diff options
97 files changed, 1364 insertions, 891 deletions
@@ -249,6 +249,7 @@ Sakari Ailus <sakari.ailus@linux.intel.com> <sakari.ailus@iki.fi> Sean Nyekjaer <sean@geanix.com> <sean.nyekjaer@prevas.dk> Sebastian Reichel <sre@kernel.org> <sre@debian.org> Sebastian Reichel <sre@kernel.org> <sebastian.reichel@collabora.co.uk> +Sedat Dilek <sedat.dilek@gmail.com> <sedat.dilek@credativ.de> Shiraz Hashim <shiraz.linux.kernel@gmail.com> <shiraz.hashim@st.com> Shuah Khan <shuah@kernel.org> <shuahkhan@gmail.com> Shuah Khan <shuah@kernel.org> <shuah.khan@hp.com> diff --git a/Documentation/admin-guide/sysctl/user.rst b/Documentation/admin-guide/sysctl/user.rst index 650eaa03f15e..c45824589339 100644 --- a/Documentation/admin-guide/sysctl/user.rst +++ b/Documentation/admin-guide/sysctl/user.rst @@ -65,6 +65,12 @@ max_pid_namespaces The maximum number of pid namespaces that any user in the current user namespace may create. +max_time_namespaces +=================== + + The maximum number of time namespaces that any user in the current + user namespace may create. + max_user_namespaces =================== diff --git a/Documentation/devicetree/bindings/fpga/fpga-region.txt b/Documentation/devicetree/bindings/fpga/fpga-region.txt index 90c44694a30b..8ab19d1d3f9a 100644 --- a/Documentation/devicetree/bindings/fpga/fpga-region.txt +++ b/Documentation/devicetree/bindings/fpga/fpga-region.txt @@ -263,7 +263,7 @@ Overlay contains: gpio@10040 { compatible = "altr,pio-1.0"; reg = <0x10040 0x20>; - altr,gpio-bank-width = <4>; + altr,ngpio = <4>; #gpio-cells = <2>; clocks = <2>; gpio-controller; @@ -468,8 +468,7 @@ programming is the FPGA based bridge of fpga_region1. compatible = "altr,pio-1.0"; reg = <0x10040 0x20>; clocks = <0x2>; - altr,gpio-bank-width = <0x4>; - resetvalue = <0x0>; + altr,ngpio = <0x4>; #gpio-cells = <0x2>; gpio-controller; }; diff --git a/Documentation/kbuild/kbuild.rst b/Documentation/kbuild/kbuild.rst index 510f38d7e78a..2d1fc03d346e 100644 --- a/Documentation/kbuild/kbuild.rst +++ b/Documentation/kbuild/kbuild.rst @@ -262,3 +262,8 @@ KBUILD_BUILD_USER, KBUILD_BUILD_HOST These two variables allow to override the user@host string displayed during boot and in /proc/version. The default value is the output of the commands whoami and host, respectively. + +LLVM +---- +If this variable is set to 1, Kbuild will use Clang and LLVM utilities instead +of GCC and GNU binutils to build the kernel. diff --git a/Documentation/kbuild/llvm.rst b/Documentation/kbuild/llvm.rst index d6c79eb4e23e..c776b6eee969 100644 --- a/Documentation/kbuild/llvm.rst +++ b/Documentation/kbuild/llvm.rst @@ -47,14 +47,21 @@ example: LLVM Utilities -------------- -LLVM has substitutes for GNU binutils utilities. These can be invoked as -additional parameters to `make`. +LLVM has substitutes for GNU binutils utilities. Kbuild supports `LLVM=1` +to enable them. - make CC=clang AS=clang LD=ld.lld AR=llvm-ar NM=llvm-nm STRIP=llvm-strip \\ - OBJCOPY=llvm-objcopy OBJDUMP=llvm-objdump OBJSIZE=llvm-objsize \\ + make LLVM=1 + +They can be enabled individually. The full list of the parameters: + + make CC=clang LD=ld.lld AR=llvm-ar NM=llvm-nm STRIP=llvm-strip \\ + OBJCOPY=llvm-objcopy OBJDUMP=llvm-objdump OBJSIZE=llvm-size \\ READELF=llvm-readelf HOSTCC=clang HOSTCXX=clang++ HOSTAR=llvm-ar \\ HOSTLD=ld.lld +Currently, the integrated assembler is disabled by default. You can pass +`LLVM_IAS=1` to enable it. + Getting Help ------------ diff --git a/Documentation/process/changes.rst b/Documentation/process/changes.rst index e47863575917..91c5ff8e161e 100644 --- a/Documentation/process/changes.rst +++ b/Documentation/process/changes.rst @@ -31,7 +31,7 @@ you probably needn't concern yourself with pcmciautils. ====================== =============== ======================================== GNU C 4.6 gcc --version GNU make 3.81 make --version -binutils 2.21 ld -v +binutils 2.23 ld -v flex 2.5.35 flex --version bison 2.0 bison --version util-linux 2.10o fdformat --version @@ -76,7 +76,7 @@ You will need GNU make 3.81 or later to build the kernel. Binutils -------- -Binutils 2.21 or newer is needed to build the kernel. +Binutils 2.23 or newer is needed to build the kernel. pkg-config ---------- diff --git a/MAINTAINERS b/MAINTAINERS index ff043097ea0e..0d186a01a37a 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -738,7 +738,6 @@ F: drivers/i2c/busses/i2c-altera.c ALTERA MAILBOX DRIVER M: Ley Foon Tan <ley.foon.tan@intel.com> -L: nios2-dev@lists.rocketboards.org (moderated for non-subscribers) S: Maintained F: drivers/mailbox/mailbox-altera.c @@ -766,14 +765,12 @@ F: include/dt-bindings/reset/altr,rst-mgr-a10sr.h ALTERA TRIPLE SPEED ETHERNET DRIVER M: Thor Thayer <thor.thayer@linux.intel.com> L: netdev@vger.kernel.org -L: nios2-dev@lists.rocketboards.org (moderated for non-subscribers) S: Maintained F: drivers/net/ethernet/altera/ ALTERA UART/JTAG UART SERIAL DRIVERS M: Tobias Klauser <tklauser@distanz.ch> L: linux-serial@vger.kernel.org -L: nios2-dev@lists.rocketboards.org (moderated for non-subscribers) S: Maintained F: drivers/tty/serial/altera_uart.c F: drivers/tty/serial/altera_jtaguart.c @@ -11925,7 +11922,6 @@ F: drivers/scsi/nsp32* NIOS2 ARCHITECTURE M: Ley Foon Tan <ley.foon.tan@intel.com> -L: nios2-dev@lists.rocketboards.org (moderated for non-subscribers) T: git git://git.kernel.org/pub/scm/linux/kernel/git/lftan/nios2.git S: Maintained F: arch/nios2/ @@ -399,8 +399,13 @@ HOST_LFS_CFLAGS := $(shell getconf LFS_CFLAGS 2>/dev/null) HOST_LFS_LDFLAGS := $(shell getconf LFS_LDFLAGS 2>/dev/null) HOST_LFS_LIBS := $(shell getconf LFS_LIBS 2>/dev/null) -HOSTCC = gcc -HOSTCXX = g++ +ifneq ($(LLVM),) +HOSTCC = clang +HOSTCXX = clang++ +else +HOSTCC = gcc +HOSTCXX = g++ +endif KBUILD_HOSTCFLAGS := -Wall -Wmissing-prototypes -Wstrict-prototypes -O2 \ -fomit-frame-pointer -std=gnu89 $(HOST_LFS_CFLAGS) \ $(HOSTCFLAGS) @@ -409,16 +414,28 @@ KBUILD_HOSTLDFLAGS := $(HOST_LFS_LDFLAGS) $(HOSTLDFLAGS) KBUILD_HOSTLDLIBS := $(HOST_LFS_LIBS) $(HOSTLDLIBS) # Make variables (CC, etc...) -LD = $(CROSS_COMPILE)ld -CC = $(CROSS_COMPILE)gcc CPP = $(CC) -E +ifneq ($(LLVM),) +CC = clang +LD = ld.lld +AR = llvm-ar +NM = llvm-nm +OBJCOPY = llvm-objcopy +OBJDUMP = llvm-objdump +READELF = llvm-readelf +OBJSIZE = llvm-size +STRIP = llvm-strip +else +CC = $(CROSS_COMPILE)gcc +LD = $(CROSS_COMPILE)ld AR = $(CROSS_COMPILE)ar NM = $(CROSS_COMPILE)nm -STRIP = $(CROSS_COMPILE)strip OBJCOPY = $(CROSS_COMPILE)objcopy OBJDUMP = $(CROSS_COMPILE)objdump -OBJSIZE = $(CROSS_COMPILE)size READELF = $(CROSS_COMPILE)readelf +OBJSIZE = $(CROSS_COMPILE)size +STRIP = $(CROSS_COMPILE)strip +endif PAHOLE = pahole LEX = flex YACC = bison @@ -538,7 +555,7 @@ endif ifneq ($(GCC_TOOLCHAIN),) CLANG_FLAGS += --gcc-toolchain=$(GCC_TOOLCHAIN) endif -ifeq ($(if $(AS),$(shell $(AS) --version 2>&1 | head -n 1 | grep clang)),) +ifneq ($(LLVM_IAS),1) CLANG_FLAGS += -no-integrated-as endif CLANG_FLAGS += -Werror=unknown-warning-option @@ -747,8 +764,6 @@ ifdef CONFIG_CC_IS_CLANG KBUILD_CPPFLAGS += -Qunused-arguments KBUILD_CFLAGS += -Wno-format-invalid-specifier KBUILD_CFLAGS += -Wno-gnu -# Quiet clang warning: comparison of unsigned expression < 0 is always false -KBUILD_CFLAGS += -Wno-tautological-compare # CLANG uses a _MergedGlobals as optimization, but this breaks modpost, as the # source of a reference will be _MergedGlobals and not on of the whitelisted names. # See modpost pattern 2 @@ -1036,8 +1051,13 @@ init-y := $(patsubst %/, %/built-in.a, $(init-y)) core-y := $(patsubst %/, %/built-in.a, $(core-y)) drivers-y := $(patsubst %/, %/built-in.a, $(drivers-y)) net-y := $(patsubst %/, %/built-in.a, $(net-y)) +libs-y2 := $(patsubst %/, %/built-in.a, $(filter %/, $(libs-y))) +ifdef CONFIG_MODULES +libs-y1 := $(filter-out %/, $(libs-y)) +libs-y2 += $(patsubst %/, %/lib.a, $(filter %/, $(libs-y))) +else libs-y1 := $(patsubst %/, %/lib.a, $(libs-y)) -libs-y2 := $(patsubst %/, %/built-in.a, $(filter-out %.a, $(libs-y))) +endif virt-y := $(patsubst %/, %/built-in.a, $(virt-y)) # Externally visible symbols (used by link-vmlinux.sh) diff --git a/arch/h8300/include/uapi/asm/bitsperlong.h b/arch/h8300/include/uapi/asm/bitsperlong.h deleted file mode 100644 index a33e358f1c1b..000000000000 --- a/arch/h8300/include/uapi/asm/bitsperlong.h +++ /dev/null @@ -1,15 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -#ifndef _UAPI__ASM_H8300_BITS_PER_LONG -#define _UAPI__ASM_H8300_BITS_PER_LONG - -#include <asm-generic/bitsperlong.h> - -#if !defined(__ASSEMBLY__) -/* h8300-unknown-linux required long */ -#define __kernel_size_t __kernel_size_t -typedef unsigned long __kernel_size_t; -typedef long __kernel_ssize_t; -typedef long __kernel_ptrdiff_t; -#endif - -#endif /* _UAPI__ASM_H8300_BITS_PER_LONG */ diff --git a/arch/h8300/include/uapi/asm/posix_types.h b/arch/h8300/include/uapi/asm/posix_types.h new file mode 100644 index 000000000000..3efc9dd59476 --- /dev/null +++ b/arch/h8300/include/uapi/asm/posix_types.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */ +#ifndef _UAPI_ASM_POSIX_TYPES_H +#define _UAPI_ASM_POSIX_TYPES_H + +/* h8300-unknown-linux required long */ +#define __kernel_size_t __kernel_size_t +typedef unsigned long __kernel_size_t; +typedef long __kernel_ssize_t; +typedef long __kernel_ptrdiff_t; + +#include <asm-generic/posix_types.h> + +#endif /* _UAPI_ASM_POSIX_TYPES_H */ diff --git a/arch/mips/fw/arc/memory.c b/arch/mips/fw/arc/memory.c index dbbcddc82823..89fa6e62a3b3 100644 --- a/arch/mips/fw/arc/memory.c +++ b/arch/mips/fw/arc/memory.c @@ -117,7 +117,7 @@ static int __init prom_memtype_classify(union linux_memtypes type) return memtype_classify_arc(type); } -void __init prom_meminit(void) +void __weak __init prom_meminit(void) { struct linux_mdesc *p; @@ -162,7 +162,7 @@ void __weak __init prom_cleanup(void) { } -void __init prom_free_prom_memory(void) +void __weak __init prom_free_prom_memory(void) { int i; diff --git a/arch/nios2/Kconfig b/arch/nios2/Kconfig index 2fc4ed210b5f..c6645141bb2a 100644 --- a/arch/nios2/Kconfig +++ b/arch/nios2/Kconfig @@ -7,6 +7,7 @@ config NIOS2 select ARCH_HAS_SYNC_DMA_FOR_DEVICE select ARCH_HAS_DMA_SET_UNCACHED select ARCH_NO_SWAP + select COMMON_CLK select TIMER_OF select GENERIC_ATOMIC64 select GENERIC_CLOCKEVENTS diff --git a/arch/nios2/boot/dts/10m50_devboard.dts b/arch/nios2/boot/dts/10m50_devboard.dts index 5e4ab032c1e8..56339bef3247 100644 --- a/arch/nios2/boot/dts/10m50_devboard.dts +++ b/arch/nios2/boot/dts/10m50_devboard.dts @@ -179,8 +179,7 @@ led_pio: gpio@180014d0 { compatible = "altr,pio-1.0"; reg = <0x180014d0 0x00000010>; - altr,gpio-bank-width = <4>; - resetvalue = <15>; + altr,ngpio = <4>; #gpio-cells = <2>; gpio-controller; }; @@ -190,11 +189,10 @@ reg = <0x180014c0 0x00000010>; interrupt-parent = <&cpu>; interrupts = <6>; - altr,gpio-bank-width = <3>; + altr,ngpio = <3>; altr,interrupt-type = <2>; edge_type = <1>; level_trigger = <0>; - resetvalue = <0>; #gpio-cells = <2>; gpio-controller; }; diff --git a/arch/nios2/platform/platform.c b/arch/nios2/platform/platform.c index 2a35154ca153..9737a87121fa 100644 --- a/arch/nios2/platform/platform.c +++ b/arch/nios2/platform/platform.c @@ -15,6 +15,12 @@ #include <linux/slab.h> #include <linux/sys_soc.h> #include <linux/io.h> +#include <linux/clk-provider.h> + +static const struct of_device_id clk_match[] __initconst = { + { .compatible = "fixed-clock", .data = of_fixed_clk_setup, }, + {} +}; static int __init nios2_soc_device_init(void) { @@ -38,6 +44,8 @@ static int __init nios2_soc_device_init(void) } } + of_clk_init(clk_match); + return 0; } diff --git a/arch/sh/include/asm/bitops-op32.h b/arch/sh/include/asm/bitops-op32.h index 466880362ad1..cfe5465acce7 100644 --- a/arch/sh/include/asm/bitops-op32.h +++ b/arch/sh/include/asm/bitops-op32.h @@ -16,11 +16,9 @@ #define BYTE_OFFSET(nr) ((nr) % BITS_PER_BYTE) #endif -#define IS_IMMEDIATE(nr) (__builtin_constant_p(nr)) - static inline void __set_bit(int nr, volatile unsigned long *addr) { - if (IS_IMMEDIATE(nr)) { + if (__builtin_constant_p(nr)) { __asm__ __volatile__ ( "bset.b %1, @(%O2,%0) ! __set_bit\n\t" : "+r" (addr) @@ -37,7 +35,7 @@ static inline void __set_bit(int nr, volatile unsigned long *addr) static inline void __clear_bit(int nr, volatile unsigned long *addr) { - if (IS_IMMEDIATE(nr)) { + if (__builtin_constant_p(nr)) { __asm__ __volatile__ ( "bclr.b %1, @(%O2,%0) ! __clear_bit\n\t" : "+r" (addr) @@ -64,7 +62,7 @@ static inline void __clear_bit(int nr, volatile unsigned long *addr) */ static inline void __change_bit(int nr, volatile unsigned long *addr) { - if (IS_IMMEDIATE(nr)) { + if (__builtin_constant_p(nr)) { __asm__ __volatile__ ( "bxor.b %1, @(%O2,%0) ! __change_bit\n\t" : "+r" (addr) diff --git a/arch/sh/include/uapi/asm/setup.h b/arch/sh/include/uapi/asm/setup.h deleted file mode 100644 index 4bd19f80f9b0..000000000000 --- a/arch/sh/include/uapi/asm/setup.h +++ /dev/null @@ -1,2 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -#include <asm-generic/setup.h> diff --git a/arch/sh/include/uapi/asm/types.h b/arch/sh/include/uapi/asm/types.h deleted file mode 100644 index 68100e108ea6..000000000000 --- a/arch/sh/include/uapi/asm/types.h +++ /dev/null @@ -1,2 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -#include <asm-generic/types.h> diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 0163d764ade4..1d6104ea8af0 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -2932,3 +2932,5 @@ config HAVE_ATOMIC_IOMAP source "drivers/firmware/Kconfig" source "arch/x86/kvm/Kconfig" + +source "arch/x86/Kconfig.assembler" diff --git a/arch/x86/Kconfig.assembler b/arch/x86/Kconfig.assembler new file mode 100644 index 000000000000..13de0db38d4e --- /dev/null +++ b/arch/x86/Kconfig.assembler @@ -0,0 +1,17 @@ +# SPDX-License-Identifier: GPL-2.0 +# Copyright (C) 2020 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. + +config AS_AVX512 + def_bool $(as-instr,vpmovm2b %k1$(comma)%zmm5) + help + Supported by binutils >= 2.25 and LLVM integrated assembler + +config AS_SHA1_NI + def_bool $(as-instr,sha1msg1 %xmm0$(comma)%xmm1) + help + Supported by binutils >= 2.24 and LLVM integrated assembler + +config AS_SHA256_NI + def_bool $(as-instr,sha256msg1 %xmm0$(comma)%xmm1) + help + Supported by binutils >= 2.24 and LLVM integrated assembler diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 513a55562d75..b65ec63c7db7 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -177,28 +177,6 @@ ifeq ($(ACCUMULATE_OUTGOING_ARGS), 1) KBUILD_CFLAGS += $(call cc-option,-maccumulate-outgoing-args,) endif -# Stackpointer is addressed different for 32 bit and 64 bit x86 -sp-$(CONFIG_X86_32) := esp -sp-$(CONFIG_X86_64) := rsp - -# do binutils support CFI? -cfi := $(call as-instr,.cfi_startproc\n.cfi_rel_offset $(sp-y)$(comma)0\n.cfi_endproc,-DCONFIG_AS_CFI=1) -# is .cfi_signal_frame supported too? -cfi-sigframe := $(call as-instr,.cfi_startproc\n.cfi_signal_frame\n.cfi_endproc,-DCONFIG_AS_CFI_SIGNAL_FRAME=1) -cfi-sections := $(call as-instr,.cfi_sections .debug_frame,-DCONFIG_AS_CFI_SECTIONS=1) - -# does binutils support specific instructions? -asinstr += $(call as-instr,pshufb %xmm0$(comma)%xmm0,-DCONFIG_AS_SSSE3=1) -avx_instr := $(call as-instr,vxorps %ymm0$(comma)%ymm1$(comma)%ymm2,-DCONFIG_AS_AVX=1) -avx2_instr :=$(call as-instr,vpbroadcastb %xmm0$(comma)%ymm1,-DCONFIG_AS_AVX2=1) -avx512_instr :=$(call as-instr,vpmovm2b %k1$(comma)%zmm5,-DCONFIG_AS_AVX512=1) -sha1_ni_instr :=$(call as-instr,sha1msg1 %xmm0$(comma)%xmm1,-DCONFIG_AS_SHA1_NI=1) -sha256_ni_instr :=$(call as-instr,sha256msg1 %xmm0$(comma)%xmm1,-DCONFIG_AS_SHA256_NI=1) -adx_instr := $(call as-instr,adox %r10$(comma)%r10,-DCONFIG_AS_ADX=1) - -KBUILD_AFLAGS += $(cfi) $(cfi-sigframe) $(cfi-sections) $(asinstr) $(avx_instr) $(avx2_instr) $(avx512_instr) $(sha1_ni_instr) $(sha256_ni_instr) $(adx_instr) -KBUILD_CFLAGS += $(cfi) $(cfi-sigframe) $(cfi-sections) $(asinstr) $(avx_instr) $(avx2_instr) $(avx512_instr) $(sha1_ni_instr) $(sha256_ni_instr) $(adx_instr) - KBUILD_LDFLAGS := -m elf_$(UTS_MACHINE) # diff --git a/arch/x86/crypto/Makefile b/arch/x86/crypto/Makefile index 8c2e9eadee8a..a31de0c6ccde 100644 --- a/arch/x86/crypto/Makefile +++ b/arch/x86/crypto/Makefile @@ -1,131 +1,97 @@ # SPDX-License-Identifier: GPL-2.0 # -# Arch-specific CryptoAPI modules. -# +# x86 crypto algorithms OBJECT_FILES_NON_STANDARD := y -avx_supported := $(call as-instr,vpxor %xmm0$(comma)%xmm0$(comma)%xmm0,yes,no) -avx2_supported := $(call as-instr,vpgatherdd %ymm0$(comma)(%eax$(comma)%ymm1\ - $(comma)4)$(comma)%ymm2,yes,no) -avx512_supported :=$(call as-instr,vpmovm2b %k1$(comma)%zmm5,yes,no) -sha1_ni_supported :=$(call as-instr,sha1msg1 %xmm0$(comma)%xmm1,yes,no) -sha256_ni_supported :=$(call as-instr,sha256msg1 %xmm0$(comma)%xmm1,yes,no) -adx_supported := $(call as-instr,adox %r10$(comma)%r10,yes,no) - obj-$(CONFIG_CRYPTO_GLUE_HELPER_X86) += glue_helper.o obj-$(CONFIG_CRYPTO_TWOFISH_586) += twofish-i586.o +twofish-i586-y := twofish-i586-asm_32.o twofish_glue.o +obj-$(CONFIG_CRYPTO_TWOFISH_X86_64) += twofish-x86_64.o +twofish-x86_64-y := twofish-x86_64-asm_64.o twofish_glue.o +obj-$(CONFIG_CRYPTO_TWOFISH_X86_64_3WAY) += twofish-x86_64-3way.o +twofish-x86_64-3way-y := twofish-x86_64-asm_64-3way.o twofish_glue_3way.o +obj-$(CONFIG_CRYPTO_TWOFISH_AVX_X86_64) += twofish-avx-x86_64.o +twofish-avx-x86_64-y := twofish-avx-x86_64-asm_64.o twofish_avx_glue.o + obj-$(CONFIG_CRYPTO_SERPENT_SSE2_586) += serpent-sse2-i586.o +serpent-sse2-i586-y := serpent-sse2-i586-asm_32.o serpent_sse2_glue.o +obj-$(CONFIG_CRYPTO_SERPENT_SSE2_X86_64) += serpent-sse2-x86_64.o +serpent-sse2-x86_64-y := serpent-sse2-x86_64-asm_64.o serpent_sse2_glue.o +obj-$(CONFIG_CRYPTO_SERPENT_AVX_X86_64) += serpent-avx-x86_64.o +serpent-avx-x86_64-y := serpent-avx-x86_64-asm_64.o serpent_avx_glue.o +obj-$(CONFIG_CRYPTO_SERPENT_AVX2_X86_64) += serpent-avx2.o +serpent-avx2-y := serpent-avx2-asm_64.o serpent_avx2_glue.o obj-$(CONFIG_CRYPTO_DES3_EDE_X86_64) += des3_ede-x86_64.o +des3_ede-x86_64-y := des3_ede-asm_64.o des3_ede_glue.o + obj-$(CONFIG_CRYPTO_CAMELLIA_X86_64) += camellia-x86_64.o +camellia-x86_64-y := camellia-x86_64-asm_64.o camellia_glue.o +obj-$(CONFIG_CRYPTO_CAMELLIA_AESNI_AVX_X86_64) += camellia-aesni-avx-x86_64.o +camellia-aesni-avx-x86_64-y := camellia-aesni-avx-asm_64.o camellia_aesni_avx_glue.o +obj-$(CONFIG_CRYPTO_CAMELLIA_AESNI_AVX2_X86_64) += camellia-aesni-avx2.o +camellia-aesni-avx2-y := camellia-aesni-avx2-asm_64.o camellia_aesni_avx2_glue.o + obj-$(CONFIG_CRYPTO_BLOWFISH_X86_64) += blowfish-x86_64.o -obj-$(CONFIG_CRYPTO_TWOFISH_X86_64) += twofish-x86_64.o -obj-$(CONFIG_CRYPTO_TWOFISH_X86_64_3WAY) += twofish-x86_64-3way.o -obj-$(CONFIG_CRYPTO_CHACHA20_X86_64) += chacha-x86_64.o -obj-$(CONFIG_CRYPTO_SERPENT_SSE2_X86_64) += serpent-sse2-x86_64.o -obj-$(CONFIG_CRYPTO_AES_NI_INTEL) += aesni-intel.o -obj-$(CONFIG_CRYPTO_GHASH_CLMUL_NI_INTEL) += ghash-clmulni-intel.o +blowfish-x86_64-y := blowfish-x86_64-asm_64.o blowfish_glue.o -obj-$(CONFIG_CRYPTO_CRC32C_INTEL) += crc32c-intel.o -obj-$(CONFIG_CRYPTO_SHA1_SSSE3) += sha1-ssse3.o -obj-$(CONFIG_CRYPTO_CRC32_PCLMUL) += crc32-pclmul.o -obj-$(CONFIG_CRYPTO_SHA256_SSSE3) += sha256-ssse3.o -obj-$(CONFIG_CRYPTO_SHA512_SSSE3) += sha512-ssse3.o -obj-$(CONFIG_CRYPTO_CRCT10DIF_PCLMUL) += crct10dif-pclmul.o -obj-$(CONFIG_CRYPTO_POLY1305_X86_64) += poly1305-x86_64.o +obj-$(CONFIG_CRYPTO_CAST5_AVX_X86_64) += cast5-avx-x86_64.o +cast5-avx-x86_64-y := cast5-avx-x86_64-asm_64.o cast5_avx_glue.o + +obj-$(CONFIG_CRYPTO_CAST6_AVX_X86_64) += cast6-avx-x86_64.o +cast6-avx-x86_64-y := cast6-avx-x86_64-asm_64.o cast6_avx_glue.o obj-$(CONFIG_CRYPTO_AEGIS128_AESNI_SSE2) += aegis128-aesni.o +aegis128-aesni-y := aegis128-aesni-asm.o aegis128-aesni-glue.o -obj-$(CONFIG_CRYPTO_NHPOLY1305_SSE2) += nhpoly1305-sse2.o -obj-$(CONFIG_CRYPTO_NHPOLY1305_AVX2) += nhpoly1305-avx2.o +obj-$(CONFIG_CRYPTO_CHACHA20_X86_64) += chacha-x86_64.o +chacha-x86_64-y := chacha-avx2-x86_64.o chacha-ssse3-x86_64.o chacha_glue.o +chacha-x86_64-$(CONFIG_AS_AVX512) += chacha-avx512vl-x86_64.o -# These modules require the assembler to support ADX. -ifeq ($(adx_supported),yes) - obj-$(CONFIG_CRYPTO_CURVE25519_X86) += curve25519-x86_64.o -endif - -# These modules require assembler to support AVX. -ifeq ($(avx_supported),yes) - obj-$(CONFIG_CRYPTO_CAMELLIA_AESNI_AVX_X86_64) += \ - camellia-aesni-avx-x86_64.o - obj-$(CONFIG_CRYPTO_CAST5_AVX_X86_64) += cast5-avx-x86_64.o - obj-$(CONFIG_CRYPTO_CAST6_AVX_X86_64) += cast6-avx-x86_64.o - obj-$(CONFIG_CRYPTO_TWOFISH_AVX_X86_64) += twofish-avx-x86_64.o - obj-$(CONFIG_CRYPTO_SERPENT_AVX_X86_64) += serpent-avx-x86_64.o - obj-$(CONFIG_CRYPTO_BLAKE2S_X86) += blake2s-x86_64.o -endif - -# These modules require assembler to support AVX2. -ifeq ($(avx2_supported),yes) - obj-$(CONFIG_CRYPTO_CAMELLIA_AESNI_AVX2_X86_64) += camellia-aesni-avx2.o - obj-$(CONFIG_CRYPTO_SERPENT_AVX2_X86_64) += serpent-avx2.o -endif +obj-$(CONFIG_CRYPTO_AES_NI_INTEL) += aesni-intel.o +aesni-intel-y := aesni-intel_asm.o aesni-intel_glue.o +aesni-intel-$(CONFIG_64BIT) += aesni-intel_avx-x86_64.o aes_ctrby8_avx-x86_64.o -twofish-i586-y := twofish-i586-asm_32.o twofish_glue.o -serpent-sse2-i586-y := serpent-sse2-i586-asm_32.o serpent_sse2_glue.o +obj-$(CONFIG_CRYPTO_SHA1_SSSE3) += sha1-ssse3.o +sha1-ssse3-y := sha1_avx2_x86_64_asm.o sha1_ssse3_asm.o sha1_ssse3_glue.o +sha1-ssse3-$(CONFIG_AS_SHA1_NI) += sha1_ni_asm.o -des3_ede-x86_64-y := des3_ede-asm_64.o des3_ede_glue.o -camellia-x86_64-y := camellia-x86_64-asm_64.o camellia_glue.o -blowfish-x86_64-y := blowfish-x86_64-asm_64.o blowfish_glue.o -twofish-x86_64-y := twofish-x86_64-asm_64.o twofish_glue.o -twofish-x86_64-3way-y := twofish-x86_64-asm_64-3way.o twofish_glue_3way.o -chacha-x86_64-y := chacha-ssse3-x86_64.o chacha_glue.o -serpent-sse2-x86_64-y := serpent-sse2-x86_64-asm_64.o serpent_sse2_glue.o +obj-$(CONFIG_CRYPTO_SHA256_SSSE3) += sha256-ssse3.o +sha256-ssse3-y := sha256-ssse3-asm.o sha256-avx-asm.o sha256-avx2-asm.o sha256_ssse3_glue.o +sha256-ssse3-$(CONFIG_AS_SHA256_NI) += sha256_ni_asm.o -aegis128-aesni-y := aegis128-aesni-asm.o aegis128-aesni-glue.o +obj-$(CONFIG_CRYPTO_SHA512_SSSE3) += sha512-ssse3.o +sha512-ssse3-y := sha512-ssse3-asm.o sha512-avx-asm.o sha512-avx2-asm.o sha512_ssse3_glue.o -nhpoly1305-sse2-y := nh-sse2-x86_64.o nhpoly1305-sse2-glue.o +obj-$(CONFIG_CRYPTO_BLAKE2S_X86) += blake2s-x86_64.o blake2s-x86_64-y := blake2s-core.o blake2s-glue.o -poly1305-x86_64-y := poly1305-x86_64-cryptogams.o poly1305_glue.o -ifneq ($(CONFIG_CRYPTO_POLY1305_X86_64),) -targets += poly1305-x86_64-cryptogams.S -endif - -ifeq ($(avx_supported),yes) - camellia-aesni-avx-x86_64-y := camellia-aesni-avx-asm_64.o \ - camellia_aesni_avx_glue.o - cast5-avx-x86_64-y := cast5-avx-x86_64-asm_64.o cast5_avx_glue.o - cast6-avx-x86_64-y := cast6-avx-x86_64-asm_64.o cast6_avx_glue.o - twofish-avx-x86_64-y := twofish-avx-x86_64-asm_64.o \ - twofish_avx_glue.o - serpent-avx-x86_64-y := serpent-avx-x86_64-asm_64.o \ - serpent_avx_glue.o -endif - -ifeq ($(avx2_supported),yes) - camellia-aesni-avx2-y := camellia-aesni-avx2-asm_64.o camellia_aesni_avx2_glue.o - chacha-x86_64-y += chacha-avx2-x86_64.o - serpent-avx2-y := serpent-avx2-asm_64.o serpent_avx2_glue.o - - nhpoly1305-avx2-y := nh-avx2-x86_64.o nhpoly1305-avx2-glue.o -endif - -ifeq ($(avx512_supported),yes) - chacha-x86_64-y += chacha-avx512vl-x86_64.o -endif -aesni-intel-y := aesni-intel_asm.o aesni-intel_glue.o -aesni-intel-$(CONFIG_64BIT) += aesni-intel_avx-x86_64.o aes_ctrby8_avx-x86_64.o +obj-$(CONFIG_CRYPTO_GHASH_CLMUL_NI_INTEL) += ghash-clmulni-intel.o ghash-clmulni-intel-y := ghash-clmulni-intel_asm.o ghash-clmulni-intel_glue.o -sha1-ssse3-y := sha1_ssse3_asm.o sha1_ssse3_glue.o -ifeq ($(avx2_supported),yes) -sha1-ssse3-y += sha1_avx2_x86_64_asm.o -endif -ifeq ($(sha1_ni_supported),yes) -sha1-ssse3-y += sha1_ni_asm.o -endif + +obj-$(CONFIG_CRYPTO_CRC32C_INTEL) += crc32c-intel.o crc32c-intel-y := crc32c-intel_glue.o crc32c-intel-$(CONFIG_64BIT) += crc32c-pcl-intel-asm_64.o + +obj-$(CONFIG_CRYPTO_CRC32_PCLMUL) += crc32-pclmul.o crc32-pclmul-y := crc32-pclmul_asm.o crc32-pclmul_glue.o -sha256-ssse3-y := sha256-ssse3-asm.o sha256-avx-asm.o sha256-avx2-asm.o sha256_ssse3_glue.o -ifeq ($(sha256_ni_supported),yes) -sha256-ssse3-y += sha256_ni_asm.o -endif -sha512-ssse3-y := sha512-ssse3-asm.o sha512-avx-asm.o sha512-avx2-asm.o sha512_ssse3_glue.o + +obj-$(CONFIG_CRYPTO_CRCT10DIF_PCLMUL) += crct10dif-pclmul.o crct10dif-pclmul-y := crct10dif-pcl-asm_64.o crct10dif-pclmul_glue.o +obj-$(CONFIG_CRYPTO_POLY1305_X86_64) += poly1305-x86_64.o +poly1305-x86_64-y := poly1305-x86_64-cryptogams.o poly1305_glue.o +targets += poly1305-x86_64-cryptogams.S + +obj-$(CONFIG_CRYPTO_NHPOLY1305_SSE2) += nhpoly1305-sse2.o +nhpoly1305-sse2-y := nh-sse2-x86_64.o nhpoly1305-sse2-glue.o +obj-$(CONFIG_CRYPTO_NHPOLY1305_AVX2) += nhpoly1305-avx2.o +nhpoly1305-avx2-y := nh-avx2-x86_64.o nhpoly1305-avx2-glue.o + +obj-$(CONFIG_CRYPTO_CURVE25519_X86) += curve25519-x86_64.o + quiet_cmd_perlasm = PERLASM $@ cmd_perlasm = $(PERL) $< > $@ $(obj)/%.S: $(src)/%.pl FORCE diff --git a/arch/x86/crypto/aesni-intel_avx-x86_64.S b/arch/x86/crypto/aesni-intel_avx-x86_64.S index bfa1c0b3e5b4..0cea33295287 100644 --- a/arch/x86/crypto/aesni-intel_avx-x86_64.S +++ b/arch/x86/crypto/aesni-intel_avx-x86_64.S @@ -886,7 +886,6 @@ _less_than_8_bytes_left_\@: _partial_block_done_\@: .endm # PARTIAL_BLOCK -#ifdef CONFIG_AS_AVX ############################################################################### # GHASH_MUL MACRO to implement: Data*HashKey mod (128,127,126,121,0) # Input: A and B (128-bits each, bit-reflected) @@ -1869,9 +1868,6 @@ key_256_finalize: ret SYM_FUNC_END(aesni_gcm_finalize_avx_gen2) -#endif /* CONFIG_AS_AVX */ - -#ifdef CONFIG_AS_AVX2 ############################################################################### # GHASH_MUL MACRO to implement: Data*HashKey mod (128,127,126,121,0) # Input: A and B (128-bits each, bit-reflected) @@ -2839,5 +2835,3 @@ key_256_finalize4: FUNC_RESTORE ret SYM_FUNC_END(aesni_gcm_finalize_avx_gen4) - -#endif /* CONFIG_AS_AVX2 */ diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c index 75b6ea20491e..ad8a7188a2bf 100644 --- a/arch/x86/crypto/aesni-intel_glue.c +++ b/arch/x86/crypto/aesni-intel_glue.c @@ -185,7 +185,6 @@ static const struct aesni_gcm_tfm_s aesni_gcm_tfm_sse = { .finalize = &aesni_gcm_finalize, }; -#ifdef CONFIG_AS_AVX asmlinkage void aes_ctr_enc_128_avx_by8(const u8 *in, u8 *iv, void *keys, u8 *out, unsigned int num_bytes); asmlinkage void aes_ctr_enc_192_avx_by8(const u8 *in, u8 *iv, @@ -234,9 +233,6 @@ static const struct aesni_gcm_tfm_s aesni_gcm_tfm_avx_gen2 = { .finalize = &aesni_gcm_finalize_avx_gen2, }; -#endif - -#ifdef CONFIG_AS_AVX2 /* * asmlinkage void aesni_gcm_init_avx_gen4() * gcm_data *my_ctx_data, context data @@ -279,8 +275,6 @@ static const struct aesni_gcm_tfm_s aesni_gcm_tfm_avx_gen4 = { .finalize = &aesni_gcm_finalize_avx_gen4, }; -#endif - static inline struct aesni_rfc4106_gcm_ctx *aesni_rfc4106_gcm_ctx_get(struct crypto_aead *tfm) { @@ -476,7 +470,6 @@ static void ctr_crypt_final(struct crypto_aes_ctx *ctx, crypto_inc(ctrblk, AES_BLOCK_SIZE); } -#ifdef CONFIG_AS_AVX static void aesni_ctr_enc_avx_tfm(struct crypto_aes_ctx *ctx, u8 *out, const u8 *in, unsigned int len, u8 *iv) { @@ -493,7 +486,6 @@ static void aesni_ctr_enc_avx_tfm(struct crypto_aes_ctx *ctx, u8 *out, else aes_ctr_enc_256_avx_by8(in, iv, (void *)ctx, out, len); } -#endif static int ctr_crypt(struct skcipher_request *req) { @@ -711,14 +703,10 @@ static int gcmaes_crypt_by_sg(bool enc, struct aead_request *req, if (!enc) left -= auth_tag_len; -#ifdef CONFIG_AS_AVX2 if (left < AVX_GEN4_OPTSIZE && gcm_tfm == &aesni_gcm_tfm_avx_gen4) gcm_tfm = &aesni_gcm_tfm_avx_gen2; -#endif -#ifdef CONFIG_AS_AVX if (left < AVX_GEN2_OPTSIZE && gcm_tfm == &aesni_gcm_tfm_avx_gen2) gcm_tfm = &aesni_gcm_tfm_sse; -#endif /* Linearize assoc, if not already linear */ if (req->src->length >= assoclen && req->src->length && @@ -1076,31 +1064,24 @@ static int __init aesni_init(void) if (!x86_match_cpu(aesni_cpu_id)) return -ENODEV; #ifdef CONFIG_X86_64 -#ifdef CONFIG_AS_AVX2 if (boot_cpu_has(X86_FEATURE_AVX2)) { pr_info("AVX2 version of gcm_enc/dec engaged.\n"); aesni_gcm_tfm = &aesni_gcm_tfm_avx_gen4; } else -#endif -#ifdef CONFIG_AS_AVX if (boot_cpu_has(X86_FEATURE_AVX)) { pr_info("AVX version of gcm_enc/dec engaged.\n"); aesni_gcm_tfm = &aesni_gcm_tfm_avx_gen2; - } else -#endif - { + } else { pr_info("SSE version of gcm_enc/dec engaged.\n"); aesni_gcm_tfm = &aesni_gcm_tfm_sse; } aesni_ctr_enc_tfm = aesni_ctr_enc; -#ifdef CONFIG_AS_AVX if (boot_cpu_has(X86_FEATURE_AVX)) { /* optimize performance of ctr mode encryption transform */ aesni_ctr_enc_tfm = aesni_ctr_enc_avx_tfm; pr_info("AES CTR mode by8 optimization enabled\n"); } #endif -#endif err = crypto_register_alg(&aesni_cipher_alg); if (err) diff --git a/arch/x86/crypto/blake2s-core.S b/arch/x86/crypto/blake2s-core.S index 24910b766bdd..2ca79974f819 100644 --- a/arch/x86/crypto/blake2s-core.S +++ b/arch/x86/crypto/blake2s-core.S @@ -46,7 +46,6 @@ SIGMA2: #endif /* CONFIG_AS_AVX512 */ .text -#ifdef CONFIG_AS_SSSE3 SYM_FUNC_START(blake2s_compress_ssse3) testq %rdx,%rdx je .Lendofloop @@ -174,7 +173,6 @@ SYM_FUNC_START(blake2s_compress_ssse3) .Lendofloop: ret SYM_FUNC_END(blake2s_compress_ssse3) -#endif /* CONFIG_AS_SSSE3 */ #ifdef CONFIG_AS_AVX512 SYM_FUNC_START(blake2s_compress_avx512) diff --git a/arch/x86/crypto/chacha_glue.c b/arch/x86/crypto/chacha_glue.c index 68a74953efaf..b412c21ee06e 100644 --- a/arch/x86/crypto/chacha_glue.c +++ b/arch/x86/crypto/chacha_glue.c @@ -79,8 +79,7 @@ static void chacha_dosimd(u32 *state, u8 *dst, const u8 *src, } } - if (IS_ENABLED(CONFIG_AS_AVX2) && - static_branch_likely(&chacha_use_avx2)) { + if (static_branch_likely(&chacha_use_avx2)) { while (bytes >= CHACHA_BLOCK_SIZE * 8) { chacha_8block_xor_avx2(state, dst, src, bytes, nrounds); bytes -= CHACHA_BLOCK_SIZE * 8; @@ -288,8 +287,7 @@ static int __init chacha_simd_mod_init(void) static_branch_enable(&chacha_use_simd); - if (IS_ENABLED(CONFIG_AS_AVX2) && - boot_cpu_has(X86_FEATURE_AVX) && + if (boot_cpu_has(X86_FEATURE_AVX) && boot_cpu_has(X86_FEATURE_AVX2) && cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL)) { static_branch_enable(&chacha_use_avx2); diff --git a/arch/x86/crypto/poly1305-x86_64-cryptogams.pl b/arch/x86/crypto/poly1305-x86_64-cryptogams.pl index 7a6b5380a46f..137edcf038cb 100644 --- a/arch/x86/crypto/poly1305-x86_64-cryptogams.pl +++ b/arch/x86/crypto/poly1305-x86_64-cryptogams.pl @@ -404,10 +404,6 @@ ___ &end_function("poly1305_emit_x86_64"); if ($avx) { -if($kernel) { - $code .= "#ifdef CONFIG_AS_AVX\n"; -} - ######################################################################## # Layout of opaque area is following. # @@ -1516,16 +1512,8 @@ $code.=<<___; ___ &end_function("poly1305_emit_avx"); -if ($kernel) { - $code .= "#endif\n"; -} - if ($avx>1) { -if ($kernel) { - $code .= "#ifdef CONFIG_AS_AVX2\n"; -} - my ($H0,$H1,$H2,$H3,$H4, $MASK, $T4,$T0,$T1,$T2,$T3, $D0,$D1,$D2,$D3,$D4) = map("%ymm$_",(0..15)); my $S4=$MASK; @@ -2816,10 +2804,6 @@ ___ poly1305_blocks_avxN(0); &end_function("poly1305_blocks_avx2"); -if($kernel) { - $code .= "#endif\n"; -} - ####################################################################### if ($avx>2) { # On entry we have input length divisible by 64. But since inner loop diff --git a/arch/x86/crypto/poly1305_glue.c b/arch/x86/crypto/poly1305_glue.c index 79bb58737d52..6dfec19f7d57 100644 --- a/arch/x86/crypto/poly1305_glue.c +++ b/arch/x86/crypto/poly1305_glue.c @@ -94,7 +94,7 @@ static void poly1305_simd_blocks(void *ctx, const u8 *inp, size_t len, BUILD_BUG_ON(PAGE_SIZE < POLY1305_BLOCK_SIZE || PAGE_SIZE % POLY1305_BLOCK_SIZE); - if (!IS_ENABLED(CONFIG_AS_AVX) || !static_branch_likely(&poly1305_use_avx) || + if (!static_branch_likely(&poly1305_use_avx) || (len < (POLY1305_BLOCK_SIZE * 18) && !state->is_base2_26) || !crypto_simd_usable()) { convert_to_base2_64(ctx); @@ -108,7 +108,7 @@ static void poly1305_simd_blocks(void *ctx, const u8 *inp, size_t len, kernel_fpu_begin(); if (IS_ENABLED(CONFIG_AS_AVX512) && static_branch_likely(&poly1305_use_avx512)) poly1305_blocks_avx512(ctx, inp, bytes, padbit); - else if (IS_ENABLED(CONFIG_AS_AVX2) && static_branch_likely(&poly1305_use_avx2)) + else if (static_branch_likely(&poly1305_use_avx2)) poly1305_blocks_avx2(ctx, inp, bytes, padbit); else poly1305_blocks_avx(ctx, inp, bytes, padbit); @@ -123,7 +123,7 @@ static void poly1305_simd_blocks(void *ctx, const u8 *inp, size_t len, static void poly1305_simd_emit(void *ctx, u8 mac[POLY1305_DIGEST_SIZE], const u32 nonce[4]) { - if (!IS_ENABLED(CONFIG_AS_AVX) || !static_branch_likely(&poly1305_use_avx)) + if (!static_branch_likely(&poly1305_use_avx)) poly1305_emit_x86_64(ctx, mac, nonce); else poly1305_emit_avx(ctx, mac, nonce); @@ -261,11 +261,10 @@ static struct shash_alg alg = { static int __init poly1305_simd_mod_init(void) { - if (IS_ENABLED(CONFIG_AS_AVX) && boot_cpu_has(X86_FEATURE_AVX) && + if (boot_cpu_has(X86_FEATURE_AVX) && cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL)) static_branch_enable(&poly1305_use_avx); - if (IS_ENABLED(CONFIG_AS_AVX2) && boot_cpu_has(X86_FEATURE_AVX) && - boot_cpu_has(X86_FEATURE_AVX2) && + if (boot_cpu_has(X86_FEATURE_AVX) && boot_cpu_has(X86_FEATURE_AVX2) && cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL)) static_branch_enable(&poly1305_use_avx2); if (IS_ENABLED(CONFIG_AS_AVX512) && boot_cpu_has(X86_FEATURE_AVX) && diff --git a/arch/x86/crypto/sha1_ssse3_asm.S b/arch/x86/crypto/sha1_ssse3_asm.S index 12e2d19d7402..d25668d2a1e9 100644 --- a/arch/x86/crypto/sha1_ssse3_asm.S +++ b/arch/x86/crypto/sha1_ssse3_asm.S @@ -467,8 +467,6 @@ W_PRECALC_SSSE3 */ SHA1_VECTOR_ASM sha1_transform_ssse3 -#ifdef CONFIG_AS_AVX - .macro W_PRECALC_AVX .purgem W_PRECALC_00_15 @@ -553,5 +551,3 @@ W_PRECALC_AVX * const u8 *data, int blocks); */ SHA1_VECTOR_ASM sha1_transform_avx - -#endif diff --git a/arch/x86/crypto/sha1_ssse3_glue.c b/arch/x86/crypto/sha1_ssse3_glue.c index d70b40ad594c..a801ffc10cbb 100644 --- a/arch/x86/crypto/sha1_ssse3_glue.c +++ b/arch/x86/crypto/sha1_ssse3_glue.c @@ -114,7 +114,6 @@ static void unregister_sha1_ssse3(void) crypto_unregister_shash(&sha1_ssse3_alg); } -#ifdef CONFIG_AS_AVX asmlinkage void sha1_transform_avx(struct sha1_state *state, const u8 *data, int blocks); @@ -175,13 +174,6 @@ static void unregister_sha1_avx(void) crypto_unregister_shash(&sha1_avx_alg); } -#else /* CONFIG_AS_AVX */ -static inline int register_sha1_avx(void) { return 0; } -static inline void unregister_sha1_avx(void) { } -#endif /* CONFIG_AS_AVX */ - - -#if defined(CONFIG_AS_AVX2) && (CONFIG_AS_AVX) #define SHA1_AVX2_BLOCK_OPTSIZE 4 /* optimal 4*64 bytes of SHA1 blocks */ asmlinkage void sha1_transform_avx2(struct sha1_state *state, @@ -253,11 +245,6 @@ static void unregister_sha1_avx2(void) crypto_unregister_shash(&sha1_avx2_alg); } -#else -static inline int register_sha1_avx2(void) { return 0; } -static inline void unregister_sha1_avx2(void) { } -#endif - #ifdef CONFIG_AS_SHA1_NI asmlinkage void sha1_ni_transform(struct sha1_state *digest, const u8 *data, int rounds); diff --git a/arch/x86/crypto/sha256-avx-asm.S b/arch/x86/crypto/sha256-avx-asm.S index fcbc30f58c38..4739cd31b9db 100644 --- a/arch/x86/crypto/sha256-avx-asm.S +++ b/arch/x86/crypto/sha256-avx-asm.S @@ -47,7 +47,6 @@ # This code schedules 1 block at a time, with 4 lanes per block ######################################################################## -#ifdef CONFIG_AS_AVX #include <linux/linkage.h> ## assume buffers not aligned @@ -498,5 +497,3 @@ _SHUF_00BA: # shuffle xDxC -> DC00 _SHUF_DC00: .octa 0x0b0a090803020100FFFFFFFFFFFFFFFF - -#endif diff --git a/arch/x86/crypto/sha256-avx2-asm.S b/arch/x86/crypto/sha256-avx2-asm.S index 499d9ec129de..11ff60c29c8b 100644 --- a/arch/x86/crypto/sha256-avx2-asm.S +++ b/arch/x86/crypto/sha256-avx2-asm.S @@ -48,7 +48,6 @@ # This code schedules 2 blocks at a time, with 4 lanes per block ######################################################################## -#ifdef CONFIG_AS_AVX2 #include <linux/linkage.h> ## assume buffers not aligned @@ -767,5 +766,3 @@ _SHUF_00BA: .align 32 _SHUF_DC00: .octa 0x0b0a090803020100FFFFFFFFFFFFFFFF,0x0b0a090803020100FFFFFFFFFFFFFFFF - -#endif diff --git a/arch/x86/crypto/sha256_ssse3_glue.c b/arch/x86/crypto/sha256_ssse3_glue.c index 03ad657c04bd..6394b5fe8db6 100644 --- a/arch/x86/crypto/sha256_ssse3_glue.c +++ b/arch/x86/crypto/sha256_ssse3_glue.c @@ -144,7 +144,6 @@ static void unregister_sha256_ssse3(void) ARRAY_SIZE(sha256_ssse3_algs)); } -#ifdef CONFIG_AS_AVX asmlinkage void sha256_transform_avx(struct sha256_state *state, const u8 *data, int blocks); @@ -221,12 +220,6 @@ static void unregister_sha256_avx(void) ARRAY_SIZE(sha256_avx_algs)); } -#else -static inline int register_sha256_avx(void) { return 0; } -static inline void unregister_sha256_avx(void) { } -#endif - -#if defined(CONFIG_AS_AVX2) && defined(CONFIG_AS_AVX) asmlinkage void sha256_transform_rorx(struct sha256_state *state, const u8 *data, int blocks); @@ -301,11 +294,6 @@ static void unregister_sha256_avx2(void) ARRAY_SIZE(sha256_avx2_algs)); } -#else -static inline int register_sha256_avx2(void) { return 0; } -static inline void unregister_sha256_avx2(void) { } -#endif - #ifdef CONFIG_AS_SHA256_NI asmlinkage void sha256_ni_transform(struct sha256_state *digest, const u8 *data, int rounds); diff --git a/arch/x86/crypto/sha512-avx-asm.S b/arch/x86/crypto/sha512-avx-asm.S index 90ea945ba5e6..63470fd6ae32 100644 --- a/arch/x86/crypto/sha512-avx-asm.S +++ b/arch/x86/crypto/sha512-avx-asm.S @@ -47,7 +47,6 @@ # ######################################################################## -#ifdef CONFIG_AS_AVX #include <linux/linkage.h> .text @@ -424,4 +423,3 @@ K512: .quad 0x3c9ebe0a15c9bebc,0x431d67c49c100d4c .quad 0x4cc5d4becb3e42b6,0x597f299cfc657e2a .quad 0x5fcb6fab3ad6faec,0x6c44198c4a475817 -#endif diff --git a/arch/x86/crypto/sha512-avx2-asm.S b/arch/x86/crypto/sha512-avx2-asm.S index 3dd886b14e7d..3a44bdcfd583 100644 --- a/arch/x86/crypto/sha512-avx2-asm.S +++ b/arch/x86/crypto/sha512-avx2-asm.S @@ -49,7 +49,6 @@ # This code schedules 1 blocks at a time, with 4 lanes per block ######################################################################## -#ifdef CONFIG_AS_AVX2 #include <linux/linkage.h> .text @@ -749,5 +748,3 @@ PSHUFFLE_BYTE_FLIP_MASK: MASK_YMM_LO: .octa 0x00000000000000000000000000000000 .octa 0xFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFF - -#endif diff --git a/arch/x86/crypto/sha512_ssse3_glue.c b/arch/x86/crypto/sha512_ssse3_glue.c index 1c444f41037c..82cc1b3ced1d 100644 --- a/arch/x86/crypto/sha512_ssse3_glue.c +++ b/arch/x86/crypto/sha512_ssse3_glue.c @@ -142,7 +142,6 @@ static void unregister_sha512_ssse3(void) ARRAY_SIZE(sha512_ssse3_algs)); } -#ifdef CONFIG_AS_AVX asmlinkage void sha512_transform_avx(struct sha512_state *state, const u8 *data, int blocks); static bool avx_usable(void) @@ -218,12 +217,7 @@ static void unregister_sha512_avx(void) crypto_unregister_shashes(sha512_avx_algs, ARRAY_SIZE(sha512_avx_algs)); } -#else -static inline int register_sha512_avx(void) { return 0; } -static inline void unregister_sha512_avx(void) { } -#endif -#if defined(CONFIG_AS_AVX2) && defined(CONFIG_AS_AVX) asmlinkage void sha512_transform_rorx(struct sha512_state *state, const u8 *data, int blocks); @@ -298,10 +292,6 @@ static void unregister_sha512_avx2(void) crypto_unregister_shashes(sha512_avx2_algs, ARRAY_SIZE(sha512_avx2_algs)); } -#else -static inline int register_sha512_avx2(void) { return 0; } -static inline void unregister_sha512_avx2(void) { } -#endif static int __init sha512_ssse3_mod_init(void) { diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index 1ba72c563313..cf76d6631afa 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -1476,6 +1476,12 @@ static const struct intel_uncore_init_fun tgl_l_uncore_init __initconst = { .mmio_init = tgl_l_uncore_mmio_init, }; +static const struct intel_uncore_init_fun icx_uncore_init __initconst = { + .cpu_init = icx_uncore_cpu_init, + .pci_init = icx_uncore_pci_init, + .mmio_init = icx_uncore_mmio_init, +}; + static const struct intel_uncore_init_fun snr_uncore_init __initconst = { .cpu_init = snr_uncore_cpu_init, .pci_init = snr_uncore_pci_init, @@ -1511,6 +1517,8 @@ static const struct x86_cpu_id intel_uncore_match[] __initconst = { X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_L, &icl_uncore_init), X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_NNPI, &icl_uncore_init), X86_MATCH_INTEL_FAM6_MODEL(ICELAKE, &icl_uncore_init), + X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_D, &icx_uncore_init), + X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_X, &icx_uncore_init), X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE_L, &tgl_l_uncore_init), X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE, &tgl_uncore_init), X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_D, &snr_uncore_init), diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h index b30429f8a53a..0da4a4605536 100644 --- a/arch/x86/events/intel/uncore.h +++ b/arch/x86/events/intel/uncore.h @@ -550,6 +550,9 @@ void skx_uncore_cpu_init(void); int snr_uncore_pci_init(void); void snr_uncore_cpu_init(void); void snr_uncore_mmio_init(void); +int icx_uncore_pci_init(void); +void icx_uncore_cpu_init(void); +void icx_uncore_mmio_init(void); /* uncore_nhmex.c */ void nhmex_uncore_cpu_init(void); diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index 01023f0d935b..07652fa20ebb 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -382,6 +382,42 @@ #define SNR_IMC_MMIO_MEM0_OFFSET 0xd8 #define SNR_IMC_MMIO_MEM0_MASK 0x7FF +/* ICX CHA */ +#define ICX_C34_MSR_PMON_CTR0 0xb68 +#define ICX_C34_MSR_PMON_CTL0 0xb61 +#define ICX_C34_MSR_PMON_BOX_CTL 0xb60 +#define ICX_C34_MSR_PMON_BOX_FILTER0 0xb65 + +/* ICX IIO */ +#define ICX_IIO_MSR_PMON_CTL0 0xa58 +#define ICX_IIO_MSR_PMON_CTR0 0xa51 +#define ICX_IIO_MSR_PMON_BOX_CTL 0xa50 + +/* ICX IRP */ +#define ICX_IRP0_MSR_PMON_CTL0 0xa4d +#define ICX_IRP0_MSR_PMON_CTR0 0xa4b +#define ICX_IRP0_MSR_PMON_BOX_CTL 0xa4a + +/* ICX M2PCIE */ +#define ICX_M2PCIE_MSR_PMON_CTL0 0xa46 +#define ICX_M2PCIE_MSR_PMON_CTR0 0xa41 +#define ICX_M2PCIE_MSR_PMON_BOX_CTL 0xa40 + +/* ICX UPI */ +#define ICX_UPI_PCI_PMON_CTL0 0x350 +#define ICX_UPI_PCI_PMON_CTR0 0x320 +#define ICX_UPI_PCI_PMON_BOX_CTL 0x318 +#define ICX_UPI_CTL_UMASK_EXT 0xffffff + +/* ICX M3UPI*/ +#define ICX_M3UPI_PCI_PMON_CTL0 0xd8 +#define ICX_M3UPI_PCI_PMON_CTR0 0xa8 +#define ICX_M3UPI_PCI_PMON_BOX_CTL 0xa0 + +/* ICX IMC */ +#define ICX_NUMBER_IMC_CHN 2 +#define ICX_IMC_MEM_STRIDE 0x4 + DEFINE_UNCORE_FORMAT_ATTR(event, event, "config:0-7"); DEFINE_UNCORE_FORMAT_ATTR(event2, event, "config:0-6"); DEFINE_UNCORE_FORMAT_ATTR(event_ext, event, "config:0-7,21"); @@ -390,6 +426,7 @@ DEFINE_UNCORE_FORMAT_ATTR(umask, umask, "config:8-15"); DEFINE_UNCORE_FORMAT_ATTR(umask_ext, umask, "config:8-15,32-43,45-55"); DEFINE_UNCORE_FORMAT_ATTR(umask_ext2, umask, "config:8-15,32-57"); DEFINE_UNCORE_FORMAT_ATTR(umask_ext3, umask, "config:8-15,32-39"); +DEFINE_UNCORE_FORMAT_ATTR(umask_ext4, umask, "config:8-15,32-55"); DEFINE_UNCORE_FORMAT_ATTR(qor, qor, "config:16"); DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18"); DEFINE_UNCORE_FORMAT_ATTR(tid_en, tid_en, "config:19"); @@ -4551,3 +4588,477 @@ void snr_uncore_mmio_init(void) } /* end of SNR uncore support */ + +/* ICX uncore support */ + +static unsigned icx_cha_msr_offsets[] = { + 0x2a0, 0x2ae, 0x2bc, 0x2ca, 0x2d8, 0x2e6, 0x2f4, 0x302, 0x310, + 0x31e, 0x32c, 0x33a, 0x348, 0x356, 0x364, 0x372, 0x380, 0x38e, + 0x3aa, 0x3b8, 0x3c6, 0x3d4, 0x3e2, 0x3f0, 0x3fe, 0x40c, 0x41a, + 0x428, 0x436, 0x444, 0x452, 0x460, 0x46e, 0x47c, 0x0, 0xe, + 0x1c, 0x2a, 0x38, 0x46, +}; + +static int icx_cha_hw_config(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; + bool tie_en = !!(event->hw.config & SNBEP_CBO_PMON_CTL_TID_EN); + + if (tie_en) { + reg1->reg = ICX_C34_MSR_PMON_BOX_FILTER0 + + icx_cha_msr_offsets[box->pmu->pmu_idx]; + reg1->config = event->attr.config1 & SKX_CHA_MSR_PMON_BOX_FILTER_TID; + reg1->idx = 0; + } + + return 0; +} + +static struct intel_uncore_ops icx_uncore_chabox_ops = { + .init_box = ivbep_uncore_msr_init_box, + .disable_box = snbep_uncore_msr_disable_box, + .enable_box = snbep_uncore_msr_enable_box, + .disable_event = snbep_uncore_msr_disable_event, + .enable_event = snr_cha_enable_event, + .read_counter = uncore_msr_read_counter, + .hw_config = icx_cha_hw_config, +}; + +static struct intel_uncore_type icx_uncore_chabox = { + .name = "cha", + .num_counters = 4, + .perf_ctr_bits = 48, + .event_ctl = ICX_C34_MSR_PMON_CTL0, + .perf_ctr = ICX_C34_MSR_PMON_CTR0, + .box_ctl = ICX_C34_MSR_PMON_BOX_CTL, + .msr_offsets = icx_cha_msr_offsets, + .event_mask = HSWEP_S_MSR_PMON_RAW_EVENT_MASK, + .event_mask_ext = SNR_CHA_RAW_EVENT_MASK_EXT, + .constraints = skx_uncore_chabox_constraints, + .ops = &icx_uncore_chabox_ops, + .format_group = &snr_uncore_chabox_format_group, +}; + +static unsigned icx_msr_offsets[] = { + 0x0, 0x20, 0x40, 0x90, 0xb0, 0xd0, +}; + +static struct event_constraint icx_uncore_iio_constraints[] = { + UNCORE_EVENT_CONSTRAINT(0x02, 0x3), + UNCORE_EVENT_CONSTRAINT(0x03, 0x3), + UNCORE_EVENT_CONSTRAINT(0x83, 0x3), + UNCORE_EVENT_CONSTRAINT(0xc0, 0xc), + UNCORE_EVENT_CONSTRAINT(0xc5, 0xc), + EVENT_CONSTRAINT_END +}; + +static struct intel_uncore_type icx_uncore_iio = { + .name = "iio", + .num_counters = 4, + .num_boxes = 6, + .perf_ctr_bits = 48, + .event_ctl = ICX_IIO_MSR_PMON_CTL0, + .perf_ctr = ICX_IIO_MSR_PMON_CTR0, + .event_mask = SNBEP_PMON_RAW_EVENT_MASK, + .event_mask_ext = SNR_IIO_PMON_RAW_EVENT_MASK_EXT, + .box_ctl = ICX_IIO_MSR_PMON_BOX_CTL, + .msr_offsets = icx_msr_offsets, + .constraints = icx_uncore_iio_constraints, + .ops = &skx_uncore_iio_ops, + .format_group = &snr_uncore_iio_format_group, +}; + +static struct intel_uncore_type icx_uncore_irp = { + .name = "irp", + .num_counters = 2, + .num_boxes = 6, + .perf_ctr_bits = 48, + .event_ctl = ICX_IRP0_MSR_PMON_CTL0, + .perf_ctr = ICX_IRP0_MSR_PMON_CTR0, + .event_mask = SNBEP_PMON_RAW_EVENT_MASK, + .box_ctl = ICX_IRP0_MSR_PMON_BOX_CTL, + .msr_offsets = icx_msr_offsets, + .ops = &ivbep_uncore_msr_ops, + .format_group = &ivbep_uncore_format_group, +}; + +static struct event_constraint icx_uncore_m2pcie_constraints[] = { + UNCORE_EVENT_CONSTRAINT(0x14, 0x3), + UNCORE_EVENT_CONSTRAINT(0x23, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2d, 0x3), + EVENT_CONSTRAINT_END +}; + +static struct intel_uncore_type icx_uncore_m2pcie = { + .name = "m2pcie", + .num_counters = 4, + .num_boxes = 6, + .perf_ctr_bits = 48, + .event_ctl = ICX_M2PCIE_MSR_PMON_CTL0, + .perf_ctr = ICX_M2PCIE_MSR_PMON_CTR0, + .box_ctl = ICX_M2PCIE_MSR_PMON_BOX_CTL, + .msr_offsets = icx_msr_offsets, + .constraints = icx_uncore_m2pcie_constraints, + .event_mask = SNBEP_PMON_RAW_EVENT_MASK, + .ops = &ivbep_uncore_msr_ops, + .format_group = &ivbep_uncore_format_group, +}; + +enum perf_uncore_icx_iio_freerunning_type_id { + ICX_IIO_MSR_IOCLK, + ICX_IIO_MSR_BW_IN, + + ICX_IIO_FREERUNNING_TYPE_MAX, +}; + +static unsigned icx_iio_clk_freerunning_box_offsets[] = { + 0x0, 0x20, 0x40, 0x90, 0xb0, 0xd0, +}; + +static unsigned icx_iio_bw_freerunning_box_offsets[] = { + 0x0, 0x10, 0x20, 0x90, 0xa0, 0xb0, +}; + +static struct freerunning_counters icx_iio_freerunning[] = { + [ICX_IIO_MSR_IOCLK] = { 0xa55, 0x1, 0x20, 1, 48, icx_iio_clk_freerunning_box_offsets }, + [ICX_IIO_MSR_BW_IN] = { 0xaa0, 0x1, 0x10, 8, 48, icx_iio_bw_freerunning_box_offsets }, +}; + +static struct uncore_event_desc icx_uncore_iio_freerunning_events[] = { + /* Free-Running IIO CLOCKS Counter */ + INTEL_UNCORE_EVENT_DESC(ioclk, "event=0xff,umask=0x10"), + /* Free-Running IIO BANDWIDTH IN Counters */ + INTEL_UNCORE_EVENT_DESC(bw_in_port0, "event=0xff,umask=0x20"), + INTEL_UNCORE_EVENT_DESC(bw_in_port0.scale, "3.814697266e-6"), + INTEL_UNCORE_EVENT_DESC(bw_in_port0.unit, "MiB"), + INTEL_UNCORE_EVENT_DESC(bw_in_port1, "event=0xff,umask=0x21"), + INTEL_UNCORE_EVENT_DESC(bw_in_port1.scale, "3.814697266e-6"), + INTEL_UNCORE_EVENT_DESC(bw_in_port1.unit, "MiB"), + INTEL_UNCORE_EVENT_DESC(bw_in_port2, "event=0xff,umask=0x22"), + INTEL_UNCORE_EVENT_DESC(bw_in_port2.scale, "3.814697266e-6"), + INTEL_UNCORE_EVENT_DESC(bw_in_port2.unit, "MiB"), + INTEL_UNCORE_EVENT_DESC(bw_in_port3, "event=0xff,umask=0x23"), + INTEL_UNCORE_EVENT_DESC(bw_in_port3.scale, "3.814697266e-6"), + INTEL_UNCORE_EVENT_DESC(bw_in_port3.unit, "MiB"), + INTEL_UNCORE_EVENT_DESC(bw_in_port4, "event=0xff,umask=0x24"), + INTEL_UNCORE_EVENT_DESC(bw_in_port4.scale, "3.814697266e-6"), + INTEL_UNCORE_EVENT_DESC(bw_in_port4.unit, "MiB"), + INTEL_UNCORE_EVENT_DESC(bw_in_port5, "event=0xff,umask=0x25"), + INTEL_UNCORE_EVENT_DESC(bw_in_port5.scale, "3.814697266e-6"), + INTEL_UNCORE_EVENT_DESC(bw_in_port5.unit, "MiB"), + INTEL_UNCORE_EVENT_DESC(bw_in_port6, "event=0xff,umask=0x26"), + INTEL_UNCORE_EVENT_DESC(bw_in_port6.scale, "3.814697266e-6"), + INTEL_UNCORE_EVENT_DESC(bw_in_port6.unit, "MiB"), + INTEL_UNCORE_EVENT_DESC(bw_in_port7, "event=0xff,umask=0x27"), + INTEL_UNCORE_EVENT_DESC(bw_in_port7.scale, "3.814697266e-6"), + INTEL_UNCORE_EVENT_DESC(bw_in_port7.unit, "MiB"), + { /* end: all zeroes */ }, +}; + +static struct intel_uncore_type icx_uncore_iio_free_running = { + .name = "iio_free_running", + .num_counters = 9, + .num_boxes = 6, + .num_freerunning_types = ICX_IIO_FREERUNNING_TYPE_MAX, + .freerunning = icx_iio_freerunning, + .ops = &skx_uncore_iio_freerunning_ops, + .event_descs = icx_uncore_iio_freerunning_events, + .format_group = &skx_uncore_iio_freerunning_format_group, +}; + +static struct intel_uncore_type *icx_msr_uncores[] = { + &skx_uncore_ubox, + &icx_uncore_chabox, + &icx_uncore_iio, + &icx_uncore_irp, + &icx_uncore_m2pcie, + &skx_uncore_pcu, + &icx_uncore_iio_free_running, + NULL, +}; + +/* + * To determine the number of CHAs, it should read CAPID6(Low) and CAPID7 (High) + * registers which located at Device 30, Function 3 + */ +#define ICX_CAPID6 0x9c +#define ICX_CAPID7 0xa0 + +static u64 icx_count_chabox(void) +{ + struct pci_dev *dev = NULL; + u64 caps = 0; + + dev = pci_get_device(PCI_VENDOR_ID_INTEL, 0x345b, dev); + if (!dev) + goto out; + + pci_read_config_dword(dev, ICX_CAPID6, (u32 *)&caps); + pci_read_config_dword(dev, ICX_CAPID7, (u32 *)&caps + 1); +out: + pci_dev_put(dev); + return hweight64(caps); +} + +void icx_uncore_cpu_init(void) +{ + u64 num_boxes = icx_count_chabox(); + + if (WARN_ON(num_boxes > ARRAY_SIZE(icx_cha_msr_offsets))) + return; + icx_uncore_chabox.num_boxes = num_boxes; + uncore_msr_uncores = icx_msr_uncores; +} + +static struct intel_uncore_type icx_uncore_m2m = { + .name = "m2m", + .num_counters = 4, + .num_boxes = 4, + .perf_ctr_bits = 48, + .perf_ctr = SNR_M2M_PCI_PMON_CTR0, + .event_ctl = SNR_M2M_PCI_PMON_CTL0, + .event_mask = SNBEP_PMON_RAW_EVENT_MASK, + .box_ctl = SNR_M2M_PCI_PMON_BOX_CTL, + .ops = &snr_m2m_uncore_pci_ops, + .format_group = &skx_uncore_format_group, +}; + +static struct attribute *icx_upi_uncore_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask_ext4.attr, + &format_attr_edge.attr, + &format_attr_inv.attr, + &format_attr_thresh8.attr, + NULL, +}; + +static const struct attribute_group icx_upi_uncore_format_group = { + .name = "format", + .attrs = icx_upi_uncore_formats_attr, +}; + +static struct intel_uncore_type icx_uncore_upi = { + .name = "upi", + .num_counters = 4, + .num_boxes = 3, + .perf_ctr_bits = 48, + .perf_ctr = ICX_UPI_PCI_PMON_CTR0, + .event_ctl = ICX_UPI_PCI_PMON_CTL0, + .event_mask = SNBEP_PMON_RAW_EVENT_MASK, + .event_mask_ext = ICX_UPI_CTL_UMASK_EXT, + .box_ctl = ICX_UPI_PCI_PMON_BOX_CTL, + .ops = &skx_upi_uncore_pci_ops, + .format_group = &icx_upi_uncore_format_group, +}; + +static struct event_constraint icx_uncore_m3upi_constraints[] = { + UNCORE_EVENT_CONSTRAINT(0x1c, 0x1), + UNCORE_EVENT_CONSTRAINT(0x1d, 0x1), + UNCORE_EVENT_CONSTRAINT(0x1e, 0x1), + UNCORE_EVENT_CONSTRAINT(0x1f, 0x1), + UNCORE_EVENT_CONSTRAINT(0x40, 0x7), + UNCORE_EVENT_CONSTRAINT(0x4e, 0x7), + UNCORE_EVENT_CONSTRAINT(0x4f, 0x7), + UNCORE_EVENT_CONSTRAINT(0x50, 0x7), + EVENT_CONSTRAINT_END +}; + +static struct intel_uncore_type icx_uncore_m3upi = { + .name = "m3upi", + .num_counters = 4, + .num_boxes = 3, + .perf_ctr_bits = 48, + .perf_ctr = ICX_M3UPI_PCI_PMON_CTR0, + .event_ctl = ICX_M3UPI_PCI_PMON_CTL0, + .event_mask = SNBEP_PMON_RAW_EVENT_MASK, + .box_ctl = ICX_M3UPI_PCI_PMON_BOX_CTL, + .constraints = icx_uncore_m3upi_constraints, + .ops = &ivbep_uncore_pci_ops, + .format_group = &skx_uncore_format_group, +}; + +enum { + ICX_PCI_UNCORE_M2M, + ICX_PCI_UNCORE_UPI, + ICX_PCI_UNCORE_M3UPI, +}; + +static struct intel_uncore_type *icx_pci_uncores[] = { + [ICX_PCI_UNCORE_M2M] = &icx_uncore_m2m, + [ICX_PCI_UNCORE_UPI] = &icx_uncore_upi, + [ICX_PCI_UNCORE_M3UPI] = &icx_uncore_m3upi, + NULL, +}; + +static const struct pci_device_id icx_uncore_pci_ids[] = { + { /* M2M 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x344a), + .driver_data = UNCORE_PCI_DEV_FULL_DATA(12, 0, ICX_PCI_UNCORE_M2M, 0), + }, + { /* M2M 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x344a), + .driver_data = UNCORE_PCI_DEV_FULL_DATA(13, 0, ICX_PCI_UNCORE_M2M, 1), + }, + { /* M2M 2 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x344a), + .driver_data = UNCORE_PCI_DEV_FULL_DATA(14, 0, ICX_PCI_UNCORE_M2M, 2), + }, + { /* M2M 3 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x344a), + .driver_data = UNCORE_PCI_DEV_FULL_DATA(15, 