Tracing fixes for 5.10-rc6

- Use correct timestamp variable for ring buffer write stamp update
  - Fix up before stamp and write stamp when crossing ring buffer sub
    buffers
  - Keep a zero delta in ring buffer in slow path if cmpxchg fails
  - Fix trace_printk static buffer for archs that care
  - Fix ftrace record accounting for ftrace ops with trampolines
  - Fix DYNAMIC_FTRACE_WITH_DIRECT_CALLS dependency
  - Remove WARN_ON in hwlat tracer that triggers on something that is OK
  - Make "my_tramp" trampoline in ftrace direct sample code global
  - Fixes in the bootconfig tool for better alignment management
 -----BEGIN PGP SIGNATURE-----
 
 iIoEABYIADIWIQRRSw7ePDh/lE+zeZMp5XQQmuv6qgUCX8ZzghQccm9zdGVkdEBn
 b29kbWlzLm9yZwAKCRAp5XQQmuv6qg0JAQCII1bDQyF3APLlNFRqfHf3bTo7Zl5z
 WaUd1Cd7JkY+WAD/eF1dWjN0JRtfU+oRlk6UZ4oNmp8WMJvQ7oV26ub2egE=
 =lts8
 -----END PGP SIGNATURE-----

Merge tag 'trace-v5.10-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace

Pull tracing fixes from Steven Rostedt:

 - Use correct timestamp variable for ring buffer write stamp update

 - Fix up before stamp and write stamp when crossing ring buffer sub
   buffers

 - Keep a zero delta in ring buffer in slow path if cmpxchg fails

 - Fix trace_printk static buffer for archs that care

 - Fix ftrace record accounting for ftrace ops with trampolines

 - Fix DYNAMIC_FTRACE_WITH_DIRECT_CALLS dependency

 - Remove WARN_ON in hwlat tracer that triggers on something that is OK

 - Make "my_tramp" trampoline in ftrace direct sample code global

 - Fixes in the bootconfig tool for better alignment management

* tag 'trace-v5.10-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace:
  ring-buffer: Always check to put back before stamp when crossing pages
  ftrace: Fix DYNAMIC_FTRACE_WITH_DIRECT_CALLS dependency
  ftrace: Fix updating FTRACE_FL_TRAMP
  tracing: Fix alignment of static buffer
  tracing: Remove WARN_ON in start_thread()
  samples/ftrace: Mark my_tramp[12]? global
  ring-buffer: Set the right timestamp in the slow path of __rb_reserve_next()
  ring-buffer: Update write stamp with the correct ts
  docs: bootconfig: Update file format on initrd image
  tools/bootconfig: Align the bootconfig applied initrd image size to 4
  tools/bootconfig: Fix to check the write failure correctly
  tools/bootconfig: Fix errno reference after printf()

Documentation/admin-guide/bootconfig.rst

@@ -137,15 +137,22 @@ Boot Kernel With a Boot Config
 ==============================
 
 Since the boot configuration file is loaded with initrd, it will be added
-to the end of the initrd (initramfs) image file with size, checksum and
-12-byte magic word as below.
+to the end of the initrd (initramfs) image file with padding, size,
+checksum and 12-byte magic word as below.
 
-[initrd][bootconfig][size(u32)][checksum(u32)][#BOOTCONFIG\n]
+[initrd][bootconfig][padding][size(u32)][checksum(u32)][#BOOTCONFIG\n]
+
+When the boot configuration is added to the initrd image, the total
+file size is aligned to 4 bytes. To fill the gap, null characters
+(``\0``) will be added. Thus the ``size`` is the length of the bootconfig
+file + padding bytes.
 
 The Linux kernel decodes the last part of the initrd image in memory to
 get the boot configuration data.
 Because of this "piggyback" method, there is no need to change or
-update the boot loader and the kernel image itself.
+update the boot loader and the kernel image itself as long as the boot
+loader passes the correct initrd file size. If by any chance, the boot
+loader passes a longer size, the kernel feils to find the bootconfig data.
 
