module: add printk formats to add module build ID to stacktraces

Let's make kernel stacktraces easier to identify by including the build
ID[1] of a module if the stacktrace is printing a symbol from a module.
This makes it simpler for developers to locate a kernel module's full
debuginfo for a particular stacktrace.  Combined with
scripts/decode_stracktrace.sh, a developer can download the matching
debuginfo from a debuginfod[2] server and find the exact file and line
number for the functions plus offsets in a stacktrace that match the
module.  This is especially useful for pstore crash debugging where the
kernel crashes are recorded in something like console-ramoops and the
recovery kernel/modules are different or the debuginfo doesn't exist on
the device due to space concerns (the debuginfo can be too large for space
limited devices).

Originally, I put this on the %pS format, but that was quickly rejected
given that %pS is used in other places such as ftrace where build IDs
aren't meaningful.  There was some discussions on the list to put every
module build ID into the "Modules linked in:" section of the stacktrace
message but that quickly becomes very hard to read once you have more than
three or four modules linked in.  It also provides too much information
when we don't expect each module to be traversed in a stacktrace.  Having
the build ID for modules that aren't important just makes things messy.
Splitting it to multiple lines for each module quickly explodes the number
of lines printed in an oops too, possibly wrapping the warning off the
console.  And finally, trying to stash away each module used in a
callstack to provide the ID of each symbol printed is cumbersome and would
require changes to each architecture to stash away modules and return
their build IDs once unwinding has completed.

Instead, we opt for the simpler approach of introducing new printk formats
'%pS[R]b' for "pointer symbolic backtrace with module build ID" and '%pBb'
for "pointer backtrace with module build ID" and then updating the few
places in the architecture layer where the stacktrace is printed to use
this new format.

Before:

 Call trace:
  lkdtm_WARNING+0x28/0x30 [lkdtm]
  direct_entry+0x16c/0x1b4 [lkdtm]
  full_proxy_write+0x74/0xa4
  vfs_write+0xec/0x2e8

After:

 Call trace:
  lkdtm_WARNING+0x28/0x30 [lkdtm 6c2215028606bda50de823490723dc4bc5bf46f9]
  direct_entry+0x16c/0x1b4 [lkdtm 6c2215028606bda50de823490723dc4bc5bf46f9]
  full_proxy_write+0x74/0xa4
  vfs_write+0xec/0x2e8

[akpm@linux-foundation.org: fix build with CONFIG_MODULES=n, tweak code layout]
[rdunlap@infradead.org: fix build when CONFIG_MODULES is not set]
  Link: https://lkml.kernel.org/r/20210513171510.20328-1-rdunlap@infradead.org
[akpm@linux-foundation.org: make kallsyms_lookup_buildid() static]
[cuibixuan@huawei.com: fix build error when CONFIG_SYSFS is disabled]
  Link: https://lkml.kernel.org/r/20210525105049.34804-1-cuibixuan@huawei.com

Link: https://lkml.kernel.org/r/20210511003845.2429846-6-swboyd@chromium.org
Link: https://fedoraproject.org/wiki/Releases/FeatureBuildId [1]
Link: https://sourceware.org/elfutils/Debuginfod.html [2]
Signed-off-by: Stephen Boyd <swboyd@chromium.org>
Signed-off-by: Bixuan Cui <cuibixuan@huawei.com>
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Jessica Yu <jeyu@kernel.org>
Cc: Evan Green <evgreen@chromium.org>
Cc: Hsin-Yi Wang <hsinyi@chromium.org>
Cc: Petr Mladek <pmladek@suse.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Baoquan He <bhe@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Dave Young <dyoung@redhat.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Cc: Sasha Levin <sashal@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vivek Goyal <vgoyal@redhat.com>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 121 insertions, 25 deletions

diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
index c851ca0ed357..0ba87982d017 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -25,7 +25,10 @@
 #include <linux/filter.h>
 #include <linux/ftrace.h>
 #include <linux/kprobes.h>
+#include <linux/build_bug.h>
 #include <linux/compiler.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
 
 /*
  * These will be re-linked against their real values
@@ -297,21 +300,14 @@ int kallsyms_lookup_size_offset(unsigned long addr, unsigned long *symbolsize,
 		get_symbol_pos(addr, symbolsize, offset);
 		return 1;
 	}
-	return !!module_address_lookup(addr, symbolsize, offset, NULL, namebuf) ||
+	return !!module_address_lookup(addr, symbolsize, offset, NULL, NULL, namebuf) ||
 	       !!__bpf_address_lookup(addr, symbolsize, offset, namebuf);
 }
 
-/*
- * Lookup an address
- * - modname is set to NULL if it's in the kernel.
- * - We guarantee that the returned name is valid until we reschedule even if.
- *   It resides in a module.
- * - We also guarantee that modname will be valid until rescheduled.
- */
-const char *kallsyms_lookup(unsigned long addr,
-			    unsigned long *symbolsize,
-			    unsigned long *offset,
-			    char **modname, char *namebuf)
+static const char *kallsyms_lookup_buildid(unsigned long addr,
+			unsigned long *symbolsize,
+			unsigned long *offset, char **modname,
+			const unsigned char **modbuildid, char *namebuf)
 {
 	const char *ret;
 
