Merge branch '7.0/cachy' into 7.0/base

Signed-off-by: Eric Naim <dnaim@cachyos.org>

Author: 1Naim

.gitignore

@@ -56,6 +56,7 @@
 *.zst
 Module.symvers
 dtbs-list
+builtin.order
 modules.order
 
 #
@@ -67,6 +68,7 @@ modules.order
 /vmlinux.32
 /vmlinux.map
 /vmlinux.symvers
+/vmlinux.thinlto-index
 /vmlinux.unstripped
 /vmlinux-gdb.py
 /vmlinuz

Documentation/admin-guide/kernel-parameters.txt

@@ -2533,6 +2533,9 @@ Kernel parameters
 			disable
 			  Do not enable intel_pstate as the default
 			  scaling driver for the supported processors
+			enable
+			  Enable intel_pstate in-case "disable" was passed
+			  previously in the kernel boot parameters
                         active
                           Use intel_pstate driver to bypass the scaling
                           governors layer of cpufreq and provides it own
@@ -5114,6 +5117,15 @@ Kernel parameters
 		nomsi		[MSI] If the PCI_MSI kernel config parameter is
 				enabled, this kernel boot option can be used to
 				disable the use of MSI interrupts system-wide.
+		pcie_acs_override =
+					[PCIE] Override missing PCIe ACS support for:
+				downstream
+					All downstream ports - full ACS capabilities
+				multfunction
+					All multifunction devices - multifunction ACS subset
+				id:nnnn:nnnn
+					Specfic device - full ACS capabilities
+					Specified as vid:did (vendor/device ID) in hex
 		noioapicquirk	[APIC] Disable all boot interrupt quirks.
 				Safety option to keep boot IRQs enabled. This
 				should never be necessary.

Makefile

@@ -893,11 +893,20 @@ KBUILD_CFLAGS	+= -fno-delete-null-pointer-checks
 ifdef CONFIG_CC_OPTIMIZE_FOR_PERFORMANCE
 KBUILD_CFLAGS += -O2
 KBUILD_RUSTFLAGS += -Copt-level=2
+else ifdef CONFIG_CC_OPTIMIZE_FOR_PERFORMANCE_O3
+KBUILD_CFLAGS += -O3
+KBUILD_RUSTFLAGS += -Copt-level=3
 else ifdef CONFIG_CC_OPTIMIZE_FOR_SIZE
 KBUILD_CFLAGS += -Os
 KBUILD_RUSTFLAGS += -Copt-level=s
 endif
 
+# Perform swing modulo scheduling immediately before the first scheduling pass.
+# This pass looks at innermost loops and reorders their instructions by
+# overlapping different iterations.
+KBUILD_CFLAGS += $(call cc-option,-fmodulo-sched -fmodulo-sched-allow-regmoves -fivopts)
+KBUILD_CFLAGS += $(call cc-option,-mllvm -enable-pipeliner)
+
 # Always set `debug-assertions` and `overflow-checks` because their default
 # depends on `opt-level` and `debug-assertions`, respectively.
 KBUILD_RUSTFLAGS += -Cdebug-assertions=$(if $(CONFIG_RUST_DEBUG_ASSERTIONS),y,n)
@@ -1033,10 +1042,10 @@ export CC_FLAGS_SCS
 endif
 
 ifdef CONFIG_LTO_CLANG
-ifdef CONFIG_LTO_CLANG_THIN
-CC_FLAGS_LTO	:= -flto=thin -fsplit-lto-unit
-else
+ifdef CONFIG_LTO_CLANG_FULL
 CC_FLAGS_LTO	:= -flto
+else
+CC_FLAGS_LTO	:= -flto=thin -fsplit-lto-unit
 endif
 CC_FLAGS_LTO	+= -fvisibility=hidden
 
@@ -1255,7 +1264,7 @@ export ARCH_DRIVERS	:= $(drivers-y) $(drivers-m)
 KBUILD_VMLINUX_OBJS := built-in.a $(patsubst %/, %/lib.a, $(filter %/, $(libs-y)))
 KBUILD_VMLINUX_LIBS := $(filter-out %/, $(libs-y))
 
-export KBUILD_VMLINUX_LIBS
+export KBUILD_VMLINUX_OBJS KBUILD_VMLINUX_LIBS
 export KBUILD_LDS          := arch/$(SRCARCH)/kernel/vmlinux.lds
 
 ifdef CONFIG_TRIM_UNUSED_KSYMS
@@ -1264,16 +1273,12 @@ ifdef CONFIG_TRIM_UNUSED_KSYMS
 KBUILD_MODULES := y
 endif
 
-# '$(AR) mPi' needs 'T' to workaround the bug of llvm-ar <= 14
-quiet_cmd_ar_vmlinux.a = AR      $@
-      cmd_ar_vmlinux.a = \
-	rm -f $@; \
-	$(AR) cDPrST $@ $(KBUILD_VMLINUX_OBJS); \
-	$(AR) mPiT $$($(AR) t $@ | sed -n 1p) $@ $$($(AR) t $@ | grep -F -f $(srctree)/scripts/head-object-list.txt)
+PHONY += vmlinux_a
+vmlinux_a: $(KBUILD_VMLINUX_OBJS) scripts/head-object-list.txt FORCE
+	$(Q)$(MAKE) -f $(srctree)/scripts/Makefile.vmlinux_a
 
