From 2475a2b6c877a0c8d1ca42c3f2b30f8ce518ac0b Mon Sep 17 00:00:00 2001 From: Alistair Popple Date: Mon, 3 Apr 2017 19:51:42 +1000 Subject: drivers/of/base.c: Add of_property_read_u64_index There is of_property_read_u32_index but no u64 variant. This patch adds one similar to the u32 version for u64. Signed-off-by: Alistair Popple Acked-by: Rob Herring Signed-off-by: Michael Ellerman --- include/linux/of.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/of.h b/include/linux/of.h index 21e6323de0f3..d08788daae5c 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -292,6 +292,9 @@ extern int of_property_count_elems_of_size(const struct device_node *np, extern int of_property_read_u32_index(const struct device_node *np, const char *propname, u32 index, u32 *out_value); +extern int of_property_read_u64_index(const struct device_node *np, + const char *propname, + u32 index, u64 *out_value); extern int of_property_read_variable_u8_array(const struct device_node *np, const char *propname, u8 *out_values, size_t sz_min, size_t sz_max); -- cgit v1.2.3 From 8c5073db0ee680c7e70e123918c9b260e49f757d Mon Sep 17 00:00:00 2001 From: Sukadev Bhattiprolu Date: Tue, 11 Apr 2017 07:21:05 +0530 Subject: powerpc/perf: Define big-endian version of perf_mem_data_src perf_mem_data_src is a union that is initialized in the kernel via the ->val field and accessed by userspace via the mem_xxx bitfields. For this to work correctly on big endian platforms, we need a big-endian definition for the bitfields. Currently on a big endian system, if a user requests PERF_SAMPLE_DATA_SRC (perf report -d), they will get the default value from perf_sample_data_init(), which is PERF_MEM_NA. The value for PERF_MEM_NA is constructed using shifts: /* TLB access */ #define PERF_MEM_TLB_NA 0x01 /* not available */ ... #define PERF_MEM_TLB_SHIFT 26 #define PERF_MEM_S(a, s) \ (((__u64)PERF_MEM_##a##_##s) << PERF_MEM_##a##_SHIFT) #define PERF_MEM_NA (PERF_MEM_S(OP, NA) |\ PERF_MEM_S(LVL, NA) |\ PERF_MEM_S(SNOOP, NA) |\ PERF_MEM_S(LOCK, NA) |\ PERF_MEM_S(TLB, NA)) Which works out as: ((0x01 << 0) | (0x01 << 5) | (0x01 << 19) | (0x01 << 24) | (0x01 << 26)) Which means the PERF_MEM_NA value comes out of the kernel as 0x5080021 in CPU endian. But then in the perf tool, the code uses the bitfields to inspect the value, and currently the bitfields are defined using little endian ordering. So eg. in perf_mem__tlb_scnprintf() we see: data_src->val = 0x5080021 op = 0x0 lvl = 0x0 snoop = 0x0 lock = 0x0 dtlb = 0x0 rsvd = 0x5080021 Because of the way the perf tool code is written this is still displayed to the user as "N/A", so there is no bug visible at the UI level. Currently there are no big endian architectures which export a meaningful value (ie. other than PERF_MEM_NA), so the extent of the bug on big endian platforms is that the PERF_MEM_NA value is exported incorrectly as described above. Subsequent patches will add support on big endian powerpc for populating the data source value. This patch does a minimal fix of adding big endian definition of the bitfields to match the values that are already exported by the kernel on big endian. And it makes no change on little endian. Signed-off-by: Sukadev Bhattiprolu Signed-off-by: Madhavan Srinivasan Acked-by: Peter Zijlstra (Intel) Signed-off-by: Michael Ellerman --- include/uapi/linux/perf_event.