diff options
Diffstat (limited to 'arch/powerpc')
322 files changed, 6879 insertions, 3020 deletions
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 0b1172cbeccb..54b9387c3691 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -157,6 +157,7 @@ config PPC select ARCH_HAS_UBSAN_SANITIZE_ALL select ARCH_HAVE_NMI_SAFE_CMPXCHG select ARCH_KEEP_MEMBLOCK + select ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE if PPC_RADIX_MMU select ARCH_MIGHT_HAVE_PC_PARPORT select ARCH_MIGHT_HAVE_PC_SERIO select ARCH_OPTIONAL_KERNEL_RWX if ARCH_HAS_STRICT_KERNEL_RWX @@ -174,6 +175,7 @@ config PPC select ARCH_WANT_IPC_PARSE_VERSION select ARCH_WANT_IRQS_OFF_ACTIVATE_MM select ARCH_WANT_LD_ORPHAN_WARN + select ARCH_WANT_OPTIMIZE_DAX_VMEMMAP if PPC_RADIX_MMU select ARCH_WANTS_MODULES_DATA_IN_VMALLOC if PPC_BOOK3S_32 || PPC_8xx select ARCH_WEAK_RELEASE_ACQUIRE select BINFMT_ELF @@ -186,6 +188,7 @@ config PPC select DYNAMIC_FTRACE if FUNCTION_TRACER select EDAC_ATOMIC_SCRUB select EDAC_SUPPORT + select FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY if ARCH_USING_PATCHABLE_FUNCTION_ENTRY select GENERIC_ATOMIC64 if PPC32 select GENERIC_CLOCKEVENTS_BROADCAST if SMP select GENERIC_CMOS_UPDATE @@ -193,6 +196,8 @@ config PPC select GENERIC_CPU_VULNERABILITIES if PPC_BARRIER_NOSPEC select GENERIC_EARLY_IOREMAP select GENERIC_GETTIMEOFDAY + select GENERIC_IDLE_POLL_SETUP + select GENERIC_IOREMAP select GENERIC_IRQ_SHOW select GENERIC_IRQ_SHOW_LEVEL select GENERIC_PCI_IOMAP if PCI @@ -226,8 +231,8 @@ config PPC select HAVE_DEBUG_KMEMLEAK select HAVE_DEBUG_STACKOVERFLOW select HAVE_DYNAMIC_FTRACE - select HAVE_DYNAMIC_FTRACE_WITH_ARGS if MPROFILE_KERNEL || PPC32 - select HAVE_DYNAMIC_FTRACE_WITH_REGS if MPROFILE_KERNEL || PPC32 + select HAVE_DYNAMIC_FTRACE_WITH_ARGS if ARCH_USING_PATCHABLE_FUNCTION_ENTRY || MPROFILE_KERNEL || PPC32 + select HAVE_DYNAMIC_FTRACE_WITH_REGS if ARCH_USING_PATCHABLE_FUNCTION_ENTRY || MPROFILE_KERNEL || PPC32 select HAVE_EBPF_JIT select HAVE_EFFICIENT_UNALIGNED_ACCESS select HAVE_FAST_GUP @@ -255,7 +260,7 @@ config PPC select HAVE_MOD_ARCH_SPECIFIC select HAVE_NMI if PERF_EVENTS || (PPC64 && PPC_BOOK3S) select HAVE_OPTPROBES - select HAVE_OBJTOOL if PPC32 || MPROFILE_KERNEL + select HAVE_OBJTOOL if ARCH_USING_PATCHABLE_FUNCTION_ENTRY || MPROFILE_KERNEL || PPC32 select HAVE_OBJTOOL_MCOUNT if HAVE_OBJTOOL select HAVE_PERF_EVENTS select HAVE_PERF_EVENTS_NMI if PPC64 @@ -272,6 +277,8 @@ config PPC select HAVE_SYSCALL_TRACEPOINTS select HAVE_VIRT_CPU_ACCOUNTING select HAVE_VIRT_CPU_ACCOUNTING_GEN + select HOTPLUG_SMT if HOTPLUG_CPU + select SMT_NUM_THREADS_DYNAMIC select HUGETLB_PAGE_SIZE_VARIABLE if PPC_BOOK3S_64 && HUGETLB_PAGE select IOMMU_HELPER if PPC64 select IRQ_DOMAIN @@ -551,6 +558,13 @@ config MPROFILE_KERNEL def_bool $(success,$(srctree)/arch/powerpc/tools/gcc-check-mprofile-kernel.sh $(CC) -mlittle-endian) if CPU_LITTLE_ENDIAN def_bool $(success,$(srctree)/arch/powerpc/tools/gcc-check-mprofile-kernel.sh $(CC) -mbig-endian) if CPU_BIG_ENDIAN +config ARCH_USING_PATCHABLE_FUNCTION_ENTRY + depends on FUNCTION_TRACER && (PPC32 || PPC64_ELF_ABI_V2) + depends on $(cc-option,-fpatchable-function-entry=2) + def_bool y if PPC32 + def_bool $(success,$(srctree)/arch/powerpc/tools/gcc-check-fpatchable-function-entry.sh $(CC) -mlittle-endian) if PPC64 && CPU_LITTLE_ENDIAN + def_bool $(success,$(srctree)/arch/powerpc/tools/gcc-check-fpatchable-function-entry.sh $(CC) -mbig-endian) if PPC64 && CPU_BIG_ENDIAN + config HOTPLUG_CPU bool "Support for enabling/disabling CPUs" depends on SMP && (PPC_PSERIES || \ @@ -589,41 +603,21 @@ config PPC64_SUPPORTS_MEMORY_FAILURE default "y" if PPC_POWERNV select ARCH_SUPPORTS_MEMORY_FAILURE -config KEXEC - bool "kexec system call" - depends on PPC_BOOK3S || PPC_E500 || (44x && !SMP) - select KEXEC_CORE - help - kexec is a system call that implements the ability to shutdown your - current kernel, and to start another kernel. It is like a reboot - but it is independent of the system firmware. And like a reboot - you can start any kernel with it, not just Linux. - - The name comes from the similarity to the exec system call. - - It is an ongoing process to be certain the hardware in a machine - is properly shutdown, so do not be surprised if this code does not - initially work for you. As of this writing the exact hardware - interface is strongly in flux, so no good recommendation can be - made. - -config KEXEC_FILE - bool "kexec file based system call" - select KEXEC_CORE - select HAVE_IMA_KEXEC if IMA - select KEXEC_ELF - depends on PPC64 - depends on CRYPTO=y - depends on CRYPTO_SHA256=y - help - This is a new version of the kexec system call. This call is - file based and takes in file descriptors as system call arguments - for kernel and initramfs as opposed to a list of segments as is the - case for the older kexec call. +config ARCH_SUPPORTS_KEXEC + def_bool PPC_BOOK3S || PPC_E500 || (44x && !SMP) + +config ARCH_SUPPORTS_KEXEC_FILE + def_bool PPC64 && CRYPTO=y && CRYPTO_SHA256=y -config ARCH_HAS_KEXEC_PURGATORY +config ARCH_SUPPORTS_KEXEC_PURGATORY def_bool KEXEC_FILE +config ARCH_SELECTS_KEXEC_FILE + def_bool y + depends on KEXEC_FILE + select KEXEC_ELF + select HAVE_IMA_KEXEC if IMA + config PPC64_BIG_ENDIAN_ELF_ABI_V2 # Option is available to BFD, but LLD does not support ELFv1 so this is # always true there. @@ -683,14 +677,13 @@ config RELOCATABLE_TEST loaded at, which tends to be non-zero and therefore test the relocation code. -config CRASH_DUMP - bool "Build a dump capture kernel" - depends on PPC64 || PPC_BOOK3S_32 || PPC_85xx || (44x && !SMP) +config ARCH_SUPPORTS_CRASH_DUMP + def_bool PPC64 || PPC_BOOK3S_32 || PPC_85xx || (44x && !SMP) + +config ARCH_SELECTS_CRASH_DUMP + def_bool y + depends on CRASH_DUMP select RELOCATABLE if PPC64 || 44x || PPC_85xx - help - Build a kernel suitable for use as a dump capture kernel. - The same kernel binary can be used as production kernel and dump - capture kernel. config FA_DUMP bool "Firmware-assisted dump" @@ -1144,12 +1137,6 @@ config FSL_GTM help Freescale General-purpose Timers support -config PCI_8260 - bool - depends on PCI && 8260 - select PPC_INDIRECT_PCI - default y - config FSL_RIO bool "Freescale Embedded SRIO Controller support" depends on RAPIDIO = y && HAVE_RAPIDIO diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index dac7ca153886..f19dbaa1d541 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -143,18 +143,21 @@ CFLAGS-$(CONFIG_PPC32) += $(call cc-option, $(MULTIPLEWORD)) CFLAGS-$(CONFIG_PPC32) += $(call cc-option,-mno-readonly-in-sdata) ifdef CONFIG_FUNCTION_TRACER +ifdef CONFIG_ARCH_USING_PATCHABLE_FUNCTION_ENTRY +KBUILD_CPPFLAGS += -DCC_USING_PATCHABLE_FUNCTION_ENTRY +CC_FLAGS_FTRACE := -fpatchable-function-entry=2 +else CC_FLAGS_FTRACE := -pg ifdef CONFIG_MPROFILE_KERNEL CC_FLAGS_FTRACE += -mprofile-kernel endif endif +endif CFLAGS-$(CONFIG_TARGET_CPU_BOOL) += -mcpu=$(CONFIG_TARGET_CPU) AFLAGS-$(CONFIG_TARGET_CPU_BOOL) += -mcpu=$(CONFIG_TARGET_CPU) -CFLAGS-$(CONFIG_POWERPC64_CPU) += $(call cc-option,-mtune=power10, \ - $(call cc-option,-mtune=power9, \ - $(call cc-option,-mtune=power8))) +CFLAGS-y += $(CONFIG_TUNE_CPU) asinstr := $(call as-instr,lis 9$(comma)foo@high,-DHAVE_AS_ATHIGH=1) diff --git a/arch/powerpc/boot/dts/fsl/c293si-post.dtsi b/arch/powerpc/boot/dts/fsl/c293si-post.dtsi index bec0fc36849d..f208fb8f64b3 100644 --- a/arch/powerpc/boot/dts/fsl/c293si-post.dtsi +++ b/arch/powerpc/boot/dts/fsl/c293si-post.dtsi @@ -124,10 +124,10 @@ reg = <0x80000 0x20000>; ranges = <0x0 0x80000 0x20000>; - jr@1000{ + jr@1000 { interrupts = <45 2 0 0>; }; - jr@2000{ + jr@2000 { interrupts = <57 2 0 0>; }; }; @@ -140,10 +140,10 @@ reg = <0xa0000 0x20000>; ranges = <0x0 0xa0000 0x20000>; - jr@1000{ + jr@1000 { interrupts = <49 2 0 0>; }; - jr@2000{ + jr@2000 { interrupts = <50 2 0 0>; }; }; @@ -156,10 +156,10 @@ reg = <0xc0000 0x20000>; ranges = <0x0 0xc0000 0x20000>; - jr@1000{ + jr@1000 { interrupts = <55 2 0 0>; }; - jr@2000{ + jr@2000 { interrupts = <56 2 0 0>; }; }; diff --git a/arch/powerpc/boot/dts/fsl/p1022rdk.dts b/arch/powerpc/boot/dts/fsl/p1022rdk.dts index 29e8af1e3711..4261c2f7e4b3 100644 --- a/arch/powerpc/boot/dts/fsl/p1022rdk.dts +++ b/arch/powerpc/boot/dts/fsl/p1022rdk.dts @@ -60,23 +60,23 @@ compatible = "st,m41t62"; reg = <0x68>; }; - adt7461@4c{ + adt7461@4c { compatible = "adi,adt7461"; reg = <0x4c>; }; - zl6100@21{ + zl6100@21 { compatible = "isil,zl6100"; reg = <0x21>; }; - zl6100@24{ + zl6100@24 { compatible = "isil,zl6100"; reg = <0x24>; }; - zl6100@26{ + zl6100@26 { compatible = "isil,zl6100"; reg = <0x26>; }; - zl6100@29{ + zl6100@29 { compatible = "isil,zl6100"; reg = <0x29>; }; diff --git a/arch/powerpc/boot/dts/fsl/p1022si-post.dtsi b/arch/powerpc/boot/dts/fsl/p1022si-post.dtsi index 5f51b7bfc064..093e4e3ed368 100644 --- a/arch/powerpc/boot/dts/fsl/p1022si-post.dtsi +++ b/arch/powerpc/boot/dts/fsl/p1022si-post.dtsi @@ -238,7 +238,7 @@ fsl,has-rstcr; }; - power@e0070{ + power@e0070 { compatible = "fsl,mpc8536-pmc", "fsl,mpc8548-pmc"; reg = <0xe0070 0x20>; }; diff --git a/arch/powerpc/boot/dts/fsl/p3041ds.dts b/arch/powerpc/boot/dts/fsl/p3041ds.dts index 6f5f7283c533..ca0e0272ac62 100644 --- a/arch/powerpc/boot/dts/fsl/p3041ds.dts +++ b/arch/powerpc/boot/dts/fsl/p3041ds.dts @@ -41,7 +41,7 @@ #size-cells = <2>; interrupt-parent = <&mpic>; - aliases{ + aliases { phy_rgmii_0 = &phy_rgmii_0; phy_rgmii_1 = &phy_rgmii_1; phy_sgmii_1c = &phy_sgmii_1c; @@ -165,7 +165,7 @@ }; }; - fman@400000{ + fman@400000 { ethernet@e0000 { phy-handle = <&phy_sgmii_1c>; phy-connection-type = "sgmii"; diff --git a/arch/powerpc/boot/dts/fsl/p5040ds.dts b/arch/powerpc/boot/dts/fsl/p5040ds.dts index 30850b3228e0..5cfc689ee474 100644 --- a/arch/powerpc/boot/dts/fsl/p5040ds.dts +++ b/arch/powerpc/boot/dts/fsl/p5040ds.dts @@ -41,7 +41,7 @@ #size-cells = <2>; interrupt-parent = <&mpic>; - aliases{ + aliases { phy_sgmii_slot2_1c = &phy_sgmii_slot2_1c; phy_sgmii_slot2_1d = &phy_sgmii_slot2_1d; phy_sgmii_slot2_1e = &phy_sgmii_slot2_1e; diff --git a/arch/powerpc/boot/dts/fsl/t4240qds.dts b/arch/powerpc/boot/dts/fsl/t4240qds.dts index c0913ac5aaad..128b5798bb97 100644 --- a/arch/powerpc/boot/dts/fsl/t4240qds.dts +++ b/arch/powerpc/boot/dts/fsl/t4240qds.dts @@ -41,7 +41,7 @@ #size-cells = <2>; interrupt-parent = <&mpic>; - aliases{ + aliases { phy_rgmii1 = &phyrgmii1; phy_rgmii2 = &phyrgmii2; phy_sgmii3 = &phy3; diff --git a/arch/powerpc/boot/dts/mpc5121.dtsi b/arch/powerpc/boot/dts/mpc5121.dtsi index 3f66b91a8e3c..d3fc8062fbcd 100644 --- a/arch/powerpc/boot/dts/mpc5121.dtsi +++ b/arch/powerpc/boot/dts/mpc5121.dtsi @@ -140,7 +140,7 @@ }; /* Power Management Controller */ - pmc@1000{ + pmc@1000 { compatible = "fsl,mpc5121-pmc"; reg = <0x1000 0x100>; interrupts = <83 0x8>; diff --git a/arch/powerpc/boot/dts/mpc5125twr.dts b/arch/powerpc/boot/dts/mpc5125twr.dts index 0bd2acc0401d..ee090709aa3a 100644 --- a/arch/powerpc/boot/dts/mpc5125twr.dts +++ b/arch/powerpc/boot/dts/mpc5125twr.dts @@ -104,7 +104,7 @@ clock-names = "osc"; }; - pmc@1000{ // Power Management Controller + pmc@1000 { // Power Management Controller compatible = "fsl,mpc5121-pmc"; reg = <0x1000 0x100>; interrupts = <83 0x2>; diff --git a/arch/powerpc/configs/40x/klondike_defconfig b/arch/powerpc/configs/40x/klondike_defconfig index acafbb8f6808..a974d1e945cc 100644 --- a/arch/powerpc/configs/40x/klondike_defconfig +++ b/arch/powerpc/configs/40x/klondike_defconfig @@ -4,7 +4,7 @@ CONFIG_LOG_BUF_SHIFT=14 CONFIG_SYSFS_DEPRECATED=y CONFIG_SYSFS_DEPRECATED_V2=y CONFIG_BLK_DEV_INITRD=y -CONFIG_EMBEDDED=y +CONFIG_EXPERT=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y CONFIG_APM8018X=y diff --git a/arch/powerpc/configs/44x/fsp2_defconfig b/arch/powerpc/configs/44x/fsp2_defconfig index 3fdfbb29b854..5492537f4c6c 100644 --- a/arch/powerpc/configs/44x/fsp2_defconfig +++ b/arch/powerpc/configs/44x/fsp2_defconfig @@ -15,7 +15,7 @@ CONFIG_BLK_DEV_INITRD=y # CONFIG_RD_LZ4 is not set CONFIG_KALLSYMS_ALL=y CONFIG_BPF_SYSCALL=y -CONFIG_EMBEDDED=y +CONFIG_EXPERT=y CONFIG_PROFILING=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y diff --git a/arch/powerpc/configs/44x/sam440ep_defconfig b/arch/powerpc/configs/44x/sam440ep_defconfig index ef09786d49b9..51499ee6366b 100644 --- a/arch/powerpc/configs/44x/sam440ep_defconfig +++ b/arch/powerpc/configs/44x/sam440ep_defconfig @@ -79,7 +79,7 @@ CONFIG_EXT2_FS_POSIX_ACL=y CONFIG_EXT4_FS=y CONFIG_EXT4_FS_POSIX_ACL=y CONFIG_REISERFS_FS=y -CONFIG_AUTOFS4_FS=y +CONFIG_AUTOFS_FS=y CONFIG_ISO9660_FS=y CONFIG_JOLIET=y CONFIG_ZISOFS=y diff --git a/arch/powerpc/configs/52xx/tqm5200_defconfig b/arch/powerpc/configs/52xx/tqm5200_defconfig index e6735b945327..688f703d8e22 100644 --- a/arch/powerpc/configs/52xx/tqm5200_defconfig +++ b/arch/powerpc/configs/52xx/tqm5200_defconfig @@ -3,7 +3,7 @@ CONFIG_LOG_BUF_SHIFT=14 CONFIG_BLK_DEV_INITRD=y # CONFIG_KALLSYMS is not set # CONFIG_EPOLL is not set -CONFIG_EMBEDDED=y +CONFIG_EXPERT=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y CONFIG_MODVERSIONS=y diff --git a/arch/powerpc/configs/85xx/stx_gp3_defconfig b/arch/powerpc/configs/85xx/stx_gp3_defconfig index ecbcc853307d..e7080497048d 100644 --- a/arch/powerpc/configs/85xx/stx_gp3_defconfig +++ b/arch/powerpc/configs/85xx/stx_gp3_defconfig @@ -50,7 +50,7 @@ CONFIG_DRM=m CONFIG_SOUND=m CONFIG_EXT2_FS=y CONFIG_EXT4_FS=y -CONFIG_AUTOFS4_FS=y +CONFIG_AUTOFS_FS=y CONFIG_ISO9660_FS=m CONFIG_UDF_FS=m CONFIG_MSDOS_FS=m diff --git a/arch/powerpc/configs/cell_defconfig b/arch/powerpc/configs/cell_defconfig index 06391cc2af3a..53f43a34e1a9 100644 --- a/arch/powerpc/configs/cell_defconfig +++ b/arch/powerpc/configs/cell_defconfig @@ -172,7 +172,7 @@ CONFIG_EDAC_CELL=y CONFIG_UIO=m CONFIG_EXT2_FS=y CONFIG_EXT4_FS=y -CONFIG_AUTOFS4_FS=m +CONFIG_AUTOFS_FS=m CONFIG_ISO9660_FS=m CONFIG_JOLIET=y CONFIG_UDF_FS=m diff --git a/arch/powerpc/configs/ep8248e_defconfig b/arch/powerpc/configs/ep8248e_defconfig index b9dfa3a0713b..0d8d3f41f194 100644 --- a/arch/powerpc/configs/ep8248e_defconfig +++ b/arch/powerpc/configs/ep8248e_defconfig @@ -47,7 +47,7 @@ CONFIG_SERIAL_CPM_CONSOLE=y # CONFIG_USB_SUPPORT is not set CONFIG_EXT2_FS=y CONFIG_EXT4_FS=y -CONFIG_AUTOFS4_FS=y +CONFIG_AUTOFS_FS=y CONFIG_PROC_KCORE=y CONFIG_TMPFS=y CONFIG_CRAMFS=y diff --git a/arch/powerpc/configs/mgcoge_defconfig b/arch/powerpc/configs/mgcoge_defconfig index ce220ceeb91c..f65001e7877f 100644 --- a/arch/powerpc/configs/mgcoge_defconfig +++ b/arch/powerpc/configs/mgcoge_defconfig @@ -9,7 +9,7 @@ CONFIG_BLK_DEV_INITRD=y # CONFIG_RD_GZIP is not set CONFIG_KALLSYMS_ALL=y # CONFIG_PCSPKR_PLATFORM is not set -CONFIG_EMBEDDED=y +CONFIG_EXPERT=y CONFIG_PARTITION_ADVANCED=y # CONFIG_PPC_PMAC is not set CONFIG_PPC_82xx=y @@ -60,7 +60,7 @@ CONFIG_USB_FSL_USB2=y CONFIG_USB_G_SERIAL=y CONFIG_UIO=y CONFIG_EXT2_FS=y -CONFIG_AUTOFS4_FS=y +CONFIG_AUTOFS_FS=y CONFIG_PROC_KCORE=y CONFIG_TMPFS=y CONFIG_JFFS2_FS=y diff --git a/arch/powerpc/configs/microwatt_defconfig b/arch/powerpc/configs/microwatt_defconfig index 795a127908e7..a64fb1ef8c75 100644 --- a/arch/powerpc/configs/microwatt_defconfig +++ b/arch/powerpc/configs/microwatt_defconfig @@ -8,7 +8,7 @@ CONFIG_CGROUPS=y CONFIG_BLK_DEV_INITRD=y CONFIG_CC_OPTIMIZE_FOR_SIZE=y CONFIG_KALLSYMS_ALL=y -CONFIG_EMBEDDED=y +CONFIG_EXPERT=y # CONFIG_VM_EVENT_COUNTERS is not set # CONFIG_SLUB_DEBUG is not set # CONFIG_COMPAT_BRK is not set diff --git a/arch/powerpc/configs/pasemi_defconfig b/arch/powerpc/configs/pasemi_defconfig index 96aa5355911f..61993944db40 100644 --- a/arch/powerpc/configs/pasemi_defconfig +++ b/arch/powerpc/configs/pasemi_defconfig @@ -143,7 +143,7 @@ CONFIG_EXT2_FS=y CONFIG_EXT2_FS_XATTR=y CONFIG_EXT2_FS_POSIX_ACL=y CONFIG_EXT4_FS=y -CONFIG_AUTOFS4_FS=y +CONFIG_AUTOFS_FS=y CONFIG_ISO9660_FS=y CONFIG_UDF_FS=y CONFIG_MSDOS_FS=y diff --git a/arch/powerpc/configs/pmac32_defconfig b/arch/powerpc/configs/pmac32_defconfig index 019163c2571e..a205da9ee5f2 100644 --- a/arch/powerpc/configs/pmac32_defconfig +++ b/arch/powerpc/configs/pmac32_defconfig @@ -176,8 +176,9 @@ CONFIG_MOUSE_APPLETOUCH=y # CONFIG_SERIO_I8042 is not set # CONFIG_SERIO_SERPORT is not set CONFIG_SERIAL_8250=m -CONFIG_SERIAL_PMACZILOG=m +CONFIG_SERIAL_PMACZILOG=y CONFIG_SERIAL_PMACZILOG_TTYS=y +CONFIG_SERIAL_PMACZILOG_CONSOLE=y CONFIG_NVRAM=y CONFIG_I2C_CHARDEV=m CONFIG_APM_POWER=y @@ -254,7 +255,7 @@ CONFIG_LEDS_TRIGGER_DEFAULT_ON=y CONFIG_EXT2_FS=y CONFIG_EXT4_FS=y CONFIG_EXT4_FS_POSIX_ACL=y -CONFIG_AUTOFS4_FS=m +CONFIG_AUTOFS_FS=m CONFIG_FUSE_FS=m CONFIG_ISO9660_FS=y CONFIG_JOLIET=y diff --git a/arch/powerpc/configs/powernv_defconfig b/arch/powerpc/configs/powernv_defconfig index e02ab94a09bf..ee84ade7a033 100644 --- a/arch/powerpc/configs/powernv_defconfig +++ b/arch/powerpc/configs/powernv_defconfig @@ -270,7 +270,7 @@ CONFIG_BTRFS_FS=m CONFIG_BTRFS_FS_POSIX_ACL=y CONFIG_NILFS2_FS=m CONFIG_FANOTIFY=y -CONFIG_AUTOFS4_FS=m +CONFIG_AUTOFS_FS=m CONFIG_FUSE_FS=m CONFIG_OVERLAY_FS=m CONFIG_ISO9660_FS=y diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig index 268fa361a06d..6e7b9e8fd225 100644 --- a/arch/powerpc/configs/ppc64_defconfig +++ b/arch/powerpc/configs/ppc64_defconfig @@ -327,7 +327,7 @@ CONFIG_BTRFS_FS=m CONFIG_BTRFS_FS_POSIX_ACL=y CONFIG_NILFS2_FS=m CONFIG_FS_DAX=y -CONFIG_AUTOFS4_FS=m +CONFIG_AUTOFS_FS=m CONFIG_FUSE_FS=m CONFIG_OVERLAY_FS=m CONFIG_ISO9660_FS=y @@ -390,8 +390,11 @@ CONFIG_CRYPTO_SHA256=y CONFIG_CRYPTO_WP512=m CONFIG_CRYPTO_LZO=m CONFIG_CRYPTO_CRC32C_VPMSUM=m +CONFIG_CRYPTO_CRCT10DIF_VPMSUM=m +CONFIG_CRYPTO_VPMSUM_TESTER=m CONFIG_CRYPTO_MD5_PPC=m CONFIG_CRYPTO_SHA1_PPC=m +CONFIG_CRYPTO_AES_GCM_P10=m CONFIG_CRYPTO_DEV_NX=y CONFIG_CRYPTO_DEV_NX_ENCRYPT=m CONFIG_CRYPTO_DEV_VMX=y diff --git a/arch/powerpc/configs/ppc64e_defconfig b/arch/powerpc/configs/ppc64e_defconfig index 776c32964e12..624c371ffcc3 100644 --- a/arch/powerpc/configs/ppc64e_defconfig +++ b/arch/powerpc/configs/ppc64e_defconfig @@ -185,7 +185,7 @@ CONFIG_JFS_SECURITY=y CONFIG_XFS_FS=m CONFIG_XFS_POSIX_ACL=y CONFIG_FS_DAX=y -CONFIG_AUTOFS4_FS=m +CONFIG_AUTOFS_FS=m CONFIG_ISO9660_FS=y CONFIG_UDF_FS=m CONFIG_MSDOS_FS=y diff --git a/arch/powerpc/configs/ppc6xx_defconfig b/arch/powerpc/configs/ppc6xx_defconfig index f21170b8fa11..eaf3273372a9 100644 --- a/arch/powerpc/configs/ppc6xx_defconfig +++ b/arch/powerpc/configs/ppc6xx_defconfig @@ -183,7 +183,6 @@ CONFIG_IP_NF_MATCH_TTL=m CONFIG_IP_NF_FILTER=m CONFIG_IP_NF_TARGET_REJECT=m CONFIG_IP_NF_MANGLE=m -CONFIG_IP_NF_TARGET_CLUSTERIP=m CONFIG_IP_NF_TARGET_ECN=m CONFIG_IP_NF_TARGET_TTL=m CONFIG_IP_NF_RAW=m @@ -969,7 +968,7 @@ CONFIG_XFS_POSIX_ACL=y CONFIG_GFS2_FS=m CONFIG_FS_DAX=y CONFIG_QUOTA_NETLINK_INTERFACE=y -CONFIG_AUTOFS4_FS=m +CONFIG_AUTOFS_FS=m CONFIG_FUSE_FS=m CONFIG_ISO9660_FS=y CONFIG_JOLIET=y diff --git a/arch/powerpc/configs/ps3_defconfig b/arch/powerpc/configs/ps3_defconfig index ea3ee0719bb2..2b175ddf82f0 100644 --- a/arch/powerpc/configs/ps3_defconfig +++ b/arch/powerpc/configs/ps3_defconfig @@ -3,7 +3,7 @@ CONFIG_POSIX_MQUEUE=y CONFIG_HIGH_RES_TIMERS=y CONFIG_BLK_DEV_INITRD=y CONFIG_CC_OPTIMIZE_FOR_SIZE=y -CONFIG_EMBEDDED=y +CONFIG_EXPERT=y # CONFIG_PERF_EVENTS is not set CONFIG_PROFILING=y CONFIG_PPC64=y @@ -129,7 +129,7 @@ CONFIG_EXT2_FS=m CONFIG_EXT4_FS=y CONFIG_QUOTA=y CONFIG_QFMT_V2=y -CONFIG_AUTOFS4_FS=m +CONFIG_AUTOFS_FS=m CONFIG_ISO9660_FS=m CONFIG_JOLIET=y CONFIG_UDF_FS=m diff --git a/arch/powerpc/configs/skiroot_defconfig b/arch/powerpc/configs/skiroot_defconfig index 71cfb990a74f..8d3eacb50d56 100644 --- a/arch/powerpc/configs/skiroot_defconfig +++ b/arch/powerpc/configs/skiroot_defconfig @@ -289,7 +289,6 @@ CONFIG_LIBCRC32C=y # CONFIG_XZ_DEC_SPARC is not set CONFIG_PRINTK_TIME=y CONFIG_MAGIC_SYSRQ=y -CONFIG_SLUB_DEBUG_ON=y CONFIG_SCHED_STACK_END_CHECK=y CONFIG_DEBUG_STACKOVERFLOW=y CONFIG_PANIC_ON_OOPS=y diff --git a/arch/powerpc/crypto/Kconfig b/arch/powerpc/crypto/Kconfig index ad1872518992..6fc2248ca561 100644 --- a/arch/powerpc/crypto/Kconfig +++ b/arch/powerpc/crypto/Kconfig @@ -100,7 +100,7 @@ config CRYPTO_AES_GCM_P10 select CRYPTO_LIB_AES select CRYPTO_ALGAPI select CRYPTO_AEAD - default m + select CRYPTO_SKCIPHER help AEAD cipher: AES cipher algorithms (FIPS-197) GCM (Galois/Counter Mode) authenticated encryption mode (NIST SP800-38D) @@ -111,4 +111,30 @@ config CRYPTO_AES_GCM_P10 Support for cryptographic acceleration instructions on Power10 or later CPU. This module supports stitched acceleration for AES/GCM. +config CRYPTO_CHACHA20_P10 + tristate "Ciphers: ChaCha20, XChacha20, XChacha12 (P10 or later)" + depends on PPC64 && CPU_LITTLE_ENDIAN && VSX + select CRYPTO_SKCIPHER + select CRYPTO_LIB_CHACHA_GENERIC + select CRYPTO_ARCH_HAVE_LIB_CHACHA + help + Length-preserving ciphers: ChaCha20, XChaCha20, and XChaCha12 + stream cipher algorithms + + Architecture: PowerPC64 + - Power10 or later + - Little-endian + +config CRYPTO_POLY1305_P10 + tristate "Hash functions: Poly1305 (P10 or later)" + depends on PPC64 && CPU_LITTLE_ENDIAN && VSX + select CRYPTO_HASH + select CRYPTO_LIB_POLY1305_GENERIC + help + Poly1305 authenticator algorithm (RFC7539) + + Architecture: PowerPC64 + - Power10 or later + - Little-endian + endmenu diff --git a/arch/powerpc/crypto/Makefile b/arch/powerpc/crypto/Makefile index 7b4f516abec1..ebdac1b9eb9a 100644 --- a/arch/powerpc/crypto/Makefile +++ b/arch/powerpc/crypto/Makefile @@ -14,6 +14,8 @@ obj-$(CONFIG_CRYPTO_CRC32C_VPMSUM) += crc32c-vpmsum.o obj-$(CONFIG_CRYPTO_CRCT10DIF_VPMSUM) += crct10dif-vpmsum.o obj-$(CONFIG_CRYPTO_VPMSUM_TESTER) += crc-vpmsum_test.o obj-$(CONFIG_CRYPTO_AES_GCM_P10) += aes-gcm-p10-crypto.o +obj-$(CONFIG_CRYPTO_CHACHA20_P10) += chacha-p10-crypto.o +obj-$(CONFIG_CRYPTO_POLY1305_P10) += poly1305-p10-crypto.o aes-ppc-spe-y := aes-spe-core.o aes-spe-keys.o aes-tab-4k.o aes-spe-modes.o aes-spe-glue.o md5-ppc-y := md5-asm.o md5-glue.o @@ -23,6 +25,8 @@ sha256-ppc-spe-y := sha256-spe-asm.o sha256-spe-glue.o crc32c-vpmsum-y := crc32c-vpmsum_asm.o crc32c-vpmsum_glue.o crct10dif-vpmsum-y := crct10dif-vpmsum_asm.o crct10dif-vpmsum_glue.o aes-gcm-p10-crypto-y := aes-gcm-p10-glue.o aes-gcm-p10.o ghashp10-ppc.o aesp10-ppc.o +chacha-p10-crypto-y := chacha-p10-glue.o chacha-p10le-8x.o +poly1305-p10-crypto-y := poly1305-p10-glue.o poly1305-p10le_64.o quiet_cmd_perl = PERL $@ cmd_perl = $(PERL) $< $(if $(CONFIG_CPU_LITTLE_ENDIAN), linux-ppc64le, linux-ppc64) > $@ diff --git a/arch/powerpc/crypto/chacha-p10-glue.c b/arch/powerpc/crypto/chacha-p10-glue.c new file mode 100644 index 000000000000..74fb86b0d209 --- /dev/null +++ b/arch/powerpc/crypto/chacha-p10-glue.c @@ -0,0 +1,221 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * PowerPC P10 (ppc64le) accelerated ChaCha and XChaCha stream ciphers, + * including ChaCha20 (RFC7539) + * + * Copyright 2023- IBM Corp. All rights reserved. + */ + +#include <crypto/algapi.h> +#include <crypto/internal/chacha.h> +#include <crypto/internal/simd.h> +#include <crypto/internal/skcipher.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/cpufeature.h> +#include <linux/sizes.h> +#include <asm/simd.h> +#include <asm/switch_to.h> + +asmlinkage void chacha_p10le_8x(u32 *state, u8 *dst, const u8 *src, + unsigned int len, int nrounds); + +static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_p10); + +static void vsx_begin(void) +{ + preempt_disable(); + enable_kernel_vsx(); +} + +static void vsx_end(void) +{ + disable_kernel_vsx(); + preempt_enable(); +} + +static void chacha_p10_do_8x(u32 *state, u8 *dst, const u8 *src, + unsigned int bytes, int nrounds) +{ + unsigned int l = bytes & ~0x0FF; + + if (l > 0) { + chacha_p10le_8x(state, dst, src, l, nrounds); + bytes -= l; + src += l; + dst += l; + state[12] += l / CHACHA_BLOCK_SIZE; + } + + if (bytes > 0) + chacha_crypt_generic(state, dst, src, bytes, nrounds); +} + +void hchacha_block_arch(const u32 *state, u32 *stream, int nrounds) +{ + hchacha_block_generic(state, stream, nrounds); +} +EXPORT_SYMBOL(hchacha_block_arch); + +void chacha_init_arch(u32 *state, const u32 *key, const u8 *iv) +{ + chacha_init_generic(state, key, iv); +} +EXPORT_SYMBOL(chacha_init_arch); + +void chacha_crypt_arch(u32 *state, u8 *dst, const u8 *src, unsigned int bytes, + int nrounds) +{ + if (!static_branch_likely(&have_p10) || bytes <= CHACHA_BLOCK_SIZE || + !crypto_simd_usable()) + return chacha_crypt_generic(state, dst, src, bytes, nrounds); + + do { + unsigned int todo = min_t(unsigned int, bytes, SZ_4K); + + vsx_begin(); + chacha_p10_do_8x(state, dst, src, todo, nrounds); + vsx_end(); + + bytes -= todo; + src += todo; + dst += todo; + } while (bytes); +} +EXPORT_SYMBOL(chacha_crypt_arch); + +static int chacha_p10_stream_xor(struct skcipher_request *req, + const struct chacha_ctx *ctx, const u8 *iv) +{ + struct skcipher_walk walk; + u32 state[16]; + int err; + + err = skcipher_walk_virt(&walk, req, false); + if (err) + return err; + + chacha_init_generic(state, ctx->key, iv); + + while (walk.nbytes > 0) { + unsigned int nbytes = walk.nbytes; + + if (nbytes < walk.total) + nbytes = rounddown(nbytes, walk.stride); + + if (!crypto_simd_usable()) { + chacha_crypt_generic(state, walk.dst.virt.addr, + walk.src.virt.addr, nbytes, + ctx->nrounds); + } else { + vsx_begin(); + chacha_p10_do_8x(state, walk.dst.virt.addr, + walk.src.virt.addr, nbytes, ctx->nrounds); + vsx_end(); + } + err = skcipher_walk_done(&walk, walk.nbytes - nbytes); + if (err) + break; + } + + return err; +} + +static int chacha_p10(struct skcipher_request *req) +{ + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm); + + return chacha_p10_stream_xor(req, ctx, req->iv); +} + +static int xchacha_p10(struct skcipher_request *req) +{ + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm); + struct chacha_ctx subctx; + u32 state[16]; + u8 real_iv[16]; + + chacha_init_generic(state, ctx->key, req->iv); + hchacha_block_arch(state, subctx.key, ctx->nrounds); + subctx.nrounds = ctx->nrounds; + + memcpy(&real_iv[0], req->iv + 24, 8); + memcpy(&real_iv[8], req->iv + 16, 8); + return chacha_p10_stream_xor(req, &subctx, real_iv); +} + +static struct skcipher_alg algs[] = { + { + .base.cra_name = "chacha20", + .base.cra_driver_name = "chacha20-p10", + .base.cra_priority = 300, + .base.cra_blocksize = 1, + .base.cra_ctxsize = sizeof(struct chacha_ctx), + .base.cra_module = THIS_MODULE, + + .min_keysize = CHACHA_KEY_SIZE, + .max_keysize = CHACHA_KEY_SIZE, + .ivsize = CHACHA_IV_SIZE, + .chunksize = CHACHA_BLOCK_SIZE, + .setkey = chacha20_setkey, + .encrypt = chacha_p10, + .decrypt = chacha_p10, + }, { + .base.cra_name = "xchacha20", + .base.cra_driver_name = "xchacha20-p10", + .base.cra_priority = 300, + .base.cra_blocksize = 1, + .base.cra_ctxsize = sizeof(struct chacha_ctx), + .base.cra_module = THIS_MODULE, + + .min_keysize = CHACHA_KEY_SIZE, + .max_keysize = CHACHA_KEY_SIZE, + .ivsize = XCHACHA_IV_SIZE, + .chunksize = CHACHA_BLOCK_SIZE, + .setkey = chacha20_setkey, + .encrypt = xchacha_p10, + .decrypt = xchacha_p10, + }, { + .base.cra_name = "xchacha12", + .base.cra_driver_name = "xchacha12-p10", + .base.cra_priority = 300, + .base.cra_blocksize = 1, + .base.cra_ctxsize = sizeof(struct chacha_ctx), + .base.cra_module = THIS_MODULE, + + .min_keysize = CHACHA_KEY_SIZE, + .max_keysize = CHACHA_KEY_SIZE, + .ivsize = XCHACHA_IV_SIZE, + .chunksize = CHACHA_BLOCK_SIZE, + .setkey = chacha12_setkey, + .encrypt = xchacha_p10, + .decrypt = xchacha_p10, + } +}; + +static int __init chacha_p10_init(void) +{ + static_branch_enable(&have_p10); + + return crypto_register_skciphers(algs, ARRAY_SIZE(algs)); +} + +static