-targets += vmlinux.a
-vmlinux.a: $(KBUILD_VMLINUX_OBJS) scripts/head-object-list.txt FORCE
-	$(call if_changed,ar_vmlinux.a)
+vmlinux.a: vmlinux_a
+	@:
 
 PHONY += vmlinux_o
 vmlinux_o: vmlinux.a $(KBUILD_VMLINUX_LIBS)
@@ -1652,6 +1657,7 @@ endif # CONFIG_MODULES
 CLEAN_FILES += vmlinux.symvers modules-only.symvers \
 	       modules.builtin modules.builtin.modinfo modules.nsdeps \
 	       modules.builtin.ranges vmlinux.o.map vmlinux.unstripped \
+	       vmlinux.thinlto-index builtin.order \
 	       compile_commands.json rust/test \
 	       rust-project.json .vmlinux.objs .vmlinux.export.c \
                .builtin-dtbs-list .builtin-dtbs.S
@@ -2113,7 +2119,7 @@ clean: $(clean-dirs)
 	$(call cmd,rmfiles)
 	@find . $(RCS_FIND_IGNORE) \
 		\( -name '*.[aios]' -o -name '*.rsi' -o -name '*.ko' -o -name '.*.cmd' \
-		-o -name '*.ko.*' \
+		-o -name '*.ko.*' -o -name '*.o.thinlto.bc' \
 		-o -name '*.dtb' -o -name '*.dtbo' \
 		-o -name '*.dtb.S' -o -name '*.dtbo.S' \
 		-o -name '*.dt.yaml' -o -name 'dtbs-list' \

arch/Kconfig

@@ -861,6 +861,25 @@ config LTO_CLANG_THIN
 	    https://clang.llvm.org/docs/ThinLTO.html
 
 	  If unsure, say Y.
+
+config LTO_CLANG_THIN_DIST
+	bool "Clang ThinLTO in distributed mode (EXPERIMENTAL)"
+	depends on HAS_LTO_CLANG && ARCH_SUPPORTS_LTO_CLANG_THIN
+	select LTO_CLANG
+	help
+	  This option enables Clang's ThinLTO in distributed build mode.
+	  In this mode, the linker performs the thin-link, generating
+	  ThinLTO index files. Subsequently, the build system explicitly
+	  invokes ThinLTO backend compilation using these index files
+	  and pre-linked IR objects. The resulting native object files
+	  are with the .thinlto-native.o suffix.
+
+	  This build mode offers improved visibility into the ThinLTO
+	  process through explicit subcommand exposure. It also makes
+	  final native object files directly available, benefiting
+	  tools like objtool and kpatch. Additionally, it provides
+	  crucial granular control over back-end options, enabling
+	  module-specific compiler options, and simplifies debugging.
 endchoice
 
 config ARCH_SUPPORTS_AUTOFDO_CLANG

arch/x86/Kconfig.cpu

@@ -255,6 +255,11 @@ config CC_HAS_MARCH_NATIVE
 	# usage warnings that only appear wth '-march=native'.
 	depends on CC_IS_GCC || CLANG_VERSION >= 190100
 
+
+choice
+	prompt "x86_64 Compiler Build Optimization"
+	default GENERIC_CPU
+
 config X86_NATIVE_CPU
 	bool "Build and optimize for local/native CPU"
 	depends on X86_64
@@ -269,6 +274,47 @@ config X86_NATIVE_CPU
 
 	  If unsure, say N.
 
+config GENERIC_CPU
+	bool "Generic-x86-64"
+	depends on X86_64
+	help
+	  Generic x86-64 CPU.
+          Runs equally well on all x86-64 CPUs.
+
+config MZEN4
+	bool "AMD Ryzen 4"
+	depends on (CC_IS_GCC && GCC_VERSION >= 130000) || (CC_IS_CLANG && CLANG_VERSION >= 160000)
+	help
+	  Select this for AMD Family 19h Zen 4 processors.
+
+          Enables -march=znver4
+
+endchoice
+
+config X86_64_VERSION
+	int "x86-64 compiler ISA level"
+	range 1 4
+	depends on (CC_IS_GCC && GCC_VERSION > 110000) || (CC_IS_CLANG && CLANG_VERSION >= 120000)
+	depends on X86_64 && GENERIC_CPU
+	help
+	  Specify a specific x86-64 compiler ISA level.
+
+	  There are three x86-64 ISA levels that work on top of
+	  the x86-64 baseline, namely: x86-64-v2 and x86-64-v3.
+
+	  x86-64-v2 brings support for vector instructions up to Streaming SIMD
+	  Extensions 4.2 (SSE4.2) and Supplemental Streaming SIMD Extensions 3
+	  (SSSE3), the POPCNT instruction, and CMPXCHG16B.
+
+	  x86-64-v3 adds vector instructions up to AVX2, MOVBE, and additional
+	  bit-manipulation instructions.
+
+	  x86-64-v4 is not included since the kernel does not use AVX512 instructions
+
+	  You can find the best version for your CPU by running one of the following:
+	  /lib/ld-linux-x86-64.so.2 --help | grep supported
+	  /lib64/ld-linux-x86-64.so.2 --help | grep supported
+
 config X86_GENERIC
 	bool "Generic x86 support"
 	depends on X86_32

