Re: [PATCH 00/27 5.10.y] Backport minmax.h updates from v6.17-rc6

["Christian König" <christian.koenig@amd.com>]

On 19.09.25 12:17, Eliav Farber wrote:
> This series includes a total of 27 patches, to align minmax.h of
> v5.15.y with v6.17-rc6.
> 
> The set consists of 24 commits that directly update minmax.h:
> 1) 92d23c6e9415 ("overflow, tracing: Define the is_signed_type() macro
>    once")
> 2) 5efcecd9a3b1 ("minmax: sanity check constant bounds when clamping")
> 3) 2122e2a4efc2 ("minmax: clamp more efficiently by avoiding extra
>    comparison")
> 4) f9bff0e31881 ("minmax: add in_range() macro")
> 5) c952c748c7a9 ("minmax: Introduce {min,max}_array()")
> 6) 5e57418a2031 ("minmax: deduplicate __unconst_integer_typeof()")
> 7) f6e9d38f8eb0 ("minmax: fix header inclusions")
> 8) d03eba99f5bf ("minmax: allow min()/max()/clamp() if the arguments
>    have the same signedness.")
> 9) f4b84b2ff851 ("minmax: fix indentation of __cmp_once() and
>    __clamp_once()")
> 10) 4ead534fba42 ("minmax: allow comparisons of 'int' against 'unsigned
>     char/short'")
> 11) 867046cc7027 ("minmax: relax check to allow comparison between
>     unsigned arguments and signed constants")
> 12) 3a7e02c040b1 ("minmax: avoid overly complicated constant
>     expressions in VM code")
> 14) 017fa3e89187 ("minmax: simplify and clarify min_t()/max_t()
>     implementation")
> 15) 1a251f52cfdc ("minmax: make generic MIN() and MAX() macros
>     available everywhere")
> 18) dc1c8034e31b ("minmax: simplify min()/max()/clamp()
>     implementation")
> 19) 22f546873149 ("minmax: improve macro expansion and type
>     checking")
> 20) 21b136cc63d2 ("minmax: fix up min3() and max3() too")
> 21) 71ee9b16251e ("minmax.h: add whitespace around operators and after
>     commas")
> 22) 10666e992048 ("minmax.h: update some comments")
> 23) b280bb27a9f7 ("minmax.h: reduce the #define expansion of min(),
>     max() and clamp()")
> 24) a5743f32baec ("minmax.h: use BUILD_BUG_ON_MSG() for the lo < hi
>     test in clamp()")
> 25) c3939872ee4a ("minmax.h: move all the clamp() definitions after the
>     min/max() ones")
> 26) 495bba17cdf9 ("minmax.h: simplify the variants of clamp()")
> 27) 2b97aaf74ed5 ("minmax.h: remove some #defines that are only
>     expanded once")
> 
> 2 prerequisite commits that adjust users of MIN and MAX macros (to
> prevent compilation issues):
> 13) 4477b39c32fd ("minmax: add a few more MIN_T/MAX_T users")
> 17) cb04e8b1d2f2 ("minmax: don't use max() in situations that want a C
>     constant expression")
> 
> 1 additional commit introduced to resolve a build failures during the
> backport:
> 16) lib: zstd: drop local MIN/MAX macros in favor of generic ones
> 
> The primary motivation is to bring in commit (8).
> In mainline, this change allows min()/max()/clamp() to accept mixed
> argument types when both share the same signedness.
> Backported patches to v5.10.y that use such forms trigger compiler
> warnings, which in turn cause build failures when -Werror is enabled.
> 
> Originaly I aligned 5.10.y to 5.15.y, but David Laight commented that I
> need to pick up the later changes (from Linus) as well.
> 
> Andy Shevchenko (2):
>   minmax: deduplicate __unconst_integer_typeof()
>   minmax: fix header inclusions
> 
> Bart Van Assche (1):
>   overflow, tracing: Define the is_signed_type() macro once
> 
> David Laight (11):
>   minmax: allow min()/max()/clamp() if the arguments have the same
>     signedness.
>   minmax: fix indentation of __cmp_once() and __clamp_once()
>   minmax: allow comparisons of 'int' against 'unsigned char/short'
>   minmax: relax check to allow comparison between unsigned arguments and
>     signed constants
>   minmax.h: add whitespace around operators and after commas
>   minmax.h: update some comments
>   minmax.h: reduce the #define expansion of min(), max() and clamp()
>   minmax.h: use BUILD_BUG_ON_MSG() for the lo < hi test in clamp()
>   minmax.h: move all the clamp() definitions after the min/max() ones
>   minmax.h: simplify the variants of clamp()
>   minmax.h: remove some #defines that are only expanded once
> 
> Eliav Farber (1):
>   lib: zstd: drop local MIN/MAX macros in favor of generic ones
> 
> Herve Codina (1):
>   minmax: Introduce {min,max}_array()
> 
> Jason A. Donenfeld (2):
>   minmax: sanity check constant bounds when clamping
>   minmax: clamp more efficiently by avoiding extra comparison
> 
> Linus Torvalds (8):
>   minmax: avoid overly complicated constant expressions in VM code
>   minmax: add a few more MIN_T/MAX_T users
>   minmax: simplify and clarify min_t()/max_t() implementation
>   minmax: make generic MIN() and MAX() macros available everywhere
>   minmax: don't use max() in situations that want a C constant
>     expression
>   minmax: simplify min()/max()/clamp() implementation
>   minmax: improve macro expansion and type checking
>   minmax: fix up min3() and max3() too
> 
> Matthew Wilcox (Oracle) (1):
>   minmax: add in_range() macro
> 
>  arch/arm/mm/pageattr.c                        |   6 +-
>  arch/um/drivers/mconsole_user.c               |   2 +
>  arch/x86/mm/pgtable.c                         |   2 +-

