1 files changed, 309 insertions, 154 deletions

diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
index fe9de067771c..a9a0ca605d4a 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -25,30 +25,14 @@
 #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>
+#include <linux/bsearch.h>
+#include <linux/btf_ids.h>
 
-/*
- * These will be re-linked against their real values
- * during the second link stage.
- */
-extern const unsigned long kallsyms_addresses[] __weak;
-extern const int kallsyms_offsets[] __weak;
-extern const u8 kallsyms_names[] __weak;
-
-/*
- * Tell the compiler that the count isn't in the small data section if the arch
- * has one (eg: FRV).
- */
-extern const unsigned int kallsyms_num_syms
-__section(".rodata") __attribute__((weak));
-
-extern const unsigned long kallsyms_relative_base
-__section(".rodata") __attribute__((weak));
-
-extern const char kallsyms_token_table[] __weak;
-extern const u16 kallsyms_token_index[] __weak;
-
-extern const unsigned int kallsyms_markers[] __weak;
+#include "kallsyms_internal.h"
 
 /*
  * Expand a compressed symbol data into the resulting uncompressed string,
@@ -66,12 +50,20 @@ static unsigned int kallsyms_expand_symbol(unsigned int off,
 	data = &kallsyms_names[off];
 	len = *data;
 	data++;
+	off++;
+
+	/* If MSB is 1, it is a "big" symbol, so needs an additional byte. */
+	if ((len & 0x80) != 0) {
+		len = (len & 0x7F) | (*data << 7);
+		data++;
+		off++;
+	}
 
 	/*
 	 * Update the offset to return the offset for the next symbol on
 	 * the compressed stream.
 	 */
-	off += len + 1;
+	off += len;
 
 	/*
 	 * For every byte on the compressed symbol data, copy the table
@@ -124,7 +116,7 @@ static char kallsyms_get_symbol_type(unsigned int off)
 static unsigned int get_symbol_offset(unsigned long pos)
 {
 	const u8 *name;
-	int i;
+	int i, len;
 
 	/*
 	 * Use the closest marker we have. We have markers every 256 positions,
@@ -138,17 +130,24 @@ static unsigned int get_symbol_offset(unsigned long pos)
 	 * so we just need to add the len to the current pointer for every
 	 * symbol we wish to skip.
 	 */
-	for (i = 0; i < (pos & 0xFF); i++)
-		name = name + (*name) + 1;
+	for (i = 0; i < (pos & 0xFF); i++) {
+		len = *name;
+
+		/*
+		 * If MSB is 1, it is a "big" symbol, so we need to look into
+		 * the next byte (and skip it, too).
+		 */
+		if ((len & 0x80) != 0)
+			len = ((len & 0x7F) | (name[1] << 7)) + 1;
+
+		name = name + len + 1;
+	}
 
 	return name - kallsyms_names;
 }
 
-static unsigned long kallsyms_sym_address(int idx)
+unsigned long kallsyms_sym_address(int idx)
 {
-	if (!IS_ENABLED(CONFIG_KALLSYMS_BASE_RELATIVE))
-		return kallsyms_addresses[idx];
-
 	/* values are unsigned offsets if --absolute-percpu is not in effect */
 	if (!IS_ENABLED(CONFIG_KALLSYMS_ABSOLUTE_PERCPU))
 		return kallsyms_relative_base + (u32)kallsyms_offsets[idx];
@@ -161,24 +160,94 @@ static unsigned long kallsyms_sym_address(int idx)
 	return kallsyms_relative_base - 1 - kallsyms_offsets[idx];
 }
 
