summaryrefslogtreecommitdiff
path: root/kernel/trace
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2016-05-17 16:26:30 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2016-05-17 16:26:30 -0700
commita7fd20d1c476af4563e66865213474a2f9f473a4 (patch)
treefb1399e2f82842450245fb058a8fb23c52865f43 /kernel/trace
parentb80fed9595513384424cd141923c9161c4b5021b (diff)
parent917fa5353da05e8a0045b8acacba8d50400d5b12 (diff)
downloadlinux-sh-a7fd20d1c476af4563e66865213474a2f9f473a4.tar.gz
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking updates from David Miller: "Highlights: 1) Support SPI based w5100 devices, from Akinobu Mita. 2) Partial Segmentation Offload, from Alexander Duyck. 3) Add GMAC4 support to stmmac driver, from Alexandre TORGUE. 4) Allow cls_flower stats offload, from Amir Vadai. 5) Implement bpf blinding, from Daniel Borkmann. 6) Optimize _ASYNC_ bit twiddling on sockets, unless the socket is actually using FASYNC these atomics are superfluous. From Eric Dumazet. 7) Run TCP more preemptibly, also from Eric Dumazet. 8) Support LED blinking, EEPROM dumps, and rxvlan offloading in mlx5e driver, from Gal Pressman. 9) Allow creating ppp devices via rtnetlink, from Guillaume Nault. 10) Improve BPF usage documentation, from Jesper Dangaard Brouer. 11) Support tunneling offloads in qed, from Manish Chopra. 12) aRFS offloading in mlx5e, from Maor Gottlieb. 13) Add RFS and RPS support to SCTP protocol, from Marcelo Ricardo Leitner. 14) Add MSG_EOR support to TCP, this allows controlling packet coalescing on application record boundaries for more accurate socket timestamp sampling. From Martin KaFai Lau. 15) Fix alignment of 64-bit netlink attributes across the board, from Nicolas Dichtel. 16) Per-vlan stats in bridging, from Nikolay Aleksandrov. 17) Several conversions of drivers to ethtool ksettings, from Philippe Reynes. 18) Checksum neutral ILA in ipv6, from Tom Herbert. 19) Factorize all of the various marvell dsa drivers into one, from Vivien Didelot 20) Add VF support to qed driver, from Yuval Mintz" * git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1649 commits) Revert "phy dp83867: Fix compilation with CONFIG_OF_MDIO=m" Revert "phy dp83867: Make rgmii parameters optional" r8169: default to 64-bit DMA on recent PCIe chips phy dp83867: Make rgmii parameters optional phy dp83867: Fix compilation with CONFIG_OF_MDIO=m bpf: arm64: remove callee-save registers use for tmp registers asix: Fix offset calculation in asix_rx_fixup() causing slow transmissions switchdev: pass pointer to fib_info instead of copy net_sched: close another race condition in tcf_mirred_release() tipc: fix nametable publication field in nl compat drivers: net: Don't print unpopulated net_device name qed: add support for dcbx. ravb: Add missing free_irq() calls to ravb_close() qed: Remove a stray tab net: ethernet: fec-mpc52xx: use phy_ethtool_{get|set}_link_ksettings net: ethernet: fec-mpc52xx: use phydev from struct net_device bpf, doc: fix typo on bpf_asm descriptions stmmac: hardware TX COE doesn't work when force_thresh_dma_mode is set net: ethernet: fs-enet: use phy_ethtool_{get|set}_link_ksettings net: ethernet: fs-enet: use phydev from struct net_device ...