0, ICX_PCI_UNCORE_M2M, 3), + }, + { /* UPI Link 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x3441), + .driver_data = UNCORE_PCI_DEV_FULL_DATA(2, 1, ICX_PCI_UNCORE_UPI, 0), + }, + { /* UPI Link 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x3441), + .driver_data = UNCORE_PCI_DEV_FULL_DATA(3, 1, ICX_PCI_UNCORE_UPI, 1), + }, + { /* UPI Link 2 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x3441), + .driver_data = UNCORE_PCI_DEV_FULL_DATA(4, 1, ICX_PCI_UNCORE_UPI, 2), + }, + { /* M3UPI Link 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x3446), + .driver_data = UNCORE_PCI_DEV_FULL_DATA(5, 1, ICX_PCI_UNCORE_M3UPI, 0), + }, + { /* M3UPI Link 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x3446), + .driver_data = UNCORE_PCI_DEV_FULL_DATA(6, 1, ICX_PCI_UNCORE_M3UPI, 1), + }, + { /* M3UPI Link 2 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x3446), + .driver_data = UNCORE_PCI_DEV_FULL_DATA(7, 1, ICX_PCI_UNCORE_M3UPI, 2), + }, + { /* end: all zeroes */ } +}; + +static struct pci_driver icx_uncore_pci_driver = { + .name = "icx_uncore", + .id_table = icx_uncore_pci_ids, +}; + +int icx_uncore_pci_init(void) +{ + /* ICX UBOX DID */ + int ret = snbep_pci2phy_map_init(0x3450, SKX_CPUNODEID, + SKX_GIDNIDMAP, true); + + if (ret) + return ret; + + uncore_pci_uncores = icx_pci_uncores; + uncore_pci_driver = &icx_uncore_pci_driver; + return 0; +} + +static void icx_uncore_imc_init_box(struct intel_uncore_box *box) +{ + unsigned int box_ctl = box->pmu->type->box_ctl + + box->pmu->type->mmio_offset * (box->pmu->pmu_idx % ICX_NUMBER_IMC_CHN); + int mem_offset = (box->pmu->pmu_idx / ICX_NUMBER_IMC_CHN) * ICX_IMC_MEM_STRIDE + + SNR_IMC_MMIO_MEM0_OFFSET; + + __snr_uncore_mmio_init_box(box, box_ctl, mem_offset); +} + +static struct intel_uncore_ops icx_uncore_mmio_ops = { + .init_box = icx_uncore_imc_init_box, + .exit_box = uncore_mmio_exit_box, + .disable_box = snr_uncore_mmio_disable_box, + .enable_box = snr_uncore_mmio_enable_box, + .disable_event = snr_uncore_mmio_disable_event, + .enable_event = snr_uncore_mmio_enable_event, + .read_counter = uncore_mmio_read_counter, +}; + +static struct intel_uncore_type icx_uncore_imc = { + .name = "imc", + .num_counters = 4, + .num_boxes = 8, + .perf_ctr_bits = 48, + .fixed_ctr_bits = 48, + .fixed_ctr = SNR_IMC_MMIO_PMON_FIXED_CTR, + .fixed_ctl = SNR_IMC_MMIO_PMON_FIXED_CTL, + .event_descs = hswep_uncore_imc_events, + .perf_ctr = SNR_IMC_MMIO_PMON_CTR0, + .event_ctl = SNR_IMC_MMIO_PMON_CTL0, + .event_mask = SNBEP_PMON_RAW_EVENT_MASK, + .box_ctl = SNR_IMC_MMIO_PMON_BOX_CTL, + .mmio_offset = SNR_IMC_MMIO_OFFSET, + .ops = &icx_uncore_mmio_ops, + .format_group = &skx_uncore_format_group, +}; + +enum perf_uncore_icx_imc_freerunning_type_id { + ICX_IMC_DCLK, + ICX_IMC_DDR, + ICX_IMC_DDRT, + + ICX_IMC_FREERUNNING_TYPE_MAX, +}; + +static struct freerunning_counters icx_imc_freerunning[] = { + [ICX_IMC_DCLK] = { 0x22b0, 0x0, 0, 1, 48 }, + [ICX_IMC_DDR] = { 0x2290, 0x8, 0, 2, 48 }, + [ICX_IMC_DDRT] = { 0x22a0, 0x8, 0, 2, 48 }, +}; + +static struct uncore_event_desc icx_uncore_imc_freerunning_events[] = { + INTEL_UNCORE_EVENT_DESC(dclk, "event=0xff,umask=0x10"), + + INTEL_UNCORE_EVENT_DESC(read, "event=0xff,umask=0x20"), + INTEL_UNCORE_EVENT_DESC(read.scale, "3.814697266e-6"), + INTEL_UNCORE_EVENT_DESC(read.unit, "MiB"), + INTEL_UNCORE_EVENT_DESC(write, "event=0xff,umask=0x21"), + INTEL_UNCORE_EVENT_DESC(write.scale, "3.814697266e-6"), + INTEL_UNCORE_EVENT_DESC(write.unit, "MiB"), + + INTEL_UNCORE_EVENT_DESC(ddrt_read, "event=0xff,umask=0x30"), + INTEL_UNCORE_EVENT_DESC(ddrt_read.scale, "3.814697266e-6"), + INTEL_UNCORE_EVENT_DESC(ddrt_read.unit, "MiB"), + INTEL_UNCORE_EVENT_DESC(ddrt_write, "event=0xff,umask=0x31"), + INTEL_UNCORE_EVENT_DESC(ddrt_write.scale, "3.814697266e-6"), + INTEL_UNCORE_EVENT_DESC(ddrt_write.unit, "MiB"), + { /* end: all zeroes */ }, +}; + +static void icx_uncore_imc_freerunning_init_box(struct intel_uncore_box *box) +{ + int mem_offset = box->pmu->pmu_idx * ICX_IMC_MEM_STRIDE + + SNR_IMC_MMIO_MEM0_OFFSET; + + __snr_uncore_mmio_init_box(box, uncore_mmio_box_ctl(box), mem_offset); +} + +static struct intel_uncore_ops icx_uncore_imc_freerunning_ops = { + .init_box = icx_uncore_imc_freerunning_init_box, + .exit_box = uncore_mmio_exit_box, + .read_counter = uncore_mmio_read_counter, + .hw_config = uncore_freerunning_hw_config, +}; + +static struct intel_uncore_type icx_uncore_imc_free_running = { + .name = "imc_free_running", + .num_counters = 5, + .num_boxes = 4, + .num_freerunning_types = ICX_IMC_FREERUNNING_TYPE_MAX, + .freerunning = icx_imc_freerunning, + .ops = &icx_uncore_imc_freerunning_ops, + .event_descs = icx_uncore_imc_freerunning_events, + .format_group = &skx_uncore_iio_freerunning_format_group, +}; + +static struct intel_uncore_type *icx_mmio_uncores[] = { + &icx_uncore_imc, + &icx_uncore_imc_free_running, + NULL, +}; + +void icx_uncore_mmio_init(void) +{ + uncore_mmio_uncores = icx_mmio_uncores; +} + +/* end of ICX uncore support */ diff --git a/arch/x86/include/asm/dwarf2.h b/arch/x86/include/asm/dwarf2.h index f71a0cce9373..430fca13bb56 100644 --- a/arch/x86/include/asm/dwarf2.h +++ b/arch/x86/include/asm/dwarf2.h @@ -6,15 +6,6 @@ #warning "asm/dwarf2.h should be only included in pure assembly files" #endif -/* - * Macros for dwarf2 CFI unwind table entries. - * See "as.info" for details on these pseudo ops. Unfortunately - * they are only supported in very new binutils, so define them - * away for older version. - */ - -#ifdef CONFIG_AS_CFI - #define CFI_STARTPROC .cfi_startproc #define CFI_ENDPROC .cfi_endproc #define CFI_DEF_CFA .cfi_def_cfa @@ -30,13 +21,6 @@ #define CFI_UNDEFINED .cfi_undefined #define CFI_ESCAPE .cfi_escape -#ifdef CONFIG_AS_CFI_SIGNAL_FRAME -#define CFI_SIGNAL_FRAME .cfi_signal_frame -#else -#define CFI_SIGNAL_FRAME -#endif - -#if defined(CONFIG_AS_CFI_SECTIONS) && defined(__ASSEMBLY__) #ifndef BUILD_VDSO /* * Emit CFI data in .debug_frame sections, not .eh_frame sections. @@ -53,33 +37,5 @@ */ .cfi_sections .eh_frame, .debug_frame #endif -#endif - -#else - -/* - * Due to the structure of pre-exisiting code, don't use assembler line - * comment character # to ignore the arguments. Instead, use a dummy macro. - */ -.macro cfi_ignore a=0, b=0, c=0, d=0 -.endm - -#define CFI_STARTPROC cfi_ignore -#define CFI_ENDPROC cfi_ignore -#define CFI_DEF_CFA cfi_ignore -#define CFI_DEF_CFA_REGISTER cfi_ignore -#define CFI_DEF_CFA_OFFSET cfi_ignore -#define CFI_ADJUST_CFA_OFFSET cfi_ignore -#define CFI_OFFSET cfi_ignore -#define CFI_REL_OFFSET cfi_ignore -#define CFI_REGISTER cfi_ignore -#define CFI_RESTORE cfi_ignore -#define CFI_REMEMBER_STATE cfi_ignore -#define CFI_RESTORE_STATE cfi_ignore -#define CFI_UNDEFINED cfi_ignore -#define CFI_ESCAPE cfi_ignore -#define CFI_SIGNAL_FRAME cfi_ignore - -#endif #endif /* _ASM_X86_DWARF2_H */ diff --git a/arch/x86/include/asm/xor_avx.h b/arch/x86/include/asm/xor_avx.h index d61ddf3d052b..0c4e5b5e3852 100644 --- a/arch/x86/include/asm/xor_avx.h +++ b/arch/x86/include/asm/xor_avx.h @@ -11,8 +11,6 @@ * Based on Ingo Molnar and Zach Brown's respective MMX and SSE routines */ -#ifdef CONFIG_AS_AVX - #include <linux/compiler.h> #include <asm/fpu/api.h> @@ -170,11 +168,4 @@ do { \ #define AVX_SELECT(FASTEST) \ (boot_cpu_has(X86_FEATURE_AVX) && boot_cpu_has(X86_FEATURE_OSXSAVE) ? &xor_block_avx : FASTEST) -#else - -#define AVX_XOR_SPEED {} - -#define AVX_SELECT(FASTEST) (FASTEST) - -#endif #endif diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile index 9f887a86e555..6cd1f6253814 100644 --- a/drivers/gpu/drm/i915/Makefile +++ b/drivers/gpu/drm/i915/Makefile @@ -28,9 +28,6 @@ subdir-ccflags-$(CONFIG_DRM_I915_WERROR) += -Werror CFLAGS_i915_pci.o = $(call cc-disable-warning, override-init) CFLAGS_display/intel_fbdev.o = $(call cc-disable-warning, override-init) -subdir-ccflags-y += \ - $(call as-instr,movntdqa (%eax)$(comma)%xmm0,-DCONFIG_AS_MOVNTDQA) - subdir-ccflags-y += -I$(srctree)/$(src) # Please keep these build lists sorted! diff --git a/drivers/gpu/drm/i915/i915_memcpy.c b/drivers/gpu/drm/i915/i915_memcpy.c index fdd550405fd3..7b3b83bd5ab8 100644 --- a/drivers/gpu/drm/i915/i915_memcpy.c +++ b/drivers/gpu/drm/i915/i915_memcpy.c @@ -35,7 +35,6 @@ static DEFINE_STATIC_KEY_FALSE(has_movntdqa); -#ifdef CONFIG_AS_MOVNTDQA static void __memcpy_ntdqa(void *dst, const void *src, unsigned long len) { kernel_fpu_begin(); @@ -93,10 +92,6 @@ static void __memcpy_ntdqu(void *dst, const void *src, unsigned long len) kernel_fpu_end(); } -#else -static void __memcpy_ntdqa(void *dst, const void *src, unsigned long len) {} -static void __memcpy_ntdqu(void *dst, const void *src, unsigned long len) {} -#endif /** * i915_memcpy_from_wc: perform an accelerated *aligned* read from WC diff --git a/fs/cifs/Kconfig b/fs/cifs/Kconfig index 22cf04fb32d3..604f65f4b6c5 100644 --- a/fs/cifs/Kconfig +++ b/fs/cifs/Kconfig @@ -202,7 +202,7 @@ config CIFS_SMB_DIRECT help Enables SMB Direct support for SMB 3.0, 3.02 and 3.1.1. SMB Direct allows transferring SMB packets over RDMA. If unsure, - say N. + say Y. config CIFS_FSCACHE bool "Provide CIFS client caching support" diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c index 276e4b5ea8e0..916567d770f5 100644 --- a/fs/cifs/cifs_debug.c +++ b/fs/cifs/cifs_debug.c @@ -323,10 +323,8 @@ static int cifs_debug_data_proc_show(struct seq_file *m, void *v) atomic_read(&server->smbd_conn->send_credits), atomic_read(&server->smbd_conn->receive_credits), server->smbd_conn->receive_credit_target); - seq_printf(m, "\nPending send_pending: %x " - "send_payload_pending: %x", - atomic_read(&server->smbd_conn->send_pending), - atomic_read(&server->smbd_conn->send_payload_pending)); + seq_printf(m, "\nPending send_pending: %x ", + atomic_read(&server->smbd_conn->send_pending)); seq_printf(m, "\nReceive buffers count_receive_queue: %x " "count_empty_packet_queue: %x", server->smbd_conn->count_receive_queue, diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 94e3ed4850b5..c31f362fa098 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -1208,6 +1208,10 @@ static ssize_t cifs_copy_file_range(struct file *src_file, loff_t off, { unsigned int xid = get_xid(); ssize_t rc; + struct cifsFileInfo *cfile = dst_file->private_data; + + if (cfile->swapfile) + return -EOPNOTSUPP; rc = cifs_file_copychunk_range(xid, src_file, off, dst_file, destoff, len, flags); diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index 0d956360e984..05dd3dea684b 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -426,7 +426,8 @@ struct smb_version_operations { /* generate new lease key */ void (*new_lease_key)(struct cifs_fid *); int (*generate_signingkey)(struct cifs_ses *); - int (*calc_signature)(struct smb_rqst *, struct TCP_Server_Info *); + int (*calc_signature)(struct smb_rqst *, struct TCP_Server_Info *, + bool allocate_crypto); int (*set_integrity)(const unsigned int, struct cifs_tcon *tcon, struct cifsFileInfo *src_file); int (*enum_snapshots)(const unsigned int xid, struct cifs_tcon *tcon, @@ -1312,6 +1313,7 @@ struct cifsFileInfo { struct tcon_link *tlink; unsigned int f_flags; bool invalidHandle:1; /* file closed via session abend */ + bool swapfile:1; bool oplock_break_cancelled:1; unsigned int oplock_epoch; /* epoch from the lease break */ __u32 oplock_level; /* oplock/lease level from the lease break */ diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 5920820bfbd0..0b1528edebcf 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -4808,6 +4808,60 @@ cifs_direct_io(struct kiocb *iocb, struct iov_iter *iter) return -EINVAL; } +static int cifs_swap_activate(struct swap_info_struct *sis, + struct file *swap_file, sector_t *span) +{ + struct cifsFileInfo *cfile = swap_file->private_data; + struct inode *inode = swap_file->f_mapping->host; + unsigned long blocks; + long long isize; + + cifs_dbg(FYI, "swap activate\n"); + + spin_lock(&inode->i_lock); + blocks = inode->i_blocks; + isize = inode->i_size; + spin_unlock(&inode->i_lock); + if (blocks*512 < isize) { + pr_warn("swap activate: swapfile has holes\n"); + return -EINVAL; + } + *span = sis->pages; + + printk_once(KERN_WARNING "Swap support over SMB3 is experimental\n"); + + /* + * TODO: consider adding ACL (or documenting how) to prevent other + * users (on this or other systems) from reading it + */ + + + /* TODO: add sk_set_memalloc(inet) or similar */ + + if (cfile) + cfile->swapfile = true; + /* + * TODO: Since file already open, we can't open with DENY_ALL here + * but we could add call to grab a byte range lock to prevent others + * from reading or writing the file + */ + + return 0; +} + +static void cifs_swap_deactivate(struct file *file) +{ + struct cifsFileInfo *cfile = file->private_data; + + cifs_dbg(FYI, "swap deactivate\n"); + + /* TODO: undo sk_set_memalloc(inet) will eventually be needed */ + + if (cfile) + cfile->swapfile = false; + + /* do we need to unpin (or unlock) the file */ +} const struct address_space_operations cifs_addr_ops = { .readpage = cifs_readpage, @@ -4821,6 +4875,13 @@ const struct address_space_operations cifs_addr_ops = { .direct_IO = cifs_direct_io, .invalidatepage = cifs_invalidate_page, .launder_page = cifs_launder_page, + /* + * TODO: investigate and if useful we could add an cifs_migratePage + * helper (under an CONFIG_MIGRATION) in the future, and also + * investigate and add an is_dirty_writeback helper if needed + */ + .swap_activate = cifs_swap_activate, + .swap_deactivate = cifs_swap_deactivate, }; /* diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 8d01ec2dca66..8fbbdcdad8ff 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -2026,6 +2026,10 @@ cifs_revalidate_mapping(struct inode *inode) int rc; unsigned long *flags = &CIFS_I(inode)->flags; + /* swapfiles are not supposed to be shared */ + if (IS_SWAPFILE(inode)) + return 0; + rc = wait_on_bit_lock_action(flags, CIFS_INO_LOCK, cifs_wait_bit_killable, TASK_KILLABLE); if (rc) diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c index 19e4a5d3b4ca..50f776a8d4ba 100644 --- a/fs/cifs/readdir.c +++ b/fs/cifs/readdir.c @@ -246,7 +246,7 @@ cifs_posix_to_fattr(struct cifs_fattr *fattr, struct smb2_posix_info *info, */ fattr->cf_mode = le32_to_cpu(info->Mode) & ~S_IFMT; - cifs_dbg(VFS, "XXX dev %d, reparse %d, mode %o", + cifs_dbg(FYI, "posix fattr: dev %d, reparse %d, mode %o", le32_to_cpu(info->DeviceId), le32_to_cpu(info->ReparseTag), le32_to_cpu(info->Mode)); diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c index 0511aaf451d4..497afb0b9960 100644 --- a/fs/cifs/smb2misc.c +++ b/fs/cifs/smb2misc.c @@ -766,6 +766,20 @@ smb2_handle_cancelled_close(struct cifs_tcon *tcon, __u64 persistent_fid, cifs_dbg(FYI, "%s: tc_count=%d\n", __func__, tcon->tc_count); spin_lock(&cifs_tcp_ses_lock); + if (tcon->tc_count <= 0) { + struct TCP_Server_Info *server = NULL; + + WARN_ONCE(tcon->tc_count < 0, "tcon refcount is negative"); + spin_unlock(&cifs_tcp_ses_lock); + + if (tcon->ses) + server = tcon->ses->server; + + cifs_server_dbg(FYI, "tid=%u: tcon is closing, skipping async close retry of fid %llu %llu\n", + tcon->tid, persistent_fid, volatile_fid); + + return 0; + } tcon->tc_count++; spin_unlock(&cifs_tcp_ses_lock); diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h index 4d1ff7b66fdc..087d5f14320b 100644 --- a/fs/cifs/smb2proto.h +++ b/fs/cifs/smb2proto.h @@ -55,9 +55,11 @@ extern struct cifs_ses *smb2_find_smb_ses(struct TCP_Server_Info *server, extern struct cifs_tcon *smb2_find_smb_tcon(struct TCP_Server_Info *server, __u64 ses_id, __u32 tid); extern int smb2_calc_signature(struct smb_rqst *rqst, - struct TCP_Server_Info *server); + struct TCP_Server_Info *server, + bool allocate_crypto); extern int smb3_calc_signature(struct smb_rqst *rqst, - struct TCP_Server_Info *server); + struct TCP_Server_Info *server, + bool allocate_crypto); extern void smb2_echo_request(struct work_struct *work); extern __le32 smb2_get_lease_state(struct cifsInodeInfo *cinode); extern bool smb2_is_valid_oplock_break(char *buffer, diff --git a/fs/cifs/smb2transport.c b/fs/cifs/smb2transport.c index 20cc79e5c15d..1a6c227ada8f 100644 --- a/fs/cifs/smb2transport.c +++ b/fs/cifs/smb2transport.c @@ -41,14 +41,6 @@ #include "smb2glob.h" static int -smb2_crypto_shash_allocate(struct TCP_Server_Info *server) -{ - return cifs_alloc_hash("hmac(sha256)", - &server->secmech.hmacsha256, - &server->secmech.sdeschmacsha256); -} - -static int smb3_crypto_shash_allocate(struct TCP_Server_Info *server) { struct cifs_secmech *p = &server->secmech; @@ -219,7 +211,8 @@ smb2_find_smb_tcon(struct TCP_Server_Info *server, __u64 ses_id, __u32 tid) } int -smb2_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server) +smb2_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server, + bool allocate_crypto) { int rc; unsigned char smb2_signature[SMB2_HMACSHA256_SIZE]; @@ -228,6 +221,8 @@ smb2_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server) struct smb2_sync_hdr *shdr = (struct smb2_sync_hdr *)iov[0].iov_base; struct cifs_ses *ses; struct shash_desc *shash; + struct crypto_shash *hash; + struct sdesc *sdesc = NULL; struct smb_rqst drqst; ses = smb2_find_smb_ses(server, shdr->SessionId); @@ -239,24 +234,32 @@ smb2_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server) memset(smb2_signature, 0x0, SMB2_HMACSHA256_SIZE); memset(shdr->Signature, 0x0, SMB2_SIGNATURE_SIZE); - rc = smb2_crypto_shash_allocate(server); - if (rc) { - cifs_server_dbg(VFS, "%s: sha256 alloc failed\n", __func__); - return rc; + if (allocate_crypto) { + rc = cifs_alloc_hash("hmac(sha256)", &hash, &sdesc); + if (rc) { + cifs_server_dbg(VFS, + "%s: sha256 alloc failed\n", __func__); + return rc; + } + shash = &sdesc->shash; + } else { + hash = server->secmech.hmacsha256; + shash = &server->secmech.sdeschmacsha256->shash; } - rc = crypto_shash_setkey(server->secmech.hmacsha256, - ses->auth_key.response, SMB2_NTLMV2_SESSKEY_SIZE); + rc = crypto_shash_setkey(hash, ses->auth_key.response, + SMB2_NTLMV2_SESSKEY_SIZE); if (rc) { - cifs_server_dbg(VFS, "%s: Could not update with response\n", __func__); - return rc; + cifs_server_dbg(VFS, + "%s: Could not update with response\n", + __func__); + goto out; } - shash = &server->secmech.sdeschmacsha256->shash; rc = crypto_shash_init(shash); if (rc) { cifs_server_dbg(VFS, "%s: Could not init sha256", __func__); - return rc; + goto out; } /* @@ -271,9 +274,10 @@ smb2_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server) rc = crypto_shash_update(shash, iov[0].iov_base, iov[0].iov_len); if (rc) { - cifs_server_dbg(VFS, "%s: Could not update with payload\n", - __func__); - return rc; + cifs_server_dbg(VFS, + "%s: Could not update with payload\n", + __func__); + goto out; } drqst.rq_iov++; drqst.rq_nvec--; @@ -283,6 +287,9 @@ smb2_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server) if (!rc) memcpy(shdr->Signature, sigptr, SMB2_SIGNATURE_SIZE); +out: + if (allocate_crypto) + cifs_free_hash(&hash, &sdesc); return rc; } @@ -504,14 +511,17 @@ generate_smb311signingkey(struct cifs_ses *ses) } int -smb3_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server) +smb3_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server, + bool allocate_crypto) { int rc; unsigned char smb3_signature[SMB2_CMACAES_SIZE]; unsigned char *sigptr = smb3_signature; struct kvec *iov = rqst->rq_iov; struct smb2_sync_hdr *shdr = (struct smb2_sync_hdr *)iov[0].iov_base; - struct shash_desc *shash = &server->secmech.sdesccmacaes->shash; + struct shash_desc *shash; + struct crypto_shash *hash; + struct sdesc *sdesc = NULL; struct smb_rqst drqst; u8 key[SMB3_SIGN_KEY_SIZE]; @@ -519,14 +529,24 @@ smb3_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server) if (rc) return 0; + if (allocate_crypto) { + rc = cifs_alloc_hash("cmac(aes)", &hash, &sdesc); + if (rc) + return rc; + + shash = &sdesc->shash; + } else { + hash = server->secmech.cmacaes; + shash = &server->secmech.sdesccmacaes->shash; + } + memset(smb3_signature, 0x0, SMB2_CMACAES_SIZE); memset(shdr->Signature, 0x0, SMB2_SIGNATURE_SIZE); - rc = crypto_shash_setkey(server->secmech.cmacaes, - key, SMB2_CMACAES_SIZE); + rc = crypto_shash_setkey(hash, key, SMB2_CMACAES_SIZE); if (rc) { cifs_server_dbg(VFS, "%s: Could not set key for cmac aes\n", __func__); - return rc; + goto out; } /* @@ -537,7 +557,7 @@ smb3_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server) rc = crypto_shash_init(shash); if (rc) { cifs_server_dbg(VFS, "%s: Could not init cmac aes\n", __func__); - return rc; + goto out; } /* @@ -554,7 +574,7 @@ smb3_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server) if (rc) { cifs_server_dbg(VFS, "%s: Could not update with payload\n", __func__); - return rc; + goto out; } drqst.rq_iov++; drqst.rq_nvec--; @@ -564,6 +584,9 @@ smb3_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server) if (!rc) memcpy(shdr->Signature, sigptr, SMB2_SIGNATURE_SIZE); +out: + if (allocate_crypto) + cifs_free_hash(&hash, &sdesc); return rc; } @@ -593,7 +616,7 @@ smb2_sign_rqst(struct smb_rqst *rqst, struct TCP_Server_Info *server) return 0; } - rc = server->ops->calc_signature(rqst, server); + rc = server->ops->calc_signature(rqst, server, false); return rc; } @@ -631,9 +654,7 @@ smb2_verify_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server) memset(shdr->Signature, 0, SMB2_SIGNATURE_SIZE); - mutex_lock(&server->srv_mutex); - rc = server->ops->calc_signature(rqst, server); - mutex_unlock(&server->srv_mutex); + rc = server->ops->calc_signature(rqst, server, true); if (rc) return rc; diff --git a/fs/cifs/smbdirect.c b/fs/cifs/smbdirect.c index 8da43a500686..1a5834a5d597 100644 --- a/fs/cifs/smbdirect.c +++ b/fs/cifs/smbdirect.c @@ -284,13 +284,10 @@ static void send_done(struct ib_cq *cq, struct ib_wc *wc) request->sge[i].length, DMA_TO_DEVICE); - if (request->has_payload) { - if (atomic_dec_and_test(&request->info->send_payload_pending)) - wake_up(&request->info->wait_send_payload_pending); - } else { - if (atomic_dec_and_test(&request->info->send_pending)) - wake_up(&request->info->wait_send_pending); - } + if (atomic_dec_and_test(&request->info->send_pending)) + wake_up(&request->info->wait_send_pending); + + wake_up(&request->info->wait_post_send); mempool_free(request, request->info->request_mempool); } @@ -383,27 +380,6 @@ static bool process_negotiation_response( return true; } -/* - * Check and schedule to send an immediate packet - * This is used to extend credtis to remote peer to keep the transport busy - */ -static void check_and_send_immediate(struct smbd_connection *info) -{ - if (info->transport_status != SMBD_CONNECTED) - return; - - info->send_immediate = true; - - /* - * Promptly send a packet if our peer is running low on receive - * credits - */ - if (atomic_read(&info->receive_credits) < - info->receive_credit_target - 1) - queue_delayed_work( - info->workqueue, &info->send_immediate_work, 0); -} - static void smbd_post_send_credits(struct work_struct *work) { int ret = 0; @@ -453,10 +429,16 @@ static void smbd_post_send_credits(struct work_struct *work) info->new_credits_offered += ret; spin_unlock(&info->lock_new_credits_offered); - atomic_add(ret, &info->receive_credits); - - /* Check if we can post new receive and grant credits to peer */ - check_and_send_immediate(info); + /* Promptly send an immediate packet as defined in [MS-SMBD] 3.1.1.1 */ + info->send_immediate = true; + if (atomic_read(&info->receive_credits) < + info->receive_credit_target - 1) { + if (info->keep_alive_requested == KEEP_ALIVE_PENDING || + info->send_immediate) { + log_keep_alive(INFO, "send an empty message\n"); + smbd_post_send_empty(info); + } + } } /* Called from softirq, when recv is done */ @@ -551,12 +533,6 @@ static void recv_done(struct ib_cq *cq, struct ib_wc *wc) info->keep_alive_requested = KEEP_ALIVE_PENDING; } - /* - * Check if we need to send something to remote peer to - * grant more credits or respond to KEEP_ALIVE packet - */ - check_and_send_immediate(info); - return; default: @@ -749,7 +725,6 @@ static int smbd_post_send_negotiate_req(struct smbd_connection *info) request->sge[0].addr, request->sge[0].length, request->sge[0].lkey); - request->has_payload = false; atomic_inc(&info->send_pending); rc = ib_post_send(info->id->qp, &send_wr, NULL); if (!rc) @@ -806,45 +781,96 @@ static int manage_keep_alive_before_sending(struct smbd_connection *info) return 0; } -/* - * Build and prepare the SMBD packet header - * This function waits for avaialbe send credits and build a SMBD packet - * header. The caller then optional append payload to the packet after - * the header - * intput values - * size: the size of the payload - * remaining_data_length: remaining data to send if this is part of a - * fragmented packet - * output values - * request_out: the request allocated from this function - * return values: 0 on success, otherwise actual error code returned - */ -static int smbd_create_header(struct smbd_connection *info, - int size, int remaining_data_length, - struct smbd_request **request_out) +/* Post the send request */ +static int smbd_post_send(struct smbd_connection *info, + struct smbd_request *request) +{ + struct ib_send_wr send_wr; + int rc, i; + + for (i = 0; i < request->num_sge; i++) { + log_rdma_send(INFO, + "rdma_request sge[%d] addr=%llu length=%u\n", + i, request->sge[i].addr, request->sge[i].length); + ib_dma_sync_single_for_device( + info->id->device, + request->sge[i].addr, + request->sge[i].length, + DMA_TO_DEVICE); + } + + request->cqe.done = send_done; + + send_wr.next = NULL; + send_wr.wr_cqe = &request->cqe; + send_wr.sg_list = request->sge; + send_wr.num_sge = request->num_sge; + send_wr.opcode = IB_WR_SEND; + send_wr.send_flags = IB_SEND_SIGNALED; + + rc = ib_post_send(info->id->qp, &send_wr, NULL); + if (rc) { + log_rdma_send(ERR, "ib_post_send failed rc=%d\n", rc); + smbd_disconnect_rdma_connection(info); + rc = -EAGAIN; + } else + /* Reset timer for idle connection after packet is sent */ + mod_delayed_work(info->workqueue, &info->idle_timer_work, + info->keep_alive_interval*HZ); + + return rc; +} + +static int smbd_post_send_sgl(struct smbd_connection *info, + struct scatterlist *sgl, int data_length, int remaining_data_length) { + int num_sgs; + int i, rc; + int header_length; struct smbd_request *request; struct smbd_data_transfer *packet; - int header_length; - int rc; + int new_credits; + struct scatterlist *sg; +wait_credit: /* Wait for send credits. A SMBD packet needs one credit */ rc = wait_event_interruptible(info->wait_send_queue, atomic_read(&info->send_credits) > 0 || info->transport_status != SMBD_CONNECTED); if (rc) - return rc; + goto err_wait_credit; + + if (info->transport_status != SMBD_CONNECTED) { + log_outgoing(ERR, "disconnected not sending on wait_credit\n"); + rc = -EAGAIN; + goto err_wait_credit; + } + if (unlikely(atomic_dec_return(&info->send_credits) < 0)) { + atomic_inc(&info->send_credits); + goto wait_credit; + } + +wait_send_queue: + wait_event(info->wait_post_send, + atomic_read(&info->send_pending) < info->send_credit_target || + info->transport_status != SMBD_CONNECTED); if (info->transport_status != SMBD_CONNECTED) { - log_outgoing(ERR, "disconnected not sending\n"); - return -EAGAIN; + log_outgoing(ERR, "disconnected not sending on wait_send_queue\n"); + rc = -EAGAIN; + goto err_wait_send_queue; + } + + if (unlikely(atomic_inc_return(&info->send_pending) > + info->send_credit_target)) { + atomic_dec(&info->send_pending); + goto wait_send_queue; } - atomic_dec(&info->send_credits); request = mempool_alloc(info->request_mempool, GFP_KERNEL); if (!request) { rc = -ENOMEM; - goto err; + goto err_alloc; } request->info = info; @@ -852,8 +878,11 @@ static int smbd_create_header(struct smbd_connection *info, /* Fill in the packet header */ packet = smbd_request_payload(request); packet->credits_requested = cpu_to_le16(info->send_credit_target); - packet->credits_granted = - cpu_to_le16(manage_credits_prior_sending(info)); + + new_credits = manage_credits_prior_sending(info); + atomic_add(new_credits, &info->receive_credits); + packet->credits_granted = cpu_to_le16(new_credits); + info->send_immediate = false; packet->flags = 0; @@ -861,11 +890,11 @@ static int smbd_create_header(struct smbd_connection *info, packet->flags |= cpu_to_le16(SMB_DIRECT_RESPONSE_REQUESTED); packet->reserved = 0; - if (!size) + if (!data_length) packet->data_offset = 0; else packet->data_offset = cpu_to_le32(24); - packet->data_length = cpu_to_le32(size); + packet->data_length = cpu_to_le32(data_length); packet->remaining_data_length = cpu_to_le32(remaining_data_length); packet->padding = 0; @@ -880,7 +909,7 @@ static int smbd_create_header(struct smbd_connection *info, /* Map the packet to DMA */ header_length = sizeof(struct smbd_data_transfer); /* If this is a packet without payload, don't send padding */ - if (!size) + if (!data_length) header_length = offsetof(struct smbd_data_transfer, padding); request->num_sge = 1; @@ -889,102 +918,15 @@ static int smbd_create_header(struct smbd_connection *info, header_length, DMA_TO_DEVICE); if (ib_dma_mapping_error(info->id->device, request->sge[0].addr)) { - mempool_free(request, info->request_mempool); rc = -EIO; - goto err; + request->sge[0].addr = 0; + goto err_dma; } request->sge[0].length = header_length; request->sge[0].lkey = info->pd->local_dma_lkey; - *request_out = request; - return 0; - -err: - atomic_inc(&info->send_credits); - return rc; -} - -static void smbd_destroy_header(struct smbd_connection *info, - struct smbd_request *request) -{ - - ib_dma_unmap_single(info->id->device, - request->sge[0].addr, - request->sge[0].length, - DMA_TO_DEVICE); - mempool_free(request, info->request_mempool); - atomic_inc(&info->send_credits); -} - -/* Post the send request */ -static int smbd_post_send(struct smbd_connection *info, - struct smbd_request *request, bool has_payload) -{ - struct ib_send_wr send_wr; - int rc, i; - - for (i = 0; i < request->num_sge; i++) { - log_rdma_send(INFO, - "rdma_request sge[%d] addr=%llu length=%u\n", - i, request->sge[i].addr, request->sge[i].length); - ib_dma_sync_single_for_device( - info->id->device, - request->sge[i].addr, - request->sge[i].length, - DMA_TO_DEVICE); - } - - request->cqe.done = send_done; - - send_wr.next = NULL; - send_wr.wr_cqe = &request->cqe; - send_wr.sg_list = request->sge; - send_wr.num_sge = request->num_sge; - send_wr.opcode = IB_WR_SEND; - send_wr.send_flags = IB_SEND_SIGNALED; - - if (has_payload) { - request->has_payload = true; - atomic_inc(&info->send_payload_pending); - } else { - request->has_payload = false; - atomic_inc(&info->send_pending); - } - - rc = ib_post_send(info->id->qp, &send_wr, NULL); - if (rc) { - log_rdma_send(ERR, "ib_post_send failed rc=%d\n", rc); - if (has_payload) { - if (atomic_dec_and_test(&info->send_payload_pending)) - wake_up(&info->wait_send_payload_pending); - } else { - if (atomic_dec_and_test(&info->send_pending)) - wake_up(&info->wait_send_pending); - } - smbd_disconnect_rdma_connection(info); - rc = -EAGAIN; - } else - /* Reset timer for idle connection after packet is sent */ - mod_delayed_work(info->workqueue, &info->idle_timer_work, - info->keep_alive_interval*HZ); - - return rc; -} - -static int smbd_post_send_sgl(struct smbd_connection *info, - struct scatterlist *sgl, int data_length, int remaining_data_length) -{ - int num_sgs; - int i, rc; - struct smbd_request *request; - struct scatterlist *sg; - - rc = smbd_create_header( - info, data_length, remaining_data_length, &request); - if (rc) - return rc; - + /* Fill in the packet data payload */ num_sgs = sgl ? sg_nents(sgl) : 0; for_each_sg(sgl, sg, num_sgs, i) { request->sge[i+1].addr = @@ -994,25 +936,41 @@ static int smbd_post_send_sgl(struct smbd_connection *info, info->id->device, request->sge[i+1].addr)) { rc = -EIO; request->sge[i+1].addr = 0; - goto dma_mapping_failure; + goto err_dma; } request->sge[i+1].length = sg->length; request->sge[i+1].lkey = info->pd->local_dma_lkey; request->num_sge++; } - rc = smbd_post_send(info, request, data_length); + rc = smbd_post_send(info, request); if (!rc) return 0; -dma_mapping_failure: - for (i = 1; i < request->num_sge; i++) +err_dma: + for (i = 0; i < request->num_sge; i++) if (request->sge[i].addr) ib_dma_unmap_single(info->id->device, request->sge[i].addr, request->sge[i].length, DMA_TO_DEVICE); - smbd_destroy_header(info, request); + mempool_free(request, info->request_mempool); + + /* roll back receive credits and credits to be offered */ + spin_lock(&info->lock_new_credits_offered); + info->new_credits_offered += new_credits; + spin_unlock(&info->lock_new_credits_offered); + atomic_sub(new_credits, &info->receive_credits); + +err_alloc: + if (atomic_dec_and_test(&info->send_pending)) + wake_up(&info->wait_send_pending); + +err_wait_send_queue: + /* roll back send credits and pending */ + atomic_inc(&info->send_credits); + +err_wait_credit: return rc; } @@ -1334,25 +1292,6 @@ static void destroy_receive_buffers(struct smbd_connection *info) mempool_free(response, info->response_mempool); } -/* - * Check and send an immediate or keep alive packet - * The condition to send those packets are defined in [MS-SMBD] 3.1.1.1 - * Connection.KeepaliveRequested and Connection.SendImmediate - * The idea is to extend credits to server as soon as it becomes available - */ -static void send_immediate_work(struct work_struct *work) -{ - struct smbd_connection *info = container_of( - work, struct smbd_connection, - send_immediate_work.work); - - if (info->keep_alive_requested == KEEP_ALIVE_PENDING || - info->send_immediate) { - log_keep_alive(INFO, "send an empty message\n"); - smbd_post_send_empty(info); - } -} - /* Implement idle connection timer [MS-SMBD] 3.1.6.2 */ static void idle_connection_timer(struct work_struct *work) { @@ -1407,14 +1346,10 @@ void smbd_destroy(struct TCP_Server_Info *server) log_rdma_event(INFO, "cancelling idle timer\n"); cancel_delayed_work_sync(&info->idle_timer_work); - log_rdma_event(INFO, "cancelling send immediate work\n"); - cancel_delayed_work_sync(&info->send_immediate_work); log_rdma_event(INFO, "wait for all send posted to IB to finish\n"); wait_event(info->wait_send_pending, atomic_read(&info->send_pending) == 0); - wait_event(info->wait_send_payload_pending, - atomic_read(&info->send_payload_pending) == 0); /* It's not posssible for upper layer to get to reassembly */ log_rdma_event(INFO, "drain the reassembly queue\n"); @@ -1744,15 +1679,13 @@ static struct smbd_connection *_smbd_get_connection( init_waitqueue_head(&info->wait_send_queue); INIT_DELAYED_WORK(&info->idle_timer_work, idle_connection_timer); - INIT_DELAYED_WORK(&info->send_immediate_work, send_immediate_work); queue_delayed_work(info->workqueue, &info->idle_timer_work, info->keep_alive_interval*HZ); init_waitqueue_head(&info->wait_send_pending); atomic_set(&info->send_pending, 0); - init_waitqueue_head(&info->wait_send_payload_pending); - atomic_set(&info->send_payload_pending, 0); + init_waitqueue_head(&info->wait_post_send); INIT_WORK(&info->disconnect_work, smbd_disconnect_rdma_work); INIT_WORK(&info->post_send_credits_work, smbd_post_send_credits); @@ -2226,8 +2159,8 @@ done: * that means all the I/Os have been out and we are good to return */ - wait_event(info->wait_send_payload_pending, - atomic_read(&info->send_payload_pending) == 0); + wait_event(info->wait_send_pending, + atomic_read(&info->send_pending) == 0); return rc; } diff --git a/fs/cifs/smbdirect.h b/fs/cifs/smbdirect.h index 8ede915f2b24..a87fca82a796 100644 --- a/fs/cifs/smbdirect.h +++ b/fs/cifs/smbdirect.h @@ -114,8 +114,7 @@ struct smbd_connection { /* Activity accoutning */ atomic_t send_pending; wait_queue_head_t wait_send_pending; - atomic_t send_payload_pending; - wait_queue_head_t