@@ -327,6 +323,8 @@ const char *kallsyms_lookup(unsigned long addr,
 				       namebuf, KSYM_NAME_LEN);
 		if (modname)
 			*modname = NULL;
+		if (modbuildid)
+			*modbuildid = NULL;
 
 		ret = namebuf;
 		goto found;
@@ -334,7 +332,7 @@ const char *kallsyms_lookup(unsigned long addr,
 
 	/* See if it's in a module or a BPF JITed image. */
 	ret = module_address_lookup(addr, symbolsize, offset,
-				    modname, namebuf);
+				    modname, modbuildid, namebuf);
 	if (!ret)
 		ret = bpf_address_lookup(addr, symbolsize,
 					 offset, modname, namebuf);
@@ -348,6 +346,22 @@ found:
 	return ret;
 }
 
+/*
+ * Lookup an address
+ * - modname is set to NULL if it's in the kernel.
+ * - We guarantee that the returned name is valid until we reschedule even if.
+ *   It resides in a module.
+ * - We also guarantee that modname will be valid until rescheduled.
+ */
+const char *kallsyms_lookup(unsigned long addr,
+			    unsigned long *symbolsize,
+			    unsigned long *offset,
+			    char **modname, char *namebuf)
+{
+	return kallsyms_lookup_buildid(addr, symbolsize, offset, modname,
+				       NULL, namebuf);
+}
+
 int lookup_symbol_name(unsigned long addr, char *symname)
 {
 	int res;
@@ -404,15 +418,17 @@ found:
 
 /* Look up a kernel symbol and return it in a text buffer. */
 static int __sprint_symbol(char *buffer, unsigned long address,
-			   int symbol_offset, int add_offset)
+			   int symbol_offset, int add_offset, int add_buildid)
 {
 	char *modname;
+	const unsigned char *buildid;
 	const char *name;
 	unsigned long offset, size;
 	int len;
 
 	address += symbol_offset;
-	name = kallsyms_lookup(address, &size, &offset, &modname, buffer);
+	name = kallsyms_lookup_buildid(address, &size, &offset, &modname, &buildid,
+				       buffer);
 	if (!name)
 		return sprintf(buffer, "0x%lx", address - symbol_offset);
 
@@ -424,8 +440,19 @@ static int __sprint_symbol(char *buffer, unsigned long address,
 	if (add_offset)
 		len += sprintf(buffer + len, "+%#lx/%#lx", offset, size);
 
-	if (modname)
-		len += sprintf(buffer + len, " [%s]", modname);
+	if (modname) {
+		len += sprintf(buffer + len, " [%s", modname);
+#if IS_ENABLED(CONFIG_STACKTRACE_BUILD_ID)
+		if (add_buildid && buildid) {
+			/* build ID should match length of sprintf */
+#if IS_ENABLED(CONFIG_MODULES)
+			static_assert(sizeof(typeof_member(struct module, build_id)) == 20);
+#endif
+			len += sprintf(buffer + len, " %20phN", buildid);
+		}
+#endif
+		len += sprintf(buffer + len, "]");
+	}
 
 	return len;
 }
@@ -443,11 +470,28 @@ static int __sprint_symbol(char *buffer, unsigned long address,
  */
 int sprint_symbol(char *buffer, unsigned long address)
 {
-	return __sprint_symbol(buffer, address, 0, 1);
+	return __sprint_symbol(buffer, address, 0, 1, 0);
 }
 EXPORT_SYMBOL_GPL(sprint_symbol);
 
 /**
+ * sprint_symbol_build_id - Look up a kernel symbol and return it in a text buffer
+ * @buffer: buffer to be stored
+ * @address: address to lookup
+ *
+ * This function looks up a kernel symbol with @address and stores its name,
+ * offset, size, module name and module build ID to @buffer if possible. If no
+ * symbol was found, just saves its @address as is.
+ *
+ * This function returns the number of bytes stored in @buffer.
+ */
+int sprint_symbol_build_id(char *buffer, unsigned long address)
+{
+	return __sprint_symbol(buffer, address, 0, 1, 1);
+}
+EXPORT_SYMBOL_GPL(sprint_symbol_build_id);
+
+/**
  * sprint_symbol_no_offset - Look up a kernel symbol and return it in a text buffer
  * @buffer: buffer to be stored
  * @address: address to lookup
@@ -460,7 +504,7 @@ EXPORT_SYMBOL_GPL(sprint_symbol);
  */
 int sprint_symbol_no_offset(char *buffer, unsigned long address)
 {
-	return __sprint_symbol(buffer, address, 0, 0);
+	return __sprint_symbol(buffer, address, 0, 0, 0);
 }
 EXPORT_SYMBOL_GPL(sprint_symbol_no_offset);
 
