diff options
Diffstat (limited to 'arch/powerpc')
177 files changed, 1358 insertions, 935 deletions
diff --git a/arch/powerpc/Kbuild b/arch/powerpc/Kbuild index 5e2f9eaa3ee7..22cd0d55a892 100644 --- a/arch/powerpc/Kbuild +++ b/arch/powerpc/Kbuild @@ -16,3 +16,6 @@ obj-$(CONFIG_KVM) += kvm/ obj-$(CONFIG_PERF_EVENTS) += perf/ obj-$(CONFIG_KEXEC_CORE) += kexec/ obj-$(CONFIG_KEXEC_FILE) += purgatory/ + +# for cleaning +subdir- += boot diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index ba5b66189358..dea74d7717c0 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -138,7 +138,8 @@ config PPC select ARCH_HAS_PTE_SPECIAL select ARCH_HAS_SCALED_CPUTIME if VIRT_CPU_ACCOUNTING_NATIVE && PPC_BOOK3S_64 select ARCH_HAS_SET_MEMORY - select ARCH_HAS_STRICT_KERNEL_RWX if ((PPC_BOOK3S_64 || PPC32) && !HIBERNATION) + select ARCH_HAS_STRICT_KERNEL_RWX if (PPC_BOOK3S || PPC_8xx || 40x) && !HIBERNATION + select ARCH_HAS_STRICT_KERNEL_RWX if FSL_BOOKE && !HIBERNATION && !RANDOMIZE_BASE select ARCH_HAS_STRICT_MODULE_RWX if ARCH_HAS_STRICT_KERNEL_RWX && !PPC_BOOK3S_32 select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST select ARCH_HAS_UACCESS_FLUSHCACHE @@ -148,9 +149,10 @@ config PPC select ARCH_MIGHT_HAVE_PC_PARPORT select ARCH_MIGHT_HAVE_PC_SERIO select ARCH_OPTIONAL_KERNEL_RWX if ARCH_HAS_STRICT_KERNEL_RWX + select ARCH_OPTIONAL_KERNEL_RWX_DEFAULT select ARCH_STACKWALK select ARCH_SUPPORTS_ATOMIC_RMW - select ARCH_SUPPORTS_DEBUG_PAGEALLOC if PPC32 || PPC_BOOK3S_64 + select ARCH_SUPPORTS_DEBUG_PAGEALLOC if PPC_BOOK3S || PPC_8xx || 40x select ARCH_USE_BUILTIN_BSWAP select ARCH_USE_CMPXCHG_LOCKREF if PPC64 select ARCH_USE_MEMTEST @@ -190,7 +192,7 @@ config PPC select HAVE_ARCH_JUMP_LABEL_RELATIVE select HAVE_ARCH_KASAN if PPC32 && PPC_PAGE_SHIFT <= 14 select HAVE_ARCH_KASAN_VMALLOC if PPC32 && PPC_PAGE_SHIFT <= 14 - select HAVE_ARCH_KFENCE if PPC32 + select HAVE_ARCH_KFENCE if PPC_BOOK3S_32 || PPC_8xx || 40x select HAVE_ARCH_KGDB select HAVE_ARCH_MMAP_RND_BITS select HAVE_ARCH_MMAP_RND_COMPAT_BITS if COMPAT @@ -241,6 +243,7 @@ config PPC select HAVE_SOFTIRQ_ON_OWN_STACK select HAVE_STACKPROTECTOR if PPC32 && $(cc-option,-mstack-protector-guard=tls -mstack-protector-guard-reg=r2) select HAVE_STACKPROTECTOR if PPC64 && $(cc-option,-mstack-protector-guard=tls -mstack-protector-guard-reg=r13) + select HAVE_STATIC_CALL if PPC32 select HAVE_SYSCALL_TRACEPOINTS select HAVE_VIRT_CPU_ACCOUNTING select HUGETLB_PAGE_SIZE_VARIABLE if PPC_BOOK3S_64 && HUGETLB_PAGE @@ -707,6 +710,7 @@ config ARCH_MEMORY_PROBE choice prompt "Page size" + default PPC_64K_PAGES if PPC_BOOK3S_64 default PPC_4K_PAGES help Select the kernel logical page size. Increasing the page size @@ -778,7 +782,8 @@ config DATA_SHIFT_BOOL bool "Set custom data alignment" depends on ADVANCED_OPTIONS depends on STRICT_KERNEL_RWX || DEBUG_PAGEALLOC || KFENCE - depends on PPC_BOOK3S_32 || (PPC_8xx && !PIN_TLB_DATA && !STRICT_KERNEL_RWX) + depends on PPC_BOOK3S_32 || (PPC_8xx && !PIN_TLB_DATA && !STRICT_KERNEL_RWX) || \ + FSL_BOOKE help This option allows you to set the kernel data alignment. When RAM is mapped by blocks, the alignment needs to fit the size and @@ -791,11 +796,13 @@ config DATA_SHIFT default 24 if STRICT_KERNEL_RWX && PPC64 range 17 28 if (STRICT_KERNEL_RWX || DEBUG_PAGEALLOC || KFENCE) && PPC_BOOK3S_32 range 19 23 if (STRICT_KERNEL_RWX || DEBUG_PAGEALLOC || KFENCE) && PPC_8xx + range 20 24 if (STRICT_KERNEL_RWX || DEBUG_PAGEALLOC || KFENCE) && PPC_FSL_BOOKE default 22 if STRICT_KERNEL_RWX && PPC_BOOK3S_32 default 18 if (DEBUG_PAGEALLOC || KFENCE) && PPC_BOOK3S_32 default 23 if STRICT_KERNEL_RWX && PPC_8xx default 23 if (DEBUG_PAGEALLOC || KFENCE) && PPC_8xx && PIN_TLB_DATA default 19 if (DEBUG_PAGEALLOC || KFENCE) && PPC_8xx + default 24 if STRICT_KERNEL_RWX && FSL_BOOKE default PPC_PAGE_SHIFT help On Book3S 32 (603+), DBATs are used to map kernel text and rodata RO. @@ -1123,7 +1130,10 @@ config LOWMEM_CAM_NUM_BOOL config LOWMEM_CAM_NUM depends on FSL_BOOKE int "Number of CAMs to use to map low memory" if LOWMEM_CAM_NUM_BOOL - default 3 + default 3 if !STRICT_KERNEL_RWX + default 9 if DATA_SHIFT >= 24 + default 12 if DATA_SHIFT >= 22 + default 15 config DYNAMIC_MEMSTART bool "Enable page aligned dynamic load address for kernel" diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index aa6808e70647..e02568f17334 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -1,7 +1,5 @@ # This file is included by the global makefile so that you can add your own -# architecture-specific flags and dependencies. Remember to do have actions -# for "archclean" and "archdep" for cleaning up and making dependencies for -# this architecture. +# architecture-specific flags and dependencies. # # This file is subject to the terms and conditions of the GNU General Public # License. See the file "COPYING" in the main directory of this archive @@ -411,9 +409,6 @@ install: sh -x $(srctree)/$(boot)/install.sh "$(KERNELRELEASE)" vmlinux \ System.map "$(INSTALL_PATH)" -archclean: - $(Q)$(MAKE) $(clean)=$(boot) - ifeq ($(KBUILD_EXTMOD),) # We need to generate vdso-offsets.h before compiling certain files in kernel/. # In order to do that, we should use the archprepare target, but we can't since @@ -446,17 +441,6 @@ else endif endif -ifdef CONFIG_SMP -ifdef CONFIG_PPC32 -prepare: task_cpu_prepare - -PHONY += task_cpu_prepare -task_cpu_prepare: prepare0 - $(eval KBUILD_CFLAGS += -D_TASK_CPU=$(shell awk '{if ($$2 == "TASK_CPU") print $$3;}' include/generated/asm-offsets.h)) - -endif # CONFIG_PPC32 -endif # CONFIG_SMP - PHONY += checkbin # Check toolchain versions: # - gcc-4.6 is the minimum kernel-wide version so nothing required. diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile index 6900d0ac2421..9993c6256ad2 100644 --- a/arch/powerpc/boot/Makefile +++ b/arch/powerpc/boot/Makefile @@ -35,7 +35,6 @@ endif BOOTCFLAGS := -Wall -Wundef -Wstrict-prototypes -Wno-trigraphs \ -fno-strict-aliasing -O2 -msoft-float -mno-altivec -mno-vsx \ -pipe -fomit-frame-pointer -fno-builtin -fPIC -nostdinc \ - -include $(srctree)/include/linux/compiler_attributes.h \ $(LINUXINCLUDE) ifdef CONFIG_PPC64_BOOT_WRAPPER @@ -70,6 +69,7 @@ ifeq ($(call cc-option-yn, -fstack-protector),y) BOOTCFLAGS += -fno-stack-protector endif +BOOTCFLAGS += -include $(srctree)/include/linux/compiler_attributes.h BOOTCFLAGS += -I$(objtree)/$(obj) -I$(srctree)/$(obj) DTC_FLAGS ?= -p 1024 @@ -123,7 +123,7 @@ src-wlib-y := string.S crt0.S stdio.c decompress.c main.c \ oflib.c ofconsole.c cuboot.c src-wlib-$(CONFIG_PPC_MPC52xx) += mpc52xx-psc.c -src-wlib-$(CONFIG_PPC64_BOOT_WRAPPER) += opal-calls.S opal.c +src-wlib-$(CONFIG_PPC_POWERNV) += opal-calls.S opal.c ifndef CONFIG_PPC64_BOOT_WRAPPER src-wlib-y += crtsavres.S endif diff --git a/arch/powerpc/boot/dts/a4m072.dts b/arch/powerpc/boot/dts/a4m072.dts index a9cef5726422..d4270a2ec6c7 100644 --- a/arch/powerpc/boot/dts/a4m072.dts +++ b/arch/powerpc/boot/dts/a4m072.dts @@ -140,8 +140,8 @@ clock-frequency = <0>; /* From boot loader */ interrupts = <2 8 0 2 9 0 2 10 0>; bus-range = <0 0>; - ranges = <0x42000000 0 0x80000000 0x80000000 0 0x10000000 - 0x02000000 0 0x90000000 0x90000000 0 0x10000000 - 0x01000000 0 0x00000000 0xa0000000 0 0x01000000>; + ranges = <0x42000000 0 0x80000000 0x80000000 0 0x10000000>, + <0x02000000 0 0x90000000 0x90000000 0 0x10000000>, + <0x01000000 0 0x00000000 0xa0000000 0 0x01000000>; }; }; diff --git a/arch/powerpc/boot/dts/charon.dts b/arch/powerpc/boot/dts/charon.dts index 408b486b13df..ea6e76ae2545 100644 --- a/arch/powerpc/boot/dts/charon.dts +++ b/arch/powerpc/boot/dts/charon.dts @@ -35,7 +35,7 @@ }; }; - memory { + memory@0 { device_type = "memory"; reg = <0x00000000 0x08000000>; // 128MB }; @@ -225,8 +225,8 @@ clock-frequency = <0>; // From boot loader interrupts = <2 8 0 2 9 0 2 10 0>; bus-range = <0 0>; - ranges = <0x42000000 0 0x80000000 0x80000000 0 0x10000000 - 0x02000000 0 0x90000000 0x90000000 0 0x10000000 - 0x01000000 0 0x00000000 0xa0000000 0 0x01000000>; + ranges = <0x42000000 0 0x80000000 0x80000000 0 0x10000000>, + <0x02000000 0 0x90000000 0x90000000 0 0x10000000>, + <0x01000000 0 0x00000000 0xa0000000 0 0x01000000>; }; }; diff --git a/arch/powerpc/boot/dts/digsy_mtc.dts b/arch/powerpc/boot/dts/digsy_mtc.dts index 0e5e9d3acf79..57024a4c1e7d 100644 --- a/arch/powerpc/boot/dts/digsy_mtc.dts +++ b/arch/powerpc/boot/dts/digsy_mtc.dts @@ -16,7 +16,7 @@ model = "intercontrol,digsy-mtc"; compatible = "intercontrol,digsy-mtc"; - memory { + memory@0 { reg = <0x00000000 0x02000000>; // 32MB }; @@ -98,9 +98,9 @@ clock-frequency = <0>; // From boot loader interrupts = <2 8 0 2 9 0 2 10 0>; bus-range = <0 0>; - ranges = <0x42000000 0 0x80000000 0x80000000 0 0x10000000 - 0x02000000 0 0x90000000 0x90000000 0 0x10000000 - 0x01000000 0 0x00000000 0xa0000000 0 0x01000000>; + ranges = <0x42000000 0 0x80000000 0x80000000 0 0x10000000>, + <0x02000000 0 0x90000000 0x90000000 0 0x10000000>, + <0x01000000 0 0x00000000 0xa0000000 0 0x01000000>; }; localbus { diff --git a/arch/powerpc/boot/dts/fsl/t1023rdb.dts b/arch/powerpc/boot/dts/fsl/t1023rdb.dts index 5ba6fbfca274..f82f85c65964 100644 --- a/arch/powerpc/boot/dts/fsl/t1023rdb.dts +++ b/arch/powerpc/boot/dts/fsl/t1023rdb.dts @@ -154,7 +154,7 @@ fm1mac3: ethernet@e4000 { phy-handle = <&sgmii_aqr_phy3>; - phy-connection-type = "sgmii-2500"; + phy-connection-type = "2500base-x"; sleep = <&rcpm 0x20000000>; }; diff --git a/arch/powerpc/boot/dts/lite5200.dts b/arch/powerpc/boot/dts/lite5200.dts index cb2782dd6132..b9d8487813b4 100644 --- a/arch/powerpc/boot/dts/lite5200.dts +++ b/arch/powerpc/boot/dts/lite5200.dts @@ -32,7 +32,7 @@ }; }; - memory { + memory@0 { device_type = "memory"; reg = <0x00000000 0x04000000>; // 64MB }; @@ -283,9 +283,9 @@ clock-frequency = <0>; // From boot loader interrupts = <2 8 0 2 9 0 2 10 0>; bus-range = <0 0>; - ranges = <0x42000000 0 0x80000000 0x80000000 0 0x20000000 - 0x02000000 0 0xa0000000 0xa0000000 0 0x10000000 - 0x01000000 0 0x00000000 0xb0000000 0 0x01000000>; + ranges = <0x42000000 0 0x80000000 0x80000000 0 0x20000000>, + <0x02000000 0 0xa0000000 0xa0000000 0 0x10000000>, + <0x01000000 0 0x00000000 0xb0000000 0 0x01000000>; }; localbus { diff --git a/arch/powerpc/boot/dts/lite5200b.dts b/arch/powerpc/boot/dts/lite5200b.dts index 2b86c81f9048..7e2d91c7cb66 100644 --- a/arch/powerpc/boot/dts/lite5200b.dts +++ b/arch/powerpc/boot/dts/lite5200b.dts @@ -31,7 +31,7 @@ led4 { gpios = <&gpio_simple 2 1>; }; }; - memory { + memory@0 { reg = <0x00000000 0x10000000>; // 256MB }; @@ -116,9 +116,9 @@ clock-frequency = <0>; // From boot loader interrupts = <2 8 0 2 9 0 2 10 0>; bus-range = <0 0>; - ranges = <0x42000000 0 0x80000000 0x80000000 0 0x20000000 - 0x02000000 0 0xa0000000 0xa0000000 0 0x10000000 - 0x01000000 0 0x00000000 0xb0000000 0 0x01000000>; + ranges = <0x42000000 0 0x80000000 0x80000000 0 0x20000000>, + <0x02000000 0 0xa0000000 0xa0000000 0 0x10000000>, + <0x01000000 0 0x00000000 0xb0000000 0 0x01000000>; }; localbus { diff --git a/arch/powerpc/boot/dts/media5200.dts b/arch/powerpc/boot/dts/media5200.dts index 61cae9dcddef..96524ede16cd 100644 --- a/arch/powerpc/boot/dts/media5200.dts +++ b/arch/powerpc/boot/dts/media5200.dts @@ -32,7 +32,7 @@ }; }; - memory { + memory@0 { reg = <0x00000000 0x08000000>; // 128MB RAM }; @@ -96,9 +96,9 @@ 0xe000 0 0 1 &media5200_fpga 0 5 // CoralIP >; - ranges = <0x42000000 0 0x80000000 0x80000000 0 0x20000000 - 0x02000000 0 0xa0000000 0xa0000000 0 0x10000000 - 0x01000000 0 0x00000000 0xb0000000 0 0x01000000>; + ranges = <0x42000000 0 0x80000000 0x80000000 0 0x20000000>, + <0x02000000 0 0xa0000000 0xa0000000 0 0x10000000>, + <0x01000000 0 0x00000000 0xb0000000 0 0x01000000>; interrupt-parent = <&mpc5200_pic>; }; diff --git a/arch/powerpc/boot/dts/mpc5200b.dtsi b/arch/powerpc/boot/dts/mpc5200b.dtsi index 648fe31795f4..ffa82c7e1055 100644 --- a/arch/powerpc/boot/dts/mpc5200b.dtsi +++ b/arch/powerpc/boot/dts/mpc5200b.dtsi @@ -33,7 +33,7 @@ }; }; - memory: memory { + memory: memory@0 { device_type = "memory"; reg = <0x00000000 0x04000000>; // 64MB }; @@ -276,7 +276,9 @@ clock-frequency = <0>; // From boot loader interrupts = <2 8 0 2 9 0 2 10 0>; bus-range = <0 0>; - // ranges = need to add + ranges = <0x42000000 0 0x80000000 0x80000000 0 0x10000000>, + <0x02000000 0 0x90000000 0x90000000 0 0x10000000>, + <0x01000000 0 0x00000000 0xa0000000 0 0x01000000>; }; localbus: localbus { diff --git a/arch/powerpc/boot/dts/mucmc52.dts b/arch/powerpc/boot/dts/mucmc52.dts index c6c66306308d..e88a7bd4034d 100644 --- a/arch/powerpc/boot/dts/mucmc52.dts +++ b/arch/powerpc/boot/dts/mucmc52.dts @@ -106,9 +106,9 @@ 0x8000 0 0 3 &mpc5200_pic 0 2 3 0x8000 0 0 4 &mpc5200_pic 0 1 3 >; - ranges = <0x42000000 0 0x60000000 0x60000000 0 0x10000000 - 0x02000000 0 0x90000000 0x90000000 0 0x10000000 - 0x01000000 0 0x00000000 0xa0000000 0 0x01000000>; + ranges = <0x42000000 0 0x60000000 0x60000000 0 0x10000000>, + <0x02000000 0 0x90000000 0x90000000 0 0x10000000>, + <0x01000000 0 0x00000000 0xa0000000 0 0x01000000>; }; localbus { diff --git a/arch/powerpc/boot/dts/o2d.dts b/arch/powerpc/boot/dts/o2d.dts index 24a46f65e529..e0a8d3034417 100644 --- a/arch/powerpc/boot/dts/o2d.dts +++ b/arch/powerpc/boot/dts/o2d.dts @@ -12,7 +12,7 @@ model = "ifm,o2d"; compatible = "ifm,o2d"; - memory { + memory@0 { reg = <0x00000000 0x08000000>; // 128MB }; diff --git a/arch/powerpc/boot/dts/o2d.dtsi b/arch/powerpc/boot/dts/o2d.dtsi index 6661955a2be4..b55a9e5bd828 100644 --- a/arch/powerpc/boot/dts/o2d.dtsi +++ b/arch/powerpc/boot/dts/o2d.dtsi @@ -19,7 +19,7 @@ model = "ifm,o2d"; compatible = "ifm,o2d"; - memory { + memory@0 { reg = <0x00000000 0x04000000>; // 64MB }; diff --git a/arch/powerpc/boot/dts/o2dnt2.dts b/arch/powerpc/boot/dts/o2dnt2.dts index eeba7f5507d5..c2eedbd1f5fc 100644 --- a/arch/powerpc/boot/dts/o2dnt2.dts +++ b/arch/powerpc/boot/dts/o2dnt2.dts @@ -12,7 +12,7 @@ model = "ifm,o2dnt2"; compatible = "ifm,o2d"; - memory { + memory@0 { reg = <0x00000000 0x08000000>; // 128MB }; diff --git a/arch/powerpc/boot/dts/o3dnt.dts b/arch/powerpc/boot/dts/o3dnt.dts index fd00396b0593..e4c1bdd41271 100644 --- a/arch/powerpc/boot/dts/o3dnt.dts +++ b/arch/powerpc/boot/dts/o3dnt.dts @@ -12,7 +12,7 @@ model = "ifm,o3dnt"; compatible = "ifm,o2d"; - memory { + memory@0 { reg = <0x00000000 0x04000000>; // 64MB }; diff --git a/arch/powerpc/boot/dts/pcm030.dts b/arch/powerpc/boot/dts/pcm030.dts index b1bc731f7afd..5cee474dcc4c 100644 --- a/arch/powerpc/boot/dts/pcm030.dts +++ b/arch/powerpc/boot/dts/pcm030.dts @@ -90,9 +90,9 @@ 0xc800 0 0 2 &mpc5200_pic 1 2 3 0xc800 0 0 3 &mpc5200_pic 1 3 3 0xc800 0 0 4 &mpc5200_pic 0 0 3>; - ranges = <0x42000000 0 0x80000000 0x80000000 0 0x20000000 - 0x02000000 0 0xa0000000 0xa0000000 0 0x10000000 - 0x01000000 0 0x00000000 0xb0000000 0 0x01000000>; + ranges = <0x42000000 0 0x80000000 0x80000000 0 0x20000000>, + <0x02000000 0 0xa0000000 0xa0000000 0 0x10000000>, + <0x01000000 0 0x00000000 0xb0000000 0 0x01000000>; }; localbus { diff --git a/arch/powerpc/boot/dts/pcm032.dts b/arch/powerpc/boot/dts/pcm032.dts index 780e13d99e7b..d00f13b62510 100644 --- a/arch/powerpc/boot/dts/pcm032.dts +++ b/arch/powerpc/boot/dts/pcm032.dts @@ -20,7 +20,7 @@ model = "phytec,pcm032"; compatible = "phytec,pcm032"; - memory { + memory@0 { reg = <0x00000000 0x08000000>; // 128MB }; @@ -87,9 +87,9 @@ 0xc800 0 0 2 &mpc5200_pic 1 2 3 0xc800 0 0 3 &mpc5200_pic 1 3 3 0xc800 0 0 4 &mpc5200_pic 0 0 3>; - ranges = <0x42000000 0 0x80000000 0x80000000 0 0x20000000 - 0x02000000 0 0xa0000000 0xa0000000 0 0x10000000 - 0x01000000 0 0x00000000 0xb0000000 0 0x01000000>; + ranges = <0x42000000 0 0x80000000 0x80000000 0 0x20000000>, + <0x02000000 0 0xa0000000 0xa0000000 0 0x10000000>, + <0x01000000 0 0x00000000 0xb0000000 0 0x01000000>; }; localbus { diff --git a/arch/powerpc/boot/dts/tqm5200.dts b/arch/powerpc/boot/dts/tqm5200.dts index 9ed0bc78967e..372177b19e60 100644 --- a/arch/powerpc/boot/dts/tqm5200.dts +++ b/arch/powerpc/boot/dts/tqm5200.dts @@ -32,7 +32,7 @@ }; }; - memory { + memory@0 { device_type = "memory"; reg = <0x00000000 0x04000000>; // 64MB }; @@ -200,8 +200,8 @@ clock-frequency = <0>; // From boot loader interrupts = <2 8 0 2 9 0 2 10 0>; bus-range = <0 0>; - ranges = <0x42000000 0 0x80000000 0x80000000 0 0x10000000 - 0x02000000 0 0x90000000 0x90000000 0 0x10000000 - 0x01000000 0 0x00000000 0xa0000000 0 0x01000000>; + ranges = <0x42000000 0 0x80000000 0x80000000 0 0x10000000>, + <0x02000000 0 0x90000000 0x90000000 0 0x10000000>, + <0x01000000 0 0x00000000 0xa0000000 0 0x01000000>; }; }; diff --git a/arch/powerpc/boot/serial.c b/arch/powerpc/boot/serial.c index 9a19e5905485..54d2522be485 100644 --- a/arch/powerpc/boot/serial.c +++ b/arch/powerpc/boot/serial.c @@ -132,7 +132,7 @@ int serial_console_init(void) else if (dt_is_compatible(devp, "fsl,mpc5200-psc-uart")) rc = mpc5200_psc_console_init(devp, &serial_cd); #endif -#ifdef CONFIG_PPC64_BOOT_WRAPPER +#ifdef CONFIG_PPC_POWERNV else if (dt_is_compatible(devp, "ibm,opal-console-raw")) rc = opal_console_init(devp, &serial_cd); #endif diff --git a/arch/powerpc/boot/wrapper b/arch/powerpc/boot/wrapper index 1cd82564c996..9184eda780fd 100755 --- a/arch/powerpc/boot/wrapper +++ b/arch/powerpc/boot/wrapper @@ -26,6 +26,8 @@ # Stop execution if any command fails set -e +export LC_ALL=C + # Allow for verbose output if [ "$V" = 1 ]; then set -x diff --git a/arch/powerpc/configs/cell_defconfig b/arch/powerpc/configs/cell_defconfig index cc2c0d51f493..7fd9e596ea33 100644 --- a/arch/powerpc/configs/cell_defconfig +++ b/arch/powerpc/configs/cell_defconfig @@ -36,7 +36,6 @@ CONFIG_GEN_RTC=y CONFIG_BINFMT_MISC=m CONFIG_IRQ_ALL_CPUS=y CONFIG_NUMA=y -CONFIG_PPC_64K_PAGES=y CONFIG_SCHED_SMT=y CONFIG_PCIEPORTBUS=y CONFIG_NET=y diff --git a/arch/powerpc/configs/g5_defconfig b/arch/powerpc/configs/g5_defconfig index 63d611cc160f..9d6212a8b195 100644 --- a/arch/powerpc/configs/g5_defconfig +++ b/arch/powerpc/configs/g5_defconfig @@ -26,6 +26,7 @@ CONFIG_CPU_FREQ_PMAC64=y CONFIG_GEN_RTC=y CONFIG_KEXEC=y CONFIG_IRQ_ALL_CPUS=y +CONFIG_PPC_4K_PAGES=y CONFIG_PCI_MSI=y CONFIG_NET=y CONFIG_PACKET=y diff --git a/arch/powerpc/configs/maple_defconfig b/arch/powerpc/configs/maple_defconfig index 9424c1e67e1c..c821a97f4a89 100644 --- a/arch/powerpc/configs/maple_defconfig +++ b/arch/powerpc/configs/maple_defconfig @@ -25,6 +25,7 @@ CONFIG_UDBG_RTAS_CONSOLE=y CONFIG_GEN_RTC=y CONFIG_KEXEC=y CONFIG_IRQ_ALL_CPUS=y +CONFIG_PPC_4K_PAGES=y CONFIG_PCI_MSI=y CONFIG_NET=y CONFIG_PACKET=y diff --git a/arch/powerpc/configs/microwatt_defconfig b/arch/powerpc/configs/microwatt_defconfig index 9465209b8c5b..07d87a4044b2 100644 --- a/arch/powerpc/configs/microwatt_defconfig +++ b/arch/powerpc/configs/microwatt_defconfig @@ -26,6 +26,7 @@ CONFIG_PPC_MICROWATT=y # CONFIG_PPC_OF_BOOT_TRAMPOLINE is not set CONFIG_CPU_FREQ=y CONFIG_HZ_100=y +CONFIG_PPC_4K_PAGES=y # CONFIG_PPC_MEM_KEYS is not set # CONFIG_SECCOMP is not set # CONFIG_MQ_IOSCHED_KYBER is not set diff --git a/arch/powerpc/configs/pasemi_defconfig b/arch/powerpc/configs/pasemi_defconfig index 78606b7e42df..e00a703581c3 100644 --- a/arch/powerpc/configs/pasemi_defconfig +++ b/arch/powerpc/configs/pasemi_defconfig @@ -22,7 +22,6 @@ CONFIG_CPU_FREQ_GOV_POWERSAVE=y CONFIG_CPU_FREQ_GOV_USERSPACE=y CONFIG_CPU_FREQ_GOV_ONDEMAND=y CONFIG_HZ_1000=y -CONFIG_PPC_64K_PAGES=y # CONFIG_SECCOMP is not set CONFIG_PCI_MSI=y CONFIG_PCCARD=y diff --git a/arch/powerpc/configs/powernv_defconfig b/arch/powerpc/configs/powernv_defconfig index 8bfeea6c7de7..49f49c263935 100644 --- a/arch/powerpc/configs/powernv_defconfig +++ b/arch/powerpc/configs/powernv_defconfig @@ -62,7 +62,6 @@ CONFIG_MEMORY_FAILURE=y CONFIG_HWPOISON_INJECT=m CONFIG_TRANSPARENT_HUGEPAGE=y CONFIG_DEFERRED_STRUCT_PAGE_INIT=y -CONFIG_PPC_64K_PAGES=y CONFIG_SCHED_SMT=y CONFIG_PM=y CONFIG_HOTPLUG_PCI=y diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig index 0ad2291337a7..203d0b7f0bb8 100644 --- a/arch/powerpc/configs/ppc64_defconfig +++ b/arch/powerpc/configs/ppc64_defconfig @@ -52,7 +52,6 @@ CONFIG_KEXEC_FILE=y CONFIG_CRASH_DUMP=y CONFIG_FA_DUMP=y CONFIG_IRQ_ALL_CPUS=y -CONFIG_PPC_64K_PAGES=y CONFIG_SCHED_SMT=y CONFIG_HOTPLUG_PCI=y CONFIG_HOTPLUG_PCI_RPA=m diff --git a/arch/powerpc/configs/ps3_defconfig b/arch/powerpc/configs/ps3_defconfig index f300dcb937cc..7c95fab4b920 100644 --- a/arch/powerpc/configs/ps3_defconfig +++ b/arch/powerpc/configs/ps3_defconfig @@ -30,6 +30,7 @@ CONFIG_PS3_LPM=m # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set CONFIG_BINFMT_MISC=y CONFIG_KEXEC=y +CONFIG_PPC_4K_PAGES=y # CONFIG_SPARSEMEM_VMEMMAP is not set # CONFIG_COMPACTION is not set CONFIG_SCHED_SMT=y diff --git a/arch/powerpc/configs/pseries_defconfig b/arch/powerpc/configs/pseries_defconfig index b183629f1bcf..de7641adb899 100644 --- a/arch/powerpc/configs/pseries_defconfig +++ b/arch/powerpc/configs/pseries_defconfig @@ -56,7 +56,6 @@ CONFIG_MEMORY_HOTPLUG=y CONFIG_MEMORY_HOTREMOVE=y CONFIG_KSM=y CONFIG_TRANSPARENT_HUGEPAGE=y -CONFIG_PPC_64K_PAGES=y CONFIG_SCHED_SMT=y CONFIG_HOTPLUG_PCI=y CONFIG_HOTPLUG_PCI_RPA=m diff --git a/arch/powerpc/configs/skiroot_defconfig b/arch/powerpc/configs/skiroot_defconfig index b806a5d3a695..f491875700e8 100644 --- a/arch/powerpc/configs/skiroot_defconfig +++ b/arch/powerpc/configs/skiroot_defconfig @@ -43,7 +43,6 @@ CONFIG_KEXEC_FILE=y CONFIG_PRESERVE_FA_DUMP=y CONFIG_IRQ_ALL_CPUS=y CONFIG_NUMA=y -CONFIG_PPC_64K_PAGES=y CONFIG_SCHED_SMT=y CONFIG_CMDLINE="console=tty0 console=hvc0 ipr.fast_reboot=1 quiet" # CONFIG_SECCOMP is not set @@ -275,7 +274,6 @@ CONFIG_NLS_UTF8=y CONFIG_ENCRYPTED_KEYS=y CONFIG_SECURITY=y CONFIG_HARDENED_USERCOPY=y -# CONFIG_HARDENED_USERCOPY_FALLBACK is not set CONFIG_HARDENED_USERCOPY_PAGESPAN=y CONFIG_FORTIFY_SOURCE=y CONFIG_SECURITY_LOCKDOWN_LSM=y diff --git a/arch/powerpc/include/asm/asm-const.h b/arch/powerpc/include/asm/asm-const.h index 0ce2368bd20f..bfb3c3534877 100644 --- a/arch/powerpc/include/asm/asm-const.h +++ b/arch/powerpc/include/asm/asm-const.h @@ -12,16 +12,4 @@ # define ASM_CONST(x) __ASM_CONST(x) #endif -/* - * Inline assembly memory constraint - * - * GCC 4.9 doesn't properly handle pre update memory constraint "m<>" - * - */ -#if defined(GCC_VERSION) && GCC_VERSION < 50000 -#define UPD_CONSTR "" -#else -#define UPD_CONSTR "<>" -#endif - #endif /* _ASM_POWERPC_ASM_CONST_H */ diff --git a/arch/powerpc/include/asm/atomic.h b/arch/powerpc/include/asm/atomic.h index 6a53ef178bfd..fd594fdbd84d 100644 --- a/arch/powerpc/include/asm/atomic.h +++ b/arch/powerpc/include/asm/atomic.h @@ -27,14 +27,14 @@ static __inline__ int arch_atomic_read(const atomic_t *v) { int t; - __asm__ __volatile__("lwz%U1%X1 %0,%1" : "=r"(t) : "m"UPD_CONSTR(v->counter)); + __asm__ __volatile__("lwz%U1%X1 %0,%1" : "=r"(t) : "m<>"(v->counter)); return t; } static __inline__ void arch_atomic_set(atomic_t *v, int i) { - __asm__ __volatile__("stw%U0%X0 %1,%0" : "=m"UPD_CONSTR(v->counter) : "r"(i)); + __asm__ __volatile__("stw%U0%X0 %1,%0" : "=m<>"(v->counter) : "r"(i)); } #define ATOMIC_OP(op, asm_op) \ @@ -320,14 +320,14 @@ static __inline__ s64 arch_atomic64_read(const atomic64_t *v) { s64 t; - __asm__ __volatile__("ld%U1%X1 %0,%1" : "=r"(t) : "m"UPD_CONSTR(v->counter)); + __asm__ __volatile__("ld%U1%X1 %0,%1" : "=r"(t) : "m<>"(v->counter)); return t; } static __inline__ void arch_atomic64_set(atomic64_t *v, s64 i) { - __asm__ __volatile__("std%U0%X0 %1,%0" : "=m"UPD_CONSTR(v->counter) : "r"(i)); + __asm__ __volatile__("std%U0%X0 %1,%0" : "=m<>"(v->counter) : "r"(i)); } #define ATOMIC64_OP(op, asm_op) \ diff --git a/arch/powerpc/include/asm/book3s/32/kup.h b/arch/powerpc/include/asm/book3s/32/kup.h index d4b145b279f6..9f38040f0641 100644 --- a/arch/powerpc/include/asm/book3s/32/kup.h +++ b/arch/powerpc/include/asm/book3s/32/kup.h @@ -136,6 +136,14 @@ static inline void kuap_kernel_restore(struct pt_regs *regs, unsigned long kuap) if (kuap_is_disabled()) return; + if (unlikely(kuap != KUAP_NONE)) { + current->thread.kuap = KUAP_NONE; + kuap_lock(kuap, false); + } + + if (likely(regs->kuap == KUAP_NONE)) + return; + current->thread.kuap = regs->kuap; kuap_unlock(regs->kuap, false); diff --git a/arch/powerpc/include/asm/book3s/64/hash.h b/arch/powerpc/include/asm/book3s/64/hash.h index d959b0195ad9..674fe0e890dc 100644 --- a/arch/powerpc/include/asm/book3s/64/hash.h +++ b/arch/powerpc/include/asm/book3s/64/hash.h @@ -255,6 +255,8 @@ int hash__create_section_mapping(unsigned long start, unsigned long end, int nid, pgprot_t prot); int hash__remove_section_mapping(unsigned long start, unsigned long end); +void hash__kernel_map_pages(struct page *page, int numpages, int enable); + #endif /* !