lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20240802230715.GA959572@thelio-3990X>
Date: Fri, 2 Aug 2024 16:07:15 -0700
From: Nathan Chancellor <nathan@...nel.org>
To: Brian Norris <briannorris@...omium.org>
Cc: Yury Norov <yury.norov@...il.com>, linux-kernel@...r.kernel.org,
	Bill Wendling <morbo@...gle.com>,
	Justin Stitt <justinstitt@...gle.com>,
	Nick Desaulniers <ndesaulniers@...gle.com>, llvm@...ts.linux.dev,
	Rasmus Villemoes <linux@...musvillemoes.dk>,
	Kees Cook <kees@...nel.org>
Subject: Re: [PATCH v3 1/4] find: Switch from inline to __always_inline

Hi Brian,

On Thu, Jul 18, 2024 at 05:50:37PM -0700, Brian Norris wrote:
> From: Yury Norov <yury.norov@...il.com>
> 
> 'inline' keyword is only a recommendation for compiler. If it decides to
> not inline find_bit nodemask functions, the whole small_const_nbits()
> machinery doesn't work.
> 
> This is how a standard GCC 11.3.0 does for my x86_64 build now. This patch
> replaces 'inline' directive with unconditional '__always_inline' to make
> sure that there's always a chance for compile-time optimization. It doesn't
> change size of kernel image, according to bloat-o-meter.
> 
> [[ Brian: split out from:
>       Subject: [PATCH 1/3] bitmap: switch from inline to __always_inline
>       https://lore.kernel.org/all/20221027043810.350460-2-yury.norov@gmail.com/
>    But rewritten, as there were too many conflicts. ]]
> 
> Signed-off-by: Yury Norov <yury.norov@...il.com>
> Co-developed-by: Brian Norris <briannorris@...omium.org>
> Signed-off-by: Brian Norris <briannorris@...omium.org>
> Reviewed-by: Kees Cook <kees@...nel.org>

Sorry for taking some time to review this. Overall, this seems
reasonable, especially given the numbers that you provided in the third
patch. I would expect the compiler to be able to optimize better at some
callsites with this.

For the series:

