From 7375dca1647fa978310f2d706ddbff537f72110b Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>
Date: Mon, 20 May 2019 09:26:24 -0400
Subject: ftrace: Make enable and update parameters bool when applicable

The code modification functions have "enable" and "update" variables that
are sometimes "int" but used as "bool". Remove the ambiguity and make them
"bool" when they are only used for true or false values.

Link: http://lkml.kernel.org/r/e1429923d9eda92a3cf5ee9e33c7eacce539781d.1558115654.git.naveen.n.rao@linux.vnet.ibm.com

Reported-by: "Naveen N. Rao" <naveen.n.rao@linux.vnet.ibm.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 kernel/trace/ftrace.c | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

(limited to 'kernel')

diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index a12aff849c04..4f2c26bebe2a 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1768,7 +1768,7 @@ static bool __ftrace_hash_rec_update(struct ftrace_ops *ops,
 		count++;
 
 		/* Must match FTRACE_UPDATE_CALLS in ftrace_modify_all_code() */
-		update |= ftrace_test_record(rec, 1) != FTRACE_UPDATE_IGNORE;
+		update |= ftrace_test_record(rec, true) != FTRACE_UPDATE_IGNORE;
 
 		/* Shortcut, if we handled all records, we are done. */
 		if (!all && count == hash->count)
@@ -2047,7 +2047,7 @@ void ftrace_bug(int failed, struct dyn_ftrace *rec)
 	}
 }
 
-static int ftrace_check_record(struct dyn_ftrace *rec, int enable, int update)
+static int ftrace_check_record(struct dyn_ftrace *rec, bool enable, bool update)
 {
 	unsigned long flag = 0UL;
 
@@ -2146,28 +2146,28 @@ static int ftrace_check_record(struct dyn_ftrace *rec, int enable, int update)
 /**
  * ftrace_update_record, set a record that now is tracing or not
  * @rec: the record to update
- * @enable: set to 1 if the record is tracing, zero to force disable
+ * @enable: set to true if the record is tracing, false to force disable
  *
  * The records that represent all functions that can be traced need
  * to be updated when tracing has been enabled.
  */
-int ftrace_update_record(struct dyn_ftrace *rec, int enable)
+int ftrace_update_record(struct dyn_ftrace *rec, bool enable)
 {
-	return ftrace_check_record(rec, enable, 1);
+	return ftrace_check_record(rec, enable, true);
 }
 
 /**
  * ftrace_test_record, check if the record has been enabled or not
  * @rec: the record to test
- * @enable: set to 1 to check if enabled, 0 if it is disabled
+ * @enable: set to true to check if enabled, false if it is disabled
  *
  * The arch code may need to test if a record is already set to
  * tracing to determine how to modify the function code that it
  * represents.
  */
-int ftrace_test_record(struct dyn_ftrace *rec, int enable)
+int ftrace_test_record(struct dyn_ftrace *rec, bool enable)
 {
-	return ftrace_check_record(rec, enable, 0);
+	return ftrace_check_record(rec, enable, false);
 }
 
 static struct ftrace_ops *
@@ -2356,7 +2356,7 @@ unsigned long ftrace_get_addr_curr(struct dyn_ftrace *rec)
 }
 
 static int
-__ftrace_replace_code(struct dyn_ftrace *rec, int enable)
+__ftrace_replace_code(struct dyn_ftrace *rec, bool enable)
 {
 	unsigned long ftrace_old_addr;
 	unsigned long ftrace_addr;
@@ -2395,7 +2395,7 @@ void __weak ftrace_replace_code(int mod_flags)
 {
 	struct dyn_ftrace *rec;
 	struct ftrace_page *pg;
-	int enable = mod_flags & FTRACE_MODIFY_ENABLE_FL;
+	bool enable = mod_flags & FTRACE_MODIFY_ENABLE_FL;
 	int schedulable = mod_flags & FTRACE_MODIFY_MAY_SLEEP_FL;
 	int failed;
 
-- 
cgit v1.2.3


From 88903c464321cdbc2d473c24cbf311f576cf05bc Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Wed, 15 May 2019 14:38:30 +0900
Subject: tracing/probe: Add ustring type for user-space string

Add "ustring" type for fetching user-space string from kprobe event.
User can specify ustring type at uprobe event, and it is same as
"string" for uprobe.

Note that probe-event provides this option but it doesn't choose the
correct type automatically since we have not way to decide the address
is in user-space or not on some arch (and on some other arch, you can
fetch the string by "string" type). So user must carefully check the
target code (e.g. if you see __user on the target variable) and
use this new type.

Link: http://lkml.kernel.org/r/155789871009.26965.14167558859557329331.stgit@devnote2

Acked-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 kernel/trace/trace.c            |  2 +-
 kernel/trace/trace_kprobe.c     | 42 ++++++++++++++++++++++++++++++++++++++---
 kernel/trace/trace_probe.c      | 14 +++++++++++---
 kernel/trace/trace_probe.h      |  1 +
 kernel/trace/trace_probe_tmpl.h | 14 +++++++++++++-
 kernel/trace/trace_uprobe.c     | 12 ++++++++++++
 6 files changed, 77 insertions(+), 8 deletions(-)

(limited to 'kernel')

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 1c80521fd436..d3a477a16e70 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -4847,7 +4847,7 @@ static const char readme_msg[] =
 	"\t           $stack<index>, $stack, $retval, $comm\n"
 #endif
 	"\t     type: s8/16/32/64, u8/16/32/64, x8/16/32/64, string, symbol,\n"
-	"\t           b<bit-width>@<bit-offset>/<container-size>,\n"
+	"\t           b<bit-width>@<bit-offset>/<container-size>, ustring,\n"
 	"\t           <type>\\[<array-size>\\]\n"
 #ifdef CONFIG_HIST_TRIGGERS
 	"\t    field: <stype> <name>;\n"
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 7d736248a070..439bf04d14ce 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -886,6 +886,15 @@ fetch_store_strlen(unsigned long addr)
 	return (ret < 0) ? ret : len;
 }
 
+/* Return the length of string -- including null terminal byte */
+static nokprobe_inline int
+fetch_store_strlen_user(unsigned long addr)
+{
+	const void __user *uaddr =  (__force const void __user *)addr;
+
+	return strnlen_unsafe_user(uaddr, MAX_STRING_SIZE);
+}
+
 /*
  * Fetch a null-terminated string. Caller MUST set *(u32 *)buf with max
  * length and relative data location.
@@ -894,19 +903,46 @@ static nokprobe_inline int
 fetch_store_string(unsigned long addr, void *dest, void *base)
 {
 	int maxlen = get_loc_len(*(u32 *)dest);
-	u8 *dst = get_loc_data(dest, base);
+	void *__dest;
 	long ret;
 
 	if (unlikely(!maxlen))
 		return -ENOMEM;
+
+	__dest = get_loc_data(dest, base);
+
 	/*
 	 * Try to get string again, since the string can be changed while
 	 * probing.
 	 */
-	ret = strncpy_from_unsafe(dst, (void *)addr, maxlen);
+	ret = strncpy_from_unsafe(__dest, (void *)addr, maxlen);
+	if (ret >= 0)
+		*(u32 *)dest = make_data_loc(ret, __dest - base);
+
+	return ret;
+}
 
+/*
+ * Fetch a null-terminated string from user. Caller MUST set *(u32 *)buf
+ * with max length and relative data location.
+ */
+static nokprobe_inline int
+fetch_store_string_user(unsigned long addr, void *dest, void *base)
+{
+	const void __user *uaddr =  (__force const void __user *)addr;
+	int maxlen = get_loc_len(*(u32 *)dest);
+	void *__dest;
+	long ret;
+
+	if (unlikely(!maxlen))
+		return -ENOMEM;
+
+	__dest = get_loc_data(dest, base);
+
+	ret = strncpy_from_unsafe_user(__dest, uaddr, maxlen);
 	if (ret >= 0)
-		*(u32 *)dest = make_data_loc(ret, (void *)dst - base);
+		*(u32 *)dest = make_data_loc(ret, __dest - base);
+
 	return ret;
 }
 
diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index a347faced959..5a0470f7b9de 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -78,6 +78,8 @@ static const struct fetch_type probe_fetch_types[] = {
 	/* Special types */
 	__ASSIGN_FETCH_TYPE("string", string, string, sizeof(u32), 1,
 			    "__data_loc char[]"),
+	__ASSIGN_FETCH_TYPE("ustring", string, string, sizeof(u32), 1,
+			    "__data_loc char[]"),
 	/* Basic types */
 	ASSIGN_FETCH_TYPE(u8,  u8,  0),
 	ASSIGN_FETCH_TYPE(u16, u16, 0),
@@ -569,7 +571,8 @@ static int traceprobe_parse_probe_arg_body(char *arg, ssize_t *size,
 		goto fail;
 