-/* Lookup the address for this symbol. Returns 0 if not found. */
-unsigned long kallsyms_lookup_name(const char *name)
+static unsigned int get_symbol_seq(int index)
 {
+	unsigned int i, seq = 0;
+
+	for (i = 0; i < 3; i++)
+		seq = (seq << 8) | kallsyms_seqs_of_names[3 * index + i];
+
+	return seq;
+}
+
+static int kallsyms_lookup_names(const char *name,
+				 unsigned int *start,
+				 unsigned int *end)
+{
+	int ret;
+	int low, mid, high;
+	unsigned int seq, off;
 	char namebuf[KSYM_NAME_LEN];
-	unsigned long i;
-	unsigned int off;
 
-	for (i = 0, off = 0; i < kallsyms_num_syms; i++) {
-		off = kallsyms_expand_symbol(off, namebuf, ARRAY_SIZE(namebuf));
+	low = 0;
+	high = kallsyms_num_syms - 1;
+
+	while (low <= high) {
+		mid = low + (high - low) / 2;
+		seq = get_symbol_seq(mid);
+		off = get_symbol_offset(seq);
+		kallsyms_expand_symbol(off, namebuf, ARRAY_SIZE(namebuf));
+		ret = strcmp(name, namebuf);
+		if (ret > 0)
+			low = mid + 1;
+		else if (ret < 0)
+			high = mid - 1;
+		else
+			break;
+	}
+
+	if (low > high)
+		return -ESRCH;
 
-		if (strcmp(namebuf, name) == 0)
-			return kallsyms_sym_address(i);
+	low = mid;
+	while (low) {
+		seq = get_symbol_seq(low - 1);
+		off = get_symbol_offset(seq);
+		kallsyms_expand_symbol(off, namebuf, ARRAY_SIZE(namebuf));
+		if (strcmp(name, namebuf))
+			break;
+		low--;
 	}
+	*start = low;
+
+	if (end) {
+		high = mid;
+		while (high < kallsyms_num_syms - 1) {
+			seq = get_symbol_seq(high + 1);
+			off = get_symbol_offset(seq);
+			kallsyms_expand_symbol(off, namebuf, ARRAY_SIZE(namebuf));
+			if (strcmp(name, namebuf))
+				break;
+			high++;
+		}
+		*end = high;
+	}
+
+	return 0;
+}
+
+/* Lookup the address for this symbol. Returns 0 if not found. */
+unsigned long kallsyms_lookup_name(const char *name)
+{
+	int ret;
+	unsigned int i;
+
+	/* Skip the search for empty string. */
+	if (!*name)
+		return 0;
+
+	ret = kallsyms_lookup_names(name, &i, NULL);
+	if (!ret)
+		return kallsyms_sym_address(get_symbol_seq(i));
+
 	return module_kallsyms_lookup_name(name);
 }
 
-int kallsyms_on_each_symbol(int (*fn)(void *, const char *, struct module *,
-				      unsigned long),
+/*
+ * Iterate over all symbols in vmlinux.  For symbols from modules use
+ * module_kallsyms_on_each_symbol instead.
+ */
+int kallsyms_on_each_symbol(int (*fn)(void *, const char *, unsigned long),
 			    void *data)
 {
 	char namebuf[KSYM_NAME_LEN];
@@ -188,11 +257,30 @@ int kallsyms_on_each_symbol(int (*fn)(void *, const char *, struct module *,
 
 	for (i = 0, off = 0; i < kallsyms_num_syms; i++) {
 		off = kallsyms_expand_symbol(off, namebuf, ARRAY_SIZE(namebuf));
-		ret = fn(data, namebuf, NULL, kallsyms_sym_address(i));
+		ret = fn(data, namebuf, kallsyms_sym_address(i));
 		if (ret != 0)
 			return ret;
+		cond_resched();
 	}
-	return module_kallsyms_on_each_symbol(fn, data);
+	return 0;
+}
+
+int kallsyms_on_each_match_symbol(int (*fn)(void *, unsigned long),
+				  const char *name, void *data)
+{
+	int ret;
+	unsigned int i, start, end;
+
+	ret = kallsyms_lookup_names(name, &start, &end);
+	if (ret)
+		return 0;
+
+	for (i = start; !ret && i <= end; i++) {
+		ret = fn(data, kallsyms_sym_address(get_symbol_seq(i)));
+		cond_resched();
+	}
+
+	return ret;
 }
 
 static unsigned long get_symbol_pos(unsigned long addr,
@@ -202,13 +290,7 @@ static unsigned long get_symbol_pos(unsigned long addr,
 	unsigned long symbol_start = 0, symbol_end = 0;
 	unsigned long i, low, high, mid;
 
