diff options
Diffstat (limited to 'arch/powerpc')
234 files changed, 5134 insertions, 2697 deletions
diff --git a/arch/powerpc/Kbuild b/arch/powerpc/Kbuild index 51e6908323ad..5e2f9eaa3ee7 100644 --- a/arch/powerpc/Kbuild +++ b/arch/powerpc/Kbuild @@ -14,4 +14,5 @@ obj-$(CONFIG_XMON) += xmon/ obj-$(CONFIG_KVM) += kvm/ obj-$(CONFIG_PERF_EVENTS) += perf/ +obj-$(CONFIG_KEXEC_CORE) += kexec/ obj-$(CONFIG_KEXEC_FILE) += purgatory/ diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 3e56c9c2f16e..1ec34e16ed65 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -161,6 +161,7 @@ config PPC select GENERIC_CMOS_UPDATE select GENERIC_CPU_AUTOPROBE select GENERIC_CPU_VULNERABILITIES if PPC_BARRIER_NOSPEC + select GENERIC_EARLY_IOREMAP select GENERIC_IRQ_SHOW select GENERIC_IRQ_SHOW_LEVEL select GENERIC_PCI_IOMAP if PCI @@ -451,6 +452,23 @@ config PPC_TRANSACTIONAL_MEM help Support user-mode Transactional Memory on POWERPC. +config PPC_UV + bool "Ultravisor support" + depends on KVM_BOOK3S_HV_POSSIBLE + select ZONE_DEVICE + select DEV_PAGEMAP_OPS + select DEVICE_PRIVATE + select MEMORY_HOTPLUG + select MEMORY_HOTREMOVE + default n + help + This option paravirtualizes the kernel to run in POWER platforms that + supports the Protected Execution Facility (PEF). On such platforms, + the ultravisor firmware runs at a privilege level above the + hypervisor. + + If unsure, say "N". + config LD_HEAD_STUB_CATCH bool "Reserve 256 bytes to cope with linker stubs in HEAD text" if EXPERT depends on PPC64 @@ -551,6 +569,17 @@ config RELOCATABLE setting can still be useful to bootwrappers that need to know the load address of the kernel (eg. u-boot/mkimage). +config RANDOMIZE_BASE + bool "Randomize the address of the kernel image" + depends on (FSL_BOOKE && FLATMEM && PPC32) + depends on RELOCATABLE + help + Randomizes the virtual address at which the kernel image is + loaded, as a security feature that deters exploit attempts + relying on knowledge of the location of kernel internals. + + If unsure, say Y. + config RELOCATABLE_TEST bool "Test relocatable kernel" depends on (PPC64 && RELOCATABLE) @@ -874,15 +903,33 @@ config CMDLINE some command-line options at build time by entering them here. In most cases you will need to specify the root device here. +choice + prompt "Kernel command line type" if CMDLINE != "" + default CMDLINE_FROM_BOOTLOADER + +config CMDLINE_FROM_BOOTLOADER + bool "Use bootloader kernel arguments if available" + help + Uses the command-line options passed by the boot loader. If + the boot loader doesn't provide any, the default kernel command + string provided in CMDLINE will be used. + +config CMDLINE_EXTEND + bool "Extend bootloader kernel arguments" + help + The command-line arguments provided by the boot loader will be + appended to the default kernel command string. + config CMDLINE_FORCE bool "Always use the default kernel command string" - depends on CMDLINE_BOOL help Always use the default kernel command string, even if the boot loader passes other arguments to the kernel. This is useful if you cannot or don't want to change the command-line options your boot loader passes to the kernel. +endchoice + config EXTRA_TARGETS string "Additional default image types" help @@ -934,6 +981,28 @@ config PPC_MEM_KEYS If unsure, say y. +config PPC_SECURE_BOOT + prompt "Enable secure boot support" + bool + depends on PPC_POWERNV + depends on IMA_ARCH_POLICY + help + Systems with firmware secure boot enabled need to define security + policies to extend secure boot to the OS. This config allows a user + to enable OS secure boot on systems that have firmware support for + it. If in doubt say N. + +config PPC_SECVAR_SYSFS + bool "Enable sysfs interface for POWER secure variables" + default y + depends on PPC_SECURE_BOOT + depends on SYSFS + help + POWER secure variables are managed and controlled by firmware. + These variables are exposed to userspace via sysfs to enable + read/write operations on these variables. Say Y if you have + secure boot enabled and want to expose variables to userspace. + endmenu config ISA_DMA_API diff --git a/arch/powerpc/Kconfig.debug b/arch/powerpc/Kconfig.debug index c59920920ddc..4e1d39847462 100644 --- a/arch/powerpc/Kconfig.debug +++ b/arch/powerpc/Kconfig.debug @@ -122,8 +122,8 @@ config XMON_DEFAULT_RO_MODE depends on XMON default y help - Operate xmon in read-only mode. The cmdline options 'xmon=rw' and - 'xmon=ro' override this default. + Operate xmon in read-only mode. The cmdline options 'xmon=rw' and + 'xmon=ro' override this default. config DEBUGGER bool @@ -222,7 +222,7 @@ config PPC_EARLY_DEBUG_44x help Select this to enable early debugging for IBM 44x chips via the inbuilt serial port. If you enable this, ensure you set - PPC_EARLY_DEBUG_44x_PHYSLOW below to suit your target board. + PPC_EARLY_DEBUG_44x_PHYSLOW below to suit your target board. config PPC_EARLY_DEBUG_40x bool "Early serial debugging for IBM/AMCC 40x CPUs" @@ -325,7 +325,7 @@ config PPC_EARLY_DEBUG_44x_PHYSLOW default "0x40000200" help You probably want 0x40000200 for ebony boards and - 0x40000300 for taishan + 0x40000300 for taishan config PPC_EARLY_DEBUG_44x_PHYSHIGH hex "EPRN of early debug UART physical address" @@ -359,9 +359,9 @@ config FAIL_IOMMU If you are unsure, say N. config PPC_PTDUMP - bool "Export kernel pagetable layout to userspace via debugfs" - depends on DEBUG_KERNEL && DEBUG_FS - help + bool "Export kernel pagetable layout to userspace via debugfs" + depends on DEBUG_KERNEL && DEBUG_FS + help This option exports the state of the kernel pagetables to a debugfs file. This is only useful for kernel developers who are working in architecture specific areas of the kernel - probably @@ -390,8 +390,8 @@ config PPC_DEBUG_WX config PPC_FAST_ENDIAN_SWITCH bool "Deprecated fast endian-switch syscall" - depends on DEBUG_KERNEL && PPC_BOOK3S_64 - help + depends on DEBUG_KERNEL && PPC_BOOK3S_64 + help If you're unsure what this is, say N. config KASAN_SHADOW_OFFSET diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index 83522c9fc7b6..f35730548e42 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -91,11 +91,13 @@ MULTIPLEWORD := -mmultiple endif ifdef CONFIG_PPC64 +ifndef CONFIG_CC_IS_CLANG cflags-$(CONFIG_CPU_BIG_ENDIAN) += $(call cc-option,-mabi=elfv1) cflags-$(CONFIG_CPU_BIG_ENDIAN) += $(call cc-option,-mcall-aixdesc) aflags-$(CONFIG_CPU_BIG_ENDIAN) += $(call cc-option,-mabi=elfv1) aflags-$(CONFIG_CPU_LITTLE_ENDIAN) += -mabi=elfv2 endif +endif ifndef CONFIG_CC_IS_CLANG cflags-$(CONFIG_CPU_LITTLE_ENDIAN) += -mno-strict-align @@ -141,6 +143,7 @@ endif endif CFLAGS-$(CONFIG_PPC64) := $(call cc-option,-mtraceback=no) +ifndef CONFIG_CC_IS_CLANG ifdef CONFIG_CPU_LITTLE_ENDIAN CFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mabi=elfv2,$(call cc-option,-mcall-aixdesc)) AFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mabi=elfv2) @@ -149,6 +152,7 @@ CFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mabi=elfv1) CFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mcall-aixdesc) AFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mabi=elfv1) endif +endif CFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mcmodel=medium,$(call cc-option,-mminimal-toc)) CFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mno-pointers-to-nested-functions) @@ -330,32 +334,32 @@ powernv_be_defconfig: PHONY += mpc85xx_defconfig mpc85xx_defconfig: - $(call merge_into_defconfig,mpc85xx_basic_defconfig,\ + $(call merge_into_defconfig,mpc85xx_base.config,\ 85xx-32bit 85xx-hw fsl-emb-nonhw) PHONY += mpc85xx_smp_defconfig mpc85xx_smp_defconfig: - $(call merge_into_defconfig,mpc85xx_basic_defconfig,\ + $(call merge_into_defconfig,mpc85xx_base.config,\ 85xx-32bit 85xx-smp 85xx-hw fsl-emb-nonhw) PHONY += corenet32_smp_defconfig corenet32_smp_defconfig: - $(call merge_into_defconfig,corenet_basic_defconfig,\ + $(call merge_into_defconfig,corenet_base.config,\ 85xx-32bit 85xx-smp 85xx-hw fsl-emb-nonhw dpaa) PHONY += corenet64_smp_defconfig corenet64_smp_defconfig: - $(call merge_into_defconfig,corenet_basic_defconfig,\ + $(call merge_into_defconfig,corenet_base.config,\ 85xx-64bit 85xx-smp altivec 85xx-hw fsl-emb-nonhw dpaa) PHONY += mpc86xx_defconfig mpc86xx_defconfig: - $(call merge_into_defconfig,mpc86xx_basic_defconfig,\ + $(call merge_into_defconfig,mpc86xx_base.config,\ 86xx-hw fsl-emb-nonhw) PHONY += mpc86xx_smp_defconfig mpc86xx_smp_defconfig: - $(call merge_into_defconfig,mpc86xx_basic_defconfig,\ + $(call merge_into_defconfig,mpc86xx_base.config,\ 86xx-smp 86xx-hw fsl-emb-nonhw) PHONY += ppc32_allmodconfig diff --git a/arch/powerpc/boot/dts/fsl/kmcent2.dts b/arch/powerpc/boot/dts/fsl/kmcent2.dts index 48b7f9797124..8e7f0828af29 100644 --- a/arch/powerpc/boot/dts/fsl/kmcent2.dts +++ b/arch/powerpc/boot/dts/fsl/kmcent2.dts @@ -210,13 +210,19 @@ fman@400000 { ethernet@e0000 { - fixed-link = <0 1 1000 0 0>; - phy-connection-type = "sgmii"; + phy-mode = "sgmii"; + fixed-link { + speed = <1000>; + full-duplex; + }; }; ethernet@e2000 { - fixed-link = <1 1 1000 0 0>; - phy-connection-type = "sgmii"; + phy-mode = "sgmii"; + fixed-link { + speed = <1000>; + full-duplex; + }; }; ethernet@e4000 { @@ -229,7 +235,7 @@ ethernet@e8000 { phy-handle = <&front_phy>; - phy-connection-type = "rgmii"; + phy-mode = "rgmii-id"; }; mdio0: mdio@fc000 { @@ -258,14 +264,50 @@ pci1: pcie@ffe250000 { status = "disabled"; + reg = <0xf 0xfe250000 0 0x10000>; + ranges = <0x02000000 0 0xe0000000 0xc 0x10000000 0 0x10000000 + 0x01000000 0 0 0xf 0xf8010000 0 0x00010000>; + pcie@0 { + ranges = <0x02000000 0 0xe0000000 + 0x02000000 0 0xe0000000 + 0 0x10000000 + + 0x01000000 0 0x00000000 + 0x01000000 0 0x00000000 + 0 0x00010000>; + }; }; pci2: pcie@ffe260000 { status = "disabled"; + reg = <0xf 0xfe260000 0 0x10000>; + ranges = <0x02000000 0 0xe0000000 0xc 0x20000000 0 0x10000000 + 0x01000000 0 0x00000000 0xf 0xf8020000 0 0x00010000>; + pcie@0 { + ranges = <0x02000000 0 0xe0000000 + 0x02000000 0 0xe0000000 + 0 0x10000000 + + 0x01000000 0 0x00000000 + 0x01000000 0 0x00000000 + 0 0x00010000>; + }; }; pci3: pcie@ffe270000 { status = "disabled"; + reg = <0xf 0xfe270000 0 0x10000>; + ranges = <0x02000000 0 0xe0000000 0xc 0x30000000 0 0x10000000 + 0x01000000 0 0x00000000 0xf 0xf8030000 0 0x00010000>; + pcie@0 { + ranges = <0x02000000 0 0xe0000000 + 0x02000000 0 0xe0000000 + 0 0x10000000 + + 0x01000000 0 0x00000000 + 0x01000000 0 0x00000000 + 0 0x00010000>; + }; }; qe: qe@ffe140000 { diff --git a/arch/powerpc/boot/libfdt_env.h b/arch/powerpc/boot/libfdt_env.h index 2abc8e83b95e..9757d4f6331e 100644 --- a/arch/powerpc/boot/libfdt_env.h +++ b/arch/powerpc/boot/libfdt_env.h @@ -6,6 +6,8 @@ #include <string.h> #define INT_MAX ((int)(~0U>>1)) +#define UINT32_MAX ((u32)~0U) +#define INT32_MAX ((s32)(UINT32_MAX >> 1)) #include "of.h" diff --git a/arch/powerpc/configs/40x/acadia_defconfig b/arch/powerpc/configs/40x/acadia_defconfig index 5a75e4f14273..db93c117be36 100644 --- a/arch/powerpc/configs/40x/acadia_defconfig +++ b/arch/powerpc/configs/40x/acadia_defconfig @@ -18,9 +18,6 @@ CONFIG_INET=y CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y CONFIG_IP_PNP_BOOTP=y -# CONFIG_INET_XFRM_MODE_TRANSPORT is not set -# CONFIG_INET_XFRM_MODE_TUNNEL is not set -# CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_IPV6 is not set CONFIG_CONNECTOR=y CONFIG_MTD=y diff --git a/arch/powerpc/configs/40x/ep405_defconfig b/arch/powerpc/configs/40x/ep405_defconfig index e2691c5db766..a3854cf65f8d 100644 --- a/arch/powerpc/configs/40x/ep405_defconfig +++ b/arch/powerpc/configs/40x/ep405_defconfig @@ -17,9 +17,6 @@ CONFIG_INET=y CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y CONFIG_IP_PNP_BOOTP=y -# CONFIG_INET_XFRM_MODE_TRANSPORT is not set -# CONFIG_INET_XFRM_MODE_TUNNEL is not set -# CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_IPV6 is not set CONFIG_CONNECTOR=y CONFIG_MTD=y diff --git a/arch/powerpc/configs/40x/kilauea_defconfig b/arch/powerpc/configs/40x/kilauea_defconfig index 949989ef2322..edc22464dfb5 100644 --- a/arch/powerpc/configs/40x/kilauea_defconfig +++ b/arch/powerpc/configs/40x/kilauea_defconfig @@ -20,9 +20,6 @@ CONFIG_INET=y CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y CONFIG_IP_PNP_BOOTP=y -# CONFIG_INET_XFRM_MODE_TRANSPORT is not set -# CONFIG_INET_XFRM_MODE_TUNNEL is not set -# CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_IPV6 is not set CONFIG_CONNECTOR=y CONFIG_MTD=y diff --git a/arch/powerpc/configs/40x/klondike_defconfig b/arch/powerpc/configs/40x/klondike_defconfig index 4347a87088dc..579fa846839c 100644 --- a/arch/powerpc/configs/40x/klondike_defconfig +++ b/arch/powerpc/configs/40x/klondike_defconfig @@ -4,7 +4,6 @@ CONFIG_LOG_BUF_SHIFT=14 CONFIG_SYSFS_DEPRECATED=y CONFIG_SYSFS_DEPRECATED_V2=y CONFIG_BLK_DEV_INITRD=y -CONFIG_SYSCTL_SYSCALL=y CONFIG_EMBEDDED=y CONFIG_SLAB=y CONFIG_MODULES=y diff --git a/arch/powerpc/configs/40x/makalu_defconfig b/arch/powerpc/configs/40x/makalu_defconfig index 90b759bbf426..188789b9aa4c 100644 --- a/arch/powerpc/configs/40x/makalu_defconfig +++ b/arch/powerpc/configs/40x/makalu_defconfig @@ -17,9 +17,6 @@ CONFIG_INET=y CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y CONFIG_IP_PNP_BOOTP=y -# CONFIG_INET_XFRM_MODE_TRANSPORT is not set -# CONFIG_INET_XFRM_MODE_TUNNEL is not set -# CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_IPV6 is not set CONFIG_CONNECTOR=y CONFIG_MTD=y diff --git a/arch/powerpc/configs/40x/obs600_defconfig b/arch/powerpc/configs/40x/obs600_defconfig index 881c300c011d..5bf6af7ef093 100644 --- a/arch/powerpc/configs/40x/obs600_defconfig +++ b/arch/powerpc/configs/40x/obs600_defconfig @@ -20,9 +20,6 @@ CONFIG_INET=y CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y CONFIG_IP_PNP_BOOTP=y -# CONFIG_INET_XFRM_MODE_TRANSPORT is not set -# CONFIG_INET_XFRM_MODE_TUNNEL is not set -# CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_IPV6 is not set CONFIG_CONNECTOR=y CONFIG_MTD=y diff --git a/arch/powerpc/configs/40x/walnut_defconfig b/arch/powerpc/configs/40x/walnut_defconfig index 0ed46704b9fa..9eaaf1a1d2c6 100644 --- a/arch/powerpc/configs/40x/walnut_defconfig +++ b/arch/powerpc/configs/40x/walnut_defconfig @@ -15,9 +15,6 @@ CONFIG_INET=y CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y CONFIG_IP_PNP_BOOTP=y -# CONFIG_INET_XFRM_MODE_TRANSPORT is not set -# CONFIG_INET_XFRM_MODE_TUNNEL is not set -# CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_IPV6 is not set CONFIG_CONNECTOR=y CONFIG_MTD=y diff --git a/arch/powerpc/configs/44x/akebono_defconfig b/arch/powerpc/configs/44x/akebono_defconfig index 2fa553ebfdc9..f0c8a07cc274 100644 --- a/arch/powerpc/configs/44x/akebono_defconfig +++ b/arch/powerpc/configs/44x/akebono_defconfig @@ -29,9 +29,6 @@ CONFIG_INET=y CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y CONFIG_IP_PNP_BOOTP=y -# CONFIG_INET_XFRM_MODE_TRANSPORT is not set -# CONFIG_INET_XFRM_MODE_TUNNEL is not set -# CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_IPV6 is not set CONFIG_DEVTMPFS=y CONFIG_DEVTMPFS_MOUNT=y diff --git a/arch/powerpc/configs/44x/arches_defconfig b/arch/powerpc/configs/44x/arches_defconfig index 5a1b9ee18075..82c6f49b8dcb 100644 --- a/arch/powerpc/configs/44x/arches_defconfig +++ b/arch/powerpc/configs/44x/arches_defconfig @@ -20,9 +20,6 @@ CONFIG_INET=y CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y CONFIG_IP_PNP_BOOTP=y -# CONFIG_INET_XFRM_MODE_TRANSPORT is not set -# CONFIG_INET_XFRM_MODE_TUNNEL is not set -# CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_IPV6 is not set CONFIG_CONNECTOR=y CONFIG_MTD=y diff --git a/arch/powerpc/configs/44x/bamboo_defconfig b/arch/powerpc/configs/44x/bamboo_defconfig index 22e1ef5272ab..679213214a75 100644 --- a/arch/powerpc/configs/44x/bamboo_defconfig +++ b/arch/powerpc/configs/44x/bamboo_defconfig @@ -18,9 +18,6 @@ CONFIG_INET=y CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y CONFIG_IP_PNP_BOOTP=y -# CONFIG_INET_XFRM_MODE_TRANSPORT is not set -# CONFIG_INET_XFRM_MODE_TUNNEL is not set -# CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_IPV6 is not set CONFIG_CONNECTOR=y CONFIG_BLK_DEV_RAM=y diff --git a/arch/powerpc/configs/44x/canyonlands_defconfig b/arch/powerpc/configs/44x/canyonlands_defconfig index 86f34ea4173a..ccc14eb7a2f1 100644 --- a/arch/powerpc/configs/44x/canyonlands_defconfig +++ b/arch/powerpc/configs/44x/canyonlands_defconfig @@ -20,9 +20,6 @@ CONFIG_INET=y CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y CONFIG_IP_PNP_BOOTP=y -# CONFIG_INET_XFRM_MODE_TRANSPORT is not set -# CONFIG_INET_XFRM_MODE_TUNNEL is not set -# CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_IPV6 is not set CONFIG_CONNECTOR=y CONFIG_MTD=y diff --git a/arch/powerpc/configs/44x/currituck_defconfig b/arch/powerpc/configs/44x/currituck_defconfig index ce3ec5a2cd15..be76e066df01 100644 --- a/arch/powerpc/configs/44x/currituck_defconfig +++ b/arch/powerpc/configs/44x/currituck_defconfig @@ -27,9 +27,6 @@ CONFIG_INET=y CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y CONFIG_IP_PNP_BOOTP=y -# CONFIG_INET_XFRM_MODE_TRANSPORT is not set -# CONFIG_INET_XFRM_MODE_TUNNEL is not set -# CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_IPV6 is not set CONFIG_DEVTMPFS=y CONFIG_DEVTMPFS_MOUNT=y diff --git a/arch/powerpc/configs/44x/ebony_defconfig b/arch/powerpc/configs/44x/ebony_defconfig index f67447c92e6f..93d2a4e64af9 100644 --- a/arch/powerpc/configs/44x/ebony_defconfig +++ b/arch/powerpc/configs/44x/ebony_defconfig @@ -16,9 +16,6 @@ CONFIG_INET=y CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y CONFIG_IP_PNP_BOOTP=y -# CONFIG_INET_XFRM_MODE_TRANSPORT is not set -# CONFIG_INET_XFRM_MODE_TUNNEL is not set -# CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_IPV6 is not set CONFIG_CONNECTOR=y CONFIG_MTD=y diff --git a/arch/powerpc/configs/44x/eiger_defconfig b/arch/powerpc/configs/44x/eiger_defconfig index 5dbd83a1c11b..1abaa63e067f 100644 --- a/arch/powerpc/configs/44x/eiger_defconfig +++ b/arch/powerpc/configs/44x/eiger_defconfig @@ -21,9 +21,6 @@ CONFIG_INET=y CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y CONFIG_IP_PNP_BOOTP=y -# CONFIG_INET_XFRM_MODE_TRANSPORT is not set -# CONFIG_INET_XFRM_MODE_TUNNEL is not set -# CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_IPV6 is not set CONFIG_CONNECTOR=y CONFIG_MTD=y diff --git a/arch/powerpc/configs/44x/fsp2_defconfig b/arch/powerpc/configs/44x/fsp2_defconfig index e49114f0e526..e67fc041ca3e 100644 --- a/arch/powerpc/configs/44x/fsp2_defconfig +++ b/arch/powerpc/configs/44x/fsp2_defconfig @@ -39,9 +39,6 @@ CONFIG_INET=y CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y CONFIG_IP_PNP_BOOTP=y -# CONFIG_INET_XFRM_MODE_TRANSPORT is not set -# CONFIG_INET_XFRM_MODE_TUNNEL is not set -# CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_IPV6 is not set CONFIG_VLAN_8021Q=m CONFIG_DEVTMPFS=y diff --git a/arch/powerpc/configs/44x/icon_defconfig b/arch/powerpc/configs/44x/icon_defconfig index fa5378af44f9..7d7ff84c8200 100644 --- a/arch/powerpc/configs/44x/icon_defconfig +++ b/arch/powerpc/configs/44x/icon_defconfig @@ -20,9 +20,6 @@ CONFIG_INET=y CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y CONFIG_IP_PNP_BOOTP=y -# CONFIG_INET_XFRM_MODE_TRANSPORT is not set -# CONFIG_INET_XFRM_MODE_TUNNEL is not set -# CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_IPV6 is not set CONFIG_CONNECTOR=y CONFIG_MTD=y diff --git a/arch/powerpc/configs/44x/iss476-smp_defconfig b/arch/powerpc/configs/44x/iss476-smp_defconfig index aae879c21239..fb5c73a29bf4 100644 --- a/arch/powerpc/configs/44x/iss476-smp_defconfig +++ b/arch/powerpc/configs/44x/iss476-smp_defconfig @@ -29,9 +29,6 @@ CONFIG_INET=y CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y CONFIG_IP_PNP_BOOTP=y -# CONFIG_INET_XFRM_MODE_TRANSPORT is not set -# CONFIG_INET_XFRM_MODE_TUNNEL is not set -# CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_IPV6 is not set CONFIG_CONNECTOR=y CONFIG_MTD=y diff --git a/arch/powerpc/configs/44x/katmai_defconfig b/arch/powerpc/configs/44x/katmai_defconfig index 56eddca998c6..c6dc1445fc04 100644 --- a/arch/powerpc/configs/44x/katmai_defconfig +++ b/arch/powerpc/configs/44x/katmai_defconfig @@ -18,9 +18,6 @@ CONFIG_INET=y CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y CONFIG_IP_PNP_BOOTP=y -# CONFIG_INET_XFRM_MODE_TRANSPORT is not set -# CONFIG_INET_XFRM_MODE_TUNNEL is not set -# CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_IPV6 is not set CONFIG_CONNECTOR=y CONFIG_MTD=y diff --git a/arch/powerpc/configs/44x/rainier_defconfig b/arch/powerpc/configs/44x/rainier_defconfig index 369bfd2e451d..c83ad03182df 100644 --- a/arch/powerpc/configs/44x/rainier_defconfig +++ b/arch/powerpc/configs/44x/rainier_defconfig @@ -19,9 +19,6 @@ CONFIG_INET=y CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y CONFIG_IP_PNP_BOOTP=y -# CONFIG_INET_XFRM_MODE_TRANSPORT is not set -# CONFIG_INET_XFRM_MODE_TUNNEL is not set -# CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_IPV6 is not set CONFIG_CONNECTOR=y CONFIG_MTD=y diff --git a/arch/powerpc/configs/44x/redwood_defconfig b/arch/powerpc/configs/44x/redwood_defconfig index 8be95f6fe3a7..640fe1d5af28 100644 --- a/arch/powerpc/configs/44x/redwood_defconfig +++ b/arch/powerpc/configs/44x/redwood_defconfig @@ -21,9 +21,6 @@ CONFIG_INET=y CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y CONFIG_IP_PNP_BOOTP=y -# CONFIG_INET_XFRM_MODE_TRANSPORT is not set -# CONFIG_INET_XFRM_MODE_TUNNEL is not set -# CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_IPV6 is not set CONFIG_CONNECTOR=y CONFIG_MTD=y diff --git a/arch/powerpc/configs/44x/sam440ep_defconfig b/arch/powerpc/configs/44x/sam440ep_defconfig index 974a4f038cda..ed02f12dbd54 100644 --- a/arch/powerpc/configs/44x/sam440ep_defconfig +++ b/arch/powerpc/configs/44x/sam440ep_defconfig @@ -23,9 +23,6 @@ CONFIG_INET=y CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y CONFIG_IP_PNP_BOOTP=y -# CONFIG_INET_XFRM_MODE_TRANSPORT is not set -# CONFIG_INET_XFRM_MODE_TUNNEL is not set -# CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_IPV6 is not set CONFIG_CONNECTOR=y CONFIG_BLK_DEV_LOOP=y diff --git a/arch/powerpc/configs/44x/sequoia_defconfig b/arch/powerpc/configs/44x/sequoia_defconfig index 10e517b69fa4..2c0973db8837 100644 --- a/arch/powerpc/configs/44x/sequoia_defconfig +++ b/arch/powerpc/configs/44x/sequoia_defconfig @@ -20,9 +20,6 @@ CONFIG_INET=y CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y CONFIG_IP_PNP_BOOTP=y -# CONFIG_INET_XFRM_MODE_TRANSPORT is not set -# CONFIG_INET_XFRM_MODE_TUNNEL is not set -# CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_IPV6 is not set CONFIG_CONNECTOR=y CONFIG_MTD=y diff --git a/arch/powerpc/configs/44x/taishan_defconfig b/arch/powerpc/configs/44x/taishan_defconfig index cd08f3ddd609..a2d355ca62b2 100644 --- a/arch/powerpc/configs/44x/taishan_defconfig +++ b/arch/powerpc/configs/44x/taishan_defconfig @@ -18,9 +18,6 @@ CONFIG_INET=y CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y CONFIG_IP_PNP_BOOTP=y -# CONFIG_INET_XFRM_MODE_TRANSPORT is not set -# CONFIG_INET_XFRM_MODE_TUNNEL is not set -# CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_IPV6 is not set CONFIG_CONNECTOR=y CONFIG_MTD=y diff --git a/arch/powerpc/configs/52xx/pcm030_defconfig b/arch/powerpc/configs/52xx/pcm030_defconfig index 303600ff1fdb..fdb11daeb688 100644 --- a/arch/powerpc/configs/52xx/pcm030_defconfig +++ b/arch/powerpc/configs/52xx/pcm030_defconfig @@ -31,9 +31,6 @@ CONFIG_IP_MULTICAST=y CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y CONFIG_IP_PNP_BOOTP=y -# CONFIG_INET_XFRM_MODE_TRANSPORT is not set -# CONFIG_INET_XFRM_MODE_TUNNEL is not set -# CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_INET_DIAG is not set # CONFIG_IPV6 is not set # CONFIG_FW_LOADER is not set diff --git a/arch/powerpc/configs/83xx/kmeter1_defconfig b/arch/powerpc/configs/83xx/kmeter1_defconfig index d21b5cb365f2..648c6b3dccf9 100644 --- a/arch/powerpc/configs/83xx/kmeter1_defconfig +++ b/arch/powerpc/configs/83xx/kmeter1_defconfig @@ -25,9 +25,6 @@ CONFIG_UNIX=y CONFIG_INET=y CONFIG_IP_MULTICAST=y CONFIG_IP_PNP=y -# CONFIG_INET_XFRM_MODE_TRANSPORT is not set -# CONFIG_INET_XFRM_MODE_TUNNEL is not set -# CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_IPV6 is not set CONFIG_TIPC=y CONFIG_BRIDGE=m diff --git a/arch/powerpc/configs/83xx/mpc837x_rdb_defconfig b/arch/powerpc/configs/83xx/mpc837x_rdb_defconfig index dad53ef86b49..cbcae2a927e9 100644 --- a/arch/powerpc/configs/83xx/mpc837x_rdb_defconfig +++ b/arch/powerpc/configs/83xx/mpc837x_rdb_defconfig @@ -22,9 +22,6 @@ CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y CONFIG_IP_PNP_BOOTP=y CONFIG_SYN_COOKIES=y -# CONFIG_INET_XFRM_MODE_TRANSPORT is not set -# CONFIG_INET_XFRM_MODE_TUNNEL is not set -# CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_IPV6 is not set # CONFIG_FW_LOADER is not set CONFIG_BLK_DEV_LOOP=y diff --git a/arch/powerpc/configs/85xx/ge_imp3a_defconfig b/arch/powerpc/configs/85xx/ge_imp3a_defconfig index 920f37316fdb..f29c166998af 100644 --- a/arch/powerpc/configs/85xx/ge_imp3a_defconfig +++ b/arch/powerpc/configs/85xx/ge_imp3a_defconfig @@ -60,7 +60,6 @@ CONFIG_SYN_COOKIES=y CONFIG_INET_AH=m CONFIG_INET_ESP=m CONFIG_INET_IPCOMP=m -# CONFIG_INET_XFRM_MODE_BEET is not set CONFIG_INET6_AH=m CONFIG_INET6_IPCOMP=m CONFIG_IPV6_TUNNEL=m diff --git a/arch/powerpc/configs/adder875_defconfig b/arch/powerpc/configs/adder875_defconfig index f7a803ab2285..510f7fd1f6a3 100644 --- a/arch/powerpc/configs/adder875_defconfig +++ b/arch/powerpc/configs/adder875_defconfig @@ -22,9 +22,6 @@ CONFIG_INET=y CONFIG_IP_MULTICAST=y CONFIG_IP_PNP=y CONFIG_SYN_COOKIES=y -# CONFIG_INET_XFRM_MODE_TRANSPORT is not set -# CONFIG_INET_XFRM_MODE_TUNNEL is not set -# CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_IPV6 is not set # CONFIG_FW_LOADER is not set CONFIG_MTD=y diff --git a/arch/powerpc/configs/amigaone_defconfig b/arch/powerpc/configs/amigaone_defconfig index cf94d28d0e31..f6d140f2d922 100644 --- a/arch/powerpc/configs/amigaone_defconfig +++ b/arch/powerpc/configs/amigaone_defconfig @@ -26,9 +26,6 @@ CONFIG_UNIX=y CONFIG_INET=y CONFIG_IP_MULTICAST=y CONFIG_SYN_COOKIES=y -# CONFIG_INET_XFRM_MODE_TRANSPORT is not set -# CONFIG_INET_XFRM_MODE_TUNNEL is not set -# CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_IPV6 is not set CONFIG_NETFILTER=y # CONFIG_NETFILTER_ADVANCED is not set diff --git a/arch/powerpc/configs/cell_defconfig b/arch/powerpc/configs/cell_defconfig index 2dd1b58a18ae..42fbc70cec33 100644 --- a/arch/powerpc/configs/cell_defconfig +++ b/arch/powerpc/configs/cell_defconfig @@ -51,11 +51,9 @@ CONFIG_IP_PNP_BOOTP=y CONFIG_IP_PNP_RARP=y CONFIG_NET_IPIP=y CONFIG_SYN_COOKIES=y -# CONFIG_INET_XFRM_MODE_BEET is not set CONFIG_INET6_AH=m CONFIG_INET6_ESP=m CONFIG_INET6_IPCOMP=m -# CONFIG_INET6_XFRM_MODE_BEET is not set # CONFIG_IPV6_SIT is not set CONFIG_IPV6_TUNNEL=m CONFIG_NETFILTER=y diff --git a/arch/powerpc/configs/chrp32_defconfig b/arch/powerpc/configs/chrp32_defconfig index 9ff493dd8439..502a75d49789 100644 --- a/arch/powerpc/configs/chrp32_defconfig +++ b/arch/powerpc/configs/chrp32_defconfig @@ -27,9 +27,6 @@ CONFIG_UNIX=y CONFIG_INET=y CONFIG_IP_MULTICAST=y CONFIG_SYN_COOKIES=y -# CONFIG_INET_XFRM_MODE_TRANSPORT is not set -# CONFIG_INET_XFRM_MODE_TUNNEL is not set -# CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_IPV6 is not set CONFIG_NETFILTER=y # CONFIG_NETFILTER_ADVANCED is not set diff --git a/arch/powerpc/configs/corenet_basic_defconfig b/arch/powerpc/configs/corenet_base.config index b568d465e59e..b568d465e59e 100644 --- a/arch/powerpc/configs/corenet_basic_defconfig +++ b/arch/powerpc/configs/corenet_base.config diff --git a/arch/powerpc/configs/debug.config b/arch/powerpc/configs/debug.config new file mode 100644 index 000000000000..a14ae1f20d60 --- /dev/null +++ b/arch/powerpc/configs/debug.config @@ -0,0 +1 @@ +CONFIG_SCOM_DEBUGFS=y diff --git a/arch/powerpc/configs/ep88xc_defconfig b/arch/powerpc/configs/ep88xc_defconfig index b20bd0cf3543..9c1bf60f1e19 100644 --- a/arch/powerpc/configs/ep88xc_defconfig +++ b/arch/powerpc/configs/ep88xc_defconfig @@ -24,9 +24,6 @@ CONFIG_INET=y CONFIG_IP_MULTICAST=y CONFIG_IP_PNP=y CONFIG_SYN_COOKIES=y -# CONFIG_INET_XFRM_MODE_TRANSPORT is not set -# CONFIG_INET_XFRM_MODE_TUNNEL is not set -# CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_IPV6 is not set # CONFIG_FW_LOADER is not set CONFIG_MTD=y diff --git a/arch/powerpc/configs/gamecube_defconfig b/arch/powerpc/configs/gamecube_defconfig index 85e73c3bd859..24c0e0ea5aeb 100644 --- a/arch/powerpc/configs/gamecube_defconfig +++ b/arch/powerpc/configs/gamecube_defconfig @@ -29,9 +29,6 @@ CONFIG_INET=y CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y CONFIG_IP_PNP_RARP=y -# CONFIG_INET_XFRM_MODE_TRANSPORT is not set -# CONFIG_INET_XFRM_MODE_TUNNEL is not set -# CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_INET_DIAG is not set # CONFIG_IPV6 is not set # CONFIG_WIRELESS is not set diff --git a/arch/powerpc/configs/mpc512x_defconfig b/arch/powerpc/configs/mpc512x_defconfig index 6203c1093a3a..1f3a045ab081 100644 --- a/arch/powerpc/configs/mpc512x_defconfig +++ b/arch/powerpc/configs/mpc512x_defconfig @@ -25,9 +25,6 @@ CONFIG_PACKET=y CONFIG_UNIX=y CONFIG_INET=y CONFIG_IP_PNP=y -# CONFIG_INET_XFRM_MODE_TRANSPORT is not set -# CONFIG_INET_XFRM_MODE_TUNNEL is not set -# CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_INET_DIAG is not set # CONFIG_IPV6 is not set CONFIG_CAN=y diff --git a/arch/powerpc/configs/mpc5200_defconfig b/arch/powerpc/configs/mpc5200_defconfig index 6f87a5c74960..83d801307178 100644 --- a/arch/powerpc/configs/mpc5200_defconfig +++ b/arch/powerpc/configs/mpc5200_defconfig @@ -15,7 +15,6 @@ CONFIG_PPC_MEDIA5200=y CONFIG_PPC_MPC5200_BUGFIX=y CONFIG_PPC_MPC5200_LPBFIFO=m # CONFIG_PPC_PMAC is not set -CONFIG_SIMPLE_GPIO=y CONFIG_NET=y CONFIG_PACKET=y CONFIG_UNIX=y diff --git a/arch/powerpc/configs/mpc85xx_basic_defconfig b/arch/powerpc/configs/mpc85xx_base.config index b1593fe6f70b..b1593fe6f70b 100644 --- a/arch/powerpc/configs/mpc85xx_basic_defconfig +++ b/arch/powerpc/configs/mpc85xx_base.config diff --git a/arch/powerpc/configs/mpc86xx_basic_defconfig b/arch/powerpc/configs/mpc86xx_base.config index 67bd1fa036ee..67bd1fa036ee 100644 --- a/arch/powerpc/configs/mpc86xx_basic_defconfig +++ b/arch/powerpc/configs/mpc86xx_base.config diff --git a/arch/powerpc/configs/mpc885_ads_defconfig b/arch/powerpc/configs/mpc885_ads_defconfig index 285d506c5a76..0327a329316f 100644 --- a/arch/powerpc/configs/mpc885_ads_defconfig +++ b/arch/powerpc/configs/mpc885_ads_defconfig @@ -23,9 +23,6 @@ CONFIG_INET=y CONFIG_IP_MULTICAST=y CONFIG_IP_PNP=y CONFIG_SYN_COOKIES=y -# CONFIG_INET_XFRM_MODE_TRANSPORT is not set -# CONFIG_INET_XFRM_MODE_TUNNEL is not set -# CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_IPV6 is not set # CONFIG_FW_LOADER is not set CONFIG_MTD=y diff --git a/arch/powerpc/configs/pmac32_defconfig b/arch/powerpc/configs/pmac32_defconfig index 4e6e95f92646..f492e7d35925 100644 --- a/arch/powerpc/configs/pmac32_defconfig +++ b/arch/powerpc/configs/pmac32_defconfig @@ -38,8 +38,6 @@ CONFIG_IP_MULTICAST=y CONFIG_SYN_COOKIES=y CONFIG_INET_AH=y CONFIG_INET_ESP=y -# CONFIG_INET_XFRM_MODE_TRANSPORT is not set -# CONFIG_INET_XFRM_MODE_TUNNEL is not set # CONFIG_IPV6 is not set CONFIG_NETFILTER=y CONFIG_NF_CONNTRACK=m diff --git a/arch/powerpc/configs/powernv_defconfig b/arch/powerpc/configs/powernv_defconfig index 6658cceb928c..32841456a573 100644 --- a/arch/powerpc/configs/powernv_defconfig +++ b/arch/powerpc/configs/powernv_defconfig @@ -83,9 +83,6 @@ CONFIG_INET_IPCOMP=m CONFIG_INET6_AH=m CONFIG_INET6_ESP=m CONFIG_INET6_IPCOMP=m -CONFIG_INET6_XFRM_MODE_TRANSPORT=m -CONFIG_INET6_XFRM_MODE_TUNNEL=m -CONFIG_INET6_XFRM_MODE_BEET=m CONFIG_IPV6_SIT=m CONFIG_NETFILTER=y # CONFIG_NETFILTER_ADVANCED is not set diff --git a/arch/powerpc/configs/ppc44x_defconfig b/arch/powerpc/configs/ppc44x_defconfig index 67952819593e..a41eedfe0a5f 100644 --- a/arch/powerpc/configs/ppc44x_defconfig +++ b/arch/powerpc/configs/ppc44x_defconfig @@ -32,9 +32,6 @@ CONFIG_INET=y CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y CONFIG_IP_PNP_BOOTP=y -# CONFIG_INET_XFRM_MODE_TRANSPORT is not set -# CONFIG_INET_XFRM_MODE_TUNNEL is not set -# CONFIG_INET_XFRM_MODE_BEET is not set CONFIG_BRIDGE=m CONFIG_CONNECTOR=y CONFIG_MTD=y diff --git a/arch/powerpc/configs/ppc6xx_defconfig b/arch/powerpc/configs/ppc6xx_defconfig index 9dca4cffa623..7e28919041cf 100644 --- a/arch/powerpc/configs/ppc6xx_defconfig +++ b/arch/powerpc/configs/ppc6xx_defconfig @@ -109,9 +109,6 @@ CONFIG_SYN_COOKIES=y CONFIG_INET_AH=m CONFIG_INET_ESP=m CONFIG_INET_IPCOMP=m -CONFIG_INET_XFRM_MODE_TRANSPORT=m -CONFIG_INET_XFRM_MODE_TUNNEL=m -CONFIG_INET_XFRM_MODE_BEET=m CONFIG_INET_DIAG=m CONFIG_TCP_CONG_ADVANCED=y CONFIG_TCP_CONG_HSTCP=m @@ -129,7 +126,6 @@ CONFIG_INET6_AH=m CONFIG_INET6_ESP=m CONFIG_INET6_IPCOMP=m CONFIG_IPV6_MIP6=m -CONFIG_INET6_XFRM_MODE_ROUTEOPTIMIZATION=m CONFIG_IPV6_TUNNEL=m CONFIG_IPV6_MULTIPLE_TABLES=y CONFIG_IPV6_SUBTREES=y diff --git a/arch/powerpc/configs/ps3_defconfig b/arch/powerpc/configs/ps3_defconfig index 314c63939816..4db51719342a 100644 --- a/arch/powerpc/configs/ps3_defconfig +++ b/arch/powerpc/configs/ps3_defconfig @@ -47,9 +47,6 @@ CONFIG_INET=y CONFIG_IP_MULTICAST=y CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y -# CONFIG_INET_XFRM_MODE_TRANSPORT is not set -# CONFIG_INET_XFRM_MODE_TUNNEL is not set -# CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_INET_DIAG is not set CONFIG_BT=m CONFIG_BT_RFCOMM=m diff --git a/arch/powerpc/configs/skiroot_defconfig b/arch/powerpc/configs/skiroot_defconfig index 1253482a67c0..069f67f12731 100644 --- a/arch/powerpc/configs/skiroot_defconfig +++ b/arch/powerpc/configs/skiroot_defconfig @@ -46,6 +46,7 @@ CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y CONFIG_CPU_IDLE=y CONFIG_HZ_100=y CONFIG_KEXEC=y +CONFIG_PRESERVE_FA_DUMP=y CONFIG_IRQ_ALL_CPUS=y CONFIG_NUMA=y # CONFIG_COMPACTION is not set @@ -63,9 +64,6 @@ CONFIG_INET=y CONFIG_IP_MULTICAST=y CONFIG_NET_IPIP=y CONFIG_SYN_COOKIES=y -# CONFIG_INET_XFRM_MODE_TRANSPORT is not set -# CONFIG_INET_XFRM_MODE_TUNNEL is not set -# CONFIG_INET_XFRM_MODE_BEET is not set CONFIG_DNS_RESOLVER=y # CONFIG_WIRELESS is not set CONFIG_DEVTMPFS=y diff --git a/arch/powerpc/configs/storcenter_defconfig b/arch/powerpc/configs/storcenter_defconfig index 6c39c52b8e4a..29b19ec7e5d7 100644 --- a/arch/powerpc/configs/storcenter_defconfig +++ b/arch/powerpc/configs/storcenter_defconfig @@ -22,9 +22,6 @@ CONFIG_INET=y CONFIG_IP_MULTICAST=y CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y -# CONFIG_INET_XFRM_MODE_TRANSPORT is not set -# CONFIG_INET_XFRM_MODE_TUNNEL is not set -# CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_IPV6 is not set CONFIG_MTD=y CONFIG_MTD_CMDLINE_PARTS=y diff --git a/arch/powerpc/configs/tqm8xx_defconfig b/arch/powerpc/configs/tqm8xx_defconfig index 7493f36dd6e9..ffed2b4256d6 100644 --- a/arch/powerpc/configs/tqm8xx_defconfig +++ b/arch/powerpc/configs/tqm8xx_defconfig @@ -27,9 +27,6 @@ CONFIG_UNIX=y CONFIG_INET=y CONFIG_IP_PNP=y CONFIG_SYN_COOKIES=y -# CONFIG_INET_XFRM_MODE_TRANSPORT is not set -# CONFIG_INET_XFRM_MODE_TUNNEL is not set -# CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_IPV6 is not set # CONFIG_WIRELESS is not set # CONFIG_FW_LOADER is not set diff --git a/arch/powerpc/configs/wii_defconfig b/arch/powerpc/configs/wii_defconfig index 5a04448ad6b5..379c171f3ddd 100644 --- a/arch/powerpc/configs/wii_defconfig +++ b/arch/powerpc/configs/wii_defconfig @@ -29,9 +29,6 @@ CONFIG_INET=y CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y CONFIG_IP_PNP_RARP=y -# CONFIG_INET_XFRM_MODE_TRANSPORT is not set -# CONFIG_INET_XFRM_MODE_TUNNEL is not set -# CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_INET_DIAG is not set # CONFIG_IPV6 is not set CONFIG_BT=y diff --git a/arch/powerpc/crypto/aes-spe-glue.c b/arch/powerpc/crypto/aes-spe-glue.c index 3a4ca7d32477..1fad5d4c658d 100644 --- a/arch/powerpc/crypto/aes-spe-glue.c +++ b/arch/powerpc/crypto/aes-spe-glue.c @@ -17,7 +17,10 @@ #include <asm/byteorder.h> #include <asm/switch_to.h> #include <crypto/algapi.h> +#include <crypto/internal/skcipher.h> #include <crypto/xts.h> +#include <crypto/gf128mul.h> +#include <crypto/scatterwalk.h> /* * MAX_BYTES defines the number of bytes that are allowed to be processed @@ -118,13 +121,19 @@ static int ppc_aes_setkey(struct crypto_tfm *tfm, const u8 *in_key, return 0; } -static int ppc_xts_setkey(struct crypto_tfm *tfm, const u8 *in_key, +static int ppc_aes_setkey_skcipher(struct crypto_skcipher *tfm, + const u8 *in_key, unsigned int key_len) +{ + return ppc_aes_setkey(crypto_skcipher_tfm(tfm), in_key, key_len); +} + +static int ppc_xts_setkey(struct crypto_skcipher *tfm, const u8 *in_key, unsigned int key_len) { - struct ppc_xts_ctx *ctx = crypto_tfm_ctx(tfm); + struct ppc_xts_ctx *ctx = crypto_skcipher_ctx(tfm); int err; - err = xts_check_key(tfm, in_key, key_len); + err = xts_verify_key(tfm, in_key, key_len); if (err) return err; @@ -133,7 +142,7 @@ static int ppc_xts_setkey(struct crypto_tfm *tfm, const u8 *in_key, if (key_len != AES_KEYSIZE_128 && key_len != AES_KEYSIZE_192 && key_len != AES_KEYSIZE_256) { - tfm->crt_flags |= CRYPTO_TFM_RES_BAD_KEY_LEN; + crypto_skcipher_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN); return -EINVAL; } @@ -178,208 +187,229 @@ static void ppc_aes_decrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in) spe_end(); } -static int ppc_ecb_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst, - struct scatterlist *src, unsigned int nbytes) +static int ppc_ecb_crypt(struct skcipher_request *req, bool enc) { - struct ppc_aes_ctx *ctx = crypto_blkcipher_ctx(desc->tfm); - struct blkcipher_walk walk; - unsigned int ubytes; + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + struct ppc_aes_ctx *ctx = crypto_skcipher_ctx(tfm); + struct skcipher_walk walk; + unsigned int nbytes; int err; - desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP; - blkcipher_walk_init(&walk, dst, src, nbytes); - err = blkcipher_walk_virt(desc, &walk); + err = skcipher_walk_virt(&walk, req, false); - while ((nbytes = walk.nbytes)) { - ubytes = nbytes > MAX_BYTES ? - nbytes - MAX_BYTES : nbytes & (AES_BLOCK_SIZE - 1); - nbytes -= ubytes; + while ((nbytes = walk.nbytes) != 0) { + nbytes = min_t(unsigned int, nbytes, MAX_BYTES); + nbytes = round_down(nbytes, AES_BLOCK_SIZE); spe_begin(); - ppc_encrypt_ecb(walk.dst.virt.addr, walk.src.virt.addr, - ctx->key_enc, ctx->rounds, nbytes); + if (enc) + ppc_encrypt_ecb(walk.dst.virt.addr, walk.src.virt.addr, + ctx->key_enc, ctx->rounds, nbytes); + else + ppc_decrypt_ecb(walk.dst.virt.addr, walk.src.virt.addr, + ctx->key_dec, ctx->rounds, nbytes); spe_end(); - err = blkcipher_walk_done(desc, &walk, ubytes); + err = skcipher_walk_done(&walk, walk.nbytes - nbytes); } return err; } -static int ppc_ecb_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst, - struct scatterlist *src, unsigned int nbytes) +static int ppc_ecb_encrypt(struct skcipher_request *req) { - struct ppc_aes_ctx *ctx = crypto_blkcipher_ctx(desc->tfm); - struct blkcipher_walk walk; - unsigned int ubytes; - int err; - - desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP; - blkcipher_walk_init(&walk, dst, src, nbytes); - err = blkcipher_walk_virt(desc, &walk); - - while ((nbytes = walk.nbytes)) { - ubytes = nbytes > MAX_BYTES ? - nbytes - MAX_BYTES : nbytes & (AES_BLOCK_SIZE - 1); - nbytes -= ubytes; - - spe_begin(); - ppc_decrypt_ecb(walk.dst.virt.addr, walk.src.virt.addr, - ctx->key_dec, ctx->rounds, nbytes); - spe_end(); - - err = blkcipher_walk_done(desc, &walk, ubytes); - } + return ppc_ecb_crypt(req, true); +} - return err; +static int ppc_ecb_decrypt(struct skcipher_request *req) +{ + return ppc_ecb_crypt(req, false); } -static int ppc_cbc_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst, - struct scatterlist *src, unsigned int nbytes) +static int ppc_cbc_crypt(struct skcipher_request *req, bool enc) { - struct ppc_aes_ctx *ctx = crypto_blkcipher_ctx(desc->tfm); - struct blkcipher_walk walk; - unsigned int ubytes; + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + struct ppc_aes_ctx *ctx = crypto_skcipher_ctx(tfm); + struct skcipher_walk walk; + unsigned int nbytes; int err; - desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP; - blkcipher_walk_init(&walk, dst, src, nbytes); - err = blkcipher_walk_virt(desc, &walk); + err = skcipher_walk_virt(&walk, req, false); - while ((nbytes = walk.nbytes)) { - ubytes = nbytes > MAX_BYTES ? - nbytes - MAX_BYTES : nbytes & (AES_BLOCK_SIZE - 1); - nbytes -= ubytes; + while ((nbytes = walk.nbytes) != 0) { + nbytes = min_t(unsigned int, nbytes, MAX_BYTES); + nbytes = round_down(nbytes, AES_BLOCK_SIZE); spe_begin(); - ppc_encrypt_cbc(walk.dst.virt.addr, walk.src.virt.addr, - ctx->key_enc, ctx->rounds, nbytes, walk.iv); + if (enc) + ppc_encrypt_cbc(walk.dst.virt.addr, walk.src.virt.addr, + ctx->key_enc, ctx->rounds, nbytes, + walk.iv); + else + ppc_decrypt_cbc(walk.dst.virt.addr, walk.src.virt.addr, + ctx->key_dec, ctx->rounds, nbytes, + walk.iv); spe_end(); - err = blkcipher_walk_done(desc, &walk, ubytes); + err = skcipher_walk_done(&walk, walk.nbytes - nbytes); } return err; } -static int ppc_cbc_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst, - struct scatterlist *src, unsigned int nbytes) +static int ppc_cbc_encrypt(struct skcipher_request *req) { - struct ppc_aes_ctx *ctx = crypto_blkcipher_ctx(desc->tfm); - struct blkcipher_walk walk; - unsigned int ubytes; - int err; - - desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP; - blkcipher_walk_init(&walk, dst, src, nbytes); - err = blkcipher_walk_virt(desc, &walk); - - while ((nbytes = walk.nbytes)) { - ubytes = nbytes > MAX_BYTES ? - nbytes - MAX_BYTES : nbytes & (AES_BLOCK_SIZE - 1); - nbytes -= ubytes; - - spe_begin(); - ppc_decrypt_cbc(walk.dst.virt.addr, walk.src.virt.addr, - ctx->key_dec, ctx->rounds, nbytes, walk.iv); - spe_end(); - - err = blkcipher_walk_done(desc, &walk, ubytes); - } + return ppc_cbc_crypt(req, true); +} - return err; +static int ppc_cbc_decrypt(struct skcipher_request *req) +{ + return ppc_cbc_crypt(req, false); } -static int ppc_ctr_crypt(struct blkcipher_desc *desc, struct scatterlist *dst, - struct scatterlist *src, unsigned int nbytes) +static int ppc_ctr_crypt(struct skcipher_request *req) { - struct ppc_aes_ctx *ctx = crypto_blkcipher_ctx(desc->tfm); - struct blkcipher_walk walk; - unsigned int pbytes, ubytes; + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + struct ppc_aes_ctx *ctx = crypto_skcipher_ctx(tfm); + struct skcipher_walk walk; + unsigned int nbytes; int err; - desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP; - blkcipher_walk_init(&walk, dst, src, nbytes); - err = blkcipher_walk_virt_block(desc, &walk, AES_BLOCK_SIZE); + err = skcipher_walk_virt(&walk, req, false); - while ((pbytes = walk.nbytes)) { - pbytes = pbytes > MAX_BYTES ? MAX_BYTES : pbytes; - pbytes = pbytes == nbytes ? - nbytes : pbytes & ~(AES_BLOCK_SIZE - 1); - ubytes = walk.nbytes - pbytes; + while ((nbytes = walk.nbytes) != 0) { + nbytes = min_t(unsigned int, nbytes, MAX_BYTES); + if (nbytes < walk.total) + nbytes = round_down(nbytes, AES_BLOCK_SIZE); spe_begin(); ppc_crypt_ctr(walk.dst.virt.addr, walk.src.virt.addr, - ctx->key_enc, ctx->rounds, pbytes , walk.iv); + ctx->key_enc, ctx->rounds, nbytes, walk.iv); spe_end(); - nbytes -= pbytes; - err = blkcipher_walk_done(desc, &walk, ubytes); + err = skcipher_walk_done(&walk, walk.nbytes - nbytes); } return err; } -static int ppc_xts_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst, - struct scatterlist *src, unsigned int nbytes) +static int ppc_xts_crypt(struct skcipher_request *req, bool enc) { - struct ppc_xts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm); - struct blkcipher_walk walk; - unsigned int ubytes; + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + struct ppc_xts_ctx *ctx = crypto_skcipher_ctx(tfm); + struct skcipher_walk walk; + unsigned int nbytes; int err; u32 *twk; - desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP; - blkcipher_walk_init(&walk, dst, src, nbytes); - err = blkcipher_walk_virt(desc, &walk); + err = skcipher_walk_virt(&walk, req, false); twk = ctx->key_twk; - while ((nbytes = walk.nbytes)) { - ubytes = nbytes > MAX_BYTES ? - nbytes - MAX_BYTES : nbytes & (AES_BLOCK_SIZE - 1); - nbytes -= ubytes; + while ((nbytes = walk.nbytes) != 0) { + nbytes = min_t(unsigned int, nbytes, MAX_BYTES); + nbytes = round_down(nbytes, AES_BLOCK_SIZE); spe_begin(); - ppc_encrypt_xts(walk.dst.virt.addr, walk.src.virt.addr, - ctx->key_enc, ctx->rounds, nbytes, walk.iv, twk); + if (enc) + ppc_encrypt_xts(walk.dst.virt.addr, walk.src.virt.addr, + ctx->key_enc, ctx->rounds, nbytes, + walk.iv, twk); + else + ppc_decrypt_xts(walk.dst.virt.addr, walk.src.virt.addr, + ctx->key_dec, ctx->rounds, nbytes, + walk.iv, twk); spe_end(); twk = NULL; - err = blkcipher_walk_done(desc, &walk, ubytes); + err = skcipher_walk_done(&walk, walk.nbytes - nbytes); } return err; } -static int ppc_xts_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst, - struct scatterlist *src, unsigned int nbytes) +static int ppc_xts_encrypt(struct skcipher_request *req) { - struct ppc_xts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm); - struct blkcipher_walk walk; - unsigned int ubytes; + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + struct ppc_xts_ctx *ctx = crypto_skcipher_ctx(tfm); + int tail = req->cryptlen % AES_BLOCK_SIZE; + int offset = req->cryptlen - tail - AES_BLOCK_SIZE; + struct skcipher_request subreq; + u8 b[2][AES_BLOCK_SIZE]; int err; - u32 *twk; - desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP; - blkcipher_walk_init(&walk, dst, src, nbytes); - err = blkcipher_walk_virt(desc, &walk); - twk = ctx->key_twk; + if (req->cryptlen < AES_BLOCK_SIZE) + return -EINVAL; + + if (tail) { + subreq = *req; + skcipher_request_set_crypt(&subreq, req->src, req->dst, + req->cryptlen - tail, req->iv); + req = &subreq; + } - while ((nbytes = walk.nbytes)) { - ubytes = nbytes > MAX_BYTES ? - nbytes - MAX_BYTES : nbytes & (AES_BLOCK_SIZE - 1); - nbytes -= ubytes; + err = ppc_xts_crypt(req, true); + if (err || !tail) + return err; - spe_begin(); - ppc_decrypt_xts(walk.dst.virt.addr, walk.src.virt.addr, - ctx->key_dec, ctx->rounds, nbytes, walk.iv, twk); - spe_end(); + scatterwalk_map_and_copy(b[0], req->dst, offset, AES_BLOCK_SIZE, 0); + memcpy(b[1], b[0], tail); + scatterwalk_map_and_copy(b[0], req->src, offset + AES_BLOCK_SIZE, tail, 0); - twk = NULL; - err = blkcipher_walk_done(desc, &walk, ubytes); + spe_begin(); + ppc_encrypt_xts(b[0], b[0], ctx->key_enc, ctx->rounds, AES_BLOCK_SIZE, + req->iv, NULL); + spe_end(); + + scatterwalk_map_and_copy(b[0], req->dst, offset, AES_BLOCK_SIZE + tail, 1); + + return 0; +} + +static int ppc_xts_decrypt(struct skcipher_request *req) +{ + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + struct ppc_xts_ctx *ctx = crypto_skcipher_ctx(tfm); + int tail = req->cryptlen % AES_BLOCK_SIZE; + int offset = req->cryptlen - tail - AES_BLOCK_SIZE; + struct skcipher_request subreq; + u8 b[3][AES_BLOCK_SIZE]; + le128 twk; + int err; + + if (req->cryptlen < AES_BLOCK_SIZE) + return -EINVAL; + + if (tail) { + subreq = *req; + skcipher_request_set_crypt(&subreq, req->src, req->dst, + offset, req->iv); + req = &subreq; } - return err; + err = ppc_xts_crypt(req, false); + if (err || !tail) + return err; + + scatterwalk_map_and_copy(b[1], req->src, offset, AES_BLOCK_SIZE + tail, 0); + + spe_begin(); + if (!offset) + ppc_encrypt_ecb(req->iv, req->iv, ctx->key_twk, ctx->rounds, + AES_BLOCK_SIZE); + + gf128mul_x_ble(&twk, (le128 *)req->iv); + + ppc_decrypt_xts(b[1], b[1], ctx->key_dec, ctx->rounds, AES_BLOCK_SIZE, + (u8 *)&twk, NULL); + memcpy(b[0], b[2], tail); + memcpy(b[0] + tail, b[1] + tail, AES_BLOCK_SIZE - tail); + ppc_decrypt_xts(b[0], b[0], ctx->key_dec, ctx->rounds, AES_BLOCK_SIZE, + req->iv, NULL); + spe_end(); + + scatterwalk_map_and_copy(b[0], req->dst, offset, AES_BLOCK_SIZE + tail, 1); + + return 0; } /* @@ -388,9 +418,9 @@ static int ppc_xts_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst, * This improves IPsec thoughput by another few percent. Additionally we assume * that AES context is always aligned to at least 8 bytes because it is created * with kmalloc() in the crypto infrastructure - * */ -static struct crypto_alg aes_algs[] = { { + +static struct crypto_alg aes_cipher_alg = { .cra_name = "aes", .cra_driver_name = "aes-ppc-spe", .cra_priority = 300, @@ -408,96 +438,84 @@ static struct crypto_alg aes_algs[] = { { .cia_decrypt = ppc_aes_decrypt } } -}, { - .cra_name = "ecb(aes)", - .cra_driver_name = "ecb-ppc-spe", - .cra_priority = 300, - .