void __exit chacha_p10_exit(void) +{ + crypto_unregister_skciphers(algs, ARRAY_SIZE(algs)); +} + +module_cpu_feature_match(PPC_MODULE_FEATURE_P10, chacha_p10_init); +module_exit(chacha_p10_exit); + +MODULE_DESCRIPTION("ChaCha and XChaCha stream ciphers (P10 accelerated)"); +MODULE_AUTHOR("Danny Tsen <dtsen@linux.ibm.com>"); +MODULE_LICENSE("GPL v2"); +MODULE_ALIAS_CRYPTO("chacha20"); +MODULE_ALIAS_CRYPTO("chacha20-p10"); +MODULE_ALIAS_CRYPTO("xchacha20"); +MODULE_ALIAS_CRYPTO("xchacha20-p10"); +MODULE_ALIAS_CRYPTO("xchacha12"); +MODULE_ALIAS_CRYPTO("xchacha12-p10"); diff --git a/arch/powerpc/crypto/chacha-p10le-8x.S b/arch/powerpc/crypto/chacha-p10le-8x.S new file mode 100644 index 000000000000..17bedb66b822 --- /dev/null +++ b/arch/powerpc/crypto/chacha-p10le-8x.S @@ -0,0 +1,842 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +# +# Accelerated chacha20 implementation for ppc64le. +# +# Copyright 2023- IBM Corp. All rights reserved +# +#=================================================================================== +# Written by Danny Tsen <dtsen@us.ibm.com> +# +# chacha_p10le_8x(u32 *state, byte *dst, const byte *src, +# size_t len, int nrounds); +# +# do rounds, 8 quarter rounds +# 1. a += b; d ^= a; d <<<= 16; +# 2. c += d; b ^= c; b <<<= 12; +# 3. a += b; d ^= a; d <<<= 8; +# 4. c += d; b ^= c; b <<<= 7 +# +# row1 = (row1 + row2), row4 = row1 xor row4, row4 rotate each word by 16 +# row3 = (row3 + row4), row2 = row3 xor row2, row2 rotate each word by 12 +# row1 = (row1 + row2), row4 = row1 xor row4, row4 rotate each word by 8 +# row3 = (row3 + row4), row2 = row3 xor row2, row2 rotate each word by 7 +# +# 4 blocks (a b c d) +# +# a0 b0 c0 d0 +# a1 b1 c1 d1 +# ... +# a4 b4 c4 d4 +# ... +# a8 b8 c8 d8 +# ... +# a12 b12 c12 d12 +# a13 ... +# a14 ... +# a15 b15 c15 d15 +# +# Column round (v0, v4, v8, v12, v1, v5, v9, v13, v2, v6, v10, v14, v3, v7, v11, v15) +# Diagnal round (v0, v5, v10, v15, v1, v6, v11, v12, v2, v7, v8, v13, v3, v4, v9, v14) +# + +#include <asm/ppc_asm.h> +#include <asm/asm-offsets.h> +#include <asm/asm-compat.h> +#include <linux/linkage.h> + +.machine "any" +.text + +.macro SAVE_GPR GPR OFFSET FRAME + std \GPR,\OFFSET(\FRAME) +.endm + +.macro SAVE_VRS VRS OFFSET FRAME + li 16, \OFFSET + stvx \VRS, 16, \FRAME +.endm + +.macro SAVE_VSX VSX OFFSET FRAME + li 16, \OFFSET + stxvx \VSX, 16, \FRAME +.endm + +.macro RESTORE_GPR GPR OFFSET FRAME + ld \GPR,\OFFSET(\FRAME) +.endm + +.macro RESTORE_VRS VRS OFFSET FRAME + li 16, \OFFSET + lvx \VRS, 16, \FRAME +.endm + +.macro RESTORE_VSX VSX OFFSET FRAME + li 16, \OFFSET + lxvx \VSX, 16, \FRAME +.endm + +.macro SAVE_REGS + mflr 0 + std 0, 16(1) + stdu 1,-752(1) + + SAVE_GPR 14, 112, 1 + SAVE_GPR 15, 120, 1 + SAVE_GPR 16, 128, 1 + SAVE_GPR 17, 136, 1 + SAVE_GPR 18, 144, 1 + SAVE_GPR 19, 152, 1 + SAVE_GPR 20, 160, 1 + SAVE_GPR 21, 168, 1 + SAVE_GPR 22, 176, 1 + SAVE_GPR 23, 184, 1 + SAVE_GPR 24, 192, 1 + SAVE_GPR 25, 200, 1 + SAVE_GPR 26, 208, 1 + SAVE_GPR 27, 216, 1 + SAVE_GPR 28, 224, 1 + SAVE_GPR 29, 232, 1 + SAVE_GPR 30, 240, 1 + SAVE_GPR 31, 248, 1 + + addi 9, 1, 256 + SAVE_VRS 20, 0, 9 + SAVE_VRS 21, 16, 9 + SAVE_VRS 22, 32, 9 + SAVE_VRS 23, 48, 9 + SAVE_VRS 24, 64, 9 + SAVE_VRS 25, 80, 9 + SAVE_VRS 26, 96, 9 + SAVE_VRS 27, 112, 9 + SAVE_VRS 28, 128, 9 + SAVE_VRS 29, 144, 9 + SAVE_VRS 30, 160, 9 + SAVE_VRS 31, 176, 9 + + SAVE_VSX 14, 192, 9 + SAVE_VSX 15, 208, 9 + SAVE_VSX 16, 224, 9 + SAVE_VSX 17, 240, 9 + SAVE_VSX 18, 256, 9 + SAVE_VSX 19, 272, 9 + SAVE_VSX 20, 288, 9 + SAVE_VSX 21, 304, 9 + SAVE_VSX 22, 320, 9 + SAVE_VSX 23, 336, 9 + SAVE_VSX 24, 352, 9 + SAVE_VSX 25, 368, 9 + SAVE_VSX 26, 384, 9 + SAVE_VSX 27, 400, 9 + SAVE_VSX 28, 416, 9 + SAVE_VSX 29, 432, 9 + SAVE_VSX 30, 448, 9 + SAVE_VSX 31, 464, 9 +.endm # SAVE_REGS + +.macro RESTORE_REGS + addi 9, 1, 256 + RESTORE_VRS 20, 0, 9 + RESTORE_VRS 21, 16, 9 + RESTORE_VRS 22, 32, 9 + RESTORE_VRS 23, 48, 9 + RESTORE_VRS 24, 64, 9 + RESTORE_VRS 25, 80, 9 + RESTORE_VRS 26, 96, 9 + RESTORE_VRS 27, 112, 9 + RESTORE_VRS 28, 128, 9 + RESTORE_VRS 29, 144, 9 + RESTORE_VRS 30, 160, 9 + RESTORE_VRS 31, 176, 9 + + RESTORE_VSX 14, 192, 9 + RESTORE_VSX 15, 208, 9 + RESTORE_VSX 16, 224, 9 + RESTORE_VSX 17, 240, 9 + RESTORE_VSX 18, 256, 9 + RESTORE_VSX 19, 272, 9 + RESTORE_VSX 20, 288, 9 + RESTORE_VSX 21, 304, 9 + RESTORE_VSX 22, 320, 9 + RESTORE_VSX 23, 336, 9 + RESTORE_VSX 24, 352, 9 + RESTORE_VSX 25, 368, 9 + RESTORE_VSX 26, 384, 9 + RESTORE_VSX 27, 400, 9 + RESTORE_VSX 28, 416, 9 + RESTORE_VSX 29, 432, 9 + RESTORE_VSX 30, 448, 9 + RESTORE_VSX 31, 464, 9 + + RESTORE_GPR 14, 112, 1 + RESTORE_GPR 15, 120, 1 + RESTORE_GPR 16, 128, 1 + RESTORE_GPR 17, 136, 1 + RESTORE_GPR 18, 144, 1 + RESTORE_GPR 19, 152, 1 + RESTORE_GPR 20, 160, 1 + RESTORE_GPR 21, 168, 1 + RESTORE_GPR 22, 176, 1 + RESTORE_GPR 23, 184, 1 + RESTORE_GPR 24, 192, 1 + RESTORE_GPR 25, 200, 1 + RESTORE_GPR 26, 208, 1 + RESTORE_GPR 27, 216, 1 + RESTORE_GPR 28, 224, 1 + RESTORE_GPR 29, 232, 1 + RESTORE_GPR 30, 240, 1 + RESTORE_GPR 31, 248, 1 + + addi 1, 1, 752 + ld 0, 16(1) + mtlr 0 +.endm # RESTORE_REGS + +.macro QT_loop_8x + # QR(v0, v4, v8, v12, v1, v5, v9, v13, v2, v6, v10, v14, v3, v7, v11, v15) + xxlor 0, 32+25, 32+25 + xxlor 32+25, 20, 20 + vadduwm 0, 0, 4 + vadduwm 1, 1, 5 + vadduwm 2, 2, 6 + vadduwm 3, 3, 7 + vadduwm 16, 16, 20 + vadduwm 17, 17, 21 + vadduwm 18, 18, 22 + vadduwm 19, 19, 23 + + vpermxor 12, 12, 0, 25 + vpermxor 13, 13, 1, 25 + vpermxor 14, 14, 2, 25 + vpermxor 15, 15, 3, 25 + vpermxor 28, 28, 16, 25 + vpermxor 29, 29, 17, 25 + vpermxor 30, 30, 18, 25 + vpermxor 31, 31, 19, 25 + xxlor 32+25, 0, 0 + vadduwm 8, 8, 12 + vadduwm 9, 9, 13 + vadduwm 10, 10, 14 + vadduwm 11, 11, 15 + vadduwm 24, 24, 28 + vadduwm 25, 25, 29 + vadduwm 26, 26, 30 + vadduwm 27, 27, 31 + vxor 4, 4, 8 + vxor 5, 5, 9 + vxor 6, 6, 10 + vxor 7, 7, 11 + vxor 20, 20, 24 + vxor 21, 21, 25 + vxor 22, 22, 26 + vxor 23, 23, 27 + + xxlor 0, 32+25, 32+25 + xxlor 32+25, 21, 21 + vrlw 4, 4, 25 # + vrlw 5, 5, 25 + vrlw 6, 6, 25 + vrlw 7, 7, 25 + vrlw 20, 20, 25 # + vrlw 21, 21, 25 + vrlw 22, 22, 25 + vrlw 23, 23, 25 + xxlor 32+25, 0, 0 + vadduwm 0, 0, 4 + vadduwm 1, 1, 5 + vadduwm 2, 2, 6 + vadduwm 3, 3, 7 + vadduwm 16, 16, 20 + vadduwm 17, 17, 21 + vadduwm 18, 18, 22 + vadduwm 19, 19, 23 + + xxlor 0, 32+25, 32+25 + xxlor 32+25, 22, 22 + vpermxor 12, 12, 0, 25 + vpermxor 13, 13, 1, 25 + vpermxor 14, 14, 2, 25 + vpermxor 15, 15, 3, 25 + vpermxor 28, 28, 16, 25 + vpermxor 29, 29, 17, 25 + vpermxor 30, 30, 18, 25 + vpermxor 31, 31, 19, 25 + xxlor 32+25, 0, 0 + vadduwm 8, 8, 12 + vadduwm 9, 9, 13 + vadduwm 10, 10, 14 + vadduwm 11, 11, 15 + vadduwm 24, 24, 28 + vadduwm 25, 25, 29 + vadduwm 26, 26, 30 + vadduwm 27, 27, 31 + xxlor 0, 32+28, 32+28 + xxlor 32+28, 23, 23 + vxor 4, 4, 8 + vxor 5, 5, 9 + vxor 6, 6, 10 + vxor 7, 7, 11 + vxor 20, 20, 24 + vxor 21, 21, 25 + vxor 22, 22, 26 + vxor 23, 23, 27 + vrlw 4, 4, 28 # + vrlw 5, 5, 28 + vrlw 6, 6, 28 + vrlw 7, 7, 28 + vrlw 20, 20, 28 # + vrlw 21, 21, 28 + vrlw 22, 22, 28 + vrlw 23, 23, 28 + xxlor 32+28, 0, 0 + + # QR(v0, v5, v10, v15, v1, v6, v11, v12, v2, v7, v8, v13, v3, v4, v9, v14) + xxlor 0, 32+25, 32+25 + xxlor 32+25, 20, 20 + vadduwm 0, 0, 5 + vadduwm 1, 1, 6 + vadduwm 2, 2, 7 + vadduwm 3, 3, 4 + vadduwm 16, 16, 21 + vadduwm 17, 17, 22 + vadduwm 18, 18, 23 + vadduwm 19, 19, 20 + + vpermxor 15, 15, 0, 25 + vpermxor 12, 12, 1, 25 + vpermxor 13, 13, 2, 25 + vpermxor 14, 14, 3, 25 + vpermxor 31, 31, 16, 25 + vpermxor 28, 28, 17, 25 + vpermxor 29, 29, 18, 25 + vpermxor 30, 30, 19, 25 + + xxlor 32+25, 0, 0 + vadduwm 10, 10, 15 + vadduwm 11, 11, 12 + vadduwm 8, 8, 13 + vadduwm 9, 9, 14 + vadduwm 26, 26, 31 + vadduwm 27, 27, 28 + vadduwm 24, 24, 29 + vadduwm 25, 25, 30 + vxor 5, 5, 10 + vxor 6, 6, 11 + vxor 7, 7, 8 + vxor 4, 4, 9 + vxor 21, 21, 26 + vxor 22, 22, 27 + vxor 23, 23, 24 + vxor 20, 20, 25 + + xxlor 0, 32+25, 32+25 + xxlor 32+25, 21, 21 + vrlw 5, 5, 25 + vrlw 6, 6, 25 + vrlw 7, 7, 25 + vrlw 4, 4, 25 + vrlw 21, 21, 25 + vrlw 22, 22, 25 + vrlw 23, 23, 25 + vrlw 20, 20, 25 + xxlor 32+25, 0, 0 + + vadduwm 0, 0, 5 + vadduwm 1, 1, 6 + vadduwm 2, 2, 7 + vadduwm 3, 3, 4 + vadduwm 16, 16, 21 + vadduwm 17, 17, 22 + vadduwm 18, 18, 23 + vadduwm 19, 19, 20 + + xxlor 0, 32+25, 32+25 + xxlor 32+25, 22, 22 + vpermxor 15, 15, 0, 25 + vpermxor 12, 12, 1, 25 + vpermxor 13, 13, 2, 25 + vpermxor 14, 14, 3, 25 + vpermxor 31, 31, 16, 25 + vpermxor 28, 28, 17, 25 + vpermxor 29, 29, 18, 25 + vpermxor 30, 30, 19, 25 + xxlor 32+25, 0, 0 + + vadduwm 10, 10, 15 + vadduwm 11, 11, 12 + vadduwm 8, 8, 13 + vadduwm 9, 9, 14 + vadduwm 26, 26, 31 + vadduwm 27, 27, 28 + vadduwm 24, 24, 29 + vadduwm 25, 25, 30 + + xxlor 0, 32+28, 32+28 + xxlor 32+28, 23, 23 + vxor 5, 5, 10 + vxor 6, 6, 11 + vxor 7, 7, 8 + vxor 4, 4, 9 + vxor 21, 21, 26 + vxor 22, 22, 27 + vxor 23, 23, 24 + vxor 20, 20, 25 + vrlw 5, 5, 28 + vrlw 6, 6, 28 + vrlw 7, 7, 28 + vrlw 4, 4, 28 + vrlw 21, 21, 28 + vrlw 22, 22, 28 + vrlw 23, 23, 28 + vrlw 20, 20, 28 + xxlor 32+28, 0, 0 +.endm + +.macro QT_loop_4x + # QR(v0, v4, v8, v12, v1, v5, v9, v13, v2, v6, v10, v14, v3, v7, v11, v15) + vadduwm 0, 0, 4 + vadduwm 1, 1, 5 + vadduwm 2, 2, 6 + vadduwm 3, 3, 7 + vpermxor 12, 12, 0, 20 + vpermxor 13, 13, 1, 20 + vpermxor 14, 14, 2, 20 + vpermxor 15, 15, 3, 20 + vadduwm 8, 8, 12 + vadduwm 9, 9, 13 + vadduwm 10, 10, 14 + vadduwm 11, 11, 15 + vxor 4, 4, 8 + vxor 5, 5, 9 + vxor 6, 6, 10 + vxor 7, 7, 11 + vrlw 4, 4, 21 + vrlw 5, 5, 21 + vrlw 6, 6, 21 + vrlw 7, 7, 21 + vadduwm 0, 0, 4 + vadduwm 1, 1, 5 + vadduwm 2, 2, 6 + vadduwm 3, 3, 7 + vpermxor 12, 12, 0, 22 + vpermxor 13, 13, 1, 22 + vpermxor 14, 14, 2, 22 + vpermxor 15, 15, 3, 22 + vadduwm 8, 8, 12 + vadduwm 9, 9, 13 + vadduwm 10, 10, 14 + vadduwm 11, 11, 15 + vxor 4, 4, 8 + vxor 5, 5, 9 + vxor 6, 6, 10 + vxor 7, 7, 11 + vrlw 4, 4, 23 + vrlw 5, 5, 23 + vrlw 6, 6, 23 + vrlw 7, 7, 23 + + # QR(v0, v5, v10, v15, v1, v6, v11, v12, v2, v7, v8, v13, v3, v4, v9, v14) + vadduwm 0, 0, 5 + vadduwm 1, 1, 6 + vadduwm 2, 2, 7 + vadduwm 3, 3, 4 + vpermxor 15, 15, 0, 20 + vpermxor 12, 12, 1, 20 + vpermxor 13, 13, 2, 20 + vpermxor 14, 14, 3, 20 + vadduwm 10, 10, 15 + vadduwm 11, 11, 12 + vadduwm 8, 8, 13 + vadduwm 9, 9, 14 + vxor 5, 5, 10 + vxor 6, 6, 11 + vxor 7, 7, 8 + vxor 4, 4, 9 + vrlw 5, 5, 21 + vrlw 6, 6, 21 + vrlw 7, 7, 21 + vrlw 4, 4, 21 + vadduwm 0, 0, 5 + vadduwm 1, 1, 6 + vadduwm 2, 2, 7 + vadduwm 3, 3, 4 + vpermxor 15, 15, 0, 22 + vpermxor 12, 12, 1, 22 + vpermxor 13, 13, 2, 22 + vpermxor 14, 14, 3, 22 + vadduwm 10, 10, 15 + vadduwm 11, 11, 12 + vadduwm 8, 8, 13 + vadduwm 9, 9, 14 + vxor 5, 5, 10 + vxor 6, 6, 11 + vxor 7, 7, 8 + vxor 4, 4, 9 + vrlw 5, 5, 23 + vrlw 6, 6, 23 + vrlw 7, 7, 23 + vrlw 4, 4, 23 +.endm + +# Transpose +.macro TP_4x a0 a1 a2 a3 + xxmrghw 10, 32+\a0, 32+\a1 # a0, a1, b0, b1 + xxmrghw 11, 32+\a2, 32+\a3 # a2, a3, b2, b3 + xxmrglw 12, 32+\a0, 32+\a1 # c0, c1, d0, d1 + xxmrglw 13, 32+\a2, 32+\a3 # c2, c3, d2, d3 + xxpermdi 32+\a0, 10, 11, 0 # a0, a1, a2, a3 + xxpermdi 32+\a1, 10, 11, 3 # b0, b1, b2, b3 + xxpermdi 32+\a2, 12, 13, 0 # c0, c1, c2, c3 + xxpermdi 32+\a3, 12, 13, 3 # d0, d1, d2, d3 +.endm + +# key stream = working state + state +.macro Add_state S + vadduwm \S+0, \S+0, 16-\S + vadduwm \S+4, \S+4, 17-\S + vadduwm \S+8, \S+8, 18-\S + vadduwm \S+12, \S+12, 19-\S + + vadduwm \S+1, \S+1, 16-\S + vadduwm \S+5, \S+5, 17-\S + vadduwm \S+9, \S+9, 18-\S + vadduwm \S+13, \S+13, 19-\S + + vadduwm \S+2, \S+2, 16-\S + vadduwm \S+6, \S+6, 17-\S + vadduwm \S+10, \S+10, 18-\S + vadduwm \S+14, \S+14, 19-\S + + vadduwm \S+3, \S+3, 16-\S + vadduwm \S+7, \S+7, 17-\S + vadduwm \S+11, \S+11, 18-\S + vadduwm \S+15, \S+15, 19-\S +.endm + +# +# write 256 bytes +# +.macro Write_256 S + add 9, 14, 5 + add 16, 14, 4 + lxvw4x 0, 0, 9 + lxvw4x 1, 17, 9 + lxvw4x 2, 18, 9 + lxvw4x 3, 19, 9 + lxvw4x 4, 20, 9 + lxvw4x 5, 21, 9 + lxvw4x 6, 22, 9 + lxvw4x 7, 23, 9 + lxvw4x 8, 24, 9 + lxvw4x 9, 25, 9 + lxvw4x 10, 26, 9 + lxvw4x 11, 27, 9 + lxvw4x 12, 28, 9 + lxvw4x 13, 29, 9 + lxvw4x 14, 30, 9 + lxvw4x 15, 31, 9 + + xxlxor \S+32, \S+32, 0 + xxlxor \S+36, \S+36, 1 + xxlxor \S+40, \S+40, 2 + xxlxor \S+44, \S+44, 3 + xxlxor \S+33, \S+33, 4 + xxlxor \S+37, \S+37, 5 + xxlxor \S+41, \S+41, 6 + xxlxor \S+45, \S+45, 7 + xxlxor \S+34, \S+34, 8 + xxlxor \S+38, \S+38, 9 + xxlxor \S+42, \S+42, 10 + xxlxor \S+46, \S+46, 11 + xxlxor \S+35, \S+35, 12 + xxlxor \S+39, \S+39, 13 + xxlxor \S+43, \S+43, 14 + xxlxor \S+47, \S+47, 15 + + stxvw4x \S+32, 0, 16 + stxvw4x \S+36, 17, 16 + stxvw4x \S+40, 18, 16 + stxvw4x \S+44, 19, 16 + + stxvw4x \S+33, 20, 16 + stxvw4x \S+37, 21, 16 + stxvw4x \S+41, 22, 16 + stxvw4x \S+45, 23, 16 + + stxvw4x \S+34, 24, 16 + stxvw4x \S+38, 25, 16 + stxvw4x \S+42, 26, 16 + stxvw4x \S+46, 27, 16 + + stxvw4x \S+35, 28, 16 + stxvw4x \S+39, 29, 16 + stxvw4x \S+43, 30, 16 + stxvw4x \S+47, 31, 16 + +.endm + +# +# chacha20_p10le_8x(u32 *state, byte *dst, const byte *src, size_t len, int nrounds); +# +SYM_FUNC_START(chacha_p10le_8x) +.align 5 + cmpdi 6, 0 + ble Out_no_chacha + + SAVE_REGS + + # r17 - r31 mainly for Write_256 macro. + li 17, 16 + li 18, 32 + li 19, 48 + li 20, 64 + li 21, 80 + li 22, 96 + li 23, 112 + li 24, 128 + li 25, 144 + li 26, 160 + li 27, 176 + li 28, 192 + li 29, 208 + li 30, 224 + li 31, 240 + + mr 15, 6 # len + li 14, 0 # offset to inp and outp + + lxvw4x 48, 0, 3 # vr16, constants + lxvw4x 49, 17, 3 # vr17, key 1 + lxvw4x 50, 18, 3 # vr18, key 2 + lxvw4x 51, 19, 3 # vr19, counter, nonce + + # create (0, 1, 2, 3) counters + vspltisw 0, 0 + vspltisw 1, 1 + vspltisw 2, 2 + vspltisw 3, 3 + vmrghw 4, 0, 1 + vmrglw 5, 2, 3 + vsldoi 30, 4, 5, 8 # vr30 counter, 4 (0, 1, 2, 3) + + vspltisw 21, 12 + vspltisw 23, 7 + + addis 11, 2, permx@toc@ha + addi 11, 11, permx@toc@l + lxvw4x 32+20, 0, 11 + lxvw4x 32+22, 17, 11 + + sradi 8, 7, 1 + + mtctr 8 + + # save constants to vsx + xxlor 16, 48, 48 + xxlor 17, 49, 49 + xxlor 18, 50, 50 + xxlor 19, 51, 51 + + vspltisw 25, 4 + vspltisw 26, 8 + + xxlor 25, 32+26, 32+26 + xxlor 24, 32+25, 32+25 + + vadduwm 31, 30, 25 # counter = (0, 1, 2, 3) + (4, 4, 4, 4) + xxlor 30, 32+30, 32+30 + xxlor 31, 32+31, 32+31 + + xxlor 20, 32+20, 32+20 + xxlor 21, 32+21, 32+21 + xxlor 22, 32+22, 32+22 + xxlor 23, 32+23, 32+23 + + cmpdi 6, 512 + blt Loop_last + +Loop_8x: + xxspltw 32+0, 16, 0 + xxspltw 32+1, 16, 1 + xxspltw 32+2, 16, 2 + xxspltw 32+3, 16, 3 + + xxspltw 32+4, 17, 0 + xxspltw 32+5, 17, 1 + xxspltw 32+6, 17, 2 + xxspltw 32+7, 17, 3 + xxspltw 32+8, 18, 0 + xxspltw 32+9, 18, 1 + xxspltw 32+10, 18, 2 + xxspltw 32+11, 18, 3 + xxspltw 32+12, 19, 0 + xxspltw 32+13, 19, 1 + xxspltw 32+14, 19, 2 + xxspltw 32+15, 19, 3 + vadduwm 12, 12, 30 # increase counter + + xxspltw 32+16, 16, 0 + xxspltw 32+17, 16, 1 + xxspltw 32+18, 16, 2 + xxspltw 32+19, 16, 3 + + xxspltw 32+20, 17, 0 + xxspltw 32+21, 17, 1 + xxspltw 32+22, 17, 2 + xxspltw 32+23, 17, 3 + xxspltw 32+24, 18, 0 + xxspltw 32+25, 18, 1 + xxspltw 32+26, 18, 2 + xxspltw 32+27, 18, 3 + xxspltw 32+28, 19, 0 + xxspltw 32+29, 19, 1 + vadduwm 28, 28, 31 # increase counter + xxspltw 32+30, 19, 2 + xxspltw 32+31, 19, 3 + +.align 5 +quarter_loop_8x: + QT_loop_8x + + bdnz quarter_loop_8x + + xxlor 0, 32+30, 32+30 + xxlor 32+30, 30, 30 + vadduwm 12, 12, 30 + xxlor 32+30, 0, 0 + TP_4x 0, 1, 2, 3 + TP_4x 4, 5, 6, 7 + TP_4x 8, 9, 10, 11 + TP_4x 12, 13, 14, 15 + + xxlor 0, 48, 48 + xxlor 1, 49, 49 + xxlor 2, 50, 50 + xxlor 3, 51, 51 + xxlor 48, 16, 16 + xxlor 49, 17, 17 + xxlor 50, 18, 18 + xxlor 51, 19, 19 + Add_state 0 + xxlor 48, 0, 0 + xxlor 49, 1, 1 + xxlor 50, 2, 2 + xxlor 51, 3, 3 + Write_256 0 + addi 14, 14, 256 # offset +=256 + addi 15, 15, -256 # len -=256 + + xxlor 5, 32+31, 32+31 + xxlor 32+31, 31, 31 + vadduwm 28, 28, 31 + xxlor 32+31, 5, 5 + TP_4x 16+0, 16+1, 16+2, 16+3 + TP_4x 16+4, 16+5, 16+6, 16+7 + TP_4x 16+8, 16+9, 16+10, 16+11 + TP_4x 16+12, 16+13, 16+14, 16+15 + + xxlor 32, 16, 16 + xxlor 33, 17, 17 + xxlor 34, 18, 18 + xxlor 35, 19, 19 + Add_state 16 + Write_256 16 + addi 14, 14, 256 # offset +=256 + addi 15, 15, -256 # len +=256 + + xxlor 32+24, 24, 24 + xxlor 32+25, 25, 25 + xxlor 32+30, 30, 30 + vadduwm 30, 30, 25 + vadduwm 31, 30, 24 + xxlor 30, 32+30, 32+30 + xxlor 31, 32+31, 32+31 + + cmpdi 15, 0 + beq Out_loop + + cmpdi 15, 512 + blt Loop_last + + mtctr 8 + b Loop_8x + +Loop_last: + lxvw4x 48, 0, 3 # vr16, constants + lxvw4x 49, 17, 3 # vr17, key 1 + lxvw4x 50, 18, 3 # vr18, key 2 + lxvw4x 51, 19, 3 # vr19, counter, nonce + + vspltisw 21, 12 + vspltisw 23, 7 + addis 11, 2, permx@toc@ha + addi 11, 11, permx@toc@l + lxvw4x 32+20, 0, 11 + lxvw4x 32+22, 17, 11 + + sradi 8, 7, 1 + mtctr 8 + +Loop_4x: + vspltw 0, 16, 0 + vspltw 1, 16, 1 + vspltw 2, 16, 2 + vspltw 3, 16, 3 + + vspltw 4, 17, 0 + vspltw 5, 17, 1 + vspltw 6, 17, 2 + vspltw 7, 17, 3 + vspltw 8, 18, 0 + vspltw 9, 18, 1 + vspltw 10, 18, 2 + vspltw 11, 18, 3 + vspltw 12, 19, 0 + vadduwm 12, 12, 30 # increase counter + vspltw 13, 19, 1 + vspltw 14, 19, 2 + vspltw 15, 19, 3 + +.align 5 +quarter_loop: + QT_loop_4x + + bdnz quarter_loop + + vadduwm 12, 12, 30 + TP_4x 0, 1, 2, 3 + TP_4x 4, 5, 6, 7 + TP_4x 8, 9, 10, 11 + TP_4x 12, 13, 14, 15 + + Add_state 0 + Write_256 0 + addi 14, 14, 256 # offset += 256 + addi 15, 15, -256 # len += 256 + + # Update state counter + vspltisw 25, 4 + vadduwm 30, 30, 25 + + cmpdi 15, 0 + beq Out_loop + cmpdi 15, 256 + blt Out_loop + + mtctr 8 + b Loop_4x + +Out_loop: + RESTORE_REGS + blr + +Out_no_chacha: + li 3, 0 + blr +SYM_FUNC_END(chacha_p10le_8x) + +SYM_DATA_START_LOCAL(PERMX) +.align 5 +permx: +.long 0x22330011, 0x66774455, 0xaabb8899, 0xeeffccdd +.long 0x11223300, 0x55667744, 0x99aabb88, 0xddeeffcc +SYM_DATA_END(PERMX) diff --git a/arch/powerpc/crypto/poly1305-p10-glue.c b/arch/powerpc/crypto/poly1305-p10-glue.c new file mode 100644 index 000000000000..95dd708573ee --- /dev/null +++ b/arch/powerpc/crypto/poly1305-p10-glue.c @@ -0,0 +1,186 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Poly1305 authenticator algorithm, RFC7539. + * + * Copyright 2023- IBM Corp. All rights reserved. + */ + +#include <crypto/algapi.h> +#include <linux/crypto.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/jump_label.h> +#include <crypto/internal/hash.h> +#include <crypto/internal/poly1305.h> +#include <crypto/internal/simd.h> +#include <linux/cpufeature.h> +#include <asm/unaligned.h> +#include <asm/simd.h> +#include <asm/switch_to.h> + +asmlinkage void poly1305_p10le_4blocks(void *h, const u8 *m, u32 mlen); +asmlinkage void poly1305_64s(void *h, const u8 *m, u32 mlen, int highbit); +asmlinkage void poly1305_emit_64(void *h, void *s, u8 *dst); + +static void vsx_begin(void) +{ + preempt_disable(); + enable_kernel_vsx(); +} + +static void vsx_end(void) +{ + disable_kernel_vsx(); + preempt_enable(); +} + +static int crypto_poly1305_p10_init(struct shash_desc *desc) +{ + struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc); + + poly1305_core_init(&dctx->h); + dctx->buflen = 0; + dctx->rset = 0; + dctx->sset = false; + + return 0; +} + +static unsigned int crypto_poly1305_setdctxkey(struct poly1305_desc_ctx *dctx, + const u8 *inp, unsigned int len) +{ + unsigned int acc = 0; + + if (unlikely(!dctx->sset)) { + if (!dctx->rset && len >= POLY1305_BLOCK_SIZE) { + struct poly1305_core_key *key = &dctx->core_r; + + key->key.r64[0] = get_unaligned_le64(&inp[0]); + key->key.r64[1] = get_unaligned_le64(&inp[8]); + inp += POLY1305_BLOCK_SIZE; + len -= POLY1305_BLOCK_SIZE; + acc += POLY1305_BLOCK_SIZE; + dctx->rset = 1; + } + if (len >= POLY1305_BLOCK_SIZE) { + dctx->s[0] = get_unaligned_le32(&inp[0]); + dctx->s[1] = get_unaligned_le32(&inp[4]); + dctx->s[2] = get_unaligned_le32(&inp[8]); + dctx->s[3] = get_unaligned_le32(&inp[12]); + acc += POLY1305_BLOCK_SIZE; + dctx->sset = true; + } + } + return acc; +} + +static int crypto_poly1305_p10_update(struct shash_desc *desc, + const u8 *src, unsigned int srclen) +{ + struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc); + unsigned int bytes, used; + + if (unlikely(dctx->buflen)) { + bytes = min(srclen, POLY1305_BLOCK_SIZE - dctx->buflen); + memcpy(dctx->buf + dctx->buflen, src, bytes); + src += bytes; + srclen -= bytes; + dctx->buflen += bytes; + + if (dctx->buflen == POLY1305_BLOCK_SIZE) { + if (likely(!crypto_poly1305_setdctxkey(dctx, dctx->buf, + POLY1305_BLOCK_SIZE))) { + vsx_begin(); + poly1305_64s(&dctx->h, dctx->buf, + POLY1305_BLOCK_SIZE, 1); + vsx_end(); + } + dctx->buflen = 0; + } + } + + if (likely(srclen >= POLY1305_BLOCK_SIZE)) { + bytes = round_down(srclen, POLY1305_BLOCK_SIZE); + used = crypto_poly1305_setdctxkey(dctx, src, bytes); + if (likely(used)) { + srclen -= used; + src += used; + } + if (crypto_simd_usable() && (srclen >= POLY1305_BLOCK_SIZE*4)) { + vsx_begin(); + poly1305_p10le_4blocks(&dctx->h, src, srclen); + vsx_end(); + src += srclen - (srclen % (POLY1305_BLOCK_SIZE * 4)); + srclen %= POLY1305_BLOCK_SIZE * 4; + } + while (srclen >= POLY1305_BLOCK_SIZE) { + vsx_begin(); + poly1305_64s(&dctx->h, src, POLY1305_BLOCK_SIZE, 1); + vsx_end(); + srclen -= POLY1305_BLOCK_SIZE; + src += POLY1305_BLOCK_SIZE; + } + } + + if (unlikely(srclen)) { + dctx->buflen = srclen; + memcpy(dctx->buf, src, srclen); + } + + return 0; +} + +static int crypto_poly1305_p10_final(struct shash_desc *desc, u8 *dst) +{ + struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc); + + if (unlikely(!dctx->sset)) + return -ENOKEY; + + if ((dctx->buflen)) { + dctx->buf[dctx->buflen++] = 1; + memset(dctx->buf + dctx->buflen, 0, + POLY1305_BLOCK_SIZE - dctx->buflen); + vsx_begin(); + poly1305_64s(&dctx->h, dctx->buf, POLY1305_BLOCK_SIZE, 0); + vsx_end(); + dctx->buflen = 0; + } + + poly1305_emit_64(&dctx->h, &dctx->s, dst); + return 0; +} + +static struct shash_alg poly1305_alg = { + .digestsize = POLY1305_DIGEST_SIZE, + .init = crypto_poly1305_p10_init, + .update = crypto_poly1305_p10_update, + .final = crypto_poly1305_p10_final, + .descsize = sizeof(struct poly1305_desc_ctx), + .base = { + .cra_name = "poly1305", + .cra_driver_name = "poly1305-p10", + .cra_priority = 300, + .cra_blocksize = POLY1305_BLOCK_SIZE, + .cra_module = THIS_MODULE, + }, +}; + +static int __init poly1305_p10_init(void) +{ + return crypto_register_shash(&poly1305_alg); +} + +static void __exit poly1305_p10_exit(void) +{ + crypto_unregister_shash(&poly1305_alg); +} + +module_cpu_feature_match(PPC_MODULE_FEATURE_P10, poly1305_p10_init); +module_exit(poly1305_p10_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Danny Tsen <dtsen@linux.ibm.com>"); +MODULE_DESCRIPTION("Optimized Poly1305 for P10"); +MODULE_ALIAS_CRYPTO("poly1305"); +MODULE_ALIAS_CRYPTO("poly1305-p10"); diff --git a/arch/powerpc/crypto/poly1305-p10le_64.S b/arch/powerpc/crypto/poly1305-p10le_64.S new file mode 100644 index 000000000000..a3c1987f1ecd --- /dev/null +++ b/arch/powerpc/crypto/poly1305-p10le_64.S @@ -0,0 +1,1075 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +# +# Accelerated poly1305 implementation for ppc64le. +# +# Copyright 2023- IBM Corp. All rights reserved +# +#=================================================================================== +# Written by Danny Tsen <dtsen@us.ibm.com> +# +# Poly1305 - this version mainly using vector/VSX/Scalar +# - 26 bits limbs +# - Handle multiple 64 byte blcok. +# +# Block size 16 bytes +# key = (r, s) +# clamp r &= 0x0FFFFFFC0FFFFFFC 0x0FFFFFFC0FFFFFFF +# p = 2^130 - 5 +# a += m +# a = (r + a) % p +# a += s +# +# Improve performance by breaking down polynominal to the sum of products with +# h4 = m1 * r⁴ + m2 * r³ + m3 * r² + m4 * r +# +# 07/22/21 - this revison based on the above sum of products. Setup r^4, r^3, r^2, r and s3, s2, s1, s0 +# to 9 vectors for multiplications. +# +# setup r^4, r^3, r^2, r vectors +# vs [r^1, r^3, r^2, r^4] +# vs0 = [r0,.....] +# vs1 = [r1,.....] +# vs2 = [r2,.....] +# vs3 = [r3,.....] +# vs4 = [r4,.....] +# vs5 = [r1*5,...] +# vs6 = [r2*5,...] +# vs7 = [r2*5,...] +# vs8 = [r4*5,...] +# +# Each word in a vector consists a member of a "r/s" in [a * r/s]. +# +# r0, r4*5, r3*5, r2*5, r1*5; +# r1, r0, r4*5, r3*5, r2*5; +# r2, r1, r0, r4*5, r3*5; +# r3, r2, r1, r0, r4*5; +# r4, r3, r2, r1, r0 ; +# +# +# poly1305_p10le_4blocks( uint8_t *k, uint32_t mlen, uint8_t *m) +# k = 32 bytes key +# r3 = k (r, s) +# r4 = mlen +# r5 = m +# +#include <asm/ppc_asm.h> +#include <asm/asm-offsets.h> +#include <asm/asm-compat.h> +#include <linux/linkage.h> + +.machine "any" + +.text + +.macro SAVE_GPR GPR OFFSET FRAME + std \GPR,\OFFSET(\FRAME) +.endm + +.macro SAVE_VRS VRS OFFSET FRAME + li 16, \OFFSET + stvx \VRS, 16, \FRAME +.endm + +.macro SAVE_VSX VSX OFFSET FRAME + li 16, \OFFSET + stxvx \VSX, 16, \FRAME +.endm + +.macro RESTORE_GPR GPR OFFSET FRAME + ld \GPR,\OFFSET(\FRAME) +.endm + +.macro RESTORE_VRS VRS OFFSET FRAME + li 16, \OFFSET + lvx \VRS, 16, \FRAME +.endm + +.macro RESTORE_VSX VSX OFFSET FRAME + li 16, \OFFSET + lxvx \VSX, 16, \FRAME +.endm + +.macro SAVE_REGS + mflr 0 + std 0, 16(1) + stdu 1,-752(1) + + SAVE_GPR 14, 112, 1 + SAVE_GPR 15, 120, 1 + SAVE_GPR 16, 128, 1 + SAVE_GPR 17, 136, 1 + SAVE_GPR 18, 144, 1 + SAVE_GPR 19, 152, 1 + SAVE_GPR 20, 160, 1 + SAVE_GPR 21, 168, 1 + SAVE_GPR 22, 176, 1 + SAVE_GPR 23, 184, 1 + SAVE_GPR 24, 192, 1 + SAVE_GPR 25, 200, 1 + SAVE_GPR 26, 208, 1 + SAVE_GPR 27, 216, 1 + SAVE_GPR 28, 224, 1 + SAVE_GPR 29, 232, 1 + SAVE_GPR 30, 240, 1 + SAVE_GPR 31, 248, 1 + + addi 9, 1, 256 + SAVE_VRS 20, 0, 9 + SAVE_VRS 21, 16, 9 + SAVE_VRS 22, 32, 9 + SAVE_VRS 23, 48, 9 + SAVE_VRS 24, 64, 9 + SAVE_VRS 25, 80, 9 + SAVE_VRS 26, 96, 9 + SAVE_VRS 27, 112, 9 + SAVE_VRS 28, 128, 9 + SAVE_VRS 29, 144, 9 + SAVE_VRS 30, 160, 9 + SAVE_VRS 31, 176, 9 + + SAVE_VSX 14, 192, 9 + SAVE_VSX 15, 208, 9 + SAVE_VSX 16, 224, 9 + SAVE_VSX 17, 240, 9 + SAVE_VSX 18, 256, 9 + SAVE_VSX 19, 272, 9 + SAVE_VSX 20, 288, 9 + SAVE_VSX 21, 304, 9 + SAVE_VSX 22, 320, 9 + SAVE_VSX 23, 336, 9 + SAVE_VSX 24, 352, 9 + SAVE_VSX 25, 368, 9 + SAVE_VSX 26, 384, 9 + SAVE_VSX 27, 400, 9 + SAVE_VSX 28, 416, 9 + SAVE_VSX 29, 432, 9 + SAVE_VSX 30, 448, 9 + SAVE_VSX 31, 464, 9 +.endm # SAVE_REGS + +.macro RESTORE_REGS + addi 9, 1, 256 + RESTORE_VRS 20, 0, 9 + RESTORE_VRS 21, 16, 9 + RESTORE_VRS 22, 32, 9 + RESTORE_VRS 23, 48, 9 + RESTORE_VRS 24, 64, 9 + RESTORE_VRS 25, 80, 9 + RESTORE_VRS 26, 96, 9 + RESTORE_VRS 27, 112, 9 + RESTORE_VRS 28, 128, 9 + RESTORE_VRS 29, 144, 9 + RESTORE_VRS 30, 160, 9 + RESTORE_VRS 31, 176, 9 + + RESTORE_VSX 14, 192, 9 + RESTORE_VSX 15, 208, 9 + RESTORE_VSX 16, 224, 9 + RESTORE_VSX 17, 240, 9 + RESTORE_VSX 18, 256, 9 + RESTORE_VSX 19, 272, 9 + RESTORE_VSX 20, 288, 9 + RESTORE_VSX 21, 304, 9 + RESTORE_VSX 22, 320, 9 + RESTORE_VSX 23, 336, 9 + RESTORE_VSX 24, 352, 9 + RESTORE_VSX 25, 368, 9 + RESTORE_VSX 26, 384, 9 + RESTORE_VSX 27, 400, 9 + RESTORE_VSX 28, 416, 9 + RESTORE_VSX 29, 432, 9 + RESTORE_VSX 30, 448, 9 + RESTORE_VSX 31, 464, 9 + + RESTORE_GPR 14, 112, 1 + RESTORE_GPR 15, 120, 1 + RESTORE_GPR 16, 128, 1 + RESTORE_GPR 17, 136, 1 + RESTORE_GPR 18, 144, 1 + RESTORE_GPR 19, 152, 1 + RESTORE_GPR 20, 160, 1 + RESTORE_GPR 21, 168, 1 + RESTORE_GPR 22, 176, 1 + RESTORE_GPR 23, 184, 1 + RESTORE_GPR 24, 192, 1 + RESTORE_GPR 25, 200, 1 + RESTORE_GPR 26, 208, 1 + RESTORE_GPR 27, 216, 1 + RESTORE_GPR 28, 224, 1 + RESTORE_GPR 29, 232, 1 + RESTORE_GPR 30, 240, 1 + RESTORE_GPR 31, 248, 1 + + addi 1, 1, 752 + ld 0, 16(1) + mtlr 0 +.endm # RESTORE_REGS + +# +# p[0] = a0*r0 + a1*r4*5 + a2*r3*5 + a3*r2*5 + a4*r1*5; +# p[1] = a0*r1 + a1*r0 + a2*r4*5 + a3*r3*5 + a4*r2*5; +# p[2] = a0*r2 + a1*r1 + a2*r0 + a3*r4*5 + a4*r3*5; +# p[3] = a0*r3 + a1*r2 + a2*r1 + a3*r0 + a4*r4*5; +# p[4] = a0*r4 + a1*r3 + a2*r2 + a3*r1 + a4*r0 ; +# +# [r^2, r^3, r^1, r^4] +# [m3, m2, m4, m1] +# +# multiply odd and even words +.macro mul_odd + vmulouw 14, 4, 26 + vmulouw 10, 5, 3 + vmulouw 11, 6, 2 + vmulouw 12, 7, 1 + vmulouw 13, 8, 0 + vmulouw 15, 4, 27 + vaddudm 14, 14, 10 + vaddudm 14, 14, 11 + vmulouw 10, 5, 26 + vmulouw 11, 6, 3 + vaddudm 14, 14, 12 + vaddudm 14, 14, 13 # x0 + vaddudm 15, 15, 10 + vaddudm 15, 15, 11 + vmulouw 12, 7, 2 + vmulouw 13, 8, 1 + vaddudm 15, 15, 12 + vaddudm 15, 15, 13 # x1 + vmulouw 16, 4, 28 + vmulouw 10, 5, 27 + vmulouw 11, 6, 26 + vaddudm 16, 16, 10 + vaddudm 16, 16, 11 + vmulouw 12, 7, 3 + vmulouw 13, 8, 2 + vaddudm 16, 16, 12 + vaddudm 16, 16, 13 # x2 + vmulouw 17, 4, 29 + vmulouw 10, 5, 28 + vmulouw 11, 6, 27 + vaddudm 17, 17, 10 + vaddudm 17, 17, 11 + vmulouw 12, 7, 26 + vmulouw 13, 8, 3 + vaddudm 17, 17, 12 + vaddudm 17, 17, 13 # x3 + vmulouw 18, 4, 30 + vmulouw 10, 5, 29 + vmulouw 11, 6, 28 + vaddudm 18, 18, 10 + vaddudm 18, 18, 11 + vmulouw 12, 7, 27 + vmulouw 13, 8, 26 + vaddudm 18, 18, 12 + vaddudm 18, 18, 13 # x4 +.endm + +.macro mul_even + vmuleuw 9, 4, 26 + vmuleuw 10, 5, 3 + vmuleuw 11, 6, 2 + vmuleuw 12, 7, 1 + vmuleuw 13, 8, 0 + vaddudm 14, 14, 9 + vaddudm 14, 14, 10 + vaddudm 14, 14, 11 + vaddudm 14, 14, 12 + vaddudm 14, 14, 13 # x0 + + vmuleuw 9, 4, 27 + vmuleuw 10, 5, 26 + vmuleuw 11, 6, 3 + vmuleuw 12, 7, 2 + vmuleuw 13, 8, 1 + vaddudm 15, 15, 9 + vaddudm 15, 15, 10 + vaddudm 15, 15, 11 + vaddudm 15, 15, 12 + vaddudm 15, 15, 13 # x1 + + vmuleuw 9, 4, 28 + vmuleuw 10, 5, 27 + vmuleuw 11, 6, 26 + vmuleuw 12, 7, 3 + vmuleuw 13, 8, 2 + vaddudm 16, 16, 9 + vaddudm 16, 16, 10 + vaddudm 16, 16, 11 + vaddudm 16, 16, 12 + vaddudm 16, 16, 13 # x2 + + vmuleuw 9, 4, 29 + vmuleuw 10, 5, 28 + vmuleuw 11, 6, 27 + vmuleuw 12, 7, 26 + vmuleuw 13, 8, 3 + vaddudm 17, 17, 9 + vaddudm 17, 17, 10 + vaddudm 17, 17, 11 + vaddudm 17, 17, 12 + vaddudm 17, 17, 13 # x3 + + vmuleuw 9, 4, 30 + vmuleuw 10, 5, 29 + vmuleuw 11, 6, 28 + vmuleuw 12, 7, 27 + vmuleuw 13, 8, 26 + vaddudm 18, 18, 9 + vaddudm 18, 18, 10 + vaddudm 18, 18, 11 + vaddudm 18, 18, 12 + vaddudm 18, 18, 13 # x4 +.endm + +# +# poly1305_setup_r +# +# setup r^4, r^3, r^2, r vectors +# [r, r^3, r^2, r^4] +# vs0 = [r0,...] +# vs1 = [r1,...] +# vs2 = [r2,...] +# vs3 = [r3,...] +# vs4 = [r4,...] +# vs5 = [r4*5,...] +# vs6 = [r3*5,...] +# vs7 = [r2*5,...] +# vs8 = [r1*5,...] +# +# r0, r4*5, r3*5, r2*5, r1*5; +# r1, r0, r4*5, r3*5, r2*5; +# r2, r1, r0, r4*5, r3*5; +# r3, r2, r1, r0, r4*5; +# r4, r3, r2, r1, r0 ; +# +.macro poly1305_setup_r + + # save r + xxlor 26, 58, 58 + xxlor 27, 59, 59 + xxlor 28, 60, 60 + xxlor 29, 61, 61 + xxlor 30, 62, 62 + + xxlxor 31, 31, 31 + +# [r, r^3, r^2, r^4] + # compute r^2 + vmr 4, 26 + vmr 5, 27 + vmr 6, 28 + vmr 7, 29 + vmr 8, 30 + bl do_mul # r^2 r^1 + xxpermdi 58, 58, 36, 0x3 # r0 + xxpermdi 59, 59, 37, 0x3 # r1 + xxpermdi 60, 60, 38, 0x3 # r2 + xxpermdi 61, 61, 39, 0x3 # r3 + xxpermdi 62, 62, 40, 0x3 # r4 + xxpermdi 36, 36, 36, 0x3 + xxpermdi 37, 37, 37, 0x3 + xxpermdi 38, 38, 38, 0x3 + xxpermdi 39, 39, 39, 0x3 + xxpermdi 40, 40, 40, 0x3 + vspltisb 13, 2 + vsld 9, 27, 13 + vsld 10, 28, 13 + vsld 11, 29, 13 + vsld 12, 30, 13 + vaddudm 0, 9, 27 + vaddudm 1, 10, 28 + vaddudm 2, 11, 29 + vaddudm 3, 12, 30 + + bl do_mul # r^4 r^3 + vmrgow 26, 26, 4 + vmrgow 27, 27, 5 + vmrgow 28, 28, 6 + vmrgow 29, 29, 7 + vmrgow 30, 30, 8 + vspltisb 13, 2 + vsld 9, 27, 13 + vsld 10, 28, 13 + vsld 11, 29, 13 + vsld 12, 30, 13 + vaddudm 0, 9, 27 + vaddudm 1, 10, 28 + vaddudm 2, 11, 29 + vaddudm 3, 12, 30 + + # r^2 r^4 + xxlor 0, 58, 58 + xxlor 1, 59, 59 + xxlor 2, 60, 60 + xxlor 3, 61, 61 + xxlor 4, 62, 62 + xxlor 5, 32, 32 + xxlor 6, 33, 33 + xxlor 7, 34, 34 + xxlor 8, 35, 35 + + vspltw 9, 26, 3 + vspltw 10, 26, 2 + vmrgow 26, 10, 9 + vspltw 9, 27, 3 + vspltw 10, 27, 2 + vmrgow 27, 10, 9 + vspltw 9, 28, 3 + vspltw 10, 28, 2 + vmrgow 28, 10, 9 + vspltw 9, 29, 3 + vspltw 10, 29, 2 + vmrgow 29, 10, 9 + vspltw 9, 30, 3 + vspltw 10, 30, 2 + vmrgow 30, 10, 9 + + vsld 9, 27, 13 + vsld 10, 28, 13 + vsld 11, 29, 13 + vsld 12, 30, 13 + vaddudm 0, 9, 27 + vaddudm 1, 10, 28 + vaddudm 2, 11, 29 + vaddudm 3, 12, 30 +.endm + +SYM_FUNC_START_LOCAL(do_mul) + mul_odd + + # do reduction ( h %= p ) + # carry reduction + vspltisb 9, 2 + vsrd 10, 14, 31 + vsrd 11, 17, 31 + vand 7, 17, 25 + vand 4, 14, 25 + vaddudm 18, 18, 11 + vsrd 12, 18, 31 + vaddudm 15, 15, 10 + + vsrd 11, 15, 31 + vand 8, 18, 25 + vand 5, 15, 25 + vaddudm 4, 4, 12 + vsld 10, 12, 9 + vaddudm 6, 16, 11 + + vsrd 13, 6, 31 + vand 6, 6, 25 + vaddudm 4, 4, 10 + vsrd 10, 4, 31 + vaddudm 7, 7, 13 + + vsrd 11, 7, 31 + vand 7, 7, 25 + vand 4, 4, 25 + vaddudm 5, 5, 10 + vaddudm 8, 8, 11 + blr +SYM_FUNC_END(do_mul) + +# +# init key +# +.macro do_poly1305_init + addis 10, 2, rmask@toc@ha + addi 10, 10, rmask@toc@l + + ld 11, 0(10) + ld 12, 8(10) + + li 14, 16 + li 15, 32 + addis 10, 2, cnum@toc@ha + addi 10, 10, cnum@toc@l + lvx 25, 0, 10 # v25 - mask + lvx 31, 14, 10 # v31 = 1a + lvx 19, 15, 10 # v19 = 1 << 24 + lxv 24, 48(10) # vs24 + lxv 25, 64(10) # vs25 + + # initialize + # load key from r3 to vectors + ld 9, 24(3) + ld 10, 32(3) + and. 9, 9, 11 + and. 10, 10, 12 + + # break 26 bits + extrdi 14, 9, 26, 38 + extrdi 15, 9, 26, 12 + extrdi 16, 9, 12, 0 + mtvsrdd 58, 0, 14 + insrdi 16, 10, 14, 38 + mtvsrdd 59, 0, 15 + extrdi 17, 10, 26, 24 + mtvsrdd 60, 0, 16 + extrdi 18, 10, 24, 0 + mtvsrdd 61, 0, 17 + mtvsrdd 62, 0, 18 + + # r1 = r1 * 5, r2 = r2 * 5, r3 = r3 * 5, r4 = r4 * 5 + li 9, 5 + mtvsrdd 36, 0, 9 + vmulouw 0, 27, 4 # v0 = rr0 + vmulouw 1, 28, 4 # v1 = rr1 + vmulouw 2, 29, 4 # v2 = rr2 + vmulouw 3, 30, 4 # v3 = rr3 +.endm + +# +# poly1305_p10le_4blocks( uint8_t *k, uint32_t mlen, uint8_t *m) +# k = 32 bytes key +# r3 = k (r, s) +# r4 = mlen +# r5 = m +# +SYM_FUNC_START(poly1305_p10le_4blocks) +.align 5 + cmpdi 5, 64 + blt Out_no_poly1305 + + SAVE_REGS + + do_poly1305_init + + li 21, 0 # counter to message + + poly1305_setup_r + + # load previous H state + # break/convert r6 to 26 bits + ld 9, 0(3) + ld 10, 8(3) + ld 19, 16(3) + sldi 19, 19, 24 + mtvsrdd 41, 0, 19 + extrdi 14, 9, 26, 38 + extrdi 15, 9, 26, 12 + extrdi 16, 9, 12, 0 + mtvsrdd 36, 0, 14 + insrdi 16, 10, 14, 38 + mtvsrdd 37, 0, 15 + extrdi 17, 10, 26, 24 + mtvsrdd 38, 0, 16 + extrdi 18, 10, 24, 0 + mtvsrdd 39, 0, 17 + mtvsrdd 40, 0, 18 + vor 8, 8, 9 + + # input m1 m2 + add 20, 4, 21 + xxlor 49, 24, 24 + xxlor 50, 25, 25 + lxvw4x 43, 0, 20 + addi 17, 20, 16 + lxvw4x 44, 0, 17 + vperm 14, 11, 12, 17 + vperm 15, 11, 12, 18 + vand 9, 14, 25 # a0 + vsrd 10, 14, 31 # >> 26 + vsrd 11, 10, 31 # 12 bits left + vand 10, 10, 25 # a1 + vspltisb 13, 12 + vand 16, 15, 25 + vsld 12, 16, 13 + vor 11, 11, 12 + vand 11, 11, 25 # a2 + vspltisb 13, 14 + vsrd 12, 15, 13 # >> 14 + vsrd 13, 12, 31 # >> 26, a4 + vand 12, 12, 25 # a3 + + vaddudm 20, 4, 9 + vaddudm 21, 5, 10 + vaddudm 22, 6, 11 + vaddudm 23, 7, 12 + vaddudm 24, 8, 13 + + # m3 m4 + addi 17, 17, 16 + lxvw4x 43, 0, 17 + addi 17, 17, 16 + lxvw4x 44, 0, 17 + vperm 14, 11, 12, 17 + vperm 15, 11, 12, 18 + vand 9, 14, 25 # a0 + vsrd 10, 14, 31 # >> 26 + vsrd 11, 10, 31 # 12 bits left + vand 10, 10, 25 # a1 + vspltisb 13, 12 + vand 16, 15, 25 + vsld 12, 16, 13 + vspltisb 13, 14 + vor 11, 11, 12 + vand 11, 11, 25 # a2 + vsrd 12, 15, 13 # >> 14 + vsrd 13, 12, 31 # >> 26, a4 + vand 12, 12, 25 # a3 + + # Smash 4 message blocks into 5 vectors of [m4, m2, m3, m1] + vmrgow 4, 9, 20 + vmrgow 5, 10, 21 + vmrgow 6, 11, 22 + vmrgow 7, 12, 23 + vmrgow 8, 13, 24 + vaddudm 8, 8, 19 + + addi 5, 5, -64 # len -= 64 + addi 21, 21, 64 # offset += 64 + + li 9, 64 + divdu 31, 5, 9 + + cmpdi 31, 0 + ble Skip_block_loop + + mtctr 31 + +# h4 = m1 * r⁴ + m2 * r³ + m3 * r² + m4 * r +# Rewrite the polynominal sum of product as follows, +# h1 = (h0 + m1) * r^2, h2 = (h0 + m2) * r^2 +# h3 = (h1 + m3) * r^2, h4 = (h2 + m4) * r^2 --> (h0 + m1) r*4 + (h3 + m3) r^2, (h0 + m2) r^4 + (h0 + m4) r^2 +# .... Repeat +# h5 = (h3 + m5) * r^2, h6 = (h4 + m6) * r^2 --> +# h7 = (h5 + m7) * r^2, h8 = (h6 + m8) * r^1 --> m5 * r^4 + m6 * r^3 + m7 * r^2 + m8 * r +# +loop_4blocks: + + # Multiply odd words and even words + mul_odd + mul_even + # carry reduction + vspltisb 9, 2 + vsrd 10, 14, 31 + vsrd 11, 17, 31 + vand 7, 17, 25 + vand 4, 14, 25 + vaddudm 18, 18, 11 + vsrd 12, 18, 31 + vaddudm 15, 15, 10 + + vsrd 11, 15, 31 + vand 8, 18, 25 + vand 5, 15, 25 + vaddudm 4, 4, 12 + vsld 10, 12, 9 + vaddudm 6, 16, 11 + + vsrd 13, 6, 31 + vand 6, 6, 25 + vaddudm 4, 4, 10 + vsrd 10, 4, 31 + vaddudm 7, 7, 13 + + vsrd 11, 7, 31 + vand 7, 7, 25 + vand 4, 4, 25 + vaddudm 5, 5, 10 + vaddudm 8, 8, 11 + + # input m1 m2 m3 m4 + add 20, 4, 21 + xxlor 49, 24, 24 + xxlor 50, 25, 25 + lxvw4x 43, 0, 20 + addi 17, 20, 16 + lxvw4x 44, 0, 17 + vperm 14, 11, 12, 17 + vperm 15, 11, 12, 18 + addi 17, 17, 16 + lxvw4x 43, 0, 17 + addi 17, 17, 16 + lxvw4x 44, 0, 17 + vperm 17, 11, 12, 17 + vperm 18, 11, 12, 18 + + vand 20, 14, 25 # a0 + vand 9, 17, 25 # a0 + vsrd 21, 14, 31 # >> 26 + vsrd 22, 21, 31 # 12 bits left + vsrd 10, 17, 31 # >> 26 + vsrd 11, 10, 31 # 12 bits left + + vand 21, 21, 25 # a1 + vand 10, 10, 25 # a1 + + vspltisb 13, 12 + vand 16, 15, 25 + vsld 23, 16, 13 + vor 22, 22, 23 + vand 22, 22, 25 # a2 + vand 16, 18, 25 + vsld 12, 16, 13 + vor 11, 11, 12 + vand 11, 11, 25 # a2 + vspltisb 13, 14 + vsrd 23, 15, 13 # >> 14 + vsrd 24, 23, 31 # >> 26, a4 + vand 23, 23, 25 # a3 + vsrd 12, 18, 13 # >> 14 + vsrd 13, 12, 31 # >> 26, a4 + vand 12, 12, 25 # a3 + + vaddudm 4, 4, 20 + vaddudm 5, 5, 21 + vaddudm 6, 6, 22 + vaddudm 7, 7, 23 + vaddudm 8, 8, 24 + + # Smash 4 message blocks into 5 vectors of [m4, m2, m3, m1] + vmrgow 4, 9, 4 + vmrgow 5, 10, 5 + vmrgow 6, 11, 6 + vmrgow 7, 12, 7 + vmrgow 8, 13, 8 + vaddudm 8, 8, 19 + + addi 5, 5, -64 # len -= 64 + addi 21, 21, 64 # offset += 64 + + bdnz loop_4blocks + +Skip_block_loop: + xxlor 58, 0, 0 + xxlor 59, 1, 1 + xxlor 60, 2, 2 + xxlor 61, 3, 3 + xxlor 62, 4, 4 + xxlor 32, 5, 5 + xxlor 33, 6, 6 + xxlor 34, 7, 7 + xxlor 35, 8, 8 + + # Multiply odd words and even words + mul_odd + mul_even + + # Sum the products. + xxpermdi 41, 31, 46, 0 + xxpermdi 42, 31, 47, 0 + vaddudm 4, 14, 9 + xxpermdi 36, 31, 36, 3 + vaddudm 5, 15, 10 + xxpermdi 37, 31, 37, 3 + xxpermdi 43, 31, 48, 0 + vaddudm 6, 16, 11 + xxpermdi 38, 31, 38, 3 + xxpermdi 44, 31, 49, 0 + vaddudm 7, 17, 12 + xxpermdi 39, 31, 39, 3 + xxpermdi 45, 31, 50, 0 + vaddudm 8, 18, 13 + xxpermdi 40, 31, 40, 3 + + # carry reduction + vspltisb 9, 2 + vsrd 10, 4, 31 + vsrd 11, 7, 31 + vand 7, 7, 25 + vand 4, 4, 25 + vaddudm 8, 8, 11 + vsrd 12, 8, 31 + vaddudm 5, 5, 10 + + vsrd 11, 5, 31 + vand 8, 8, 25 + vand 5, 5, 25 + vaddudm 4, 4, 12 + vsld 10, 12, 9 + vaddudm 6, 6, 11 + + vsrd 13, 6, 31 + vand 6, 6, 25 + vaddudm 4, 4, 10 + vsrd 10, 4, 31 + vaddudm 7, 7, 13 + + vsrd 11, 7, 31 + vand 7, 7, 25 + vand 4, 4, 25 + vaddudm 5, 5, 10 + vsrd 10, 5, 31 + vand 5, 5, 25 + vaddudm 6, 6, 10 + vaddudm 8, 8, 11 + + b do_final_update + +do_final_update: + # combine 26 bit limbs + # v4, v5, v6, v7 and v8 are 26 bit vectors + vsld 5, 5, 31 + vor 20, 4, 5 + vspltisb 11, 12 + vsrd 12, 6, 11 + vsld 6, 6, 31 + vsld 6, 6, 31 + vor 20, 20, 6 + vspltisb 11, 14 + vsld 7, 7, 11 + vor 21, 7, 12 + mfvsrld 16, 40 # save last 2 bytes + vsld 8, 8, 11 + vsld 8, 8, 31 + vor 21, 21, 8 + mfvsrld 17, 52 + mfvsrld 19, 53 + srdi 16, 16, 24 + + std 17, 0(3) + std 19, 8(3) + stw 16, 16(3) + +Out_loop: + li 3, 0 + + RESTORE_REGS + + blr + +Out_no_poly1305: + li 3, 0 + blr +SYM_FUNC_END(poly1305_p10le_4blocks) + +# +# ======================================================================= +# The following functions implement 64 x 64 bits multiplication poly1305. +# +SYM_FUNC_START_LOCAL(Poly1305_init_64) + # mask 0x0FFFFFFC0FFFFFFC + # mask 0x0FFFFFFC0FFFFFFF + addis 10, 2, rmask@toc@ha + addi 10, 10, rmask@toc@l + ld 11, 0(10) + ld 12, 8(10) + + # initialize + # load key from r3 + ld 9, 24(3) + ld 10, 32(3) + and. 9, 9, 11 # cramp mask r0 + and. 10, 10, 12 # cramp mask r1 + + srdi 21, 10, 2 + add 19, 21, 10 # s1: r19 - (r1 >> 2) *5 + + # setup r and s + li 25, 0 + mtvsrdd 32+0, 9, 19 # r0, s1 + mtvsrdd 32+1, 10, 9 # r1, r0 + mtvsrdd 32+2, 19, 25 # s1 + mtvsrdd 32+3, 9, 25 # r0 + + blr +SYM_FUNC_END(Poly1305_init_64) + +# Poly1305_mult +# v6 = (h0, h1), v8 = h2 +# v0 = (r0, s1), v1 = (r1, r0), v2 = s1, v3 = r0 +# +# Output: v7, v10, v11 +# +SYM_FUNC_START_LOCAL(Poly1305_mult) + # + # d0 = h0 * r0 + h1 * s1 + vmsumudm 7, 6, 0, 9 # h0 * r0, h1 * s1 + + # d1 = h0 * r1 + h1 * r0 + h2 * s1 + vmsumudm 11, 6, 1, 9 # h0 * r1, h1 * r0 + vmsumudm 10, 8, 2, 11 # d1 += h2 * s1 + + # d2 = r0 + vmsumudm 11, 8, 3, 9 # d2 = h2 * r0 + blr +SYM_FUNC_END(Poly1305_mult) + +# +# carry reduction +# h %=p +# +# Input: v7, v10, v11 +# Output: r27, r28, r29 +# +SYM_FUNC_START_LOCAL(Carry_reduction) + mfvsrld 27, 32+7 + mfvsrld 28, 32+10 + mfvsrld 29, 32+11 + mfvsrd 20, 32+7 # h0.h + mfvsrd 21, 32+10 # h1.h + + addc 28, 28, 20 + adde 29, 29, 21 + srdi 22, 29, 0x2 + sldi 23, 22, 0x2 + add 23, 23, 22 # (h2 & 3) * 5 + addc 27, 27, 23 # h0 + addze 28, 28 # h1 + andi. 29, 29, 0x3 # h2 + blr +SYM_FUNC_END(Carry_reduction) + +# +# poly1305 multiplication +# h *= r, h %= p +# d0 = h0 * r0 + h1 * s1 +# d1 = h0 * r1 + h1 * r0 + h2 * s1 +# d2 = h0 * r0 +# +# +# unsigned int poly1305_test_64s(unisgned char *state, const byte *src, size_t len, highbit) +# - no highbit if final leftover block (highbit = 0) +# +SYM_FUNC_START(poly1305_64s) + cmpdi 5, 0 + ble Out_no_poly1305_64 + + mflr 0 + std 0, 16(1) + stdu 1,-400(1) + + SAVE_GPR 14, 112, 1 + SAVE_GPR 15, 120, 1 + SAVE_GPR 16, 128, 1 + SAVE_GPR 17, 136, 1 + SAVE_GPR 18, 144, 1 + SAVE_GPR 19, 152, 1 + SAVE_GPR 20, 160, 1 + SAVE_GPR 21, 168, 1 + SAVE_GPR 22, 176, 1 + SAVE_GPR 23, 184, 1 + SAVE_GPR 24, 192, 1 + SAVE_GPR 25, 200, 1 + SAVE_GPR 26, 208, 1 + SAVE_GPR 27, 216, 1 + SAVE_GPR 28, 224, 1 + SAVE_GPR 29, 232, 1 + SAVE_GPR 30, 240, 1 + SAVE_GPR 31, 248, 1 + + # Init poly1305 + bl Poly1305_init_64 + + li 25, 0 # offset to inp and outp + + add 11, 25, 4 + + # load h + # h0, h1, h2? + ld 27, 0(3) + ld 28, 8(3) + lwz 29, 16(3) + + li 30, 16 + divdu 31, 5, 30 + + mtctr 31 + + mr 24, 6 # highbit + +Loop_block_64: + vxor 9, 9, 9 + + ld 20, 0(11) + ld 21, 8(11) + addi 11, 11, 16 + + addc 27, 27, 20 + adde 28, 28, 21 + adde 29, 29, 24 + + li 22, 0 + mtvsrdd 32+6, 27, 28 # h0, h1 + mtvsrdd 32+8, 29, 22 # h2 + + bl Poly1305_mult + + bl Carry_reduction + + bdnz Loop_block_64 + + std 27, 0(3) + std 28, 8(3) + stw 29, 16(3) + + li 3, 0 + + RESTORE_GPR 14, 112, 1 + RESTORE_GPR 15, 120, 1 + RESTORE_GPR 16, 128, 1 + RESTORE_GPR 17, 136, 1 + RESTORE_GPR 18, 144, 1 + RESTORE_GPR 19, 152, 1 + RESTORE_GPR 20, 160, 1 + RESTORE_GPR 21, 168, 1 + RESTORE_GPR 22, 176, 1 + RESTORE_GPR 23, 184, 1 + RESTORE_GPR 24, 192, 1 + RESTORE_GPR 25, 200, 1 + RESTORE_GPR 26, 208, 1 + RESTORE_GPR 27, 216, 1 + RESTORE_GPR 28, 224, 1 + RESTORE_GPR 29, 232, 1 + RESTORE_GPR 30, 240, 1 + RESTORE_GPR 31, 248, 1 + + addi 1, 1, 400 + ld 0, 16(1) + mtlr 0 + + blr + +Out_no_poly1305_64: + li 3, 0 + blr +SYM_FUNC_END(poly1305_64s) + +# +# Input: r3 = h, r4 = s, r5 = mac +# mac = h + s +# +SYM_FUNC_START(poly1305_emit_64) + ld 10, 0(3) + ld 11, 8(3) + ld 12, 16(3) + + # compare modulus + # h + 5 + (-p) + mr 6, 10 + mr 7, 11 + mr 8, 12 + addic. 6, 6, 5 + addze 7, 7 + addze 8, 8 + srdi 9, 8, 2 # overflow? + cmpdi 9, 0 + beq Skip_h64 + mr 10, 6 + mr 11, 7 + mr 12, 8 + +Skip_h64: + ld 6, 0(4) + ld 7, 8(4) + addc 10, 10, 6 + adde 11, 11, 7 + addze 12, 12 + + std 10, 0(5) + std 11, 8(5) + blr +SYM_FUNC_END(poly1305_emit_64) + +SYM_DATA_START_LOCAL(RMASK) +.align 5 +rmask: +.byte 0xff, 0xff, 0xff, 0x0f, 0xfc, 0xff, 0xff, 0x0f, 0xfc, 0xff, 0xff, 0x0f, 0xfc, 0xff, 0xff, 0x0f +cnum: +.long 0x03ffffff, 0x00000000, 0x03ffffff, 0x00000000 +.long 0x1a, 0x00, 0x1a, 0x00 +.long 0x01000000, 0x01000000, 0x01000000, 0x01000000 +.long 0x00010203, 0x04050607, 0x10111213, 0x14151617 +.long 0x08090a0b, 0x0c0d0e0f, 0x18191a1b, 0x1c1d1e1f +SYM_DATA_END(RMASK) diff --git a/arch/powerpc/include/asm/8xx_immap.h b/arch/powerpc/include/asm/8xx_immap.h index bdf0563ba423..f9cac46a95cb 100644 --- a/arch/powerpc/include/asm/8xx_immap.h +++ b/arch/powerpc/include/asm/8xx_immap.h @@ -560,5 +560,7 @@ typedef struct immap { cpm8xx_t im_cpm; /* Communication processor */ } immap_t; +extern immap_t __iomem *mpc8xx_immr; + #endif /* __IMMAP_8XX__ */ #endif /* __KERNEL__ */ diff --git a/arch/powerpc/include/asm/Kbuild b/arch/powerpc/include/asm/Kbuild index 419319c4963c..61a8d5555cd7 100644 --- a/arch/powerpc/include/asm/Kbuild +++ b/arch/powerpc/include/asm/Kbuild @@ -3,7 +3,6 @@ generated-y += syscall_table_32.h generated-y += syscall_table_64.h generated-y += syscall_table_spu.h generic-y += agp.h -generic-y += export.h generic-y += kvm_types.h generic-y += mcs_spinlock.h generic-y += qrwlock.h diff --git a/arch/powerpc/include/asm/book3s/32/kup.h b/arch/powerpc/include/asm/book3s/32/kup.h index 678f9c9d89b6..4e14a5427a63 100644 --- a/arch/powerpc/include/asm/book3s/32/kup.h +++ b/arch/powerpc/include/asm/book3s/32/kup.h @@ -9,79 +9,53 @@ #ifndef __ASSEMBLY__ -#include <linux/jump_label.h> - -extern struct static_key_false disable_kuap_key; - -static __always_inline bool kuep_is_disabled(void) -{ - return !IS_ENABLED(CONFIG_PPC_KUEP); -} - #ifdef CONFIG_PPC_KUAP #include <linux/sched.h> #define KUAP_NONE (~0UL) -#define KUAP_ALL (~1UL) -static __always_inline bool kuap_is_disabled(void) -{ - return static_branch_unlikely(&disable_kuap_key); -} - -static inline void kuap_lock_one(unsigned long addr) +static __always_inline void kuap_lock_one(unsigned long addr) { mtsr(mfsr(addr) | SR_KS, addr); isync(); /* Context sync required after mtsr() */ } -static inline void kuap_unlock_one(unsigned long addr) +static __always_inline void kuap_unlock_one(unsigned long addr) { mtsr(mfsr(addr) & ~SR_KS, addr); isync(); /* Context sync required after mtsr() */ } -static inline void kuap_lock_all(void) +static __always_inline void uaccess_begin_32s(unsigned long addr) { - update_user_segments(mfsr(0) | SR_KS); - isync(); /* Context sync required after mtsr() */ -} + unsigned long tmp; -static inline void kuap_unlock_all(void) -{ - update_user_segments(mfsr(0) & ~SR_KS); - isync(); /* Context sync required after mtsr() */ + asm volatile(ASM_MMU_FTR_IFSET( + "mfsrin %0, %1;" + "rlwinm %0, %0, 0, %2;" + "mtsrin %0, %1;" + "isync", "", %3) + : "=&r"(tmp) + : "r"(addr), "i"(~SR_KS), "i"(MMU_FTR_KUAP) + : "memory"); } -void kuap_lock_all_ool(void); -void kuap_unlock_all_ool(void); - -static inline void kuap_lock_addr(unsigned long addr, bool ool) +static __always_inline void uaccess_end_32s(unsigned long addr) { - if (likely(addr != KUAP_ALL)) - kuap_lock_one(addr); - else if (!ool) - kuap_lock_all(); - else - kuap_lock_all_ool(); -} + unsigned long tmp; -static inline void kuap_unlock(unsigned long addr, bool ool) -{ - if (likely(addr != KUAP_ALL)) - kuap_unlock_one(addr); - else if (!ool) - kuap_unlock_all(); - else - kuap_unlock_all_ool(); + asm volatile(ASM_MMU_FTR_IFSET( + "mfsrin %0, %1;" + "oris %0, %0, %2;" + "mtsrin %0, %1;" + "isync", "", %3) + : "=&r"(tmp) + : "r"(addr), "i"(SR_KS >> 16), "i"(MMU_FTR_KUAP) + : "memory"); } -static inline void __kuap_lock(void) -{ -} - -static inline void __kuap_save_and_lock(struct pt_regs *regs) +static __always_inline void __kuap_save_and_lock(struct pt_regs *regs) { unsigned long kuap = current->thread.kuap; @@ -90,18 +64,19 @@ static inline void __kuap_save_and_lock(struct pt_regs *regs) return; current->thread.kuap = KUAP_NONE; - kuap_lock_addr(kuap, false); + kuap_lock_one(kuap); } +#define __kuap_save_and_lock __kuap_save_and_lock -static inline void kuap_user_restore(struct pt_regs *regs) +static __always_inline void kuap_user_restore(struct pt_regs *regs) { } -static inline void __kuap_kernel_restore(struct pt_regs *regs, unsigned long kuap) +static __always_inline void __kuap_kernel_restore(struct pt_regs *regs, unsigned long kuap) { if (unlikely(kuap != KUAP_NONE)) { current->thread.kuap = KUAP_NONE; - kuap_lock_addr(kuap, false); + kuap_lock_one(kuap); } if (likely(regs->kuap == KUAP_NONE)) @@ -109,10 +84,10 @@ static inline void __kuap_kernel_restore(struct pt_regs *regs, unsigned long kua current->thread.kuap = regs->kuap; - kuap_unlock(regs->kuap, false); + kuap_unlock_one(regs->kuap); } -static inline unsigned long __kuap_get_and_assert_locked(void) +static __always_inline unsigned long __kuap_get_and_assert_locked(void) { unsigned long kuap = current->thread.kuap; @@ -120,9 +95,10 @@ static inline unsigned long __kuap_get_and_assert_locked(void) return kuap; } +#define __kuap_get_and_assert_locked __kuap_get_and_assert_locked -static __always_inline void __allow_user_access(void __user *to, const void __user *from, - u32 size, unsigned long dir) +static __always_inline void allow_user_access(void __user *to, const void __user *from, + u32 size, unsigned long dir) { BUILD_BUG_ON(!__builtin_constant_p(dir)); @@ -130,10 +106,10 @@ static __always_inline void __allow_user_access(void __user *to, const void __us return; current->thread.kuap = (__force u32)to; - kuap_unlock_one((__force u32)to); + uaccess_begin_32s((__force u32)to); } -static __always_inline void __prevent_user_access(unsigned long dir) +static __always_inline void prevent_user_access(unsigned long dir) { u32 kuap = current->thread.kuap; @@ -143,42 +119,51 @@ static __always_inline void __prevent_user_access(unsigned long dir) return; current->thread.kuap = KUAP_NONE; - kuap_lock_addr(kuap, true); + uaccess_end_32s(kuap); } -static inline unsigned long __prevent_user_access_return(void) +static __always_inline unsigned long prevent_user_access_return(void) { unsigned long flags = current->thread.kuap; if (flags != KUAP_NONE) { current->thread.kuap = KUAP_NONE; - kuap_lock_addr(flags, true); + uaccess_end_32s(flags); } return flags; } -static inline void __restore_user_access(unsigned long flags) +static __always_inline void restore_user_access(unsigned long flags) { if (flags != KUAP_NONE) { current->thread.kuap = flags; - kuap_unlock(flags, true); + uaccess_begin_32s(flags); } } -static inline bool +static __always_inline bool __bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write) { unsigned long kuap = regs->kuap; - if (!is_write || kuap == KUAP_ALL) + if (!is_write) return false; if (kuap == KUAP_NONE) return true; - /* If faulting address doesn't match unlocked segment, unlock all */ - if ((kuap ^ address) & 0xf0000000) - regs->kuap = KUAP_ALL; + /* + * If faulting address doesn't match unlocked segment, change segment. + * In case of unaligned store crossing two segments, emulate store. + */ + if ((kuap ^ address) & 0xf0000000) { + if (!(kuap & 0x0fffffff) && address > kuap - 4 && fix_alignment(regs)) { + regs_add_return_ip(regs, 4); + emulate_single_step(regs); + } else { + regs->kuap = address; + } + } return false; } diff --git a/arch/powerpc/include/asm/book3s/32/pgtable.h b/arch/powerpc/include/asm/book3s/32/pgtable.h index 7bf1fe7297c6..9b13eb14e21b 100644 --- a/arch/powerpc/include/asm/book3s/32/pgtable.h +++ b/arch/powerpc/include/asm/book3s/32/pgtable.h @@ -462,11 +462,6 @@ static inline pte_t pfn_pte(unsigned long pfn, pgprot_t pgprot) pgprot_val(pgprot)); } -static inline unsigned long pte_pfn(pte_t pte) -{ - return pte_val(pte) >> PTE_RPN_SHIFT; -} - /* Generic modifiers for PTE bits */ static inline pte_t pte_wrprotect(pte_t pte) { @@ -498,7 +493,7 @@ static inline pte_t pte_mkpte(pte_t pte) return pte; } -static inline pte_t pte_mkwrite(pte_t pte) +static inline pte_t pte_mkwrite_novma(pte_t pte) { return __pte(pte_val(pte) | _PAGE_RW); } @@ -541,58 +536,43 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) /* This low level function performs the actual PTE insertion - * Setting the PTE depends on the MMU type and other factors. It's - * an horrible mess that I'm not going to try to clean up now but - * I'm keeping it in one place rather than spread around + * Setting the PTE depends on the MMU type and other factors. + * + * First case is 32-bit in UP mode with 32-bit PTEs, we need to preserve + * the _PAGE_HASHPTE bit since we may not have invalidated the previous + * translation in the hash yet (done in a subsequent flush_tlb_xxx()) + * and see we need to keep track that this PTE needs invalidating. + * + * Second case is 32-bit with 64-bit PTE. In this case, we + * can just store as long as we do the two halves in the right order + * with a barrier in between. This is possible because we take care, + * in the hash code, to pre-invalidate if the PTE was already hashed, + * which synchronizes us with any concurrent invalidation. + * In the percpu case, we fallback to the simple update preserving + * the hash bits (ie, same as the non-SMP case). + * + * Third case is 32-bit in SMP mode with 32-bit PTEs. We use the + * helper pte_update() which does an atomic update. We need to do that + * because a concurrent invalidation can clear _PAGE_HASHPTE. If it's a + * per-CPU PTE such as a kmap_atomic, we also do a simple update preserving + * the hash bits instead. */ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte, int percpu) { -#if defined(CONFIG_SMP) && !defined(CONFIG_PTE_64BIT) - /* First case is 32-bit Hash MMU in SMP mode with 32-bit PTEs. We use the - * helper pte_update() which does an atomic update. We need to do that - * because a concurrent invalidation can clear _PAGE_HASHPTE. If it's a - * per-CPU PTE such as a kmap_atomic, we do a simple update preserving - * the hash bits instead (ie, same as the non-SMP case) - */ - if (percpu) - *ptep = __pte((pte_val(*ptep) & _PAGE_HASHPTE) - | (pte_val(pte) & ~_PAGE_HASHPTE)); - else - pte_update(mm, addr, ptep, ~_PAGE_HASHPTE, pte_val(pte), 0); + if ((!IS_ENABLED(CONFIG_SMP) && !IS_ENABLED(CONFIG_PTE_64BIT)) || percpu) { + *ptep = __pte((pte_val(*ptep) & _PAGE_HASHPTE) | + (pte_val(pte) & ~_PAGE_HASHPTE)); + } else if (IS_ENABLED(CONFIG_PTE_64BIT)) { + if (pte_val(*ptep) & _PAGE_HASHPTE) + flush_hash_entry(mm, ptep, addr); -#elif defined(CONFIG_PTE_64BIT) - /* Second case is 32-bit with 64-bit PTE. In this case, we - * can just store as long as we do the two halves in the right order - * with a barrier in between. This is possible because we take care, - * in the hash code, to pre-invalidate if the PTE was already hashed, - * which synchronizes us with any concurrent invalidation. - * In the percpu case, we also fallback to the simple update preserving - * the hash bits - */ - if (percpu) { - *ptep = __pte((pte_val(*ptep) & _PAGE_HASHPTE) - | (pte_val(pte) & ~_PAGE_HASHPTE)); - return; + asm volatile("stw%X0 %2,%0; eieio; stw%X1 %L2,%1" : + "=m" (*ptep), "=m" (*((unsigned char *)ptep+4)) : + "r" (pte) : "memory"); + } else { + pte_update(mm, addr, ptep, ~_PAGE_HASHPTE, pte_val(pte), 0); } - if (pte_val(*ptep) & _PAGE_HASHPTE) - flush_hash_entry(mm, ptep, addr); - __asm__ __volatile__("\ - stw%X0 %2,%0\n\ - eieio\n\ - stw%X1 %L2,%1" - : "=m" (*ptep), "=m" (*((unsigned char *)ptep+4)) - : "r" (pte) : "memory"); - -#else - /* Third case is 32-bit hash table in UP mode, we need to preserve - * the _PAGE_HASHPTE bit since we may not have invalidated the previous - * translation in the hash yet (done in a subsequent flush_tlb_xxx()) - * and see we need to keep track that this PTE needs invalidating - */ - *ptep = __pte((pte_val(*ptep) & _PAGE_HASHPTE) - | (pte_val(pte) & ~_PAGE_HASHPTE)); -#endif } /* diff --git a/arch/powerpc/include/asm/book3s/64/hash-pkey.h