 To do this operation, Linux kernel provides "bootconfig" command under
 tools/bootconfig, which allows admin to apply or delete the config file
@@ -176,7 +183,8 @@ up to 512 key-value pairs. If keys contains 3 words in average, it can
 contain 256 key-value pairs. In most cases, the number of config items
 will be under 100 entries and smaller than 8KB, so it would be enough.
 If the node number exceeds 1024, parser returns an error even if the file
-size is smaller than 32KB.
+size is smaller than 32KB. (Note that this maximum size is not including
+the padding null characters.)
 Anyway, since bootconfig command verifies it when appending a boot config
 to initrd image, user can notice it before boot.
 

include/linux/bootconfig.h

@@ -12,6 +12,9 @@
 
 #define BOOTCONFIG_MAGIC	"#BOOTCONFIG\n"
 #define BOOTCONFIG_MAGIC_LEN	12
+#define BOOTCONFIG_ALIGN_SHIFT	2
+#define BOOTCONFIG_ALIGN	(1 << BOOTCONFIG_ALIGN_SHIFT)
+#define BOOTCONFIG_ALIGN_MASK	(BOOTCONFIG_ALIGN - 1)
 
 /* XBC tree node */
 struct xbc_node {

kernel/trace/Kconfig

@@ -202,7 +202,7 @@ config DYNAMIC_FTRACE_WITH_REGS
 
 config DYNAMIC_FTRACE_WITH_DIRECT_CALLS
 	def_bool y
-	depends on DYNAMIC_FTRACE
+	depends on DYNAMIC_FTRACE_WITH_REGS
 	depends on HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
 
 config FUNCTION_PROFILER

kernel/trace/ftrace.c

@@ -1629,6 +1629,8 @@ static bool test_rec_ops_needs_regs(struct dyn_ftrace *rec)
 static struct ftrace_ops *
 ftrace_find_tramp_ops_any(struct dyn_ftrace *rec);
 static struct ftrace_ops *
+ftrace_find_tramp_ops_any_other(struct dyn_ftrace *rec, struct ftrace_ops *op_exclude);
+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,
@@ -1778,7 +1780,7 @@ static bool __ftrace_hash_rec_update(struct ftrace_ops *ops,
 			 * to it.
 			 */
 			if (ftrace_rec_count(rec) == 1 &&
-			    ftrace_find_tramp_ops_any(rec))
+			    ftrace_find_tramp_ops_any_other(rec, ops))
 				rec->flags |= FTRACE_FL_TRAMP;
 			else
 				rec->flags &= ~FTRACE_FL_TRAMP;
@@ -2244,6 +2246,24 @@ ftrace_find_tramp_ops_any(struct dyn_ftrace *rec)
 	return NULL;
 }
 
+static struct ftrace_ops *
+ftrace_find_tramp_ops_any_other(struct dyn_ftrace *rec, struct ftrace_ops *op_exclude)
+{
+	struct ftrace_ops *op;
+	unsigned long ip = rec->ip;
+
+	do_for_each_ftrace_op(op, ftrace_ops_list) {
+
+		if (op == op_exclude || !op->trampoline)
+			continue;
+
+		if (hash_contains_ip(ip, op->func_hash))
+			return op;
+	} while_for_each_ftrace_op(op);
+
+	return NULL;
+}
+
 static struct ftrace_ops *
 ftrace_find_tramp_ops_next(struct dyn_ftrace *rec,
 			   struct ftrace_ops *op)

kernel/trace/ring_buffer.c

@@ -3234,14 +3234,12 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 
 	/* See if we shot pass the end of this buffer page */
 	if (unlikely(write > BUF_PAGE_SIZE)) {
-		if (tail != w) {
-			/* before and after may now different, fix it up*/
-			b_ok = rb_time_read(&cpu_buffer->before_stamp, &info->before);
-			a_ok = rb_time_read(&cpu_buffer->write_stamp, &info->after);
-			if (a_ok && b_ok && info->before != info->after)
-				(void)rb_time_cmpxchg(&cpu_buffer->before_stamp,
-						      info->before, info->after);
-		}
+		/* before and after may now different, fix it up*/
+		b_ok = rb_time_read(&cpu_buffer->before_stamp, &info->before);
+		a_ok = rb_time_read(&cpu_buffer->write_stamp, &info->after);
+		if (a_ok && b_ok && info->before != info->after)
+			(void)rb_time_cmpxchg(&cpu_buffer->before_stamp,
+					      info->before, info->after);
 		return rb_move_tail(cpu_buffer, tail, info);
 	}
 
