On 20.09.25 12:21, David Laight wrote: > On Fri, 19 Sep 2025 14:11:37 +0200 > Christian König <[email protected]> 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(-) >>> >> >> >