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, - .cra_blocksize = AES_BLOCK_SIZE, - .cra_ctxsize = sizeof(struct ppc_aes_ctx), - .cra_alignmask = 0, - .cra_type = &crypto_blkcipher_type, - .cra_module = THIS_MODULE, - .cra_u = { - .blkcipher = { - .min_keysize = AES_MIN_KEY_SIZE, - .max_keysize = AES_MAX_KEY_SIZE, - .ivsize = AES_BLOCK_SIZE, - .setkey = ppc_aes_setkey, - .encrypt = ppc_ecb_encrypt, - .decrypt = ppc_ecb_decrypt, - } - } -}, { - .cra_name = "cbc(aes)", - .cra_driver_name = "cbc-ppc-spe", - .cra_priority = 300, - .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, - .cra_blocksize = AES_BLOCK_SIZE, - .cra_ctxsize = sizeof(struct ppc_aes_ctx), - .cra_alignmask = 0, - .cra_type = &crypto_blkcipher_type, - .cra_module = THIS_MODULE, - .cra_u = { - .blkcipher = { - .min_keysize = AES_MIN_KEY_SIZE, - .max_keysize = AES_MAX_KEY_SIZE, - .ivsize = AES_BLOCK_SIZE, - .setkey = ppc_aes_setkey, - .encrypt = ppc_cbc_encrypt, - .decrypt = ppc_cbc_decrypt, - } - } -}, { - .cra_name = "ctr(aes)", - .cra_driver_name = "ctr-ppc-spe", - .cra_priority = 300, - .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, - .cra_blocksize = 1, - .cra_ctxsize = sizeof(struct ppc_aes_ctx), - .cra_alignmask = 0, - .cra_type = &crypto_blkcipher_type, - .cra_module = THIS_MODULE, - .cra_u = { - .blkcipher = { - .min_keysize = AES_MIN_KEY_SIZE, - .max_keysize = AES_MAX_KEY_SIZE, - .ivsize = AES_BLOCK_SIZE, - .setkey = ppc_aes_setkey, - .encrypt = ppc_ctr_crypt, - .decrypt = ppc_ctr_crypt, - } - } -}, { - .cra_name = "xts(aes)", - .cra_driver_name = "xts-ppc-spe", - .cra_priority = 300, - .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, - .cra_blocksize = AES_BLOCK_SIZE, - .cra_ctxsize = sizeof(struct ppc_xts_ctx), - .cra_alignmask = 0, - .cra_type = &crypto_blkcipher_type, - .cra_module = THIS_MODULE, - .cra_u = { - .blkcipher = { - .min_keysize = AES_MIN_KEY_SIZE * 2, - .max_keysize = AES_MAX_KEY_SIZE * 2, - .ivsize = AES_BLOCK_SIZE, - .setkey = ppc_xts_setkey, - .encrypt = ppc_xts_encrypt, - .decrypt = ppc_xts_decrypt, - } +}; + +static struct skcipher_alg aes_skcipher_algs[] = { + { + .base.cra_name = "ecb(aes)", + .base.cra_driver_name = "ecb-ppc-spe", + .base.cra_priority = 300, + .base.cra_blocksize = AES_BLOCK_SIZE, + .base.cra_ctxsize = sizeof(struct ppc_aes_ctx), + .base.cra_module = THIS_MODULE, + .min_keysize = AES_MIN_KEY_SIZE, + .max_keysize = AES_MAX_KEY_SIZE, + .setkey = ppc_aes_setkey_skcipher, + .encrypt = ppc_ecb_encrypt, + .decrypt = ppc_ecb_decrypt, + }, { + .base.cra_name = "cbc(aes)", + .base.cra_driver_name = "cbc-ppc-spe", + .base.cra_priority = 300, + .base.cra_blocksize = AES_BLOCK_SIZE, + .base.cra_ctxsize = sizeof(struct ppc_aes_ctx), + .base.cra_module = THIS_MODULE, + .min_keysize = AES_MIN_KEY_SIZE, + .max_keysize = AES_MAX_KEY_SIZE, + .ivsize = AES_BLOCK_SIZE, + .setkey = ppc_aes_setkey_skcipher, + .encrypt = ppc_cbc_encrypt, + .decrypt = ppc_cbc_decrypt, + }, { + .base.cra_name = "ctr(aes)", + .base.cra_driver_name = "ctr-ppc-spe", + .base.cra_priority = 300, + .base.cra_blocksize = 1, + .base.cra_ctxsize = sizeof(struct ppc_aes_ctx), + .base.cra_module = THIS_MODULE, + .min_keysize = AES_MIN_KEY_SIZE, + .max_keysize = AES_MAX_KEY_SIZE, + .ivsize = AES_BLOCK_SIZE, + .setkey = ppc_aes_setkey_skcipher, + .encrypt = ppc_ctr_crypt, + .decrypt = ppc_ctr_crypt, + .chunksize = AES_BLOCK_SIZE, + }, { + .base.cra_name = "xts(aes)", + .base.cra_driver_name = "xts-ppc-spe", + .base.cra_priority = 300, + .base.cra_blocksize = AES_BLOCK_SIZE, + .base.cra_ctxsize = sizeof(struct ppc_xts_ctx), + .base.cra_module = THIS_MODULE, + .min_keysize = AES_MIN_KEY_SIZE * 2, + .max_keysize = AES_MAX_KEY_SIZE * 2, + .ivsize = AES_BLOCK_SIZE, + .setkey = ppc_xts_setkey, + .encrypt = ppc_xts_encrypt, + .decrypt = ppc_xts_decrypt, } -} }; +}; static int __init ppc_aes_mod_init(void) { - return crypto_register_algs(aes_algs, ARRAY_SIZE(aes_algs)); + int err; + + err = crypto_register_alg(&aes_cipher_alg); + if (err) + return err; + + err = crypto_register_skciphers(aes_skcipher_algs, + ARRAY_SIZE(aes_skcipher_algs)); + if (err) + crypto_unregister_alg(&aes_cipher_alg); + return err; } static void __exit ppc_aes_mod_fini(void) { - crypto_unregister_algs(aes_algs, ARRAY_SIZE(aes_algs)); + crypto_unregister_alg(&aes_cipher_alg); + crypto_unregister_skciphers(aes_skcipher_algs, + ARRAY_SIZE(aes_skcipher_algs)); } module_init(ppc_aes_mod_init); diff --git a/arch/powerpc/crypto/crc-vpmsum_test.c b/arch/powerpc/crypto/crc-vpmsum_test.c index 47985219a68f..dce86e75f1a8 100644 --- a/arch/powerpc/crypto/crc-vpmsum_test.c +++ b/arch/powerpc/crypto/crc-vpmsum_test.c @@ -103,6 +103,7 @@ static int __init crc_test_init(void) crc32, verify32, len); break; } + cond_resched(); } pr_info("crc-vpmsum_test done, completed %lu iterations\n", i); } while (0); diff --git a/arch/powerpc/include/asm/Kbuild b/arch/powerpc/include/asm/Kbuild index 64870c7be4a3..d0a23d0db863 100644 --- a/arch/powerpc/include/asm/Kbuild +++ b/arch/powerpc/include/asm/Kbuild @@ -4,10 +4,11 @@ generated-y += syscall_table_64.h generated-y += syscall_table_c32.h generated-y += syscall_table_spu.h generic-y += div64.h +generic-y += dma-mapping.h generic-y += export.h generic-y += irq_regs.h generic-y += local64.h generic-y += mcs_spinlock.h generic-y += preempt.h generic-y += vtime.h -generic-y += msi.h +generic-y += early_ioremap.h diff --git a/arch/powerpc/include/asm/asm-prototypes.h b/arch/powerpc/include/asm/asm-prototypes.h index 8561498e653c..983c0084fb3f 100644 --- a/arch/powerpc/include/asm/asm-prototypes.h +++ b/arch/powerpc/include/asm/asm-prototypes.h @@ -92,7 +92,8 @@ long sys_swapcontext(struct ucontext __user *old_ctx, long sys_debug_setcontext(struct ucontext __user *ctx, int ndbg, struct sig_dbg_op __user *dbg); int -ppc_select(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp, struct timeval __user *tvp); +ppc_select(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp, + struct __kernel_old_timeval __user *tvp); unsigned long __init early_init(unsigned long dt_ptr); void __init machine_init(u64 dt_ptr); #endif @@ -152,9 +153,12 @@ void _kvmppc_save_tm_pr(struct kvm_vcpu *vcpu, u64 guest_msr); /* Patch sites */ extern s32 patch__call_flush_count_cache; extern s32 patch__flush_count_cache_return; +extern s32 patch__flush_link_stack_return; +extern s32 patch__call_kvm_flush_link_stack; extern s32 patch__memset_nocache, patch__memcpy_nocache; extern long flush_count_cache; +extern long kvm_flush_link_stack; #ifdef CONFIG_PPC_TRANSACTIONAL_MEM void kvmppc_save_tm_hv(struct kvm_vcpu *vcpu, u64 msr, bool preserve_nv); diff --git a/arch/powerpc/include/asm/book3s/32/kup.h b/arch/powerpc/include/asm/book3s/32/kup.h index 677e9babef80..f9dc597b0b86 100644 --- a/arch/powerpc/include/asm/book3s/32/kup.h +++ b/arch/powerpc/include/asm/book3s/32/kup.h @@ -91,6 +91,7 @@ static inline void kuap_update_sr(u32 sr, u32 addr, u32 end) { + addr &= 0xf0000000; /* align addr to start of segment */ barrier(); /* make sure thread.kuap is updated before playing with SRs */ while (addr < end) { mtsrin(sr, addr); diff --git a/arch/powerpc/include/asm/book3s/64/pgalloc.h b/arch/powerpc/include/asm/book3s/64/pgalloc.h index d5a44912902f..f6968c811026 100644 --- a/arch/powerpc/include/asm/book3s/64/pgalloc.h +++ b/arch/powerpc/include/asm/book3s/64/pgalloc.h @@ -122,11 +122,6 @@ static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd) static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pud, unsigned long address) { - /* - * By now all the pud entries should be none entries. So go - * ahead and flush the page walk cache - */ - flush_tlb_pgtable(tlb, address); pgtable_free_tlb(tlb, pud, PUD_INDEX); } @@ -143,11 +138,6 @@ static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd) static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd, unsigned long address) { - /* - * By now all the pud entries should be none entries. So go - * ahead and flush the page walk cache - */ - flush_tlb_pgtable(tlb, address); return pgtable_free_tlb(tlb, pmd, PMD_INDEX); } @@ -166,11 +156,6 @@ static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table, unsigned long address) { - /* - * By now all the pud entries should be none entries. So go - * ahead and flush the page walk cache - */ - flush_tlb_pgtable(tlb, address); pgtable_free_tlb(tlb, table, PTE_INDEX); } diff --git a/arch/powerpc/include/asm/book3s/64/pgtable-4k.h b/arch/powerpc/include/asm/book3s/64/pgtable-4k.h index a069dfcac9a9..4e697bc2f4cd 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable-4k.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable-4k.h @@ -70,9 +70,6 @@ static inline int get_hugepd_cache_index(int index) /* should not reach */ } -#else /* !CONFIG_HUGETLB_PAGE */ -static inline int pmd_huge(pmd_t pmd) { return 0; } -static inline int pud_huge(pud_t pud) { return 0; } #endif /* CONFIG_HUGETLB_PAGE */ #endif /* __ASSEMBLY__ */ diff --git a/arch/powerpc/include/asm/book3s/64/pgtable-64k.h b/arch/powerpc/include/asm/book3s/64/pgtable-64k.h index e3d4dd4ae2fa..34d1018896b3 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable-64k.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable-64k.h @@ -59,9 +59,6 @@ static inline int get_hugepd_cache_index(int index) BUG(); } -#else /* !CONFIG_HUGETLB_PAGE */ -static inline int pmd_huge(pmd_t pmd) { return 0; } -static inline int pud_huge(pud_t pud) { return 0; } #endif /* CONFIG_HUGETLB_PAGE */ static inline int remap_4k_pfn(struct vm_area_struct *vma, unsigned long addr, diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush.h b/arch/powerpc/include/asm/book3s/64/tlbflush.h index 7aa8195b6cff..dcb5c3839d2f 100644 --- a/arch/powerpc/include/asm/book3s/64/tlbflush.h +++ b/arch/powerpc/include/asm/book3s/64/tlbflush.h @@ -147,22 +147,6 @@ static inline void flush_tlb_fix_spurious_fault(struct vm_area_struct *vma, flush_tlb_page(vma, address); } -/* - * flush the page walk cache for the address - */ -static inline void flush_tlb_pgtable(struct mmu_gather *tlb, unsigned long address) -{ - /* - * Flush the page table walk cache on freeing a page table. We already - * have marked the upper/higher level page table entry none by now. - * So it is safe to flush PWC here. - */ - if (!radix_enabled()) - return; - - radix__flush_tlb_pwc(tlb, address); -} - extern bool tlbie_capable; extern bool tlbie_enabled; diff --git a/arch/powerpc/include/asm/bug.h b/arch/powerpc/include/asm/bug.h index f47e6ff6554d..338f36cd9934 100644 --- a/arch/powerpc/include/asm/bug.h +++ b/arch/powerpc/include/asm/bug.h @@ -49,6 +49,15 @@ ".previous\n" #endif +#define BUG_ENTRY(insn, flags, ...) \ + __asm__ __volatile__( \ + "1: " insn "\n" \ + _EMIT_BUG_ENTRY \ + : : "i" (__FILE__), "i" (__LINE__), \ + "i" (flags), \ + "i" (sizeof(struct bug_entry)), \ + ##__VA_ARGS__) + /* * BUG_ON() and WARN_ON() do their best to cooperate with compile-time * optimisations. However depending on the complexity of the condition @@ -56,11 +65,7 @@ */ #define BUG() do { \ - __asm__ __volatile__( \ - "1: twi 31,0,0\n" \ - _EMIT_BUG_ENTRY \ - : : "i" (__FILE__), "i" (__LINE__), \ - "i" (0), "i" (sizeof(struct bug_entry))); \ + BUG_ENTRY("twi 31, 0, 0", 0); \ unreachable(); \ } while (0) @@ -69,23 +74,11 @@ if (x) \ BUG(); \ } else { \ - __asm__ __volatile__( \ - "1: "PPC_TLNEI" %4,0\n" \ - _EMIT_BUG_ENTRY \ - : : "i" (__FILE__), "i" (__LINE__), "i" (0), \ - "i" (sizeof(struct bug_entry)), \ - "r" ((__force long)(x))); \ + BUG_ENTRY(PPC_TLNEI " %4, 0", 0, "r" ((__force long)(x))); \ } \ } while (0) -#define __WARN_FLAGS(flags) do { \ - __asm__ __volatile__( \ - "1: twi 31,0,0\n" \ - _EMIT_BUG_ENTRY \ - : : "i" (__FILE__), "i" (__LINE__), \ - "i" (BUGFLAG_WARNING|(flags)), \ - "i" (sizeof(struct bug_entry))); \ -} while (0) +#define __WARN_FLAGS(flags) BUG_ENTRY("twi 31, 0, 0", BUGFLAG_WARNING | (flags)) #define WARN_ON(x) ({ \ int __ret_warn_on = !!(x); \ @@ -93,13 +86,9 @@ if (__ret_warn_on) \ __WARN(); \ } else { \ - __asm__ __volatile__( \ - "1: "PPC_TLNEI" %4,0\n" \ - _EMIT_BUG_ENTRY \ - : : "i" (__FILE__), "i" (__LINE__), \ - "i" (BUGFLAG_WARNING|BUGFLAG_TAINT(TAINT_WARN)),\ - "i" (sizeof(struct bug_entry)), \ - "r" (__ret_warn_on)); \ + BUG_ENTRY(PPC_TLNEI " %4, 0", \ + BUGFLAG_WARNING | BUGFLAG_TAINT(TAINT_WARN), \ + "r" (__ret_warn_on)); \ } \ unlikely(__ret_warn_on); \ }) diff --git a/arch/powerpc/include/asm/cache.h b/arch/powerpc/include/asm/cache.h index 45e3137ccd71..72b81015cebe 100644 --- a/arch/powerpc/include/asm/cache.h +++ b/arch/powerpc/include/asm/cache.h @@ -55,42 +55,48 @@ struct ppc64_caches { extern struct ppc64_caches ppc64_caches; -static inline u32 l1_cache_shift(void) +static inline u32 l1_dcache_shift(void) { return ppc64_caches.l1d.log_block_size; } -static inline u32 l1_cache_bytes(void) +static inline u32 l1_dcache_bytes(void) { return ppc64_caches.l1d.block_size; } + +static inline u32 l1_icache_shift(void) +{ + return ppc64_caches.l1i.log_block_size; +} + +static inline u32 l1_icache_bytes(void) +{ + return ppc64_caches.l1i.block_size; +} #else -static inline u32 l1_cache_shift(void) +static inline u32 l1_dcache_shift(void) { return L1_CACHE_SHIFT; } -static inline u32 l1_cache_bytes(void) +static inline u32 l1_dcache_bytes(void) { return L1_CACHE_BYTES; } + +static inline u32 l1_icache_shift(void) +{ + return L1_CACHE_SHIFT; +} + +static inline u32 l1_icache_bytes(void) +{ + return L1_CACHE_BYTES; +} + #endif -#endif /* ! __ASSEMBLY__ */ - -#if defined(__ASSEMBLY__) -/* - * For a snooping icache, we still need a dummy icbi to purge all the - * prefetched instructions from the ifetch buffers. We also need a sync - * before the icbi to order the the actual stores to memory that might - * have modified instructions with the icbi. - */ -#define PURGE_PREFETCHED_INS \ - sync; \ - icbi 0,r3; \ - sync; \ - isync -#else #define __read_mostly __attribute__((__section__(".data..read_mostly"))) #ifdef CONFIG_PPC_BOOK3S_32 @@ -124,6 +130,17 @@ static inline void dcbst(void *addr) { __asm__ __volatile__ ("dcbst 0, %0" : : "r"(addr) : "memory"); } + +static inline void icbi(void *addr) +{ + asm volatile ("icbi 0, %0" : : "r"(addr) : "memory"); +} + +static inline void iccci(void *addr) +{ + asm volatile ("iccci 0, %0" : : "r"(addr) : "memory"); +} + #endif /* !__ASSEMBLY__ */ #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_CACHE_H */ diff --git a/arch/powerpc/include/asm/cacheflush.h b/arch/powerpc/include/asm/cacheflush.h index eef388f2659f..4a1c9f0200e1 100644 --- a/arch/powerpc/include/asm/cacheflush.h +++ b/arch/powerpc/include/asm/cacheflush.h @@ -42,29 +42,25 @@ extern void flush_dcache_page(struct page *page); #define flush_dcache_mmap_lock(mapping) do { } while (0) #define flush_dcache_mmap_unlock(mapping) do { } while (0) -extern void flush_icache_range(unsigned long, unsigned long); +void flush_icache_range(unsigned long start, unsigned long stop); extern void flush_icache_user_range(struct vm_area_struct *vma, struct page *page, unsigned long addr, int len); -extern void __flush_dcache_icache(void *page_va); extern void flush_dcache_icache_page(struct page *page); -#if defined(CONFIG_PPC32) && !defined(CONFIG_BOOKE) -extern void __flush_dcache_icache_phys(unsigned long physaddr); -#else -static inline void __flush_dcache_icache_phys(unsigned long physaddr) -{ - BUG(); -} -#endif - -/* - * Write any modified data cache blocks out to memory and invalidate them. - * Does not invalidate the corresponding instruction cache blocks. +void __flush_dcache_icache(void *page); + +/** + * flush_dcache_range(): Write any modified data cache blocks out to memory and + * invalidate them. Does not invalidate the corresponding instruction cache + * blocks. + * + * @start: the start address + * @stop: the stop address (exclusive) */ static inline void flush_dcache_range(unsigned long start, unsigned long stop) { - unsigned long shift = l1_cache_shift(); - unsigned long bytes = l1_cache_bytes(); + unsigned long shift = l1_dcache_shift(); + unsigned long bytes = l1_dcache_bytes(); void *addr = (void *)(start & ~(bytes - 1)); unsigned long size = stop - (unsigned long)addr + (bytes - 1); unsigned long i; @@ -89,8 +85,8 @@ static inline void flush_dcache_range(unsigned long start, unsigned long stop) */ static inline void clean_dcache_range(unsigned long start, unsigned long stop) { - unsigned long shift = l1_cache_shift(); - unsigned long bytes = l1_cache_bytes(); + unsigned long shift = l1_dcache_shift(); + unsigned long bytes = l1_dcache_bytes(); void *addr = (void *)(start & ~(bytes - 1)); unsigned long size = stop - (unsigned long)addr + (bytes - 1); unsigned long i; @@ -108,8 +104,8 @@ static inline void clean_dcache_range(unsigned long start, unsigned long stop) static inline void invalidate_dcache_range(unsigned long start, unsigned long stop) { - unsigned long shift = l1_cache_shift(); - unsigned long bytes = l1_cache_bytes(); + unsigned long shift = l1_dcache_shift(); + unsigned long bytes = l1_dcache_bytes(); void *addr = (void *)(start & ~(bytes - 1)); unsigned long size = stop - (unsigned long)addr + (bytes - 1); unsigned long i; diff --git a/arch/powerpc/include/asm/dma-direct.h b/arch/powerpc/include/asm/dma-direct.h index a2912b47102c..abc154d784b0 100644 --- a/arch/powerpc/include/asm/dma-direct.h +++ b/arch/powerpc/include/asm/dma-direct.h @@ -2,26 +2,13 @@ #ifndef ASM_POWERPC_DMA_DIRECT_H #define ASM_POWERPC_DMA_DIRECT_H 1 -static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size) -{ - if (!dev->dma_mask) - return false; - - return addr + size - 1 <= - min_not_zero(*dev->dma_mask, dev->bus_dma_mask); -} - static inline dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr) { - if (!dev) - return paddr + PCI_DRAM_OFFSET; return paddr + dev->archdata.dma_offset; } static inline phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t daddr) { - if (!dev) - return daddr - PCI_DRAM_OFFSET; return daddr - dev->archdata.dma_offset; } #endif /* ASM_POWERPC_DMA_DIRECT_H */ diff --git a/arch/powerpc/include/asm/dma-mapping.h b/arch/powerpc/include/asm/dma-mapping.h deleted file mode 100644 index 565d6f74b189..000000000000 --- a/arch/powerpc/include/asm/dma-mapping.h +++ /dev/null @@ -1,18 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Copyright (C) 2004 IBM - */ -#ifndef _ASM_DMA_MAPPING_H -#define _ASM_DMA_MAPPING_H - -static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus) -{ - /* We don't handle the NULL dev case for ISA for now. We could - * do it via an out of line call but it is not needed for now. The - * only ISA DMA device we support is the floppy and we have a hack - * in the floppy driver directly to get a device for us. - */ - return NULL; -} - -#endif /* _ASM_DMA_MAPPING_H */ diff --git a/arch/powerpc/include/asm/elf.h b/arch/powerpc/include/asm/elf.h index 409c9bfb43d9..57c229a86f08 100644 --- a/arch/powerpc/include/asm/elf.h +++ b/arch/powerpc/include/asm/elf.h @@ -175,4 +175,7 @@ do { \ ARCH_DLINFO_CACHE_GEOMETRY; \ } while (0) +/* Relocate the kernel image to @final_address */ +void relocate(unsigned long final_address); + #endif /* _ASM_POWERPC_ELF_H */ diff --git a/arch/powerpc/include/asm/fixmap.h b/arch/powerpc/include/asm/fixmap.h index 0cfc365d814b..2ef155a3c821 100644 --- a/arch/powerpc/include/asm/fixmap.h +++ b/arch/powerpc/include/asm/fixmap.h @@ -15,6 +15,7 @@ #define _ASM_FIXMAP_H #ifndef __ASSEMBLY__ +#include <linux/sizes.h> #include <asm/page.h> #include <asm/pgtable.h> #ifdef CONFIG_HIGHMEM @@ -63,7 +64,22 @@ enum fixed_addresses { FIX_IMMR_BASE = __ALIGN_MASK(FIX_IMMR_START, FIX_IMMR_SIZE - 1) - 1 + FIX_IMMR_SIZE, #endif +#ifdef CONFIG_PPC_83xx + /* For IMMR we need an aligned 2M area */ +#define FIX_IMMR_SIZE (SZ_2M / PAGE_SIZE) + FIX_IMMR_START, + FIX_IMMR_BASE = __ALIGN_MASK(FIX_IMMR_START, FIX_IMMR_SIZE - 1) - 1 + + FIX_IMMR_SIZE, +#endif /* FIX_PCIE_MCFG, */ + __end_of_permanent_fixed_addresses, + +#define NR_FIX_BTMAPS (SZ_256K / PAGE_SIZE) +#define FIX_BTMAPS_SLOTS 16 +#define TOTAL_FIX_BTMAPS (NR_FIX_BTMAPS * FIX_BTMAPS_SLOTS) + + FIX_BTMAP_END = __end_of_permanent_fixed_addresses, + FIX_BTMAP_BEGIN = FIX_BTMAP_END + TOTAL_FIX_BTMAPS - 1, __end_of_fixed_addresses }; @@ -71,14 +87,22 @@ enum fixed_addresses { #define FIXADDR_START (FIXADDR_TOP - __FIXADDR_SIZE) #define FIXMAP_PAGE_NOCACHE PAGE_KERNEL_NCG +#define FIXMAP_PAGE_IO PAGE_KERNEL_NCG #include <asm-generic/fixmap.h> static inline void __set_fixmap(enum fixed_addresses idx, phys_addr_t phys, pgprot_t flags) { - map_kernel_page(fix_to_virt(idx), phys, flags); + if (__builtin_constant_p(idx)) + BUILD_BUG_ON(idx >= __end_of_fixed_addresses); + else if (WARN_ON(idx >= __end_of_fixed_addresses)) + return; + + map_kernel_page(__fix_to_virt(idx), phys, flags); } +#define __early_set_fixmap __set_fixmap + #endif /* !__ASSEMBLY__ */ #endif diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h index 11112023e327..13bd870609c3 100644 --- a/arch/powerpc/include/asm/hvcall.h +++ b/arch/powerpc/include/asm/hvcall.h @@ -342,6 +342,15 @@ #define H_TLB_INVALIDATE 0xF808 #define H_COPY_TOFROM_GUEST 0xF80C +/* Flags for H_SVM_PAGE_IN */ +#define H_PAGE_IN_SHARED 0x1 + +/* Platform-specific hcalls used by the Ultravisor */ +#define H_SVM_PAGE_IN 0xEF00 +#define H_SVM_PAGE_OUT 0xEF04 +#define H_SVM_INIT_START 0xEF08 +#define H_SVM_INIT_DONE 0xEF0C + /* Values for 2nd argument to H_SET_MODE */ #define H_SET_MODE_RESOURCE_SET_CIABR 1 #define H_SET_MODE_RESOURCE_SET_DAWR 2 diff --git a/arch/powerpc/include/asm/hw_breakpoint.h b/arch/powerpc/include/asm/hw_breakpoint.h index 67e2da195eae..27ac6f5d2891 100644 --- a/arch/powerpc/include/asm/hw_breakpoint.h +++ b/arch/powerpc/include/asm/hw_breakpoint.h @@ -14,6 +14,7 @@ struct arch_hw_breakpoint { unsigned long address; u16 type; u16 len; /* length of the target data symbol */ + u16 hw_len; /* length programmed in hw */ }; /* Note: Don't change the the first 6 bits below as they are in the same order @@ -33,6 +34,11 @@ struct arch_hw_breakpoint { #define HW_BRK_TYPE_PRIV_ALL (HW_BRK_TYPE_USER | HW_BRK_TYPE_KERNEL | \ HW_BRK_TYPE_HYP) +#define HW_BREAKPOINT_ALIGN 0x7 + +#define DABR_MAX_LEN 8 +#define DAWR_MAX_LEN 512 + #ifdef CONFIG_HAVE_HW_BREAKPOINT #include <linux/kdebug.h> #include <asm/reg.h> @@ -44,8 +50,6 @@ struct pmu; struct perf_sample_data; struct task_struct; -#define HW_BREAKPOINT_ALIGN 0x7 - extern int hw_breakpoint_slots(int type); extern int arch_bp_generic_fields(int type, int *gen_bp_type); extern int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw); @@ -70,6 +74,7 @@ static inline void hw_breakpoint_disable(void) brk.address = 0; brk.type = 0; brk.len = 0; + brk.hw_len = 0; if (ppc_breakpoint_available()) __set_breakpoint(&brk); } diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h index 32a18f2f49bc..e3a905e3d573 100644 --- a/arch/powerpc/include/asm/hw_irq.h +++ b/arch/powerpc/include/asm/hw_irq.h @@ -226,8 +226,8 @@ static inline bool arch_irqs_disabled(void) #endif /* CONFIG_PPC_BOOK3S */ #ifdef CONFIG_PPC_BOOK3E -#define __hard_irq_enable() asm volatile("wrteei 1" : : : "memory") -#define __hard_irq_disable() asm volatile("wrteei 0" : : : "memory") +#define __hard_irq_enable() wrtee(MSR_EE) +#define __hard_irq_disable() wrtee(0) #else #define __hard_irq_enable() __mtmsrd(MSR_EE|MSR_RI, 1) #define __hard_irq_disable() __mtmsrd(MSR_RI, 1) @@ -280,8 +280,6 @@ extern void force_external_irq_replay(void); #else /* CONFIG_PPC64 */ -#define SET_MSR_EE(x) mtmsr(x) - static inline unsigned long arch_local_save_flags(void) { return mfmsr(); @@ -289,47 +287,44 @@ static inline unsigned long arch_local_save_flags(void) static inline void arch_local_irq_restore(unsigned long flags) { -#if defined(CONFIG_BOOKE) - asm volatile("wrtee %0" : : "r" (flags) : "memory"); -#else - mtmsr(flags); -#endif + if (IS_ENABLED(CONFIG_BOOKE)) + wrtee(flags); + else + mtmsr(flags); } static inline unsigned long arch_local_irq_save(void) { unsigned long flags = arch_local_save_flags(); -#ifdef CONFIG_BOOKE - asm volatile("wrteei 0" : : : "memory"); -#elif defined(CONFIG_PPC_8xx) - wrtspr(SPRN_EID); -#else - SET_MSR_EE(flags & ~MSR_EE); -#endif + + if (IS_ENABLED(CONFIG_BOOKE)) + wrtee(0); + else if (IS_ENABLED(CONFIG_PPC_8xx)) + wrtspr(SPRN_EID); + else + mtmsr(flags & ~MSR_EE); + return flags; } static inline void arch_local_irq_disable(void) { -#ifdef CONFIG_BOOKE - asm volatile("wrteei 0" : : : "memory"); -#elif defined(CONFIG_PPC_8xx) - wrtspr(SPRN_EID); -#else - arch_local_irq_save(); -#endif + if (IS_ENABLED(CONFIG_BOOKE)) + wrtee(0); + else if (IS_ENABLED(CONFIG_PPC_8xx)) + wrtspr(SPRN_EID); + else + mtmsr(mfmsr() & ~MSR_EE); } static inline void arch_local_irq_enable(void) { -#ifdef CONFIG_BOOKE - asm volatile("wrteei 1" : : : "memory"); -#elif defined(CONFIG_PPC_8xx) - wrtspr(SPRN_EIE); -#else - unsigned long msr = mfmsr(); - SET_MSR_EE(msr | MSR_EE); -#endif + if (IS_ENABLED(CONFIG_BOOKE)) + wrtee(MSR_EE); + else if (IS_ENABLED(CONFIG_PPC_8xx)) + wrtspr(SPRN_EIE); + else + mtmsr(mfmsr() | MSR_EE); } static inline bool arch_irqs_disabled_flags(unsigned long flags) diff --git a/arch/powerpc/include/asm/kvm_book3s_uvmem.h b/arch/powerpc/include/asm/kvm_book3s_uvmem.h new file mode 100644 index 000000000000..50204e228f16 --- /dev/null +++ b/arch/powerpc/include/asm/kvm_book3s_uvmem.h @@ -0,0 +1,74 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __ASM_KVM_BOOK3S_UVMEM_H__ +#define __ASM_KVM_BOOK3S_UVMEM_H__ + +#ifdef CONFIG_PPC_UV +int kvmppc_uvmem_init(void); +void kvmppc_uvmem_free(void); +int kvmppc_uvmem_slot_init(struct kvm *kvm, const struct kvm_memory_slot *slot); +void kvmppc_uvmem_slot_free(struct kvm *kvm, + const struct kvm_memory_slot *slot); +unsigned long kvmppc_h_svm_page_in(struct kvm *kvm, + unsigned long gra, + unsigned long flags, + unsigned long page_shift); +unsigned long kvmppc_h_svm_page_out(struct kvm *kvm, + unsigned long gra, + unsigned long flags, + unsigned long page_shift); +unsigned long kvmppc_h_svm_init_start(struct kvm *kvm); +unsigned long kvmppc_h_svm_init_done(struct kvm *kvm); +int kvmppc_send_page_to_uv(struct kvm *kvm, unsigned long gfn); +void kvmppc_uvmem_drop_pages(const struct kvm_memory_slot *free, + struct kvm *kvm); +#else +static inline int kvmppc_uvmem_init(void) +{ + return 0; +} + +static inline void kvmppc_uvmem_free(void) { } + +static inline int +kvmppc_uvmem_slot_init(struct kvm *kvm, const struct kvm_memory_slot *slot) +{ + return 0; +} + +static inline void +kvmppc_uvmem_slot_free(struct kvm *kvm, const struct kvm_memory_slot *slot) { } + +static inline unsigned long +kvmppc_h_svm_page_in(struct kvm *kvm, unsigned long gra, + unsigned long flags, unsigned long page_shift) +{ + return H_UNSUPPORTED; +} + +static inline unsigned long +kvmppc_h_svm_page_out(struct kvm *kvm, unsigned long gra, + unsigned long flags, unsigned long page_shift) +{ + return H_UNSUPPORTED; +} + +static inline unsigned long kvmppc_h_svm_init_start(struct kvm *kvm) +{ + return H_UNSUPPORTED; +} + +static inline unsigned long kvmppc_h_svm_init_done(struct kvm *kvm) +{ + return H_UNSUPPORTED; +} + +static inline int kvmppc_send_page_to_uv(struct kvm *kvm, unsigned long gfn) +{ + return -EFAULT; +} + +static inline void +kvmppc_uvmem_drop_pages(const struct kvm_memory_slot *free, + struct kvm *kvm) { } +#endif /* CONFIG_PPC_UV */ +#endif /* __ASM_KVM_BOOK3S_UVMEM_H__ */ diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index 6fe6ad64cba5..0a398f2321c2 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -275,6 +275,10 @@ struct kvm_hpt_info { struct kvm_resize_hpt; +/* Flag values for kvm_arch.secure_guest */ +#define KVMPPC_SECURE_INIT_START 0x1 /* H_SVM_INIT_START has been called */ +#define KVMPPC_SECURE_INIT_DONE 0x2 /* H_SVM_INIT_DONE completed */ + struct kvm_arch { unsigned int lpid; unsigned int smt_mode; /* # vcpus per virtual core */ @@ -330,6 +334,8 @@ struct kvm_arch { #endif struct kvmppc_ops *kvm_ops; #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE + struct mutex uvmem_lock; + struct list_head uvmem_pfns; struct mutex mmu_setup_lock; /* nests inside vcpu mutexes */ u64 l1_ptcr; int max_nested_lpid; @@ -401,7 +407,6 @@ struct kvmppc_mmu { u32 (*mfsrin)(struct kvm_vcpu *vcpu, u32 srnum); int (*xlate)(struct kvm_vcpu *vcpu, gva_t eaddr, struct kvmppc_pte *pte, bool data, bool iswrite); - void (*reset_msr)(struct kvm_vcpu *vcpu); void (*tlbie)(struct kvm_vcpu *vcpu, ulong addr, bool large); int (*esid_to_vsid)(struct kvm_vcpu *vcpu, ulong esid, u64 *vsid); u64 (*ea_to_vp)(struct kvm_vcpu *vcpu, gva_t eaddr, bool data); diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index ee62776e5433..3d2f871241a8 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -271,6 +271,7 @@ struct kvmppc_ops { union kvmppc_one_reg *val); void (*vcpu_load)(struct kvm_vcpu *vcpu, int cpu); void (*vcpu_put)(struct kvm_vcpu *vcpu); + void (*inject_interrupt)(struct kvm_vcpu *vcpu, int vec, u64 srr1_flags); void (*set_msr)(struct kvm_vcpu *vcpu, u64 msr); int (*vcpu_run)(struct kvm_run *run, struct kvm_vcpu *vcpu); struct kvm_vcpu *(*vcpu_create)(struct kvm *kvm, unsigned int id); @@ -321,6 +322,7 @@ struct kvmppc_ops { int size); int (*store_to_eaddr)(struct kvm_vcpu *vcpu, ulong *eaddr, void *ptr, int size); + int (*svm_off)(struct kvm *kvm); }; extern struct kvmppc_ops *kvmppc_hv_ops; diff --git a/arch/powerpc/include/asm/local.h b/arch/powerpc/include/asm/local.h index fdd00939270b..bc4bd19b7fc2 100644 --- a/arch/powerpc/include/asm/local.h +++ b/arch/powerpc/include/asm/local.h @@ -17,7 +17,7 @@ typedef struct #define LOCAL_INIT(i) { (i) } -static __inline__ long local_read(local_t *l) +static __inline__ long local_read(const local_t *l) { return READ_ONCE(l->v); } diff --git a/arch/powerpc/include/asm/nohash/32/kup-8xx.h b/arch/powerpc/include/asm/nohash/32/kup-8xx.h index 1c3133b5f86a..1006a427e99c 100644 --- a/arch/powerpc/include/asm/nohash/32/kup-8xx.h +++ b/arch/powerpc/include/asm/nohash/32/kup-8xx.h @@ -3,6 +3,7 @@ #define _ASM_POWERPC_KUP_8XX_H_ #include <asm/bug.h> +#include <asm/mmu.h> #ifdef CONFIG_PPC_KUAP diff --git a/arch/powerpc/include/asm/nohash/mmu-book3e.h b/arch/powerpc/include/asm/nohash/mmu-book3e.h index 4c9777d256fb..b41004664312 100644 --- a/arch/powerpc/include/asm/nohash/mmu-book3e.h +++ b/arch/powerpc/include/asm/nohash/mmu-book3e.h @@ -75,7 +75,6 @@ #define MAS2_E 0x00000001 #define MAS2_WIMGE_MASK 0x0000001f #define MAS2_EPN_MASK(size) (~0 << (size + 10)) -#define MAS2_VAL(addr, size, flags) ((addr) & MAS2_EPN_MASK(size) | (flags)) #define MAS3_RPN 0xFFFFF000 #define MAS3_U0 0x00000200 @@ -221,6 +220,16 @@ #define TLBILX_T_CLASS2 6 #define TLBILX_T_CLASS3 7 +/* + * The mapping only needs to be cache-coherent on SMP, except on + * Freescale e500mc derivatives where it's also needed for coherent DMA. + */ +#if defined(CONFIG_SMP) || defined(CONFIG_PPC_E500MC) +#define MAS2_M_IF_NEEDED MAS2_M +#else +#define MAS2_M_IF_NEEDED 0 +#endif + #ifndef __ASSEMBLY__ #include <asm/bug.h> diff --git a/arch/powerpc/include/asm/opal-api.h b/arch/powerpc/include/asm/opal-api.h index 378e3997845a..c1f25a760eb1 100644 --- a/arch/powerpc/include/asm/opal-api.h +++ b/arch/powerpc/include/asm/opal-api.h @@ -211,7 +211,10 @@ #define OPAL_MPIPL_UPDATE 173 #define OPAL_MPIPL_REGISTER_TAG 174 #define OPAL_MPIPL_QUERY_TAG 175 -#define OPAL_LAST 175 +#define OPAL_SECVAR_GET 176 +#define OPAL_SECVAR_GET_NEXT 177 +#define OPAL_SECVAR_ENQUEUE_UPDATE 178 +#define OPAL_LAST 178 #define QUIESCE_HOLD 1 /* Spin all calls at entry */ #define QUIESCE_REJECT 2 /* Fail all calls with OPAL_BUSY */ diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h index a0cf8fba4d12..9986ac34b8e2 100644 --- a/arch/powerpc/include/asm/opal.h +++ b/arch/powerpc/include/asm/opal.h @@ -298,6 +298,13 @@ int opal_sensor_group_clear(u32 group_hndl, int token); int opal_sensor_group_enable(u32 group_hndl, int token, bool enable); int opal_nx_coproc_init(uint32_t chip_id, uint32_t ct); +int opal_secvar_get(const char *key, uint64_t key_len, u8 *data, + uint64_t *data_size); +int opal_secvar_get_next(const char *key, uint64_t *key_len, + uint64_t key_buf_size); +int opal_secvar_enqueue_update(const char *key, uint64_t key_len, u8 *data, + uint64_t data_size); + s64 opal_mpipl_update(enum opal_mpipl_ops op, u64 src, u64 dest, u64 size); s64 opal_mpipl_register_tag(enum opal_mpipl_tags tag, u64 addr); s64 opal_mpipl_query_tag(enum opal_mpipl_tags tag, u64 *addr); diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h index c8bb14ff4713..7f1fd41e3065 100644 --- a/arch/powerpc/include/asm/page.h +++ b/arch/powerpc/include/asm/page.h @@ -325,17 +325,15 @@ void arch_free_page(struct page *page, int order); struct vm_area_struct; +extern unsigned long kernstart_virt_addr; + +static inline unsigned long kaslr_offset(void) +{ + return kernstart_virt_addr - KERNELBASE; +} + #include <asm-generic/memory_model.h> #endif /* __ASSEMBLY__ */ #include <asm/slice.h> -/* - * Allow 30-bit DMA for very limited Broadcom wifi chips on many powerbooks. - */ -#ifdef CONFIG_PPC32 -#define ARCH_ZONE_DMA_BITS 30 -#else -#define ARCH_ZONE_DMA_BITS 31 -#endif - #endif /* _ASM_POWERPC_PAGE_H */ diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h index 4053b2ab427c..0e4ec8cc37b7 100644 --- a/arch/powerpc/include/asm/pgtable.h +++ b/arch/powerpc/include/asm/pgtable.h @@ -157,13 +157,9 @@ static inline bool pgd_is_leaf(pgd_t pgd) #define is_ioremap_addr is_ioremap_addr static inline bool is_ioremap_addr(const void *x) { -#ifdef CONFIG_MMU unsigned long addr = (unsigned long)x; return addr >= IOREMAP_BASE && addr < IOREMAP_END; -#else - return false; -#endif } #endif /* CONFIG_PPC64 */ diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index b3cbb1136bce..1aa46dff0957 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -25,9 +25,7 @@ #include <asm/reg_fsl_emb.h> #endif -#ifdef CONFIG_PPC_8xx #include <asm/reg_8xx.h> -#endif /* CONFIG_PPC_8xx */ #define MSR_SF_LG 63 /* Enable 64 bit mode */ #define MSR_ISF_LG 61 /* Interrupt 64b mode valid on 630 */ @@ -748,6 +746,18 @@ #define SPRN_USPRG7 0x107 /* SPRG7 userspace read */ #define SPRN_SRR0 0x01A /* Save/Restore Register 0 */ #define SPRN_SRR1 0x01B /* Save/Restore Register 1 */ + +#ifdef CONFIG_PPC_BOOK3S +/* + * Bits loaded from MSR upon interrupt. + * PPC (64-bit) bits 33-36,42-47 are interrupt dependent, the others are + * loaded from MSR. The exception is that SRESET and MCE do not always load + * bit 62 (RI) from MSR. Don't use PPC_BITMASK for this because 32-bit uses + * it. + */ +#define SRR1_MSR_BITS (~0x783f0000UL) +#endif + #define SRR1_ISI_NOPT 0x40000000 /* ISI: Not found in hash */ #define SRR1_ISI_N_OR_G 0x10000000 /* ISI: Access is no-exec or G */ #define SRR1_ISI_PROT 0x08000000 /* ISI: Other protection fault */ @@ -1370,6 +1380,14 @@ static inline void mtmsr_isync(unsigned long val) #define wrtspr(rn) asm volatile("mtspr " __stringify(rn) ",0" : \ : : "memory") +static inline void wrtee(unsigned long val) +{ + if (__builtin_constant_p(val)) + asm volatile("wrteei %0" : : "i" ((val & MSR_EE) ? 1 : 0) : "memory"); + else + asm volatile("wrtee %0" : : "r" (val) : "memory"); +} + extern unsigned long msr_check_and_set(unsigned long bits); extern bool strict_msr_control; extern void __msr_check_and_clear(unsigned long bits); @@ -1384,19 +1402,9 @@ static inline void msr_check_and_clear(unsigned long bits) #define mftb() ({unsigned long rval; \ asm volatile( \ "90: mfspr %0, %2;\n" \ - "97: cmpwi %0,0;\n" \ - " beq- 90b;\n" \ - "99:\n" \ - ".section __ftr_fixup,\"a\"\n" \ - ".align 3\n" \ - "98:\n" \ - " .8byte %1\n" \ - " .8byte %1\n" \ - " .8byte 97b-98b\n" \ - " .8byte 99b-98b\n" \ - " .8byte 0\n" \ - " .8byte 0\n" \ - ".previous" \ + ASM_FTR_IFSET( \ + "97: cmpwi %0,0;\n" \ + " beq- 90b;\n", "", %1) \ : "=r" (rval) \ : "i" (CPU_FTR_CELL_TB_BUG), "i" (SPRN_TBRL) : "cr0"); \ rval;}) diff --git a/arch/powerpc/include/asm/reg_8xx.h b/arch/powerpc/include/asm/reg_8xx.h index 7192eece6c3e..07df35ee8cbc 100644 --- a/arch/powerpc/include/asm/reg_8xx.h +++ b/arch/powerpc/include/asm/reg_8xx.h @@ -5,8 +5,6 @@ #ifndef _ASM_POWERPC_REG_8xx_H #define _ASM_POWERPC_REG_8xx_H -#include <asm/mmu.h> - /* Cache control on the MPC8xx is provided through some additional * special purpose registers. */ @@ -38,7 +36,9 @@ #define SPRN_CMPF 153 #define SPRN_LCTRL1 156 #define SPRN_LCTRL2 157 +#ifdef CONFIG_PPC_8xx #define SPRN_ICTRL 158 +#endif #define SPRN_BAR 159 /* Commands. Only the first few are available to the instruction cache. diff --git a/arch/powerpc/include/asm/sections.h b/arch/powerpc/include/asm/sections.h index 5a9b6eb651b6..d19871763ed4 100644 --- a/arch/powerpc/include/asm/sections.h +++ b/arch/powerpc/include/asm/sections.h @@ -5,8 +5,22 @@ #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/secure_boot.h b/arch/powerpc/include/asm/secure_boot.h new file mode 100644 index 000000000000..a2ff556916c6 --- /dev/null +++ b/arch/powerpc/include/asm/secure_boot.h @@ -0,0 +1,29 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Secure boot definitions + * + * Copyright (C) 2019 IBM Corporation + * Author: Nayna Jain + */ +#ifndef _ASM_POWER_SECURE_BOOT_H +#define _ASM_POWER_SECURE_BOOT_H + +#ifdef CONFIG_PPC_SECURE_BOOT + +bool is_ppc_secureboot_enabled(void); +bool is_ppc_trustedboot_enabled(void); + +#else + +static inline bool is_ppc_secureboot_enabled(void) +{ + return false; +} + +static inline bool is_ppc_trustedboot_enabled(void) +{ + return false; +} + +#endif +#endif diff --git a/arch/powerpc/include/asm/security_features.h b/arch/powerpc/include/asm/security_features.h index 759597bf0fd8..7c05e95a5c44 100644 --- a/arch/powerpc/include/asm/security_features.h +++ b/arch/powerpc/include/asm/security_features.h @@ -9,7 +9,7 @@ #define _ASM_POWERPC_SECURITY_FEATURES_H -extern unsigned long powerpc_security_features; +extern u64 powerpc_security_features; extern bool rfi_flush; /* These are bit flags */ @@ -24,17 +24,17 @@ void setup_stf_barrier(void); void do_stf_barrier_fixups(enum stf_barrier_type types); void setup_count_cache_flush(void); -static inline void security_ftr_set(unsigned long feature) +static inline void security_ftr_set(u64 feature) { powerpc_security_features |= feature; } -static inline void security_ftr_clear(unsigned long feature) +static inline void security_ftr_clear(u64 feature) { powerpc_security_features &= ~feature; } -static inline bool security_ftr_enabled(unsigned long feature) +static inline bool security_ftr_enabled(u64 feature) { return !!