>  drivers/edac/sb_edac.c                        |   4 +-
>  drivers/edac/skx_common.h                     |   1 -
>  .../drm/amd/display/modules/hdcp/hdcp_ddc.c   |   2 +
>  .../drm/amd/pm/powerplay/hwmgr/ppevvmath.h    |  14 +-
>  .../drm/arm/display/include/malidp_utils.h    |   2 +-
>  .../display/komeda/komeda_pipeline_state.c    |  24 +-
>  drivers/gpu/drm/drm_color_mgmt.c              |   2 +-
>  drivers/gpu/drm/msm/adreno/a6xx_gmu.c         |   6 -
>  drivers/gpu/drm/radeon/evergreen_cs.c         |   2 +
>  drivers/hwmon/adt7475.c                       |  24 +-
>  drivers/input/touchscreen/cyttsp4_core.c      |   2 +-
>  drivers/md/dm-integrity.c                     |   2 +-
>  drivers/media/dvb-frontends/stv0367_priv.h    |   3 +
>  .../net/ethernet/chelsio/cxgb3/cxgb3_main.c   |  18 +-
>  .../net/ethernet/stmicro/stmmac/stmmac_main.c |   2 +-
>  drivers/net/fjes/fjes_main.c                  |   4 +-
>  drivers/nfc/pn544/i2c.c                       |   2 -
>  drivers/platform/x86/sony-laptop.c            |   1 -
>  drivers/scsi/isci/init.c                      |   6 +-

I do see the value to backport the infrastructure, but why are driver specific changes backported as well?

I mean the changes are most likely correct but also not valuable in anyway as bug fix.

Regards,
Christian.

>  .../pci/hive_isp_css_include/math_support.h   |   5 -
>  fs/btrfs/misc.h                               |   2 -
>  fs/btrfs/tree-checker.c                       |   2 +-
>  fs/ext2/balloc.c                              |   2 -
>  fs/ext4/ext4.h                                |   2 -
>  fs/ufs/util.h                                 |   6 -
>  include/linux/compiler.h                      |  15 +
>  include/linux/minmax.h                        | 267 ++++++++++++++----
>  include/linux/overflow.h                      |   1 -
>  include/linux/trace_events.h                  |   2 -
>  kernel/trace/preemptirq_delay_test.c          |   2 -
>  lib/btree.c                                   |   1 -
>  lib/decompress_unlzma.c                       |   2 +
>  lib/logic_pio.c                               |   3 -
>  lib/vsprintf.c                                |   2 +-
>  lib/zstd/zstd_internal.h                      |   2 -
>  mm/zsmalloc.c                                 |   1 -
>  net/ipv4/proc.c                               |   2 +-
>  net/ipv6/proc.c                               |   2 +-
>  net/netfilter/nf_nat_core.c                   |   6 +-
>  net/tipc/core.h                               |   2 +-
>  net/tipc/link.c                               |  10 +-
>  44 files changed, 306 insertions(+), 164 deletions(-)
>