@@ -3287,11 +3285,11 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 		ts = rb_time_stamp(cpu_buffer->buffer);
 		barrier();
  /*E*/		if (write == (local_read(&tail_page->write) & RB_WRITE_MASK) &&
-		    info->after < ts) {
+		    info->after < ts &&
+		    rb_time_cmpxchg(&cpu_buffer->write_stamp,
+				    info->after, ts)) {
 			/* Nothing came after this event between C and E */
 			info->delta = ts - info->after;
-			(void)rb_time_cmpxchg(&cpu_buffer->write_stamp,
-					      info->after, info->ts);
 			info->ts = ts;
 		} else {
 			/*

kernel/trace/trace.c

@@ -3534,7 +3534,7 @@ __find_next_entry(struct trace_iterator *iter, int *ent_cpu,
 }
 
 #define STATIC_TEMP_BUF_SIZE	128
-static char static_temp_buf[STATIC_TEMP_BUF_SIZE];
+static char static_temp_buf[STATIC_TEMP_BUF_SIZE] __aligned(4);
 
 /* Find the next real entry, without updating the iterator itself */
 struct trace_entry *trace_find_next_entry(struct trace_iterator *iter,

kernel/trace/trace_hwlat.c

@@ -368,7 +368,7 @@ static int start_kthread(struct trace_array *tr)
 	struct task_struct *kthread;
 	int next_cpu;
 
-	if (WARN_ON(hwlat_kthread))
+	if (hwlat_kthread)
 		return 0;
 
 	/* Just pick the first CPU on first iteration */

samples/ftrace/ftrace-direct-modify.c

@@ -21,6 +21,7 @@ static unsigned long my_ip = (unsigned long)schedule;
 asm (
 "	.pushsection    .text, \"ax\", @progbits\n"
 "	.type		my_tramp1, @function\n"
+"	.globl		my_tramp1\n"
 "   my_tramp1:"
 "	pushq %rbp\n"
 "	movq %rsp, %rbp\n"
@@ -29,6 +30,7 @@ asm (
 "	.size		my_tramp1, .-my_tramp1\n"
 "	ret\n"
 "	.type		my_tramp2, @function\n"
+"	.globl		my_tramp2\n"
 "   my_tramp2:"
 "	pushq %rbp\n"
 "	movq %rsp, %rbp\n"

samples/ftrace/ftrace-direct-too.c

@@ -16,6 +16,7 @@ extern void my_tramp(void *);
 asm (
 "	.pushsection    .text, \"ax\", @progbits\n"
 "	.type		my_tramp, @function\n"
+"	.globl		my_tramp\n"
 "   my_tramp:"
 "	pushq %rbp\n"
 "	movq %rsp, %rbp\n"

samples/ftrace/ftrace-direct.c

@@ -14,6 +14,7 @@ extern void my_tramp(void *);
 asm (
 "	.pushsection    .text, \"ax\", @progbits\n"
 "	.type		my_tramp, @function\n"
+"	.globl		my_tramp\n"
 "   my_tramp:"
 "	pushq %rbp\n"
 "	movq %rsp, %rbp\n"

tools/bootconfig/main.c

@@ -147,6 +147,12 @@ static int load_xbc_file(const char *path, char **buf)
 	return ret;
 }
 
+static int pr_errno(const char *msg, int err)
+{
+	pr_err("%s: %d\n", msg, err);
+	return err;
+}
+
 static int load_xbc_from_initrd(int fd, char **buf)
 {
 	struct stat stat;
@@ -162,26 +168,24 @@ static int load_xbc_from_initrd(int fd, char **buf)
 	if (stat.st_size < 8 + BOOTCONFIG_MAGIC_LEN)
 		return 0;
 