(powerpc_security_features & feature); } @@ -81,6 +81,9 @@ static inline bool security_ftr_enabled(unsigned long feature) // Software required to flush count cache on context switch #define SEC_FTR_FLUSH_COUNT_CACHE 0x0000000000000400ull +// Software required to flush link stack on context switch +#define SEC_FTR_FLUSH_LINK_STACK 0x0000000000001000ull + // Features enabled by default #define SEC_FTR_DEFAULT \ diff --git a/arch/powerpc/include/asm/secvar.h b/arch/powerpc/include/asm/secvar.h new file mode 100644 index 000000000000..4cc35b58b986 --- /dev/null +++ b/arch/powerpc/include/asm/secvar.h @@ -0,0 +1,35 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2019 IBM Corporation + * Author: Nayna Jain + * + * PowerPC secure variable operations. + */ +#ifndef SECVAR_OPS_H +#define SECVAR_OPS_H + +#include <linux/types.h> +#include <linux/errno.h> + +extern const struct secvar_operations *secvar_ops; + +struct secvar_operations { + int (*get)(const char *key, uint64_t key_len, u8 *data, + uint64_t *data_size); + int (*get_next)(const char *key, uint64_t *key_len, + uint64_t keybufsize); + int (*set)(const char *key, uint64_t key_len, u8 *data, + uint64_t data_size); +}; + +#ifdef CONFIG_PPC_SECURE_BOOT + +extern void set_secvar_ops(const struct secvar_operations *ops); + +#else + +static inline void set_secvar_ops(const struct secvar_operations *ops) { } + +#endif + +#endif diff --git a/arch/powerpc/include/asm/ultravisor-api.h b/arch/powerpc/include/asm/ultravisor-api.h index 4fcda1d5793d..b66f6db7be6c 100644 --- a/arch/powerpc/include/asm/ultravisor-api.h +++ b/arch/powerpc/include/asm/ultravisor-api.h @@ -26,8 +26,14 @@ #define UV_WRITE_PATE 0xF104 #define UV_RETURN 0xF11C #define UV_ESM 0xF110 +#define UV_REGISTER_MEM_SLOT 0xF120 +#define UV_UNREGISTER_MEM_SLOT 0xF124 +#define UV_PAGE_IN 0xF128 +#define UV_PAGE_OUT 0xF12C #define UV_SHARE_PAGE 0xF130 #define UV_UNSHARE_PAGE 0xF134 #define UV_UNSHARE_ALL_PAGES 0xF140 +#define UV_PAGE_INVAL 0xF138 +#define UV_SVM_TERMINATE 0xF13C #endif /* _ASM_POWERPC_ULTRAVISOR_API_H */ diff --git a/arch/powerpc/include/asm/ultravisor.h b/arch/powerpc/include/asm/ultravisor.h index b1bc2e043ed4..790b0e63681f 100644 --- a/arch/powerpc/include/asm/ultravisor.h +++ b/arch/powerpc/include/asm/ultravisor.h @@ -46,4 +46,40 @@ static inline int uv_unshare_all_pages(void) return ucall_norets(UV_UNSHARE_ALL_PAGES); } +static inline int uv_page_in(u64 lpid, u64 src_ra, u64 dst_gpa, u64 flags, + u64 page_shift) +{ + return ucall_norets(UV_PAGE_IN, lpid, src_ra, dst_gpa, flags, + page_shift); +} + +static inline int uv_page_out(u64 lpid, u64 dst_ra, u64 src_gpa, u64 flags, + u64 page_shift) +{ + return ucall_norets(UV_PAGE_OUT, lpid, dst_ra, src_gpa, flags, + page_shift); +} + +static inline int uv_register_mem_slot(u64 lpid, u64 start_gpa, u64 size, + u64 flags, u64 slotid) +{ + return ucall_norets(UV_REGISTER_MEM_SLOT, lpid, start_gpa, + size, flags, slotid); +} + +static inline int uv_unregister_mem_slot(u64 lpid, u64 slotid) +{ + return ucall_norets(UV_UNREGISTER_MEM_SLOT, lpid, slotid); +} + +static inline int uv_page_inval(u64 lpid, u64 gpa, u64 page_shift) +{ + return ucall_norets(UV_PAGE_INVAL, lpid, gpa, page_shift); +} + +static inline int uv_svm_terminate(u64 lpid) +{ + return ucall_norets(UV_SVM_TERMINATE, lpid); +} + #endif /* _ASM_POWERPC_ULTRAVISOR_H */ diff --git a/arch/powerpc/include/asm/vdso_datapage.h b/arch/powerpc/include/asm/vdso_datapage.h index c61d59ed3b45..a115970a6809 100644 --- a/arch/powerpc/include/asm/vdso_datapage.h +++ b/arch/powerpc/include/asm/vdso_datapage.h @@ -81,7 +81,8 @@ struct vdso_data { __u32 stamp_sec_fraction; /* fractional seconds of stamp_xtime */ __s32 wtom_clock_nsec; /* Wall to monotonic clock nsec */ __s64 wtom_clock_sec; /* Wall to monotonic clock sec */ - struct timespec stamp_xtime; /* xtime as at tb_orig_stamp */ + __s64 stamp_xtime_sec; /* xtime secs as at tb_orig_stamp */ + __s64 stamp_xtime_nsec; /* xtime nsecs as at tb_orig_stamp */ __u32 syscall_map_64[SYSCALL_MAP_SIZE]; /* map of syscalls */ __u32 syscall_map_32[SYSCALL_MAP_SIZE]; /* map of syscalls */ }; @@ -101,7 +102,8 @@ struct vdso_data { __u32 tz_dsttime; /* Type of dst correction 0x5C */ __s32 wtom_clock_sec; /* Wall to monotonic clock */ __s32 wtom_clock_nsec; - struct timespec stamp_xtime; /* xtime as at tb_orig_stamp */ + __s32 stamp_xtime_sec; /* xtime seconds as at tb_orig_stamp */ + __s32 stamp_xtime_nsec; /* xtime nsecs as at tb_orig_stamp */ __u32 stamp_sec_fraction; /* fractional seconds of stamp_xtime */ __u32 syscall_map_32[SYSCALL_MAP_SIZE]; /* map of syscalls */ __u32 dcache_block_size; /* L1 d-cache block size */ diff --git a/arch/powerpc/include/uapi/asm/kvm.h b/arch/powerpc/include/uapi/asm/kvm.h index b0f72dea8b11..264e266a85bf 100644 --- a/arch/powerpc/include/uapi/asm/kvm.h +++ b/arch/powerpc/include/uapi/asm/kvm.h @@ -667,6 +667,8 @@ struct kvm_ppc_cpu_char { /* PPC64 eXternal Interrupt Controller Specification */ #define KVM_DEV_XICS_GRP_SOURCES 1 /* 64-bit source attributes */ +#define KVM_DEV_XICS_GRP_CTRL 2 +#define KVM_DEV_XICS_NR_SERVERS 1 /* Layout of 64-bit source attribute values */ #define KVM_XICS_DESTINATION_SHIFT 0 @@ -683,6 +685,7 @@ struct kvm_ppc_cpu_char { #define KVM_DEV_XIVE_GRP_CTRL 1 #define KVM_DEV_XIVE_RESET 1 #define KVM_DEV_XIVE_EQ_SYNC 2 +#define KVM_DEV_XIVE_NR_SERVERS 3 #define KVM_DEV_XIVE_GRP_SOURCE 2 /* 64-bit source identifier */ #define KVM_DEV_XIVE_GRP_SOURCE_CONFIG 3 /* 64-bit source identifier */ #define KVM_DEV_XIVE_GRP_EQ_CONFIG 4 /* 64-bit EQ identifier */ diff --git a/arch/powerpc/include/uapi/asm/msgbuf.h b/arch/powerpc/include/uapi/asm/msgbuf.h index 2b1b37797a47..7919b2ba41b5 100644 --- a/arch/powerpc/include/uapi/asm/msgbuf.h +++ b/arch/powerpc/include/uapi/asm/msgbuf.h @@ -2,6 +2,8 @@ #ifndef _ASM_POWERPC_MSGBUF_H #define _ASM_POWERPC_MSGBUF_H +#include <asm/ipcbuf.h> + /* * The msqid64_ds structure for the PowerPC architecture. * Note extra padding because this structure is passed back and forth @@ -11,9 +13,9 @@ struct msqid64_ds { struct ipc64_perm msg_perm; #ifdef __powerpc64__ - __kernel_time_t msg_stime; /* last msgsnd time */ - __kernel_time_t msg_rtime; /* last msgrcv time */ - __kernel_time_t msg_ctime; /* last change time */ + long msg_stime; /* last msgsnd time */ + long msg_rtime; /* last msgrcv time */ + long msg_ctime; /* last change time */ #else unsigned long msg_stime_high; unsigned long msg_stime; /* last msgsnd time */ diff --git a/arch/powerpc/include/uapi/asm/sembuf.h b/arch/powerpc/include/uapi/asm/sembuf.h index 3f60946f77e3..85e96ccb5f0f 100644 --- a/arch/powerpc/include/uapi/asm/sembuf.h +++ b/arch/powerpc/include/uapi/asm/sembuf.h @@ -2,6 +2,8 @@ #ifndef _ASM_POWERPC_SEMBUF_H #define _ASM_POWERPC_SEMBUF_H +#include <asm/ipcbuf.h> + /* * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License @@ -26,8 +28,8 @@ struct semid64_ds { unsigned long sem_ctime_high; unsigned long sem_ctime; /* last change time */ #else - __kernel_time_t sem_otime; /* last semop time */ - __kernel_time_t sem_ctime; /* last change time */ + long sem_otime; /* last semop time */ + long sem_ctime; /* last change time */ #endif unsigned long sem_nsems; /* no. of semaphores in array */ unsigned long __unused3; diff --git a/arch/powerpc/include/uapi/asm/shmbuf.h b/arch/powerpc/include/uapi/asm/shmbuf.h index b591c4d7e4c5..00422b2f3c63 100644 --- a/arch/powerpc/include/uapi/asm/shmbuf.h +++ b/arch/powerpc/include/uapi/asm/shmbuf.h @@ -22,9 +22,9 @@ struct shmid64_ds { struct ipc64_perm shm_perm; /* operation perms */ #ifdef __powerpc64__ - __kernel_time_t shm_atime; /* last attach time */ - __kernel_time_t shm_dtime; /* last detach time */ - __kernel_time_t shm_ctime; /* last change time */ + long shm_atime; /* last attach time */ + long shm_dtime; /* last detach time */ + long shm_ctime; /* last change time */ #else unsigned long shm_atime_high; unsigned long shm_atime; /* last attach time */ diff --git a/arch/powerpc/include/uapi/asm/spu_info.h b/arch/powerpc/include/uapi/asm/spu_info.h index cabfcbba9eac..45f97150587b 100644 --- a/arch/powerpc/include/uapi/asm/spu_info.h +++ b/arch/powerpc/include/uapi/asm/spu_info.h @@ -5,20 +5,6 @@ * (C) Copyright 2006 IBM Corp. * * Author: Dwayne Grant McConnell <decimal@us.ibm.com> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2, or (at your option) - * any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */ #ifndef _UAPI_SPU_INFO_H diff --git a/arch/powerpc/include/uapi/asm/stat.h b/arch/powerpc/include/uapi/asm/stat.h index afd25f2ff4e8..7871055e5e32 100644 --- a/arch/powerpc/include/uapi/asm/stat.h +++ b/arch/powerpc/include/uapi/asm/stat.h @@ -40,7 +40,7 @@ struct stat { uid_t st_uid; gid_t st_gid; unsigned long st_rdev; - off_t st_size; + long st_size; unsigned long st_blksize; unsigned long st_blocks; unsigned long st_atime; diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index a7ca8fe62368..157b0147921f 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -5,9 +5,6 @@ CFLAGS_ptrace.o += -DUTS_MACHINE='"$(UTS_MACHINE)"' -# Disable clang warning for using setjmp without setjmp.h header -CFLAGS_crash.o += $(call cc-disable-warning, builtin-requires-header) - ifdef CONFIG_PPC64 CFLAGS_prom_init.o += $(NO_MINIMAL_TOC) endif @@ -22,6 +19,8 @@ CFLAGS_btext.o += $(DISABLE_LATENT_ENTROPY_PLUGIN) CFLAGS_prom.o += $(DISABLE_LATENT_ENTROPY_PLUGIN) CFLAGS_prom_init.o += $(call cc-option, -fno-stack-protector) +CFLAGS_prom_init.o += -DDISABLE_BRANCH_PROFILING +CFLAGS_prom_init.o += -ffreestanding ifdef CONFIG_FUNCTION_TRACER # Do not trace early boot code @@ -39,7 +38,6 @@ KASAN_SANITIZE_btext.o := n ifdef CONFIG_KASAN CFLAGS_early_32.o += -DDISABLE_BRANCH_PROFILING CFLAGS_cputable.o += -DDISABLE_BRANCH_PROFILING -CFLAGS_prom_init.o += -DDISABLE_BRANCH_PROFILING CFLAGS_btext.o += -DDISABLE_BRANCH_PROFILING endif @@ -78,9 +76,8 @@ obj-$(CONFIG_EEH) += eeh.o eeh_pe.o eeh_dev.o eeh_cache.o \ eeh_driver.o eeh_event.o eeh_sysfs.o obj-$(CONFIG_GENERIC_TBSYNC) += smp-tbsync.o obj-$(CONFIG_CRASH_DUMP) += crash_dump.o -ifneq ($(CONFIG_FA_DUMP)$(CONFIG_PRESERVE_FA_DUMP),) -obj-y += fadump.o -endif +obj-$(CONFIG_FA_DUMP) += fadump.o +obj-$(CONFIG_PRESERVE_FA_DUMP) += fadump.o ifdef CONFIG_PPC32 obj-$(CONFIG_E500) += idle_e500.o endif @@ -126,14 +123,6 @@ pci64-$(CONFIG_PPC64) += pci_dn.o pci-hotplug.o isa-bridge.o obj-$(CONFIG_PCI) += pci_$(BITS).o $(pci64-y) \ pci-common.o pci_of_scan.o obj-$(CONFIG_PCI_MSI) += msi.o -obj-$(CONFIG_KEXEC_CORE) += machine_kexec.o crash.o \ - machine_kexec_$(BITS).o -obj-$(CONFIG_KEXEC_FILE) += machine_kexec_file_$(BITS).o kexec_elf_$(BITS).o -ifdef CONFIG_HAVE_IMA_KEXEC -ifdef CONFIG_IMA -obj-y += ima_kexec.o -endif -endif obj-$(CONFIG_AUDIT) += audit.o obj64-$(CONFIG_AUDIT) += compat_audit.o @@ -161,16 +150,13 @@ ifneq ($(CONFIG_PPC_POWERNV)$(CONFIG_PPC_SVM),) obj-y += ucall.o endif +obj-$(CONFIG_PPC_SECURE_BOOT) += secure_boot.o ima_arch.o secvar-ops.o +obj-$(CONFIG_PPC_SECVAR_SYSFS) += secvar-sysfs.o + # Disable GCOV, KCOV & sanitizers in odd or sensitive code GCOV_PROFILE_prom_init.o := n KCOV_INSTRUMENT_prom_init.o := n UBSAN_SANITIZE_prom_init.o := n -GCOV_PROFILE_machine_kexec_64.o := n -KCOV_INSTRUMENT_machine_kexec_64.o := n -UBSAN_SANITIZE_machine_kexec_64.o := n -GCOV_PROFILE_machine_kexec_32.o := n -KCOV_INSTRUMENT_machine_kexec_32.o := n -UBSAN_SANITIZE_machine_kexec_32.o := n GCOV_PROFILE_kprobes.o := n KCOV_INSTRUMENT_kprobes.o := n UBSAN_SANITIZE_kprobes.o := n diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 484f54dab247..f22bd6d1fe93 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -385,7 +385,8 @@ int main(void) OFFSET(CFG_SYSCALL_MAP32, vdso_data, syscall_map_32); OFFSET(WTOM_CLOCK_SEC, vdso_data, wtom_clock_sec); OFFSET(WTOM_CLOCK_NSEC, vdso_data, wtom_clock_nsec); - OFFSET(STAMP_XTIME, vdso_data, stamp_xtime); + OFFSET(STAMP_XTIME_SEC, vdso_data, stamp_xtime_sec); + OFFSET(STAMP_XTIME_NSEC, vdso_data, stamp_xtime_nsec); OFFSET(STAMP_SEC_FRAC, vdso_data, stamp_sec_fraction); OFFSET(CFG_ICACHE_BLOCKSZ, vdso_data, icache_block_size); OFFSET(CFG_DCACHE_BLOCKSZ, vdso_data, dcache_block_size); @@ -393,20 +394,15 @@ int main(void) OFFSET(CFG_DCACHE_LOGBLOCKSZ, vdso_data, dcache_log_block_size); #ifdef CONFIG_PPC64 OFFSET(CFG_SYSCALL_MAP64, vdso_data, syscall_map_64); - OFFSET(TVAL64_TV_SEC, timeval, tv_sec); - OFFSET(TVAL64_TV_USEC, timeval, tv_usec); + OFFSET(TVAL64_TV_SEC, __kernel_old_timeval, tv_sec); + OFFSET(TVAL64_TV_USEC, __kernel_old_timeval, tv_usec); +#endif + OFFSET(TSPC64_TV_SEC, __kernel_timespec, tv_sec); + OFFSET(TSPC64_TV_NSEC, __kernel_timespec, tv_nsec); OFFSET(TVAL32_TV_SEC, old_timeval32, tv_sec); OFFSET(TVAL32_TV_USEC, old_timeval32, tv_usec); - OFFSET(TSPC64_TV_SEC, timespec, tv_sec); - OFFSET(TSPC64_TV_NSEC, timespec, tv_nsec); OFFSET(TSPC32_TV_SEC, old_timespec32, tv_sec); OFFSET(TSPC32_TV_NSEC, old_timespec32, tv_nsec); -#else - OFFSET(TVAL32_TV_SEC, timeval, tv_sec); - OFFSET(TVAL32_TV_USEC, timeval, tv_usec); - OFFSET(TSPC32_TV_SEC, timespec, tv_sec); - OFFSET(TSPC32_TV_NSEC, timespec, tv_nsec); -#endif /* timeval/timezone offsets for use by vdso */ OFFSET(TZONE_TZ_MINWEST, timezone, tz_minuteswest); OFFSET(TZONE_TZ_DSTTIME, timezone, tz_dsttime); diff --git a/arch/powerpc/kernel/cpu_setup_fsl_booke.S b/arch/powerpc/kernel/cpu_setup_fsl_booke.S index 2b4f3ec0acf7..1d308780e0d3 100644 --- a/arch/powerpc/kernel/cpu_setup_fsl_booke.S +++ b/arch/powerpc/kernel/cpu_setup_fsl_booke.S @@ -231,7 +231,7 @@ _GLOBAL(__setup_cpu_e5500) blr #endif -/* flush L1 date cache, it can apply to e500v2, e500mc and e5500 */ +/* flush L1 data cache, it can apply to e500v2, e500mc and e5500 */ _GLOBAL(flush_dcache_L1) mfmsr r10 wrteei 0 diff --git a/arch/powerpc/kernel/dawr.c b/arch/powerpc/kernel/dawr.c index 5f66b95b6858..cc14aa6c4a1b 100644 --- a/arch/powerpc/kernel/dawr.c +++ b/arch/powerpc/kernel/dawr.c @@ -30,10 +30,10 @@ int set_dawr(struct arch_hw_breakpoint *brk) * DAWR length is stored in field MDR bits 48:53. Matches range in * doublewords (64 bits) baised by -1 eg. 0b000000=1DW and * 0b111111=64DW. - * brk->len is in bytes. + * brk->hw_len is in bytes. * This aligns up to double word size, shifts and does the bias. */ - mrd = ((brk->len + 7) >> 3) - 1; + mrd = ((brk->hw_len + 7) >> 3) - 1; dawrx |= (mrd & 0x3f) << (63 - 53); if (ppc_md.set_dawr) @@ -54,7 +54,7 @@ static ssize_t dawr_write_file_bool(struct file *file, const char __user *user_buf, size_t count, loff_t *ppos) { - struct arch_hw_breakpoint null_brk = {0, 0, 0}; + struct arch_hw_breakpoint null_brk = {0}; size_t rc; /* Send error to user if they hypervisor won't allow us to write DAWR */ diff --git a/arch/powerpc/kernel/early_32.c b/arch/powerpc/kernel/early_32.c index 3482118ffe76..ef2ad4945904 100644 --- a/arch/powerpc/kernel/early_32.c +++ b/arch/powerpc/kernel/early_32.c @@ -19,10 +19,13 @@ */ notrace unsigned long __init early_init(unsigned long dt_ptr) { - unsigned long offset = reloc_offset(); + unsigned long kva, offset = reloc_offset(); + + kva = *PTRRELOC(&kernstart_virt_addr); /* First zero the BSS */ - memset(PTRRELOC(&__bss_start), 0, __bss_stop - __bss_start); + if (kva == KERNELBASE) + memset(PTRRELOC(&__bss_start), 0, __bss_stop - __bss_start); /* * Identify the CPU type and fix up code sections @@ -32,5 +35,5 @@ notrace unsigned long __init early_init(unsigned long dt_ptr) apply_feature_fixups(); - return KERNELBASE + offset; + return kva + offset; } diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index d9279d0ee9f5..3dd1a422fc29 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -1,25 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * PCI Error Recovery Driver for RPA-compliant PPC64 platform. * Copyright IBM Corp. 2004 2005 * Copyright Linas Vepstas <linas@linas.org> 2004, 2005 * - * All rights reserved. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or (at - * your option) any later version. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or - * NON INFRINGEMENT. See the GNU General Public License for more - * details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. - * * Send comments and feedback to Linas Vepstas <linas@austin.ibm.com> */ #include <linux/delay.h> @@ -897,12 +881,12 @@ void eeh_handle_normal_event(struct eeh_pe *pe) /* Log the event */ if (pe->type & EEH_PE_PHB) { - pr_err("EEH: PHB#%x failure detected, location: %s\n", + pr_err("EEH: Recovering PHB#%x, location: %s\n", pe->phb->global_number, eeh_pe_loc_get(pe)); } else { struct eeh_pe *phb_pe = eeh_phb_pe_get(pe->phb); - pr_err("EEH: Frozen PHB#%x-PE#%x detected\n", + pr_err("EEH: Recovering PHB#%x-PE#%x\n", pe->phb->global_number, pe->addr); pr_err("EEH: PE location: %s, PHB location: %s\n", eeh_pe_loc_get(pe), eeh_pe_loc_get(phb_pe)); diff --git a/arch/powerpc/kernel/eeh_sysfs.c b/arch/powerpc/kernel/eeh_sysfs.c index 3fa04dda1737..ab44d965a53c 100644 --- a/arch/powerpc/kernel/eeh_sysfs.c +++ b/arch/powerpc/kernel/eeh_sysfs.c @@ -1,25 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Sysfs entries for PCI Error Recovery for PAPR-compliant platform. * Copyright IBM Corporation 2007 * Copyright Linas Vepstas <linas@austin.ibm.com> 2007 * - * All rights reserved. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or (at - * your option) any later version. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or - * NON INFRINGEMENT. See the GNU General Public License for more - * details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. - * * Send comments and feedback to Linas Vepstas <linas@austin.ibm.com> */ #include <linux/pci.h> diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index 6467bdab8d40..3fd3ef352e3f 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -537,6 +537,7 @@ flush_count_cache: /* Save LR into r9 */ mflr r9 + // Flush the link stack .rept 64 bl .+4 .endr @@ -546,6 +547,11 @@ flush_count_cache: .balign 32 /* Restore LR */ 1: mtlr r9 + + // If we're just flushing the link stack, return here +3: nop + patch_site 3b patch__flush_link_stack_return + li r9,0x7fff mtctr r9 diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S index 829950b96d29..e4076e3c072d 100644 --- a/arch/powerpc/kernel/exceptions-64e.S +++ b/arch/powerpc/kernel/exceptions-64e.S @@ -1346,16 +1346,6 @@ skpinv: addi r6,r6,1 /* Increment */ sync isync -/* - * The mapping only needs to be cache-coherent on SMP, except on - * Freescale e500mc derivatives where it's also needed for coherent DMA. - */ -#if defined(CONFIG_SMP) || defined(CONFIG_PPC_E500MC) -#define M_IF_NEEDED MAS2_M -#else -#define M_IF_NEEDED 0 -#endif - /* 6. Setup KERNELBASE mapping in TLB[0] * * r3 = MAS0 w/TLBSEL & ESEL for the entry we started in @@ -1368,7 +1358,7 @@ skpinv: addi r6,r6,1 /* Increment */ ori r6,r6,(MAS1_TSIZE(BOOK3E_PAGESZ_1GB))@l mtspr SPRN_MAS1,r6 - LOAD_REG_IMMEDIATE(r6, PAGE_OFFSET | M_IF_NEEDED) + LOAD_REG_IMMEDIATE(r6, PAGE_OFFSET | MAS2_M_IF_NEEDED) mtspr SPRN_MAS2,r6 rlwinm r5,r5,0,0,25 diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index d0018dd17e0a..46508b148e16 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -514,7 +514,7 @@ END_FTR_SECTION_NESTED(CPU_FTR_HAS_PPR,CPU_FTR_HAS_PPR,948) * If stack=0, then the stack is already set in r1, and r1 is saved in r10. * PPR save and CPU accounting is not done for the !stack case (XXX why not?) */ -.macro INT_COMMON vec, area, stack, kaup, reconcile, dar, dsisr +.macro INT_COMMON vec, area, stack, kuap, reconcile, dar, dsisr .if \stack andi. r10,r12,MSR_PR /* See if coming from user */ mr r10,r1 /* Save r1 */ @@ -533,7 +533,7 @@ END_FTR_SECTION_NESTED(CPU_FTR_HAS_PPR,CPU_FTR_HAS_PPR,948) std r10,GPR1(r1) /* save r1 in stackframe */ .if \stack - .if \kaup + .if \kuap kuap_save_amr_and_lock r9, r10, cr1, cr0 .endif beq 101f /* if from kernel mode */ @@ -541,7 +541,7 @@ END_FTR_SECTION_NESTED(CPU_FTR_HAS_PPR,CPU_FTR_HAS_PPR,948) SAVE_PPR(\area, r9) 101: .else - .if \kaup + .if \kuap kuap_save_amr_and_lock r9, r10, cr1 .endif .endif diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c index ed59855430b9..ff0114aeba9b 100644 --- a/arch/powerpc/kernel/fadump.c +++ b/arch/powerpc/kernel/fadump.c @@ -1466,16 +1466,15 @@ static void fadump_init_files(void) */ int __init setup_fadump(void) { - if (!fw_dump.fadump_enabled) - return 0; - - if (!fw_dump.fadump_supported) { - printk(KERN_ERR "Firmware-assisted dump is not supported on" - " this hardware\n"); + if (!fw_dump.fadump_supported) return 0; - } + fadump_init_files(); fadump_show_config(); + + if (!fw_dump.fadump_enabled) + return 1; + /* * If dump data is available then see if it is valid and prepare for * saving it to the disk. @@ -1492,8 +1491,6 @@ int __init setup_fadump(void) else if (fw_dump.reserve_dump_area_size) fw_dump.ops->fadump_init_mem_struct(&fw_dump); - fadump_init_files(); - return 1; } subsys_initcall(setup_fadump); diff --git a/arch/powerpc/kernel/fsl_booke_entry_mapping.S b/arch/powerpc/kernel/fsl_booke_entry_mapping.S index ea065282b303..8bccce6544b5 100644 --- a/arch/powerpc/kernel/fsl_booke_entry_mapping.S +++ b/arch/powerpc/kernel/fsl_booke_entry_mapping.S @@ -153,35 +153,24 @@ skpinv: addi r6,r6,1 /* Increment */ tlbivax 0,r9 TLBSYNC -/* - * The mapping only needs to be cache-coherent on SMP, except on - * Freescale e500mc derivatives where it's also needed for coherent DMA. - */ -#if defined(CONFIG_SMP) || defined(CONFIG_PPC_E500MC) -#define M_IF_NEEDED MAS2_M -#else -#define M_IF_NEEDED 0 -#endif - #if defined(ENTRY_MAPPING_BOOT_SETUP) -/* 6. Setup KERNELBASE mapping in TLB1[0] */ +/* 6. Setup kernstart_virt_addr mapping in TLB1[0] */ lis r6,0x1000 /* Set MAS0(TLBSEL) = TLB1(1), ESEL = 0 */ mtspr SPRN_MAS0,r6 lis r6,(MAS1_VALID|MAS1_IPROT)@h ori r6,r6,(MAS1_TSIZE(BOOK3E_PAGESZ_64M))@l mtspr SPRN_MAS1,r6 - lis r6,MAS2_VAL(PAGE_OFFSET, BOOK3E_PAGESZ_64M, M_IF_NEEDED)@h - ori r6,r6,MAS2_VAL(PAGE_OFFSET, BOOK3E_PAGESZ_64M, M_IF_NEEDED)@l + lis r6,MAS2_EPN_MASK(BOOK3E_PAGESZ_64M)@h + ori r6,r6,MAS2_EPN_MASK(BOOK3E_PAGESZ_64M)@l + and r6,r6,r20 + ori r6,r6,MAS2_M_IF_NEEDED@l mtspr SPRN_MAS2,r6 mtspr SPRN_MAS3,r8 tlbwe -/* 7. Jump to KERNELBASE mapping */ - lis r6,(KERNELBASE & ~0xfff)@h - ori r6,r6,(KERNELBASE & ~0xfff)@l - rlwinm r7,r25,0,0x03ffffff - add r6,r7,r6 +/* 7. Jump to kernstart_virt_addr mapping */ + mr r6,r20 #elif defined(ENTRY_MAPPING_KEXEC_SETUP) /* diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S index adf0505dbe02..838d9d4650c7 100644 --- a/arch/powerpc/kernel/head_fsl_booke.S +++ b/arch/powerpc/kernel/head_fsl_booke.S @@ -155,6 +155,8 @@ _ENTRY(_start); */ _ENTRY(__early_start) + LOAD_REG_ADDR_PIC(r20, kernstart_virt_addr) + lwz r20,0(r20) #define ENTRY_MAPPING_BOOT_SETUP #include "fsl_booke_entry_mapping.S" @@ -277,8 +279,8 @@ set_ivor: ori r6, r6, swapper_pg_dir@l lis r5, abatron_pteptrs@h ori r5, r5, abatron_pteptrs@l - lis r4, KERNELBASE@h - ori r4, r4, KERNELBASE@l + lis r3, kernstart_virt_addr@ha + lwz r4, kernstart_virt_addr@l(r3) stw r5, 0(r4) /* Save abatron_pteptrs at a fixed location */ stw r6, 0(r5) @@ -1067,7 +1069,12 @@ __secondary_start: mr r5,r25 /* phys kernel start */ rlwinm r5,r5,0,~0x3ffffff /* aligned 64M */ subf r4,r5,r4 /* memstart_addr - phys kernel start */ - li r5,0 /* no device tree */ + lis r7,KERNELBASE@h + ori r7,r7,KERNELBASE@l + cmpw r20,r7 /* if kernstart_virt_addr != KERNELBASE, randomized */ + beq 2f + li r4,0 +2: li r5,0 /* no device tree */ li r6,0 /* not boot cpu */ bl restore_to_as0 @@ -1115,6 +1122,54 @@ __secondary_hold_acknowledge: #endif /* + * Create a 64M tlb by address and entry + * r3 - entry + * r4 - virtual address + * r5/r6 - physical address + */ +_GLOBAL(create_kaslr_tlb_entry) + lis r7,0x1000 /* Set MAS0(TLBSEL) = 1 */ + rlwimi r7,r3,16,4,15 /* Setup MAS0 = TLBSEL | ESEL(r6) */ + mtspr SPRN_MAS0,r7 /* Write MAS0 */ + + lis r3,(MAS1_VALID|MAS1_IPROT)@h + ori r3,r3,(MAS1_TSIZE(BOOK3E_PAGESZ_64M))@l + mtspr SPRN_MAS1,r3 /* Write MAS1 */ + + lis r3,MAS2_EPN_MASK(BOOK3E_PAGESZ_64M)@h + ori r3,r3,MAS2_EPN_MASK(BOOK3E_PAGESZ_64M)@l + and r3,r3,r4 + ori r3,r3,MAS2_M_IF_NEEDED@l + mtspr SPRN_MAS2,r3 /* Write MAS2(EPN) */ + +#ifdef CONFIG_PHYS_64BIT + ori r8,r6,(MAS3_SW|MAS3_SR|MAS3_SX) + mtspr SPRN_MAS3,r8 /* Write MAS3(RPN) */ + mtspr SPRN_MAS7,r5 +#else + ori r8,r5,(MAS3_SW|MAS3_SR|MAS3_SX) + mtspr SPRN_MAS3,r8 /* Write MAS3(RPN) */ +#endif + + tlbwe /* Write TLB */ + isync + sync + blr + +/* + * Return to the start of the relocated kernel and run again + * r3 - virtual address of fdt + * r4 - entry of the kernel + */ +_GLOBAL(reloc_kernel_entry) + mfmsr r7 + rlwinm r7, r7, 0, ~(MSR_IS | MSR_DS) + + mtspr SPRN_SRR0,r4 + mtspr SPRN_SRR1,r7 + rfi + +/* * Create a tlb entry with the same effective and physical address as * the tlb entry used by the current running code. But set the TS to 1. * Then switch to the address space 1. It will return with the r3 set to diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c index 1007ec36b4cb..58ce3d37c2a3 100644 --- a/arch/powerpc/kernel/hw_breakpoint.c +++ b/arch/powerpc/kernel/hw_breakpoint.c @@ -127,15 +127,58 @@ int arch_bp_generic_fields(int type, int *gen_bp_type) } /* + * Watchpoint match range is always doubleword(8 bytes) aligned on + * powerpc. If the given range is crossing doubleword boundary, we + * need to increase the length such that next doubleword also get + * covered. Ex, + * + * address len = 6 bytes + * |=========. + * |------------v--|------v--------| + * | | | | | | | | | | | | | | | | | + * |---------------|---------------| + * <---8 bytes---> + * + * In this case, we should configure hw as: + * start_addr = address & ~HW_BREAKPOINT_ALIGN + * len = 16 bytes + * + * @start_addr and @end_addr are inclusive. + */ +static int hw_breakpoint_validate_len(struct arch_hw_breakpoint *hw) +{ + u16 max_len = DABR_MAX_LEN; + u16 hw_len; + unsigned long start_addr, end_addr; + + start_addr = hw->address & ~HW_BREAKPOINT_ALIGN; + end_addr = (hw->address + hw->len - 1) | HW_BREAKPOINT_ALIGN; + hw_len = end_addr - start_addr + 1; + + if (dawr_enabled()) { + max_len = DAWR_MAX_LEN; + /* DAWR region can't cross 512 bytes boundary */ + if ((start_addr >> 9) != (end_addr >> 9)) + return -EINVAL; + } + + if (hw_len > max_len) + return -EINVAL; + + hw->hw_len = hw_len; + return 0; +} + +/* * Validate the arch-specific HW Breakpoint register settings */ int hw_breakpoint_arch_parse(struct perf_event *bp, const struct perf_event_attr *attr, struct arch_hw_breakpoint *hw) { - int ret = -EINVAL, length_max; + int ret = -EINVAL; - if (!bp) + if (!bp || !attr->bp_len) return ret; hw->type = HW_BRK_TYPE_TRANSLATE; @@ -155,26 +198,10 @@ int hw_breakpoint_arch_parse(struct perf_event *bp, hw->address = attr->bp_addr; hw->len = attr->bp_len; - /* - * Since breakpoint length can be a maximum of HW_BREAKPOINT_LEN(8) - * and breakpoint addresses are aligned to nearest double-word - * HW_BREAKPOINT_ALIGN by rounding off to the lower address, the - * 'symbolsize' should satisfy the check below. - */ if (!ppc_breakpoint_available()) return -ENODEV; - length_max = 8; /* DABR */ - if (dawr_enabled()) { - length_max = 512 ; /* 64 doublewords */ - /* DAWR region can't cross 512 boundary */ - if ((attr->bp_addr >> 9) != - ((attr->bp_addr + attr->bp_len - 1) >> 9)) - return -EINVAL; - } - if (hw->len > - (length_max - (hw->address & HW_BREAKPOINT_ALIGN))) - return -EINVAL; - return 0; + + return hw_breakpoint_validate_len(hw); } /* @@ -195,33 +222,49 @@ void thread_change_pc(struct task_struct *tsk, struct pt_regs *regs) tsk->thread.last_hit_ubp = NULL; } -static bool is_larx_stcx_instr(struct pt_regs *regs, unsigned int instr) +static bool dar_within_range(unsigned long dar, struct arch_hw_breakpoint *info) { - int ret, type; - struct instruction_op op; + return ((info->address <= dar) && (dar - info->address < info->len)); +} - ret = analyse_instr(&op, regs, instr); - type = GETTYPE(op.type); - return (!ret && (type == LARX || type == STCX)); +static bool +dar_range_overlaps(unsigned long dar, int size, struct arch_hw_breakpoint *info) +{ + return ((dar <= info->address + info->len - 1) && + (dar + size - 1 >= info->address)); } /* * Handle debug exception notifications. */ static bool stepping_handler(struct pt_regs *regs, struct perf_event *bp, - unsigned long addr) + struct arch_hw_breakpoint *info) { unsigned int instr = 0; + int ret, type, size; + struct instruction_op op; + unsigned long addr = info->address; if (__get_user_inatomic(instr, (unsigned int *)regs->nip)) goto fail; - if (is_larx_stcx_instr(regs, instr)) { + ret = analyse_instr(&op, regs, instr); + type = GETTYPE(op.type); + size = GETSIZE(op.type); + + if (!ret && (type == LARX || type == STCX)) { printk_ratelimited("Breakpoint hit on instruction that can't be emulated." " Breakpoint at 0x%lx will be disabled.\n", addr); goto disable; } + /* + * If it's extraneous event, we still need to emulate/single- + * step the instruction, but we don't generate an event. + */ + if (size && !dar_range_overlaps(regs->dar, size, info)) + info->type |= HW_BRK_TYPE_EXTRANEOUS_IRQ; + /* Do not emulate user-space instructions, instead single-step them */ if (user_mode(regs)) { current->thread.last_hit_ubp = bp; @@ -253,7 +296,6 @@ int hw_breakpoint_handler(struct die_args *args) struct perf_event *bp; struct pt_regs *regs = args->regs; struct arch_hw_breakpoint *info; - unsigned long dar = regs->dar; /* Disable breakpoints during exception handling */ hw_breakpoint_disable(); @@ -285,19 +327,14 @@ int hw_breakpoint_handler(struct die_args *args) goto out; } - /* - * Verify if dar lies within the address range occupied by the symbol - * being watched to filter extraneous exceptions. If it doesn't, - * we still need to single-step the instruction, but we don't - * generate an event. - */ info->type &= ~HW_BRK_TYPE_EXTRANEOUS_IRQ; - if (!((bp->attr.bp_addr <= dar) && - (dar - bp->attr.bp_addr < bp->attr.bp_len))) - info->type |= HW_BRK_TYPE_EXTRANEOUS_IRQ; - - if (!IS_ENABLED(CONFIG_PPC_8xx) && !stepping_handler(regs, bp, info->address)) - goto out; + if (IS_ENABLED(CONFIG_PPC_8xx)) { + if (!dar_within_range(regs->dar, info)) + info->type |= HW_BRK_TYPE_EXTRANEOUS_IRQ; + } else { + if (!stepping_handler(regs, bp, info)) + goto out; + } /* * As a policy, the callback is invoked in a 'trigger-after-execute' diff --git a/arch/powerpc/kernel/ima_arch.c b/arch/powerpc/kernel/ima_arch.c new file mode 100644 index 000000000000..e34116255ced --- /dev/null +++ b/arch/powerpc/kernel/ima_arch.c @@ -0,0 +1,78 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2019 IBM Corporation + * Author: Nayna Jain + */ + +#include <linux/ima.h> +#include <asm/secure_boot.h> + +bool arch_ima_get_secureboot(void) +{ + return is_ppc_secureboot_enabled(); +} + +/* + * The "secure_rules" are enabled only on "secureboot" enabled systems. + * These rules verify the file signatures against known good values. + * The "appraise_type=imasig|modsig" option allows the known good signature + * to be stored as an xattr or as an appended signature. + * + * To avoid duplicate signature verification as much as possible, the IMA + * policy rule for module appraisal is added only if CONFIG_MODULE_SIG_FORCE + * is not enabled. + */ +static const char *const secure_rules[] = { + "appraise func=KEXEC_KERNEL_CHECK appraise_flag=check_blacklist appraise_type=imasig|modsig", +#ifndef CONFIG_MODULE_SIG_FORCE + "appraise func=MODULE_CHECK appraise_flag=check_blacklist appraise_type=imasig|modsig", +#endif + NULL +}; + +/* + * The "trusted_rules" are enabled only on "trustedboot" enabled systems. + * These rules add the kexec kernel image and kernel modules file hashes to + * the IMA measurement list. + */ +static const char *const trusted_rules[] = { + "measure func=KEXEC_KERNEL_CHECK", + "measure func=MODULE_CHECK", + NULL +}; + +/* + * The "secure_and_trusted_rules" contains rules for both the secure boot and + * trusted boot. The "template=ima-modsig" option includes the appended + * signature, when available, in the IMA measurement list. + */ +static const char *const secure_and_trusted_rules[] = { + "measure func=KEXEC_KERNEL_CHECK template=ima-modsig", + "measure func=MODULE_CHECK template=ima-modsig", + "appraise func=KEXEC_KERNEL_CHECK appraise_flag=check_blacklist appraise_type=imasig|modsig", +#ifndef CONFIG_MODULE_SIG_FORCE + "appraise func=MODULE_CHECK appraise_flag=check_blacklist appraise_type=imasig|modsig", +#endif + NULL +}; + +/* + * Returns the relevant IMA arch-specific policies based on the system secure + * boot state. + */ +const char *const *arch_get_ima_policy(void) +{ + if (is_ppc_secureboot_enabled()) { + if (IS_ENABLED(CONFIG_MODULE_SIG)) + set_module_sig_enforced(); + + if (is_ppc_trustedboot_enabled()) + return secure_and_trusted_rules; + else + return secure_rules; + } else if (is_ppc_trustedboot_enabled()) { + return trusted_rules; + } + + return NULL; +} diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S index 82df4b09e79f..d80212be8698 100644 --- a/arch/powerpc/kernel/misc_32.S +++ b/arch/powerpc/kernel/misc_32.S @@ -6,11 +6,6 @@ * Largely rewritten by Cort Dougan (cort@cs.nmt.edu) * and Paul Mackerras. * - * kexec bits: - * Copyright (C) 2002-2003 Eric Biederman <ebiederm@xmission.com> - * GameCube/ppc32 port Copyright (C) 2004 Albert Herranz - * PPC44x port. Copyright (C) 2011, IBM Corporation - * Author: Suzuki Poulose <suzuki@in.ibm.com> */ #include <linux/sys.h> @@ -25,7 +20,6 @@ #include <asm/thread_info.h> #include <asm/asm-offsets.h> #include <asm/processor.h> -#include <asm/kexec.h> #include <asm/bug.h> #include <asm/ptrace.h> #include <asm/export.h> @@ -317,126 +311,6 @@ EXPORT_SYMBOL(flush_instruction_cache) #endif /* CONFIG_PPC_8xx */ /* - * Write any modified data cache blocks out to memory - * and invalidate the corresponding instruction cache blocks. - * This is a no-op on the 601. - * - * flush_icache_range(unsigned long start, unsigned long stop) - */ -_GLOBAL(flush_icache_range) -#if defined(CONFIG_PPC_BOOK3S_601) || defined(CONFIG_E200) - PURGE_PREFETCHED_INS - blr /* for 601 and e200, do nothing */ -#else - rlwinm r3,r3,0,0,31 - L1_CACHE_SHIFT - subf r4,r3,r4 - addi r4,r4,L1_CACHE_BYTES - 1 - srwi. r4,r4,L1_CACHE_SHIFT - beqlr - mtctr r4 - mr r6,r3 -1: dcbst 0,r3 - addi r3,r3,L1_CACHE_BYTES - bdnz 1b - sync /* wait for dcbst's to get to ram */ -#ifndef CONFIG_44x - mtctr r4 -2: icbi 0,r6 - addi r6,r6,L1_CACHE_BYTES - bdnz 2b -#else - /* Flash invalidate on 44x because we are passed kmapped addresses and - this doesn't work for userspace pages due to the virtually tagged - icache. Sigh. */ - iccci 0, r0 -#endif - sync /* additional sync needed on g4 */ - isync - blr -#endif -_ASM_NOKPROBE_SYMBOL(flush_icache_range) -EXPORT_SYMBOL(flush_icache_range) - -/* - * Flush a particular page from the data cache to RAM. - * Note: this is necessary because the instruction cache does *not* - * snoop from the data cache. - * This is a no-op on the 601 and e200 which have a unified cache. - * - * void __flush_dcache_icache(void *page) - */ -_GLOBAL(__flush_dcache_icache) -#if defined(CONFIG_PPC_BOOK3S_601) || defined(CONFIG_E200) - PURGE_PREFETCHED_INS - blr -#else - rlwinm r3,r3,0,0,31-PAGE_SHIFT /* Get page base address */ - li r4,PAGE_SIZE/L1_CACHE_BYTES /* Number of lines in a page */ - mtctr r4 - mr r6,r3 -0: dcbst 0,r3 /* Write line to ram */ - addi r3,r3,L1_CACHE_BYTES - bdnz 0b - sync -#ifdef CONFIG_44x - /* We don't flush the icache on 44x. Those have a virtual icache - * and we don't have access to the virtual address here (it's - * not the page vaddr but where it's mapped in user space). The - * flushing of the icache on these is handled elsewhere, when - * a change in the address space occurs, before returning to - * user space - */ -BEGIN_MMU_FTR_SECTION - blr -END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_44x) -#endif /* CONFIG_44x */ - mtctr r4 -1: icbi 0,r6 - addi r6,r6,L1_CACHE_BYTES - bdnz 1b - sync - isync - blr -#endif - -#ifndef CONFIG_BOOKE -/* - * Flush a particular page from the data cache to RAM, identified - * by its physical address. We turn off the MMU so we can just use - * the physical address (this may be a highmem page without a kernel - * mapping). - * - * void __flush_dcache_icache_phys(unsigned long physaddr) - */ -_GLOBAL(__flush_dcache_icache_phys) -#if defined(CONFIG_PPC_BOOK3S_601) || defined(CONFIG_E200) - PURGE_PREFETCHED_INS - blr /* for 601 and e200, do nothing */ -#else - mfmsr r10 - rlwinm r0,r10,0,28,26 /* clear DR */ - mtmsr r0 - isync - rlwinm r3,r3,0,0,31-PAGE_SHIFT /* Get page base address */ - li r4,PAGE_SIZE/L1_CACHE_BYTES /* Number of lines in a page */ - mtctr r4 - mr r6,r3 -0: dcbst 0,r3 /* Write line to ram */ - addi r3,r3,L1_CACHE_BYTES - bdnz 0b - sync - mtctr r4 -1: icbi 0,r6 - addi r6,r6,L1_CACHE_BYTES - bdnz 1b - sync - mtmsr r10 /* restore DR */ - isync - blr -#endif -#endif /* CONFIG_BOOKE */ - -/* * Copy a whole page. We use the dcbz instruction on the destination * to reduce memory traffic (it eliminates the unnecessary reads of * the destination into cache). This requires that the destination @@ -614,488 +488,3 @@ _GLOBAL(start_secondary_resume) */ _GLOBAL(__main) blr - -#ifdef CONFIG_KEXEC_CORE - /* - * Must be relocatable PIC code callable as a C function. - */ - .globl relocate_new_kernel -relocate_new_kernel: - /* r3 = page_list */ - /* r4 = reboot_code_buffer */ - /* r5 = start_address */ - -#ifdef CONFIG_FSL_BOOKE - - mr r29, r3 - mr r30, r4 - mr r31, r5 - -#define ENTRY_MAPPING_KEXEC_SETUP -#include "fsl_booke_entry_mapping.S" -#undef ENTRY_MAPPING_KEXEC_SETUP - - mr r3, r29 - mr r4, r30 - mr r5, r31 - - li r0, 0 -#elif defined(CONFIG_44x) - - /* Save our parameters */ - mr r29, r3 - mr r30, r4 - mr r31, r5 - -#ifdef CONFIG_PPC_47x - /* Check for 47x cores */ - mfspr r3,SPRN_PVR - srwi r3,r3,16 - cmplwi cr0,r3,PVR_476FPE@h - beq setup_map_47x - cmplwi cr0,r3,PVR_476@h - beq setup_map_47x - cmplwi cr0,r3,PVR_476_ISS@h - beq setup_map_47x -#endif /* CONFIG_PPC_47x */ - -/* - * Code for setting up 1:1 mapping for PPC440x for KEXEC - * - * We cannot switch off the MMU on PPC44x. - * So we: - * 1) Invalidate all the mappings except the one we are running from. - * 2) Create a tmp mapping for our code in the other address space(TS) and - * jump to it. Invalidate the entry we started in. - * 3) Create a 1:1 mapping for 0-2GiB in chunks of 256M in original TS. - * 4) Jump to the 1:1 mapping in original TS. - * 5) Invalidate the tmp mapping. - * - * - Based on the kexec support code for FSL BookE - * - */ - - /* - * Load the PID with kernel PID (0). - * Also load our MSR_IS and TID to MMUCR for TLB search. - */ - li r3, 0 - mtspr SPRN_PID, r3 - mfmsr r4 - andi. r4,r4,MSR_IS@l - beq wmmucr - oris r3,r3,PPC44x_MMUCR_STS@h -wmmucr: - mtspr SPRN_MMUCR,r3 - sync - - /* - * Invalidate all the TLB entries except the current entry - * where we are running from - */ - bl 0f /* Find our address */ -0: mflr r5 /* Make it accessible */ - tlbsx r23,0,r5 /* Find entry we are in */ - li r4,0 /* Start at TLB entry 0 */ - li r3,0 /* Set PAGEID inval value */ -1: cmpw r23,r4 /* Is this our entry? */ - beq skip /* If so, skip the inval */ - tlbwe r3,r4,PPC44x_TLB_PAGEID /* If not, inval the entry */ -skip: - addi r4,r4,1 /* Increment */ - cmpwi r4,64 /* Are we done? */ - bne 1b /* If not, repeat */ - isync - - /* Create a temp mapping and jump to it */ - andi. r6, r23, 1 /* Find the index to use */ - addi r24, r6, 1 /* r24 will contain 1 or 2 */ - - mfmsr r9 /* get the MSR */ - rlwinm r5, r9, 27, 31, 31 /* Extract the MSR[IS] */ - xori r7, r5, 1 /* Use the other address space */ - - /* Read the current mapping entries */ - tlbre r3, r23, PPC44x_TLB_PAGEID - tlbre r4, r23, PPC44x_TLB_XLAT - tlbre r5, r23, PPC44x_TLB_ATTRIB - - /* Save our current XLAT entry */ - mr r25, r4 - - /* Extract the TLB PageSize */ - li r10, 1 /* r10 will hold PageSize */ - rlwinm r11, r3, 0, 24, 27 /* bits 24-27 */ - - /* XXX: As of now we use 256M, 4K pages */ - cmpwi r11, PPC44x_TLB_256M - bne tlb_4k - rotlwi r10, r10, 28 /* r10 = 256M */ - b write_out -tlb_4k: - cmpwi r11, PPC44x_TLB_4K - bne default - rotlwi r10, r10, 12 /* r10 = 4K */ - b write_out -default: - rotlwi r10, r10, 10 /* r10 = 1K */ - -write_out: - /* - * Write out the tmp 1:1 mapping for this code in other address space - * Fixup EPN = RPN , TS=other address space - */ - insrwi r3, r7, 1, 23 /* Bit 23 is TS for PAGEID field */ - - /* Write out the tmp mapping entries */ - tlbwe r3, r24, PPC44x_TLB_PAGEID - tlbwe r4, r24, PPC44x_TLB_XLAT - tlbwe r5, r24, PPC44x_TLB_ATTRIB - - subi r11, r10, 1 /* PageOffset Mask = PageSize - 1 */ - not r10, r11 /* Mask for PageNum */ - - /* Switch to other address space in MSR */ - insrwi r9, r7, 1, 26 /* Set MSR[IS] = r7 */ - - bl 1f -1: mflr r8 - addi r8, r8, (2f-1b) /* Find the target offset */ - - /* Jump to the tmp mapping */ - mtspr SPRN_SRR0, r8 - mtspr SPRN_SRR1, r9 - rfi - -2: - /* Invalidate the entry we were executing from */ - li r3, 0 - tlbwe r3, r23, PPC44x_TLB_PAGEID - - /* attribute fields. rwx for SUPERVISOR mode */ - li r5, 0 - ori r5, r5, (PPC44x_TLB_SW | PPC44x_TLB_SR | PPC44x_TLB_SX | PPC44x_TLB_G) - - /* Create 1:1 mapping in 256M pages */ - xori r7, r7, 1 /* Revert back to Original TS */ - - li r8, 0 /* PageNumber */ - li r6, 3 /* TLB Index, start at 3 */ - -next_tlb: - rotlwi r3, r8, 28 /* Create EPN (bits 0-3) */ - mr r4, r3 /* RPN = EPN */ - ori r3, r3, (PPC44x_TLB_VALID | PPC44x_TLB_256M) /* SIZE = 256M, Valid */ - insrwi r3, r7, 1, 23 /* Set TS from r7 */ - - tlbwe r3, r6, PPC44x_TLB_PAGEID /* PageID field : EPN, V, SIZE */ - tlbwe r4, r6, PPC44x_TLB_XLAT /* Address translation : RPN */ - tlbwe r5, r6, PPC44x_TLB_ATTRIB /* Attributes */ - - addi r8, r8, 1 /* Increment PN */ - addi r6, r6, 1 /* Increment TLB Index */ - cmpwi r8, 8 /* Are we done ? */ - bne next_tlb - isync - - /* Jump to the new mapping 1:1 */ - li r9,0 - insrwi r9, r7, 1, 26 /* Set MSR[IS] = r7 */ - - bl 1f -1: mflr r8 - and r8, r8, r11 /* Get our offset within page */ - addi r8, r8, (2f-1b) - - and r5, r25, r10 /* Get our target PageNum */ - or r8, r8, r5 /* Target jump address */ - - mtspr SPRN_SRR0, r8 - mtspr SPRN_SRR1, r9 - rfi -2: - /* Invalidate the tmp entry we used */ - li r3, 0 - tlbwe r3, r24, PPC44x_TLB_PAGEID - sync - b ppc44x_map_done - -#ifdef CONFIG_PPC_47x - - /* 1:1 mapping for 47x */ - -setup_map_47x: - - /* - * Load the kernel pid (0) to PID and also to MMUCR[TID]. - * Also set the MSR IS->MMUCR STS - */ - li r3, 0 - mtspr SPRN_PID, r3 /* Set PID */ - mfmsr r4 /* Get MSR */ - andi. r4, r4, MSR_IS@l /* TS=1? */ - beq 1f /* If not, leave STS=0 */ - oris r3, r3, PPC47x_MMUCR_STS@h /* Set STS=1 */ -1: mtspr SPRN_MMUCR, r3 /* Put MMUCR */ - sync - - /* Find the entry we are running from */ - bl 2f -2: mflr r23 - tlbsx r23, 0, r23 - tlbre r24, r23, 0 /* TLB Word 0 */ - tlbre r25, r23, 1 /* TLB Word 1 */ - tlbre r26, r23, 2 /* TLB Word 2 */ - - - /* - * Invalidates all the tlb entries by writing to 256 RPNs(r4) - * of 4k page size in all 4 ways (0-3 in r3). - * This would invalidate the entire UTLB including the one we are - * running from. However the shadow TLB entries would help us - * to continue the execution, until we flush them (rfi/isync). - */ - addis r3, 0, 0x8000 /* specify the way */ - addi r4, 0, 0 /* TLB Word0 = (EPN=0, VALID = 0) */ - addi r5, 0, 0 - b clear_utlb_entry - - /* Align the loop to speed things up. from head_44x.S */ - .align 6 - -clear_utlb_entry: - - tlbwe r4, r3, 0 - tlbwe r5, r3, 1 - tlbwe r5, r3, 2 - addis r3, r3, 0x2000 /* Increment the way */ - cmpwi r3, 0 - bne clear_utlb_entry - addis r3, 0, 0x8000 - addis r4, r4, 0x100 /* Increment the EPN */ - cmpwi r4, 0 - bne clear_utlb_entry - - /* Create the entries in the other address space */ - mfmsr r5 - rlwinm r7, r5, 27, 31, 31 /* Get the TS (Bit 26) from MSR */ - xori r7, r7, 1 /* r7 = !TS */ - - insrwi r24, r7, 1, 21 /* Change the TS in the saved TLB word 0 */ - - /* - * write out the TLB entries for the tmp mapping - * Use way '0' so that we could easily invalidate it later. - */ - lis r3, 0x8000 /* Way '0' */ - - tlbwe r24, r3, 0 - tlbwe r25, r3, 1 - tlbwe r26, r3, 2 - - /* Update the msr to the new TS */ - insrwi r5, r7, 1, 26 - - bl 1f -1: mflr r6 - addi r6, r6, (2f-1b) - - mtspr SPRN_SRR0, r6 - mtspr SPRN_SRR1, r5 - rfi - - /* - * Now we are in the tmp address space. - * Create a 1:1 mapping for 0-2GiB in the original TS. - */ -2: - li r3, 0 - li r4, 0 /* TLB Word 0 */ - li r5, 0 /* TLB Word 1 */ - li r6, 0 - ori r6, r6, PPC47x_TLB2_S_RWX /* TLB word 2 */ - - li r8, 0 /* PageIndex */ - - xori r7, r7, 1 /* revert back to original TS */ - -write_utlb: - rotlwi r5, r8, 28 /* RPN = PageIndex * 256M */ - /* ERPN = 0 as we don't use memory above 2G */ - - mr r4, r5 /* EPN = RPN */ - ori r4, r4, (PPC47x_TLB0_VALID | PPC47x_TLB0_256M) - insrwi r4, r7, 1, 21 /* Insert the TS to Word 0 */ - - tlbwe r4, r3, 0 /* Write out the entries */ - tlbwe r5, r3, 1 - tlbwe r6, r3, 2 - addi r8, r8, 1 - cmpwi r8, 8 /* Have we completed ? */ - bne write_utlb - - /* make sure we complete the TLB write up */ - isync - - /* - * Prepare to jump to the 1:1 mapping. - * 1) Extract page size of the tmp mapping - * DSIZ = TLB_Word0[22:27] - * 2) Calculate the physical address of the address - * to jump to. - */ - rlwinm r10, r24, 0, 22, 27 - - cmpwi r10, PPC47x_TLB0_4K - bne 0f - li r10, 0x1000 /* r10 = 4k */ - bl 1f - -0: - /* Defaults to 256M */ - lis r10, 0x1000 - - bl 1f -1: mflr r4 - addi r4, r4, (2f-1b) /* virtual address of 2f */ - - subi r11, r10, 1 /* offsetmask = Pagesize - 1 */ - not r10, r11 /* Pagemask = ~(offsetmask) */ - - and r5, r25, r10 /* Physical page */ - and r6, r4, r11 /* offset within the current page */ - - or r5, r5, r6 /* Physical address for 2f */ - - /* Switch the TS in MSR to the original one */ - mfmsr r8 - insrwi r8, r7, 1, 26 - - mtspr SPRN_SRR1, r8 - mtspr SPRN_SRR0, r5 - rfi - -2: - /* Invalidate the tmp mapping */ - lis r3, 0x8000 /* Way '0' */ - - clrrwi r24, r24, 12 /* Clear the valid bit */ - tlbwe r24, r3, 0 - tlbwe r25, r3, 1 - tlbwe r26, r3, 2 - - /* Make sure we complete the TLB write and flush the shadow TLB */ - isync - -#endif - -ppc44x_map_done: - - - /* Restore the parameters */ - mr r3, r29 - mr r4, r30 - mr r5, r31 - - li r0, 0 -#else - li r0, 0 - - /* - * Set Machine Status Register to a known status, - * switch the MMU off and jump to 1: in a single step. - */ - - mr r8, r0 - ori r8, r8, MSR_RI|MSR_ME - mtspr SPRN_SRR1, r8 - addi r8, r4, 1f - relocate_new_kernel - mtspr SPRN_SRR0, r8 - sync - rfi - -1: -#endif - /* from this point address translation is turned off */ - /* and interrupts are disabled */ - - /* set a new stack at the bottom of our page... */ - /* (not really needed now) */ - addi r1, r4, KEXEC_CONTROL_PAGE_SIZE - 8 /* for LR Save+Back Chain */ - stw r0, 0(r1) - - /* Do the copies */ - li r6, 0 /* checksum */ - mr r0, r3 - b 1f - -0: /* top, read another word for the indirection page */ - lwzu r0, 4(r3) - -1: - /* is it a destination page? (r8) */ - rlwinm. r7, r0, 0, 31, 31 /* IND_DESTINATION (1<<0) */ - beq 2f - - rlwinm r8, r0, 0, 0, 19 /* clear kexec flags, page align */ - b 0b - -2: /* is it an indirection page? (r3) */ - rlwinm. r7, r0, 0, 30, 30 /* IND_INDIRECTION (1<<1) */ - beq 2f - - rlwinm r3, r0, 0, 0, 19 /* clear kexec flags, page align */ - subi r3, r3, 4 - b 0b - -2: /* are we done? */ - rlwinm. r7, r0, 0, 29, 29 /* IND_DONE (1<<2) */ - beq 2f - b 3f - -2: /* is it a source page? (r9) */ - rlwinm. r7, r0, 0, 28, 28 /* IND_SOURCE (1<<3) */ - beq 0b - - rlwinm r9, r0, 0, 0, 19 /* clear kexec flags, page align */ - - li r7, PAGE_SIZE / 4 - mtctr r7 - subi r9, r9, 4 - subi r8, r8, 4 -9: - lwzu r0, 4(r9) /* do the copy */ - xor r6, r6, r0 - stwu r0, 4(r8) - dcbst 0, r8 - sync - icbi 0, r8 - bdnz 9b - - addi r9, r9, 4 - addi r8, r8, 4 - b 0b - -3: - - /* To be certain of avoiding problems with self-modifying code - * execute a serializing instruction here. - */ - isync - sync - - mfspr r3, SPRN_PIR /* current core we are running on */ - mr r4, r5 /* load physical address of chunk called */ - - /* jump to the entry point, usually the setup routine */ - mtlr r5 - blrl - -1: b 1b - -relocate_new_kernel_end: - - .globl relocate_new_kernel_size -relocate_new_kernel_size: - .long relocate_new_kernel_end - relocate_new_kernel -#endif diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S index b55a7b4cb543..1864605eca29 100644 --- a/arch/powerpc/kernel/misc_64.S +++ b/arch/powerpc/kernel/misc_64.S @@ -49,108 +49,6 @@ _GLOBAL(call_do_irq) mtlr r0 blr - .section ".toc","aw" -PPC64_CACHES: - .tc ppc64_caches[TC],ppc64_caches - .section ".text" - -/* - * Write any modified data cache blocks out to memory - * and invalidate the corresponding instruction cache blocks. - * - * flush_icache_range(unsigned long start, unsigned long stop) - * - * flush all bytes from start through stop-1 inclusive - */ - -_GLOBAL_TOC(flush_icache_range) -BEGIN_FTR_SECTION - PURGE_PREFETCHED_INS - blr -END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE) -/* - * Flush the data cache to memory - * - * Different systems have different cache line sizes - * and in some cases i-cache and d-cache line sizes differ from - * each other. - */ - ld r10,PPC64_CACHES@toc(r2) - lwz r7,DCACHEL1BLOCKSIZE(r10)/* Get cache block size */ - addi r5,r7,-1 - andc r6,r3,r5 /* round low to line bdy */ - subf r8,r6,r4 /* compute length */ - add r8,r8,r5 /* ensure we get enough */ - lwz r9,DCACHEL1LOGBLOCKSIZE(r10) /* Get log-2 of cache block size */ - srw. r8,r8,r9 /* compute line count */ - beqlr /* nothing to do? */ - mtctr r8 -1: dcbst 0,r6 - add r6,r6,r7 - bdnz 1b - sync - -/* Now invalidate the instruction cache */ - - lwz r7,ICACHEL1BLOCKSIZE(r10) /* Get Icache block size */ - addi r5,r7,-1 - andc r6,r3,r5 /* round low to line bdy */ - subf r8,r6,r4 /* compute length */ - add r8,r8,r5 - lwz r9,ICACHEL1LOGBLOCKSIZE(r10) /* Get log-2 of Icache block size */ - srw. r8,r8,r9 /* compute line count */ - beqlr /* nothing to do? */ - mtctr r8 -2: icbi 0,r6 - add r6,r6,r7 - bdnz 2b - isync - blr -_ASM_NOKPROBE_SYMBOL(flush_icache_range) -EXPORT_SYMBOL(flush_icache_range) - -/* - * Flush a particular page from the data cache to RAM. - * Note: this is necessary because the instruction cache does *not* - * snoop from the data cache. - * - * void __flush_dcache_icache(void *page) - */ -_GLOBAL(__flush_dcache_icache) -/* - * Flush the data cache to memory - * - * Different systems have different cache line sizes - */ - -BEGIN_FTR_SECTION - PURGE_PREFETCHED_INS - blr -END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE) - -/* Flush the dcache */ - ld r7,PPC64_CACHES@toc(r2) - clrrdi r3,r3,PAGE_SHIFT /* Page align */ - lwz r4,DCACHEL1BLOCKSPERPAGE(r7) /* Get # dcache blocks per page */ - lwz r5,DCACHEL1BLOCKSIZE(r7) /* Get dcache block size */ - mr r6,r3 - mtctr r4 -0: dcbst 0,r6 - add r6,r6,r5 - bdnz 0b - sync - -/* Now invalidate the icache */ - - lwz r4,ICACHEL1BLOCKSPERPAGE(r7) /* Get # icache blocks per page */ - lwz r5,ICACHEL1BLOCKSIZE(r7) /* Get icache block size */ - mtctr r4 -1: icbi 0,r3 - add r3,r3,r5 - bdnz 1b - isync - blr - _GLOBAL(__bswapdi2) EXPORT_SYMBOL(__bswapdi2) srdi r8,r3,32 @@ -432,18 +330,13 @@ kexec_create_tlb: rlwimi r9,r10,16,4,15 /* Setup MAS0 = TLBSEL | ESEL(r9) */ /* Set up a temp identity mapping v:0 to p:0 and return to it. */ -#if defined(CONFIG_SMP) || defined(CONFIG_PPC_E500MC) -#define M_IF_NEEDED MAS2_M -#else -#define M_IF_NEEDED 0 -#endif mtspr SPRN_MAS0,r9 lis r9,(MAS1_VALID|MAS1_IPROT)@h ori r9,r9,(MAS1_TSIZE(BOOK3E_PAGESZ_1GB))@l mtspr SPRN_MAS1,r9 - LOAD_REG_IMMEDIATE(r9, 0x0 | M_IF_NEEDED) + LOAD_REG_IMMEDIATE(r9, 0x0 | MAS2_M_IF_NEEDED) mtspr SPRN_MAS2,r9 LOAD_REG_IMMEDIATE(r9, 0x0 | MAS3_SR | MAS3_SW | MAS3_SX) diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 639ceae7da9d..4df94b6e2f32 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -715,6 +715,8 @@ static void set_debug_reg_defaults(struct thread_struct *thread) { thread->hw_brk.address = 0; thread->hw_brk.type = 0; + thread->hw_brk.len = 0; + thread->hw_brk.hw_len = 0; if (ppc_breakpoint_available()) set_breakpoint(&thread->hw_brk); } @@ -816,6 +818,7 @@ static inline bool hw_brk_match(struct arch_hw_breakpoint *a, return false; if (a->len != b->len) return false; + /* no need to check hw_len. it's calculated from address and len */ return true; } diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index a4e7762dd286..577345382b23 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -303,16 +303,24 @@ static char __init *prom_strstr(const char *s1, const char *s2) return NULL; } -static size_t __init prom_strlcpy(char *dest, const char *src, size_t size) -{ - size_t ret = prom_strlen(src); +static size_t __init prom_strlcat(char *dest, const char *src, size_t count) +{ + size_t dsize = prom_strlen(dest); + size_t len = prom_strlen(src); + size_t res = dsize + len; + + /* This would be a bug */ + if (dsize >= count) + return count; + + dest += dsize; + count -= dsize; + if (len >= count) + len = count-1; + memcpy(dest, src, len); + dest[len] = 0; + return res; - if (size) { - size_t len = (ret >= size) ? size - 1 : ret; - memcpy(dest, src, len); - dest[len] = '\0'; - } - return ret; } #ifdef CONFIG_PPC_PSERIES @@ -764,10 +772,14 @@ static void __init early_cmdline_parse(void) prom_cmd_line[0] = 0; p = prom_cmd_line; - if ((long)prom.chosen > 0) + + if (!IS_ENABLED(CONFIG_CMDLINE_FORCE) && (long)prom.chosen > 0) l = prom_getprop(prom.chosen, "bootargs", p, COMMAND_LINE_SIZE-1); - if (IS_ENABLED(CONFIG_CMDLINE_BOOL) && (l <= 0 || p[0] == '\0')) /* dbl check */ - prom_strlcpy(prom_cmd_line, CONFIG_CMDLINE, sizeof(prom_cmd_line)); + + if (IS_ENABLED(CONFIG_CMDLINE_EXTEND) || l <= 0 || p[0] == '\0') + prom_strlcat(prom_cmd_line, " " CONFIG_CMDLINE, + sizeof(prom_cmd_line)); + prom_printf("command line: %s\n", prom_cmd_line); #ifdef CONFIG_PPC64 @@ -1053,7 +1065,7 @@ static const struct ibm_arch_vec ibm_architecture_vec_template __initconst = { .reserved2 = 0, .reserved3 = 0, .subprocessors = 1, - .byte22 = OV5_FEAT(OV5_DRMEM_V2), + .byte22 = OV5_FEAT(OV5_DRMEM_V2) | OV5_FEAT(OV5_DRC_INFO), .intarch = 0, .mmu = 0, .hash_ext = 0, @@ -3249,7 +3261,20 @@ static void setup_secure_guest(unsigned long kbase, unsigned long fdt) /* Switch to secure mode. */ prom_printf("Switching to secure mode.