__ASSEMBLY__ */ #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_BOOK3S_64_HASH_H */ diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index 5d34a8646f08..33e073d6b0c4 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -1101,6 +1101,16 @@ static inline void vmemmap_remove_mapping(unsigned long start, } #endif +#ifdef CONFIG_DEBUG_PAGEALLOC +static inline void __kernel_map_pages(struct page *page, int numpages, int enable) +{ + if (radix_enabled()) + radix__kernel_map_pages(page, numpages, enable); + else + hash__kernel_map_pages(page, numpages, enable); +} +#endif + static inline pte_t pmd_pte(pmd_t pmd) { return __pte_raw(pmd_raw(pmd)); diff --git a/arch/powerpc/include/asm/book3s/64/radix.h b/arch/powerpc/include/asm/book3s/64/radix.h index 59cab558e2f0..d090d9612348 100644 --- a/arch/powerpc/include/asm/book3s/64/radix.h +++ b/arch/powerpc/include/asm/book3s/64/radix.h @@ -316,5 +316,8 @@ int radix__create_section_mapping(unsigned long start, unsigned long end, int nid, pgprot_t prot); int radix__remove_section_mapping(unsigned long start, unsigned long end); #endif /* CONFIG_MEMORY_HOTPLUG */ + +void radix__kernel_map_pages(struct page *page, int numpages, int enable); + #endif /* __ASSEMBLY__ */ #endif diff --git a/arch/powerpc/include/asm/code-patching.h b/arch/powerpc/include/asm/code-patching.h index a95f63788c6b..4ba834599c4d 100644 --- a/arch/powerpc/include/asm/code-patching.h +++ b/arch/powerpc/include/asm/code-patching.h @@ -23,6 +23,7 @@ #define BRANCH_ABSOLUTE 0x2 bool is_offset_in_branch_range(long offset); +bool is_offset_in_cond_branch_range(long offset); int create_branch(struct ppc_inst *instr, const u32 *addr, unsigned long target, int flags); int create_cond_branch(struct ppc_inst *instr, const u32 *addr, diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h index 6b800d3e2681..a1d238255f07 100644 --- a/arch/powerpc/include/asm/interrupt.h +++ b/arch/powerpc/include/asm/interrupt.h @@ -265,13 +265,16 @@ static inline void interrupt_nmi_enter_prepare(struct pt_regs *regs, struct inte local_paca->irq_soft_mask = IRQS_ALL_DISABLED; local_paca->irq_happened |= PACA_IRQ_HARD_DIS; - if (is_implicit_soft_masked(regs)) { - // Adjust regs->softe soft implicit soft-mask, so - // arch_irq_disabled_regs(regs) behaves as expected. + if (!(regs->msr & MSR_EE) || is_implicit_soft_masked(regs)) { + /* + * Adjust regs->softe to be soft-masked if it had not been + * reconcied (e.g., interrupt entry with MSR[EE]=0 but softe + * not yet set disabled), or if it was in an implicit soft + * masked state. This makes arch_irq_disabled_regs(regs) + * behave as expected. + */ regs->softe = IRQS_ALL_DISABLED; } - if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) - BUG_ON(!arch_irq_disabled_regs(regs) && !(regs->msr & MSR_EE)); /* Don't do any per-CPU operations until interrupt state is fixed */ @@ -525,10 +528,9 @@ static __always_inline long ____##func(struct pt_regs *regs) /* kernel/traps.c */ DECLARE_INTERRUPT_HANDLER_NMI(system_reset_exception); #ifdef CONFIG_PPC_BOOK3S_64 -DECLARE_INTERRUPT_HANDLER_ASYNC(machine_check_exception); -#else -DECLARE_INTERRUPT_HANDLER_NMI(machine_check_exception); +DECLARE_INTERRUPT_HANDLER_ASYNC(machine_check_exception_async); #endif +DECLARE_INTERRUPT_HANDLER_NMI(machine_check_exception); DECLARE_INTERRUPT_HANDLER(SMIException); DECLARE_INTERRUPT_HANDLER(handle_hmi_exception); DECLARE_INTERRUPT_HANDLER(unknown_exception); diff --git a/arch/powerpc/include/asm/io.h b/arch/powerpc/include/asm/io.h index f130783c8301..beba4979bff9 100644 --- a/arch/powerpc/include/asm/io.h +++ b/arch/powerpc/include/asm/io.h @@ -122,7 +122,7 @@ static inline u##size name(const volatile u##size __iomem *addr) \ { \ u##size ret; \ __asm__ __volatile__("sync;"#insn"%U1%X1 %0,%1;twi 0,%0,0;isync"\ - : "=r" (ret) : "m"UPD_CONSTR (*addr) : "memory"); \ + : "=r" (ret) : "m<>" (*addr) : "memory"); \ return ret; \ } @@ -130,7 +130,7 @@ static inline u##size name(const volatile u##size __iomem *addr) \ static inline void name(volatile u##size __iomem *addr, u##size val) \ { \ __asm__ __volatile__("sync;"#insn"%U0%X0 %1,%0" \ - : "=m"UPD_CONSTR (*addr) : "r" (val) : "memory"); \ + : "=m<>" (*addr) : "r" (val) : "memory"); \ mmiowb_set_pending(); \ } diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h index bf3b84128525..c361212ac160 100644 --- a/arch/powerpc/include/asm/iommu.h +++ b/arch/powerpc/include/asm/iommu.h @@ -280,12 +280,6 @@ extern void iommu_init_early_dart(struct pci_controller_ops *controller_ops); extern void iommu_init_early_pasemi(void); #if defined(CONFIG_PPC64) && defined(CONFIG_PM) -static inline void iommu_save(void) -{ - if (ppc_md.iommu_save) - ppc_md.iommu_save(); -} - static inline void iommu_restore(void) { if (ppc_md.iommu_restore) diff --git a/arch/powerpc/include/asm/kexec.h b/arch/powerpc/include/asm/kexec.h index 88d0d7cf3a79..c6f250eca3fb 100644 --- a/arch/powerpc/include/asm/kexec.h +++ b/arch/powerpc/include/asm/kexec.h @@ -79,7 +79,6 @@ extern int crash_wake_offline; struct kimage; struct pt_regs; extern void default_machine_kexec(struct kimage *image); -extern int default_machine_kexec_prepare(struct kimage *image); extern void default_machine_crash_shutdown(struct pt_regs *regs); extern int crash_shutdown_register(crash_shutdown_t handler); extern int crash_shutdown_unregister(crash_shutdown_t handler); diff --git a/arch/powerpc/include/asm/kprobes.h b/arch/powerpc/include/asm/kprobes.h index 4fc0e15e23a5..bab364152b29 100644 --- a/arch/powerpc/include/asm/kprobes.h +++ b/arch/powerpc/include/asm/kprobes.h @@ -51,7 +51,7 @@ extern kprobe_opcode_t optprobe_template_end[]; #define flush_insn_slot(p) do { } while (0) #define kretprobe_blacklist_size 0 -void kretprobe_trampoline(void); +void __kretprobe_trampoline(void); extern void arch_remove_kprobe(struct kprobe *p); /* Architecture specific copy of original instruction */ diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h index caaa0f592d8e..3d31f2c59e43 100644 --- a/arch/powerpc/include/asm/kvm_book3s.h +++ b/arch/powerpc/include/asm/kvm_book3s.h @@ -434,7 +434,7 @@ extern int kvmppc_h_logical_ci_store(struct kvm_vcpu *vcpu); #define SPLIT_HACK_OFFS 0xfb000000 /* - * This packs a VCPU ID from the [0..KVM_MAX_VCPU_ID) space down to the + * This packs a VCPU ID from the [0..KVM_MAX_VCPU_IDS) space down to the * [0..KVM_MAX_VCPUS) space, using knowledge of the guest's core stride * (but not its actual threading mode, which is not available) to avoid * collisions. diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h index 19b6942c6969..fff391b9b97b 100644 --- a/arch/powerpc/include/asm/kvm_book3s_64.h +++ b/arch/powerpc/include/asm/kvm_book3s_64.h @@ -378,6 +378,10 @@ static inline unsigned long compute_tlbie_rb(unsigned long v, unsigned long r, rb |= 1; /* L field */ rb |= r & 0xff000 & ((1ul << a_pgshift) - 1); /* LP field */ } + /* + * This sets both bits of the B field in the PTE. 0b1x values are + * reserved, but those will have been filtered by kvmppc_do_h_enter. + */ rb |= (v >> HPTE_V_SSIZE_SHIFT) << 8; /* B field */ return rb; } diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index 080a7feb7731..e4d23193eba7 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -33,11 +33,11 @@ #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE #include <asm/kvm_book3s_asm.h> /* for MAX_SMT_THREADS */ -#define KVM_MAX_VCPU_ID (MAX_SMT_THREADS * KVM_MAX_VCORES) +#define KVM_MAX_VCPU_IDS (MAX_SMT_THREADS * KVM_MAX_VCORES) #define KVM_MAX_NESTED_GUESTS KVMPPC_NR_LPIDS #else -#define KVM_MAX_VCPU_ID KVM_MAX_VCPUS +#define KVM_MAX_VCPU_IDS KVM_MAX_VCPUS #endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */ #define __KVM_HAVE_ARCH_INTC_INITIALIZED @@ -190,7 +190,7 @@ struct kvmppc_spapr_tce_table { u64 size; /* window size in pages */ struct list_head iommu_tables; struct mutex alloc_lock; - struct page *pages[0]; + struct page *pages[]; }; /* XICS components, defined in book3s_xics.c */ diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h index 764f2732a821..9c3c9f04129f 100644 --- a/arch/powerpc/include/asm/machdep.h +++ b/arch/powerpc/include/asm/machdep.h @@ -29,10 +29,9 @@ struct machdep_calls { char *name; #ifdef CONFIG_PPC64 #ifdef CONFIG_PM - void (*iommu_save)(void); void (*iommu_restore)(void); #endif -#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE +#ifdef CONFIG_MEMORY_HOTPLUG unsigned long (*memory_block_size)(void); #endif #endif /* CONFIG_PPC64 */ @@ -43,7 +42,6 @@ struct machdep_calls { void (*setup_arch)(void); /* Optional, may be NULL */ /* Optional, may be NULL. */ void (*show_cpuinfo)(struct seq_file *m); - void (*show_percpuinfo)(struct seq_file *m, int i); /* Returns the current operating frequency of "cpu" in Hz */ unsigned long (*get_proc_freq)(unsigned int cpu); @@ -74,8 +72,6 @@ struct machdep_calls { int (*set_rtc_time)(struct rtc_time *); void (*get_rtc_time)(struct rtc_time *); time64_t (*get_boot_time)(void); - unsigned char (*rtc_read_val)(int addr); - void (*rtc_write_val)(int addr, unsigned char val); void (*calibrate_decr)(void); @@ -141,8 +137,6 @@ struct machdep_calls { May be NULL. */ void (*init)(void); - void (*kgdb_map_scc)(void); - /* * optional PCI "hooks" */ @@ -187,13 +181,6 @@ struct machdep_calls { #ifdef CONFIG_KEXEC_CORE void (*kexec_cpu_down)(int crash_shutdown, int secondary); - /* Called to do what every setup is needed on image and the - * reboot code buffer. Returns 0 on success. - * Provide your own (maybe dummy) implementation if your platform - * claims to support kexec. - */ - int (*machine_kexec_prepare)(struct kimage *image); - /* Called to perform the _real_ kexec. * Do NOT allocate memory or fail here. We are past the point of * no return. diff --git a/arch/powerpc/include/asm/mem_encrypt.h b/arch/powerpc/include/asm/mem_encrypt.h index ba9dab07c1be..2f26b8fc8d29 100644 --- a/arch/powerpc/include/asm/mem_encrypt.h +++ b/arch/powerpc/include/asm/mem_encrypt.h @@ -10,11 +10,6 @@ #include <asm/svm.h> -static inline bool mem_encrypt_active(void) -{ - return is_secure_guest(); -} - static inline bool force_dma_unencrypted(struct device *dev) { return is_secure_guest(); diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h index f06ae00f2a65..b67742e2a9b2 100644 --- a/arch/powerpc/include/asm/nohash/32/pgtable.h +++ b/arch/powerpc/include/asm/nohash/32/pgtable.h @@ -193,10 +193,12 @@ static inline pte_t pte_wrprotect(pte_t pte) } #endif +#ifndef pte_mkexec static inline pte_t pte_mkexec(pte_t pte) { return __pte(pte_val(pte) | _PAGE_EXEC); } +#endif #define pmd_none(pmd) (!pmd_val(pmd)) #define pmd_bad(pmd) (pmd_val(pmd) & _PMD_BAD) @@ -245,7 +247,7 @@ static int number_of_cells_per_pte(pmd_t *pmd, pte_basic_t val, int huge) static inline pte_basic_t pte_update(struct mm_struct *mm, unsigned long addr, pte_t *p, unsigned long clr, unsigned long set, int huge) { - pte_basic_t *entry = &p->pte; + pte_basic_t *entry = (pte_basic_t *)p; pte_basic_t old = pte_val(*p); pte_basic_t new = (old & ~(pte_basic_t)clr) | set; int num, i; @@ -306,30 +308,29 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, } #define __HAVE_ARCH_PTEP_SET_WRPROTECT +#ifndef ptep_set_wrprotect static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { - unsigned long clr = ~pte_val(pte_wrprotect(__pte(~0))); - unsigned long set = pte_val(pte_wrprotect(__pte(0))); - - pte_update(mm, addr, ptep, clr, set, 0); + pte_update(mm, addr, ptep, _PAGE_RW, 0, 0); } +#endif +#ifndef __ptep_set_access_flags static inline void __ptep_set_access_flags(struct vm_area_struct *vma, pte_t *ptep, pte_t entry, unsigned long address, int psize) { - pte_t pte_set = pte_mkyoung(pte_mkdirty(pte_mkwrite(pte_mkexec(__pte(0))))); - pte_t pte_clr = pte_mkyoung(pte_mkdirty(pte_mkwrite(pte_mkexec(__pte(~0))))); - unsigned long set = pte_val(entry) & pte_val(pte_set); - unsigned long clr = ~pte_val(entry) & ~pte_val(pte_clr); + unsigned long set = pte_val(entry) & + (_PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_RW | _PAGE_EXEC); int huge = psize > mmu_virtual_psize ? 1 : 0; - pte_update(vma->vm_mm, address, ptep, clr, set, huge); + pte_update(vma->vm_mm, address, ptep, 0, set, huge); flush_tlb_page(vma, address); } +#endif static inline int pte_young(pte_t pte) { diff --git a/arch/powerpc/include/asm/nohash/32/pte-8xx.h b/arch/powerpc/include/asm/nohash/32/pte-8xx.h index fcc48d590d88..1a89ebdc3acc 100644 --- a/arch/powerpc/include/asm/nohash/32/pte-8xx.h +++ b/arch/powerpc/include/asm/nohash/32/pte-8xx.h @@ -136,6 +136,28 @@ static inline pte_t pte_mkhuge(pte_t pte) #define pte_mkhuge pte_mkhuge +static inline pte_basic_t pte_update(struct mm_struct *mm, unsigned long addr, pte_t *p, + unsigned long clr, unsigned long set, int huge); + +static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) +{ + pte_update(mm, addr, ptep, 0, _PAGE_RO, 0); +} +#define ptep_set_wrprotect ptep_set_wrprotect + +static inline void __ptep_set_access_flags(struct vm_area_struct *vma, pte_t *ptep, + pte_t entry, unsigned long address, int psize) +{ + unsigned long set = pte_val(entry) & (_PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_EXEC); + unsigned long clr = ~pte_val(entry) & _PAGE_RO; + int huge = psize > mmu_virtual_psize ? 1 : 0; + + pte_update(vma->vm_mm, address, ptep, clr, set, huge); + + flush_tlb_page(vma, address); +} +#define __ptep_set_access_flags __ptep_set_access_flags + static inline unsigned long pgd_leaf_size(pgd_t pgd) { if (pgd_val(pgd) & _PMD_PAGE_8M) diff --git a/arch/powerpc/include/asm/nohash/64/pgtable.h b/arch/powerpc/include/asm/nohash/64/pgtable.h index d081704b13fb..9d2905a47410 100644 --- a/arch/powerpc/include/asm/nohash/64/pgtable.h +++ b/arch/powerpc/include/asm/nohash/64/pgtable.h @@ -118,11 +118,6 @@ static inline pte_t pte_wrprotect(pte_t pte) return __pte(pte_val(pte) & ~_PAGE_RW); } -static inline pte_t pte_mkexec(pte_t pte) -{ - return __pte(pte_val(pte) | _PAGE_EXEC); -} - #define PMD_BAD_BITS (PTE_TABLE_SIZE-1) #define PUD_BAD_BITS (PMD_TABLE_SIZE-1) diff --git a/arch/powerpc/include/asm/nohash/pte-book3e.h b/arch/powerpc/include/asm/nohash/pte-book3e.h index 813918f40765..f798640422c2 100644 --- a/arch/powerpc/include/asm/nohash/pte-book3e.h +++ b/arch/powerpc/include/asm/nohash/pte-book3e.h @@ -48,7 +48,7 @@ #define _PAGE_WRITETHRU 0x800000 /* W: cache write-through */ /* "Higher level" linux bit combinations */ -#define _PAGE_EXEC _PAGE_BAP_UX /* .. and was cache cleaned */ +#define _PAGE_EXEC (_PAGE_BAP_SX | _PAGE_BAP_UX) /* .. and was cache cleaned */ #define _PAGE_RW (_PAGE_BAP_SW | _PAGE_BAP_UW) /* User write permission */ #define _PAGE_KERNEL_RW (_PAGE_BAP_SW | _PAGE_BAP_SR | _PAGE_DIRTY) #define _PAGE_KERNEL_RO (_PAGE_BAP_SR) @@ -93,11 +93,11 @@ /* Permission masks used to generate the __P and __S table */ #define PAGE_NONE __pgprot(_PAGE_BASE) #define PAGE_SHARED __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_RW) -#define PAGE_SHARED_X __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_RW | _PAGE_EXEC) +#define PAGE_SHARED_X __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_RW | _PAGE_BAP_UX) #define PAGE_COPY __pgprot(_PAGE_BASE | _PAGE_USER) -#define PAGE_COPY_X __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_EXEC) +#define PAGE_COPY_X __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_BAP_UX) #define PAGE_READONLY __pgprot(_PAGE_BASE | _PAGE_USER) -#define PAGE_READONLY_X __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_EXEC) +#define PAGE_READONLY_X __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_BAP_UX) #ifndef __ASSEMBLY__ static inline pte_t pte_mkprivileged(pte_t pte) @@ -113,6 +113,16 @@ static inline pte_t pte_mkuser(pte_t pte) } #define pte_mkuser pte_mkuser + +static inline pte_t pte_mkexec(pte_t pte) +{ + if (pte_val(pte) & _PAGE_BAP_UR) + return __pte((pte_val(pte) & ~_PAGE_BAP_SX) | _PAGE_BAP_UX); + else + return __pte((pte_val(pte) & ~_PAGE_BAP_UX) | _PAGE_BAP_SX); +} +#define pte_mkexec pte_mkexec + #endif /* __ASSEMBLY__ */ #endif /* __KERNEL__ */ diff --git a/arch/powerpc/include/asm/nohash/tlbflush.h b/arch/powerpc/include/asm/nohash/tlbflush.h index 1edb7243e515..c08d25e3e626 100644 --- a/arch/powerpc/include/asm/nohash/tlbflush.h +++ b/arch/powerpc/include/asm/nohash/tlbflush.h @@ -32,11 +32,26 @@ extern void flush_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end); extern void flush_tlb_kernel_range(unsigned long start, unsigned long end); +#ifdef CONFIG_PPC_8xx +static inline void local_flush_tlb_mm(struct mm_struct *mm) +{ + unsigned int pid = READ_ONCE(mm->context.id); + + if (pid != MMU_NO_CONTEXT) + asm volatile ("sync; tlbia; isync" : : : "memory"); +} + +static inline void local_flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr) +{ + asm volatile ("tlbie %0; sync" : : "r" (vmaddr) : "memory"); +} +#else extern void local_flush_tlb_mm(struct mm_struct *mm); extern void local_flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr); extern void __local_flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr, int tsize, int ind); +#endif #ifdef CONFIG_SMP extern void flush_tlb_mm(struct mm_struct *mm); diff --git a/arch/powerpc/include/asm/paravirt.h b/arch/powerpc/include/asm/paravirt.h index bcb7b5f917be..eb7df559ae74 100644 --- a/arch/powerpc/include/asm/paravirt.h +++ b/arch/powerpc/include/asm/paravirt.h @@ -21,7 +21,7 @@ static inline bool is_shared_processor(void) return static_branch_unlikely(&shared_processor); } -/* If bit 0 is set, the cpu has been preempted */ +/* If bit 0 is set, the cpu has been ceded, conferred, or preempted */ static inline u32 yield_count_of(int cpu) { __be32 yield_count = READ_ONCE(lppaca_of(cpu).yield_count); @@ -92,17 +92,47 @@ static inline void prod_cpu(int cpu) #define vcpu_is_preempted vcpu_is_preempted static inline bool vcpu_is_preempted(int cpu) { + /* + * The dispatch/yield bit alone is an imperfect indicator of + * whether the hypervisor has dispatched @cpu to run on a physical + * processor. When it is clear, @cpu is definitely not preempted. + * But when it is set, it means only that it *might* be, subject to + * other conditions. So we check other properties of the VM and + * @cpu first, resorting to the yield count last. + */ + + /* + * Hypervisor preemption isn't possible in dedicated processor + * mode by definition. + */ if (!is_shared_processor()) return false; #ifdef CONFIG_PPC_SPLPAR if (!is_kvm_guest()) { - int first_cpu = cpu_first_thread_sibling(smp_processor_id()); + int first_cpu; /* - * Preemption can only happen at core granularity. This CPU - * is not preempted if one of the CPU of this core is not - * preempted. + * The result of vcpu_is_preempted() is used in a + * speculative way, and is always subject to invalidation + * by events internal and external to Linux. While we can + * be called in preemptable context (in the Linux sense), + * we're not accessing per-cpu resources in a way that can + * race destructively with Linux scheduler preemption and + * migration, and callers can tolerate the potential for + * error introduced by sampling the CPU index without + * pinning the task to it. So it is permissible to use + * raw_smp_processor_id() here to defeat the preempt debug + * warnings that can arise from using smp_processor_id() + * in arbitrary contexts. + */ + first_cpu = cpu_first_thread_sibling(raw_smp_processor_id()); + + /* + * The PowerVM hypervisor dispatches VMs on a whole core + * basis. So we know that a thread sibling of the local CPU + * cannot have been preempted by the hypervisor, even if it + * has called H_CONFER, which will set the yield bit. */ if (cpu_first_thread_sibling(cpu) == first_cpu) return false; diff --git a/arch/powerpc/include/asm/pgtable-types.h b/arch/powerpc/include/asm/pgtable-types.h index d11b4c61d686..efed0db7b1db 100644 --- a/arch/powerpc/include/asm/pgtable-types.h +++ b/arch/powerpc/include/asm/pgtable-types.h @@ -2,17 +2,33 @@ #ifndef _ASM_POWERPC_PGTABLE_TYPES_H #define _ASM_POWERPC_PGTABLE_TYPES_H +#if defined(__CHECKER__) || !defined(CONFIG_PPC32) +#define STRICT_MM_TYPECHECKS +#endif + /* PTE level */ #if defined(CONFIG_PPC_8xx) && defined(CONFIG_PPC_16K_PAGES) typedef struct { pte_basic_t pte, pte1, pte2, pte3; } pte_t; -#else +#elif defined(STRICT_MM_TYPECHECKS) typedef struct { pte_basic_t pte; } pte_t; +#else +typedef pte_basic_t pte_t; #endif + +#if defined(STRICT_MM_TYPECHECKS) || \ + (defined(CONFIG_PPC_8xx) && defined(CONFIG_PPC_16K_PAGES)) #define __pte(x) ((pte_t) { (x) }) static inline pte_basic_t pte_val(pte_t x) { return x.pte; } +#else +#define __pte(x) ((pte_t)(x)) +static inline pte_basic_t pte_val(pte_t x) +{ + return x; +} +#endif /* PMD level */ #ifdef CONFIG_PPC64 diff --git a/arch/powerpc/include/asm/ppc-pci.h b/arch/powerpc/include/asm/ppc-pci.h index 2b9edbf6e929..f6cf0159024e 100644 --- a/arch/powerpc/include/asm/ppc-pci.h +++ b/arch/powerpc/include/asm/ppc-pci.h @@ -55,11 +55,6 @@ void eeh_pe_dev_mode_mark(struct eeh_pe *pe, int mode); void eeh_sysfs_add_device(struct pci_dev *pdev); void eeh_sysfs_remove_device(struct pci_dev *pdev); -static inline const char *eeh_driver_name(struct pci_dev *pdev) -{ - return (pdev && pdev->driver) ? pdev->driver->name : "<null>"; -} - #endif /* CONFIG_EEH */ #define PCI_BUSNO(bdfn) ((bdfn >> 8) & 0xff) diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h index 1c538a9a11e0..7be24048b8d1 100644 --- a/arch/powerpc/include/asm/ppc_asm.h +++ b/arch/powerpc/include/asm/ppc_asm.h @@ -28,8 +28,8 @@ #else #define SAVE_GPR(n, base) stw n,GPR0+4*(n)(base) #define REST_GPR(n, base) lwz n,GPR0+4*(n)(base) -#define SAVE_NVGPRS(base) stmw 13, GPR0+4*13(base) -#define REST_NVGPRS(base) lmw 13, GPR0+4*13(base) +#define SAVE_NVGPRS(base) SAVE_GPR(13, base); SAVE_8GPRS(14, base); SAVE_10GPRS(22, base) +#define REST_NVGPRS(base) REST_GPR(13, base); REST_8GPRS(14, base); REST_10GPRS(22, base) #endif #define SAVE_2GPRS(n, base) SAVE_GPR(n, base); SAVE_GPR(n+1, base) diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h index f348e564f7dd..e39bd0ff69f3 100644 --- a/arch/powerpc/include/asm/processor.h +++ b/arch/powerpc/include/asm/processor.h @@ -300,7 +300,7 @@ struct thread_struct { #define task_pt_regs(tsk) ((tsk)->thread.regs) -unsigned long get_wchan(struct task_struct *p); +unsigned long __get_wchan(struct task_struct *p); #define KSTK_EIP(tsk) ((tsk)->thread.regs? (tsk)->thread.regs->nip: 0) #define KSTK_ESP(tsk) ((tsk)->thread.regs? (tsk)->thread.regs->gpr[1]: 0) diff --git a/arch/powerpc/include/asm/sections.h b/arch/powerpc/include/asm/sections.h index 6e4af4492a14..79cb7a25a5fb 100644 --- a/arch/powerpc/include/asm/sections.h +++ b/arch/powerpc/include/asm/sections.h @@ -6,21 +6,8 @@ #include <linux/elf.h> #include <linux/uaccess.h> -#define arch_is_kernel_initmem_freed arch_is_kernel_initmem_freed - #include <asm-generic/sections.h> -extern bool init_mem_is_free; - -static inline int arch_is_kernel_initmem_freed(unsigned long addr) -{ - if (!init_mem_is_free) - return 0; - - return addr >= (unsigned long)__init_begin && - addr < (unsigned long)__init_end; -} - extern char __head_end[]; #ifdef __powerpc64__ diff --git a/arch/powerpc/include/asm/security_features.h b/arch/powerpc/include/asm/security_features.h index 792eefaf230b..27574f218b37 100644 --- a/arch/powerpc/include/asm/security_features.h +++ b/arch/powerpc/include/asm/security_features.h @@ -39,6 +39,11 @@ static inline bool security_ftr_enabled(u64 feature) return !!