-	/* This kernel should never had been booted. */
-	if (!IS_ENABLED(CONFIG_KALLSYMS_BASE_RELATIVE))
-		BUG_ON(!kallsyms_addresses);
-	else
-		BUG_ON(!kallsyms_offsets);
-
-	/* Do a binary search on the sorted kallsyms_addresses array. */
+	/* Do a binary search on the sorted kallsyms_offsets array. */
 	low = 0;
 	high = kallsyms_num_syms;
 
@@ -267,23 +349,16 @@ 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 int kallsyms_lookup_buildid(unsigned long addr,
+			unsigned long *symbolsize,
+			unsigned long *offset, char **modname,
+			const unsigned char **modbuildid, char *namebuf)
 {
-	const char *ret;
+	int ret;
 
 	namebuf[KSYM_NAME_LEN - 1] = 0;
 	namebuf[0] = 0;
@@ -297,12 +372,15 @@ const char *kallsyms_lookup(unsigned long addr,
 				       namebuf, KSYM_NAME_LEN);
 		if (modname)
 			*modname = NULL;
-		return namebuf;
+		if (modbuildid)
+			*modbuildid = NULL;
+
+		return strlen(namebuf);
 	}
 
 	/* 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);
@@ -310,9 +388,31 @@ const char *kallsyms_lookup(unsigned long addr,
 	if (!ret)
 		ret = ftrace_mod_address_lookup(addr, symbolsize,
 						offset, modname, namebuf);
+
 	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)
+{
+	int ret = kallsyms_lookup_buildid(addr, symbolsize, offset, modname,
+					  NULL, namebuf);
+
+	if (!ret)
+		return NULL;
+
+	return namebuf;
+}
+
 int lookup_symbol_name(unsigned long addr, char *symname)
 {
 	symname[0] = '\0';
@@ -331,50 +431,39 @@ int lookup_symbol_name(unsigned long addr, char *symname)
 	return lookup_module_symbol_name(addr, symname);
 }
 
-int lookup_symbol_attrs(unsigned long addr, unsigned long *size,
-			unsigned long *offset, char *modname, char *name)
-{
-	name[0] = '\0';
-	name[KSYM_NAME_LEN - 1] = '\0';
-
-	if (is_ksym_addr(addr)) {
-		unsigned long pos;
-
-		pos = get_symbol_pos(addr, size, offset);
-		/* Grab name */
-		kallsyms_expand_symbol(get_symbol_offset(pos),
-				       name, KSYM_NAME_LEN);
-		modname[0] = '\0';
-		return 0;
-	}
-	/* See if it's in a module. */
-	return lookup_module_symbol_attrs(addr, size, offset, modname, name);
-}
-
 /* 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 char *name;
+	const unsigned char *buildid;
 	unsigned long offset, size;
 	int len;
 
 	address += symbol_offset;
-	name = kallsyms_lookup(address, &size, &offset, &modname, buffer);
-	if (!name)
+	len = kallsyms_lookup_buildid(address, &size, &offset, &modname, &buildid,
+				       buffer);
+	if (!len)
 		return sprintf(buffer, "0x%lx", address - symbol_offset);
 
-	if (name != buffer)
-		strcpy(buffer, name);
-	len = strlen(buffer);
 	offset -= symbol_offset;
 
 	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;
 }
@@ -392,11 +481,28 @@ 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
@@ -409,7 +515,7 @@ 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);
 