Diffstat (limited to 'kernel/trace')
-rw-r--r--kernel/trace/bpf_trace.c129
-rw-r--r--kernel/trace/trace_event_perf.c40
-rw-r--r--kernel/trace/trace_events.c18
-rw-r--r--kernel/trace/trace_kprobe.c10
-rw-r--r--kernel/trace/trace_syscalls.c13
-rw-r--r--kernel/trace/trace_uprobe.c5
6 files changed, 178 insertions, 37 deletions
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 3e4ffb3ace5f..780bcbe1d4de 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -62,17 +62,21 @@ EXPORT_SYMBOL_GPL(trace_call_bpf);
static u64 bpf_probe_read(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
{
void *dst = (void *) (long) r1;
- int size = (int) r2;
+ int ret, size = (int) r2;
void *unsafe_ptr = (void *) (long) r3;
- return probe_kernel_read(dst, unsafe_ptr, size);
+ ret = probe_kernel_read(dst, unsafe_ptr, size);
+ if (unlikely(ret < 0))
+ memset(dst, 0, size);
+
+ return ret;
}
static const struct bpf_func_proto bpf_probe_read_proto = {
.func = bpf_probe_read,
.gpl_only = true,
.ret_type = RET_INTEGER,
- .arg1_type = ARG_PTR_TO_STACK,
+ .arg1_type = ARG_PTR_TO_RAW_STACK,
.arg2_type = ARG_CONST_STACK_SIZE,
.arg3_type = ARG_ANYTHING,
};
@@ -221,11 +225,12 @@ static const struct bpf_func_proto bpf_perf_event_read_proto = {
.arg2_type = ARG_ANYTHING,
};
-static u64 bpf_perf_event_output(u64 r1, u64 r2, u64 index, u64 r4, u64 size)
+static u64 bpf_perf_event_output(u64 r1, u64 r2, u64 flags, u64 r4, u64 size)
{
struct pt_regs *regs = (struct pt_regs *) (long) r1;
struct bpf_map *map = (struct bpf_map *) (long) r2;
struct bpf_array *array = container_of(map, struct bpf_array, map);
+ u64 index = flags & BPF_F_INDEX_MASK;
void *data = (void *) (long) r4;
struct perf_sample_data sample_data;
struct perf_event *event;
@@ -235,6 +240,10 @@ static u64 bpf_perf_event_output(u64 r1, u64 r2, u64 index, u64 r4, u64 size)
.data = data,
};
+ if (unlikely(flags & ~(BPF_F_INDEX_MASK)))
+ return -EINVAL;
+ if (index == BPF_F_CURRENT_CPU)
+ index = raw_smp_processor_id();
if (unlikely(index >= array->map.max_entries))
return -E2BIG;
@@ -268,7 +277,34 @@ static const struct bpf_func_proto bpf_perf_event_output_proto = {
.arg5_type = ARG_CONST_STACK_SIZE,
};
-static const struct bpf_func_proto *kprobe_prog_func_proto(enum bpf_func_id func_id)
+static DEFINE_PER_CPU(struct pt_regs, bpf_pt_regs);
+
+static u64 bpf_event_output(u64 r1, u64 r2, u64 flags, u64 r4, u64 size)
+{
+ struct pt_regs *regs = this_cpu_ptr(&bpf_pt_regs);
+
+ perf_fetch_caller_regs(regs);
+
+ return bpf_perf_event_output((long)regs, r2, flags, r4, size);
+}
+
+static const struct bpf_func_proto bpf_event_output_proto = {
+ .func = bpf_event_output,
+ .gpl_only = true,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_CONST_MAP_PTR,
+ .arg3_type = ARG_ANYTHING,
+ .arg4_type = ARG_PTR_TO_STACK,
+ .arg5_type = ARG_CONST_STACK_SIZE,
+};
+
+const struct bpf_func_proto *bpf_get_event_output_proto(void)
+{
+ return &bpf_event_output_proto;
+}
+
+static const struct bpf_func_proto *tracing_func_proto(enum bpf_func_id func_id)
{
switch (func_id) {
case BPF_FUNC_map_lookup_elem:
@@ -295,12 +331,20 @@ static const struct bpf_func_proto *kprobe_prog_func_proto(enum bpf_func_id func