b/arch/powerpc/include/asm/book3s/64/hash-pkey.h index f1e60d579f6c..6c5564c4fae4 100644 --- a/arch/powerpc/include/asm/book3s/64/hash-pkey.h +++ b/arch/powerpc/include/asm/book3s/64/hash-pkey.h @@ -24,7 +24,7 @@ static inline u64 pte_to_hpte_pkey_bits(u64 pteflags, unsigned long flags) ((pteflags & H_PTE_PKEY_BIT1) ? HPTE_R_KEY_BIT1 : 0x0UL) | ((pteflags & H_PTE_PKEY_BIT0) ? HPTE_R_KEY_BIT0 : 0x0UL)); - if (mmu_has_feature(MMU_FTR_BOOK3S_KUAP) || + if (mmu_has_feature(MMU_FTR_KUAP) || mmu_has_feature(MMU_FTR_BOOK3S_KUEP)) { if ((pte_pkey == 0) && (flags & HPTE_USE_KERNEL_KEY)) return HASH_DEFAULT_KERNEL_KEY; diff --git a/arch/powerpc/include/asm/book3s/64/hash.h b/arch/powerpc/include/asm/book3s/64/hash.h index d4a19e6547ac..6e70ae511631 100644 --- a/arch/powerpc/include/asm/book3s/64/hash.h +++ b/arch/powerpc/include/asm/book3s/64/hash.h @@ -138,7 +138,16 @@ static inline int hash__pmd_same(pmd_t pmd_a, pmd_t pmd_b) } #define hash__pmd_bad(pmd) (pmd_val(pmd) & H_PMD_BAD_BITS) + +/* + * pud comparison that will work with both pte and page table pointer. + */ +static inline int hash__pud_same(pud_t pud_a, pud_t pud_b) +{ + return (((pud_raw(pud_a) ^ pud_raw(pud_b)) & ~cpu_to_be64(_PAGE_HPTEFLAGS)) == 0); +} #define hash__pud_bad(pud) (pud_val(pud) & H_PUD_BAD_BITS) + static inline int hash__p4d_bad(p4d_t p4d) { return (p4d_val(p4d) == 0); diff --git a/arch/powerpc/include/asm/book3s/64/kup.h b/arch/powerpc/include/asm/book3s/64/kup.h index 84c09e546115..497a7bd31ecc 100644 --- a/arch/powerpc/include/asm/book3s/64/kup.h +++ b/arch/powerpc/include/asm/book3s/64/kup.h @@ -31,7 +31,7 @@ mfspr \gpr2, SPRN_AMR cmpd \gpr1, \gpr2 beq 99f - END_MMU_FTR_SECTION_NESTED_IFCLR(MMU_FTR_BOOK3S_KUAP, 68) + END_MMU_FTR_SECTION_NESTED_IFCLR(MMU_FTR_KUAP, 68) isync mtspr SPRN_AMR, \gpr1 @@ -78,7 +78,7 @@ * No need to restore IAMR when returning to kernel space. */ 100: - END_MMU_FTR_SECTION_NESTED_IFSET(MMU_FTR_BOOK3S_KUAP, 67) + END_MMU_FTR_SECTION_NESTED_IFSET(MMU_FTR_KUAP, 67) #endif .endm @@ -91,7 +91,7 @@ LOAD_REG_IMMEDIATE(\gpr2, AMR_KUAP_BLOCKED) 999: tdne \gpr1, \gpr2 EMIT_WARN_ENTRY 999b, __FILE__, __LINE__, (BUGFLAG_WARNING | BUGFLAG_ONCE) - END_MMU_FTR_SECTION_NESTED_IFSET(MMU_FTR_BOOK3S_KUAP, 67) + END_MMU_FTR_SECTION_NESTED_IFSET(MMU_FTR_KUAP, 67) #endif .endm #endif @@ -130,7 +130,7 @@ */ BEGIN_MMU_FTR_SECTION_NESTED(68) b 100f // skip_save_amr - END_MMU_FTR_SECTION_NESTED_IFCLR(MMU_FTR_PKEY | MMU_FTR_BOOK3S_KUAP, 68) + END_MMU_FTR_SECTION_NESTED_IFCLR(MMU_FTR_PKEY | MMU_FTR_KUAP, 68) /* * if pkey is disabled and we are entering from userspace @@ -166,7 +166,7 @@ mtspr SPRN_AMR, \gpr2 isync 102: - END_MMU_FTR_SECTION_NESTED_IFSET(MMU_FTR_BOOK3S_KUAP, 69) + END_MMU_FTR_SECTION_NESTED_IFSET(MMU_FTR_KUAP, 69) /* * if entering from kernel we don't need save IAMR @@ -213,14 +213,14 @@ extern u64 __ro_after_init default_iamr; * access restrictions. Because of this ignore AMR value when accessing * userspace via kernel thread. */ -static inline u64 current_thread_amr(void) +static __always_inline u64 current_thread_amr(void) { if (current->thread.regs) return current->thread.regs->amr; return default_amr; } -static inline u64 current_thread_iamr(void) +static __always_inline u64 current_thread_iamr(void) { if (current->thread.regs) return current->thread.regs->iamr; @@ -230,12 +230,7 @@ static inline u64 current_thread_iamr(void) #ifdef CONFIG_PPC_KUAP -static __always_inline bool kuap_is_disabled(void) -{ - return !mmu_has_feature(MMU_FTR_BOOK3S_KUAP); -} - -static inline void kuap_user_restore(struct pt_regs *regs) +static __always_inline void kuap_user_restore(struct pt_regs *regs) { bool restore_amr = false, restore_iamr = false; unsigned long amr, iamr; @@ -243,7 +238,7 @@ static inline void kuap_user_restore(struct pt_regs *regs) if (!mmu_has_feature(MMU_FTR_PKEY)) return; - if (!mmu_has_feature(MMU_FTR_BOOK3S_KUAP)) { + if (!mmu_has_feature(MMU_FTR_KUAP)) { amr = mfspr(SPRN_AMR); if (amr != regs->amr) restore_amr = true; @@ -274,7 +269,7 @@ static inline void kuap_user_restore(struct pt_regs *regs) */ } -static inline void __kuap_kernel_restore(struct pt_regs *regs, unsigned long amr) +static __always_inline void __kuap_kernel_restore(struct pt_regs *regs, unsigned long amr) { if (likely(regs->amr == amr)) return; @@ -290,7 +285,7 @@ static inline void __kuap_kernel_restore(struct pt_regs *regs, unsigned long amr */ } -static inline unsigned long __kuap_get_and_assert_locked(void) +static __always_inline unsigned long __kuap_get_and_assert_locked(void) { unsigned long amr = mfspr(SPRN_AMR); @@ -298,22 +293,16 @@ static inline unsigned long __kuap_get_and_assert_locked(void) WARN_ON_ONCE(amr != AMR_KUAP_BLOCKED); return amr; } +#define __kuap_get_and_assert_locked __kuap_get_and_assert_locked -/* Do nothing, book3s/64 does that in ASM */ -static inline void __kuap_lock(void) -{ -} - -static inline void __kuap_save_and_lock(struct pt_regs *regs) -{ -} +/* __kuap_lock() not required, book3s/64 does that in ASM */ /* * We support individually allowing read or write, but we don't support nesting * because that would require an expensive read/modify write of the AMR. */ -static inline unsigned long get_kuap(void) +static __always_inline unsigned long get_kuap(void) { /* * We return AMR_KUAP_BLOCKED when we don't support KUAP because @@ -323,7 +312,7 @@ static inline unsigned long get_kuap(void) * This has no effect in terms of actually blocking things on hash, * so it doesn't break anything. */ - if (!mmu_has_feature(MMU_FTR_BOOK3S_KUAP)) + if (!mmu_has_feature(MMU_FTR_KUAP)) return AMR_KUAP_BLOCKED; return mfspr(SPRN_AMR); @@ -331,7 +320,7 @@ static inline unsigned long get_kuap(void) static __always_inline void set_kuap(unsigned long value) { - if (!mmu_has_feature(MMU_FTR_BOOK3S_KUAP)) + if (!mmu_has_feature(MMU_FTR_KUAP)) return; /* @@ -343,7 +332,8 @@ static __always_inline void set_kuap(unsigned long value) isync(); } -static inline bool __bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write) +static __always_inline bool +__bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write) { /* * For radix this will be a storage protection fault (DSISR_PROTFAULT). @@ -386,12 +376,12 @@ static __always_inline void allow_user_access(void __user *to, const void __user #else /* CONFIG_PPC_KUAP */ -static inline unsigned long get_kuap(void) +static __always_inline unsigned long get_kuap(void) { return AMR_KUAP_BLOCKED; } -static inline void set_kuap(unsigned long value) { } +static __always_inline void set_kuap(unsigned long value) { } static __always_inline void allow_user_access(void __user *to, const void __user *from, unsigned long size, unsigned long dir) @@ -406,7 +396,7 @@ static __always_inline void prevent_user_access(unsigned long dir) do_uaccess_flush(); } -static inline unsigned long prevent_user_access_return(void) +static __always_inline unsigned long prevent_user_access_return(void) { unsigned long flags = get_kuap(); @@ -417,7 +407,7 @@ static inline unsigned long prevent_user_access_return(void) return flags; } -static inline void restore_user_access(unsigned long flags) +static __always_inline void restore_user_access(unsigned long flags) { set_kuap(flags); if (static_branch_unlikely(&uaccess_flush_key) && flags == AMR_KUAP_BLOCKED) diff --git a/arch/powerpc/include/asm/book3s/64/mmu.h b/arch/powerpc/include/asm/book3s/64/mmu.h index 570a4960cf17..fedbc5d38191 100644 --- a/arch/powerpc/include/asm/book3s/64/mmu.h +++ b/arch/powerpc/include/asm/book3s/64/mmu.h @@ -71,10 +71,7 @@ extern unsigned int mmu_pid_bits; /* Base PID to allocate from */ extern unsigned int mmu_base_pid; -/* - * memory block size used with radix translation. - */ -extern unsigned long __ro_after_init radix_mem_block_size; +extern unsigned long __ro_after_init memory_block_size; #define PRTB_SIZE_SHIFT (mmu_pid_bits + 4) #define PRTB_ENTRIES (1ul << mmu_pid_bits) @@ -261,7 +258,7 @@ static inline void radix_init_pseries(void) { } #define arch_clear_mm_cpumask_cpu(cpu, mm) \ do { \ if (cpumask_test_cpu(cpu, mm_cpumask(mm))) { \ - atomic_dec(&(mm)->context.active_cpus); \ + dec_mm_active_cpus(mm); \ cpumask_clear_cpu(cpu, mm_cpumask(mm)); \ } \ } while (0) diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index 4acc9690f599..5c497c862d75 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -104,6 +104,7 @@ * and every thing below PAGE_SHIFT; */ #define PTE_RPN_MASK (((1UL << _PAGE_PA_MAX) - 1) & (PAGE_MASK)) +#define PTE_RPN_SHIFT PAGE_SHIFT /* * set of bits not changed in pmd_modify. Even though we have hash specific bits * in here, on radix we expect them to be zero. @@ -569,11 +570,6 @@ static inline pte_t pfn_pte(unsigned long pfn, pgprot_t pgprot) return __pte(((pte_basic_t)pfn << PAGE_SHIFT) | pgprot_val(pgprot) | _PAGE_PTE); } -static inline unsigned long pte_pfn(pte_t pte) -{ - return (pte_val(pte) & PTE_RPN_MASK) >> PAGE_SHIFT; -} - /* Generic modifiers for PTE bits */ static inline pte_t pte_wrprotect(pte_t pte) { @@ -600,7 +596,7 @@ static inline pte_t pte_mkexec(pte_t pte) return __pte_raw(pte_raw(pte) | cpu_to_be64(_PAGE_EXEC)); } -static inline pte_t pte_mkwrite(pte_t pte) +static inline pte_t pte_mkwrite_novma(pte_t pte) { /* * write implies read, hence set both @@ -921,8 +917,29 @@ static inline pud_t pte_pud(pte_t pte) { return __pud_raw(pte_raw(pte)); } + +static inline pte_t *pudp_ptep(pud_t *pud) +{ + return (pte_t *)pud; +} + +#define pud_pfn(pud) pte_pfn(pud_pte(pud)) +#define pud_dirty(pud) pte_dirty(pud_pte(pud)) +#define pud_young(pud) pte_young(pud_pte(pud)) +#define pud_mkold(pud) pte_pud(pte_mkold(pud_pte(pud))) +#define pud_wrprotect(pud) pte_pud(pte_wrprotect(pud_pte(pud))) +#define pud_mkdirty(pud) pte_pud(pte_mkdirty(pud_pte(pud))) +#define pud_mkclean(pud) pte_pud(pte_mkclean(pud_pte(pud))) +#define pud_mkyoung(pud) pte_pud(pte_mkyoung(pud_pte(pud))) +#define pud_mkwrite(pud) pte_pud(pte_mkwrite_novma(pud_pte(pud))) #define pud_write(pud) pte_write(pud_pte(pud)) +#ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY +#define pud_soft_dirty(pmd) pte_soft_dirty(pud_pte(pud)) +#define pud_mksoft_dirty(pmd) pte_pud(pte_mksoft_dirty(pud_pte(pud))) +#define pud_clear_soft_dirty(pmd) pte_pud(pte_clear_soft_dirty(pud_pte(pud))) +#endif /* CONFIG_HAVE_ARCH_SOFT_DIRTY */ + static inline int pud_bad(pud_t pud) { if (radix_enabled()) @@ -1071,7 +1088,7 @@ static inline pte_t *pmdp_ptep(pmd_t *pmd) #define pmd_mkdirty(pmd) pte_pmd(pte_mkdirty(pmd_pte(pmd))) #define pmd_mkclean(pmd) pte_pmd(pte_mkclean(pmd_pte(pmd))) #define pmd_mkyoung(pmd) pte_pmd(pte_mkyoung(pmd_pte(pmd))) -#define pmd_mkwrite(pmd) pte_pmd(pte_mkwrite(pmd_pte(pmd))) +#define pmd_mkwrite_novma(pmd) pte_pmd(pte_mkwrite_novma(pmd_pte(pmd))) #ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY #define pmd_soft_dirty(pmd) pte_soft_dirty(pmd_pte(pmd)) @@ -1115,15 +1132,24 @@ static inline bool pmd_access_permitted(pmd_t pmd, bool write) #ifdef CONFIG_TRANSPARENT_HUGEPAGE extern pmd_t pfn_pmd(unsigned long pfn, pgprot_t pgprot); +extern pud_t pfn_pud(unsigned long pfn, pgprot_t pgprot); extern pmd_t mk_pmd(struct page *page, pgprot_t pgprot); extern pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot); extern void set_pmd_at(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, pmd_t pmd); +extern void set_pud_at(struct mm_struct *mm, unsigned long addr, + pud_t *pudp, pud_t pud); + static inline void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd) { } +static inline void update_mmu_cache_pud(struct vm_area_struct *vma, + unsigned long addr, pud_t *pud) +{ +} + extern int hash__has_transparent_hugepage(void); static inline int has_transparent_hugepage(void) { @@ -1133,6 +1159,14 @@ static inline int has_transparent_hugepage(void) } #define has_transparent_hugepage has_transparent_hugepage +static inline int has_transparent_pud_hugepage(void) +{ + if (radix_enabled()) + return radix__has_transparent_pud_hugepage(); + return 0; +} +#define has_transparent_pud_hugepage has_transparent_pud_hugepage + static inline unsigned long pmd_hugepage_update(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, unsigned long clr, unsigned long set) @@ -1142,6 +1176,16 @@ pmd_hugepage_update(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, return hash__pmd_hugepage_update(mm, addr, pmdp, clr, set); } +static inline unsigned long +pud_hugepage_update(struct mm_struct *mm, unsigned long addr, pud_t *pudp, + unsigned long clr, unsigned long set) +{ + if (radix_enabled()) + return radix__pud_hugepage_update(mm, addr, pudp, clr, set); + BUG(); + return pud_val(*pudp); +} + /* * returns true for pmd migration entries, THP, devmap, hugetlb * But compile time dependent on THP config @@ -1151,6 +1195,11 @@ static inline int pmd_large(pmd_t pmd) return !!(pmd_raw(pmd) & cpu_to_be64(_PAGE_PTE)); } +static inline int pud_large(pud_t pud) +{ + return !!(pud_raw(pud) & cpu_to_be64(_PAGE_PTE)); +} + /* * For radix we should always find H_PAGE_HASHPTE zero. Hence * the below will work for radix too @@ -1166,6 +1215,17 @@ static inline int __pmdp_test_and_clear_young(struct mm_struct *mm, return ((old & _PAGE_ACCESSED) != 0); } +static inline int __pudp_test_and_clear_young(struct mm_struct *mm, + unsigned long addr, pud_t *pudp) +{ + unsigned long old; + + if ((pud_raw(*pudp) & cpu_to_be64(_PAGE_ACCESSED | H_PAGE_HASHPTE)) == 0) + return 0; + old = pud_hugepage_update(mm, addr, pudp, _PAGE_ACCESSED, 0); + return ((old & _PAGE_ACCESSED) != 0); +} + #define __HAVE_ARCH_PMDP_SET_WRPROTECT static inline void pmdp_set_wrprotect(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp) @@ -1174,6 +1234,14 @@ static inline void pmdp_set_wrprotect(struct mm_struct *mm, unsigned long addr, pmd_hugepage_update(mm, addr, pmdp, _PAGE_WRITE, 0); } +#define __HAVE_ARCH_PUDP_SET_WRPROTECT +static inline void pudp_set_wrprotect(struct mm_struct *mm, unsigned long addr, + pud_t *pudp) +{ + if (pud_write(*pudp)) + pud_hugepage_update(mm, addr, pudp, _PAGE_WRITE, 0); +} + /* * Only returns true for a THP. False for pmd migration entry. * We also need to return true when we come across a pte that @@ -1195,6 +1263,17 @@ static inline int pmd_trans_huge(pmd_t pmd) return hash__pmd_trans_huge(pmd); } +static inline int pud_trans_huge(pud_t pud) +{ + if (!pud_present(pud)) + return false; + + if (radix_enabled()) + return radix__pud_trans_huge(pud); + return 0; +} + + #define __HAVE_ARCH_PMD_SAME static inline int pmd_same(pmd_t pmd_a, pmd_t pmd_b) { @@ -1203,6 +1282,15 @@ static inline int pmd_same(pmd_t pmd_a, pmd_t pmd_b) return hash__pmd_same(pmd_a, pmd_b); } +#define pud_same pud_same +static inline int pud_same(pud_t pud_a, pud_t pud_b) +{ + if (radix_enabled()) + return radix__pud_same(pud_a, pud_b); + return hash__pud_same(pud_a, pud_b); +} + + static inline pmd_t __pmd_mkhuge(pmd_t pmd) { if (radix_enabled()) @@ -1210,6 +1298,14 @@ static inline pmd_t __pmd_mkhuge(pmd_t pmd) return hash__pmd_mkhuge(pmd); } +static inline pud_t __pud_mkhuge(pud_t pud) +{ + if (radix_enabled()) + return radix__pud_mkhuge(pud); + BUG(); + return pud; +} + /* * pfn_pmd return a pmd_t that can be used as pmd pte entry. */ @@ -1225,14 +1321,34 @@ static inline pmd_t pmd_mkhuge(pmd_t pmd) return pmd; } +static inline pud_t pud_mkhuge(pud_t pud) +{ +#ifdef CONFIG_DEBUG_VM + if (radix_enabled()) + WARN_ON((pud_raw(pud) & cpu_to_be64(_PAGE_PTE)) == 0); + else + WARN_ON(1); +#endif + return pud; +} + + #define __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS extern int pmdp_set_access_flags(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp, pmd_t entry, int dirty); +#define __HAVE_ARCH_PUDP_SET_ACCESS_FLAGS +extern int pudp_set_access_flags(struct vm_area_struct *vma, + unsigned long address, pud_t *pudp, + pud_t entry, int dirty); #define __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG extern int pmdp_test_and_clear_young(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp); +#define __HAVE_ARCH_PUDP_TEST_AND_CLEAR_YOUNG +extern int pudp_test_and_clear_young(struct vm_area_struct *vma, + unsigned long address, pud_t *pudp); + #define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, @@ -1243,6 +1359,16 @@ static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, return hash__pmdp_huge_get_and_clear(mm, addr, pmdp); } +#define __HAVE_ARCH_PUDP_HUGE_GET_AND_CLEAR +static inline pud_t pudp_huge_get_and_clear(struct mm_struct *mm, + unsigned long addr, pud_t *pudp) +{ + if (radix_enabled()) + return radix__pudp_huge_get_and_clear(mm, addr, pudp); + BUG(); + return *pudp; +} + static inline pmd_t pmdp_collapse_flush(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { @@ -1257,6 +1383,11 @@ pmd_t pmdp_huge_get_and_clear_full(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmdp, int full); +#define __HAVE_ARCH_PUDP_HUGE_GET_AND_CLEAR_FULL +pud_t pudp_huge_get_and_clear_full(struct vm_area_struct *vma, + unsigned long addr, + pud_t *pudp, int full); + #define __HAVE_ARCH_PGTABLE_DEPOSIT static inline void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp, pgtable_t pgtable) @@ -1305,6 +1436,14 @@ static inline pmd_t pmd_mkdevmap(pmd_t pmd) return hash__pmd_mkdevmap(pmd); } +static inline pud_t pud_mkdevmap(pud_t pud) +{ + if (radix_enabled()) + return radix__pud_mkdevmap(pud); + BUG(); + return pud; +} + static inline int pmd_devmap(pmd_t pmd) { return pte_devmap(pmd_pte(pmd)); @@ -1312,7 +1451,7 @@ static inline int pmd_devmap(pmd_t pmd) static inline int pud_devmap(pud_t pud) { - return 0; + return pte_devmap(pud_pte(pud)); } static inline int pgd_devmap(pgd_t pgd) @@ -1321,16 +1460,6 @@ static inline int pgd_devmap(pgd_t pgd) } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ -static inline int pud_pfn(pud_t pud) -{ - /* - * Currently all calls to pud_pfn() are gated around a pud_devmap() - * check so this should never be used. If it grows another user we - * want to know about it. - */ - BUILD_BUG(); - return 0; -} #define __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION pte_t ptep_modify_prot_start(struct vm_area_struct *, unsigned long, pte_t *); void ptep_modify_prot_commit(struct vm_area_struct *, unsigned long, diff --git a/arch/powerpc/include/asm/book3s/64/radix.h b/arch/powerpc/include/asm/book3s/64/radix.h index 686001eda936..357e23a403d3 100644 --- a/arch/powerpc/include/asm/book3s/64/radix.h +++ b/arch/powerpc/include/asm/book3s/64/radix.h @@ -250,6 +250,10 @@ static inline int radix__pud_bad(pud_t pud) return !!(pud_val(pud) & RADIX_PUD_BAD_BITS); } +static inline int radix__pud_same(pud_t pud_a, pud_t pud_b) +{ + return ((pud_raw(pud_a) ^ pud_raw(pud_b)) == 0); +} static inline int radix__p4d_bad(p4d_t p4d) { @@ -268,9 +272,22 @@ static inline pmd_t radix__pmd_mkhuge(pmd_t pmd) return __pmd(pmd_val(pmd) | _PAGE_PTE); } +static inline int radix__pud_trans_huge(pud_t pud) +{ + return (pud_val(pud) & (_PAGE_PTE | _PAGE_DEVMAP)) == _PAGE_PTE; +} + +static inline pud_t radix__pud_mkhuge(pud_t pud) +{ + return __pud(pud_val(pud) | _PAGE_PTE); +} + extern unsigned long radix__pmd_hugepage_update(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, unsigned long clr, unsigned long set); +extern unsigned long radix__pud_hugepage_update(struct mm_struct *mm, unsigned long addr, + pud_t *pudp, unsigned long clr, + unsigned long set); extern pmd_t radix__pmdp_collapse_flush(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp); extern void radix__pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp, @@ -278,6 +295,9 @@ extern void radix__pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp, extern pgtable_t radix__pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp); extern pmd_t radix__pmdp_huge_get_and_clear(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp); +pud_t radix__pudp_huge_get_and_clear(struct mm_struct *mm, + unsigned long addr, pud_t *pudp); + static inline int radix__has_transparent_hugepage(void) { /* For radix 2M at PMD level means thp */ @@ -285,6 +305,14 @@ static inline int radix__has_transparent_hugepage(void) return 1; return 0; } + +static inline int radix__has_transparent_pud_hugepage(void) +{ + /* For radix 1G at PUD level means pud hugepage support */ + if (mmu_psize_defs[MMU_PAGE_1G].shift == PUD_SHIFT) + return 1; + return 0; +} #endif static inline pmd_t radix__pmd_mkdevmap(pmd_t pmd) @@ -292,9 +320,20 @@ static inline pmd_t radix__pmd_mkdevmap(pmd_t pmd) return __pmd(pmd_val(pmd) | (_PAGE_PTE | _PAGE_DEVMAP)); } +static inline pud_t radix__pud_mkdevmap(pud_t pud) +{ + return __pud(pud_val(pud) | (_PAGE_PTE | _PAGE_DEVMAP)); +} + +struct vmem_altmap; +struct dev_pagemap; extern int __meminit radix__vmemmap_create_mapping(unsigned long start, unsigned long page_size, unsigned long phys); +int __meminit radix__vmemmap_populate(unsigned long start, unsigned long end, + int node, struct vmem_altmap *altmap); +void __ref radix__vmemmap_free(unsigned long start, unsigned long end, + struct vmem_altmap *altmap); extern void radix__vmemmap_remove_mapping(unsigned long start, unsigned long page_size); @@ -325,5 +364,15 @@ int radix__remove_section_mapping(unsigned long start, unsigned long end); void radix__kernel_map_pages(struct page *page, int numpages, int enable); +#ifdef CONFIG_ARCH_WANT_OPTIMIZE_DAX_VMEMMAP +#define vmemmap_can_optimize vmemmap_can_optimize +bool vmemmap_can_optimize(struct vmem_altmap *altmap, struct dev_pagemap *pgmap); +#endif + +#define vmemmap_populate_compound_pages vmemmap_populate_compound_pages +int __meminit vmemmap_populate_compound_pages(unsigned long start_pfn, + unsigned long start, + unsigned long end, int node, + struct dev_pagemap *pgmap); #endif /* __ASSEMBLY__ */ #endif diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h index 77797a2a82eb..a38542259fab 100644 --- a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h +++ b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h @@ -68,6 +68,8 @@ void radix__flush_tlb_pwc_range_psize(struct mm_struct *mm, unsigned long start, unsigned long end, int psize); extern void radix__flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end); +extern void radix__flush_pud_tlb_range(struct vm_area_struct *vma, + unsigned long start, unsigned long end); extern void radix__flush_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end); extern void radix__flush_tlb_kernel_range(unsigned long start, unsigned long end); diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush.h b/arch/powerpc/include/asm/book3s/64/tlbflush.h index 0d0c1447ecf0..1950c1b825b4 100644 --- a/arch/powerpc/include/asm/book3s/64/tlbflush.h +++ b/arch/powerpc/include/asm/book3s/64/tlbflush.h @@ -5,6 +5,7 @@ #define MMU_NO_CONTEXT ~0UL #include <linux/mm_types.h> +#include <linux/mmu_notifier.h> #include <asm/book3s/64/tlbflush-hash.h> #include <asm/book3s/64/tlbflush-radix.h> @@ -50,6 +51,14 @@ static inline void flush_pmd_tlb_range(struct vm_area_struct *vma, radix__flush_pmd_tlb_range(vma, start, end); } +#define __HAVE_ARCH_FLUSH_PUD_TLB_RANGE +static inline void flush_pud_tlb_range(struct vm_area_struct *vma, + unsigned long start, unsigned long end) +{ + if (radix_enabled()) + radix__flush_pud_tlb_range(vma, start, end); +} + #define __HAVE_ARCH_FLUSH_HUGETLB_TLB_RANGE static inline void flush_hugetlb_tlb_range(struct vm_area_struct *vma, unsigned long start, diff --git a/arch/powerpc/include/asm/book3s/pgtable.h b/arch/powerpc/include/asm/book3s/pgtable.h index d18b748ea3ae..3b7bd36a2321 100644 --- a/arch/powerpc/include/asm/book3s/pgtable.h +++ b/arch/powerpc/include/asm/book3s/pgtable.h @@ -9,13 +9,6 @@ #endif #ifndef __ASSEMBLY__ -/* Insert a PTE, top-level function is out of line. It uses an inline - * low level function in the respective pgtable-* files - */ -extern void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, - pte_t pte); - - #define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS extern int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address, pte_t *ptep, pte_t entry, int dirty); @@ -36,7 +29,9 @@ void __update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t * corresponding HPTE into the hash table ahead of time, instead of * waiting for the inevitable extra hash-table miss exception. */ -static inline void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) +static inline void update_mmu_cache_range(struct vm_fault *vmf, + struct vm_area_struct *vma, unsigned long address, + pte_t *ptep, unsigned int nr) { if (IS_ENABLED(CONFIG_PPC32) && !mmu_has_feature(MMU_FTR_HPTE_TABLE)) return; diff --git a/arch/powerpc/include/asm/bug.h b/arch/powerpc/include/asm/bug.h index 00c6b0b4ede4..1db485aacbd9 100644 --- a/arch/powerpc/include/asm/bug.h +++ b/arch/powerpc/include/asm/bug.h @@ -120,6 +120,7 @@ struct pt_regs; void hash__do_page_fault(struct pt_regs *); void bad_page_fault(struct pt_regs *, int); +void emulate_single_step(struct pt_regs *regs); extern void _exception(int, struct pt_regs *, int, unsigned long); extern void _exception_pkey(struct pt_regs *, unsigned long, int); extern void die(const char *, struct pt_regs *, long); diff --git a/arch/powerpc/include/asm/cacheflush.h b/arch/powerpc/include/asm/cacheflush.h index 7564dd4fd12b..ef7d2de33b89 100644 --- a/arch/powerpc/include/asm/cacheflush.h +++ b/arch/powerpc/include/asm/cacheflush.h @@ -35,13 +35,19 @@ static inline void flush_cache_vmap(unsigned long start, unsigned long end) * It just marks the page as not i-cache clean. We do the i-cache * flush later when the page is given to a user process, if necessary. */ -static inline void flush_dcache_page(struct page *page) +static inline void flush_dcache_folio(struct folio *folio) { if (cpu_has_feature(CPU_FTR_COHERENT_ICACHE)) return; /* avoid an atomic op if possible */ - if (test_bit(PG_dcache_clean, &page->flags)) - clear_bit(PG_dcache_clean, &page->flags); + if (test_bit(PG_dcache_clean, &folio->flags)) + clear_bit(PG_dcache_clean, &folio->flags); +} +#define flush_dcache_folio flush_dcache_folio + +static inline void flush_dcache_page(struct page *page) +{ + flush_dcache_folio(page_folio(page)); } void flush_icache_range(unsigned long start, unsigned long stop); @@ -51,7 +57,7 @@ void flush_icache_user_page(struct vm_area_struct *vma, struct page *page, unsigned long addr, int len); #define flush_icache_user_page flush_icache_user_page -void flush_dcache_icache_page(struct page *page); +void flush_dcache_icache_folio(struct folio *folio); /** * flush_dcache_range(): Write any modified data cache blocks out to memory and diff --git a/arch/powerpc/include/asm/cpm2.h b/arch/powerpc/include/asm/cpm2.h index 9ee192a6c5d7..249d43cc6427 100644 --- a/arch/powerpc/include/asm/cpm2.h +++ b/arch/powerpc/include/asm/cpm2.h @@ -1080,6 +1080,9 @@ typedef struct im_idma { #define FCC2_MEM_OFFSET FCC_MEM_OFFSET(1) #define FCC3_MEM_OFFSET FCC_MEM_OFFSET(2) +/* Pipeline Maximum Depth */ +#define MPC82XX_BCR_PLDP 0x00800000 + /* Clocks and GRG's */ enum cpm_clk_dir { diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h index 443a9d482b15..8765d5158324 100644 --- a/arch/powerpc/include/asm/cputable.h +++ b/arch/powerpc/include/asm/cputable.h @@ -252,7 +252,7 @@ static inline void cpu_feature_keys_init(void) { } * This is also required by 52xx family. */ #if defined(CONFIG_SMP) || defined(CONFIG_MPC10X_BRIDGE) \ - || defined(CONFIG_PPC_83xx) || defined(CONFIG_8260) \ + || defined(CONFIG_PPC_83xx) || defined(CONFIG_PPC_82xx) \ || defined(CONFIG_PPC_MPC52xx) #define CPU_FTR_COMMON CPU_FTR_NEED_COHERENT #else diff --git a/arch/powerpc/include/asm/dtl.h