusy && @@ -1020,6 +1055,11 @@ int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full) } schedule(); + + /* Make sure to see the new wait index */ + smp_rmb(); + if (wait_index != work->wait_index) + break; } if (full) @@ -2608,6 +2648,9 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer, /* Mark the rest of the page with padding */ rb_event_set_padding(event); + /* Make sure the padding is visible before the write update */ + smp_wmb(); + /* Set the write back to the previous setting */ local_sub(length, &tail_page->write); return; @@ -2619,6 +2662,9 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer, /* time delta must be non zero */ event->time_delta = 1; + /* Make sure the padding is visible before the tail_page->write update */ + smp_wmb(); + /* Set write to end of buffer */ length = (tail + length) - BUF_PAGE_SIZE; local_sub(length, &tail_page->write); @@ -4587,6 +4633,33 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer) arch_spin_unlock(&cpu_buffer->lock); local_irq_restore(flags); + /* + * The writer has preempt disable, wait for it. But not forever + * Although, 1 second is pretty much "forever" + */ +#define USECS_WAIT 1000000 + for (nr_loops = 0; nr_loops < USECS_WAIT; nr_loops++) { + /* If the write is past the end of page, a writer is still updating it */ + if (likely(!reader || rb_page_write(reader) <= BUF_PAGE_SIZE)) + break; + + udelay(1); + + /* Get the latest version of the reader write value */ + smp_rmb(); + } + + /* The writer is not moving forward? Something is wrong */ + if (RB_WARN_ON(cpu_buffer, nr_loops == USECS_WAIT)) + reader = NULL; + + /* + * Make sure we see any padding after the write update + * (see rb_reset_tail()) + */ + smp_rmb(); + + return reader; } @@ -5616,7 +5689,15 @@ int ring_buffer_read_page(struct trace_buffer *buffer, unsigned int pos = 0; unsigned int size; - if (full) + /* + * If a full page is expected, this can still be returned + * if there's been a previous partial read and the + * rest of the page can be read and the commit page is off + * the reader page. + */ + if (full && + (!read || (len < (commit - read)) || + cpu_buffer->reader_page == cpu_buffer->commit_page)) goto out_unlock; if (len > (commit - read)) diff --git a/kernel/trace/rv/monitors/wip/wip.c b/kernel/trace/rv/monitors/wip/wip.c index 83cace53b9fa..b2b49a27e886 100644 --- a/kernel/trace/rv/monitors/wip/wip.c +++ b/kernel/trace/rv/monitors/wip/wip.c @@ -16,7 +16,7 @@ #include "wip.h" -struct rv_monitor rv_wip; +static struct rv_monitor rv_wip; DECLARE_DA_MON_PER_CPU(wip, unsigned char); static void handle_preempt_disable(void *data, unsigned long ip, unsigned long parent_ip) @@ -60,7 +60,7 @@ static void disable_wip(void) da_monitor_destroy_wip(); } -struct rv_monitor rv_wip = { +static struct rv_monitor rv_wip = { .name = "wip", .description = "wakeup in preemptive per-cpu testing monitor.", .enable = enable_wip, @@ -69,13 +69,13 @@ struct rv_monitor rv_wip = { .enabled = 0, }; -static int register_wip(void) +static int __init register_wip(void) { rv_register_monitor(&rv_wip); return 0; } -static void unregister_wip(void) +static void __exit unregister_wip(void) { rv_unregister_monitor(&rv_wip); } diff --git a/kernel/trace/rv/monitors/wwnr/wwnr.c b/kernel/trace/rv/monitors/wwnr/wwnr.c index 599225d9cf38..0e43dd2db685 100644 --- a/kernel/trace/rv/monitors/wwnr/wwnr.c +++ b/kernel/trace/rv/monitors/wwnr/wwnr.c @@ -15,7 +15,7 @@ #include "wwnr.h" -struct rv_monitor rv_wwnr; +static struct rv_monitor rv_wwnr; DECLARE_DA_MON_PER_TASK(wwnr, unsigned char); static void handle_switch(void *data, bool preempt, struct task_struct *p, @@ -59,7 +59,7 @@ static void disable_wwnr(void) da_monitor_destroy_wwnr(); } -struct rv_monitor rv_wwnr = { +static struct rv_monitor rv_wwnr = { .name = "wwnr", .description = "wakeup while not running per-task testing model.", .enable = enable_wwnr, @@ -68,13 +68,13 @@ struct rv_monitor rv_wwnr = { .enabled = 0, }; -static int register_wwnr(void) +static int __init register_wwnr(void) { rv_register_monitor(&rv_wwnr); return 0; } -static void unregister_wwnr(void) +static void __exit unregister_wwnr(void) { rv_unregister_monitor(&rv_wwnr); } diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index e5d2caa2e7b3..0b104a5cbb98 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1194,12 +1194,14 @@ void *tracing_cond_snapshot_data(struct trace_array *tr) { void *cond_data = NULL; + local_irq_disable(); arch_spin_lock(&tr->max_lock); if (tr->cond_snapshot) cond_data = tr->cond_snapshot->cond_data; arch_spin_unlock(&tr->max_lock); + local_irq_enable(); return cond_data; } @@ -1335,9 +1337,11 @@ int tracing_snapshot_cond_enable(struct trace_array *tr, void *cond_data, goto fail_unlock; } + local_irq_disable(); arch_spin_lock(&tr->max_lock); tr->cond_snapshot = cond_snapshot; arch_spin_unlock(&tr->max_lock); + local_irq_enable(); mutex_unlock(&trace_types_lock); @@ -1364,6 +1368,7 @@ int tracing_snapshot_cond_disable(struct trace_array *tr) { int ret = 0; + local_irq_disable(); arch_spin_lock(&tr->max_lock); if (!tr->cond_snapshot) @@ -1374,6 +1379,7 @@ int tracing_snapshot_cond_disable(struct trace_array *tr) } arch_spin_unlock(&tr->max_lock); + local_irq_enable(); return ret; } @@ -2201,6 +2207,11 @@ static size_t tgid_map_max; #define SAVED_CMDLINES_DEFAULT 128 #define NO_CMDLINE_MAP UINT_MAX +/* + * Preemption must be disabled before acquiring trace_cmdline_lock. + * The various trace_arrays' max_lock must be acquired in a context + * where interrupt is disabled. + */ static arch_spinlock_t trace_cmdline_lock = __ARCH_SPIN_LOCK_UNLOCKED; struct saved_cmdlines_buffer { unsigned map_pid_to_cmdline[PID_MAX_DEFAULT+1]; @@ -2413,7 +2424,11 @@ static int trace_save_cmdline(struct task_struct *tsk) * the lock, but we also don't want to spin * nor do we want to disable interrupts, * so if we miss here, then better luck next time. + * + * This is called within the scheduler and wake up, so interrupts + * had better been disabled and run queue lock been held. */ + lockdep_assert_preemption_disabled(); if (!arch_spin_trylock(&trace_cmdline_lock)) return 0; @@ -5891,9 +5906,11 @@ tracing_saved_cmdlines_size_read(struct file *filp, char __user *ubuf, char buf[64]; int r; + preempt_disable(); arch_spin_lock(&trace_cmdline_lock); r = scnprintf(buf, sizeof(buf), "%u\n", savedcmd->cmdline_num); arch_spin_unlock(&trace_cmdline_lock); + preempt_enable(); return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); } @@ -5918,10 +5935,12 @@ static int tracing_resize_saved_cmdlines(unsigned int val) return -ENOMEM; } + preempt_disable(); arch_spin_lock(&trace_cmdline_lock); savedcmd_temp = savedcmd; savedcmd = s; arch_spin_unlock(&trace_cmdline_lock); + preempt_enable(); free_saved_cmdlines_buffer(savedcmd_temp); return 0; @@ -6374,10 +6393,12 @@ int tracing_set_tracer(struct trace_array *tr, const char *buf) #ifdef CONFIG_TRACER_SNAPSHOT if (t->use_max_tr) { + local_irq_disable(); arch_spin_lock(&tr->max_lock); if (tr->cond_snapshot) ret = -EBUSY; arch_spin_unlock(&tr->max_lock); + local_irq_enable(); if (ret) goto out; } @@ -6408,12 +6429,12 @@ int tracing_set_tracer(struct trace_array *tr, const char *buf) if (tr->current_trace->reset) tr->current_trace->reset(tr); +#ifdef CONFIG_TRACER_MAX_TRACE + had_max_tr = tr->current_trace->use_max_tr; + /* Current trace needs to be nop_trace before synchronize_rcu */ tr->current_trace = &nop_trace; -#ifdef CONFIG_TRACER_MAX_TRACE - had_max_tr = tr->allocated_snapshot; - if (had_max_tr && !t->use_max_tr) { /* * We need to make sure that the update_max_tr sees that @@ -6426,11 +6447,13 @@ int tracing_set_tracer(struct trace_array *tr, const char *buf) free_snapshot(tr); } - if (t->use_max_tr && !had_max_tr) { + if (t->use_max_tr && !tr->allocated_snapshot) { ret = tracing_alloc_snapshot_instance(tr); if (ret < 0) goto out; } +#else + tr->current_trace = &nop_trace; #endif if (t->init) { @@ -7437,10 +7460,12 @@ tracing_snapshot_write(struct file *filp, const char __user *ubuf, size_t cnt, goto out; } + local_irq_disable(); arch_spin_lock(&tr->max_lock); if (tr->cond_snapshot) ret = -EBUSY; arch_spin_unlock(&tr->max_lock); + local_irq_enable(); if (ret) goto out; @@ -8138,6 +8163,12 @@ static int tracing_buffers_release(struct inode *inode, struct file *file) __trace_array_put(iter->tr); + iter->wait_index++; + /* Make sure the waiters see the new wait_index */ + smp_wmb(); + + ring_buffer_wake_waiters(iter->array_buffer->buffer, iter->cpu_file); + if (info->spare) ring_buffer_free_read_page(iter->array_buffer->buffer, info->spare_cpu, info->spare); @@ -8291,6 +8322,8 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, /* did we read anything? */ if (!spd.nr_pages) { + long wait_index; + if (ret) goto out; @@ -8298,10 +8331,21 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, if ((file->f_flags & O_NONBLOCK) || (flags & SPLICE_F_NONBLOCK)) goto out; + wait_index = READ_ONCE(iter->wait_index); + ret = wait_on_pipe(iter, iter->tr->buffer_percent); if (ret) goto out; + /* No need to wait after waking up when tracing is off */ + if (!tracer_tracing_is_on(iter->tr)) + goto out; + + /* Make sure we see the new wait_index */ + smp_rmb(); + if (wait_index != iter->wait_index) + goto out; + goto again; } @@ -8312,12 +8356,34 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, return ret; } +/* An ioctl call with cmd 0 to the ring buffer file will wake up all waiters */ +static long tracing_buffers_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +{ + struct ftrace_buffer_info *info = file->private_data; + struct trace_iterator *iter = &info->iter; + + if (cmd) + return -ENOIOCTLCMD; + + mutex_lock(&trace_types_lock); + + iter->wait_index++; + /* Make sure the waiters see the new wait_index */ + smp_wmb(); + + ring_buffer_wake_waiters(iter->array_buffer->buffer, iter->cpu_file); + + mutex_unlock(&trace_types_lock); + return 0; +} + static const struct file_operations tracing_buffers_fops = { .open = tracing_buffers_open, .read = tracing_buffers_read, .poll = tracing_buffers_poll, .release = tracing_buffers_release, .splice_read = tracing_buffers_splice_read, + .unlocked_ioctl = tracing_buffers_ioctl, .llseek = no_llseek, }; @@ -9006,6 +9072,8 @@ rb_simple_write(struct file *filp, const char __user *ubuf, tracer_tracing_off(tr); if (tr->current_trace->stop) tr->current_trace->stop(tr); + /* Wake up any waiters */ + ring_buffer_wake_waiters(buffer, RING_BUFFER_ALL_CPUS); } mutex_unlock(&trace_types_lock); } @@ -10124,7 +10192,7 @@ __init static int tracer_alloc_buffers(void) * buffer. The memory will be removed once the "instance" is removed. */ ret = cpuhp_setup_state_multi(CPUHP_TRACE_RB_PREPARE, - "trace/RB:preapre", trace_rb_cpu_prepare, + "trace/RB:prepare", trace_rb_cpu_prepare, NULL); if (ret < 0) goto out_free_cpumask; diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 900e75d96c84..54ee5711c729 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -1435,8 +1435,6 @@ event_trigger_unlock_commit(struct trace_event_file *file, struct filter_pred; struct regex; -typedef int (*filter_pred_fn_t) (struct filter_pred *pred, void *event); - typedef int (*regex_match_func)(char *str, struct regex *r, int len); enum regex_type { @@ -1455,17 +1453,6 @@ struct regex { regex_match_func match; }; -struct filter_pred { - filter_pred_fn_t fn; - u64 val; - struct regex regex; - unsigned short *ops; - struct ftrace_event_field *field; - int offset; - int not; - int op; -}; - static inline bool is_string_field(struct ftrace_event_field *field) { return field->filter_type == FILTER_DYN_STRING || diff --git a/kernel/trace/trace_benchmark.c b/kernel/trace/trace_benchmark.c index 801c2a7f7605..54d5fa35c90a 100644 --- a/kernel/trace/trace_benchmark.c +++ b/kernel/trace/trace_benchmark.c @@ -51,7 +51,7 @@ static void trace_do_benchmark(void) local_irq_disable(); start = trace_clock_local(); - trace_benchmark_event(bm_str); + trace_benchmark_event(bm_str, bm_last); stop = trace_clock_local(); local_irq_enable(); diff --git a/kernel/trace/trace_benchmark.h b/kernel/trace/trace_benchmark.h index 79e6fbe5b365..c3e91060dc94 100644 --- a/kernel/trace/trace_benchmark.h +++ b/kernel/trace/trace_benchmark.h @@ -14,19 +14,21 @@ extern void trace_benchmark_unreg(void); TRACE_EVENT_FN(benchmark_event, - TP_PROTO(const char *str), + TP_PROTO(const char *str, u64 delta), - TP_ARGS(str), + TP_ARGS(str, delta), TP_STRUCT__entry( __array( char, str, BENCHMARK_EVENT_STRLEN ) + __field( u64, delta) ), TP_fast_assign( memcpy(__entry->str, str, BENCHMARK_EVENT_STRLEN); + __entry->delta = delta; ), - TP_printk("%s", __entry->str), + TP_printk("%s delta=%llu", __entry->str, __entry->delta), trace_benchmark_reg, trace_benchmark_unreg ); diff --git a/kernel/trace/trace_eprobe.c b/kernel/trace/trace_eprobe.c index 1783e3478912..c08bde9871ec 100644 --- a/kernel/trace/trace_eprobe.c +++ b/kernel/trace/trace_eprobe.c @@ -26,6 +26,9 @@ struct trace_eprobe { /* tracepoint event */ const char *event_name; + /* filter string for the tracepoint */ + char *filter_str; + struct trace_event_call *event; struct dyn_event devent; @@ -664,14 +667,15 @@ static struct event_trigger_data * new_eprobe_trigger(struct trace_eprobe *ep, struct trace_event_file *file) { struct event_trigger_data *trigger; + struct event_filter *filter = NULL; struct eprobe_data *edata; + int ret; edata = kzalloc(sizeof(*edata), GFP_KERNEL); trigger = kzalloc(sizeof(*trigger), GFP_KERNEL); if (!trigger || !edata) { - kfree(edata); - kfree(trigger); - return ERR_PTR(-ENOMEM); + ret = -ENOMEM; + goto error; } trigger->flags = EVENT_TRIGGER_FL_PROBE; @@ -686,13 +690,25 @@ new_eprobe_trigger(struct trace_eprobe *ep, struct trace_event_file *file) trigger->cmd_ops = &event_trigger_cmd; INIT_LIST_HEAD(&trigger->list); - RCU_INIT_POINTER(trigger->filter, NULL); + + if (ep->filter_str) { + ret = create_event_filter(file->tr, file->event_call, + ep->filter_str, false, &filter); + if (ret) + goto error; + } + RCU_INIT_POINTER(trigger->filter, filter); edata->file = file; edata->ep = ep; trigger->private_data = edata; return trigger; +error: + free_event_filter(filter); + kfree(edata); + kfree(trigger); + return ERR_PTR(ret); } static int enable_eprobe(struct trace_eprobe *ep, @@ -726,6 +742,7 @@ static int disable_eprobe(struct trace_eprobe *ep, { struct event_trigger_data *trigger = NULL, *iter; struct trace_event_file *file; + struct event_filter *filter; struct eprobe_data *edata; file = find_event_file(tr, ep->event_system, ep->event_name); @@ -752,6 +769,10 @@ static int disable_eprobe(struct trace_eprobe *ep, /* Make sure nothing is using the edata or trigger */ tracepoint_synchronize_unregister(); + filter = rcu_access_pointer(trigger->filter); + + if (filter) + free_event_filter(filter); kfree(edata); kfree(trigger); @@ -927,12 +948,62 @@ static int trace_eprobe_tp_update_arg(struct trace_eprobe *ep, const char *argv[ return ret; } +static int trace_eprobe_parse_filter(struct trace_eprobe *ep, int argc, const char *argv[]) +{ + struct event_filter *dummy; + int i, ret, len = 0; + char *p; + + if (argc == 0) { + trace_probe_log_err(0, NO_EP_FILTER); + return -EINVAL; + } + + /* Recover the filter string */ + for (i = 0; i < argc; i++) + len += strlen(argv[i]) + 1; + + ep->filter_str = kzalloc(len, GFP_KERNEL); + if (!ep->filter_str) + return -ENOMEM; + + p = ep->filter_str; + for (i = 0; i < argc; i++) { + ret = snprintf(p, len, "%s ", argv[i]); + if (ret < 0) + goto error; + if (ret > len) { + ret = -E2BIG; + goto error; + } + p += ret; + len -= ret; + } + p[-1] = '\0'; + + /* + * Ensure the filter string can be parsed correctly. Note, this + * filter string is for the original event, not for the eprobe. + */ + ret = create_event_filter(top_trace_array(), ep->event, ep->filter_str, + true, &dummy); + free_event_filter(dummy); + if (ret) + goto error; + + return 0; +error: + kfree(ep->filter_str); + ep->filter_str = NULL; + return ret; +} + static int __trace_eprobe_create(int argc, const char *argv[]) { /* * Argument syntax: - * e[:[GRP/][ENAME]] SYSTEM.EVENT [FETCHARGS] - * Fetch args: + * e[:[GRP/][ENAME]] SYSTEM.EVENT [FETCHARGS] [if FILTER] + * Fetch args (no space): * =$[:TYPE] */ const char *event = NULL, *group = EPROBE_EVENT_SYSTEM; @@ -942,8 +1013,8 @@ static int __trace_eprobe_create(int argc, const char *argv[]) char buf1[MAX_EVENT_NAME_LEN]; char buf2[MAX_EVENT_NAME_LEN]; char gbuf[MAX_EVENT_NAME_LEN]; - int ret = 0; - int i; + int ret = 0, filter_idx = 0; + int i, filter_cnt; if (argc < 2 || argv[0][0] != 'e') return -ECANCELED; @@ -968,11 +1039,19 @@ static int __trace_eprobe_create(int argc, const char *argv[]) } if (!event) { - strscpy(buf1, argv[1], MAX_EVENT_NAME_LEN); - sanitize_event_name(buf1); + strscpy(buf1, sys_event, MAX_EVENT_NAME_LEN); event = buf1; } + for (i = 2; i < argc; i++) { + if (!strcmp(argv[i], "if")) { + filter_idx = i + 1; + filter_cnt = argc - filter_idx; + argc = i; + break; + } + } + mutex_lock(&event_mutex); event_call = find_and_get_event(sys_name, sys_event); ep = alloc_event_probe(group, event, event_call, argc - 2); @@ -988,6 +1067,14 @@ static int __trace_eprobe_create(int argc, const char *argv[]) goto error; } + if (filter_idx) { + trace_probe_log_set_index(filter_idx); + ret = trace_eprobe_parse_filter(ep, filter_cnt, argv + filter_idx); + if (ret) + goto parse_error; + } else + ep->filter_str = NULL; + argc -= 2; argv += 2; /* parse arguments */ for (i = 0; i < argc && i < MAX_TRACE_ARGS; i++) { diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index 4b1057ab9d96..96acc2b71ac7 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -43,6 +43,42 @@ enum filter_op_ids { OPS }; static const char * ops[] = { OPS }; +enum filter_pred_fn { + FILTER_PRED_FN_NOP, + FILTER_PRED_FN_64, + FILTER_PRED_FN_S64, + FILTER_PRED_FN_U64, + FILTER_PRED_FN_32, + FILTER_PRED_FN_S32, + FILTER_PRED_FN_U32, + FILTER_PRED_FN_16, + FILTER_PRED_FN_S16, + FILTER_PRED_FN_U16, + FILTER_PRED_FN_8, + FILTER_PRED_FN_S8, + FILTER_PRED_FN_U8, + FILTER_PRED_FN_COMM, + FILTER_PRED_FN_STRING, + FILTER_PRED_FN_STRLOC, + FILTER_PRED_FN_STRRELLOC, + FILTER_PRED_FN_PCHAR_USER, + FILTER_PRED_FN_PCHAR, + FILTER_PRED_FN_CPU, + FILTER_PRED_FN_, + FILTER_PRED_TEST_VISITED, +}; + +struct filter_pred { + enum filter_pred_fn fn_num; + u64 val; + struct regex regex; + unsigned short *ops; + struct ftrace_event_field *field; + int offset; + int not; + int op; +}; + /* * pred functions are OP_LE, OP_LT, OP_GE, OP_GT, and OP_BAND * pred_funcs_##type below must match the order of them above. @@ -590,45 +626,49 @@ predicate_parse(const char *str, int nr_parens, int nr_preds, return ERR_PTR(ret); } -#define DEFINE_COMPARISON_PRED(type) \ -static int filter_pred_LT_##type(struct filter_pred *pred, void *event) \ -{ \ - type *addr = (type *)(event + pred->offset); \ - type val = (type)pred->val; \ - return *addr < val; \ -} \ -static int filter_pred_LE_##type(struct filter_pred *pred, void *event) \ -{ \ - type *addr = (type *)(event + pred->offset); \ - type val = (type)pred->val; \ - return *addr <= val; \ -} \ -static int filter_pred_GT_##type(struct filter_pred *pred, void *event) \ -{ \ - type *addr = (type *)(event + pred->offset); \ - type val = (type)pred->val; \ - return *addr > val; \ -} \ -static int filter_pred_GE_##type(struct filter_pred *pred, void *event) \ -{ \ - type *addr = (type *)(event + pred->offset); \ - type val = (type)pred->val; \ - return *addr >= val; \ -} \ -static int filter_pred_BAND_##type(struct filter_pred *pred, void *event) \ -{ \ - type *addr = (type *)(event + pred->offset); \ - type val = (type)pred->val; \ - return !!(*addr & val); \ -} \ -static const filter_pred_fn_t pred_funcs_##type[] = { \ - filter_pred_LE_##type, \ - filter_pred_LT_##type, \ - filter_pred_GE_##type, \ - filter_pred_GT_##type, \ - filter_pred_BAND_##type, \ +enum pred_cmp_types { + PRED_CMP_TYPE_NOP, + PRED_CMP_TYPE_LT, + PRED_CMP_TYPE_LE, + PRED_CMP_TYPE_GT, + PRED_CMP_TYPE_GE, + PRED_CMP_TYPE_BAND, }; +#define DEFINE_COMPARISON_PRED(type) \ +static int filter_pred_##type(struct filter_pred *pred, void *event) \ +{ \ + switch (pred->op) { \ + case OP_LT: { \ + type *addr = (type *)(event + pred->offset); \ + type val = (type)pred->val; \ + return *addr < val; \ + } \ + case OP_LE: { \ + type *addr = (type *)(event + pred->offset); \ + type val = (type)pred->val; \ + return *addr <= val; \ + } \ + case OP_GT: { \ + type *addr = (type *)(event + pred->offset); \ + type val = (type)pred->val; \ + return *addr > val; \ + } \ + case OP_GE: { \ + type *addr = (type *)(event + pred->offset); \ + type val = (type)pred->val; \ + return *addr >= val; \ + } \ + case OP_BAND: { \ + type *addr = (type *)(event + pred->offset); \ + type val = (type)pred->val; \ + return !!(*addr & val); \ + } \ + default: \ + return 0; \ + } \ +} + #define DEFINE_EQUALITY_PRED(size) \ static int filter_pred_##size(struct filter_pred *pred, void *event) \ { \ @@ -836,11 +876,6 @@ static int filter_pred_comm(struct filter_pred *pred, void *event) return cmp ^ pred->not; } -static int filter_pred_none(struct filter_pred *pred, void *event) -{ - return 0; -} - /* * regex_match_foo - Basic regex callbacks * @@ -986,6 +1021,19 @@ static void filter_build_regex(struct filter_pred *pred) } } + +#ifdef CONFIG_FTRACE_STARTUP_TEST +static int test_pred_visited_fn(struct filter_pred *pred, void *event); +#else +static int test_pred_visited_fn(struct filter_pred *pred, void *event) +{ + return 0; +} +#endif + + +static int filter_pred_fn_call(struct filter_pred *pred, void *event); + /* return 1 if event matches, 0 otherwise (discard) */ int filter_match_preds(struct event_filter *filter, void *rec) { @@ -1003,7 +1051,7 @@ int filter_match_preds(struct event_filter *filter, void *rec) for (i = 0; prog[i].pred; i++) { struct filter_pred *pred = prog[i].pred; - int match = pred->fn(pred, rec); + int match = filter_pred_fn_call(pred, rec); if (match == prog[i].when_to_branch) i = prog[i].target; } @@ -1189,10 +1237,10 @@ int filter_assign_type(const char *type) return FILTER_OTHER; } -static filter_pred_fn_t select_comparison_fn(enum filter_op_ids op, - int field_size, int field_is_signed) +static enum filter_pred_fn select_comparison_fn(enum filter_op_ids op, + int field_size, int field_is_signed) { - filter_pred_fn_t fn = NULL; + enum filter_pred_fn fn = FILTER_PRED_FN_NOP; int pred_func_index = -1; switch (op) { @@ -1201,50 +1249,99 @@ static filter_pred_fn_t select_comparison_fn(enum filter_op_ids op, break; default: if (WARN_ON_ONCE(op < PRED_FUNC_START)) - return NULL; + return fn; pred_func_index = op - PRED_FUNC_START; if (WARN_ON_ONCE(pred_func_index > PRED_FUNC_MAX)) - return NULL; + return fn; } switch (field_size) { case 8: if (pred_func_index < 0) - fn = filter_pred_64; + fn = FILTER_PRED_FN_64; else if (field_is_signed) - fn = pred_funcs_s64[pred_func_index]; + fn = FILTER_PRED_FN_S64; else - fn = pred_funcs_u64[pred_func_index]; + fn = FILTER_PRED_FN_U64; break; case 4: if (pred_func_index < 0) - fn = filter_pred_32; + fn = FILTER_PRED_FN_32; else if (field_is_signed) - fn = pred_funcs_s32[pred_func_index]; + fn = FILTER_PRED_FN_S32; else - fn = pred_funcs_u32[pred_func_index]; + fn = FILTER_PRED_FN_U32; break; case 2: if (pred_func_index < 0) - fn = filter_pred_16; + fn = FILTER_PRED_FN_16; else if (field_is_signed) - fn = pred_funcs_s16[pred_func_index]; + fn = FILTER_PRED_FN_S16; else - fn = pred_funcs_u16[pred_func_index]; + fn = FILTER_PRED_FN_U16; break; case 1: if (pred_func_index < 0) - fn = filter_pred_8; + fn = FILTER_PRED_FN_8; else if (field_is_signed) - fn = pred_funcs_s8[pred_func_index]; + fn = FILTER_PRED_FN_S8; else - fn = pred_funcs_u8[pred_func_index]; + fn = FILTER_PRED_FN_U8; break; } return fn; } + +static int filter_pred_fn_call(struct filter_pred *pred, void *event) +{ + switch (pred->fn_num) { + case FILTER_PRED_FN_64: + return filter_pred_64(pred, event); + case FILTER_PRED_FN_S64: + return filter_pred_s64(pred, event); + case FILTER_PRED_FN_U64: + return filter_pred_u64(pred, event); + case FILTER_PRED_FN_32: + return filter_pred_32(pred, event); + case FILTER_PRED_FN_S32: + return filter_pred_s32(pred, event); + case FILTER_PRED_FN_U32: + return filter_pred_u32(pred, event); + case FILTER_PRED_FN_16: + return filter_pred_16(pred, event); + case FILTER_PRED_FN_S16: + return filter_pred_s16(pred, event); + case FILTER_PRED_FN_U16: + return filter_pred_u16(pred, event); + case FILTER_PRED_FN_8: + return filter_pred_8(pred, event); + case FILTER_PRED_FN_S8: + return filter_pred_s8(pred, event); + case FILTER_PRED_FN_U8: + return filter_pred_u8(pred, event); + case FILTER_PRED_FN_COMM: + return filter_pred_comm(pred, event); + case FILTER_PRED_FN_STRING: + return filter_pred_string(pred, event); + case FILTER_PRED_FN_STRLOC: + return filter_pred_strloc(pred, event); + case FILTER_PRED_FN_STRRELLOC: + return filter_pred_strrelloc(pred, event); + case FILTER_PRED_FN_PCHAR_USER: + return filter_pred_pchar_user(pred, event); + case FILTER_PRED_FN_PCHAR: + return filter_pred_pchar(pred, event); + case FILTER_PRED_FN_CPU: + return filter_pred_cpu(pred, event); + case FILTER_PRED_TEST_VISITED: + return test_pred_visited_fn(pred, event); + default: + return 0; + } +} + /* Called when a predicate is encountered by predicate_parse() */ static int parse_pred(const char *str, void *data, int pos, struct filter_parse_error *pe, @@ -1338,7 +1435,7 @@ static int parse_pred(const char *str, void *data, parse_error(pe, FILT_ERR_IP_FIELD_ONLY, pos + i); goto err_free; } - pred->fn = filter_pred_none; + pred->fn_num = FILTER_PRED_FN_NOP; /* * Quotes are not required, but if they exist then we need @@ -1416,16 +1513,16 @@ static int parse_pred(const char *str, void *data, filter_build_regex(pred); if (field->filter_type == FILTER_COMM) { - pred->fn = filter_pred_comm; + pred->fn_num = FILTER_PRED_FN_COMM; } else if (field->filter_type == FILTER_STATIC_STRING) { - pred->fn = filter_pred_string; + pred->fn_num = FILTER_PRED_FN_STRING; pred->regex.field_len = field->size; } else if (field->filter_type == FILTER_DYN_STRING) { - pred->fn = filter_pred_strloc; + pred->fn_num = FILTER_PRED_FN_STRLOC; } else if (field->filter_type == FILTER_RDYN_STRING) - pred->fn = filter_pred_strrelloc; + pred->fn_num = FILTER_PRED_FN_STRRELLOC; else { if (!ustring_per_cpu) { @@ -1436,9 +1533,9 @@ static int parse_pred(const char *str, void *data, } if (ustring) - pred->fn = filter_pred_pchar_user; + pred->fn_num = FILTER_PRED_FN_PCHAR_USER; else - pred->fn = filter_pred_pchar; + pred->fn_num = FILTER_PRED_FN_PCHAR; } /* go past the last quote */ i++; @@ -1486,10 +1583,10 @@ static int parse_pred(const char *str, void *data, pred->val = val; if (field->filter_type == FILTER_CPU) - pred->fn = filter_pred_cpu; + pred->fn_num = FILTER_PRED_FN_CPU; else { - pred->fn = select_comparison_fn(pred->op, field->size, - field->is_signed); + pred->fn_num = select_comparison_fn(pred->op, field->size, + field->is_signed); if (pred->op == OP_NE) pred->not = 1; } @@ -2296,7 +2393,7 @@ static void update_pred_fn(struct event_filter *filter, char *fields) struct filter_pred *pred = prog[i].pred; struct ftrace_event_field *field = pred->field; - WARN_ON_ONCE(!pred->fn); + WARN_ON_ONCE(pred->fn_num == FILTER_PRED_FN_NOP); if (!field) { WARN_ONCE(1, "all leafs should have field defined %d", i); @@ -2306,7 +2403,7 @@ static void update_pred_fn(struct event_filter *filter, char *fields) if (!strchr(fields, *field->name)) continue; - pred->fn = test_pred_visited_fn; + pred->fn_num = FILTER_PRED_TEST_VISITED; } } diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index fdf784620c28..48465f7e97b4 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -104,6 +104,38 @@ enum field_op_id { FIELD_OP_MULT, }; +enum hist_field_fn { + HIST_FIELD_FN_NOP, + HIST_FIELD_FN_VAR_REF, + HIST_FIELD_FN_COUNTER, + HIST_FIELD_FN_CONST, + HIST_FIELD_FN_LOG2, + HIST_FIELD_FN_BUCKET, + HIST_FIELD_FN_TIMESTAMP, + HIST_FIELD_FN_CPU, + HIST_FIELD_FN_STRING, + HIST_FIELD_FN_DYNSTRING, + HIST_FIELD_FN_RELDYNSTRING, + HIST_FIELD_FN_PSTRING, + HIST_FIELD_FN_S64, + HIST_FIELD_FN_U64, + HIST_FIELD_FN_S32, + HIST_FIELD_FN_U32, + HIST_FIELD_FN_S16, + HIST_FIELD_FN_U16, + HIST_FIELD_FN_S8, + HIST_FIELD_FN_U8, + HIST_FIELD_FN_UMINUS, + HIST_FIELD_FN_MINUS, + HIST_FIELD_FN_PLUS, + HIST_FIELD_FN_DIV, + HIST_FIELD_FN_MULT, + HIST_FIELD_FN_DIV_POWER2, + HIST_FIELD_FN_DIV_NOT_POWER2, + HIST_FIELD_FN_DIV_MULT_SHIFT, + HIST_FIELD_FN_EXECNAME, +}; + /* * A hist_var (histogram variable) contains variable information for * hist_fields having the HIST_FIELD_FL_VAR or HIST_FIELD_FL_VAR_REF @@ -123,15 +155,15 @@ struct hist_var { struct hist_field { struct ftrace_event_field *field; unsigned long flags; - hist_field_fn_t fn; - unsigned int ref; - unsigned int size; - unsigned int offset; - unsigned int is_signed; unsigned long buckets; const char *type; struct hist_field *operands[HIST_FIELD_OPERANDS_MAX]; struct hist_trigger_data *hist_data; + enum hist_field_fn fn_num; + unsigned int ref; + unsigned int size; + unsigned int offset; + unsigned int is_signed; /* * Variable fields contain variable-specific info in var. @@ -166,14 +198,11 @@ struct hist_field { u64 div_multiplier; }; -static u64 hist_field_none(struct hist_field *field, - struct tracing_map_elt *elt, - struct trace_buffer *buffer, - struct ring_buffer_event *rbe, - void *event) -{ - return 0; -} +static u64 hist_fn_call(struct hist_field *hist_field, + struct tracing_map_elt *elt, + struct trace_buffer *buffer, + struct ring_buffer_event *rbe, + void *event); static u64 hist_field_const(struct hist_field *field, struct tracing_map_elt *elt, @@ -250,7 +279,7 @@ static u64 hist_field_log2(struct hist_field *hist_field, { struct hist_field *operand = hist_field->operands[0]; - u64 val = operand->fn(operand, elt, buffer, rbe, event); + u64 val = hist_fn_call(operand, elt, buffer, rbe, event); return (u64) ilog2(roundup_pow_of_two(val)); } @@ -264,7 +293,7 @@ static u64 hist_field_bucket(struct hist_field *hist_field, struct hist_field *operand = hist_field->operands[0]; unsigned long buckets = hist_field->buckets; - u64 val = operand->fn(operand, elt, buffer, rbe, event); + u64 val = hist_fn_call(operand, elt, buffer, rbe, event); if (WARN_ON_ONCE(!buckets)) return val; @@ -285,8 +314,8 @@ static u64 hist_field_plus(struct hist_field *hist_field, struct hist_field *operand1 = hist_field->operands[0]; struct hist_field *operand2 = hist_field->operands[1]; - u64 val1 = operand1->fn(operand1, elt, buffer, rbe, event); - u64 val2 = operand2->fn(operand2, elt, buffer, rbe, event); + u64 val1 = hist_fn_call(operand1, elt, buffer, rbe, event); + u64 val2 = hist_fn_call(operand2, elt, buffer, rbe, event); return val1 + val2; } @@ -300,8 +329,8 @@ static u64 hist_field_minus(struct hist_field *hist_field, struct hist_field *operand1 = hist_field->operands[0]; struct hist_field *operand2 = hist_field->operands[1]; - u64 val1 = operand1->fn(operand1, elt, buffer, rbe, event); - u64 val2 = operand2->fn(operand2, elt, buffer, rbe, event); + u64 val1 = hist_fn_call(operand1, elt, buffer, rbe, event); + u64 val2 = hist_fn_call(operand2, elt, buffer, rbe, event); return val1 - val2; } @@ -315,8 +344,8 @@ static u64 hist_field_div(struct hist_field *hist_field, struct hist_field *operand1 = hist_field->operands[0]; struct hist_field *operand2 = hist_field->operands[1]; - u64 val1 = operand1->fn(operand1, elt, buffer, rbe, event); - u64 val2 = operand2->fn(operand2, elt, buffer, rbe, event); + u64 val1 = hist_fn_call(operand1, elt, buffer, rbe, event); + u64 val2 = hist_fn_call(operand2, elt, buffer, rbe, event); /* Return -1 for the undefined case */ if (!val2) @@ -338,7 +367,7 @@ static u64 div_by_power_of_two(struct hist_field *hist_field, struct hist_field *operand1 = hist_field->operands[0]; struct hist_field *operand2 = hist_field->operands[1]; - u64 val1 = operand1->fn(operand1, elt, buffer, rbe, event); + u64 val1 = hist_fn_call(operand1, elt, buffer, rbe, event); return val1 >> __ffs64(operand2->constant); } @@ -352,7 +381,7 @@ static u64 div_by_not_power_of_two(struct hist_field *hist_field, struct hist_field *operand1 = hist_field->operands[0]; struct hist_field *operand2 = hist_field->operands[1]; - u64 val1 = operand1->fn(operand1, elt, buffer, rbe, event); + u64 val1 = hist_fn_call(operand1, elt, buffer, rbe, event); return div64_u64(val1, operand2->constant); } @@ -366,7 +395,7 @@ static u64 div_by_mult_and_shift(struct hist_field *hist_field, struct hist_field *operand1 = hist_field->operands[0]; struct hist_field *operand2 = hist_field->operands[1]; - u64 val1 = operand1->fn(operand1, elt, buffer, rbe, event); + u64 val1 = hist_fn_call(operand1, elt, buffer, rbe, event); /* * If the divisor is a constant, do a multiplication and shift instead. @@ -400,8 +429,8 @@ static u64 hist_field_mult(struct hist_field *hist_field, struct hist_field *operand1 = hist_field->operands[0]; struct hist_field *operand2 = hist_field->operands[1]; - u64 val1 = operand1->fn(operand1, elt, buffer, rbe, event); - u64 val2 = operand2->fn(operand2, elt, buffer, rbe, event); + u64 val1 = hist_fn_call(operand1, elt, buffer, rbe, event); + u64 val2 = hist_fn_call(operand2, elt, buffer, rbe, event); return val1 * val2; } @@ -414,7 +443,7 @@ static u64 hist_field_unary_minus(struct hist_field *hist_field, { struct hist_field *operand = hist_field->operands[0]; - s64 sval = (s64)operand->fn(operand, elt, buffer, rbe, event); + s64 sval = (s64)hist_fn_call(operand, elt, buffer, rbe, event); u64 val = (u64)-sval; return val; @@ -657,19 +686,19 @@ struct snapshot_context { * Returns the specific division function to use if the divisor * is constant. This avoids extra branches when the trigger is hit. */ -static hist_field_fn_t hist_field_get_div_fn(struct hist_field *divisor) +static enum hist_field_fn hist_field_get_div_fn(struct hist_field *divisor) { u64 div = divisor->constant; if (!(div & (div - 1))) - return div_by_power_of_two; + return HIST_FIELD_FN_DIV_POWER2; /* If the divisor is too large, do a regular division */ if (div > (1 << HIST_DIV_SHIFT)) - return div_by_not_power_of_two; + return HIST_FIELD_FN_DIV_NOT_POWER2; divisor->div_multiplier = div64_u64((u64)(1 << HIST_DIV_SHIFT), div); - return div_by_mult_and_shift; + return HIST_FIELD_FN_DIV_MULT_SHIFT; } static void track_data_free(struct track_data *track_data) @@ -1334,38 +1363,32 @@ static const char *hist_field_name(struct hist_field *field, return field_name; } -static hist_field_fn_t select_value_fn(int field_size, int field_is_signed) +static enum hist_field_fn select_value_fn(int field_size, int field_is_signed) { - hist_field_fn_t fn = NULL; - switch (field_size) { case 8: if (field_is_signed) - fn = hist_field_s64; + return HIST_FIELD_FN_S64; else - fn = hist_field_u64; - break; + return HIST_FIELD_FN_U64; case 4: if (field_is_signed) - fn = hist_field_s32; + return HIST_FIELD_FN_S32; else - fn = hist_field_u32; - break; + return HIST_FIELD_FN_U32; case 2: if (field_is_signed) - fn = hist_field_s16; + return HIST_FIELD_FN_S16; else - fn = hist_field_u16; - break; + return HIST_FIELD_FN_U16; case 1: if (field_is_signed) - fn = hist_field_s8; + return HIST_FIELD_FN_S8; else - fn = hist_field_u8; - break; + return HIST_FIELD_FN_U8; } - return fn; + return HIST_FIELD_FN_NOP; } static int parse_map_size(char *str) @@ -1922,19 +1945,19 @@ static struct hist_field *create_hist_field(struct hist_trigger_data *hist_data, goto out; /* caller will populate */ if (flags & HIST_FIELD_FL_VAR_REF) { - hist_field->fn = hist_field_var_ref; + hist_field->fn_num = HIST_FIELD_FN_VAR_REF; goto out; } if (flags & HIST_FIELD_FL_HITCOUNT) { - hist_field->fn = hist_field_counter; + hist_field->fn_num = HIST_FIELD_FN_COUNTER; hist_field->size = sizeof(u64); hist_field->type = "u64"; goto out; } if (flags & HIST_FIELD_FL_CONST) { - hist_field->fn = hist_field_const; + hist_field->fn_num = HIST_FIELD_FN_CONST; hist_field->size = sizeof(u64); hist_field->type = kstrdup("u64", GFP_KERNEL); if (!hist_field->type) @@ -1943,14 +1966,14 @@ static struct hist_field *create_hist_field(struct hist_trigger_data *hist_data, } if (flags & HIST_FIELD_FL_STACKTRACE) { - hist_field->fn = hist_field_none; + hist_field->fn_num = HIST_FIELD_FN_NOP; goto out; } if (flags & (HIST_FIELD_FL_LOG2 | HIST_FIELD_FL_BUCKET)) { unsigned long fl = flags & ~(HIST_FIELD_FL_LOG2 | HIST_FIELD_FL_BUCKET); - hist_field->fn = flags & HIST_FIELD_FL_LOG2 ? hist_field_log2 : - hist_field_bucket; + hist_field->fn_num = flags & HIST_FIELD_FL_LOG2 ? HIST_FIELD_FN_LOG2 : + HIST_FIELD_FN_BUCKET; hist_field->operands[0] = create_hist_field(hist_data, field, fl, NULL); hist_field->size = hist_field->operands[0]->size; hist_field->type = kstrdup_const(hist_field->operands[0]->type, GFP_KERNEL); @@ -1960,14 +1983,14 @@ static struct hist_field *create_hist_field(struct hist_trigger_data *hist_data, } if (flags & HIST_FIELD_FL_TIMESTAMP) { - hist_field->fn = hist_field_timestamp; + hist_field->fn_num = HIST_FIELD_FN_TIMESTAMP; hist_field->size = sizeof(u64); hist_field->type = "u64"; goto out; } if (flags & HIST_FIELD_FL_CPU) { - hist_field->fn = hist_field_cpu; + hist_field->fn_num = HIST_FIELD_FN_CPU; hist_field->size = sizeof(int); hist_field->type = "unsigned int"; goto out; @@ -1987,14 +2010,14 @@ static struct hist_field *create_hist_field(struct hist_trigger_data *hist_data, goto free; if (field->filter_type == FILTER_STATIC_STRING) { - hist_field->fn = hist_field_string; + hist_field->fn_num = HIST_FIELD_FN_STRING; hist_field->size = field->size; } else if (field->filter_type == FILTER_DYN_STRING) { - hist_field->fn = hist_field_dynstring; + hist_field->fn_num = HIST_FIELD_FN_DYNSTRING; } else if (field->filter_type == FILTER_RDYN_STRING) - hist_field->fn = hist_field_reldynstring; + hist_field->fn_num = HIST_FIELD_FN_RELDYNSTRING; else - hist_field->fn = hist_field_pstring; + hist_field->fn_num = HIST_FIELD_FN_PSTRING; } else { hist_field->size = field->size; hist_field->is_signed = field->is_signed; @@ -2002,9 +2025,9 @@ static struct hist_field *create_hist_field(struct hist_trigger_data *hist_data, if (!hist_field->type) goto free; - hist_field->fn = select_value_fn(field->size, - field->is_signed); - if (!hist_field->fn) { + hist_field->fn_num = select_value_fn(field->size, + field->is_signed); + if (hist_field->fn_num == HIST_FIELD_FN_NOP) { destroy_hist_field(hist_field, 0); return NULL; } @@ -2340,7 +2363,7 @@ static struct hist_field *create_alias(struct hist_trigger_data *hist_data, if (!alias) return NULL; - alias->fn = var_ref->fn; + alias->fn_num = var_ref->fn_num; alias->operands[0] = var_ref; if (init_var_ref(alias, var_ref, var_ref->system, var_ref->event_name)) { @@ -2523,7 +2546,7 @@ static struct hist_field *parse_unary(struct hist_trigger_data *hist_data, expr->flags |= operand1->flags & (HIST_FIELD_FL_TIMESTAMP | HIST_FIELD_FL_TIMESTAMP_USECS); - expr->fn = hist_field_unary_minus; + expr->fn_num = HIST_FIELD_FN_UMINUS; expr->operands[0] = operand1; expr->size = operand1->size; expr->is_signed = operand1->is_signed; @@ -2595,7 +2618,7 @@ static struct hist_field *parse_expr(struct hist_trigger_data *hist_data, unsigned long operand_flags, operand2_flags; int field_op, ret = -EINVAL; char *sep, *operand1_str; - hist_field_fn_t op_fn; + enum hist_field_fn op_fn; bool combine_consts; if (*n_subexprs > 3) { @@ -2654,16 +2677,16 @@ static struct hist_field *parse_expr(struct hist_trigger_data *hist_data, switch (field_op) { case FIELD_OP_MINUS: - op_fn = hist_field_minus; + op_fn = HIST_FIELD_FN_MINUS; break; case FIELD_OP_PLUS: - op_fn = hist_field_plus; + op_fn = HIST_FIELD_FN_PLUS; break; case FIELD_OP_DIV: - op_fn = hist_field_div; + op_fn = HIST_FIELD_FN_DIV; break; case FIELD_OP_MULT: - op_fn = hist_field_mult; + op_fn = HIST_FIELD_FN_MULT; break; default: ret = -EINVAL; @@ -2719,13 +2742,16 @@ static struct hist_field *parse_expr(struct hist_trigger_data *hist_data, op_fn = hist_field_get_div_fn(operand2); } + expr->fn_num = op_fn; + if (combine_consts) { if (var1) expr->operands[0] = var1; if (var2) expr->operands[1] = var2; - expr->constant = op_fn(expr, NULL, NULL, NULL, NULL); + expr->constant = hist_fn_call(expr, NULL, NULL, NULL, NULL); + expr->fn_num = HIST_FIELD_FN_CONST; expr->operands[0] = NULL; expr->operands[1] = NULL; @@ -2739,8 +2765,6 @@ static struct hist_field *parse_expr(struct hist_trigger_data *hist_data, expr->name = expr_str(expr, 0); } else { - expr->fn = op_fn; - /* The operand sizes should be the same, so just pick one */ expr->size = operand1->size; expr->is_signed = operand1->is_signed; @@ -3065,7 +3089,7 @@ static inline void __update_field_vars(struct tracing_map_elt *elt, struct hist_field *var = field_var->var; struct hist_field *val = field_var->val; - var_val = val->fn(val, elt, buffer, rbe, rec); + var_val = hist_fn_call(val, elt, buffer, rbe, rec); var_idx = var->var.idx; if (val->flags & HIST_FIELD_FL_STRING) { @@ -4186,6 +4210,74 @@ static u64 hist_field_execname(struct hist_field *hist_field, return (u64)(unsigned long)(elt_data->comm); } +static u64 hist_fn_call(struct hist_field *hist_field, + struct tracing_map_elt *elt, + struct trace_buffer *buffer, + struct ring_buffer_event *rbe, + void *event) +{ + switch (hist_field->fn_num) { + case HIST_FIELD_FN_VAR_REF: + return hist_field_var_ref(hist_field, elt, buffer, rbe, event); + case HIST_FIELD_FN_COUNTER: + return hist_field_counter(hist_field, elt, buffer, rbe, event); + case HIST_FIELD_FN_CONST: + return hist_field_const(hist_field, elt, buffer, rbe, event); + case HIST_FIELD_FN_LOG2: + return hist_field_log2(hist_field, elt, buffer, rbe, event); + case HIST_FIELD_FN_BUCKET: + return hist_field_bucket(hist_field, elt, buffer, rbe, event); + case HIST_FIELD_FN_TIMESTAMP: + return hist_field_timestamp(hist_field, elt, buffer, rbe, event); + case HIST_FIELD_FN_CPU: + return hist_field_cpu(hist_field, elt, buffer, rbe, event); + case HIST_FIELD_FN_STRING: + return hist_field_string(hist_field, elt, buffer, rbe, event); + case HIST_FIELD_FN_DYNSTRING: + return hist_field_dynstring(hist_field, elt, buffer, rbe, event); + case HIST_FIELD_FN_RELDYNSTRING: + return hist_field_reldynstring(hist_field, elt, buffer, rbe, event); + case HIST_FIELD_FN_PSTRING: + return hist_field_pstring(hist_field, elt, buffer, rbe, event); + case HIST_FIELD_FN_S64: + return hist_field_s64(hist_field, elt, buffer, rbe, event); + case HIST_FIELD_FN_U64: + return hist_field_u64(hist_field, elt, buffer, rbe, event); + case HIST_FIELD_FN_S32: + return hist_field_s32(hist_field, elt, buffer, rbe, event); + case HIST_FIELD_FN_U32: + return hist_field_u32(hist_field, elt, buffer, rbe, event); + case HIST_FIELD_FN_S16: + return hist_field_s16(hist_field, elt, buffer, rbe, event); + case HIST_FIELD_FN_U16: + return hist_field_u16(hist_field, elt, buffer, rbe, event); + case HIST_FIELD_FN_S8: + return hist_field_s8(hist_field, elt, buffer, rbe, event); + case HIST_FIELD_FN_U8: + return hist_field_u8(hist_field, elt, buffer, rbe, event); + case HIST_FIELD_FN_UMINUS: + return hist_field_unary_minus(hist_field, elt, buffer, rbe, event); + case HIST_FIELD_FN_MINUS: + return hist_field_minus(hist_field, elt, buffer, rbe, event); + case HIST_FIELD_FN_PLUS: + return hist_field_plus(hist_field, elt, buffer, rbe, event); + case HIST_FIELD_FN_DIV: + return hist_field_div(hist_field, elt, buffer, rbe, event); + case HIST_FIELD_FN_MULT: + return hist_field_mult(hist_field, elt, buffer, rbe, event); + case HIST_FIELD_FN_DIV_POWER2: + return div_by_power_of_two(hist_field, elt, buffer, rbe, event); + case HIST_FIELD_FN_DIV_NOT_POWER2: + return div_by_not_power_of_two(hist_field, elt, buffer, rbe, event); + case HIST_FIELD_FN_DIV_MULT_SHIFT: + return div_by_mult_and_shift(hist_field, elt, buffer, rbe, event); + case HIST_FIELD_FN_EXECNAME: + return hist_field_execname(hist_field, elt, buffer, rbe, event); + default: + return 0; + } +} + /* Convert a var that points to common_pid.execname to a string */ static void update_var_execname(struct hist_field *hist_field) { @@ -4197,7 +4289,7 @@ static void update_var_execname(struct hist_field *hist_field) kfree_const(hist_field->type); hist_field->type = "char[]"; - hist_field->fn = hist_field_execname; + hist_field->fn_num = HIST_FIELD_FN_EXECNAME; } static int create_var_field(struct hist_trigger_data *hist_data, @@ -4956,7 +5048,7 @@ static void hist_trigger_elt_update(struct hist_trigger_data *hist_data, for_each_hist_val_field(i, hist_data) { hist_field = hist_data->fields[i]; - hist_val = hist_field->fn(hist_field, elt, buffer, rbe, rec); + hist_val = hist_fn_call(hist_field, elt, buffer, rbe, rec); if (hist_field->flags & HIST_FIELD_FL_VAR) { var_idx = hist_field->var.idx; @@ -4987,7 +5079,7 @@ static void hist_trigger_elt_update(struct hist_trigger_data *hist_data, for_each_hist_key_field(i, hist_data) { hist_field = hist_data->fields[i]; if (hist_field->flags & HIST_FIELD_FL_VAR) { - hist_val = hist_field->fn(hist_field, elt, buffer, rbe, rec); + hist_val = hist_fn_call(hist_field, elt, buffer, rbe, rec); var_idx = hist_field->var.idx; tracing_map_set_var(elt, var_idx, hist_val); } @@ -5062,7 +5154,7 @@ static void event_hist_trigger(struct event_trigger_data *data, HIST_STACKTRACE_SKIP); key = entries; } else { - field_contents = key_field->fn(key_field, elt, buffer, rbe, rec); + field_contents = hist_fn_call(key_field, elt, buffer, rbe, rec); if (key_field->flags & HIST_FIELD_FL_STRING) { key = (void *)(unsigned long)field_contents; use_compound_key = true; diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c index a6621c52ce45..ae78c2d53c8a 100644 --- a/kernel/trace/trace_events_user.c +++ b/kernel/trace/trace_events_user.