(powerpc_security_features & feature); } +#ifdef CONFIG_PPC_BOOK3S_64 +enum stf_barrier_type stf_barrier_type_get(void); +#else +static inline enum stf_barrier_type stf_barrier_type_get(void) { return STF_BARRIER_NONE; } +#endif // Features indicating support for Spectre/Meltdown mitigations diff --git a/arch/powerpc/include/asm/simple_spinlock.h b/arch/powerpc/include/asm/simple_spinlock.h index 8985791a2ba5..7ae6aeef8464 100644 --- a/arch/powerpc/include/asm/simple_spinlock.h +++ b/arch/powerpc/include/asm/simple_spinlock.h @@ -123,27 +123,6 @@ static inline void arch_spin_lock(arch_spinlock_t *lock) } } -static inline -void arch_spin_lock_flags(arch_spinlock_t *lock, unsigned long flags) -{ - unsigned long flags_dis; - - while (1) { - if (likely(__arch_spin_trylock(lock) == 0)) - break; - local_save_flags(flags_dis); - local_irq_restore(flags); - do { - HMT_low(); - if (is_shared_processor()) - splpar_spin_yield(lock); - } while (unlikely(lock->slock != 0)); - HMT_medium(); - local_irq_restore(flags_dis); - } -} -#define arch_spin_lock_flags arch_spin_lock_flags - static inline void arch_spin_unlock(arch_spinlock_t *lock) { __asm__ __volatile__("# arch_spin_unlock\n\t" diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h index 7ef1cd8168a0..007332a4a732 100644 --- a/arch/powerpc/include/asm/smp.h +++ b/arch/powerpc/include/asm/smp.h @@ -87,22 +87,7 @@ int is_cpu_dead(unsigned int cpu); /* 32-bit */ extern int smp_hw_index[]; -/* - * This is particularly ugly: it appears we can't actually get the definition - * of task_struct here, but we need access to the CPU this task is running on. - * Instead of using task_struct we're using _TASK_CPU which is extracted from - * asm-offsets.h by kbuild to get the current processor ID. - * - * This also needs to be safeguarded when building asm-offsets.s because at - * that time _TASK_CPU is not defined yet. It could have been guarded by - * _TASK_CPU itself, but we want the build to fail if _TASK_CPU is missing - * when building something else than asm-offsets.s - */ -#ifdef GENERATING_ASM_OFFSETS -#define raw_smp_processor_id() (0) -#else -#define raw_smp_processor_id() (*(unsigned int *)((void *)current + _TASK_CPU)) -#endif +#define raw_smp_processor_id() (current_thread_info()->cpu) #define hard_smp_processor_id() (smp_hw_index[smp_processor_id()]) static inline int get_hard_smp_processor_id(int cpu) diff --git a/arch/powerpc/include/asm/static_call.h b/arch/powerpc/include/asm/static_call.h new file mode 100644 index 000000000000..0a0bc79bd1fa --- /dev/null +++ b/arch/powerpc/include/asm/static_call.h @@ -0,0 +1,28 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_POWERPC_STATIC_CALL_H +#define _ASM_POWERPC_STATIC_CALL_H + +#define __PPC_SCT(name, inst) \ + asm(".pushsection .text, \"ax\" \n" \ + ".align 5 \n" \ + ".globl " STATIC_CALL_TRAMP_STR(name) " \n" \ + STATIC_CALL_TRAMP_STR(name) ": \n" \ + inst " \n" \ + " lis 12,2f@ha \n" \ + " lwz 12,2f@l(12) \n" \ + " mtctr 12 \n" \ + " bctr \n" \ + "1: li 3, 0 \n" \ + " blr \n" \ + "2: .long 0 \n" \ + ".type " STATIC_CALL_TRAMP_STR(name) ", @function \n" \ + ".size " STATIC_CALL_TRAMP_STR(name) ", . - " STATIC_CALL_TRAMP_STR(name) " \n" \ + ".popsection \n") + +#define PPC_SCT_RET0 20 /* Offset of label 1 */ +#define PPC_SCT_DATA 28 /* Offset of label 2 */ + +#define ARCH_DEFINE_STATIC_CALL_TRAMP(name, func) __PPC_SCT(name, "b " #func) +#define ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name) __PPC_SCT(name, "blr") + +#endif /* _ASM_POWERPC_STATIC_CALL_H */ diff --git a/arch/powerpc/include/asm/syscall.h b/arch/powerpc/include/asm/syscall.h index c60ebd04b2ed..52d05b465e3e 100644 --- a/arch/powerpc/include/asm/syscall.h +++ b/arch/powerpc/include/asm/syscall.h @@ -103,16 +103,6 @@ static inline void syscall_get_arguments(struct task_struct *task, } } -static inline void syscall_set_arguments(struct task_struct *task, - struct pt_regs *regs, - const unsigned long *args) -{ - memcpy(®s->gpr[3], args, 6 * sizeof(args[0])); - - /* Also copy the first argument into orig_gpr3 */ - regs->orig_gpr3 = args[0]; -} - static inline int syscall_get_arch(struct task_struct *task) { if (is_32bit_task()) diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h index b4ec6c7dd72e..5725029aaa29 100644 --- a/arch/powerpc/include/asm/thread_info.h +++ b/arch/powerpc/include/asm/thread_info.h @@ -47,6 +47,9 @@ struct thread_info { int preempt_count; /* 0 => preemptable, <0 => BUG */ +#ifdef CONFIG_SMP + unsigned int cpu; +#endif unsigned long local_flags; /* private flags for thread */ #ifdef CONFIG_LIVEPATCH unsigned long *livepatch_sp; diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h index 22c79ab40006..63316100080c 100644 --- a/arch/powerpc/include/asm/uaccess.h +++ b/arch/powerpc/include/asm/uaccess.h @@ -86,7 +86,7 @@ __pu_failed: \ "1: " op "%U1%X1 %0,%1 # put_user\n" \ EX_TABLE(1b, %l2) \ : \ - : "r" (x), "m"UPD_CONSTR (*addr) \ + : "r" (x), "m<>" (*addr) \ : \ : label) @@ -143,7 +143,7 @@ do { \ "1: "op"%U1%X1 %0, %1 # get_user\n" \ EX_TABLE(1b, %l2) \ : "=r" (x) \ - : "m"UPD_CONSTR (*addr) \ + : "m<>" (*addr) \ : \ : label) @@ -200,7 +200,7 @@ __gus_failed: \ ".previous\n" \ EX_TABLE(1b, 3b) \ : "=r" (err), "=r" (x) \ - : "m"UPD_CONSTR (*addr), "i" (-EFAULT), "0" (err)) + : "m<>" (*addr), "i" (-EFAULT), "0" (err)) #ifdef __powerpc64__ #define __get_user_asm2(x, addr, err) \ diff --git a/arch/powerpc/include/uapi/asm/perf_regs.h b/arch/powerpc/include/uapi/asm/perf_regs.h index 578b3ee86105..749a2e3af89e 100644 --- a/arch/powerpc/include/uapi/asm/perf_regs.h +++ b/arch/powerpc/include/uapi/asm/perf_regs.h @@ -61,27 +61,35 @@ enum perf_event_powerpc_regs { PERF_REG_POWERPC_PMC4, PERF_REG_POWERPC_PMC5, PERF_REG_POWERPC_PMC6, - /* Max regs without the extended regs */ + PERF_REG_POWERPC_SDAR, + PERF_REG_POWERPC_SIAR, + /* Max mask value for interrupt regs w/o extended regs */ PERF_REG_POWERPC_MAX = PERF_REG_POWERPC_MMCRA + 1, + /* Max mask value for interrupt regs including extended regs */ + PERF_REG_EXTENDED_MAX = PERF_REG_POWERPC_SIAR + 1, }; #define PERF_REG_PMU_MASK ((1ULL << PERF_REG_POWERPC_MAX) - 1) -/* Exclude MMCR3, SIER2, SIER3 for CPU_FTR_ARCH_300 */ -#define PERF_EXCLUDE_REG_EXT_300 (7ULL << PERF_REG_POWERPC_MMCR3) - /* * PERF_REG_EXTENDED_MASK value for CPU_FTR_ARCH_300 - * includes 9 SPRS from MMCR0 to PMC6 excluding the - * unsupported SPRS in PERF_EXCLUDE_REG_EXT_300. + * includes 11 SPRS from MMCR0 to SIAR excluding the + * unsupported SPRS MMCR3, SIER2 and SIER3. */ -#define PERF_REG_PMU_MASK_300 ((0xfffULL << PERF_REG_POWERPC_MMCR0) - PERF_EXCLUDE_REG_EXT_300) +#define PERF_REG_PMU_MASK_300 \ + ((1ULL << PERF_REG_POWERPC_MMCR0) | (1ULL << PERF_REG_POWERPC_MMCR1) | \ + (1ULL << PERF_REG_POWERPC_MMCR2) | (1ULL << PERF_REG_POWERPC_PMC1) | \ + (1ULL << PERF_REG_POWERPC_PMC2) | (1ULL << PERF_REG_POWERPC_PMC3) | \ + (1ULL << PERF_REG_POWERPC_PMC4) | (1ULL << PERF_REG_POWERPC_PMC5) | \ + (1ULL << PERF_REG_POWERPC_PMC6) | (1ULL << PERF_REG_POWERPC_SDAR) | \ + (1ULL << PERF_REG_POWERPC_SIAR)) /* * PERF_REG_EXTENDED_MASK value for CPU_FTR_ARCH_31 - * includes 12 SPRs from MMCR0 to PMC6. + * includes 14 SPRs from MMCR0 to SIAR. */ -#define PERF_REG_PMU_MASK_31 (0xfffULL << PERF_REG_POWERPC_MMCR0) +#define PERF_REG_PMU_MASK_31 \ + (PERF_REG_PMU_MASK_300 | (1ULL << PERF_REG_POWERPC_MMCR3) | \ + (1ULL << PERF_REG_POWERPC_SIER2) | (1ULL << PERF_REG_POWERPC_SIER3)) -#define PERF_REG_EXTENDED_MAX (PERF_REG_POWERPC_PMC6 + 1) #endif /* _UAPI_ASM_POWERPC_PERF_REGS_H */ diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index 7be36c1e1db6..0e3640e14eb1 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -106,7 +106,7 @@ extra-y += vmlinux.lds obj-$(CONFIG_RELOCATABLE) += reloc_$(BITS).o -obj-$(CONFIG_PPC32) += entry_32.o setup_32.o early_32.o +obj-$(CONFIG_PPC32) += entry_32.o setup_32.o early_32.o static_call.o obj-$(CONFIG_PPC64) += dma-iommu.o iommu.o obj-$(CONFIG_KGDB) += kgdb.o obj-$(CONFIG_BOOTX_TEXT) += btext.o diff --git a/arch/powerpc/kernel/align.c b/arch/powerpc/kernel/align.c index bbb4181621dd..bf96b954a4eb 100644 --- a/arch/powerpc/kernel/align.c +++ b/arch/powerpc/kernel/align.c @@ -349,6 +349,7 @@ int fix_alignment(struct pt_regs *regs) if (op.type != CACHEOP + DCBZ) return -EINVAL; PPC_WARN_ALIGNMENT(dcbz, regs); + WARN_ON_ONCE(!user_mode(regs)); r = emulate_dcbz(op.ea, regs); } else { if (type == LARX || type == STCX) diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index e563d3222d69..cc05522f50bf 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -9,8 +9,6 @@ * #defines from the assembly-language output. */ -#define GENERATING_ASM_OFFSETS /* asm/smp.h */ - #include <linux/compat.h> #include <linux/signal.h> #include <linux/sched.h> @@ -93,7 +91,7 @@ int main(void) #endif /* CONFIG_PPC64 */ OFFSET(TASK_STACK, task_struct, stack); #ifdef CONFIG_SMP - OFFSET(TASK_CPU, task_struct, cpu); + OFFSET(TASK_CPU, task_struct, thread_info.cpu); #endif #ifdef CONFIG_LIVEPATCH diff --git a/arch/powerpc/kernel/audit.c b/arch/powerpc/kernel/audit.c index a2dddd7f3d09..1bcfca5fdf67 100644 --- a/arch/powerpc/kernel/audit.c +++ b/arch/powerpc/kernel/audit.c @@ -47,15 +47,17 @@ int audit_classify_syscall(int abi, unsigned syscall) #endif switch(syscall) { case __NR_open: - return 2; + return AUDITSC_OPEN; case __NR_openat: - return 3; + return AUDITSC_OPENAT; case __NR_socketcall: - return 4; + return AUDITSC_SOCKETCALL; case __NR_execve: - return 5; + return AUDITSC_EXECVE; + case __NR_openat2: + return AUDITSC_OPENAT2; default: - return 0; + return AUDITSC_NATIVE; } } diff --git a/arch/powerpc/kernel/compat_audit.c b/arch/powerpc/kernel/compat_audit.c index 55c6ccda0a85..d92ffe4e5dc1 100644 --- a/arch/powerpc/kernel/compat_audit.c +++ b/arch/powerpc/kernel/compat_audit.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #undef __powerpc64__ +#include <linux/audit_arch.h> #include <asm/unistd.h> unsigned ppc32_dir_class[] = { @@ -31,14 +32,16 @@ int ppc32_classify_syscall(unsigned syscall) { switch(syscall) { case __NR_open: - return 2; + return AUDITSC_OPEN; case __NR_openat: - return 3; + return AUDITSC_OPENAT; case __NR_socketcall: - return 4; + return AUDITSC_SOCKETCALL; case __NR_execve: - return 5; + return AUDITSC_EXECVE; + case __NR_openat2: + return AUDITSC_OPENAT2; default: - return 1; + return AUDITSC_COMPAT; } } diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c index 111249fd619d..038ce8d9061d 100644 --- a/arch/powerpc/kernel/dma-iommu.c +++ b/arch/powerpc/kernel/dma-iommu.c @@ -184,6 +184,15 @@ u64 dma_iommu_get_required_mask(struct device *dev) struct iommu_table *tbl = get_iommu_table_base(dev); u64 mask; + if (dev_is_pci(dev)) { + u64 bypass_mask = dma_direct_get_required_mask(dev); + + if (dma_iommu_dma_supported(dev, bypass_mask)) { + dev_info(dev, "%s: returning bypass mask 0x%llx\n", __func__, bypass_mask); + return bypass_mask; + } + } + if (!tbl) return 0; diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c index 358aee7c2d79..ba527fb52993 100644 --- a/arch/powerpc/kernel/dt_cpu_ftrs.c +++ b/arch/powerpc/kernel/dt_cpu_ftrs.c @@ -1095,8 +1095,8 @@ static int __init dt_cpu_ftrs_scan_callback(unsigned long node, const char cpufeatures_setup_finished(); - memblock_free(__pa(dt_cpu_features), - sizeof(struct dt_cpu_feature)*nr_dt_cpu_features); + memblock_free(dt_cpu_features, + sizeof(struct dt_cpu_feature) * nr_dt_cpu_features); return 0; } diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index e9b597ed423c..28bb1e7263a6 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -399,6 +399,14 @@ out: return ret; } +static inline const char *eeh_driver_name(struct pci_dev *pdev) +{ + if (pdev) + return dev_driver_string(&pdev->dev); + + return "<null>"; +} + /** * eeh_dev_check_failure - Check if all 1's data is due to EEH slot freeze * @edev: eeh device @@ -589,6 +597,7 @@ EXPORT_SYMBOL(eeh_check_failure); /** * eeh_pci_enable - Enable MMIO or DMA transfers for this slot * @pe: EEH PE + * @function: EEH option * * This routine should be called to reenable frozen MMIO or DMA * so that it would work correctly again. It's useful while doing @@ -761,8 +770,8 @@ int pcibios_set_pcie_reset_state(struct pci_dev *dev, enum pcie_reset_state stat } /** - * eeh_set_pe_freset - Check the required reset for the indicated device - * @data: EEH device + * eeh_set_dev_freset - Check the required reset for the indicated device + * @edev: EEH device * @flag: return value * * Each device might have its preferred reset type: fundamental or @@ -801,6 +810,7 @@ static void eeh_pe_refreeze_passed(struct eeh_pe *root) /** * eeh_pe_reset_full - Complete a full reset process on the indicated PE * @pe: EEH PE + * @include_passed: include passed-through devices? * * This function executes a full reset procedure on a PE, including setting * the appropriate flags, performing a fundamental or hot reset, and then @@ -937,6 +947,7 @@ static struct notifier_block eeh_device_nb = { /** * eeh_init - System wide EEH initialization + * @ops: struct to trace EEH operation callback functions * * It's the platform's job to call this from an arch_initcall(). */ @@ -1442,6 +1453,7 @@ static int eeh_pe_reenable_devices(struct eeh_pe *pe, bool include_passed) * eeh_pe_reset - Issue PE reset according to specified type * @pe: EEH PE * @option: reset type + * @include_passed: include passed-through devices? * * The routine is called to reset the specified PE with the * indicated type, either fundamental reset or hot reset. @@ -1513,12 +1525,12 @@ EXPORT_SYMBOL_GPL(eeh_pe_configure); * eeh_pe_inject_err - Injecting the specified PCI error to the indicated PE * @pe: the indicated PE * @type: error type - * @function: error function + * @func: error function * @addr: address * @mask: address mask * * The routine is called to inject the specified PCI error, which - * is determined by @type and @function, to the indicated PE for + * is determined by @type and @func, to the indicated PE for * testing purpose. */ int eeh_pe_inject_err(struct eeh_pe *pe, int type, int func, diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index 3eff6a4888e7..350dab18e137 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -104,13 +104,13 @@ static bool eeh_edev_actionable(struct eeh_dev *edev) */ static inline struct pci_driver *eeh_pcid_get(struct pci_dev *pdev) { - if (!pdev || !pdev->driver) + if (!pdev || !pdev->dev.driver) return NULL; - if (!try_module_get(pdev->driver->driver.owner)) + if (!try_module_get(pdev->dev.driver->owner)) return NULL; - return pdev->driver; + return to_pci_driver(pdev->dev.driver); } /** @@ -122,10 +122,10 @@ static inline struct pci_driver *eeh_pcid_get(struct pci_dev *pdev) */ static inline void eeh_pcid_put(struct pci_dev *pdev) { - if (!pdev || !pdev->driver) + if (!pdev || !pdev->dev.driver) return; - module_put(pdev->driver->driver.owner); + module_put(pdev->dev.driver->owner); } /** diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 37859e62a8dc..eaf1f72131a1 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -1243,7 +1243,7 @@ EXC_COMMON_BEGIN(machine_check_common) li r10,MSR_RI mtmsrd r10,1 addi r3,r1,STACK_FRAME_OVERHEAD - bl machine_check_exception + bl machine_check_exception_async b interrupt_return_srr @@ -1303,7 +1303,11 @@ END_FTR_SECTION_IFSET(CPU_FTR_HVMODE) subi r12,r12,1 sth r12,PACA_IN_MCE(r13) - /* Invoke machine_check_exception to print MCE event and panic. */ + /* + * Invoke machine_check_exception to print MCE event and panic. + * This is the NMI version of the handler because we are called from + * the early handler which is a true NMI. + */ addi r3,r1,STACK_FRAME_OVERHEAD bl machine_check_exception @@ -1665,27 +1669,30 @@ EXC_COMMON_BEGIN(program_check_common) */ andi. r10,r12,MSR_PR - bne 2f /* If userspace, go normal path */ + bne .Lnormal_stack /* If userspace, go normal path */ andis. r10,r12,(SRR1_PROGTM)@h - bne 1f /* If TM, emergency */ + bne .Lemergency_stack /* If TM, emergency */ cmpdi r1,-INT_FRAME_SIZE /* check if r1 is in userspace */ - blt 2f /* normal path if not */ + blt .Lnormal_stack /* normal path if not */ /* Use the emergency stack */ -1: andi. r10,r12,MSR_PR /* Set CR0 correctly for label */ +.Lemergency_stack: + andi. r10,r12,MSR_PR /* Set CR0 correctly for label */ /* 3 in EXCEPTION_PROLOG_COMMON */ mr r10,r1 /* Save r1 */ ld r1,PACAEMERGSP(r13) /* Use emergency stack */ subi r1,r1,INT_FRAME_SIZE /* alloc stack frame */ __ISTACK(program_check)=0 __GEN_COMMON_BODY program_check - b 3f -2: + b .Ldo_program_check + +.Lnormal_stack: __ISTACK(program_check)=1 __GEN_COMMON_BODY program_check -3: + +.Ldo_program_check: addi r3,r1,STACK_FRAME_OVERHEAD bl program_check_exception REST_NVGPRS(r1) /* instruction emulation may change GPRs */ diff --git a/arch/powerpc/kernel/firmware.c b/arch/powerpc/kernel/firmware.c index c7022c41cc31..20328f72f9f2 100644 --- a/arch/powerpc/kernel/firmware.c +++ b/arch/powerpc/kernel/firmware.c @@ -31,11 +31,10 @@ int __init check_kvm_guest(void) if (!hyper_node) return 0; - if (!of_device_is_compatible(hyper_node, "linux,kvm")) - return 0; - - static_branch_enable(&kvm_guest); + if (of_device_is_compatible(hyper_node, "linux,kvm")) + static_branch_enable(&kvm_guest); + of_node_put(hyper_node); return 0; } core_initcall(check_kvm_guest); // before kvm_guest_init() diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S index 9bdb95f5694f..2d596881b70e 100644 --- a/arch/powerpc/kernel/head_8xx.S +++ b/arch/powerpc/kernel/head_8xx.S @@ -755,7 +755,7 @@ _GLOBAL(mmu_pin_tlb) cmplw r6, r9 bdnzt lt, 2b -4: LOAD_REG_IMMEDIATE(r8, 0xf0 | _PAGE_SPS | _PAGE_SH | _PAGE_PRESENT) +4: LOAD_REG_IMMEDIATE(r8, 0xf0 | _PAGE_DIRTY | _PAGE_SPS | _PAGE_SH | _PAGE_PRESENT) 2: ori r0, r6, MD_EVALID mtspr SPRN_MD_CTR, r5 mtspr SPRN_MD_EPN, r0 diff --git a/arch/powerpc/kernel/head_booke.h b/arch/powerpc/kernel/head_booke.h index e5503420b6c6..ef8d1b1c234e 100644 --- a/arch/powerpc/kernel/head_booke.h +++ b/arch/powerpc/kernel/head_booke.h @@ -465,12 +465,21 @@ label: bl do_page_fault; \ b interrupt_return +/* + * Instruction TLB Error interrupt handlers may call InstructionStorage + * directly without clearing ESR, so the ESR at this point may be left over + * from a prior interrupt. + * + * In any case, do_page_fault for BOOK3E does not use ESR and always expects + * dsisr to be 0. ESR_DST from a prior store in particular would confuse fault + * handling. + */ #define INSTRUCTION_STORAGE_EXCEPTION \ START_EXCEPTION(InstructionStorage) \ - NORMAL_EXCEPTION_PROLOG(0x400, INST_STORAGE); \ - mfspr r5,SPRN_ESR; /* Grab the ESR and save it */ \ + NORMAL_EXCEPTION_PROLOG(0x400, INST_STORAGE); \ + li r5,0; /* Store 0 in regs->esr (dsisr) */ \ stw r5,_ESR(r11); \ - stw r12, _DEAR(r11); /* Pass SRR0 as arg2 */ \ + stw r12, _DEAR(r11); /* Set regs->dear (dar) to SRR0 */ \ prepare_transfer_to_handler; \ bl do_page_fault; \ b interrupt_return diff --git a/arch/powerpc/kernel/hw_breakpoint_constraints.c b/arch/powerpc/kernel/hw_breakpoint_constraints.c index 675d1f66ab72..42b967e3d85c 100644 --- a/arch/powerpc/kernel/hw_breakpoint_constraints.c +++ b/arch/powerpc/kernel/hw_breakpoint_constraints.c @@ -127,15 +127,6 @@ bool wp_check_constraints(struct pt_regs *regs, struct ppc_inst instr, return false; } -static int cache_op_size(void) -{ -#ifdef __powerpc64__ - return ppc64_caches.l1d.block_size; -#else - return L1_CACHE_BYTES; -#endif -} - void wp_get_instr_detail(struct pt_regs *regs, struct ppc_inst *instr, int *type, int *size, unsigned long *ea) { @@ -147,14 +138,14 @@ void wp_get_instr_detail(struct pt_regs *regs, struct ppc_inst *instr, analyse_instr(&op, regs, *instr); *type = GETTYPE(op.type); *ea = op.ea; -#ifdef __powerpc64__ + if (!