b/arch/powerpc/include/asm/dtl.h index 4bcb9f9ac764..d6f43d149f8d 100644 --- a/arch/powerpc/include/asm/dtl.h +++ b/arch/powerpc/include/asm/dtl.h @@ -39,6 +39,5 @@ extern rwlock_t dtl_access_lock; extern void register_dtl_buffer(int cpu); extern void alloc_dtl_buffers(unsigned long *time_limit); -extern long hcall_vphn(unsigned long cpu, u64 flags, __be32 *associativity); #endif /* _ASM_POWERPC_DTL_H */ diff --git a/arch/powerpc/include/asm/feature-fixups.h b/arch/powerpc/include/asm/feature-fixups.h index ac605fc369c4..77824bd289a3 100644 --- a/arch/powerpc/include/asm/feature-fixups.h +++ b/arch/powerpc/include/asm/feature-fixups.h @@ -292,6 +292,7 @@ extern long __start___barrier_nospec_fixup, __stop___barrier_nospec_fixup; extern long __start__btb_flush_fixup, __stop__btb_flush_fixup; void apply_feature_fixups(void); +void update_mmu_feature_fixups(unsigned long mask); void setup_feature_keys(void); #endif diff --git a/arch/powerpc/include/asm/fs_pd.h b/arch/powerpc/include/asm/fs_pd.h deleted file mode 100644 index 8def56ec05c6..000000000000 --- a/arch/powerpc/include/asm/fs_pd.h +++ /dev/null @@ -1,49 +0,0 @@ -/* - * Platform information definitions. - * - * 2006 (c) MontaVista Software, Inc. - * Vitaly Bordug <vbordug@ru.mvista.com> - * - * This file is licensed under the terms of the GNU General Public License - * version 2. This program is licensed "as is" without any warranty of any - * kind, whether express or implied. - */ - -#ifndef FS_PD_H -#define FS_PD_H -#include <sysdev/fsl_soc.h> -#include <asm/time.h> - -#ifdef CONFIG_CPM2 -#include <asm/cpm2.h> - -#if defined(CONFIG_8260) -#include <asm/mpc8260.h> -#endif - -#define cpm2_map(member) (&cpm2_immr->member) -#define cpm2_map_size(member, size) (&cpm2_immr->member) -#define cpm2_unmap(addr) do {} while(0) -#endif - -#ifdef CONFIG_PPC_8xx -#include <asm/8xx_immap.h> - -extern immap_t __iomem *mpc8xx_immr; - -#define immr_map(member) (&mpc8xx_immr->member) -#define immr_map_size(member, size) (&mpc8xx_immr->member) -#define immr_unmap(addr) do {} while (0) -#endif - -static inline int uart_baudrate(void) -{ - return get_baudrate(); -} - -static inline int uart_clock(void) -{ - return ppc_proc_freq; -} - -#endif diff --git a/arch/powerpc/include/asm/ftrace.h b/arch/powerpc/include/asm/ftrace.h index 91c049d51d0e..9e5a39b6a311 100644 --- a/arch/powerpc/include/asm/ftrace.h +++ b/arch/powerpc/include/asm/ftrace.h @@ -11,8 +11,8 @@ #define HAVE_FUNCTION_GRAPH_RET_ADDR_PTR /* Ignore unused weak functions which will have larger offsets */ -#ifdef CONFIG_MPROFILE_KERNEL -#define FTRACE_MCOUNT_MAX_OFFSET 12 +#if defined(CONFIG_MPROFILE_KERNEL) || defined(CONFIG_ARCH_USING_PATCHABLE_FUNCTION_ENTRY) +#define FTRACE_MCOUNT_MAX_OFFSET 16 #elif defined(CONFIG_PPC32) #define FTRACE_MCOUNT_MAX_OFFSET 8 #endif @@ -22,18 +22,26 @@ extern void _mcount(void); static inline unsigned long ftrace_call_adjust(unsigned long addr) { - /* relocation of mcount call site is the same as the address */ + if (IS_ENABLED(CONFIG_ARCH_USING_PATCHABLE_FUNCTION_ENTRY)) + addr += MCOUNT_INSN_SIZE; + return addr; } unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip, unsigned long sp); +struct module; +struct dyn_ftrace; struct dyn_arch_ftrace { struct module *mod; }; #ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS +#define ftrace_need_init_nop() (true) +int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec); +#define ftrace_init_nop ftrace_init_nop + struct ftrace_regs { struct pt_regs regs; }; @@ -124,15 +132,19 @@ static inline u8 this_cpu_get_ftrace_enabled(void) { return get_paca()->ftrace_enabled; } - -void ftrace_free_init_tramp(void); #else /* CONFIG_PPC64 */ static inline void this_cpu_disable_ftrace(void) { } static inline void this_cpu_enable_ftrace(void) { } static inline void this_cpu_set_ftrace_enabled(u8 ftrace_enabled) { } static inline u8 this_cpu_get_ftrace_enabled(void) { return 1; } -static inline void ftrace_free_init_tramp(void) { } #endif /* CONFIG_PPC64 */ + +#ifdef CONFIG_FUNCTION_TRACER +extern unsigned int ftrace_tramp_text[], ftrace_tramp_init[]; +void ftrace_free_init_tramp(void); +#else +static inline void ftrace_free_init_tramp(void) { } +#endif #endif /* !__ASSEMBLY__ */ #endif /* _ASM_POWERPC_FTRACE */ diff --git a/arch/powerpc/include/asm/hw_breakpoint.h b/arch/powerpc/include/asm/hw_breakpoint.h index 84d39fd42f71..66db0147d5b4 100644 --- a/arch/powerpc/include/asm/hw_breakpoint.h +++ b/arch/powerpc/include/asm/hw_breakpoint.h @@ -18,6 +18,7 @@ struct arch_hw_breakpoint { u16 len; /* length of the target data symbol */ u16 hw_len; /* length programmed in hw */ u8 flags; + bool perf_single_step; /* temporarily uninstalled for a perf single step */ }; /* Note: Don't change the first 6 bits below as they are in the same order diff --git a/arch/powerpc/include/asm/ibmebus.h b/arch/powerpc/include/asm/ibmebus.h index 088f95b2e14f..6f33253a364a 100644 --- a/arch/powerpc/include/asm/ibmebus.h +++ b/arch/powerpc/include/asm/ibmebus.h @@ -46,6 +46,8 @@ #include <linux/of_device.h> #include <linux/of_platform.h> +struct platform_driver; + extern struct bus_type ibmebus_bus_type; int ibmebus_register_driver(struct platform_driver *drv); diff --git a/arch/powerpc/include/asm/io.h b/arch/powerpc/include/asm/io.h index f1e657c9bbe8..0732b743e099 100644 --- a/arch/powerpc/include/asm/io.h +++ b/arch/powerpc/include/asm/io.h @@ -3,11 +3,6 @@ #define _ASM_POWERPC_IO_H #ifdef __KERNEL__ -#define ARCH_HAS_IOREMAP_WC -#ifdef CONFIG_PPC32 -#define ARCH_HAS_IOREMAP_WT -#endif - /* */ @@ -732,9 +727,7 @@ static inline void name at \ #define writel_relaxed(v, addr) writel(v, addr) #define writeq_relaxed(v, addr) writeq(v, addr) -#ifdef CONFIG_GENERIC_IOMAP -#include <asm-generic/iomap.h> -#else +#ifndef CONFIG_GENERIC_IOMAP /* * Here comes the implementation of the IOMAP interfaces. */ @@ -896,8 +889,8 @@ static inline void iosync(void) * */ extern void __iomem *ioremap(phys_addr_t address, unsigned long size); -extern void __iomem *ioremap_prot(phys_addr_t address, unsigned long size, - unsigned long flags); +#define ioremap ioremap +#define ioremap_prot ioremap_prot extern void __iomem *ioremap_wc(phys_addr_t address, unsigned long size); #define ioremap_wc ioremap_wc @@ -911,14 +904,12 @@ void __iomem *ioremap_coherent(phys_addr_t address, unsigned long size); #define ioremap_cache(addr, size) \ ioremap_prot((addr), (size), pgprot_val(PAGE_KERNEL)) -extern void iounmap(volatile void __iomem *addr); +#define iounmap iounmap void __iomem *ioremap_phb(phys_addr_t paddr, unsigned long size); int early_ioremap_range(unsigned long ea, phys_addr_t pa, unsigned long size, pgprot_t prot); -void __iomem *do_ioremap(phys_addr_t pa, phys_addr_t offset, unsigned long size, - pgprot_t prot, void *caller); extern void __iomem *__ioremap_caller(phys_addr_t, unsigned long size, pgprot_t prot, void *caller); diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h index 34e14dfd8e04..026695943550 100644 --- a/arch/powerpc/include/asm/iommu.h +++ b/arch/powerpc/include/asm/iommu.h @@ -28,6 +28,9 @@ #define IOMMU_PAGE_MASK(tblptr) (~((1 << (tblptr)->it_page_shift) - 1)) #define IOMMU_PAGE_ALIGN(addr, tblptr) ALIGN(addr, IOMMU_PAGE_SIZE(tblptr)) +#define DIRECT64_PROPNAME "linux,direct64-ddr-window-info" +#define DMA64_PROPNAME "linux,dma64-ddr-window-info" + /* Boot time flags */ extern int iommu_is_off; extern int iommu_force_on; diff --git a/arch/powerpc/include/asm/irq.h b/arch/powerpc/include/asm/irq.h index f257cacb49a9..ba1a5974e714 100644 --- a/arch/powerpc/include/asm/irq.h +++ b/arch/powerpc/include/asm/irq.h @@ -55,7 +55,7 @@ int irq_choose_cpu(const struct cpumask *mask); #if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_NMI_IPI) extern void arch_trigger_cpumask_backtrace(const cpumask_t *mask, - bool exclude_self); + int exclude_cpu); #define arch_trigger_cpumask_backtrace arch_trigger_cpumask_backtrace #endif diff --git a/arch/powerpc/include/asm/kfence.h b/arch/powerpc/include/asm/kfence.h index 6fd2b4d486c5..424ceef82ae6 100644 --- a/arch/powerpc/include/asm/kfence.h +++ b/arch/powerpc/include/asm/kfence.h @@ -23,7 +23,7 @@ static inline bool arch_kfence_init_pool(void) #ifdef CONFIG_PPC64 static inline bool kfence_protect_page(unsigned long addr, bool protect) { - struct page *page = virt_to_page(addr); + struct page *page = virt_to_page((void *)addr); __kernel_map_pages(page, 1, !protect); diff --git a/arch/powerpc/include/asm/kup.h b/arch/powerpc/include/asm/kup.h index d751ddd08110..ad7e8c5aec3f 100644 --- a/arch/powerpc/include/asm/kup.h +++ b/arch/powerpc/include/asm/kup.h @@ -6,6 +6,12 @@ #define KUAP_WRITE 2 #define KUAP_READ_WRITE (KUAP_READ | KUAP_WRITE) +#ifndef __ASSEMBLY__ +#include <linux/types.h> + +static __always_inline bool kuap_is_disabled(void); +#endif + #ifdef CONFIG_PPC_BOOK3S_64 #include <asm/book3s/64/kup.h> #endif @@ -41,26 +47,24 @@ void setup_kuep(bool disabled); #ifdef CONFIG_PPC_KUAP void setup_kuap(bool disabled); + +static __always_inline bool kuap_is_disabled(void) +{ + return !mmu_has_feature(MMU_FTR_KUAP); +} #else static inline void setup_kuap(bool disabled) { } static __always_inline bool kuap_is_disabled(void) { return true; } -static inline bool +static __always_inline bool __bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write) { return false; } -static inline void __kuap_lock(void) { } -static inline void __kuap_save_and_lock(struct pt_regs *regs) { } -static inline void kuap_user_restore(struct pt_regs *regs) { } -static inline void __kuap_kernel_restore(struct pt_regs *regs, unsigned long amr) { } - -static inline unsigned long __kuap_get_and_assert_locked(void) -{ - return 0; -} +static __always_inline void kuap_user_restore(struct pt_regs *regs) { } +static __always_inline void __kuap_kernel_restore(struct pt_regs *regs, unsigned long amr) { } /* * book3s/64/kup-radix.h defines these functions for the !KUAP case to flush @@ -68,11 +72,11 @@ static inline unsigned long __kuap_get_and_assert_locked(void) * platforms. */ #ifndef CONFIG_PPC_BOOK3S_64 -static inline void __allow_user_access(void __user *to, const void __user *from, - unsigned long size, unsigned long dir) { } -static inline void __prevent_user_access(unsigned long dir) { } -static inline unsigned long __prevent_user_access_return(void) { return 0UL; } -static inline void __restore_user_access(unsigned long flags) { } +static __always_inline void allow_user_access(void __user *to, const void __user *from, + unsigned long size, unsigned long dir) { } +static __always_inline void prevent_user_access(unsigned long dir) { } +static __always_inline unsigned long prevent_user_access_return(void) { return 0UL; } +static __always_inline void restore_user_access(unsigned long flags) { } #endif /* CONFIG_PPC_BOOK3S_64 */ #endif /* CONFIG_PPC_KUAP */ @@ -85,29 +89,24 @@ bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write) return __bad_kuap_fault(regs, address, is_write); } -static __always_inline void kuap_assert_locked(void) -{ - if (kuap_is_disabled()) - return; - - if (IS_ENABLED(CONFIG_PPC_KUAP_DEBUG)) - __kuap_get_and_assert_locked(); -} - static __always_inline void kuap_lock(void) { +#ifdef __kuap_lock if (kuap_is_disabled()) return; __kuap_lock(); +#endif } static __always_inline void kuap_save_and_lock(struct pt_regs *regs) { +#ifdef __kuap_save_and_lock if (kuap_is_disabled()) return; __kuap_save_and_lock(regs); +#endif } static __always_inline void kuap_kernel_restore(struct pt_regs *regs, unsigned long amr) @@ -120,46 +119,18 @@ static __always_inline void kuap_kernel_restore(struct pt_regs *regs, unsigned l static __always_inline unsigned long kuap_get_and_assert_locked(void) { - if (kuap_is_disabled()) - return 0; - - return __kuap_get_and_assert_locked(); -} - -#ifndef CONFIG_PPC_BOOK3S_64 -static __always_inline void allow_user_access(void __user *to, const void __user *from, - unsigned long size, unsigned long dir) -{ - if (kuap_is_disabled()) - return; - - __allow_user_access(to, from, size, dir); -} - -static __always_inline void prevent_user_access(unsigned long dir) -{ - if (kuap_is_disabled()) - return; - - __prevent_user_access(dir); -} - -static __always_inline unsigned long prevent_user_access_return(void) -{ - if (kuap_is_disabled()) - return 0; - - return __prevent_user_access_return(); +#ifdef __kuap_get_and_assert_locked + if (!kuap_is_disabled()) + return __kuap_get_and_assert_locked(); +#endif + return 0; } -static __always_inline void restore_user_access(unsigned long flags) +static __always_inline void kuap_assert_locked(void) { - if (kuap_is_disabled()) - return; - - __restore_user_access(flags); + if (IS_ENABLED(CONFIG_PPC_KUAP_DEBUG)) + kuap_get_and_assert_locked(); } -#endif /* CONFIG_PPC_BOOK3S_64 */ static __always_inline void allow_read_from_user(const void __user *from, unsigned long size) { diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index d16d80ad2ae4..b4da8514af43 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -894,7 +894,7 @@ void kvmppc_init_lpid(unsigned long nr_lpids); static inline void kvmppc_mmu_flush_icache(kvm_pfn_t pfn) { - struct page *page; + struct folio *folio; /* * We can only access pages that the kernel maps * as memory. Bail out for unmapped ones. @@ -903,10 +903,10 @@ static inline void kvmppc_mmu_flush_icache(kvm_pfn_t pfn) return; /* Clear i-cache for new pages */ - page = pfn_to_page(pfn); - if (!test_bit(PG_dcache_clean, &page->flags)) { - flush_dcache_icache_page(page); - set_bit(PG_dcache_clean, &page->flags); + folio = page_folio(pfn_to_page(pfn)); + if (!test_bit(PG_dcache_clean, &folio->flags)) { + flush_dcache_icache_folio(folio); + set_bit(PG_dcache_clean, &folio->flags); } } diff --git a/arch/powerpc/include/asm/lppaca.h b/arch/powerpc/include/asm/lppaca.h index 34d44cb17c87..61ec2447dabf 100644 --- a/arch/powerpc/include/asm/lppaca.h +++ b/arch/powerpc/include/asm/lppaca.h @@ -6,28 +6,6 @@ #ifndef _ASM_POWERPC_LPPACA_H #define _ASM_POWERPC_LPPACA_H -/* - * The below VPHN macros are outside the __KERNEL__ check since these are - * used for compiling the vphn selftest in userspace - */ - -/* The H_HOME_NODE_ASSOCIATIVITY h_call returns 6 64-bit registers. */ -#define VPHN_REGISTER_COUNT 6 - -/* - * 6 64-bit registers unpacked into up to 24 be32 associativity values. To - * form the complete property we have to add the length in the first cell. - */ -#define VPHN_ASSOC_BUFSIZE (VPHN_REGISTER_COUNT*sizeof(u64)/sizeof(u16) + 1) - -/* - * The H_HOME_NODE_ASSOCIATIVITY hcall takes two values for flags: - * 1 for retrieving associativity information for a guest cpu - * 2 for retrieving associativity information for a host/hypervisor cpu - */ -#define VPHN_FLAG_VCPU 1 -#define VPHN_FLAG_PCPU 2 - #ifdef __KERNEL__ /* @@ -45,6 +23,7 @@ #include <asm/types.h> #include <asm/mmu.h> #include <asm/firmware.h> +#include <asm/paca.h> /* * The lppaca is the "virtual processor area" registered with the hypervisor, @@ -127,13 +106,23 @@ struct lppaca { */ #define LPPACA_OLD_SHARED_PROC 2 -static inline bool lppaca_shared_proc(struct lppaca *l) +#ifdef CONFIG_PPC_PSERIES +/* + * All CPUs should have the same shared proc value, so directly access the PACA + * to avoid false positives from DEBUG_PREEMPT. + */ +static inline bool lppaca_shared_proc(void) { + struct lppaca *l = local_paca->lppaca_ptr; + if (!firmware_has_feature(FW_FEATURE_SPLPAR)) return false; return !!(l->__old_status & LPPACA_OLD_SHARED_PROC); } +#define get_lppaca() (get_paca()->lppaca_ptr) +#endif + /* * SLB shadow buffer structure as defined in the PAPR. The save_area * contains adjacent ESID and VSID pairs for each shadowed SLB. The @@ -149,8 +138,6 @@ struct slb_shadow { } save_area[SLB_NUM_BOLTED]; } ____cacheline_aligned; -extern long hcall_vphn(unsigned long cpu, u64 flags, __be32 *associativity); - #endif /* CONFIG_PPC_BOOK3S */ #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_LPPACA_H */ diff --git a/arch/powerpc/include/asm/macio.h b/arch/powerpc/include/asm/macio.h index ff5fd82d9ff0..3a07c62973aa 100644 --- a/arch/powerpc/include/asm/macio.h +++ b/arch/powerpc/include/asm/macio.h @@ -3,7 +3,8 @@ #define __MACIO_ASIC_H__ #ifdef __KERNEL__ -#include <linux/of_device.h> +#include <linux/of.h> +#include <linux/platform_device.h> extern struct bus_type macio_bus_type; diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h index 94b981152667..52cc25864a1b 100644 --- a/arch/powerpc/include/asm/mmu.h +++ b/arch/powerpc/include/asm/mmu.h @@ -33,7 +33,7 @@ * key 0 controlling userspace addresses on radix * Key 3 on hash */ -#define MMU_FTR_BOOK3S_KUAP ASM_CONST(0x00000200) +#define MMU_FTR_KUAP ASM_CONST(0x00000200) /* * Supports KUEP feature @@ -144,11 +144,6 @@ typedef pte_t *pgtable_t; -#ifdef CONFIG_PPC_E500 -#include <asm/percpu.h> -DECLARE_PER_CPU(int, next_tlbcam_idx); -#endif - enum { MMU_FTRS_POSSIBLE = #if defined(CONFIG_PPC_BOOK3S_604) @@ -188,7 +183,7 @@ enum { #endif /* CONFIG_PPC_RADIX_MMU */ #endif #ifdef CONFIG_PPC_KUAP - MMU_FTR_BOOK3S_KUAP | + MMU_FTR_KUAP | #endif /* CONFIG_PPC_KUAP */ #ifdef CONFIG_PPC_MEM_KEYS MMU_FTR_PKEY | diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h index 57f5017111f4..37bffa0f7918 100644 --- a/arch/powerpc/include/asm/mmu_context.h +++ b/arch/powerpc/include/asm/mmu_context.h @@ -127,6 +127,7 @@ static inline void inc_mm_active_cpus(struct mm_struct *mm) static inline void dec_mm_active_cpus(struct mm_struct *mm) { + VM_WARN_ON_ONCE(atomic_read(&mm->context.active_cpus) <= 0); atomic_dec(&mm->context.active_cpus); } diff --git a/arch/powerpc/include/asm/module.h b/arch/powerpc/include/asm/module.h index ac53606c2594..a8e2e8339fb7 100644 --- a/arch/powerpc/include/asm/module.h +++ b/arch/powerpc/include/asm/module.h @@ -75,10 +75,6 @@ struct mod_arch_specific { #endif #ifdef CONFIG_DYNAMIC_FTRACE -# ifdef MODULE - asm(".section .ftrace.tramp,\"ax\",@nobits; .align 3; .previous"); -# endif /* MODULE */ - int module_trampoline_target(struct module *mod, unsigned long trampoline, unsigned long *target); int module_finalize_ftrace(struct module *mod, const Elf_Shdr *sechdrs); diff --git a/arch/powerpc/include/asm/mpc8260.h b/arch/powerpc/include/asm/mpc8260.h deleted file mode 100644 index 155114bbd1a2..000000000000 --- a/arch/powerpc/include/asm/mpc8260.h +++ /dev/null @@ -1,22 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Since there are many different boards and no standard configuration, - * we have a unique include file for each. Rather than change every - * file that has to include MPC8260 configuration, they all include - * this one and the configuration switching is done here. - */ -#ifdef __KERNEL__ -#ifndef __ASM_POWERPC_MPC8260_H__ -#define __ASM_POWERPC_MPC8260_H__ - -#define MPC82XX_BCR_PLDP 0x00800000 /* Pipeline Maximum Depth */ - -#ifdef CONFIG_8260 - -#ifdef CONFIG_PCI_8260 -#include <platforms/82xx/m82xx_pci.h> -#endif - -#endif /* CONFIG_8260 */ -#endif /* !__ASM_POWERPC_MPC8260_H__ */ -#endif /* __KERNEL__ */ diff --git a/arch/powerpc/include/asm/nohash/32/kup-8xx.h b/arch/powerpc/include/asm/nohash/32/kup-8xx.h index c44d97751723..46bc5925e5fd 100644 --- a/arch/powerpc/include/asm/nohash/32/kup-8xx.h +++ b/arch/powerpc/include/asm/nohash/32/kup-8xx.h @@ -9,76 +9,74 @@ #ifndef __ASSEMBLY__ -#include <linux/jump_label.h> - #include <asm/reg.h> -extern struct static_key_false disable_kuap_key; - -static __always_inline bool kuap_is_disabled(void) -{ - return static_branch_unlikely(&disable_kuap_key); -} - -static inline void __kuap_lock(void) -{ -} - -static inline void __kuap_save_and_lock(struct pt_regs *regs) +static __always_inline void __kuap_save_and_lock(struct pt_regs *regs) { regs->kuap = mfspr(SPRN_MD_AP); mtspr(SPRN_MD_AP, MD_APG_KUAP); } +#define __kuap_save_and_lock __kuap_save_and_lock -static inline void kuap_user_restore(struct pt_regs *regs) +static __always_inline void kuap_user_restore(struct pt_regs *regs) { } -static inline void __kuap_kernel_restore(struct pt_regs *regs, unsigned long kuap) +static __always_inline void __kuap_kernel_restore(struct pt_regs *regs, unsigned long kuap) { mtspr(SPRN_MD_AP, regs->kuap); } -static inline unsigned long __kuap_get_and_assert_locked(void) +#ifdef CONFIG_PPC_KUAP_DEBUG +static __always_inline unsigned long __kuap_get_and_assert_locked(void) { - unsigned long kuap; + WARN_ON_ONCE(mfspr(SPRN_MD_AP) >> 16 != MD_APG_KUAP >> 16); - kuap = mfspr(SPRN_MD_AP); + return 0; +} +#define __kuap_get_and_assert_locked __kuap_get_and_assert_locked +#endif - if (IS_ENABLED(CONFIG_PPC_KUAP_DEBUG)) - WARN_ON_ONCE(kuap >> 16 != MD_APG_KUAP >> 16); +static __always_inline void uaccess_begin_8xx(unsigned long val) +{ + asm(ASM_MMU_FTR_IFSET("mtspr %0, %1", "", %2) : : + "i"(SPRN_MD_AP), "r"(val), "i"(MMU_FTR_KUAP) : "memory"); +} - return kuap; +static __always_inline void uaccess_end_8xx(void) +{ + asm(ASM_MMU_FTR_IFSET("mtspr %0, %1", "", %2) : : + "i"(SPRN_MD_AP), "r"(MD_APG_KUAP), "i"(MMU_FTR_KUAP) : "memory"); } -static inline void __allow_user_access(void __user *to, const void __user *from, - unsigned long size, unsigned long dir) +static __always_inline void allow_user_access(void __user *to, const void __user *from, + unsigned long size, unsigned long dir) { - mtspr(SPRN_MD_AP, MD_APG_INIT); + uaccess_begin_8xx(MD_APG_INIT); } -static inline void __prevent_user_access(unsigned long dir) +static __always_inline void prevent_user_access(unsigned long dir) { - mtspr(SPRN_MD_AP, MD_APG_KUAP); + uaccess_end_8xx(); } -static inline unsigned long __prevent_user_access_return(void) +static __always_inline unsigned long prevent_user_access_return(void) { unsigned long flags; flags = mfspr(SPRN_MD_AP); - mtspr(SPRN_MD_AP, MD_APG_KUAP); + uaccess_end_8xx(); return flags; } -static inline void __restore_user_access(unsigned long flags) +static __always_inline void restore_user_access(unsigned long flags) { - mtspr(SPRN_MD_AP, flags); + uaccess_begin_8xx(flags); } -static inline bool +static __always_inline bool __bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write) { return !((regs->kuap ^ MD_APG_KUAP) & 0xff000000); diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h index fec56d965f00..f99c53a5f184 100644 --- a/arch/powerpc/include/asm/nohash/32/pgtable.h +++ b/arch/powerpc/include/asm/nohash/32/pgtable.h @@ -170,8 +170,8 @@ void unmap_kernel_page(unsigned long va); #define pte_clear(mm, addr, ptep) \ do { pte_update(mm, addr, ptep, ~0, 0, 0); } while (0) -#ifndef pte_mkwrite -static inline pte_t pte_mkwrite(pte_t pte) +#ifndef pte_mkwrite_novma +static inline pte_t pte_mkwrite_novma(pte_t pte) { return __pte(pte_val(pte) | _PAGE_RW); } @@ -355,7 +355,7 @@ static inline int pte_young(pte_t pte) #define pmd_pfn(pmd) (pmd_val(pmd) >> PAGE_SHIFT) #else #define pmd_page_vaddr(pmd) \ - ((unsigned long)(pmd_val(pmd) & ~(PTE_TABLE_SIZE - 1))) + ((const void *)(pmd_val(pmd) & ~(PTE_TABLE_SIZE - 1))) #define pmd_pfn(pmd) (__pa(pmd_val(pmd)) >> PAGE_SHIFT) #endif diff --git a/arch/powerpc/include/asm/nohash/32/pte-8xx.h b/arch/powerpc/include/asm/nohash/32/pte-8xx.h index 1a89ebdc3acc..21f681ee535a 100644 --- a/arch/powerpc/include/asm/nohash/32/pte-8xx.h +++ b/arch/powerpc/include/asm/nohash/32/pte-8xx.h @@ -101,12 +101,12 @@ static inline int pte_write(pte_t pte) #define pte_write pte_write -static inline pte_t pte_mkwrite(pte_t pte) +static inline pte_t pte_mkwrite_novma(pte_t pte) { return __pte(pte_val(pte) & ~_PAGE_RO); } -#define pte_mkwrite pte_mkwrite +#define pte_mkwrite_novma pte_mkwrite_novma static inline bool pte_user(pte_t pte) { diff --git a/arch/powerpc/include/asm/nohash/64/pgtable.h b/arch/powerpc/include/asm/nohash/64/pgtable.h index 287e25864ffa..5cd9acf58a7d 100644 --- a/arch/powerpc/include/asm/nohash/64/pgtable.h +++ b/arch/powerpc/include/asm/nohash/64/pgtable.h @@ -85,7 +85,7 @@ #ifndef __ASSEMBLY__ /* pte_clear moved to later in this file */ -static inline pte_t pte_mkwrite(pte_t pte) +static inline pte_t pte_mkwrite_novma(pte_t pte) { return __pte(pte_val(pte) | _PAGE_RW); } @@ -127,7 +127,7 @@ static inline pte_t pmd_pte(pmd_t pmd) #define pmd_bad(pmd) (!is_kernel_addr(pmd_val(pmd)) \ || (pmd_val(pmd) & PMD_BAD_BITS)) #define pmd_present(pmd) (!pmd_none(pmd)) -#define pmd_page_vaddr(pmd) (pmd_val(pmd) & ~PMD_MASKED_BITS) +#define pmd_page_vaddr(pmd) ((const void *)(pmd_val(pmd) & ~PMD_MASKED_BITS)) extern struct page *pmd_page(pmd_t pmd); #define pmd_pfn(pmd) (page_to_pfn(pmd_page(pmd))) diff --git a/arch/powerpc/include/asm/nohash/kup-booke.h b/arch/powerpc/include/asm/nohash/kup-booke.h index 49bb41ed0816..0c7c3258134c 100644 --- a/arch/powerpc/include/asm/nohash/kup-booke.h +++ b/arch/powerpc/include/asm/nohash/kup-booke.h @@ -3,6 +3,7 @@ #define _ASM_POWERPC_KUP_BOOKE_H_ #include <asm/bug.h> +#include <asm/mmu.h> #ifdef CONFIG_PPC_KUAP @@ -13,32 +14,26 @@ #else -#include <linux/jump_label.h> #include <linux/sched.h> #include <asm/reg.h> -extern struct static_key_false disable_kuap_key; - -static __always_inline bool kuap_is_disabled(void) -{ - return static_branch_unlikely(&disable_kuap_key); -} - -static inline void __kuap_lock(void) +static __always_inline void __kuap_lock(void) { mtspr(SPRN_PID, 0); isync(); } +#define __kuap_lock __kuap_lock -static inline void __kuap_save_and_lock(struct pt_regs *regs) +static __always_inline void __kuap_save_and_lock(struct pt_regs *regs) { regs->kuap = mfspr(SPRN_PID); mtspr(SPRN_PID, 0); isync(); } +#define __kuap_save_and_lock __kuap_save_and_lock -static inline void kuap_user_restore(struct pt_regs *regs) +static __always_inline void kuap_user_restore(struct pt_regs *regs) { if (kuap_is_disabled()) return; @@ -48,7 +43,7 @@ static inline void kuap_user_restore(struct pt_regs *regs) /* Context synchronisation is performed by rfi */ } -static inline void __kuap_kernel_restore(struct pt_regs *regs, unsigned long kuap) +static __always_inline void __kuap_kernel_restore(struct pt_regs *regs, unsigned long kuap) { if (regs->kuap) mtspr(SPRN_PID, current->thread.pid); @@ -56,48 +51,55 @@ static inline void __kuap_kernel_restore(struct pt_regs *regs, unsigned long kua /* Context synchronisation is performed by rfi */ } -static inline unsigned long __kuap_get_and_assert_locked(void) +#ifdef CONFIG_PPC_KUAP_DEBUG +static __always_inline unsigned long __kuap_get_and_assert_locked(void) { - unsigned long kuap = mfspr(SPRN_PID); + WARN_ON_ONCE(mfspr(SPRN_PID)); - if (IS_ENABLED(CONFIG_PPC_KUAP_DEBUG)) - WARN_ON_ONCE(kuap); + return 0; +} +#define __kuap_get_and_assert_locked __kuap_get_and_assert_locked +#endif - return kuap; +static __always_inline void uaccess_begin_booke(unsigned long val) +{ + asm(ASM_MMU_FTR_IFSET("mtspr %0, %1; isync", "", %2) : : + "i"(SPRN_PID), "r"(val), "i"(MMU_FTR_KUAP) : "memory"); } -static inline void __allow_user_access(void __user *to, const void __user *from, - unsigned long size, unsigned long dir) +static __always_inline void uaccess_end_booke(void) { - mtspr(SPRN_PID, current->thread.pid); - isync(); + asm(ASM_MMU_FTR_IFSET("mtspr %0, %1; isync", "", %2) : : + "i"(SPRN_PID), "r"(0), "i"(MMU_FTR_KUAP) : "memory"); } -static inline void __prevent_user_access(unsigned long dir) +static __always_inline void allow_user_access(void __user *to, const void __user *from, + unsigned long size, unsigned long dir) { - mtspr(SPRN_PID, 0); - isync(); + uaccess_begin_booke(current->thread.pid); +} + +static __always_inline void prevent_user_access(unsigned long dir) +{ + uaccess_end_booke(); } -static inline unsigned long __prevent_user_access_return(void) +static __always_inline unsigned long prevent_user_access_return(void) { unsigned long flags = mfspr(SPRN_PID); - mtspr(SPRN_PID, 0); - isync(); + uaccess_end_booke(); return flags; } -static inline void __restore_user_access(unsigned long flags) +static __always_inline void restore_user_access(unsigned long flags) { - if (flags) { - mtspr(SPRN_PID, current->thread.pid); - isync(); - } + if (flags) + uaccess_begin_booke(current->thread.pid); } -static inline bool +static __always_inline bool __bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write) { return !regs->kuap; diff --git a/arch/powerpc/include/asm/nohash/mmu-e500.h b/arch/powerpc/include/asm/nohash/mmu-e500.h index e43a418d3ccd..6ddced0415cb 100644 --- a/arch/powerpc/include/asm/nohash/mmu-e500.h +++ b/arch/powerpc/include/asm/nohash/mmu-e500.h @@ -319,6 +319,9 @@ extern int book3e_htw_mode; #endif +#include <asm/percpu.h> +DECLARE_PER_CPU(int, next_tlbcam_idx); + #endif /* !