@@ -480,7 +524,27 @@ EXPORT_SYMBOL_GPL(sprint_symbol_no_offset);
  */
 int sprint_backtrace(char *buffer, unsigned long address)
 {
-	return __sprint_symbol(buffer, address, -1, 1);
+	return __sprint_symbol(buffer, address, -1, 1, 0);
+}
+
+/**
+ * sprint_backtrace_build_id - Look up a backtrace symbol and return it in a text buffer
+ * @buffer: buffer to be stored
+ * @address: address to lookup
+ *
+ * This function is for stack backtrace and does the same thing as
+ * sprint_symbol() but with modified/decreased @address. If there is a
+ * tail-call to the function marked "noreturn", gcc optimized out code after
+ * the call so that the stack-saved return address could point outside of the
+ * caller. This function ensures that kallsyms will find the original caller
+ * by decreasing @address. This function also appends the module build ID to
+ * the @buffer if @address is within a kernel module.
+ *
+ * This function returns the number of bytes stored in @buffer.
+ */
+int sprint_backtrace_build_id(char *buffer, unsigned long address)
+{
+	return __sprint_symbol(buffer, address, -1, 1, 1);
 }
 
 /* To avoid using get_symbol_offset for every symbol, we carry prefix along. */
diff --git a/kernel/module.c b/kernel/module.c
index 64bd61b2d3ad..ed13917ea5f3 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -13,6 +13,7 @@
 #include <linux/trace_events.h>
 #include <linux/init.h>
 #include <linux/kallsyms.h>
+#include <linux/buildid.h>
 #include <linux/file.h>
 #include <linux/fs.h>
 #include <linux/sysfs.h>
@@ -1465,6 +1466,13 @@ resolve_symbol_wait(struct module *mod,
 	return ksym;
 }
 
+#ifdef CONFIG_KALLSYMS
+static inline bool sect_empty(const Elf_Shdr *sect)
+{
+	return !(sect->sh_flags & SHF_ALLOC) || sect->sh_size == 0;
+}
+#endif
+
 /*
  * /sys/module/foo/sections stuff
  * J. Corbet <corbet@lwn.net>
@@ -1472,11 +1480,6 @@ resolve_symbol_wait(struct module *mod,
 #ifdef CONFIG_SYSFS
 
 #ifdef CONFIG_KALLSYMS
-static inline bool sect_empty(const Elf_Shdr *sect)
-{
-	return !(sect->sh_flags & SHF_ALLOC) || sect->sh_size == 0;
-}
-
 struct module_sect_attr {
 	struct bin_attribute battr;
 	unsigned long address;
@@ -2797,6 +2800,26 @@ static void add_kallsyms(struct module *mod, const struct load_info *info)
 }
 #endif /* CONFIG_KALLSYMS */
 
+#if IS_ENABLED(CONFIG_KALLSYMS) && IS_ENABLED(CONFIG_STACKTRACE_BUILD_ID)
+static void init_build_id(struct module *mod, const struct load_info *info)
+{
+	const Elf_Shdr *sechdr;
+	unsigned int i;
+
+	for (i = 0; i < info->hdr->e_shnum; i++) {
+		sechdr = &info->sechdrs[i];
+		if (!sect_empty(sechdr) && sechdr->sh_type == SHT_NOTE &&
+		    !build_id_parse_buf((void *)sechdr->sh_addr, mod->build_id,
+					sechdr->sh_size))
+			break;
+	}
+}
+#else
+static void init_build_id(struct module *mod, const struct load_info *info)
+{
+}
+#endif
+
 static void dynamic_debug_setup(struct module *mod, struct _ddebug *debug, unsigned int num)
 {
 	if (!debug)
@@ -4021,6 +4044,7 @@ static int load_module(struct load_info *info, const char __user *uargs,
 		goto free_arch_cleanup;
 	}
 
+	init_build_id(mod, info);
 	dynamic_debug_setup(mod, info->debug, info->num_debug);
 
 	/* Ftrace init must be called in the MODULE_STATE_UNFORMED state */
@@ -4254,6 +4278,7 @@ const char *module_address_lookup(unsigned long addr,
 			    unsigned long *size,
 			    unsigned long *offset,
 			    char **modname,
+			    const unsigned char **modbuildid,
 			    char *namebuf)
 {
 	const char *ret = NULL;
@@ -4264,6 +4289,13 @@ const char *module_address_lookup(unsigned long addr,
 	if (mod) {
 		if (modname)
 			*modname = mod->name;
+		if (modbuildid) {
+#if IS_ENABLED(CONFIG_STACKTRACE_BUILD_ID)
+			*modbuildid = mod->build_id;
+#else
+			*modbuildid = NULL;
+#endif
+		}
 
 		ret = find_kallsyms_symbol(mod, addr, size, offset);
 	}