return &bpf_get_smp_processor_id_proto;
case BPF_FUNC_perf_event_read:
return &bpf_perf_event_read_proto;
+ default:
+ return NULL;
+ }
+}
+
+static const struct bpf_func_proto *kprobe_prog_func_proto(enum bpf_func_id func_id)
+{
+ switch (func_id) {
case BPF_FUNC_perf_event_output:
return &bpf_perf_event_output_proto;
case BPF_FUNC_get_stackid:
return &bpf_get_stackid_proto;
default:
- return NULL;
+ return tracing_func_proto(func_id);
}
}
@@ -332,9 +376,82 @@ static struct bpf_prog_type_list kprobe_tl = {
.type = BPF_PROG_TYPE_KPROBE,
};
+static u64 bpf_perf_event_output_tp(u64 r1, u64 r2, u64 index, u64 r4, u64 size)
+{
+ /*
+ * r1 points to perf tracepoint buffer where first 8 bytes are hidden
+ * from bpf program and contain a pointer to 'struct pt_regs'. Fetch it
+ * from there and call the same bpf_perf_event_output() helper
+ */
+ u64 ctx = *(long *)(uintptr_t)r1;
+
+ return bpf_perf_event_output(ctx, r2, index, r4, size);
+}
+
+static const struct bpf_func_proto bpf_perf_event_output_proto_tp = {
+ .func = bpf_perf_event_output_tp,
+ .gpl_only = true,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_CONST_MAP_PTR,
+ .arg3_type = ARG_ANYTHING,
+ .arg4_type = ARG_PTR_TO_STACK,
+ .arg5_type = ARG_CONST_STACK_SIZE,
+};
+
+static u64 bpf_get_stackid_tp(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
+{
+ u64 ctx = *(long *)(uintptr_t)r1;
+
+ return bpf_get_stackid(ctx, r2, r3, r4, r5);
+}
+
+static const struct bpf_func_proto bpf_get_stackid_proto_tp = {
+ .func = bpf_get_stackid_tp,
+ .gpl_only = true,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_CONST_MAP_PTR,
+ .arg3_type = ARG_ANYTHING,
+};
+
+static const struct bpf_func_proto *tp_prog_func_proto(enum bpf_func_id func_id)
+{
+ switch (func_id) {
+ case BPF_FUNC_perf_event_output:
+ return &bpf_perf_event_output_proto_tp;
+ case BPF_FUNC_get_stackid:
+ return &bpf_get_stackid_proto_tp;
+ default:
+ return tracing_func_proto(func_id);
+ }
+}
+
+static bool tp_prog_is_valid_access(int off, int size, enum bpf_access_type type)
+{
+ if (off < sizeof(void *) || off >= PERF_MAX_TRACE_SIZE)
+ return false;
+ if (type != BPF_READ)
+ return false;
+ if (off % size != 0)
+ return false;
+ return true;
+}
+
+static const struct bpf_verifier_ops tracepoint_prog_ops = {
+ .get_func_proto = tp_prog_func_proto,
+ .is_valid_access = tp_prog_is_valid_access,
+};
+
+static struct bpf_prog_type_list tracepoint_tl = {
+ .ops = &tracepoint_prog_ops,
+ .type = BPF_PROG_TYPE_TRACEPOINT,
+};
+
static int __init register_kprobe_prog_ops(void)
{
bpf_register_prog_type(&kprobe_tl);
+ bpf_register_prog_type(&tracepoint_tl);
return 0;
}
late_initcall(register_kprobe_prog_ops);
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index e11108f1d197..562fa69df5d3 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -263,42 +263,43 @@ void perf_trace_del(struct perf_event *p_event, int flags)
tp_event->class->reg(tp_event, TRACE_REG_PERF_DEL, p_event);
}
-void *perf_trace_buf_prepare(int size, unsigned short type,
- struct pt_regs **regs, int *rctxp)
+void *perf_trace_buf_alloc(int size, struct pt_regs **regs, int *rctxp)
{
- struct trace_entry *entry;