@@ -429,13 +535,32 @@ 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. */
 struct kallsym_iter {
 	loff_t pos;
-	loff_t pos_arch_end;
 	loff_t pos_mod_end;
 	loff_t pos_ftrace_mod_end;
 	loff_t pos_bpf_end;
@@ -448,29 +573,9 @@ struct kallsym_iter {
 	int show_value;
 };
 
-int __weak arch_get_kallsym(unsigned int symnum, unsigned long *value,
-			    char *type, char *name)
-{
-	return -EINVAL;
-}
-
-static int get_ksymbol_arch(struct kallsym_iter *iter)
-{
-	int ret = arch_get_kallsym(iter->pos - kallsyms_num_syms,
-				   &iter->value, &iter->type,
-				   iter->name);
-
-	if (ret < 0) {
-		iter->pos_arch_end = iter->pos;
-		return 0;
-	}
-
-	return 1;
-}
-
 static int get_ksymbol_mod(struct kallsym_iter *iter)
 {
-	int ret = module_get_kallsym(iter->pos - iter->pos_arch_end,
+	int ret = module_get_kallsym(iter->pos - kallsyms_num_syms,
 				     &iter->value, &iter->type,
 				     iter->name, iter->module_name,
 				     &iter->exported);
@@ -505,7 +610,7 @@ static int get_ksymbol_bpf(struct kallsym_iter *iter)
 {
 	int ret;
 
-	strlcpy(iter->module_name, "bpf", MODULE_NAME_LEN);
+	strscpy(iter->module_name, "bpf", MODULE_NAME_LEN);
 	iter->exported = 0;
 	ret = bpf_get_kallsym(iter->pos - iter->pos_ftrace_mod_end,
 			      &iter->value, &iter->type,
@@ -525,7 +630,7 @@ static int get_ksymbol_bpf(struct kallsym_iter *iter)
  */
 static int get_ksymbol_kprobe(struct kallsym_iter *iter)
 {
-	strlcpy(iter->module_name, "__builtin__kprobes", MODULE_NAME_LEN);
+	strscpy(iter->module_name, "__builtin__kprobes", MODULE_NAME_LEN);
 	iter->exported = 0;
 	return kprobe_get_kallsym(iter->pos - iter->pos_bpf_end,
 				  &iter->value, &iter->type,
@@ -553,7 +658,6 @@ static void reset_iter(struct kallsym_iter *iter, loff_t new_pos)
 	iter->nameoff = get_symbol_offset(new_pos);
 	iter->pos = new_pos;
 	if (new_pos == 0) {
-		iter->pos_arch_end = 0;
 		iter->pos_mod_end = 0;
 		iter->pos_ftrace_mod_end = 0;
 		iter->pos_bpf_end = 0;
@@ -569,10 +673,6 @@ static int update_iter_mod(struct kallsym_iter *iter, loff_t pos)
 {
 	iter->pos = pos;
 
-	if ((!iter->pos_arch_end || iter->pos_arch_end > pos) &&
-	    get_ksymbol_arch(iter))
-		return 1;
-
 	if ((!iter->pos_mod_end || iter->pos_mod_end > pos) &&
 	    get_ksymbol_mod(iter))
 		return 1;
@@ -660,41 +760,96 @@ static const struct seq_operations kallsyms_op = {
 	.show = s_show
 };
 