__ASSEMBLY__ */ #endif /* _ASM_POWERPC_MMU_BOOK3E_H_ */ diff --git a/arch/powerpc/include/asm/nohash/pgtable.h b/arch/powerpc/include/asm/nohash/pgtable.h index a6caaaab6f92..56ea48276356 100644 --- a/arch/powerpc/include/asm/nohash/pgtable.h +++ b/arch/powerpc/include/asm/nohash/pgtable.h @@ -101,8 +101,6 @@ static inline bool pte_access_permitted(pte_t pte, bool write) static inline pte_t pfn_pte(unsigned long pfn, pgprot_t pgprot) { return __pte(((pte_basic_t)(pfn) << PTE_RPN_SHIFT) | pgprot_val(pgprot)); } -static inline unsigned long pte_pfn(pte_t pte) { - return pte_val(pte) >> PTE_RPN_SHIFT; } /* Generic modifiers for PTE bits */ static inline pte_t pte_exprotect(pte_t pte) @@ -166,12 +164,6 @@ static inline pte_t pte_swp_clear_exclusive(pte_t pte) return __pte(pte_val(pte) & ~_PAGE_SWP_EXCLUSIVE); } -/* Insert a PTE, top-level function is out of line. It uses an inline - * low level function in the respective pgtable-* files - */ -extern void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, - pte_t pte); - /* This low level function performs the actual PTE insertion * Setting the PTE depends on the MMU type and other factors. It's * an horrible mess that I'm not going to try to clean up now but @@ -282,10 +274,12 @@ static inline int pud_huge(pud_t pud) * for the page which has just been mapped in. */ #if defined(CONFIG_PPC_E500) && defined(CONFIG_HUGETLB_PAGE) -void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep); +void update_mmu_cache_range(struct vm_fault *vmf, struct vm_area_struct *vma, + unsigned long address, pte_t *ptep, unsigned int nr); #else -static inline -void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) {} +static inline void update_mmu_cache_range(struct vm_fault *vmf, + struct vm_area_struct *vma, unsigned long address, + pte_t *ptep, unsigned int nr) {} #endif #endif /* __ASSEMBLY__ */ diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h index cb325938766a..e667d455ecb4 100644 --- a/arch/powerpc/include/asm/paca.h +++ b/arch/powerpc/include/asm/paca.h @@ -15,7 +15,6 @@ #include <linux/cache.h> #include <linux/string.h> #include <asm/types.h> -#include <asm/lppaca.h> #include <asm/mmu.h> #include <asm/page.h> #ifdef CONFIG_PPC_BOOK3E_64 @@ -47,14 +46,11 @@ extern unsigned int debug_smp_processor_id(void); /* from linux/smp.h */ #define get_paca() local_paca #endif -#ifdef CONFIG_PPC_PSERIES -#define get_lppaca() (get_paca()->lppaca_ptr) -#endif - #define get_slb_shadow() (get_paca()->slb_shadow_ptr) struct task_struct; struct rtas_args; +struct lppaca; /* * Defines the layout of the paca. diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h index f2b6bf5687d0..e5fcc79b5bfb 100644 --- a/arch/powerpc/include/asm/page.h +++ b/arch/powerpc/include/asm/page.h @@ -9,6 +9,7 @@ #ifndef __ASSEMBLY__ #include <linux/types.h> #include <linux/kernel.h> +#include <linux/bug.h> #else #include <asm/types.h> #endif @@ -119,16 +120,6 @@ extern long long virt_phys_offset; #define ARCH_PFN_OFFSET ((unsigned long)(MEMORY_START >> PAGE_SHIFT)) #endif -#define virt_to_pfn(kaddr) (__pa(kaddr) >> PAGE_SHIFT) -#define virt_to_page(kaddr) pfn_to_page(virt_to_pfn(kaddr)) -#define pfn_to_kaddr(pfn) __va((pfn) << PAGE_SHIFT) - -#define virt_addr_valid(vaddr) ({ \ - unsigned long _addr = (unsigned long)vaddr; \ - _addr >= PAGE_OFFSET && _addr < (unsigned long)high_memory && \ - pfn_valid(virt_to_pfn(_addr)); \ -}) - /* * On Book-E parts we need __va to parse the device tree and we can't * determine MEMORY_START until then. However we can determine PHYSICAL_START @@ -233,6 +224,25 @@ extern long long virt_phys_offset; #endif #endif +#ifndef __ASSEMBLY__ +static inline unsigned long virt_to_pfn(const void *kaddr) +{ + return __pa(kaddr) >> PAGE_SHIFT; +} + +static inline const void *pfn_to_kaddr(unsigned long pfn) +{ + return __va(pfn << PAGE_SHIFT); +} +#endif + +#define virt_to_page(kaddr) pfn_to_page(virt_to_pfn(kaddr)) +#define virt_addr_valid(vaddr) ({ \ + unsigned long _addr = (unsigned long)vaddr; \ + _addr >= PAGE_OFFSET && _addr < (unsigned long)high_memory && \ + pfn_valid(virt_to_pfn((void *)_addr)); \ +}) + /* * Unfortunately the PLT is in the BSS in the PPC32 ELF ABI, * and needs to be executable. This means the whole heap ends diff --git a/arch/powerpc/include/asm/paravirt.h b/arch/powerpc/include/asm/paravirt.h index f5ba1a3c41f8..e08513d73119 100644 --- a/arch/powerpc/include/asm/paravirt.h +++ b/arch/powerpc/include/asm/paravirt.h @@ -6,6 +6,7 @@ #include <asm/smp.h> #ifdef CONFIG_PPC64 #include <asm/paca.h> +#include <asm/lppaca.h> #include <asm/hvcall.h> #endif diff --git a/arch/powerpc/include/asm/pci.h b/arch/powerpc/include/asm/pci.h index 289f1ec85bc5..f5078a7dd85a 100644 --- a/arch/powerpc/include/asm/pci.h +++ b/arch/powerpc/include/asm/pci.h @@ -82,7 +82,8 @@ extern int pci_legacy_write(struct pci_bus *bus, loff_t port, u32 val, extern int pci_mmap_legacy_page_range(struct pci_bus *bus, struct vm_area_struct *vma, enum pci_mmap_state mmap_state); - +extern void pci_adjust_legacy_attr(struct pci_bus *bus, + enum pci_mmap_state mmap_type); #define HAVE_PCI_LEGACY 1 extern void pcibios_claim_one_bus(struct pci_bus *b); diff --git a/arch/powerpc/include/asm/pgalloc.h b/arch/powerpc/include/asm/pgalloc.h index 3360cad78ace..3a971e2a8c73 100644 --- a/arch/powerpc/include/asm/pgalloc.h +++ b/arch/powerpc/include/asm/pgalloc.h @@ -45,6 +45,10 @@ static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage) pte_fragment_free((unsigned long *)ptepage, 0); } +/* arch use pte_free_defer() implementation in arch/powerpc/mm/pgtable-frag.c */ +#define pte_free_defer pte_free_defer +void pte_free_defer(struct mm_struct *mm, pgtable_t pgtable); + /* * Functions that deal with pagetables that could be at any level of * the table need to be passed an "index_size" so they know how to diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h index 6a88bfdaa69b..d0ee46de248e 100644 --- a/arch/powerpc/include/asm/pgtable.h +++ b/arch/powerpc/include/asm/pgtable.h @@ -41,6 +41,12 @@ struct mm_struct; #ifndef __ASSEMBLY__ +void set_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, + pte_t pte, unsigned int nr); +#define set_ptes set_ptes +#define update_mmu_cache(vma, addr, ptep) \ + update_mmu_cache_range(NULL, vma, addr, ptep, 1) + #ifndef MAX_PTRS_PER_PGD #define MAX_PTRS_PER_PGD PTRS_PER_PGD #endif @@ -48,6 +54,12 @@ struct mm_struct; /* Keep these as a macros to avoid include dependency mess */ #define pte_page(x) pfn_to_page(pte_pfn(x)) #define mk_pte(page, pgprot) pfn_pte(page_to_pfn(page), (pgprot)) + +static inline unsigned long pte_pfn(pte_t pte) +{ + return (pte_val(pte) & PTE_RPN_MASK) >> PTE_RPN_SHIFT; +} + /* * Select all bits except the pfn */ @@ -60,9 +72,9 @@ static inline pgprot_t pte_pgprot(pte_t pte) } #ifndef pmd_page_vaddr -static inline unsigned long pmd_page_vaddr(pmd_t pmd) +static inline const void *pmd_page_vaddr(pmd_t pmd) { - return ((unsigned long)__va(pmd_val(pmd) & ~PMD_MASKED_BITS)); + return __va(pmd_val(pmd) & ~PMD_MASKED_BITS); } #define pmd_page_vaddr pmd_page_vaddr #endif @@ -158,13 +170,30 @@ static inline pgtable_t pmd_pgtable(pmd_t pmd) } #ifdef CONFIG_PPC64 -#define is_ioremap_addr is_ioremap_addr -static inline bool is_ioremap_addr(const void *x) +int __meminit vmemmap_populated(unsigned long vmemmap_addr, int vmemmap_map_size); +bool altmap_cross_boundary(struct vmem_altmap *altmap, unsigned long start, + unsigned long page_size); +/* + * mm/memory_hotplug.c:mhp_supports_memmap_on_memory goes into details + * some of the restrictions. We don't check for PMD_SIZE because our + * vmemmap allocation code can fallback correctly. The pageblock + * alignment requirement is met using altmap->reserve blocks. + */ +#define arch_supports_memmap_on_memory arch_supports_memmap_on_memory +static inline bool arch_supports_memmap_on_memory(unsigned long vmemmap_size) { - unsigned long addr = (unsigned long)x; - - return addr >= IOREMAP_BASE && addr < IOREMAP_END; + if (!radix_enabled()) + return false; + /* + * With 4K page size and 2M PMD_SIZE, we can align + * things better with memory block size value + * starting from 128MB. Hence align things with PMD_SIZE. + */ + if (IS_ENABLED(CONFIG_PPC_4K_PAGES)) + return IS_ALIGNED(vmemmap_size, PMD_SIZE); + return true; } + #endif /* CONFIG_PPC64 */ #endif /* __ASSEMBLY__ */ diff --git a/arch/powerpc/include/asm/plpar_wrappers.h b/arch/powerpc/include/asm/plpar_wrappers.h index 8239c0af5eb2..fe3d0ea0058a 100644 --- a/arch/powerpc/include/asm/plpar_wrappers.h +++ b/arch/powerpc/include/asm/plpar_wrappers.h @@ -9,6 +9,7 @@ #include <asm/hvcall.h> #include <asm/paca.h> +#include <asm/lppaca.h> #include <asm/page.h> static inline long poll_pending(void) diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h index ef6972aa33b9..005601243dda 100644 --- a/arch/powerpc/include/asm/ppc-opcode.h +++ b/arch/powerpc/include/asm/ppc-opcode.h @@ -397,6 +397,7 @@ #define PPC_RAW_RFCI (0x4c000066) #define PPC_RAW_RFDI (0x4c00004e) #define PPC_RAW_RFMCI (0x4c00004c) +#define PPC_RAW_TLBILX_LPID (0x7c000024) #define PPC_RAW_TLBILX(t, a, b) (0x7c000024 | __PPC_T_TLB(t) | __PPC_RA0(a) | __PPC_RB(b)) #define PPC_RAW_WAIT_v203 (0x7c00007c) #define PPC_RAW_WAIT(w, p) (0x7c00003c | __PPC_WC(w) | __PPC_PL(p)) @@ -616,6 +617,7 @@ #define PPC_TLBILX(t, a, b) stringify_in_c(.long PPC_RAW_TLBILX(t, a, b)) #define PPC_TLBILX_ALL(a, b) PPC_TLBILX(0, a, b) #define PPC_TLBILX_PID(a, b) PPC_TLBILX(1, a, b) +#define PPC_TLBILX_LPID stringify_in_c(.long PPC_RAW_TLBILX_LPID) #define PPC_TLBILX_VA(a, b) PPC_TLBILX(3, a, b) #define PPC_WAIT_v203 stringify_in_c(.long PPC_RAW_WAIT_v203) #define PPC_WAIT(w, p) stringify_in_c(.long PPC_RAW_WAIT(w, p)) diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h index 8a6754ffdc7e..b2c51d337e60 100644 --- a/arch/powerpc/include/asm/processor.h +++ b/arch/powerpc/include/asm/processor.h @@ -172,11 +172,6 @@ struct thread_struct { unsigned int align_ctl; /* alignment handling control */ #ifdef CONFIG_HAVE_HW_BREAKPOINT struct perf_event *ptrace_bps[HBP_NUM_MAX]; - /* - * Helps identify source of single-step exception and subsequent - * hw-breakpoint enablement - */ - struct perf_event *last_hit_ubp[HBP_NUM_MAX]; #endif /* CONFIG_HAVE_HW_BREAKPOINT */ struct arch_hw_breakpoint hw_brk[HBP_NUM_MAX]; /* hardware breakpoint info */ unsigned long trap_nr; /* last trap # on this thread */ @@ -393,7 +388,6 @@ int validate_sp_size(unsigned long sp, struct task_struct *p, */ #define ARCH_HAS_PREFETCH #define ARCH_HAS_PREFETCHW -#define ARCH_HAS_SPINLOCK_PREFETCH static inline void prefetch(const void *x) { @@ -411,8 +405,6 @@ static inline void prefetchw(const void *x) __asm__ __volatile__ ("dcbtst 0,%0" : : "r" (x)); } -#define spin_lock_prefetch(x) prefetchw(x) - /* asm stubs */ extern unsigned long isa300_idle_stop_noloss(unsigned long psscr_val); extern unsigned long isa300_idle_stop_mayloss(unsigned long psscr_val); diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index bb0121222ee3..4ae4ab9090a2 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -1414,11 +1414,9 @@ static inline void mtmsr_isync(unsigned long val) #define mfspr(rn) ({unsigned long rval; \ asm volatile("mfspr %0," __stringify(rn) \ : "=r" (rval)); rval;}) -#ifndef mtspr #define mtspr(rn, v) asm volatile("mtspr " __stringify(rn) ",%0" : \ : "r" ((unsigned long)(v)) \ : "memory") -#endif #define wrtspr(rn) asm volatile("mtspr " __stringify(rn) ",2" : : : "memory") static inline void wrtee(unsigned long val) diff --git a/arch/powerpc/include/asm/rtas.h b/arch/powerpc/include/asm/rtas.h index 3abe15ac79db..c697c3c74694 100644 --- a/arch/powerpc/include/asm/rtas.h +++ b/arch/powerpc/include/asm/rtas.h @@ -202,7 +202,9 @@ typedef struct { #define RTAS_USER_REGION_SIZE (64 * 1024) /* RTAS return status codes */ +#define RTAS_HARDWARE_ERROR -1 /* Hardware Error */ #define RTAS_BUSY -2 /* RTAS Busy */ +#define RTAS_INVALID_PARAMETER -3 /* Invalid indicator/domain/sensor etc. */ #define RTAS_EXTENDED_DELAY_MIN 9900 #define RTAS_EXTENDED_DELAY_MAX 9905 @@ -425,6 +427,7 @@ extern int rtas_set_indicator(int indicator, int index, int new_value); extern int rtas_set_indicator_fast(int indicator, int index, int new_value); extern void rtas_progress(char *s, unsigned short hex); int rtas_ibm_suspend_me(int *fw_status); +int rtas_error_rc(int rtas_rc); struct rtc_time; extern time64_t rtas_get_boot_time(void); diff --git a/arch/powerpc/include/asm/sections.h b/arch/powerpc/include/asm/sections.h index 4e1f548c8d37..ea26665f82cf 100644 --- a/arch/powerpc/include/asm/sections.h +++ b/arch/powerpc/include/asm/sections.h @@ -74,6 +74,8 @@ static inline int overlaps_kernel_text(unsigned long start, unsigned long end) (unsigned long)_stext < end; } +#else +static inline unsigned long kernel_toc_addr(void) { BUILD_BUG(); return -1UL; } #endif #endif /* __KERNEL__ */ diff --git a/arch/powerpc/include/asm/setup.h b/arch/powerpc/include/asm/setup.h index e29e83f8a89c..eed74c1fb832 100644 --- a/arch/powerpc/include/asm/setup.h +++ b/arch/powerpc/include/asm/setup.h @@ -8,7 +8,6 @@ extern void ppc_printk_progress(char *s, unsigned short hex); extern unsigned long long memory_limit; -extern void *zalloc_maybe_bootmem(size_t size, gfp_t mask); struct device_node; diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h index 8a4d4f4d9749..f4e6f2dd04b7 100644 --- a/arch/powerpc/include/asm/topology.h +++ b/arch/powerpc/include/asm/topology.h @@ -143,5 +143,20 @@ static inline int cpu_to_coregroup_id(int cpu) #endif #endif +#ifdef CONFIG_HOTPLUG_SMT +#include <linux/cpu_smt.h> +#include <asm/cputhreads.h> + +static inline bool topology_is_primary_thread(unsigned int cpu) +{ + return cpu == cpu_first_thread_sibling(cpu); +} + +static inline bool topology_smt_thread_allowed(unsigned int cpu) +{ + return cpu_thread_in_core(cpu) < cpu_smt_num_threads; +} +#endif + #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_TOPOLOGY_H */ diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h index a2d255aa9627..fb725ec77926 100644 --- a/arch/powerpc/include/asm/uaccess.h +++ b/arch/powerpc/include/asm/uaccess.h @@ -386,7 +386,7 @@ copy_mc_to_user(void __user *to, const void *from, unsigned long n) extern long __copy_from_user_flushcache(void *dst, const void __user *src, unsigned size); -static __must_check inline bool user_access_begin(const void __user *ptr, size_t len) +static __must_check __always_inline bool user_access_begin(const void __user *ptr, size_t len) { if (unlikely(!access_ok(ptr, len))) return false; @@ -401,7 +401,7 @@ static __must_check inline bool user_access_begin(const void __user *ptr, size_t #define user_access_save prevent_user_access_return #define user_access_restore restore_user_access -static __must_check inline bool +static __must_check __always_inline bool user_read_access_begin(const void __user *ptr, size_t len) { if (unlikely(!access_ok(ptr, len))) @@ -415,7 +415,7 @@ user_read_access_begin(const void __user *ptr, size_t len) #define user_read_access_begin user_read_access_begin #define user_read_access_end prevent_current_read_from_user -static __must_check inline bool +static __must_check __always_inline bool user_write_access_begin(const void __user *ptr, size_t len) { if (unlikely(!access_ok(ptr, len))) diff --git a/arch/powerpc/include/asm/vermagic.h b/arch/powerpc/include/asm/vermagic.h index b054a8576e5d..6f250fe506bd 100644 --- a/arch/powerpc/include/asm/vermagic.h +++ b/arch/powerpc/include/asm/vermagic.h @@ -2,7 +2,9 @@ #ifndef _ASM_VERMAGIC_H #define _ASM_VERMAGIC_H -#ifdef CONFIG_MPROFILE_KERNEL +#ifdef CONFIG_ARCH_USING_PATCHABLE_FUNCTION_ENTRY +#define MODULE_ARCH_VERMAGIC_FTRACE "patchable-function-entry " +#elif defined(CONFIG_MPROFILE_KERNEL) #define MODULE_ARCH_VERMAGIC_FTRACE "mprofile-kernel " #else #define MODULE_ARCH_VERMAGIC_FTRACE "" diff --git a/arch/powerpc/include/asm/vphn.h b/arch/powerpc/include/asm/vphn.h new file mode 100644 index 000000000000..8c2f795eea68 --- /dev/null +++ b/arch/powerpc/include/asm/vphn.h @@ -0,0 +1,24 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef _ASM_POWERPC_VPHN_H +#define _ASM_POWERPC_VPHN_H + +/* The H_HOME_NODE_ASSOCIATIVITY h_call returns 6 64-bit registers. */ +#define VPHN_REGISTER_COUNT 6 + +/* + * 6 64-bit registers unpacked into up to 24 be32 associativity values. To + * form the complete property we have to add the length in the first cell. + */ +#define VPHN_ASSOC_BUFSIZE (VPHN_REGISTER_COUNT*sizeof(u64)/sizeof(u16) + 1) + +/* + * The H_HOME_NODE_ASSOCIATIVITY hcall takes two values for flags: + * 1 for retrieving associativity information for a guest cpu + * 2 for retrieving associativity information for a host/hypervisor cpu + */ +#define VPHN_FLAG_VCPU 1 +#define VPHN_FLAG_PCPU 2 + +long hcall_vphn(unsigned long cpu, u64 flags, __be32 *associativity); + +#endif // _ASM_POWERPC_VPHN_H diff --git a/arch/powerpc/include/asm/word-at-a-time.h b/arch/powerpc/include/asm/word-at-a-time.h index 46c31fb8748d..30a12d208687 100644 --- a/arch/powerpc/include/asm/word-at-a-time.h +++ b/arch/powerpc/include/asm/word-at-a-time.h @@ -34,7 +34,7 @@ static inline long find_zero(unsigned long mask) return leading_zero_bits >> 3; } -static inline bool has_zero(unsigned long val, unsigned long *data, const struct word_at_a_time *c) +static inline unsigned long has_zero(unsigned long val, unsigned long *data, const struct word_at_a_time *c) { unsigned long rhs = val | c->low_bits; *data = rhs; diff --git a/arch/powerpc/kernel/audit.c b/arch/powerpc/kernel/audit.c index 1bcfca5fdf67..92298d6a3a37 100644 --- a/arch/powerpc/kernel/audit.c +++ b/arch/powerpc/kernel/audit.c @@ -4,6 +4,8 @@ #include <linux/audit.h> #include <asm/unistd.h> +#include "audit_32.h" + static unsigned dir_class[] = { #include <asm-generic/audit_dir_write.h> ~0U @@ -41,7 +43,6 @@ int audit_classify_arch(int arch) int audit_classify_syscall(int abi, unsigned syscall) { #ifdef CONFIG_PPC64 - extern int ppc32_classify_syscall(unsigned); if (abi == AUDIT_ARCH_PPC) return ppc32_classify_syscall(syscall); #endif diff --git a/arch/powerpc/kernel/audit_32.h b/arch/powerpc/kernel/audit_32.h new file mode 100644 index 000000000000..c6c79c3041ab --- /dev/null +++ b/arch/powerpc/kernel/audit_32.h @@ -0,0 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0 +#ifndef __AUDIT_32_H__ +#define __AUDIT_32_H__ + +extern int ppc32_classify_syscall(unsigned); + +#endif diff --git a/arch/powerpc/kernel/compat_audit.c b/arch/powerpc/kernel/compat_audit.c index d92ffe4e5dc1..57b38c592b9f 100644 --- a/arch/powerpc/kernel/compat_audit.c +++ b/arch/powerpc/kernel/compat_audit.c @@ -3,6 +3,8 @@ #include <linux/audit_arch.h> #include <asm/unistd.h> +#include "audit_32.h" + unsigned ppc32_dir_class[] = { #include <asm-generic/audit_dir_write.h> ~0U diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index 8a32bffefa5b..e97a0fd0ae90 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -75,6 +75,10 @@ static struct cpu_spec * __init setup_cpu_spec(unsigned long offset, t->cpu_features |= old.cpu_features & CPU_FTR_PMAO_BUG; } + /* Set kuap ON at startup, will be disabled later if cmdline has 'nosmap' */ + if (IS_ENABLED(CONFIG_PPC_KUAP) && IS_ENABLED(CONFIG_PPC32)) + t->mmu_features |= MMU_FTR_KUAP; + *PTRRELOC(&cur_cpu_spec) = &the_cpu_spec; /* diff --git a/arch/powerpc/kernel/dma-mask.c b/arch/powerpc/kernel/dma-mask.c index ffbbbc432612..5b07ca7b73aa 100644 --- a/arch/powerpc/kernel/dma-mask.c +++ b/arch/powerpc/kernel/dma-mask.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/dma-mapping.h> +#include <linux/dma-map-ops.h> #include <linux/export.h> #include <asm/machdep.h> diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S index fe27d41f9a3d..9692acb0361f 100644 --- a/arch/powerpc/kernel/entry_32.S +++ b/arch/powerpc/kernel/entry_32.S @@ -29,7 +29,6 @@ #include <asm/asm-offsets.h> #include <asm/unistd.h> #include <asm/ptrace.h> -#include <asm/export.h> #include <asm/feature-fixups.h> #include <asm/barrier.h> #include <asm/kup.h> diff --git a/arch/powerpc/kernel/epapr_hcalls.S b/arch/powerpc/kernel/epapr_hcalls.S index 033116e465d0..1a9b5ae8ccb2 100644 --- a/arch/powerpc/kernel/epapr_hcalls.S +++ b/arch/powerpc/kernel/epapr_hcalls.S @@ -3,6 +3,7 @@ * Copyright (C) 2012 Freescale Semiconductor, Inc. */ +#include <linux/export.h> #include <linux/threads.h> #include <asm/epapr_hcalls.h> #include <asm/reg.h> @@ -12,7 +13,6 @@ #include <asm/ppc_asm.h> #include <asm/asm-compat.h> #include <asm/asm-offsets.h> -#include <asm/export.h> #ifndef CONFIG_PPC64 /* epapr_ev_idle() was derived from e500_idle() */ diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c index ea0a073abd96..3ff2da7b120b 100644 --- a/arch/powerpc/kernel/fadump.c +++ b/arch/powerpc/kernel/fadump.c @@ -654,6 +654,7 @@ int __init fadump_reserve_mem(void) return ret; error_out: fw_dump.fadump_enabled = 0; + fw_dump.reserve_dump_area_size = 0; return 0; } diff --git a/arch/powerpc/kernel/fpu.S b/arch/powerpc/kernel/fpu.S index f71f2bbd4de6..6a9acfb690c9 100644 --- a/arch/powerpc/kernel/fpu.S +++ b/arch/powerpc/kernel/fpu.S @@ -9,6 +9,7 @@ * Copyright (C) 1997 Dan Malek (dmalek@jlc.net). */ +#include <linux/export.h> #include <asm/reg.h> #include <asm/page.h> #include <asm/mmu.h> @@ -18,7 +19,6 @@ #include <asm/ppc_asm.h> #include <asm/asm-offsets.h> #include <asm/ptrace.h> -#include <asm/export.h> #include <asm/asm-compat.h> #include <asm/feature-fixups.h> diff --git a/arch/powerpc/kernel/head_40x.S b/arch/powerpc/kernel/head_40x.S index 3f68a1624646..b32e7b2ebdcf 100644 --- a/arch/powerpc/kernel/head_40x.S +++ b/arch/powerpc/kernel/head_40x.S @@ -38,7 +38,6 @@ #include <asm/ppc_asm.h> #include <asm/asm-offsets.h> #include <asm/ptrace.h> -#include <asm/export.h> #include "head_32.h" diff --git a/arch/powerpc/kernel/head_44x.S b/arch/powerpc/kernel/head_44x.S index 63a85c16fef4..a3197c9f721c 100644 --- a/arch/powerpc/kernel/head_44x.S +++ b/arch/powerpc/kernel/head_44x.S @@ -35,7 +35,6 @@ #include <asm/asm-offsets.h> #include <asm/ptrace.h> #include <asm/synch.h> -#include <asm/export.h> #include <asm/code-patching-asm.h> #include "head_booke.h" diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S index f132d8704263..4690c219bfa4 100644 --- a/arch/powerpc/kernel/head_64.S +++ b/arch/powerpc/kernel/head_64.S @@ -40,7 +40,6 @@ #include <asm/hw_irq.h> #include <asm/cputhreads.h> #include <asm/ppc-opcode.h> -#include <asm/export.h> #include <asm/feature-fixups.h> #ifdef CONFIG_PPC_BOOK3S #include <asm/exception-64s.h> @@ -375,8 +374,7 @@ _GLOBAL(generic_secondary_smp_init) beq 20f /* start the specified thread */ - LOAD_REG_ADDR(r5, fsl_secondary_thread_init) - ld r4, 0(r5) + LOAD_REG_ADDR(r5, DOTSYM(fsl_secondary_thread_init)) bl book3e_start_thread /* stop the current thread */ diff --git a/arch/powerpc/kernel/head_85xx.S b/arch/powerpc/kernel/head_85xx.S index fdbee1093e2b..97e9ea0c7297 100644 --- a/arch/powerpc/kernel/head_85xx.S +++ b/arch/powerpc/kernel/head_85xx.S @@ -40,7 +40,6 @@ #include <asm/asm-offsets.h> #include <asm/cache.h> #include <asm/ptrace.h> -#include <asm/export.h> #include <asm/feature-fixups.h> #include "head_booke.h" diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S index a79751e05781..647b0b445e89 100644 --- a/arch/powerpc/kernel/head_8xx.S +++ b/arch/powerpc/kernel/head_8xx.S @@ -29,7 +29,6 @@ #include <asm/ppc_asm.h> #include <asm/asm-offsets.h> #include <asm/ptrace.h> -#include <asm/export.h> #include <asm/code-patching-asm.h> #include <asm/interrupt.h> diff --git a/arch/powerpc/kernel/head_book3s_32.S b/arch/powerpc/kernel/head_book3s_32.S index c51f28b5abc0..6764b98ca360 100644 --- a/arch/powerpc/kernel/head_book3s_32.S +++ b/arch/powerpc/kernel/head_book3s_32.S @@ -31,7 +31,6 @@ #include <asm/ptrace.h> #include <asm/bug.h> #include <asm/kvm_book3s_asm.h> -#include <asm/export.h> #include <asm/feature-fixups.h> #include <asm/interrupt.h> diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c index e1b4e70c8fd0..b8513dc3e53a 100644 --- a/arch/powerpc/kernel/hw_breakpoint.c +++ b/arch/powerpc/kernel/hw_breakpoint.c @@ -43,16 +43,6 @@ int hw_breakpoint_slots(int type) return 0; /* no instruction breakpoints available */ } -static bool single_step_pending(void) -{ - int i; - - for (i = 0; i < nr_wp_slots(); i++) { - if (current->thread.last_hit_ubp[i]) - return true; - } - return false; -} /* * Install a perf counter breakpoint. @@ -84,7 +74,7 @@ int arch_install_hw_breakpoint(struct perf_event *bp) * Do not install DABR values if the instruction must be single-stepped. * If so, DABR will be populated in single_step_dabr_instruction(). */ - if (!single_step_pending()) + if (!info->perf_single_step) __set_breakpoint(i, info); return 0; @@ -124,275 +114,6 @@ static bool is_ptrace_bp(struct perf_event *bp) return bp->overflow_handler == ptrace_triggered; } -struct breakpoint { - struct list_head list; - struct perf_event *bp; - bool ptrace_bp; -}; - -/* - * While kernel/events/hw_breakpoint.c does its own synchronization, we cannot - * rely on it safely synchronizing internals here; however, we can rely on it - * not requesting more breakpoints than available. - */ -static DEFINE_SPINLOCK(cpu_bps_lock); -static DEFINE_PER_CPU(struct breakpoint *, cpu_bps[HBP_NUM_MAX]); -static DEFINE_SPINLOCK(task_bps_lock); -static LIST_HEAD(task_bps); - -static struct breakpoint *alloc_breakpoint(struct perf_event *bp) -{ - struct breakpoint *tmp; - - tmp = kzalloc(sizeof(*tmp), GFP_KERNEL); - if (!tmp) - return ERR_PTR(-ENOMEM); - tmp->bp = bp; - tmp->ptrace_bp = is_ptrace_bp(bp); - return tmp; -} - -static bool bp_addr_range_overlap(struct perf_event *bp1, struct perf_event *bp2) -{ - __u64 bp1_saddr, bp1_eaddr, bp2_saddr, bp2_eaddr; - - bp1_saddr = ALIGN_DOWN(bp1->attr.bp_addr, HW_BREAKPOINT_SIZE); - bp1_eaddr = ALIGN(bp1->attr.bp_addr + bp1->attr.bp_len, HW_BREAKPOINT_SIZE); - bp2_saddr = ALIGN_DOWN(bp2->attr.bp_addr, HW_BREAKPOINT_SIZE); - bp2_eaddr = ALIGN(bp2->attr.bp_addr + bp2->attr.bp_len, HW_BREAKPOINT_SIZE); - - return (bp1_saddr < bp2_eaddr && bp1_eaddr > bp2_saddr); -} - -static bool alternate_infra_bp(struct breakpoint *b, struct perf_event *bp) -{ - return is_ptrace_bp(bp) ? !b->ptrace_bp : b->ptrace_bp; -} - -static bool can_co_exist(struct breakpoint *b, struct perf_event *bp) -{ - return !