Reviewed-by: Nathan Chancellor <nathan@...nel.org>

> ---
> 
> Changes in v3:
>  - newly split out in v3
> 
>  include/linux/find.h | 50 ++++++++++++++++++++++----------------------
>  1 file changed, 25 insertions(+), 25 deletions(-)
> 
> diff --git a/include/linux/find.h b/include/linux/find.h
> index 5dfca4225fef..68685714bc18 100644
> --- a/include/linux/find.h
> +++ b/include/linux/find.h
> @@ -52,7 +52,7 @@ unsigned long _find_next_bit_le(const unsigned long *addr, unsigned
>   * Returns the bit number for the next set bit
>   * If no bits are set, returns @size.
>   */
> -static inline
> +static __always_inline
>  unsigned long find_next_bit(const unsigned long *addr, unsigned long size,
>  			    unsigned long offset)
>  {
> @@ -81,7 +81,7 @@ unsigned long find_next_bit(const unsigned long *addr, unsigned long size,
>   * Returns the bit number for the next set bit
>   * If no bits are set, returns @size.
>   */
> -static inline
> +static __always_inline
>  unsigned long find_next_and_bit(const unsigned long *addr1,
>  		const unsigned long *addr2, unsigned long size,
>  		unsigned long offset)
> @@ -112,7 +112,7 @@ unsigned long find_next_and_bit(const unsigned long *addr1,
>   * Returns the bit number for the next set bit
>   * If no bits are set, returns @size.
>   */
> -static inline
> +static __always_inline
>  unsigned long find_next_andnot_bit(const unsigned long *addr1,
>  		const unsigned long *addr2, unsigned long size,
>  		unsigned long offset)
> @@ -142,7 +142,7 @@ unsigned long find_next_andnot_bit(const unsigned long *addr1,
>   * Returns the bit number for the next set bit
>   * If no bits are set, returns @size.
>   */
> -static inline
> +static __always_inline
>  unsigned long find_next_or_bit(const unsigned long *addr1,
>  		const unsigned long *addr2, unsigned long size,
>  		unsigned long offset)
> @@ -171,7 +171,7 @@ unsigned long find_next_or_bit(const unsigned long *addr1,
>   * Returns the bit number of the next zero bit
>   * If no bits are zero, returns @size.
>   */
> -static inline
> +static __always_inline
>  unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size,
>  				 unsigned long offset)
>  {
> @@ -198,7 +198,7 @@ unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size,
>   * Returns the bit number of the first set bit.
>   * If no bits are set, returns @size.
>   */
> -static inline
> +static __always_inline
>  unsigned long find_first_bit(const unsigned long *addr, unsigned long size)
>  {
>  	if (small_const_nbits(size)) {
> @@ -224,7 +224,7 @@ unsigned long find_first_bit(const unsigned long *addr, unsigned long size)
>   * Returns the bit number of the N'th set bit.
>   * If no such, returns >= @size.
>   */
> -static inline
> +static __always_inline
>  unsigned long find_nth_bit(const unsigned long *addr, unsigned long size, unsigned long n)
>  {
>  	if (n >= size)
> @@ -249,7 +249,7 @@ unsigned long find_nth_bit(const unsigned long *addr, unsigned long size, unsign
>   * Returns the bit number of the N'th set bit.
>   * If no such, returns @size.
>   */
> -static inline
> +static __always_inline
>  unsigned long find_nth_and_bit(const unsigned long *addr1, const unsigned long *addr2,
>  				unsigned long size, unsigned long n)
>  {
> @@ -276,7 +276,7 @@ unsigned long find_nth_and_bit(const unsigned long *addr1, const unsigned long *
>   * Returns the bit number of the N'th set bit.
>   * If no such, returns @size.
>   */
> -static inline
> +static __always_inline
>  unsigned long find_nth_andnot_bit(const unsigned long *addr1, const unsigned long *addr2,
>  				unsigned long size, unsigned long n)
>  {
> @@ -332,7 +332,7 @@ unsigned long find_nth_and_andnot_bit(const unsigned long *addr1,
>   * Returns the bit number for the next set bit
>   * If no bits are set, returns @size.
>   */
> -static inline
> +static __always_inline
>  unsigned long find_first_and_bit(const unsigned long *addr1,
>  				 const unsigned long *addr2,
>  				 unsigned long size)
> @@ -357,7 +357,7 @@ unsigned long find_first_and_bit(const unsigned long *addr1,
>   * Returns the bit number for the first set bit
>   * If no bits are set, returns @size.
>   */
> -static inline
> +static __always_inline
>  unsigned long find_first_and_and_bit(const unsigned long *addr1,
>  				     const unsigned long *addr2,
>  				     const unsigned long *addr3,
> @@ -381,7 +381,7 @@ unsigned long find_first_and_and_bit(const unsigned long *addr1,
>   * Returns the bit number of the first cleared bit.
>   * If no bits are zero, returns @size.
>   */
> -static inline
> +static __always_inline
>  unsigned long find_first_zero_bit(const unsigned long *addr, unsigned long size)
>  {
>  	if (small_const_nbits(size)) {
> @@ -402,7 +402,7 @@ unsigned long find_first_zero_bit(const unsigned long *addr, unsigned long size)
>   *
>   * Returns the bit number of the last set bit, or size.
>   */
> -static inline
> +static __always_inline
>  unsigned long find_last_bit(const unsigned long *addr, unsigned long size)
>  {
>  	if (small_const_nbits(size)) {
> @@ -425,7 +425,7 @@ unsigned long find_last_bit(const unsigned long *addr, unsigned long size)
>   * Returns the bit number for the next set bit, or first set bit up to @offset
>   * If no bits are set, returns @size.
>   */
> -static inline
> +static __always_inline
>  unsigned long find_next_and_bit_wrap(const unsigned long *addr1,
>  					const unsigned long *addr2,
>  					unsigned long size, unsigned long offset)
> @@ -448,7 +448,7 @@ unsigned long find_next_and_bit_wrap(const unsigned long *addr1,
>   * Returns the bit number for the next set bit, or first set bit up to @offset
>   * If no bits are set, returns @size.
>   */
> -static inline
> +static __always_inline
>  unsigned long find_next_bit_wrap(const unsigned long *addr,
>  					unsigned long size, unsigned long offset)
>  {
> @@ -465,7 +465,7 @@ unsigned long find_next_bit_wrap(const unsigned long *addr,
>   * Helper for for_each_set_bit_wrap(). Make sure you're doing right thing
>   * before using it alone.
>   */
> -static inline
> +static __always_inline
>  unsigned long __for_each_wrap(const unsigned long *bitmap, unsigned long size,
>  				 unsigned long start, unsigned long n)
>  {
> @@ -506,20 +506,20 @@ extern unsigned long find_next_clump8(unsigned long *clump,
>  
>  #if defined(__LITTLE_ENDIAN)
>  
> -static inline unsigned long find_next_zero_bit_le(const void *addr,
> -		unsigned long size, unsigned long offset)
> +static __always_inline
> +unsigned long find_next_zero_bit_le(const void *addr, unsigned long size, unsigned long offset)
>  {
>  	return find_next_zero_bit(addr, size, offset);
>  }
>  
> -static inline unsigned long find_next_bit_le(const void *addr,
> -		unsigned long size, unsigned long offset)
> +static __always_inline
> +unsigned long find_next_bit_le(const void *addr, unsigned long size, unsigned long offset)
>  {
>  	return find_next_bit(addr, size, offset);
>  }
>  
> -static inline unsigned long find_first_zero_bit_le(const void *addr,
> -		unsigned long size)
> +static __always_inline
> +unsigned long find_first_zero_bit_le(const void *addr, unsigned long size)
>  {
>  	return find_first_zero_bit(addr, size);
>  }
> @@ -527,7 +527,7 @@ static inline unsigned long find_first_zero_bit_le(const void *addr,
>  #elif defined(__BIG_ENDIAN)
>  
>  #ifndef find_next_zero_bit_le
> -static inline
> +static __always_inline
>  unsigned long find_next_zero_bit_le(const void *addr, unsigned
>  		long size, unsigned long offset)
>  {
> @@ -546,7 +546,7 @@ unsigned long find_next_zero_bit_le(const void *addr, unsigned
>  #endif
>  
>  #ifndef find_first_zero_bit_le
> -static inline
> +static __always_inline
>  unsigned long find_first_zero_bit_le(const void *addr, unsigned long size)
>  {
>  	if (small_const_nbits(size)) {
> @@ -560,7 +560,7 @@ unsigned long find_first_zero_bit_le(const void *addr, unsigned long size)
>  #endif
>  
>  #ifndef find_next_bit_le
> -static inline
> +static __always_inline
>  unsigned long find_next_bit_le(const void *addr, unsigned
>  		long size, unsigned long offset)
>  {
> -- 
> 2.45.2.1089.g2a221341d9-goog
> 

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