\n"); + /* + * The ultravisor will do an integrity check of the kernel image but we + * relocated it so the check will fail. Restore the original image by + * relocating it back to the kernel virtual base address. + */ + if (IS_ENABLED(CONFIG_RELOCATABLE)) + relocate(KERNELBASE); + ret = enter_secure_mode(kbase, fdt); + + /* Relocate the kernel again. */ + if (IS_ENABLED(CONFIG_RELOCATABLE)) + relocate(kbase); + if (ret != U_SUCCESS) { prom_printf("Returned %d from switching to secure mode.\n", ret); prom_rtas_os_term("Switch to secure mode failed.\n"); diff --git a/arch/powerpc/kernel/prom_init_check.sh b/arch/powerpc/kernel/prom_init_check.sh index 78bab17b1396..b183ab9c5107 100644 --- a/arch/powerpc/kernel/prom_init_check.sh +++ b/arch/powerpc/kernel/prom_init_check.sh @@ -26,7 +26,8 @@ _end enter_prom $MEM_FUNCS reloc_offset __secondary_hold __secondary_hold_acknowledge __secondary_hold_spinloop __start logo_linux_clut224 btext_prepare_BAT reloc_got2 kernstart_addr memstart_addr linux_banner _stext -__prom_init_toc_start __prom_init_toc_end btext_setup_display TOC." +__prom_init_toc_start __prom_init_toc_end btext_setup_display TOC. +relocate" NM="$1" OBJ="$2" diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c index 8c92febf5f44..25c0424e8868 100644 --- a/arch/powerpc/kernel/ptrace.c +++ b/arch/powerpc/kernel/ptrace.c @@ -2425,7 +2425,8 @@ static int ptrace_set_debugreg(struct task_struct *task, unsigned long addr, return -EIO; hw_brk.address = data & (~HW_BRK_TYPE_DABR); hw_brk.type = (data & HW_BRK_TYPE_DABR) | HW_BRK_TYPE_PRIV_ALL; - hw_brk.len = 8; + hw_brk.len = DABR_MAX_LEN; + hw_brk.hw_len = DABR_MAX_LEN; set_bp = (data) && (hw_brk.type & HW_BRK_TYPE_RDWR); #ifdef CONFIG_HAVE_HW_BREAKPOINT bp = thread->ptrace_bps[0]; @@ -2439,6 +2440,7 @@ static int ptrace_set_debugreg(struct task_struct *task, unsigned long addr, if (bp) { attr = bp->attr; attr.bp_addr = hw_brk.address; + attr.bp_len = DABR_MAX_LEN; arch_bp_generic_fields(hw_brk.type, &attr.bp_type); /* Enable breakpoint */ @@ -2456,7 +2458,7 @@ static int ptrace_set_debugreg(struct task_struct *task, unsigned long addr, /* Create a new breakpoint request if one doesn't exist already */ hw_breakpoint_init(&attr); attr.bp_addr = hw_brk.address; - attr.bp_len = 8; + attr.bp_len = DABR_MAX_LEN; arch_bp_generic_fields(hw_brk.type, &attr.bp_type); @@ -2880,18 +2882,14 @@ static long ppc_set_hwdebug(struct task_struct *child, if ((unsigned long)bp_info->addr >= TASK_SIZE) return -EIO; - brk.address = bp_info->addr & ~7UL; + brk.address = bp_info->addr & ~HW_BREAKPOINT_ALIGN; brk.type = HW_BRK_TYPE_TRANSLATE; - brk.len = 8; + brk.len = DABR_MAX_LEN; if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_READ) brk.type |= HW_BRK_TYPE_READ; if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_WRITE) brk.type |= HW_BRK_TYPE_WRITE; #ifdef CONFIG_HAVE_HW_BREAKPOINT - /* - * Check if the request is for 'range' breakpoints. We can - * support it if range < 8 bytes. - */ if (bp_info->addr_mode == PPC_BREAKPOINT_MODE_RANGE_INCLUSIVE) len = bp_info->addr2 - bp_info->addr; else if (bp_info->addr_mode == PPC_BREAKPOINT_MODE_EXACT) @@ -2904,7 +2902,7 @@ static long ppc_set_hwdebug(struct task_struct *child, /* Create a new breakpoint request if one doesn't exist already */ hw_breakpoint_init(&attr); - attr.bp_addr = (unsigned long)bp_info->addr & ~HW_BREAKPOINT_ALIGN; + attr.bp_addr = (unsigned long)bp_info->addr; attr.bp_len = len; arch_bp_generic_fields(brk.type, &attr.bp_type); @@ -3361,6 +3359,12 @@ void do_syscall_trace_leave(struct pt_regs *regs) user_enter(); } +void __init pt_regs_check(void); + +/* + * Dummy function, its purpose is to break the build if struct pt_regs and + * struct user_pt_regs don't match. + */ void __init pt_regs_check(void) { BUILD_BUG_ON(offsetof(struct pt_regs, gpr) != @@ -3398,4 +3402,67 @@ void __init pt_regs_check(void) offsetof(struct user_pt_regs, result)); BUILD_BUG_ON(sizeof(struct user_pt_regs) > sizeof(struct pt_regs)); + + // Now check that the pt_regs offsets match the uapi #defines + #define CHECK_REG(_pt, _reg) \ + BUILD_BUG_ON(_pt != (offsetof(struct user_pt_regs, _reg) / \ + sizeof(unsigned long))); + + CHECK_REG(PT_R0, gpr[0]); + CHECK_REG(PT_R1, gpr[1]); + CHECK_REG(PT_R2, gpr[2]); + CHECK_REG(PT_R3, gpr[3]); + CHECK_REG(PT_R4, gpr[4]); + CHECK_REG(PT_R5, gpr[5]); + CHECK_REG(PT_R6, gpr[6]); + CHECK_REG(PT_R7, gpr[7]); + CHECK_REG(PT_R8, gpr[8]); + CHECK_REG(PT_R9, gpr[9]); + CHECK_REG(PT_R10, gpr[10]); + CHECK_REG(PT_R11, gpr[11]); + CHECK_REG(PT_R12, gpr[12]); + CHECK_REG(PT_R13, gpr[13]); + CHECK_REG(PT_R14, gpr[14]); + CHECK_REG(PT_R15, gpr[15]); + CHECK_REG(PT_R16, gpr[16]); + CHECK_REG(PT_R17, gpr[17]); + CHECK_REG(PT_R18, gpr[18]); + CHECK_REG(PT_R19, gpr[19]); + CHECK_REG(PT_R20, gpr[20]); + CHECK_REG(PT_R21, gpr[21]); + CHECK_REG(PT_R22, gpr[22]); + CHECK_REG(PT_R23, gpr[23]); + CHECK_REG(PT_R24, gpr[24]); + CHECK_REG(PT_R25, gpr[25]); + CHECK_REG(PT_R26, gpr[26]); + CHECK_REG(PT_R27, gpr[27]); + CHECK_REG(PT_R28, gpr[28]); + CHECK_REG(PT_R29, gpr[29]); + CHECK_REG(PT_R30, gpr[30]); + CHECK_REG(PT_R31, gpr[31]); + CHECK_REG(PT_NIP, nip); + CHECK_REG(PT_MSR, msr); + CHECK_REG(PT_ORIG_R3, orig_gpr3); + CHECK_REG(PT_CTR, ctr); + CHECK_REG(PT_LNK, link); + CHECK_REG(PT_XER, xer); + CHECK_REG(PT_CCR, ccr); +#ifdef CONFIG_PPC64 + CHECK_REG(PT_SOFTE, softe); +#else + CHECK_REG(PT_MQ, mq); +#endif + CHECK_REG(PT_TRAP, trap); + CHECK_REG(PT_DAR, dar); + CHECK_REG(PT_DSISR, dsisr); + CHECK_REG(PT_RESULT, result); + #undef CHECK_REG + + BUILD_BUG_ON(PT_REGS_COUNT != sizeof(struct user_pt_regs) / sizeof(unsigned long)); + + /* + * PT_DSCR isn't a real reg, but it's important that it doesn't overlap the + * real registers. + */ + BUILD_BUG_ON(PT_DSCR < sizeof(struct user_pt_regs) / sizeof(unsigned long)); } diff --git a/arch/powerpc/kernel/secure_boot.c b/arch/powerpc/kernel/secure_boot.c new file mode 100644 index 000000000000..4b982324d368 --- /dev/null +++ b/arch/powerpc/kernel/secure_boot.c @@ -0,0 +1,50 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2019 IBM Corporation + * Author: Nayna Jain + */ +#include <linux/types.h> +#include <linux/of.h> +#include <asm/secure_boot.h> + +static struct device_node *get_ppc_fw_sb_node(void) +{ + static const struct of_device_id ids[] = { + { .compatible = "ibm,secureboot", }, + { .compatible = "ibm,secureboot-v1", }, + { .compatible = "ibm,secureboot-v2", }, + {}, + }; + + return of_find_matching_node(NULL, ids); +} + +bool is_ppc_secureboot_enabled(void) +{ + struct device_node *node; + bool enabled = false; + + node = get_ppc_fw_sb_node(); + enabled = of_property_read_bool(node, "os-secureboot-enforcing"); + + of_node_put(node); + + pr_info("Secure boot mode %s\n", enabled ? "enabled" : "disabled"); + + return enabled; +} + +bool is_ppc_trustedboot_enabled(void) +{ + struct device_node *node; + bool enabled = false; + + node = get_ppc_fw_sb_node(); + enabled = of_property_read_bool(node, "trusted-enabled"); + + of_node_put(node); + + pr_info("Trusted boot mode %s\n", enabled ? "enabled" : "disabled"); + + return enabled; +} diff --git a/arch/powerpc/kernel/security.c b/arch/powerpc/kernel/security.c index 7cfcb294b11c..bd70f5be1c27 100644 --- a/arch/powerpc/kernel/security.c +++ b/arch/powerpc/kernel/security.c @@ -16,7 +16,7 @@ #include <asm/setup.h> -unsigned long powerpc_security_features __read_mostly = SEC_FTR_DEFAULT; +u64 powerpc_security_features __read_mostly = SEC_FTR_DEFAULT; enum count_cache_flush_type { COUNT_CACHE_FLUSH_NONE = 0x1, @@ -24,6 +24,7 @@ enum count_cache_flush_type { COUNT_CACHE_FLUSH_HW = 0x4, }; static enum count_cache_flush_type count_cache_flush_type = COUNT_CACHE_FLUSH_NONE; +static bool link_stack_flush_enabled; bool barrier_nospec_enabled; static bool no_nospec; @@ -94,13 +95,14 @@ static int barrier_nospec_get(void *data, u64 *val) return 0; } -DEFINE_SIMPLE_ATTRIBUTE(fops_barrier_nospec, - barrier_nospec_get, barrier_nospec_set, "%llu\n"); +DEFINE_DEBUGFS_ATTRIBUTE(fops_barrier_nospec, barrier_nospec_get, + barrier_nospec_set, "%llu\n"); static __init int barrier_nospec_debugfs_init(void) { - debugfs_create_file("barrier_nospec", 0600, powerpc_debugfs_root, NULL, - &fops_barrier_nospec); + debugfs_create_file_unsafe("barrier_nospec", 0600, + powerpc_debugfs_root, NULL, + &fops_barrier_nospec); return 0; } device_initcall(barrier_nospec_debugfs_init); @@ -108,7 +110,7 @@ device_initcall(barrier_nospec_debugfs_init); static __init int security_feature_debugfs_init(void) { debugfs_create_x64("security_features", 0400, powerpc_debugfs_root, - (u64 *)&powerpc_security_features); + &powerpc_security_features); return 0; } device_initcall(security_feature_debugfs_init); @@ -141,32 +143,33 @@ ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, cha thread_priv = security_ftr_enabled(SEC_FTR_L1D_THREAD_PRIV); - if (rfi_flush || thread_priv) { + if (rfi_flush) { struct seq_buf s; seq_buf_init(&s, buf, PAGE_SIZE - 1); - seq_buf_printf(&s, "Mitigation: "); - - if (rfi_flush) - seq_buf_printf(&s, "RFI Flush"); - - if (rfi_flush && thread_priv) - seq_buf_printf(&s, ", "); - + seq_buf_printf(&s, "Mitigation: RFI Flush"); if (thread_priv) - seq_buf_printf(&s, "L1D private per thread"); + seq_buf_printf(&s, ", L1D private per thread"); seq_buf_printf(&s, "\n"); return s.len; } + if (thread_priv) + return sprintf(buf, "Vulnerable: L1D private per thread\n"); + if (!security_ftr_enabled(SEC_FTR_L1D_FLUSH_HV) && !security_ftr_enabled(SEC_FTR_L1D_FLUSH_PR)) return sprintf(buf, "Not affected\n"); return sprintf(buf, "Vulnerable\n"); } + +ssize_t cpu_show_l1tf(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_meltdown(dev, attr, buf); +} #endif ssize_t cpu_show_spectre_v1(struct device *dev, struct device_attribute *attr, char *buf) @@ -212,11 +215,19 @@ ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr, c if (ccd) seq_buf_printf(&s, "Indirect branch cache disabled"); + + if (link_stack_flush_enabled) + seq_buf_printf(&s, ", Software link stack flush"); + } else if (count_cache_flush_type != COUNT_CACHE_FLUSH_NONE) { seq_buf_printf(&s, "Mitigation: Software count cache flush"); if (count_cache_flush_type == COUNT_CACHE_FLUSH_HW) seq_buf_printf(&s, " (hardware accelerated)"); + + if (link_stack_flush_enabled) + seq_buf_printf(&s, ", Software link stack flush"); + } else if (btb_flush_enabled) { seq_buf_printf(&s, "Mitigation: Branch predictor state flush"); } else { @@ -367,28 +378,61 @@ static int stf_barrier_get(void *data, u64 *val) return 0; } -DEFINE_SIMPLE_ATTRIBUTE(fops_stf_barrier, stf_barrier_get, stf_barrier_set, "%llu\n"); +DEFINE_DEBUGFS_ATTRIBUTE(fops_stf_barrier, stf_barrier_get, stf_barrier_set, + "%llu\n"); static __init int stf_barrier_debugfs_init(void) { - debugfs_create_file("stf_barrier", 0600, powerpc_debugfs_root, NULL, &fops_stf_barrier); + debugfs_create_file_unsafe("stf_barrier", 0600, powerpc_debugfs_root, + NULL, &fops_stf_barrier); return 0; } device_initcall(stf_barrier_debugfs_init); #endif /* CONFIG_DEBUG_FS */ +static void no_count_cache_flush(void) +{ + count_cache_flush_type = COUNT_CACHE_FLUSH_NONE; + pr_info("count-cache-flush: software flush disabled.\n"); +} + static void toggle_count_cache_flush(bool enable) { - if (!enable || !security_ftr_enabled(SEC_FTR_FLUSH_COUNT_CACHE)) { + if (!security_ftr_enabled(SEC_FTR_FLUSH_COUNT_CACHE) && + !security_ftr_enabled(SEC_FTR_FLUSH_LINK_STACK)) + enable = false; + + if (!enable) { patch_instruction_site(&patch__call_flush_count_cache, PPC_INST_NOP); - count_cache_flush_type = COUNT_CACHE_FLUSH_NONE; - pr_info("count-cache-flush: software flush disabled.\n"); +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE + patch_instruction_site(&patch__call_kvm_flush_link_stack, PPC_INST_NOP); +#endif + pr_info("link-stack-flush: software flush disabled.\n"); + link_stack_flush_enabled = false; + no_count_cache_flush(); return; } + // This enables the branch from _switch to flush_count_cache patch_branch_site(&patch__call_flush_count_cache, (u64)&flush_count_cache, BRANCH_SET_LINK); +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE + // This enables the branch from guest_exit_cont to kvm_flush_link_stack + patch_branch_site(&patch__call_kvm_flush_link_stack, + (u64)&kvm_flush_link_stack, BRANCH_SET_LINK); +#endif + + pr_info("link-stack-flush: software flush enabled.\n"); + link_stack_flush_enabled = true; + + // If we just need to flush the link stack, patch an early return + if (!security_ftr_enabled(SEC_FTR_FLUSH_COUNT_CACHE)) { + patch_instruction_site(&patch__flush_link_stack_return, PPC_INST_BLR); + no_count_cache_flush(); + return; + } + if (!security_ftr_enabled(SEC_FTR_BCCTR_FLUSH_ASSIST)) { count_cache_flush_type = COUNT_CACHE_FLUSH_SW; pr_info("count-cache-flush: full software flush sequence enabled.\n"); @@ -407,11 +451,20 @@ void setup_count_cache_flush(void) if (no_spectrev2 || cpu_mitigations_off()) { if (security_ftr_enabled(SEC_FTR_BCCTRL_SERIALISED) || security_ftr_enabled(SEC_FTR_COUNT_CACHE_DISABLED)) - pr_warn("Spectre v2 mitigations not under software control, can't disable\n"); + pr_warn("Spectre v2 mitigations not fully under software control, can't disable\n"); enable = false; } + /* + * There's no firmware feature flag/hypervisor bit to tell us we need to + * flush the link stack on context switch. So we set it here if we see + * either of the Spectre v2 mitigations that aim to protect userspace. + */ + if (security_ftr_enabled(SEC_FTR_COUNT_CACHE_DISABLED) || + security_ftr_enabled(SEC_FTR_FLUSH_COUNT_CACHE)) + security_ftr_set(SEC_FTR_FLUSH_LINK_STACK); + toggle_count_cache_flush(enable); } @@ -442,13 +495,14 @@ static int count_cache_flush_get(void *data, u64 *val) return 0; } -DEFINE_SIMPLE_ATTRIBUTE(fops_count_cache_flush, count_cache_flush_get, - count_cache_flush_set, "%llu\n"); +DEFINE_DEBUGFS_ATTRIBUTE(fops_count_cache_flush, count_cache_flush_get, + count_cache_flush_set, "%llu\n"); static __init int count_cache_flush_debugfs_init(void) { - debugfs_create_file("count_cache_flush", 0600, powerpc_debugfs_root, - NULL, &fops_count_cache_flush); + debugfs_create_file_unsafe("count_cache_flush", 0600, + powerpc_debugfs_root, NULL, + &fops_count_cache_flush); return 0; } device_initcall(count_cache_flush_debugfs_init); diff --git a/arch/powerpc/kernel/secvar-ops.c b/arch/powerpc/kernel/secvar-ops.c new file mode 100644 index 000000000000..6a29777d6a2d --- /dev/null +++ b/arch/powerpc/kernel/secvar-ops.c @@ -0,0 +1,17 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2019 IBM Corporation + * Author: Nayna Jain + * + * This file initializes secvar operations for PowerPC Secureboot + */ + +#include <linux/cache.h> +#include <asm/secvar.h> + +const struct secvar_operations *secvar_ops __ro_after_init; + +void set_secvar_ops(const struct secvar_operations *ops) +{ + secvar_ops = ops; +} diff --git a/arch/powerpc/kernel/secvar-sysfs.c b/arch/powerpc/kernel/secvar-sysfs.c new file mode 100644 index 000000000000..a0a78aba2083 --- /dev/null +++ b/arch/powerpc/kernel/secvar-sysfs.c @@ -0,0 +1,248 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Copyright (C) 2019 IBM Corporation <nayna@linux.ibm.com> + * + * This code exposes secure variables to user via sysfs + */ + +#define pr_fmt(fmt) "secvar-sysfs: "fmt + +#include <linux/slab.h> +#include <linux/compat.h> +#include <linux/string.h> +#include <linux/of.h> +#include <asm/secvar.h> + +#define NAME_MAX_SIZE 1024 + +static struct kobject *secvar_kobj; +static struct kset *secvar_kset; + +static ssize_t format_show(struct kobject *kobj, struct kobj_attribute *attr, + char *buf) +{ + ssize_t rc = 0; + struct device_node *node; + const char *format; + + node = of_find_compatible_node(NULL, NULL, "ibm,secvar-backend"); + if (!of_device_is_available(node)) + return -ENODEV; + + rc = of_property_read_string(node, "format", &format); + if (rc) + return rc; + + rc = sprintf(buf, "%s\n", format); + + of_node_put(node); + + return rc; +} + + +static ssize_t size_show(struct kobject *kobj, struct kobj_attribute *attr, + char *buf) +{ + uint64_t dsize; + int rc; + + rc = secvar_ops->get(kobj->name, strlen(kobj->name) + 1, NULL, &dsize); + if (rc) { + pr_err("Error retrieving %s variable size %d\n", kobj->name, + rc); + return rc; + } + + return sprintf(buf, "%llu\n", dsize); +} + +static ssize_t data_read(struct file *filep, struct kobject *kobj, + struct bin_attribute *attr, char *buf, loff_t off, + size_t count) +{ + uint64_t dsize; + char *data; + int rc; + + rc = secvar_ops->get(kobj->name, strlen(kobj->name) + 1, NULL, &dsize); + if (rc) { + pr_err("Error getting %s variable size %d\n", kobj->name, rc); + return rc; + } + pr_debug("dsize is %llu\n", dsize); + + data = kzalloc(dsize, GFP_KERNEL); + if (!data) + return -ENOMEM; + + rc = secvar_ops->get(kobj->name, strlen(kobj->name) + 1, data, &dsize); + if (rc) { + pr_err("Error getting %s variable %d\n", kobj->name, rc); + goto data_fail; + } + + rc = memory_read_from_buffer(buf, count, &off, data, dsize); + +data_fail: + kfree(data); + return rc; +} + +static ssize_t update_write(struct file *filep, struct kobject *kobj, + struct bin_attribute *attr, char *buf, loff_t off, + size_t count) +{ + int rc; + + pr_debug("count is %ld\n", count); + rc = secvar_ops->set(kobj->name, strlen(kobj->name) + 1, buf, count); + if (rc) { + pr_err("Error setting the %s variable %d\n", kobj->name, rc); + return rc; + } + + return count; +} + +static struct kobj_attribute format_attr = __ATTR_RO(format); + +static struct kobj_attribute size_attr = __ATTR_RO(size); + +static struct bin_attribute data_attr = __BIN_ATTR_RO(data, 0); + +static struct bin_attribute update_attr = __BIN_ATTR_WO(update, 0); + +static struct bin_attribute *secvar_bin_attrs[] = { + &data_attr, + &update_attr, + NULL, +}; + +static struct attribute *secvar_attrs[] = { + &size_attr.attr, + NULL, +}; + +static const struct attribute_group secvar_attr_group = { + .attrs = secvar_attrs, + .bin_attrs = secvar_bin_attrs, +}; +__ATTRIBUTE_GROUPS(secvar_attr); + +static struct kobj_type secvar_ktype = { + .sysfs_ops = &kobj_sysfs_ops, + .default_groups = secvar_attr_groups, +}; + +static int update_kobj_size(void) +{ + + struct device_node *node; + u64 varsize; + int rc = 0; + + node = of_find_compatible_node(NULL, NULL, "ibm,secvar-backend"); + if (!of_device_is_available(node)) { + rc = -ENODEV; + goto out; + } + + rc = of_property_read_u64(node, "max-var-size", &varsize); + if (rc) + goto out; + + data_attr.size = varsize; + update_attr.size = varsize; + +out: + of_node_put(node); + + return rc; +} + +static int secvar_sysfs_load(void) +{ + char *name; + uint64_t namesize = 0; + struct kobject *kobj; + int rc; + + name = kzalloc(NAME_MAX_SIZE, GFP_KERNEL); + if (!name) + return -ENOMEM; + + do { + rc = secvar_ops->get_next(name, &namesize, NAME_MAX_SIZE); + if (rc) { + if (rc != -ENOENT) + pr_err("error getting secvar from firmware %d\n", + rc); + break; + } + + kobj = kzalloc(sizeof(*kobj), GFP_KERNEL); + if (!kobj) { + rc = -ENOMEM; + break; + } + + kobject_init(kobj, &secvar_ktype); + + rc = kobject_add(kobj, &secvar_kset->kobj, "%s", name); + if (rc) { + pr_warn("kobject_add error %d for attribute: %s\n", rc, + name); + kobject_put(kobj); + kobj = NULL; + } + + if (kobj) + kobject_uevent(kobj, KOBJ_ADD); + + } while (!rc); + + kfree(name); + return rc; +} + +static int secvar_sysfs_init(void) +{ + int rc; + + if (!secvar_ops) { + pr_warn("secvar: failed to retrieve secvar operations.\n"); + return -ENODEV; + } + + secvar_kobj = kobject_create_and_add("secvar", firmware_kobj); + if (!secvar_kobj) { + pr_err("secvar: Failed to create firmware kobj\n"); + return -ENOMEM; + } + + rc = sysfs_create_file(secvar_kobj, &format_attr.attr); + if (rc) { + kobject_put(secvar_kobj); + return -ENOMEM; + } + + secvar_kset = kset_create_and_add("vars", NULL, secvar_kobj); + if (!secvar_kset) { + pr_err("secvar: sysfs kobject registration failed.\n"); + kobject_put(secvar_kobj); + return -ENOMEM; + } + + rc = update_kobj_size(); + if (rc) { + pr_err("Cannot read the size of the attribute\n"); + return rc; + } + + secvar_sysfs_load(); + + return 0; +} + +late_initcall(secvar_sysfs_init); diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index 25aaa3903000..488f1eecc0de 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -715,8 +715,28 @@ static struct notifier_block ppc_panic_block = { .priority = INT_MIN /* may not return; must be done last */ }; +/* + * Dump out kernel offset information on panic. + */ +static int dump_kernel_offset(struct notifier_block *self, unsigned long v, + void *p) +{ + pr_emerg("Kernel Offset: 0x%lx from 0x%lx\n", + kaslr_offset(), KERNELBASE); + + return 0; +} + +static struct notifier_block kernel_offset_notifier = { + .notifier_call = dump_kernel_offset +}; + void __init setup_panic(void) { + if (IS_ENABLED(CONFIG_RANDOMIZE_BASE) && kaslr_offset() > 0) + atomic_notifier_chain_register(&panic_notifier_list, + &kernel_offset_notifier); + /* PPC64 always does a hard irq disable in its panic handler */ if (!IS_ENABLED(CONFIG_PPC64) && !ppc_md.panic) return; diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c index a7541edf0cdb..dcffe927f5b9 100644 --- a/arch/powerpc/kernel/setup_32.c +++ b/arch/powerpc/kernel/setup_32.c @@ -44,6 +44,7 @@ #include <asm/asm-prototypes.h> #include <asm/kdump.h> #include <asm/feature-fixups.h> +#include <asm/early_ioremap.h> #include "setup.h" @@ -80,6 +81,8 @@ notrace void __init machine_init(u64 dt_ptr) /* Configure static keys first, now that we're relocated. */ setup_feature_keys(); + early_ioremap_setup(); + /* Enable early debugging if any specified (see udbg.h) */ udbg_early_init(); diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 44b4c432a273..6104917a282d 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -65,15 +65,10 @@ #include <asm/hw_irq.h> #include <asm/feature-fixups.h> #include <asm/kup.h> +#include <asm/early_ioremap.h> #include "setup.h" -#ifdef DEBUG -#define DBG(fmt...) udbg_printf(fmt) -#else -#define DBG(fmt...) -#endif - int spinning_secondaries; u64 ppc64_pft_size; @@ -305,7 +300,7 @@ void __init early_setup(unsigned long dt_ptr) /* Enable early debugging if any specified (see udbg.h) */ udbg_early_init(); - DBG(" -> early_setup(), dt_ptr: 0x%lx\n", dt_ptr); + udbg_printf(" -> %s(), dt_ptr: 0x%lx\n", __func__, dt_ptr); /* * Do early initialization using the flattened device @@ -338,6 +333,8 @@ void __init early_setup(unsigned long dt_ptr) apply_feature_fixups(); setup_feature_keys(); + early_ioremap_setup(); + /* Initialize the hash table or TLB handling */ early_init_mmu(); @@ -362,11 +359,11 @@ void __init early_setup(unsigned long dt_ptr) */ this_cpu_enable_ftrace(); - DBG(" <- early_setup()\n"); + udbg_printf(" <- %s()\n", __func__); #ifdef CONFIG_PPC_EARLY_DEBUG_BOOTX /* - * This needs to be done *last* (after the above DBG() even) + * This needs to be done *last* (after the above udbg_printf() even) * * Right after we return from this function, we turn on the MMU * which means the real-mode access trick that btext does will @@ -436,8 +433,6 @@ void smp_release_cpus(void) if (!use_spinloop()) return; - DBG(" -> smp_release_cpus()\n"); - /* All secondary cpus are spinning on a common spinloop, release them * all now so they can start to spin on their individual paca * spinloops. For non SMP kernels, the secondary cpus never get out @@ -456,9 +451,7 @@ void smp_release_cpus(void) break; udelay(1); } - DBG("spinning_secondaries = %d\n", spinning_secondaries); - - DBG(" <- smp_release_cpus()\n"); + pr_debug("spinning_secondaries = %d\n", spinning_secondaries); } #endif /* CONFIG_SMP || CONFIG_KEXEC_CORE */ @@ -551,8 +544,6 @@ void __init initialize_cache_info(void) struct device_node *cpu = NULL, *l2, *l3 = NULL; u32 pvr; - DBG(" -> initialize_cache_info()\n"); - /* * All shipping POWER8 machines have a firmware bug that * puts incorrect information in the device-tree. This will @@ -576,10 +567,10 @@ void __init initialize_cache_info(void) */ if (cpu) { if (!parse_cache_info(cpu, false, &ppc64_caches.l1d)) - DBG("Argh, can't find dcache properties !\n"); + pr_warn("Argh, can't find dcache properties !\n"); if (!parse_cache_info(cpu, true, &ppc64_caches.l1i)) - DBG("Argh, can't find icache properties !\n"); + pr_warn("Argh, can't find icache properties !\n"); /* * Try to find the L2 and L3 if any. Assume they are @@ -604,8 +595,6 @@ void __init initialize_cache_info(void) cur_cpu_spec->dcache_bsize = dcache_bsize; cur_cpu_spec->icache_bsize = icache_bsize; - - DBG(" <- initialize_cache_info()\n"); } /* diff --git a/arch/powerpc/kernel/syscalls.c b/arch/powerpc/kernel/syscalls.c index 3bfb3888e897..078608ec2e92 100644 --- a/arch/powerpc/kernel/syscalls.c +++ b/arch/powerpc/kernel/syscalls.c @@ -79,7 +79,7 @@ SYSCALL_DEFINE6(mmap, unsigned long, addr, size_t, len, * sys_select() with the appropriate args. -- Cort */ int -ppc_select(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp, struct timeval __user *tvp) +ppc_select(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp, struct __kernel_old_timeval __user *tvp) { if ( (unsigned long)n >= 4096 ) { @@ -89,7 +89,7 @@ ppc_select(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp, s || __get_user(inp, ((fd_set __user * __user *)(buffer+1))) || __get_user(outp, ((fd_set __user * __user *)(buffer+2))) || __get_user(exp, ((fd_set __user * __user *)(buffer+3))) - || __get_user(tvp, ((struct timeval __user * __user *)(buffer+4)))) + || __get_user(tvp, ((struct __kernel_old_timeval __user * __user *)(buffer+4)))) return -EFAULT; } return sys_select(n, inp, outp, exp, tvp); diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index 694522308cd5..2d13cea13954 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -232,7 +232,7 @@ static u64 scan_dispatch_log(u64 stop_tb) * Accumulate stolen time by scanning the dispatch trace log. * Called on entry from user mode. */ -void accumulate_stolen_time(void) +void notrace accumulate_stolen_time(void) { u64 sst, ust; unsigned long save_irq_soft_mask = irq_soft_mask_return(); @@ -338,7 +338,7 @@ static unsigned long vtime_delta(struct task_struct *tsk, return stime; } -void vtime_account_system(struct task_struct *tsk) +void vtime_account_kernel(struct task_struct *tsk) { unsigned long stime, stime_scaled, steal_time; struct cpu_accounting_data *acct = get_accounting(tsk); @@ -366,7 +366,7 @@ void vtime_account_system(struct task_struct *tsk) #endif } } -EXPORT_SYMBOL_GPL(vtime_account_system); +EXPORT_SYMBOL_GPL(vtime_account_kernel); void vtime_account_idle(struct task_struct *tsk) { @@ -395,7 +395,7 @@ static void vtime_flush_scaled(struct task_struct *tsk, /* * Account the whole cputime accumulated in the paca * Must be called with interrupts disabled. - * Assumes that vtime_account_system/idle() has been called + * Assumes that vtime_account_kernel/idle() has been called * recently (i.e. since the last entry from usermode) so that * get_paca()->user_time_scaled is up to date. */ @@ -885,7 +885,7 @@ static notrace u64 timebase_read(struct clocksource *cs) void update_vsyscall(struct timekeeper *tk) { - struct timespec xt; + struct timespec64 xt; struct clocksource *clock = tk->tkr_mono.clock; u32 mult = tk->tkr_mono.mult; u32 shift = tk->tkr_mono.shift; @@ -957,7 +957,8 @@ void update_vsyscall(struct timekeeper *tk) vdso_data->tb_to_xs = new_tb_to_xs; vdso_data->wtom_clock_sec = tk->wall_to_monotonic.tv_sec; vdso_data->wtom_clock_nsec = tk->wall_to_monotonic.tv_nsec; - vdso_data->stamp_xtime = xt; + vdso_data->stamp_xtime_sec = xt.tv_sec; + vdso_data->stamp_xtime_nsec = xt.tv_nsec; vdso_data->stamp_sec_fraction = frac_sec; smp_wmb(); ++(vdso_data->tb_update_count); diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index 82f43535e686..014ff0701f24 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -250,15 +250,22 @@ static void oops_end(unsigned long flags, struct pt_regs *regs, } NOKPROBE_SYMBOL(oops_end); +static char *get_mmu_str(void) +{ + if (early_radix_enabled()) + return " MMU=Radix"; + if (early_mmu_has_feature(MMU_FTR_HPTE_TABLE)) + return " MMU=Hash"; + return ""; +} + static int __die(const char *str, struct pt_regs *regs, long err) { printk("Oops: %s, sig: %ld [#%d]\n", str, err, ++die_counter); - printk("%s PAGE_SIZE=%luK%s%s%s%s%s%s%s %s\n", + printk("%s PAGE_SIZE=%luK%s%s%s%s%s%s %s\n", IS_ENABLED(CONFIG_CPU_LITTLE_ENDIAN) ? "LE" : "BE", - PAGE_SIZE / 1024, - early_radix_enabled() ? " MMU=Radix" : "", - early_mmu_has_feature(MMU_FTR_HPTE_TABLE) ? " MMU=Hash" : "", + PAGE_SIZE / 1024, get_mmu_str(), IS_ENABLED(CONFIG_PREEMPT) ? " PREEMPT" : "", IS_ENABLED(CONFIG_SMP) ? " SMP" : "", IS_ENABLED(CONFIG_SMP) ? (" NR_CPUS=" __stringify(NR_CPUS)) : "", diff --git a/arch/powerpc/kernel/udbg.c b/arch/powerpc/kernel/udbg.c index a384e7c8b01c..01595e8cafe7 100644 --- a/arch/powerpc/kernel/udbg.c +++ b/arch/powerpc/kernel/udbg.c @@ -120,13 +120,15 @@ int udbg_write(const char *s, int n) #define UDBG_BUFSIZE 256 void udbg_printf(const char *fmt, ...) { - char buf[UDBG_BUFSIZE]; - va_list args; + if (udbg_putc) { + char buf[UDBG_BUFSIZE]; + va_list args; - va_start(args, fmt); - vsnprintf(buf, UDBG_BUFSIZE, fmt, args); - udbg_puts(buf); - va_end(args); + va_start(args, fmt); + vsnprintf(buf, UDBG_BUFSIZE, fmt, args); + udbg_puts(buf); + va_end(args); + } } void __init udbg_progress(char *s, unsigned short hex) diff --git a/arch/powerpc/kernel/vdso32/gettimeofday.S b/arch/powerpc/kernel/vdso32/gettimeofday.S index becd9f8767ed..c8e6902cb01b 100644 --- a/arch/powerpc/kernel/vdso32/gettimeofday.S +++ b/arch/powerpc/kernel/vdso32/gettimeofday.S @@ -15,10 +15,8 @@ /* Offset for the low 32-bit part of a field of long type */ #ifdef CONFIG_PPC64 #define LOPART 4 -#define TSPEC_TV_SEC TSPC64_TV_SEC+LOPART #else #define LOPART 0 -#define TSPEC_TV_SEC TSPC32_TV_SEC #endif .text @@ -192,7 +190,7 @@ V_FUNCTION_BEGIN(__kernel_time) bl __get_datapage@local mr r9, r3 /* datapage ptr in r9 */ - lwz r3,STAMP_XTIME+TSPEC_TV_SEC(r9) + lwz r3,STAMP_XTIME_SEC+LOPART(r9) cmplwi r11,0 /* check if t is NULL */ beq 2f @@ -268,7 +266,7 @@ __do_get_tspec: * as a 32.32 fixed-point number in r3 and r4. * Load & add the xtime stamp. */ - lwz r5,STAMP_XTIME+TSPEC_TV_SEC(r9) + lwz r5,STAMP_XTIME_SEC+LOPART(r9) lwz r6,STAMP_SEC_FRAC(r9) addc r4,r4,r6 adde r3,r3,r5 diff --git a/arch/powerpc/kernel/vdso64/cacheflush.S b/arch/powerpc/kernel/vdso64/cacheflush.S index 3f92561a64c4..526f5ba2593e 100644 --- a/arch/powerpc/kernel/vdso64/cacheflush.S +++ b/arch/powerpc/kernel/vdso64/cacheflush.S @@ -35,7 +35,7 @@ V_FUNCTION_BEGIN(__kernel_sync_dicache) subf r8,r6,r4 /* compute length */ add r8,r8,r5 /* ensure we get enough */ lwz r9,CFG_DCACHE_LOGBLOCKSZ(r10) - srw. r8,r8,r9 /* compute line count */ + srd. r8,r8,r9 /* compute line count */ crclr cr0*4+so beqlr /* nothing to do? */ mtctr r8 @@ -52,7 +52,7 @@ V_FUNCTION_BEGIN(__kernel_sync_dicache) subf r8,r6,r4 /* compute length */ add r8,r8,r5 lwz r9,CFG_ICACHE_LOGBLOCKSZ(r10) - srw. r8,r8,r9 /* compute line count */ + srd. r8,r8,r9 /* compute line count */ crclr cr0*4+so beqlr /* nothing to do? */ mtctr r8 diff --git a/arch/powerpc/kernel/vdso64/gettimeofday.S b/arch/powerpc/kernel/vdso64/gettimeofday.S index 07bfe33fe874..1f24e411af80 100644 --- a/arch/powerpc/kernel/vdso64/gettimeofday.S +++ b/arch/powerpc/kernel/vdso64/gettimeofday.S @@ -116,8 +116,8 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime) * CLOCK_REALTIME_COARSE, below values are needed for MONOTONIC_COARSE * too */ - ld r4,STAMP_XTIME+TSPC64_TV_SEC(r3) - ld r5,STAMP_XTIME+TSPC64_TV_NSEC(r3) + ld r4,STAMP_XTIME_SEC(r3) + ld r5,STAMP_XTIME_NSEC(r3) bne cr6,75f /* CLOCK_MONOTONIC_COARSE */ @@ -220,7 +220,7 @@ V_FUNCTION_BEGIN(__kernel_time) mr r11,r3 /* r11 holds t */ bl V_LOCAL_FUNC(__get_datapage) - ld r4,STAMP_XTIME+TSPC64_TV_SEC(r3) + ld r4,STAMP_XTIME_SEC(r3) cmpldi r11,0 /* check if t is NULL */ beq 2f @@ -265,7 +265,7 @@ V_FUNCTION_BEGIN(__do_get_tspec) mulhdu r6,r6,r5 /* in units of 2^-32 seconds */ /* Add stamp since epoch */ - ld r4,STAMP_XTIME+TSPC64_TV_SEC(r3) + ld r4,STAMP_XTIME_SEC(r3) lwz r5,STAMP_SEC_FRAC(r3) or r0,r4,r5 or r0,r0,r6 diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index 060a1acd7c6d..8834220036a5 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -6,6 +6,8 @@ #endif #define BSS_FIRST_SECTIONS *(.bss.prominit) +#define EMITS_PT_NOTE +#define RO_EXCEPTION_TABLE_ALIGN 0 #include <asm/page.h> #include <asm-generic/vmlinux.lds.h> @@ -18,22 +20,8 @@ ENTRY(_stext) PHDRS { - kernel PT_LOAD FLAGS(7); /* RWX */ - notes PT_NOTE FLAGS(0); - dummy PT_NOTE FLAGS(0); - - /* binutils < 2.18 has a bug that makes it misbehave when taking an - ELF file with all segments at load address 0 as input. This - happens when running "strip" on vmlinux, because of the AT() magic - in this linker script. People using GCC >= 4.2 won't run into - this problem, because the "build-id" support will put some data - into the "notes" segment (at a non-zero load address). - - To work around this, we force some data into both the "dummy" - segment and the kernel segment, so the dummy segment will get a - non-zero load address. It's not enough to always create the - "notes" segment, since if nothing gets assigned to it, its load - address will be zero. */ + text PT_LOAD FLAGS(7); /* RWX */ + note PT_NOTE FLAGS(0); } #ifdef CONFIG_PPC64 @@ -77,7 +65,7 @@ SECTIONS #else /* !CONFIG_PPC64 */ HEAD_TEXT #endif - } :kernel + } :text __head_end = .; @@ -126,7 +114,7 @@ SECTIONS __got2_end = .; #endif /* CONFIG_PPC32 */ - } :kernel + } :text . = ALIGN(ETEXT_ALIGN_SIZE); _etext = .; @@ -175,17 +163,6 @@ SECTIONS __stop__btb_flush_fixup = .; } #endif - EXCEPTION_TABLE(0) - - NOTES :kernel :notes - - /* The dummy segment contents for the bug workaround mentioned above - near PHDRS. */ - .dummy : AT(ADDR(.dummy) - LOAD_OFFSET) { - LONG(0) - LONG(0) - LONG(0) - } :kernel :dummy /* * Init sections discarded at runtime @@ -200,7 +177,7 @@ SECTIONS #ifdef CONFIG_PPC64 *(.tramp.ftrace.init); #endif - } :kernel + } :text /* .exit.text is discarded at runtime, not link time, * to deal with references from __bug_table diff --git a/arch/powerpc/kexec/Makefile b/arch/powerpc/kexec/Makefile new file mode 100644 index 000000000000..378f6108a414 --- /dev/null +++ b/arch/powerpc/kexec/Makefile @@ -0,0 +1,25 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# Makefile for the linux kernel. +# + +# Avoid clang warnings around longjmp/setjmp declarations +CFLAGS_crash.o += -ffreestanding + +obj-y += core.o crash.o core_$(BITS).o + +obj-$(CONFIG_PPC32) += relocate_32.o + +obj-$(CONFIG_KEXEC_FILE) += file_load.o elf_$(BITS).o + +ifdef CONFIG_HAVE_IMA_KEXEC +ifdef CONFIG_IMA +obj-y += ima.o +endif +endif + + +# Disable GCOV, KCOV & sanitizers in odd or sensitive code +GCOV_PROFILE_core_$(BITS).o := n +KCOV_INSTRUMENT_core_$(BITS).o := n +UBSAN_SANITIZE_core_$(BITS).o := n diff --git a/arch/powerpc/kernel/machine_kexec.c b/arch/powerpc/kexec/core.c index c4ed328a7b96..078fe3d76feb 100644 --- a/arch/powerpc/kernel/machine_kexec.c +++ b/arch/powerpc/kexec/core.c @@ -86,6 +86,7 @@ void arch_crash_save_vmcoreinfo(void) VMCOREINFO_STRUCT_SIZE(mmu_psize_def); VMCOREINFO_OFFSET(mmu_psize_def, shift); #endif + vmcoreinfo_append_str("KERNELOFFSET=%lx\n", kaslr_offset()); } /* diff --git a/arch/powerpc/kernel/machine_kexec_32.c b/arch/powerpc/kexec/core_32.c index bf9f1f906d64..bf9f1f906d64 100644 --- a/arch/powerpc/kernel/machine_kexec_32.c +++ b/arch/powerpc/kexec/core_32.c diff --git a/arch/powerpc/kernel/machine_kexec_64.c b/arch/powerpc/kexec/core_64.c index 04a7cba58eff..04a7cba58eff 100644 --- a/arch/powerpc/kernel/machine_kexec_64.c +++ b/arch/powerpc/kexec/core_64.c diff --git a/arch/powerpc/kernel/crash.c b/arch/powerpc/kexec/crash.c index d488311efab1..d488311efab1 100644 --- a/arch/powerpc/kernel/crash.c +++ b/arch/powerpc/kexec/crash.c diff --git a/arch/powerpc/kernel/kexec_elf_64.c b/arch/powerpc/kexec/elf_64.c index 3072fd6dbe94..3072fd6dbe94 100644 --- a/arch/powerpc/kernel/kexec_elf_64.c +++ b/arch/powerpc/kexec/elf_64.c diff --git a/arch/powerpc/kernel/machine_kexec_file_64.c b/arch/powerpc/kexec/file_load.c index 143c91724617..143c91724617 100644 --- a/arch/powerpc/kernel/machine_kexec_file_64.c +++ b/arch/powerpc/kexec/file_load.c diff --git a/arch/powerpc/kernel/ima_kexec.c b/arch/powerpc/kexec/ima.c index 720e50e490b6..720e50e490b6 100644 --- a/arch/powerpc/kernel/ima_kexec.c +++ b/arch/powerpc/kexec/ima.c diff --git a/arch/powerpc/kexec/relocate_32.S b/arch/powerpc/kexec/relocate_32.S new file mode 100644 index 000000000000..61946c19e07c --- /dev/null +++ b/arch/powerpc/kexec/relocate_32.S @@ -0,0 +1,500 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * This file contains kexec low-level functions. + * + * Copyright (C) 2002-2003 Eric Biederman <ebiederm@xmission.com> + * GameCube/ppc32 port Copyright (C) 2004 Albert Herranz + * PPC44x port. Copyright (C) 2011, IBM Corporation + * Author: Suzuki Poulose <suzuki@in.ibm.com> + */ + +#include <asm/reg.h> +#include <asm/page.h> +#include <asm/mmu.h> +#include <asm/ppc_asm.h> +#include <asm/kexec.h> + + .text + + /* + * Must be relocatable PIC code callable as a C function. + */ + .globl relocate_new_kernel +relocate_new_kernel: + /* r3 = page_list */ + /* r4 = reboot_code_buffer */ + /* r5 = start_address */ + +#ifdef CONFIG_FSL_BOOKE + + mr r29, r3 + mr r30, r4 + mr r31, r5 + +#define ENTRY_MAPPING_KEXEC_SETUP +#include <kernel/fsl_booke_entry_mapping.S> +#undef ENTRY_MAPPING_KEXEC_SETUP + + mr r3, r29 + mr r4, r30 + mr r5, r31 + + li r0, 0 +#elif defined(CONFIG_44x) + + /* Save our parameters */ + mr r29, r3 + mr r30, r4 + mr r31, r5 + +#ifdef CONFIG_PPC_47x + /* Check for 47x cores */ + mfspr r3,SPRN_PVR + srwi r3,r3,16 + cmplwi cr0,r3,PVR_476FPE@h + beq setup_map_47x + cmplwi cr0,r3,PVR_476@h + beq setup_map_47x + cmplwi cr0,r3,PVR_476_ISS@h + beq setup_map_47x +#endif /* CONFIG_PPC_47x */ + +/* + * Code for setting up 1:1 mapping for PPC440x for KEXEC + * + * We cannot switch off the MMU on PPC44x. + * So we: + * 1) Invalidate all the mappings except the one we are running from. + * 2) Create a tmp mapping for our code in the other address space(TS) and + * jump to it. Invalidate the entry we started in. + * 3) Create a 1:1 mapping for 0-2GiB in chunks of 256M in original TS. + * 4) Jump to the 1:1 mapping in original TS. + * 5) Invalidate the tmp mapping. + * + * - Based on the kexec support code for FSL BookE + * + */ + + /* + * Load the PID with kernel PID (0). + * Also load our MSR_IS and TID to MMUCR for TLB search. + */ + li r3, 0 + mtspr SPRN_PID, r3 + mfmsr r4 + andi. r4,r4,MSR_IS@l + beq wmmucr + oris r3,r3,PPC44x_MMUCR_STS@h +wmmucr: + mtspr SPRN_MMUCR,r3 + sync + + /* + * Invalidate all the TLB entries except the current entry + * where we are running from + */ + bl 0f /* Find our address */ +0: mflr r5 /* Make it accessible */ + tlbsx r23,0,r5 /* Find entry we are in */ + li r4,0 /* Start at TLB entry 0 */ + li r3,0 /* Set PAGEID inval value */ +1: cmpw r23,r4 /* Is this our entry? */ + beq skip /* If so, skip the inval */ + tlbwe r3,r4,PPC44x_TLB_PAGEID /* If not, inval the entry */ +skip: + addi r4,r4,1 /* Increment */ + cmpwi r4,64 /* Are we done? */ + bne 1b /* If not, repeat */ + isync + + /* Create a temp mapping and jump to it */ + andi. r6, r23, 1 /* Find the index to use */ + addi r24, r6, 1 /* r24 will contain 1 or 2 */ + + mfmsr r9 /* get the MSR */ + rlwinm r5, r9, 27, 31, 31 /* Extract the MSR[IS] */ + xori r7, r5, 1 /* Use the other address space */ + + /* Read the current mapping entries */ + tlbre r3, r23, PPC44x_TLB_PAGEID + tlbre r4, r23, PPC44x_TLB_XLAT + tlbre r5, r23, PPC44x_TLB_ATTRIB + + /* Save our current XLAT entry */ + mr r25, r4 + + /* Extract the TLB PageSize */ + li r10, 1 /* r10 will hold PageSize */ + rlwinm r11, r3, 0, 24, 27 /* bits 24-27 */ + + /* XXX: As of now we use 256M, 4K pages */ + cmpwi r11, PPC44x_TLB_256M + bne tlb_4k + rotlwi r10, r10, 28 /* r10 = 256M */ + b write_out +tlb_4k: + cmpwi r11, PPC44x_TLB_4K + bne default + rotlwi r10, r10, 12 /* r10 = 4K */ + b write_out +default: + rotlwi r10, r10, 10 /* r10 = 1K */ + +write_out: + /* + * Write out the tmp 1:1 mapping for this code in other address space + * Fixup EPN = RPN , TS=other address space + */ + insrwi r3, r7, 1, 23 /* Bit 23 is TS for PAGEID field */ + + /* Write out the tmp mapping entries */ + tlbwe r3, r24, PPC44x_TLB_PAGEID + tlbwe r4, r24, PPC44x_TLB_XLAT + tlbwe r5, r24, PPC44x_TLB_ATTRIB + + subi r11, r10, 1 /* PageOffset Mask = PageSize - 1 */ + not r10, r11 /* Mask for PageNum */ + + /* Switch to other address space in MSR */ + insrwi r9, r7, 1, 26 /* Set MSR[IS] = r7 */ + + bl 1f +1: mflr r8 + addi r8, r8, (2f-1b) /* Find the target offset */ + + /* Jump to the tmp mapping */ + mtspr SPRN_SRR0, r8 + mtspr SPRN_SRR1, r9 + rfi + +2: + /* Invalidate the entry we were executing from */ + li r3, 0 + tlbwe r3, r23, PPC44x_TLB_PAGEID + + /* attribute fields. rwx for SUPERVISOR mode */ + li r5, 0 + ori r5, r5, (PPC44x_TLB_SW | PPC44x_TLB_SR | PPC44x_TLB_SX | PPC44x_TLB_G) + + /* Create 1:1 mapping in 256M pages */ + xori r7, r7, 1 /* Revert back to Original TS */ + + li r8, 0 /* PageNumber */ + li r6, 3 /* TLB Index, start at 3 */ + +next_tlb: + rotlwi r3, r8, 28 /* Create EPN (bits 0-3) */ + mr r4, r3 /* RPN = EPN */ + ori r3, r3, (PPC44x_TLB_VALID | PPC44x_TLB_256M) /* SIZE = 256M, Valid */ + insrwi r3, r7, 1, 23 /* Set TS from r7 */ + + tlbwe r3, r6, PPC44x_TLB_PAGEID /* PageID field : EPN, V, SIZE */ + tlbwe r4, r6, PPC44x_TLB_XLAT /* Address translation : RPN */ + tlbwe r5, r6, PPC44x_TLB_ATTRIB /* Attributes */ + + addi r8, r8, 1 /* Increment PN */ + addi r6, r6, 1 /* Increment TLB Index */ + cmpwi r8, 8 /* Are we done ? */ + bne next_tlb + isync + + /* Jump to the new mapping 1:1 */ + li r9,0 + insrwi r9, r7, 1, 26 /* Set MSR[IS] = r7 */ + + bl 1f +1: mflr r8 + and r8, r8, r11 /* Get our offset within page */ + addi r8, r8, (2f-1b) + + and r5, r25, r10 /* Get our target PageNum */ + or r8, r8, r5 /* Target jump address */ + + mtspr SPRN_SRR0, r8 + mtspr SPRN_SRR1, r9 + rfi +2: + /* Invalidate the tmp entry we used */ + li r3, 0 + tlbwe r3, r24, PPC44x_TLB_PAGEID + sync + b ppc44x_map_done + +#ifdef CONFIG_PPC_47x + + /* 1:1 mapping for 47x */ + +setup_map_47x: + + /* + * Load the kernel pid (0) to PID and also to MMUCR[TID]. + * Also set the MSR IS->MMUCR STS + */ + li r3, 0 + mtspr SPRN_PID, r3 /* Set PID */ + mfmsr r4 /* Get MSR */ + andi. r4, r4, MSR_IS@l /* TS=1? */ + beq 1f /* If not, leave STS=0 */ + oris r3, r3, PPC47x_MMUCR_STS@h /* Set STS=1 */ +1: mtspr SPRN_MMUCR, r3 /* Put MMUCR */ + sync + + /* Find the entry we are running from */ + bl 2f +2: mflr r23 + tlbsx r23, 0, r23 + tlbre r24, r23, 0 /* TLB Word 0 */ + tlbre r25, r23, 1 /* TLB Word 1 */ + tlbre r26, r23, 2 /* TLB Word 2 */ + + + /* + * Invalidates all the tlb entries by writing to 256 RPNs(r4) + * of 4k page size in all 4 ways (0-3 in r3). + * This would invalidate the entire UTLB including the one we are + * running from. However the shadow TLB entries would help us + * to continue the execution, until we flush them (rfi/isync). + */ + addis r3, 0, 0x8000 /* specify the way */ + addi r4, 0, 0 /* TLB Word0 = (EPN=0, VALID = 0) */ + addi r5, 0, 0 + b clear_utlb_entry + + /* Align the loop to speed things up. from head_44x.S */ + .align 6 + +clear_utlb_entry: + + tlbwe r4, r3, 0 + tlbwe r5, r3, 1 + tlbwe r5, r3, 2 + addis r3, r3, 0x2000 /* Increment the way */ + cmpwi r3, 0 + bne clear_utlb_entry + addis r3, 0, 0x8000 + addis r4, r4, 0x100 /* Increment the EPN */ + cmpwi r4, 0 + bne clear_utlb_entry + + /* Create the entries in the other address space */ + mfmsr r5 + rlwinm r7, r5, 27, 31, 31 /* Get the TS (Bit 26) from MSR */ + xori r7, r7, 1 /* r7 = !TS */ + + insrwi r24, r7, 1, 21 /* Change the TS in the saved TLB word 0 */ + + /* + * write out the TLB entries for the tmp mapping + * Use way '0' so that we could easily invalidate it later. + */ + lis r3, 0x8000 /* Way '0' */ + + tlbwe r24, r3, 0 + tlbwe r25, r3, 1 + tlbwe r26, r3, 2 + + /* Update the msr to the new TS */ + insrwi r5, r7, 1, 26 + + bl 1f +1: mflr r6 + addi r6, r6, (2f-1b) + + mtspr SPRN_SRR0, r6 + mtspr SPRN_SRR1, r5 + rfi + + /* + * Now we are in the tmp address space. + * Create a 1:1 mapping for 0-2GiB in the original TS. + */ +2: + li r3, 0 + li r4, 0 /* TLB Word 0 */ + li r5, 0 /* TLB Word 1 */ + li r6, 0 + ori r6, r6, PPC47x_TLB2_S_RWX /* TLB word 2 */ + + li r8, 0 /* PageIndex */ + + xori r7, r7, 1 /* revert back to original TS */ + +write_utlb: + rotlwi r5, r8, 28 /* RPN = PageIndex * 256M */ + /* ERPN = 0 as we don't use memory above 2G */ + + mr r4, r5 /* EPN = RPN */ + ori r4, r4, (PPC47x_TLB0_VALID | PPC47x_TLB0_256M) + insrwi r4, r7, 1, 21 /* Insert the TS to Word 0 */ + + tlbwe r4, r3, 0 /* Write out the entries */ + tlbwe r5, r3, 1 + tlbwe r6, r3, 2 + addi r8, r8, 1 + cmpwi r8, 8 /* Have we completed ? */ + bne write_utlb + + /* make sure we complete the TLB write up */ + isync + + /* + * Prepare to jump to the 1:1 mapping. + * 1) Extract page size of the tmp mapping + * DSIZ = TLB_Word0[22:27] + * 2) Calculate the physical address of the address + * to jump to. + */ + rlwinm r10, r24, 0, 22, 27 + + cmpwi r10, PPC47x_TLB0_4K + bne 0f + li r10, 0x1000 /* r10 = 4k */ + bl 1f + +0: + /* Defaults to 256M */ + lis r10, 0x1000 + + bl 1f +1: mflr r4 + addi r4, r4, (2f-1b) /* virtual address of 2f */ + + subi r11, r10, 1 /* offsetmask = Pagesize - 1 */ + not r10, r11 /* Pagemask = ~(offsetmask) */ + + and r5, r25, r10 /* Physical page */ + and r6, r4, r11 /* offset within the current page */ + + or r5, r5, r6 /* Physical address for 2f */ + + /* Switch the TS in MSR to the original one */ + mfmsr r8 + insrwi r8, r7, 1, 26 + + mtspr SPRN_SRR1, r8 + mtspr SPRN_SRR0, r5 + rfi + +2: + /* Invalidate the tmp mapping */ + lis r3, 0x8000 /* Way '0' */ + + clrrwi r24, r24, 12 /* Clear the valid bit */ + tlbwe r24, r3, 0 + tlbwe r25, r3, 1 + tlbwe r26, r3, 2 + + /* Make sure we complete the TLB write and flush the shadow TLB */ + isync + +#endif + +ppc44x_map_done: + + + /* Restore the parameters */ + mr r3, r29 + mr r4, r30 + mr r5, r31 + + li r0, 0 +#else + li r0, 0 + + /* + * Set Machine Status Register to a known status, + * switch the MMU off and jump to 1: in a single step. + */ + + mr r8, r0 + ori r8, r8, MSR_RI|MSR_ME + mtspr SPRN_SRR1, r8 + addi r8, r4, 1f - relocate_new_kernel + mtspr