[v1,6/7] RISC-V: remove decrement/increment dance in ISA string parser

Commit Message

Conor Dooley May 4, 2023, 6:14 p.m. UTC

From: Conor Dooley <[e-mail]>

While expanding on the comments in the ISA string parsing code, I
noticed that the conditional decrement of `isa` at the end of the loop
was a bit odd.
The parsing code expects that at the start of the for loop, `isa` will
point to the first character of the next unparsed extension.
However, depending on what the next extension is, this may not be true.
Unless the next extension is a multi-letter extension preceded by an
underscore, `isa` will either point to the string's null-terminator or
to the first character of the next extension, once the switch statement
has been evaluated.
Obviously incrementing `isa` at the end of the loop could cause it to
increment past the null terminator or miss a single letter extension, so
`isa` is conditionally decremented, just so that the loop can increment
it again.

It's easier to understand the code if, instead of this decrement +
increment dance, we instead use a while loop & rely on the handling of
individual extension types to leave `isa` pointing to the first
character of the next extension.
As already mentioned, this won't be the case where the following
extension is multi-letter & preceded by an underscore. To handle that,
invert the check and increment rather than decrement.
Hopefully this eliminates a "huh?!?" moment the next time somebody tries
to understand this code.

Signed-off-by: Conor Dooley <[e-mail]>
---
 arch/riscv/kernel/cpufeature.c | 14 ++++++--------
 1 file changed, 6 insertions(+), 8 deletions(-)

Comments

Andrew Jones May 5, 2023, 11:01 a.m. UTC | #1

On Thu, May 04, 2023 at 07:14:25PM +0100, Conor Dooley wrote:
> From: Conor Dooley <[e-mail]>
> 
> While expanding on the comments in the ISA string parsing code, I
> noticed that the conditional decrement of `isa` at the end of the loop
> was a bit odd.
> The parsing code expects that at the start of the for loop, `isa` will
> point to the first character of the next unparsed extension.
> However, depending on what the next extension is, this may not be true.
> Unless the next extension is a multi-letter extension preceded by an
> underscore, `isa` will either point to the string's null-terminator or
> to the first character of the next extension, once the switch statement
> has been evaluated.
> Obviously incrementing `isa` at the end of the loop could cause it to
> increment past the null terminator or miss a single letter extension, so
> `isa` is conditionally decremented, just so that the loop can increment
> it again.
> 
> It's easier to understand the code if, instead of this decrement +
> increment dance, we instead use a while loop & rely on the handling of
> individual extension types to leave `isa` pointing to the first
> character of the next extension.
> As already mentioned, this won't be the case where the following
> extension is multi-letter & preceded by an underscore. To handle that,
> invert the check and increment rather than decrement.
> Hopefully this eliminates a "huh?!?" moment the next time somebody tries
> to understand this code.
> 
> Signed-off-by: Conor Dooley <[e-mail]>
> ---
>  arch/riscv/kernel/cpufeature.c | 14 ++++++--------
>  1 file changed, 6 insertions(+), 8 deletions(-)
>

Reviewed-by: Andrew Jones <[e-mail]>

Patch

diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
index 2fc72f092057..b425658bbf08 100644
--- a/arch/riscv/kernel/cpufeature.c
+++ b/arch/riscv/kernel/cpufeature.c
@@ -139,7 +139,7 @@  void __init riscv_fill_hwcap(void)
 		isa += 4;
 
 		bitmap_zero(this_isa, RISCV_ISA_EXT_MAX);
-		for (; *isa; ++isa) {
+		while (*isa) {
 			const char *ext = isa++;
 			const char *ext_end = isa;
 			bool ext_long = false, ext_err = false;
@@ -253,14 +253,12 @@  void __init riscv_fill_hwcap(void)
 
 			/*
 			 * The parser expects that at the start of an iteration isa points to the
-			 * character before the start of the next extension. This will not be the
-			 * case if we have just parsed a single-letter extension and the next
-			 * extension is not a multi-letter extension prefixed with an "_". It is
-			 * also not the case at the end of the string, where it will point to the
-			 * terminating null character.
+			 * first character of the next extension. As we stop parsing an extension
+			 * on meeting a non-alphanumeric character, an extra increment is needed
+			 * where the succeeding extension is a multi-letter prefixed with an "_".
 			 */
-			if (*isa != '_')
-				--isa;
+			if (*isa == '_')
+				++isa;
 
 #define SET_ISA_EXT_MAP(name, bit)							\
 			do {								\