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include #include @@ -39,28 +40,69 @@ */ #define MAX_PAGE_ORDER 0 #define MAX_PAGES (1 << MAX_PAGE_ORDER) -#define MAX_EVENTS (MAX_PAGES * PAGE_SIZE) +#define MAX_BYTES (MAX_PAGES * PAGE_SIZE) +#define MAX_EVENTS (MAX_BYTES * 8) /* Limit how long of an event name plus args within the subsystem. */ #define MAX_EVENT_DESC 512 #define EVENT_NAME(user_event) ((user_event)->tracepoint.name) #define MAX_FIELD_ARRAY_SIZE 1024 -#define MAX_FIELD_ARG_NAME 256 -static char *register_page_data; +/* + * The MAP_STATUS_* macros are used for taking a index and determining the + * appropriate byte and the bit in the byte to set/reset for an event. + * + * The lower 3 bits of the index decide which bit to set. + * The remaining upper bits of the index decide which byte to use for the bit. + * + * This is used when an event has a probe attached/removed to reflect live + * status of the event wanting tracing or not to user-programs via shared + * memory maps. + */ +#define MAP_STATUS_BYTE(index) ((index) >> 3) +#define MAP_STATUS_MASK(index) BIT((index) & 7) -static DEFINE_MUTEX(reg_mutex); -static DEFINE_HASHTABLE(register_table, 4); -static DECLARE_BITMAP(page_bitmap, MAX_EVENTS); +/* + * Internal bits (kernel side only) to keep track of connected probes: + * These are used when status is requested in text form about an event. These + * bits are compared against an internal byte on the event to determine which + * probes to print out to the user. + * + * These do not reflect the mapped bytes between the user and kernel space. + */ +#define EVENT_STATUS_FTRACE BIT(0) +#define EVENT_STATUS_PERF BIT(1) +#define EVENT_STATUS_OTHER BIT(7) + +/* + * Stores the pages, tables, and locks for a group of events. + * Each logical grouping of events has its own group, with a + * matching page for status checks within user programs. This + * allows for isolation of events to user programs by various + * means. + */ +struct user_event_group { + struct page *pages; + char *register_page_data; + char *system_name; + struct hlist_node node; + struct mutex reg_mutex; + DECLARE_HASHTABLE(register_table, 8); + DECLARE_BITMAP(page_bitmap, MAX_EVENTS); +}; + +/* Group for init_user_ns mapping, top-most group */ +static struct user_event_group *init_group; /* * Stores per-event properties, as users register events * within a file a user_event might be created if it does not * already exist. These are globally used and their lifetime * is tied to the refcnt member. These cannot go away until the - * refcnt reaches zero. + * refcnt reaches one. */ struct user_event { + struct user_event_group *group; struct tracepoint tracepoint; struct trace_event_call call; struct trace_event_class class; @@ -68,10 +110,11 @@ struct user_event { struct hlist_node node; struct list_head fields; struct list_head validators; - atomic_t refcnt; + refcount_t refcnt; int index; int flags; int min_size; + char status; }; /* @@ -86,6 +129,11 @@ struct user_event_refs { struct user_event *events[]; }; +struct user_event_file_info { + struct user_event_group *group; + struct user_event_refs *refs; +}; + #define VALIDATOR_ENSURE_NULL (1 << 0) #define VALIDATOR_REL (1 << 1) @@ -98,7 +146,8 @@ struct user_event_validator { typedef void (*user_event_func_t) (struct user_event *user, struct iov_iter *i, void *tpdata, bool *faulted); -static int user_event_parse(char *name, char *args, char *flags, +static int user_event_parse(struct user_event_group *group, char *name, + char *args, char *flags, struct user_event **newuser); static u32 user_event_key(char *name) @@ -106,6 +155,144 @@ static u32 user_event_key(char *name) return jhash(name, strlen(name), 0); } +static void set_page_reservations(char *pages, bool set) +{ + int page; + + for (page = 0; page < MAX_PAGES; ++page) { + void *addr = pages + (PAGE_SIZE * page); + + if (set) + SetPageReserved(virt_to_page(addr)); + else + ClearPageReserved(virt_to_page(addr)); + } +} + +static void user_event_group_destroy(struct user_event_group *group) +{ + if (group->register_page_data) + set_page_reservations(group->register_page_data, false); + + if (group->pages) + __free_pages(group->pages, MAX_PAGE_ORDER); + + kfree(group->system_name); + kfree(group); +} + +static char *user_event_group_system_name(struct user_namespace *user_ns) +{ + char *system_name; + int len = sizeof(USER_EVENTS_SYSTEM) + 1; + + if (user_ns != &init_user_ns) { + /* + * Unexpected at this point: + * We only currently support init_user_ns. + * When we enable more, this will trigger a failure so log. + */ + pr_warn("user_events: Namespace other than init_user_ns!\n"); + return NULL; + } + + system_name = kmalloc(len, GFP_KERNEL); + + if (!system_name) + return NULL; + + snprintf(system_name, len, "%s", USER_EVENTS_SYSTEM); + + return system_name; +} + +static inline struct user_event_group +*user_event_group_from_user_ns(struct user_namespace *user_ns) +{ + if (user_ns == &init_user_ns) + return init_group; + + return NULL; +} + +static struct user_event_group *current_user_event_group(void) +{ + struct user_namespace *user_ns = current_user_ns(); + struct user_event_group *group = NULL; + + while (user_ns) { + group = user_event_group_from_user_ns(user_ns); + + if (group) + break; + + user_ns = user_ns->parent; + } + + return group; +} + +static struct user_event_group +*user_event_group_create(struct user_namespace *user_ns) +{ + struct user_event_group *group; + + group = kzalloc(sizeof(*group), GFP_KERNEL); + + if (!group) + return NULL; + + group->system_name = user_event_group_system_name(user_ns); + + if (!group->system_name) + goto error; + + group->pages = alloc_pages(GFP_KERNEL | __GFP_ZERO, MAX_PAGE_ORDER); + + if (!group->pages) + goto error; + + group->register_page_data = page_address(group->pages); + + set_page_reservations(group->register_page_data, true); + + /* Zero all bits beside 0 (which is reserved for failures) */ + bitmap_zero(group->page_bitmap, MAX_EVENTS); + set_bit(0, group->page_bitmap); + + mutex_init(&group->reg_mutex); + hash_init(group->register_table); + + return group; +error: + if (group) + user_event_group_destroy(group); + + return NULL; +}; + +static __always_inline +void user_event_register_set(struct user_event *user) +{ + int i = user->index; + + user->group->register_page_data[MAP_STATUS_BYTE(i)] |= MAP_STATUS_MASK(i); +} + +static __always_inline +void user_event_register_clear(struct user_event *user) +{ + int i = user->index; + + user->group->register_page_data[MAP_STATUS_BYTE(i)] &= ~MAP_STATUS_MASK(i); +} + +static __always_inline __must_check +bool user_event_last_ref(struct user_event *user) +{ + return refcount_read(&user->refcnt) == 1; +} + static __always_inline __must_check size_t copy_nofault(void *addr, size_t bytes, struct iov_iter *i) { @@ -141,7 +328,8 @@ static struct list_head *user_event_get_fields(struct trace_event_call *call) * * Upon success user_event has its ref count increased by 1. */ -static int user_event_parse_cmd(char *raw_command, struct user_event **newuser) +static int user_event_parse_cmd(struct user_event_group *group, + char *raw_command, struct user_event **newuser) { char *name = raw_command; char *args = strpbrk(name, " "); @@ -155,7 +343,7 @@ static int user_event_parse_cmd(char *raw_command, struct user_event **newuser) if (flags) *flags++ = '\0'; - return user_event_parse(name, args, flags, newuser); + return user_event_parse(group, name, args, flags, newuser); } static int user_field_array_size(const char *type) @@ -277,7 +465,7 @@ static int user_event_add_field(struct user_event *user, const char *type, goto add_field; add_validator: - if (strstr(type, "char") != 0) + if (strstr(type, "char") != NULL) validator_flags |= VALIDATOR_ENSURE_NULL; validator = kmalloc(sizeof(*validator), GFP_KERNEL); @@ -458,7 +646,7 @@ static const char *user_field_format(const char *type) return "%d"; if (strcmp(type, "unsigned char") == 0) return "%u"; - if (strstr(type, "char[") != 0) + if (strstr(type, "char[") != NULL) return "%s"; /* Unknown, likely struct, allowed treat as 64-bit */ @@ -479,10 +667,52 @@ static bool user_field_is_dyn_string(const char *type, const char **str_func) return false; check: - return strstr(type, "char") != 0; + return strstr(type, "char") != NULL; } #define LEN_OR_ZERO (len ? len - pos : 0) +static int user_dyn_field_set_string(int argc, const char **argv, int *iout, + char *buf, int len, bool *colon) +{ + int pos = 0, i = *iout; + + *colon = false; + + for (; i < argc; ++i) { + if (i != *iout) + pos += snprintf(buf + pos, LEN_OR_ZERO, " "); + + pos += snprintf(buf + pos, LEN_OR_ZERO, "%s", argv[i]); + + if (strchr(argv[i], ';')) { + ++i; + *colon = true; + break; + } + } + + /* Actual set, advance i */ + if (len != 0) + *iout = i; + + return pos + 1; +} + +static int user_field_set_string(struct ftrace_event_field *field, + char *buf, int len, bool colon) +{ + int pos = 0; + + pos += snprintf(buf + pos, LEN_OR_ZERO, "%s", field->type); + pos += snprintf(buf + pos, LEN_OR_ZERO, " "); + pos += snprintf(buf + pos, LEN_OR_ZERO, "%s", field->name); + + if (colon) + pos += snprintf(buf + pos, LEN_OR_ZERO, ";"); + + return pos + 1; +} + static int user_event_set_print_fmt(struct user_event *user, char *buf, int len) { struct ftrace_event_field *field, *next; @@ -600,8 +830,8 @@ static int destroy_user_event(struct user_event *user) dyn_event_remove(&user->devent); - register_page_data[user->index] = 0; - clear_bit(user->index, page_bitmap); + user_event_register_clear(user); + clear_bit(user->index, user->group->page_bitmap); hash_del(&user->node); user_event_destroy_validators(user); @@ -612,16 +842,17 @@ static int destroy_user_event(struct user_event *user) return ret; } -static struct user_event *find_user_event(char *name, u32 *outkey) +static struct user_event *find_user_event(struct user_event_group *group, + char *name, u32 *outkey) { struct user_event *user; u32 key = user_event_key(name); *outkey = key; - hash_for_each_possible(register_table, user, node, key) + hash_for_each_possible(group->register_table, user, node, key) if (!strcmp(EVENT_NAME(user), name)) { - atomic_inc(&user->refcnt); + refcount_inc(&user->refcnt); return user; } @@ -779,7 +1010,12 @@ static void update_reg_page_for(struct user_event *user) rcu_read_unlock_sched(); } - register_page_data[user->index] = status; + if (status) + user_event_register_set(user); + else + user_event_register_clear(user); + + user->status = status; } /* @@ -835,17 +1071,18 @@ static int user_event_reg(struct trace_event_call *call, return ret; inc: - atomic_inc(&user->refcnt); + refcount_inc(&user->refcnt); update_reg_page_for(user); return 0; dec: update_reg_page_for(user); - atomic_dec(&user->refcnt); + refcount_dec(&user->refcnt); return 0; } static int user_event_create(const char *raw_command) { + struct user_event_group *group; struct user_event *user; char *name; int ret; @@ -861,14 +1098,19 @@ static int user_event_create(const char *raw_command) if (!name) return -ENOMEM; - mutex_lock(®_mutex); + group = current_user_event_group(); - ret = user_event_parse_cmd(name, &user); + if (!group) + return -ENOENT; + + mutex_lock(&group->reg_mutex); + + ret = user_event_parse_cmd(group, name, &user); if (!ret) - atomic_dec(&user->refcnt); + refcount_dec(&user->refcnt); - mutex_unlock(®_mutex); + mutex_unlock(&group->reg_mutex); if (ret) kfree(name); @@ -910,14 +1152,14 @@ static bool user_event_is_busy(struct dyn_event *ev) { struct user_event *user = container_of(ev, struct user_event, devent); - return atomic_read(&user->refcnt) != 0; + return !user_event_last_ref(user); } static int user_event_free(struct dyn_event *ev) { struct user_event *user = container_of(ev, struct user_event, devent); - if (atomic_read(&user->refcnt) != 0) + if (!user_event_last_ref(user)) return -EBUSY; return destroy_user_event(user); @@ -926,49 +1168,35 @@ static int user_event_free(struct dyn_event *ev) static bool user_field_match(struct ftrace_event_field *field, int argc, const char **argv, int *iout) { - char *field_name, *arg_name; - int len, pos, i = *iout; + char *field_name = NULL, *dyn_field_name = NULL; bool colon = false, match = false; + int dyn_len, len; - if (i >= argc) + if (*iout >= argc) return false; - len = MAX_FIELD_ARG_NAME; - field_name = kmalloc(len, GFP_KERNEL); - arg_name = kmalloc(len, GFP_KERNEL); + dyn_len = user_dyn_field_set_string(argc, argv, iout, dyn_field_name, + 0, &colon); - if (!arg_name || !field_name) + len = user_field_set_string(field, field_name, 0, colon); + + if (dyn_len != len) + return false; + + dyn_field_name = kmalloc(dyn_len, GFP_KERNEL); + field_name = kmalloc(len, GFP_KERNEL); + + if (!dyn_field_name || !field_name) goto out; - pos = 0; + user_dyn_field_set_string(argc, argv, iout, dyn_field_name, + dyn_len, &colon); - for (; i < argc; ++i) { - if (i != *iout) - pos += snprintf(arg_name + pos, len - pos, " "); + user_field_set_string(field, field_name, len, colon); - pos += snprintf(arg_name + pos, len - pos, argv[i]); - - if (strchr(argv[i], ';')) { - ++i; - colon = true; - break; - } - } - - pos = 0; - - pos += snprintf(field_name + pos, len - pos, field->type); - pos += snprintf(field_name + pos, len - pos, " "); - pos += snprintf(field_name + pos, len - pos, field->name); - - if (colon) - pos += snprintf(field_name + pos, len - pos, ";"); - - *iout = i; - - match = strcmp(arg_name, field_name) == 0; + match = strcmp(dyn_field_name, field_name) == 0; out: - kfree(arg_name); + kfree(dyn_field_name); kfree(field_name); return match; @@ -1036,7 +1264,8 @@ static int user_event_trace_register(struct user_event *user) * The name buffer lifetime is owned by this method for success cases only. * Upon success the returned user_event has its ref count increased by 1. */ -static int user_event_parse(char *name, char *args, char *flags, +static int user_event_parse(struct user_event_group *group, char *name, + char *args, char *flags, struct user_event **newuser) { int ret; @@ -1046,7 +1275,7 @@ static int user_event_parse(char *name, char *args, char *flags, /* Prevent dyn_event from racing */ mutex_lock(&event_mutex); - user = find_user_event(name, &key); + user = find_user_event(group, name, &key); mutex_unlock(&event_mutex); if (user) { @@ -1059,7 +1288,7 @@ static int user_event_parse(char *name, char *args, char *flags, return 0; } - index = find_first_zero_bit(page_bitmap, MAX_EVENTS); + index = find_first_zero_bit(group->page_bitmap, MAX_EVENTS); if (index == MAX_EVENTS) return -EMFILE; @@ -1073,6 +1302,7 @@ static int user_event_parse(char *name, char *args, char *flags, INIT_LIST_HEAD(&user->fields); INIT_LIST_HEAD(&user->validators); + user->group = group; user->tracepoint.name = name; ret = user_event_parse_fields(user, args); @@ -1091,8 +1321,8 @@ static int user_event_parse(char *name, char *args, char *flags, user->call.flags = TRACE_EVENT_FL_TRACEPOINT; user->call.tp = &user->tracepoint; user->call.event.funcs = &user_event_funcs; + user->class.system = group->system_name; - user->class.system = USER_EVENTS_SYSTEM; user->class.fields_array = user_event_fields_array; user->class.get_fields = user_event_get_fields; user->class.reg = user_event_reg; @@ -1110,13 +1340,13 @@ static int user_event_parse(char *name, char *args, char *flags, user->index = index; - /* Ensure we track ref */ - atomic_inc(&user->refcnt); + /* Ensure we track self ref and caller ref (2) */ + refcount_set(&user->refcnt, 2); dyn_event_init(&user->devent, &user_event_dops); dyn_event_add(&user->devent, &user->call); - set_bit(user->index, page_bitmap); - hash_add(register_table, &user->node, key); + set_bit(user->index, group->page_bitmap); + hash_add(group->register_table, &user->node, key); mutex_unlock(&event_mutex); @@ -1134,32 +1364,20 @@ static int user_event_parse(char *name, char *args, char *flags, /* * Deletes a previously created event if it is no longer being used. */ -static int delete_user_event(char *name) +static int delete_user_event(struct user_event_group *group, char *name) { u32 key; - int ret; - struct user_event *user = find_user_event(name, &key); + struct user_event *user = find_user_event(group, name, &key); if (!user) return -ENOENT; - /* Ensure we are the last ref */ - if (atomic_read(&user->refcnt) != 1) { - ret = -EBUSY; - goto put_ref; - } + refcount_dec(&user->refcnt); - ret = destroy_user_event(user); + if (!user_event_last_ref(user)) + return -EBUSY; - if (ret) - goto put_ref; - - return ret; -put_ref: - /* No longer have this ref */ - atomic_dec(&user->refcnt); - - return ret; + return destroy_user_event(user); } /* @@ -1167,6 +1385,7 @@ static int delete_user_event(char *name) */ static ssize_t user_events_write_core(struct file *file, struct iov_iter *i) { + struct user_event_file_info *info = file->private_data; struct user_event_refs *refs; struct user_event *user = NULL; struct tracepoint *tp; @@ -1178,7 +1397,7 @@ static ssize_t user_events_write_core(struct file *file, struct iov_iter *i) rcu_read_lock_sched(); - refs = rcu_dereference_sched(file->private_data); + refs = rcu_dereference_sched(info->refs); /* * The refs->events array is protected by RCU, and new items may be @@ -1236,6 +1455,28 @@ static ssize_t user_events_write_core(struct file *file, struct iov_iter *i) return ret; } +static int user_events_open(struct inode *node, struct file *file) +{ + struct user_event_group *group; + struct user_event_file_info *info; + + group = current_user_event_group(); + + if (!group) + return -ENOENT; + + info = kzalloc(sizeof(*info), GFP_KERNEL); + + if (!info) + return -ENOMEM; + + info->group = group; + + file->private_data = info; + + return 0; +} + static ssize_t user_events_write(struct file *file, const char __user *ubuf, size_t count, loff_t *ppos) { @@ -1245,7 +1486,8 @@ static ssize_t user_events_write(struct file *file, const char __user *ubuf, if (unlikely(*ppos != 0)) return -EFAULT; - if (unlikely(import_single_range(READ, (char *)ubuf, count, &iov, &i))) + if (unlikely(import_single_range(WRITE, (char __user *)ubuf, + count, &iov, &i))) return -EFAULT; return user_events_write_core(file, &i); @@ -1256,13 +1498,15 @@ static ssize_t user_events_write_iter(struct kiocb *kp, struct iov_iter *i) return user_events_write_core(kp->ki_filp, i); } -static int user_events_ref_add(struct file *file, struct user_event *user) +static int user_events_ref_add(struct user_event_file_info *info, + struct user_event *user) { + struct user_event_group *group = info->group; struct user_event_refs *refs, *new_refs; int i, size, count = 0; - refs = rcu_dereference_protected(file->private_data, - lockdep_is_held(®_mutex)); + refs = rcu_dereference_protected(info->refs, + lockdep_is_held(&group->reg_mutex)); if (refs) { count = refs->count; @@ -1286,9 +1530,9 @@ static int user_events_ref_add(struct file *file, struct user_event *user) new_refs->events[i] = user; - atomic_inc(&user->refcnt); + refcount_inc(&user->refcnt); - rcu_assign_pointer(file->private_data, new_refs); + rcu_assign_pointer(info->refs, new_refs); if (refs) kfree_rcu(refs, rcu); @@ -1309,13 +1553,24 @@ static long user_reg_get(struct user_reg __user *ureg, struct user_reg *kreg) if (size > PAGE_SIZE) return -E2BIG; - return copy_struct_from_user(kreg, sizeof(*kreg), ureg, size); + if (size < offsetofend(struct user_reg, write_index)) + return -EINVAL; + + ret = copy_struct_from_user(kreg, sizeof(*kreg), ureg, size); + + if (ret) + return ret; + + kreg->size = size; + + return 0; } /* * Registers a user_event on behalf of a user process. */ -static long user_events_ioctl_reg(struct file *file, unsigned long uarg) +static long user_events_ioctl_reg(struct user_event_file_info *info, + unsigned long uarg) { struct user_reg __user *ureg = (struct user_reg __user *)uarg; struct user_reg reg; @@ -1336,24 +1591,24 @@ static long user_events_ioctl_reg(struct file *file, unsigned long uarg) return ret; } - ret = user_event_parse_cmd(name, &user); + ret = user_event_parse_cmd(info->group, name, &user); if (ret) { kfree(name); return ret; } - ret = user_events_ref_add(file, user); + ret = user_events_ref_add(info, user); /* No longer need parse ref, ref_add either worked or not */ - atomic_dec(&user->refcnt); + refcount_dec(&user->refcnt); /* Positive number is index and valid */ if (ret < 0) return ret; put_user((u32)ret, &ureg->write_index); - put_user(user->index, &ureg->status_index); + put_user(user->index, &ureg->status_bit); return 0; } @@ -1361,7 +1616,8 @@ static long user_events_ioctl_reg(struct file *file, unsigned long uarg) /* * Deletes a user_event on behalf of a user process. */ -static long user_events_ioctl_del(struct file *file, unsigned long uarg) +static long user_events_ioctl_del(struct user_event_file_info *info, + unsigned long uarg) { void __user *ubuf = (void __user *)uarg; char *name; @@ -1374,7 +1630,7 @@ static long user_events_ioctl_del(struct file *file, unsigned long uarg) /* event_mutex prevents dyn_event from racing */ mutex_lock(&event_mutex); - ret = delete_user_event(name); + ret = delete_user_event(info->group, name); mutex_unlock(&event_mutex); kfree(name); @@ -1388,19 +1644,21 @@ static long user_events_ioctl_del(struct file *file, unsigned long uarg) static long user_events_ioctl(struct file *file, unsigned int cmd, unsigned long uarg) { + struct user_event_file_info *info = file->private_data; + struct user_event_group *group = info->group; long ret = -ENOTTY; switch (cmd) { case DIAG_IOCSREG: - mutex_lock(®_mutex); - ret = user_events_ioctl_reg(file, uarg); - mutex_unlock(®_mutex); + mutex_lock(&group->reg_mutex); + ret = user_events_ioctl_reg(info, uarg); + mutex_unlock(&group->reg_mutex); break; case DIAG_IOCSDEL: - mutex_lock(®_mutex); - ret = user_events_ioctl_del(file, uarg); - mutex_unlock(®_mutex); + mutex_lock(&group->reg_mutex); + ret = user_events_ioctl_del(info, uarg); + mutex_unlock(&group->reg_mutex); break; } @@ -1412,17 +1670,24 @@ static long user_events_ioctl(struct file *file, unsigned int cmd, */ static int user_events_release(struct inode *node, struct file *file) { + struct user_event_file_info *info = file->private_data; + struct user_event_group *group; struct user_event_refs *refs; struct user_event *user; int i; + if (!info) + return -EINVAL; + + group = info->group; + /* * Ensure refs cannot change under any situation by taking the * register mutex during the final freeing of the references. */ - mutex_lock(®_mutex); + mutex_lock(&group->reg_mutex); - refs = file->private_data; + refs = info->refs; if (!refs) goto out; @@ -1436,37 +1701,56 @@ static int user_events_release(struct inode *node, struct file *file) user = refs->events[i]; if (user) - atomic_dec(&user->refcnt); + refcount_dec(&user->refcnt); } out: file->private_data = NULL; - mutex_unlock(®_mutex); + mutex_unlock(&group->reg_mutex); kfree(refs); + kfree(info); return 0; } static const struct file_operations user_data_fops = { + .open = user_events_open, .write = user_events_write, .write_iter = user_events_write_iter, .unlocked_ioctl = user_events_ioctl, .release = user_events_release, }; +static struct user_event_group *user_status_group(struct file *file) +{ + struct seq_file *m = file->private_data; + + if (!m) + return NULL; + + return m->private; +} + /* * Maps the shared page into the user process for checking if event is enabled. */ static int user_status_mmap(struct file *file, struct vm_area_struct *vma) { + char *pages; + struct user_event_group *group = user_status_group(file); unsigned long size = vma->vm_end - vma->vm_start; - if (size != MAX_EVENTS) + if (size != MAX_BYTES) return -EINVAL; + if (!group) + return -EINVAL; + + pages = group->register_page_data; + return remap_pfn_range(vma, vma->vm_start, - virt_to_phys(register_page_data) >> PAGE_SHIFT, + virt_to_phys(pages) >> PAGE_SHIFT, size, vm_get_page_prot(VM_READ)); } @@ -1490,14 +1774,18 @@ static void user_seq_stop(struct seq_file *m, void *p) static int user_seq_show(struct seq_file *m, void *p) { + struct user_event_group *group = m->private; struct user_event *user; char status; int i, active = 0, busy = 0, flags; - mutex_lock(®_mutex); + if (!group) + return -EINVAL; - hash_for_each(register_table, i, user, node) { - status = register_page_data[user->index]; + mutex_lock(&group->reg_mutex); + + hash_for_each(group->register_table, i, user, node) { + status = user->status; flags = user->flags; seq_printf(m, "%d:%s", user->index, EVENT_NAME(user)); @@ -1520,7 +1808,7 @@ static int user_seq_show(struct seq_file *m, void *p) active++; } - mutex_unlock(®_mutex); + mutex_unlock(&group->reg_mutex); seq_puts(m, "\n"); seq_printf(m, "Active: %d\n", active); @@ -1539,7 +1827,24 @@ static const struct seq_operations user_seq_ops = { static int user_status_open(struct inode *node, struct file *file) { - return seq_open(file, &user_seq_ops); + struct user_event_group *group; + int ret; + + group = current_user_event_group(); + + if (!group) + return -ENOENT; + + ret = seq_open(file, &user_seq_ops); + + if (!ret) { + /* Chain group to seq_file */ + struct seq_file *m = file->private_data; + + m->private = group; + } + + return ret; } static const struct file_operations user_status_fops = { @@ -1580,42 +1885,21 @@ static int create_user_tracefs(void) return -ENODEV; } -static void set_page_reservations(bool set) -{ - int page; - - for (page = 0; page < MAX_PAGES; ++page) { - void *addr = register_page_data + (PAGE_SIZE * page); - - if (set) - SetPageReserved(virt_to_page(addr)); - else - ClearPageReserved(virt_to_page(addr)); - } -} - static int __init trace_events_user_init(void) { - struct page *pages; int ret; - /* Zero all bits beside 0 (which is reserved for failures) */ - bitmap_zero(page_bitmap, MAX_EVENTS); - set_bit(0, page_bitmap); + init_group = user_event_group_create(&init_user_ns); - pages = alloc_pages(GFP_KERNEL | __GFP_ZERO, MAX_PAGE_ORDER); - if (!pages) + if (!init_group) return -ENOMEM; - register_page_data = page_address(pages); - - set_page_reservations(true); ret = create_user_tracefs(); if (ret) { pr_warn("user_events could not register with tracefs\n"); - set_page_reservations(false); - __free_pages(pages, MAX_PAGE_ORDER); + user_event_group_destroy(init_group); + init_group = NULL; return ret; } diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c index 313439920a8c..78d536d3ff3d 100644 --- a/kernel/trace/trace_osnoise.c +++ b/kernel/trace/trace_osnoise.c @@ -1786,8 +1786,9 @@ static int start_per_cpu_kthreads(void) for_each_cpu(cpu, current_mask) { retval = start_kthread(cpu); if (retval) { + cpus_read_unlock(); stop_per_cpu_kthreads(); - break; + return retval; } } diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h index 3b3869ae8cfd..de38f1c03776 100644 --- a/kernel/trace/trace_probe.h +++ b/kernel/trace/trace_probe.h @@ -445,7 +445,8 @@ extern int traceprobe_define_arg_fields(struct trace_event_call *event_call, C(SAME_PROBE, "There is already the exact same probe event"),\ C(NO_EVENT_INFO, "This requires both group and event name to attach"),\ C(BAD_ATTACH_EVENT, "Attached event does not exist"),\ - C(BAD_ATTACH_ARG, "Attached event does not have this field"), + C(BAD_ATTACH_ARG, "Attached event does not have this field"),\ + C(NO_EP_FILTER, "No filter rule after 'if'"), #undef C #define C(a, b) TP_ERR_##a diff --git a/kernel/trace/tracing_map.c b/kernel/trace/tracing_map.c index 9901708ce6b8..c774e560f2f9 100644 --- a/kernel/trace/tracing_map.c +++ b/kernel/trace/tracing_map.c @@ -961,7 +961,7 @@ create_sort_entry(void *key, struct tracing_map_elt *elt) static void detect_dups(struct tracing_map_sort_entry **sort_entries, int n_entries, unsigned int key_size) { - unsigned int dups = 0, total_dups = 0; + unsigned int total_dups = 0; int i; void *key; @@ -974,11 +974,10 @@ static void detect_dups(struct tracing_map_sort_entry **sort_entries, key = sort_entries[0]->key; for (i = 1; i < n_entries; i++) { if (!memcmp(sort_entries[i]->key, key, key_size)) { - dups++; total_dups++; + total_dups++; continue; } key = sort_entries[i]->key; - dups = 0; } WARN_ONCE(total_dups > 0, diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c index 5c87206f144d..a644ecccc6a4 100644 --- a/kernel/tracepoint.c +++ b/kernel/tracepoint.c @@ -640,7 +640,6 @@ static void tp_module_going_check_quiescent(struct tracepoint *tp, void *priv) static int tracepoint_module_coming(struct module *mod) { struct tp_module *tp_mod; - int ret = 0; if (!mod->num_tracepoints) return 0; @@ -652,19 +651,18 @@ static int tracepoint_module_coming(struct module *mod) */ if (trace_module_has_bad_taint(mod)) return 0; - mutex_lock(&tracepoint_module_list_mutex); + tp_mod = kmalloc(sizeof(struct tp_module), GFP_KERNEL); - if (!tp_mod) { - ret = -ENOMEM; - goto end; - } + if (!tp_mod) + return -ENOMEM; tp_mod->mod = mod; + + mutex_lock(&tracepoint_module_list_mutex); list_add_tail(&tp_mod->list, &tracepoint_module_list); blocking_notifier_call_chain(&tracepoint_notify_list, MODULE_STATE_COMING, tp_mod); -end: mutex_unlock(&tracepoint_module_list_mutex); - return ret; + return 0; } static void tracepoint_module_going(struct module *mod) diff --git a/lib/Kconfig b/lib/Kconfig index 3ea8941ab18d..d628235f7934 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -531,6 +531,15 @@ config CPUMASK_OFFSTACK them on the stack. This is a bit more expensive, but avoids stack overflow. +config FORCE_NR_CPUS + bool "NR_CPUS is set to an actual number of CPUs" + depends on SMP + help + Say Yes if you have NR_CPUS set to an actual number of possible + CPUs in your system, not to a default value. This forces the core + code to rely on compile-time value and optimize kernel routines + better. + config CPU_RMAP bool depends on SMP diff --git a/lib/bitmap.c b/lib/bitmap.c index 488e6c3e5acc..1c81413c51f8 100644 --- a/lib/bitmap.c +++ b/lib/bitmap.c @@ -333,20 +333,32 @@ bool __bitmap_subset(const unsigned long *bitmap1, } EXPORT_SYMBOL(__bitmap_subset); +#define