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index c66a485a24ac..c4af1159a200 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -891,6 +891,7 @@ enum perf_callchain_context { #define PERF_FLAG_PID_CGROUP (1UL << 2) /* pid=cgroup id, per-cpu mode only */ #define PERF_FLAG_FD_CLOEXEC (1UL << 3) /* O_CLOEXEC */ +#if defined(__LITTLE_ENDIAN_BITFIELD) union perf_mem_data_src { __u64 val; struct { @@ -902,6 +903,21 @@ union perf_mem_data_src { mem_rsvd:31; }; }; +#elif defined(__BIG_ENDIAN_BITFIELD) +union perf_mem_data_src { + __u64 val; + struct { + __u64 mem_rsvd:31, + mem_dtlb:7, /* tlb access */ + mem_lock:2, /* lock instr */ + mem_snoop:5, /* snoop mode */ + mem_lvl:14, /* memory hierarchy level */ + mem_op:5; /* type of opcode */ + }; +}; +#else +#error "Unknown endianness" +#endif /* type of opcode (load/store/prefetch,code) */ #define PERF_MEM_OP_NA 0x01 /* not available */ -- cgit v1.2.3 From 49e0b4658fe6aab5bf6bfe0738a86c1895930ad1 Mon Sep 17 00:00:00 2001 From: "Naveen N. Rao" Date: Wed, 19 Apr 2017 18:21:00 +0530 Subject: kprobes: Convert kprobe_lookup_name() to a function The macro is now pretty long and ugly on powerpc. In the light of further changes needed here, convert it to a __weak variant to be over-ridden with a nicer looking function. Suggested-by: Masami Hiramatsu Acked-by: Masami Hiramatsu Signed-off-by: Naveen N. Rao Signed-off-by: Michael Ellerman --- include/linux/kprobes.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index c328e4f7dcad..16f153c84646 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -379,6 +379,7 @@ static inline struct kprobe_ctlblk *get_kprobe_ctlblk(void) return this_cpu_ptr(&kprobe_ctlblk); } +kprobe_opcode_t *kprobe_lookup_name(const char *name); int register_kprobe(struct kprobe *p); void unregister_kprobe(struct kprobe *p); int register_kprobes(struct kprobe **kps, int num); -- cgit v1.2.3 From 290e3070762ac80e5fc4087d8c4de7e3f1d90aca Mon Sep 17 00:00:00 2001 From: "Naveen N. Rao" Date: Wed, 19 Apr 2017 18:21:01 +0530 Subject: powerpc/kprobes: Fix handling of function offsets on ABIv2 commit 239aeba76409 ("perf powerpc: Fix kprobe and kretprobe handling with kallsyms on ppc64le") changed how we use the offset field in struct kprobe on ABIv2. perf now offsets from the global entry point if an offset is specified and otherwise chooses the local entry point. Fix the same in kernel for kprobe API users. We do this by extending kprobe_lookup_name() to accept an additional parameter to indicate the offset specified with the kprobe registration. If offset is 0, we return the local function entry and return the global entry point otherwise. With: # cd /sys/kernel/debug/tracing/ # echo "p _do_fork" >> kprobe_events # echo "p _do_fork+0x10" >> kprobe_events before this patch: # cat ../kprobes/list c0000000000d0748 k _do_fork+0x8 [DISABLED] c0000000000d0758 k _do_fork+0x18 [DISABLED] c0000000000412b0 k kretprobe_trampoline+0x0 [OPTIMIZED] and after: # cat ../kprobes/list c0000000000d04c8 k _do_fork+0x8 [DISABLED] c0000000000d04d0 k _do_fork+0x10 [DISABLED] c0000000000412b0 k kretprobe_trampoline+0x0 [OPTIMIZED] Acked-by: Ananth N Mavinakayanahalli Signed-off-by: Naveen N. Rao Signed-off-by: Michael Ellerman --- include/linux/kprobes.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 16f153c84646..1f82a3db00b1 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -379,7 +379,7 @@ static inline struct kprobe_ctlblk *get_kprobe_ctlblk(void) return this_cpu_ptr(&kprobe_ctlblk); } -kprobe_opcode_t *kprobe_lookup_name(const char *name); +kprobe_opcode_t *kprobe_lookup_name(const char *name, unsigned int offset); int register_kprobe(struct kprobe *p); void unregister_kprobe(struct kprobe *p); int register_kprobes(struct kprobe **kps, int num); -- cgit v1.2.3