SPRN_SRR0, r8 + sync + rfi + +1: +#endif + /* from this point address translation is turned off */ + /* and interrupts are disabled */ + + /* set a new stack at the bottom of our page... */ + /* (not really needed now) */ + addi r1, r4, KEXEC_CONTROL_PAGE_SIZE - 8 /* for LR Save+Back Chain */ + stw r0, 0(r1) + + /* Do the copies */ + li r6, 0 /* checksum */ + mr r0, r3 + b 1f + +0: /* top, read another word for the indirection page */ + lwzu r0, 4(r3) + +1: + /* is it a destination page? (r8) */ + rlwinm. r7, r0, 0, 31, 31 /* IND_DESTINATION (1<<0) */ + beq 2f + + rlwinm r8, r0, 0, 0, 19 /* clear kexec flags, page align */ + b 0b + +2: /* is it an indirection page? (r3) */ + rlwinm. r7, r0, 0, 30, 30 /* IND_INDIRECTION (1<<1) */ + beq 2f + + rlwinm r3, r0, 0, 0, 19 /* clear kexec flags, page align */ + subi r3, r3, 4 + b 0b + +2: /* are we done? */ + rlwinm. r7, r0, 0, 29, 29 /* IND_DONE (1<<2) */ + beq 2f + b 3f + +2: /* is it a source page? (r9) */ + rlwinm. r7, r0, 0, 28, 28 /* IND_SOURCE (1<<3) */ + beq 0b + + rlwinm r9, r0, 0, 0, 19 /* clear kexec flags, page align */ + + li r7, PAGE_SIZE / 4 + mtctr r7 + subi r9, r9, 4 + subi r8, r8, 4 +9: + lwzu r0, 4(r9) /* do the copy */ + xor r6, r6, r0 + stwu r0, 4(r8) + dcbst 0, r8 + sync + icbi 0, r8 + bdnz 9b + + addi r9, r9, 4 + addi r8, r8, 4 + b 0b + +3: + + /* To be certain of avoiding problems with self-modifying code + * execute a serializing instruction here. + */ + isync + sync + + mfspr r3, SPRN_PIR /* current core we are running on */ + mr r4, r5 /* load physical address of chunk called */ + + /* jump to the entry point, usually the setup routine */ + mtlr r5 + blrl + +1: b 1b + +relocate_new_kernel_end: + + .globl relocate_new_kernel_size +relocate_new_kernel_size: + .long relocate_new_kernel_end - relocate_new_kernel diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile index 4c67cc79de7c..2bfeaa13befb 100644 --- a/arch/powerpc/kvm/Makefile +++ b/arch/powerpc/kvm/Makefile @@ -71,6 +71,9 @@ kvm-hv-y += \ book3s_64_mmu_radix.o \ book3s_hv_nested.o +kvm-hv-$(CONFIG_PPC_UV) += \ + book3s_hv_uvmem.o + kvm-hv-$(CONFIG_PPC_TRANSACTIONAL_MEM) += \ book3s_hv_tm.o diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c index ec2547cc5ecb..58a59ee998e2 100644 --- a/arch/powerpc/kvm/book3s.c +++ b/arch/powerpc/kvm/book3s.c @@ -74,27 +74,6 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { NULL } }; -void kvmppc_unfixup_split_real(struct kvm_vcpu *vcpu) -{ - if (vcpu->arch.hflags & BOOK3S_HFLAG_SPLIT_HACK) { - ulong pc = kvmppc_get_pc(vcpu); - ulong lr = kvmppc_get_lr(vcpu); - if ((pc & SPLIT_HACK_MASK) == SPLIT_HACK_OFFS) - kvmppc_set_pc(vcpu, pc & ~SPLIT_HACK_MASK); - if ((lr & SPLIT_HACK_MASK) == SPLIT_HACK_OFFS) - kvmppc_set_lr(vcpu, lr & ~SPLIT_HACK_MASK); - vcpu->arch.hflags &= ~BOOK3S_HFLAG_SPLIT_HACK; - } -} -EXPORT_SYMBOL_GPL(kvmppc_unfixup_split_real); - -static inline unsigned long kvmppc_interrupt_offset(struct kvm_vcpu *vcpu) -{ - if (!is_kvmppc_hv_enabled(vcpu->kvm)) - return to_book3s(vcpu)->hior; - return 0; -} - static inline void kvmppc_update_int_pending(struct kvm_vcpu *vcpu, unsigned long pending_now, unsigned long old_pending) { @@ -134,11 +113,7 @@ static inline bool kvmppc_critical_section(struct kvm_vcpu *vcpu) void kvmppc_inject_interrupt(struct kvm_vcpu *vcpu, int vec, u64 flags) { - kvmppc_unfixup_split_real(vcpu); - kvmppc_set_srr0(vcpu, kvmppc_get_pc(vcpu)); - kvmppc_set_srr1(vcpu, (kvmppc_get_msr(vcpu) & ~0x783f0000ul) | flags); - kvmppc_set_pc(vcpu, kvmppc_interrupt_offset(vcpu) + vec); - vcpu->arch.mmu.reset_msr(vcpu); + vcpu->kvm->arch.kvm_ops->inject_interrupt(vcpu, vec, flags); } static int kvmppc_book3s_vec2irqprio(unsigned int vec) diff --git a/arch/powerpc/kvm/book3s.h b/arch/powerpc/kvm/book3s.h index 2ef1311a2a13..3a4613985949 100644 --- a/arch/powerpc/kvm/book3s.h +++ b/arch/powerpc/kvm/book3s.h @@ -32,4 +32,7 @@ extern void kvmppc_emulate_tabort(struct kvm_vcpu *vcpu, int ra_val); static inline void kvmppc_emulate_tabort(struct kvm_vcpu *vcpu, int ra_val) {} #endif +extern void kvmppc_set_msr_hv(struct kvm_vcpu *vcpu, u64 msr); +extern void kvmppc_inject_interrupt_hv(struct kvm_vcpu *vcpu, int vec, u64 srr1_flags); + #endif diff --git a/arch/powerpc/kvm/book3s_32_mmu.c b/arch/powerpc/kvm/book3s_32_mmu.c index 18f244aad7aa..f21e73492ce3 100644 --- a/arch/powerpc/kvm/book3s_32_mmu.c +++ b/arch/powerpc/kvm/book3s_32_mmu.c @@ -90,11 +90,6 @@ static u64 kvmppc_mmu_book3s_32_ea_to_vp(struct kvm_vcpu *vcpu, gva_t eaddr, return (((u64)eaddr >> 12) & 0xffff) | (vsid << 16); } -static void kvmppc_mmu_book3s_32_reset_msr(struct kvm_vcpu *vcpu) -{ - kvmppc_set_msr(vcpu, 0); -} - static hva_t kvmppc_mmu_book3s_32_get_pteg(struct kvm_vcpu *vcpu, u32 sre, gva_t eaddr, bool primary) @@ -406,7 +401,6 @@ void kvmppc_mmu_book3s_32_init(struct kvm_vcpu *vcpu) mmu->mtsrin = kvmppc_mmu_book3s_32_mtsrin; mmu->mfsrin = kvmppc_mmu_book3s_32_mfsrin; mmu->xlate = kvmppc_mmu_book3s_32_xlate; - mmu->reset_msr = kvmppc_mmu_book3s_32_reset_msr; mmu->tlbie = kvmppc_mmu_book3s_32_tlbie; mmu->esid_to_vsid = kvmppc_mmu_book3s_32_esid_to_vsid; mmu->ea_to_vp = kvmppc_mmu_book3s_32_ea_to_vp; diff --git a/arch/powerpc/kvm/book3s_64_mmu.c b/arch/powerpc/kvm/book3s_64_mmu.c index 5f63a5f7f24f..599133256a95 100644 --- a/arch/powerpc/kvm/book3s_64_mmu.c +++ b/arch/powerpc/kvm/book3s_64_mmu.c @@ -24,20 +24,6 @@ #define dprintk(X...) do { } while(0) #endif -static void kvmppc_mmu_book3s_64_reset_msr(struct kvm_vcpu *vcpu) -{ - unsigned long msr = vcpu->arch.intr_msr; - unsigned long cur_msr = kvmppc_get_msr(vcpu); - - /* If transactional, change to suspend mode on IRQ delivery */ - if (MSR_TM_TRANSACTIONAL(cur_msr)) - msr |= MSR_TS_S; - else - msr |= cur_msr & MSR_TS_MASK; - - kvmppc_set_msr(vcpu, msr); -} - static struct kvmppc_slb *kvmppc_mmu_book3s_64_find_slbe( struct kvm_vcpu *vcpu, gva_t eaddr) @@ -676,7 +662,6 @@ void kvmppc_mmu_book3s_64_init(struct kvm_vcpu *vcpu) mmu->slbie = kvmppc_mmu_book3s_64_slbie; mmu->slbia = kvmppc_mmu_book3s_64_slbia; mmu->xlate = kvmppc_mmu_book3s_64_xlate; - mmu->reset_msr = kvmppc_mmu_book3s_64_reset_msr; mmu->tlbie = kvmppc_mmu_book3s_64_tlbie; mmu->esid_to_vsid = kvmppc_mmu_book3s_64_esid_to_vsid; mmu->ea_to_vp = kvmppc_mmu_book3s_64_ea_to_vp; diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c index 9a75f0e1933b..d381526c5c9b 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_hv.c +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c @@ -275,18 +275,6 @@ int kvmppc_mmu_hv_init(void) return 0; } -static void kvmppc_mmu_book3s_64_hv_reset_msr(struct kvm_vcpu *vcpu) -{ - unsigned long msr = vcpu->arch.intr_msr; - - /* If transactional, change to suspend mode on IRQ delivery */ - if (MSR_TM_TRANSACTIONAL(vcpu->arch.shregs.msr)) - msr |= MSR_TS_S; - else - msr |= vcpu->arch.shregs.msr & MSR_TS_MASK; - kvmppc_set_msr(vcpu, msr); -} - static long kvmppc_virtmode_do_h_enter(struct kvm *kvm, unsigned long flags, long pte_index, unsigned long pteh, unsigned long ptel, unsigned long *pte_idx_ret) @@ -508,6 +496,7 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, struct vm_area_struct *vma; unsigned long rcbits; long mmio_update; + struct mm_struct *mm; if (kvm_is_radix(kvm)) return kvmppc_book3s_radix_page_fault(run, vcpu, ea, dsisr); @@ -584,6 +573,7 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, is_ci = false; pfn = 0; page = NULL; + mm = current->mm; pte_size = PAGE_SIZE; writing = (dsisr & DSISR_ISSTORE) != 0; /* If writing != 0, then the HPTE must allow writing, if we get here */ @@ -592,8 +582,8 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, npages = get_user_pages_fast(hva, 1, writing ? FOLL_WRITE : 0, pages); if (npages < 1) { /* Check if it's an I/O mapping */ - down_read(¤t->mm->mmap_sem); - vma = find_vma(current->mm, hva); + down_read(&mm->mmap_sem); + vma = find_vma(mm, hva); if (vma && vma->vm_start <= hva && hva + psize <= vma->vm_end && (vma->vm_flags & VM_PFNMAP)) { pfn = vma->vm_pgoff + @@ -602,7 +592,7 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, is_ci = pte_ci(__pte((pgprot_val(vma->vm_page_prot)))); write_ok = vma->vm_flags & VM_WRITE; } - up_read(¤t->mm->mmap_sem); + up_read(&mm->mmap_sem); if (!pfn) goto out_put; } else { @@ -621,8 +611,7 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, * hugepage split and collapse. */ local_irq_save(flags); - ptep = find_current_mm_pte(current->mm->pgd, - hva, NULL, NULL); + ptep = find_current_mm_pte(mm->pgd, hva, NULL, NULL); if (ptep) { pte = kvmppc_read_update_linux_pte(ptep, 1); if (__pte_write(pte)) @@ -2000,7 +1989,7 @@ int kvm_vm_ioctl_get_htab_fd(struct kvm *kvm, struct kvm_get_htab_fd *ghf) ret = anon_inode_getfd("kvm-htab", &kvm_htab_fops, ctx, rwflag | O_CLOEXEC); if (ret < 0) { kfree(ctx); - kvm_put_kvm(kvm); + kvm_put_kvm_no_destroy(kvm); return ret; } @@ -2161,7 +2150,6 @@ void kvmppc_mmu_book3s_hv_init(struct kvm_vcpu *vcpu) vcpu->arch.slb_nr = 32; /* POWER7/POWER8 */ mmu->xlate = kvmppc_mmu_book3s_64_hv_xlate; - mmu->reset_msr = kvmppc_mmu_book3s_64_hv_reset_msr; vcpu->arch.hflags |= BOOK3S_HFLAG_SLB; } diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c index 2d415c36a61d..da857c8ba6e4 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_radix.c +++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c @@ -19,6 +19,8 @@ #include <asm/pgtable.h> #include <asm/pgalloc.h> #include <asm/pte-walk.h> +#include <asm/ultravisor.h> +#include <asm/kvm_book3s_uvmem.h> /* * Supported radix tree geometry. @@ -915,6 +917,9 @@ int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, if (!(dsisr & DSISR_PRTABLE_FAULT)) gpa |= ea & 0xfff; + if (kvm->arch.secure_guest & KVMPPC_SECURE_INIT_DONE) + return kvmppc_send_page_to_uv(kvm, gfn); + /* Get the corresponding memslot */ memslot = gfn_to_memslot(kvm, gfn); @@ -972,6 +977,11 @@ int kvm_unmap_radix(struct kvm *kvm, struct kvm_memory_slot *memslot, unsigned long gpa = gfn << PAGE_SHIFT; unsigned int shift; + if (kvm->arch.secure_guest & KVMPPC_SECURE_INIT_DONE) { + uv_page_inval(kvm->arch.lpid, gpa, PAGE_SHIFT); + return 0; + } + ptep = __find_linux_pte(kvm->arch.pgtable, gpa, NULL, &shift); if (ptep && pte_present(*ptep)) kvmppc_unmap_pte(kvm, ptep, gpa, shift, memslot, @@ -989,6 +999,9 @@ int kvm_age_radix(struct kvm *kvm, struct kvm_memory_slot *memslot, int ref = 0; unsigned long old, *rmapp; + if (kvm->arch.secure_guest & KVMPPC_SECURE_INIT_DONE) + return ref; + ptep = __find_linux_pte(kvm->arch.pgtable, gpa, NULL, &shift); if (ptep && pte_present(*ptep) && pte_young(*ptep)) { old = kvmppc_radix_update_pte(kvm, ptep, _PAGE_ACCESSED, 0, @@ -1013,6 +1026,9 @@ int kvm_test_age_radix(struct kvm *kvm, struct kvm_memory_slot *memslot, unsigned int shift; int ref = 0; + if (kvm->arch.secure_guest & KVMPPC_SECURE_INIT_DONE) + return ref; + ptep = __find_linux_pte(kvm->arch.pgtable, gpa, NULL, &shift); if (ptep && pte_present(*ptep) && pte_young(*ptep)) ref = 1; @@ -1030,6 +1046,9 @@ static int kvm_radix_test_clear_dirty(struct kvm *kvm, int ret = 0; unsigned long old, *rmapp; + if (kvm->arch.secure_guest & KVMPPC_SECURE_INIT_DONE) + return ret; + ptep = __find_linux_pte(kvm->arch.pgtable, gpa, NULL, &shift); if (ptep && pte_present(*ptep) && pte_dirty(*ptep)) { ret = 1; @@ -1082,6 +1101,12 @@ void kvmppc_radix_flush_memslot(struct kvm *kvm, unsigned long gpa; unsigned int shift; + if (kvm->arch.secure_guest & KVMPPC_SECURE_INIT_START) + kvmppc_uvmem_drop_pages(memslot, kvm); + + if (kvm->arch.secure_guest & KVMPPC_SECURE_INIT_DONE) + return; + gpa = memslot->base_gfn << PAGE_SHIFT; spin_lock(&kvm->mmu_lock); for (n = memslot->npages; n; --n) { diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c index 5834db0a54c6..883a66e76638 100644 --- a/arch/powerpc/kvm/book3s_64_vio.c +++ b/arch/powerpc/kvm/book3s_64_vio.c @@ -317,7 +317,7 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm, if (ret >= 0) list_add_rcu(&stt->list, &kvm->arch.spapr_tce_tables); else - kvm_put_kvm(kvm); + kvm_put_kvm_no_destroy(kvm); mutex_unlock(&kvm->lock); diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 709cf1fd4cf4..dc53578193ee 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -72,6 +72,9 @@ #include <asm/xics.h> #include <asm/xive.h> #include <asm/hw_breakpoint.h> +#include <asm/kvm_host.h> +#include <asm/kvm_book3s_uvmem.h> +#include <asm/ultravisor.h> #include "book3s.h" @@ -133,7 +136,6 @@ static inline bool nesting_enabled(struct kvm *kvm) /* If set, the threads on each CPU core have to be in the same MMU mode */ static bool no_mixing_hpt_and_radix; -static void kvmppc_end_cede(struct kvm_vcpu *vcpu); static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu); /* @@ -338,18 +340,6 @@ static void kvmppc_core_vcpu_put_hv(struct kvm_vcpu *vcpu) spin_unlock_irqrestore(&vcpu->arch.tbacct_lock, flags); } -static void kvmppc_set_msr_hv(struct kvm_vcpu *vcpu, u64 msr) -{ - /* - * Check for illegal transactional state bit combination - * and if we find it, force the TS field to a safe state. - */ - if ((msr & MSR_TS_MASK) == MSR_TS_MASK) - msr &= ~MSR_TS_MASK; - vcpu->arch.shregs.msr = msr; - kvmppc_end_cede(vcpu); -} - static void kvmppc_set_pvr_hv(struct kvm_vcpu *vcpu, u32 pvr) { vcpu->arch.pvr = pvr; @@ -792,6 +782,11 @@ static int kvmppc_h_set_mode(struct kvm_vcpu *vcpu, unsigned long mflags, vcpu->arch.dawr = value1; vcpu->arch.dawrx = value2; return H_SUCCESS; + case H_SET_MODE_RESOURCE_ADDR_TRANS_MODE: + /* KVM does not support mflags=2 (AIL=2) */ + if (mflags != 0 && mflags != 3) + return H_UNSUPPORTED_FLAG_START; + return H_TOO_HARD; default: return H_TOO_HARD; } @@ -1078,6 +1073,25 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu) kvmppc_get_gpr(vcpu, 5), kvmppc_get_gpr(vcpu, 6)); break; + case H_SVM_PAGE_IN: + ret = kvmppc_h_svm_page_in(vcpu->kvm, + kvmppc_get_gpr(vcpu, 4), + kvmppc_get_gpr(vcpu, 5), + kvmppc_get_gpr(vcpu, 6)); + break; + case H_SVM_PAGE_OUT: + ret = kvmppc_h_svm_page_out(vcpu->kvm, + kvmppc_get_gpr(vcpu, 4), + kvmppc_get_gpr(vcpu, 5), + kvmppc_get_gpr(vcpu, 6)); + break; + case H_SVM_INIT_START: + ret = kvmppc_h_svm_init_start(vcpu->kvm); + break; + case H_SVM_INIT_DONE: + ret = kvmppc_h_svm_init_done(vcpu->kvm); + break; + default: return RESUME_HOST; } @@ -2454,15 +2468,6 @@ static void kvmppc_set_timer(struct kvm_vcpu *vcpu) vcpu->arch.timer_running = 1; } -static void kvmppc_end_cede(struct kvm_vcpu *vcpu) -{ - vcpu->arch.ceded = 0; - if (vcpu->arch.timer_running) { - hrtimer_try_to_cancel(&vcpu->arch.dec_timer); - vcpu->arch.timer_running = 0; - } -} - extern int __kvmppc_vcore_entry(void); static void kvmppc_remove_runnable(struct kvmppc_vcore *vc, @@ -4511,6 +4516,29 @@ static void kvmppc_core_commit_memory_region_hv(struct kvm *kvm, if (change == KVM_MR_FLAGS_ONLY && kvm_is_radix(kvm) && ((new->flags ^ old->flags) & KVM_MEM_LOG_DIRTY_PAGES)) kvmppc_radix_flush_memslot(kvm, old); + /* + * If UV hasn't yet called H_SVM_INIT_START, don't register memslots. + */ + if (!kvm->arch.secure_guest) + return; + + switch (change) { + case KVM_MR_CREATE: + if (kvmppc_uvmem_slot_init(kvm, new)) + return; + uv_register_mem_slot(kvm->arch.lpid, + new->base_gfn << PAGE_SHIFT, + new->npages * PAGE_SIZE, + 0, new->id); + break; + case KVM_MR_DELETE: + uv_unregister_mem_slot(kvm->arch.lpid, old->id); + kvmppc_uvmem_slot_free(kvm, old); + break; + default: + /* TODO: Handle KVM_MR_MOVE */ + break; + } } /* @@ -4784,6 +4812,8 @@ static int kvmppc_core_init_vm_hv(struct kvm *kvm) char buf[32]; int ret; + mutex_init(&kvm->arch.uvmem_lock); + INIT_LIST_HEAD(&kvm->arch.uvmem_pfns); mutex_init(&kvm->arch.mmu_setup_lock); /* Allocate the guest's logical partition ID */ @@ -4953,8 +4983,10 @@ static void kvmppc_core_destroy_vm_hv(struct kvm *kvm) if (nesting_enabled(kvm)) kvmhv_release_all_nested(kvm); kvm->arch.process_table = 0; + uv_svm_terminate(kvm->arch.lpid); kvmhv_set_ptbl_entry(kvm->arch.lpid, 0, 0); } + kvmppc_free_lpid(kvm->arch.lpid); kvmppc_free_pimap(kvm); @@ -5394,6 +5426,94 @@ static int kvmhv_store_to_eaddr(struct kvm_vcpu *vcpu, ulong *eaddr, void *ptr, return rc; } +static void unpin_vpa_reset(struct kvm *kvm, struct kvmppc_vpa *vpa) +{ + unpin_vpa(kvm, vpa); + vpa->gpa = 0; + vpa->pinned_addr = NULL; + vpa->dirty = false; + vpa->update_pending = 0; +} + +/* + * IOCTL handler to turn off secure mode of guest + * + * - Release all device pages + * - Issue ucall to terminate the guest on the UV side + * - Unpin the VPA pages. + * - Reinit the partition scoped page tables + */ +static int kvmhv_svm_off(struct kvm *kvm) +{ + struct kvm_vcpu *vcpu; + int mmu_was_ready; + int srcu_idx; + int ret = 0; + int i; + + if (!(kvm->arch.secure_guest & KVMPPC_SECURE_INIT_START)) + return ret; + + mutex_lock(&kvm->arch.mmu_setup_lock); + mmu_was_ready = kvm->arch.mmu_ready; + if (kvm->arch.mmu_ready) { + kvm->arch.mmu_ready = 0; + /* order mmu_ready vs. vcpus_running */ + smp_mb(); + if (atomic_read(&kvm->arch.vcpus_running)) { + kvm->arch.mmu_ready = 1; + ret = -EBUSY; + goto out; + } + } + + srcu_idx = srcu_read_lock(&kvm->srcu); + for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { + struct kvm_memory_slot *memslot; + struct kvm_memslots *slots = __kvm_memslots(kvm, i); + + if (!slots) + continue; + + kvm_for_each_memslot(memslot, slots) { + kvmppc_uvmem_drop_pages(memslot, kvm); + uv_unregister_mem_slot(kvm->arch.lpid, memslot->id); + } + } + srcu_read_unlock(&kvm->srcu, srcu_idx); + + ret = uv_svm_terminate(kvm->arch.lpid); + if (ret != U_SUCCESS) { + ret = -EINVAL; + goto out; + } + + /* + * When secure guest is reset, all the guest pages are sent + * to UV via UV_PAGE_IN before the non-boot vcpus get a + * chance to run and unpin their VPA pages. Unpinning of all + * VPA pages is done here explicitly so that VPA pages + * can be migrated to the secure side. + * + * This is required to for the secure SMP guest to reboot + * correctly. + */ + kvm_for_each_vcpu(i, vcpu, kvm) { + spin_lock(&vcpu->arch.vpa_update_lock); + unpin_vpa_reset(kvm, &vcpu->arch.dtl); + unpin_vpa_reset(kvm, &vcpu->arch.slb_shadow); + unpin_vpa_reset(kvm, &vcpu->arch.vpa); + spin_unlock(&vcpu->arch.vpa_update_lock); + } + + kvmppc_setup_partition_table(kvm); + kvm->arch.secure_guest = 0; + kvm->arch.mmu_ready = mmu_was_ready; +out: + mutex_unlock(&kvm->arch.mmu_setup_lock); + return ret; +} + static struct kvmppc_ops kvm_ops_hv = { .get_sregs = kvm_arch_vcpu_ioctl_get_sregs_hv, .set_sregs = kvm_arch_vcpu_ioctl_set_sregs_hv, @@ -5401,6 +5521,7 @@ static struct kvmppc_ops kvm_ops_hv = { .set_one_reg = kvmppc_set_one_reg_hv, .vcpu_load = kvmppc_core_vcpu_load_hv, .vcpu_put = kvmppc_core_vcpu_put_hv, + .inject_interrupt = kvmppc_inject_interrupt_hv, .set_msr = kvmppc_set_msr_hv, .vcpu_run = kvmppc_vcpu_run_hv, .vcpu_create = kvmppc_core_vcpu_create_hv, @@ -5436,6 +5557,7 @@ static struct kvmppc_ops kvm_ops_hv = { .enable_nested = kvmhv_enable_nested, .load_from_eaddr = kvmhv_load_from_eaddr, .store_to_eaddr = kvmhv_store_to_eaddr, + .svm_off = kvmhv_svm_off, }; static int kvm_init_subcore_bitmap(void) @@ -5544,11 +5666,16 @@ static int kvmppc_book3s_init_hv(void) no_mixing_hpt_and_radix = true; } + r = kvmppc_uvmem_init(); + if (r < 0) + pr_err("KVM-HV: kvmppc_uvmem_init failed %d\n", r); + return r; } static void kvmppc_book3s_exit_hv(void) { + kvmppc_uvmem_free(); kvmppc_free_host_rm_ops(); if (kvmppc_radix_possible()) kvmppc_radix_exit(); diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c index 7c1909657b55..7cd3cf3d366b 100644 --- a/arch/powerpc/kvm/book3s_hv_builtin.c +++ b/arch/powerpc/kvm/book3s_hv_builtin.c @@ -755,6 +755,71 @@ void kvmhv_p9_restore_lpcr(struct kvm_split_mode *sip) local_paca->kvm_hstate.kvm_split_mode = NULL; } +static void kvmppc_end_cede(struct kvm_vcpu *vcpu) +{ + vcpu->arch.ceded = 0; + if (vcpu->arch.timer_running) { + hrtimer_try_to_cancel(&vcpu->arch.dec_timer); + vcpu->arch.timer_running = 0; + } +} + +void kvmppc_set_msr_hv(struct kvm_vcpu *vcpu, u64 msr) +{ + /* + * Check for illegal transactional state bit combination + * and if we find it, force the TS field to a safe state. + */ + if ((msr & MSR_TS_MASK) == MSR_TS_MASK) + msr &= ~MSR_TS_MASK; + vcpu->arch.shregs.msr = msr; + kvmppc_end_cede(vcpu); +} +EXPORT_SYMBOL_GPL(kvmppc_set_msr_hv); + +static void inject_interrupt(struct kvm_vcpu *vcpu, int vec, u64 srr1_flags) +{ + unsigned long msr, pc, new_msr, new_pc; + + msr = kvmppc_get_msr(vcpu); + pc = kvmppc_get_pc(vcpu); + new_msr = vcpu->arch.intr_msr; + new_pc = vec; + + /* If transactional, change to suspend mode on IRQ delivery */ + if (MSR_TM_TRANSACTIONAL(msr)) + new_msr |= MSR_TS_S; + else + new_msr |= msr & MSR_TS_MASK; + + /* + * Perform MSR and PC adjustment for LPCR[AIL]=3 if it is set and + * applicable. AIL=2 is not supported. + * + * AIL does not apply to SRESET, MCE, or HMI (which is never + * delivered to the guest), and does not apply if IR=0 or DR=0. + */ + if (vec != BOOK3S_INTERRUPT_SYSTEM_RESET && + vec != BOOK3S_INTERRUPT_MACHINE_CHECK && + (vcpu->arch.vcore->lpcr & LPCR_AIL) == LPCR_AIL_3 && + (msr & (MSR_IR|MSR_DR)) == (MSR_IR|MSR_DR) ) { + new_msr |= MSR_IR | MSR_DR; + new_pc += 0xC000000000004000ULL; + } + + kvmppc_set_srr0(vcpu, pc); + kvmppc_set_srr1(vcpu, (msr & SRR1_MSR_BITS) | srr1_flags); + kvmppc_set_pc(vcpu, new_pc); + vcpu->arch.shregs.msr = new_msr; +} + +void kvmppc_inject_interrupt_hv(struct kvm_vcpu *vcpu, int vec, u64 srr1_flags) +{ + inject_interrupt(vcpu, vec, srr1_flags); + kvmppc_end_cede(vcpu); +} +EXPORT_SYMBOL_GPL(kvmppc_inject_interrupt_hv); + /* * Is there a PRIV_DOORBELL pending for the guest (on POWER9)? * Can we inject a Decrementer or a External interrupt? @@ -762,7 +827,6 @@ void kvmhv_p9_restore_lpcr(struct kvm_split_mode *sip) void kvmppc_guest_entry_inject_int(struct kvm_vcpu *vcpu) { int ext; - unsigned long vec = 0; unsigned long lpcr; /* Insert EXTERNAL bit into LPCR at the MER bit position */ @@ -774,26 +838,16 @@ void kvmppc_guest_entry_inject_int(struct kvm_vcpu *vcpu) if (vcpu->arch.shregs.msr & MSR_EE) { if (ext) { - vec = BOOK3S_INTERRUPT_EXTERNAL; + inject_interrupt(vcpu, BOOK3S_INTERRUPT_EXTERNAL, 0); } else { long int dec = mfspr(SPRN_DEC); if (!(lpcr & LPCR_LD)) dec = (int) dec; if (dec < 0) - vec = BOOK3S_INTERRUPT_DECREMENTER; + inject_interrupt(vcpu, + BOOK3S_INTERRUPT_DECREMENTER, 0); } } - if (vec) { - unsigned long msr, old_msr = vcpu->arch.shregs.msr; - - kvmppc_set_srr0(vcpu, kvmppc_get_pc(vcpu)); - kvmppc_set_srr1(vcpu, old_msr); - kvmppc_set_pc(vcpu, vec); - msr = vcpu->arch.intr_msr; - if (MSR_TM_ACTIVE(old_msr)) - msr |= MSR_TS_S; - vcpu->arch.shregs.msr = msr; - } if (vcpu->arch.doorbell_request) { mtspr(SPRN_DPDES, 1); diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c index cdf30c6eaf54..dc97e5be76f6 100644 --- a/arch/powerpc/kvm/book3s_hv_nested.c +++ b/arch/powerpc/kvm/book3s_hv_nested.c @@ -1186,7 +1186,7 @@ static int kvmhv_translate_addr_nested(struct kvm_vcpu *vcpu, forward_to_l1: vcpu->arch.fault_dsisr = flags; if (vcpu->arch.trap == BOOK3S_INTERRUPT_H_INST_STORAGE) { - vcpu->arch.shregs.msr &= ~0x783f0000ul; + vcpu->arch.shregs.msr &= SRR1_MSR_BITS; vcpu->arch.shregs.msr |= flags; } return RESUME_HOST; diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index faebcbb8c4db..0496e66aaa56 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -11,6 +11,7 @@ */ #include <asm/ppc_asm.h> +#include <asm/code-patching-asm.h> #include <asm/kvm_asm.h> #include <asm/reg.h> #include <asm/mmu.h> @@ -1487,6 +1488,13 @@ guest_exit_cont: /* r9 = vcpu, r12 = trap, r13 = paca */ 1: #endif /* CONFIG_KVM_XICS */ + /* + * Possibly flush the link stack here, before we do a blr in + * guest_exit_short_path. + */ +1: nop + patch_site 1b patch__call_kvm_flush_link_stack + /* If we came in through the P9 short path, go back out to C now */ lwz r0, STACK_SLOT_SHORT_PATH(r1) cmpwi r0, 0 @@ -1963,6 +1971,28 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) mtlr r0 blr +.balign 32 +.global kvm_flush_link_stack +kvm_flush_link_stack: + /* Save LR into r0 */ + mflr r0 + + /* Flush the link stack. On Power8 it's up to 32 entries in size. */ + .rept 32 + bl .+4 + .endr + + /* And on Power9 it's up to 64. */ +BEGIN_FTR_SECTION + .rept 32 + bl .+4 + .endr +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) + + /* Restore LR */ + mtlr r0 + blr + kvmppc_guest_external: /* External interrupt, first check for host_ipi. If this is * set, we know the host wants us out so let's do it now diff --git a/arch/powerpc/kvm/book3s_hv_uvmem.c b/arch/powerpc/kvm/book3s_hv_uvmem.c new file mode 100644 index 000000000000..2de264fc3156 --- /dev/null +++ b/arch/powerpc/kvm/book3s_hv_uvmem.c @@ -0,0 +1,785 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Secure pages management: Migration of pages between normal and secure + * memory of KVM guests. + * + * Copyright 2018 Bharata B Rao, IBM Corp. <bharata@linux.ibm.com> + */ + +/* + * A pseries guest can be run as secure guest on Ultravisor-enabled + * POWER platforms. On such platforms, this driver will be used to manage + * the movement of guest pages between the normal memory managed by + * hypervisor (HV) and secure memory managed by Ultravisor (UV). + * + * The page-in or page-out requests from UV will come to HV as hcalls and + * HV will call back into UV via ultracalls to satisfy these page requests. + * + * Private ZONE_DEVICE memory equal to the amount of secure memory + * available in the platform for running secure guests is hotplugged. + * Whenever a page belonging to the guest becomes secure, a page from this + * private device memory is used to represent and track that secure page + * on the HV side. Some pages (like virtio buffers, VPA pages etc) are + * shared between UV and HV. However such pages aren't represented by + * device private memory and mappings to shared memory exist in both + * UV and HV page tables. + */ + +/* + * Notes on locking + * + * kvm->arch.uvmem_lock is a per-guest lock that prevents concurrent + * page-in and page-out requests for the same GPA. Concurrent accesses + * can either come via UV (guest vCPUs requesting for same page) + * or when HV and guest simultaneously access the same page. + * This mutex serializes the migration of page from HV(normal) to + * UV(secure) and vice versa. So the serialization points are around + * migrate_vma routines and page-in/out routines. + * + * Per-guest mutex comes with a cost though. Mainly it serializes the + * fault path as page-out can occur when HV faults on accessing secure + * guest pages. Currently UV issues page-in requests for all the guest + * PFNs one at a time during early boot (UV_ESM uvcall), so this is + * not a cause for concern. Also currently the number of page-outs caused + * by HV touching secure pages is very very low. If an when UV supports + * overcommitting, then we might see concurrent guest driven page-outs. + * + * Locking order + * + * 1. kvm->srcu - Protects KVM memslots + * 2. kvm->mm->mmap_sem - find_vma, migrate_vma_pages and helpers, ksm_madvise + * 3. kvm->arch.uvmem_lock - protects read/writes to uvmem slots thus acting + * as sync-points for page-in/out + */ + +/* + * Notes on page size + * + * Currently UV uses 2MB mappings internally, but will issue H_SVM_PAGE_IN + * and H_SVM_PAGE_OUT hcalls in PAGE_SIZE(64K) granularity. HV tracks + * secure GPAs at 64K page size and maintains one device PFN for each + * 64K secure GPA. UV_PAGE_IN and UV_PAGE_OUT calls by HV are also issued + * for 64K page at a time. + * + * HV faulting on secure pages: When HV touches any secure page, it + * faults and issues a UV_PAGE_OUT request with 64K page size. Currently + * UV splits and remaps the 2MB page if necessary and copies out the + * required 64K page contents. + * + * Shared pages: Whenever guest shares a secure page, UV will split and + * remap the 2MB page if required and issue H_SVM_PAGE_IN with 64K page size. + * + * HV invalidating a page: When a regular page belonging to secure + * guest gets unmapped, HV informs UV with UV_PAGE_INVAL of 64K + * page size. Using 64K page size is correct here because any non-secure + * page will essentially be of 64K page size. Splitting by UV during sharing + * and page-out ensures this. + * + * Page fault handling: When HV handles page fault of a page belonging + * to secure guest, it sends that to UV with a 64K UV_PAGE_IN request. + * Using 64K size is correct here too as UV would have split the 2MB page + * into 64k mappings and would have done page-outs earlier. + * + * In summary, the current secure pages handling code in HV assumes + * 64K page size and in fact fails any page-in/page-out requests of + * non-64K size upfront. If and when UV starts supporting multiple + * page-sizes, we need to break this assumption. + */ + +#include <linux/pagemap.h> +#include <linux/migrate.h> +#include <linux/kvm_host.h> +#include <linux/ksm.h> +#include <asm/ultravisor.h> +#include <asm/mman.h> +#include <asm/kvm_ppc.h> + +static struct dev_pagemap kvmppc_uvmem_pgmap; +static unsigned long *kvmppc_uvmem_bitmap; +static DEFINE_SPINLOCK(kvmppc_uvmem_bitmap_lock); + +#define KVMPPC_UVMEM_PFN (1UL << 63) + +struct kvmppc_uvmem_slot { + struct list_head list; + unsigned long nr_pfns; + unsigned long base_pfn; + unsigned long *pfns; +}; + +struct kvmppc_uvmem_page_pvt { + struct kvm *kvm; + unsigned long gpa; + bool skip_page_out; +}; + +int kvmppc_uvmem_slot_init(struct kvm *kvm, const struct kvm_memory_slot *slot) +{ + struct kvmppc_uvmem_slot *p; + + p = kzalloc(sizeof(*p), GFP_KERNEL); + if (!p) + return -ENOMEM; + p->pfns = vzalloc(array_size(slot->npages, sizeof(*p->pfns))); + if (!p->pfns) { + kfree(p); + return -ENOMEM; + } + p->nr_pfns = slot->npages; + p->base_pfn = slot->base_gfn; + + mutex_lock(&kvm->arch.uvmem_lock); + list_add(&p->list, &kvm->arch.uvmem_pfns); + mutex_unlock(&kvm->arch.uvmem_lock); + + return 0; +} + +/* + * All device PFNs are already released by the time we come here. + */ +void kvmppc_uvmem_slot_free(struct kvm *kvm, const struct kvm_memory_slot *slot) +{ + struct kvmppc_uvmem_slot *p, *next; + + mutex_lock(&kvm->arch.uvmem_lock); + list_for_each_entry_safe(p, next, &kvm->arch.uvmem_pfns, list) { + if (p->base_pfn == slot->base_gfn) { + vfree(p->pfns); + list_del(&p->list); + kfree(p); + break; + } + } + mutex_unlock(&kvm->arch.uvmem_lock); +} + +static void kvmppc_uvmem_pfn_insert(unsigned long gfn, unsigned long uvmem_pfn, + struct kvm *kvm) +{ + struct kvmppc_uvmem_slot *p; + + list_for_each_entry(p, &kvm->arch.uvmem_pfns, list) { + if (gfn >= p->base_pfn && gfn < p->base_pfn + p->nr_pfns) { + unsigned long index = gfn - p->base_pfn; + + p->pfns[index] = uvmem_pfn | KVMPPC_UVMEM_PFN; + return; + } + } +} + +static void kvmppc_uvmem_pfn_remove(unsigned long gfn, struct kvm *kvm) +{ + struct kvmppc_uvmem_slot *p; + + list_for_each_entry(p, &kvm->arch.uvmem_pfns, list) { + if (gfn >= p->base_pfn && gfn < p->base_pfn + p->nr_pfns) { + p->pfns[gfn - p->base_pfn] = 0; + return; + } + } +} + +static bool kvmppc_gfn_is_uvmem_pfn(unsigned long gfn, struct kvm *kvm, + unsigned long *uvmem_pfn) +{ + struct kvmppc_uvmem_slot *p; + + list_for_each_entry(p, &kvm->arch.uvmem_pfns, list) { + if (gfn >= p->base_pfn && gfn < p->base_pfn + p->nr_pfns) { + unsigned long index = gfn - p->base_pfn; + + if (p->pfns[index] & KVMPPC_UVMEM_PFN) { + if (uvmem_pfn) + *uvmem_pfn = p->pfns[index] & + ~KVMPPC_UVMEM_PFN; + return true; + } else + return false; + } + } + return false; +} + +unsigned long kvmppc_h_svm_init_start(struct kvm *kvm) +{ + struct kvm_memslots *slots; + struct kvm_memory_slot *memslot; + int ret = H_SUCCESS; + int srcu_idx; + + if (!kvmppc_uvmem_bitmap) + return H_UNSUPPORTED; + + /* Only radix guests can be secure guests */ + if (!kvm_is_radix(kvm)) + return H_UNSUPPORTED; + + srcu_idx = srcu_read_lock(&kvm->srcu); + slots = kvm_memslots(kvm); + kvm_for_each_memslot(memslot, slots) { + if (kvmppc_uvmem_slot_init(kvm, memslot)) { + ret = H_PARAMETER; + goto out; + } + ret = uv_register_mem_slot(kvm->arch.lpid, + memslot->base_gfn << PAGE_SHIFT, + memslot->npages * PAGE_SIZE, + 0, memslot->id); + if (ret < 0) { + kvmppc_uvmem_slot_free(kvm, memslot); + ret = H_PARAMETER; + goto out; + } + } + kvm->arch.secure_guest |= KVMPPC_SECURE_INIT_START; +out: + srcu_read_unlock(&kvm->srcu, srcu_idx); + return ret; +} + +unsigned long kvmppc_h_svm_init_done(struct kvm *kvm) +{ + if (!(kvm->arch.secure_guest & KVMPPC_SECURE_INIT_START)) + return H_UNSUPPORTED; + + kvm->arch.secure_guest |= KVMPPC_SECURE_INIT_DONE; + pr_info("LPID %d went secure\n", kvm->arch.lpid); + return H_SUCCESS; +} + +/* + * Drop device pages that we maintain for the secure guest + * + * We first mark the pages to be skipped from UV_PAGE_OUT when there + * is HV side fault on these pages. Next we *get* these pages, forcing + * fault on them, do fault time migration to replace the device PTEs in + * QEMU page table with normal PTEs from newly allocated pages. + */ +void kvmppc_uvmem_drop_pages(const struct kvm_memory_slot *free, + struct kvm *kvm) +{ + int i; + struct kvmppc_uvmem_page_pvt *pvt; + unsigned long pfn, uvmem_pfn; + unsigned long gfn = free->base_gfn; + + for (i = free->npages; i; --i, ++gfn) { + struct page *uvmem_page; + + mutex_lock(&kvm->arch.uvmem_lock); + if (!kvmppc_gfn_is_uvmem_pfn(gfn, kvm, &uvmem_pfn)) { + mutex_unlock(&kvm->arch.uvmem_lock); + continue; + } + + uvmem_page = pfn_to_page(uvmem_pfn); + pvt = uvmem_page->zone_device_data; + pvt->skip_page_out = true; + mutex_unlock(&kvm->arch.uvmem_lock); + + pfn = gfn_to_pfn(kvm, gfn); + if (is_error_noslot_pfn(pfn)) + continue; + kvm_release_pfn_clean(pfn); + } +} + +/* + * Get a free device PFN from the pool + * + * Called when a normal page is moved to secure memory (UV_PAGE_IN). Device + * PFN will be used to keep track of the secure page on HV side. + * + * Called with kvm->arch.uvmem_lock held + */ +static struct page *kvmppc_uvmem_get_page(unsigned long gpa, struct kvm *kvm) +{ + struct page *dpage = NULL; + unsigned long bit, uvmem_pfn; + struct kvmppc_uvmem_page_pvt *pvt; + unsigned long pfn_last, pfn_first; + + pfn_first = kvmppc_uvmem_pgmap.res.start >> PAGE_SHIFT; + pfn_last = pfn_first + + (resource_size(&kvmppc_uvmem_pgmap.res) >> PAGE_SHIFT); + + spin_lock(&kvmppc_uvmem_bitmap_lock); + bit = find_first_zero_bit(kvmppc_uvmem_bitmap, + pfn_last - pfn_first); + if (bit >= (pfn_last - pfn_first)) + goto out; + bitmap_set(kvmppc_uvmem_bitmap, bit, 1); + spin_unlock(&kvmppc_uvmem_bitmap_lock); + + pvt = kzalloc(sizeof(*pvt), GFP_KERNEL); + if (!pvt) + goto out_clear; + + uvmem_pfn = bit + pfn_first; + kvmppc_uvmem_pfn_insert(gpa >> PAGE_SHIFT, uvmem_pfn, kvm); + + pvt->gpa = gpa; + pvt->kvm = kvm; + + dpage = pfn_to_page(uvmem_pfn); + dpage->zone_device_data = pvt; + get_page(dpage); + lock_page(dpage); + return dpage; +out_clear: + spin_lock(&kvmppc_uvmem_bitmap_lock); + bitmap_clear(kvmppc_uvmem_bitmap, bit, 1); +out: + spin_unlock(&kvmppc_uvmem_bitmap_lock); + return NULL; +} + +/* + * Alloc a PFN from private device memory pool and copy page from normal + * memory to secure memory using UV_PAGE_IN uvcall. + */ +static int +kvmppc_svm_page_in(struct vm_area_struct *vma, unsigned long start, + unsigned long end, unsigned long gpa, struct kvm *kvm, + unsigned long page_shift, bool *downgrade) +{ + unsigned long src_pfn, dst_pfn = 0; + struct migrate_vma mig; + struct page *spage; + unsigned long pfn; + struct page *dpage; + int ret = 0; + + memset(&mig, 0, sizeof(mig)); + mig.vma = vma; + mig.start = start; + mig.end = end; + mig.src = &src_pfn; + mig.dst = &dst_pfn; + + /* + * We come here with mmap_sem write lock held just for + * ksm_madvise(), otherwise we only need read mmap_sem. + * Hence downgrade to read lock once ksm_madvise() is done. + */ + ret = ksm_madvise(vma, vma->vm_start, vma->vm_end, + MADV_UNMERGEABLE, &vma->vm_flags); + downgrade_write(&kvm->mm->mmap_sem); + *downgrade = true; + if (ret) + return ret; + + ret = migrate_vma_setup(&mig); + if (ret) + return ret; + + if (!(*mig.src & MIGRATE_PFN_MIGRATE)) { + ret = -1; + goto out_finalize; + } + + dpage = kvmppc_uvmem_get_page(gpa, kvm); + if (!dpage) { + ret = -1; + goto out_finalize; + } + + pfn = *mig.src >> MIGRATE_PFN_SHIFT; + spage = migrate_pfn_to_page(*mig.src); + if (spage) + uv_page_in(kvm->arch.lpid, pfn << page_shift, gpa, 0, + page_shift); + + *mig.dst = migrate_pfn(page_to_pfn(dpage)) | MIGRATE_PFN_LOCKED; + migrate_vma_pages(&mig); +out_finalize: + migrate_vma_finalize(&mig); + return ret; +} + +/* + * Shares the page with HV, thus making it a normal page. + * + * - If the page is already secure, then provision a new page and share + * - If the page is a normal page, share the existing page + * + * In the former case, uses dev_pagemap_ops.migrate_to_ram handler + * to unmap the device page from QEMU's page tables. + */ +static unsigned long +kvmppc_share_page(struct kvm *kvm, unsigned long gpa, unsigned long page_shift) +{ + + int ret = H_PARAMETER; + struct page *uvmem_page; + struct kvmppc_uvmem_page_pvt *pvt; + unsigned long pfn; + unsigned long gfn = gpa >> page_shift; + int srcu_idx; + unsigned long uvmem_pfn; + + srcu_idx = srcu_read_lock(&kvm->srcu); + mutex_lock(&kvm->arch.uvmem_lock); + if (kvmppc_gfn_is_uvmem_pfn(gfn, kvm, &uvmem_pfn)) { + uvmem_page = pfn_to_page(uvmem_pfn); + pvt = uvmem_page->zone_device_data; + pvt->skip_page_out = true; + } + +retry: + mutex_unlock(&kvm->arch.uvmem_lock); + pfn = gfn_to_pfn(kvm, gfn); + if (is_error_noslot_pfn(pfn)) + goto out; + + mutex_lock(&kvm->arch.uvmem_lock); + if (kvmppc_gfn_is_uvmem_pfn(gfn, kvm, &uvmem_pfn)) { + uvmem_page = pfn_to_page(uvmem_pfn); + pvt = uvmem_page->zone_device_data; + pvt->skip_page_out = true; + kvm_release_pfn_clean(pfn); + goto retry; + } + + if (!uv_page_in(kvm->arch.lpid, pfn << page_shift, gpa, 0, page_shift)) + ret = H_SUCCESS; + kvm_release_pfn_clean(pfn); + mutex_unlock(&kvm->arch.uvmem_lock); +out: + srcu_read_unlock(&kvm->srcu, srcu_idx); + return ret; +} + +/* + * H_SVM_PAGE_IN: Move page from normal memory to secure memory. + * + * H_PAGE_IN_SHARED flag makes the page shared which means that the same + * memory in is visible from both UV and HV. + */ +unsigned long +kvmppc_h_svm_page_in(struct kvm *kvm, unsigned long gpa, + unsigned long flags, unsigned long page_shift) +{ + bool downgrade = false; + unsigned long start, end; + struct vm_area_struct *vma; + int srcu_idx; + unsigned long gfn = gpa >> page_shift; + int ret; + + if (!(kvm->arch.secure_guest & KVMPPC_SECURE_INIT_START)) + return H_UNSUPPORTED; + + if (page_shift != PAGE_SHIFT) + return H_P3; + + if (flags & ~H_PAGE_IN_SHARED) + return H_P2; + + if (flags & H_PAGE_IN_SHARED) + return kvmppc_share_page(kvm, gpa, page_shift); + + ret = H_PARAMETER; + srcu_idx = srcu_read_lock(&kvm->srcu); + down_write(&kvm->mm->mmap_sem); + + start = gfn_to_hva(kvm, gfn); + if (kvm_is_error_hva(start)) + goto out; + + mutex_lock(&kvm->arch.uvmem_lock); + /* Fail the page-in request of an already paged-in page */ + if (kvmppc_gfn_is_uvmem_pfn(gfn, kvm, NULL)) + goto out_unlock; + + end = start + (1UL << page_shift); + vma = find_vma_intersection(kvm->mm, start, end); + if (!vma || vma->vm_start > start || vma->vm_end < end) + goto out_unlock; + + if (!kvmppc_svm_page_in(vma, start, end, gpa, kvm, page_shift, + &downgrade)) + ret = H_SUCCESS; +out_unlock: + mutex_unlock(&kvm->arch.uvmem_lock); +out: + if (downgrade) + up_read(&kvm->mm->mmap_sem); + else + up_write(&kvm->mm->mmap_sem); + srcu_read_unlock(&kvm->srcu, srcu_idx); + return ret; +} + +/* + * Provision a new page on HV side and copy over the contents + * from secure memory using UV_PAGE_OUT uvcall. + */ +static int +kvmppc_svm_page_out(struct vm_area_struct *vma, unsigned long start, + unsigned long end, unsigned long page_shift, + struct kvm *kvm, unsigned long gpa) +{ + unsigned long src_pfn, dst_pfn = 0; + struct migrate_vma mig; + struct page *dpage, *spage; + struct kvmppc_uvmem_page_pvt *pvt; + unsigned long pfn; + int ret = U_SUCCESS; + + memset(&mig, 0, sizeof(mig)); + mig.vma = vma; + mig.start = start; + mig.end = end; + mig.src = &src_pfn; + mig.dst = &dst_pfn; + + mutex_lock(&kvm->arch.uvmem_lock); + /* The requested page is already paged-out, nothing to do */ + if (!kvmppc_gfn_is_uvmem_pfn(gpa >> page_shift, kvm, NULL)) + goto out; + + ret = migrate_vma_setup(&mig); + if (ret) + return ret; + + spage = migrate_pfn_to_page(*mig.src); + if (!spage || !(*mig.src & MIGRATE_PFN_MIGRATE)) + goto out_finalize; + + if (!is_zone_device_page(spage)) + goto out_finalize; + + dpage = alloc_page_vma(GFP_HIGHUSER, vma, start); + if (!dpage) { + ret = -1; + goto out_finalize; + } + + lock_page(dpage); + pvt = spage->zone_device_data; + pfn = page_to_pfn(dpage); + + /* + * This function is used in two cases: + * - When HV touches a secure page, for which we do UV_PAGE_OUT + * - When a secure page is converted to shared page, we *get* + * the page to essentially unmap the device page. In this + * case we skip page-out. + */ + if (!pvt->skip_page_out) + ret = uv_page_out(kvm->arch.lpid, pfn << page_shift, + gpa, 0, page_shift); + + if (ret == U_SUCCESS) + *mig.dst = migrate_pfn(pfn) | MIGRATE_PFN_LOCKED; + else { + unlock_page(dpage); + __free_page(dpage); + goto out_finalize; + } + + migrate_vma_pages(&mig); +out_finalize: + migrate_vma_finalize(&mig); +out: + mutex_unlock(&kvm->arch.uvmem_lock); + return ret; +} + +/* + * Fault handler callback that gets called when HV touches any page that + * has been moved to secure memory, we ask UV to give back the page by + * issuing UV_PAGE_OUT uvcall. + * + * This eventually results in dropping of device PFN and the newly + * provisioned page/PFN gets populated in QEMU page tables. + */ +static vm_fault_t kvmppc_uvmem_migrate_to_ram(struct vm_fault *vmf) +{ + struct kvmppc_uvmem_page_pvt *pvt = vmf->page->zone_device_data; + + if (kvmppc_svm_page_out(vmf->vma, vmf->address, + vmf->address + PAGE_SIZE, PAGE_SHIFT, + pvt->kvm, pvt->gpa)) + return VM_FAULT_SIGBUS; + else + return 0; +} + +/* + * Release the device PFN back to the pool + * + * Gets called when secure page becomes a normal page during H_SVM_PAGE_OUT. + * Gets called with kvm->arch.uvmem_lock held. + */ +static void kvmppc_uvmem_page_free(struct page *page) +{ + unsigned long pfn = page_to_pfn(page) - + (kvmppc_uvmem_pgmap.res.start >> PAGE_SHIFT); + struct kvmppc_uvmem_page_pvt *pvt; + + spin_lock(&kvmppc_uvmem_bitmap_lock); + bitmap_clear(kvmppc_uvmem_bitmap, pfn, 1); + spin_unlock(&kvmppc_uvmem_bitmap_lock); + + pvt = page->zone_device_data; + page->zone_device_data = NULL; + kvmppc_uvmem_pfn_remove(pvt->gpa >> PAGE_SHIFT, pvt->kvm); + kfree(pvt); +} + +static const struct dev_pagemap_ops kvmppc_uvmem_ops = { + .page_free = kvmppc_uvmem_page_free, + .migrate_to_ram = kvmppc_uvmem_migrate_to_ram, +}; + +/* + * H_SVM_PAGE_OUT: Move page from secure memory to normal memory. + */ +unsigned long +kvmppc_h_svm_page_out(struct kvm *kvm, unsigned long gpa, + unsigned long flags, unsigned long page_shift) +{ + unsigned long gfn = gpa >> page_shift; + unsigned long start, end; + struct vm_area_struct *vma; + int srcu_idx; + int ret; + + if (!(kvm->arch.secure_guest & KVMPPC_SECURE_INIT_START)) + return H_UNSUPPORTED; + + if (page_shift != PAGE_SHIFT) + return H_P3; + + if (flags) + return H_P2; + + ret = H_PARAMETER; + srcu_idx = srcu_read_lock(&kvm->srcu); + down_read(&kvm->mm->mmap_sem); + start = gfn_to_hva(kvm, gfn); + if (kvm_is_error_hva(start)) + goto out; + + end = start + (1UL << page_shift); + vma = find_vma_intersection(kvm->mm, start, end); + if (!vma || vma->vm_start > start || vma->vm_end < end) + goto out; + + if (!kvmppc_svm_page_out(vma, start, end, page_shift, kvm, gpa)) + ret = H_SUCCESS; +out: + up_read(&kvm->mm->mmap_sem); + srcu_read_unlock(&kvm->srcu, srcu_idx); + return ret; +} + +int kvmppc_send_page_to_uv(struct kvm *kvm, unsigned long gfn) +{ + unsigned long pfn; + int ret = U_SUCCESS; + + pfn = gfn_to_pfn(kvm, gfn); + if (is_error_noslot_pfn(pfn)) + return -EFAULT; + + mutex_lock(&kvm->arch.uvmem_lock); + if (kvmppc_gfn_is_uvmem_pfn(gfn, kvm, NULL)) + goto out; + + ret = uv_page_in(kvm->arch.lpid, pfn << PAGE_SHIFT, gfn << PAGE_SHIFT, + 0, PAGE_SHIFT); +out: + kvm_release_pfn_clean(pfn); + mutex_unlock(&kvm->arch.uvmem_lock); + return (ret == U_SUCCESS) ? RESUME_GUEST : -EFAULT; +} + +static u64 kvmppc_get_secmem_size(void) +{ + struct device_node *np; + int i, len; + const __be32 *prop; + u64 size = 0; + + np = of_find_compatible_node(NULL, NULL, "ibm,uv-firmware"); + if (!np) + goto out; + + prop = of_get_property(np, "secure-memory-ranges", &len); + if (!prop) + goto out_put; + + for (i = 0; i < len / (sizeof(*prop) * 4); i++) + size += of_read_number(prop + (i * 4) + 2, 2); + +out_put: + of_node_put(np); +out: + return size; +} + +int kvmppc_uvmem_init(void) +{ + int ret = 0; + unsigned long size; + struct resource *res; + void *addr; + unsigned long pfn_last, pfn_first; + + size = kvmppc_get_secmem_size(); + if (!size) { + /* + * Don't fail the initialization of kvm-hv module if + * the platform doesn't export ibm,uv-firmware node. + * Let normal guests run on such PEF-disabled platform. + */ + pr_info("KVMPPC-UVMEM: No support for secure guests\n"); + goto out; + } + + res = request_free_mem_region(&iomem_resource, size, "kvmppc_uvmem"); + if (IS_ERR(res)) { + ret = PTR_ERR(res); + goto out; + } + + kvmppc_uvmem_pgmap.type = MEMORY_DEVICE_PRIVATE; + kvmppc_uvmem_pgmap.res = *res; + kvmppc_uvmem_pgmap.ops = &kvmppc_uvmem_ops; + addr = memremap_pages(&kvmppc_uvmem_pgmap, NUMA_NO_NODE); + if (IS_ERR(addr)) { + ret = PTR_ERR(addr); + goto out_free_region; + } + + pfn_first = res->start >> PAGE_SHIFT; + pfn_last = pfn_first + (resource_size(res) >> PAGE_SHIFT); + kvmppc_uvmem_bitmap = kcalloc(BITS_TO_LONGS(pfn_last - pfn_first), + sizeof(unsigned long), GFP_KERNEL); + if (!kvmppc_uvmem_bitmap) { + ret = -ENOMEM; + goto out_unmap; + } + + pr_info("KVMPPC-UVMEM: Secure Memory size 0x%lx\n", size); + return ret; +out_unmap: + memunmap_pages(&kvmppc_uvmem_pgmap); +out_free_region: + release_mem_region(res->start, size); +out: + return ret; +} + +void kvmppc_uvmem_free(void) +{ + memunmap_pages(&kvmppc_uvmem_pgmap); + release_mem_region(kvmppc_uvmem_pgmap.res.start, + resource_size(&kvmppc_uvmem_pgmap.res)); + kfree(kvmppc_uvmem_bitmap); +} diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c index cc65af8fe6f7..ce4fcf76e53e 100644 --- a/arch/powerpc/kvm/book3s_pr.c +++ b/arch/powerpc/kvm/book3s_pr.c @@ -90,7 +90,43 @@ static void kvmppc_fixup_split_real(struct kvm_vcpu *vcpu) kvmppc_set_pc(vcpu, pc | SPLIT_HACK_OFFS); } -void kvmppc_unfixup_split_real(struct kvm_vcpu *vcpu); +static void kvmppc_unfixup_split_real(struct kvm_vcpu *vcpu) +{ + if (vcpu->arch.hflags & BOOK3S_HFLAG_SPLIT_HACK) { + ulong pc = kvmppc_get_pc(vcpu); + ulong lr = kvmppc_get_lr(vcpu); + if ((pc & SPLIT_HACK_MASK) == SPLIT_HACK_OFFS) + kvmppc_set_pc(vcpu, pc & ~SPLIT_HACK_MASK); + if ((lr & SPLIT_HACK_MASK) == SPLIT_HACK_OFFS) + kvmppc_set_lr(vcpu, lr & ~SPLIT_HACK_MASK); + vcpu->arch.hflags &= ~BOOK3S_HFLAG_SPLIT_HACK; + } +} + +static void kvmppc_inject_interrupt_pr(struct kvm_vcpu *vcpu, int vec, u64 srr1_flags) +{ + unsigned long msr, pc, new_msr, new_pc; + + kvmppc_unfixup_split_real(vcpu); + + msr = kvmppc_get_msr(vcpu); + pc = kvmppc_get_pc(vcpu); + new_msr = vcpu->arch.intr_msr; + new_pc = to_book3s(vcpu)->hior + vec; + +#ifdef CONFIG_PPC_BOOK3S_64 + /* If transactional, change to suspend mode on IRQ delivery */ + if (MSR_TM_TRANSACTIONAL(msr)) + new_msr |= MSR_TS_S; + else + new_msr |= msr & MSR_TS_MASK; +#endif + + kvmppc_set_srr0(vcpu, pc); + kvmppc_set_srr1(vcpu, (msr & SRR1_MSR_BITS) | srr1_flags); + kvmppc_set_pc(vcpu, new_pc); + kvmppc_set_msr(vcpu, new_msr); +} static void kvmppc_core_vcpu_load_pr(struct kvm_vcpu *vcpu, int cpu) { @@ -1761,6 +1797,7 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_pr(struct kvm *kvm, #else /* default to book3s_32 (750) */ vcpu->arch.pvr = 0x84202; + vcpu->arch.intr_msr = 0; #endif kvmppc_set_pvr_pr(vcpu, vcpu->arch.pvr); vcpu->arch.slb_nr = 64; @@ -2058,6 +2095,7 @@ static struct kvmppc_ops kvm_ops_pr = { .set_one_reg = kvmppc_set_one_reg_pr, .vcpu_load = kvmppc_core_vcpu_load_pr, .vcpu_put = kvmppc_core_vcpu_put_pr, + .inject_interrupt = kvmppc_inject_interrupt_pr, .set_msr = kvmppc_set_msr_pr, .vcpu_run = kvmppc_vcpu_run_pr, .vcpu_create = kvmppc_core_vcpu_create_pr, diff --git a/arch/powerpc/kvm/book3s_xive.c b/arch/powerpc/kvm/book3s_xive.c index 591bfb4bfd0f..66858b7d3c6b 100644 --- a/arch/powerpc/kvm/book3s_xive.c +++ b/arch/powerpc/kvm/book3s_xive.c @@ -1211,12 +1211,52 @@ void kvmppc_xive_cleanup_vcpu(struct kvm_vcpu *vcpu) vcpu->arch.xive_vcpu = NULL; } +static bool kvmppc_xive_vcpu_id_valid(struct kvmppc_xive *xive, u32 cpu) +{ + /* We have a block of xive->nr_servers VPs. We just need to check + * raw vCPU ids are below the expected limit for this guest's + * core stride ; kvmppc_pack_vcpu_id() will pack them down to an + * index that can be safely used to compute a VP id that belongs + * to the VP block. + */ + return cpu < xive->nr_servers * xive->kvm->arch.emul_smt_mode; +} + +int kvmppc_xive_compute_vp_id(struct kvmppc_xive *xive, u32 cpu, u32 *vp) +{ + u32 vp_id; + + if (!kvmppc_xive_vcpu_id_valid(xive, cpu)) { + pr_devel("Out of bounds !