-	if (lseek(fd, -BOOTCONFIG_MAGIC_LEN, SEEK_END) < 0) {
-		pr_err("Failed to lseek: %d\n", -errno);
-		return -errno;
-	}
+	if (lseek(fd, -BOOTCONFIG_MAGIC_LEN, SEEK_END) < 0)
+		return pr_errno("Failed to lseek for magic", -errno);
+
 	if (read(fd, magic, BOOTCONFIG_MAGIC_LEN) < 0)
-		return -errno;
+		return pr_errno("Failed to read", -errno);
+
 	/* Check the bootconfig magic bytes */
 	if (memcmp(magic, BOOTCONFIG_MAGIC, BOOTCONFIG_MAGIC_LEN) != 0)
 		return 0;
 
-	if (lseek(fd, -(8 + BOOTCONFIG_MAGIC_LEN), SEEK_END) < 0) {
-		pr_err("Failed to lseek: %d\n", -errno);
-		return -errno;
-	}
+	if (lseek(fd, -(8 + BOOTCONFIG_MAGIC_LEN), SEEK_END) < 0)
+		return pr_errno("Failed to lseek for size", -errno);
 
 	if (read(fd, &size, sizeof(u32)) < 0)
-		return -errno;
+		return pr_errno("Failed to read size", -errno);
 
 	if (read(fd, &csum, sizeof(u32)) < 0)
-		return -errno;
+		return pr_errno("Failed to read checksum", -errno);
 
 	/* Wrong size error  */
 	if (stat.st_size < size + 8 + BOOTCONFIG_MAGIC_LEN) {
@@ -190,10 +194,8 @@ static int load_xbc_from_initrd(int fd, char **buf)
 	}
 
 	if (lseek(fd, stat.st_size - (size + 8 + BOOTCONFIG_MAGIC_LEN),
-		  SEEK_SET) < 0) {
-		pr_err("Failed to lseek: %d\n", -errno);
-		return -errno;
-	}
+		  SEEK_SET) < 0)
+		return pr_errno("Failed to lseek", -errno);
 
 	ret = load_xbc_fd(fd, buf, size);
 	if (ret < 0)
@@ -262,14 +264,16 @@ static int show_xbc(const char *path, bool list)
 
 	ret = stat(path, &st);
 	if (ret < 0) {
-		pr_err("Failed to stat %s: %d\n", path, -errno);
-		return -errno;
+		ret = -errno;
+		pr_err("Failed to stat %s: %d\n", path, ret);
+		return ret;
 	}
 
 	fd = open(path, O_RDONLY);
 	if (fd < 0) {
-		pr_err("Failed to open initrd %s: %d\n", path, fd);
-		return -errno;
+		ret = -errno;
+		pr_err("Failed to open initrd %s: %d\n", path, ret);
+		return ret;
 	}
 
 	ret = load_xbc_from_initrd(fd, &buf);
@@ -307,8 +311,9 @@ static int delete_xbc(const char *path)
 
 	fd = open(path, O_RDWR);
 	if (fd < 0) {
-		pr_err("Failed to open initrd %s: %d\n", path, fd);
-		return -errno;
+		ret = -errno;
+		pr_err("Failed to open initrd %s: %d\n", path, ret);
+		return ret;
 	}
 
 	size = load_xbc_from_initrd(fd, &buf);
@@ -332,11 +337,13 @@ static int delete_xbc(const char *path)
 
 static int apply_xbc(const char *path, const char *xbc_path)
 {
-	u32 size, csum;
-	char *buf, *data;
-	int ret, fd;
+	char *buf, *data, *p;
+	size_t total_size;
+	struct stat stat;
 	const char *msg;
-	int pos;
+	u32 size, csum;
+	int pos, pad;
+	int ret, fd;
 
 	ret = load_xbc_file(xbc_path, &buf);
 	if (ret < 0) {
@@ -346,13 +353,12 @@ static int apply_xbc(const char *path, const char *xbc_path)
 	size = strlen(buf) + 1;
 	csum = checksum((unsigned char *)buf, size);
 
