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 +-
 .../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(-)

-- 
2.47.3

On Fri, Sep 19, 2025 at 10:17:00AM +0000, 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")

But this isn't in 5.15.y, so how is this syncing things up?

I'm all for this, but I got confused here, at the first commit :)

> 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")

Some of these are also only in newer kernels, which, as you know, is
generally a bad thing (i.e. I can't take patches only for older
kernels.)

I want these changes, as they are great, but can you perhaps provide
patch series for newer kernels first so that I can then take these?

thanks,

greg k-h

> On Fri, Sep 19, 2025 at 10:17:00AM +0000, 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")
>
> But this isn't in 5.15.y, so how is this syncing things up?
>
> I'm all for this, but I got confused here, at the first commit :)

It's a typo.
It should be 5.10.y and not 5.15.y.

> Some of these are also only in newer kernels, which, as you know, is
> generally a bad thing (i.e. I can't take patches only for older
> kernels.)
>
> I want these changes, as they are great, but can you perhaps provide
> patch series for newer kernels first so that I can then take these?

So you'd first like first to align 6.16 with 6.17, then 6.15 with 6.16,
then 6.12 with 6.15, then 6.6 with 6.12, and so on until we eventually
align 5.10 and even 5.4?

---
Regards, Eliav

On Sun, Sep 21, 2025 at 09:37:02PM +0000, Farber, Eliav wrote:
> > On Fri, Sep 19, 2025 at 10:17:00AM +0000, 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")
> >
> > But this isn't in 5.15.y, so how is this syncing things up?
> >
> > I'm all for this, but I got confused here, at the first commit :)
> 
> It's a typo.
> It should be 5.10.y and not 5.15.y.
> 
> > Some of these are also only in newer kernels, which, as you know, is
> > generally a bad thing (i.e. I can't take patches only for older
> > kernels.)
> >
> > I want these changes, as they are great, but can you perhaps provide
> > patch series for newer kernels first so that I can then take these?
> 
> So you'd first like first to align 6.16 with 6.17, then 6.15 with 6.16,
> then 6.12 with 6.15, then 6.6 with 6.12, and so on until we eventually
> align 5.10 and even 5.4?

Yes please!

> On Sun, Sep 21, 2025 at 09:37:02PM +0000, Farber, Eliav wrote:
> > > On Fri, Sep 19, 2025 at 10:17:00AM +0000, 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")
> > >
> > > But this isn't in 5.15.y, so how is this syncing things up?
> > >
> > > I'm all for this, but I got confused here, at the first commit :)
> >
> > It's a typo.
> > It should be 5.10.y and not 5.15.y.
> >
> > > Some of these are also only in newer kernels, which, as you know, is 
> > > generally a bad thing (i.e. I can't take patches only for older
> > > kernels.)
> > >
> > > I want these changes, as they are great, but can you perhaps provide 
> > > patch series for newer kernels first so that I can then take these?
> >
> > So you'd first like first to align 6.16 with 6.17, then 6.15 with 
> > 6.16, then 6.12 with 6.15, then 6.6 with 6.12, and so on until we 
> > eventually align 5.10 and even 5.4?
>
> Yes please!

Stable 6.16.8 didn't require any changs.

I pulled the changes for 6.12.48:
https://lore.kernel.org/stable/20250922103123.14538-1-farbere@amazon.com/T/#t
and 6.6.107:
https://lore.kernel.org/stable/20250922103241.16213-1-farbere@amazon.com/T/#t

Once approved, I'll continue with other longterm branches.

---
Regards, Eliav

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(-)
>