(regs->msr & MSR_64BIT)) *ea &= 0xffffffffUL; -#endif + *size = GETSIZE(op.type); if (*type == CACHEOP) { - *size = cache_op_size(); + *size = l1_dcache_bytes(); *ea &= ~(*size - 1); } else if (*type == LOAD_VMX || *type == STORE_VMX) { *ea &= ~(*size - 1); diff --git a/arch/powerpc/kernel/idle_book3s.S b/arch/powerpc/kernel/idle_book3s.S index abb719b21cae..3d97fb833834 100644 --- a/arch/powerpc/kernel/idle_book3s.S +++ b/arch/powerpc/kernel/idle_book3s.S @@ -126,14 +126,16 @@ _GLOBAL(idle_return_gpr_loss) /* * This is the sequence required to execute idle instructions, as * specified in ISA v2.07 (and earlier). MSR[IR] and MSR[DR] must be 0. - * - * The 0(r1) slot is used to save r2 in isa206, so use that here. + * We have to store a GPR somewhere, ptesync, then reload it, and create + * a false dependency on the result of the load. It doesn't matter which + * GPR we store, or where we store it. We have already stored r2 to the + * stack at -8(r1) in isa206_idle_insn_mayloss, so use that. */ #define IDLE_STATE_ENTER_SEQ_NORET(IDLE_INST) \ /* Magic NAP/SLEEP/WINKLE mode enter sequence */ \ - std r2,0(r1); \ + std r2,-8(r1); \ ptesync; \ - ld r2,0(r1); \ + ld r2,-8(r1); \ 236: cmpd cr0,r2,r2; \ bne 236b; \ IDLE_INST; \ diff --git a/arch/powerpc/kernel/interrupt.c b/arch/powerpc/kernel/interrupt.c index a73f3f70a657..835b626cd476 100644 --- a/arch/powerpc/kernel/interrupt.c +++ b/arch/powerpc/kernel/interrupt.c @@ -18,6 +18,7 @@ #include <asm/switch_to.h> #include <asm/syscall.h> #include <asm/time.h> +#include <asm/tm.h> #include <asm/unistd.h> #if defined(CONFIG_PPC_ADV_DEBUG_REGS) && defined(CONFIG_PPC32) @@ -136,6 +137,48 @@ notrace long system_call_exception(long r3, long r4, long r5, */ irq_soft_mask_regs_set_state(regs, IRQS_ENABLED); + /* + * If system call is called with TM active, set _TIF_RESTOREALL to + * prevent RFSCV being used to return to userspace, because POWER9 + * TM implementation has problems with this instruction returning to + * transactional state. Final register values are not relevant because + * the transaction will be aborted upon return anyway. Or in the case + * of unsupported_scv SIGILL fault, the return state does not much + * matter because it's an edge case. + */ + if (IS_ENABLED(CONFIG_PPC_TRANSACTIONAL_MEM) && + unlikely(MSR_TM_TRANSACTIONAL(regs->msr))) + current_thread_info()->flags |= _TIF_RESTOREALL; + + /* + * If the system call was made with a transaction active, doom it and + * return without performing the system call. Unless it was an + * unsupported scv vector, in which case it's treated like an illegal + * instruction. + */ +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + if (unlikely(MSR_TM_TRANSACTIONAL(regs->msr)) && + !trap_is_unsupported_scv(regs)) { + /* Enable TM in the kernel, and disable EE (for scv) */ + hard_irq_disable(); + mtmsr(mfmsr() | MSR_TM); + + /* tabort, this dooms the transaction, nothing else */ + asm volatile(".long 0x7c00071d | ((%0) << 16)" + :: "r"(TM_CAUSE_SYSCALL|TM_CAUSE_PERSISTENT)); + + /* + * Userspace will never see the return value. Execution will + * resume after the tbegin. of the aborted transaction with the + * checkpointed register state. A context switch could occur + * or signal delivered to the process before resuming the + * doomed transaction context, but that should all be handled + * as expected. + */ + return -ENOSYS; + } +#endif // CONFIG_PPC_TRANSACTIONAL_MEM + local_irq_enable(); if (unlikely(current_thread_info()->flags & _TIF_SYSCALL_DOTRACE)) { @@ -223,7 +266,7 @@ static void check_return_regs_valid(struct pt_regs *regs) if (trap_is_scv(regs)) return; - trap = regs->trap; + trap = TRAP(regs); // EE in HV mode sets HSRRs like 0xea0 if (cpu_has_feature(CPU_FTR_HVMODE) && trap == INTERRUPT_EXTERNAL) trap = 0xea0; diff --git a/arch/powerpc/kernel/interrupt_64.S b/arch/powerpc/kernel/interrupt_64.S index d4212d2ff0b5..ec950b08a8dc 100644 --- a/arch/powerpc/kernel/interrupt_64.S +++ b/arch/powerpc/kernel/interrupt_64.S @@ -12,7 +12,6 @@ #include <asm/mmu.h> #include <asm/ppc_asm.h> #include <asm/ptrace.h> -#include <asm/tm.h> .section ".toc","aw" SYS_CALL_TABLE: @@ -55,12 +54,6 @@ COMPAT_SYS_CALL_TABLE: .globl system_call_vectored_\name system_call_vectored_\name: _ASM_NOKPROBE_SYMBOL(system_call_vectored_\name) -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM -BEGIN_FTR_SECTION - extrdi. r10, r12, 1, (63-MSR_TS_T_LG) /* transaction active? */ - bne tabort_syscall -END_FTR_SECTION_IFSET(CPU_FTR_TM) -#endif SCV_INTERRUPT_TO_KERNEL mr r10,r1 ld r1,PACAKSAVE(r13) @@ -247,12 +240,6 @@ _ASM_NOKPROBE_SYMBOL(system_call_common_real) .globl system_call_common system_call_common: _ASM_NOKPROBE_SYMBOL(system_call_common) -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM -BEGIN_FTR_SECTION - extrdi. r10, r12, 1, (63-MSR_TS_T_LG) /* transaction active? */ - bne tabort_syscall -END_FTR_SECTION_IFSET(CPU_FTR_TM) -#endif mr r10,r1 ld r1,PACAKSAVE(r13) std r10,0(r1) @@ -425,34 +412,6 @@ SOFT_MASK_TABLE(.Lsyscall_rst_start, 1b) RESTART_TABLE(.Lsyscall_rst_start, .Lsyscall_rst_end, syscall_restart) #endif -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM -tabort_syscall: -_ASM_NOKPROBE_SYMBOL(tabort_syscall) - /* Firstly we need to enable TM in the kernel */ - mfmsr r10 - li r9, 1 - rldimi r10, r9, MSR_TM_LG, 63-MSR_TM_LG - mtmsrd r10, 0 - - /* tabort, this dooms the transaction, nothing else */ - li r9, (TM_CAUSE_SYSCALL|TM_CAUSE_PERSISTENT) - TABORT(R9) - - /* - * Return directly to userspace. We have corrupted user register state, - * but userspace will never see that register state. Execution will - * resume after the tbegin of the aborted transaction with the - * checkpointed register state. - */ - li r9, MSR_RI - andc r10, r10, r9 - mtmsrd r10, 1 - mtspr SPRN_SRR0, r11 - mtspr SPRN_SRR1, r12 - RFI_TO_USER - b . /* prevent speculative execution */ -#endif - /* * If MSR EE/RI was never enabled, IRQs not reconciled, NVGPRs not * touched, no exit work created, then this can be used. diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index 551b653228c4..c4f1d6b7d992 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -229,6 +229,9 @@ notrace void arch_local_irq_restore(unsigned long mask) return; } + if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) + WARN_ON_ONCE(in_nmi() || in_hardirq()); + /* * After the stb, interrupts are unmasked and there are no interrupts * pending replay. The restart sequence makes this atomic with @@ -321,6 +324,9 @@ notrace void arch_local_irq_restore(unsigned long mask) if (mask) return; + if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) + WARN_ON_ONCE(in_nmi() || in_hardirq()); + /* * From this point onward, we can take interrupts, preempt, * etc... unless we got hard-disabled. We check if an event diff --git a/arch/powerpc/kernel/kprobes-ftrace.c b/arch/powerpc/kernel/kprobes-ftrace.c index 7154d58338cc..072ebe7f290b 100644 --- a/arch/powerpc/kernel/kprobes-ftrace.c +++ b/arch/powerpc/kernel/kprobes-ftrace.c @@ -26,7 +26,6 @@ void kprobe_ftrace_handler(unsigned long nip, unsigned long parent_nip, return; regs = ftrace_get_regs(fregs); - preempt_disable_notrace(); p = get_kprobe((kprobe_opcode_t *)nip); if (unlikely(!p) || kprobe_disabled(p)) goto out; @@ -61,7 +60,6 @@ void kprobe_ftrace_handler(unsigned long nip, unsigned long parent_nip, __this_cpu_write(current_kprobe, NULL); } out: - preempt_enable_notrace(); ftrace_test_recursion_unlock(bit); } NOKPROBE_SYMBOL(kprobe_ftrace_handler); diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c index 7a7cd6bda53e..86d77ff056a6 100644 --- a/arch/powerpc/kernel/kprobes.c +++ b/arch/powerpc/kernel/kprobes.c @@ -237,7 +237,7 @@ void arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs) ri->fp = NULL; /* Replace the return addr with trampoline addr */ - regs->link = (unsigned long)kretprobe_trampoline; + regs->link = (unsigned long)__kretprobe_trampoline; } NOKPROBE_SYMBOL(arch_prepare_kretprobe); @@ -403,12 +403,12 @@ NOKPROBE_SYMBOL(kprobe_handler); * - When the probed function returns, this probe * causes the handlers to fire */ -asm(".global kretprobe_trampoline\n" - ".type kretprobe_trampoline, @function\n" - "kretprobe_trampoline:\n" +asm(".global __kretprobe_trampoline\n" + ".type __kretprobe_trampoline, @function\n" + "__kretprobe_trampoline:\n" "nop\n" "blr\n" - ".size kretprobe_trampoline, .-kretprobe_trampoline\n"); + ".size __kretprobe_trampoline, .-__kretprobe_trampoline\n"); /* * Called when the probe at kretprobe trampoline is hit @@ -417,7 +417,7 @@ static int trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) { unsigned long orig_ret_address; - orig_ret_address = __kretprobe_trampoline_handler(regs, &kretprobe_trampoline, NULL); + orig_ret_address = __kretprobe_trampoline_handler(regs, NULL); /* * We get here through one of two paths: * 1. by taking a trap -> kprobe_handler() -> here @@ -427,7 +427,7 @@ static int trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) * as it is used to determine the return address from the trap. * For (2), since nip is not honoured with optprobes, we instead setup * the link register properly so that the subsequent 'blr' in - * kretprobe_trampoline jumps back to the right instruction. + * __kretprobe_trampoline jumps back to the right instruction. * * For nip, we should set the address to the previous instruction since * we end up emulating it in kprobe_handler(), which increments the nip @@ -542,19 +542,8 @@ int kprobe_fault_handler(struct pt_regs *regs, int trapnr) } NOKPROBE_SYMBOL(kprobe_fault_handler); -unsigned long arch_deref_entry_point(void *entry) -{ -#ifdef PPC64_ELF_ABI_v1 - if (!kernel_text_address((unsigned long)entry)) - return ppc_global_function_entry(entry); - else -#endif - return (unsigned long)entry; -} -NOKPROBE_SYMBOL(arch_deref_entry_point); - static struct kprobe trampoline_p = { - .addr = (kprobe_opcode_t *) &kretprobe_trampoline, + .addr = (kprobe_opcode_t *) &__kretprobe_trampoline, .pre_handler = trampoline_probe_handler }; @@ -565,7 +554,7 @@ int __init arch_init_kprobes(void) int arch_trampoline_kprobe(struct kprobe *p) { - if (p->addr == (kprobe_opcode_t *)&kretprobe_trampoline) + if (p->addr == (kprobe_opcode_t *)&__kretprobe_trampoline) return 1; return 0; diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c index 617eba82531c..6568823cf306 100644 --- a/arch/powerpc/kernel/kvm.c +++ b/arch/powerpc/kernel/kvm.c @@ -669,7 +669,8 @@ static void __init kvm_use_magic_page(void) on_each_cpu(kvm_map_magic_page, &features, 1); /* Quick self-test to see if the mapping works */ - if (!fault_in_pages_readable((const char *)KVM_MAGIC_PAGE, sizeof(u32))) { + if (fault_in_readable((const char __user *)KVM_MAGIC_PAGE, + sizeof(u32))) { kvm_patching_worked = false; return; } diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c index 47a683cd00d2..fd829f7f25a4 100644 --- a/arch/powerpc/kernel/mce.c +++ b/arch/powerpc/kernel/mce.c @@ -249,6 +249,7 @@ void machine_check_queue_event(void) { int index; struct machine_check_event evt; + unsigned long msr; if (!get_mce_event(&evt, MCE_EVENT_RELEASE)) return; @@ -262,8 +263,20 @@ void machine_check_queue_event(void) memcpy(&local_paca->mce_info->mce_event_queue[index], &evt, sizeof(evt)); - /* Queue irq work to process this event later. */ - irq_work_queue(&mce_event_process_work); + /* + * Queue irq work to process this event later. Before + * queuing the work enable translation for non radix LPAR, + * as irq_work_queue may try to access memory outside RMO + * region. + */ + if (!radix_enabled() && firmware_has_feature(FW_FEATURE_LPAR)) { + msr = mfmsr(); + mtmsr(msr | MSR_IR | MSR_DR); + irq_work_queue(&mce_event_process_work); + mtmsr(msr); + } else { + irq_work_queue(&mce_event_process_work); + } } void mce_common_process_ue(struct pt_regs *regs, diff --git a/arch/powerpc/kernel/optprobes.c b/arch/powerpc/kernel/optprobes.c index c79899abcec8..ce1903064031 100644 --- a/arch/powerpc/kernel/optprobes.c +++ b/arch/powerpc/kernel/optprobes.c @@ -56,7 +56,7 @@ static unsigned long can_optimize(struct kprobe *p) * has a 'nop' instruction, which can be emulated. * So further checks can be skipped. */ - if (p->addr == (kprobe_opcode_t *)&kretprobe_trampoline) + if (p->addr == (kprobe_opcode_t *)&__kretprobe_trampoline) return addr + sizeof(kprobe_opcode_t); /* @@ -301,8 +301,8 @@ void arch_unoptimize_kprobes(struct list_head *oplist, struct list_head *done_li } } -int arch_within_optimized_kprobe(struct optimized_kprobe *op, unsigned long addr) +int arch_within_optimized_kprobe(struct optimized_kprobe *op, kprobe_opcode_t *addr) { - return ((unsigned long)op->kp.addr <= addr && - (unsigned long)op->kp.addr + RELATIVEJUMP_SIZE > addr); + return (op->kp.addr <= addr && + op->kp.addr + (RELATIVEJUMP_SIZE / sizeof(kprobe_opcode_t)) > addr); } diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c index 9bd30cac852b..4208b4044d12 100644 --- a/arch/powerpc/kernel/paca.c +++ b/arch/powerpc/kernel/paca.c @@ -322,8 +322,8 @@ void __init free_unused_pacas(void) new_ptrs_size = sizeof(struct paca_struct *) * nr_cpu_ids; if (new_ptrs_size < paca_ptrs_size) - memblock_free(__pa(paca_ptrs) + new_ptrs_size, - paca_ptrs_size - new_ptrs_size); + memblock_phys_free(__pa(paca_ptrs) + new_ptrs_size, + paca_ptrs_size - new_ptrs_size); paca_nr_cpu_ids = nr_cpu_ids; paca_ptrs_size = new_ptrs_size; @@ -331,8 +331,8 @@ void __init free_unused_pacas(void) #ifdef CONFIG_PPC_BOOK3S_64 if (early_radix_enabled()) { /* Ugly fixup, see new_slb_shadow() */ - memblock_free(__pa(paca_ptrs[boot_cpuid]->slb_shadow_ptr), - sizeof(struct slb_shadow)); + memblock_phys_free(__pa(paca_ptrs[boot_cpuid]->slb_shadow_ptr), + sizeof(struct slb_shadow)); paca_ptrs[boot_cpuid]->slb_shadow_ptr = NULL; } #endif diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index c3573430919d..6749905932f4 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -1059,7 +1059,7 @@ void pcibios_bus_add_device(struct pci_dev *dev) ppc_md.pcibios_bus_add_device(dev); } -int pcibios_add_device(struct pci_dev *dev) +int pcibios_device_add(struct pci_dev *dev) { struct irq_domain *d; diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 50436b52c213..406d7ee9e322 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -2111,14 +2111,11 @@ int validate_sp(unsigned long sp, struct task_struct *p, EXPORT_SYMBOL(validate_sp); -static unsigned long __get_wchan(struct task_struct *p) +static unsigned long ___get_wchan(struct task_struct *p) { unsigned long ip, sp; int count = 0; - if (!p || p == current || task_is_running(p)) - return 0; - sp = p->thread.ksp; if (!validate_sp(sp, p, STACK_FRAME_OVERHEAD)) return 0; @@ -2137,14 +2134,14 @@ static unsigned long __get_wchan(struct task_struct *p) return 0; } -unsigned long get_wchan(struct task_struct *p) +unsigned long __get_wchan(struct task_struct *p) { unsigned long ret; if (!try_get_task_stack(p)) return 0; - ret = __get_wchan(p); + ret = ___get_wchan(p); put_task_stack(p); diff --git a/arch/powerpc/kernel/security.c b/arch/powerpc/kernel/security.c index 1a998490fe60..15fb5ea1b9ea 100644 --- a/arch/powerpc/kernel/security.c +++ b/arch/powerpc/kernel/security.c @@ -263,6 +263,11 @@ static int __init handle_no_stf_barrier(char *p) early_param("no_stf_barrier", handle_no_stf_barrier); +enum stf_barrier_type stf_barrier_type_get(void) +{ + return stf_enabled_flush_types; +} + /* This is the generic flag used by other architectures */ static int __init handle_ssbd(char *p) { diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index b1e43b69a559..4f1322b65760 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -278,9 +278,6 @@ static int show_cpuinfo(struct seq_file *m, void *v) seq_printf(m, "clock\t\t: %lu.%06luMHz\n", proc_freq / 1000000, proc_freq % 1000000); - if (ppc_md.show_percpuinfo != NULL) - ppc_md.show_percpuinfo(m, cpu_id); - /* If we are a Freescale core do a simple check so * we dont have to keep adding cases in the future */ if (PVR_VER(pvr) & 0x8000) { @@ -825,7 +822,7 @@ static void __init smp_setup_pacas(void) set_hard_smp_processor_id(cpu, cpu_to_phys_id[cpu]); } - memblock_free(__pa(cpu_to_phys_id), nr_cpu_ids * sizeof(u32)); + memblock_free(cpu_to_phys_id, nr_cpu_ids * sizeof(u32)); cpu_to_phys_id = NULL; } #endif diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index eaa79a0996d1..6052f5d5ded3 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -812,7 +812,7 @@ static void * __init pcpu_alloc_bootmem(unsigned int cpu, size_t size, static void __init pcpu_free_bootmem(void *ptr, size_t size) { - memblock_free(__pa(ptr), size); + memblock_free(ptr, size); } static int pcpu_cpu_distance(unsigned int from, unsigned int to) @@ -912,7 +912,7 @@ void __init setup_per_cpu_areas(void) } #endif -#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE +#ifdef CONFIG_MEMORY_HOTPLUG unsigned long memory_block_size_bytes(void) { if (ppc_md.memory_block_size) diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c index e600764a926c..b93b87df499d 100644 --- a/arch/powerpc/kernel/signal.c +++ b/arch/powerpc/kernel/signal.c @@ -293,10 +293,8 @@ void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags) do_signal(current); } - if (thread_info_flags & _TIF_NOTIFY_RESUME) { + if (thread_info_flags & _TIF_NOTIFY_RESUME) tracehook_notify_resume(regs); - rseq_handle_notify_resume(NULL, regs); - } } static unsigned long get_tm_stackpointer(struct task_struct *tsk) diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index 933ab95805a6..00a9c9cd6d42 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -1048,7 +1048,7 @@ SYSCALL_DEFINE3(swapcontext, struct ucontext __user *, old_ctx, if (new_ctx == NULL) return 0; if (!access_ok(new_ctx, ctx_size) || - fault_in_pages_readable((u8 __user *)new_ctx, ctx_size)) + fault_in_readable((char __user *)new_ctx, ctx_size)) return -EFAULT; /* @@ -1239,7 +1239,7 @@ SYSCALL_DEFINE3(debug_setcontext, struct ucontext __user *, ctx, #endif if (!access_ok(ctx, sizeof(*ctx)) || - fault_in_pages_readable((u8 __user *)ctx, sizeof(*ctx))) + fault_in_readable((char __user *)ctx, sizeof(*ctx))) return -EFAULT; /* diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index 8ead9b3f47c6..ef518535d436 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -688,7 +688,7 @@ SYSCALL_DEFINE3(swapcontext, struct ucontext __user *, old_ctx, if (new_ctx == NULL) return 0; if (!access_ok(new_ctx, ctx_size) || - fault_in_pages_readable((u8 __user *)new_ctx, ctx_size)) + fault_in_readable((char __user *)new_ctx, ctx_size)) return -EFAULT; /* diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 9cc7d3dbf439..c23ee842c4c3 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -1223,7 +1223,7 @@ static void cpu_idle_thread_init(unsigned int cpu, struct task_struct *idle) paca_ptrs[cpu]->kstack = (unsigned long)task_stack_page(idle) + THREAD_SIZE - STACK_FRAME_OVERHEAD; #endif - idle->cpu = cpu; + task_thread_info(idle)->cpu = cpu; secondary_current = current_set[cpu] = idle; } @@ -1313,18 +1313,13 @@ int __cpu_up(unsigned int cpu, struct task_struct *tidle) int cpu_to_core_id(int cpu) { struct device_node *np; - const __be32 *reg; int id = -1; np = of_get_cpu_node(cpu, NULL); if (!np) goto out; - reg = of_get_property(np, "reg", NULL); - if (!reg) - goto out; - - id = be32_to_cpup(reg); + id = of_get_cpu_hwid(np, 0); out: of_node_put(np); return id; @@ -1730,8 +1725,6 @@ void __cpu_die(unsigned int cpu) void arch_cpu_idle_dead(void) { - sched_preempt_enable_no_resched(); - /* * Disable on the down path. This will be re-enabled by * start_secondary() via start_secondary_resume() below diff --git a/arch/powerpc/kernel/stacktrace.c b/arch/powerpc/kernel/stacktrace.c index 9e4a4a7af380..a2443d61728e 100644 --- a/arch/powerpc/kernel/stacktrace.c +++ b/arch/powerpc/kernel/stacktrace.c @@ -155,7 +155,7 @@ int __no_sanitize_address arch_stack_walk_reliable(stack_trace_consume_fn consum * Mark stacktraces with kretprobed functions on them * as unreliable. */ - if (ip == (unsigned long)kretprobe_trampoline) + if (ip == (unsigned long)__kretprobe_trampoline) return -EINVAL; #endif diff --git a/arch/powerpc/kernel/static_call.c b/arch/powerpc/kernel/static_call.c new file mode 100644 index 000000000000..863a7aa24650 --- /dev/null +++ b/arch/powerpc/kernel/static_call.c @@ -0,0 +1,37 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/memory.h> +#include <linux/static_call.h> + +#include <asm/code-patching.h> + +void arch_static_call_transform(void *site, void *tramp, void *func, bool tail) +{ + int err; + bool is_ret0 = (func == __static_call_return0); + unsigned long target = (unsigned long)(is_ret0 ? tramp + PPC_SCT_RET0 : func); + bool is_short = is_offset_in_branch_range((long)target - (long)tramp); + + if (!tramp) + return; + + mutex_lock(&text_mutex); + + if (func && !is_short) { + err = patch_instruction(tramp + PPC_SCT_DATA, ppc_inst(target)); + if (err) + goto out; + } + + if (!func) + err = patch_instruction(tramp, ppc_inst(PPC_RAW_BLR())); + else if (is_short) + err = patch_branch(tramp, target, 0); + else + err = patch_instruction(tramp, ppc_inst(PPC_RAW_NOP())); +out: + mutex_unlock(&text_mutex); + + if (err) + panic("%s: patching failed %pS at %pS\n", __func__, func, tramp); +} +EXPORT_SYMBOL_GPL(arch_static_call_transform); diff --git a/arch/powerpc/kernel/swsusp_64.c b/arch/powerpc/kernel/swsusp_64.c index aeea97ad85cf..16ee3baaf09a 100644 --- a/arch/powerpc/kernel/swsusp_64.c +++ b/arch/powerpc/kernel/swsusp_64.c @@ -17,8 +17,3 @@ void do_after_copyback(void) touch_softlockup_watchdog(); mb(); } - -void _iommu_save(void) -{ - iommu_save(); -} diff --git a/arch/powerpc/kernel/swsusp_asm64.S b/arch/powerpc/kernel/swsusp_asm64.S index 6d3189830dd3..96bb20715aa9 100644 --- a/arch/powerpc/kernel/swsusp_asm64.S +++ b/arch/powerpc/kernel/swsusp_asm64.S @@ -128,7 +128,6 @@ END_FW_FTR_SECTION_IFCLR(FW_FEATURE_LPAR) * stack pointer on the stack like a real stackframe */ addi r1,r1,-128 - bl _iommu_save bl swsusp_save /* restore LR */ diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c index defecb3b1b15..08d8072d6e7a 100644 --- a/arch/powerpc/kernel/sysfs.c +++ b/arch/powerpc/kernel/sysfs.c @@ -928,7 +928,8 @@ static int unregister_cpu_online(unsigned int cpu) struct device_attribute *attrs, *pmc_attrs; int i, nattrs; - BUG_ON(!c->hotpluggable); + if (WARN_RATELIMIT(!c->hotpluggable, "cpu %d can't be offlined\n", cpu)) + return -EBUSY; #ifdef CONFIG_PPC64 if (cpu_has_feature(CPU_FTR_SMT)) diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index 934d8ae66cc6..cae8f03a44fe 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -631,8 +631,12 @@ void timer_broadcast_interrupt(void) #endif #ifdef CONFIG_SUSPEND -static void generic_suspend_disable_irqs(void) +/* Overrides the weak version in kernel/power/main.c */ +void arch_suspend_disable_irqs(void) { + if (ppc_md.suspend_disable_irqs) + ppc_md.suspend_disable_irqs(); + /* Disable the decrementer, so that it doesn't interfere * with suspending. */ @@ -642,23 +646,11 @@ static void generic_suspend_disable_irqs(void) set_dec(decrementer_max); } -static void generic_suspend_enable_irqs(void) -{ - local_irq_enable(); -} - -/* Overrides the weak version in kernel/power/main.c */ -void arch_suspend_disable_irqs(void) -{ - if (ppc_md.suspend_disable_irqs) - ppc_md.suspend_disable_irqs(); - generic_suspend_disable_irqs(); -} - /* Overrides the weak version in kernel/power/main.c */ void arch_suspend_enable_irqs(void) { - generic_suspend_enable_irqs(); + local_irq_enable(); + if (ppc_md.suspend_enable_irqs) ppc_md.suspend_enable_irqs(); } diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index aac8c0412ff9..11741703d26e 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -340,10 +340,16 @@ static bool exception_common(int signr, struct pt_regs *regs, int code, return false; } - show_signal_msg(signr, regs, code, addr); + /* + * Must not enable interrupts even for user-mode exception, because + * this can be called from machine check, which may be a NMI or IRQ + * which don't like interrupts being enabled. Could check for + * in_hardirq || in_nmi perhaps, but there doesn't seem to be a good + * reason why _exception() should enable irqs for an exception handler, + * the handlers themselves do that directly. + */ - if (arch_irqs_disabled()) - interrupt_cond_local_irq_enable(regs); + show_signal_msg(signr, regs, code, addr); current->thread.trap_nr = code; @@ -790,24 +796,22 @@ void die_mce(const char *str, struct pt_regs *regs, long err) * do_exit() checks for in_interrupt() and panics in that case, so * exit the irq/nmi before calling die. */ - if (IS_ENABLED(CONFIG_PPC_BOOK3S_64)) - irq_exit(); - else + if (in_nmi()) nmi_exit(); + else + irq_exit(); die(str, regs, err); } /* - * BOOK3S_64 does not call this handler as a non-maskable interrupt + * BOOK3S_64 does not usually call this handler as a non-maskable interrupt * (it uses its own early real-mode handler to handle the MCE proper * and then raises irq_work to call this handler when interrupts are - * enabled). + * enabled). The only time when this is not true is if the early handler + * is unrecoverable, then it does call this directly to try to get a + * message out. */ -#ifdef CONFIG_PPC_BOOK3S_64 -DEFINE_INTERRUPT_HANDLER_ASYNC(machine_check_exception) -#else -DEFINE_INTERRUPT_HANDLER_NMI(machine_check_exception) -#endif +static void __machine_check_exception(struct pt_regs *regs) { int recover = 0; @@ -841,12 +845,19 @@ bail: /* Must die if the interrupt is not recoverable */ if (regs_is_unrecoverable(regs)) die_mce("Unrecoverable Machine check", regs, SIGBUS); +} #ifdef CONFIG_PPC_BOOK3S_64 - return; -#else - return 0; +DEFINE_INTERRUPT_HANDLER_ASYNC(machine_check_exception_async) +{ + __machine_check_exception(regs); +} #endif +DEFINE_INTERRUPT_HANDLER_NMI(machine_check_exception) +{ + __machine_check_exception(regs); + + return 0; } DEFINE_INTERRUPT_HANDLER(SMIException) /* async? */ diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index 40bdefe9caa7..18e42c74abdd 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -143,6 +143,12 @@ SECTIONS SOFT_MASK_TABLE(8) RESTART_TABLE(8) + .opd : AT(ADDR(.opd) - LOAD_OFFSET) { + __start_opd = .; + KEEP(*(.opd)) + __end_opd = .; + } + . = ALIGN(8); __stf_entry_barrier_fixup : AT(ADDR(__stf_entry_barrier_fixup) - LOAD_OFFSET) { __start___stf_entry_barrier_fixup = .; @@ -339,12 +345,6 @@ SECTIONS *(.branch_lt) } - .opd : AT(ADDR(.opd) - LOAD_OFFSET) { - __start_opd = .; - KEEP(*(.opd)) - __end_opd = .; - } - . = ALIGN(256); .got : AT(ADDR(.got) - LOAD_OFFSET) { __toc_start = .; diff --git a/arch/powerpc/kexec/core.c b/arch/powerpc/kexec/core.c index 48525e8b5730..a2242017e55f 100644 --- a/arch/powerpc/kexec/core.c +++ b/arch/powerpc/kexec/core.c @@ -48,19 +48,6 @@ void machine_crash_shutdown(struct pt_regs *regs) default_machine_crash_shutdown(regs); } -/* - * Do what every setup is needed on image and the - * reboot code buffer to allow us to avoid allocations - * later. - */ -int machine_kexec_prepare(struct kimage *image) -{ - if (ppc_md.machine_kexec_prepare) - return ppc_md.machine_kexec_prepare(image); - else - return default_machine_kexec_prepare(image); -} - void machine_kexec_cleanup(struct kimage *image) { } diff --git a/arch/powerpc/kexec/core_32.c b/arch/powerpc/kexec/core_32.c index bf9f1f906d64..b50aed48d09d 100644 --- a/arch/powerpc/kexec/core_32.c +++ b/arch/powerpc/kexec/core_32.c @@ -63,7 +63,7 @@ void default_machine_kexec(struct kimage *image) (*rnk)(page_list, reboot_code_buffer_phys, image->start); } -int default_machine_kexec_prepare(struct kimage *image) +int machine_kexec_prepare(struct kimage *image) { return 0; } diff --git a/arch/powerpc/kexec/core_64.c b/arch/powerpc/kexec/core_64.c index 89c069d664a5..66678518b938 100644 --- a/arch/powerpc/kexec/core_64.c +++ b/arch/powerpc/kexec/core_64.c @@ -32,7 +32,7 @@ #include <asm/svm.h> #include <asm/ultravisor.h> -int default_machine_kexec_prepare(struct kimage *image) +int machine_kexec_prepare(struct kimage *image) { int i; unsigned long begin, end; /* limits of segment */ diff --git a/arch/powerpc/kexec/file_load_64.c b/arch/powerpc/kexec/file_load_64.c index 5056e175ca2c..b4981b651d9a 100644 --- a/arch/powerpc/kexec/file_load_64.c +++ b/arch/powerpc/kexec/file_load_64.c @@ -700,6 +700,7 @@ static int update_usable_mem_fdt(void *fdt, struct crash_mem *usable_mem) if (ret) { pr_err("Failed to set linux,usable-memory property for %s node", dn->full_name); + of_node_put(dn); goto out; } } diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c index 6365087f3160..d42b4b6d4a79 100644 --- a/arch/powerpc/kvm/book3s_64_vio.c +++ b/arch/powerpc/kvm/book3s_64_vio.c @@ -295,8 +295,7 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm, return ret; ret = -ENOMEM; - stt = kzalloc(sizeof(*stt) + npages * sizeof(struct page *), - GFP_KERNEL); + stt = kzalloc(struct_size(stt, pages, npages), GFP_KERNEL); if (!stt) goto fail_acct; diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 2acb1c96cfaf..7b74fc0a986b 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -3726,7 +3726,20 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) kvmppc_set_host_core(pcpu); - guest_exit_irqoff(); + context_tracking_guest_exit(); + if (!vtime_accounting_enabled_this_cpu()) { + local_irq_enable(); + /* + * Service IRQs here before vtime_account_guest_exit() so any + * ticks that occurred while running the guest are accounted to + * the guest. If vtime accounting is enabled, accounting uses + * TB rather than ticks, so it can be done without enabling + * interrupts here, which has the problem that it accounts + * interrupt processing overhead to the host. + */ + local_irq_disable(); + } + vtime_account_guest_exit(); local_irq_enable(); @@ -4510,7 +4523,20 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit, kvmppc_set_host_core(pcpu); - guest_exit_irqoff(); + context_tracking_guest_exit(); + if (!vtime_accounting_enabled_this_cpu()) { + local_irq_enable(); + /* + * Service IRQs here before vtime_account_guest_exit() so any + * ticks that occurred while running the guest are accounted to + * the guest. If vtime accounting is enabled, accounting uses + * TB rather than ticks, so it can be done without enabling + * interrupts here, which has the problem that it accounts + * interrupt processing overhead to the host. + */ + local_irq_disable(); + } + vtime_account_guest_exit(); local_irq_enable(); diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c index 632b2545072b..2c1f3c6e72d1 100644 --- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c +++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c @@ -207,6 +207,15 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags, if (kvm_is_radix(kvm)) return H_FUNCTION; + /* + * The HPTE gets used by compute_tlbie_rb() to set TLBIE bits, so + * these functions should work together -- must ensure a guest can not + * cause problems with the TLBIE that KVM executes. + */ + if ((pteh >> HPTE_V_SSIZE_SHIFT) & 0x2) { + /* B=0b1x is a reserved value, disallow it. */ + return H_PARAMETER; + } psize = kvmppc_actual_pgsz(pteh, ptel); if (!psize) return H_PARAMETER; diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index 75079397c2a5..eb776d0c5d8e 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -255,13 +255,16 @@ kvm_novcpu_exit: * r3 contains the SRR1 wakeup value, SRR1 is trashed. */ _GLOBAL(idle_kvm_start_guest) - ld r4,PACAEMERGSP(r13) mfcr r5 mflr r0 - std r1,0(r4) - std r5,8(r4) - std r0,16(r4) - subi r1,r4,STACK_FRAME_OVERHEAD + std r5, 8(r1) // Save CR in caller's frame + std r0, 16(r1) // Save LR in caller's frame + // Create frame on emergency stack + ld r4, PACAEMERGSP(r13) + stdu r1, -SWITCH_FRAME_SIZE(r4) + // Switch to new frame on emergency stack + mr r1, r4 + std r3, 32(r1) // Save SRR1 wakeup value SAVE_NVGPRS(r1) /* @@ -313,6 +316,10 @@ kvm_unsplit_wakeup: kvm_secondary_got_guest: + // About to go to guest, clear saved SRR1 + li r0, 0 + std r0, 32(r1) + /* Set HSTATE_DSCR(r13) to something sensible */ ld r6, PACA_DSCR_DEFAULT(r13) std r6, HSTATE_DSCR(r13) @@ -392,13 +399,12 @@ kvm_no_guest: mfspr r4, SPRN_LPCR rlwimi r4, r3, 0, LPCR_PECE0 | LPCR_PECE1 mtspr SPRN_LPCR, r4 - /* set up r3 for return */ - mfspr r3,SPRN_SRR1 + // Return SRR1 wakeup value, or 0 if we went into the guest + ld r3, 32(r1) REST_NVGPRS(r1) - addi r1, r1, STACK_FRAME_OVERHEAD - ld r0, 16(r1) - ld r5, 8(r1) - ld r1, 0(r1) + ld r1, 0(r1) // Switch back to caller stack + ld r0, 16(r1) // Reload LR + ld r5, 8(r1) // Reload CR mtlr r0 mtcr r5 blr @@ -2536,7 +2542,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_P9_TM_HV_ASSIST) /* The following code handles the fake_suspend = 1 case */ mflr r0 std r0, PPC_LR_STKOFF(r1) - stdu r1, -PPC_MIN_STKFRM(r1) + stdu r1, -TM_FRAME_SIZE(r1) /* Turn on TM. */ mfmsr r8 @@ -2551,10 +2557,42 @@ BEGIN_FTR_SECTION END_FTR_SECTION_IFSET(CPU_FTR_P9_TM_XER_SO_BUG) nop + /* + * It's possible that treclaim. may modify registers, if we have lost + * track of fake-suspend state in the guest due to it using rfscv. + * Save and restore registers in case this occurs. + */ + mfspr r3, SPRN_DSCR + mfspr r4, SPRN_XER + mfspr r5, SPRN_AMR + /* SPRN_TAR would need to be saved here if the kernel ever used it */ + mfcr r12 + SAVE_NVGPRS(r1) + SAVE_GPR(2, r1) + SAVE_GPR(3, r1) + SAVE_GPR(4, r1) + SAVE_GPR(5, r1) + stw r12, 8(r1) + std r1, HSTATE_HOST_R1(r13) + /* We have to treclaim here because that's the only way to do S->N */ li r3, TM_CAUSE_KVM_RESCHED TRECLAIM(R3) + GET_PACA(r13) + ld r1, HSTATE_HOST_R1(r13) + REST_GPR(2, r1) + REST_GPR(3, r1) + REST_GPR(4, r1) + REST_GPR(5, r1) + lwz r12, 8(r1) + REST_NVGPRS(r1) + mtspr SPRN_DSCR, r3 + mtspr SPRN_XER, r4 + mtspr SPRN_AMR, r5 + mtcr r12 + HMT_MEDIUM + /* * We were in fake suspend, so we are not going to save the * register state as the guest checkpointed state (since @@ -2582,7 +2620,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_P9_TM_XER_SO_BUG) std r5, VCPU_TFHAR(r9) std r6, VCPU_TFIAR(r9) - addi r1, r1, PPC_MIN_STKFRM + addi r1, r1, TM_FRAME_SIZE ld r0, PPC_LR_STKOFF(r1) mtlr r0 blr diff --git a/arch/powerpc/kvm/book3s_xive.c b/arch/powerpc/kvm/book3s_xive.c index a18db9e16ea4..225008882958 100644 --- a/arch/powerpc/kvm/book3s_xive.c +++ b/arch/powerpc/kvm/book3s_xive.c @@ -1928,7 +1928,7 @@ int kvmppc_xive_set_nr_servers(struct kvmppc_xive *xive, u64 addr) pr_devel("%s nr_servers=%u\n", __func__, nr_servers); - if (!nr_servers || nr_servers > KVM_MAX_VCPU_ID) + if (!nr_servers || nr_servers > KVM_MAX_VCPU_IDS) return -EINVAL; mutex_lock(&xive->lock); diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c index 977801c83aff..8c15c90dd3a9 100644 --- a/arch/powerpc/kvm/booke.c +++ b/arch/powerpc/kvm/booke.c @@ -1042,7 +1042,21 @@ int kvmppc_handle_exit(struct kvm_vcpu *vcpu, unsigned int exit_nr) } trace_kvm_exit(exit_nr, vcpu); - guest_exit_irqoff(); + + context_tracking_guest_exit(); + if (!vtime_accounting_enabled_this_cpu()) { + local_irq_enable(); + /* + * Service IRQs here before vtime_account_guest_exit() so any + * ticks that occurred while running the guest are accounted to + * the guest. If vtime accounting is enabled, accounting uses + * TB rather than ticks, so it can be done without enabling + * interrupts here, which has the problem that it accounts + * interrupt processing overhead to the host. + */ + local_irq_disable(); + } + vtime_account_guest_exit(); local_irq_enable(); diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index b4e6f70b97b9..35e9cccdeef9 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -649,7 +649,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) r = KVM_MAX_VCPUS; break; case KVM_CAP_MAX_VCPU_ID: - r = KVM_MAX_VCPU_ID; + r = KVM_MAX_VCPU_IDS; break; #ifdef CONFIG_PPC_BOOK3S_64 case KVM_CAP_PPC_GET_SMMU_INFO: @@ -1094,7 +1094,7 @@ static inline u64 sp_to_dp(u32 fprs) preempt_disable(); enable_kernel_fp(); - asm ("lfs%U1%X1 0,%1; stfd%U0%X0 0,%0" : "=m"UPD_CONSTR (fprd) : "m"UPD_CONSTR (fprs) + asm ("lfs%U1%X1 0,%1; stfd%U0%X0 0,%0" : "=m<>" (fprd) : "m<>" (fprs) : "fr0"); preempt_enable(); return fprd; @@ -1106,7 +1106,7 @@ static inline u32 dp_to_sp(u64 fprd) preempt_disable(); enable_kernel_fp(); - asm ("lfd%U1%X1 0,%1; stfs%U0%X0 0,%0" : "=m"UPD_CONSTR (fprs) : "m"UPD_CONSTR (fprd) + asm ("lfd%U1%X1 0,%1; stfs%U0%X0 0,%0" : "=m<>" (fprs) : "m<>" (fprd) : "fr0"); preempt_enable(); return fprs; diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile index 99a7c9132422..9e5d0f413b71 100644 --- a/arch/powerpc/lib/Makefile +++ b/arch/powerpc/lib/Makefile @@ -65,5 +65,7 @@ obj-$(CONFIG_FTR_FIXUP_SELFTEST) += feature-fixups-test.o obj-$(CONFIG_ALTIVEC) += xor_vmx.o xor_vmx_glue.o CFLAGS_xor_vmx.o += -maltivec $(call cc-option,-mabi=altivec) +# Enable <altivec.h> +CFLAGS_xor_vmx.o += -isystem $(shell $(CC) -print-file-name=include) obj-$(CONFIG_PPC64) += $(obj64-y) diff --git a/arch/powerpc/lib/code-patching.c b/arch/powerpc/lib/code-patching.c index f9a3019e37b4..c5ed98823835 100644 --- a/arch/powerpc/lib/code-patching.c +++ b/arch/powerpc/lib/code-patching.c @@ -228,6 +228,11 @@ bool is_offset_in_branch_range(long offset) return (offset >= -0x2000000 && offset <= 0x1fffffc && !(offset & 0x3)); } +bool is_offset_in_cond_branch_range(long offset) +{ + return offset >= -0x8000 && offset <= 0x7fff && !(offset & 0x3); +} + /* * Helper to check if a given instruction is a conditional branch * Derived from the conditional checks in analyse_instr() @@ -280,7 +285,7 @@ int create_cond_branch(struct ppc_inst *instr, const u32 *addr, offset = offset - (unsigned long)addr; /* Check we can represent the target in the instruction format */ - if (offset < -0x8000 || offset > 0x7FFF || offset & 0x3) + if (!is_offset_in_cond_branch_range(offset)) return 1; /* Mask out the flags and target, so they don't step on each other. */ diff --git a/arch/powerpc/lib/feature-fixups.c b/arch/powerpc/lib/feature-fixups.c index cda17bee5afe..c3e06922468b 100644 --- a/arch/powerpc/lib/feature-fixups.c +++ b/arch/powerpc/lib/feature-fixups.c @@ -228,6 +228,7 @@ static void do_stf_exit_barrier_fixups(enum stf_barrier_type types) static bool stf_exit_reentrant = false; static bool rfi_exit_reentrant = false; +static DEFINE_MUTEX(exit_flush_lock); static int __do_stf_barrier_fixups(void *data) { @@ -253,6 +254,9 @@ void do_stf_barrier_fixups(enum stf_barrier_type types) * low level interrupt exit code before patching. After the patching, * if allowed, then flip the branch to allow fast exits. */ + + // Prevent static key update races with do_rfi_flush_fixups() + mutex_lock(&exit_flush_lock); static_branch_enable(&interrupt_exit_not_reentrant); stop_machine(__do_stf_barrier_fixups, &types, NULL); @@ -264,6 +268,8 @@ void do_stf_barrier_fixups(enum stf_barrier_type types) if (stf_exit_reentrant && rfi_exit_reentrant) static_branch_disable(&interrupt_exit_not_reentrant); + + mutex_unlock(&exit_flush_lock); } void do_uaccess_flush_fixups(enum l1d_flush_type types) @@ -486,6 +492,9 @@ void do_rfi_flush_fixups(enum l1d_flush_type types) * without stop_machine, so this could be achieved with a broadcast * IPI instead, but this matches the stf sequence. */ + + // Prevent static key update races with do_stf_barrier_fixups() + mutex_lock(&exit_flush_lock); static_branch_enable(&interrupt_exit_not_reentrant); stop_machine(__do_rfi_flush_fixups, &types, NULL); @@ -497,6 +506,8 @@ void do_rfi_flush_fixups(enum l1d_flush_type types) if (stf_exit_reentrant && rfi_exit_reentrant) static_branch_disable(&interrupt_exit_not_reentrant); + + mutex_unlock(&exit_flush_lock); } void do_barrier_nospec_fixups_range(bool enable, void *fixup_start, void *fixup_end) diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c index d8d5f901cee1..86f49e3e7cf5 100644 --- a/arch/powerpc/lib/sstep.c +++ b/arch/powerpc/lib/sstep.c @@ -302,33 +302,51 @@ static nokprobe_inline void do_byte_reverse(void *ptr, int nb) } } -static nokprobe_inline int read_mem_aligned(unsigned long *dest, - unsigned long ea, int nb, - struct pt_regs *regs) +static __always_inline int +__read_mem_aligned(unsigned long *dest, unsigned long ea, int nb, struct pt_regs *regs) { - int err = 0; unsigned long x = 0; switch (nb) { case 1: - err = __get_user(x, (unsigned char __user *) ea); + unsafe_get_user(x, (unsigned char __user *)ea, Efault); break; case 2: - err = __get_user(x, (unsigned short __user *) ea); + unsafe_get_user(x, (unsigned short __user *)ea, Efault); break; case 4: - err = __get_user(x, (unsigned int __user *) ea); + unsafe_get_user(x, (unsigned int __user *)ea, Efault); break; #ifdef __powerpc64__ case 8: - err = __get_user(x, (unsigned long __user *) ea); + unsafe_get_user(x, (unsigned long __user *)ea, Efault); break; #endif } - if (!err) - *dest = x; - else + *dest = x; + return 0; + +Efault: + regs->dar = ea; + return -EFAULT; +} + +static nokprobe_inline int +read_mem_aligned(unsigned long *dest, unsigned long ea, int nb, struct pt_regs *regs) +{ + int err; + + if (is_kernel_addr(ea)) + return __read_mem_aligned(dest, ea, nb, regs); + + if (user_read_access_begin((void __user *)ea, nb)) { + err = __read_mem_aligned(dest, ea, nb, regs); + user_read_access_end(); + } else { + err = -EFAULT; regs->dar = ea; + } + return err; } @@ -336,10 +354,8 @@ static nokprobe_inline int read_mem_aligned(unsigned long *dest, * Copy from userspace to a buffer, using the largest possible * aligned accesses, up to sizeof(long). */ -static nokprobe_inline int copy_mem_in(u8 *dest, unsigned long ea, int nb, - struct pt_regs *regs) +static __always_inline int __copy_mem_in(u8 *dest, unsigned long ea, int nb, struct pt_regs *regs) { - int err = 0; int c; for (; nb > 0; nb -= c) { @@ -348,31 +364,46 @@ static nokprobe_inline int copy_mem_in(u8 *dest, unsigned long ea, int nb, c = max_align(nb); switch (c) { case 1: - err = __get_user(*dest, (unsigned char __user *) ea); + unsafe_get_user(*dest, (u8 __user *)ea, Efault); break; case 2: - err = __get_user(*(u16 *)dest, - (unsigned short __user *) ea); + unsafe_get_user(*(u16 *)dest, (u16 __user *)ea, Efault); break; case 4: - err = __get_user(*(u32 *)dest, - (unsigned int __user *) ea); + unsafe_get_user(*(u32 *)dest, (u32 __user *)ea, Efault); break; #ifdef __powerpc64__ case 8: - err = __get_user(*(unsigned long *)dest, - (unsigned long __user *) ea); + unsafe_get_user(*(u64 *)dest, (u64 __user *)ea, Efault); break; #endif } - if (err) { - regs->dar = ea; - return err; - } dest += c; ea += c; } return 0; + +Efault: + regs->dar = ea; + return -EFAULT; +} + +static nokprobe_inline int copy_mem_in(u8 *dest, unsigned long ea, int nb, struct pt_regs *regs) +{ + int err; + + if (is_kernel_addr(ea)) + return __copy_mem_in(dest, ea, nb, regs); + + if (user_read_access_begin((void __user *)ea, nb)) { + err = __copy_mem_in(dest, ea, nb, regs); + user_read_access_end(); + } else { + err = -EFAULT; + regs->dar = ea; + } + + return err; } static nokprobe_inline int read_mem_unaligned(unsigned long *dest, @@ -410,30 +441,48 @@ static int read_mem(unsigned long *dest, unsigned long ea, int nb, } NOKPROBE_SYMBOL(read_mem); -static nokprobe_inline int write_mem_aligned(unsigned long val, - unsigned long ea, int nb, - struct pt_regs *regs) +static __always_inline int +__write_mem_aligned(unsigned long val, unsigned long ea, int nb, struct pt_regs *regs) { - int err = 0; - switch (nb) { case 1: - err = __put_user(val, (unsigned char __user *) ea); + unsafe_put_user(val, (unsigned char __user *)ea, Efault); break; case 2: - err = __put_user(val, (unsigned short __user *) ea); + unsafe_put_user(val, (unsigned short __user *)ea, Efault); break; case 4: - err = __put_user(val, (unsigned int __user *) ea); + unsafe_put_user(val, (unsigned int __user *)ea, Efault); break; #ifdef __powerpc64__ case 8: - err = __put_user(val, (unsigned long __user *) ea); + unsafe_put_user(val, (unsigned long __user *)ea, Efault); break; #endif } - if (err) + return 0; + +Efault: + regs->dar = ea; + return -EFAULT; +} + +static nokprobe_inline int +write_mem_aligned(unsigned long val, unsigned long ea, int nb, struct pt_regs *regs) +{ + int err; + + if (is_kernel_addr(ea)) + return __write_mem_aligned(val, ea, nb, regs); + + if (user_write_access_begin((void __user *)ea, nb)) { + err = __write_mem_aligned(val, ea, nb, regs); + user_write_access_end(); + } else { + err = -EFAULT; regs->dar = ea; + } + return err; } @@ -441,10 +490,8 @@ static nokprobe_inline int write_mem_aligned(unsigned long val, * Copy from a buffer to userspace, using the largest possible * aligned accesses, up to sizeof(long). */ -static nokprobe_inline int copy_mem_out(u8 *dest, unsigned long ea, int nb, - struct pt_regs *regs) +static nokprobe_inline int __copy_mem_out(u8 *dest, unsigned long ea, int nb, struct pt_regs *regs) { - int err = 0; int c; for (; nb > 0; nb -= c) { @@ -453,31 +500,46 @@ static nokprobe_inline int copy_mem_out(u8 *dest, unsigned long ea, int nb, c = max_align(nb); switch (c) { case 1: - err = __put_user(*dest, (unsigned char __user *) ea); + unsafe_put_user(*dest, (u8 __user *)ea, Efault); break; case 2: - err = __put_user(*(u16 *)dest, - (unsigned short __user *) ea); + unsafe_put_user(*(u16 *)dest, (u16 __user *)ea, Efault); break; case 4: - err = __put_user(*(u32 *)dest, - (unsigned int __user *) ea); + unsafe_put_user(*(u32 *)dest, (u32 __user *)ea, Efault); break; #ifdef __powerpc64__ case 8: - err = __put_user(*(unsigned long *)dest, - (unsigned long __user *) ea); + unsafe_put_user(*(u64 *)dest, (u64 __user *)ea, Efault); break; #endif } - if (err) { - regs->dar = ea; - return err; - } dest += c; ea += c; } return 0; + +Efault: + regs->dar = ea; + return -EFAULT; +} + +static nokprobe_inline int copy_mem_out(u8 *dest, unsigned long ea, int nb, struct pt_regs *regs) +{ + int err; + + if (is_kernel_addr(ea)) + return __copy_mem_out(dest, ea, nb, regs); + + if (user_write_access_begin((void __user *)ea, nb)) { + err = __copy_mem_out(dest, ea, nb, regs); + user_write_access_end(); + } else { + err = -EFAULT; + regs->dar = ea; + } + + return err; } static nokprobe_inline int write_mem_unaligned(unsigned long val, @@ -986,10 +1048,24 @@ static nokprobe_inline int do_vsx_store(struct instruction_op *op, } #endif /* CONFIG_VSX */ +static int __emulate_dcbz(unsigned long ea) +{ + unsigned long i; + unsigned long size = l1_dcache_bytes(); + + for (i = 0; i < size; i += sizeof(long)) + unsafe_put_user(0, (unsigned long __user *)(ea + i), Efault); + + return 0; + +Efault: + return -EFAULT; +} + int emulate_dcbz(unsigned long ea, struct pt_regs *regs) { int err; - unsigned long i, size; + unsigned long size; #ifdef __powerpc64__ size = ppc64_caches.l1d.block_size; @@ -1001,14 +1077,21 @@ int emulate_dcbz(unsigned long ea, struct pt_regs *regs) ea &= ~(size - 1); if (!address_ok(regs, ea, size)) return -EFAULT; - for (i = 0; i < size; i += sizeof(long)) { - err = __put_user(0, (unsigned long __user *) (ea + i)); - if (err) { - regs->dar = ea; - return err; - } + + if (is_kernel_addr(ea)) { + err = __emulate_dcbz(ea); + } else if (user_write_access_begin((void __user *)ea, size)) { + err = __emulate_dcbz(ea); + user_write_access_end(); + } else { + err = -EFAULT; } - return 0; + + if (err) + regs->dar = ea; + + + return err; } NOKPROBE_SYMBOL(emulate_dcbz); diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c index c145776d3ae5..cfd45245d009 100644 --- a/arch/powerpc/mm/book3s64/hash_utils.c +++ b/arch/powerpc/mm/book3s64/hash_utils.c @@ -1988,7 +1988,7 @@ static void kernel_unmap_linear_page(unsigned long vaddr, unsigned long lmi) mmu_kernel_ssize, 0); } -void __kernel_map_pages(struct page *page, int numpages, int enable) +void hash__kernel_map_pages(struct page *page, int numpages, int enable) { unsigned long flags, vaddr, lmi; int i; diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c index ae20add7954a..3a600bd7fbc6 100644 --- a/arch/powerpc/mm/book3s64/radix_pgtable.c +++ b/arch/powerpc/mm/book3s64/radix_pgtable.c @@ -920,6 +920,13 @@ void __meminit radix__vmemmap_remove_mapping(unsigned long start, unsigned long #endif #endif +#ifdef CONFIG_DEBUG_PAGEALLOC +void radix__kernel_map_pages(struct page *page, int numpages, int enable) +{ + pr_warn_once("DEBUG_PAGEALLOC not supported in radix mode\n"); +} +#endif + #ifdef CONFIG_TRANSPARENT_HUGEPAGE unsigned long radix__pmd_hugepage_update(struct mm_struct *mm, unsigned long addr, diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index 9a75ba078e1b..82d8b368ca6d 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -229,17 +229,22 @@ static int __init pseries_alloc_bootmem_huge_page(struct hstate *hstate) m->hstate = hstate; return 1; } + +bool __init hugetlb_node_alloc_supported(void) +{ + return false; +} #endif -int __init alloc_bootmem_huge_page(struct hstate *h) +int __init alloc_bootmem_huge_page(struct hstate *h, int nid) { #ifdef CONFIG_PPC_BOOK3S_64 if (firmware_has_feature(FW_FEATURE_LPAR) && !radix_enabled()) return pseries_alloc_bootmem_huge_page(h); #endif - return __alloc_bootmem_huge_page(h); + return __alloc_bootmem_huge_page(h, nid); } #ifndef CONFIG_PPC_BOOK3S_64 diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index c3c4e31462ec..bd5d91a31183 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -20,8 +20,8 @@ #include <asm/machdep.h> #include <asm/rtas.h> #include <asm/kasan.h> -#include <asm/sparsemem.h> #include <asm/svm.h> +#include <asm/mmzone.h> #include <mm/mmu_decl.h> @@ -256,7 +256,7 @@ void __init mem_init(void) #endif high_memory = (void *) __va(max_low_pfn * PAGE_SIZE); - set_max_mapnr(max_pfn); + set_max_mapnr(max_low_pfn); kasan_late_init(); diff --git a/arch/powerpc/mm/mmu_decl.h b/arch/powerpc/mm/mmu_decl.h index dd1cabc2ea0f..0dd4c18f8363 100644 --- a/arch/powerpc/mm/mmu_decl.h +++ b/arch/powerpc/mm/mmu_decl.h @@ -126,7 +126,7 @@ unsigned long mmu_mapin_ram(unsigned long base, unsigned long top); #ifdef CONFIG_PPC_FSL_BOOK3E extern unsigned long map_mem_in_cams(unsigned long ram, int max_cam_idx, - bool dryrun); + bool dryrun, bool init); extern unsigned long calc_cam_sz(unsigned long ram, unsigned long virt, phys_addr_t phys); #ifdef CONFIG_PPC32 @@ -168,7 +168,7 @@ static inline phys_addr_t v_block_mapped(unsigned long va) { return 0; } static inline unsigned long p_block_mapped(phys_addr_t pa) { return 0; } #endif -#if defined(CONFIG_PPC_BOOK3S_32) || defined(CONFIG_PPC_8xx) +#if defined(CONFIG_PPC_BOOK3S_32) || defined(CONFIG_PPC_8xx) || defined(CONFIG_PPC_FSL_BOOK3E) void mmu_mark_initmem_nx(void); void mmu_mark_rodata_ro(void); #else diff --git a/arch/powerpc/mm/nohash/Makefile b/arch/powerpc/mm/nohash/Makefile index 0424f6ce5bd8..b1f630d423d8 100644 --- a/arch/powerpc/mm/nohash/Makefile +++ b/arch/powerpc/mm/nohash/Makefile @@ -7,7 +7,7 @@ obj-$(CONFIG_PPC_BOOK3E_64) += tlb_low_64e.o book3e_pgtable.o obj-$(CONFIG_40x) += 40x.o obj-$(CONFIG_44x) += 44x.o obj-$(CONFIG_PPC_8xx) += 8xx.o -obj-$(CONFIG_PPC_FSL_BOOK3E) += fsl_booke.o +obj-$(CONFIG_PPC_FSL_BOOK3E) += fsl_book3e.o obj-$(CONFIG_RANDOMIZE_BASE) += kaslr_booke.o ifdef CONFIG_HUGETLB_PAGE obj-$(CONFIG_PPC_FSL_BOOK3E) += book3e_hugetlbpage.o @@ -16,4 +16,4 @@ endif # Disable kcov instrumentation on sensitive code # This is necessary for booting with kcov enabled on book3e machines KCOV_INSTRUMENT_tlb.o := n -KCOV_INSTRUMENT_fsl_booke.o := n +KCOV_INSTRUMENT_fsl_book3e.o := n diff --git a/arch/powerpc/mm/nohash/fsl_booke.c b/arch/powerpc/mm/nohash/fsl_book3e.c index 03dacbe940e5..b231a54f540c 100644 --- a/arch/powerpc/mm/nohash/fsl_booke.c +++ b/arch/powerpc/mm/nohash/fsl_book3e.c @@ -122,15 +122,18 @@ static void settlbcam(int index, unsigned long virt, phys_addr_t phys, TLBCAM[index].MAS2 |= (flags & _PAGE_GUARDED) ? MAS2_G : 0; TLBCAM[index].MAS2 |= (flags & _PAGE_ENDIAN) ? MAS2_E : 0; - TLBCAM[index].MAS3 = (phys & MAS3_RPN) | MAS3_SX | MAS3_SR; - TLBCAM[index].MAS3 |= ((flags & _PAGE_RW) ? MAS3_SW : 0); + TLBCAM[index].MAS3 = (phys & MAS3_RPN) | MAS3_SR; + TLBCAM[index].MAS3 |= (flags & _PAGE_RW) ? MAS3_SW : 0; if (mmu_has_feature(MMU_FTR_BIG_PHYS)) TLBCAM[index].MAS7 = (u64)phys >> 32; /* Below is unlikely -- only for large user pages or similar */ if (pte_user(__pte(flags))) { - TLBCAM[index].MAS3 |= MAS3_UX | MAS3_UR; - TLBCAM[index].MAS3 |= ((flags & _PAGE_RW) ? MAS3_UW : 0); + TLBCAM[index].MAS3 |= MAS3_UR; + TLBCAM[index].MAS3 |= (flags & _PAGE_EXEC) ? MAS3_UX : 0; + TLBCAM[index].MAS3 |= (flags & _PAGE_RW) ? MAS3_UW : 0; + } else { + TLBCAM[index].MAS3 |= (flags & _PAGE_EXEC) ? MAS3_SX : 0; } tlbcam_addrs[index].start = virt; @@ -165,19 +168,38 @@ unsigned long calc_cam_sz(unsigned long ram, unsigned long virt, static unsigned long map_mem_in_cams_addr(phys_addr_t phys, unsigned long virt, unsigned long ram, int max_cam_idx, - bool dryrun) + bool dryrun, bool init) { int i; unsigned long amount_mapped = 0; + unsigned long boundary; + + if (strict_kernel_rwx_enabled()) + boundary = (unsigned long)(_sinittext - _stext); + else + boundary = ram; /* Calculate CAM values */ - for (i = 0; ram && i < max_cam_idx; i++) { + for (i = 0; boundary && i < max_cam_idx; i++) { + unsigned long cam_sz; + pgprot_t prot = init ? PAGE_KERNEL_X : PAGE_KERNEL_ROX; + + cam_sz = calc_cam_sz(boundary, virt, phys); + if (!dryrun) + settlbcam(i, virt, phys, cam_sz, pgprot_val(prot), 0); + + boundary -= cam_sz; + amount_mapped += cam_sz; + virt += cam_sz; + phys += cam_sz; + } + for (ram -= amount_mapped; ram && i < max_cam_idx; i++) { unsigned long cam_sz; + pgprot_t prot = init ? PAGE_KERNEL_X : PAGE_KERNEL; cam_sz = calc_cam_sz(ram, virt, phys); if (!dryrun) - settlbcam(i, virt, phys, cam_sz, - pgprot_val(PAGE_KERNEL_X), 0); + settlbcam(i, virt, phys, cam_sz, pgprot_val(prot), 0); ram -= cam_sz; amount_mapped += cam_sz; @@ -188,8 +210,13 @@ static unsigned long map_mem_in_cams_addr(phys_addr_t phys, unsigned long virt, if (dryrun) return amount_mapped; - loadcam_multi(0, i, max_cam_idx); - tlbcam_index = i; + if (init) { + loadcam_multi(0, i, max_cam_idx); + tlbcam_index = i; + } else { + loadcam_multi(0, i, 0); + WARN_ON(i > tlbcam_index); + } #ifdef CONFIG_PPC64 get_paca()->tcd.esel_next = i; @@ -200,12 +227,12 @@ static unsigned long map_mem_in_cams_addr(phys_addr_t phys, unsigned long virt, return amount_mapped; } -unsigned long map_mem_in_cams(unsigned long ram, int max_cam_idx, bool dryrun) +unsigned long map_mem_in_cams(unsigned long ram, int max_cam_idx, bool dryrun, bool init) { unsigned long virt = PAGE_OFFSET; phys_addr_t phys = memstart_addr; - return map_mem_in_cams_addr(phys, virt, ram, max_cam_idx, dryrun); + return map_mem_in_cams_addr(phys, virt, ram, max_cam_idx, dryrun, init); } #ifdef CONFIG_PPC32 @@ -246,7 +273,7 @@ void __init adjust_total_lowmem(void) ram = min((phys_addr_t)__max_low_memory, (phys_addr_t)total_lowmem); i = switch_to_as1(); - __max_low_memory = map_mem_in_cams(ram, CONFIG_LOWMEM_CAM_NUM, false); + __max_low_memory = map_mem_in_cams(ram, CONFIG_LOWMEM_CAM_NUM, false, true); restore_to_as0(i, 0, 0, 1); pr_info("Memory CAM mapping: "); @@ -258,6 +285,25 @@ void __init adjust_total_lowmem(void) memblock_set_current_limit(memstart_addr + __max_low_memory); } +#ifdef CONFIG_STRICT_KERNEL_RWX +void mmu_mark_rodata_ro(void) +{ + /* Everything is done in mmu_mark_initmem_nx() */ +} +#endif + +void mmu_mark_initmem_nx(void) +{ + unsigned long remapped; + + if (!strict_kernel_rwx_enabled()) + return; + + remapped = map_mem_in_cams(__max_low_memory, CONFIG_LOWMEM_CAM_NUM, false, false); + + WARN_ON(__max_low_memory != remapped); +} + void setup_initial_memory_limit(phys_addr_t first_memblock_base, phys_addr_t first_memblock_size) { @@ -317,11 +363,11 @@ notrace void __init relocate_init(u64 dt_ptr, phys_addr_t start) /* map a 64M area for the second relocation */ if (memstart_addr > start) map_mem_in_cams(0x4000000, CONFIG_LOWMEM_CAM_NUM, - false); + false, true); else map_mem_in_cams_addr(start, PAGE_OFFSET + offset, 0x4000000, CONFIG_LOWMEM_CAM_NUM, - false); + false, true); restore_to_as0(n, offset, __va(dt_ptr), 1); /* We should never reach here */ panic("Relocation error"); diff --git a/arch/powerpc/mm/nohash/kaslr_booke.c b/arch/powerpc/mm/nohash/kaslr_booke.c index 4c74e8a5482b..8fc49b1b4a91 100644 --- a/arch/powerpc/mm/nohash/kaslr_booke.c +++ b/arch/powerpc/mm/nohash/kaslr_booke.c @@ -314,7 +314,7 @@ static unsigned long __init kaslr_choose_location(void *dt_ptr, phys_addr_t size pr_warn("KASLR: No safe seed for randomizing the kernel base.\n"); ram = min_t(phys_addr_t, __max_low_memory, size); - ram = map_mem_in_cams(ram, CONFIG_LOWMEM_CAM_NUM, true); + ram = map_mem_in_cams(ram, CONFIG_LOWMEM_CAM_NUM, true, false); linear_sz = min_t(unsigned long, ram, SZ_512M); /* If the linear size is smaller than 64M, do not randmize */ diff --git a/arch/powerpc/mm/nohash/tlb.c b/arch/powerpc/mm/nohash/tlb.c index 5872f69141d5..89353d4f5604 100644 --- a/arch/powerpc/mm/nohash/tlb.c +++ b/arch/powerpc/mm/nohash/tlb.c @@ -185,6 +185,7 @@ EXPORT_PER_CPU_SYMBOL(next_tlbcam_idx); * processor */ +#ifndef CONFIG_PPC_8xx /* * These are the base non-SMP variants of page and mm flushing */ @@ -218,6 +219,7 @@ void local_flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr) mmu_get_tsize(mmu_virtual_psize), 0); } EXPORT_SYMBOL(local_flush_tlb_page); +#endif /* * And here are the SMP non-local implementations @@ -643,7 +645,7 @@ static void early_init_this_mmu(void) if (map) linear_map_top = map_mem_in_cams(linear_map_top, - num_cams, false); + num_cams, true, true); } #endif @@ -764,7 +766,7 @@ void setup_initial_memory_limit(phys_addr_t first_memblock_base, num_cams = (mfspr(SPRN_TLB1CFG) & TLBnCFG_N_ENTRY) / 4; linear_sz = map_mem_in_cams(first_memblock_size, num_cams, - true); + false, true); ppc64_rma_size = min_t(u64, linear_sz, 0x40000000); } else diff --git a/arch/powerpc/mm/nohash/tlb_low.S b/arch/powerpc/mm/nohash/tlb_low.S index 5add4a51e51f..dd39074de9af 100644 --- a/arch/powerpc/mm/nohash/tlb_low.S +++ b/arch/powerpc/mm/nohash/tlb_low.S @@ -369,7 +369,7 @@ _GLOBAL(_tlbivax_bcast) * extern void loadcam_entry(unsigned int index) * * Load TLBCAM[index] entry in to the L2 CAM MMU - * Must preserve r7, r8, r9, r10 and r11 + * Must preserve r7, r8, r9, r10, r11, r12 */ _GLOBAL(loadcam_entry) mflr r5 @@ -401,7 +401,7 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_BIG_PHYS) * * r3 = first entry to write * r4 = number of entries to write - * r5 = temporary tlb entry + * r5 = temporary tlb entry (0 means no switch to AS1) */ _GLOBAL(loadcam_multi) mflr r8 @@ -409,6 +409,8 @@ _GLOBAL(loadcam_multi) mfmsr r11 andi. r11,r11,MSR_IS bne 10f + mr. r12, r5 + beq 10f /* * Set up temporary TLB entry that is the same as what we're @@ -446,6 +448,8 @@ _GLOBAL(loadcam_multi) /* Don't return to AS=0 if we were in AS=1 at function start */ andi. r11,r11,MSR_IS bne 3f + cmpwi r12, 0 + beq 3f /* Return to AS=0 and clear the temporary entry */ mfmsr r6 diff --git a/arch/powerpc/mm/nohash/tlb_low_64e.S b/arch/powerpc/mm/nohash/tlb_low_64e.S index bf24451f3e71..9235e720e357 100644 --- a/arch/powerpc/mm/nohash/tlb_low_64e.S +++ b/arch/powerpc/mm/nohash/tlb_low_64e.S @@ -222,7 +222,7 @@ tlb_miss_kernel_bolted: tlb_miss_fault_bolted: /* We need to check if it was an instruction miss */ - andi. r10,r11,_PAGE_EXEC|_PAGE_BAP_SX + andi. r10,r11,_PAGE_BAP_UX|_PAGE_BAP_SX bne itlb_miss_fault_bolted dtlb_miss_fault_bolted: tlb_epilog_bolted @@ -239,7 +239,7 @@ itlb_miss_fault_bolted: srdi r15,r16,60 /* get region */ bne- itlb_miss_fault_bolted - li r11,_PAGE_PRESENT|_PAGE_EXEC /* Base perm */ + li r11,_PAGE_PRESENT|_PAGE_BAP_UX /* Base perm */ /* We do the user/kernel test for the PID here along with the RW test */ @@ -614,7 +614,7 @@ itlb_miss_fault_e6500: /* We do the user/kernel test for the PID here along with the RW test */ - li r11,_PAGE_PRESENT|_PAGE_EXEC /* Base perm */ + li r11,_PAGE_PRESENT|_PAGE_BAP_UX /* Base perm */ oris r11,r11,_PAGE_ACCESSED@h cmpldi cr0,r15,0 /* Check for user region */ @@ -734,7 +734,7 @@ normal_tlb_miss_done: normal_tlb_miss_access_fault: /* We need to check if it was an instruction miss */ - andi. r10,r11,_PAGE_EXEC + andi. r10,r11,_PAGE_BAP_UX bne 1f ld r14,EX_TLB_DEAR(r12) ld r15,EX_TLB_ESR(r12) diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c index cd16b407f47e..ce9482383144 100644 --- a/arch/powerpc/mm/pgtable.c +++ b/arch/powerpc/mm/pgtable.c @@ -271,7 +271,7 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_ { pmd_t *pmd = pmd_off(mm, addr); pte_basic_t val; - pte_basic_t *entry = &ptep->pte; + pte_basic_t *entry = (pte_basic_t *)ptep; int num, i; /* diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c index dcf5ecca19d9..906e4e4328b2 100644 --- a/arch/powerpc/mm/pgtable_32.c +++ b/arch/powerpc/mm/pgtable_32.c @@ -33,8 +33,6 @@ #include <mm/mmu_decl.h> -extern char etext[], _stext[], _sinittext[], _einittext[]; - static u8 early_fixmap_pagetable[FIXMAP_PTE_SIZE] __page_aligned_data; notrace void __init early_ioremap_init(void) @@ -104,14 +102,13 @@ static void __init __mapin_ram_chunk(unsigned long offset, unsigned long top) { unsigned long v, s; phys_addr_t p; - int ktext; + bool ktext; s = offset; v = PAGE_OFFSET + s; p = memstart_addr + s; for (; s < top; s += PAGE_SIZE) { - ktext = ((char *)v >= _stext && (char *)v < etext) || - ((char *)v >= _sinittext && (char *)v < _einittext); + ktext = core_kernel_text(v); map_kernel_page(v, p, ktext ? PAGE_KERNEL_TEXT : PAGE_KERNEL); v += PAGE_SIZE; p += PAGE_SIZE; @@ -173,7 +170,7 @@ void mark_rodata_ro(void) } #endif -#ifdef CONFIG_DEBUG_PAGEALLOC +#if defined(CONFIG_ARCH_SUPPORTS_DEBUG_PAGEALLOC) && defined(CONFIG_DEBUG_PAGEALLOC) void __kernel_map_pages(struct page *page, int numpages, int enable) { unsigned long addr = (unsigned long)page_address(page); diff --git a/arch/powerpc/net/bpf_jit.h b/arch/powerpc/net/bpf_jit.h index 99fad093f43e..7e9b978b768e 100644 --- a/arch/powerpc/net/bpf_jit.h +++ b/arch/powerpc/net/bpf_jit.h @@ -24,16 +24,30 @@ #define EMIT(instr) PLANT_INSTR(image, ctx->idx, instr) /* Long jump; (unconditional 'branch') */ -#define PPC_JMP(dest) EMIT(PPC_INST_BRANCH | \ - (((dest) - (ctx->idx * 4)) & 0x03fffffc)) +#define PPC_JMP(dest) \ + do { \ + long offset = (long)(dest) - (ctx->idx * 4); \ + if (!is_offset_in_branch_range(offset)) { \ + pr_err_ratelimited("Branch offset 0x%lx (@%u) out of range\n", offset, ctx->idx); \ + return -ERANGE; \ + } \ + EMIT(PPC_INST_BRANCH | (offset & 0x03fffffc)); \ + } while (0) + /* blr; (unconditional 'branch' with link) to absolute address */ #define PPC_BL_ABS(dest) EMIT(PPC_INST_BL | \ (((dest) - (unsigned long)(image + ctx->idx)) & 0x03fffffc)) /* "cond" here covers BO:BI fields. */ -#define PPC_BCC_SHORT(cond, dest) EMIT(PPC_INST_BRANCH_COND | \ - (((cond) & 0x3ff) << 16) | \ - (((dest) - (ctx->idx * 4)) & \ - 0xfffc)) +#define PPC_BCC_SHORT(cond, dest) \ + do { \ + long offset = (long)(dest) - (ctx->idx * 4); \ + if (!is_offset_in_cond_branch_range(offset)) { \ + pr_err_ratelimited("Conditional branch offset 0x%lx (@%u) out of range\n", offset, ctx->idx); \ + return -ERANGE; \ + } \ + EMIT(PPC_INST_BRANCH_COND | (((cond) & 0x3ff) << 16) | (offset & 0xfffc)); \ + } while (0) + /* Sign-extended 32-bit immediate load */ #define PPC_LI32(d, i) do { \ if ((int)(uintptr_t)(i) >= -32768 && \ @@ -78,11 +92,6 @@ #define PPC_FUNC_ADDR(d,i) do { PPC_LI32(d, i); } while(0) #endif -static inline bool is_nearbranch(int offset) -{ - return (offset < 32768) && (offset >= -32768); -} - /* * The fly in the ointment of code size changing from pass to pass is * avoided by padding the short branch case with a NOP. If code size differs @@ -91,7 +100,7 @@ static inline bool is_nearbranch(int offset) * state. */ #define PPC_BCC(cond, dest) do { \ - if (is_nearbranch((dest) - (ctx->idx * 4))) { \ + if (is_offset_in_cond_branch_range((long)(dest) - (ctx->idx * 4))) { \ PPC_BCC_SHORT(cond, dest); \ EMIT(PPC_RAW_NOP()); \ } else { \ diff --git a/arch/powerpc/net/bpf_jit64.h b/arch/powerpc/net/bpf_jit64.h index 7b713edfa7e2..b63b35e45e55 100644 --- a/arch/powerpc/net/bpf_jit64.h +++ b/arch/powerpc/net/bpf_jit64.h @@ -16,18 +16,18 @@ * with our redzone usage. * * [ prev sp ] <------------- - * [ nv gpr save area ] 6*8 | + * [ nv gpr save area ] 5*8 | * [ tail_call_cnt ] 8 | - * [ local_tmp_var ] 8 | + * [ local_tmp_var ] 16 | * fp (r31) --> [ ebpf stack space ] upto 512 | * [ frame header ] 32/112 | * sp (r1) ---> [ stack pointer ] -------------- */ /* for gpr non volatile registers BPG_REG_6 to 10 */ -#define BPF_PPC_STACK_SAVE (6*8) +#define BPF_PPC_STACK_SAVE (5*8) /* for bpf JIT code internal usage */ -#define BPF_PPC_STACK_LOCALS 16 +#define BPF_PPC_STACK_LOCALS 24 /* stack frame excluding BPF stack, ensure this is quadword aligned */ #define BPF_PPC_STACKFRAME (STACK_FRAME_MIN_SIZE + \ BPF_PPC_STACK_LOCALS + BPF_PPC_STACK_SAVE) diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c index 53aefee3fe70..90ce75f0f1e2 100644 --- a/arch/powerpc/net/bpf_jit_comp.c +++ b/arch/powerpc/net/bpf_jit_comp.c @@ -210,7 +210,11 @@ skip_init_ctx: /* Now build the prologue, body code & epilogue for real. */ cgctx.idx = 0; bpf_jit_build_prologue(code_base, &cgctx); - bpf_jit_build_body(fp, code_base, &cgctx, addrs, extra_pass); + if (bpf_jit_build_body(fp, code_base, &cgctx, addrs, extra_pass)) { + bpf_jit_binary_free(bpf_hdr); + fp = org_fp; + goto out_addrs; + } bpf_jit_build_epilogue(code_base, &cgctx); if (bpf_jit_enable > 1) @@ -237,8 +241,8 @@ skip_codegen_passes: fp->jited_len = alloclen; bpf_flush_icache(bpf_hdr, (u8 *)bpf_hdr + (bpf_hdr->pages * PAGE_SIZE)); - bpf_jit_binary_lock_ro(bpf_hdr); if (!fp->is_func || extra_pass) { + bpf_jit_binary_lock_ro(bpf_hdr); bpf_prog_fill_jited_linfo(fp, addrs); out_addrs: kfree(addrs); diff --git a/arch/powerpc/net/bpf_jit_comp32.c b/arch/powerpc/net/bpf_jit_comp32.c index beb12cbc8c29..0da31d41d413 100644 --- a/arch/powerpc/net/bpf_jit_comp32.c +++ b/arch/powerpc/net/bpf_jit_comp32.c @@ -200,7 +200,7 @@ void bpf_jit_emit_func_call_rel(u32 *image, struct codegen_context *ctx, u64 fun } } -static void bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 out) +static int bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 out) { /* * By now, the eBPF program has already setup parameters in r3-r6 @@ -261,7 +261,9 @@ static void bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 bpf_jit_emit_common_epilogue(image, ctx); EMIT(PPC_RAW_BCTR()); + /* out: */ + return 0; } /* Assemble the body code between the prologue & epilogue */ @@ -355,7 +357,7 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context * PPC_LI32(_R0, imm); EMIT(PPC_RAW_ADDC(dst_reg, dst_reg, _R0)); } - if (imm >= 0) + if (imm >= 0 || (BPF_OP(code) == BPF_SUB && imm == 0x80000000)) EMIT(PPC_RAW_ADDZE(dst_reg_h, dst_reg_h)); else EMIT(PPC_RAW_ADDME(dst_reg_h, dst_reg_h)); @@ -623,7 +625,7 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context * EMIT(PPC_RAW_LI(dst_reg_h, 0)); break; case BPF_ALU | BPF_ARSH | BPF_X: /* (s32) dst >>= src */ - EMIT(PPC_RAW_SRAW(dst_reg_h, dst_reg, src_reg)); + EMIT(PPC_RAW_SRAW(dst_reg, dst_reg, src_reg)); break; case BPF_ALU64 | BPF_ARSH | BPF_X: /* (s64) dst >>= src */ bpf_set_seen_register(ctx, tmp_reg); @@ -1073,7 +1075,7 @@ cond_branch: break; case BPF_JMP32 | BPF_JSET | BPF_K: /* andi does not sign-extend the immediate */ - if (imm >= -32768 && imm < 32768) { + if (imm >= 0 && imm < 32768) { /* PPC_ANDI is _only/always_ dot-form */ EMIT(PPC_RAW_ANDI(_R0, dst_reg, imm)); } else { @@ -1090,7 +1092,9 @@ cond_branch: */ case BPF_JMP | BPF_TAIL_CALL: ctx->seen |= SEEN_TAILCALL; - bpf_jit_emit_tail_call(image, ctx, addrs[i + 1]); + ret = bpf_jit_emit_tail_call(image, ctx, addrs[i + 1]); + if (ret < 0) + return ret; break; default: @@ -1103,7 +1107,7 @@ cond_branch: return -EOPNOTSUPP; } if (BPF_CLASS(code) == BPF_ALU && !fp->aux->verifier_zext && - !insn_is_zext(&insn[i + 1])) + !insn_is_zext(&insn[i + 1]) && !