-	/* Prepare xbc_path data */
-	data = malloc(size + 8);
+	/* Backup the bootconfig data */
+	data = calloc(size + BOOTCONFIG_ALIGN +
+		      sizeof(u32) + sizeof(u32) + BOOTCONFIG_MAGIC_LEN, 1);
 	if (!data)
 		return -ENOMEM;
-	strcpy(data, buf);
-	*(u32 *)(data + size) = size;
-	*(u32 *)(data + size + 4) = csum;
+	memcpy(data, buf, size);
 
 	/* Check the data format */
 	ret = xbc_init(buf, &msg, &pos);
@@ -383,28 +389,61 @@ static int apply_xbc(const char *path, const char *xbc_path)
 	/* Apply new one */
 	fd = open(path, O_RDWR | O_APPEND);
 	if (fd < 0) {
-		pr_err("Failed to open %s: %d\n", path, fd);
+		ret = -errno;
+		pr_err("Failed to open %s: %d\n", path, ret);
 		free(data);
-		return fd;
+		return ret;
 	}
 	/* TODO: Ensure the @path is initramfs/initrd image */
-	ret = write(fd, data, size + 8);
-	if (ret < 0) {
+	if (fstat(fd, &stat) < 0) {
+		pr_err("Failed to get the size of %s\n", path);
+		goto out;
+	}
+
+	/* To align up the total size to BOOTCONFIG_ALIGN, get padding size */
+	total_size = stat.st_size + size + sizeof(u32) * 2 + BOOTCONFIG_MAGIC_LEN;
+	pad = ((total_size + BOOTCONFIG_ALIGN - 1) & (~BOOTCONFIG_ALIGN_MASK)) - total_size;
+	size += pad;
+
+	/* Add a footer */
+	p = data + size;
+	*(u32 *)p = size;
+	p += sizeof(u32);
+
+	*(u32 *)p = csum;
+	p += sizeof(u32);
+
+	memcpy(p, BOOTCONFIG_MAGIC, BOOTCONFIG_MAGIC_LEN);
+	p += BOOTCONFIG_MAGIC_LEN;
+
+	total_size = p - data;
+
+	ret = write(fd, data, total_size);
+	if (ret < total_size) {
+		if (ret < 0)
+			ret = -errno;
 		pr_err("Failed to apply a boot config: %d\n", ret);
-		goto out;
-	}
-	/* Write a magic word of the bootconfig */
-	ret = write(fd, BOOTCONFIG_MAGIC, BOOTCONFIG_MAGIC_LEN);
-	if (ret < 0) {
-		pr_err("Failed to apply a boot config magic: %d\n", ret);
-		goto out;
-	}
-	ret = 0;
+		if (ret >= 0)
+			goto out_rollback;
+	} else
+		ret = 0;
+
 out:
 	close(fd);
 	free(data);
 
 	return ret;
+
+out_rollback:
+	/* Map the partial write to -ENOSPC */
+	if (ret >= 0)
+		ret = -ENOSPC;
+	if (ftruncate(fd, stat.st_size) < 0) {
+		ret = -errno;
+		pr_err("Failed to rollback the write error: %d\n", ret);
+		pr_err("The initrd %s may be corrupted. Recommend to rebuild.\n", path);
+	}
+	goto out;
 }
 
 static int usage(void)

tools/bootconfig/test-bootconfig.sh

@@ -9,6 +9,7 @@ else
   TESTDIR=.
 fi
 BOOTCONF=${TESTDIR}/bootconfig
+ALIGN=4
 
 INITRD=`mktemp ${TESTDIR}/initrd-XXXX`
 TEMPCONF=`mktemp ${TESTDIR}/temp-XXXX.bconf`
@@ -59,7 +60,10 @@ echo "Show command test"
 xpass $BOOTCONF $INITRD
 
 echo "File size check"
-xpass test $new_size -eq $(expr $bconf_size + $initrd_size + 9 + 12)
+total_size=$(expr $bconf_size + $initrd_size + 9 + 12 + $ALIGN - 1 )
+total_size=$(expr $total_size / $ALIGN)
+total_size=$(expr $total_size \* $ALIGN)
+xpass test $new_size -eq $total_size
 
 echo "Apply command repeat test"
 xpass $BOOTCONF -a $TEMPCONF $INITRD