BITMAP_WEIGHT(FETCH, bits) \ +({ \ + unsigned int __bits = (bits), idx, w = 0; \ + \ + for (idx = 0; idx < __bits / BITS_PER_LONG; idx++) \ + w += hweight_long(FETCH); \ + \ + if (__bits % BITS_PER_LONG) \ + w += hweight_long((FETCH) & BITMAP_LAST_WORD_MASK(__bits)); \ + \ + w; \ +}) + unsigned int __bitmap_weight(const unsigned long *bitmap, unsigned int bits) { - unsigned int k, lim = bits/BITS_PER_LONG, w = 0; - - for (k = 0; k < lim; k++) - w += hweight_long(bitmap[k]); - - if (bits % BITS_PER_LONG) - w += hweight_long(bitmap[k] & BITMAP_LAST_WORD_MASK(bits)); - - return w; + return BITMAP_WEIGHT(bitmap[idx], bits); } EXPORT_SYMBOL(__bitmap_weight); +unsigned int __bitmap_weight_and(const unsigned long *bitmap1, + const unsigned long *bitmap2, unsigned int bits) +{ + return BITMAP_WEIGHT(bitmap1[idx] & bitmap2[idx], bits); +} +EXPORT_SYMBOL(__bitmap_weight_and); + void __bitmap_set(unsigned long *map, unsigned int start, int len) { unsigned long *p = map + BIT_WORD(start); @@ -953,37 +965,7 @@ static int bitmap_pos_to_ord(const unsigned long *buf, unsigned int pos, unsigne if (pos >= nbits || !test_bit(pos, buf)) return -1; - return __bitmap_weight(buf, pos); -} - -/** - * bitmap_ord_to_pos - find position of n-th set bit in bitmap - * @buf: pointer to bitmap - * @ord: ordinal bit position (n-th set bit, n >= 0) - * @nbits: number of valid bit positions in @buf - * - * Map the ordinal offset of bit @ord in @buf to its position in @buf. - * Value of @ord should be in range 0 <= @ord < weight(buf). If @ord - * >= weight(buf), returns @nbits. - * - * If for example, just bits 4 through 7 are set in @buf, then @ord - * values 0 through 3 will get mapped to 4 through 7, respectively, - * and all other @ord values returns @nbits. When @ord value 3 - * gets mapped to (returns) @pos value 7 in this example, that means - * that the 3rd set bit (starting with 0th) is at position 7 in @buf. - * - * The bit positions 0 through @nbits-1 are valid positions in @buf. - */ -unsigned int bitmap_ord_to_pos(const unsigned long *buf, unsigned int ord, unsigned int nbits) -{ - unsigned int pos; - - for (pos = find_first_bit(buf, nbits); - pos < nbits && ord; - pos = find_next_bit(buf, nbits, pos + 1)) - ord--; - - return pos; + return bitmap_weight(buf, pos); } /** @@ -1035,7 +1017,7 @@ void bitmap_remap(unsigned long *dst, const unsigned long *src, if (n < 0 || w == 0) set_bit(oldbit, dst); /* identity map */ else - set_bit(bitmap_ord_to_pos(new, n % w, nbits), dst); + set_bit(find_nth_bit(new, nbits, n % w), dst); } } EXPORT_SYMBOL(bitmap_remap); @@ -1074,7 +1056,7 @@ int bitmap_bitremap(int oldbit, const unsigned long *old, if (n < 0 || w == 0) return oldbit; else - return bitmap_ord_to_pos(new, n % w, bits); + return find_nth_bit(new, bits, n % w); } EXPORT_SYMBOL(bitmap_bitremap); @@ -1198,7 +1180,7 @@ void bitmap_onto(unsigned long *dst, const unsigned long *orig, * The following code is a more efficient, but less * obvious, equivalent to the loop: * for (m = 0; m < bitmap_weight(relmap, bits); m++) { - * n = bitmap_ord_to_pos(orig, m, bits); + * n = find_nth_bit(orig, bits, m); * if (test_bit(m, orig)) * set_bit(n, dst); * } diff --git a/lib/cpumask.c b/lib/cpumask.c index f0ae119be8c4..c7c392514fd3 100644 --- a/lib/cpumask.c +++ b/lib/cpumask.c @@ -128,23 +128,21 @@ unsigned int cpumask_local_spread(unsigned int i, int node) i %= num_online_cpus(); if (node == NUMA_NO_NODE) { - for_each_cpu(cpu, cpu_online_mask) - if (i-- == 0) - return cpu; + cpu = cpumask_nth(i, cpu_online_mask); + if (cpu < nr_cpu_ids) + return cpu; } else { /* NUMA first. */ - for_each_cpu_and(cpu, cpumask_of_node(node), cpu_online_mask) - if (i-- == 0) - return cpu; + cpu = cpumask_nth_and(i, cpu_online_mask, cpumask_of_node(node)); + if (cpu < nr_cpu_ids) + return cpu; - for_each_cpu(cpu, cpu_online_mask) { - /* Skip NUMA nodes, done above. */ - if (cpumask_test_cpu(cpu, cpumask_of_node(node))) - continue; + i -= cpumask_weight_and(cpu_online_mask, cpumask_of_node(node)); - if (i-- == 0) - return cpu; - } + /* Skip NUMA nodes, done above. */ + cpu = cpumask_nth_andnot(i, cpu_online_mask, cpumask_of_node(node)); + if (cpu < nr_cpu_ids) + return cpu; } BUG(); } @@ -168,10 +166,8 @@ unsigned int cpumask_any_and_distribute(const struct cpumask *src1p, /* NOTE: our first selection will skip 0. */ prev = __this_cpu_read(distribute_cpu_mask_prev); - next = cpumask_next_and(prev, src1p, src2p); - if (next >= nr_cpu_ids) - next = cpumask_first_and(src1p, src2p); - + next = find_next_and_bit_wrap(cpumask_bits(src1p), cpumask_bits(src2p), + nr_cpumask_bits, prev + 1); if (next < nr_cpu_ids) __this_cpu_write(distribute_cpu_mask_prev, next); @@ -185,11 +181,7 @@ unsigned int cpumask_any_distribute(const struct cpumask *srcp) /* NOTE: our first selection will skip 0. */ prev = __this_cpu_read(distribute_cpu_mask_prev); - - next = cpumask_next(prev, srcp); - if (next >= nr_cpu_ids) - next = cpumask_first(srcp); - + next = find_next_bit_wrap(cpumask_bits(srcp), nr_cpumask_bits, prev + 1); if (next < nr_cpu_ids) __this_cpu_write(distribute_cpu_mask_prev, next); diff --git a/lib/cpumask_kunit.c b/lib/cpumask_kunit.c index ecbeec72221e..d1fc6ece21f3 100644 --- a/lib/cpumask_kunit.c +++ b/lib/cpumask_kunit.c @@ -33,6 +33,19 @@ KUNIT_EXPECT_EQ_MSG((test), nr_cpu_ids - mask_weight, iter, MASK_MSG(mask)); \ } while (0) +#define EXPECT_FOR_EACH_CPU_OP_EQ(test, op, mask1, mask2) \ + do { \ + const cpumask_t *m1 = (mask1); \ + const cpumask_t *m2 = (mask2); \ + int weight; \ + int cpu, iter = 0; \ + cpumask_##op(&mask_tmp, m1, m2); \ + weight = cpumask_weight(&mask_tmp); \ + for_each_cpu_##op(cpu, mask1, mask2) \ + iter++; \ + KUNIT_EXPECT_EQ((test), weight, iter); \ + } while (0) + #define EXPECT_FOR_EACH_CPU_WRAP_EQ(test, mask) \ do { \ const cpumask_t *m = (mask); \ @@ -54,6 +67,7 @@ static cpumask_t mask_empty; static cpumask_t mask_all; +static cpumask_t mask_tmp; static void test_cpumask_weight(struct kunit *test) { @@ -101,10 +115,15 @@ static void test_cpumask_iterators(struct kunit *test) EXPECT_FOR_EACH_CPU_EQ(test, &mask_empty); EXPECT_FOR_EACH_CPU_NOT_EQ(test, &mask_empty); EXPECT_FOR_EACH_CPU_WRAP_EQ(test, &mask_empty); + EXPECT_FOR_EACH_CPU_OP_EQ(test, and, &mask_empty, &mask_empty); + EXPECT_FOR_EACH_CPU_OP_EQ(test, and, cpu_possible_mask, &mask_empty); + EXPECT_FOR_EACH_CPU_OP_EQ(test, andnot, &mask_empty, &mask_empty); EXPECT_FOR_EACH_CPU_EQ(test, cpu_possible_mask); EXPECT_FOR_EACH_CPU_NOT_EQ(test, cpu_possible_mask); EXPECT_FOR_EACH_CPU_WRAP_EQ(test, cpu_possible_mask); + EXPECT_FOR_EACH_CPU_OP_EQ(test, and, cpu_possible_mask, cpu_possible_mask); + EXPECT_FOR_EACH_CPU_OP_EQ(test, andnot, cpu_possible_mask, &mask_empty); } static void test_cpumask_iterators_builtin(struct kunit *test) diff --git a/lib/find_bit.c b/lib/find_bit.c index 1b8e4b2a9cba..18bc0a7ac8ee 100644 --- a/lib/find_bit.c +++ b/lib/find_bit.c @@ -19,57 +19,78 @@ #include #include -#if !defined(find_next_bit) || !defined(find_next_zero_bit) || \ - !defined(find_next_bit_le) || !defined(find_next_zero_bit_le) || \ - !defined(find_next_and_bit) /* - * This is a common helper function for find_next_bit, find_next_zero_bit, and - * find_next_and_bit. The differences are: - * - The "invert" argument, which is XORed with each fetched word before - * searching it for one bits. - * - The optional "addr2", which is anded with "addr1" if present. + * Common helper for find_bit() function family + * @FETCH: The expression that fetches and pre-processes each word of bitmap(s) + * @MUNGE: The expression that post-processes a word containing found bit (may be empty) + * @size: The bitmap size in bits */ -unsigned long _find_next_bit(const unsigned long *addr1, - const unsigned long *addr2, unsigned long nbits, - unsigned long start, unsigned long invert, unsigned long le) -{ - unsigned long tmp, mask; +#define FIND_FIRST_BIT(FETCH, MUNGE, size) \ +({ \ + unsigned long idx, val, sz = (size); \ + \ + for (idx = 0; idx * BITS_PER_LONG < sz; idx++) { \ + val = (FETCH); \ + if (val) { \ + sz = min(idx * BITS_PER_LONG + __ffs(MUNGE(val)), sz); \ + break; \ + } \ + } \ + \ + sz; \ +}) - if (unlikely(start >= nbits)) - return nbits; +/* + * Common helper for find_next_bit() function family + * @FETCH: The expression that fetches and pre-processes each word of bitmap(s) + * @MUNGE: The expression that post-processes a word containing found bit (may be empty) + * @size: The bitmap size in bits + * @start: The bitnumber to start searching at + */ +#define FIND_NEXT_BIT(FETCH, MUNGE, size, start) \ +({ \ + unsigned long mask, idx, tmp, sz = (size), __start = (start); \ + \ + if (unlikely(__start >= sz)) \ + goto out; \ + \ + mask = MUNGE(BITMAP_FIRST_WORD_MASK(__start)); \ + idx = __start / BITS_PER_LONG; \ + \ + for (tmp = (FETCH) & mask; !tmp; tmp = (FETCH)) { \ + if ((idx + 1) * BITS_PER_LONG >= sz) \ + goto out; \ + idx++; \ + } \ + \ + sz = min(idx * BITS_PER_LONG + __ffs(MUNGE(tmp)), sz); \ +out: \ + sz; \ +}) - tmp = addr1[start / BITS_PER_LONG]; - if (addr2) - tmp &= addr2[start / BITS_PER_LONG]; - tmp ^= invert; - - /* Handle 1st word. */ - mask = BITMAP_FIRST_WORD_MASK(start); - if (le) - mask = swab(mask); - - tmp &= mask; - - start = round_down(start, BITS_PER_LONG); - - while (!tmp) { - start += BITS_PER_LONG; - if (start >= nbits) - return nbits; - - tmp = addr1[start / BITS_PER_LONG]; - if (addr2) - tmp &= addr2[start / BITS_PER_LONG]; - tmp ^= invert; - } - - if (le) - tmp = swab(tmp); - - return min(start + __ffs(tmp), nbits); -} -EXPORT_SYMBOL(_find_next_bit); -#endif +#define FIND_NTH_BIT(FETCH, size, num) \ +({ \ + unsigned long sz = (size), nr = (num), idx, w, tmp; \ + \ + for (idx = 0; (idx + 1) * BITS_PER_LONG <= sz; idx++) { \ + if (idx * BITS_PER_LONG + nr >= sz) \ + goto out; \ + \ + tmp = (FETCH); \ + w = hweight_long(tmp); \ + if (w > nr) \ + goto found; \ + \ + nr -= w; \ + } \ + \ + if (sz % BITS_PER_LONG) \ + tmp = (FETCH) & BITMAP_LAST_WORD_MASK(sz); \ +found: \ + sz = min(idx * BITS_PER_LONG + fns(tmp, nr), sz); \ +out: \ + sz; \ +}) #ifndef find_first_bit /* @@ -77,14 +98,7 @@ EXPORT_SYMBOL(_find_next_bit); */ unsigned long _find_first_bit(const unsigned long *addr, unsigned long size) { - unsigned long idx; - - for (idx = 0; idx * BITS_PER_LONG < size; idx++) { - if (addr[idx]) - return min(idx * BITS_PER_LONG + __ffs(addr[idx]), size); - } - - return size; + return FIND_FIRST_BIT(addr[idx], /* nop */, size); } EXPORT_SYMBOL(_find_first_bit); #endif @@ -97,15 +111,7 @@ unsigned long _find_first_and_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size) { - unsigned long idx, val; - - for (idx = 0; idx * BITS_PER_LONG < size; idx++) { - val = addr1[idx] & addr2[idx]; - if (val) - return min(idx * BITS_PER_LONG + __ffs(val), size); - } - - return size; + return FIND_FIRST_BIT(addr1[idx] & addr2[idx], /* nop */, size); } EXPORT_SYMBOL(_find_first_and_bit); #endif @@ -116,18 +122,66 @@ EXPORT_SYMBOL(_find_first_and_bit); */ unsigned long _find_first_zero_bit(const unsigned long *addr, unsigned long size) { - unsigned long idx; - - for (idx = 0; idx * BITS_PER_LONG < size; idx++) { - if (addr[idx] != ~0UL) - return min(idx * BITS_PER_LONG + ffz(addr[idx]), size); - } - - return size; + return FIND_FIRST_BIT(~addr[idx], /* nop */, size); } EXPORT_SYMBOL(_find_first_zero_bit); #endif +#ifndef find_next_bit +unsigned long _find_next_bit(const unsigned long *addr, unsigned long nbits, unsigned long start) +{ + return FIND_NEXT_BIT(addr[idx], /* nop */, nbits, start); +} +EXPORT_SYMBOL(_find_next_bit); +#endif + +unsigned long __find_nth_bit(const unsigned long *addr, unsigned long size, unsigned long n) +{ + return FIND_NTH_BIT(addr[idx], size, n); +} +EXPORT_SYMBOL(__find_nth_bit); + +unsigned long __find_nth_and_bit(const unsigned long *addr1, const unsigned long *addr2, + unsigned long size, unsigned long n) +{ + return FIND_NTH_BIT(addr1[idx] & addr2[idx], size, n); +} +EXPORT_SYMBOL(__find_nth_and_bit); + +unsigned long __find_nth_andnot_bit(const unsigned long *addr1, const unsigned long *addr2, + unsigned long size, unsigned long n) +{ + return FIND_NTH_BIT(addr1[idx] & ~addr2[idx], size, n); +} +EXPORT_SYMBOL(__find_nth_andnot_bit); + +#ifndef find_next_and_bit +unsigned long _find_next_and_bit(const unsigned long *addr1, const unsigned long *addr2, + unsigned long nbits, unsigned long start) +{ + return FIND_NEXT_BIT(addr1[idx] & addr2[idx], /* nop */, nbits, start); +} +EXPORT_SYMBOL(_find_next_and_bit); +#endif + +#ifndef find_next_andnot_bit +unsigned long _find_next_andnot_bit(const unsigned long *addr1, const unsigned long *addr2, + unsigned long nbits, unsigned long start) +{ + return FIND_NEXT_BIT(addr1[idx] & ~addr2[idx], /* nop */, nbits, start); +} +EXPORT_SYMBOL(_find_next_andnot_bit); +#endif + +#ifndef find_next_zero_bit +unsigned long _find_next_zero_bit(const unsigned long *addr, unsigned long nbits, + unsigned long start) +{ + return FIND_NEXT_BIT(~addr[idx], /* nop */, nbits, start); +} +EXPORT_SYMBOL(_find_next_zero_bit); +#endif + #ifndef find_last_bit unsigned long _find_last_bit(const unsigned long *addr, unsigned long size) { @@ -161,3 +215,38 @@ unsigned long find_next_clump8(unsigned long *clump, const unsigned long *addr, return offset; } EXPORT_SYMBOL(find_next_clump8); + +#ifdef __BIG_ENDIAN + +#ifndef find_first_zero_bit_le +/* + * Find the first cleared bit in an LE memory region. + */ +unsigned long _find_first_zero_bit_le(const unsigned long *addr, unsigned long size) +{ + return FIND_FIRST_BIT(~addr[idx], swab, size); +} +EXPORT_SYMBOL(_find_first_zero_bit_le); + +#endif + +#ifndef find_next_zero_bit_le +unsigned long _find_next_zero_bit_le(const unsigned long *addr, + unsigned long size, unsigned long offset) +{ + return FIND_NEXT_BIT(~addr[idx], swab, size, offset); +} +EXPORT_SYMBOL(_find_next_zero_bit_le); +#endif + +#ifndef find_next_bit_le +unsigned long _find_next_bit_le(const unsigned long *addr, + unsigned long size, unsigned long offset) +{ + return FIND_NEXT_BIT(addr[idx], swab, size, offset); +} +EXPORT_SYMBOL(_find_next_bit_le); + +#endif + +#endif /* __BIG_ENDIAN */ diff --git a/lib/find_bit_benchmark.c b/lib/find_bit_benchmark.c index db904b57d4b8..10754586403b 100644 --- a/lib/find_bit_benchmark.c +++ b/lib/find_bit_benchmark.c @@ -115,6 +115,22 @@ static int __init test_find_last_bit(const void *bitmap, unsigned long len) return 0; } +static int __init test_find_nth_bit(const unsigned long *bitmap, unsigned long len) +{ + unsigned long l, n, w = bitmap_weight(bitmap, len); + ktime_t time; + + time = ktime_get(); + for (n = 0; n < w; n++) { + l = find_nth_bit(bitmap, len, n); + WARN_ON(l >= len); + } + time = ktime_get() - time; + pr_err("find_nth_bit: %18llu ns, %6ld iterations\n", time, w); + + return 0; +} + static int __init test_find_next_and_bit(const void *bitmap, const void *bitmap2, unsigned long len) { @@ -142,6 +158,7 @@ static int __init find_bit_test(void) test_find_next_bit(bitmap, BITMAP_LEN); test_find_next_zero_bit(bitmap, BITMAP_LEN); test_find_last_bit(bitmap, BITMAP_LEN); + test_find_nth_bit(bitmap, BITMAP_LEN / 