(BPF_OP(code) == BPF_END && imm == 64)) EMIT(PPC_RAW_LI(dst_reg_h, 0)); } diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c index b87a63dba9c8..8b5157ccfeba 100644 --- a/arch/powerpc/net/bpf_jit_comp64.c +++ b/arch/powerpc/net/bpf_jit_comp64.c @@ -15,6 +15,7 @@ #include <linux/if_vlan.h> #include <asm/kprobes.h> #include <linux/bpf.h> +#include <asm/security_features.h> #include "bpf_jit64.h" @@ -35,9 +36,9 @@ static inline bool bpf_has_stack_frame(struct codegen_context *ctx) * [ prev sp ] <------------- * [ ... ] | * sp (r1) ---> [ stack pointer ] -------------- - * [ nv gpr save area ] 6*8 + * [ nv gpr save area ] 5*8 * [ tail_call_cnt ] 8 - * [ local_tmp_var ] 8 + * [ local_tmp_var ] 16 * [ unused red zone ] 208 bytes protected */ static int bpf_jit_stack_local(struct codegen_context *ctx) @@ -45,12 +46,12 @@ static int bpf_jit_stack_local(struct codegen_context *ctx) if (bpf_has_stack_frame(ctx)) return STACK_FRAME_MIN_SIZE + ctx->stack_size; else - return -(BPF_PPC_STACK_SAVE + 16); + return -(BPF_PPC_STACK_SAVE + 24); } static int bpf_jit_stack_tailcallcnt(struct codegen_context *ctx) { - return bpf_jit_stack_local(ctx) + 8; + return bpf_jit_stack_local(ctx) + 16; } static int bpf_jit_stack_offsetof(struct codegen_context *ctx, int reg) @@ -206,7 +207,7 @@ void bpf_jit_emit_func_call_rel(u32 *image, struct codegen_context *ctx, u64 fun EMIT(PPC_RAW_BCTRL()); } -static void bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 out) +static int bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 out) { /* * By now, the eBPF program has already setup parameters in r3, r4 and r5 @@ -267,13 +268,38 @@ static void bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 bpf_jit_emit_common_epilogue(image, ctx); EMIT(PPC_RAW_BCTR()); + /* out: */ + return 0; } +/* + * We spill into the redzone always, even if the bpf program has its own stackframe. + * Offsets hardcoded based on BPF_PPC_STACK_SAVE -- see bpf_jit_stack_local() + */ +void bpf_stf_barrier(void); + +asm ( +" .global bpf_stf_barrier ;" +" bpf_stf_barrier: ;" +" std 21,-64(1) ;" +" std 22,-56(1) ;" +" sync ;" +" ld 21,-64(1) ;" +" ld 22,-56(1) ;" +" ori 31,31,0 ;" +" .rept 14 ;" +" b 1f ;" +" 1: ;" +" .endr ;" +" blr ;" +); + /* Assemble the body code between the prologue & epilogue */ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *ctx, u32 *addrs, bool extra_pass) { + enum stf_barrier_type stf_barrier = stf_barrier_type_get(); const struct bpf_insn *insn = fp->insnsi; int flen = fp->len; int i, ret; @@ -328,18 +354,25 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context * EMIT(PPC_RAW_SUB(dst_reg, dst_reg, src_reg)); goto bpf_alu32_trunc; case BPF_ALU | BPF_ADD | BPF_K: /* (u32) dst += (u32) imm */ - case BPF_ALU | BPF_SUB | BPF_K: /* (u32) dst -= (u32) imm */ case BPF_ALU64 | BPF_ADD | BPF_K: /* dst += imm */ + if (!imm) { + goto bpf_alu32_trunc; + } else if (imm >= -32768 && imm < 32768) { + EMIT(PPC_RAW_ADDI(dst_reg, dst_reg, IMM_L(imm))); + } else { + PPC_LI32(b2p[TMP_REG_1], imm); + EMIT(PPC_RAW_ADD(dst_reg, dst_reg, b2p[TMP_REG_1])); + } + goto bpf_alu32_trunc; + case BPF_ALU | BPF_SUB | BPF_K: /* (u32) dst -= (u32) imm */ case BPF_ALU64 | BPF_SUB | BPF_K: /* dst -= imm */ - if (BPF_OP(code) == BPF_SUB) - imm = -imm; - if (imm) { - if (imm >= -32768 && imm < 32768) - EMIT(PPC_RAW_ADDI(dst_reg, dst_reg, IMM_L(imm))); - else { - PPC_LI32(b2p[TMP_REG_1], imm); - EMIT(PPC_RAW_ADD(dst_reg, dst_reg, b2p[TMP_REG_1])); - } + if (!imm) { + goto bpf_alu32_trunc; + } else if (imm > -32768 && imm <= 32768) { + EMIT(PPC_RAW_ADDI(dst_reg, dst_reg, IMM_L(-imm))); + } else { + PPC_LI32(b2p[TMP_REG_1], imm); + EMIT(PPC_RAW_SUB(dst_reg, dst_reg, b2p[TMP_REG_1])); } goto bpf_alu32_trunc; case BPF_ALU | BPF_MUL | BPF_X: /* (u32) dst *= (u32) src */ @@ -389,8 +422,14 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context * case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ if (imm == 0) return -EINVAL; - else if (imm == 1) - goto bpf_alu32_trunc; + if (imm == 1) { + if (BPF_OP(code) == BPF_DIV) { + goto bpf_alu32_trunc; + } else { + EMIT(PPC_RAW_LI(dst_reg, 0)); + break; + } + } PPC_LI32(b2p[TMP_REG_1], imm); switch (BPF_CLASS(code)) { @@ -631,6 +670,29 @@ emit_clear: * BPF_ST NOSPEC (speculation barrier) */ case BPF_ST | BPF_NOSPEC: + if (!security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) || + !security_ftr_enabled(SEC_FTR_STF_BARRIER)) + break; + + switch (stf_barrier) { + case STF_BARRIER_EIEIO: + EMIT(PPC_RAW_EIEIO() | 0x02000000); + break; + case STF_BARRIER_SYNC_ORI: + EMIT(PPC_RAW_SYNC()); + EMIT(PPC_RAW_LD(b2p[TMP_REG_1], _R13, 0)); + EMIT(PPC_RAW_ORI(_R31, _R31, 0)); + break; + case STF_BARRIER_FALLBACK: + EMIT(PPC_RAW_MFLR(b2p[TMP_REG_1])); + PPC_LI64(12, dereference_kernel_function_descriptor(bpf_stf_barrier)); + EMIT(PPC_RAW_MTCTR(12)); + EMIT(PPC_RAW_BCTRL()); + EMIT(PPC_RAW_MTLR(b2p[TMP_REG_1])); + break; + case STF_BARRIER_NONE: + break; + } break; /* @@ -993,7 +1055,9 @@ cond_branch: */ case BPF_JMP | BPF_TAIL_CALL: ctx->seen |= SEEN_TAILCALL; - bpf_jit_emit_tail_call(image, ctx, addrs[i + 1]); + ret = bpf_jit_emit_tail_call(image, ctx, addrs[i + 1]); + if (ret < 0) + return ret; break; default: diff --git a/arch/powerpc/perf/isa207-common.c b/arch/powerpc/perf/isa207-common.c index f92bf5f6b74f..7ea873ab2e6f 100644 --- a/arch/powerpc/perf/isa207-common.c +++ b/arch/powerpc/perf/isa207-common.c @@ -238,11 +238,27 @@ static inline u64 isa207_find_source(u64 idx, u32 sub_idx) ret |= P(SNOOP, HIT); break; case 5: - ret = PH(LVL, REM_CCE1); - if ((sub_idx == 0) || (sub_idx == 2) || (sub_idx == 4)) - ret |= P(SNOOP, HIT); - else if ((sub_idx == 1) || (sub_idx == 3) || (sub_idx == 5)) - ret |= P(SNOOP, HITM); + if (cpu_has_feature(CPU_FTR_ARCH_31)) { + ret = REM | P(HOPS, 0); + + if (sub_idx == 0 || sub_idx == 4) + ret |= PH(LVL, L2) | LEVEL(L2) | P(SNOOP, HIT); + else if (sub_idx == 1 || sub_idx == 5) + ret |= PH(LVL, L2) | LEVEL(L2) | P(SNOOP, HITM); + else if (sub_idx == 2 || sub_idx == 6) + ret |= PH(LVL, L3) | LEVEL(L3) | P(SNOOP, HIT); + else if (sub_idx == 3 || sub_idx == 7) + ret |= PH(LVL, L3) | LEVEL(L3) | P(SNOOP, HITM); + } else { + if (sub_idx == 0) + ret = PH(LVL, L2) | LEVEL(L2) | REM | P(SNOOP, HIT) | P(HOPS, 0); + else if (sub_idx == 1) + ret = PH(LVL, L2) | LEVEL(L2) | REM | P(SNOOP, HITM) | P(HOPS, 0); + else if (sub_idx == 2 || sub_idx == 4) + ret = PH(LVL, L3) | LEVEL(L3) | REM | P(SNOOP, HIT) | P(HOPS, 0); + else if (sub_idx == 3 || sub_idx == 5) + ret = PH(LVL, L3) | LEVEL(L3) | REM | P(SNOOP, HITM) | P(HOPS, 0); + } break; case 6: ret = PH(LVL, REM_CCE2); diff --git a/arch/powerpc/perf/isa207-common.h b/arch/powerpc/perf/isa207-common.h index 4a2cbc3dc047..ff122603989b 100644 --- a/arch/powerpc/perf/isa207-common.h +++ b/arch/powerpc/perf/isa207-common.h @@ -273,6 +273,8 @@ #define P(a, b) PERF_MEM_S(a, b) #define PH(a, b) (P(LVL, HIT) | P(a, b)) #define PM(a, b) (P(LVL, MISS) | P(a, b)) +#define LEVEL(x) P(LVLNUM, x) +#define REM P(REMOTE, REMOTE) int isa207_get_constraint(u64 event, unsigned long *maskp, unsigned long *valp, u64 event_config1); int isa207_compute_mmcr(u64 event[], int n_ev, diff --git a/arch/powerpc/perf/perf_regs.c b/arch/powerpc/perf/perf_regs.c index b931eed482c9..51d31b65e423 100644 --- a/arch/powerpc/perf/perf_regs.c +++ b/arch/powerpc/perf/perf_regs.c @@ -90,7 +90,11 @@ static u64 get_ext_regs_value(int idx) return mfspr(SPRN_SIER2); case PERF_REG_POWERPC_SIER3: return mfspr(SPRN_SIER3); + case PERF_REG_POWERPC_SDAR: + return mfspr(SPRN_SDAR); #endif + case PERF_REG_POWERPC_SIAR: + return mfspr(SPRN_SIAR); default: return 0; } } diff --git a/arch/powerpc/perf/power10-events-list.h b/arch/powerpc/perf/power10-events-list.h index 93be7197d250..564f14097f07 100644 --- a/arch/powerpc/perf/power10-events-list.h +++ b/arch/powerpc/perf/power10-events-list.h @@ -9,10 +9,10 @@ /* * Power10 event codes. */ -EVENT(PM_RUN_CYC, 0x600f4); +EVENT(PM_CYC, 0x600f4); EVENT(PM_DISP_STALL_CYC, 0x100f8); EVENT(PM_EXEC_STALL, 0x30008); -EVENT(PM_RUN_INST_CMPL, 0x500fa); +EVENT(PM_INST_CMPL, 0x500fa); EVENT(PM_BR_CMPL, 0x4d05e); EVENT(PM_BR_MPRED_CMPL, 0x400f6); EVENT(PM_BR_FIN, 0x2f04a); @@ -50,8 +50,8 @@ EVENT(PM_DTLB_MISS, 0x300fc); /* ITLB Reloaded */ EVENT(PM_ITLB_MISS, 0x400fc); -EVENT(PM_RUN_CYC_ALT, 0x0001e); -EVENT(PM_RUN_INST_CMPL_ALT, 0x00002); +EVENT(PM_CYC_ALT, 0x0001e); +EVENT(PM_INST_CMPL_ALT, 0x00002); /* * Memory Access Events diff --git a/arch/powerpc/perf/power10-pmu.c b/arch/powerpc/perf/power10-pmu.c index f9d64c63bb4a..9dd75f385837 100644 --- a/arch/powerpc/perf/power10-pmu.c +++ b/arch/powerpc/perf/power10-pmu.c @@ -91,8 +91,8 @@ extern u64 PERF_REG_EXTENDED_MASK; /* Table of alternatives, sorted by column 0 */ static const unsigned int power10_event_alternatives[][MAX_ALT] = { - { PM_RUN_CYC_ALT, PM_RUN_CYC }, - { PM_RUN_INST_CMPL_ALT, PM_RUN_INST_CMPL }, + { PM_CYC_ALT, PM_CYC }, + { PM_INST_CMPL_ALT, PM_INST_CMPL }, }; static int power10_get_alternatives(u64 event, unsigned int flags, u64 alt[]) @@ -118,8 +118,8 @@ static int power10_check_attr_config(struct perf_event *ev) return 0; } -GENERIC_EVENT_ATTR(cpu-cycles, PM_RUN_CYC); -GENERIC_EVENT_ATTR(instructions, PM_RUN_INST_CMPL); +GENERIC_EVENT_ATTR(cpu-cycles, PM_CYC); +GENERIC_EVENT_ATTR(instructions, PM_INST_CMPL); GENERIC_EVENT_ATTR(branch-instructions, PM_BR_CMPL); GENERIC_EVENT_ATTR(branch-misses, PM_BR_MPRED_CMPL); GENERIC_EVENT_ATTR(cache-references, PM_LD_REF_L1); @@ -148,8 +148,8 @@ CACHE_EVENT_ATTR(dTLB-load-misses, PM_DTLB_MISS); CACHE_EVENT_ATTR(iTLB-load-misses, PM_ITLB_MISS); static struct attribute *power10_events_attr_dd1[] = { - GENERIC_EVENT_PTR(PM_RUN_CYC), - GENERIC_EVENT_PTR(PM_RUN_INST_CMPL), + GENERIC_EVENT_PTR(PM_CYC), + GENERIC_EVENT_PTR(PM_INST_CMPL), GENERIC_EVENT_PTR(PM_BR_CMPL), GENERIC_EVENT_PTR(PM_BR_MPRED_CMPL), GENERIC_EVENT_PTR(PM_LD_REF_L1), @@ -173,8 +173,8 @@ static struct attribute *power10_events_attr_dd1[] = { }; static struct attribute *power10_events_attr[] = { - GENERIC_EVENT_PTR(PM_RUN_CYC), - GENERIC_EVENT_PTR(PM_RUN_INST_CMPL), + GENERIC_EVENT_PTR(PM_CYC), + GENERIC_EVENT_PTR(PM_INST_CMPL), GENERIC_EVENT_PTR(PM_BR_FIN), GENERIC_EVENT_PTR(PM_MPRED_BR_FIN), GENERIC_EVENT_PTR(PM_LD_REF_L1), @@ -271,8 +271,8 @@ static const struct attribute_group *power10_pmu_attr_groups[] = { }; static int power10_generic_events_dd1[] = { - [PERF_COUNT_HW_CPU_CYCLES] = PM_RUN_CYC, - [PERF_COUNT_HW_INSTRUCTIONS] = PM_RUN_INST_CMPL, + [PERF_COUNT_HW_CPU_CYCLES] = PM_CYC, + [PERF_COUNT_HW_INSTRUCTIONS] = PM_INST_CMPL, [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = PM_BR_CMPL, [PERF_COUNT_HW_BRANCH_MISSES] = PM_BR_MPRED_CMPL, [PERF_COUNT_HW_CACHE_REFERENCES] = PM_LD_REF_L1, @@ -280,8 +280,8 @@ static int power10_generic_events_dd1[] = { }; static int power10_generic_events[] = { - [PERF_COUNT_HW_CPU_CYCLES] = PM_RUN_CYC, - [PERF_COUNT_HW_INSTRUCTIONS] = PM_RUN_INST_CMPL, + [PERF_COUNT_HW_CPU_CYCLES] = PM_CYC, + [PERF_COUNT_HW_INSTRUCTIONS] = PM_INST_CMPL, [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = PM_BR_FIN, [PERF_COUNT_HW_BRANCH_MISSES] = PM_MPRED_BR_FIN, [PERF_COUNT_HW_CACHE_REFERENCES] = PM_LD_REF_L1, @@ -548,6 +548,24 @@ static u64 power10_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { #undef C +/* + * Set the MMCR0[CC56RUN] bit to enable counting for + * PMC5 and PMC6 regardless of the state of CTRL[RUN], + * so that we can use counters 5 and 6 as PM_INST_CMPL and + * PM_CYC. + */ +static int power10_compute_mmcr(u64 event[], int n_ev, + unsigned int hwc[], struct mmcr_regs *mmcr, + struct perf_event *pevents[], u32 flags) +{ + int ret; + + ret = isa207_compute_mmcr(event, n_ev, hwc, mmcr, pevents, flags); + if (!ret) + mmcr->mmcr0 |= MMCR0_C56RUN; + return ret; +} + static struct power_pmu power10_pmu = { .name = "POWER10", .n_counter = MAX_PMU_COUNTERS, @@ -555,7 +573,7 @@ static struct power_pmu power10_pmu = { .test_adder = ISA207_TEST_ADDER, .group_constraint_mask = CNST_CACHE_PMC4_MASK, .group_constraint_val = CNST_CACHE_PMC4_VAL, - .compute_mmcr = isa207_compute_mmcr, + .compute_mmcr = power10_compute_mmcr, .config_bhrb = power10_config_bhrb, .bhrb_filter_map = power10_bhrb_filter_map, .get_constraint = isa207_get_constraint, diff --git a/arch/powerpc/platforms/44x/fsp2.c b/arch/powerpc/platforms/44x/fsp2.c index b299e43f5ef9..823397c802de 100644 --- a/arch/powerpc/platforms/44x/fsp2.c +++ b/arch/powerpc/platforms/44x/fsp2.c @@ -208,6 +208,7 @@ static void node_irq_request(const char *compat, irq_handler_t errirq_handler) if (irq == NO_IRQ) { pr_err("device tree node %pOFn is missing a interrupt", np); + of_node_put(np); return; } @@ -215,6 +216,7 @@ static void node_irq_request(const char *compat, irq_handler_t errirq_handler) if (rc) { pr_err("fsp_of_probe: request_irq failed: np=%pOF rc=%d", np, rc); + of_node_put(np); return; } } diff --git a/arch/powerpc/platforms/44x/ppc476.c b/arch/powerpc/platforms/44x/ppc476.c index 07f7e3ce67b5..fb7db5cedd4e 100644 --- a/arch/powerpc/platforms/44x/ppc476.c +++ b/arch/powerpc/platforms/44x/ppc476.c @@ -219,7 +219,7 @@ static int board_rev = -1; static int __init ppc47x_get_board_rev(void) { int reg; - u8 *fpga; + u8 __iomem *fpga; struct device_node *np = NULL; if (of_machine_is_compatible("ibm,currituck")) { @@ -233,7 +233,7 @@ static int __init ppc47x_get_board_rev(void) if (!np) goto fail; - fpga = (u8 *) of_iomap(np, 0); + fpga = of_iomap(np, 0); of_node_put(np); if (!fpga) goto fail; diff --git a/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c b/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c index 409481016928..bb789f33c70e 100644 --- a/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c +++ b/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c @@ -135,11 +135,10 @@ static int mcu_gpiochip_add(struct mcu *mcu) return gpiochip_add_data(gc, mcu); } -static int mcu_gpiochip_remove(struct mcu *mcu) +static void mcu_gpiochip_remove(struct mcu *mcu) { kfree(mcu->gc.label); gpiochip_remove(&mcu->gc); - return 0; } static int mcu_probe(struct i2c_client *client) @@ -198,9 +197,7 @@ static int mcu_remove(struct i2c_client *client) glob_mcu = NULL; } - ret = mcu_gpiochip_remove(mcu); - if (ret) - return ret; + mcu_gpiochip_remove(mcu); kfree(mcu); return 0; } diff --git a/arch/powerpc/platforms/85xx/Makefile b/arch/powerpc/platforms/85xx/Makefile index 60e4e97a929d..260fbad7967b 100644 --- a/arch/powerpc/platforms/85xx/Makefile +++ b/arch/powerpc/platforms/85xx/Makefile @@ -3,7 +3,9 @@ # Makefile for the PowerPC 85xx linux kernel. # obj-$(CONFIG_SMP) += smp.o -obj-$(CONFIG_FSL_PMC) += mpc85xx_pm_ops.o +ifneq ($(CONFIG_FSL_CORENET_RCPM),y) +obj-$(CONFIG_SMP) += mpc85xx_pm_ops.o +endif obj-y += common.o diff --git a/arch/powerpc/platforms/85xx/mpc85xx_pm_ops.c b/arch/powerpc/platforms/85xx/mpc85xx_pm_ops.c index 7c0133f558d0..4a8af80011a6 100644 --- a/arch/powerpc/platforms/85xx/mpc85xx_pm_ops.c +++ b/arch/powerpc/platforms/85xx/mpc85xx_pm_ops.c @@ -17,6 +17,7 @@ static struct ccsr_guts __iomem *guts; +#ifdef CONFIG_FSL_PMC static void mpc85xx_irq_mask(int cpu) { @@ -49,6 +50,7 @@ static void mpc85xx_cpu_up_prepare(int cpu) { } +#endif static void mpc85xx_freeze_time_base(bool freeze) { @@ -76,10 +78,12 @@ static const struct of_device_id mpc85xx_smp_guts_ids[] = { static const struct fsl_pm_ops mpc85xx_pm_ops = { .freeze_time_base = mpc85xx_freeze_time_base, +#ifdef CONFIG_FSL_PMC .irq_mask = mpc85xx_irq_mask, .irq_unmask = mpc85xx_irq_unmask, .cpu_die = mpc85xx_cpu_die, .cpu_up_prepare = mpc85xx_cpu_up_prepare, +#endif }; int __init mpc85xx_setup_pmc(void) @@ -94,9 +98,8 @@ int __init mpc85xx_setup_pmc(void) pr_err("Could not map guts node address\n"); return -ENOMEM; } + qoriq_pm_ops = &mpc85xx_pm_ops; } - qoriq_pm_ops = &mpc85xx_pm_ops; - return 0; } diff --git a/arch/powerpc/platforms/85xx/smp.c b/arch/powerpc/platforms/85xx/smp.c index c6df294054fe..83f4a6389a28 100644 --- a/arch/powerpc/platforms/85xx/smp.c +++ b/arch/powerpc/platforms/85xx/smp.c @@ -40,7 +40,6 @@ struct epapr_spin_table { u32 pir; }; -#ifdef CONFIG_HOTPLUG_CPU static u64 timebase; static int tb_req; static int tb_valid; @@ -112,6 +111,7 @@ static void mpc85xx_take_timebase(void) local_irq_restore(flags); } +#ifdef CONFIG_HOTPLUG_CPU static void smp_85xx_cpu_offline_self(void) { unsigned int cpu = smp_processor_id(); @@ -495,21 +495,21 @@ void __init mpc85xx_smp_init(void) smp_85xx_ops.probe = NULL; } -#ifdef CONFIG_HOTPLUG_CPU #ifdef CONFIG_FSL_CORENET_RCPM + /* Assign a value to qoriq_pm_ops on PPC_E500MC */ fsl_rcpm_init(); -#endif - -#ifdef CONFIG_FSL_PMC +#else + /* Assign a value to qoriq_pm_ops on !PPC_E500MC */ mpc85xx_setup_pmc(); #endif if (qoriq_pm_ops) { smp_85xx_ops.give_timebase = mpc85xx_give_timebase; smp_85xx_ops.take_timebase = mpc85xx_take_timebase; +#ifdef CONFIG_HOTPLUG_CPU smp_85xx_ops.cpu_offline_self = smp_85xx_cpu_offline_self; smp_85xx_ops.cpu_die = qoriq_cpu_kill; - } #endif + } smp_ops = &smp_85xx_ops; #ifdef CONFIG_KEXEC_CORE diff --git a/arch/powerpc/platforms/book3s/vas-api.c b/arch/powerpc/platforms/book3s/vas-api.c index 30172e52e16b..4d82c92ddd52 100644 --- a/arch/powerpc/platforms/book3s/vas-api.c +++ b/arch/powerpc/platforms/book3s/vas-api.c @@ -303,7 +303,7 @@ static int coproc_ioc_tx_win_open(struct file *fp, unsigned long arg) return -EINVAL; } - if (!cp_inst->coproc->vops && !cp_inst->coproc->vops->open_win) { + if (!cp_inst->coproc->vops || !cp_inst->coproc->vops->open_win) { pr_err("VAS API is not registered\n"); return -EACCES; } @@ -373,7 +373,7 @@ static int coproc_mmap(struct file *fp, struct vm_area_struct *vma) return -EINVAL; } - if (!cp_inst->coproc->vops && !cp_inst->coproc->vops->paste_addr) { + if (!cp_inst->coproc->vops || !cp_inst->coproc->vops->paste_addr) { pr_err("%s(): VAS API is not registered\n", __func__); return -EACCES; } diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c index bed05b644c2c..cb25acccd746 100644 --- a/arch/powerpc/platforms/cell/spufs/inode.c +++ b/arch/powerpc/platforms/cell/spufs/inode.c @@ -21,6 +21,7 @@ #include <linux/namei.h> #include <linux/pagemap.h> #include <linux/poll.h> +#include <linux/seq_file.h> #include <linux/slab.h> #include <asm/prom.h> diff --git a/arch/powerpc/platforms/powermac/pmac.h b/arch/powerpc/platforms/powermac/pmac.h index 0d715db434dc..29d2036dcc9d 100644 --- a/arch/powerpc/platforms/powermac/pmac.h +++ b/arch/powerpc/platforms/powermac/pmac.h @@ -27,7 +27,6 @@ extern void pmac_nvram_update(void); extern unsigned char pmac_nvram_read_byte(int addr); extern void pmac_nvram_write_byte(int addr, unsigned char val); extern void pmac_pcibios_after_init(void); -extern int of_show_percpuinfo(struct seq_file *m, int i); extern void pmac_setup_pci_dma(void); extern void pmac_check_ht_link(void); diff --git a/arch/powerpc/platforms/powermac/setup.c b/arch/powerpc/platforms/powermac/setup.c index 86aee3f2483f..13e8a8a9841c 100644 --- a/arch/powerpc/platforms/powermac/setup.c +++ b/arch/powerpc/platforms/powermac/setup.c @@ -79,8 +79,6 @@ int pmac_newworld; static int current_root_goodness = -1; -extern struct machdep_calls pmac_md; - #define DEFAULT_ROOT_DEVICE Root_SDA1 /* sda1 - slightly silly choice */ #ifdef CONFIG_PPC64 diff --git a/arch/powerpc/platforms/powernv/ocxl.c b/arch/powerpc/platforms/powernv/ocxl.c index 9105efcf242a..28b009b46464 100644 --- a/arch/powerpc/platforms/powernv/ocxl.c +++ b/arch/powerpc/platforms/powernv/ocxl.c @@ -107,7 +107,8 @@ static int get_max_afu_index(struct pci_dev *dev, int *afu_idx) int pos; u32 val; - pos = find_dvsec_from_pos(dev, OCXL_DVSEC_FUNC_ID, 0); + pos = pci_find_dvsec_capability(dev, PCI_VENDOR_ID_IBM, + OCXL_DVSEC_FUNC_ID); if (!pos) return -ESRCH; diff --git a/arch/powerpc/platforms/powernv/opal-dump.c b/arch/powerpc/platforms/powernv/opal-dump.c index 00c5a59d82d9..717d1d30ade5 100644 --- a/arch/powerpc/platforms/powernv/opal-dump.c +++ b/arch/powerpc/platforms/powernv/opal-dump.c @@ -419,7 +419,7 @@ void __init opal_platform_dump_init(void) int rc; int dump_irq; - /* ELOG not supported by firmware */ + /* Dump not supported by firmware */ if (!opal_check_token(OPAL_DUMP_READ)) return; diff --git a/arch/powerpc/platforms/powernv/opal-prd.c b/arch/powerpc/platforms/powernv/opal-prd.c index a191f4c60ce7..113bdb151f68 100644 --- a/arch/powerpc/platforms/powernv/opal-prd.c +++ b/arch/powerpc/platforms/powernv/opal-prd.c @@ -369,6 +369,12 @@ static struct notifier_block opal_prd_event_nb = { .priority = 0, }; +static struct notifier_block opal_prd_event_nb2 = { + .notifier_call = opal_prd_msg_notifier, + .next = NULL, + .priority = 0, +}; + static int opal_prd_probe(struct platform_device *pdev) { int rc; @@ -390,9 +396,10 @@ static int opal_prd_probe(struct platform_device *pdev) return rc; } - rc = opal_message_notifier_register(OPAL_MSG_PRD2, &opal_prd_event_nb); + rc = opal_message_notifier_register(OPAL_MSG_PRD2, &opal_prd_event_nb2); if (rc) { pr_err("Couldn't register PRD2 event notifier\n"); + opal_message_notifier_unregister(OPAL_MSG_PRD, &opal_prd_event_nb); return rc; } @@ -401,6 +408,8 @@ static int opal_prd_probe(struct platform_device *pdev) pr_err("failed to register miscdev\n"); opal_message_notifier_unregister(OPAL_MSG_PRD, &opal_prd_event_nb); + opal_message_notifier_unregister(OPAL_MSG_PRD2, + &opal_prd_event_nb2); return rc; } @@ -411,6 +420,7 @@ static int opal_prd_remove(struct platform_device *pdev) { misc_deregister(&opal_prd_dev); opal_message_notifier_unregister(OPAL_MSG_PRD, &opal_prd_event_nb); + opal_message_notifier_unregister(OPAL_MSG_PRD2, &opal_prd_event_nb2); return 0; } diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 3dd35c327d1c..004cd6a96c8a 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -2981,7 +2981,7 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np, if (!phb->hose) { pr_err(" Can't allocate PCI controller for %pOF\n", np); - memblock_free(__pa(phb), sizeof(struct pnv_phb)); + memblock_free(phb, sizeof(struct pnv_phb)); return; } diff --git a/arch/powerpc/platforms/powernv/pci-sriov.c b/arch/powerpc/platforms/powernv/pci-sriov.c index 28aac933a439..04155aaaadb1 100644 --- a/arch/powerpc/platforms/powernv/pci-sriov.c +++ b/arch/powerpc/platforms/powernv/pci-sriov.c @@ -9,9 +9,6 @@ #include "pci.h" -/* for pci_dev_is_added() */ -#include "../../../../drivers/pci/pci.h" - /* * The majority of the complexity in supporting SR-IOV on PowerNV comes from * the need to put the MMIO space for each VF into a separate PE. Internally @@ -54,7 +51,7 @@ * to "new_size", calculated above. Implementing this is a convoluted process * which requires several hooks in the PCI core: * - * 1. In pcibios_add_device() we call pnv_pci_ioda_fixup_iov(). + * 1. In pcibios_device_add() we call pnv_pci_ioda_fixup_iov(). * * At this point the device has been probed and the device's BARs are sized, * but no resource allocations have been done. The SR-IOV BARs are sized @@ -228,9 +225,6 @@ disable_iov: void pnv_pci_ioda_fixup_iov(struct pci_dev *pdev) { - if (WARN_ON(pci_dev_is_added(pdev))) - return; - if (pdev->is_virtfn) { struct pnv_ioda_pe *pe = pnv_ioda_get_pe(pdev); diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c index a8db3f153063..ad56a54ac9c5 100644 --- a/arch/powerpc/platforms/powernv/setup.c +++ b/arch/powerpc/platforms/powernv/setup.c @@ -440,7 +440,7 @@ static void pnv_kexec_cpu_down(int crash_shutdown, int secondary) } #endif /* CONFIG_KEXEC_CORE */ -#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE +#ifdef CONFIG_MEMORY_HOTPLUG static unsigned long pnv_memory_block_size(void) { /* @@ -553,7 +553,7 @@ define_machine(powernv) { #ifdef CONFIG_KEXEC_CORE .kexec_cpu_down = pnv_kexec_cpu_down, #endif -#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE +#ifdef CONFIG_MEMORY_HOTPLUG .memory_block_size = pnv_memory_block_size, #endif }; diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig index 5e037df2a3a1..2e57391e0778 100644 --- a/arch/powerpc/platforms/pseries/Kconfig +++ b/arch/powerpc/platforms/pseries/Kconfig @@ -159,6 +159,7 @@ config PPC_SVM select SWIOTLB select ARCH_HAS_MEM_ENCRYPT select ARCH_HAS_FORCE_DMA_UNENCRYPTED + select ARCH_HAS_CC_PLATFORM help There are certain POWER platforms which support secure guests using the Protected Execution Facility, with the help of an Ultravisor diff --git a/arch/powerpc/platforms/pseries/Makefile b/arch/powerpc/platforms/pseries/Makefile index 4cda0ef87be0..41d8aee98da4 100644 --- a/arch/powerpc/platforms/pseries/Makefile +++ b/arch/powerpc/platforms/pseries/Makefile @@ -31,3 +31,5 @@ obj-$(CONFIG_FA_DUMP) += rtas-fadump.o obj-$(CONFIG_SUSPEND) += suspend.o obj-$(CONFIG_PPC_VAS) += vas.o + +obj-$(CONFIG_ARCH_HAS_CC_PLATFORM) += cc_platform.o diff --git a/arch/powerpc/platforms/pseries/cc_platform.c b/arch/powerpc/platforms/pseries/cc_platform.c new file mode 100644 index 000000000000..e8021af83a19 --- /dev/null +++ b/arch/powerpc/platforms/pseries/cc_platform.c @@ -0,0 +1,26 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Confidential Computing Platform Capability checks + * + * Copyright (C) 2021 Advanced Micro Devices, Inc. + * + * Author: Tom Lendacky <thomas.lendacky@amd.com> + */ + +#include <linux/export.h> +#include <linux/cc_platform.h> + +#include <asm/machdep.h> +#include <asm/svm.h> + +bool cc_platform_has(enum cc_attr attr) +{ + switch (attr) { + case CC_ATTR_MEM_ENCRYPT: + return is_secure_guest(); + + default: + return false; + } +} +EXPORT_SYMBOL_GPL(cc_platform_has); diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c index bc15200852b7..09fafcf2d3a0 100644 --- a/arch/powerpc/platforms/pseries/eeh_pseries.c +++ b/arch/powerpc/platforms/pseries/eeh_pseries.c @@ -867,6 +867,10 @@ static int __init eeh_pseries_init(void) if (is_kdump_kernel() || reset_devices) { pr_info("Issue PHB reset ...