-static inline int kallsyms_for_perf(void)
+#ifdef CONFIG_BPF_SYSCALL
+
+struct bpf_iter__ksym {
+	__bpf_md_ptr(struct bpf_iter_meta *, meta);
+	__bpf_md_ptr(struct kallsym_iter *, ksym);
+};
+
+static int ksym_prog_seq_show(struct seq_file *m, bool in_stop)
 {
-#ifdef CONFIG_PERF_EVENTS
-	extern int sysctl_perf_event_paranoid;
-	if (sysctl_perf_event_paranoid <= 1)
-		return 1;
-#endif
+	struct bpf_iter__ksym ctx;
+	struct bpf_iter_meta meta;
+	struct bpf_prog *prog;
+
+	meta.seq = m;
+	prog = bpf_iter_get_info(&meta, in_stop);
+	if (!prog)
+		return 0;
+
+	ctx.meta = &meta;
+	ctx.ksym = m ? m->private : NULL;
+	return bpf_iter_run_prog(prog, &ctx);
+}
+
+static int bpf_iter_ksym_seq_show(struct seq_file *m, void *p)
+{
+	return ksym_prog_seq_show(m, false);
+}
+
+static void bpf_iter_ksym_seq_stop(struct seq_file *m, void *p)
+{
+	if (!p)
+		(void) ksym_prog_seq_show(m, true);
+	else
+		s_stop(m, p);
+}
+
+static const struct seq_operations bpf_iter_ksym_ops = {
+	.start = s_start,
+	.next = s_next,
+	.stop = bpf_iter_ksym_seq_stop,
+	.show = bpf_iter_ksym_seq_show,
+};
+
+static int bpf_iter_ksym_init(void *priv_data, struct bpf_iter_aux_info *aux)
+{
+	struct kallsym_iter *iter = priv_data;
+
+	reset_iter(iter, 0);
+
+	/* cache here as in kallsyms_open() case; use current process
+	 * credentials to tell BPF iterators if values should be shown.
+	 */
+	iter->show_value = kallsyms_show_value(current_cred());
+
 	return 0;
 }
 
-/*
- * We show kallsyms information even to normal users if we've enabled
- * kernel profiling and are explicitly not paranoid (so kptr_restrict
- * is clear, and sysctl_perf_event_paranoid isn't set).
- *
- * Otherwise, require CAP_SYSLOG (assuming kptr_restrict isn't set to
- * block even that).
- */
-bool kallsyms_show_value(const struct cred *cred)
-{
-	switch (kptr_restrict) {
-	case 0:
-		if (kallsyms_for_perf())
-			return true;
-		fallthrough;
-	case 1:
-		if (security_capable(cred, &init_user_ns, CAP_SYSLOG,
-				     CAP_OPT_NOAUDIT) == 0)
-			return true;
-		fallthrough;
-	default:
-		return false;
-	}
+DEFINE_BPF_ITER_FUNC(ksym, struct bpf_iter_meta *meta, struct kallsym_iter *ksym)
+
+static const struct bpf_iter_seq_info ksym_iter_seq_info = {
+	.seq_ops		= &bpf_iter_ksym_ops,
+	.init_seq_private	= bpf_iter_ksym_init,
+	.fini_seq_private	= NULL,
+	.seq_priv_size		= sizeof(struct kallsym_iter),
+};
+
+static struct bpf_iter_reg ksym_iter_reg_info = {
+	.target                 = "ksym",
+	.feature		= BPF_ITER_RESCHED,
+	.ctx_arg_info_size	= 1,
+	.ctx_arg_info		= {
+		{ offsetof(struct bpf_iter__ksym, ksym),
+		  PTR_TO_BTF_ID_OR_NULL },
+	},
+	.seq_info		= &ksym_iter_seq_info,
+};
+
+BTF_ID_LIST(btf_ksym_iter_id)
+BTF_ID(struct, kallsym_iter)
+
+static int __init bpf_ksym_iter_register(void)
+{
+	ksym_iter_reg_info.ctx_arg_info[0].btf_id = *btf_ksym_iter_id;
+	return bpf_iter_reg_target(&ksym_iter_reg_info);
 }
 
+late_initcall(bpf_ksym_iter_register);
+
+#endif /* CONFIG_BPF_SYSCALL */
+
 static int kallsyms_open(struct inode *inode, struct file *file)
 {
 	/*