[PATCH v2 0/3] kallsyms: Rust requirements

[PATCH v2 0/3] kallsyms: Rust requirements

[Miguel Ojeda]

These are the kallsyms patches we carry on the Rust patch series as
prerequisites. We were requested to submit them independently, so
here they are!

  - The first one is an improvement that may be applied even without
    the big symbol support.

  - The second adds support for "big" symbols without actually
    increasing the limit.

  - The third performs the actual increase.

Thanks!

Boqun Feng (1):
  kallsyms: avoid hardcoding the buffer size

Miguel Ojeda (2):
  kallsyms: support "big" kernel symbols
  kallsyms: increase maximum kernel symbol length to 512

 include/linux/kallsyms.h            |  2 +-
 kernel/kallsyms.c                   | 26 +++++++++++++---
 kernel/livepatch/core.c             |  4 +--
 scripts/kallsyms.c                  | 47 ++++++++++++++++++++++++-----
 tools/include/linux/kallsyms.h      |  2 +-
 tools/lib/perf/include/perf/event.h |  2 +-
 tools/lib/symbol/kallsyms.h         |  2 +-
 7 files changed, 68 insertions(+), 17 deletions(-)


base-commit: 672c0c5173427e6b3e2a9bbb7be51ceeec78093a
-- 
2.35.3

[PATCH v2 1/3] kallsyms: avoid hardcoding the buffer size

[Miguel Ojeda]

From: Boqun Feng <boqun.feng@gmail.com>

This makes it easier to update the size later on.

Furthermore, a static assert is added to ensure both are updated
when that happens. The relationship used is one that keeps the new
size (512+1) close to the original buffer size (500).

Reviewed-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Boqun Feng <boqun.feng@gmail.com>
Co-developed-by: Miguel Ojeda <ojeda@kernel.org>
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
v2:
  - Collected Reviewed-by.
  - Use `sizeof(name)` in one instance, suggested by Kees Cook.

 scripts/kallsyms.c | 16 +++++++++++++---
 1 file changed, 13 insertions(+), 3 deletions(-)

diff --git a/scripts/kallsyms.c b/scripts/kallsyms.c
index 8caabddf817c..82d6508bdf29 100644
--- a/scripts/kallsyms.c
+++ b/scripts/kallsyms.c
@@ -27,8 +27,18 @@
 
 #define ARRAY_SIZE(arr) (sizeof(arr) / sizeof(arr[0]))
 
+#define _stringify_1(x)	#x
+#define _stringify(x)	_stringify_1(x)
+
 #define KSYM_NAME_LEN		128
 
+/* A substantially bigger size than the current maximum. */
+#define KSYM_NAME_LEN_BUFFER	512
+_Static_assert(
+	KSYM_NAME_LEN_BUFFER == KSYM_NAME_LEN * 4,
+	"Please keep KSYM_NAME_LEN_BUFFER in sync with KSYM_NAME_LEN"
+);
+
 struct sym_entry {
 	unsigned long long addr;
 	unsigned int len;
@@ -197,15 +207,15 @@ static void check_symbol_range(const char *sym, unsigned long long addr,
 
 static struct sym_entry *read_symbol(FILE *in)
 {
-	char name[500], type;
+	char name[KSYM_NAME_LEN_BUFFER+1], type;
 	unsigned long long addr;
 	unsigned int len;
 	struct sym_entry *sym;
 	int rc;
 
-	rc = fscanf(in, "%llx %c %499s\n", &addr, &type, name);
+	rc = fscanf(in, "%llx %c %" _stringify(KSYM_NAME_LEN_BUFFER) "s\n", &addr, &type, name);
 	if (rc != 3) {
-		if (rc != EOF && fgets(name, 500, in) == NULL)
+		if (rc != EOF && fgets(name, sizeof(name), in) == NULL)
 			fprintf(stderr, "Read error or end of file.\n");
 		return NULL;
 	}
-- 
2.35.3

[PATCH v2 2/3] kallsyms: support "big" kernel symbols

[Miguel Ojeda]

Rust symbols can become quite long due to namespacing introduced
by modules, types, traits, generics, etc.

Increasing to 255 is not enough in some cases, and therefore
we need to introduce longer lengths to the symbol table.

In order to avoid increasing all lengths to 2 bytes (since most
of them are small, including many Rust ones), we use ULEB128 to
keep smaller symbols in 1 byte, with the rest in 2 bytes.