 	/* Store operation */
-	if (!strcmp(parg->type->name, "string")) {
+	if (!strcmp(parg->type->name, "string") ||
+	    !strcmp(parg->type->name, "ustring")) {
 		if (code->op != FETCH_OP_DEREF && code->op != FETCH_OP_IMM &&
 		    code->op != FETCH_OP_COMM) {
 			trace_probe_log_err(offset + (t ? (t - arg) : 0),
@@ -590,7 +593,11 @@ static int traceprobe_parse_probe_arg_body(char *arg, ssize_t *size,
 				goto fail;
 			}
 		}
-		code->op = FETCH_OP_ST_STRING;	/* In DEREF case, replace it */
+		/* If op == DEREF, replace it with STRING */
+		if (!strcmp(parg->type->name, "ustring"))
+			code->op = FETCH_OP_ST_USTRING;
+		else
+			code->op = FETCH_OP_ST_STRING;
 		code->size = parg->type->size;
 		parg->dynamic = true;
 	} else if (code->op == FETCH_OP_DEREF) {
@@ -618,7 +625,8 @@ static int traceprobe_parse_probe_arg_body(char *arg, ssize_t *size,
 	/* Loop(Array) operation */
 	if (parg->count) {
 		if (scode->op != FETCH_OP_ST_MEM &&
-		    scode->op != FETCH_OP_ST_STRING) {
+		    scode->op != FETCH_OP_ST_STRING &&
+		    scode->op != FETCH_OP_ST_USTRING) {
 			trace_probe_log_err(offset + (t ? (t - arg) : 0),
 					    BAD_STRING);
 			ret = -EINVAL;
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index f9a8c632188b..c7546e7ff8e2 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -96,6 +96,7 @@ enum fetch_op {
 	FETCH_OP_ST_RAW,	/* Raw: .size */
 	FETCH_OP_ST_MEM,	/* Mem: .offset, .size */
 	FETCH_OP_ST_STRING,	/* String: .offset, .size */
+	FETCH_OP_ST_USTRING,	/* User String: .offset, .size */
 	// Stage 4 (modify) op
 	FETCH_OP_MOD_BF,	/* Bitfield: .basesize, .lshift, .rshift */
 	// Stage 5 (loop) op
diff --git a/kernel/trace/trace_probe_tmpl.h b/kernel/trace/trace_probe_tmpl.h
index c30c61f12ddd..2e9e4dae8839 100644
--- a/kernel/trace/trace_probe_tmpl.h
+++ b/kernel/trace/trace_probe_tmpl.h
@@ -59,6 +59,9 @@ process_fetch_insn(struct fetch_insn *code, struct pt_regs *regs,
 static nokprobe_inline int fetch_store_strlen(unsigned long addr);
 static nokprobe_inline int
 fetch_store_string(unsigned long addr, void *dest, void *base);
+static nokprobe_inline int fetch_store_strlen_user(unsigned long addr);
+static nokprobe_inline int
+fetch_store_string_user(unsigned long addr, void *dest, void *base);
 static nokprobe_inline int
 probe_mem_read(void *dest, void *src, size_t size);
 
@@ -91,6 +94,10 @@ stage3:
 			ret = fetch_store_strlen(val + code->offset);
 			code++;
 			goto array;
+		} else if (code->op == FETCH_OP_ST_USTRING) {
+			ret += fetch_store_strlen_user(val + code->offset);
+			code++;
+			goto array;
 		} else
 			return -EILSEQ;
 	}
@@ -106,6 +113,10 @@ stage3:
 		loc = *(u32 *)dest;
 		ret = fetch_store_string(val + code->offset, dest, base);
 		break;
+	case FETCH_OP_ST_USTRING:
+		loc = *(u32 *)dest;
+		ret = fetch_store_string_user(val + code->offset, dest, base);
+		break;
 	default:
 		return -EILSEQ;
 	}
@@ -123,7 +134,8 @@ array:
 		total += ret;
 		if (++i < code->param) {
 			code = s3;
-			if (s3->op != FETCH_OP_ST_STRING) {
+			if (s3->op != FETCH_OP_ST_STRING &&
+			    s3->op != FETCH_OP_ST_USTRING) {
 				dest += s3->size;
 				val += s3->size;
 				goto stage3;
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index eb7e06b54741..852e998051f6 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -176,6 +176,12 @@ fetch_store_string(unsigned long addr, void *dest, void *base)
 	return ret;
 }
 
+static nokprobe_inline int
+fetch_store_string_user(unsigned long addr, void *dest, void *base)
+{
+	return fetch_store_string(addr, dest, base);
+}
+
 /* Return the length of string -- including null terminal byte */
 static nokprobe_inline int
 fetch_store_strlen(unsigned long addr)
@@ -191,6 +197,12 @@ fetch_store_strlen(unsigned long addr)
 	return (len > MAX_STRING_SIZE) ? 0 : len;
 }
 
+static nokprobe_inline int
+fetch_store_strlen_user(unsigned long addr)
+{
+	return fetch_store_strlen(addr);
+}
+
 static unsigned long translate_user_vaddr(unsigned long file_offset)
 {
 	unsigned long base_addr;
-- 
cgit v1.2.3


From e65f7ae7f4da56622ecf8f1eaed333b9a13f9435 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Wed, 15 May 2019 14:38:42 +0900
Subject: tracing/probe: Support user-space dereference

Support user-space dereference syntax for probe event arguments
to dereference the data-structure or array in user-space.

The syntax is just adding 'u' before an offset value.

 +|-u<OFFSET>(<FETCHARG>)

e.g. +u8(%ax), +u0(+0(%si))

For example, if you probe do_sched_setscheduler(pid, policy,
param) and record param->sched_priority, you can add new
probe as below;

 p do_sched_setscheduler priority=+u0($arg3)

Note that kprobe event provides this and it doesn't change the
dereference method automatically because we do not know whether
the given address is in userspace or kernel on some archs.

So as same as "ustring", this is an option for user, who has to
carefully choose the dereference method.

Link: http://lkml.kernel.org/r/155789872187.26965.4468456816590888687.stgit@devnote2

Acked-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 kernel/trace/trace.c            |  5 +++--
 kernel/trace/trace_kprobe.c     |  6 ++++++
 kernel/trace/trace_probe.c      | 25 ++++++++++++++++++-------
 kernel/trace/trace_probe.h      |  2 ++
 kernel/trace/trace_probe_tmpl.h | 22 +++++++++++++++++-----
 kernel/trace/trace_uprobe.c     |  7 +++++++
 6 files changed, 53 insertions(+), 14 deletions(-)

(limited to 'kernel')

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index d3a477a16e70..6b3b5b0495a8 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -4842,10 +4842,11 @@ static const char readme_msg[] =
 	"\t     args: <name>=fetcharg[:type]\n"
 	"\t fetcharg: %<register>, @<address>, @<symbol>[+|-<offset>],\n"
 #ifdef CONFIG_HAVE_FUNCTION_ARG_ACCESS_API
-	"\t           $stack<index>, $stack, $retval, $comm, $arg<N>\n"
+	"\t           $stack<index>, $stack, $retval, $comm, $arg<N>,\n"
 #else
-	"\t           $stack<index>, $stack, $retval, $comm\n"
+	"\t           $stack<index>, $stack, $retval, $comm,\n"
 #endif
+	"\t           +|-[u]<offset>(<fetcharg>)\n"
 	"\t     type: s8/16/32/64, u8/16/32/64, x8/16/32/64, string, symbol,\n"
 	"\t           b<bit-width>@<bit-offset>/<container-size>, ustring,\n"
 	"\t           <type>\\[<array-size>\\]\n"
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 439bf04d14ce..ff14eb011c1c 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -952,6 +952,12 @@ probe_mem_read(void *dest, void *src, size_t size)
 	return probe_kernel_read(dest, src, size);
 }
 
+static nokprobe_inline int
+probe_mem_read_user(void *dest, void *src, size_t size)
+{
+	return probe_user_read(dest, src, size);
+}
+
 /* Note that we don't verify it, since the code does not come from user space */
 static int
 process_fetch_insn(struct fetch_insn *code, struct pt_regs *regs, void *dest,
diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index 5a0470f7b9de..b6b0593844cd 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -324,6 +324,7 @@ parse_probe_arg(char *arg, const struct fetch_type *type,
 {
 	struct fetch_insn *code = *pcode;
 	unsigned long param;
+	int deref = FETCH_OP_DEREF;
 	long offset = 0;
 	char *tmp;
 	int ret = 0;
@@ -396,9 +397,14 @@ parse_probe_arg(char *arg, const struct fetch_type *type,
 		break;
 
 	case '+':	/* deref memory */
-		arg++;	/* Skip '+', because kstrtol() rejects it. */
-		/* fall through */
 	case '-':
+		if (arg[1] == 'u') {
+			deref = FETCH_OP_UDEREF;
+			arg[1] = arg[0];
+			arg++;
+		}
+		if (arg[0] == '+')
+			arg++;	/* Skip '+', because kstrtol() rejects it. */
 		tmp = strchr(arg, '(');
 		if (!tmp) {
 			trace_probe_log_err(offs, DEREF_NEED_BRACE);
@@ -434,7 +440,7 @@ parse_probe_arg(char *arg, const struct fetch_type *type,
 			}
 			*pcode = code;
 