arch/x86/Makefile

@@ -167,10 +167,22 @@ else
 ifdef CONFIG_X86_NATIVE_CPU
         KBUILD_CFLAGS += -march=native
         KBUILD_RUSTFLAGS += -Ctarget-cpu=native
-else
+endif
+
+ifdef CONFIG_MZEN4
+        KBUILD_CFLAGS += -march=znver4
+        KBUILD_RUSTFLAGS += -Ctarget-cpu=znver4
+endif
+
+ifdef CONFIG_GENERIC_CPU
+ifeq ($(CONFIG_X86_64_VERSION),1)
         KBUILD_CFLAGS += -march=x86-64 -mtune=generic
         KBUILD_RUSTFLAGS += -Ctarget-cpu=x86-64 -Ztune-cpu=generic
-endif
+else
+        KBUILD_CFLAGS +=-march=x86-64-v$(CONFIG_X86_64_VERSION)
+        KBUILD_RUSTFLAGS += -Ctarget-cpu=x86-64-v$(CONFIG_X86_64_VERSION)
+endif # CONFIG_X86_64_VERSION
+endif # CONFIG_GENERIC_CPU
 
         KBUILD_CFLAGS += -mno-red-zone
         KBUILD_CFLAGS += -mcmodel=kernel

arch/x86/include/asm/pci.h

@@ -26,6 +26,7 @@ struct pci_sysdata {
 #if IS_ENABLED(CONFIG_VMD)
 	struct pci_dev	*vmd_dev;	/* VMD Device if in Intel VMD domain */
 #endif
+	struct pci_dev	*nvme_remap_dev;	/* AHCI Device if NVME remapped bus */
 };
 
 extern int pci_routeirq;
@@ -69,6 +70,11 @@ static inline bool is_vmd(struct pci_bus *bus)
 #define is_vmd(bus)		false
 #endif /* CONFIG_VMD */
 
+static inline bool is_nvme_remap(struct pci_bus *bus)
+{
+	return to_pci_sysdata(bus)->nvme_remap_dev != NULL;
+}
+
 /* Can be used to override the logic in pci_scan_bus for skipping
    already-configured bus numbers - to be used for buggy BIOSes
    or architectures with incomplete PCI setup by the loader */

arch/x86/kernel/cpu/bus_lock.c

@@ -47,7 +47,11 @@ static const struct {
 
 static struct ratelimit_state bld_ratelimit;
 
+#ifdef CONFIG_CACHY
+static unsigned int sysctl_sld_mitigate = 0;
+#else
 static unsigned int sysctl_sld_mitigate = 1;
+#endif /* CONFIG_CACHY */
 static DEFINE_SEMAPHORE(buslock_sem, 1);
 
 #ifdef CONFIG_PROC_SYSCTL

arch/x86/pci/common.c

@@ -723,12 +723,15 @@ int pci_ext_cfg_avail(void)
 		return 0;
 }
 
-#if IS_ENABLED(CONFIG_VMD)
 struct pci_dev *pci_real_dma_dev(struct pci_dev *dev)
 {
+#if IS_ENABLED(CONFIG_VMD)
 	if (is_vmd(dev->bus))
 		return to_pci_sysdata(dev->bus)->vmd_dev;
+#endif
+
+	if (is_nvme_remap(dev->bus))
+		return to_pci_sysdata(dev->bus)->nvme_remap_dev;
 
 	return dev;
 }
-#endif

block/Kconfig.iosched

@@ -16,6 +16,20 @@ config MQ_IOSCHED_KYBER
 	  synchronous writes, it will self-tune queue depths to achieve that
 	  goal.
 
+config MQ_IOSCHED_ADIOS
+	tristate "Adaptive Deadline I/O scheduler"
+	default m
+	help
+	  The Adaptive Deadline I/O Scheduler (ADIOS) is a multi-queue I/O
+	  scheduler with learning-based adaptive latency control.
+
+config MQ_IOSCHED_DEFAULT_ADIOS
+	bool "Enable ADIOS I/O scheduler as default MQ I/O scheduler"
+	depends on MQ_IOSCHED_ADIOS=y
+	default n
+	help
+	  Enable the ADIOS I/O scheduler as the default scheduler for MQ I/O.
+
 config IOSCHED_BFQ
 	tristate "BFQ I/O scheduler"
 	select BLK_ICQ