Reviewed-by: Kees Cook <keescook@chromium.org>
Co-developed-by: Alex Gaynor <alex.gaynor@gmail.com>
Signed-off-by: Alex Gaynor <alex.gaynor@gmail.com>
Co-developed-by: Wedson Almeida Filho <wedsonaf@google.com>
Signed-off-by: Wedson Almeida Filho <wedsonaf@google.com>
Co-developed-by: Gary Guo <gary@garyguo.net>
Signed-off-by: Gary Guo <gary@garyguo.net>
Co-developed-by: Boqun Feng <boqun.feng@gmail.com>
Signed-off-by: Boqun Feng <boqun.feng@gmail.com>
Co-developed-by: Matthew Wilcox <willy@infradead.org>
Signed-off-by: Matthew Wilcox <willy@infradead.org>
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
v2:
  - Collected Reviewed-by.

 kernel/kallsyms.c  | 26 ++++++++++++++++++++++----
 scripts/kallsyms.c | 29 ++++++++++++++++++++++++++---
 2 files changed, 48 insertions(+), 7 deletions(-)

diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
index 79f2eb617a62..e8d2262ef2d2 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -69,12 +69,20 @@ 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
@@ -127,7 +135,7 @@ 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,
@@ -141,8 +149,18 @@ 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;
 }
diff --git a/scripts/kallsyms.c b/scripts/kallsyms.c
index 82d6508bdf29..7e99799aa7b9 100644
--- a/scripts/kallsyms.c
+++ b/scripts/kallsyms.c
@@ -480,12 +480,35 @@ static void write_src(void)
 		if ((i & 0xFF) == 0)
 			markers[i >> 8] = off;
 
-		printf("\t.byte 0x%02x", table[i]->len);
+		/* There cannot be any symbol of length zero. */
+		if (table[i]->len == 0) {
+			fprintf(stderr, "kallsyms failure: "
+				"unexpected zero symbol length\n");
+			exit(EXIT_FAILURE);
+		}
+
+		/* Only lengths that fit in up-to-two-byte ULEB128 are supported. */
+		if (table[i]->len > 0x3FFF) {
+			fprintf(stderr, "kallsyms failure: "
+				"unexpected huge symbol length\n");
+			exit(EXIT_FAILURE);
+		}
+
+		/* Encode length with ULEB128. */
+		if (table[i]->len <= 0x7F) {
+			/* Most symbols use a single byte for the length. */
+			printf("\t.byte 0x%02x", table[i]->len);
+			off += table[i]->len + 1;
+		} else {
+			/* "Big" symbols use two bytes. */
+			printf("\t.byte 0x%02x, 0x%02x",
+				(table[i]->len & 0x7F) | 0x80,
+				(table[i]->len >> 7) & 0x7F);
+			off += table[i]->len + 2;
+		}
 		for (k = 0; k < table[i]->len; k++)
 			printf(", 0x%02x", table[i]->sym[k]);
 		printf("\n");
-
-		off += table[i]->len + 1;
 	}
 	printf("\n");
 
-- 
2.35.3

[PATCH v2 3/3] kallsyms: increase maximum kernel symbol length to 512

[Miguel Ojeda]

Rust symbols can become quite long due to namespacing introduced
by modules, types, traits, generics, etc. For instance,
the following code:

    pub mod my_module {
        pub struct MyType;
        pub struct MyGenericType<T>(T);

        pub trait MyTrait {
            fn my_method() -> u32;
        }

        impl MyTrait for MyGenericType<MyType> {
            fn my_method() -> u32 {
                42
            }
        }
    }

generates a symbol of length 96 when using the upcoming v0 mangling scheme:

    _RNvXNtCshGpAVYOtgW1_7example9my_moduleINtB2_13MyGenericTypeNtB2_6MyTypeENtB2_7MyTrait9my_method

At the moment, Rust symbols may reach up to 300 in length.
Setting 512 as the maximum seems like a reasonable choice to
keep some headroom.

Reviewed-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Petr Mladek <pmladek@suse.com>
Co-developed-by: Alex Gaynor <alex.gaynor@gmail.com>
Signed-off-by: Alex Gaynor <alex.gaynor@gmail.com>
Co-developed-by: Wedson Almeida Filho <wedsonaf@google.com>
Signed-off-by: Wedson Almeida Filho <wedsonaf@google.com>
Co-developed-by: Gary Guo <gary@garyguo.net>
Signed-off-by: Gary Guo <gary@garyguo.net>
Co-developed-by: Boqun Feng <boqun.feng@gmail.com>
Signed-off-by: Boqun Feng <boqun.feng@gmail.com>
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
v2:
  - Collected Reviewed-bys.