-			code->op = FETCH_OP_DEREF;
+			code->op = deref;
 			code->offset = offset;
 		}
 		break;
@@ -573,14 +579,15 @@ static int traceprobe_parse_probe_arg_body(char *arg, ssize_t *size,
 	/* Store operation */
 	if (!strcmp(parg->type->name, "string") ||
 	    !strcmp(parg->type->name, "ustring")) {
-		if (code->op != FETCH_OP_DEREF && code->op != FETCH_OP_IMM &&
-		    code->op != FETCH_OP_COMM) {
+		if (code->op != FETCH_OP_DEREF && code->op != FETCH_OP_UDEREF &&
+		    code->op != FETCH_OP_IMM && code->op != FETCH_OP_COMM) {
 			trace_probe_log_err(offset + (t ? (t - arg) : 0),
 					    BAD_STRING);
 			ret = -EINVAL;
 			goto fail;
 		}
-		if (code->op != FETCH_OP_DEREF || parg->count) {
+		if ((code->op == FETCH_OP_IMM || code->op == FETCH_OP_COMM) ||
+		     parg->count) {
 			/*
 			 * IMM and COMM is pointing actual address, those must
 			 * be kept, and if parg->count != 0, this is an array
@@ -594,7 +601,8 @@ static int traceprobe_parse_probe_arg_body(char *arg, ssize_t *size,
 			}
 		}
 		/* If op == DEREF, replace it with STRING */
-		if (!strcmp(parg->type->name, "ustring"))
+		if (!strcmp(parg->type->name, "ustring") ||
+		    code->op == FETCH_OP_UDEREF)
 			code->op = FETCH_OP_ST_USTRING;
 		else
 			code->op = FETCH_OP_ST_STRING;
@@ -603,6 +611,9 @@ static int traceprobe_parse_probe_arg_body(char *arg, ssize_t *size,
 	} else if (code->op == FETCH_OP_DEREF) {
 		code->op = FETCH_OP_ST_MEM;
 		code->size = parg->type->size;
+	} else if (code->op == FETCH_OP_UDEREF) {
+		code->op = FETCH_OP_ST_UMEM;
+		code->size = parg->type->size;
 	} else {
 		code++;
 		if (code->op != FETCH_OP_NOP) {
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index c7546e7ff8e2..42816358dd48 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -92,9 +92,11 @@ enum fetch_op {
 	FETCH_OP_FOFFS,		/* File offset: .immediate */
 	// Stage 2 (dereference) op
 	FETCH_OP_DEREF,		/* Dereference: .offset */
+	FETCH_OP_UDEREF,	/* User-space Dereference: .offset */
 	// Stage 3 (store) ops
 	FETCH_OP_ST_RAW,	/* Raw: .size */
 	FETCH_OP_ST_MEM,	/* Mem: .offset, .size */
+	FETCH_OP_ST_UMEM,	/* Mem: .offset, .size */
 	FETCH_OP_ST_STRING,	/* String: .offset, .size */
 	FETCH_OP_ST_USTRING,	/* User String: .offset, .size */
 	// Stage 4 (modify) op
diff --git a/kernel/trace/trace_probe_tmpl.h b/kernel/trace/trace_probe_tmpl.h
index 2e9e4dae8839..e5282828f4a6 100644
--- a/kernel/trace/trace_probe_tmpl.h
+++ b/kernel/trace/trace_probe_tmpl.h
@@ -64,6 +64,8 @@ static nokprobe_inline int
 fetch_store_string_user(unsigned long addr, void *dest, void *base);
 static nokprobe_inline int
 probe_mem_read(void *dest, void *src, size_t size);
+static nokprobe_inline int
+probe_mem_read_user(void *dest, void *src, size_t size);
 
 /* From the 2nd stage, routine is same */
 static nokprobe_inline int
@@ -77,14 +79,21 @@ process_fetch_insn_bottom(struct fetch_insn *code, unsigned long val,
 
 stage2:
 	/* 2nd stage: dereference memory if needed */
-	while (code->op == FETCH_OP_DEREF) {
-		lval = val;
-		ret = probe_mem_read(&val, (void *)val + code->offset,
-					sizeof(val));
+	do {
+		if (code->op == FETCH_OP_DEREF) {
+			lval = val;
+			ret = probe_mem_read(&val, (void *)val + code->offset,
+					     sizeof(val));
+		} else if (code->op == FETCH_OP_UDEREF) {
+			lval = val;
+			ret = probe_mem_read_user(&val,
+				 (void *)val + code->offset, sizeof(val));
+		} else
+			break;
 		if (ret)
 			return ret;
 		code++;
-	}
+	} while (1);
 
 	s3 = code;
 stage3:
@@ -109,6 +118,9 @@ stage3:
 	case FETCH_OP_ST_MEM:
 		probe_mem_read(dest, (void *)val + code->offset, code->size);
 		break;
+	case FETCH_OP_ST_UMEM:
+		probe_mem_read_user(dest, (void *)val + code->offset, code->size);
+		break;
 	case FETCH_OP_ST_STRING:
 		loc = *(u32 *)dest;
 		ret = fetch_store_string(val + code->offset, dest, base);
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index 852e998051f6..3d6b868830f3 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -140,6 +140,13 @@ probe_mem_read(void *dest, void *src, size_t size)
 
 	return copy_from_user(dest, vaddr, size) ? -EFAULT : 0;
 }
+
+static nokprobe_inline int
+probe_mem_read_user(void *dest, void *src, size_t size)
+{
+	return probe_mem_read(dest, src, size);
+}
+
 /*
  * Fetch a null-terminated string. Caller MUST set *(u32 *)dest with max
  * length and relative data location.
-- 
cgit v1.2.3


From f08367b3643b5340f9d9ea07808ddd72b74beb30 Mon Sep 17 00:00:00 2001
From: Matthias Kaehlcke <mka@chromium.org>
Date: Thu, 23 May 2019 12:26:28 -0700
Subject: tracing: Use correct function name in trace_filter_add_remove_task()
 comment

The comment of trace_filter_add_remove_task() refers to the function as
'trace_pid_filter_add_remove_task', use the correct name.

Link: http://lkml.kernel.org/r/20190523192628.134406-1-mka@chromium.org

Signed-off-by: Matthias Kaehlcke <mka@chromium.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 kernel/trace/trace.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'kernel')

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 6b3b5b0495a8..77b9c4ca5faa 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -366,7 +366,7 @@ trace_ignore_this_task(struct trace_pid_list *filtered_pids, struct task_struct
 }
 
 /**
- * trace_pid_filter_add_remove_task - Add or remove a task from a pid_list
+ * trace_filter_add_remove_task - Add or remove a task from a pid_list
  * @pid_list: The list to modify
  * @self: The current task for fork or NULL for exit
  * @task: The task to add or remove
-- 
cgit v1.2.3


From 539b75b2b9eece3fc6da5672d4b67440d5e454a9 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Wed, 22 May 2019 17:27:52 +0900
Subject: tracing/kprobe: Cast user-space address correctly

Cast user-space address correctly to pass to probe_user_read().

Reported-by: kbuild test robot <lkp@intel.com>
Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 kernel/trace/trace_kprobe.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'kernel')

diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index ff14eb011c1c..2c5357dddb92 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -955,7 +955,9 @@ probe_mem_read(void *dest, void *src, size_t size)
 static nokprobe_inline int
 probe_mem_read_user(void *dest, void *src, size_t size)
 {
-	return probe_user_read(dest, src, size);
+	const void __user *uaddr =  (__force const void __user *)src;
+
+	return probe_user_read(dest, uaddr, size);
 }
 
 /* Note that we don't verify it, since the code does not come from user space */
-- 
cgit v1.2.3


From b5f8b32c93b21c457a958d2a6bf938dab41bac4e Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Wed, 22 May 2019 17:32:27 +0900
Subject: kprobes: Initialize kprobes at postcore_initcall

Initialize kprobes at postcore_initcall level instead of module_init
since kprobes is not a module, and it depends on only subsystems
initialized in core_initcall.
This will allow ftrace kprobe event to add new events when it is
initializing because ftrace kprobe event is initialized at
later initcall level.

Link: http://lkml.kernel.org/r/155851394736.15728.13626739508905120098.stgit@devnote2

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 kernel/kprobes.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

(limited to 'kernel')

diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index b1ea30a5540e..54aaaad00a47 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -2289,6 +2289,7 @@ static int __init init_kprobes(void)
 		init_test_probes();
 	return err;
 }
+postcore_initcall(init_kprobes);
 
 #ifdef CONFIG_DEBUG_FS
 static void report_probe(struct seq_file *pi, struct kprobe *p,
@@ -2614,5 +2615,3 @@ error:
 
 late_initcall(debugfs_kprobe_init);
 #endif /* CONFIG_DEBUG_FS */
-
-module_init(init_kprobes);
-- 
cgit v1.2.3


From 970988e19eb0a0dc24fe14bf91972019e48336e2 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Wed, 22 May 2019 17:32:35 +0900
Subject: tracing/kprobe: Add kprobe_event= boot parameter

Add kprobe_event= boot parameter to define kprobe events
at boot time.
The definition syntax is similar to tracefs/kprobe_events
interface, but use ',' and ';' instead of ' ' and '\n'
respectively. e.g.

  kprobe_event=p,vfs_read,$arg1,$arg2

This puts a probe on vfs_read with argument1 and 2, and
enable the new event.

