On Mon, Dec 06, 2021 at 03:02:55PM +0100, Miguel Ojeda wrote:
> 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.
>
> Co-developed-by: Alex Gaynor <alex.gaynor@xxxxxxxxx>
> Signed-off-by: Alex Gaynor <alex.gaynor@xxxxxxxxx>
> Co-developed-by: Wedson Almeida Filho <wedsonaf@xxxxxxxxxx>
> Signed-off-by: Wedson Almeida Filho <wedsonaf@xxxxxxxxxx>
> Co-developed-by: Gary Guo <gary@xxxxxxxxxxx>
> Signed-off-by: Gary Guo <gary@xxxxxxxxxxx>
> Co-developed-by: Boqun Feng <boqun.feng@xxxxxxxxx>
> Signed-off-by: Boqun Feng <boqun.feng@xxxxxxxxx>
Who are all these people, who didn't actually do any of this
implementation, and where am I who did?
> Signed-off-by: Miguel Ojeda <ojeda@xxxxxxxxxx>
> ---
> 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 3011bc33a5ba..80702273494a 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 54ad86d13784..79b11bb7f07d 100644
> --- a/scripts/kallsyms.c
> +++ b/scripts/kallsyms.c
> @@ -470,12 +470,35 @@ 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");
>
> --
> 2.34.0
>