 include/linux/kallsyms.h            | 2 +-
 kernel/livepatch/core.c             | 4 ++--
 scripts/kallsyms.c                  | 4 ++--
 tools/include/linux/kallsyms.h      | 2 +-
 tools/lib/perf/include/perf/event.h | 2 +-
 tools/lib/symbol/kallsyms.h         | 2 +-
 6 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/include/linux/kallsyms.h b/include/linux/kallsyms.h
index ce1bd2fbf23e..e5ad6e31697d 100644
--- a/include/linux/kallsyms.h
+++ b/include/linux/kallsyms.h
@@ -15,7 +15,7 @@
 
 #include <asm/sections.h>
 
-#define KSYM_NAME_LEN 128
+#define KSYM_NAME_LEN 512
 #define KSYM_SYMBOL_LEN (sizeof("%s+%#lx/%#lx [%s %s]") + \
 			(KSYM_NAME_LEN - 1) + \
 			2*(BITS_PER_LONG*3/10) + (MODULE_NAME_LEN - 1) + \
diff --git a/kernel/livepatch/core.c b/kernel/livepatch/core.c
index bc475e62279d..ec06ce59d728 100644
--- a/kernel/livepatch/core.c
+++ b/kernel/livepatch/core.c
@@ -213,7 +213,7 @@ static int klp_resolve_symbols(Elf_Shdr *sechdrs, const char *strtab,
 	 * we use the smallest/strictest upper bound possible (56, based on
 	 * the current definition of MODULE_NAME_LEN) to prevent overflows.
 	 */
-	BUILD_BUG_ON(MODULE_NAME_LEN < 56 || KSYM_NAME_LEN != 128);
+	BUILD_BUG_ON(MODULE_NAME_LEN < 56 || KSYM_NAME_LEN != 512);
 
 	relas = (Elf_Rela *) relasec->sh_addr;
 	/* For each rela in this klp relocation section */
@@ -227,7 +227,7 @@ static int klp_resolve_symbols(Elf_Shdr *sechdrs, const char *strtab,
 
 		/* Format: .klp.sym.sym_objname.sym_name,sympos */
 		cnt = sscanf(strtab + sym->st_name,
-			     ".klp.sym.%55[^.].%127[^,],%lu",
+			     ".klp.sym.%55[^.].%511[^,],%lu",
 			     sym_objname, sym_name, &sympos);
 		if (cnt != 3) {
 			pr_err("symbol %s has an incorrectly formatted name\n",
diff --git a/scripts/kallsyms.c b/scripts/kallsyms.c
index 7e99799aa7b9..275044b840dc 100644
--- a/scripts/kallsyms.c
+++ b/scripts/kallsyms.c
@@ -30,10 +30,10 @@
 #define _stringify_1(x)	#x
 #define _stringify(x)	_stringify_1(x)
 
-#define KSYM_NAME_LEN		128
+#define KSYM_NAME_LEN		512
 
 /* A substantially bigger size than the current maximum. */
-#define KSYM_NAME_LEN_BUFFER	512
+#define KSYM_NAME_LEN_BUFFER	2048
 _Static_assert(
 	KSYM_NAME_LEN_BUFFER == KSYM_NAME_LEN * 4,
 	"Please keep KSYM_NAME_LEN_BUFFER in sync with KSYM_NAME_LEN"
diff --git a/tools/include/linux/kallsyms.h b/tools/include/linux/kallsyms.h
index efb6c3f5f2a9..5a37ccbec54f 100644
--- a/tools/include/linux/kallsyms.h
+++ b/tools/include/linux/kallsyms.h
@@ -6,7 +6,7 @@
 #include <stdio.h>
 #include <unistd.h>
 
-#define KSYM_NAME_LEN 128
+#define KSYM_NAME_LEN 512
 
 struct module;
 
diff --git a/tools/lib/perf/include/perf/event.h b/tools/lib/perf/include/perf/event.h
index e7758707cadd..116a80c31675 100644
--- a/tools/lib/perf/include/perf/event.h
+++ b/tools/lib/perf/include/perf/event.h
@@ -95,7 +95,7 @@ struct perf_record_throttle {
 };
 
 #ifndef KSYM_NAME_LEN
-#define KSYM_NAME_LEN 256
+#define KSYM_NAME_LEN 512
 #endif
 
 struct perf_record_ksymbol {
diff --git a/tools/lib/symbol/kallsyms.h b/tools/lib/symbol/kallsyms.h
index 72ab9870454b..542f9b059c3b 100644
--- a/tools/lib/symbol/kallsyms.h
+++ b/tools/lib/symbol/kallsyms.h
@@ -7,7 +7,7 @@
 #include <linux/types.h>
 
 #ifndef KSYM_NAME_LEN
-#define KSYM_NAME_LEN 256
+#define KSYM_NAME_LEN 512
 #endif
 
 static inline u8 kallsyms2elf_binding(char type)
-- 
2.35.3