\n"); + return -EINVAL; + } + + if (xive->vp_base == XIVE_INVALID_VP) { + xive->vp_base = xive_native_alloc_vp_block(xive->nr_servers); + pr_devel("VP_Base=%x nr_servers=%d\n", xive->vp_base, xive->nr_servers); + + if (xive->vp_base == XIVE_INVALID_VP) + return -ENOSPC; + } + + vp_id = kvmppc_xive_vp(xive, cpu); + if (kvmppc_xive_vp_in_use(xive->kvm, vp_id)) { + pr_devel("Duplicate !\n"); + return -EEXIST; + } + + *vp = vp_id; + + return 0; +} + int kvmppc_xive_connect_vcpu(struct kvm_device *dev, struct kvm_vcpu *vcpu, u32 cpu) { struct kvmppc_xive *xive = dev->private; struct kvmppc_xive_vcpu *xc; int i, r = -EBUSY; + u32 vp_id; pr_devel("connect_vcpu(cpu=%d)\n", cpu); @@ -1228,25 +1268,25 @@ int kvmppc_xive_connect_vcpu(struct kvm_device *dev, return -EPERM; if (vcpu->arch.irq_type != KVMPPC_IRQ_DEFAULT) return -EBUSY; - if (kvmppc_xive_find_server(vcpu->kvm, cpu)) { - pr_devel("Duplicate !\n"); - return -EEXIST; - } - if (cpu >= (KVM_MAX_VCPUS * vcpu->kvm->arch.emul_smt_mode)) { - pr_devel("Out of bounds !\n"); - return -EINVAL; - } - xc = kzalloc(sizeof(*xc), GFP_KERNEL); - if (!xc) - return -ENOMEM; /* We need to synchronize with queue provisioning */ mutex_lock(&xive->lock); + + r = kvmppc_xive_compute_vp_id(xive, cpu, &vp_id); + if (r) + goto bail; + + xc = kzalloc(sizeof(*xc), GFP_KERNEL); + if (!xc) { + r = -ENOMEM; + goto bail; + } + vcpu->arch.xive_vcpu = xc; xc->xive = xive; xc->vcpu = vcpu; xc->server_num = cpu; - xc->vp_id = kvmppc_xive_vp(xive, cpu); + xc->vp_id = vp_id; xc->mfrr = 0xff; xc->valid = true; @@ -1826,6 +1866,43 @@ int kvmppc_xive_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level, return 0; } +int kvmppc_xive_set_nr_servers(struct kvmppc_xive *xive, u64 addr) +{ + u32 __user *ubufp = (u32 __user *) addr; + u32 nr_servers; + int rc = 0; + + if (get_user(nr_servers, ubufp)) + return -EFAULT; + + pr_devel("%s nr_servers=%u\n", __func__, nr_servers); + + if (!nr_servers || nr_servers > KVM_MAX_VCPU_ID) + return -EINVAL; + + mutex_lock(&xive->lock); + if (xive->vp_base != XIVE_INVALID_VP) + /* The VP block is allocated once and freed when the device + * is released. Better not allow to change its size since its + * used by connect_vcpu to validate vCPU ids are valid (eg, + * setting it back to a higher value could allow connect_vcpu + * to come up with a VP id that goes beyond the VP block, which + * is likely to cause a crash in OPAL). + */ + rc = -EBUSY; + else if (nr_servers > KVM_MAX_VCPUS) + /* We don't need more servers. Higher vCPU ids get packed + * down below KVM_MAX_VCPUS by kvmppc_pack_vcpu_id(). + */ + xive->nr_servers = KVM_MAX_VCPUS; + else + xive->nr_servers = nr_servers; + + mutex_unlock(&xive->lock); + + return rc; +} + static int xive_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr) { struct kvmppc_xive *xive = dev->private; @@ -1834,6 +1911,11 @@ static int xive_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr) switch (attr->group) { case KVM_DEV_XICS_GRP_SOURCES: return xive_set_source(xive, attr->attr, attr->addr); + case KVM_DEV_XICS_GRP_CTRL: + switch (attr->attr) { + case KVM_DEV_XICS_NR_SERVERS: + return kvmppc_xive_set_nr_servers(xive, attr->addr); + } } return -ENXIO; } @@ -1859,6 +1941,11 @@ static int xive_has_attr(struct kvm_device *dev, struct kvm_device_attr *attr) attr->attr < KVMPPC_XICS_NR_IRQS) return 0; break; + case KVM_DEV_XICS_GRP_CTRL: + switch (attr->attr) { + case KVM_DEV_XICS_NR_SERVERS: + return 0; + } } return -ENXIO; } @@ -1993,10 +2080,13 @@ static int kvmppc_xive_create(struct kvm_device *dev, u32 type) { struct kvmppc_xive *xive; struct kvm *kvm = dev->kvm; - int ret = 0; pr_devel("Creating xive for partition\n"); + /* Already there ? */ + if (kvm->arch.xive) + return -EEXIST; + xive = kvmppc_xive_get_device(kvm, type); if (!xive) return -ENOMEM; @@ -2006,12 +2096,6 @@ static int kvmppc_xive_create(struct kvm_device *dev, u32 type) xive->kvm = kvm; mutex_init(&xive->lock); - /* Already there ? */ - if (kvm->arch.xive) - ret = -EEXIST; - else - kvm->arch.xive = xive; - /* We use the default queue size set by the host */ xive->q_order = xive_native_default_eq_shift(); if (xive->q_order < PAGE_SHIFT) @@ -2019,18 +2103,16 @@ static int kvmppc_xive_create(struct kvm_device *dev, u32 type) else xive->q_page_order = xive->q_order - PAGE_SHIFT; - /* Allocate a bunch of VPs */ - xive->vp_base = xive_native_alloc_vp_block(KVM_MAX_VCPUS); - pr_devel("VP_Base=%x\n", xive->vp_base); - - if (xive->vp_base == XIVE_INVALID_VP) - ret = -ENOMEM; + /* VP allocation is delayed to the first call to connect_vcpu */ + xive->vp_base = XIVE_INVALID_VP; + /* KVM_MAX_VCPUS limits the number of VMs to roughly 64 per sockets + * on a POWER9 system. + */ + xive->nr_servers = KVM_MAX_VCPUS; xive->single_escalation = xive_native_has_single_escalation(); - if (ret) - return ret; - + kvm->arch.xive = xive; return 0; } @@ -2100,9 +2182,9 @@ static int xive_debug_show(struct seq_file *m, void *private) if (!xc) continue; - seq_printf(m, "cpu server %#x CPPR:%#x HWCPPR:%#x" + seq_printf(m, "cpu server %#x VP:%#x CPPR:%#x HWCPPR:%#x" " MFRR:%#x PEND:%#x h_xirr: R=%lld V=%lld\n", - xc->server_num, xc->cppr, xc->hw_cppr, + xc->server_num, xc->vp_id, xc->cppr, xc->hw_cppr, xc->mfrr, xc->pending, xc->stat_rm_h_xirr, xc->stat_vm_h_xirr); diff --git a/arch/powerpc/kvm/book3s_xive.h b/arch/powerpc/kvm/book3s_xive.h index 955b820ffd6d..382e3a56e789 100644 --- a/arch/powerpc/kvm/book3s_xive.h +++ b/arch/powerpc/kvm/book3s_xive.h @@ -135,6 +135,9 @@ struct kvmppc_xive { /* Flags */ u8 single_escalation; + /* Number of entries in the VP block */ + u32 nr_servers; + struct kvmppc_xive_ops *ops; struct address_space *mapping; struct mutex mapping_lock; @@ -220,6 +223,18 @@ static inline u32 kvmppc_xive_vp(struct kvmppc_xive *xive, u32 server) return xive->vp_base + kvmppc_pack_vcpu_id(xive->kvm, server); } +static inline bool kvmppc_xive_vp_in_use(struct kvm *kvm, u32 vp_id) +{ + struct kvm_vcpu *vcpu = NULL; + int i; + + kvm_for_each_vcpu(i, vcpu, kvm) { + if (vcpu->arch.xive_vcpu && vp_id == vcpu->arch.xive_vcpu->vp_id) + return true; + } + return false; +} + /* * Mapping between guest priorities and host priorities * is as follow. @@ -284,6 +299,8 @@ int kvmppc_xive_attach_escalation(struct kvm_vcpu *vcpu, u8 prio, struct kvmppc_xive *kvmppc_xive_get_device(struct kvm *kvm, u32 type); void xive_cleanup_single_escalation(struct kvm_vcpu *vcpu, struct kvmppc_xive_vcpu *xc, int irq); +int kvmppc_xive_compute_vp_id(struct kvmppc_xive *xive, u32 cpu, u32 *vp); +int kvmppc_xive_set_nr_servers(struct kvmppc_xive *xive, u64 addr); #endif /* CONFIG_KVM_XICS */ #endif /* _KVM_PPC_BOOK3S_XICS_H */ diff --git a/arch/powerpc/kvm/book3s_xive_native.c b/arch/powerpc/kvm/book3s_xive_native.c index 248c1ea9e788..d83adb1e1490 100644 --- a/arch/powerpc/kvm/book3s_xive_native.c +++ b/arch/powerpc/kvm/book3s_xive_native.c @@ -50,6 +50,24 @@ static void kvmppc_xive_native_cleanup_queue(struct kvm_vcpu *vcpu, int prio) } } +static int kvmppc_xive_native_configure_queue(u32 vp_id, struct xive_q *q, + u8 prio, __be32 *qpage, + u32 order, bool can_escalate) +{ + int rc; + __be32 *qpage_prev = q->qpage; + + rc = xive_native_configure_queue(vp_id, q, prio, qpage, order, + can_escalate); + if (rc) + return rc; + + if (qpage_prev) + put_page(virt_to_page(qpage_prev)); + + return rc; +} + void kvmppc_xive_native_cleanup_vcpu(struct kvm_vcpu *vcpu) { struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu; @@ -106,6 +124,7 @@ int kvmppc_xive_native_connect_vcpu(struct kvm_device *dev, struct kvmppc_xive *xive = dev->private; struct kvmppc_xive_vcpu *xc = NULL; int rc; + u32 vp_id; pr_devel("native_connect_vcpu(server=%d)\n", server_num); @@ -117,18 +136,12 @@ int kvmppc_xive_native_connect_vcpu(struct kvm_device *dev, return -EPERM; if (vcpu->arch.irq_type != KVMPPC_IRQ_DEFAULT) return -EBUSY; - if (server_num >= (KVM_MAX_VCPUS * vcpu->kvm->arch.emul_smt_mode)) { - pr_devel("Out of bounds !\n"); - return -EINVAL; - } mutex_lock(&xive->lock); - if (kvmppc_xive_find_server(vcpu->kvm, server_num)) { - pr_devel("Duplicate !\n"); - rc = -EEXIST; + rc = kvmppc_xive_compute_vp_id(xive, server_num, &vp_id); + if (rc) goto bail; - } xc = kzalloc(sizeof(*xc), GFP_KERNEL); if (!xc) { @@ -141,7 +154,7 @@ int kvmppc_xive_native_connect_vcpu(struct kvm_device *dev, xc->vcpu = vcpu; xc->server_num = server_num; - xc->vp_id = kvmppc_xive_vp(xive, server_num); + xc->vp_id = vp_id; xc->valid = true; vcpu->arch.irq_type = KVMPPC_IRQ_XIVE; @@ -580,19 +593,14 @@ static int kvmppc_xive_native_set_queue_config(struct kvmppc_xive *xive, q->guest_qaddr = 0; q->guest_qshift = 0; - rc = xive_native_configure_queue(xc->vp_id, q, priority, - NULL, 0, true); + rc = kvmppc_xive_native_configure_queue(xc->vp_id, q, priority, + NULL, 0, true); if (rc) { pr_err("Failed to reset queue %d for VCPU %d: %d\n", priority, xc->server_num, rc); return rc; } - if (q->qpage) { - put_page(virt_to_page(q->qpage)); - q->qpage = NULL; - } - return 0; } @@ -622,12 +630,6 @@ static int kvmppc_xive_native_set_queue_config(struct kvmppc_xive *xive, srcu_idx = srcu_read_lock(&kvm->srcu); gfn = gpa_to_gfn(kvm_eq.qaddr); - page = gfn_to_page(kvm, gfn); - if (is_error_page(page)) { - srcu_read_unlock(&kvm->srcu, srcu_idx); - pr_err("Couldn't get queue page %llx!\n", kvm_eq.qaddr); - return -EINVAL; - } page_size = kvm_host_page_size(kvm, gfn); if (1ull << kvm_eq.qshift > page_size) { @@ -636,6 +638,13 @@ static int kvmppc_xive_native_set_queue_config(struct kvmppc_xive *xive, return -EINVAL; } + page = gfn_to_page(kvm, gfn); + if (is_error_page(page)) { + srcu_read_unlock(&kvm->srcu, srcu_idx); + pr_err("Couldn't get queue page %llx!\n", kvm_eq.qaddr); + return -EINVAL; + } + qaddr = page_to_virt(page) + (kvm_eq.qaddr & ~PAGE_MASK); srcu_read_unlock(&kvm->srcu, srcu_idx); @@ -651,8 +660,8 @@ static int kvmppc_xive_native_set_queue_config(struct kvmppc_xive *xive, * OPAL level because the use of END ESBs is not supported by * Linux. */ - rc = xive_native_configure_queue(xc->vp_id, q, priority, - (__be32 *) qaddr, kvm_eq.qshift, true); + rc = kvmppc_xive_native_configure_queue(xc->vp_id, q, priority, + (__be32 *) qaddr, kvm_eq.qshift, true); if (rc) { pr_err("Failed to configure queue %d for VCPU %d: %d\n", priority, xc->server_num, rc); @@ -926,6 +935,8 @@ static int kvmppc_xive_native_set_attr(struct kvm_device *dev, return kvmppc_xive_reset(xive); case KVM_DEV_XIVE_EQ_SYNC: return kvmppc_xive_native_eq_sync(xive); + case KVM_DEV_XIVE_NR_SERVERS: + return kvmppc_xive_set_nr_servers(xive, attr->addr); } break; case KVM_DEV_XIVE_GRP_SOURCE: @@ -965,6 +976,7 @@ static int kvmppc_xive_native_has_attr(struct kvm_device *dev, switch (attr->attr) { case KVM_DEV_XIVE_RESET: case KVM_DEV_XIVE_EQ_SYNC: + case KVM_DEV_XIVE_NR_SERVERS: return 0; } break; @@ -1065,7 +1077,6 @@ static int kvmppc_xive_native_create(struct kvm_device *dev, u32 type) { struct kvmppc_xive *xive; struct kvm *kvm = dev->kvm; - int ret = 0; pr_devel("Creating xive native device\n"); @@ -1079,27 +1090,20 @@ static int kvmppc_xive_native_create(struct kvm_device *dev, u32 type) dev->private = xive; xive->dev = dev; xive->kvm = kvm; - kvm->arch.xive = xive; mutex_init(&xive->mapping_lock); mutex_init(&xive->lock); - /* - * Allocate a bunch of VPs. KVM_MAX_VCPUS is a large value for - * a default. Getting the max number of CPUs the VM was - * configured with would improve our usage of the XIVE VP space. + /* VP allocation is delayed to the first call to connect_vcpu */ + xive->vp_base = XIVE_INVALID_VP; + /* KVM_MAX_VCPUS limits the number of VMs to roughly 64 per sockets + * on a POWER9 system. */ - xive->vp_base = xive_native_alloc_vp_block(KVM_MAX_VCPUS); - pr_devel("VP_Base=%x\n", xive->vp_base); - - if (xive->vp_base == XIVE_INVALID_VP) - ret = -ENXIO; + xive->nr_servers = KVM_MAX_VCPUS; xive->single_escalation = xive_native_has_single_escalation(); xive->ops = &kvmppc_xive_native_ops; - if (ret) - return ret; - + kvm->arch.xive = xive; return 0; } @@ -1202,8 +1206,8 @@ static int xive_native_debug_show(struct seq_file *m, void *private) if (!xc) continue; - seq_printf(m, "cpu server %#x NSR=%02x CPPR=%02x IBP=%02x PIPR=%02x w01=%016llx w2=%08x\n", - xc->server_num, + seq_printf(m, "cpu server %#x VP=%#x NSR=%02x CPPR=%02x IBP=%02x PIPR=%02x w01=%016llx w2=%08x\n", + xc->server_num, xc->vp_id, vcpu->arch.xive_saved_state.nsr, vcpu->arch.xive_saved_state.cppr, vcpu->arch.xive_saved_state.ipb, diff --git a/arch/powerpc/kvm/e500_mmu_host.c b/arch/powerpc/kvm/e500_mmu_host.c index 321db0fdb9db..425d13806645 100644 --- a/arch/powerpc/kvm/e500_mmu_host.c +++ b/arch/powerpc/kvm/e500_mmu_host.c @@ -355,9 +355,9 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500, if (tlbsel == 1) { struct vm_area_struct *vma; - down_read(¤t->mm->mmap_sem); + down_read(&kvm->mm->mmap_sem); - vma = find_vma(current->mm, hva); + vma = find_vma(kvm->mm, hva); if (vma && hva >= vma->vm_start && (vma->vm_flags & VM_PFNMAP)) { /* @@ -441,7 +441,7 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500, tsize = max(BOOK3E_PAGESZ_4K, tsize & ~1); } - up_read(¤t->mm->mmap_sem); + up_read(&kvm->mm->mmap_sem); } if (likely(!pfnmap)) { diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 3a77bb643452..416fb3d2a1d0 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -31,6 +31,8 @@ #include <asm/hvcall.h> #include <asm/plpar_wrappers.h> #endif +#include <asm/ultravisor.h> +#include <asm/kvm_host.h> #include "timing.h" #include "irq.h" @@ -522,6 +524,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_IMMEDIATE_EXIT: r = 1; break; + case KVM_CAP_PPC_GUEST_DEBUG_SSTEP: + /* fall through */ case KVM_CAP_PPC_PAIRED_SINGLES: case KVM_CAP_PPC_OSI: case KVM_CAP_PPC_GET_PVINFO: @@ -2411,6 +2415,16 @@ long kvm_arch_vm_ioctl(struct file *filp, r = -EFAULT; break; } + case KVM_PPC_SVM_OFF: { + struct kvm *kvm = filp->private_data; + + r = 0; + if (!kvm->arch.kvm_ops->svm_off) + goto out; + + r = kvm->arch.kvm_ops->svm_off(kvm); + break; + } default: { struct kvm *kvm = filp->private_data; r = kvm->arch.kvm_ops->arch_vm_ioctl(filp, ioctl, arg); diff --git a/arch/powerpc/mm/book3s32/mmu.c b/arch/powerpc/mm/book3s32/mmu.c index 84d5fab94f8f..69b2419accef 100644 --- a/arch/powerpc/mm/book3s32/mmu.c +++ b/arch/powerpc/mm/book3s32/mmu.c @@ -251,9 +251,18 @@ void __init setbat(int index, unsigned long virt, phys_addr_t phys, { unsigned int bl; int wimgxpp; - struct ppc_bat *bat = BATS[index]; + struct ppc_bat *bat; unsigned long flags = pgprot_val(prot); + if (index == -1) + index = find_free_bat(); + if (index == -1) { + pr_err("%s: no BAT available for mapping 0x%llx\n", __func__, + (unsigned long long)phys); + return; + } + bat = BATS[index]; + if ((flags & _PAGE_NO_CACHE) || (cpu_has_feature(CPU_FTR_NEED_COHERENT) == 0)) flags &= ~_PAGE_COHERENT; diff --git a/arch/powerpc/mm/book3s64/hash_native.c b/arch/powerpc/mm/book3s64/hash_native.c index 523e42eb11da..d2d8237ea9d5 100644 --- a/arch/powerpc/mm/book3s64/hash_native.c +++ b/arch/powerpc/mm/book3s64/hash_native.c @@ -482,19 +482,12 @@ static long native_hpte_updatepp(unsigned long slot, unsigned long newpp, return ret; } -static long native_hpte_find(unsigned long vpn, int psize, int ssize) +static long __native_hpte_find(unsigned long want_v, unsigned long slot) { struct hash_pte *hptep; - unsigned long hash; + unsigned long hpte_v; unsigned long i; - long slot; - unsigned long want_v, hpte_v; - hash = hpt_hash(vpn, mmu_psize_defs[psize].shift, ssize); - want_v = hpte_encode_avpn(vpn, psize, ssize); - - /* Bolted mappings are only ever in the primary group */ - slot = (hash & htab_hash_mask) * HPTES_PER_GROUP; for (i = 0; i < HPTES_PER_GROUP; i++) { hptep = htab_address + slot; @@ -508,6 +501,33 @@ static long native_hpte_find(unsigned long vpn, int psize, int ssize) return -1; } +static long native_hpte_find(unsigned long vpn, int psize, int ssize) +{ + unsigned long hpte_group; + unsigned long want_v; + unsigned long hash; + long slot; + + hash = hpt_hash(vpn, mmu_psize_defs[psize].shift, ssize); + want_v = hpte_encode_avpn(vpn, psize, ssize); + + /* + * We try to keep bolted entries always in primary hash + * But in some case we can find them in secondary too. + */ + hpte_group = (hash & htab_hash_mask) * HPTES_PER_GROUP; + slot = __native_hpte_find(want_v, hpte_group); + if (slot < 0) { + /* Try in secondary */ + hpte_group = (~hash & htab_hash_mask) * HPTES_PER_GROUP; + slot = __native_hpte_find(want_v, hpte_group); + if (slot < 0) + return -1; + } + + return slot; +} + /* * Update the page protection bits. Intended to be used to create * guard pages for kernel data structures on pages which are bolted diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c index 6c123760164e..b30435c7d804 100644 --- a/arch/powerpc/mm/book3s64/hash_utils.c +++ b/arch/powerpc/mm/book3s64/hash_utils.c @@ -263,6 +263,7 @@ int htab_bolt_mapping(unsigned long vstart, unsigned long vend, unsigned long vsid = get_kernel_vsid(vaddr, ssize); unsigned long vpn = hpt_vpn(vaddr, vsid, ssize); unsigned long tprot = prot; + bool secondary_hash = false; /* * If we hit a bad address return error. @@ -291,13 +292,31 @@ int htab_bolt_mapping(unsigned long vstart, unsigned long vend, hpteg = ((hash & htab_hash_mask) * HPTES_PER_GROUP); BUG_ON(!mmu_hash_ops.hpte_insert); +repeat: ret = mmu_hash_ops.hpte_insert(hpteg, vpn, paddr, tprot, HPTE_V_BOLTED, psize, psize, ssize); + if (ret == -1) { + /* + * Try to to keep bolted entries in primary. + * Remove non bolted entries and try insert again + */ + ret = mmu_hash_ops.hpte_remove(hpteg); + if (ret != -1) + ret = mmu_hash_ops.hpte_insert(hpteg, vpn, paddr, tprot, + HPTE_V_BOLTED, psize, psize, + ssize); + if (ret == -1 && !secondary_hash) { + secondary_hash = true; + hpteg = ((~hash & htab_hash_mask) * HPTES_PER_GROUP); + goto repeat; + } + } if (ret < 0) break; + cond_resched(); #ifdef CONFIG_DEBUG_PAGEALLOC if (debug_pagealloc_enabled() && (paddr >> PAGE_SHIFT) < linear_map_hash_count) diff --git a/arch/powerpc/mm/book3s64/pkeys.c b/arch/powerpc/mm/book3s64/pkeys.c index ae7fca40e5b3..59e0ebbd8036 100644 --- a/arch/powerpc/mm/book3s64/pkeys.c +++ b/arch/powerpc/mm/book3s64/pkeys.c @@ -307,16 +307,6 @@ void thread_pkey_regs_init(struct thread_struct *thread) write_iamr(pkey_iamr_mask); } -static inline bool pkey_allows_readwrite(int pkey) -{ - int pkey_shift = pkeyshift(pkey); - - if (!is_pkey_enabled(pkey)) - return true; - - return !(read_amr() & ((AMR_RD_BIT|AMR_WR_BIT) << pkey_shift)); -} - int __execute_only_pkey(struct mm_struct *mm) { return mm->context.execute_only_pkey; diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c index 6ee17d09649c..974109bb85db 100644 --- a/arch/powerpc/mm/book3s64/radix_pgtable.c +++ b/arch/powerpc/mm/book3s64/radix_pgtable.c @@ -13,6 +13,7 @@ #include <linux/memblock.h> #include <linux/of_fdt.h> #include <linux/mm.h> +#include <linux/hugetlb.h> #include <linux/string_helpers.h> #include <linux/stop_machine.h> diff --git a/arch/powerpc/mm/book3s64/radix_tlb.c b/arch/powerpc/mm/book3s64/radix_tlb.c index 67af871190c6..a95175c0972b 100644 --- a/arch/powerpc/mm/book3s64/radix_tlb.c +++ b/arch/powerpc/mm/book3s64/radix_tlb.c @@ -732,18 +732,13 @@ local: } preempt_enable(); } + void radix__flush_all_mm(struct mm_struct *mm) { __flush_all_mm(mm, false); } EXPORT_SYMBOL(radix__flush_all_mm); -void radix__flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr) -{ - tlb->need_flush_all = 1; -} -EXPORT_SYMBOL(radix__flush_tlb_pwc); - void radix__flush_tlb_page_psize(struct mm_struct *mm, unsigned long vmaddr, int psize) { @@ -832,8 +827,7 @@ static unsigned long tlb_single_page_flush_ceiling __read_mostly = 33; static unsigned long tlb_local_single_page_flush_ceiling __read_mostly = POWER9_TLB_SETS_RADIX * 2; static inline void __radix__flush_tlb_range(struct mm_struct *mm, - unsigned long start, unsigned long end, - bool flush_all_sizes) + unsigned long start, unsigned long end) { unsigned long pid; @@ -879,26 +873,16 @@ is_local: } } } else { - bool hflush = flush_all_sizes; - bool gflush = flush_all_sizes; + bool hflush = false; unsigned long hstart, hend; - unsigned long gstart, gend; - if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) - hflush = true; - - if (hflush) { + if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) { hstart = (start + PMD_SIZE - 1) & PMD_MASK; hend = end & PMD_MASK; if (hstart == hend) hflush = false; - } - - if (gflush) { - gstart = (start + PUD_SIZE - 1) & PUD_MASK; - gend = end & PUD_MASK; - if (gstart == gend) - gflush = false; + else + hflush = true; } if (local) { @@ -907,9 +891,6 @@ is_local: if (hflush) __tlbiel_va_range(hstart, hend, pid, PMD_SIZE, MMU_PAGE_2M); - if (gflush) - __tlbiel_va_range(gstart, gend, pid, - PUD_SIZE, MMU_PAGE_1G); asm volatile("ptesync": : :"memory"); } else if (cputlb_use_tlbie()) { asm volatile("ptesync": : :"memory"); @@ -917,10 +898,6 @@ is_local: if (hflush) __tlbie_va_range(hstart, hend, pid, PMD_SIZE, MMU_PAGE_2M); - if (gflush) - __tlbie_va_range(gstart, gend, pid, - PUD_SIZE, MMU_PAGE_1G); - asm volatile("eieio; tlbsync; ptesync": : :"memory"); } else { _tlbiel_va_range_multicast(mm, @@ -928,9 +905,6 @@ is_local: if (hflush) _tlbiel_va_range_multicast(mm, hstart, hend, pid, PMD_SIZE, MMU_PAGE_2M, false); - if (gflush) - _tlbiel_va_range_multicast(mm, - gstart, gend, pid, PUD_SIZE, MMU_PAGE_1G, false); } } preempt_enable(); @@ -945,7 +919,7 @@ void radix__flush_tlb_range(struct vm_area_struct *vma, unsigned long start, return radix__flush_hugetlb_tlb_range(vma, start, end); #endif - __radix__flush_tlb_range(vma->vm_mm, start, end, false); + __radix__flush_tlb_range(vma->vm_mm, start, end); } EXPORT_SYMBOL(radix__flush_tlb_range); @@ -1021,53 +995,19 @@ void radix__tlb_flush(struct mmu_gather *tlb) * that flushes the process table entry cache upon process teardown. * See the comment for radix in arch_exit_mmap(). */ - if (tlb->fullmm) { + if (tlb->fullmm || tlb->need_flush_all) { __flush_all_mm(mm, true); -#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLB_PAGE) - } else if (mm_tlb_flush_nested(mm)) { - /* - * If there is a concurrent invalidation that is clearing ptes, - * then it's possible this invalidation will miss one of those - * cleared ptes and miss flushing the TLB. If this invalidate - * returns before the other one flushes TLBs, that can result - * in it returning while there are still valid TLBs inside the - * range to be invalidated. - * - * See mm/memory.c:tlb_finish_mmu() for more details. - * - * The solution to this is ensure the entire range is always - * flushed here. The problem for powerpc is that the flushes - * are page size specific, so this "forced flush" would not - * do the right thing if there are a mix of page sizes in - * the range to be invalidated. So use __flush_tlb_range - * which invalidates all possible page sizes in the range. - * - * PWC flush probably is not be required because the core code - * shouldn't free page tables in this path, but accounting - * for the possibility makes us a bit more robust. - * - * need_flush_all is an uncommon case because page table - * teardown should be done with exclusive locks held (but - * after locks are dropped another invalidate could come - * in), it could be optimized further if necessary. - */ - if (!tlb->need_flush_all) - __radix__flush_tlb_range(mm, start, end, true); - else - radix__flush_all_mm(mm); -#endif } else if ( (psize = radix_get_mmu_psize(page_size)) == -1) { - if (!tlb->need_flush_all) + if (!tlb->freed_tables) radix__flush_tlb_mm(mm); else radix__flush_all_mm(mm); } else { - if (!tlb->need_flush_all) + if (!tlb->freed_tables) radix__flush_tlb_range_psize(mm, start, end, psize); else radix__flush_tlb_pwc_range_psize(mm, start, end, psize); } - tlb->need_flush_all = 0; } static __always_inline void __radix__flush_tlb_range_psize(struct mm_struct *mm, diff --git a/arch/powerpc/mm/dma-noncoherent.c b/arch/powerpc/mm/dma-noncoherent.c index 2a82984356f8..5ab4f868e919 100644 --- a/arch/powerpc/mm/dma-noncoherent.c +++ b/arch/powerpc/mm/dma-noncoherent.c @@ -104,14 +104,14 @@ static void __dma_sync_page(phys_addr_t paddr, size_t size, int dir) #endif } -void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr, - size_t size, enum dma_data_direction dir) +void arch_sync_dma_for_device(phys_addr_t paddr, size_t size, + enum dma_data_direction dir) { __dma_sync_page(paddr, size, dir); } -void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr, - size_t size, enum dma_data_direction dir) +void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size, + enum dma_data_direction dir) { __dma_sync_page(paddr, size, dir); } diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index 8432c281de92..b5047f9b5dec 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -645,6 +645,7 @@ NOKPROBE_SYMBOL(do_page_fault); void bad_page_fault(struct pt_regs *regs, unsigned long address, int sig) { const struct exception_table_entry *entry; + int is_write = page_fault_is_write(regs->dsisr); /* Are we prepared to handle this fault? */ if ((entry = search_exception_tables(regs->nip)) != NULL) { @@ -658,9 +659,10 @@ void bad_page_fault(struct pt_regs *regs, unsigned long address, int sig) case 0x300: case 0x380: case 0xe00: - pr_alert("BUG: %s at 0x%08lx\n", + pr_alert("BUG: %s on %s at 0x%08lx\n", regs->dar < PAGE_SIZE ? "Kernel NULL pointer dereference" : - "Unable to handle kernel data access", regs->dar); + "Unable to handle kernel data access", + is_write ? "write" : "read", regs->dar); break; case 0x400: case 0x480: diff --git a/arch/powerpc/mm/init-common.c b/arch/powerpc/mm/init-common.c index a84da92920f7..42ef7a6e6098 100644 --- a/arch/powerpc/mm/init-common.c +++ b/arch/powerpc/mm/init-common.c @@ -21,6 +21,13 @@ #include <asm/pgtable.h> #include <asm/kup.h> +phys_addr_t memstart_addr __ro_after_init = (phys_addr_t)~0ull; +EXPORT_SYMBOL_GPL(memstart_addr); +phys_addr_t kernstart_addr __ro_after_init; +EXPORT_SYMBOL_GPL(kernstart_addr); +unsigned long kernstart_virt_addr __ro_after_init = KERNELBASE; +EXPORT_SYMBOL_GPL(kernstart_virt_addr); + static bool disable_kuep = !IS_ENABLED(CONFIG_PPC_KUEP); static bool disable_kuap = !IS_ENABLED(CONFIG_PPC_KUAP); diff --git a/arch/powerpc/mm/init_32.c b/arch/powerpc/mm/init_32.c index b04896a88d79..872df48ae41b 100644 --- a/arch/powerpc/mm/init_32.c +++ b/arch/powerpc/mm/init_32.c @@ -56,11 +56,6 @@ phys_addr_t total_memory; phys_addr_t total_lowmem; -phys_addr_t memstart_addr = (phys_addr_t)~0ull; -EXPORT_SYMBOL(memstart_addr); -phys_addr_t kernstart_addr; -EXPORT_SYMBOL(kernstart_addr); - #ifdef CONFIG_RELOCATABLE /* Used in __va()/__pa() */ long long virt_phys_offset; diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c index 4e08246acd79..4002ced3596f 100644 --- a/arch/powerpc/mm/init_64.c +++ b/arch/powerpc/mm/init_64.c @@ -63,38 +63,48 @@ #include <mm/mmu_decl.h> -phys_addr_t memstart_addr = ~0; -EXPORT_SYMBOL_GPL(memstart_addr); -phys_addr_t kernstart_addr; -EXPORT_SYMBOL_GPL(kernstart_addr); - #ifdef CONFIG_SPARSEMEM_VMEMMAP /* - * Given an address within the vmemmap, determine the pfn of the page that - * represents the start of the section it is within. Note that we have to + * Given an address within the vmemmap, determine the page that + * represents the start of the subsection it is within. Note that we have to * do this by hand as the proffered address may not be correctly aligned. * Subtraction of non-aligned pointers produces undefined results. */ -static unsigned long __meminit vmemmap_section_start(unsigned long page) +static struct page * __meminit vmemmap_subsection_start(unsigned long vmemmap_addr) { - unsigned long offset = page - ((unsigned long)(vmemmap)); + unsigned long start_pfn; + unsigned long offset = vmemmap_addr - ((unsigned long)(vmemmap)); /* Return the pfn of the start of the section. */ - return (offset / sizeof(struct page)) & PAGE_SECTION_MASK; + start_pfn = (offset / sizeof(struct page)) & PAGE_SUBSECTION_MASK; + return pfn_to_page(start_pfn); } /* - * Check if this vmemmap page is already initialised. If any section - * which overlaps this vmemmap page is initialised then this page is - * initialised already. + * Since memory is added in sub-section chunks, before creating a new vmemmap + * mapping, the kernel should check whether there is an existing memmap mapping + * covering the new subsection added. This is needed because kernel can map + * vmemmap area using 16MB pages which will cover a memory range of 16G. Such + * a range covers multiple subsections (2M) + * + * If any subsection in the 16G range mapped by vmemmap is valid we consider the + * vmemmap populated (There is a page table entry already present). We can't do + * a page table lookup here because with the hash translation we don't keep + * vmemmap details in linux page table. */ -static int __meminit vmemmap_populated(unsigned long start, int page_size) +static int __meminit vmemmap_populated(unsigned long vmemmap_addr, int vmemmap_map_size) { - unsigned long end = start + page_size; - start = (unsigned long)(pfn_to_page(vmemmap_section_start(start))); + struct page *start; + unsigned long vmemmap_end = vmemmap_addr + vmemmap_map_size; + start = vmemmap_subsection_start(vmemmap_addr); - for (; start < end; start += (PAGES_PER_SECTION * sizeof(struct page))) - if (pfn_valid(page_to_pfn((struct page *)start))) + for (; (unsigned long)start < vmemmap_end; start += PAGES_PER_SUBSECTION) + /* + * pfn valid check here is intended to really check + * whether we have any subsection already initialized + * in this range. + */ + if (pfn_valid(page_to_pfn(start))) return 1; return 0; @@ -201,6 +211,12 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, void *p = NULL; int rc; + /* + * This vmemmap range is backing different subsections. If any + * of that subsection is marked valid, that means we already + * have initialized a page table covering this range and hence + * the vmemmap range is populated. + */ if (vmemmap_populated(start, page_size)) continue; @@ -290,9 +306,10 @@ void __ref vmemmap_free(unsigned long start, unsigned long end, struct page *page; /* - * the section has already be marked as invalid, so - * vmemmap_populated() true means some other sections still - * in this page, so skip it. + * We have already marked the subsection we are trying to remove + * invalid. So if we want to remove the vmemmap range, we + * need to make sure there is no subsection marked valid + * in this range. */ if (vmemmap_populated(start, page_size)) continue; diff --git a/arch/powerpc/mm/ioremap_32.c b/arch/powerpc/mm/ioremap_32.c index f36121f25243..743e11384dea 100644 --- a/arch/powerpc/mm/ioremap_32.c +++ b/arch/powerpc/mm/ioremap_32.c @@ -68,6 +68,7 @@ __ioremap_caller(phys_addr_t addr, unsigned long size, pgprot_t prot, void *call /* * Should check if it is a candidate for a BAT mapping */ + pr_warn("ioremap() called early from %pS. Use early_ioremap() instead\n", caller); err = early_ioremap_range(ioremap_bot - size, p, size, prot); if (err) diff --git a/arch/powerpc/mm/ioremap_64.c b/arch/powerpc/mm/ioremap_64.c index fd29e51700cd..50a99d9684f7 100644 --- a/arch/powerpc/mm/ioremap_64.c +++ b/arch/powerpc/mm/ioremap_64.c @@ -81,6 +81,8 @@ void __iomem *__ioremap_caller(phys_addr_t addr, unsigned long size, if (slab_is_available()) return do_ioremap(paligned, offset, size, prot, caller); + pr_warn("ioremap() called early from %pS. Use early_ioremap() instead\n", caller); + err = early_ioremap_range(ioremap_bot, paligned, size, prot); if (err) return NULL; diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index be941d382c8d..ad299e72ec30 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -31,6 +31,7 @@ #include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/memremap.h> +#include <linux/dma-direct.h> #include <asm/pgalloc.h> #include <asm/prom.h> @@ -104,6 +105,27 @@ int __weak remove_section_mapping(unsigned long start, unsigned long end) return -ENODEV; } +#define FLUSH_CHUNK_SIZE SZ_1G +/** + * flush_dcache_range_chunked(): Write any modified data cache blocks out to + * memory and invalidate them, in chunks of up to FLUSH_CHUNK_SIZE + * Does not invalidate the corresponding instruction cache blocks. + * + * @start: the start address + * @stop: the stop address (exclusive) + * @chunk: the max size of the chunks + */ +static void flush_dcache_range_chunked(unsigned long start, unsigned long stop, + unsigned long chunk) +{ + unsigned long i; + + for (i = start; i < stop; i += chunk) { + flush_dcache_range(i, min(stop, start + chunk)); + cond_resched(); + } +} + int __ref arch_add_memory(int nid, u64 start, u64 size, struct mhp_restrictions *restrictions) { @@ -120,7 +142,6 @@ int __ref arch_add_memory(int nid, u64 start, u64 size, start, start + size, rc); return -EFAULT; } - flush_dcache_range(start, start + size); return __add_pages(nid, start_pfn, nr_pages, restrictions); } @@ -137,7 +158,8 @@ void __ref arch_remove_memory(int nid, u64 start, u64 size, /* Remove htab bolted mappings for this section of memory */ start = (unsigned long)__va(start); - flush_dcache_range(start, start + size); + flush_dcache_range_chunked(start, start + size, FLUSH_CHUNK_SIZE); + ret = remove_section_mapping(start, start + size); WARN_ON_ONCE(ret); @@ -201,10 +223,10 @@ static int __init mark_nonram_nosave(void) * everything else. GFP_DMA32 page allocations automatically fall back to * ZONE_DMA. * - * By using 31-bit unconditionally, we can exploit ARCH_ZONE_DMA_BITS to - * inform the generic DMA mapping code. 32-bit only devices (if not handled - * by an IOMMU anyway) will take a first dip into ZONE_NORMAL and get - * otherwise served by ZONE_DMA. + * By using 31-bit unconditionally, we can exploit zone_dma_bits to inform the + * generic DMA mapping code. 32-bit only devices (if not handled by an IOMMU + * anyway) will take a first dip into ZONE_NORMAL and get otherwise served by + * ZONE_DMA. */ static unsigned long max_zone_pfns[MAX_NR_ZONES]; @@ -216,15 +238,13 @@ void __init paging_init(void) unsigned long long total_ram = memblock_phys_mem_size(); phys_addr_t top_of_ram = memblock_end_of_DRAM(); -#ifdef CONFIG_PPC32 - unsigned long v = __fix_to_virt(__end_of_fixed_addresses - 1); - unsigned long end = __fix_to_virt(FIX_HOLE); +#ifdef CONFIG_HIGHMEM + unsigned long v = __fix_to_virt(FIX_KMAP_END); + unsigned long end = __fix_to_virt(FIX_KMAP_BEGIN); for (; v < end; v += PAGE_SIZE) map_kernel_page(v, 0, __pgprot(0)); /* XXX gross */ -#endif -#ifdef CONFIG_HIGHMEM map_kernel_page(PKMAP_BASE, 0, __pgprot(0)); /* XXX gross */ pkmap_page_table = virt_to_kpte(PKMAP_BASE); @@ -237,9 +257,18 @@ void __init paging_init(void) printk(KERN_DEBUG "Memory hole size: %ldMB\n", (long int)((top_of_ram - total_ram) >> 20)); + /* + * Allow 30-bit DMA for very limited Broadcom wifi chips on many + * powerbooks. + */ + if (IS_ENABLED(CONFIG_PPC32)) + zone_dma_bits = 30; + else + zone_dma_bits = 31; + #ifdef CONFIG_ZONE_DMA max_zone_pfns[ZONE_DMA] = min(max_low_pfn, - 1UL << (ARCH_ZONE_DMA_BITS - PAGE_SHIFT)); + 1UL << (zone_dma_bits - PAGE_SHIFT)); #endif max_zone_pfns[ZONE_NORMAL] = max_low_pfn; #ifdef CONFIG_HIGHMEM @@ -318,6 +347,120 @@ void free_initmem(void) free_initmem_default(POISON_FREE_INITMEM); } +/** + * flush_coherent_icache() - if a CPU has a coherent icache, flush it + * @addr: The base address to use (can be any valid address, the whole cache will be flushed) + * Return true if the cache was flushed, false otherwise + */ +static inline bool flush_coherent_icache(unsigned long addr) +{ + /* + * For a snooping icache, we still need a dummy icbi to purge all the + * prefetched instructions from the ifetch buffers. We also need a sync + * before the icbi to order the the actual stores to memory that might + * have modified instructions with the icbi. + */ + if (cpu_has_feature(CPU_FTR_COHERENT_ICACHE)) { + mb(); /* sync */ + icbi((void *)addr); + mb(); /* sync */ + isync(); + return true; + } + + return false; +} + +/** + * invalidate_icache_range() - Flush the icache by issuing icbi across an address range + * @start: the start address + * @stop: the stop address (exclusive) + */ +static void invalidate_icache_range(unsigned long start, unsigned long stop) +{ + unsigned long shift = l1_icache_shift(); + unsigned long bytes = l1_icache_bytes(); + char *addr = (char *)(start & ~(bytes - 1)); + unsigned long size = stop - (unsigned long)addr + (bytes - 1); + unsigned long i; + + for (i = 0; i < size >> shift; i++, addr += bytes) + icbi(addr); + + mb(); /* sync */ + isync(); +} + +/** + * flush_icache_range: Write any modified data cache blocks out to memory + * and invalidate the corresponding blocks in the instruction cache + * + * Generic code will call this after writing memory, before executing from it. + * + * @start: the start address + * @stop: the stop address (exclusive) + */ +void flush_icache_range(unsigned long start, unsigned long stop) +{ + if (flush_coherent_icache(start)) + return; + + clean_dcache_range(start, stop); + + if (IS_ENABLED(CONFIG_44x)) { + /* + * Flash invalidate on 44x because we are passed kmapped + * addresses and this doesn't work for userspace pages due to + * the virtually tagged icache. + */ + iccci((void *)start); + mb(); /* sync */ + isync(); + } else + invalidate_icache_range(start, stop); +} +EXPORT_SYMBOL(flush_icache_range); + +#if !defined(CONFIG_PPC_8xx) && !defined(CONFIG_PPC64) +/** + * flush_dcache_icache_phys() - Flush a page by it's physical address + * @physaddr: the physical address of the page + */ +static void flush_dcache_icache_phys(unsigned long physaddr) +{ + unsigned long bytes = l1_dcache_bytes(); + unsigned long nb = PAGE_SIZE / bytes; + unsigned long addr = physaddr & PAGE_MASK; + unsigned long msr, msr0; + unsigned long loop1 = addr, loop2 = addr; + + msr0 = mfmsr(); + msr = msr0 & ~MSR_DR; + /* + * This must remain as ASM to prevent potential memory accesses + * while the data MMU is disabled + */ + asm volatile( + " mtctr %2;\n" + " mtmsr %3;\n" + " isync;\n" + "0: dcbst 0, %0;\n" + " addi %0, %0, %4;\n" + " bdnz 0b;\n" + " sync;\n" + " mtctr %2;\n" + "1: icbi 0, %1;\n" + " addi %1, %1, %4;\n" + " bdnz 1b;\n" + " sync;\n" + " mtmsr %5;\n" + " isync;\n" + : "+&r" (loop1), "+&r" (loop2) + : "r" (nb), "r" (msr), "i" (bytes), "r" (msr0) + : "ctr", "memory"); +} +#endif // !defined(CONFIG_PPC_8xx) && !defined(CONFIG_PPC64) + /* * This is called when a page has been modified by the kernel. * It just marks the page as not i-cache clean. We do the i-cache @@ -350,12 +493,46 @@ void flush_dcache_icache_page(struct page *page) __flush_dcache_icache(start); kunmap_atomic(start); } else { - __flush_dcache_icache_phys(page_to_pfn(page) << PAGE_SHIFT); + unsigned long addr = page_to_pfn(page) << PAGE_SHIFT; + + if (flush_coherent_icache(addr)) + return; + flush_dcache_icache_phys(addr); } #endif } EXPORT_SYMBOL(flush_dcache_icache_page); +/** + * __flush_dcache_icache(): Flush a particular page from the data cache to RAM. + * Note: this is necessary because the instruction cache does *not* + * snoop from the data cache. + * + * @page: the address of the page to flush + */ +void __flush_dcache_icache(void *p) +{ + unsigned long addr = (unsigned long)p; + + if (flush_coherent_icache(addr)) + return; + + clean_dcache_range(addr, addr + PAGE_SIZE); + + /* + * We don't flush the icache on 44x. Those have a virtual icache and we + * don't have access to the virtual address here (it's not the page + * vaddr but where it's mapped in user space). The flushing of the + * icache on these is handled elsewhere, when a change in the address + * space occurs, before returning to user space. + */ + + if (cpu_has_feature(MMU_FTR_TYPE_44x)) + return; + + invalidate_icache_range(addr, addr + PAGE_SIZE); +} + void clear_user_page(void *page, unsigned long vaddr, struct page *pg) { clear_page(page); diff --git a/arch/powerpc/mm/mmu_decl.h b/arch/powerpc/mm/mmu_decl.h index c750ac9ec713..8e99649c24fc 100644 --- a/arch/powerpc/mm/mmu_decl.h +++ b/arch/powerpc/mm/mmu_decl.h @@ -139,10 +139,21 @@ extern unsigned long calc_cam_sz(unsigned long ram, unsigned long virt, extern void adjust_total_lowmem(void); extern int switch_to_as1(void); extern void restore_to_as0(int esel, int offset, void *dt_ptr, int bootcpu); +void create_kaslr_tlb_entry(int entry, unsigned long virt, phys_addr_t phys); +void reloc_kernel_entry(void *fdt, int addr); +extern int is_second_reloc; #endif extern void loadcam_entry(unsigned int index); extern void loadcam_multi(int first_idx, int num, int tmp_idx); +#ifdef CONFIG_RANDOMIZE_BASE +void kaslr_early_init(void *dt_ptr, phys_addr_t size); +void kaslr_late_init(void); +#else +static inline void kaslr_early_init(void *dt_ptr, phys_addr_t size) {} +static inline void kaslr_late_init(void) {} +#endif + struct tlbcam { u32 MAS0; u32 MAS1; diff --git a/arch/powerpc/mm/nohash/8xx.c b/arch/powerpc/mm/nohash/8xx.c index 4a06cb342da2..090af2d2d3e4 100644 --- a/arch/powerpc/mm/nohash/8xx.c +++ b/arch/powerpc/mm/nohash/8xx.c @@ -103,6 +103,19 @@ static void mmu_patch_addis(s32 *site, long simm) patch_instruction_site(site, instr); } +void __init mmu_mapin_ram_chunk(unsigned long offset, unsigned long top, pgprot_t prot) +{ + unsigned long s = offset; + unsigned long v = PAGE_OFFSET + s; + phys_addr_t p = memstart_addr + s; + + for (; s < top; s += PAGE_SIZE) { + map_kernel_page(v, p, prot); + v += PAGE_SIZE; + p += PAGE_SIZE; + } +} + unsigned long __init mmu_mapin_ram(unsigned long base, unsigned long top) { unsigned long mapped; @@ -115,10 +128,20 @@ unsigned long __init mmu_mapin_ram(unsigned long base, unsigned long top) if (!IS_ENABLED(CONFIG_PIN_TLB_TEXT)) mmu_patch_cmp_limit(&patch__itlbmiss_linmem_top, 0); } else { + unsigned long einittext8 = ALIGN(__pa(_einittext), SZ_8M); + mapped = top & ~(LARGE_PAGE_SIZE_8M - 1); if (!IS_ENABLED(CONFIG_PIN_TLB_TEXT)) - mmu_patch_cmp_limit(&patch__itlbmiss_linmem_top, - _ALIGN(__pa(_einittext), 8 << 20)); + mmu_patch_cmp_limit(&patch__itlbmiss_linmem_top, einittext8); + + /* + * Populate page tables to: + * - have them appear in /sys/kernel/debug/kernel_page_tables + * - allow the BDI to find the pages when they are not PINNED + */ + mmu_mapin_ram_chunk(0, einittext8, PAGE_KERNEL_X); + mmu_mapin_ram_chunk(einittext8, mapped, PAGE_KERNEL); + mmu_mapin_immr(); } mmu_patch_cmp_limit(&patch__dtlbmiss_linmem_top, mapped); @@ -144,18 +167,41 @@ void mmu_mark_initmem_nx(void) if (IS_ENABLED(CONFIG_STRICT_KERNEL_RWX) && CONFIG_ETEXT_SHIFT < 23) mmu_patch_addis(&patch__itlbmiss_linmem_top8, -((long)_etext & ~(LARGE_PAGE_SIZE_8M - 1))); - if (!IS_ENABLED(CONFIG_PIN_TLB_TEXT)) + if (!IS_ENABLED(CONFIG_PIN_TLB_TEXT)) { + unsigned long einittext8 = ALIGN(__pa(_einittext), SZ_8M); + unsigned long etext8 = ALIGN(__pa(_etext), SZ_8M); + unsigned long etext = __pa(_etext); + mmu_patch_cmp_limit(&patch__itlbmiss_linmem_top, __pa(_etext)); + + /* Update page tables for PTDUMP and BDI */ + mmu_mapin_ram_chunk(0, einittext8, __pgprot(0)); + if (IS_ENABLED(CONFIG_STRICT_KERNEL_RWX)) { + mmu_mapin_ram_chunk(0, etext, PAGE_KERNEL_TEXT); + mmu_mapin_ram_chunk(etext, einittext8, PAGE_KERNEL); + } else { + mmu_mapin_ram_chunk(0, etext8, PAGE_KERNEL_TEXT); + mmu_mapin_ram_chunk(etext8, einittext8, PAGE_KERNEL); + } + } } #ifdef CONFIG_STRICT_KERNEL_RWX void mmu_mark_rodata_ro(void) { + unsigned long sinittext = __pa(_sinittext); + unsigned long etext = __pa(_etext); + if (CONFIG_DATA_SHIFT < 23) mmu_patch_addis(&patch__dtlbmiss_romem_top8, -__pa(((unsigned long)_sinittext) & ~(LARGE_PAGE_SIZE_8M - 1))); mmu_patch_addis(&patch__dtlbmiss_romem_top, -__pa(_sinittext)); + + /* Update page tables for PTDUMP and BDI */ + mmu_mapin_ram_chunk(0, sinittext, __pgprot(0)); + mmu_mapin_ram_chunk(0, etext, PAGE_KERNEL_ROX); + mmu_mapin_ram_chunk(etext, sinittext, PAGE_KERNEL_RO); } #endif diff --git a/arch/powerpc/mm/nohash/Makefile b/arch/powerpc/mm/nohash/Makefile index 33b6f6f29d3f..0424f6ce5bd8 100644 --- a/arch/powerpc/mm/nohash/Makefile +++ b/arch/powerpc/mm/nohash/Makefile @@ -8,6 +8,7 @@ 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-$(CONFIG_RANDOMIZE_BASE) += kaslr_booke.o ifdef CONFIG_HUGETLB_PAGE obj-$(CONFIG_PPC_FSL_BOOK3E) += book3e_hugetlbpage.o endif diff --git a/arch/powerpc/mm/nohash/fsl_booke.c b/arch/powerpc/mm/nohash/fsl_booke.c index 556e3cd52a35..b4eb06ceb189 100644 --- a/arch/powerpc/mm/nohash/fsl_booke.c +++ b/arch/powerpc/mm/nohash/fsl_booke.c @@ -263,11 +263,13 @@ void setup_initial_memory_limit(phys_addr_t first_memblock_base, int __initdata is_second_reloc; notrace void __init relocate_init(u64 dt_ptr, phys_addr_t start) { - unsigned long base = KERNELBASE; + unsigned long base = kernstart_virt_addr; + phys_addr_t size; kernstart_addr = start; if (is_second_reloc) { virt_phys_offset = PAGE_OFFSET - memstart_addr; + kaslr_late_init(); return; } @@ -291,7 +293,7 @@ notrace void __init relocate_init(u64 dt_ptr, phys_addr_t start) start &= ~0x3ffffff; base &= ~0x3ffffff; virt_phys_offset = base - start; - early_get_first_memblock_info(__va(dt_ptr), NULL); + early_get_first_memblock_info(__va(dt_ptr), &size); /* * We now get the memstart_addr, then we should check if this * address is the same as what the PAGE_OFFSET map to now. If @@ -316,6 +318,8 @@ notrace void __init relocate_init(u64 dt_ptr, phys_addr_t start) /* We should never reach here */ panic("Relocation error"); } + + kaslr_early_init(__va(dt_ptr), size); } #endif #endif diff --git a/arch/powerpc/mm/nohash/kaslr_booke.c b/arch/powerpc/mm/nohash/kaslr_booke.c new file mode 100644 index 000000000000..4a75f2d9bf0e --- /dev/null +++ b/arch/powerpc/mm/nohash/kaslr_booke.c @@ -0,0 +1,401 @@ +// SPDX-License-Identifier: GPL-2.0-only +// +// Copyright (C) 2019 Jason Yan <yanaijie@huawei.com> + +#include <linux/kernel.h> +#include <linux/errno.h> +#include <linux/string.h> +#include <linux/types.h> +#include <linux/mm.h> +#include <linux/swap.h> +#include <linux/stddef.h> +#include <linux/init.h> +#include <linux/delay.h> +#include <linux/memblock.h> +#include <linux/libfdt.h> +#include <linux/crash_core.h> +#include <asm/pgalloc.h> +#include <asm/prom.h> +#include <asm/kdump.h> +#include <mm/mmu_decl.h> +#include <generated/compile.h> +#include <generated/utsrelease.h> + +struct regions { + unsigned long pa_start; + unsigned long pa_end; + unsigned long kernel_size; + unsigned long dtb_start; + unsigned long dtb_end; + unsigned long initrd_start; + unsigned long initrd_end; + unsigned long crash_start; + unsigned long crash_end; + int reserved_mem; + int reserved_mem_addr_cells; + int reserved_mem_size_cells; +}; + +/* Simplified build-specific string for starting entropy. */ +static const char build_str[] = UTS_RELEASE " (" LINUX_COMPILE_BY "@" + LINUX_COMPILE_HOST ") (" LINUX_COMPILER ") " UTS_VERSION; + +struct regions __initdata regions; + +static __init void kaslr_get_cmdline(void *fdt) +{ + int node = fdt_path_offset(fdt, "/chosen"); + + early_init_dt_scan_chosen(node, "chosen", 1, boot_command_line); +} + +static unsigned long __init rotate_xor(unsigned long hash, const void *area, + size_t size) +{ + size_t i; + const unsigned long *ptr = area; + + for (i = 0; i < size / sizeof(hash); i++) { + /* Rotate by odd number of bits and XOR. */ + hash = (hash << ((sizeof(hash) * 8) - 7)) | (hash >> 7); + hash ^= ptr[i]; + } + + return hash; +} + +/* Attempt to create a simple starting entropy. This can make it defferent for + * every build but it is still not enough. Stronger entropy should + * be added to make it change for every boot. + */ +static unsigned long __init get_boot_seed(void *fdt) +{ + unsigned long hash = 0; + + hash = rotate_xor(hash, build_str, sizeof(build_str)); + hash = rotate_xor(hash, fdt, fdt_totalsize(fdt)); + + return hash; +} + +static __init u64 get_kaslr_seed(void *fdt) +{ + int node, len; + fdt64_t *prop; + u64 ret; + + node = fdt_path_offset(fdt, "/chosen"); + if (node < 0) + return 0; + + prop = fdt_getprop_w(fdt, node, "kaslr-seed", &len); + if (!prop || len != sizeof(u64)) + return 0; + + ret = fdt64_to_cpu(*prop); + *prop = 0; + return ret; +} + +static __init bool regions_overlap(u32 s1, u32 e1, u32 s2, u32 e2) +{ + return e1 >= s2 && e2 >= s1; +} + +static __init bool overlaps_reserved_region(const void *fdt, u32 start, + u32 end) +{ + int subnode, len, i; + u64 base, size; + + /* check for overlap with /memreserve/ entries */ + for (i = 0; i < fdt_num_mem_rsv(fdt); i++) { + if (fdt_get_mem_rsv(fdt, i, &base, &size) < 0) + continue; + if (regions_overlap(start, end, base, base + size)) + return true; + } + + if (regions.reserved_mem < 0) + return false; + + /* check for overlap with static reservations in /reserved-memory */ + for (subnode = fdt_first_subnode(fdt, regions.reserved_mem); + subnode >= 0; + subnode = fdt_next_subnode(fdt, subnode)) { + const fdt32_t *reg; + u64 rsv_end; + + len = 0; + reg = fdt_getprop(fdt, subnode, "reg", &len); + while (len >= (regions.reserved_mem_addr_cells + + regions.reserved_mem_size_cells)) { + base = fdt32_to_cpu(reg[0]); + if (regions.reserved_mem_addr_cells == 2) + base = (base << 32) | fdt32_to_cpu(reg[1]); + + reg += regions.reserved_mem_addr_cells; + len -= 4 * regions.reserved_mem_addr_cells; + + size = fdt32_to_cpu(reg[0]); + if (regions.reserved_mem_size_cells == 2) + size = (size << 32) | fdt32_to_cpu(reg[1]); + + reg += regions.reserved_mem_size_cells; + len -= 4 * regions.reserved_mem_size_cells; + + if (base >= regions.pa_end) + continue; + + rsv_end = min(base + size, (u64)U32_MAX); + + if (regions_overlap(start, end, base, rsv_end)) + return true; + } + } + return false; +} + +static __init bool overlaps_region(const void *fdt, u32 start, + u32 end) +{ + if (regions_overlap(start, end, __pa(_stext), __pa(_end))) + return true; + + if (regions_overlap(start, end, regions.dtb_start, + regions.dtb_end)) + return true; + + if (regions_overlap(start, end, regions.initrd_start, + regions.initrd_end)) + return true; + + if (regions_overlap(start, end, regions.crash_start, + regions.crash_end)) + return true; + + return overlaps_reserved_region(fdt, start, end); +} + +static void __init get_crash_kernel(void *fdt, unsigned long size) +{ +#ifdef CONFIG_CRASH_CORE + unsigned long long crash_size, crash_base; + int ret; + + ret = parse_crashkernel(boot_command_line, size, &crash_size, + &crash_base); + if (ret != 0 || crash_size == 0) + return; + if (crash_base == 0) + crash_base = KDUMP_KERNELBASE; + + regions.crash_start = (unsigned long)crash_base; + regions.crash_end = (unsigned long)(crash_base + crash_size); + + pr_debug("crash_base=0x%llx crash_size=0x%llx\n", crash_base, crash_size); +#endif +} + +static void __init get_initrd_range(void *fdt) +{ + u64 start, end; + int node, len; + const __be32 *prop; + + node = fdt_path_offset(fdt, "/chosen"); + if (node < 0) + return; + + prop = fdt_getprop(fdt, node, "linux,initrd-start", &len); + if (!prop) + return; + start = of_read_number(prop, len / 4); + + prop = fdt_getprop(fdt, node, "linux,initrd-end", &len); + if (!prop) + return; + end = of_read_number(prop, len / 4); + + regions.initrd_start = (unsigned long)start; + regions.initrd_end = (unsigned long)end; + + pr_debug("initrd_start=0x%llx initrd_end=0x%llx\n", start, end); +} + +static __init unsigned long get_usable_address(const void *fdt, + unsigned long start, + unsigned long offset) +{ + unsigned long pa; + unsigned long pa_end; + + for (pa = offset; (long)pa > (long)start; pa -= SZ_16K) { + pa_end = pa + regions.kernel_size; + if (overlaps_region(fdt, pa, pa_end)) + continue; + + return pa; + } + return 0; +} + +static __init void get_cell_sizes(const void *fdt, int node, int *addr_cells, + int *size_cells) +{ + const int *prop; + int len; + + /* + * Retrieve the #address-cells and #size-cells properties + * from the 'node', or use the default if not provided. + */ + *addr_cells = *size_cells = 1; + + prop = fdt_getprop(fdt, node, "#address-cells", &len); + if (len == 4) + *addr_cells = fdt32_to_cpu(*prop); + prop = fdt_getprop(fdt, node, "#size-cells", &len); + if (len == 4) + *size_cells = fdt32_to_cpu(*prop); +} + +static unsigned long __init kaslr_legal_offset(void *dt_ptr, unsigned long index, + unsigned long offset) +{ + unsigned long koffset = 0; + unsigned long start; + + while ((long)index >= 0) { + offset = memstart_addr + index * SZ_64M + offset; + start = memstart_addr + index * SZ_64M; + koffset = get_usable_address(dt_ptr, start, offset); + if (koffset) + break; + index--; + } + + if (koffset != 0) + koffset -= memstart_addr; + + return koffset; +} + +static inline __init bool kaslr_disabled(void) +{ + return strstr(boot_command_line, "nokaslr") != NULL; +} + +static unsigned long __init kaslr_choose_location(void *dt_ptr, phys_addr_t size, + unsigned long kernel_sz) +{ + unsigned long offset, random; + unsigned long ram, linear_sz; + u64 seed; + unsigned long index; + + kaslr_get_cmdline(dt_ptr); + if (kaslr_disabled()) + return 0; + + random = get_boot_seed(dt_ptr); + + seed = get_tb() << 32; + seed ^= get_tb(); + random = rotate_xor(random, &seed, sizeof(seed)); + + /* + * Retrieve (and wipe) the seed from the FDT + */ + seed = get_kaslr_seed(dt_ptr); + if (seed) + random = rotate_xor(random, &seed, sizeof(seed)); + else + 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); + linear_sz = min_t(unsigned long, ram, SZ_512M); + + /* If the linear size is smaller than 64M, do not randmize */ + if (linear_sz < SZ_64M) + return 0; + + /* check for a reserved-memory node and record its cell sizes */ + regions.reserved_mem = fdt_path_offset(dt_ptr, "/reserved-memory"); + if (regions.reserved_mem >= 0) + get_cell_sizes(dt_ptr, regions.reserved_mem, + ®ions.reserved_mem_addr_cells, + ®ions.reserved_mem_size_cells); + + regions.pa_start = memstart_addr; + regions.pa_end = memstart_addr + linear_sz; + regions.dtb_start = __pa(dt_ptr); + regions.dtb_end = __pa(dt_ptr) + fdt_totalsize(dt_ptr); + regions.kernel_size = kernel_sz; + + get_initrd_range(dt_ptr); + get_crash_kernel(dt_ptr, ram); + + /* + * Decide which 64M we want to start + * Only use the low 8 bits of the random seed + */ + index = random & 0xFF; + index %= linear_sz / SZ_64M; + + /* Decide offset inside 64M */ + offset = random % (SZ_64M - kernel_sz); + offset = round_down(offset, SZ_16K); + + return kaslr_legal_offset(dt_ptr, index, offset); +} + +/* + * To see if we need to relocate the kernel to a random offset + * void *dt_ptr - address of the device tree + * phys_addr_t size - size of the first memory block + */ +notrace void __init kaslr_early_init(void *dt_ptr, phys_addr_t size) +{ + unsigned long tlb_virt; + phys_addr_t tlb_phys; + unsigned long offset; + unsigned long kernel_sz; + + kernel_sz = (unsigned long)_end - (unsigned long)_stext; + + offset = kaslr_choose_location(dt_ptr, size, kernel_sz); + if (offset == 0) + return; + + kernstart_virt_addr += offset; + kernstart_addr += offset; + + is_second_reloc = 1; + + if (offset >= SZ_64M) { + tlb_virt = round_down(kernstart_virt_addr, SZ_64M); + tlb_phys = round_down(kernstart_addr, SZ_64M); + + /* Create kernel map to relocate in */ + create_kaslr_tlb_entry(1, tlb_virt, tlb_phys); + } + + /* Copy the kernel to it's new location and run */ + memcpy((void *)kernstart_virt_addr, (void *)_stext, kernel_sz); + flush_icache_range(kernstart_virt_addr, kernstart_virt_addr + kernel_sz); + + reloc_kernel_entry(dt_ptr, kernstart_virt_addr); +} + +void __init kaslr_late_init(void) +{ + /* If randomized, clear the original kernel */ + if (kernstart_virt_addr != KERNELBASE) { + unsigned long kernel_sz; + + kernel_sz = (unsigned long)_end - kernstart_virt_addr; + memzero_explicit((void *)KERNELBASE, kernel_sz); + } +} diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c index 8ec5dfb65b2e..73b84166d06a 100644 --- a/arch/powerpc/mm/pgtable_32.c +++ b/arch/powerpc/mm/pgtable_32.c @@ -117,10 +117,7 @@ void __init mapin_ram(void) if (base >= top) continue; base = mmu_mapin_ram(base, top); - if (IS_ENABLED(CONFIG_BDI_SWITCH)) - __mapin_ram_chunk(reg->base, top); - else - __mapin_ram_chunk(base, top); + __mapin_ram_chunk(base, top); } } diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c index 02a59946a78a..be3517ef0574 100644 --- a/arch/powerpc/net/bpf_jit_comp64.c +++ b/arch/powerpc/net/bpf_jit_comp64.c @@ -1142,6 +1142,19 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp) } /* + * If we have seen a tail call, we need a second pass. + * This is because bpf_jit_emit_common_epilogue() is called + * from bpf_jit_emit_tail_call() with a not yet stable ctx->seen. + */ + if (cgctx.seen & SEEN_TAILCALL) { + cgctx.idx = 0; + if (bpf_jit_build_body(fp, 0, &cgctx, addrs, false)) { + fp = org_fp; + goto out_addrs; + } + } + + /* * Pretend to build prologue, given the features we've seen. This will * update ctgtx.idx as it pretends to output instructions, then we can * calculate total size from idx. diff --git a/arch/powerpc/perf/callchain.c b/arch/powerpc/perf/callchain.c index c84bbd4298a0..35d542515faf 100644 --- a/arch/powerpc/perf/callchain.c +++ b/arch/powerpc/perf/callchain.c @@ -284,16 +284,6 @@ static void perf_callchain_user_64(struct perf_callchain_entry_ctx *entry, } } -static inline int current_is_64bit(void) -{ - /* - * We can't use test_thread_flag() here because we may be on an - * interrupt stack, and the thread flags don't get copied over - * from the thread_info on the main stack to the interrupt stack. - */ - return !test_ti_thread_flag(task_thread_info(current), TIF_32BIT); -} - #else /* CONFIG_PPC64 */ /* * On 32-bit we just access the address and let hash_page create a @@ -321,11 +311,6 @@ static inline void perf_callchain_user_64(struct perf_callchain_entry_ctx *entry { } -static inline int current_is_64bit(void) -{ - return 0; -} - static inline int valid_user_sp(unsigned long sp, int is_64) { if (!sp || (sp & 7) || sp > TASK_SIZE - 32) @@ -486,7 +471,7 @@ static void perf_callchain_user_32(struct perf_callchain_entry_ctx *entry, void perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs) { - if (current_is_64bit()) + if (!is_32bit_task()) perf_callchain_user_64(entry, regs); else perf_callchain_user_32(entry, regs); diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index ca92e01d0bd1..48604625ab31 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -96,7 +96,7 @@ static inline unsigned long perf_ip_adjust(struct pt_regs *regs) { return 0; } -static inline void perf_get_data_addr(struct pt_regs *regs, u64 *addrp) { } +static inline void perf_get_data_addr(struct perf_event *event, struct pt_regs *regs, u64 *addrp) { } static inline u32 perf_get_misc_flags(struct pt_regs *regs) { return 0; @@ -127,7 +127,7 @@ static unsigned long ebb_switch_in(bool ebb, struct cpu_hw_events *cpuhw) static inline void power_pmu_bhrb_enable(struct perf_event *event) {} static inline void power_pmu_bhrb_disable(struct perf_event *event) {} static void power_pmu_sched_task(struct perf_event_context *ctx, bool sched_in) {} -static inline void power_pmu_bhrb_read(struct cpu_hw_events *cpuhw) {} +static inline void power_pmu_bhrb_read(struct perf_event *event, struct cpu_hw_events *cpuhw) {} static void pmao_restore_workaround(bool ebb) { } #endif /* CONFIG_PPC32 */ @@ -179,7 +179,7 @@ static inline unsigned long perf_ip_adjust(struct pt_regs *regs) * pointed to by SIAR; this is indicated by the [POWER6_]MMCRA_SDSYNC, the * [POWER7P_]MMCRA_SDAR_VALID bit in MMCRA, or the SDAR_VALID bit in SIER. */ -static inline void perf_get_data_addr(struct pt_regs *regs, u64 *addrp) +static inline void perf_get_data_addr(struct perf_event *event, struct pt_regs *regs, u64 *addrp) { unsigned long mmcra = regs->dsisr; bool sdar_valid; @@ -204,8 +204,7 @@ static inline void perf_get_data_addr(struct pt_regs *regs, u64 *addrp) if (!(mmcra & MMCRA_SAMPLE_ENABLE) || sdar_valid) *addrp = mfspr(SPRN_SDAR); - if (perf_paranoid_kernel() && !capable(CAP_SYS_ADMIN) && - is_kernel_addr(mfspr(SPRN_SDAR))) + if (is_kernel_addr(mfspr(SPRN_SDAR)) && perf_allow_kernel(&event->attr) != 0) *addrp = 0; } @@ -444,7 +443,7 @@ static __u64 power_pmu_bhrb_to(u64 addr) } /* Processing BHRB entries */ -static void power_pmu_bhrb_read(struct cpu_hw_events *cpuhw) +static void power_pmu_bhrb_read(struct perf_event *event, struct cpu_hw_events *cpuhw) { u64 val; u64 addr; @@ -472,8 +471,7 @@ static void power_pmu_bhrb_read(struct cpu_hw_events *cpuhw) * exporting it to userspace (avoid exposure of regions * where we could have speculative execution) */ - if (perf_paranoid_kernel() && !capable(CAP_SYS_ADMIN) && - is_kernel_addr(addr)) + if (is_kernel_addr(addr) && perf_allow_kernel(&event->attr) != 0) continue; /* Branches are read most recent first (ie. mfbhrb 0 is @@ -2087,12 +2085,12 @@ static void record_and_restart(struct perf_event *event, unsigned long val, if (event->attr.sample_type & (PERF_SAMPLE_ADDR | PERF_SAMPLE_PHYS_ADDR)) - perf_get_data_addr(regs, &data.addr); + perf_get_data_addr(event, regs, &data.addr); if (event->attr.sample_type & PERF_SAMPLE_BRANCH_STACK) { struct cpu_hw_events *cpuhw; cpuhw = this_cpu_ptr(&cpu_hw_events); - power_pmu_bhrb_read(cpuhw); + power_pmu_bhrb_read(event, cpuhw); data.br_stack = &cpuhw->bhrb_stack; } diff --git a/arch/powerpc/platforms/52xx/mpc52xx_gpt.c b/arch/powerpc/platforms/52xx/mpc52xx_gpt.c index ba12dc14a3d1..8c0d324f657e 100644 --- a/arch/powerpc/platforms/52xx/mpc52xx_gpt.c +++ b/arch/powerpc/platforms/52xx/mpc52xx_gpt.c @@ -650,6 +650,7 @@ static const struct file_operations mpc52xx_wdt_fops = { .llseek = no_llseek, .write = mpc52xx_wdt_write, .unlocked_ioctl = mpc52xx_wdt_ioctl, + .compat_ioctl = compat_ptr_ioctl, .open = mpc52xx_wdt_open, .release = mpc52xx_wdt_release, }; diff --git a/arch/powerpc/platforms/83xx/misc.c b/arch/powerpc/platforms/83xx/misc.c index f46d7bf3b140..6399865a625e 100644 --- a/arch/powerpc/platforms/83xx/misc.c +++ b/arch/powerpc/platforms/83xx/misc.c @@ -18,6 +18,8 @@ #include <sysdev/fsl_soc.h> #include <sysdev/fsl_pci.h> +#include <mm/mmu_decl.h> + #include "mpc83xx.h" static __be32 __iomem *restart_reg_base; @@ -145,6 +147,15 @@ void __init mpc83xx_setup_arch(void) if (ppc_md.progress) ppc_md.progress("mpc83xx_setup_arch()", 0); + if (!__map_without_bats) { + phys_addr_t immrbase = get_immrbase(); + int immrsize = IS_ALIGNED(immrbase, SZ_2M) ? SZ_2M : SZ_1M; + unsigned long va = fix_to_virt(FIX_IMMR_BASE); + + setbat(-1, va, immrbase, immrsize, PAGE_KERNEL_NCG); + update_bats(); + } + mpc83xx_setup_pci(); } diff --git a/arch/powerpc/platforms/83xx/mpc836x_mds.c b/arch/powerpc/platforms/83xx/mpc836x_mds.c index 4a4efa906d35..240a26d88b07 100644 --- a/arch/powerpc/platforms/83xx/mpc836x_mds.c +++ b/arch/powerpc/platforms/83xx/mpc836x_mds.c @@ -39,7 +39,6 @@ #include <asm/udbg.h> #include <sysdev/fsl_soc.h> #include <sysdev/fsl_pci.h> -#include <sysdev/simple_gpio.h> #include <soc/fsl/qe/qe.h> #include <soc/fsl/qe/qe_ic.h> @@ -181,12 +180,6 @@ static int __init mpc836x_usb_cfg(void) qe_usb_clock_set(QE_CLK21, 48000000); } else { setbits8(&bcsr[13], BCSR13_USBMODE); - /* - * The BCSR GPIOs are used to control power and - * speed of the USB transceiver. This is needed for - * the USB Host only. - */ - simple_gpiochip_init("fsl,mpc8360mds-bcsr-gpio"); } of_node_put(np); diff --git a/arch/powerpc/platforms/85xx/common.c b/arch/powerpc/platforms/85xx/common.c index fe0606439b5a..a554b6d87cf7 100644 --- a/arch/powerpc/platforms/85xx/common.c +++ b/arch/powerpc/platforms/85xx/common.c @@ -86,29 +86,6 @@ void __init mpc85xx_cpm2_pic_init(void) #endif #ifdef CONFIG_QUICC_ENGINE -void __init mpc85xx_qe_init(void) -{ - struct device_node *np; - - np = of_find_compatible_node(NULL, NULL, "fsl,qe"); - if (!np) { - np = of_find_node_by_name(NULL, "qe"); - if (!np) { - pr_err("%s: Could not find Quicc Engine node\n", - __func__); - return; - } - } - - if (!of_device_is_available(np)) { - of_node_put(np); - return; - } - - of_node_put(np); - -} - void __init mpc85xx_qe_par_io_init(void) { struct device_node *np; diff --git a/arch/powerpc/platforms/85xx/corenet_generic.c b/arch/powerpc/platforms/85xx/corenet_generic.c index 7ee2c6628f64..a328a741b457 100644 --- a/arch/powerpc/platforms/85xx/corenet_generic.c +++ b/arch/powerpc/platforms/85xx/corenet_generic.c @@ -66,8 +66,6 @@ void __init corenet_gen_setup_arch(void) swiotlb_detect_4g(); pr_info("%s board\n", ppc_md.name); - - mpc85xx_qe_init(); } static const struct of_device_id of_device_ids[] = { diff --git a/arch/powerpc/platforms/85xx/mpc85xx.h b/arch/powerpc/platforms/85xx/mpc85xx.h index fa23f9b0592c..cb84c5c56c36 100644 --- a/arch/powerpc/platforms/85xx/mpc85xx.h +++ b/arch/powerpc/platforms/85xx/mpc85xx.h @@ -10,10 +10,8 @@ static inline void __init mpc85xx_cpm2_pic_init(void) {} #endif /* CONFIG_CPM2 */ #ifdef CONFIG_QUICC_ENGINE -extern void mpc85xx_qe_init(void); extern void mpc85xx_qe_par_io_init(void); #else -static inline void __init mpc85xx_qe_init(void) {} static inline void __init mpc85xx_qe_par_io_init(void) {} #endif diff --git a/arch/powerpc/platforms/85xx/mpc85xx_mds.c b/arch/powerpc/platforms/85xx/mpc85xx_mds.c index 5ca254256c47..381a6ac8cb4b 100644 --- a/arch/powerpc/platforms/85xx/mpc85xx_mds.c +++ b/arch/powerpc/platforms/85xx/mpc85xx_mds.c @@ -43,7 +43,6 @@ #include <asm/udbg.h> #include <sysdev/fsl_soc.h> #include <sysdev/fsl_pci.h> -#include <sysdev/simple_gpio.h> #include <soc/fsl/qe/qe.h> #include <soc/fsl/qe/qe_ic.h> #include <asm/mpic.h> @@ -238,7 +237,6 @@ static void __init mpc85xx_mds_qe_init(void) { struct device_node *np; - mpc85xx_qe_init(); mpc85xx_qe_par_io_init(); mpc85xx_mds_reset_ucc_phys(); @@ -351,11 +349,6 @@ machine_arch_initcall(mpc8569_mds, board_fixups); static int __init mpc85xx_publish_devices(void) { - if (machine_is(mpc8568_mds)) - simple_gpiochip_init("fsl,mpc8568mds-bcsr-gpio"); - if (machine_is(mpc8569_mds)) - simple_gpiochip_init("fsl,mpc8569mds-bcsr-gpio"); - return mpc85xx_common_publish_devices(); } diff --git a/arch/powerpc/platforms/85xx/mpc85xx_rdb.c b/arch/powerpc/platforms/85xx/mpc85xx_rdb.c index d3c540ee558f..7f9a84f85766 100644 --- a/arch/powerpc/platforms/85xx/mpc85xx_rdb.c +++ b/arch/powerpc/platforms/85xx/mpc85xx_rdb.c @@ -89,7 +89,6 @@ static void __init mpc85xx_rdb_setup_arch(void) fsl_pci_assign_primary(); #ifdef CONFIG_QUICC_ENGINE - mpc85xx_qe_init(); mpc85xx_qe_par_io_init(); #if defined(CONFIG_UCC_GETH) || defined(CONFIG_SERIAL_QE) if (machine_is(p1025_rdb)) { diff --git a/arch/powerpc/platforms/85xx/twr_p102x.c b/arch/powerpc/platforms/85xx/twr_p102x.c index 720b0c0f03ba..6c3c0cdaee9a 100644 --- a/arch/powerpc/platforms/85xx/twr_p102x.c +++ b/arch/powerpc/platforms/85xx/twr_p102x.c @@ -72,7 +72,6 @@ static void __init twr_p1025_setup_arch(void) fsl_pci_assign_primary(); #ifdef CONFIG_QUICC_ENGINE - mpc85xx_qe_init(); mpc85xx_qe_par_io_init(); #if IS_ENABLED(CONFIG_UCC_GETH) || IS_ENABLED(CONFIG_SERIAL_QE) diff --git a/arch/powerpc/platforms/86xx/mpc8610_hpcd.c b/arch/powerpc/platforms/86xx/mpc8610_hpcd.c index 96b27f6fdd0f..7733d0607da2 100644 --- a/arch/powerpc/platforms/86xx/mpc8610_hpcd.c +++ b/arch/powerpc/platforms/86xx/mpc8610_hpcd.c @@ -34,7 +34,6 @@ #include <linux/of_platform.h> #include <sysdev/fsl_pci.h> #include <sysdev/fsl_soc.h> -#include <sysdev/simple_gpio.h> #include "mpc86xx.h" @@ -93,9 +92,6 @@ static const struct of_device_id mpc8610_ids[] __initconst = { static int __init mpc8610_declare_of_platform_devices(void) { - /* Firstly, register PIXIS GPIOs. */ - simple_gpiochip_init("fsl,fpga-pixis-gpio-bank"); - /* Enable wakeup on PIXIS' event IRQ. */ mpc8610_suspend_init(); diff --git a/arch/powerpc/platforms/8xx/cpm1.c b/arch/powerpc/platforms/8xx/cpm1.c index 0f65c51271db..a43ee7d1ff85 100644 --- a/arch/powerpc/platforms/8xx/cpm1.c +++ b/arch/powerpc/platforms/8xx/cpm1.c @@ -51,7 +51,7 @@ #define CPM_MAP_SIZE (0x4000) cpm8xx_t __iomem *cpmp; /* Pointer to comm processor space */ -immap_t __iomem *mpc8xx_immr; +immap_t __iomem *mpc8xx_immr = (void __iomem *)VIRT_IMMR_BASE; static cpic8xx_t __iomem *cpic_reg; static struct irq_domain *cpm_pic_host; @@ -130,7 +130,7 @@ static const struct irq_domain_ops cpm_pic_host_ops = { .map = cpm_pic_host_map, }; -unsigned int cpm_pic_init(void) +unsigned int __init cpm_pic_init(void) { struct device_node *np = NULL; struct resource res; @@ -201,12 +201,6 @@ void __init cpm_reset(void) { sysconf8xx_t __iomem *siu_conf; - mpc8xx_immr = ioremap(get_immrbase(), 0x4000); - if (!mpc8xx_immr) { - printk(KERN_CRIT "Could not map IMMR\n"); - return; - } - cpmp = &mpc8xx_immr->im_cpm; #ifndef CONFIG_PPC_EARLY_DEBUG_CPM @@ -306,7 +300,7 @@ struct cpm_ioport32e { __be32 dir, par, sor, odr, dat; }; -static void cpm1_set_pin32(int port, int pin, int flags) +static void __init cpm1_set_pin32(int port, int pin, int flags) { struct cpm_ioport32e __iomem *iop; pin = 1 << (31 - pin); @@ -348,7 +342,7 @@ static void cpm1_set_pin32(int port, int pin, int flags) } } -static void cpm1_set_pin16(int port, int pin, int flags) +static void __init cpm1_set_pin16(int port, int pin, int flags) { struct cpm_ioport16 __iomem *iop = (struct cpm_ioport16 __iomem *)&mpc8xx_immr->im_ioport; @@ -386,7 +380,7 @@ static void cpm1_set_pin16(int port, int pin, int flags) } } -void cpm1_set_pin(enum cpm_port port, int pin, int flags) +void __init cpm1_set_pin(enum cpm_port port, int pin, int flags) { if (port == CPM_PORTB || port == CPM_PORTE) cpm1_set_pin32(port, pin, flags); @@ -394,7 +388,7 @@ void cpm1_set_pin(enum cpm_port port, int pin, int flags) cpm1_set_pin16(port, pin, flags); } -int cpm1_clk_setup(enum cpm_clk_target target, int clock, int mode) +int __init cpm1_clk_setup(enum cpm_clk_target target, int clock, int mode) { int shift; int i, bits = 0; diff --git a/arch/powerpc/platforms/8xx/pic.c b/arch/powerpc/platforms/8xx/pic.c index e9617d35fd1f..f2ba837249d6 100644 --- a/arch/powerpc/platforms/8xx/pic.c +++ b/arch/powerpc/platforms/8xx/pic.c @@ -125,7 +125,7 @@ static const struct irq_domain_ops mpc8xx_pic_host_ops = { .xlate = mpc8xx_pic_host_xlate, }; -int mpc8xx_pic_init(void) +int __init mpc8xx_pic_init(void) { struct resource res; struct device_node *np; diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig index d82e3664ffdf..e28df298df56 100644 --- a/arch/powerpc/platforms/Kconfig +++ b/arch/powerpc/platforms/Kconfig @@ -303,16 +303,6 @@ config GEN_RTC replacing their get_rtc_time/set_rtc_time callbacks with a proper RTC device driver. -config SIMPLE_GPIO - bool "Support for simple, memory-mapped GPIO controllers" - depends on PPC - select GPIOLIB - help - Say Y here to support simple, memory-mapped GPIO controllers. - These are usually BCSRs used to control board's switches, LEDs, - chip-selects, Ethernet/USB PHY's power and various other small - on-board peripherals. - config MCU_MPC8349EMITX bool "MPC8349E-mITX MCU driver" depends on I2C=y && PPC_83xx diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype index 12543e53fa96..8d7f9c3dc771 100644 --- a/arch/powerpc/platforms/Kconfig.cputype +++ b/arch/powerpc/platforms/Kconfig.cputype @@ -415,13 +415,13 @@ config PPC_MM_SLICES bool config PPC_HAVE_PMU_SUPPORT - bool + bool config PPC_PERF_CTRS - def_bool y - depends on PERF_EVENTS && PPC_HAVE_PMU_SUPPORT - help - This enables the powerpc-specific perf_event back-end. + def_bool y + depends on PERF_EVENTS && PPC_HAVE_PMU_SUPPORT + help + This enables the powerpc-specific perf_event back-end. config FORCE_SMP # Allow platforms to force SMP=y by selecting this @@ -459,7 +459,6 @@ config NOT_COHERENT_CACHE bool depends on 4xx || PPC_8xx || E200 || PPC_MPC512x || \ GAMECUBE_COMMON || AMIGAONE - select ARCH_HAS_DMA_COHERENT_TO_PFN select ARCH_HAS_DMA_PREP_COHERENT select ARCH_HAS_SYNC_DMA_FOR_DEVICE select ARCH_HAS_SYNC_DMA_FOR_CPU diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c index 2dd452a047cd..9b1586b85152 100644 --- a/arch/powerpc/platforms/cell/spufs/inode.c +++ b/arch/powerpc/platforms/cell/spufs/inode.c @@ -198,14 +198,12 @@ static int spufs_fill_dir(struct dentry *dir, static int spufs_dir_close(struct inode *inode, struct file *file) { - struct spu_context *ctx; struct inode *parent; struct dentry *dir; int ret; dir = file->f_path.dentry; parent = d_inode(dir->d_parent); - ctx = SPUFS_I(d_inode(dir))->i_ctx; inode_lock_nested(parent, I_MUTEX_PARENT); ret = spufs_rmdir(parent, dir); diff --git a/arch/powerpc/platforms/powernv/Makefile b/arch/powerpc/platforms/powernv/Makefile index a3ac9646119d..c0f8120045c3 100644 --- a/arch/powerpc/platforms/powernv/Makefile +++ b/arch/powerpc/platforms/powernv/Makefile @@ -20,3 +20,4 @@ obj-$(CONFIG_PPC_MEMTRACE) += memtrace.o obj-$(CONFIG_PPC_VAS) += vas.o vas-window.o vas-debug.o obj-$(CONFIG_OCXL_BASE) += ocxl.o obj-$(CONFIG_SCOM_DEBUGFS) += opal-xscom.o +obj-$(CONFIG_PPC_SECURE_BOOT) += opal-secvar.o diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c index 6bc24a47e9ef..6f300ab7f0e9 100644 --- a/arch/powerpc/platforms/powernv/eeh-powernv.c +++ b/arch/powerpc/platforms/powernv/eeh-powernv.c @@ -42,7 +42,7 @@ void pnv_pcibios_bus_add_device(struct pci_dev *pdev) { struct pci_dn *pdn = pci_get_pdn(pdev); - if (eeh_has_flag(EEH_FORCE_DISABLED)) + if (!pdn || eeh_has_flag(EEH_FORCE_DISABLED)) return; dev_dbg(&pdev->dev, "EEH: Setting up device\n"); diff --git a/arch/powerpc/platforms/powernv/opal-call.c b/arch/powerpc/platforms/powernv/opal-call.c index a2aa5e433ac8..5cd0f52d258f 100644 --- a/arch/powerpc/platforms/powernv/opal-call.c +++ b/arch/powerpc/platforms/powernv/opal-call.c @@ -290,3 +290,6 @@ OPAL_CALL(opal_nx_coproc_init, OPAL_NX_COPROC_INIT); OPAL_CALL(opal_mpipl_update, OPAL_MPIPL_UPDATE); OPAL_CALL(opal_mpipl_register_tag, OPAL_MPIPL_REGISTER_TAG); OPAL_CALL(opal_mpipl_query_tag, OPAL_MPIPL_QUERY_TAG); +OPAL_CALL(opal_secvar_get, OPAL_SECVAR_GET); +OPAL_CALL(opal_secvar_get_next, OPAL_SECVAR_GET_NEXT); +OPAL_CALL(opal_secvar_enqueue_update, OPAL_SECVAR_ENQUEUE_UPDATE); diff --git a/arch/powerpc/platforms/powernv/opal-powercap.c b/arch/powerpc/platforms/powernv/opal-powercap.c index dc599e787f78..c16d44f6f1d1 100644 --- a/arch/powerpc/platforms/powernv/opal-powercap.c +++ b/arch/powerpc/platforms/powernv/opal-powercap.c @@ -13,7 +13,7 @@ #include <asm/opal.h> -DEFINE_MUTEX(powercap_mutex); +static DEFINE_MUTEX(powercap_mutex); static struct kobject *powercap_kobj; diff --git a/arch/powerpc/platforms/powernv/opal-psr.c b/arch/powerpc/platforms/powernv/opal-psr.c index b6ccb3026c6c..69d7e75950d1 100644 --- a/arch/powerpc/platforms/powernv/opal-psr.c +++ b/arch/powerpc/platforms/powernv/opal-psr.c @@ -13,11 +13,11 @@ #include <asm/opal.h> -DEFINE_MUTEX(psr_mutex); +static DEFINE_MUTEX(psr_mutex); static struct kobject *psr_kobj; -struct psr_attr { +static struct psr_attr { u32 handle; struct kobj_attribute attr; } *psr_attrs; diff --git a/arch/powerpc/platforms/powernv/opal-secvar.c b/arch/powerpc/platforms/powernv/opal-secvar.c new file mode 100644 index 000000000000..14133e120bdd --- /dev/null +++ b/arch/powerpc/platforms/powernv/opal-secvar.c @@ -0,0 +1,140 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * PowerNV code for secure variables + * + * Copyright (C) 2019 IBM Corporation + * Author: Claudio Carvalho + * Nayna Jain + * + * APIs to access secure variables managed by OPAL. + */ + +#define pr_fmt(fmt) "secvar: "fmt + +#include <linux/types.h> +#include <linux/platform_device.h> +#include <linux/of_platform.h> +#include <asm/opal.h> +#include <asm/secvar.h> +#include <asm/secure_boot.h> + +static int opal_status_to_err(int rc) +{ + int err; + + switch (rc) { + case OPAL_SUCCESS: + err = 0; + break; + case OPAL_UNSUPPORTED: + err = -ENXIO; + break; + case OPAL_PARAMETER: + err = -EINVAL; + break; + case OPAL_RESOURCE: + err = -ENOSPC; + break; + case OPAL_HARDWARE: + err = -EIO; + break; + case OPAL_NO_MEM: + err = -ENOMEM; + break; + case OPAL_EMPTY: + err = -ENOENT; + break; + case OPAL_PARTIAL: + err = -EFBIG; + break; + default: + err = -EINVAL; + } + + return err; +} + +static int opal_get_variable(const char *key, uint64_t ksize, + u8 *data, uint64_t *dsize) +{ + int rc; + + if (!key || !dsize) + return -EINVAL; + + *dsize = cpu_to_be64(*dsize); + + rc = opal_secvar_get(key, ksize, data, dsize); + + *dsize = be64_to_cpu(*dsize); + + return opal_status_to_err(rc); +} + +static int opal_get_next_variable(const char *key, uint64_t *keylen, + uint64_t keybufsize) +{ + int rc; + + if (!key || !keylen) + return -EINVAL; + + *keylen = cpu_to_be64(*keylen); + + rc = opal_secvar_get_next(key, keylen, keybufsize); + + *keylen = be64_to_cpu(*keylen); + + return opal_status_to_err(rc); +} + +static int opal_set_variable(const char *key, uint64_t ksize, u8 *data, + uint64_t dsize) +{ + int rc; + + if (!key || !data) + return -EINVAL; + + rc = opal_secvar_enqueue_update(key, ksize, data, dsize); + + return opal_status_to_err(rc); +} + +static const struct secvar_operations opal_secvar_ops = { + .get = opal_get_variable, + .get_next = opal_get_next_variable, + .set = opal_set_variable, +}; + +static int opal_secvar_probe(struct platform_device *pdev) +{ + if (!opal_check_token(OPAL_SECVAR_GET) + || !opal_check_token(OPAL_SECVAR_GET_NEXT) + || !opal_check_token(OPAL_SECVAR_ENQUEUE_UPDATE)) { + pr_err("OPAL doesn't support secure variables\n"); + return -ENODEV; + } + + set_secvar_ops(&opal_secvar_ops); + + return 0; +} + +static const struct of_device_id opal_secvar_match[] = { + { .compatible = "ibm,secvar-backend",}, + {}, +}; + +static struct platform_driver opal_secvar_driver = { + .driver = { + .name = "secvar", + .of_match_table = opal_secvar_match, + }, +}; + +static int __init opal_secvar_init(void) +{ + return platform_driver_probe(&opal_secvar_driver, opal_secvar_probe); +} +device_initcall(opal_secvar_init); diff --git a/arch/powerpc/platforms/powernv/opal-sensor-groups.c b/arch/powerpc/platforms/powernv/opal-sensor-groups.c index 31f13c13275f..f8ae1fb0c102 100644 --- a/arch/powerpc/platforms/powernv/opal-sensor-groups.c +++ b/arch/powerpc/platforms/powernv/opal-sensor-groups.c @@ -13,7 +13,7 @@ #include <asm/opal.h> -DEFINE_MUTEX(sg_mutex); +static DEFINE_MUTEX(sg_mutex); static struct kobject *sg_kobj; diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c index 38e90270280b..a6ee08009f0f 100644 --- a/arch/powerpc/platforms/powernv/opal.c +++ b/arch/powerpc/platforms/powernv/opal.c @@ -35,6 +35,16 @@ #include "powernv.h" +#define OPAL_MSG_QUEUE_MAX 16 + +struct opal_msg_node { + struct list_head list; + struct opal_msg msg; +}; + +static DEFINE_SPINLOCK(msg_list_lock); +static LIST_HEAD(msg_list); + /* /sys/firmware/opal */ struct kobject *opal_kobj; @@ -50,6 +60,8 @@ struct mcheck_recoverable_range { u64 recover_addr; }; +static int msg_list_size; + static struct mcheck_recoverable_range *mc_recoverable_range; static int mc_recoverable_range_len; @@ -237,6 +249,43 @@ static int __init opal_register_exception_handlers(void) } machine_early_initcall(powernv, opal_register_exception_handlers); +static void queue_replay_msg(void *msg) +{ + struct opal_msg_node *msg_node; + + if (msg_list_size < OPAL_MSG_QUEUE_MAX) { + msg_node = kzalloc(sizeof(*msg_node), GFP_ATOMIC); + if (msg_node) { + INIT_LIST_HEAD(&msg_node->list); + memcpy(&msg_node->msg, msg, sizeof(struct opal_msg)); + list_add_tail(&msg_node->list, &msg_list); + msg_list_size++; + } else + pr_warn_once("message queue no memory\n"); + + if (msg_list_size >= OPAL_MSG_QUEUE_MAX) + pr_warn_once("message queue full\n"); + } +} + +static void dequeue_replay_msg(enum opal_msg_type msg_type) +{ + struct opal_msg_node *msg_node, *tmp; + + list_for_each_entry_safe(msg_node, tmp, &msg_list, list) { + if (be32_to_cpu(msg_node->msg.msg_type) != msg_type) + continue; + + atomic_notifier_call_chain(&opal_msg_notifier_head[msg_type], + msg_type, + &msg_node->msg); + + list_del(&msg_node->list); + kfree(msg_node); + msg_list_size--; + } +} + /* * Opal message notifier based on message type. Allow subscribers to get * notified for specific messgae type. @@ -244,14 +293,30 @@ machine_early_initcall(powernv, opal_register_exception_handlers); int opal_message_notifier_register(enum opal_msg_type msg_type, struct notifier_block *nb) { + int ret; + unsigned long flags; + if (!nb || msg_type >= OPAL_MSG_TYPE_MAX) { pr_warn("%s: Invalid arguments, msg_type:%d\n", __func__, msg_type); return -EINVAL; } - return atomic_notifier_chain_register( - &opal_msg_notifier_head[msg_type], nb); + spin_lock_irqsave(&msg_list_lock, flags); + ret = atomic_notifier_chain_register( + &opal_msg_notifier_head[msg_type], nb); + + /* + * If the registration succeeded, replay any queued messages that came + * in prior to the notifier chain registration. msg_list_lock held here + * to ensure they're delivered prior to any subsequent messages. + */ + if (ret == 0) + dequeue_replay_msg(msg_type); + + spin_unlock_irqrestore(&msg_list_lock, flags); + + return ret; } EXPORT_SYMBOL_GPL(opal_message_notifier_register); @@ -265,6 +330,23 @@ EXPORT_SYMBOL_GPL(opal_message_notifier_unregister); static void opal_message_do_notify(uint32_t msg_type, void *msg) { + unsigned long flags; + bool queued = false; + + spin_lock_irqsave(&msg_list_lock, flags); + if (opal_msg_notifier_head[msg_type].head == NULL) { + /* + * Queue up the msg since no notifiers have registered + * yet for this msg_type. + */ + queue_replay_msg(msg); + queued = true; + } + spin_unlock_irqrestore(&msg_list_lock, flags); + + if (queued) + return; + /* notify subscribers */ atomic_notifier_call_chain(&opal_msg_notifier_head[msg_type], msg_type, msg); @@ -1002,6 +1084,9 @@ static int __init opal_init(void) /* Initialise OPAL Power control interface */ opal_power_control_init(); + /* Initialize OPAL secure variables */ + opal_pdev_init("ibm,secvar-backend"); + return 0; } machine_subsys_initcall(powernv, opal_init); diff --git a/arch/powerpc/platforms/powernv/pci-ioda-tce.c b/arch/powerpc/platforms/powernv/pci-ioda-tce.c index a0b9c0c23ed2..5dc6847d5f4c 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda-tce.c +++ b/arch/powerpc/platforms/powernv/pci-ioda-tce.c @@ -340,14 +340,6 @@ free_tces_exit: return -ENOMEM; } -static void pnv_iommu_table_group_link_free(struct rcu_head *head) -{ - struct iommu_table_group_link *tgl = container_of(head, - struct iommu_table_group_link, rcu); - - kfree(tgl); -} - void pnv_pci_unlink_table_and_group(struct iommu_table *tbl, struct iommu_table_group *table_group) { @@ -363,7 +355,7 @@ void pnv_pci_unlink_table_and_group(struct iommu_table *tbl, list_for_each_entry_rcu(tgl, &tbl->it_group_list, next) { if (tgl->table_group == table_group) { list_del_rcu(&tgl->next); - call_rcu(&tgl->rcu, pnv_iommu_table_group_link_free); + kfree_rcu(tgl, rcu); found = true; break; } diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index c28d0d9b7ee0..da1068a9c263 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -3086,8 +3086,8 @@ static int pnv_pci_diag_data_set(void *data, u64 val) return 0; } -DEFINE_SIMPLE_ATTRIBUTE(pnv_pci_diag_data_fops, NULL, - pnv_pci_diag_data_set, "%llu\n"); +DEFINE_DEBUGFS_ATTRIBUTE(pnv_pci_diag_data_fops, NULL, pnv_pci_diag_data_set, + "%llu\n"); #endif /* CONFIG_DEBUG_FS */ @@ -3112,8 +3112,8 @@ static void pnv_pci_ioda_create_dbgfs(void) continue; } - debugfs_create_file("dump_diag_regs", 0200, phb->dbgfs, hose, - &pnv_pci_diag_data_fops); + debugfs_create_file_unsafe("dump_diag_regs", 0200, phb->dbgfs, + hose, &pnv_pci_diag_data_fops); } #endif /* CONFIG_DEBUG_FS */ } diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c index 2825d004dece..c0bea75ac27b 100644 --- a/arch/powerpc/platforms/powernv/pci.c +++ b/arch/powerpc/platforms/powernv/pci.c @@ -945,6 +945,23 @@ void __init pnv_pci_init(void) if (!firmware_has_feature(FW_FEATURE_OPAL)) return; +#ifdef CONFIG_PCIEPORTBUS + /* + * On PowerNV PCIe devices are (currently) managed in cooperation + * with firmware. This isn't *strictly* required, but there's enough + * assumptions baked into both firmware and the platform code that + * it's unwise to allow the portbus services to be used. + * + * We need to fix this eventually, but for now set this flag to disable + * the portbus driver. The AER service isn't required since that AER + * events are handled via EEH. The pciehp hotplug driver can't work + * without kernel changes (and portbus binding breaks pnv_php). The + * other services also require some thinking about how we're going + * to integrate them. + */ + pcie_ports_disabled = true; +#endif + /* Look for IODA IO-Hubs. */ for_each_compatible_node(np, NULL, "ibm,ioda-hub") { pnv_pci_init_ioda_hub(np); diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c index fbd6e6b7bbf2..13e251699346 100644 --- a/arch/powerpc/platforms/powernv/smp.c +++ b/arch/powerpc/platforms/powernv/smp.c @@ -146,20 +146,25 @@ static int pnv_smp_cpu_disable(void) return 0; } +static void pnv_flush_interrupts(void) +{ + if (cpu_has_feature(CPU_FTR_ARCH_300)) { + if (xive_enabled()) + xive_flush_interrupt(); + else + icp_opal_flush_interrupt(); + } else { + icp_native_flush_interrupt(); + } +} + static void pnv_smp_cpu_kill_self(void) { + unsigned long srr1, unexpected_mask, wmask; unsigned int cpu; - unsigned long srr1, wmask; u64 lpcr_val; /* Standard hot unplug procedure */ - /* - * This hard disables local interurpts, ensuring we have no lazy - * irqs pending. - */ - WARN_ON(irqs_disabled()); - hard_irq_disable(); - WARN_ON(lazy_irq_pending()); idle_task_exit(); current->active_mm = NULL; /* for sanity */ @@ -173,6 +178,27 @@ static void pnv_smp_cpu_kill_self(void) wmask = SRR1_WAKEMASK_P8; /* + * This turns the irq soft-disabled state we're called with, into a + * hard-disabled state with pending irq_happened interrupts cleared. + * + * PACA_IRQ_DEC - Decrementer should be ignored. + * PACA_IRQ_HMI - Can be ignored, processing is done in real mode. + * PACA_IRQ_DBELL, EE, PMI - Unexpected. + */ + hard_irq_disable(); + if (generic_check_cpu_restart(cpu)) + goto out; + + unexpected_mask = ~(PACA_IRQ_DEC | PACA_IRQ_HMI | PACA_IRQ_HARD_DIS); + if (local_paca->irq_happened & unexpected_mask) { + if (local_paca->irq_happened & PACA_IRQ_EE) + pnv_flush_interrupts(); + DBG("CPU%d Unexpected exit while offline irq_happened=%lx!\n", + cpu, local_paca->irq_happened); + } + local_paca->irq_happened = PACA_IRQ_HARD_DIS; + + /* * We don't want to take decrementer interrupts while we are * offline, so clear LPCR:PECE1. We keep PECE2 (and * LPCR_PECE_HVEE on P9) enabled so as to let IPIs in. @@ -197,6 +223,7 @@ static void pnv_smp_cpu_kill_self(void) srr1 = pnv_cpu_offline(cpu); + WARN_ON_ONCE(!irqs_disabled()); WARN_ON(lazy_irq_pending()); /* @@ -212,13 +239,7 @@ static void pnv_smp_cpu_kill_self(void) */ if (((srr1 & wmask) == SRR1_WAKEEE) || ((srr1 & wmask) == SRR1_WAKEHVI)) { - if (cpu_has_feature(CPU_FTR_ARCH_300)) { - if (xive_enabled()) - xive_flush_interrupt(); - else - icp_opal_flush_interrupt(); - } else - icp_native_flush_interrupt(); + pnv_flush_interrupts(); } else if ((srr1 & wmask) == SRR1_WAKEHDBELL) { unsigned long msg = PPC_DBELL_TYPE(PPC_DBELL_SERVER); asm volatile(PPC_MSGCLR(%0) : : "r" (msg)); @@ -266,7 +287,7 @@ static void pnv_smp_cpu_kill_self(void) */ lpcr_val = mfspr(SPRN_LPCR) | (u64)LPCR_PECE1; pnv_program_cpu_hotplug_lpcr(cpu, lpcr_val); - +out: DBG("CPU%d coming online...\n", cpu); } diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig index 9e35cddddf73..595e9f8a6539 100644 --- a/arch/powerpc/platforms/pseries/Kconfig +++ b/arch/powerpc/platforms/pseries/Kconfig @@ -108,6 +108,7 @@ config PPC_SMLPAR config CMM tristate "Collaborative memory management" depends on PPC_SMLPAR + select MEMORY_BALLOON default y help Select this option, if you want to enable the kernel interface diff --git a/arch/powerpc/platforms/pseries/cmm.c b/arch/powerpc/platforms/pseries/cmm.c index b33251d75927..91571841df8a 100644 --- a/arch/powerpc/platforms/pseries/cmm.c +++ b/arch/powerpc/platforms/pseries/cmm.c @@ -19,6 +19,10 @@ #include <linux/stringify.h> #include <linux/swap.h> #include <linux/device.h> +#include <linux/mount.h> +#include <linux/pseudo_fs.h> +#include <linux/magic.h> +#include <linux/balloon_compaction.h> #include <asm/firmware.h> #include <asm/hvcall.h> #include <asm/mmu.h> @@ -38,12 +42,8 @@ #define CMM_MIN_MEM_MB 256 #define KB2PAGES(_p) ((_p)>>(PAGE_SHIFT-10)) #define PAGES2KB(_p) ((_p)<<(PAGE_SHIFT-10)) -/* - * The priority level tries to ensure that this notifier is called as - * late as possible to reduce thrashing in the shared memory pool. - */ + #define CMM_MEM_HOTPLUG_PRI 1 -#define CMM_MEM_ISOLATE_PRI 15 static unsigned int delay = CMM_DEFAULT_DELAY; static unsigned int hotplug_delay = CMM_HOTPLUG_DELAY; @@ -51,6 +51,8 @@ static unsigned int oom_kb = CMM_OOM_KB; static unsigned int cmm_debug = CMM_DEBUG; static unsigned int cmm_disabled = CMM_DISABLE; static unsigned long min_mem_mb = CMM_MIN_MEM_MB; +static bool __read_mostly simulate; +static unsigned long simulate_loan_target_kb; static struct device cmm_dev; MODULE_AUTHOR("Brian King <brking@linux.vnet.ibm.com>"); @@ -74,35 +76,31 @@ MODULE_PARM_DESC(min_mem_mb, "Minimum amount of memory (in MB) to not balloon. " module_param_named(debug, cmm_debug, uint, 0644); MODULE_PARM_DESC(debug, "Enable module debugging logging. Set to 1 to enable. " "[Default=" __stringify(CMM_DEBUG) "]"); - -#define CMM_NR_PAGES ((PAGE_SIZE - sizeof(void *) - sizeof(unsigned long)) / sizeof(unsigned long)) +module_param_named(simulate, simulate, bool, 0444); +MODULE_PARM_DESC(simulate, "Enable simulation mode (no communication with hw)."); #define cmm_dbg(...) if (cmm_debug) { printk(KERN_INFO "cmm: "__VA_ARGS__); } -struct cmm_page_array { - struct cmm_page_array *next; - unsigned long index; - unsigned long page[CMM_NR_PAGES]; -}; - -static unsigned long loaned_pages; +static atomic_long_t loaned_pages; static unsigned long loaned_pages_target; static unsigned long oom_freed_pages; -static struct cmm_page_array *cmm_page_list; -static DEFINE_SPINLOCK(cmm_lock); - static DEFINE_MUTEX(hotplug_mutex); static int hotplug_occurred; /* protected by the hotplug mutex */ static struct task_struct *cmm_thread_ptr; +static struct balloon_dev_info b_dev_info; -static long plpar_page_set_loaned(unsigned long vpa) +static long plpar_page_set_loaned(struct page *page) { + const unsigned long vpa = page_to_phys(page); unsigned long cmo_page_sz = cmo_get_page_size(); long rc = 0; int i; + if (unlikely(simulate)) + return 0; + for (i = 0; !rc && i < PAGE_SIZE; i += cmo_page_sz) rc = plpar_hcall_norets(H_PAGE_INIT, H_PAGE_SET_LOANED, vpa + i, 0); @@ -113,12 +111,16 @@ static long plpar_page_set_loaned(unsigned long vpa) return rc; } -static long plpar_page_set_active(unsigned long vpa) +static long plpar_page_set_active(struct page *page) { + const unsigned long vpa = page_to_phys(page); unsigned long cmo_page_sz = cmo_get_page_size(); long rc = 0; int i; + if (unlikely(simulate)) + return 0; + for (i = 0; !rc && i < PAGE_SIZE; i += cmo_page_sz) rc = plpar_hcall_norets(H_PAGE_INIT, H_PAGE_SET_ACTIVE, vpa + i, 0); @@ -138,8 +140,7 @@ static long plpar_page_set_active(unsigned long vpa) **/ static long cmm_alloc_pages(long nr) { - struct cmm_page_array *pa, *npa; - unsigned long addr; + struct page *page; long rc; cmm_dbg("Begin request for %ld pages\n", nr); @@ -156,46 +157,19 @@ static long cmm_alloc_pages(long nr) break; } - addr = __get_free_page(GFP_NOIO | __GFP_NOWARN | - __GFP_NORETRY | __GFP_NOMEMALLOC); - if (!addr) + page = balloon_page_alloc(); + if (!page) break; - spin_lock(&cmm_lock); - pa = cmm_page_list; - if (!pa || pa->index >= CMM_NR_PAGES) { - /* Need a new page for the page list. */ - spin_unlock(&cmm_lock); - npa = (struct cmm_page_array *)__get_free_page( - GFP_NOIO | __GFP_NOWARN | - __GFP_NORETRY | __GFP_NOMEMALLOC); - if (!npa) { - pr_info("%s: Can not allocate new page list\n", __func__); - free_page(addr); - break; - } - spin_lock(&cmm_lock); - pa = cmm_page_list; - - if (!pa || pa->index >= CMM_NR_PAGES) { - npa->next = pa; - npa->index = 0; - pa = npa; - cmm_page_list = pa; - } else - free_page((unsigned long) npa); - } - - if ((rc = plpar_page_set_loaned(__pa(addr)))) { + rc = plpar_page_set_loaned(page); + if (rc) { pr_err("%s: Can not set page to loaned. rc=%ld\n", __func__, rc); - spin_unlock(&cmm_lock); - free_page(addr); + __free_page(page); break; } - pa->page[pa->index++] = addr; - loaned_pages++; - totalram_pages_dec(); - spin_unlock(&cmm_lock); + balloon_page_enqueue(&b_dev_info, page); + atomic_long_inc(&loaned_pages); + adjust_managed_page_count(page, -1); nr--; } @@ -212,30 +186,19 @@ static long cmm_alloc_pages(long nr) **/ static long cmm_free_pages(long nr) { - struct cmm_page_array *pa; - unsigned long addr; + struct page *page; cmm_dbg("Begin free of %ld pages.