Link: http://lkml.kernel.org/r/155851395498.15728.830529496248543583.stgit@devnote2

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 kernel/trace/trace_kprobe.c | 54 +++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 54 insertions(+)

(limited to 'kernel')

diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 2c5357dddb92..004fffd24ec1 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -12,6 +12,8 @@
 #include <linux/rculist.h>
 #include <linux/error-injection.h>
 
+#include <asm/setup.h>  /* for COMMAND_LINE_SIZE */
+
 #include "trace_dynevent.h"
 #include "trace_kprobe_selftest.h"
 #include "trace_probe.h"
@@ -19,6 +21,17 @@
 
 #define KPROBE_EVENT_SYSTEM "kprobes"
 #define KRETPROBE_MAXACTIVE_MAX 4096
+#define MAX_KPROBE_CMDLINE_SIZE 1024
+
+/* Kprobe early definition from command line */
+static char kprobe_boot_events_buf[COMMAND_LINE_SIZE] __initdata;
+
+static int __init set_kprobe_boot_events(char *str)
+{
+	strlcpy(kprobe_boot_events_buf, str, COMMAND_LINE_SIZE);
+	return 0;
+}
+__setup("kprobe_event=", set_kprobe_boot_events);
 
 static int trace_kprobe_create(int argc, const char **argv);
 static int trace_kprobe_show(struct seq_file *m, struct dyn_event *ev);
@@ -1494,6 +1507,44 @@ void destroy_local_trace_kprobe(struct trace_event_call *event_call)
 }
 #endif /* CONFIG_PERF_EVENTS */
 
+static __init void enable_boot_kprobe_events(void)
+{
+	struct trace_array *tr = top_trace_array();
+	struct trace_event_file *file;
+	struct trace_kprobe *tk;
+	struct dyn_event *pos;
+
+	mutex_lock(&event_mutex);
+	for_each_trace_kprobe(tk, pos) {
+		list_for_each_entry(file, &tr->events, list)
+			if (file->event_call == &tk->tp.call)
+				trace_event_enable_disable(file, 1, 0);
+	}
+	mutex_unlock(&event_mutex);
+}
+
+static __init void setup_boot_kprobe_events(void)
+{
+	char *p, *cmd = kprobe_boot_events_buf;
+	int ret;
+
+	strreplace(kprobe_boot_events_buf, ',', ' ');
+
+	while (cmd && *cmd != '\0') {
+		p = strchr(cmd, ';');
+		if (p)
+			*p++ = '\0';
+
+		ret = trace_run_command(cmd, create_or_delete_trace_kprobe);
+		if (ret)
+			pr_warn("Failed to add event(%d): %s\n", ret, cmd);
+
+		cmd = p;
+	}
+
+	enable_boot_kprobe_events();
+}
+
 /* Make a tracefs interface for controlling probe points */
 static __init int init_kprobe_trace(void)
 {
@@ -1525,6 +1576,9 @@ static __init int init_kprobe_trace(void)
 
 	if (!entry)
 		pr_warn("Could not create tracefs 'kprobe_profile' entry\n");
+
+	setup_boot_kprobe_events();
+
 	return 0;
 }
 fs_initcall(init_kprobe_trace);
-- 
cgit v1.2.3


From b3015fe41d9af7515a7b7b6f7f8f172d193fb3a6 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>
Date: Thu, 23 May 2019 19:40:17 -0400
Subject: tracing: Make a separate config for trace event self tests

The trace event self tests enable loop through *all* events, enables each
one, one at a time, runs some code to trigger various events (not
necessarily the same events), and checks if anything went wrong. The issue
is that trace events are usually the least likely start up test to cause a
problem, but they take the longest to run (because there are so many
events). When one of the other tests trigger a bug, the trace event start up
tests causes the bisect to take much longer, because it takes 10s of seconds
to get through the trace event tests.

By making them a separate config (even though they are enabled by default if
start up tests are set), it is possible to turn them off and still run the
other tracing start up tests much quicker.

Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 kernel/trace/Kconfig        | 12 +++++++++++-
 kernel/trace/trace_events.c |  2 +-
 2 files changed, 12 insertions(+), 2 deletions(-)

(limited to 'kernel')

diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 5d965cef6c77..07d22c61b634 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -596,9 +596,19 @@ config FTRACE_STARTUP_TEST
 	  functioning properly. It will do tests on all the configured
 	  tracers of ftrace.
 
+config EVENT_TRACE_STARTUP_TEST
+	bool "Run selftest on trace events"
+	depends on FTRACE_STARTUP_TEST
+	default y
+	help
+	  This option performs a test on all trace events in the system.
+	  It basically just enables each event and runs some code that
+	  will trigger events (not necessarily the event it enables)
+	  This may take some time run as there are a lot of events.
+
 config EVENT_TRACE_TEST_SYSCALLS
 	bool "Run selftest on syscall events"
-	depends on FTRACE_STARTUP_TEST
+	depends on EVENT_TRACE_STARTUP_TEST
 	help
 	 This option will also enable testing every syscall event.
 	 It only enables the event and disables it and runs various loads
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 0ce3db67f556..edc72f3b080c 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -3190,7 +3190,7 @@ void __init trace_event_init(void)
 	event_trace_enable();
 }
 
-#ifdef CONFIG_FTRACE_STARTUP_TEST
+#ifdef CONFIG_EVENT_TRACE_STARTUP_TEST
 
 static DEFINE_SPINLOCK(test_spinlock);
 static DEFINE_SPINLOCK(test_spinlock_irq);
-- 
cgit v1.2.3


From b6399cc789341fc49a0603fb7d388a4e50aca212 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>
Date: Thu, 23 May 2019 19:50:34 -0400
Subject: tracing/kprobe: Do not run kprobe boot tests if kprobe_event is on
 cmdline

When having kprobe trace event start up tests enabled and adding a
kprobe_event on the kernel command line, it produced the following:

 trace_kprobe: Testing kprobe tracing:
 WARNING: CPU: 5 PID: 1 at kernel/trace/trace_kprobe.c:1724 kprobe_trace_self_tests_init+0x32d/0x36b
 Modules linked in:
 CPU: 5 PID: 1 Comm: swapper/0 Not tainted 5.2.0-rc1-test+ #249
 Hardware name: Hewlett-Packard HP Compaq Pro 6300 SFF/339A, BIOS K01 v03.03 07/14/2016
 RIP: 0010:kprobe_trace_self_tests_init+0x32d/0x36b
 Code: b7 e8 4f 8d a2 fe 85 c0 74 10 0f 0b 48 c7 c7 c8 1b 0d b7 ff c3 e8 19 af 99 fe 48 c7 c7 40 93 27 b7 e8 7f 1a a5 fe 85 c0 74 10 <0f> 0b 48 c7 c7 f8 1b 0d b7 ff c3 e8 f9 ae
9 a0 fe 85
 RSP: 0018:ffffb36e40653e08 EFLAGS: 00010286
 RAX: 00000000fffffff0 RBX: 0000000000000000 RCX: ffffb36e40653d5c
 RDX: 0000000000000000 RSI: ffffffffb72776e0 RDI: 0000000000000246
 RBP: ffff98414fe58ff8 R08: 0000000000000000 R09: 0000000000000000
 R10: 0000000000000000 R11: ffff98415d8aa940 R12: 0000000000000000
 R13: ffffffffb737c1b0 R14: 0000000000000000 R15: 0000000000000000
 FS:  0000000000000000(0000) GS:ffff98415ea80000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 00007f959ce741b8 CR3: 000000011a210002 CR4: 00000000001606e0
 Call Trace:
  ? init_kprobe_trace+0x19e/0x19e
  ? do_early_param+0x8e/0x8e
  do_one_initcall+0x6f/0x2b4
  ? do_early_param+0x8e/0x8e
  kernel_init_freeable+0x21d/0x2c6
  ? rest_init+0x146/0x146
  kernel_init+0xa/0x10a
  ret_from_fork+0x3a/0x50
 ---[ end trace 488430c083a4c956 ]---

As with the trace events, if a trace event is set on the kernel command
line, the trace events start up tests are suspended. The kprobe start up
tests should do the same when a kprobe is enabled on the kernel command
line.

Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 kernel/trace/trace_kprobe.c | 8 ++++++++
 1 file changed, 8 insertions(+)

(limited to 'kernel')

diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 004fffd24ec1..7958da2fd922 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -25,6 +25,7 @@
 
 /* Kprobe early definition from command line */
 static char kprobe_boot_events_buf[COMMAND_LINE_SIZE] __initdata;
+static bool kprobe_boot_events_enabled __initdata;
 
 static int __init set_kprobe_boot_events(char *str)
 {
@@ -1538,6 +1539,8 @@ static __init void setup_boot_kprobe_events(void)
 		ret = trace_run_command(cmd, create_or_delete_trace_kprobe);
 		if (ret)
 			pr_warn("Failed to add event(%d): %s\n", ret, cmd);
+		else
+			kprobe_boot_events_enabled = true;
 
 		cmd = p;
 	}
@@ -1611,6 +1614,11 @@ static __init int kprobe_trace_self_tests_init(void)
 	if (tracing_is_disabled())
 		return -ENODEV;
 
+	if (kprobe_boot_events_enabled) {
+		pr_info("Skipping kprobe tests due to kprobe_event on cmdline\n");
+		return 0;
+	}
+
 	target = kprobe_trace_selftest_target;
 
 	pr_info("Testing kprobe tracing: ");
-- 
cgit v1.2.3


From a124692b698b00026a58d89831ceda2331b2e1d0 Mon Sep 17 00:00:00 2001
From: Cheng Jian <cj.chengjian@huawei.com>
Date: Sat, 4 May 2019 19:39:39 +0800
Subject: ftrace: Enable trampoline when rec count returns back to one

Custom trampolines can only be enabled if there is only a single ops
attached to it. If there's only a single callback registered to a function,
and the ops has a trampoline registered for it, then we can call the
trampoline directly. This is very useful for improving the performance of
ftrace and livepatch.

If more than one callback is registered to a function, the general
trampoline is used, and the custom trampoline is not restored back to the
direct call even if all the other callbacks were unregistered and we are
back to one callback for the function.

To fix this, set FTRACE_FL_TRAMP flag if rec count is decremented
to one, and the ops that left has a trampoline.

Testing After this patch :

insmod livepatch_unshare_files.ko
cat /sys/kernel/debug/tracing/enabled_functions

	unshare_files (1) R I	tramp: 0xffffffffc0000000(klp_ftrace_handler+0x0/0xa0) ->ftrace_ops_assist_func+0x0/0xf0

echo unshare_files > /sys/kernel/debug/tracing/set_ftrace_filter
echo function > /sys/kernel/debug/tracing/current_tracer
cat /sys/kernel/debug/tracing/enabled_functions

	unshare_files (2) R I ->ftrace_ops_list_func+0x0/0x150

echo nop > /sys/kernel/debug/tracing/current_tracer
cat /sys/kernel/debug/tracing/enabled_functions

	unshare_files (1) R I	tramp: 0xffffffffc0000000(klp_ftrace_handler+0x0/0xa0) ->ftrace_ops_assist_func+0x0/0xf0

Link: http://lkml.kernel.org/r/1556969979-111047-1-git-send-email-cj.chengjian@huawei.com

Signed-off-by: Cheng Jian <cj.chengjian@huawei.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 kernel/trace/ftrace.c | 28 +++++++++++++++-------------
 1 file changed, 15 insertions(+), 13 deletions(-)

(limited to 'kernel')

diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 4f2c26bebe2a..5c3eadb143ed 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1622,6 +1622,11 @@ static bool test_rec_ops_needs_regs(struct dyn_ftrace *rec)
 	return  keep_regs;
 }
 
+static struct ftrace_ops *
+ftrace_find_tramp_ops_any(struct dyn_ftrace *rec);
+static struct ftrace_ops *
+ftrace_find_tramp_ops_next(struct dyn_ftrace *rec, struct ftrace_ops *ops);
+
 static bool __ftrace_hash_rec_update(struct ftrace_ops *ops,
 				     int filter_hash,
 				     bool inc)
@@ -1750,15 +1755,17 @@ static bool __ftrace_hash_rec_update(struct ftrace_ops *ops,
 			}
 
 			/*
-			 * If the rec had TRAMP enabled, then it needs to
-			 * be cleared. As TRAMP can only be enabled iff
-			 * there is only a single ops attached to it.
-			 * In otherwords, always disable it on decrementing.
-			 * In the future, we may set it if rec count is
-			 * decremented to one, and the ops that is left
-			 * has a trampoline.
+			 * The TRAMP needs to be set only if rec count
+			 * is decremented to one, and the ops that is
+			 * left has a trampoline. As TRAMP can only be
+			 * enabled if there is only a single ops attached
+			 * to it.
 			 */
-			rec->flags &= ~FTRACE_FL_TRAMP;
+			if (ftrace_rec_count(rec) == 1 &&
+			    ftrace_find_tramp_ops_any(rec))
+				rec->flags |= FTRACE_FL_TRAMP;
+			else
+				rec->flags &= ~FTRACE_FL_TRAMP;
 
 			/*
 			 * flags will be cleared in ftrace_check_record()
@@ -1951,11 +1958,6 @@ static void print_ip_ins(const char *fmt, const unsigned char *p)
 		printk(KERN_CONT "%s%02x", i ? ":" : "", p[i]);
 }
 
-static struct ftrace_ops *
-ftrace_find_tramp_ops_any(struct dyn_ftrace *rec);
-static struct ftrace_ops *
-ftrace_find_tramp_ops_next(struct dyn_ftrace *rec, struct ftrace_ops *ops);
-
 enum ftrace_bug_type ftrace_bug_type;
 const void *ftrace_expected;
 
-- 
cgit v1.2.3


From 86b3de60a0b634cdcef82d0a2091bc5444a00020 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>
Date: Tue, 28 May 2019 09:36:19 -0400
Subject: ring-buffer: Remove HAVE_64BIT_ALIGNED_ACCESS

Commit c19fa94a8fed ("Add HAVE_64BIT_ALIGNED_ACCESS") added the config for
architectures that required 64bit aligned access for all 64bit words. As
the ftrace ring buffer stores data on 4 byte alignment, this config option
was used to force it to store data on 8 byte alignment to make sure the data
being stored and written directly into the ring buffer was 8 byte aligned as
it would cause issues trying to write an 8 byte word on a 4 not 8 byte
aligned memory location.

But with the removal of the metag architecture, which was the only
architecture to use this, there is no architecture supported by Linux that
requires 8 byte aligne access for all 8 byte words (4 byte alignment is good
enough). Removing this config can simplify the code a bit.

Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 kernel/trace/ring_buffer.c | 17 ++++-------------
 1 file changed, 4 insertions(+), 13 deletions(-)

(limited to 'kernel')

diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 05b0b3139ebc..66358d66c933 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -128,16 +128,7 @@ int ring_buffer_print_entry_header(struct trace_seq *s)
 #define RB_ALIGNMENT		4U
 #define RB_MAX_SMALL_DATA	(RB_ALIGNMENT * RINGBUF_TYPE_DATA_TYPE_LEN_MAX)
 #define RB_EVNT_MIN_SIZE	8U	/* two 32bit words */
-
-#ifndef CONFIG_HAVE_64BIT_ALIGNED_ACCESS
-# define RB_FORCE_8BYTE_ALIGNMENT	0
-# define RB_ARCH_ALIGNMENT		RB_ALIGNMENT
-#else
-# define RB_FORCE_8BYTE_ALIGNMENT	1
-# define RB_ARCH_ALIGNMENT		8U
-#endif
-
-#define RB_ALIGN_DATA		__aligned(RB_ARCH_ALIGNMENT)
+#define RB_ALIGN_DATA		__aligned(RB_ALIGNMENT)
 
 /* define RINGBUF_TYPE_DATA for 'case RINGBUF_TYPE_DATA:' */
 #define RINGBUF_TYPE_DATA 0 ... RINGBUF_TYPE_DATA_TYPE_LEN_MAX
@@ -2373,7 +2364,7 @@ rb_update_event(struct ring_buffer_per_cpu *cpu_buffer,
 
 	event->time_delta = delta;
 	length -= RB_EVNT_HDR_SIZE;
-	if (length > RB_MAX_SMALL_DATA || RB_FORCE_8BYTE_ALIGNMENT) {
+	if (length > RB_MAX_SMALL_DATA) {
 		event->type_len = 0;
 		event->array[0] = length;
 	} else
@@ -2388,11 +2379,11 @@ static unsigned rb_calculate_event_length(unsigned length)
 	if (!length)
 		length++;
 
-	if (length > RB_MAX_SMALL_DATA || RB_FORCE_8BYTE_ALIGNMENT)
+	if (length > RB_MAX_SMALL_DATA)
 		length += sizeof(event.array[0]);
 
 	length += RB_EVNT_HDR_SIZE;
-	length = ALIGN(length, RB_ARCH_ALIGNMENT);
+	length = ALIGN(length, RB_ALIGNMENT);
 
 	/*
 	 * In case the time delta is larger than the 27 bits for it
-- 
cgit v1.2.3


From f0553dcb9778c343641d3a41f1db01be02e7551b Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Mon, 10 Jun 2019 16:22:19 -0500
Subject: tracepoint: Use struct_size() in kmalloc()

One of the more common cases of allocation size calculations is finding
the size of a structure that has a zero-sized array at the end, along
with memory for some number of elements for that array. For example:

struct tp_probes {
	...
        struct tracepoint_func probes[0];
};

instance = kmalloc(sizeof(sizeof(struct tp_probes) +
			sizeof(struct tracepoint_func) * count, GFP_KERNEL);

Instead of leaving these open-coded and prone to type mistakes, we can
now use the new struct_size() helper:

instance = kmalloc(struct_size(instance, probes, count) GFP_KERNEL);

This code was detected with the help of Coccinelle.