10); /* * test_find_first_bit() may take some time, so @@ -164,6 +181,7 @@ static int __init find_bit_test(void) test_find_next_bit(bitmap, BITMAP_LEN); test_find_next_zero_bit(bitmap, BITMAP_LEN); test_find_last_bit(bitmap, BITMAP_LEN); + test_find_nth_bit(bitmap, BITMAP_LEN); test_find_first_bit(bitmap, BITMAP_LEN); test_find_first_and_bit(bitmap, bitmap2, BITMAP_LEN); test_find_next_and_bit(bitmap, bitmap2, BITMAP_LEN); diff --git a/lib/test_bitmap.c b/lib/test_bitmap.c index 98754ff9fe68..a8005ad3bd58 100644 --- a/lib/test_bitmap.c +++ b/lib/test_bitmap.c @@ -16,6 +16,8 @@ #include "../tools/testing/selftests/kselftest_module.h" +#define EXP1_IN_BITS (sizeof(exp1) * 8) + KSTM_MODULE_GLOBALS(); static char pbl_buffer[PAGE_SIZE] __initdata; @@ -219,6 +221,47 @@ static void __init test_zero_clear(void) expect_eq_pbl("", bmap, 1024); } +static void __init test_find_nth_bit(void) +{ + unsigned long b, bit, cnt = 0; + DECLARE_BITMAP(bmap, 64 * 3); + + bitmap_zero(bmap, 64 * 3); + __set_bit(10, bmap); + __set_bit(20, bmap); + __set_bit(30, bmap); + __set_bit(40, bmap); + __set_bit(50, bmap); + __set_bit(60, bmap); + __set_bit(80, bmap); + __set_bit(123, bmap); + + expect_eq_uint(10, find_nth_bit(bmap, 64 * 3, 0)); + expect_eq_uint(20, find_nth_bit(bmap, 64 * 3, 1)); + expect_eq_uint(30, find_nth_bit(bmap, 64 * 3, 2)); + expect_eq_uint(40, find_nth_bit(bmap, 64 * 3, 3)); + expect_eq_uint(50, find_nth_bit(bmap, 64 * 3, 4)); + expect_eq_uint(60, find_nth_bit(bmap, 64 * 3, 5)); + expect_eq_uint(80, find_nth_bit(bmap, 64 * 3, 6)); + expect_eq_uint(123, find_nth_bit(bmap, 64 * 3, 7)); + expect_eq_uint(64 * 3, find_nth_bit(bmap, 64 * 3, 8)); + + expect_eq_uint(10, find_nth_bit(bmap, 64 * 3 - 1, 0)); + expect_eq_uint(20, find_nth_bit(bmap, 64 * 3 - 1, 1)); + expect_eq_uint(30, find_nth_bit(bmap, 64 * 3 - 1, 2)); + expect_eq_uint(40, find_nth_bit(bmap, 64 * 3 - 1, 3)); + expect_eq_uint(50, find_nth_bit(bmap, 64 * 3 - 1, 4)); + expect_eq_uint(60, find_nth_bit(bmap, 64 * 3 - 1, 5)); + expect_eq_uint(80, find_nth_bit(bmap, 64 * 3 - 1, 6)); + expect_eq_uint(123, find_nth_bit(bmap, 64 * 3 - 1, 7)); + expect_eq_uint(64 * 3 - 1, find_nth_bit(bmap, 64 * 3 - 1, 8)); + + for_each_set_bit(bit, exp1, EXP1_IN_BITS) { + b = find_nth_bit(exp1, EXP1_IN_BITS, cnt++); + expect_eq_uint(b, bit); + } +} + static void __init test_fill_set(void) { DECLARE_BITMAP(bmap, 1024); @@ -557,8 +600,6 @@ static void __init test_bitmap_parse(void) } } -#define EXP1_IN_BITS (sizeof(exp1) * 8) - static void __init test_bitmap_arr32(void) { unsigned int nbits, next_bit; @@ -685,6 +726,239 @@ static void __init test_for_each_set_clump8(void) expect_eq_clump8(start, CLUMP_EXP_NUMBITS, clump_exp, &clump); } +static void __init test_for_each_set_bit_wrap(void) +{ + DECLARE_BITMAP(orig, 500); + DECLARE_BITMAP(copy, 500); + unsigned int wr, bit; + + bitmap_zero(orig, 500); + + /* Set individual bits */ + for (bit = 0; bit < 500; bit += 10) + bitmap_set(orig, bit, 1); + + /* Set range of bits */ + bitmap_set(orig, 100, 50); + + for (wr = 0; wr < 500; wr++) { + bitmap_zero(copy, 500); + + for_each_set_bit_wrap(bit, orig, 500, wr) + bitmap_set(copy, bit, 1); + + expect_eq_bitmap(orig, copy, 500); + } +} + +static void __init test_for_each_set_bit(void) +{ + DECLARE_BITMAP(orig, 500); + DECLARE_BITMAP(copy, 500); + unsigned int bit; + + bitmap_zero(orig, 500); + bitmap_zero(copy, 500); + + /* Set individual bits */ + for (bit = 0; bit < 500; bit += 10) + bitmap_set(orig, bit, 1); + + /* Set range of bits */ + bitmap_set(orig, 100, 50); + + for_each_set_bit(bit, orig, 500) + bitmap_set(copy, bit, 1); + + expect_eq_bitmap(orig, copy, 500); +} + +static void __init test_for_each_set_bit_from(void) +{ + DECLARE_BITMAP(orig, 500); + DECLARE_BITMAP(copy, 500); + unsigned int wr, bit; + + bitmap_zero(orig, 500); + + /* Set individual bits */ + for (bit = 0; bit < 500; bit += 10) + bitmap_set(orig, bit, 1); + + /* Set range of bits */ + bitmap_set(orig, 100, 50); + + for (wr = 0; wr < 500; wr++) { + DECLARE_BITMAP(tmp, 500); + + bitmap_zero(copy, 500); + bit = wr; + + for_each_set_bit_from(bit, orig, 500) + bitmap_set(copy, bit, 1); + + bitmap_copy(tmp, orig, 500); + bitmap_clear(tmp, 0, wr); + expect_eq_bitmap(tmp, copy, 500); + } +} + +static void __init test_for_each_clear_bit(void) +{ + DECLARE_BITMAP(orig, 500); + DECLARE_BITMAP(copy, 500); + unsigned int bit; + + bitmap_fill(orig, 500); + bitmap_fill(copy, 500); + + /* Set individual bits */ + for (bit = 0; bit < 500; bit += 10) + bitmap_clear(orig, bit, 1); + + /* Set range of bits */ + bitmap_clear(orig, 100, 50); + + for_each_clear_bit(bit, orig, 500) + bitmap_clear(copy, bit, 1); + + expect_eq_bitmap(orig, copy, 500); +} + +static void __init test_for_each_clear_bit_from(void) +{ + DECLARE_BITMAP(orig, 500); + DECLARE_BITMAP(copy, 500); + unsigned int wr, bit; + + bitmap_fill(orig, 500); + + /* Set individual bits */ + for (bit = 0; bit < 500; bit += 10) + bitmap_clear(orig, bit, 1); + + /* Set range of bits */ + bitmap_clear(orig, 100, 50); + + for (wr = 0; wr < 500; wr++) { + DECLARE_BITMAP(tmp, 500); + + bitmap_fill(copy, 500); + bit = wr; + + for_each_clear_bit_from(bit, orig, 500) + bitmap_clear(copy, bit, 1); + + bitmap_copy(tmp, orig, 500); + bitmap_set(tmp, 0, wr); + expect_eq_bitmap(tmp, copy, 500); + } +} + +static void __init test_for_each_set_bitrange(void) +{ + DECLARE_BITMAP(orig, 500); + DECLARE_BITMAP(copy, 500); + unsigned int s, e; + + bitmap_zero(orig, 500); + bitmap_zero(copy, 500); + + /* Set individual bits */ + for (s = 0; s < 500; s += 10) + bitmap_set(orig, s, 1); + + /* Set range of bits */ + bitmap_set(orig, 100, 50); + + for_each_set_bitrange(s, e, orig, 500) + bitmap_set(copy, s, e-s); + + expect_eq_bitmap(orig, copy, 500); +} + +static void __init test_for_each_clear_bitrange(void) +{ + DECLARE_BITMAP(orig, 500); + DECLARE_BITMAP(copy, 500); + unsigned int s, e; + + bitmap_fill(orig, 500); + bitmap_fill(copy, 500); + + /* Set individual bits */ + for (s = 0; s < 500; s += 10) + bitmap_clear(orig, s, 1); + + /* Set range of bits */ + bitmap_clear(orig, 100, 50); + + for_each_clear_bitrange(s, e, orig, 500) + bitmap_clear(copy, s, e-s); + + expect_eq_bitmap(orig, copy, 500); +} + +static void __init test_for_each_set_bitrange_from(void) +{ + DECLARE_BITMAP(orig, 500); + DECLARE_BITMAP(copy, 500); + unsigned int wr, s, e; + + bitmap_zero(orig, 500); + + /* Set individual bits */ + for (s = 0; s < 500; s += 10) + bitmap_set(orig, s, 1); + + /* Set range of bits */ + bitmap_set(orig, 100, 50); + + for (wr = 0; wr < 500; wr++) { + DECLARE_BITMAP(tmp, 500); + + bitmap_zero(copy, 500); + s = wr; + + for_each_set_bitrange_from(s, e, orig, 500) + bitmap_set(copy, s, e - s); + + bitmap_copy(tmp, orig, 500); + bitmap_clear(tmp, 0, wr); + expect_eq_bitmap(tmp, copy, 500); + } +} + +static void __init test_for_each_clear_bitrange_from(void) +{ + DECLARE_BITMAP(orig, 500); + DECLARE_BITMAP(copy, 500); + unsigned int wr, s, e; + + bitmap_fill(orig, 500); + + /* Set individual bits */ + for (s = 0; s < 500; s += 10) + bitmap_clear(orig, s, 1); + + /* Set range of bits */ + bitmap_set(orig, 100, 50); + + for (wr = 0; wr < 500; wr++) { + DECLARE_BITMAP(tmp, 500); + + bitmap_fill(copy, 500); + s = wr; + + for_each_clear_bitrange_from(s, e, orig, 500) + bitmap_clear(copy, s, e - s); + + bitmap_copy(tmp, orig, 500); + bitmap_set(tmp, 0, wr); + expect_eq_bitmap(tmp, copy, 500); + } +} + struct test_bitmap_cut { unsigned int first; unsigned int cut; @@ -948,10 +1222,21 @@ static void __init selftest(void) test_bitmap_parselist(); test_bitmap_printlist(); test_mem_optimisations(); - test_for_each_set_clump8(); test_bitmap_cut(); test_bitmap_print_buf(); test_bitmap_const_eval(); + + test_find_nth_bit(); + test_for_each_set_bit(); + test_for_each_set_bit_from(); + test_for_each_clear_bit(); + test_for_each_clear_bit_from(); + test_for_each_set_bitrange(); + test_for_each_clear_bitrange(); + test_for_each_set_bitrange_from(); + test_for_each_clear_bitrange_from(); + test_for_each_set_clump8(); + test_for_each_set_bit_wrap(); } KSTM_MODULE_LOADERS(test_bitmap); diff --git a/samples/user_events/example.c b/samples/user_events/example.c index 4f5778e441c0..d06dc24156ec 100644 --- a/samples/user_events/example.c +++ b/samples/user_events/example.c @@ -12,13 +12,21 @@ #include #include #include +#include +#include #include +#if __BITS_PER_LONG == 64 +#define endian_swap(x) htole64(x) +#else +#define endian_swap(x) htole32(x) +#endif + /* Assumes debugfs is mounted */ const char *data_file = "/sys/kernel/debug/tracing/user_events_data"; const char *status_file = "/sys/kernel/debug/tracing/user_events_status"; -static int event_status(char **status) +static int event_status(long **status) { int fd = open(status_file, O_RDONLY); @@ -33,7 +41,8 @@ static int event_status(char **status) return 0; } -static int event_reg(int fd, const char *command, int *status, int *write) +static int event_reg(int fd, const char *command, long *index, long *mask, + int *write) { struct user_reg reg = {0}; @@ -43,7 +52,8 @@ static int event_reg(int fd, const char *command, int *status, int *write) if (ioctl(fd, DIAG_IOCSREG, ®) == -1) return -1; - *status = reg.status_index; + *index = reg.status_bit / __BITS_PER_LONG; + *mask = endian_swap(1L << (reg.status_bit % __BITS_PER_LONG)); *write = reg.write_index; return 0; @@ -51,8 +61,9 @@ static int event_reg(int fd, const char *command, int *status, int *write) int main(int argc, char **argv) { - int data_fd, status, write; - char *status_page; + int data_fd, write; + long index, mask; + long *status_page; struct iovec io[2]; __u32 count = 0; @@ -61,7 +72,7 @@ int main(int argc, char **argv) data_fd = open(data_file, O_RDWR); - if (event_reg(data_fd, "test u32 count", &status, &write) == -1) + if (event_reg(data_fd, "test u32 count", &index, &mask, &write) == -1) return errno; /* Setup iovec */ @@ -75,7 +86,7 @@ int main(int argc, char **argv) getchar(); /* Check if anyone is listening */ - if (status_page[status]) { + if (status_page[index] & mask) { /* Yep, trace out our data */ writev(data_fd, (const struct iovec *)io, 2); diff --git a/tools/include/linux/find.h b/tools/include/linux/find.h index 47e2bd6c5174..38c0a542b0e2 100644 --- a/tools/include/linux/find.h +++ b/tools/include/linux/find.h @@ -8,21 +8,23 @@ #include -extern unsigned long _find_next_bit(const unsigned long *addr1, - const unsigned long *addr2, unsigned long nbits, - unsigned long start, unsigned long invert, unsigned long le); +unsigned long _find_next_bit(const unsigned long *addr1, unsigned long nbits, + unsigned long start); +unsigned long _find_next_and_bit(const unsigned long *addr1, const unsigned long *addr2, + unsigned long nbits, unsigned long start); +unsigned long _find_next_zero_bit(const unsigned long *addr, unsigned long nbits, + unsigned long start); extern unsigned long _find_first_bit(const unsigned long *addr, unsigned long size); extern unsigned long _find_first_and_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size); extern unsigned long _find_first_zero_bit(const unsigned long *addr, unsigned long size); -extern unsigned long _find_last_bit(const unsigned long *addr, unsigned long size); #ifndef find_next_bit /** * find_next_bit - find the next set bit in a memory region * @addr: The address to base the search on - * @offset: The bitnumber to start searching at * @size: The bitmap size in bits + * @offset: The bitnumber to start searching at * * Returns the bit number for the next set bit * If no bits are set, returns @size. @@ -41,7 +43,7 @@ unsigned long find_next_bit(const unsigned long *addr, unsigned long size, return val ? __ffs(val) : size; } - return _find_next_bit(addr, NULL, size, offset, 0UL, 0); + return _find_next_bit(addr, size, offset); } #endif @@ -50,8 +52,8 @@ unsigned long find_next_bit(const unsigned long *addr, unsigned long size, * find_next_and_bit - find the next set bit in both memory regions * @addr1: The first address to base the search on * @addr2: The second address to base the search on - * @offset: The bitnumber to start searching at * @size: The bitmap size in bits + * @offset: The bitnumber to start searching at * * Returns the bit number for the next set bit * If no bits are set, returns @size. @@ -71,7 +73,7 @@ unsigned long find_next_and_bit(const unsigned long *addr1, return val ? __ffs(val) : size; } - return _find_next_bit(addr1, addr2, size, offset, 0UL, 0); + return _find_next_and_bit(addr1, addr2, size, offset); } #endif @@ -79,8 +81,8 @@ unsigned long find_next_and_bit(const unsigned long *addr1, /** * find_next_zero_bit - find the next cleared bit in a memory region * @addr: The address to base the search on - * @offset: The bitnumber to start searching at * @size: The bitmap size in bits + * @offset: The bitnumber to start searching at * * Returns the bit number of the next zero bit * If no bits are zero, returns @size. @@ -99,7 +101,7 @@ unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size, return val == ~0UL ? size : ffz(val); } - return _find_next_bit(addr, NULL, size, offset, ~0UL, 0); + return _find_next_zero_bit(addr, size, offset); } #endif @@ -172,43 +174,4 @@ unsigned long find_first_zero_bit(const unsigned long *addr, unsigned long size) } #endif -#ifndef find_last_bit -/** - * find_last_bit - find the last set bit in a memory region - * @addr: The address to start the search at - * @size: The number of bits to search - * - * Returns the bit number of the last set bit, or size. - */ -static inline -unsigned long find_last_bit(const unsigned long *addr, unsigned long size) -{ - if (small_const_nbits(size)) { - unsigned long val = *addr & GENMASK(size - 1, 0); - - return val ? __fls(val) : size; - } - - return _find_last_bit(addr, size); -} -#endif - -/** - * find_next_clump8 - find next 8-bit clump with set bits in a memory region - * @clump: location to store copy of found clump - * @addr: address to base the search on - * @size: bitmap size in number of bits - * @offset: bit offset at which to start searching - * - * Returns the bit offset for the next set clump; the found clump value is - * copied to the location pointed by @clump. If no bits are set, returns @size. - */ -extern unsigned long find_next_clump8(unsigned long *clump, - const unsigned long *addr, - unsigned long size, unsigned long offset); - -#define find_first_clump8(clump, bits, size) \ - find_next_clump8((clump), (bits), (size), 0) - - #endif /*__LINUX_FIND_H_ */ diff --git a/tools/lib/find_bit.c b/tools/lib/find_bit.c index ba4b8d94e004..6a3dc167d30e 100644 --- a/tools/lib/find_bit.c +++ b/tools/lib/find_bit.c @@ -18,66 +18,54 @@ #include #include -#if !defined(find_next_bit) || !defined(find_next_zero_bit) || \ - !defined(find_next_and_bit) +/* + * Common helper for find_bit() function family + * @FETCH: The expression that fetches and pre-processes each word of bitmap(s) + * @MUNGE: The expression that post-processes a word containing found bit (may be empty) + * @size: The bitmap size in bits + */ +#define FIND_FIRST_BIT(FETCH, MUNGE, size) \ +({ \ + unsigned long idx, val, sz = (size); \ + \ + for (idx = 