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

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

On 20.09.25 12:21, David Laight wrote:
> On Fri, 19 Sep 2025 14:11:37 +0200
> Christian König <christian.koenig@amd.com> wrote:
> 
>> 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?
> 
> They will be about removing local definitions of MIN() and MAX() freeing
> them up for simple implementations (usable as constant initialisers) and then
> using them in places where the compound statements in min() and max() can't
> be used.
> 
> Linus did all those changes - so he didn't have to wait for the maintainers
> to apply the changes (etc).

Sounds reasonable, feel free to add my acked-by for radeon and amdgpu driver changes.

Regards,
Christian.

> 
> 	David
>  
>>
>> 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(-)
>>>   
>>
>>
>