commit: 458c4e0f9c4e70e70c669eaf74f3bb990312db59 Author: Mike Pagano <mpagano <AT> gentoo <DOT> org> AuthorDate: Sun Feb 26 18:23:44 2023 +0000 Commit: Mike Pagano <mpagano <AT> gentoo <DOT> org> CommitDate: Sun Feb 26 18:23:44 2023 +0000 URL: https://gitweb.gentoo.org/proj/linux-patches.git/commit/?id=458c4e0f
Update CPU Opt patch, add Emerald Rapids and update Sapphire Rapids Signed-off-by: Mike Pagano <mpagano <AT> gentoo.org> 5010_enable-cpu-optimizations-universal.patch | 125 ++++++++++++++------------ 1 file changed, 69 insertions(+), 56 deletions(-) diff --git a/5010_enable-cpu-optimizations-universal.patch b/5010_enable-cpu-optimizations-universal.patch index 0841340b..7a1b717a 100644 --- a/5010_enable-cpu-optimizations-universal.patch +++ b/5010_enable-cpu-optimizations-universal.patch @@ -1,7 +1,6 @@ -From a0825feea3f100656d58446885b5f190284fd219 +From 70d4906b87983ed2ed5da78930a701625d881dd0 Mon Sep 17 00:00:00 2001 From: graysky <[email protected]> -Date: Fri, 4 Nov 2022 15:34:36 -0400 -Subject: [PATCH] more uarches for kernel 5.17+ +Date: Thu, 5 Jan 2023 14:29:37 -0500 FEATURES This patch adds additional CPU options to the Linux kernel accessible under: @@ -50,11 +49,12 @@ CPU-specific microarchitectures include: • Intel Xeon (Cascade Lake) • Intel Xeon (Cooper Lake)* • Intel 3rd Gen 10nm++ i3/i5/i7/i9-family (Tiger Lake)* -• Intel 3rd Gen 10nm++ Xeon (Sapphire Rapids)‡ +• Intel 4th Gen 10nm++ Xeon (Sapphire Rapids)‡ • Intel 11th Gen i3/i5/i7/i9-family (Rocket Lake)‡ • Intel 12th Gen i3/i5/i7/i9-family (Alder Lake)‡ • Intel 13th Gen i3/i5/i7/i9-family (Raptor Lake)§ • Intel 14th Gen i3/i5/i7/i9-family (Meteor Lake)§ +• Intel 5th Gen 10nm++ Xeon (Emerald Rapids)§ Notes: If not otherwise noted, gcc >=9.1 is required for support. *Requires gcc >=10.1 or clang >=10.0 @@ -99,20 +99,19 @@ REFERENCES 3. https://bugzilla.kernel.org/show_bug.cgi?id=77461 4. https://github.com/graysky2/kernel_gcc_patch/issues/15 5. http://www.linuxforge.net/docs/linux/linux-gcc.php - --- - arch/x86/Kconfig.cpu | 416 ++++++++++++++++++++++++++++++-- - arch/x86/Makefile | 43 +++- - arch/x86/include/asm/vermagic.h | 72 ++++++ - 3 files changed, 514 insertions(+), 17 deletions(-) + arch/x86/Kconfig.cpu | 427 ++++++++++++++++++++++++++++++-- + arch/x86/Makefile | 44 +++- + arch/x86/include/asm/vermagic.h | 74 ++++++ + 3 files changed, 528 insertions(+), 17 deletions(-) diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu -index 542377cd419d..08d887d1220d 100644 +index 542377cd419d..f589971df2d3 100644 --- a/arch/x86/Kconfig.cpu +++ b/arch/x86/Kconfig.cpu @@ -157,7 +157,7 @@ config MPENTIUM4 - - + + config MK6 - bool "K6/K6-II/K6-III" + bool "AMD K6/K6-II/K6-III" @@ -121,7 +120,7 @@ index 542377cd419d..08d887d1220d 100644 Select this for an AMD K6-family processor. Enables use of @@ -165,7 +165,7 @@ config MK6 flags to GCC. - + config MK7 - bool "Athlon/Duron/K7" + bool "AMD Athlon/Duron/K7" @@ -130,7 +129,7 @@ index 542377cd419d..08d887d1220d 100644 Select this for an AMD Athlon K7-family processor. Enables use of @@ -173,12 +173,106 @@ config MK7 flags to GCC. - + config MK8 - bool "Opteron/Athlon64/Hammer/K8" + bool "AMD Opteron/Athlon64/Hammer/K8" @@ -138,7 +137,7 @@ index 542377cd419d..08d887d1220d 100644 Select this for an AMD Opteron or Athlon64 Hammer-family processor. Enables use of some extended instructions, and passes appropriate optimization flags to GCC. - + +config MK8SSE3 + bool "AMD Opteron/Athlon64/Hammer/K8 with SSE3" + help @@ -227,7 +226,7 @@ index 542377cd419d..08d887d1220d 100644 + +config MZEN4 + bool "AMD Zen 4" -+ depends on (CC_IS_GCC && GCC_VERSION >= 130000) || (CC_IS_CLANG && CLANG_VERSION >= 150500) ++ depends on (CC_IS_GCC && GCC_VERSION >= 130000) || (CC_IS_CLANG && CLANG_VERSION >= 160000) + help + Select this for AMD Family 19h Zen 4 processors. + @@ -238,26 +237,26 @@ index 542377cd419d..08d887d1220d 100644 depends on X86_32 @@ -270,7 +364,7 @@ config MPSC in /proc/cpuinfo. Family 15 is an older Xeon, Family 6 a newer one. - + config MCORE2 - bool "Core 2/newer Xeon" + bool "Intel Core 2" help - + Select this for Intel Core 2 and newer Core 2 Xeons (Xeon 51xx and @@ -278,6 +372,8 @@ config MCORE2 family in /proc/cpuinfo. Newer ones have 6 and older ones 15 (not a typo) - + + Enables -march=core2 + config MATOM bool "Intel Atom" help -@@ -287,6 +383,202 @@ config MATOM +@@ -287,6 +383,212 @@ config MATOM accordingly optimized code. Use a recent GCC with specific Atom support in order to fully benefit from selecting this option. - + +config MNEHALEM + bool "Intel Nehalem" + select X86_P6_NOP @@ -410,7 +409,7 @@ index 542377cd419d..08d887d1220d 100644 + select X86_P6_NOP + help + -+ Select this for third-generation 10 nm process processors in the Sapphire Rapids family. ++ Select this for fourth-generation 10 nm process processors in the Sapphire Rapids family. + + Enables -march=sapphirerapids + @@ -453,14 +452,24 @@ index 542377cd419d..08d887d1220d 100644 + Select this for fourteenth-generation processors in the Meteor Lake family. + + Enables -march=meteorlake ++ ++config MEMERALDRAPIDS ++ bool "Intel Emerald Rapids" ++ depends on (CC_IS_GCC && GCC_VERSION > 130000) || (CC_IS_CLANG && CLANG_VERSION >= 150500) ++ select X86_P6_NOP ++ help ++ ++ Select this for fifth-generation 10 nm process processors in the Emerald Rapids family. ++ ++ Enables -march=emeraldrapids + config GENERIC_CPU bool "Generic-x86-64" depends on X86_64 -@@ -294,6 +586,50 @@ config GENERIC_CPU +@@ -294,6 +596,50 @@ config GENERIC_CPU Generic x86-64 CPU. Run equally well on all x86-64 CPUs. - + +config GENERIC_CPU2 + bool "Generic-x86-64-v2" + depends on (CC_IS_GCC && GCC_VERSION > 110000) || (CC_IS_CLANG && CLANG_VERSION >= 120000) @@ -506,9 +515,9 @@ index 542377cd419d..08d887d1220d 100644 + Enables -march=native + endchoice - + config X86_GENERIC -@@ -318,9 +654,17 @@ config X86_INTERNODE_CACHE_SHIFT +@@ -318,9 +664,17 @@ config X86_INTERNODE_CACHE_SHIFT config X86_L1_CACHE_SHIFT int default "7" if MPENTIUM4 || MPSC @@ -519,23 +528,23 @@ index 542377cd419d..08d887d1220d 100644 + || MGOLDMONT || MGOLDMONTPLUS || MSANDYBRIDGE || MIVYBRIDGE || MHASWELL || MBROADWELL \ + || MSKYLAKE || MSKYLAKEX || MCANNONLAKE || MICELAKE || MCASCADELAKE || MCOOPERLAKE \ + || MTIGERLAKE || MSAPPHIRERAPIDS || MROCKETLAKE || MALDERLAKE || MRAPTORLAKE || MMETEORLAKE \ -+ || MNATIVE_INTEL || MNATIVE_AMD || X86_GENERIC || GENERIC_CPU || GENERIC_CPU2 || GENERIC_CPU3 \ -+ || GENERIC_CPU4 ++ || MEMERALDRAPIDS || MNATIVE_INTEL || MNATIVE_AMD || X86_GENERIC || GENERIC_CPU || GENERIC_CPU2 \ ++ || GENERIC_CPU3 || GENERIC_CPU4 default "4" if MELAN || M486SX || M486 || MGEODEGX1 - default "5" if MWINCHIP3D || MWINCHIPC6 || MCRUSOE || MEFFICEON || MCYRIXIII || MK6 || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || M586 || MVIAC3_2 || MGEODE_LX + default "5" if MWINCHIP3D || MWINCHIPC6 || MCRUSOE || MEFFICEON || MCYRIXIII || MK6 || MPENTIUMIII \ + || MPENTIUMII || M686 || M586MMX || M586TSC || M586 || MVIAC3_2 || MGEODE_LX - + config X86_F00F_BUG def_bool y -@@ -332,15 +676,27 @@ config X86_INVD_BUG - +@@ -332,15 +686,27 @@ config X86_INVD_BUG + config X86_ALIGNMENT_16 def_bool y - depends on MWINCHIP3D || MWINCHIPC6 || MCYRIXIII || MELAN || MK6 || M586MMX || M586TSC || M586 || M486SX || M486 || MVIAC3_2 || MGEODEGX1 + depends on MWINCHIP3D || MWINCHIPC6 || MCYRIXIII || MELAN || MK6 || M586MMX || M586TSC \ + || M586 || M486SX || M486 || MVIAC3_2 || MGEODEGX1 - + config X86_INTEL_USERCOPY def_bool y - depends on MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M586MMX || X86_GENERIC || MK8 || MK7 || MEFFICEON || MCORE2 @@ -543,8 +552,8 @@ index 542377cd419d..08d887d1220d 100644 + || MK8 || MK7 || MEFFICEON || MCORE2 || MNEHALEM || MWESTMERE || MSILVERMONT || MGOLDMONT \ + || MGOLDMONTPLUS || MSANDYBRIDGE || MIVYBRIDGE || MHASWELL || MBROADWELL || MSKYLAKE || MSKYLAKEX \ + || MCANNONLAKE || MICELAKE || MCASCADELAKE || MCOOPERLAKE || MTIGERLAKE || MSAPPHIRERAPIDS \ -+ || MROCKETLAKE || MALDERLAKE || MRAPTORLAKE || MMETEORLAKE || MNATIVE_INTEL - ++ || MROCKETLAKE || MALDERLAKE || MRAPTORLAKE || MMETEORLAKE || MEMERALDRAPIDS || MNATIVE_INTEL + config X86_USE_PPRO_CHECKSUM def_bool y - depends on MWINCHIP3D || MWINCHIPC6 || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MK8 || MVIAC3_2 || MVIAC7 || MEFFICEON || MGEODE_LX || MCORE2 || MATOM @@ -555,11 +564,11 @@ index 542377cd419d..08d887d1220d 100644 + || MWESTMERE || MSILVERMONT || MGOLDMONT || MGOLDMONTPLUS || MSANDYBRIDGE || MIVYBRIDGE \ + || MHASWELL || MBROADWELL || MSKYLAKE || MSKYLAKEX || MCANNONLAKE || MICELAKE \ + || MCASCADELAKE || MCOOPERLAKE || MTIGERLAKE || MSAPPHIRERAPIDS || MROCKETLAKE \ -+ || MALDERLAKE || MRAPTORLAKE || MMETEORLAKE || MNATIVE_INTEL || MNATIVE_AMD - ++ || MALDERLAKE || MRAPTORLAKE || MMETEORLAKE || MEMERALDRAPIDS || MNATIVE_INTEL || MNATIVE_AMD + # # P6_NOPs are a relatively minor optimization that require a family >= -@@ -356,32 +712,62 @@ config X86_USE_PPRO_CHECKSUM +@@ -356,32 +722,63 @@ config X86_USE_PPRO_CHECKSUM config X86_P6_NOP def_bool y depends on X86_64 @@ -567,8 +576,9 @@ index 542377cd419d..08d887d1220d 100644 + depends on (MCORE2 || MPENTIUM4 || MPSC || MNEHALEM || MWESTMERE || MSILVERMONT || MGOLDMONT \ + || MGOLDMONTPLUS || MSANDYBRIDGE || MIVYBRIDGE || MHASWELL || MBROADWELL || MSKYLAKE \ + || MSKYLAKEX || MCANNONLAKE || MICELAKE || MCASCADELAKE || MCOOPERLAKE || MTIGERLAKE \ -+ || MSAPPHIRERAPIDS || MROCKETLAKE || MALDERLAKE || MRAPTORLAKE || MMETEORLAKE || MNATIVE_INTEL) - ++ || MSAPPHIRERAPIDS || MROCKETLAKE || MALDERLAKE || MRAPTORLAKE || MMETEORLAKE || MEMERALDRAPIDS \ ++ || MNATIVE_INTEL) + config X86_TSC def_bool y - depends on (MWINCHIP3D || MCRUSOE || MEFFICEON || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || MK8 || MVIAC3_2 || MVIAC7 || MGEODEGX1 || MGEODE_LX || MCORE2 || MATOM) || X86_64 @@ -578,9 +588,9 @@ index 542377cd419d..08d887d1220d 100644 + || MPILEDRIVER || MSTEAMROLLER || MEXCAVATOR || MZEN || MZEN2 || MZEN3 || MZEN4 || MNEHALEM \ + || MWESTMERE || MSILVERMONT || MGOLDMONT || MGOLDMONTPLUS || MSANDYBRIDGE || MIVYBRIDGE || MHASWELL \ + || MBROADWELL || MSKYLAKE || MSKYLAKEX || MCANNONLAKE || MICELAKE || MCASCADELAKE || MCOOPERLAKE \ -+ || MTIGERLAKE || MSAPPHIRERAPIDS || MROCKETLAKE || MALDERLAKE || MRAPTORLAKE || MMETEORLAKE || MNATIVE_INTEL \ -+ || MNATIVE_AMD) || X86_64 - ++ || MTIGERLAKE || MSAPPHIRERAPIDS || MROCKETLAKE || MALDERLAKE || MRAPTORLAKE || MMETEORLAKE || MEMERALDRAPIDS \ ++ || MNATIVE_INTEL || MNATIVE_AMD) || X86_64 + config X86_CMPXCHG64 def_bool y - depends on X86_PAE || X86_64 || MCORE2 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || M586TSC || M586MMX || MATOM || MGEODE_LX || MGEODEGX1 || MK6 || MK7 || MK8 @@ -590,8 +600,8 @@ index 542377cd419d..08d887d1220d 100644 + || MZEN2 || MZEN3 || MZEN4 || MNEHALEM || MWESTMERE || MSILVERMONT || MGOLDMONT || MGOLDMONTPLUS \ + || MSANDYBRIDGE || MIVYBRIDGE || MHASWELL || MBROADWELL || MSKYLAKE || MSKYLAKEX || MCANNONLAKE \ + || MICELAKE || MCASCADELAKE || MCOOPERLAKE || MTIGERLAKE || MSAPPHIRERAPIDS || MROCKETLAKE \ -+ || MALDERLAKE || MRAPTORLAKE || MMETEORLAKE || MNATIVE_INTEL || MNATIVE_AMD - ++ || MALDERLAKE || MRAPTORLAKE || MMETEORLAKE || MEMERALDRAPIDS || MNATIVE_INTEL || MNATIVE_AMD + # this should be set for all -march=.. options where the compiler # generates cmov. config X86_CMOV @@ -603,8 +613,8 @@ index 542377cd419d..08d887d1220d 100644 + || MZEN || MZEN2 || MZEN3 || MZEN4 || MNEHALEM || MWESTMERE || MSILVERMONT || MGOLDMONT \ + || MGOLDMONTPLUS || MSANDYBRIDGE || MIVYBRIDGE || MHASWELL || MBROADWELL || MSKYLAKE || MSKYLAKEX \ + || MCANNONLAKE || MICELAKE || MCASCADELAKE || MCOOPERLAKE || MTIGERLAKE || MSAPPHIRERAPIDS \ -+ || MROCKETLAKE || MALDERLAKE || MRAPTORLAKE || MMETEORLAKE || MNATIVE_INTEL || MNATIVE_AMD) - ++ || MROCKETLAKE || MALDERLAKE || MRAPTORLAKE || MMETEORLAKE || MEMERALDRAPIDS || MNATIVE_INTEL || MNATIVE_AMD) + config X86_MINIMUM_CPU_FAMILY int default "64" if X86_64 @@ -619,20 +629,20 @@ index 542377cd419d..08d887d1220d 100644 + || MNATIVE_INTEL || MNATIVE_AMD) default "5" if X86_32 && X86_CMPXCHG64 default "4" - + config X86_DEBUGCTLMSR def_bool y - depends on !(MK6 || MWINCHIPC6 || MWINCHIP3D || MCYRIXIII || M586MMX || M586TSC || M586 || M486SX || M486) && !UML + depends on !(MK6 || MWINCHIPC6 || MWINCHIP3D || MCYRIXIII || M586MMX || M586TSC || M586 \ + || M486SX || M486) && !UML - + config IA32_FEAT_CTL def_bool y diff --git a/arch/x86/Makefile b/arch/x86/Makefile -index bafbd905e6e7..7fae52788560 100644 +index 415a5d138de4..17b1e039d955 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile -@@ -150,8 +150,47 @@ else +@@ -151,8 +151,48 @@ else # FIXME - should be integrated in Makefile.cpu (Makefile_32.cpu) cflags-$(CONFIG_MK8) += -march=k8 cflags-$(CONFIG_MPSC) += -march=nocona @@ -676,17 +686,18 @@ index bafbd905e6e7..7fae52788560 100644 + cflags-$(CONFIG_MALDERLAKE) += -march=alderlake + cflags-$(CONFIG_MRAPTORLAKE) += -march=raptorlake + cflags-$(CONFIG_MMETEORLAKE) += -march=meteorlake ++ cflags-$(CONFIG_MEMERALDRAPIDS) += -march=emeraldrapids + cflags-$(CONFIG_GENERIC_CPU2) += -march=x86-64-v2 + cflags-$(CONFIG_GENERIC_CPU3) += -march=x86-64-v3 + cflags-$(CONFIG_GENERIC_CPU4) += -march=x86-64-v4 cflags-$(CONFIG_GENERIC_CPU) += -mtune=generic KBUILD_CFLAGS += $(cflags-y) - + diff --git a/arch/x86/include/asm/vermagic.h b/arch/x86/include/asm/vermagic.h -index 75884d2cdec3..18021e8c0c28 100644 +index 75884d2cdec3..02c1386eb653 100644 --- a/arch/x86/include/asm/vermagic.h +++ b/arch/x86/include/asm/vermagic.h -@@ -17,6 +17,52 @@ +@@ -17,6 +17,54 @@ #define MODULE_PROC_FAMILY "586MMX " #elif defined CONFIG_MCORE2 #define MODULE_PROC_FAMILY "CORE2 " @@ -736,10 +747,12 @@ index 75884d2cdec3..18021e8c0c28 100644 +#define MODULE_PROC_FAMILY "RAPTORLAKE " +#elif defined CONFIG_MMETEORLAKE +#define MODULE_PROC_FAMILY "METEORLAKE " ++#elif defined CONFIG_MEMERALDRAPIDS ++#define MODULE_PROC_FAMILY "EMERALDRAPIDS " #elif defined CONFIG_MATOM #define MODULE_PROC_FAMILY "ATOM " #elif defined CONFIG_M686 -@@ -35,6 +81,32 @@ +@@ -35,6 +83,32 @@ #define MODULE_PROC_FAMILY "K7 " #elif defined CONFIG_MK8 #define MODULE_PROC_FAMILY "K8 " @@ -772,5 +785,5 @@ index 75884d2cdec3..18021e8c0c28 100644 #elif defined CONFIG_MELAN #define MODULE_PROC_FAMILY "ELAN " #elif defined CONFIG_MCRUSOE --- -2.38.1 +-- +2.39.0