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 kernel/tracepoint.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'kernel')

diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c
index 46f2ab1e08a9..fb9353ed901b 100644
--- a/kernel/tracepoint.c
+++ b/kernel/tracepoint.c
@@ -68,8 +68,8 @@ struct tp_probes {
 
 static inline void *allocate_probes(int count)
 {
-	struct tp_probes *p  = kmalloc(count * sizeof(struct tracepoint_func)
-			+ sizeof(struct tp_probes), GFP_KERNEL);
+	struct tp_probes *p  = kmalloc(struct_size(p, probes, count),
+				       GFP_KERNEL);
 	return p == NULL ? NULL : p->probes;
 }
 
-- 
cgit v1.2.3


From 65fc965c708c90b8c8b2cea980db0618333dd7fe Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Mon, 3 Jun 2019 22:04:42 +0900
Subject: kprobes: Fix to init kprobes in subsys_initcall

Since arm64 kernel initializes breakpoint trap vector in arch_initcall(),
initializing kprobe (and run smoke test) in postcore_initcall() causes
a kernel panic.

To fix this issue, move the kprobe initialization in subsys_initcall()
(which is called right afer the arch_initcall).

In-kernel kprobe users (ftrace and bpf) are using fs_initcall() which is
called after subsys_initcall(), so this shouldn't cause more problem.

Link: http://lkml.kernel.org/r/155956708268.12228.10363800793132214198.stgit@devnote2
Link: http://lkml.kernel.org/r/20190709153755.GB10123@lakrids.cambridge.arm.com

Reported-by: Anders Roxell <anders.roxell@linaro.org>
Fixes: b5f8b32c93b2 ("kprobes: Initialize kprobes at postcore_initcall")
Tested-by: Anders Roxell <anders.roxell@linaro.org>
Tested-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 kernel/kprobes.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'kernel')

diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 54aaaad00a47..5471efbeb937 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -2289,7 +2289,7 @@ static int __init init_kprobes(void)
 		init_test_probes();
 	return err;
 }
-postcore_initcall(init_kprobes);
+subsys_initcall(init_kprobes);
 
 #ifdef CONFIG_DEBUG_FS
 static void report_probe(struct seq_file *pi, struct kprobe *p,
-- 
cgit v1.2.3


From f730e0f2da4d0035775ab3c85757fee37bb9cbbe Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Sat, 1 Jun 2019 00:16:46 +0900
Subject: tracing/kprobe: Set print format right after parsed command

Set event call's print format right after parsed command for
simplifying (un)register_kprobe_event().

Link: http://lkml.kernel.org/r/155931580625.28323.5158822928646225903.stgit@devnote2

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 kernel/trace/trace_kprobe.c | 25 +++++++++----------------
 1 file changed, 9 insertions(+), 16 deletions(-)

(limited to 'kernel')

diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 7958da2fd922..01fc49f08b70 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -272,6 +272,7 @@ static void free_trace_kprobe(struct trace_kprobe *tk)
 
 	kfree(tk->tp.call.class->system);
 	kfree(tk->tp.call.name);
+	kfree(tk->tp.call.print_fmt);
 	kfree(tk->symbol);
 	free_percpu(tk->nhit);
 	kfree(tk);
@@ -730,6 +731,10 @@ static int trace_kprobe_create(int argc, const char *argv[])
 			goto error;	/* This can be -ENOMEM */
 	}
 
+	ret = traceprobe_set_print_fmt(&tk->tp, is_return);
+	if (ret < 0)
+		goto error;
+
 	ret = register_trace_kprobe(tk);
 	if (ret) {
 		trace_probe_log_set_index(1);
@@ -1416,18 +1421,14 @@ static int register_kprobe_event(struct trace_kprobe *tk)
 
 	init_trace_event_call(tk, call);
 
-	if (traceprobe_set_print_fmt(&tk->tp, trace_kprobe_is_return(tk)) < 0)
-		return -ENOMEM;
 	ret = register_trace_event(&call->event);
-	if (!ret) {
-		kfree(call->print_fmt);
+	if (!ret)
 		return -ENODEV;
-	}
+
 	ret = trace_add_event_call(call);
 	if (ret) {
 		pr_info("Failed to register kprobe event: %s\n",
 			trace_event_name(call));
-		kfree(call->print_fmt);
 		unregister_trace_event(&call->event);
 	}
 	return ret;
@@ -1435,13 +1436,8 @@ static int register_kprobe_event(struct trace_kprobe *tk)
 
 static int unregister_kprobe_event(struct trace_kprobe *tk)
 {
-	int ret;
-
 	/* tp->event is unregistered in trace_remove_event_call() */
-	ret = trace_remove_event_call(&tk->tp.call);
-	if (!ret)
-		kfree(tk->tp.call.print_fmt);
-	return ret;
+	return trace_remove_event_call(&tk->tp.call);
 }
 
 #ifdef CONFIG_PERF_EVENTS
@@ -1479,10 +1475,8 @@ create_local_trace_kprobe(char *func, void *addr, unsigned long offs,
 	}
 
 	ret = __register_trace_kprobe(tk);
-	if (ret < 0) {
-		kfree(tk->tp.call.print_fmt);
+	if (ret < 0)
 		goto error;
-	}
 
 	return &tk->tp.call;
 error:
@@ -1503,7 +1497,6 @@ void destroy_local_trace_kprobe(struct trace_event_call *event_call)
 
 	__unregister_trace_kprobe(tk);
 
-	kfree(tk->tp.call.print_fmt);
 	free_trace_kprobe(tk);
 }
 #endif /* CONFIG_PERF_EVENTS */
-- 
cgit v1.2.3


From b4d4b96be89466049a0d383d019edc1403bf0ba9 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Sat, 1 Jun 2019 00:16:56 +0900
Subject: tracing/uprobe: Set print format when parsing command

Set event call's print format right after parsed command for
simplifying (un)register_uprobe_event().

Link: http://lkml.kernel.org/r/155931581659.28323.5404667166417404076.stgit@devnote2

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 kernel/trace/trace_uprobe.c | 25 +++++++------------------
 1 file changed, 7 insertions(+), 18 deletions(-)

(limited to 'kernel')

diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index 3d6b868830f3..34ce671b6080 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -345,6 +345,7 @@ static void free_trace_uprobe(struct trace_uprobe *tu)
 	path_put(&tu->path);
 	kfree(tu->tp.call.class->system);
 	kfree(tu->tp.call.name);
+	kfree(tu->tp.call.print_fmt);
 	kfree(tu->filename);
 	kfree(tu);
 }
@@ -592,6 +593,10 @@ static int trace_uprobe_create(int argc, const char **argv)
 			goto error;
 	}
 
+	ret = traceprobe_set_print_fmt(&tu->tp, is_ret_probe(tu));
+	if (ret < 0)
+		goto error;
+
 	ret = register_trace_uprobe(tu);
 	if (!ret)
 		goto out;
@@ -1362,21 +1367,15 @@ static int register_uprobe_event(struct trace_uprobe *tu)
 
 	init_trace_event_call(tu, call);
 
-	if (traceprobe_set_print_fmt(&tu->tp, is_ret_probe(tu)) < 0)
-		return -ENOMEM;
-
 	ret = register_trace_event(&call->event);
-	if (!ret) {
-		kfree(call->print_fmt);
+	if (!ret)
 		return -ENODEV;
-	}
 
 	ret = trace_add_event_call(call);
 
 	if (ret) {
 		pr_info("Failed to register uprobe event: %s\n",
 			trace_event_name(call));
-		kfree(call->print_fmt);
 		unregister_trace_event(&call->event);
 	}
 
@@ -1385,15 +1384,8 @@ static int register_uprobe_event(struct trace_uprobe *tu)
 
 static int unregister_uprobe_event(struct trace_uprobe *tu)
 {
-	int ret;
-
 	/* tu->event is unregistered in trace_remove_event_call() */
-	ret = trace_remove_event_call(&tu->tp.call);
-	if (ret)
-		return ret;
-	kfree(tu->tp.call.print_fmt);
-	tu->tp.call.print_fmt = NULL;
-	return 0;
+	return trace_remove_event_call(&tu->tp.call);
 }
 
 #ifdef CONFIG_PERF_EVENTS
@@ -1452,9 +1444,6 @@ void destroy_local_trace_uprobe(struct trace_event_call *event_call)
 
 	tu = container_of(event_call, struct trace_uprobe, tp.call);
 
-	kfree(tu->tp.call.print_fmt);
-	tu->tp.call.print_fmt = NULL;
-
 	free_trace_uprobe(tu);
 }
 #endif /* CONFIG_PERF_EVENTS */
-- 
cgit v1.2.3


From 455b289973f7df350ea179c7eb8bfed0c766ec40 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Sat, 1 Jun 2019 00:17:06 +0900
Subject: tracing/probe: Add trace_probe init and free functions

Add common trace_probe init and cleanup function in
trace_probe.c, and use it from trace_kprobe.c and trace_uprobe.c

Link: http://lkml.kernel.org/r/155931582664.28323.5934870189034740822.stgit@devnote2

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 kernel/trace/trace_kprobe.c | 49 ++++++++++++---------------------------------
 kernel/trace/trace_probe.c  | 36 +++++++++++++++++++++++++++++++++
 kernel/trace/trace_probe.h  |  4 ++++
 kernel/trace/trace_uprobe.c | 27 +++++--------------------
 4 files changed, 58 insertions(+), 58 deletions(-)