0; idx * BITS_PER_LONG < sz; idx++) { \ + val = (FETCH); \ + if (val) { \ + sz = min(idx * BITS_PER_LONG + __ffs(MUNGE(val)), sz); \ + break; \ + } \ + } \ + \ + sz; \ +}) /* - * This is a common helper function for find_next_bit, find_next_zero_bit, and - * find_next_and_bit. The differences are: - * - The "invert" argument, which is XORed with each fetched word before - * searching it for one bits. - * - The optional "addr2", which is anded with "addr1" if present. + * Common helper for find_next_bit() function family + * @FETCH: The expression that fetches and pre-processes each word of bitmap(s) + * @MUNGE: The expression that post-processes a word containing found bit (may be empty) + * @size: The bitmap size in bits + * @start: The bitnumber to start searching at */ -unsigned long _find_next_bit(const unsigned long *addr1, - const unsigned long *addr2, unsigned long nbits, - unsigned long start, unsigned long invert, unsigned long le) -{ - unsigned long tmp, mask; - (void) le; - - if (unlikely(start >= nbits)) - return nbits; - - tmp = addr1[start / BITS_PER_LONG]; - if (addr2) - tmp &= addr2[start / BITS_PER_LONG]; - tmp ^= invert; - - /* Handle 1st word. */ - mask = BITMAP_FIRST_WORD_MASK(start); - - /* - * Due to the lack of swab() in tools, and the fact that it doesn't - * need little-endian support, just comment it out - */ -#if (0) - if (le) - mask = swab(mask); -#endif - - tmp &= mask; - - start = round_down(start, BITS_PER_LONG); - - while (!tmp) { - start += BITS_PER_LONG; - if (start >= nbits) - return nbits; - - tmp = addr1[start / BITS_PER_LONG]; - if (addr2) - tmp &= addr2[start / BITS_PER_LONG]; - tmp ^= invert; - } - -#if (0) - if (le) - tmp = swab(tmp); -#endif - - return min(start + __ffs(tmp), nbits); -} -#endif +#define FIND_NEXT_BIT(FETCH, MUNGE, size, start) \ +({ \ + unsigned long mask, idx, tmp, sz = (size), __start = (start); \ + \ + if (unlikely(__start >= sz)) \ + goto out; \ + \ + mask = MUNGE(BITMAP_FIRST_WORD_MASK(__start)); \ + idx = __start / BITS_PER_LONG; \ + \ + for (tmp = (FETCH) & mask; !tmp; tmp = (FETCH)) { \ + if ((idx + 1) * BITS_PER_LONG >= sz) \ + goto out; \ + idx++; \ + } \ + \ + sz = min(idx * BITS_PER_LONG + __ffs(MUNGE(tmp)), sz); \ +out: \ + sz; \ +}) #ifndef find_first_bit /* @@ -85,14 +73,7 @@ unsigned long _find_next_bit(const unsigned long *addr1, */ unsigned long _find_first_bit(const unsigned long *addr, unsigned long size) { - unsigned long idx; - - for (idx = 0; idx * BITS_PER_LONG < size; idx++) { - if (addr[idx]) - return min(idx * BITS_PER_LONG + __ffs(addr[idx]), size); - } - - return size; + return FIND_FIRST_BIT(addr[idx], /* nop */, size); } #endif @@ -104,15 +85,7 @@ unsigned long _find_first_and_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size) { - unsigned long idx, val; - - for (idx = 0; idx * BITS_PER_LONG < size; idx++) { - val = addr1[idx] & addr2[idx]; - if (val) - return min(idx * BITS_PER_LONG + __ffs(val), size); - } - - return size; + return FIND_FIRST_BIT(addr1[idx] & addr2[idx], /* nop */, size); } #endif @@ -122,13 +95,29 @@ unsigned long _find_first_and_bit(const unsigned long *addr1, */ unsigned long _find_first_zero_bit(const unsigned long *addr, unsigned long size) { - unsigned long idx; - - for (idx = 0; idx * BITS_PER_LONG < size; idx++) { - if (addr[idx] != ~0UL) - return min(idx * BITS_PER_LONG + ffz(addr[idx]), size); - } - - return size; + return FIND_FIRST_BIT(~addr[idx], /* nop */, size); +} +#endif + +#ifndef find_next_bit +unsigned long _find_next_bit(const unsigned long *addr, unsigned long nbits, unsigned long start) +{ + return FIND_NEXT_BIT(addr[idx], /* nop */, nbits, start); +} +#endif + +#ifndef find_next_and_bit +unsigned long _find_next_and_bit(const unsigned long *addr1, const unsigned long *addr2, + unsigned long nbits, unsigned long start) +{ + return FIND_NEXT_BIT(addr1[idx] & addr2[idx], /* nop */, nbits, start); +} +#endif + +#ifndef find_next_zero_bit +unsigned long _find_next_zero_bit(const unsigned long *addr, unsigned long nbits, + unsigned long start) +{ + return FIND_NEXT_BIT(~addr[idx], /* nop */, nbits, start); } #endif diff --git a/tools/testing/selftests/ftrace/test.d/dynevent/eprobes_syntax_errors.tc b/tools/testing/selftests/ftrace/test.d/dynevent/eprobes_syntax_errors.tc new file mode 100644 index 000000000000..fc1daac7f066 --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/dynevent/eprobes_syntax_errors.tc @@ -0,0 +1,27 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# description: Event probe event parser error log check +# requires: dynamic_events events/syscalls/sys_enter_openat ". []":README error_log + +check_error() { # command-with-error-pos-by-^ + ftrace_errlog_check 'event_probe' "$1" 'dynamic_events' +} + +check_error 'e ^a.' # NO_EVENT_INFO +check_error 'e ^.b' # NO_EVENT_INFO +check_error 'e ^a.b' # BAD_ATTACH_EVENT +check_error 'e syscalls/sys_enter_openat ^foo' # BAD_ATTACH_ARG +check_error 'e:^/bar syscalls/sys_enter_openat' # NO_GROUP_NAME +check_error 'e:^12345678901234567890123456789012345678901234567890123456789012345/bar syscalls/sys_enter_openat' # GROUP_TOO_LONG + +check_error 'e:^foo.1/bar syscalls/sys_enter_openat' # BAD_GROUP_NAME +check_error 'e:^ syscalls/sys_enter_openat' # NO_EVENT_NAME +check_error 'e:foo/^12345678901234567890123456789012345678901234567890123456789012345 syscalls/sys_enter_openat' # EVENT_TOO_LONG +check_error 'e:foo/^bar.1 syscalls/sys_enter_openat' # BAD_EVENT_NAME + +check_error 'e:foo/bar syscalls/sys_enter_openat arg=^dfd' # BAD_FETCH_ARG +check_error 'e:foo/bar syscalls/sys_enter_openat ^arg=$foo' # BAD_ATTACH_ARG + +check_error 'e:foo/bar syscalls/sys_enter_openat if ^' # NO_EP_FILTER + +exit 0 diff --git a/tools/testing/selftests/user_events/ftrace_test.c b/tools/testing/selftests/user_events/ftrace_test.c index a80fb5ef61d5..404a2713dcae 100644 --- a/tools/testing/selftests/user_events/ftrace_test.c +++ b/tools/testing/selftests/user_events/ftrace_test.c @@ -22,6 +22,11 @@ const char *enable_file = "/sys/kernel/debug/tracing/events/user_events/__test_e const char *trace_file = "/sys/kernel/debug/tracing/trace"; const char *fmt_file = "/sys/kernel/debug/tracing/events/user_events/__test_event/format"; +static inline int status_check(char *status_page, int status_bit) +{ + return status_page[status_bit >> 3] & (1 << (status_bit & 7)); +} + static int trace_bytes(void) { int fd = open(trace_file, O_RDONLY); @@ -197,12 +202,12 @@ TEST_F(user, register_events) { /* Register should work */ ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSREG, ®)); ASSERT_EQ(0, reg.write_index); - ASSERT_NE(0, reg.status_index); + ASSERT_NE(0, reg.status_bit); /* Multiple registers should result in same index */ ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSREG, ®)); ASSERT_EQ(0, reg.write_index); - ASSERT_NE(0, reg.status_index); + ASSERT_NE(0, reg.status_bit); /* Ensure disabled */ self->enable_fd = open(enable_file, O_RDWR); @@ -212,15 +217,15 @@ TEST_F(user, register_events) { /* MMAP should work and be zero'd */ ASSERT_NE(MAP_FAILED, status_page); ASSERT_NE(NULL, status_page); - ASSERT_EQ(0, status_page[reg.status_index]); + ASSERT_EQ(0, status_check(status_page, reg.status_bit)); /* Enable event and ensure bits updated in status */ ASSERT_NE(-1, write(self->enable_fd, "1", sizeof("1"))) - ASSERT_EQ(EVENT_STATUS_FTRACE, status_page[reg.status_index]); + ASSERT_NE(0, status_check(status_page, reg.status_bit)); /* Disable event and ensure bits updated in status */ ASSERT_NE(-1, write(self->enable_fd, "0", sizeof("0"))) - ASSERT_EQ(0, status_page[reg.status_index]); + ASSERT_EQ(0, status_check(status_page, reg.status_bit)); /* File still open should return -EBUSY for delete */ ASSERT_EQ(-1, ioctl(self->data_fd, DIAG_IOCSDEL, "__test_event")); @@ -240,6 +245,8 @@ TEST_F(user, write_events) { struct iovec io[3]; __u32 field1, field2; int before = 0, after = 0; + int page_size = sysconf(_SC_PAGESIZE); + char *status_page; reg.size = sizeof(reg); reg.name_args = (__u64)"__test_event u32 field1; u32 field2"; @@ -254,10 +261,18 @@ TEST_F(user, write_events) { io[2].iov_base = &field2; io[2].iov_len = sizeof(field2); + status_page = mmap(NULL, page_size, PROT_READ, MAP_SHARED, + self->status_fd, 0); + /* Register should work */ ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSREG, ®)); ASSERT_EQ(0, reg.write_index); - ASSERT_NE(0, reg.status_index); + ASSERT_NE(0, reg.status_bit); + + /* MMAP should work and be zero'd */ + ASSERT_NE(MAP_FAILED, status_page); + ASSERT_NE(NULL, status_page); + ASSERT_EQ(0, status_check(status_page, reg.status_bit)); /* Write should fail on invalid slot with ENOENT */ io[0].iov_base = &field2; @@ -271,6 +286,9 @@ TEST_F(user, write_events) { self->enable_fd = open(enable_file, O_RDWR); ASSERT_NE(-1, write(self->enable_fd, "1", sizeof("1"))) + /* Event should now be enabled */ + ASSERT_NE(0, status_check(status_page, reg.status_bit)); + /* Write should make it out to ftrace buffers */ before = trace_bytes(); ASSERT_NE(-1, writev(self->data_fd, (const struct iovec *)io, 3)); @@ -298,7 +316,7 @@ TEST_F(user, write_fault) { /* Register should work */ ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSREG, ®)); ASSERT_EQ(0, reg.write_index); - ASSERT_NE(0, reg.status_index); + ASSERT_NE(0, reg.status_bit); /* Write should work normally */ ASSERT_NE(-1, writev(self->data_fd, (const struct iovec *)io, 2)); @@ -315,6 +333,11 @@ TEST_F(user, write_validator) { int loc, bytes; char data[8]; int before = 0, after = 0; + int page_size = sysconf(_SC_PAGESIZE); + char *status_page; + + status_page = mmap(NULL, page_size, PROT_READ, MAP_SHARED, + self->status_fd, 0); reg.size = sizeof(reg); reg.name_args = (__u64)"__test_event __rel_loc char[] data"; @@ -322,7 +345,12 @@ TEST_F(user, write_validator) { /* Register should work */ ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSREG, ®)); ASSERT_EQ(0, reg.write_index); - ASSERT_NE(0, reg.status_index); + ASSERT_NE(0, reg.status_bit); + + /* MMAP should work and be zero'd */ + ASSERT_NE(MAP_FAILED, status_page); + ASSERT_NE(NULL, status_page); + ASSERT_EQ(0, status_check(status_page, reg.status_bit)); io[0].iov_base = ®.write_index; io[0].iov_len = sizeof(reg.write_index); @@ -340,6 +368,9 @@ TEST_F(user, write_validator) { self->enable_fd = open(enable_file, O_RDWR); ASSERT_NE(-1, write(self->enable_fd, "1", sizeof("1"))) + /* Event should now be enabled */ + ASSERT_NE(0, status_check(status_page, reg.status_bit)); + /* Full in-bounds write should work */ before = trace_bytes(); loc = DYN_LOC(0, bytes); diff --git a/tools/testing/selftests/user_events/perf_test.c b/tools/testing/selftests/user_events/perf_test.c index 26851d51d6bb..8b4c7879d5a7 100644 --- a/tools/testing/selftests/user_events/perf_test.c +++ b/tools/testing/selftests/user_events/perf_test.c @@ -35,6 +35,11 @@ static long perf_event_open(struct perf_event_attr *pe, pid_t pid, return syscall(__NR_perf_event_open, pe, pid, cpu, group_fd, flags); } +static inline int status_check(char *status_page, int status_bit) +{ + return status_page[status_bit >> 3] & (1 << (status_bit & 7)); +} + static int get_id(void) { FILE *fp = fopen(id_file, "r"); @@ -120,8 +125,8 @@ TEST_F(user, perf_write) { /* Register should work */ ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSREG, ®)); ASSERT_EQ(0, reg.write_index); - ASSERT_NE(0, reg.status_index); - ASSERT_EQ(0, status_page[reg.status_index]); + ASSERT_NE(0, reg.status_bit); + ASSERT_EQ(0, status_check(status_page, reg.status_bit)); /* Id should be there */ id = get_id(); @@ -144,7 +149,7 @@ TEST_F(user, perf_write) { ASSERT_NE(MAP_FAILED, perf_page); /* Status should be updated */ - ASSERT_EQ(EVENT_STATUS_PERF, status_page[reg.status_index]); + ASSERT_NE(0, status_check(status_page, reg.status_bit)); event.index = reg.write_index; event.field1 = 0xc001; diff --git a/tools/verification/dot2/dot2k_templates/main_global.c b/tools/verification/dot2/dot2k_templates/main_global.c index f4b712dbc92e..a5658bfb9044 100644 --- a/tools/verification/dot2/dot2k_templates/main_global.c +++ b/tools/verification/dot2/dot2k_templates/main_global.c @@ -27,7 +27,7 @@ * * The rv monitor reference is needed for the monitor declaration. */ -struct rv_monitor rv_MODEL_NAME; +static struct rv_monitor rv_MODEL_NAME; DECLARE_DA_MON_GLOBAL(MODEL_NAME, MIN_TYPE); /* @@ -63,7 +63,7 @@ TRACEPOINT_DETACH /* * This is the monitor register section. */ -struct rv_monitor rv_MODEL_NAME = { +static struct rv_monitor rv_MODEL_NAME = { .name = "MODEL_NAME", .description = "auto-generated MODEL_NAME", .enable = enable_MODEL_NAME, @@ -72,13 +72,13 @@ struct rv_monitor rv_MODEL_NAME = { .enabled = 0, }; -static int register_MODEL_NAME(void) +static int __init register_MODEL_NAME(void) { rv_register_monitor(&rv_MODEL_NAME); return 0; } -static void unregister_MODEL_NAME(void) +static void __exit unregister_MODEL_NAME(void) { rv_unregister_monitor(&rv_MODEL_NAME); } diff --git a/tools/verification/dot2/dot2k_templates/main_per_cpu.c b/tools/verification/dot2/dot2k_templates/main_per_cpu.c index 4080d1ca3354..03539a97633f 100644 --- a/tools/verification/dot2/dot2k_templates/main_per_cpu.c +++ b/tools/verification/dot2/dot2k_templates/main_per_cpu.c @@ -27,7 +27,7 @@ * * The rv monitor reference is needed for the monitor declaration. */ -struct rv_monitor rv_MODEL_NAME; +static struct rv_monitor rv_MODEL_NAME; DECLARE_DA_MON_PER_CPU(MODEL_NAME, MIN_TYPE); /* @@ -63,7 +63,7 @@ TRACEPOINT_DETACH /* * This is the monitor register section. */ -struct rv_monitor rv_MODEL_NAME = { +static struct rv_monitor rv_MODEL_NAME = { .name = "MODEL_NAME", .description = "auto-generated MODEL_NAME", .enable = enable_MODEL_NAME, @@ -72,13 +72,13 @@ struct rv_monitor rv_MODEL_NAME = { .enabled = 0, }; -static int register_MODEL_NAME(void) +static int __init register_MODEL_NAME(void) { rv_register_monitor(&rv_MODEL_NAME); return 0; } -static void unregister_MODEL_NAME(void) +static void __exit unregister_MODEL_NAME(void) { rv_unregister_monitor(&rv_MODEL_NAME); } diff --git a/tools/verification/dot2/dot2k_templates/main_per_task.c b/tools/verification/dot2/dot2k_templates/main_per_task.c index 89197175384f..ffd92af87a86 100644 --- a/tools/verification/dot2/dot2k_templates/main_per_task.c +++ b/tools/verification/dot2/dot2k_templates/main_per_task.c @@ -27,7 +27,7 @@ * * The rv monitor reference is needed for the monitor declaration. */ -struct rv_monitor rv_MODEL_NAME; +static struct rv_monitor rv_MODEL_NAME; DECLARE_DA_MON_PER_TASK(MODEL_NAME, MIN_TYPE); /* @@ -63,7 +63,7 @@ TRACEPOINT_DETACH /* * This is the monitor register section. */ -struct rv_monitor rv_MODEL_NAME = { +static struct rv_monitor rv_MODEL_NAME = { .name = "MODEL_NAME", .description = "auto-generated MODEL_NAME", .enable = enable_MODEL_NAME, @@ -72,13 +72,13 @@ struct rv_monitor rv_MODEL_NAME = { .enabled = 0, }; -static int register_MODEL_NAME(void) +static int __init register_MODEL_NAME(void) { rv_register_monitor(&rv_MODEL_NAME); return 0; } -static void unregister_MODEL_NAME(void) +static void __exit unregister_MODEL_NAME(void) { rv_unregister_monitor(&rv_MODEL_NAME); }