(alternate_infra_bp(b, bp) && bp_addr_range_overlap(b->bp, bp)); -} - -static int task_bps_add(struct perf_event *bp) -{ - struct breakpoint *tmp; - - tmp = alloc_breakpoint(bp); - if (IS_ERR(tmp)) - return PTR_ERR(tmp); - - spin_lock(&task_bps_lock); - list_add(&tmp->list, &task_bps); - spin_unlock(&task_bps_lock); - return 0; -} - -static void task_bps_remove(struct perf_event *bp) -{ - struct list_head *pos, *q; - - spin_lock(&task_bps_lock); - list_for_each_safe(pos, q, &task_bps) { - struct breakpoint *tmp = list_entry(pos, struct breakpoint, list); - - if (tmp->bp == bp) { - list_del(&tmp->list); - kfree(tmp); - break; - } - } - spin_unlock(&task_bps_lock); -} - -/* - * If any task has breakpoint from alternate infrastructure, - * return true. Otherwise return false. - */ -static bool all_task_bps_check(struct perf_event *bp) -{ - struct breakpoint *tmp; - bool ret = false; - - spin_lock(&task_bps_lock); - list_for_each_entry(tmp, &task_bps, list) { - if (!can_co_exist(tmp, bp)) { - ret = true; - break; - } - } - spin_unlock(&task_bps_lock); - return ret; -} - -/* - * If same task has breakpoint from alternate infrastructure, - * return true. Otherwise return false. - */ -static bool same_task_bps_check(struct perf_event *bp) -{ - struct breakpoint *tmp; - bool ret = false; - - spin_lock(&task_bps_lock); - list_for_each_entry(tmp, &task_bps, list) { - if (tmp->bp->hw.target == bp->hw.target && - !can_co_exist(tmp, bp)) { - ret = true; - break; - } - } - spin_unlock(&task_bps_lock); - return ret; -} - -static int cpu_bps_add(struct perf_event *bp) -{ - struct breakpoint **cpu_bp; - struct breakpoint *tmp; - int i = 0; - - tmp = alloc_breakpoint(bp); - if (IS_ERR(tmp)) - return PTR_ERR(tmp); - - spin_lock(&cpu_bps_lock); - cpu_bp = per_cpu_ptr(cpu_bps, bp->cpu); - for (i = 0; i < nr_wp_slots(); i++) { - if (!cpu_bp[i]) { - cpu_bp[i] = tmp; - break; - } - } - spin_unlock(&cpu_bps_lock); - return 0; -} - -static void cpu_bps_remove(struct perf_event *bp) -{ - struct breakpoint **cpu_bp; - int i = 0; - - spin_lock(&cpu_bps_lock); - cpu_bp = per_cpu_ptr(cpu_bps, bp->cpu); - for (i = 0; i < nr_wp_slots(); i++) { - if (!cpu_bp[i]) - continue; - - if (cpu_bp[i]->bp == bp) { - kfree(cpu_bp[i]); - cpu_bp[i] = NULL; - break; - } - } - spin_unlock(&cpu_bps_lock); -} - -static bool cpu_bps_check(int cpu, struct perf_event *bp) -{ - struct breakpoint **cpu_bp; - bool ret = false; - int i; - - spin_lock(&cpu_bps_lock); - cpu_bp = per_cpu_ptr(cpu_bps, cpu); - for (i = 0; i < nr_wp_slots(); i++) { - if (cpu_bp[i] && !can_co_exist(cpu_bp[i], bp)) { - ret = true; - break; - } - } - spin_unlock(&cpu_bps_lock); - return ret; -} - -static bool all_cpu_bps_check(struct perf_event *bp) -{ - int cpu; - - for_each_online_cpu(cpu) { - if (cpu_bps_check(cpu, bp)) - return true; - } - return false; -} - -int arch_reserve_bp_slot(struct perf_event *bp) -{ - int ret; - - /* ptrace breakpoint */ - if (is_ptrace_bp(bp)) { - if (all_cpu_bps_check(bp)) - return -ENOSPC; - - if (same_task_bps_check(bp)) - return -ENOSPC; - - return task_bps_add(bp); - } - - /* perf breakpoint */ - if (is_kernel_addr(bp->attr.bp_addr)) - return 0; - - if (bp->hw.target && bp->cpu == -1) { - if (same_task_bps_check(bp)) - return -ENOSPC; - - return task_bps_add(bp); - } else if (!bp->hw.target && bp->cpu != -1) { - if (all_task_bps_check(bp)) - return -ENOSPC; - - return cpu_bps_add(bp); - } - - if (same_task_bps_check(bp)) - return -ENOSPC; - - ret = cpu_bps_add(bp); - if (ret) - return ret; - ret = task_bps_add(bp); - if (ret) - cpu_bps_remove(bp); - - return ret; -} - -void arch_release_bp_slot(struct perf_event *bp) -{ - if (!is_kernel_addr(bp->attr.bp_addr)) { - if (bp->hw.target) - task_bps_remove(bp); - if (bp->cpu != -1) - cpu_bps_remove(bp); - } -} - -/* - * Perform cleanup of arch-specific counters during unregistration - * of the perf-event - */ -void arch_unregister_hw_breakpoint(struct perf_event *bp) -{ - /* - * If the breakpoint is unregistered between a hw_breakpoint_handler() - * and the single_step_dabr_instruction(), then cleanup the breakpoint - * restoration variables to prevent dangling pointers. - * FIXME, this should not be using bp->ctx at all! Sayeth peterz. - */ - if (bp->ctx && bp->ctx->task && bp->ctx->task != ((void *)-1L)) { - int i; - - for (i = 0; i < nr_wp_slots(); i++) { - if (bp->ctx->task->thread.last_hit_ubp[i] == bp) - bp->ctx->task->thread.last_hit_ubp[i] = NULL; - } - } -} - /* * Check for virtual address in kernel space. */ @@ -499,6 +220,10 @@ int hw_breakpoint_arch_parse(struct perf_event *bp, * Restores the breakpoint on the debug registers. * Invoke this function if it is known that the execution context is * about to change to cause loss of MSR_SE settings. + * + * The perf watchpoint will simply re-trigger once the thread is started again, + * and the watchpoint handler will set up MSR_SE and perf_single_step as + * needed. */ void thread_change_pc(struct task_struct *tsk, struct pt_regs *regs) { @@ -506,7 +231,9 @@ void thread_change_pc(struct task_struct *tsk, struct pt_regs *regs) int i; for (i = 0; i < nr_wp_slots(); i++) { - if (unlikely(tsk->thread.last_hit_ubp[i])) + struct perf_event *bp = __this_cpu_read(bp_per_reg[i]); + + if (unlikely(bp && counter_arch_bp(bp)->perf_single_step)) goto reset; } return; @@ -516,7 +243,7 @@ reset: for (i = 0; i < nr_wp_slots(); i++) { info = counter_arch_bp(__this_cpu_read(bp_per_reg[i])); __set_breakpoint(i, info); - tsk->thread.last_hit_ubp[i] = NULL; + info->perf_single_step = false; } } @@ -534,23 +261,22 @@ static bool is_octword_vsx_instr(int type, int size) * We've failed in reliably handling the hw-breakpoint. Unregister * it and throw a warning message to let the user know about it. */ -static void handler_error(struct perf_event *bp, struct arch_hw_breakpoint *info) +static void handler_error(struct perf_event *bp) { WARN(1, "Unable to handle hardware breakpoint. Breakpoint at 0x%lx will be disabled.", - info->address); + counter_arch_bp(bp)->address); perf_event_disable_inatomic(bp); } -static void larx_stcx_err(struct perf_event *bp, struct arch_hw_breakpoint *info) +static void larx_stcx_err(struct perf_event *bp) { printk_ratelimited("Breakpoint hit on instruction that can't be emulated. Breakpoint at 0x%lx will be disabled.\n", - info->address); + counter_arch_bp(bp)->address); perf_event_disable_inatomic(bp); } static bool stepping_handler(struct pt_regs *regs, struct perf_event **bp, - struct arch_hw_breakpoint **info, int *hit, - ppc_inst_t instr) + int *hit, ppc_inst_t instr) { int i; int stepped; @@ -560,8 +286,9 @@ static bool stepping_handler(struct pt_regs *regs, struct perf_event **bp, for (i = 0; i < nr_wp_slots(); i++) { if (!hit[i]) continue; - current->thread.last_hit_ubp[i] = bp[i]; - info[i] = NULL; + + counter_arch_bp(bp[i])->perf_single_step = true; + bp[i] = NULL; } regs_set_return_msr(regs, regs->msr | MSR_SE); return false; @@ -572,15 +299,15 @@ static bool stepping_handler(struct pt_regs *regs, struct perf_event **bp, for (i = 0; i < nr_wp_slots(); i++) { if (!hit[i]) continue; - handler_error(bp[i], info[i]); - info[i] = NULL; + handler_error(bp[i]); + bp[i] = NULL; } return false; } return true; } -static void handle_p10dd1_spurious_exception(struct arch_hw_breakpoint **info, +static void handle_p10dd1_spurious_exception(struct perf_event **bp, int *hit, unsigned long ea) { int i; @@ -592,10 +319,14 @@ static void handle_p10dd1_spurious_exception(struct arch_hw_breakpoint **info, * spurious exception. */ for (i = 0; i < nr_wp_slots(); i++) { - if (!info[i]) + struct arch_hw_breakpoint *info; + + if (!bp[i]) continue; - hw_end_addr = ALIGN(info[i]->address + info[i]->len, HW_BREAKPOINT_SIZE); + info = counter_arch_bp(bp[i]); + + hw_end_addr = ALIGN(info->address + info->len, HW_BREAKPOINT_SIZE); /* * Ending address of DAWR range is less than starting @@ -625,9 +356,9 @@ static void handle_p10dd1_spurious_exception(struct arch_hw_breakpoint **info, return; for (i = 0; i < nr_wp_slots(); i++) { - if (info[i]) { + if (bp[i]) { hit[i] = 1; - info[i]->type |= HW_BRK_TYPE_EXTRANEOUS_IRQ; + counter_arch_bp(bp[i])->type |= HW_BRK_TYPE_EXTRANEOUS_IRQ; } } } @@ -638,7 +369,6 @@ int hw_breakpoint_handler(struct die_args *args) int rc = NOTIFY_STOP; struct perf_event *bp[HBP_NUM_MAX] = { NULL }; struct pt_regs *regs = args->regs; - struct arch_hw_breakpoint *info[HBP_NUM_MAX] = { NULL }; int i; int hit[HBP_NUM_MAX] = {0}; int nr_hit = 0; @@ -663,18 +393,20 @@ int hw_breakpoint_handler(struct die_args *args) wp_get_instr_detail(regs, &instr, &type, &size, &ea); for (i = 0; i < nr_wp_slots(); i++) { + struct arch_hw_breakpoint *info; + bp[i] = __this_cpu_read(bp_per_reg[i]); if (!bp[i]) continue; - info[i] = counter_arch_bp(bp[i]); - info[i]->type &= ~HW_BRK_TYPE_EXTRANEOUS_IRQ; + info = counter_arch_bp(bp[i]); + info->type &= ~HW_BRK_TYPE_EXTRANEOUS_IRQ; - if (wp_check_constraints(regs, instr, ea, type, size, info[i])) { + if (wp_check_constraints(regs, instr, ea, type, size, info)) { if (!IS_ENABLED(CONFIG_PPC_8xx) && ppc_inst_equal(instr, ppc_inst(0))) { - handler_error(bp[i], info[i]); - info[i] = NULL; + handler_error(bp[i]); + bp[i] = NULL; err = 1; continue; } @@ -693,7 +425,7 @@ int hw_breakpoint_handler(struct die_args *args) /* Workaround for Power10 DD1 */ if (!IS_ENABLED(CONFIG_PPC_8xx) && mfspr(SPRN_PVR) == 0x800100 && is_octword_vsx_instr(type, size)) { - handle_p10dd1_spurious_exception(info, hit, ea); + handle_p10dd1_spurious_exception(bp, hit, ea); } else { rc = NOTIFY_DONE; goto out; @@ -708,10 +440,10 @@ int hw_breakpoint_handler(struct die_args *args) */ if (ptrace_bp) { for (i = 0; i < nr_wp_slots(); i++) { - if (!hit[i]) + if (!hit[i] || !is_ptrace_bp(bp[i])) continue; perf_bp_event(bp[i], regs); - info[i] = NULL; + bp[i] = NULL; } rc = NOTIFY_DONE; goto reset; @@ -722,13 +454,13 @@ int hw_breakpoint_handler(struct die_args *args) for (i = 0; i < nr_wp_slots(); i++) { if (!hit[i]) continue; - larx_stcx_err(bp[i], info[i]); - info[i] = NULL; + larx_stcx_err(bp[i]); + bp[i] = NULL; } goto reset; } - if (!stepping_handler(regs, bp, info, hit, instr)) + if (!stepping_handler(regs, bp, hit, instr)) goto reset; } @@ -739,15 +471,15 @@ int hw_breakpoint_handler(struct die_args *args) for (i = 0; i < nr_wp_slots(); i++) { if (!hit[i]) continue; - if (!(info[i]->type & HW_BRK_TYPE_EXTRANEOUS_IRQ)) + if (!(counter_arch_bp(bp[i])->type & HW_BRK_TYPE_EXTRANEOUS_IRQ)) perf_bp_event(bp[i], regs); } reset: for (i = 0; i < nr_wp_slots(); i++) { - if (!info[i]) + if (!bp[i]) continue; - __set_breakpoint(i, info[i]); + __set_breakpoint(i, counter_arch_bp(bp[i])); } out: @@ -762,24 +494,28 @@ NOKPROBE_SYMBOL(hw_breakpoint_handler); static int single_step_dabr_instruction(struct die_args *args) { struct pt_regs *regs = args->regs; - struct perf_event *bp = NULL; - struct arch_hw_breakpoint *info; - int i; bool found = false; /* * Check if we are single-stepping as a result of a * previous HW Breakpoint exception */ - for (i = 0; i < nr_wp_slots(); i++) { - bp = current->thread.last_hit_ubp[i]; + for (int i = 0; i < nr_wp_slots(); i++) { + struct perf_event *bp; + struct arch_hw_breakpoint *info; + + bp = __this_cpu_read(bp_per_reg[i]); if (!bp) continue; - found = true; info = counter_arch_bp(bp); + if (!info->perf_single_step) + continue; + + found = true; + /* * We shall invoke the user-defined callback function in the * single stepping handler to confirm to 'trigger-after-execute' @@ -787,26 +523,16 @@ static int single_step_dabr_instruction(struct die_args *args) */ if (!(info->type & HW_BRK_TYPE_EXTRANEOUS_IRQ)) perf_bp_event(bp, regs); - current->thread.last_hit_ubp[i] = NULL; - } - if (!found) - return NOTIFY_DONE; - - for (i = 0; i < nr_wp_slots(); i++) { - bp = __this_cpu_read(bp_per_reg[i]); - if (!bp) - continue; - - info = counter_arch_bp(bp); - __set_breakpoint(i, info); + info->perf_single_step = false; + __set_breakpoint(i, counter_arch_bp(bp)); } /* * If the process was being single-stepped by ptrace, let the * other single-step actions occur (e.g. generate SIGTRAP). */ - if (test_thread_flag(TIF_SINGLESTEP)) + if (!found || test_thread_flag(TIF_SINGLESTEP)) return NOTIFY_DONE; return NOTIFY_STOP; diff --git a/arch/powerpc/kernel/ima_arch.c b/arch/powerpc/kernel/ima_arch.c index 957abd592075..b7029beed847 100644 --- a/arch/powerpc/kernel/ima_arch.c +++ b/arch/powerpc/kernel/ima_arch.c @@ -23,9 +23,9 @@ bool arch_ima_get_secureboot(void) * is not enabled. */ static const char *const secure_rules[] = { - "appraise func=KEXEC_KERNEL_CHECK appraise_flag=check_blacklist appraise_type=imasig|modsig", + "appraise func=KEXEC_KERNEL_CHECK appraise_type=imasig|modsig", #ifndef CONFIG_MODULE_SIG - "appraise func=MODULE_CHECK appraise_flag=check_blacklist appraise_type=imasig|modsig", + "appraise func=MODULE_CHECK appraise_type=imasig|modsig", #endif NULL }; @@ -49,9 +49,9 @@ static const char *const trusted_rules[] = { 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", + "appraise func=KEXEC_KERNEL_CHECK appraise_type=imasig|modsig", #ifndef CONFIG_MODULE_SIG - "appraise func=MODULE_CHECK appraise_flag=check_blacklist appraise_type=imasig|modsig", + "appraise func=MODULE_CHECK appraise_type=imasig|modsig", #endif NULL }; diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index c52449ae6936..14251bc5219e 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -172,17 +172,28 @@ static int fail_iommu_bus_notify(struct notifier_block *nb, return 0; } -static struct notifier_block fail_iommu_bus_notifier = { +/* + * PCI and VIO buses need separate notifier_block structs, since they're linked + * list nodes. Sharing a notifier_block would mean that any notifiers later + * registered for PCI buses would also get called by VIO buses and vice versa. + */ +static struct notifier_block fail_iommu_pci_bus_notifier = { .notifier_call = fail_iommu_bus_notify }; +#ifdef CONFIG_IBMVIO +static struct notifier_block fail_iommu_vio_bus_notifier = { + .notifier_call = fail_iommu_bus_notify +}; +#endif + static int __init fail_iommu_setup(void) { #ifdef CONFIG_PCI - bus_register_notifier(&pci_bus_type, &fail_iommu_bus_notifier); + bus_register_notifier(&pci_bus_type, &fail_iommu_pci_bus_notifier); #endif #ifdef CONFIG_IBMVIO - bus_register_notifier(&vio_bus_type, &fail_iommu_bus_notifier); + bus_register_notifier(&vio_bus_type, &fail_iommu_vio_bus_notifier); #endif return 0; diff --git a/arch/powerpc/kernel/legacy_serial.c b/arch/powerpc/kernel/legacy_serial.c index 6ee65741dbd5..1da2f6e7d2a1 100644 --- a/arch/powerpc/kernel/legacy_serial.c +++ b/arch/powerpc/kernel/legacy_serial.c @@ -5,8 +5,8 @@ #include <linux/serial_core.h> #include <linux/console.h> #include <linux/pci.h> +#include <linux/of.h> #include <linux/of_address.h> -#include <linux/of_device.h> #include <linux/of_irq.h> #include <linux/serial_reg.h> #include <asm/io.h> diff --git a/arch/powerpc/kernel/misc.S b/arch/powerpc/kernel/misc.S index fb7de3543c03..29e1440d14cc 100644 --- a/arch/powerpc/kernel/misc.S +++ b/arch/powerpc/kernel/misc.S @@ -10,11 +10,11 @@ * * setjmp/longjmp code by Paul Mackerras. */ +#include <linux/export.h> #include <asm/ppc_asm.h> #include <asm/unistd.h> #include <asm/asm-compat.h> #include <asm/asm-offsets.h> -#include <asm/export.h> .text diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S index daf8f87d2372..2eabb15687a6 100644 --- a/arch/powerpc/kernel/misc_32.S +++ b/arch/powerpc/kernel/misc_32.S @@ -8,6 +8,7 @@ * */ +#include <linux/export.h> #include <linux/sys.h> #include <asm/unistd.h> #include <asm/errno.h> @@ -22,7 +23,6 @@ #include <asm/processor.h> #include <asm/bug.h> #include <asm/ptrace.h> -#include <asm/export.h> #include <asm/feature-fixups.h> .text diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S index 2c9ac70aaf0c..1a8cdafd68e8 100644 --- a/arch/powerpc/kernel/misc_64.S +++ b/arch/powerpc/kernel/misc_64.S @@ -9,6 +9,7 @@ * PPC64 updates by Dave Engebretsen (engebret@us.ibm.com) */ +#include <linux/export.h> #include <linux/linkage.h> #include <linux/sys.h> #include <asm/unistd.h> @@ -23,7 +24,6 @@ #include <asm/kexec.h> #include <asm/ptrace.h> #include <asm/mmu.h> -#include <asm/export.h> #include <asm/feature-fixups.h> .text diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c index 92570289ce08..7112adc597a8 100644 --- a/arch/powerpc/kernel/module_64.c +++ b/arch/powerpc/kernel/module_64.c @@ -465,7 +465,7 @@ int module_frob_arch_sections(Elf64_Ehdr *hdr, return 0; } -#ifdef CONFIG_MPROFILE_KERNEL +#if defined(CONFIG_MPROFILE_KERNEL) || defined(CONFIG_ARCH_USING_PATCHABLE_FUNCTION_ENTRY) static u32 stub_insns[] = { #ifdef CONFIG_PPC_KERNEL_PCREL diff --git a/arch/powerpc/kernel/of_platform.c b/arch/powerpc/kernel/of_platform.c index f89376ff633e..adc76fa58d1e 100644 --- a/arch/powerpc/kernel/of_platform.c +++ b/arch/powerpc/kernel/of_platform.c @@ -13,9 +13,7 @@ #include <linux/export.h> #include <linux/mod_devicetable.h> #include <linux/pci.h> -#include <linux/of.h> -#include <linux/of_device.h> -#include <linux/of_platform.h> +#include <linux/platform_device.h> #include <linux/atomic.h> #include <asm/errno.h> diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index e88d7c9feeec..040255ddb569 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -125,7 +125,7 @@ struct pci_controller *pcibios_alloc_controller(struct device_node *dev) { struct pci_controller *phb; - phb = zalloc_maybe_bootmem(sizeof(struct pci_controller), GFP_KERNEL); + phb = kzalloc(sizeof(struct pci_controller), GFP_KERNEL); if (phb == NULL) return NULL; diff --git a/arch/powerpc/kernel/pmc.c b/arch/powerpc/kernel/pmc.c index 15414c8a2837..9fabb4d9235e 100644 --- a/arch/powerpc/kernel/pmc.c +++ b/arch/powerpc/kernel/pmc.c @@ -74,7 +74,7 @@ void release_pmc_hardware(void) } EXPORT_SYMBOL_GPL(release_pmc_hardware); -#ifdef CONFIG_PPC64 +#ifdef CONFIG_PPC_BOOK3S_64 void power4_enable_pmcs(void) { unsigned long hid0; diff --git a/arch/powerpc/kernel/ptrace/ptrace-view.c b/arch/powerpc/kernel/ptrace/ptrace-view.c index 3910cd7bb2d9..584cf5c3df50 100644 --- a/arch/powerpc/kernel/ptrace/ptrace-view.c +++ b/arch/powerpc/kernel/ptrace/ptrace-view.c @@ -716,69 +716,86 @@ int gpr32_get_common(struct task_struct *target, return membuf_zero(&to, (ELF_NGREG - PT_REGS_COUNT) * sizeof(u32)); } -int gpr32_set_common(struct task_struct *target, - const struct user_regset *regset, - unsigned int pos, unsigned int count, - const void *kbuf, const void __user *ubuf, - unsigned long *regs) +static int gpr32_set_common_kernel(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, unsigned long *regs) { const compat_ulong_t *k = kbuf; + + pos /= sizeof(compat_ulong_t); + count /= sizeof(compat_ulong_t); + + for (; count > 0 && pos < PT_MSR; --count) + regs[pos++] = *k++; + + if (count > 0 && pos == PT_MSR) { + set_user_msr(target, *k++); + ++pos; + --count; + } + + for (; count > 0 && pos <= PT_MAX_PUT_REG; --count) + regs[pos++] = *k++; + for (; count > 0 && pos < PT_TRAP; --count, ++pos) + ++k; + + if (count > 0 && pos == PT_TRAP) { + set_user_trap(target, *k++); + ++pos; + --count; + } + + kbuf = k; + pos *= sizeof(compat_ulong_t); + count *= sizeof(compat_ulong_t); + user_regset_copyin_ignore(&pos, &count, &kbuf, NULL, + (PT_TRAP + 1) * sizeof(compat_ulong_t), -1); + return 0; +} + +static int gpr32_set_common_user(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void __user *ubuf, unsigned long *regs) +{ const compat_ulong_t __user *u = ubuf; + const void *kbuf = NULL; compat_ulong_t reg; - if (!kbuf && !user_read_access_begin(u, count)) + if (!user_read_access_begin(u, count)) return -EFAULT; pos /= sizeof(reg); count /= sizeof(reg); - if (kbuf) - for (; count > 0 && pos < PT_MSR; --count) - regs[pos++] = *k++; - else - for (; count > 0 && pos < PT_MSR; --count) { - unsafe_get_user(reg, u++, Efault); - regs[pos++] = reg; - } - + for (; count > 0 && pos < PT_MSR; --count) { + unsafe_get_user(reg, u++, Efault); + regs[pos++] = reg; + } if (count > 0 && pos == PT_MSR) { - if (kbuf) - reg = *k++; - else - unsafe_get_user(reg, u++, Efault); + unsafe_get_user(reg, u++, Efault); set_user_msr(target, reg); ++pos; --count; } - if (kbuf) { - for (; count > 0 && pos <= PT_MAX_PUT_REG; --count) - regs[pos++] = *k++; - for (; count > 0 && pos < PT_TRAP; --count, ++pos) - ++k; - } else { - for (; count > 0 && pos <= PT_MAX_PUT_REG; --count) { - unsafe_get_user(reg, u++, Efault); - regs[pos++] = reg; - } - for (; count > 0 && pos < PT_TRAP; --count, ++pos) - unsafe_get_user(reg, u++, Efault); + for (; count > 0 && pos <= PT_MAX_PUT_REG; --count) { + unsafe_get_user(reg, u++, Efault); + regs[pos++] = reg; } + for (; count > 0 && pos < PT_TRAP; --count, ++pos) + unsafe_get_user(reg, u++, Efault); if (count > 0 && pos == PT_TRAP) { - if (kbuf) - reg = *k++; - else - unsafe_get_user(reg, u++, Efault); + unsafe_get_user(reg, u++, Efault); set_user_trap(target, reg); ++pos; --count; } - if (!kbuf) - user_read_access_end(); + user_read_access_end(); - kbuf = k; ubuf = u; pos *= sizeof(reg); count *= sizeof(reg); @@ -791,6 +808,18 @@ Efault: return -EFAULT; } +int gpr32_set_common(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf, + unsigned long *regs) +{ + if (kbuf) + return gpr32_set_common_kernel(target, regset, pos, count, kbuf, regs); + else + return gpr32_set_common_user(target, regset, pos, count, ubuf, regs); +} + static int gpr32_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c index c087eeee320f..eddc031c4b95 100644 --- a/arch/powerpc/kernel/rtas.c +++ b/arch/powerpc/kernel/rtas.c @@ -1330,33 +1330,34 @@ bool __ref rtas_busy_delay(int status) } EXPORT_SYMBOL_GPL(rtas_busy_delay); -static int rtas_error_rc(int rtas_rc) +int rtas_error_rc(int rtas_rc) { int rc; switch (rtas_rc) { - case -1: /* Hardware Error */ - rc = -EIO; - break; - case -3: /* Bad indicator/domain/etc */ - rc = -EINVAL; - break; - case -9000: /* Isolation error */ - rc = -EFAULT; - break; - case -9001: /* Outstanding TCE/PTE */ - rc = -EEXIST; - break; - case -9002: /* No usable slot */ - rc = -ENODEV; - break; - default: - pr_err("%s: unexpected error %d\n", __func__, rtas_rc); - rc = -ERANGE; - break; + case RTAS_HARDWARE_ERROR: /* Hardware Error */ + rc = -EIO; + break; + case RTAS_INVALID_PARAMETER: /* Bad indicator/domain/etc */ + rc = -EINVAL; + break; + case -9000: /* Isolation error */ + rc = -EFAULT; + break; + case -9001: /* Outstanding TCE/PTE */ + rc = -EEXIST; + break; + case -9002: /* No usable slot */ + rc = -ENODEV; + break; + default: + pr_err("%s: unexpected error %d\n", __func__, rtas_rc); + rc = -ERANGE; + break; } return rc; } +EXPORT_SYMBOL_GPL(rtas_error_rc); int rtas_get_power_level(int powerdomain, int *level) { @@ -1587,6 +1588,7 @@ static bool ibm_extended_os_term; void rtas_os_term(char *str) { s32 token = rtas_function_token(RTAS_FN_IBM_OS_TERM); + static struct rtas_args args; int status; /* @@ -1607,7 +1609,8 @@ void rtas_os_term(char *str) * schedules. */ do { - status = rtas_call(token, 1, 1, NULL, __pa(rtas_os_term_buf)); + rtas_call_unlocked(&args, token, 1, 1, NULL, __pa(rtas_os_term_buf)); + status = be32_to_cpu(args.rets[0]); } while (rtas_busy_delay_time(status)); if (status != 0) diff --git a/arch/powerpc/kernel/rtas_flash.c b/arch/powerpc/kernel/rtas_flash.c index 4caf5e3079eb..359577ec1680 100644 --- a/arch/powerpc/kernel/rtas_flash.c +++ b/arch/powerpc/kernel/rtas_flash.c @@ -709,9 +709,9 @@ static int __init rtas_flash_init(void) if (!rtas_validate_flash_data.buf) return -ENOMEM; - flash_block_cache = kmem_cache_create("rtas_flash_cache", - RTAS_BLK_SIZE, RTAS_BLK_SIZE, 0, - NULL); + flash_block_cache = kmem_cache_create_usercopy("rtas_flash_cache", + RTAS_BLK_SIZE, RTAS_BLK_SIZE, + 0, 0, RTAS_BLK_SIZE, NULL); if (!flash_block_cache) { printk(KERN_ERR "%s: failed to create block cache\n", __func__); diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index d2a446216444..2f1026fba00d 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -31,9 +31,9 @@ #include <linux/serial_8250.h> #include <linux/percpu.h> #include <linux/memblock.h> -#include <linux/of_irq.h> +#include <linux/of.h> #include <linux/of_fdt.h> -#include <linux/of_platform.h> +#include <linux/of_irq.h> #include <linux/hugetlb.h> #include <linux/pgtable.h> #include <asm/io.h> @@ -969,8 +969,12 @@ void __init setup_arch(char **cmdline_p) klp_init_thread_info(&init_task); setup_initial_init_mm(_stext, _etext, _edata, _end); - + /* sched_init() does the mmgrab(&init_mm) for the primary CPU */ + VM_WARN_ON(cpumask_test_cpu(smp_processor_id(), mm_cpumask(&init_mm))); + cpumask_set_cpu(smp_processor_id(), mm_cpumask(&init_mm)); + inc_mm_active_cpus(&init_mm); mm_iommu_init(&init_mm); + irqstack_early_init(); exc_lvl_early_init(); emergency_stack_init(); diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index fbbb695bae3d..5826f5108a12 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -47,6 +47,7 @@ #include <asm/smp.h> #include <asm/time.h> #include <asm/machdep.h> +#include <asm/mmu_context.h> #include <asm/cputhreads.h> #include <asm/cputable.h> #include <asm/mpic.h> @@ -1087,7 +1088,7 @@ static int __init init_big_cores(void) void __init smp_prepare_cpus(unsigned int max_cpus) { - unsigned int cpu; + unsigned int cpu, num_threads; DBG("smp_prepare_cpus\n"); @@ -1154,6 +1155,12 @@ void __init smp_prepare_cpus(unsigned int max_cpus) if (smp_ops && smp_ops->probe) smp_ops->probe(); + + // Initalise the generic SMT topology support + num_threads = 1; + if (smt_enabled_at_boot) + num_threads = smt_enabled_at_boot; + cpu_smt_set_num_threads(num_threads, threads_per_core); } void smp_prepare_boot_cpu(void) @@ -1616,6 +1623,9 @@ void start_secondary(void *unused) mmgrab_lazy_tlb(&init_mm); current->active_mm = &init_mm; + VM_WARN_ON(cpumask_test_cpu(smp_processor_id(), mm_cpumask(&init_mm))); + cpumask_set_cpu(cpu, mm_cpumask(&init_mm)); + inc_mm_active_cpus(&init_mm); smp_store_cpu_info(cpu); set_dec(tb_ticks_per_jiffy); @@ -1751,6 +1761,14 @@ int __cpu_disable(void) void __cpu_die(unsigned int cpu) { + /* + * This could perhaps be a generic call in idlea_task_dead(), but + * that requires testing from all archs, so first put it here to + */ + VM_WARN_ON_ONCE(!cpumask_test_cpu(cpu, mm_cpumask(&init_mm))); + dec_mm_active_cpus(&init_mm); + cpumask_clear_cpu(cpu, mm_cpumask(&init_mm)); + if (smp_ops->cpu_die) smp_ops->cpu_die(cpu); } diff --git a/arch/powerpc/kernel/stacktrace.c b/arch/powerpc/kernel/stacktrace.c index 5de8597eaab8..b15f15dcacb5 100644 --- a/arch/powerpc/kernel/stacktrace.c +++ b/arch/powerpc/kernel/stacktrace.c @@ -221,8 +221,8 @@ static void raise_backtrace_ipi(cpumask_t *mask) } } -void arch_trigger_cpumask_backtrace(const cpumask_t *mask, bool exclude_self) +void arch_trigger_cpumask_backtrace(const cpumask_t *mask, int exclude_cpu) { - nmi_trigger_cpumask_backtrace(mask, exclude_self, raise_backtrace_ipi); + nmi_trigger_cpumask_backtrace(mask, exclude_cpu, raise_backtrace_ipi); } #endif /* defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_NMI_IPI) */ diff --git a/arch/powerpc/kernel/syscall.c b/arch/powerpc/kernel/syscall.c index 18b9d325395f..77fedb190c93 100644 --- a/arch/powerpc/kernel/syscall.c +++ b/arch/powerpc/kernel/syscall.c @@ -46,7 +46,7 @@ notrace long system_call_exception(struct pt_regs *regs, unsigned long r0) iamr = mfspr(SPRN_IAMR); regs->amr = amr; regs->iamr = iamr; - if (mmu_has_feature(MMU_FTR_BOOK3S_KUAP)) { + if (mmu_has_feature(MMU_FTR_KUAP)) { mtspr(SPRN_AMR, AMR_KUAP_BLOCKED); flush_needed = true; } diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl index 8c0b08b7a80e..20e50586e8a2 100644 --- a/arch/powerpc/kernel/syscalls/syscall.tbl +++ b/arch/powerpc/kernel/syscalls/syscall.tbl @@ -538,3 +538,4 @@ 449 common futex_waitv sys_futex_waitv 450 nospu set_mempolicy_home_node sys_set_mempolicy_home_node 451 common cachestat sys_cachestat +452 common fchmodat2 sys_fchmodat2 diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S index 9feab5e0485b..a9cd6507163a 100644 --- a/arch/powerpc/kernel/tm.S +++ b/arch/powerpc/kernel/tm.S @@ -6,13 +6,13 @@ * Copyright 2012 Matt Evans & Michael Neuling, IBM Corporation. */ +#include <linux/export.h> #include <asm/asm-offsets.h> #include <asm/ppc_asm.h> #include <asm/ppc-opcode.h> #include <asm/ptrace.h> #include <asm/reg.h> #include <asm/bug.h> -#include <asm/export.h> #include <asm/feature-fixups.h> #ifdef CONFIG_VSX diff --git a/arch/powerpc/kernel/trace/Makefile b/arch/powerpc/kernel/trace/Makefile index b16a9f9c0b35..125f4ca588b9 100644 --- a/arch/powerpc/kernel/trace/Makefile +++ b/arch/powerpc/kernel/trace/Makefile @@ -6,15 +6,15 @@ ifdef CONFIG_FUNCTION_TRACER # do not trace tracer code CFLAGS_REMOVE_ftrace.