wait_send_payload_pending; + wait_queue_head_t wait_post_send; /* Receive queue */ struct list_head receive_queue; @@ -154,7 +153,6 @@ struct smbd_connection { struct workqueue_struct *workqueue; struct delayed_work idle_timer_work; - struct delayed_work send_immediate_work; /* Memory pool for preallocating buffers */ /* request pool for RDMA send */ @@ -234,9 +232,6 @@ struct smbd_request { struct smbd_connection *info; struct ib_cqe cqe; - /* true if this request carries upper layer payload */ - bool has_payload; - /* the SGE entries for this packet */ struct ib_sge sge[SMBDIRECT_MAX_SGE]; int num_sge; diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c index 25f135572fc8..e7ddbce48321 100644 --- a/fs/nfs/pnfs_nfs.c +++ b/fs/nfs/pnfs_nfs.c @@ -501,6 +501,7 @@ pnfs_alloc_ds_commits_list(struct list_head *list, rcu_read_lock(); pnfs_put_commit_array(array, cinfo->inode); } + rcu_read_unlock(); return ret; } diff --git a/include/crypto/curve25519.h b/include/crypto/curve25519.h index 9ecb3c1f0f15..4e6dc840b159 100644 --- a/include/crypto/curve25519.h +++ b/include/crypto/curve25519.h @@ -33,8 +33,7 @@ bool __must_check curve25519(u8 mypublic[CURVE25519_KEY_SIZE], const u8 secret[CURVE25519_KEY_SIZE], const u8 basepoint[CURVE25519_KEY_SIZE]) { - if (IS_ENABLED(CONFIG_CRYPTO_ARCH_HAVE_LIB_CURVE25519) && - (!IS_ENABLED(CONFIG_CRYPTO_CURVE25519_X86) || IS_ENABLED(CONFIG_AS_ADX))) + if (IS_ENABLED(CONFIG_CRYPTO_ARCH_HAVE_LIB_CURVE25519)) curve25519_arch(mypublic, secret, basepoint); else curve25519_generic(mypublic, secret, basepoint); @@ -50,8 +49,7 @@ __must_check curve25519_generate_public(u8 pub[CURVE25519_KEY_SIZE], CURVE25519_KEY_SIZE))) return false; - if (IS_ENABLED(CONFIG_CRYPTO_ARCH_HAVE_LIB_CURVE25519) && - (!IS_ENABLED(CONFIG_CRYPTO_CURVE25519_X86) || IS_ENABLED(CONFIG_AS_ADX))) + if (IS_ENABLED(CONFIG_CRYPTO_ARCH_HAVE_LIB_CURVE25519)) curve25519_base_arch(pub, secret); else curve25519_generic(pub, secret, curve25519_base_point); diff --git a/include/linux/refcount.h b/include/linux/refcount.h index 0ac50cf62d06..0e3ee25eb156 100644 --- a/include/linux/refcount.h +++ b/include/linux/refcount.h @@ -38,11 +38,24 @@ * atomic operations, then the count will continue to edge closer to 0. If it * reaches a value of 1 before /any/ of the threads reset it to the saturated * value, then a concurrent refcount_dec_and_test() may erroneously free the - * underlying object. Given the precise timing details involved with the - * round-robin scheduling of each thread manipulating the refcount and the need - * to hit the race multiple times in succession, there doesn't appear to be a - * practical avenue of attack even if using refcount_add() operations with - * larger increments. + * underlying object. + * Linux limits the maximum number of tasks to PID_MAX_LIMIT, which is currently + * 0x400000 (and can't easily be raised in the future beyond FUTEX_TID_MASK). + * With the current PID limit, if no batched refcounting operations are used and + * the attacker can't repeatedly trigger kernel oopses in the middle of refcount + * operations, this makes it impossible for a saturated refcount to leave the + * saturation range, even if it is possible for multiple uses of the same + * refcount to nest in the context of a single task: + * + * (UINT_MAX+1-REFCOUNT_SATURATED) / PID_MAX_LIMIT = + * 0x40000000 / 0x400000 = 0x100 = 256 + * + * If hundreds of references are added/removed with a single refcounting + * operation, it may potentially be possible to leave the saturation range; but + * given the precise timing details involved with the round-robin scheduling of + * each thread manipulating the refcount and the need to hit the race multiple + * times in succession, there doesn't appear to be a practical avenue of attack + * even if using refcount_add() operations with larger increments. * * Memory ordering * =============== diff --git a/init/Makefile b/init/Makefile index 6246a06364d0..d45e967483b2 100644 --- a/init/Makefile +++ b/init/Makefile @@ -35,4 +35,4 @@ include/generated/compile.h: FORCE @$($(quiet)chk_compile.h) $(Q)$(CONFIG_SHELL) $(srctree)/scripts/mkcompile_h $@ \ "$(UTS_MACHINE)" "$(CONFIG_SMP)" "$(CONFIG_PREEMPT)" \ - "$(CONFIG_PREEMPT_RT)" "$(CC) $(KBUILD_CFLAGS)" + "$(CONFIG_PREEMPT_RT)" "$(CC)" "$(LD)" diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c index 2031ed1ad7fa..9e1777c81f55 100644 --- a/kernel/dma/debug.c +++ b/kernel/dma/debug.c @@ -137,9 +137,12 @@ static const char *const maperr2str[] = { [MAP_ERR_CHECKED] = "dma map error checked", }; -static const char *type2name[5] = { "single", "page", - "scather-gather", "coherent", - "resource" }; +static const char *type2name[] = { + [dma_debug_single] = "single", + [dma_debug_sg] = "scather-gather", + [dma_debug_coherent] = "coherent", + [dma_debug_resource] = "resource", +}; static const char *dir2name[4] = { "DMA_BIDIRECTIONAL", "DMA_TO_DEVICE", "DMA_FROM_DEVICE", "DMA_NONE" }; diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index a8560052a915..8f4bbdaf965e 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -39,7 +39,8 @@ static inline struct page *dma_direct_to_page(struct device *dev, u64 dma_direct_get_required_mask(struct device *dev) { - u64 max_dma = phys_to_dma_direct(dev, (max_pfn - 1) << PAGE_SHIFT); + phys_addr_t phys = (phys_addr_t)(max_pfn - 1) << PAGE_SHIFT; + u64 max_dma = phys_to_dma_direct(dev, phys); return (1ULL << (fls64(max_dma) - 1)) * 2 - 1; } diff --git a/kernel/events/core.c b/kernel/events/core.c index 55e44417f66d..bc9b98a9af9a 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -983,16 +983,10 @@ perf_cgroup_set_shadow_time(struct perf_event *event, u64 now) event->shadow_ctx_time = now - t->timestamp; } -/* - * Update cpuctx->cgrp so that it is set when first cgroup event is added and - * cleared when last cgroup event is removed. - */ static inline void -list_update_cgroup_event(struct perf_event *event, - struct perf_event_context *ctx, bool add) +perf_cgroup_event_enable(struct perf_event *event, struct perf_event_context *ctx) { struct perf_cpu_context *cpuctx; - struct list_head *cpuctx_entry; if (!is_cgroup_event(event)) return; @@ -1009,28 +1003,41 @@ list_update_cgroup_event(struct perf_event *event, * because if the first would mismatch, the second would not try again * and we would leave cpuctx->cgrp unset. */ - if (add && !cpuctx->cgrp) { + if (ctx->is_active && !cpuctx->cgrp) { struct perf_cgroup *cgrp = perf_cgroup_from_task(current, ctx); if (cgroup_is_descendant(cgrp->css.cgroup, event->cgrp->css.cgroup)) cpuctx->cgrp = cgrp; } - if (add && ctx->nr_cgroups++) + if (ctx->nr_cgroups++) return; - else if (!add && --ctx->nr_cgroups) + + list_add(&cpuctx->cgrp_cpuctx_entry, + per_cpu_ptr(&cgrp_cpuctx_list, event->cpu)); +} + +static inline void +perf_cgroup_event_disable(struct perf_event *event, struct perf_event_context *ctx) +{ + struct perf_cpu_context *cpuctx; + + if (!is_cgroup_event(event)) + return; + + /* + * Because cgroup events are always per-cpu events, + * @ctx == &cpuctx->ctx. + */ + cpuctx = container_of(ctx, struct perf_cpu_context, ctx); + + if (--ctx->nr_cgroups) return; - /* no cgroup running */ - if (!add) + if (ctx->is_active && cpuctx->cgrp) cpuctx->cgrp = NULL; - cpuctx_entry = &cpuctx->cgrp_cpuctx_entry; - if (add) - list_add(cpuctx_entry, - per_cpu_ptr(&cgrp_cpuctx_list, event->cpu)); - else - list_del(cpuctx_entry); + list_del(&cpuctx->cgrp_cpuctx_entry); } #else /* !CONFIG_CGROUP_PERF */ @@ -1096,11 +1103,14 @@ static inline u64 perf_cgroup_event_time(struct perf_event *event) } static inline void -list_update_cgroup_event(struct perf_event *event, - struct perf_event_context *ctx, bool add) +perf_cgroup_event_enable(struct perf_event *event, struct perf_event_context *ctx) { } +static inline void +perf_cgroup_event_disable(struct perf_event *event, struct perf_event_context *ctx) +{ +} #endif /* @@ -1791,13 +1801,14 @@ list_add_event(struct perf_event *event, struct perf_event_context *ctx) add_event_to_groups(event, ctx); } - list_update_cgroup_event(event, ctx, true); - list_add_rcu(&event->event_entry, &ctx->event_list); ctx->nr_events++; if (event->attr.inherit_stat) ctx->nr_stat++; + if (event->state > PERF_EVENT_STATE_OFF) + perf_cgroup_event_enable(event, ctx); + ctx->generation++; } @@ -1976,8 +1987,6 @@ list_del_event(struct perf_event *event, struct perf_event_context *ctx) event->attach_state &= ~PERF_ATTACH_CONTEXT; - list_update_cgroup_event(event, ctx, false); - ctx->nr_events--; if (event->attr.inherit_stat) ctx->nr_stat--; @@ -1994,8 +2003,10 @@ list_del_event(struct perf_event *event, struct perf_event_context *ctx) * of error state is by explicit re-enabling * of the event */ - if (event->state > PERF_EVENT_STATE_OFF) + if (event->state > PERF_EVENT_STATE_OFF) { + perf_cgroup_event_disable(event, ctx); perf_event_set_state(event, PERF_EVENT_STATE_OFF); + } ctx->generation++; } @@ -2226,6 +2237,7 @@ event_sched_out(struct perf_event *event, if (READ_ONCE(event->pending_disable) >= 0) { WRITE_ONCE(event->pending_disable, -1); + perf_cgroup_event_disable(event, ctx); state = PERF_EVENT_STATE_OFF; } perf_event_set_state(event, state); @@ -2363,6 +2375,7 @@ static void __perf_event_disable(struct perf_event *event, event_sched_out(event, cpuctx, ctx); perf_event_set_state(event, PERF_EVENT_STATE_OFF); + perf_cgroup_event_disable(event, ctx); } /* @@ -2746,7 +2759,7 @@ static int __perf_install_in_context(void *info) } #ifdef CONFIG_CGROUP_PERF - if (is_cgroup_event(event)) { + if (event->state > PERF_EVENT_STATE_OFF && is_cgroup_event(event)) { /* * If the current cgroup doesn't match the event's * cgroup, we should not try to schedule it. @@ -2906,6 +2919,7 @@ static void __perf_event_enable(struct perf_event *event, ctx_sched_out(ctx, cpuctx, EVENT_TIME); perf_event_set_state(event, PERF_EVENT_STATE_INACTIVE); + perf_cgroup_event_enable(event, ctx); if (!ctx->is_active) return; @@ -3508,7 +3522,8 @@ static void cpu_ctx_sched_out(struct perf_cpu_context *cpuctx, static bool perf_less_group_idx(const void *l, const void *r) { - const struct perf_event *le = l, *re = r; + const struct perf_event *le = *(const struct perf_event **)l; + const struct perf_event *re = *(const struct perf_event **)r; return le->group_index < re->group_index; } @@ -3616,8 +3631,10 @@ static int merge_sched_in(struct perf_event *event, void *data) } if (event->state == PERF_EVENT_STATE_INACTIVE) { - if (event->attr.pinned) + if (event->attr.pinned) { + perf_cgroup_event_disable(event, ctx); perf_event_set_state(event, PERF_EVENT_STATE_ERROR); + } *can_add_hw = 0; ctx->rotate_necessary = 1; @@ -6917,9 +6934,12 @@ static u64 perf_virt_to_phys(u64 virt) * Try IRQ-safe __get_user_pages_fast first. * If failed, leave phys_addr as 0. */ - if ((current->mm != NULL) && - (__get_user_pages_fast(virt, 1, 0, &p) == 1)) - phys_addr = page_to_phys(p) + virt % PAGE_SIZE; + if (current->mm != NULL) { + pagefault_disable(); + if (__get_user_pages_fast(virt, 1, 0, &p) == 1) + phys_addr = page_to_phys(p) + virt % PAGE_SIZE; + pagefault_enable(); + } if (p) put_page(p); diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 1511690e4de7..ac10db66cc63 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -3952,10 +3952,36 @@ static int mark_lock(struct task_struct *curr, struct held_lock *this, return ret; } +static inline short task_wait_context(struct task_struct *curr) +{ + /* + * Set appropriate wait type for the context; for IRQs we have to take + * into account force_irqthread as that is implied by PREEMPT_RT. + */ + if (curr->hardirq_context) { + /* + * Check if force_irqthreads will run us threaded. + */ + if (curr->hardirq_threaded || curr->irq_config) + return LD_WAIT_CONFIG; + + return LD_WAIT_SPIN; + } else if (curr->softirq_context) { + /* + * Softirqs are always threaded. + */ + return LD_WAIT_CONFIG; + } + + return LD_WAIT_MAX; +} + static int print_lock_invalid_wait_context(struct task_struct *curr, struct held_lock *hlock) { + short curr_inner; + if (!debug_locks_off()) return 0; if (debug_locks_silent) @@ -3971,6 +3997,10 @@ print_lock_invalid_wait_context(struct task_struct *curr, print_lock(hlock); pr_warn("other info that might help us debug this:\n"); + + curr_inner = task_wait_context(curr); + pr_warn("context-{%d:%d}\n", curr_inner, curr_inner); + lockdep_print_held_locks(curr); pr_warn("stack backtrace:\n"); @@ -4017,26 +4047,7 @@ static int check_wait_context(struct task_struct *curr, struct held_lock *next) } depth++; - /* - * Set appropriate wait type for the context; for IRQs we have to take - * into account force_irqthread as that is implied by PREEMPT_RT. - */ - if (curr->hardirq_context) { - /* - * Check if force_irqthreads will run us threaded. - */ - if (curr->hardirq_threaded || curr->irq_config) - curr_inner = LD_WAIT_CONFIG; - else - curr_inner = LD_WAIT_SPIN; - } else if (curr->softirq_context) { - /* - * Softirqs are always threaded. - */ - curr_inner = LD_WAIT_CONFIG; - } else { - curr_inner = LD_WAIT_MAX; - } + curr_inner = task_wait_context(curr); for (; depth < curr->lockdep_depth; depth++) { struct held_lock *prev = curr->held_locks + depth; diff --git a/kernel/locking/percpu-rwsem.c b/kernel/locking/percpu-rwsem.c index a008a1ba21a7..8bbafe3e5203 100644 --- a/kernel/locking/percpu-rwsem.c +++ b/kernel/locking/percpu-rwsem.c @@ -118,14 +118,15 @@ static int percpu_rwsem_wake_function(struct wait_queue_entry *wq_entry, unsigned int mode, int wake_flags, void *key) { - struct task_struct *p = get_task_struct(wq_entry->private); bool reader = wq_entry->flags & WQ_FLAG_CUSTOM; struct percpu_rw_semaphore *sem = key; + struct task_struct *p; /* concurrent against percpu_down_write(), can get stolen */ if (!__percpu_rwsem_trylock(sem, reader)) return 1; + p = get_task_struct(wq_entry->private); list_del_init(&wq_entry->entry); smp_store_release(&wq_entry->private, NULL); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index a2694ba82874..3a61a3b8eaa9 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -2119,12 +2119,6 @@ int select_task_rq(struct task_struct *p, int cpu, int sd_flags, int wake_flags) return cpu; } -static void update_avg(u64 *avg, u64 sample) -{ - s64 diff = sample - *avg; - *avg += diff >> 3; -} - void sched_set_stop_task(int cpu, struct task_struct *stop) { struct sched_param param = { .sched_priority = MAX_RT_PRIO - 1 }; @@ -4126,7 +4120,8 @@ static inline void sched_submit_work(struct task_struct *tsk) * it wants to wake up a task to maintain concurrency. * As this function is called inside the schedule() context, * we disable preemption to avoid it calling schedule() again - * in the possible wakeup of a kworker. + * in the possible wakeup of a kworker and because wq_worker_sleeping() + * requires it. */ if (tsk->flags & (PF_WQ_WORKER | PF_IO_WORKER)) { preempt_disable(); @@ -6699,7 +6694,6 @@ void __init sched_init(void) rq_attach_root(rq, &def_root_domain); #ifdef CONFIG_NO_HZ_COMMON - rq->last_load_update_tick = jiffies; rq->last_blocked_load_update_tick = jiffies; atomic_set(&rq->nohz_flags, 0); #endif diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 8331bc04aea2..a562df57a86e 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -816,10 +816,12 @@ static int __init init_sched_debug_procfs(void) __initcall(init_sched_debug_procfs); -#define __P(F) SEQ_printf(m, "%-45s:%21Ld\n", #F, (long long)F) -#define P(F) SEQ_printf(m, "%-45s:%21Ld\n", #F, (long long)p->F) -#define __PN(F) SEQ_printf(m, "%-45s:%14Ld.%06ld\n", #F, SPLIT_NS((long long)F)) -#define PN(F) SEQ_printf(m, "%-45s:%14Ld.%06ld\n", #F, SPLIT_NS((long long)p->F)) +#define __PS(S, F) SEQ_printf(m, "%-45s:%21Ld\n", S, (long long)(F)) +#define __P(F) __PS(#F, F) +#define P(F) __PS(#F, p->F) +#define __PSN(S, F) SEQ_printf(m, "%-45s:%14Ld.%06ld\n", S, SPLIT_NS((long long)(F))) +#define __PN(F) __PSN(#F, F) +#define PN(F) __PSN(#F, p->F) #ifdef CONFIG_NUMA_BALANCING @@ -868,18 +870,9 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns, SEQ_printf(m, "---------------------------------------------------------" "----------\n"); -#define __P(F) \ - SEQ_printf(m, "%-45s:%21Ld\n", #F, (long long)F) -#define P(F) \ - SEQ_printf(m, "%-45s:%21Ld\n", #F, (long long)p->F) -#define P_SCHEDSTAT(F) \ - SEQ_printf(m, "%-45s:%21Ld\n", #F, (long long)schedstat_val(p->F)) -#define __PN(F) \ - SEQ_printf(m, "%-45s:%14Ld.%06ld\n", #F, SPLIT_NS((long long)F)) -#define PN(F) \ - SEQ_printf(m, "%-45s:%14Ld.%06ld\n", #F, SPLIT_NS((long long)p->F)) -#define PN_SCHEDSTAT(F) \ - SEQ_printf(m, "%-45s:%14Ld.