\n"); list_for_each_entry(phb, &hose_list, list_node) { + // Skip if the slot is empty + if (list_empty(&PCI_DN(phb->dn)->child_list)) + continue; + pdn = list_first_entry(&PCI_DN(phb->dn)->child_list, struct pci_dn, list); config_addr = pseries_eeh_get_pe_config_addr(pdn); diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c index d646c22e94ab..5ab44600c8d3 100644 --- a/arch/powerpc/platforms/pseries/hotplug-cpu.c +++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c @@ -137,11 +137,6 @@ static void pseries_cpu_die(unsigned int cpu) cpu, pcpu); } - /* Isolation and deallocation are definitely done by - * drslot_chrp_cpu. If they were not they would be - * done here. Change isolate state to Isolate and - * change allocation-state to Unusable. - */ paca_ptrs[cpu]->cpu_start = 0; } @@ -521,6 +516,27 @@ static bool valid_cpu_drc_index(struct device_node *parent, u32 drc_index) return found; } +static int pseries_cpuhp_attach_nodes(struct device_node *dn) +{ + struct of_changeset cs; + int ret; + + /* + * This device node is unattached but may have siblings; open-code the + * traversal. + */ + for (of_changeset_init(&cs); dn != NULL; dn = dn->sibling) { + ret = of_changeset_attach_node(&cs, dn); + if (ret) + goto out; + } + + ret = of_changeset_apply(&cs); +out: + of_changeset_destroy(&cs); + return ret; +} + static ssize_t dlpar_cpu_add(u32 drc_index) { struct device_node *dn, *parent; @@ -563,7 +579,7 @@ static ssize_t dlpar_cpu_add(u32 drc_index) return -EINVAL; } - rc = dlpar_attach_node(dn, parent); + rc = pseries_cpuhp_attach_nodes(dn); /* Regardless we are done with parent now */ of_node_put(parent); @@ -600,6 +616,53 @@ static ssize_t dlpar_cpu_add(u32 drc_index) return rc; } +static unsigned int pseries_cpuhp_cache_use_count(const struct device_node *cachedn) +{ + unsigned int use_count = 0; + struct device_node *dn; + + WARN_ON(!of_node_is_type(cachedn, "cache")); + + for_each_of_cpu_node(dn) { + if (of_find_next_cache_node(dn) == cachedn) + use_count++; + } + + for_each_node_by_type(dn, "cache") { + if (of_find_next_cache_node(dn) == cachedn) + use_count++; + } + + return use_count; +} + +static int pseries_cpuhp_detach_nodes(struct device_node *cpudn) +{ + struct device_node *dn; + struct of_changeset cs; + int ret = 0; + + of_changeset_init(&cs); + ret = of_changeset_detach_node(&cs, cpudn); + if (ret) + goto out; + + dn = cpudn; + while ((dn = of_find_next_cache_node(dn))) { + if (pseries_cpuhp_cache_use_count(dn) > 1) + break; + + ret = of_changeset_detach_node(&cs, dn); + if (ret) + goto out; + } + + ret = of_changeset_apply(&cs); +out: + of_changeset_destroy(&cs); + return ret; +} + static ssize_t dlpar_cpu_remove(struct device_node *dn, u32 drc_index) { int rc; @@ -621,7 +684,7 @@ static ssize_t dlpar_cpu_remove(struct device_node *dn, u32 drc_index) return rc; } - rc = dlpar_detach_node(dn); + rc = pseries_cpuhp_detach_nodes(dn); if (rc) { int saved_rc = rc; @@ -673,231 +736,18 @@ static int dlpar_cpu_remove_by_index(u32 drc_index) return rc; } -static int find_dlpar_cpus_to_remove(u32 *cpu_drcs, int cpus_to_remove) -{ - struct device_node *dn; - int cpus_found = 0; - int rc; - - /* We want to find cpus_to_remove + 1 CPUs to ensure we do not - * remove the last CPU. - */ - for_each_node_by_type(dn, "cpu") { - cpus_found++; - - if (cpus_found > cpus_to_remove) { - of_node_put(dn); - break; - } - - /* Note that cpus_found is always 1 ahead of the index - * into the cpu_drcs array, so we use cpus_found - 1 - */ - rc = of_property_read_u32(dn, "ibm,my-drc-index", - &cpu_drcs[cpus_found - 1]); - if (rc) { - pr_warn("Error occurred getting drc-index for %pOFn\n", - dn); - of_node_put(dn); - return -1; - } - } - - if (cpus_found < cpus_to_remove) { - pr_warn("Failed to find enough CPUs (%d of %d) to remove\n", - cpus_found, cpus_to_remove); - } else if (cpus_found == cpus_to_remove) { - pr_warn("Cannot remove all CPUs\n"); - } - - return cpus_found; -} - -static int dlpar_cpu_remove_by_count(u32 cpus_to_remove) -{ - u32 *cpu_drcs; - int cpus_found; - int cpus_removed = 0; - int i, rc; - - pr_debug("Attempting to hot-remove %d CPUs\n", cpus_to_remove); - - cpu_drcs = kcalloc(cpus_to_remove, sizeof(*cpu_drcs), GFP_KERNEL); - if (!cpu_drcs) - return -EINVAL; - - cpus_found = find_dlpar_cpus_to_remove(cpu_drcs, cpus_to_remove); - if (cpus_found <= cpus_to_remove) { - kfree(cpu_drcs); - return -EINVAL; - } - - for (i = 0; i < cpus_to_remove; i++) { - rc = dlpar_cpu_remove_by_index(cpu_drcs[i]); - if (rc) - break; - - cpus_removed++; - } - - if (cpus_removed != cpus_to_remove) { - pr_warn("CPU hot-remove failed, adding back removed CPUs\n"); - - for (i = 0; i < cpus_removed; i++) - dlpar_cpu_add(cpu_drcs[i]); - - rc = -EINVAL; - } else { - rc = 0; - } - - kfree(cpu_drcs); - return rc; -} - -static int find_drc_info_cpus_to_add(struct device_node *cpus, - struct property *info, - u32 *cpu_drcs, u32 cpus_to_add) -{ - struct of_drc_info drc; - const __be32 *value; - u32 count, drc_index; - int cpus_found = 0; - int i, j; - - if (!info) - return -1; - - value = of_prop_next_u32(info, NULL, &count); - if (value) - value++; - - for (i = 0; i < count; i++) { - of_read_drc_info_cell(&info, &value, &drc); - if (strncmp(drc.drc_type, "CPU", 3)) - break; - - drc_index = drc.drc_index_start; - for (j = 0; j < drc.num_sequential_elems; j++) { - if (dlpar_cpu_exists(cpus, drc_index)) - continue; - - cpu_drcs[cpus_found++] = drc_index; - - if (cpus_found == cpus_to_add) - return cpus_found; - - drc_index += drc.sequential_inc; - } - } - - return cpus_found; -} - -static int find_drc_index_cpus_to_add(struct device_node *cpus, - u32 *cpu_drcs, u32 cpus_to_add) -{ - int cpus_found = 0; - int index, rc; - u32 drc_index; - - /* Search the ibm,drc-indexes array for possible CPU drcs to - * add. Note that the format of the ibm,drc-indexes array is - * the number of entries in the array followed by the array - * of drc values so we start looking at index = 1. - */ - index = 1; - while (cpus_found < cpus_to_add) { - rc = of_property_read_u32_index(cpus, "ibm,drc-indexes", - index++, &drc_index); - - if (rc) - break; - - if (dlpar_cpu_exists(cpus, drc_index)) - continue; - - cpu_drcs[cpus_found++] = drc_index; - } - - return cpus_found; -} - -static int dlpar_cpu_add_by_count(u32 cpus_to_add) -{ - struct device_node *parent; - struct property *info; - u32 *cpu_drcs; - int cpus_added = 0; - int cpus_found; - int i, rc; - - pr_debug("Attempting to hot-add %d CPUs\n", cpus_to_add); - - cpu_drcs = kcalloc(cpus_to_add, sizeof(*cpu_drcs), GFP_KERNEL); - if (!cpu_drcs) - return -EINVAL; - - parent = of_find_node_by_path("/cpus"); - if (!parent) { - pr_warn("Could not find CPU root node in device tree\n"); - kfree(cpu_drcs); - return -1; - } - - info = of_find_property(parent, "ibm,drc-info", NULL); - if (info) - cpus_found = find_drc_info_cpus_to_add(parent, info, cpu_drcs, cpus_to_add); - else - cpus_found = find_drc_index_cpus_to_add(parent, cpu_drcs, cpus_to_add); - - of_node_put(parent); - - if (cpus_found < cpus_to_add) { - pr_warn("Failed to find enough CPUs (%d of %d) to add\n", - cpus_found, cpus_to_add); - kfree(cpu_drcs); - return -EINVAL; - } - - for (i = 0; i < cpus_to_add; i++) { - rc = dlpar_cpu_add(cpu_drcs[i]); - if (rc) - break; - - cpus_added++; - } - - if (cpus_added < cpus_to_add) { - pr_warn("CPU hot-add failed, removing any added CPUs\n"); - - for (i = 0; i < cpus_added; i++) - dlpar_cpu_remove_by_index(cpu_drcs[i]); - - rc = -EINVAL; - } else { - rc = 0; - } - - kfree(cpu_drcs); - return rc; -} - int dlpar_cpu(struct pseries_hp_errorlog *hp_elog) { - u32 count, drc_index; + u32 drc_index; int rc; - count = hp_elog->_drc_u.drc_count; drc_index = hp_elog->_drc_u.drc_index; lock_device_hotplug(); switch (hp_elog->action) { case PSERIES_HP_ELOG_ACTION_REMOVE: - if (hp_elog->id_type == PSERIES_HP_ELOG_ID_DRC_COUNT) - rc = dlpar_cpu_remove_by_count(count); - else if (hp_elog->id_type == PSERIES_HP_ELOG_ID_DRC_INDEX) { + if (hp_elog->id_type == PSERIES_HP_ELOG_ID_DRC_INDEX) { rc = dlpar_cpu_remove_by_index(drc_index); /* * Setting the isolation state of an UNISOLATED/CONFIGURED @@ -911,9 +761,7 @@ int dlpar_cpu(struct pseries_hp_errorlog *hp_elog) rc = -EINVAL; break; case PSERIES_HP_ELOG_ACTION_ADD: - if (hp_elog->id_type == PSERIES_HP_ELOG_ID_DRC_COUNT) - rc = dlpar_cpu_add_by_count(count); - else if (hp_elog->id_type == PSERIES_HP_ELOG_ID_DRC_INDEX) + if (hp_elog->id_type == PSERIES_HP_ELOG_ID_DRC_INDEX) rc = dlpar_cpu_add(drc_index); else rc = -EINVAL; diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index dab5c56ffd0e..49b401536d29 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -929,8 +929,10 @@ static void find_existing_ddw_windows_named(const char *name) } window = ddw_list_new_entry(pdn, dma64); - if (!window) + if (!window) { + of_node_put(pdn); break; + } spin_lock(&dma_win_list_lock); list_add(&window->list, &dma_win_list); @@ -1159,14 +1161,15 @@ static void reset_dma_window(struct pci_dev *dev, struct device_node *par_dn) /* Return largest page shift based on "IO Page Sizes" output of ibm,query-pe-dma-window. */ static int iommu_get_page_shift(u32 query_page_size) { - /* Supported IO page-sizes according to LoPAR */ + /* Supported IO page-sizes according to LoPAR, note that 2M is out of order */ const int shift[] = { __builtin_ctzll(SZ_4K), __builtin_ctzll(SZ_64K), __builtin_ctzll(SZ_16M), __builtin_ctzll(SZ_32M), __builtin_ctzll(SZ_64M), __builtin_ctzll(SZ_128M), - __builtin_ctzll(SZ_256M), __builtin_ctzll(SZ_16G) + __builtin_ctzll(SZ_256M), __builtin_ctzll(SZ_16G), __builtin_ctzll(SZ_2M) }; int i = ARRAY_SIZE(shift) - 1; + int ret = 0; /* * On LoPAR, ibm,query-pe-dma-window outputs "IO Page Sizes" using a bit field: @@ -1176,11 +1179,10 @@ static int iommu_get_page_shift(u32 query_page_size) */ for (; i >= 0 ; i--) { if (query_page_size & (1 << i)) - return shift[i]; + ret = max(ret, shift[i]); } - /* No valid page size found. */ - return 0; + return ret; } static struct property *ddw_property_create(const char *propname, u32 liobn, u64 dma_addr, @@ -1302,6 +1304,12 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn) struct property *default_win; int reset_win_ext; + /* DDW + IOMMU on single window may fail if there is any allocation */ + if (iommu_table_in_use(tbl)) { + dev_warn(&dev->dev, "current IOMMU table in use, can't be replaced.\n"); + goto out_failed; + } + default_win = of_find_property(pdn, "ibm,dma-window", NULL); if (!default_win) goto out_failed; @@ -1356,12 +1364,6 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn) query.largest_available_block, 1ULL << page_shift); - /* DDW + IOMMU on single window may fail if there is any allocation */ - if (default_win_removed && iommu_table_in_use(tbl)) { - dev_dbg(&dev->dev, "current IOMMU table in use, can't be replaced.\n"); - goto out_failed; - } - len = order_base_2(query.largest_available_block << page_shift); win_name = DMA64_PROPNAME; } else { @@ -1411,18 +1413,19 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn) } else { struct iommu_table *newtbl; int i; + unsigned long start = 0, end = 0; for (i = 0; i < ARRAY_SIZE(pci->phb->mem_resources); i++) { const unsigned long mask = IORESOURCE_MEM_64 | IORESOURCE_MEM; /* Look for MMIO32 */ - if ((pci->phb->mem_resources[i].flags & mask) == IORESOURCE_MEM) + if ((pci->phb->mem_resources[i].flags & mask) == IORESOURCE_MEM) { + start = pci->phb->mem_resources[i].start; + end = pci->phb->mem_resources[i].end; break; + } } - if (i == ARRAY_SIZE(pci->phb->mem_resources)) - goto out_del_list; - /* New table for using DDW instead of the default DMA window */ newtbl = iommu_pseries_alloc_table(pci->phb->node); if (!newtbl) { @@ -1432,15 +1435,15 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn) iommu_table_setparms_common(newtbl, pci->phb->bus->number, create.liobn, win_addr, 1UL << len, page_shift, NULL, &iommu_table_lpar_multi_ops); - iommu_init_table(newtbl, pci->phb->node, pci->phb->mem_resources[i].start, - pci->phb->mem_resources[i].end); + iommu_init_table(newtbl, pci->phb->node, start, end); pci->table_group->tables[1] = newtbl; /* Keep default DMA window stuct if removed */ if (default_win_removed) { tbl->it_size = 0; - kfree(tbl->it_map); + vfree(tbl->it_map); + tbl->it_map = NULL; } set_iommu_table_base(&dev->dev, newtbl); diff --git a/arch/powerpc/platforms/pseries/mobility.c b/arch/powerpc/platforms/pseries/mobility.c index e83e0891272d..210a37a065fb 100644 --- a/arch/powerpc/platforms/pseries/mobility.c +++ b/arch/powerpc/platforms/pseries/mobility.c @@ -63,6 +63,27 @@ static int mobility_rtas_call(int token, char *buf, s32 scope) static int delete_dt_node(struct device_node *dn) { + struct device_node *pdn; + bool is_platfac; + + pdn = of_get_parent(dn); + is_platfac = of_node_is_type(dn, "ibm,platform-facilities") || + of_node_is_type(pdn, "ibm,platform-facilities"); + of_node_put(pdn); + + /* + * The drivers that bind to nodes in the platform-facilities + * hierarchy don't support node removal, and the removal directive + * from firmware is always followed by an add of an equivalent + * node. The capability (e.g. RNG, encryption, compression) + * represented by the node is never interrupted by the migration. + * So ignore changes to this part of the tree. + */ + if (is_platfac) { + pr_notice("ignoring remove operation for %pOFfp\n", dn); + return 0; + } + pr_debug("removing node %pOFfp\n", dn); dlpar_detach_node(dn); return 0; @@ -222,6 +243,19 @@ static int add_dt_node(struct device_node *parent_dn, __be32 drc_index) if (!dn) return -ENOENT; + /* + * Since delete_dt_node() ignores this node type, this is the + * necessary counterpart. We also know that a platform-facilities + * node returned from dlpar_configure_connector() has children + * attached, and dlpar_attach_node() only adds the parent, leaking + * the children. So ignore these on the add side for now. + */ + if (of_node_is_type(dn, "ibm,platform-facilities")) { + pr_notice("ignoring add operation for %pOF\n", dn); + dlpar_free_cc_nodes(dn); + return 0; + } + rc = dlpar_attach_node(dn, parent_dn); if (rc) dlpar_free_cc_nodes(dn); diff --git a/arch/powerpc/platforms/pseries/msi.c b/arch/powerpc/platforms/pseries/msi.c index 1b305e411862..8627362f613e 100644 --- a/arch/powerpc/platforms/pseries/msi.c +++ b/arch/powerpc/platforms/pseries/msi.c @@ -507,12 +507,27 @@ static void pseries_msi_unmask(struct irq_data *d) irq_chip_unmask_parent(d); } +static void pseries_msi_write_msg(struct irq_data *data, struct msi_msg *msg) +{ + struct msi_desc *entry = irq_data_get_msi_desc(data); + + /* + * Do not update the MSIx vector table. It's not strictly necessary + * because the table is initialized by the underlying hypervisor, PowerVM + * or QEMU/KVM. However, if the MSIx vector entry is cleared, any further + * activation will fail. This can happen in some drivers (eg. IPR) which + * deactivate an IRQ used for testing MSI support. + */ + entry->msg = *msg; +} + static struct irq_chip pseries_pci_msi_irq_chip = { .name = "pSeries-PCI-MSI", .irq_shutdown = pseries_msi_shutdown, .irq_mask = pseries_msi_mask, .irq_unmask = pseries_msi_unmask, .irq_eoi = irq_chip_eoi_parent, + .irq_write_msi_msg = pseries_msi_write_msg, }; static struct msi_domain_info pseries_msi_domain_info = { diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index f79126f16258..8a62af5b9c24 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -74,7 +74,6 @@ #include <asm/hvconsole.h> #include "pseries.h" -#include "../../../../drivers/pci/pci.h" DEFINE_STATIC_KEY_FALSE(shared_processor); EXPORT_SYMBOL(shared_processor); @@ -750,7 +749,7 @@ static void pseries_pci_fixup_iov_resources(struct pci_dev *pdev) const int *indexes; struct device_node *dn = pci_device_to_OF_node(pdev); - if (!pdev->is_physfn || pci_dev_is_added(pdev)) + if (!pdev->is_physfn) return; /*Firmware must support open sriov otherwise dont configure*/ indexes = of_get_property(dn, "ibm,open-sriov-vf-bar-info", NULL); @@ -1089,7 +1088,7 @@ define_machine(pseries) { .machine_kexec = pSeries_machine_kexec, .kexec_cpu_down = pseries_kexec_cpu_down, #endif -#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE +#ifdef CONFIG_MEMORY_HOTPLUG .memory_block_size = pseries_memory_block_size, #endif }; diff --git a/arch/powerpc/platforms/pseries/svm.c b/arch/powerpc/platforms/pseries/svm.c index 87f001b4c4e4..c5228f4969eb 100644 --- a/arch/powerpc/platforms/pseries/svm.c +++ b/arch/powerpc/platforms/pseries/svm.c @@ -8,6 +8,7 @@ #include <linux/mm.h> #include <linux/memblock.h> +#include <linux/cc_platform.h> #include <asm/machdep.h> #include <asm/svm.h> #include <asm/swiotlb.h> @@ -56,14 +57,13 @@ void __init svm_swiotlb_init(void) return; - memblock_free_early(__pa(vstart), - PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT)); + memblock_free(vstart, PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT)); panic("SVM: Cannot allocate SWIOTLB buffer"); } int set_memory_encrypted(unsigned long addr, int numpages) { - if (!mem_encrypt_active()) + if (!cc_platform_has(CC_ATTR_MEM_ENCRYPT)) return 0; if (!PAGE_ALIGNED(addr)) @@ -76,7 +76,7 @@ int set_memory_encrypted(unsigned long addr, int numpages) int set_memory_decrypted(unsigned long addr, int numpages) { - if (!mem_encrypt_active()) + if (!cc_platform_has(CC_ATTR_MEM_ENCRYPT)) return 0; if (!PAGE_ALIGNED(addr)) diff --git a/arch/powerpc/sysdev/dcr-low.S b/arch/powerpc/sysdev/dcr-low.S index efeeb1b885a1..329b9c4ae542 100644 --- a/arch/powerpc/sysdev/dcr-low.S +++ b/arch/powerpc/sysdev/dcr-low.S @@ -11,7 +11,7 @@ #include <asm/export.h> #define DCR_ACCESS_PROLOG(table) \ - cmpli cr0,r3,1024; \ + cmplwi cr0,r3,1024; \ rlwinm r3,r3,4,18,27; \ lis r5,table@h; \ ori r5,r5,table@l; \ diff --git a/arch/powerpc/sysdev/xics/xics-common.c b/arch/powerpc/sysdev/xics/xics-common.c index 5c1a157a83b8..244a727c6ba4 100644 --- a/arch/powerpc/sysdev/xics/xics-common.c +++ b/arch/powerpc/sysdev/xics/xics-common.c @@ -348,9 +348,9 @@ static int xics_host_map(struct irq_domain *domain, unsigned int virq, if (xics_ics->check(xics_ics, hwirq)) return -EINVAL; - /* No chip data for the XICS domain */ + /* Let the ICS be the chip data for the XICS domain. For ICS native */ irq_domain_set_info(domain, virq, hwirq, xics_ics->chip, - NULL, handle_fasteoi_irq, NULL, NULL); + xics_ics, handle_fasteoi_irq, NULL, NULL); return 0; } diff --git a/arch/powerpc/sysdev/xive/common.c b/arch/powerpc/sysdev/xive/common.c index c732ce5a3e1a..c5d75c02ad8b 100644 --- a/arch/powerpc/sysdev/xive/common.c +++ b/arch/powerpc/sysdev/xive/common.c @@ -945,7 +945,8 @@ static int xive_get_irqchip_state(struct irq_data *data, * interrupt to be inactive in that case. */ *state = (pq != XIVE_ESB_INVALID) && !xd->stale_p && - (xd->saved_p || !!(pq & XIVE_ESB_VAL_P)); + (xd->saved_p || (!!(pq & XIVE_ESB_VAL_P) && + !irqd_irq_disabled(data))); return 0; default: return -EINVAL; diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index dd8241c009e5..8b28ff9d98d1 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -3264,8 +3264,7 @@ static void show_task(struct task_struct *volatile tsk) * appropriate for calling from xmon. This could be moved * to a common, generic, routine used by both. */ - state = (p_state == 0) ? 'R' : - (p_state < 0) ? 'U' : + state = (p_state == TASK_RUNNING) ? 'R' : (p_state & TASK_UNINTERRUPTIBLE) ? 'D' : (p_state & TASK_STOPPED) ? 'T' : (p_state & TASK_TRACED) ? 'C' : |