\n", nr); - spin_lock(&cmm_lock); - pa = cmm_page_list; while (nr) { - if (!pa || pa->index <= 0) + page = balloon_page_dequeue(&b_dev_info); + if (!page) break; - addr = pa->page[--pa->index]; - - if (pa->index == 0) { - pa = pa->next; - free_page((unsigned long) cmm_page_list); - cmm_page_list = pa; - } - - plpar_page_set_active(__pa(addr)); - free_page(addr); - loaned_pages--; + plpar_page_set_active(page); + adjust_managed_page_count(page, 1); + __free_page(page); + atomic_long_dec(&loaned_pages); nr--; - totalram_pages_inc(); } - spin_unlock(&cmm_lock); cmm_dbg("End request with %ld pages unfulfilled\n", nr); return nr; } @@ -257,7 +220,7 @@ static int cmm_oom_notify(struct notifier_block *self, cmm_dbg("OOM processing started\n"); nr = cmm_free_pages(nr); - loaned_pages_target = loaned_pages; + loaned_pages_target = atomic_long_read(&loaned_pages); *freed += KB2PAGES(oom_kb) - nr; oom_freed_pages += KB2PAGES(oom_kb) - nr; cmm_dbg("OOM processing complete\n"); @@ -274,19 +237,24 @@ static int cmm_oom_notify(struct notifier_block *self, **/ static void cmm_get_mpp(void) { + const long __loaned_pages = atomic_long_read(&loaned_pages); + const long total_pages = totalram_pages() + __loaned_pages; int rc; struct hvcall_mpp_data mpp_data; signed long active_pages_target, page_loan_request, target; - signed long total_pages = totalram_pages() + loaned_pages; signed long min_mem_pages = (min_mem_mb * 1024 * 1024) / PAGE_SIZE; - rc = h_get_mpp(&mpp_data); - - if (rc != H_SUCCESS) - return; - - page_loan_request = div_s64((s64)mpp_data.loan_request, PAGE_SIZE); - target = page_loan_request + (signed long)loaned_pages; + if (likely(!simulate)) { + rc = h_get_mpp(&mpp_data); + if (rc != H_SUCCESS) + return; + page_loan_request = div_s64((s64)mpp_data.loan_request, + PAGE_SIZE); + target = page_loan_request + __loaned_pages; + } else { + target = KB2PAGES(simulate_loan_target_kb); + page_loan_request = target - __loaned_pages; + } if (target < 0 || total_pages < min_mem_pages) target = 0; @@ -307,7 +275,7 @@ static void cmm_get_mpp(void) loaned_pages_target = target; cmm_dbg("delta = %ld, loaned = %lu, target = %lu, oom = %lu, totalram = %lu\n", - page_loan_request, loaned_pages, loaned_pages_target, + page_loan_request, __loaned_pages, loaned_pages_target, oom_freed_pages, totalram_pages()); } @@ -325,6 +293,7 @@ static struct notifier_block cmm_oom_nb = { static int cmm_thread(void *dummy) { unsigned long timeleft; + long __loaned_pages; while (1) { timeleft = msleep_interruptible(delay * 1000); @@ -355,11 +324,12 @@ static int cmm_thread(void *dummy) cmm_get_mpp(); - if (loaned_pages_target > loaned_pages) { - if (cmm_alloc_pages(loaned_pages_target - loaned_pages)) - loaned_pages_target = loaned_pages; - } else if (loaned_pages_target < loaned_pages) - cmm_free_pages(loaned_pages - loaned_pages_target); + __loaned_pages = atomic_long_read(&loaned_pages); + if (loaned_pages_target > __loaned_pages) { + if (cmm_alloc_pages(loaned_pages_target - __loaned_pages)) + loaned_pages_target = __loaned_pages; + } else if (loaned_pages_target < __loaned_pages) + cmm_free_pages(__loaned_pages - loaned_pages_target); } return 0; } @@ -373,7 +343,7 @@ static int cmm_thread(void *dummy) } \ static DEVICE_ATTR(name, 0444, show_##name, NULL) -CMM_SHOW(loaned_kb, "%lu\n", PAGES2KB(loaned_pages)); +CMM_SHOW(loaned_kb, "%lu\n", PAGES2KB(atomic_long_read(&loaned_pages))); CMM_SHOW(loaned_target_kb, "%lu\n", PAGES2KB(loaned_pages_target)); static ssize_t show_oom_pages(struct device *dev, @@ -406,11 +376,18 @@ static struct device_attribute *cmm_attrs[] = { &dev_attr_oom_freed_kb, }; +static DEVICE_ULONG_ATTR(simulate_loan_target_kb, 0644, + simulate_loan_target_kb); + static struct bus_type cmm_subsys = { .name = "cmm", .dev_name = "cmm", }; +static void cmm_release_device(struct device *dev) +{ +} + /** * cmm_sysfs_register - Register with sysfs * @@ -426,6 +403,7 @@ static int cmm_sysfs_register(struct device *dev) dev->id = 0; dev->bus = &cmm_subsys; + dev->release = cmm_release_device; if ((rc = device_register(dev))) goto subsys_unregister; @@ -435,6 +413,11 @@ static int cmm_sysfs_register(struct device *dev) goto fail; } + if (!simulate) + return 0; + rc = device_create_file(dev, &dev_attr_simulate_loan_target_kb.attr); + if (rc) + goto fail; return 0; fail: @@ -471,7 +454,7 @@ static int cmm_reboot_notifier(struct notifier_block *nb, if (cmm_thread_ptr) kthread_stop(cmm_thread_ptr); cmm_thread_ptr = NULL; - cmm_free_pages(loaned_pages); + cmm_free_pages(atomic_long_read(&loaned_pages)); } return NOTIFY_DONE; } @@ -481,142 +464,6 @@ static struct notifier_block cmm_reboot_nb = { }; /** - * cmm_count_pages - Count the number of pages loaned in a particular range. - * - * @arg: memory_isolate_notify structure with address range and count - * - * Return value: - * 0 on success - **/ -static unsigned long cmm_count_pages(void *arg) -{ - struct memory_isolate_notify *marg = arg; - struct cmm_page_array *pa; - unsigned long start = (unsigned long)pfn_to_kaddr(marg->start_pfn); - unsigned long end = start + (marg->nr_pages << PAGE_SHIFT); - unsigned long idx; - - spin_lock(&cmm_lock); - pa = cmm_page_list; - while (pa) { - if ((unsigned long)pa >= start && (unsigned long)pa < end) - marg->pages_found++; - for (idx = 0; idx < pa->index; idx++) - if (pa->page[idx] >= start && pa->page[idx] < end) - marg->pages_found++; - pa = pa->next; - } - spin_unlock(&cmm_lock); - return 0; -} - -/** - * cmm_memory_isolate_cb - Handle memory isolation notifier calls - * @self: notifier block struct - * @action: action to take - * @arg: struct memory_isolate_notify data for handler - * - * Return value: - * NOTIFY_OK or notifier error based on subfunction return value - **/ -static int cmm_memory_isolate_cb(struct notifier_block *self, - unsigned long action, void *arg) -{ - int ret = 0; - - if (action == MEM_ISOLATE_COUNT) - ret = cmm_count_pages(arg); - - return notifier_from_errno(ret); -} - -static struct notifier_block cmm_mem_isolate_nb = { - .notifier_call = cmm_memory_isolate_cb, - .priority = CMM_MEM_ISOLATE_PRI -}; - -/** - * cmm_mem_going_offline - Unloan pages where memory is to be removed - * @arg: memory_notify structure with page range to be offlined - * - * Return value: - * 0 on success - **/ -static int cmm_mem_going_offline(void *arg) -{ - struct memory_notify *marg = arg; - unsigned long start_page = (unsigned long)pfn_to_kaddr(marg->start_pfn); - unsigned long end_page = start_page + (marg->nr_pages << PAGE_SHIFT); - struct cmm_page_array *pa_curr, *pa_last, *npa; - unsigned long idx; - unsigned long freed = 0; - - cmm_dbg("Memory going offline, searching 0x%lx (%ld pages).\n", - start_page, marg->nr_pages); - spin_lock(&cmm_lock); - - /* Search the page list for pages in the range to be offlined */ - pa_last = pa_curr = cmm_page_list; - while (pa_curr) { - for (idx = (pa_curr->index - 1); (idx + 1) > 0; idx--) { - if ((pa_curr->page[idx] < start_page) || - (pa_curr->page[idx] >= end_page)) - continue; - - plpar_page_set_active(__pa(pa_curr->page[idx])); - free_page(pa_curr->page[idx]); - freed++; - loaned_pages--; - totalram_pages_inc(); - pa_curr->page[idx] = pa_last->page[--pa_last->index]; - if (pa_last->index == 0) { - if (pa_curr == pa_last) - pa_curr = pa_last->next; - pa_last = pa_last->next; - free_page((unsigned long)cmm_page_list); - cmm_page_list = pa_last; - } - } - pa_curr = pa_curr->next; - } - - /* Search for page list structures in the range to be offlined */ - pa_last = NULL; - pa_curr = cmm_page_list; - while (pa_curr) { - if (((unsigned long)pa_curr >= start_page) && - ((unsigned long)pa_curr < end_page)) { - npa = (struct cmm_page_array *)__get_free_page( - GFP_NOIO | __GFP_NOWARN | - __GFP_NORETRY | __GFP_NOMEMALLOC); - if (!npa) { - spin_unlock(&cmm_lock); - cmm_dbg("Failed to allocate memory for list " - "management. Memory hotplug " - "failed.\n"); - return -ENOMEM; - } - memcpy(npa, pa_curr, PAGE_SIZE); - if (pa_curr == cmm_page_list) - cmm_page_list = npa; - if (pa_last) - pa_last->next = npa; - free_page((unsigned long) pa_curr); - freed++; - pa_curr = npa; - } - - pa_last = pa_curr; - pa_curr = pa_curr->next; - } - - spin_unlock(&cmm_lock); - cmm_dbg("Released %ld pages in the search range.\n", freed); - - return 0; -} - -/** * cmm_memory_cb - Handle memory hotplug notifier calls * @self: notifier block struct * @action: action to take @@ -635,7 +482,6 @@ static int cmm_memory_cb(struct notifier_block *self, case MEM_GOING_OFFLINE: mutex_lock(&hotplug_mutex); hotplug_occurred = 1; - ret = cmm_mem_going_offline(arg); break; case MEM_OFFLINE: case MEM_CANCEL_OFFLINE: @@ -656,6 +502,106 @@ static struct notifier_block cmm_mem_nb = { .priority = CMM_MEM_HOTPLUG_PRI }; +#ifdef CONFIG_BALLOON_COMPACTION +static struct vfsmount *balloon_mnt; + +static int cmm_init_fs_context(struct fs_context *fc) +{ + return init_pseudo(fc, PPC_CMM_MAGIC) ? 0 : -ENOMEM; +} + +static struct file_system_type balloon_fs = { + .name = "ppc-cmm", + .init_fs_context = cmm_init_fs_context, + .kill_sb = kill_anon_super, +}; + +static int cmm_migratepage(struct balloon_dev_info *b_dev_info, + struct page *newpage, struct page *page, + enum migrate_mode mode) +{ + unsigned long flags; + + /* + * loan/"inflate" the newpage first. + * + * We might race against the cmm_thread who might discover after our + * loan request that another page is to be unloaned. However, once + * the cmm_thread runs again later, this error will automatically + * be corrected. + */ + if (plpar_page_set_loaned(newpage)) { + /* Unlikely, but possible. Tell the caller not to retry now. */ + pr_err_ratelimited("%s: Cannot set page to loaned.", __func__); + return -EBUSY; + } + + /* balloon page list reference */ + get_page(newpage); + + spin_lock_irqsave(&b_dev_info->pages_lock, flags); + balloon_page_insert(b_dev_info, newpage); + balloon_page_delete(page); + b_dev_info->isolated_pages--; + spin_unlock_irqrestore(&b_dev_info->pages_lock, flags); + + /* + * activate/"deflate" the old page. We ignore any errors just like the + * other callers. + */ + plpar_page_set_active(page); + + /* balloon page list reference */ + put_page(page); + + return MIGRATEPAGE_SUCCESS; +} + +static int cmm_balloon_compaction_init(void) +{ + int rc; + + balloon_devinfo_init(&b_dev_info); + b_dev_info.migratepage = cmm_migratepage; + + balloon_mnt = kern_mount(&balloon_fs); + if (IS_ERR(balloon_mnt)) { + rc = PTR_ERR(balloon_mnt); + balloon_mnt = NULL; + return rc; + } + + b_dev_info.inode = alloc_anon_inode(balloon_mnt->mnt_sb); + if (IS_ERR(b_dev_info.inode)) { + rc = PTR_ERR(b_dev_info.inode); + b_dev_info.inode = NULL; + kern_unmount(balloon_mnt); + balloon_mnt = NULL; + return rc; + } + + b_dev_info.inode->i_mapping->a_ops = &balloon_aops; + return 0; +} +static void cmm_balloon_compaction_deinit(void) +{ + if (b_dev_info.inode) + iput(b_dev_info.inode); + b_dev_info.inode = NULL; + kern_unmount(balloon_mnt); + balloon_mnt = NULL; +} +#else /* CONFIG_BALLOON_COMPACTION */ +static int cmm_balloon_compaction_init(void) +{ + return 0; +} + +static void cmm_balloon_compaction_deinit(void) +{ +} +#endif /* CONFIG_BALLOON_COMPACTION */ + /** * cmm_init - Module initialization * @@ -664,26 +610,31 @@ static struct notifier_block cmm_mem_nb = { **/ static int cmm_init(void) { - int rc = -ENOMEM; + int rc; - if (!firmware_has_feature(FW_FEATURE_CMO)) + if (!firmware_has_feature(FW_FEATURE_CMO) && !simulate) return -EOPNOTSUPP; - if ((rc = register_oom_notifier(&cmm_oom_nb)) < 0) + rc = cmm_balloon_compaction_init(); + if (rc) return rc; + rc = register_oom_notifier(&cmm_oom_nb); + if (rc < 0) + goto out_balloon_compaction; + if ((rc = register_reboot_notifier(&cmm_reboot_nb))) goto out_oom_notifier; if ((rc = cmm_sysfs_register(&cmm_dev))) goto out_reboot_notifier; - if (register_memory_notifier(&cmm_mem_nb) || - register_memory_isolate_notifier(&cmm_mem_isolate_nb)) + rc = register_memory_notifier(&cmm_mem_nb); + if (rc) goto out_unregister_notifier; if (cmm_disabled) - return rc; + return 0; cmm_thread_ptr = kthread_run(cmm_thread, NULL, "cmmthread"); if (IS_ERR(cmm_thread_ptr)) { @@ -691,16 +642,16 @@ static int cmm_init(void) goto out_unregister_notifier; } - return rc; - + return 0; out_unregister_notifier: unregister_memory_notifier(&cmm_mem_nb); - unregister_memory_isolate_notifier(&cmm_mem_isolate_nb); cmm_unregister_sysfs(&cmm_dev); out_reboot_notifier: unregister_reboot_notifier(&cmm_reboot_nb); out_oom_notifier: unregister_oom_notifier(&cmm_oom_nb); +out_balloon_compaction: + cmm_balloon_compaction_deinit(); return rc; } @@ -717,9 +668,9 @@ static void cmm_exit(void) unregister_oom_notifier(&cmm_oom_nb); unregister_reboot_notifier(&cmm_reboot_nb); unregister_memory_notifier(&cmm_mem_nb); - unregister_memory_isolate_notifier(&cmm_mem_isolate_nb); - cmm_free_pages(loaned_pages); + cmm_free_pages(atomic_long_read(&loaned_pages)); cmm_unregister_sysfs(&cmm_dev); + cmm_balloon_compaction_deinit(); } /** @@ -739,7 +690,7 @@ static int cmm_set_disable(const char *val, const struct kernel_param *kp) if (cmm_thread_ptr) kthread_stop(cmm_thread_ptr); cmm_thread_ptr = NULL; - cmm_free_pages(loaned_pages); + cmm_free_pages(atomic_long_read(&loaned_pages)); } else if (!disable && cmm_disabled) { cmm_thread_ptr = kthread_run(cmm_thread, NULL, "cmmthread"); if (IS_ERR(cmm_thread_ptr)) diff --git a/arch/powerpc/platforms/pseries/dtl.c b/arch/powerpc/platforms/pseries/dtl.c index 2b87480f2837..eab8aa293743 100644 --- a/arch/powerpc/platforms/pseries/dtl.c +++ b/arch/powerpc/platforms/pseries/dtl.c @@ -19,7 +19,6 @@ struct dtl { struct dtl_entry *buf; - struct dentry *file; int cpu; int buf_entries; u64 last_idx; @@ -320,46 +319,28 @@ static const struct file_operations dtl_fops = { static struct dentry *dtl_dir; -static int dtl_setup_file(struct dtl *dtl) +static void dtl_setup_file(struct dtl *dtl) { char name[10]; sprintf(name, "cpu-%d", dtl->cpu); - dtl->file = debugfs_create_file(name, 0400, dtl_dir, dtl, &dtl_fops); - if (!dtl->file) - return -ENOMEM; - - return 0; + debugfs_create_file(name, 0400, dtl_dir, dtl, &dtl_fops); } static int dtl_init(void) { - struct dentry *event_mask_file, *buf_entries_file; - int rc, i; + int i; if (!firmware_has_feature(FW_FEATURE_SPLPAR)) return -ENODEV; /* set up common debugfs structure */ - rc = -ENOMEM; dtl_dir = debugfs_create_dir("dtl", powerpc_debugfs_root); - if (!dtl_dir) { - printk(KERN_WARNING "%s: can't create dtl root dir\n", - __func__); - goto err; - } - event_mask_file = debugfs_create_x8("dtl_event_mask", 0600, - dtl_dir, &dtl_event_mask); - buf_entries_file = debugfs_create_u32("dtl_buf_entries", 0400, - dtl_dir, &dtl_buf_entries); - - if (!event_mask_file || !buf_entries_file) { - printk(KERN_WARNING "%s: can't create dtl files\n", __func__); - goto err_remove_dir; - } + debugfs_create_x8("dtl_event_mask", 0600, dtl_dir, &dtl_event_mask); + debugfs_create_u32("dtl_buf_entries", 0400, dtl_dir, &dtl_buf_entries); /* set up the per-cpu log structures */ for_each_possible_cpu(i) { @@ -367,16 +348,9 @@ static int dtl_init(void) spin_lock_init(&dtl->lock); dtl->cpu = i; - rc = dtl_setup_file(dtl); - if (rc) - goto err_remove_dir; + dtl_setup_file(dtl); } return 0; - -err_remove_dir: - debugfs_remove_recursive(dtl_dir); -err: - return rc; } machine_arch_initcall(pseries, dtl_init); diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c index bbda646b63b5..3e8cbfe7a80f 100644 --- a/arch/powerpc/platforms/pseries/hotplug-cpu.c +++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c @@ -338,6 +338,62 @@ static void pseries_remove_processor(struct device_node *np) cpu_maps_update_done(); } +static int dlpar_offline_cpu(struct device_node *dn) +{ + int rc = 0; + unsigned int cpu; + int len, nthreads, i; + const __be32 *intserv; + u32 thread; + + intserv = of_get_property(dn, "ibm,ppc-interrupt-server#s", &len); + if (!intserv) + return -EINVAL; + + nthreads = len / sizeof(u32); + + cpu_maps_update_begin(); + for (i = 0; i < nthreads; i++) { + thread = be32_to_cpu(intserv[i]); + for_each_present_cpu(cpu) { + if (get_hard_smp_processor_id(cpu) != thread) + continue; + + if (get_cpu_current_state(cpu) == CPU_STATE_OFFLINE) + break; + + if (get_cpu_current_state(cpu) == CPU_STATE_ONLINE) { + set_preferred_offline_state(cpu, + CPU_STATE_OFFLINE); + cpu_maps_update_done(); + timed_topology_update(1); + rc = device_offline(get_cpu_device(cpu)); + if (rc) + goto out; + cpu_maps_update_begin(); + break; + } + + /* + * The cpu is in CPU_STATE_INACTIVE. + * Upgrade it's state to CPU_STATE_OFFLINE. + */ + set_preferred_offline_state(cpu, CPU_STATE_OFFLINE); + WARN_ON(plpar_hcall_norets(H_PROD, thread) != H_SUCCESS); + __cpu_die(cpu); + break; + } + if (cpu == num_possible_cpus()) { + pr_warn("Could not find cpu to offline with physical id 0x%x\n", + thread); + } + } + cpu_maps_update_done(); + +out: + return rc; +} + static int dlpar_online_cpu(struct device_node *dn) { int rc = 0; @@ -364,8 +420,10 @@ static int dlpar_online_cpu(struct device_node *dn) timed_topology_update(1); find_and_online_cpu_nid(cpu); rc = device_online(get_cpu_device(cpu)); - if (rc) + if (rc) { + dlpar_offline_cpu(dn); goto out; + } cpu_maps_update_begin(); break; @@ -407,17 +465,67 @@ static bool dlpar_cpu_exists(struct device_node *parent, u32 drc_index) return found; } +static bool drc_info_valid_index(struct device_node *parent, u32 drc_index) +{ + struct property *info; + struct of_drc_info drc; + const __be32 *value; + u32 index; + int count, i, j; + + info = of_find_property(parent, "ibm,drc-info", NULL); + if (!info) + return false; + + value = of_prop_next_u32(info, NULL, &count); + + /* First value of ibm,drc-info is number of drc-info records */ + if (value) + value++; + else + return false; + + for (i = 0; i < count; i++) { + if (of_read_drc_info_cell(&info, &value, &drc)) + return false; + + if (strncmp(drc.drc_type, "CPU", 3)) + break; + + if (drc_index > drc.last_drc_index) + continue; + + index = drc.drc_index_start; + for (j = 0; j < drc.num_sequential_elems; j++) { + if (drc_index == index) + return true; + + index += drc.sequential_inc; + } + } + + return false; +} + static bool valid_cpu_drc_index(struct device_node *parent, u32 drc_index) { bool found = false; int rc, index; - index = 0; + if (of_find_property(parent, "ibm,drc-info", NULL)) + return drc_info_valid_index(parent, drc_index); + + /* 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 (!found) { u32 drc; rc = of_property_read_u32_index(parent, "ibm,drc-indexes", index++, &drc); + if (rc) break; @@ -505,63 +613,6 @@ static ssize_t dlpar_cpu_add(u32 drc_index) return rc; } -static int dlpar_offline_cpu(struct device_node *dn) -{ - int rc = 0; - unsigned int cpu; - int len, nthreads, i; - const __be32 *intserv; - u32 thread; - - intserv = of_get_property(dn, "ibm,ppc-interrupt-server#s", &len); - if (!intserv) - return -EINVAL; - - nthreads = len / sizeof(u32); - - cpu_maps_update_begin(); - for (i = 0; i < nthreads; i++) { - thread = be32_to_cpu(intserv[i]); - for_each_present_cpu(cpu) { - if (get_hard_smp_processor_id(cpu) != thread) - continue; - - if (get_cpu_current_state(cpu) == CPU_STATE_OFFLINE) - break; - - if (get_cpu_current_state(cpu) == CPU_STATE_ONLINE) { - set_preferred_offline_state(cpu, - CPU_STATE_OFFLINE); - cpu_maps_update_done(); - timed_topology_update(1); - rc = device_offline(get_cpu_device(cpu)); - if (rc) - goto out; - cpu_maps_update_begin(); - break; - - } - - /* - * The cpu is in CPU_STATE_INACTIVE. - * Upgrade it's state to CPU_STATE_OFFLINE. - */ - set_preferred_offline_state(cpu, CPU_STATE_OFFLINE); - BUG_ON(plpar_hcall_norets(H_PROD, thread) - != H_SUCCESS); - __cpu_die(cpu); - break; - } - if (cpu == num_possible_cpus()) - printk(KERN_WARNING "Could not find cpu to offline with physical id 0x%x\n", thread); - } - cpu_maps_update_done(); - -out: - return rc; - -} - static ssize_t dlpar_cpu_remove(struct device_node *dn, u32 drc_index) { int rc; @@ -717,19 +768,52 @@ static int dlpar_cpu_remove_by_count(u32 cpus_to_remove) return rc; } -static int find_dlpar_cpus_to_add(u32 *cpu_drcs, u32 cpus_to_add) +static int find_drc_info_cpus_to_add(struct device_node *cpus, + struct property *info, + u32 *cpu_drcs, u32 cpus_to_add) { - struct device_node *parent; + struct of_drc_info drc; + const __be32 *value; + u32 count, drc_index; int cpus_found = 0; - int index, rc; + int i, j; - parent = of_find_node_by_path("/cpus"); - if (!parent) { - pr_warn("Could not find CPU root node in device tree\n"); - kfree(cpu_drcs); + 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 @@ -737,25 +821,25 @@ static int find_dlpar_cpus_to_add(u32 *cpu_drcs, u32 cpus_to_add) */ index = 1; while (cpus_found < cpus_to_add) { - u32 drc; + rc = of_property_read_u32_index(cpus, "ibm,drc-indexes", + index++, &drc_index); - rc = of_property_read_u32_index(parent, "ibm,drc-indexes", - index++, &drc); if (rc) break; - if (dlpar_cpu_exists(parent, drc)) + if (dlpar_cpu_exists(cpus, drc_index)) continue; - cpu_drcs[cpus_found++] = drc; + cpu_drcs[cpus_found++] = drc_index; } - of_node_put(parent); 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; @@ -767,7 +851,21 @@ static int dlpar_cpu_add_by_count(u32 cpus_to_add) if (!cpu_drcs) return -EINVAL; - cpus_found = find_dlpar_cpus_to_add(cpu_drcs, cpus_to_add); + 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); diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c index 8e700390f3d6..c126b94d1943 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -338,7 +338,7 @@ static int pseries_remove_mem_node(struct device_node *np) static bool lmb_is_removable(struct drmem_lmb *lmb) { int i, scns_per_block; - int rc = 1; + bool rc = true; unsigned long pfn, block_sz; u64 phys_addr; @@ -363,11 +363,11 @@ static bool lmb_is_removable(struct drmem_lmb *lmb) if (!pfn_present(pfn)) continue; - rc &= is_mem_section_removable(pfn, PAGES_PER_SECTION); + rc = rc && is_mem_section_removable(pfn, PAGES_PER_SECTION); phys_addr += MIN_MEMORY_BLOCK_SIZE; } - return rc ? true : false; + return rc; } static int dlpar_add_lmb(struct drmem_lmb *); diff --git a/arch/powerpc/platforms/pseries/hvCall_inst.c b/arch/powerpc/platforms/pseries/hvCall_inst.c index bcc1b67417a8..c40c62ec432e 100644 --- a/arch/powerpc/platforms/pseries/hvCall_inst.c +++ b/arch/powerpc/platforms/pseries/hvCall_inst.c @@ -129,7 +129,6 @@ static void probe_hcall_exit(void *ignored, unsigned long opcode, long retval, static int __init hcall_inst_init(void) { struct dentry *hcall_root; - struct dentry *hcall_file; char cpu_name_buf[CPU_NAME_BUF_SIZE]; int cpu; @@ -145,17 +144,12 @@ static int __init hcall_inst_init(void) } hcall_root = debugfs_create_dir(HCALL_ROOT_DIR, NULL); - if (!hcall_root) - return -ENOMEM; for_each_possible_cpu(cpu) { snprintf(cpu_name_buf, CPU_NAME_BUF_SIZE, "cpu%d", cpu); - hcall_file = debugfs_create_file(cpu_name_buf, 0444, - hcall_root, - per_cpu(hcall_stats, cpu), - &hcall_inst_seq_fops); - if (!hcall_file) - return -ENOMEM; + debugfs_create_file(cpu_name_buf, 0444, hcall_root, + per_cpu(hcall_stats, cpu), + &hcall_inst_seq_fops); } return 0; diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index f87a5c64e24d..60cb29ae4739 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -774,7 +774,7 @@ static long pSeries_lpar_hpte_remove(unsigned long hpte_group) /* don't remove a bolted entry */ lpar_rc = plpar_pte_remove(H_ANDCOND, hpte_group + slot_offset, - (0x1UL << 4), &dummy1, &dummy2); + HPTE_V_BOLTED, &dummy1, &dummy2); if (lpar_rc == H_SUCCESS) return i; @@ -938,11 +938,19 @@ static long pSeries_lpar_hpte_find(unsigned long vpn, int psize, int ssize) hash = hpt_hash(vpn, mmu_psize_defs[psize].shift, ssize); want_v = hpte_encode_avpn(vpn, psize, ssize); - /* Bolted entries are always in the primary group */ + /* + * We try to keep bolted entries always in primary hash + * But in some case we can find them in secondary too. + */ hpte_group = (hash & htab_hash_mask) * HPTES_PER_GROUP; slot = __pSeries_lpar_hpte_find(want_v, hpte_group); - if (slot < 0) - return -1; + if (slot < 0) { + /* Try in secondary */ + hpte_group = (~hash & htab_hash_mask) * HPTES_PER_GROUP; + slot = __pSeries_lpar_hpte_find(want_v, hpte_group); + if (slot < 0) + return -1; + } return hpte_group + slot; } @@ -1992,30 +2000,17 @@ static int __init vpa_debugfs_init(void) { char name[16]; long i; - static struct dentry *vpa_dir; + struct dentry *vpa_dir; if (!firmware_has_feature(FW_FEATURE_SPLPAR)) return 0; vpa_dir = debugfs_create_dir("vpa", powerpc_debugfs_root); - if (!vpa_dir) { - pr_warn("%s: can't create vpa root dir\n", __func__); - return -ENOMEM; - } /* set up the per-cpu vpa file*/ for_each_possible_cpu(i) { - struct dentry *d; - sprintf(name, "cpu-%ld", i); - - d = debugfs_create_file(name, 0400, vpa_dir, (void *)i, - &vpa_fops); - if (!d) { - pr_warn("%s: can't create per-cpu vpa file\n", - __func__); - return -ENOMEM; - } + debugfs_create_file(name, 0400, vpa_dir, (void *)i, &vpa_fops); } return 0; diff --git a/arch/powerpc/platforms/pseries/of_helpers.c b/arch/powerpc/platforms/pseries/of_helpers.c index 6df192f38f80..66dfd8256712 100644 --- a/arch/powerpc/platforms/pseries/of_helpers.c +++ b/arch/powerpc/platforms/pseries/of_helpers.c @@ -45,14 +45,14 @@ struct device_node *pseries_of_derive_parent(const char *path) int of_read_drc_info_cell(struct property **prop, const __be32 **curval, struct of_drc_info *data) { - const char *p; + const char *p = (char *)(*curval); const __be32 *p2; if (!data) return -EINVAL; /* Get drc-type:encode-string */ - p = data->drc_type = (char*) (*curval); + data->drc_type = (char *)p; p = of_prop_next_string(*prop, p); if (!p) return -EINVAL; @@ -65,9 +65,7 @@ int of_read_drc_info_cell(struct property **prop, const __be32 **curval, /* Get drc-index-start:encode-int */ p2 = (const __be32 *)p; - p2 = of_prop_next_u32(*prop, p2, &data->drc_index_start); - if (!p2) - return -EINVAL; + data->drc_index_start = be32_to_cpu(*p2); /* Get drc-name-suffix-start:encode-int */ p2 = of_prop_next_u32(*prop, p2, &data->drc_name_suffix_start); diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c index 61883291defc..c2ef320ba1bf 100644 --- a/arch/powerpc/platforms/pseries/papr_scm.c +++ b/arch/powerpc/platforms/pseries/papr_scm.c @@ -152,7 +152,7 @@ static int papr_scm_meta_get(struct papr_scm_priv *p, int len, read; int64_t ret; - if ((hdr->in_offset + hdr->in_length) >= p->metadata_size) + if ((hdr->in_offset + hdr->in_length) > p->metadata_size) return -EINVAL; for (len = hdr->in_length; len; len -= read) { @@ -206,7 +206,7 @@ static int papr_scm_meta_set(struct papr_scm_priv *p, __be64 data_be; int64_t ret; - if ((hdr->in_offset + hdr->in_length) >= p->metadata_size) + if ((hdr->in_offset + hdr->in_length) > p->metadata_size) return -EINVAL; for (len = hdr->in_length; len; len -= wrote) { @@ -284,25 +284,6 @@ int papr_scm_ndctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm, return 0; } -static const struct attribute_group *region_attr_groups[] = { - &nd_region_attribute_group, - &nd_device_attribute_group, - &nd_mapping_attribute_group, - &nd_numa_attribute_group, - NULL, -}; - -static const struct attribute_group *bus_attr_groups[] = { - &nvdimm_bus_attribute_group, - NULL, -}; - -static const struct attribute_group *papr_scm_dimm_groups[] = { - &nvdimm_attribute_group, - &nd_device_attribute_group, - NULL, -}; - static inline int papr_scm_node(int node) { int min_dist = INT_MAX, dist; @@ -333,7 +314,6 @@ static int papr_scm_nvdimm_init(struct papr_scm_priv *p) p->bus_desc.ndctl = papr_scm_ndctl; p->bus_desc.module = THIS_MODULE; p->bus_desc.of_node = p->pdev->dev.of_node; - p->bus_desc.attr_groups = bus_attr_groups; p->bus_desc.provider_name = kstrdup(p->pdev->name, GFP_KERNEL); if (!p->bus_desc.provider_name) @@ -348,8 +328,8 @@ static int papr_scm_nvdimm_init(struct papr_scm_priv *p) dimm_flags = 0; set_bit(NDD_ALIASING, &dimm_flags); - p->nvdimm = nvdimm_create(p->bus, p, papr_scm_dimm_groups, - dimm_flags, PAPR_SCM_DIMM_CMD_MASK, 0, NULL); + p->nvdimm = nvdimm_create(p->bus, p, NULL, dimm_flags, + PAPR_SCM_DIMM_CMD_MASK, 0, NULL); if (!p->nvdimm) { dev_err(dev, "Error creating DIMM object for %pOF\n", p->dn); goto err; @@ -366,7 +346,6 @@ static int papr_scm_nvdimm_init(struct papr_scm_priv *p) mapping.size = p->blocks * p->block_size; // XXX: potential overflow? memset(&ndr_desc, 0, sizeof(ndr_desc)); - ndr_desc.attr_groups = region_attr_groups; target_nid = dev_to_node(&p->pdev->dev); online_nid = papr_scm_node(target_nid); ndr_desc.numa_node = online_nid; @@ -513,7 +492,6 @@ static struct platform_driver papr_scm_driver = { .remove = papr_scm_remove, .driver = { .name = "papr_scm", - .owner = THIS_MODULE, .of_match_table = papr_scm_match, }, }; diff --git a/arch/powerpc/platforms/pseries/pci_dlpar.c b/arch/powerpc/platforms/pseries/pci_dlpar.c index 561917fa54a8..361986e4354e 100644 --- a/arch/powerpc/platforms/pseries/pci_dlpar.c +++ b/arch/powerpc/platforms/pseries/pci_dlpar.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * PCI Dynamic LPAR, PCI Hot Plug and PCI EEH recovery code * for RPA-compliant PPC64 platform. @@ -6,23 +7,6 @@ * * Updates, 2005, John Rose <johnrose@austin.ibm.com> * Updates, 2005, Linas Vepstas <linas@austin.ibm.com> - * - * All rights reserved. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or (at - * your option) any later version. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or - * NON INFRINGEMENT. See the GNU General Public License for more - * details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */ #include <linux/pci.h> diff --git a/arch/powerpc/platforms/pseries/pseries_energy.c b/arch/powerpc/platforms/pseries/pseries_energy.c index a96874f9492f..09e98d301db0 100644 --- a/arch/powerpc/platforms/pseries/pseries_energy.c +++ b/arch/powerpc/platforms/pseries/pseries_energy.c @@ -36,6 +36,7 @@ static int sysfs_entries; static u32 cpu_to_drc_index(int cpu) { struct device_node *dn = NULL; + struct property *info; int thread_index; int rc = 1; u32 ret = 0; @@ -47,20 +48,18 @@ static u32 cpu_to_drc_index(int cpu) /* Convert logical cpu number to core number */ thread_index = cpu_core_index_of_thread(cpu); - if (firmware_has_feature(FW_FEATURE_DRC_INFO)) { - struct property *info = NULL; + info = of_find_property(dn, "ibm,drc-info", NULL); + if (info) { struct of_drc_info drc; int j; u32 num_set_entries; const __be32 *value; - info = of_find_property(dn, "ibm,drc-info", NULL); - if (info == NULL) - goto err_of_node_put; - value = of_prop_next_u32(info, NULL, &num_set_entries); if (!value) goto err_of_node_put; + else + value++; for (j = 0; j < num_set_entries; j++) { @@ -110,6 +109,7 @@ err: static int drc_index_to_cpu(u32 drc_index) { struct device_node *dn = NULL; + struct property *info; const int *indexes; int thread_index = 0, cpu = 0; int rc = 1; @@ -117,21 +117,18 @@ static int drc_index_to_cpu(u32 drc_index) dn = of_find_node_by_path("/cpus"); if (dn == NULL) goto err; - - if (firmware_has_feature(FW_FEATURE_DRC_INFO)) { - struct property *info = NULL; + info = of_find_property(dn, "ibm,drc-info", NULL); + if (info) { struct of_drc_info drc; int j; u32 num_set_entries; const __be32 *value; - info = of_find_property(dn, "ibm,drc-info", NULL); - if (info == NULL) - goto err_of_node_put; - value = of_prop_next_u32(info, NULL, &num_set_entries); if (!value) goto err_of_node_put; + else + value++; for (j = 0; j < num_set_entries; j++) { diff --git a/arch/powerpc/platforms/pseries/ras.c b/arch/powerpc/platforms/pseries/ras.c index 3acdcc3bb908..1d7f973c647b 100644 --- a/arch/powerpc/platforms/pseries/ras.c +++ b/arch/powerpc/platforms/pseries/ras.c @@ -255,7 +255,7 @@ static void rtas_parse_epow_errlog(struct rtas_error_log *log) break; case EPOW_SYSTEM_SHUTDOWN: - handle_system_shutdown(epow_log->event_modifier); + handle_system_shutdown(modifier); break; case EPOW_SYSTEM_HALT: diff --git a/arch/powerpc/sysdev/Makefile b/arch/powerpc/sysdev/Makefile index 603b3c656d19..cb5a5bd2cef5 100644 --- a/arch/powerpc/sysdev/Makefile +++ b/arch/powerpc/sysdev/Makefile @@ -24,7 +24,6 @@ obj-$(CONFIG_FSL_CORENET_RCPM) += fsl_rcpm.o obj-$(CONFIG_FSL_LBC) += fsl_lbc.o obj-$(CONFIG_FSL_GTM) += fsl_gtm.o obj-$(CONFIG_FSL_85XX_CACHE_SRAM) += fsl_85xx_l2ctlr.o fsl_85xx_cache_sram.o -obj-$(CONFIG_SIMPLE_GPIO) += simple_gpio.o obj-$(CONFIG_FSL_RIO) += fsl_rio.o fsl_rmu.o obj-$(CONFIG_TSI108_BRIDGE) += tsi108_pci.o tsi108_dev.o obj-$(CONFIG_RTC_DRV_CMOS) += rtc_cmos_setup.o diff --git a/arch/powerpc/sysdev/fsl_pci.c b/arch/powerpc/sysdev/fsl_pci.c index ff0e2b156cb5..617a443d673d 100644 --- a/arch/powerpc/sysdev/fsl_pci.c +++ b/arch/powerpc/sysdev/fsl_pci.c @@ -115,8 +115,8 @@ static void pci_dma_dev_setup_swiotlb(struct pci_dev *pdev) { struct pci_controller *hose = pci_bus_to_host(pdev->bus); - pdev->dev.bus_dma_mask = - hose->dma_window_base_cur + hose->dma_window_size; + pdev->dev.bus_dma_limit = + hose->dma_window_base_cur + hose->dma_window_size - 1; } static void setup_swiotlb_ops(struct pci_controller *hose) @@ -135,7 +135,7 @@ static void fsl_pci_dma_set_mask(struct device *dev, u64 dma_mask) * mapping that allows addressing any RAM address from across PCI. */ if (dev_is_pci(dev) && dma_mask >= pci64_dma_offset * 2 - 1) { - dev->bus_dma_mask = 0; + dev->bus_dma_limit = 0; dev->archdata.dma_offset = pci64_dma_offset; } } diff --git a/arch/powerpc/sysdev/simple_gpio.c b/arch/powerpc/sysdev/simple_gpio.c deleted file mode 100644 index dc1740cd9e42..000000000000 --- a/arch/powerpc/sysdev/simple_gpio.c +++ /dev/null @@ -1,143 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * Simple Memory-Mapped GPIOs - * - * Copyright (c) MontaVista Software, Inc. 2008. - * - * Author: Anton Vorontsov <avorontsov@ru.mvista.com> - */ - -#include <linux/init.h> -#include <linux/kernel.h> -#include <linux/spinlock.h> -#include <linux/types.h> -#include <linux/ioport.h> -#include <linux/io.h> -#include <linux/of.h> -#include <linux/of_gpio.h> -#include <linux/gpio/driver.h> -#include <linux/slab.h> -#include <asm/prom.h> -#include "simple_gpio.h" - -struct u8_gpio_chip { - struct of_mm_gpio_chip mm_gc; - spinlock_t lock; - - /* shadowed data register to clear/set bits safely */ - u8 data; -}; - -static u8 u8_pin2mask(unsigned int pin) -{ - return 1 << (8 - 1 - pin); -} - -static int u8_gpio_get(struct gpio_chip *gc, unsigned int gpio) -{ - struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc); - - return !!(in_8(mm_gc->regs) & u8_pin2mask(gpio)); -} - -static void u8_gpio_set(struct gpio_chip *gc, unsigned int gpio, int val) -{ - struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc); - struct u8_gpio_chip *u8_gc = gpiochip_get_data(gc); - unsigned long flags; - - spin_lock_irqsave(&u8_gc->lock, flags); - - if (val) - u8_gc->data |= u8_pin2mask(gpio); - else - u8_gc->data &= ~u8_pin2mask(gpio); - - out_8(mm_gc->regs, u8_gc->data); - - spin_unlock_irqrestore(&u8_gc->lock, flags); -} - -static int u8_gpio_dir_in(struct gpio_chip *gc, unsigned int gpio) -{ - return 0; -} - -static int u8_gpio_dir_out(struct gpio_chip *gc, unsigned int gpio, int val) -{ - u8_gpio_set(gc, gpio, val); - return 0; -} - -static void u8_gpio_save_regs(struct of_mm_gpio_chip *mm_gc) -{ - struct u8_gpio_chip *u8_gc = - container_of(mm_gc, struct u8_gpio_chip, mm_gc); - - u8_gc->data = in_8(mm_gc->regs); -} - -static int __init u8_simple_gpiochip_add(struct device_node *np) -{ - int ret; - struct u8_gpio_chip *u8_gc; - struct of_mm_gpio_chip *mm_gc; - struct gpio_chip *gc; - - u8_gc = kzalloc(sizeof(*u8_gc), GFP_KERNEL); - if (!u8_gc) - return -ENOMEM; - - spin_lock_init(&u8_gc->lock); - - mm_gc = &u8_gc->mm_gc; - gc = &mm_gc->gc; - - mm_gc->save_regs = u8_gpio_save_regs; - gc->ngpio = 8; - gc->direction_input = u8_gpio_dir_in; - gc->direction_output = u8_gpio_dir_out; - gc->get = u8_gpio_get; - gc->set = u8_gpio_set; - - ret = of_mm_gpiochip_add_data(np, mm_gc, u8_gc); - if (ret) - goto err; - return 0; -err: - kfree(u8_gc); - return ret; -} - -void __init simple_gpiochip_init(const char *compatible) -{ - struct device_node *np; - - for_each_compatible_node(np, NULL, compatible) { - int ret; - struct resource r; - - ret = of_address_to_resource(np, 0, &r); - if (ret) - goto err; - - switch (resource_size(&r)) { - case 1: - ret = u8_simple_gpiochip_add(np); - if (ret) - goto err; - break; - default: - /* - * Whenever you need support for GPIO bank width > 1, - * please just turn u8_ code into huge macros, and - * construct needed uX_ code with it. - */ - ret = -ENOSYS; - goto err; - } - continue; -err: - pr_err("%pOF: registration failed, status %d\n", np, ret); - } -} diff --git a/arch/powerpc/sysdev/simple_gpio.h b/arch/powerpc/sysdev/simple_gpio.h deleted file mode 100644 index f3f3a20d39e2..000000000000 --- a/arch/powerpc/sysdev/simple_gpio.h +++ /dev/null @@ -1,13 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __SYSDEV_SIMPLE_GPIO_H -#define __SYSDEV_SIMPLE_GPIO_H - -#include <linux/errno.h> - -#ifdef CONFIG_SIMPLE_GPIO -extern void simple_gpiochip_init(const char *compatible); -#else -static inline void simple_gpiochip_init(const char *compatible) {} -#endif /* CONFIG_SIMPLE_GPIO */ - -#endif /* __SYSDEV_SIMPLE_GPIO_H */ diff --git a/arch/powerpc/sysdev/xive/common.c b/arch/powerpc/sysdev/xive/common.c index df832b09e3e9..f5fadbd2533a 100644 --- a/arch/powerpc/sysdev/xive/common.c +++ b/arch/powerpc/sysdev/xive/common.c @@ -1035,6 +1035,15 @@ static int xive_irq_alloc_data(unsigned int virq, irq_hw_number_t hw) xd->target = XIVE_INVALID_TARGET; irq_set_handler_data(virq, xd); + /* + * Turn OFF by default the interrupt being mapped. A side + * effect of this check is the mapping the ESB page of the + * interrupt in the Linux address space. This prevents page + * fault issues in the crash handler which masks all + * interrupts. + */ + xive_esb_read(xd, XIVE_ESB_SET_PQ_01); + return 0; } diff --git a/arch/powerpc/tools/relocs_check.sh b/arch/powerpc/tools/relocs_check.sh index 2b4e959caa36..7b9fe0a567cf 100755 --- a/arch/powerpc/tools/relocs_check.sh +++ b/arch/powerpc/tools/relocs_check.sh @@ -20,7 +20,7 @@ objdump="$1" vmlinux="$2" bad_relocs=$( -"$objdump" -R "$vmlinux" | +$objdump -R "$vmlinux" | # Only look at relocation lines. grep -E '\<R_' | # These relocations are okay diff --git a/arch/powerpc/tools/unrel_branch_check.sh b/arch/powerpc/tools/unrel_branch_check.sh index 1e972df3107e..77114755dc6f 100755 --- a/arch/powerpc/tools/unrel_branch_check.sh +++ b/arch/powerpc/tools/unrel_branch_check.sh @@ -18,14 +18,14 @@ vmlinux="$2" #__end_interrupts should be located within the first 64K end_intr=0x$( -"$objdump" -R "$vmlinux" -d --start-address=0xc000000000000000 \ +$objdump -R "$vmlinux" -d --start-address=0xc000000000000000 \ --stop-address=0xc000000000010000 | grep '\<__end_interrupts>:' | awk '{print $1}' ) BRANCHES=$( -"$objdump" -R "$vmlinux" -D --start-address=0xc000000000000000 \ +$objdump -R "$vmlinux" -D --start-address=0xc000000000000000 \ --stop-address=${end_intr} | grep -e "^c[0-9a-f]*:[[:space:]]*\([0-9a-f][0-9a-f][[:space:]]\)\{4\}[[:space:]]*b" | grep -v '\<__start_initialization_multiplatform>' | diff --git a/arch/powerpc/xmon/Makefile b/arch/powerpc/xmon/Makefile index f142570ad860..c3842dbeb1b7 100644 --- a/arch/powerpc/xmon/Makefile +++ b/arch/powerpc/xmon/Makefile @@ -1,8 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 # Makefile for xmon -# Disable clang warning for using setjmp without setjmp.h header -subdir-ccflags-y := $(call cc-disable-warning, builtin-requires-header) +# Avoid clang warnings around longjmp/setjmp declarations +subdir-ccflags-y := -ffreestanding GCOV_PROFILE := n KCOV_INSTRUMENT := n diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index d83364ebc5c5..a7056049709e 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -25,6 +25,7 @@ #include <linux/nmi.h> #include <linux/ctype.h> #include <linux/highmem.h> +#include <linux/security.h> #include <asm/debugfs.h> #include <asm/ptrace.h> @@ -187,6 +188,8 @@ static void dump_tlb_44x(void); static void dump_tlb_book3e(void); #endif +static void clear_all_bpt(void); + #ifdef CONFIG_PPC64 #define REG "%.16lx" #else @@ -283,10 +286,38 @@ Commands:\n\ " U show uptime information\n" " ? help\n" " # n limit output to n lines per page (for dp, dpa, dl)\n" -" zr reboot\n\ - zh halt\n" +" zr reboot\n" +" zh halt\n" ; +#ifdef CONFIG_SECURITY +static bool xmon_is_locked_down(void) +{ + static bool lockdown; + + if (!lockdown) { + lockdown = !!security_locked_down(LOCKDOWN_XMON_RW); + if (lockdown) { + printf("xmon: Disabled due to kernel lockdown\n"); + xmon_is_ro = true; + } + } + + if (!xmon_is_ro) { + xmon_is_ro = !!security_locked_down(LOCKDOWN_XMON_WR); + if (xmon_is_ro) + printf("xmon: Read-only due to kernel lockdown\n"); + } + + return lockdown; +} +#else /* CONFIG_SECURITY */ +static inline bool xmon_is_locked_down(void) +{ + return false; +} +#endif + static struct pt_regs *xmon_regs; static inline void sync(void) @@ -438,7 +469,10 @@ static bool wait_for_other_cpus(int ncpus) return false; } -#endif /* CONFIG_SMP */ +#else /* CONFIG_SMP */ +static inline void get_output_lock(void) {} +static inline void release_output_lock(void) {} +#endif static inline int unrecoverable_excp(struct pt_regs *regs) { @@ -455,6 +489,7 @@ static int xmon_core(struct pt_regs *regs, int fromipi) int cmd = 0; struct bpt *bp; long recurse_jmp[JMP_BUF_LEN]; + bool locked_down; unsigned long offset; unsigned long flags; #ifdef CONFIG_SMP @@ -465,6 +500,8 @@ static int xmon_core(struct pt_regs *regs, int fromipi) local_irq_save(flags); hard_irq_disable(); + locked_down = xmon_is_locked_down(); + if (!fromipi) { tracing_enabled = tracing_is_on(); tracing_off(); @@ -518,7 +555,8 @@ static int xmon_core(struct pt_regs *regs, int fromipi) if (!fromipi) { get_output_lock(); - excprint(regs); + if (!locked_down) + excprint(regs); if (bp) { printf("cpu 0x%x stopped at breakpoint 0x%tx (", cpu, BP_NUM(bp)); @@ -570,10 +608,14 @@ static int xmon_core(struct pt_regs *regs, int fromipi) } remove_bpts(); disable_surveillance(); - /* for breakpoint or single step, print the current instr. */ - if (bp || TRAP(regs) == 0xd00) - ppc_inst_dump(regs->nip, 1, 0); - printf("enter ? for help\n"); + + if (!locked_down) { + /* for breakpoint or single step, print curr insn */ + if (bp || TRAP(regs) == 0xd00) + ppc_inst_dump(regs->nip, 1, 0); + printf("enter ? for help\n"); + } + mb(); xmon_gate = 1; barrier(); @@ -597,8 +639,9 @@ static int xmon_core(struct pt_regs *regs, int fromipi) spin_cpu_relax(); touch_nmi_watchdog(); } else { - cmd = cmds(regs); - if (cmd != 0) { + if (!locked_down) + cmd = cmds(regs); + if (locked_down || cmd != 0) { /* exiting xmon */ insert_bpts(); xmon_gate = 0; @@ -635,13 +678,16 @@ static int xmon_core(struct pt_regs *regs, int fromipi) "can't continue\n"); remove_bpts(); disable_surveillance(); - /* for breakpoint or single step, print the current instr. */ - if (bp || TRAP(regs) == 0xd00) - ppc_inst_dump(regs->nip, 1, 0); - printf("enter ? for help\n"); + if (!locked_down) { + /* for breakpoint or single step, print current insn */ + if (bp || TRAP(regs) == 0xd00) + ppc_inst_dump(regs->nip, 1, 0); + printf("enter ? for help\n"); + } } - cmd = cmds(regs); + if (!locked_down) + cmd = cmds(regs); insert_bpts(); in_xmon = 0; @@ -670,7 +716,10 @@ static int xmon_core(struct pt_regs *regs, int fromipi) } } #endif - insert_cpu_bpts(); + if (locked_down) + clear_all_bpt(); + else + insert_cpu_bpts(); touch_nmi_watchdog(); local_irq_restore(flags); @@ -884,7 +933,7 @@ static void insert_cpu_bpts(void) if (dabr.enabled) { brk.address = dabr.address; brk.type = (dabr.enabled & HW_BRK_TYPE_DABR) | HW_BRK_TYPE_PRIV_ALL; - brk.len = 8; + brk.len = DABR_MAX_LEN; __set_breakpoint(&brk); } @@ -1047,10 +1096,6 @@ cmds(struct pt_regs *excp) set_lpp_cmd(); break; case 'b': - if (xmon_is_ro) { - printf(xmon_ro_msg); - break; - } bpt_cmds(); break; case 'C': @@ -1319,11 +1364,16 @@ bpt_cmds(void) struct bpt *bp; cmd = inchar(); + switch (cmd) { #ifndef CONFIG_PPC_8xx static const char badaddr[] = "Only kernel addresses are permitted for breakpoints\n"; int mode; case 'd': /* bd - hardware data breakpoint */ + if (xmon_is_ro) { + printf(xmon_ro_msg); + break; + } if (!ppc_breakpoint_available()) { printf("Hardware data breakpoint not supported on this cpu\n"); break; @@ -1351,6 +1401,10 @@ bpt_cmds(void) break; case 'i': /* bi - hardware instr breakpoint */ + if (xmon_is_ro) { + printf(xmon_ro_msg); + break; + } if (!cpu_has_feature(CPU_FTR_ARCH_207S)) { printf("Hardware instruction breakpoint " "not supported on this cpu\n"); @@ -1409,7 +1463,8 @@ bpt_cmds(void) break; } termch = cmd; - if (!scanhex(&a)) { + + if (xmon_is_ro || !scanhex(&a)) { /* print all breakpoints */ printf(" type address\n"); if (dabr.enabled) { @@ -3762,6 +3817,11 @@ static void xmon_init(int enable) #ifdef CONFIG_MAGIC_SYSRQ static void sysrq_handle_xmon(int key) { + if (xmon_is_locked_down()) { + clear_all_bpt(); + xmon_init(0); + return; + } /* ensure xmon is enabled */ xmon_init(1); debugger(get_irq_regs()); @@ -3783,7 +3843,6 @@ static int __init setup_xmon_sysrq(void) device_initcall(setup_xmon_sysrq); #endif /* CONFIG_MAGIC_SYSRQ */ -#ifdef CONFIG_DEBUG_FS static void clear_all_bpt(void) { int i; @@ -3801,18 +3860,22 @@ static void clear_all_bpt(void) iabr = NULL; dabr.enabled = 0; } - - printf("xmon: All breakpoints cleared\n"); } +#ifdef CONFIG_DEBUG_FS static int xmon_dbgfs_set(void *data, u64 val) { xmon_on = !!val; xmon_init(xmon_on); /* make sure all breakpoints removed when disabling */ - if (!xmon_on) + if (!xmon_on) { clear_all_bpt(); + get_output_lock(); + printf("xmon: All breakpoints cleared\n"); + release_output_lock(); + } + return 0; } @@ -3838,7 +3901,11 @@ static int xmon_early __initdata; static int __init early_parse_xmon(char *p) { - if (!p || strncmp(p, "early", 5) == 0) { + if (xmon_is_locked_down()) { + xmon_init(0); + xmon_early = 0; + xmon_on = 0; + } else if (!p || strncmp(p, "early", 5) == 0) { /* just "xmon" is equivalent to "xmon=early" */ xmon_init(1); xmon_early = 1; |