(limited to 'kernel')

diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 01fc49f08b70..c43c2d419ded 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -197,6 +197,16 @@ static int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs);
 static int kretprobe_dispatcher(struct kretprobe_instance *ri,
 				struct pt_regs *regs);
 
+static void free_trace_kprobe(struct trace_kprobe *tk)
+{
+	if (tk) {
+		trace_probe_cleanup(&tk->tp);
+		kfree(tk->symbol);
+		free_percpu(tk->nhit);
+		kfree(tk);
+	}
+}
+
 /*
  * Allocate new trace_probe and initialize it (including kprobes).
  */
@@ -235,49 +245,17 @@ static struct trace_kprobe *alloc_trace_kprobe(const char *group,
 
 	tk->rp.maxactive = maxactive;
 
-	if (!event || !group) {
-		ret = -EINVAL;
-		goto error;
-	}
-
-	tk->tp.call.class = &tk->tp.class;
-	tk->tp.call.name = kstrdup(event, GFP_KERNEL);
-	if (!tk->tp.call.name)
-		goto error;
-
-	tk->tp.class.system = kstrdup(group, GFP_KERNEL);
-	if (!tk->tp.class.system)
+	ret = trace_probe_init(&tk->tp, event, group);
+	if (ret < 0)
 		goto error;
 
 	dyn_event_init(&tk->devent, &trace_kprobe_ops);
-	INIT_LIST_HEAD(&tk->tp.files);
 	return tk;
 error:
-	kfree(tk->tp.call.name);
-	kfree(tk->symbol);
-	free_percpu(tk->nhit);
-	kfree(tk);
+	free_trace_kprobe(tk);
 	return ERR_PTR(ret);
 }
 
-static void free_trace_kprobe(struct trace_kprobe *tk)
-{
-	int i;
-
-	if (!tk)
-		return;
-
-	for (i = 0; i < tk->tp.nr_args; i++)
-		traceprobe_free_probe_arg(&tk->tp.args[i]);
-
-	kfree(tk->tp.call.class->system);
-	kfree(tk->tp.call.name);
-	kfree(tk->tp.call.print_fmt);
-	kfree(tk->symbol);
-	free_percpu(tk->nhit);
-	kfree(tk);
-}
-
 static struct trace_kprobe *find_trace_kprobe(const char *event,
 					      const char *group)
 {
@@ -1400,7 +1378,6 @@ static struct trace_event_functions kprobe_funcs = {
 static inline void init_trace_event_call(struct trace_kprobe *tk,
 					 struct trace_event_call *call)
 {
-	INIT_LIST_HEAD(&call->class->fields);
 	if (trace_kprobe_is_return(tk)) {
 		call->event.funcs = &kretprobe_funcs;
 		call->class->define_fields = kretprobe_event_define_fields;
diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index b6b0593844cd..fe4ee2e73d92 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -884,3 +884,39 @@ int traceprobe_define_arg_fields(struct trace_event_call *event_call,
 	}
 	return 0;
 }
+
+
+void trace_probe_cleanup(struct trace_probe *tp)
+{
+	int i;
+
+	for (i = 0; i < tp->nr_args; i++)
+		traceprobe_free_probe_arg(&tp->args[i]);
+
+	kfree(tp->call.class->system);
+	kfree(tp->call.name);
+	kfree(tp->call.print_fmt);
+}
+
+int trace_probe_init(struct trace_probe *tp, const char *event,
+		     const char *group)
+{
+	if (!event || !group)
+		return -EINVAL;
+
+	tp->call.class = &tp->class;
+	tp->call.name = kstrdup(event, GFP_KERNEL);
+	if (!tp->call.name)
+		return -ENOMEM;
+
+	tp->class.system = kstrdup(group, GFP_KERNEL);
+	if (!tp->class.system) {
+		kfree(tp->call.name);
+		tp->call.name = NULL;
+		return -ENOMEM;
+	}
+	INIT_LIST_HEAD(&tp->files);
+	INIT_LIST_HEAD(&tp->class.fields);
+
+	return 0;
+}
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index 42816358dd48..818b1d7693ba 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -248,6 +248,10 @@ static inline bool trace_probe_is_registered(struct trace_probe *tp)
 	return !!(tp->flags & TP_FLAG_REGISTERED);
 }
 
+int trace_probe_init(struct trace_probe *tp, const char *event,
+		     const char *group);
+void trace_probe_cleanup(struct trace_probe *tp);
+
 /* Check the name is good for event/group/fields */
 static inline bool is_good_name(const char *name)
 {
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index 34ce671b6080..b18b7eb1a76f 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -300,25 +300,17 @@ static struct trace_uprobe *
 alloc_trace_uprobe(const char *group, const char *event, int nargs, bool is_ret)
 {
 	struct trace_uprobe *tu;
-
-	if (!event || !group)
-		return ERR_PTR(-EINVAL);
+	int ret;
 
 	tu = kzalloc(SIZEOF_TRACE_UPROBE(nargs), GFP_KERNEL);
 	if (!tu)
 		return ERR_PTR(-ENOMEM);
 
-	tu->tp.call.class = &tu->tp.class;
-	tu->tp.call.name = kstrdup(event, GFP_KERNEL);
-	if (!tu->tp.call.name)
-		goto error;
-
-	tu->tp.class.system = kstrdup(group, GFP_KERNEL);
-	if (!tu->tp.class.system)
+	ret = trace_probe_init(&tu->tp, event, group);
+	if (ret < 0)
 		goto error;
 
 	dyn_event_init(&tu->devent, &trace_uprobe_ops);
-	INIT_LIST_HEAD(&tu->tp.files);
 	tu->consumer.handler = uprobe_dispatcher;
 	if (is_ret)
 		tu->consumer.ret_handler = uretprobe_dispatcher;
@@ -326,26 +318,18 @@ alloc_trace_uprobe(const char *group, const char *event, int nargs, bool is_ret)
 	return tu;
 
 error:
-	kfree(tu->tp.call.name);
 	kfree(tu);
 
-	return ERR_PTR(-ENOMEM);
+	return ERR_PTR(ret);
 }
 
 static void free_trace_uprobe(struct trace_uprobe *tu)
 {
-	int i;
-
 	if (!tu)
 		return;
 
-	for (i = 0; i < tu->tp.nr_args; i++)
-		traceprobe_free_probe_arg(&tu->tp.args[i]);
-
 	path_put(&tu->path);
-	kfree(tu->tp.call.class->system);
-	kfree(tu->tp.call.name);
-	kfree(tu->tp.call.print_fmt);
+	trace_probe_cleanup(&tu->tp);
 	kfree(tu->filename);
 	kfree(tu);
 }
@@ -1351,7 +1335,6 @@ static struct trace_event_functions uprobe_funcs = {
 static inline void init_trace_event_call(struct trace_uprobe *tu,
 					 struct trace_event_call *call)
 {
-	INIT_LIST_HEAD(&call->class->fields);
 	call->event.funcs = &uprobe_funcs;
 	call->class->define_fields = uprobe_event_define_fields;
 
-- 
cgit v1.2.3


From 46e5376d404d14cb321f5d4e446fe3fb6d8a93ab Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Sat, 1 Jun 2019 00:17:16 +0900
Subject: tracing/probe: Add trace_event_call register API for trace_probe

Since trace_event_call is a field of trace_probe, these
operations should be done in trace_probe.c. trace_kprobe
and trace_uprobe use new functions to register/unregister
trace_event_call.

Link: http://lkml.kernel.org/r/155931583643.28323.14828411185591538876.stgit@devnote2

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 kernel/trace/trace_kprobe.c | 20 +++-----------------
 kernel/trace/trace_probe.c  | 16 ++++++++++++++++
 kernel/trace/trace_probe.h  |  6 ++++++
 kernel/trace/trace_uprobe.c | 22 +++-------------------
 4 files changed, 28 insertions(+), 36 deletions(-)

(limited to 'kernel')

diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index c43c2d419ded..7f802ee27266 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -1393,28 +1393,14 @@ static inline void init_trace_event_call(struct trace_kprobe *tk,
 
 static int register_kprobe_event(struct trace_kprobe *tk)
 {
-	struct trace_event_call *call = &tk->tp.call;
-	int ret = 0;
-
-	init_trace_event_call(tk, call);
-
-	ret = register_trace_event(&call->event);
-	if (!ret)
-		return -ENODEV;
+	init_trace_event_call(tk, &tk->tp.call);
 
-	ret = trace_add_event_call(call);
-	if (ret) {
-		pr_info("Failed to register kprobe event: %s\n",
-			trace_event_name(call));
-		unregister_trace_event(&call->event);
-	}
-	return ret;
+	return trace_probe_register_event_call(&tk->tp);
 }
 
 static int unregister_kprobe_event(struct trace_kprobe *tk)
 {
-	/* tp->event is unregistered in trace_remove_event_call() */
-	return trace_remove_event_call(&tk->tp.call);
+	return trace_probe_unregister_event_call(&tk->tp);
 }
 