- unsigned long flags;
char *raw_data;
- int pc;
+ int rctx;
BUILD_BUG_ON(PERF_MAX_TRACE_SIZE % sizeof(unsigned long));
if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE,
- "perf buffer not large enough"))
+ "perf buffer not large enough"))
return NULL;
- pc = preempt_count();
-
- *rctxp = perf_swevent_get_recursion_context();
- if (*rctxp < 0)
+ *rctxp = rctx = perf_swevent_get_recursion_context();
+ if (rctx < 0)
return NULL;
if (regs)
- *regs = this_cpu_ptr(&__perf_regs[*rctxp]);
- raw_data = this_cpu_ptr(perf_trace_buf[*rctxp]);
+ *regs = this_cpu_ptr(&__perf_regs[rctx]);
+ raw_data = this_cpu_ptr(perf_trace_buf[rctx]);
/* zero the dead bytes from align to not leak stack to user */
memset(&raw_data[size - sizeof(u64)], 0, sizeof(u64));
+ return raw_data;
+}
+EXPORT_SYMBOL_GPL(perf_trace_buf_alloc);
+NOKPROBE_SYMBOL(perf_trace_buf_alloc);
+
+void perf_trace_buf_update(void *record, u16 type)
+{
+ struct trace_entry *entry = record;
+ int pc = preempt_count();
+ unsigned long flags;
- entry = (struct trace_entry *)raw_data;
local_save_flags(flags);
tracing_generic_entry_update(entry, flags, pc);
entry->type = type;
-
- return raw_data;
}
-EXPORT_SYMBOL_GPL(perf_trace_buf_prepare);
-NOKPROBE_SYMBOL(perf_trace_buf_prepare);
+NOKPROBE_SYMBOL(perf_trace_buf_update);
#ifdef CONFIG_FUNCTION_TRACER
static void
@@ -319,15 +320,16 @@ perf_ftrace_function_call(unsigned long ip, unsigned long parent_ip,
BUILD_BUG_ON(ENTRY_SIZE > PERF_MAX_TRACE_SIZE);
+ memset(&regs, 0, sizeof(regs));
perf_fetch_caller_regs(&regs);
- entry = perf_trace_buf_prepare(ENTRY_SIZE, TRACE_FN, NULL, &rctx);
+ entry = perf_trace_buf_alloc(ENTRY_SIZE, NULL, &rctx);
if (!entry)
return;
entry->ip = ip;
entry->parent_ip = parent_ip;
- perf_trace_buf_submit(entry, ENTRY_SIZE, rctx, 0,
+ perf_trace_buf_submit(entry, ENTRY_SIZE, rctx, TRACE_FN,
1, &regs, head, NULL);
#undef ENTRY_SIZE
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 6f965864cc02..b7b0760ba6ee 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -204,6 +204,24 @@ static void trace_destroy_fields(struct trace_event_call *call)
}
}
+/*
+ * run-time version of trace_event_get_offsets_<call>() that returns the last
+ * accessible offset of trace fields excluding __dynamic_array bytes
+ */
+int trace_event_get_offsets(struct trace_event_call *call)
+{
+ struct ftrace_event_field *tail;
+ struct list_head *head;
+
+ head = trace_get_fields(call);
+ /*
+ * head->next points to the last field with the largest offset,
+ * since it was added last by trace_define_field()
+ */
+ tail = list_first_entry(head, struct ftrace_event_field, link);
+ return tail->offset + tail->size;
+}
+
int trace_event_raw_init(struct trace_event_call *call)
{
int id;
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 919e0ddd8fcc..5546eec0505f 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -1149,14 +1149,15 @@ kprobe_perf_func(struct trace_kprobe *tk, struct pt_regs *regs)
size = ALIGN(__size + sizeof(u32), sizeof(u64));
size -= sizeof(u32);
- entry = perf_trace_buf_prepare(size, call->event.type, NULL, &rctx);
+ entry = perf_trace_buf_alloc(size, NULL, &rctx);
if (!entry)
return;