%06ld\n", #F, SPLIT_NS((long long)schedstat_val(p->F))) + +#define P_SCHEDSTAT(F) __PS(#F, schedstat_val(p->F)) +#define PN_SCHEDSTAT(F) __PSN(#F, schedstat_val(p->F)) PN(se.exec_start); PN(se.vruntime); @@ -939,10 +932,8 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns, } __P(nr_switches); - SEQ_printf(m, "%-45s:%21Ld\n", - "nr_voluntary_switches", (long long)p->nvcsw); - SEQ_printf(m, "%-45s:%21Ld\n", - "nr_involuntary_switches", (long long)p->nivcsw); + __PS("nr_voluntary_switches", p->nvcsw); + __PS("nr_involuntary_switches", p->nivcsw); P(se.load.weight); #ifdef CONFIG_SMP @@ -956,6 +947,12 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns, P(se.avg.util_est.ewma); P(se.avg.util_est.enqueued); #endif +#ifdef CONFIG_UCLAMP_TASK + __PS("uclamp.min", p->uclamp[UCLAMP_MIN].value); + __PS("uclamp.max", p->uclamp[UCLAMP_MAX].value); + __PS("effective uclamp.min", uclamp_eff_value(p, UCLAMP_MIN)); + __PS("effective uclamp.max", uclamp_eff_value(p, UCLAMP_MAX)); +#endif P(policy); P(prio); if (task_has_dl_policy(p)) { @@ -963,11 +960,7 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns, P(dl.deadline); } #undef PN_SCHEDSTAT -#undef PN -#undef __PN #undef P_SCHEDSTAT -#undef P -#undef __P { unsigned int this_cpu = raw_smp_processor_id(); @@ -975,8 +968,7 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns, t0 = cpu_clock(this_cpu); t1 = cpu_clock(this_cpu); - SEQ_printf(m, "%-45s:%21Ld\n", - "clock-delta", (long long)(t1-t0)); + __PS("clock-delta", t1-t0); } sched_show_numa(p, m); diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 1ea3dddafe69..02f323b85b6d 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -4836,11 +4836,10 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq) resched_curr(rq); } -static u64 distribute_cfs_runtime(struct cfs_bandwidth *cfs_b, u64 remaining) +static void distribute_cfs_runtime(struct cfs_bandwidth *cfs_b) { struct cfs_rq *cfs_rq; - u64 runtime; - u64 starting_runtime = remaining; + u64 runtime, remaining = 1; rcu_read_lock(); list_for_each_entry_rcu(cfs_rq, &cfs_b->throttled_cfs_rq, @@ -4855,10 +4854,13 @@ static u64 distribute_cfs_runtime(struct cfs_bandwidth *cfs_b, u64 remaining) /* By the above check, this should never be true */ SCHED_WARN_ON(cfs_rq->runtime_remaining > 0); + raw_spin_lock(&cfs_b->lock); runtime = -cfs_rq->runtime_remaining + 1; - if (runtime > remaining) - runtime = remaining; - remaining -= runtime; + if (runtime > cfs_b->runtime) + runtime = cfs_b->runtime; + cfs_b->runtime -= runtime; + remaining = cfs_b->runtime; + raw_spin_unlock(&cfs_b->lock); cfs_rq->runtime_remaining += runtime; @@ -4873,8 +4875,6 @@ next: break; } rcu_read_unlock(); - - return starting_runtime - remaining; } /* @@ -4885,7 +4885,6 @@ next: */ static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun, unsigned long flags) { - u64 runtime; int throttled; /* no need to continue the timer with no bandwidth constraint */ @@ -4914,24 +4913,17 @@ static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun, u cfs_b->nr_throttled += overrun; /* - * This check is repeated as we are holding onto the new bandwidth while - * we unthrottle. This can potentially race with an unthrottled group - * trying to acquire new bandwidth from the global pool. This can result - * in us over-using our runtime if it is all used during this loop, but - * only by limited amounts in that extreme case. + * This check is repeated as we release cfs_b->lock while we unthrottle. */ while (throttled && cfs_b->runtime > 0 && !cfs_b->distribute_running) { - runtime = cfs_b->runtime; cfs_b->distribute_running = 1; raw_spin_unlock_irqrestore(&cfs_b->lock, flags); /* we can't nest cfs_b->lock while distributing bandwidth */ - runtime = distribute_cfs_runtime(cfs_b, runtime); + distribute_cfs_runtime(cfs_b); raw_spin_lock_irqsave(&cfs_b->lock, flags); cfs_b->distribute_running = 0; throttled = !list_empty(&cfs_b->throttled_cfs_rq); - - lsub_positive(&cfs_b->runtime, runtime); } /* @@ -5065,10 +5057,9 @@ static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b) if (!runtime) return; - runtime = distribute_cfs_runtime(cfs_b, runtime); + distribute_cfs_runtime(cfs_b); raw_spin_lock_irqsave(&cfs_b->lock, flags); - lsub_positive(&cfs_b->runtime, runtime); cfs_b->distribute_running = 0; raw_spin_unlock_irqrestore(&cfs_b->lock, flags); } @@ -6080,8 +6071,7 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t struct cpumask *cpus = this_cpu_cpumask_var_ptr(select_idle_mask); struct sched_domain *this_sd; u64 avg_cost, avg_idle; - u64 time, cost; - s64 delta; + u64 time; int this = smp_processor_id(); int cpu, nr = INT_MAX; @@ -6119,9 +6109,7 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t } time = cpu_clock(this) - time; - cost = this_sd->avg_scan_cost; - delta = (s64)(time - cost) / 8; - this_sd->avg_scan_cost += delta; + update_avg(&this_sd->avg_scan_cost, time); return cpu; } @@ -9048,6 +9036,14 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s sds->avg_load = (sds->total_load * SCHED_CAPACITY_SCALE) / sds->total_capacity; + /* + * If the local group is more loaded than the selected + * busiest group don't try to pull any tasks. + */ + if (local->avg_load >= busiest->avg_load) { + env->imbalance = 0; + return; + } } /* diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 0f616bf7bce3..db3a57675ccf 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -195,6 +195,12 @@ static inline int task_has_dl_policy(struct task_struct *p) #define cap_scale(v, s) ((v)*(s) >> SCHED_CAPACITY_SHIFT) +static inline void update_avg(u64 *avg, u64 sample) +{ + s64 diff = sample - *avg; + *avg += diff / 8; +} + /* * !! For sched_setattr_nocheck() (kernel) only !! * @@ -882,7 +888,6 @@ struct rq { #endif #ifdef CONFIG_NO_HZ_COMMON #ifdef CONFIG_SMP - unsigned long last_load_update_tick; unsigned long last_blocked_load_update_tick; unsigned int has_blocked_load; #endif /* CONFIG_SMP */ diff --git a/kernel/time/namespace.c b/kernel/time/namespace.c index e6ba064ce773..3b30288793fe 100644 --- a/kernel/time/namespace.c +++ b/kernel/time/namespace.c @@ -447,6 +447,7 @@ const struct proc_ns_operations timens_operations = { const struct proc_ns_operations timens_for_children_operations = { .name = "time_for_children", + .real_ns_name = "time", .type = CLONE_NEWTIME, .get = timens_for_children_get, .put = timens_put, diff --git a/kernel/ucount.c b/kernel/ucount.c index a53cc2b4179c..11b1596e2542 100644 --- a/kernel/ucount.c +++ b/kernel/ucount.c @@ -69,6 +69,7 @@ static struct ctl_table user_table[] = { UCOUNT_ENTRY("max_net_namespaces"), UCOUNT_ENTRY("max_mnt_namespaces"), UCOUNT_ENTRY("max_cgroup_namespaces"), + UCOUNT_ENTRY("max_time_namespaces"), #ifdef CONFIG_INOTIFY_USER UCOUNT_ENTRY("max_inotify_instances"), UCOUNT_ENTRY("max_inotify_watches"), @@ -81,6 +82,8 @@ bool setup_userns_sysctls(struct user_namespace *ns) { #ifdef CONFIG_SYSCTL struct ctl_table *tbl; + + BUILD_BUG_ON(ARRAY_SIZE(user_table) != UCOUNT_COUNTS + 1); setup_sysctl_set(&ns->set, &set_root, set_is_seen); tbl = kmemdup(user_table, sizeof(user_table), GFP_KERNEL); if (tbl) { diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 3816a18c251e..891ccad5f271 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -858,7 +858,8 @@ void wq_worker_running(struct task_struct *task) * @task: task going to sleep * * This function is called from schedule() when a busy worker is - * going to sleep. + * going to sleep. Preemption needs to be disabled to protect ->sleeping + * assignment. */ void wq_worker_sleeping(struct task_struct *task) { @@ -875,7 +876,8 @@ void wq_worker_sleeping(struct task_struct *task) pool = worker->pool; - if (WARN_ON_ONCE(worker->sleeping)) + /* Return if preempted before wq_worker_running() was reached */ + if (worker->sleeping) return; worker->sleeping = 1; diff --git a/lib/raid6/algos.c b/lib/raid6/algos.c index bf1b4765c8f6..6d5e5000fdd7 100644 --- a/lib/raid6/algos.c +++ b/lib/raid6/algos.c @@ -34,10 +34,8 @@ const struct raid6_calls * const raid6_algos[] = { &raid6_avx512x2, &raid6_avx512x1, #endif -#ifdef CONFIG_AS_AVX2 &raid6_avx2x2, &raid6_avx2x1, -#endif &raid6_sse2x2, &raid6_sse2x1, &raid6_sse1x2, @@ -51,11 +49,9 @@ const struct raid6_calls * const raid6_algos[] = { &raid6_avx512x2, &raid6_avx512x1, #endif -#ifdef CONFIG_AS_AVX2 &raid6_avx2x4, &raid6_avx2x2, &raid6_avx2x1, -#endif &raid6_sse2x4, &raid6_sse2x2, &raid6_sse2x1, @@ -97,13 +93,11 @@ void (*raid6_datap_recov)(int, size_t, int, void **); EXPORT_SYMBOL_GPL(raid6_datap_recov); const struct raid6_recov_calls *const raid6_recov_algos[] = { +#ifdef CONFIG_X86 #ifdef CONFIG_AS_AVX512 &raid6_recov_avx512, #endif -#ifdef CONFIG_AS_AVX2 &raid6_recov_avx2, -#endif -#ifdef CONFIG_AS_SSSE3 &raid6_recov_ssse3, #endif #ifdef CONFIG_S390 diff --git a/lib/raid6/avx2.c b/lib/raid6/avx2.c index 87184b6da28a..f299476e1d76 100644 --- a/lib/raid6/avx2.c +++ b/lib/raid6/avx2.c @@ -13,8 +13,6 @@ * */ -#ifdef CONFIG_AS_AVX2 - #include <linux/raid/pq.h> #include "x86.h" @@ -470,5 +468,3 @@ const struct raid6_calls raid6_avx2x4 = { 1 /* Has cache hints */ }; #endif - -#endif /* CONFIG_AS_AVX2 */ diff --git a/lib/raid6/recov_avx2.c b/lib/raid6/recov_avx2.c index 7a3b5e7f66ee..4e8095403ee2 100644 --- a/lib/raid6/recov_avx2.c +++ b/lib/raid6/recov_avx2.c @@ -4,8 +4,6 @@ * Author: Jim Kukunas <james.t.kukunas@linux.intel.com> */ -#ifdef CONFIG_AS_AVX2 - #include <linux/raid/pq.h> #include "x86.h" @@ -313,7 +311,3 @@ const struct raid6_recov_calls raid6_recov_avx2 = { #endif .priority = 2, }; - -#else -#warning "your version of binutils lacks AVX2 support" -#endif diff --git a/lib/raid6/recov_ssse3.c b/lib/raid6/recov_ssse3.c index 1de97d2405d0..4bfa3c6b60de 100644 --- a/lib/raid6/recov_ssse3.c +++ b/lib/raid6/recov_ssse3.c @@ -3,8 +3,6 @@ * Copyright (C) 2012 Intel Corporation */ -#ifdef CONFIG_AS_SSSE3 - #include <linux/raid/pq.h> #include "x86.h" @@ -328,7 +326,3 @@ const struct raid6_recov_calls raid6_recov_ssse3 = { #endif .priority = 1, }; - -#else -#warning "your version of binutils lacks SSSE3 support" -#endif diff --git a/lib/raid6/test/Makefile b/lib/raid6/test/Makefile index 3ab8720aa2f8..a4c7cd74cff5 100644 --- a/lib/raid6/test/Makefile +++ b/lib/raid6/test/Makefile @@ -34,14 +34,9 @@ endif ifeq ($(IS_X86),yes) OBJS += mmx.o sse1.o sse2.o avx2.o recov_ssse3.o recov_avx2.o avx512.o recov_avx512.o - CFLAGS += $(shell echo "pshufb %xmm0, %xmm0" | \ - gcc -c -x assembler - >&/dev/null && \ - rm ./-.o && echo -DCONFIG_AS_SSSE3=1) - CFLAGS += $(shell echo "vpbroadcastb %xmm0, %ymm1" | \ - gcc -c -x assembler - >&/dev/null && \ - rm ./-.o && echo -DCONFIG_AS_AVX2=1) + CFLAGS += -DCONFIG_X86 CFLAGS += $(shell echo "vpmovm2b %k1, %zmm5" | \ - gcc -c -x assembler - >&/dev/null && \ + gcc -c -x assembler - >/dev/null 2>&1 && \ rm ./-.o && echo -DCONFIG_AS_AVX512=1) else ifeq ($(HAS_NEON),yes) OBJS += neon.o neon1.o neon2.o neon4.o neon8.o recov_neon.o recov_neon_inner.o diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index 292e71dc7ba4..0e0ded87e27b 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -83,7 +83,7 @@ nf_tables-objs := nf_tables_core.o nf_tables_api.o nft_chain_filter.o \ nft_set_pipapo.o ifdef CONFIG_X86_64 -ifneq (,$(findstring -DCONFIG_AS_AVX2=1,$(KBUILD_CFLAGS))) +ifndef CONFIG_UML nf_tables-objs += nft_set_pipapo_avx2.o endif endif diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index d0ab5ffa1e2c..4471393da6d8 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -3291,7 +3291,7 @@ static const struct nft_set_type *nft_set_types[] = { &nft_set_rhash_type, &nft_set_bitmap_type, &nft_set_rbtree_type, -#if defined(CONFIG_X86_64) && defined(CONFIG_AS_AVX2) +#if defined(CONFIG_X86_64) && !defined(CONFIG_UML) &nft_set_pipapo_avx2_type, #endif &nft_set_pipapo_type, diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index 87aabf651cfe..8b5acc6910fd 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -2201,7 +2201,7 @@ const struct nft_set_type nft_set_pipapo_type = { }, }; -#if defined(CONFIG_X86_64) && defined(CONFIG_AS_AVX2) +#if defined(CONFIG_X86_64) && !defined(CONFIG_UML) const struct nft_set_type nft_set_pipapo_avx2_type = { .features = NFT_SET_INTERVAL | NFT_SET_MAP | NFT_SET_OBJECT | NFT_SET_TIMEOUT, diff --git a/net/netfilter/nft_set_pipapo_avx2.h b/net/netfilter/nft_set_pipapo_avx2.h index 396caf7bfca8..394bcb704db7 100644 --- a/net/netfilter/nft_set_pipapo_avx2.h +++ b/net/netfilter/nft_set_pipapo_avx2.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0-only */ #ifndef _NFT_SET_PIPAPO_AVX2_H -#ifdef CONFIG_AS_AVX2 +#if defined(CONFIG_X86_64) && !defined(CONFIG_UML) #include <asm/fpu/xstate.h> #define NFT_PIPAPO_ALIGN (XSAVE_YMM_SIZE / BITS_PER_BYTE) @@ -9,6 +9,6 @@ bool nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set, const u32 *key, const struct nft_set_ext **ext); bool nft_pipapo_avx2_estimate(const struct nft_set_desc *desc, u32 features, struct nft_set_estimate *est); -#endif /* CONFIG_AS_AVX2 */ +#endif /* defined(CONFIG_X86_64) && !defined(CONFIG_UML) */ #endif /* _NFT_SET_PIPAPO_AVX2_H */ diff --git a/scripts/Kconfig.include b/scripts/Kconfig.include index 8074f14d9d0d..c264da2b9b30 100644 --- a/scripts/Kconfig.include +++ b/scripts/Kconfig.include @@ -48,9 +48,6 @@ $(error-if,$(failure,command -v $(LD)),linker '$(LD)' not found) # Fail if the linker is gold as it's not capable of linking the kernel proper $(error-if,$(success, $(LD) -v | grep -q gold), gold linker '$(LD)' not supported) -# gcc version including patch level -gcc-version := $(shell,$(srctree)/scripts/gcc-version.sh $(CC)) - # machine bit flags # $(m32-flag): -m32 if the compiler supports it, or an empty string otherwise. # $(m64-flag): -m64 if the compiler supports it, or an empty string otherwise. diff --git a/scripts/Makefile b/scripts/Makefile index 5e75802b1a44..95ecf970c74c 100644 --- a/scripts/Makefile +++ b/scripts/Makefile @@ -2,10 +2,6 @@ ### # scripts contains sources for various helper programs used throughout # the kernel for the build process. -# --------------------------------------------------------------------------- -# kallsyms: Find all symbols in vmlinux - -HOST_EXTRACFLAGS += -I$(srctree)/tools/include always-$(CONFIG_BUILD_BIN2C) += bin2c always-$(CONFIG_KALLSYMS) += kallsyms diff --git a/scripts/Makefile.build b/scripts/Makefile.build index a1730d42e5f3..9fcbfac15d1d 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -46,7 +46,7 @@ include $(kbuild-file) include scripts/Makefile.lib # Do not include host rules unless needed -ifneq ($(hostprogs)$(hostlibs-y)$(hostlibs-m)$(hostcxxlibs-y)$(hostcxxlibs-m),) +ifneq ($(hostprogs)$(hostcxxlibs-y)$(hostcxxlibs-m),) include scripts/Makefile.host endif @@ -65,7 +65,6 @@ endif ifneq ($(strip $(lib-y) $(lib-m) $(lib-)),) lib-target := $(obj)/lib.a -real-obj-y += $(obj)/lib-ksyms.o endif ifdef need-builtin @@ -410,22 +409,6 @@ $(lib-target): $(lib-y) FORCE targets += $(lib-target) -dummy-object = $(obj)/.lib_exports.o -ksyms-lds = $(dot-target).lds - -quiet_cmd_export_list = EXPORTS $@ -cmd_export_list = $(OBJDUMP) -h $< | \ - sed -ne '/___ksymtab/s/.*+\([^ ]*\).*/EXTERN(\1)/p' >$(ksyms-lds);\ - rm -f $(dummy-object);\ - echo | $(CC) $(a_flags) -c -o $(dummy-object) -x assembler -;\ - $(LD) $(ld_flags) -r -o $@ -T $(ksyms-lds) $(dummy-object);\ - rm $(dummy-object) $(ksyms-lds) - -$(obj)/lib-ksyms.o: $(lib-target) FORCE - $(call if_changed,export_list) - -targets += $(obj)/lib-ksyms.o - endif # NOTE: diff --git a/scripts/Makefile.clean b/scripts/Makefile.clean index 1e4206566a82..075f0cc2d8d7 100644 --- a/scripts/Makefile.clean +++ b/scripts/Makefile.clean @@ -30,7 +30,6 @@ subdir-ymn := $(addprefix $(obj)/,$(subdir-ymn)) __clean-files := $(extra-y) $(extra-m) $(extra-) \ $(always) $(always-y) $(always-m) $(always-) $(targets) $(clean-files) \ $(hostprogs) $(hostprogs-y) $(hostprogs-m) $(hostprogs-) \ - $(hostlibs-y) $(hostlibs-m) $(hostlibs-) \ $(hostcxxlibs-y) $(hostcxxlibs-m) __clean-files := $(filter-out $(no-clean-files), $(__clean-files)) diff --git a/scripts/Makefile.extrawarn b/scripts/Makefile.extrawarn index ca08f2fe7c34..4aea7cf71d11 100644 --- a/scripts/Makefile.extrawarn +++ b/scripts/Makefile.extrawarn @@ -49,6 +49,7 @@ KBUILD_CFLAGS += -Wno-format KBUILD_CFLAGS += -Wno-sign-compare KBUILD_CFLAGS += -Wno-format-zero-length KBUILD_CFLAGS += $(call cc-disable-warning, pointer-to-enum-cast) +KBUILD_CFLAGS += -Wno-tautological-constant-out-of-range-compare endif endif diff --git a/scripts/Makefile.host b/scripts/Makefile.host index 3b7121d43324..2045855d0b75 100644 --- a/scripts/Makefile.host +++ b/scripts/Makefile.host @@ -39,7 +39,6 @@ $(obj)/%.tab.c $(obj)/%.tab.h: $(src)/%.y FORCE # They are linked as C++ code to the executable qconf __hostprogs := $(sort $(hostprogs)) -host-cshlib := $(sort $(hostlibs-y) $(hostlibs-m)) host-cxxshlib := $(sort $(hostcxxlibs-y) $(hostcxxlibs-m)) # C code @@ -63,7 +62,6 @@ host-cxxmulti := $(foreach m,$(__hostprogs),$(if $($(m)-cxxobjs),$(m))) host-cxxobjs := $(sort $(foreach m,$(host-cxxmulti),$($(m)-cxxobjs))) # Object (.o) files used by the shared libaries -host-cshobjs := $(sort $(foreach m,$(host-cshlib),$($(m:.so=-objs)))) host-cxxshobjs := $(sort $(foreach m,$(host-cxxshlib),$($(m:.so=-objs)))) host-csingle := $(addprefix $(obj)/,$(host-csingle)) @@ -71,9 +69,7 @@ host-cmulti := $(addprefix $(obj)/,$(host-cmulti)) host-cobjs := $(addprefix $(obj)/,$(host-cobjs)) host-cxxmulti := $(addprefix $(obj)/,$(host-cxxmulti)) host-cxxobjs := $(addprefix $(obj)/,$(host-cxxobjs)) -host-cshlib := $(addprefix $(obj)/,$(host-cshlib)) host-cxxshlib := $(addprefix $(obj)/,$(host-cxxshlib)) -host-cshobjs := $(addprefix $(obj)/,$(host-cshobjs)) host-cxxshobjs := $(addprefix $(obj)/,$(host-cxxshobjs)) ##### @@ -141,13 +137,6 @@ $(host-cxxobjs): $(obj)/%.o: $(src)/%.cc FORCE $(call if_changed_dep,host-cxxobjs) # Compile .c file, create position independent .o file -# host-cshobjs -> .o -quiet_cmd_host-cshobjs = HOSTCC -fPIC $@ - cmd_host-cshobjs = $(HOSTCC) $(hostc_flags) -fPIC -c -o $@ $< -$(host-cshobjs): $(obj)/%.o: $(src)/%.c FORCE - $(call if_changed_dep,host-cshobjs) - -# Compile .c file, create position independent .o file # Note that plugin capable gcc versions can be either C or C++ based # therefore plugin source files have to be compilable in both C and C++ mode. # This is why a C++ compiler is invoked on a .c file. @@ -158,16 +147,6 @@ $(host-cxxshobjs): $(obj)/%.o: $(src)/%.c FORCE $(call if_changed_dep,host-cxxshobjs) # Link a shared library, based on position independent .o files -# *.o -> .so shared library (host-cshlib) -quiet_cmd_host-cshlib = HOSTLLD -shared $@ - cmd_host-cshlib = $(HOSTCC) $(KBUILD_HOSTLDFLAGS) -shared -o $@ \ - $(addprefix $(obj)/, $($(target-stem)-objs)) \ - $(KBUILD_HOSTLDLIBS) $(HOSTLDLIBS_$(target-stem).so) -$(host-cshlib): FORCE - $(call if_changed,host-cshlib) -$(call multi_depend, $(host-cshlib), .so, -objs) - -# Link a shared library, based on position independent .o files # *.o -> .so shared library (host-cxxshlib) quiet_cmd_host-cxxshlib = HOSTLLD -shared $@ cmd_host-cxxshlib = $(HOSTCXX) $(KBUILD_HOSTLDFLAGS) -shared -o $@ \ @@ -178,4 +157,4 @@ $(host-cxxshlib): FORCE $(call multi_depend, $(host-cxxshlib), .so, -objs) targets += $(host-csingle) $(host-cmulti) $(host-cobjs)\ - $(host-cxxmulti) $(host-cxxobjs) $(host-cshlib) $(host-cshobjs) $(host-cxxshlib) $(host-cxxshobjs) + $(host-cxxmulti) $(host-cxxobjs) $(host-cxxshlib) $(host-cxxshobjs) diff --git a/scripts/dummy-tools/gcc b/scripts/dummy-tools/gcc new file mode 100755 index 000000000000..33487e99d83e --- /dev/null +++ b/scripts/dummy-tools/gcc @@ -0,0 +1,91 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0-only +# +# Staring v4.18, Kconfig evaluates compiler capabilities, and hides CONFIG +# options your compiler does not support. This works well if you configure and +# build the kernel on the same host machine. +# +# It is inconvenient if you prepare the .config that is carried to a different +# build environment (typically this happens when you package the kernel for +# distros) because using a different compiler potentially produces different +# CONFIG options than the real build environment. So, you probably want to make +# as many options visible as possible. In other words, you need to create a +# super-set of CONFIG options that cover any build environment. If some of the +# CONFIG options turned out to be unsupported on the build machine, they are +# automatically disabled by the nature of Kconfig. +# +# However, it is not feasible to get a full-featured compiler for every arch. +# Hence these dummy toolchains to make all compiler tests pass. +# +# Usage: +# +# From the top directory of the source tree, run +# +# $ make CROSS_COMPILE=scripts/dummy-tools/ oldconfig +# +# Most of compiler features are tested by cc-option, which simply checks the +# exit code of $(CC). This script does nothing and just exits with 0 in most +# cases. So, $(cc-option, ...) is evaluated as 'y'. +# +# This scripts caters to more checks; handle --version and pre-process __GNUC__ +# etc. to pretend to be GCC, and also do right things to satisfy some scripts. + +# Check if the first parameter appears in the rest. Succeeds if found. +# This helper is useful if a particular option was passed to this script. +# Typically used like this: +# arg_contain <word-you-are-searching-for> "$@" +arg_contain () +{ + search="$1" + shift + + while [ $# -gt 0 ] + do + if [ "$search" = "$1" ]; then + return 0 + fi + shift + done + + return 1 +} + +# To set CONFIG_CC_IS_GCC=y +if arg_contain --version "$@"; then + echo "gcc (scripts/dummy-tools/gcc)" + exit 0 +fi + +if arg_contain -E "$@"; then + # For scripts/gcc-version.sh; This emulates GCC 20.0.0 + if arg_contain - "$@"; then + sed 's/^__GNUC__$/20/; s/^__GNUC_MINOR__$/0/; s/^__GNUC_PATCHLEVEL__$/0/' + exit 0 + else + echo "no input files" >&2 + exit 1 + fi +fi + +if arg_contain -S "$@"; then + # For scripts/gcc-x86-*-has-stack-protector.sh + if arg_contain -fstack-protector "$@"; then + echo "%gs" + exit 0 + fi +fi + +# For scripts/gcc-plugin.sh +if arg_contain -print-file-name=plugin "$@"; then + plugin_dir=$(mktemp -d) + + sed -n 's/.*#include "\(.*\)"/\1/p' $(dirname $0)/../gcc-plugins/gcc-common.h | + while read header + do + mkdir -p $plugin_dir/include/$(dirname $header) + touch $plugin_dir/include/$header + done + + echo $plugin_dir + exit 0 +fi diff --git a/scripts/dummy-tools/ld b/scripts/dummy-tools/ld new file mode 100755 index 000000000000..f68233050405 --- /dev/null +++ b/scripts/dummy-tools/ld @@ -0,0 +1,30 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0-only + +# Dummy script that always succeeds. + +# Check if the first parameter appears in the rest. Succeeds if found. +# This helper is useful if a particular option was passed to this script. +# Typically used like this: +# arg_contain <word-you-are-searching-for> "$@" +arg_contain () +{ + search="$1" + shift + + while [ $# -gt 0 ] + do + if [ "$search" = "$1" ]; then + return 0 + fi + shift + done + + return 1 +} + +if arg_contain --version "$@" || arg_contain -v "$@"; then + progname=$(basename $0) + echo "GNU $progname (scripts/dummy-tools/$progname) 2.50" + exit 0 +fi diff --git a/scripts/dummy-tools/nm b/scripts/dummy-tools/nm new file mode 120000 index 000000000000..c0648b38dd42 --- /dev/null +++ b/scripts/dummy-tools/nm @@ -0,0 +1 @@ +ld
\ No newline at end of file diff --git a/scripts/dummy-tools/objcopy b/scripts/dummy-tools/objcopy new file mode 120000 index 000000000000..c0648b38dd42 --- /dev/null +++ b/scripts/dummy-tools/objcopy @@ -0,0 +1 @@ +ld
\ No newline at end of file diff --git a/scripts/gcc-plugin.sh b/scripts/gcc-plugin.sh index d3caefe53eab..b79fd0bea838 100755 --- a/scripts/gcc-plugin.sh +++ b/scripts/gcc-plugin.sh @@ -1,49 +1,14 @@ #!/bin/sh # SPDX-License-Identifier: GPL-2.0 -srctree=$(dirname "$0") - -SHOW_ERROR= -if [ "$1" = "--show-error" ] ; then - SHOW_ERROR=1 - shift || true -fi - -gccplugins_dir=$($3 -print-file-name=plugin) -plugincc=$($1 -E -x c++ - -o /dev/null -I"${srctree}"/gcc-plugins -I"${gccplugins_dir}"/include 2>&1 <<EOF -#include "gcc-common.h" -#if BUILDING_GCC_VERSION >= 4008 || defined(ENABLE_BUILD_WITH_CXX) -#warning $2 CXX -#else -#warning $1 CC -#endif -EOF -) -if [ $? -ne 0 ] -then - if [ -n "$SHOW_ERROR" ] ; then - echo "${plugincc}" >&2 - fi - exit 1 -fi +set -e -case "$plugincc" in - *"$1 CC"*) - echo "$1" - exit 0 - ;; - - *"$2 CXX"*) - # the c++ compiler needs another test, see below - ;; +srctree=$(dirname "$0") - *) - exit 1 - ;; -esac +gccplugins_dir=$($* -print-file-name=plugin) # we need a c++ compiler that supports the designated initializer GNU extension -plugincc=$($2 -c -x c++ -std=gnu++98 - -fsyntax-only -I"${srctree}"/gcc-plugins -I"${gccplugins_dir}"/include 2>&1 <<EOF +$HOSTCC -c -x c++ -std=gnu++98 - -fsyntax-only -I $srctree/gcc-plugins -I $gccplugins_dir/include 2>/dev/null <<EOF #include "gcc-common.h" class test { public: @@ -52,15 +17,3 @@ public: .test = 1 }; EOF -) - -if [ $? -eq 0 ] -then - echo "$2" - exit 0 -fi - -if [ -n "$SHOW_ERROR" ] ; then - echo "${plugincc}" >&2 -fi -exit 1 diff --git a/scripts/gcc-plugins/Kconfig b/scripts/gcc-plugins/Kconfig index f8ca236d6165..013ba3a57669 100644 --- a/scripts/gcc-plugins/Kconfig +++ b/scripts/gcc-plugins/Kconfig @@ -1,13 +1,4 @@ # SPDX-License-Identifier: GPL-2.0-only -preferred-plugin-hostcc := $(if-success,[ $(gcc-version) -ge 40800 ],$(HOSTCXX),$(HOSTCC)) - -config PLUGIN_HOSTCC - string - default "$(shell,$(srctree)/scripts/gcc-plugin.sh "$(preferred-plugin-hostcc)" "$(HOSTCXX)" "$(CC)")" if CC_IS_GCC - help - Host compiler used to build GCC plugins. This can be $(HOSTCXX), - $(HOSTCC), or a null string if GCC plugin is unsupported. - config HAVE_GCC_PLUGINS bool help @@ -17,7 +8,8 @@ config HAVE_GCC_PLUGINS menuconfig GCC_PLUGINS bool "GCC plugins" depends on HAVE_GCC_PLUGINS - depends on PLUGIN_HOSTCC != "" + depends on CC_IS_GCC && GCC_VERSION >= 40800 + depends on $(success,$(srctree)/scripts/gcc-plugin.sh $(CC)) default y help GCC plugins are loadable modules that provide extra features to the diff --git a/scripts/gcc-plugins/Makefile b/scripts/gcc-plugins/Makefile index efff00959a9c..f22858b2c3d6 100644 --- a/scripts/gcc-plugins/Makefile +++ b/scripts/gcc-plugins/Makefile @@ -1,18 +1,9 @@ # SPDX-License-Identifier: GPL-2.0 -PLUGINCC := $(CONFIG_PLUGIN_HOSTCC:"%"=%) GCC_PLUGINS_DIR := $(shell $(CC) -print-file-name=plugin) -ifeq ($(PLUGINCC),$(HOSTCC)) - HOSTLIBS := hostlibs - HOST_EXTRACFLAGS += -I$(GCC_PLUGINS_DIR)/include -I$(src) -std=gnu99 -ggdb - export HOST_EXTRACFLAGS -else - HOSTLIBS := hostcxxlibs - HOST_EXTRACXXFLAGS += -I$(GCC_PLUGINS_DIR)/include -I$(src) -std=gnu++98 -fno-rtti - HOST_EXTRACXXFLAGS += -fno-exceptions -fasynchronous-unwind-tables -ggdb - HOST_EXTRACXXFLAGS += -Wno-narrowing -Wno-unused-variable -Wno-c++11-compat - export HOST_EXTRACXXFLAGS -endif +HOST_EXTRACXXFLAGS += -I$(GCC_PLUGINS_DIR)/include -I$(src) -std=gnu++98 -fno-rtti +HOST_EXTRACXXFLAGS += -fno-exceptions -fasynchronous-unwind-tables -ggdb +HOST_EXTRACXXFLAGS += -Wno-narrowing -Wno-unused-variable -Wno-c++11-compat $(obj)/randomize_layout_plugin.o: $(objtree)/$(obj)/randomize_layout_seed.h quiet_cmd_create_randomize_layout_seed = GENSEED $@ @@ -22,9 +13,9 @@ $(objtree)/$(obj)/randomize_layout_seed.h: FORCE $(call if_changed,create_randomize_layout_seed) targets = randomize_layout_seed.h randomize_layout_hash.h -$(HOSTLIBS)-y := $(foreach p,$(GCC_PLUGIN),$(if $(findstring /,$(p)),,$(p))) -always-y := $($(HOSTLIBS)-y) +hostcxxlibs-y := $(foreach p,$(GCC_PLUGIN),$(if $(findstring /,$(p)),,$(p))) +always-y := $(hostcxxlibs-y) -$(foreach p,$($(HOSTLIBS)-y:%.so=%),$(eval $(p)-objs := $(p).o)) +$(foreach p,$(hostcxxlibs-y:%.so=%),$(eval $(p)-objs := $(p).o)) clean-files += *.so diff --git a/scripts/kconfig/qconf.cc b/scripts/kconfig/qconf.cc index 50a5245d87bb..c0ac8f7b5f1a 100644 --- a/scripts/kconfig/qconf.cc +++ b/scripts/kconfig/qconf.cc @@ -154,9 +154,9 @@ void ConfigItem::updateMenu(void) if (!sym_is_changeable(sym) && list->optMode == normalOpt) { setPixmap(promptColIdx, QIcon()); - setText(noColIdx, QString::null); - setText(modColIdx, QString::null); - setText(yesColIdx, QString::null); + setText(noColIdx, QString()); + setText(modColIdx, QString()); + setText(yesColIdx, QString()); break; } expr = sym_get_tristate_value(sym); @@ -276,7 +276,7 @@ void ConfigLineEdit::show(ConfigItem* i) if (sym_get_string_value(item->menu->sym)) setText(QString::fromLocal8Bit(sym_get_string_value(item->menu->sym))); else - setText(QString::null); + setText(QString()); Parent::show(); setFocus(); } @@ -316,7 +316,10 @@ ConfigList::ConfigList(ConfigView* p, const char *name) setVerticalScrollMode(ScrollPerPixel); setHorizontalScrollMode(ScrollPerPixel); - setHeaderLabels(QStringList() << "Option" << "Name" << "N" << "M" << "Y" << "Value"); + if (mode == symbolMode) + setHeaderLabels(QStringList() << "Item" << "Name" << "N" << "M" << "Y" << "Value"); + else + setHeaderLabels(QStringList() << "Option" << "Name" << "N" << "M" << "Y" << "Value"); connect(this, SIGNAL(itemSelectionChanged(void)), SLOT(updateSelection(void))); @@ -397,6 +400,11 @@ void ConfigList::updateSelection(void) struct menu *menu; enum prop_type type; + if (mode == symbolMode) + setHeaderLabels(QStringList() << "Item" << "Name" << "N" << "M" << "Y" << "Value"); + else + setHeaderLabels(QStringList() << "Option" << "Name" << "N" << "M" << "Y" << "Value"); + if (selectedItems().count() == 0) return; @@ -625,7 +633,7 @@ void ConfigList::updateMenuList(ConfigItem *parent, struct menu* menu) last = item; continue; } - hide: +hide: if (item && item->menu == child) { last = parent->firstChild(); if (last == item) @@ -690,7 +698,7 @@ void ConfigList::updateMenuList(ConfigList *parent, struct menu* menu) last = item; continue; } - hide: +hide: if (item && item->menu == child) { last = (ConfigItem*)parent->topLevelItem(0); if (last == item) @@ -734,7 +742,10 @@ void ConfigList::keyPressEvent(QKeyEvent* ev) type = menu->prompt ? menu->prompt->type : P_UNKNOWN; if (type == P_MENU && rootEntry != menu && mode != fullMode && mode != menuMode) { - emit menuSelected(menu); + if (mode == menuMode) + emit menuSelected(menu); + else + emit itemSelected(menu); break; } case Qt::Key_Space: @@ -826,7 +837,7 @@ void ConfigList::mouseMoveEvent(QMouseEvent* e) void ConfigList::mouseDoubleClickEvent(QMouseEvent* e) { - QPoint p = e->pos(); // TODO: Check if this works(was contentsToViewport). + QPoint p = e->pos(); ConfigItem* item = (ConfigItem*)itemAt(p); struct menu *menu; enum prop_type ptype; @@ -841,9 +852,12 @@ void ConfigList::mouseDoubleClickEvent(QMouseEvent* e) if (!menu) goto skip; ptype = menu->prompt ? menu->prompt->type : P_UNKNOWN; - if (ptype == P_MENU && (mode == singleMode || mode == symbolMode)) - emit menuSelected(menu); - else if (menu->sym) + if (ptype == P_MENU) { + if (mode == singleMode) + emit itemSelected(menu); + else if (mode == symbolMode) + emit menuSelected(menu); + } else if (menu->sym) changeValue(item); skip: @@ -1223,10 +1237,11 @@ QMenu* ConfigInfoView::createStandardContextMenu(const QPoint & pos) { QMenu* popup = Parent::createStandardContextMenu(pos); QAction* action = new QAction("Show Debug Info", popup); - action->setCheckable(true); - connect(action, SIGNAL(toggled(bool)), SLOT(setShowDebug(bool))); - connect(this, SIGNAL(showDebugChanged(bool)), action, SLOT(setOn(bool))); - action->setChecked(showDebug()); + + action->setCheckable(true); + connect(action, SIGNAL(toggled(bool)), SLOT(setShowDebug(bool))); + connect(this, SIGNAL(showDebugChanged(bool)), action, SLOT(setOn(bool))); + action->setChecked(showDebug()); popup->addSeparator(); popup->addAction(action); return popup; @@ -1352,21 +1367,32 @@ ConfigMainWindow::ConfigMainWindow(void) if ((x.isValid())&&(y.isValid())) move(x.toInt(), y.toInt()); - split1 = new QSplitter(this); + QWidget *widget = new QWidget(this); + QVBoxLayout *layout = new QVBoxLayout(widget); + setCentralWidget(widget); + + split1 = new QSplitter(widget); split1->setOrientation(Qt::Horizontal); - setCentralWidget(split1); + split1->setChildrenCollapsible(false); - menuView = new ConfigView(split1, "menu"); + menuView = new ConfigView(widget, "menu"); menuList = menuView->list; - split2 = new QSplitter(split1); + split2 = new QSplitter(widget); + split2->setChildrenCollapsible(false); split2->setOrientation(Qt::Vertical); // create config tree - configView = new ConfigView(split2, "config"); + configView = new ConfigView(widget, "config"); configList = configView->list; - helpText = new ConfigInfoView(split2, "help"); + helpText = new ConfigInfoView(widget, "help"); + + layout->addWidget(split2); + split2->addWidget(split1); + split1->addWidget(configView); + split1->addWidget(menuView); + split2->addWidget(helpText); setTabOrder(configList, helpText); configList->setFocus(); @@ -1484,6 +1510,8 @@ ConfigMainWindow::ConfigMainWindow(void) helpText, SLOT(setInfo(struct menu *))); connect(configList, SIGNAL(menuSelected(struct menu *)), SLOT(changeMenu(struct menu *))); + connect(configList, SIGNAL(itemSelected(struct menu *)), + SLOT(changeItens(struct menu *))); connect(configList, SIGNAL(parentSelected()), SLOT(goBack())); connect(menuList, SIGNAL(menuChanged(struct menu *)), @@ -1580,15 +1608,26 @@ void ConfigMainWindow::searchConfig(void) searchWindow->show(); } -void ConfigMainWindow::changeMenu(struct menu *menu) +void ConfigMainWindow::changeItens(struct menu *menu) { configList->setRootMenu(menu); + if (configList->rootEntry->parent == &rootmenu) backAction->setEnabled(false); else backAction->setEnabled(true); } +void ConfigMainWindow::changeMenu(struct menu *menu) +{ + menuList->setRootMenu(menu); + + if (menuList->rootEntry->parent == &rootmenu) + backAction->setEnabled(false); + else + backAction->setEnabled(true); +} + void ConfigMainWindow::setMenuLink(struct menu *menu) { struct menu *parent; @@ -1698,14 +1737,14 @@ void ConfigMainWindow::showSplitView(void) fullViewAction->setEnabled(true); fullViewAction->setChecked(false); - configList->mode = symbolMode; + configList->mode = menuMode; if (configList->rootEntry == &rootmenu) configList->updateListAll(); else configList->setRootMenu(&rootmenu); configList->setAllOpen(true); configApp->processEvents(); - menuList->mode = menuMode; + menuList->mode = symbolMode; menuList->setRootMenu(&rootmenu); menuList->setAllOpen(true); menuView->show(); @@ -1733,7 +1772,6 @@ void ConfigMainWindow::showFullView(void) /* * ask for saving configuration before quitting - * TODO ask only when something changed */ void ConfigMainWindow::closeEvent(QCloseEvent* e) { diff --git a/scripts/kconfig/qconf.h b/scripts/kconfig/qconf.h index 45bfe9b2b966..c879d79ce817 100644 --- a/scripts/kconfig/qconf.h +++ b/scripts/kconfig/qconf.h @@ -71,6 +71,7 @@ public slots: signals: void menuChanged(struct menu *menu); void menuSelected(struct menu *menu); + void itemSelected(struct menu *menu); void parentSelected(void); void gotFocus(struct menu *); @@ -298,6 +299,7 @@ public: ConfigMainWindow(void); public slots: void changeMenu(struct menu *); + void changeItens(struct menu *); void setMenuLink(struct menu *); void listFocusChanged(void); void goBack(void); diff --git a/scripts/mkcompile_h b/scripts/mkcompile_h index 3ff26e5b2eac..5b80a4699740 100755 --- a/scripts/mkcompile_h +++ b/scripts/mkcompile_h @@ -7,6 +7,7 @@ SMP=$3 PREEMPT=$4 PREEMPT_RT=$5 CC=$6 +LD=$7 vecho() { [ "${quiet}" = "silent_" ] || echo "$@" ; } @@ -61,7 +62,10 @@ UTS_VERSION="$(echo $UTS_VERSION $CONFIG_FLAGS $TIMESTAMP | cut -b -$UTS_LEN)" printf '#define LINUX_COMPILE_BY "%s"\n' "$LINUX_COMPILE_BY" echo \#define LINUX_COMPILE_HOST \"$LINUX_COMPILE_HOST\" - echo \#define LINUX_COMPILER \"`$CC -v 2>&1 | grep ' version ' | sed 's/[[:space:]]*$//'`\" + CC_VERSION=$($CC -v 2>&1 | grep ' version ' | sed 's/[[:space:]]*$//') + LD_VERSION=$($LD -v | head -n1 | sed 's/(compatible with [^)]*)//' \ + | sed 's/[[:space:]]*$//') + printf '#define LINUX_COMPILER "%s"\n' "$CC_VERSION, $LD_VERSION" } > .tmpcompile # Only replace the real compile.h if the new one is different, diff --git a/tools/objtool/Makefile b/tools/objtool/Makefile index ee08aeff30a1..f591c4d1b6fe 100644 --- a/tools/objtool/Makefile +++ b/tools/objtool/Makefile @@ -3,9 +3,15 @@ include ../scripts/Makefile.include include ../scripts/Makefile.arch # always use the host compiler +ifneq ($(LLVM),) +HOSTAR ?= llvm-ar +HOSTCC ?= clang +HOSTLD ?= ld.lld +else HOSTAR ?= ar HOSTCC ?= gcc HOSTLD ?= ld +endif AR = $(HOSTAR) CC = $(HOSTCC) LD = $(HOSTLD) diff --git a/usr/include/Makefile b/usr/include/Makefile index a339ef325aa5..b568a95d1f62 100644 --- a/usr/include/Makefile +++ b/usr/include/Makefile @@ -93,7 +93,7 @@ no-header-test += asm-generic/% extra-y := $(patsubst $(obj)/%.h,%.hdrtest, $(shell find $(obj) -name '*.h' 2>/dev/null)) -# Include the header to detect missing include guard. +# Include the header twice to detect missing include guard. quiet_cmd_hdrtest = HDRTEST $< cmd_hdrtest = \ $(CC) $(c_flags) -S -o /dev/null -x c /dev/null \ |