 #ifdef CONFIG_PERF_EVENTS
diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index fe4ee2e73d92..509a26024b4f 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -920,3 +920,19 @@ int trace_probe_init(struct trace_probe *tp, const char *event,
 
 	return 0;
 }
+
+int trace_probe_register_event_call(struct trace_probe *tp)
+{
+	struct trace_event_call *call = &tp->call;
+	int ret;
+
+	ret = register_trace_event(&call->event);
+	if (!ret)
+		return -ENODEV;
+
+	ret = trace_add_event_call(call);
+	if (ret)
+		unregister_trace_event(&call->event);
+
+	return ret;
+}
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index 818b1d7693ba..01d7b222e004 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -251,6 +251,12 @@ static inline bool trace_probe_is_registered(struct trace_probe *tp)
 int trace_probe_init(struct trace_probe *tp, const char *event,
 		     const char *group);
 void trace_probe_cleanup(struct trace_probe *tp);
+int trace_probe_register_event_call(struct trace_probe *tp);
+static inline int trace_probe_unregister_event_call(struct trace_probe *tp)
+{
+	/* tp->event is unregistered in trace_remove_event_call() */
+	return trace_remove_event_call(&tp->call);
+}
 
 /* Check the name is good for event/group/fields */
 static inline bool is_good_name(const char *name)
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index b18b7eb1a76f..c262494fa793 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -1345,30 +1345,14 @@ static inline void init_trace_event_call(struct trace_uprobe *tu,
 
 static int register_uprobe_event(struct trace_uprobe *tu)
 {
-	struct trace_event_call *call = &tu->tp.call;
-	int ret = 0;
-
-	init_trace_event_call(tu, call);
-
-	ret = register_trace_event(&call->event);
-	if (!ret)
-		return -ENODEV;
-
-	ret = trace_add_event_call(call);
-
-	if (ret) {
-		pr_info("Failed to register uprobe event: %s\n",
-			trace_event_name(call));
-		unregister_trace_event(&call->event);
-	}
+	init_trace_event_call(tu, &tu->tp.call);
 
-	return ret;
+	return trace_probe_register_event_call(&tu->tp);
 }
 
 static int unregister_uprobe_event(struct trace_uprobe *tu)
 {
-	/* tu->event is unregistered in trace_remove_event_call() */
-	return trace_remove_event_call(&tu->tp.call);
+	return trace_probe_unregister_event_call(&tu->tp);
 }
 
 #ifdef CONFIG_PERF_EVENTS
-- 
cgit v1.2.3


From b5f935ee133911b3ed2d4429dd86d2bd5385519d Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Sat, 1 Jun 2019 00:17:26 +0900
Subject: tracing/probe: Add trace_event_file access APIs for trace_probe

Add trace_event_file access APIs for trace_probe data structure.
This simplifies enabling/disabling operations in uprobe and kprobe
events so that those don't touch deep inside the trace_probe.

This also removing a redundant synchronization when the
kprobe event is used from perf, since the perf itself uses
tracepoint_synchronize_unregister() after disabling (ftrace-
defined) event, thus we don't have to synchronize in that
path. Also we don't need to identify local trace_kprobe too
anymore.

Link: http://lkml.kernel.org/r/155931584587.28323.372301976283354629.stgit@devnote2

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 kernel/trace/trace_kprobe.c | 85 ++++++++++++++++-----------------------------
 kernel/trace/trace_probe.c  | 47 +++++++++++++++++++++++++
 kernel/trace/trace_probe.h  | 36 ++++++++++---------
 kernel/trace/trace_uprobe.c | 42 +++++++---------------
 4 files changed, 109 insertions(+), 101 deletions(-)

(limited to 'kernel')

diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 7f802ee27266..87a52094378c 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -290,34 +290,27 @@ static inline int __enable_trace_kprobe(struct trace_kprobe *tk)
 static int
 enable_trace_kprobe(struct trace_kprobe *tk, struct trace_event_file *file)
 {
-	struct event_file_link *link;
+	bool enabled = trace_probe_is_enabled(&tk->tp);
 	int ret = 0;
 
 	if (file) {
-		link = kmalloc(sizeof(*link), GFP_KERNEL);
-		if (!link) {
-			ret = -ENOMEM;
-			goto out;
-		}
-
-		link->file = file;
-		list_add_tail_rcu(&link->list, &tk->tp.files);
+		ret = trace_probe_add_file(&tk->tp, file);
+		if (ret)
+			return ret;
+	} else
+		tk->tp.flags |= TP_FLAG_PROFILE;
 
-		tk->tp.flags |= TP_FLAG_TRACE;
-		ret = __enable_trace_kprobe(tk);
-		if (ret) {
-			list_del_rcu(&link->list);
-			kfree(link);
-			tk->tp.flags &= ~TP_FLAG_TRACE;
-		}
+	if (enabled)
+		return 0;
 
-	} else {
-		tk->tp.flags |= TP_FLAG_PROFILE;
-		ret = __enable_trace_kprobe(tk);
-		if (ret)
+	ret = __enable_trace_kprobe(tk);
+	if (ret) {
+		if (file)
+			trace_probe_remove_file(&tk->tp, file);
+		else
 			tk->tp.flags &= ~TP_FLAG_PROFILE;
 	}
- out:
+
 	return ret;
 }
 
@@ -328,54 +321,34 @@ enable_trace_kprobe(struct trace_kprobe *tk, struct trace_event_file *file)
 static int
 disable_trace_kprobe(struct trace_kprobe *tk, struct trace_event_file *file)
 {
-	struct event_file_link *link = NULL;
-	int wait = 0;
+	struct trace_probe *tp = &tk->tp;
 	int ret = 0;
 
 	if (file) {
-		link = find_event_file_link(&tk->tp, file);
-		if (!link) {
-			ret = -EINVAL;
-			goto out;
-		}
-
-		list_del_rcu(&link->list);
-		wait = 1;
-		if (!list_empty(&tk->tp.files))
+		if (!trace_probe_get_file_link(tp, file))
+			return -ENOENT;
+		if (!trace_probe_has_single_file(tp))
 			goto out;
-
-		tk->tp.flags &= ~TP_FLAG_TRACE;
+		tp->flags &= ~TP_FLAG_TRACE;
 	} else
-		tk->tp.flags &= ~TP_FLAG_PROFILE;
+		tp->flags &= ~TP_FLAG_PROFILE;
 
-	if (!trace_probe_is_enabled(&tk->tp) && trace_probe_is_registered(&tk->tp)) {
+	if (!trace_probe_is_enabled(tp) && trace_probe_is_registered(tp)) {
 		if (trace_kprobe_is_return(tk))
 			disable_kretprobe(&tk->rp);
 		else
 			disable_kprobe(&tk->rp.kp);
-		wait = 1;
 	}
 
-	/*
-	 * if tk is not added to any list, it must be a local trace_kprobe
-	 * created with perf_event_open. We don't need to wait for these
-	 * trace_kprobes
-	 */
-	if (list_empty(&tk->devent.list))
-		wait = 0;
  out:
-	if (wait) {
+	if (file)
 		/*
-		 * Synchronize with kprobe_trace_func/kretprobe_trace_func
-		 * to ensure disabled (all running handlers are finished).
-		 * This is not only for kfree(), but also the caller,
-		 * trace_remove_event_call() supposes it for releasing
-		 * event_call related objects, which will be accessed in
-		 * the kprobe_trace_func/kretprobe_trace_func.
+		 * Synchronization is done in below function. For perf event,
+		 * file == NULL and perf_trace_event_unreg() calls
+		 * tracepoint_synchronize_unregister() to ensure synchronize
+		 * event. We don't need to care about it.
 		 */
-		synchronize_rcu();
-		kfree(link);	/* Ignored if link == NULL */
-	}
+		trace_probe_remove_file(tp, file);
 
 	return ret;
 }
@@ -1044,7 +1017,7 @@ kprobe_trace_func(struct trace_kprobe *tk, struct pt_regs *regs)
 {
 	struct event_file_link *link;
 
-	list_for_each_entry_rcu(link, &tk->tp.files, list)
+	trace_probe_for_each_link_rcu(link, &tk->tp)
 		__kprobe_trace_func(tk, regs, link->file);
 }
 NOKPROBE_SYMBOL(kprobe_trace_func);
@@ -1094,7 +1067,7 @@ kretprobe_trace_func(struct trace_kprobe *tk, struct kretprobe_instance *ri,
 {
 	struct event_file_link *link;
 
-	list_for_each_entry_rcu(link, &tk->tp.files, list)
+	trace_probe_for_each_link_rcu(link, &tk->tp)
 		__kretprobe_trace_func(tk, ri, regs, link->file);
 }
 NOKPROBE_SYMBOL(kretprobe_trace_func);
diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index 509a26024b4f..abb05608a09d 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -936,3 +936,50 @@ int trace_probe_register_event_call(struct trace_probe *tp)
 
 	return ret;
 }
+
+int trace_probe_add_file(struct trace_probe *tp, struct trace_event_file *file)
+{
+	struct event_file_link *link;
+
+	link = kmalloc(sizeof(*link), GFP_KERNEL);
+	if (!link)
+		return -ENOMEM;
+
+	link->f