entry->ip = (unsigned long)tk->rp.kp.addr;
memset(&entry[1], 0, dsize);
store_trace_args(sizeof(*entry), &tk->tp, regs, (u8 *)&entry[1], dsize);
- perf_trace_buf_submit(entry, size, rctx, 0, 1, regs, head, NULL);
+ perf_trace_buf_submit(entry, size, rctx, call->event.type, 1, regs,
+ head, NULL);
}
NOKPROBE_SYMBOL(kprobe_perf_func);
@@ -1184,14 +1185,15 @@ kretprobe_perf_func(struct trace_kprobe *tk, struct kretprobe_instance *ri,
size = ALIGN(__size + sizeof(u32), sizeof(u64));
size -= sizeof(u32);
- entry = perf_trace_buf_prepare(size, call->event.type, NULL, &rctx);
+ entry = perf_trace_buf_alloc(size, NULL, &rctx);
if (!entry)
return;
entry->func = (unsigned long)tk->rp.kp.addr;
entry->ret_ip = (unsigned long)ri->ret_addr;
store_trace_args(sizeof(*entry), &tk->tp, regs, (u8 *)&entry[1], dsize);
- perf_trace_buf_submit(entry, size, rctx, 0, 1, regs, head, NULL);
+ perf_trace_buf_submit(entry, size, rctx, call->event.type, 1, regs,
+ head, NULL);
}
NOKPROBE_SYMBOL(kretprobe_perf_func);
#endif /* CONFIG_PERF_EVENTS */
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index e78f364cc192..b2b6efc083a4 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -587,15 +587,16 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
size = ALIGN(size + sizeof(u32), sizeof(u64));
size -= sizeof(u32);
- rec = (struct syscall_trace_enter *)perf_trace_buf_prepare(size,
- sys_data->enter_event->event.type, NULL, &rctx);
+ rec = perf_trace_buf_alloc(size, NULL, &rctx);
if (!rec)
return;
rec->nr = syscall_nr;
syscall_get_arguments(current, regs, 0, sys_data->nb_args,
(unsigned long *)&rec->args);
- perf_trace_buf_submit(rec, size, rctx, 0, 1, regs, head, NULL);
+ perf_trace_buf_submit(rec, size, rctx,
+ sys_data->enter_event->event.type, 1, regs,
+ head, NULL);
}
static int perf_sysenter_enable(struct trace_event_call *call)
@@ -660,14 +661,14 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
size = ALIGN(sizeof(*rec) + sizeof(u32), sizeof(u64));
size -= sizeof(u32);
- rec = (struct syscall_trace_exit *)perf_trace_buf_prepare(size,
- sys_data->exit_event->event.type, NULL, &rctx);
+ rec = perf_trace_buf_alloc(size, NULL, &rctx);
if (!rec)
return;
rec->nr = syscall_nr;
rec->ret = syscall_get_return_value(current, regs);
- perf_trace_buf_submit(rec, size, rctx, 0, 1, regs, head, NULL);
+ perf_trace_buf_submit(rec, size, rctx, sys_data->exit_event->event.type,
+ 1, regs, head, NULL);
}
static int perf_sysexit_enable(struct trace_event_call *call)
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index 7915142c89e4..c53485441c88 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -1131,7 +1131,7 @@ static void __uprobe_perf_func(struct trace_uprobe *tu,
if (hlist_empty(head))
goto out;
- entry = perf_trace_buf_prepare(size, call->event.type, NULL, &rctx);
+ entry = perf_trace_buf_alloc(size, NULL, &rctx);
if (!entry)
goto out;
@@ -1152,7 +1152,8 @@ static void __uprobe_perf_func(struct trace_uprobe *tu,
memset(data + len, 0, size - esize - len);
}
- perf_trace_buf_submit(entry, size, rctx, 0, 1, regs, head, NULL);
+ perf_trace_buf_submit(entry, size, rctx, call->event.type, 1, regs,
+ head, NULL);
out:
preempt_enable();
}