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_ftrace_64_pg.o = $(CC_FLAGS_FTRACE) endif -obj32-$(CONFIG_FUNCTION_TRACER) += ftrace_mprofile.o +obj32-$(CONFIG_FUNCTION_TRACER) += ftrace.o ftrace_entry.o ifdef CONFIG_MPROFILE_KERNEL -obj64-$(CONFIG_FUNCTION_TRACER) += ftrace_mprofile.o +obj64-$(CONFIG_FUNCTION_TRACER) += ftrace.o ftrace_entry.o else -obj64-$(CONFIG_FUNCTION_TRACER) += ftrace_64_pg.o +obj64-$(CONFIG_FUNCTION_TRACER) += ftrace_64_pg.o ftrace_64_pg_entry.o endif -obj-$(CONFIG_FUNCTION_TRACER) += ftrace_low.o ftrace.o obj-$(CONFIG_TRACING) += trace_clock.o obj-$(CONFIG_PPC64) += $(obj64-y) @@ -25,3 +25,7 @@ GCOV_PROFILE_ftrace.o := n KCOV_INSTRUMENT_ftrace.o := n KCSAN_SANITIZE_ftrace.o := n UBSAN_SANITIZE_ftrace.o := n +GCOV_PROFILE_ftrace_64_pg.o := n +KCOV_INSTRUMENT_ftrace_64_pg.o := n +KCSAN_SANITIZE_ftrace_64_pg.o := n +UBSAN_SANITIZE_ftrace_64_pg.o := n diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c index a47f30373423..82010629cf88 100644 --- a/arch/powerpc/kernel/trace/ftrace.c +++ b/arch/powerpc/kernel/trace/ftrace.c @@ -28,203 +28,64 @@ #include <asm/syscall.h> #include <asm/inst.h> -/* - * We generally only have a single long_branch tramp and at most 2 or 3 plt - * tramps generated. But, we don't use the plt tramps currently. We also allot - * 2 tramps after .text and .init.text. So, we only end up with around 3 usable - * tramps in total. Set aside 8 just to be sure. - */ -#define NUM_FTRACE_TRAMPS 8 +#define NUM_FTRACE_TRAMPS 2 static unsigned long ftrace_tramps[NUM_FTRACE_TRAMPS]; -static ppc_inst_t -ftrace_call_replace(unsigned long ip, unsigned long addr, int link) +static ppc_inst_t ftrace_create_branch_inst(unsigned long ip, unsigned long addr, int link) { ppc_inst_t op; - addr = ppc_function_entry((void *)addr); - - /* if (link) set op to 'bl' else 'b' */ + WARN_ON(!is_offset_in_branch_range(addr - ip)); create_branch(&op, (u32 *)ip, addr, link ? BRANCH_SET_LINK : 0); return op; } -static inline int -ftrace_modify_code(unsigned long ip, ppc_inst_t old, ppc_inst_t new) +static inline int ftrace_read_inst(unsigned long ip, ppc_inst_t *op) { - ppc_inst_t replaced; - - /* - * Note: - * We are paranoid about modifying text, as if a bug was to happen, it - * could cause us to read or write to someplace that could cause harm. - * Carefully read and modify the code with probe_kernel_*(), and make - * sure what we read is what we expected it to be before modifying it. - */ - - /* read the text we want to modify */ - if (copy_inst_from_kernel_nofault(&replaced, (void *)ip)) + if (copy_inst_from_kernel_nofault(op, (void *)ip)) { + pr_err("0x%lx: fetching instruction failed\n", ip); return -EFAULT; - - /* Make sure it is what we expect it to be */ - if (!ppc_inst_equal(replaced, old)) { - pr_err("%p: replaced (%08lx) != old (%08lx)", (void *)ip, - ppc_inst_as_ulong(replaced), ppc_inst_as_ulong(old)); - return -EINVAL; } - /* replace the text with the new text */ - return patch_instruction((u32 *)ip, new); + return 0; } -/* - * Helper functions that are the same for both PPC64 and PPC32. - */ -static int test_24bit_addr(unsigned long ip, unsigned long addr) +static inline int ftrace_validate_inst(unsigned long ip, ppc_inst_t inst) { - addr = ppc_function_entry((void *)addr); - - return is_offset_in_branch_range(addr - ip); -} + ppc_inst_t op; + int ret; -static int is_bl_op(ppc_inst_t op) -{ - return (ppc_inst_val(op) & ~PPC_LI_MASK) == PPC_RAW_BL(0); -} + ret = ftrace_read_inst(ip, &op); + if (!ret && !ppc_inst_equal(op, inst)) { + pr_err("0x%lx: expected (%08lx) != found (%08lx)\n", + ip, ppc_inst_as_ulong(inst), ppc_inst_as_ulong(op)); + ret = -EINVAL; + } -static int is_b_op(ppc_inst_t op) -{ - return (ppc_inst_val(op) & ~PPC_LI_MASK) == PPC_RAW_BRANCH(0); + return ret; } -static unsigned long find_bl_target(unsigned long ip, ppc_inst_t op) +static inline int ftrace_modify_code(unsigned long ip, ppc_inst_t old, ppc_inst_t new) { - int offset; + int ret = ftrace_validate_inst(ip, old); - offset = PPC_LI(ppc_inst_val(op)); - /* make it signed */ - if (offset & 0x02000000) - offset |= 0xfe000000; + if (!ret) + ret = patch_instruction((u32 *)ip, new); - return ip + (long)offset; + return ret; } -#ifdef CONFIG_MODULES -static int -__ftrace_make_nop(struct module *mod, - struct dyn_ftrace *rec, unsigned long addr) -{ - unsigned long entry, ptr, tramp; - unsigned long ip = rec->ip; - ppc_inst_t op, pop; - - /* read where this goes */ - if (copy_inst_from_kernel_nofault(&op, (void *)ip)) { - pr_err("Fetching opcode failed.\n"); - return -EFAULT; - } - - /* Make sure that this is still a 24bit jump */ - if (!is_bl_op(op)) { - pr_err("Not expected bl: opcode is %08lx\n", ppc_inst_as_ulong(op)); - return -EINVAL; - } - - /* lets find where the pointer goes */ - tramp = find_bl_target(ip, op); - - pr_devel("ip:%lx jumps to %lx", ip, tramp); - - if (module_trampoline_target(mod, tramp, &ptr)) { - pr_err("Failed to get trampoline target\n"); - return -EFAULT; - } - - pr_devel("trampoline target %lx", ptr); - - entry = ppc_global_function_entry((void *)addr); - /* This should match what was called */ - if (ptr != entry) { - pr_err("addr %lx does not match expected %lx\n", ptr, entry); - return -EINVAL; - } - - if (IS_ENABLED(CONFIG_MPROFILE_KERNEL)) { - if (copy_inst_from_kernel_nofault(&op, (void *)(ip - 4))) { - pr_err("Fetching instruction at %lx failed.\n", ip - 4); - return -EFAULT; - } - - /* We expect either a mflr r0, or a std r0, LRSAVE(r1) */ - if (!ppc_inst_equal(op, ppc_inst(PPC_RAW_MFLR(_R0))) && - !ppc_inst_equal(op, ppc_inst(PPC_INST_STD_LR))) { - pr_err("Unexpected instruction %08lx around bl _mcount\n", - ppc_inst_as_ulong(op)); - return -EINVAL; - } - } else if (IS_ENABLED(CONFIG_PPC64)) { - /* - * Check what is in the next instruction. We can see ld r2,40(r1), but - * on first pass after boot we will see mflr r0. - */ - if (copy_inst_from_kernel_nofault(&op, (void *)(ip + 4))) { - pr_err("Fetching op failed.\n"); - return -EFAULT; - } - - if (!ppc_inst_equal(op, ppc_inst(PPC_INST_LD_TOC))) { - pr_err("Expected %08lx found %08lx\n", PPC_INST_LD_TOC, - ppc_inst_as_ulong(op)); - return -EINVAL; - } - } - - /* - * When using -mprofile-kernel or PPC32 there is no load to jump over. - * - * Otherwise our original call site looks like: - * - * bl <tramp> - * ld r2,XX(r1) - * - * Milton Miller pointed out that we can not simply nop the branch. - * If a task was preempted when calling a trace function, the nops - * will remove the way to restore the TOC in r2 and the r2 TOC will - * get corrupted. - * - * Use a b +8 to jump over the load. - * XXX: could make PCREL depend on MPROFILE_KERNEL - * XXX: check PCREL && MPROFILE_KERNEL calling sequence - */ - if (IS_ENABLED(CONFIG_MPROFILE_KERNEL) || IS_ENABLED(CONFIG_PPC32)) - pop = ppc_inst(PPC_RAW_NOP()); - else - pop = ppc_inst(PPC_RAW_BRANCH(8)); /* b +8 */ - - if (patch_instruction((u32 *)ip, pop)) { - pr_err("Patching NOP failed.\n"); - return -EPERM; - } - - return 0; -} -#else -static int __ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, unsigned long addr) +static int is_bl_op(ppc_inst_t op) { - return 0; + return (ppc_inst_val(op) & ~PPC_LI_MASK) == PPC_RAW_BL(0); } -#endif /* CONFIG_MODULES */ static unsigned long find_ftrace_tramp(unsigned long ip) { int i; - /* - * We have the compiler generated long_branch tramps at the end - * and we prefer those - */ - for (i = NUM_FTRACE_TRAMPS - 1; i >= 0; i--) + for (i = 0; i < NUM_FTRACE_TRAMPS; i++) if (!ftrace_tramps[i]) continue; else if (is_offset_in_branch_range(ftrace_tramps[i] - ip)) @@ -233,449 +94,195 @@ static unsigned long find_ftrace_tramp(unsigned long ip) return 0; } -static int add_ftrace_tramp(unsigned long tramp) +static int ftrace_get_call_inst(struct dyn_ftrace *rec, unsigned long addr, ppc_inst_t *call_inst) { - int i; + unsigned long ip = rec->ip; + unsigned long stub; - for (i = 0; i < NUM_FTRACE_TRAMPS; i++) - if (!ftrace_tramps[i]) { - ftrace_tramps[i] = tramp; - return 0; + if (is_offset_in_branch_range(addr - ip)) { + /* Within range */ + stub = addr; +#ifdef CONFIG_MODULES + } else if (rec->arch.mod) { + /* Module code would be going to one of the module stubs */ + stub = (addr == (unsigned long)ftrace_caller ? rec->arch.mod->arch.tramp : + rec->arch.mod->arch.tramp_regs); +#endif + } else if (core_kernel_text(ip)) { + /* We would be branching to one of our ftrace stubs */ + stub = find_ftrace_tramp(ip); + if (!stub) { + pr_err("0x%lx: No ftrace stubs reachable\n", ip); + return -EINVAL; } - - return -1; -} - -/* - * If this is a compiler generated long_branch trampoline (essentially, a - * trampoline that has a branch to _mcount()), we re-write the branch to - * instead go to ftrace_[regs_]caller() and note down the location of this - * trampoline. - */ -static int setup_mcount_compiler_tramp(unsigned long tramp) -{ - int i; - ppc_inst_t op; - unsigned long ptr; - - /* Is this a known long jump tramp? */ - for (i = 0; i < NUM_FTRACE_TRAMPS; i++) - if (ftrace_tramps[i] == tramp) - return 0; - - /* New trampoline -- read where this goes */ - if (copy_inst_from_kernel_nofault(&op, (void *)tramp)) { - pr_debug("Fetching opcode failed.\n"); - return -1; - } - - /* Is this a 24 bit branch? */ - if (!is_b_op(op)) { - pr_debug("Trampoline is not a long branch tramp.\n"); - return -1; - } - - /* lets find where the pointer goes */ - ptr = find_bl_target(tramp, op); - - if (ptr != ppc_global_function_entry((void *)_mcount)) { - pr_debug("Trampoline target %p is not _mcount\n", (void *)ptr); - return -1; - } - - /* Let's re-write the tramp to go to ftrace_[regs_]caller */ - if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS)) - ptr = ppc_global_function_entry((void *)ftrace_regs_caller); - else - ptr = ppc_global_function_entry((void *)ftrace_caller); - - if (patch_branch((u32 *)tramp, ptr, 0)) { - pr_debug("REL24 out of range!\n"); - return -1; - } - - if (add_ftrace_tramp(tramp)) { - pr_debug("No tramp locations left\n"); - return -1; + } else { + return -EINVAL; } + *call_inst = ftrace_create_branch_inst(ip, stub, 1); return 0; } -static int __ftrace_make_nop_kernel(struct dyn_ftrace *rec, unsigned long addr) +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS +int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, unsigned long addr) { - unsigned long tramp, ip = rec->ip; - ppc_inst_t op; - - /* Read where this goes */ - if (copy_inst_from_kernel_nofault(&op, (void *)ip)) { - pr_err("Fetching opcode failed.\n"); - return -EFAULT; - } - - /* Make sure that this is still a 24bit jump */ - if (!is_bl_op(op)) { - pr_err("Not expected bl: opcode is %08lx\n", ppc_inst_as_ulong(op)); - return -EINVAL; - } - - /* Let's find where the pointer goes */ - tramp = find_bl_target(ip, op); - - pr_devel("ip:%lx jumps to %lx", ip, tramp); - - if (setup_mcount_compiler_tramp(tramp)) { - /* Are other trampolines reachable? */ - if (!find_ftrace_tramp(ip)) { - pr_err("No ftrace trampolines reachable from %ps\n", - (void *)ip); - return -EINVAL; - } - } - - if (patch_instruction((u32 *)ip, ppc_inst(PPC_RAW_NOP()))) { - pr_err("Patching NOP failed.\n"); - return -EPERM; - } - - return 0; + /* This should never be called since we override ftrace_replace_code() */ + WARN_ON(1); + return -EINVAL; } +#endif -int ftrace_make_nop(struct module *mod, - struct dyn_ftrace *rec, unsigned long addr) +int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) { - unsigned long ip = rec->ip; ppc_inst_t old, new; + int ret; - /* - * If the calling address is more that 24 bits away, - * then we had to use a trampoline to make the call. - * Otherwise just update the call site. - */ - if (test_24bit_addr(ip, addr)) { - /* within range */ - old = ftrace_call_replace(ip, addr, 1); - new = ppc_inst(PPC_RAW_NOP()); - return ftrace_modify_code(ip, old, new); - } else if (core_kernel_text(ip)) { - return __ftrace_make_nop_kernel(rec, addr); - } else if (!IS_ENABLED(CONFIG_MODULES)) { + /* This can only ever be called during module load */ + if (WARN_ON(!IS_ENABLED(CONFIG_MODULES) || core_kernel_text(rec->ip))) return -EINVAL; - } - /* - * Out of range jumps are called from modules. - * We should either already have a pointer to the module - * or it has been passed in. - */ - if (!rec->arch.mod) { - if (!mod) { - pr_err("No module loaded addr=%lx\n", addr); - return -EFAULT; - } - rec->arch.mod = mod; - } else if (mod) { - if (mod != rec->arch.mod) { - pr_err("Record mod %p not equal to passed in mod %p\n", - rec->arch.mod, mod); - return -EINVAL; - } - /* nothing to do if mod == rec->arch.mod */ - } else - mod = rec->arch.mod; + old = ppc_inst(PPC_RAW_NOP()); + ret = ftrace_get_call_inst(rec, addr, &new); + if (ret) + return ret; - return __ftrace_make_nop(mod, rec, addr); + return ftrace_modify_code(rec->ip, old, new); } -#ifdef CONFIG_MODULES -/* - * Examine the existing instructions for __ftrace_make_call. - * They should effectively be a NOP, and follow formal constraints, - * depending on the ABI. Return false if they don't. - */ -static bool expected_nop_sequence(void *ip, ppc_inst_t op0, ppc_inst_t op1) -{ - if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS)) - return ppc_inst_equal(op0, ppc_inst(PPC_RAW_NOP())); - else - return ppc_inst_equal(op0, ppc_inst(PPC_RAW_BRANCH(8))) && - ppc_inst_equal(op1, ppc_inst(PPC_INST_LD_TOC)); -} - -static int -__ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) -{ - ppc_inst_t op[2]; - void *ip = (void *)rec->ip; - unsigned long entry, ptr, tramp; - struct module *mod = rec->arch.mod; - - /* read where this goes */ - if (copy_inst_from_kernel_nofault(op, ip)) - return -EFAULT; - - if (!IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS) && - copy_inst_from_kernel_nofault(op + 1, ip + 4)) - return -EFAULT; - - if (!expected_nop_sequence(ip, op[0], op[1])) { - pr_err("Unexpected call sequence at %p: %08lx %08lx\n", ip, - ppc_inst_as_ulong(op[0]), ppc_inst_as_ulong(op[1])); - return -EINVAL; - } - - /* If we never set up ftrace trampoline(s), then bail */ - if (!mod->arch.tramp || - (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS) && !mod->arch.tramp_regs)) { - pr_err("No ftrace trampoline\n"); - return -EINVAL; - } - - if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS) && rec->flags & FTRACE_FL_REGS) - tramp = mod->arch.tramp_regs; - else - tramp = mod->arch.tramp; - - if (module_trampoline_target(mod, tramp, &ptr)) { - pr_err("Failed to get trampoline target\n"); - return -EFAULT; - } - - pr_devel("trampoline target %lx", ptr); - - entry = ppc_global_function_entry((void *)addr); - /* This should match what was called */ - if (ptr != entry) { - pr_err("addr %lx does not match expected %lx\n", ptr, entry); - return -EINVAL; - } - - if (patch_branch(ip, tramp, BRANCH_SET_LINK)) { - pr_err("REL24 out of range!\n"); - return -EINVAL; - } - - return 0; -} -#else -static int __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) +int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, unsigned long addr) { - return 0; + /* + * This should never be called since we override ftrace_replace_code(), + * as well as ftrace_init_nop() + */ + WARN_ON(1); + return -EINVAL; } -#endif /* CONFIG_MODULES */ -static int __ftrace_make_call_kernel(struct dyn_ftrace *rec, unsigned long addr) +void ftrace_replace_code(int enable) { - ppc_inst_t op; - void *ip = (void *)rec->ip; - unsigned long tramp, entry, ptr; + ppc_inst_t old, new, call_inst, new_call_inst; + ppc_inst_t nop_inst = ppc_inst(PPC_RAW_NOP()); + unsigned long ip, new_addr, addr; + struct ftrace_rec_iter *iter; + struct dyn_ftrace *rec; + int ret = 0, update; - /* Make sure we're being asked to patch branch to a known ftrace addr */ - entry = ppc_global_function_entry((void *)ftrace_caller); - ptr = ppc_global_function_entry((void *)addr); + for_ftrace_rec_iter(iter) { + rec = ftrace_rec_iter_record(iter); + ip = rec->ip; - if (ptr != entry && IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS)) - entry = ppc_global_function_entry((void *)ftrace_regs_caller); - - if (ptr != entry) { - pr_err("Unknown ftrace addr to patch: %ps\n", (void *)ptr); - return -EINVAL; - } - - /* Make sure we have a nop */ - if (copy_inst_from_kernel_nofault(&op, ip)) { - pr_err("Unable to read ftrace location %p\n", ip); - return -EFAULT; - } + if (rec->flags & FTRACE_FL_DISABLED && !(rec->flags & FTRACE_FL_ENABLED)) + continue; - if (!ppc_inst_equal(op, ppc_inst(PPC_RAW_NOP()))) { - pr_err("Unexpected call sequence at %p: %08lx\n", - ip, ppc_inst_as_ulong(op)); - return -EINVAL; - } + addr = ftrace_get_addr_curr(rec); + new_addr = ftrace_get_addr_new(rec); + update = ftrace_update_record(rec, enable); - tramp = find_ftrace_tramp((unsigned long)ip); - if (!tramp) { - pr_err("No ftrace trampolines reachable from %ps\n", ip); - return -EINVAL; - } + switch (update) { + case FTRACE_UPDATE_IGNORE: + default: + continue; + case FTRACE_UPDATE_MODIFY_CALL: + ret = ftrace_get_call_inst(rec, new_addr, &new_call_inst); + ret |= ftrace_get_call_inst(rec, addr, &call_inst); + old = call_inst; + new = new_call_inst; + break; + case FTRACE_UPDATE_MAKE_NOP: + ret = ftrace_get_call_inst(rec, addr, &call_inst); + old = call_inst; + new = nop_inst; + break; + case FTRACE_UPDATE_MAKE_CALL: + ret = ftrace_get_call_inst(rec, new_addr, &call_inst); + old = nop_inst; + new = call_inst; + break; + } - if (patch_branch(ip, tramp, BRANCH_SET_LINK)) { - pr_err("Error patching branch to ftrace tramp!\n"); - return -EINVAL; + if (!ret) + ret = ftrace_modify_code(ip, old, new); + if (ret) + goto out; } - return 0; +out: + if (ret) + ftrace_bug(ret, rec); + return; } -int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) +int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec) { - unsigned long ip = rec->ip; + unsigned long addr, ip = rec->ip; ppc_inst_t old, new; - - /* - * If the calling address is more that 24 bits away, - * then we had to use a trampoline to make the call. - * Otherwise just update the call site. - */ - if (test_24bit_addr(ip, addr)) { - /* within range */ - old = ppc_inst(PPC_RAW_NOP()); - new = ftrace_call_replace(ip, addr, 1); - return ftrace_modify_code(ip, old, new); - } else if (core_kernel_text(ip)) { - return __ftrace_make_call_kernel(rec, addr); - } else if (!IS_ENABLED(CONFIG_MODULES)) { - /* We should not get here without modules */ - return -EINVAL; - } - - /* - * Out of range jumps are called from modules. - * Being that we are converting from nop, it had better - * already have a module defined. - */ - if (!rec->arch.mod) { - pr_err("No module loaded\n"); - return -EINVAL; - } - - return __ftrace_make_call(rec, addr); -} - -#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS -#ifdef CONFIG_MODULES -static int -__ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, - unsigned long addr) -{ - ppc_inst_t op; - unsigned long ip = rec->ip; - unsigned long entry, ptr, tramp; - struct module *mod = rec->arch.mod; - - /* If we never set up ftrace trampolines, then bail */ - if (!mod->arch.tramp || !mod->arch.tramp_regs) { - pr_err("No ftrace trampoline\n"); - return -EINVAL; - } - - /* read where this goes */ - if (copy_inst_from_kernel_nofault(&op, (void *)ip)) { - pr_err("Fetching opcode failed.\n"); - return -EFAULT; - } - - /* Make sure that this is still a 24bit jump */ - if (!is_bl_op(op)) { - pr_err("Not expected bl: opcode is %08lx\n", ppc_inst_as_ulong(op)); + int ret = 0; + + /* Verify instructions surrounding the ftrace location */ + if (IS_ENABLED(CONFIG_ARCH_USING_PATCHABLE_FUNCTION_ENTRY)) { + /* Expect nops */ + ret = ftrace_validate_inst(ip - 4, ppc_inst(PPC_RAW_NOP())); + if (!ret) + ret = ftrace_validate_inst(ip, ppc_inst(PPC_RAW_NOP())); + } else if (IS_ENABLED(CONFIG_PPC32)) { + /* Expected sequence: 'mflr r0', 'stw r0,4(r1)', 'bl _mcount' */ + ret = ftrace_validate_inst(ip - 8, ppc_inst(PPC_RAW_MFLR(_R0))); + if (!ret) + ret = ftrace_validate_inst(ip - 4, ppc_inst(PPC_RAW_STW(_R0, _R1, 4))); + } else if (IS_ENABLED(CONFIG_MPROFILE_KERNEL)) { + /* Expected sequence: 'mflr r0', ['std r0,16(r1)'], 'bl _mcount' */ + ret = ftrace_read_inst(ip - 4, &old); + if (!ret && !ppc_inst_equal(old, ppc_inst(PPC_RAW_MFLR(_R0)))) { + ret = ftrace_validate_inst(ip - 8, ppc_inst(PPC_RAW_MFLR(_R0))); + ret |= ftrace_validate_inst(ip - 4, ppc_inst(PPC_RAW_STD(_R0, _R1, 16))); + } + } else { return -EINVAL; } - /* lets find where the pointer goes */ - tramp = find_bl_target(ip, op); - entry = ppc_global_function_entry((void *)old_addr); - - pr_devel("ip:%lx jumps to %lx", ip, tramp); + if (ret) + return ret; - if (tramp != entry) { - /* old_addr is not within range, so we must have used a trampoline */ - if (module_trampoline_target(mod, tramp, &ptr)) { - pr_err("Failed to get trampoline target\n"); + if (!core_kernel_text(ip)) { + if (!mod) { + pr_err("0x%lx: No module provided for non-kernel address\n", ip); return -EFAULT; } - - pr_devel("trampoline target %lx", ptr); - - /* This should match what was called */ - if (ptr != entry) { - pr_err("addr %lx does not match expected %lx\n", ptr, entry); - return -EINVAL; - } - } - - /* The new target may be within range */ - if (test_24bit_addr(ip, addr)) { - /* within range */ - if (patch_branch((u32 *)ip, addr, BRANCH_SET_LINK)) { - pr_err("REL24 out of range!\n"); - return -EINVAL; - } - - return 0; - } - - if (rec->flags & FTRACE_FL_REGS) - tramp = mod->arch.tramp_regs; - else - tramp = mod->arch.tramp; - - if (module_trampoline_target(mod, tramp, &ptr)) { - pr_err("Failed to get trampoline target\n"); - return -EFAULT; - } - - pr_devel("trampoline target %lx", ptr); - - entry = ppc_global_function_entry((void *)addr); - /* This should match what was called */ - if (ptr != entry) { - pr_err("addr %lx does not match expected %lx\n", ptr, entry); - return -EINVAL; - } - - if (patch_branch((u32 *)ip, tramp, BRANCH_SET_LINK)) { - pr_err("REL24 out of range!\n"); - return -EINVAL; + rec->arch.mod = mod; } - return 0; -} -#else -static int __ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, unsigned long addr) -{ - return 0; -} -#endif - -int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, - unsigned long addr) -{ - unsigned long ip = rec->ip; - ppc_inst_t old, new; - - /* - * If the calling address is more that 24 bits away, - * then we had to use a trampoline to make the call. - * Otherwise just update the call site. - */ - if (test_24bit_addr(ip, addr) && test_24bit_addr(ip, old_addr)) { - /* within range */ - old = ftrace_call_replace(ip, old_addr, 1); - new = ftrace_call_replace(ip, addr, 1); - return ftrace_modify_code(ip, old, new); - } else if (core_kernel_text(ip)) { + /* Nop-out the ftrace location */ + new = ppc_inst(PPC_RAW_NOP()); + addr = MCOUNT_ADDR; + if (IS_ENABLED(CONFIG_ARCH_USING_PATCHABLE_FUNCTION_ENTRY)) { + /* we instead patch-in the 'mflr r0' */ + old = ppc_inst(PPC_RAW_NOP()); + new = ppc_inst(PPC_RAW_MFLR(_R0)); + ret = ftrace_modify_code(ip - 4, old, new); + } else if (is_offset_in_branch_range(addr - ip)) { + /* Within range */ + old = ftrace_create_branch_inst(ip, addr, 1); + ret = ftrace_modify_code(ip, old, new); + } else if (core_kernel_text(ip) || (IS_ENABLED(CONFIG_MODULES) && mod)) { /* - * We always patch out of range locations to go to the regs - * variant, so there is nothing to do here + * We would be branching to a linker-generated stub, or to the module _mcount + * stub. Let's just confirm we have a 'bl' here. */ - return 0; - } else if (!IS_ENABLED(CONFIG_MODULES)) { - /* We should not get here without modules */ - return -EINVAL; - } - - /* - * Out of range jumps are called from modules. - */ - if (!rec->arch.mod) { - pr_err("No module loaded\n"); + ret = ftrace_read_inst(ip, &old); + if (ret) + return ret; + if (!is_bl_op(old)) { + pr_err("0x%lx: expected (bl) != found (%08lx)\n", ip, ppc_inst_as_ulong(old)); + return -EINVAL; + } + ret = patch_instruction((u32 *)ip, new); + } else { return -EINVAL; } - return __ftrace_modify_call(rec, old_addr, addr); + return ret; } -#endif int ftrace_update_ftrace_func(ftrace_func_t func) { @@ -684,14 +291,14 @@ int ftrace_update_ftrace_func(ftrace_func_t func) int ret; old = ppc_inst_read((u32 *)&ftrace_call); - new = ftrace_call_replace(ip, (unsigned long)func, 1); + new = ftrace_create_branch_inst(ip, ppc_function_entry(func), 1); ret = ftrace_modify_code(ip, old, new); /* Also update the regs callback function */ if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS) && !ret) { ip = (unsigned long)(&ftrace_regs_call); old = ppc_inst_read((u32 *)&ftrace_regs_call); - new = ftrace_call_replace(ip, (unsigned long)func, 1); + new = ftrace_create_branch_inst(ip, ppc_function_entry(func), 1); ret = ftrace_modify_code(ip, old, new); } @@ -707,11 +314,6 @@ void arch_ftrace_update_code(int command) ftrace_modify_all_code(command); } -#ifdef CONFIG_PPC64 -#define PACATOC offsetof(struct paca_struct, kernel_toc) - -extern unsigned int ftrace_tramp_text[], ftrace_tramp_init[]; - void ftrace_free_init_tramp(void) { int i; @@ -723,35 +325,43 @@ void ftrace_free_init_tramp(void) } } -int __init ftrace_dyn_arch_init(void) +static void __init add_ftrace_tramp(unsigned long tramp) { int i; + + for (i = 0; i < NUM_FTRACE_TRAMPS; i++) + if (!ftrace_tramps[i]) { + ftrace_tramps[i] = tramp; + return; + } +} + +int __init ftrace_dyn_arch_init(void) +{ unsigned int *tramp[] = { ftrace_tramp_text, ftrace_tramp_init }; -#ifdef CONFIG_PPC_KERNEL_PCREL + unsigned long addr = FTRACE_REGS_ADDR; + long reladdr; + int i; u32 stub_insns[] = { +#ifdef CONFIG_PPC_KERNEL_PCREL /* pla r12,addr */ PPC_PREFIX_MLS | __PPC_PRFX_R(1), PPC_INST_PADDI | ___PPC_RT(_R12), PPC_RAW_MTCTR(_R12), PPC_RAW_BCTR() - }; -#else - u32 stub_insns[] = { - PPC_RAW_LD(_R12, _R13, PACATOC), +#elif defined(CONFIG_PPC64) + PPC_RAW_LD(_R12, _R13, offsetof(struct paca_struct, kernel_toc)), PPC_RAW_ADDIS(_R12, _R12, 0), PPC_RAW_ADDI(_R12, _R12, 0), PPC_RAW_MTCTR(_R12), PPC_RAW_BCTR() - }; +#else + PPC_RAW_LIS(_R12, 0), + PPC_RAW_ADDI(_R12, _R12, 0), + PPC_RAW_MTCTR(_R12), + PPC_RAW_BCTR() #endif - - unsigned long addr; - long reladdr; - - if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS)) - addr = ppc_global_function_entry((void *)ftrace_regs_caller); - else - addr = ppc_global_function_entry((void *)ftrace_caller); + }; if (IS_ENABLED(CONFIG_PPC_KERNEL_PCREL)) { for (i = 0; i < 2; i++) { @@ -768,10 +378,10 @@ int __init ftrace_dyn_arch_init(void) tramp[i][1] |= IMM_L(reladdr); add_ftrace_tramp((unsigned long)tramp[i]); } - } else { + } else if (IS_ENABLED(CONFIG_PPC64)) { reladdr = addr - kernel_toc_addr(); - if (reladdr >= (long)SZ_2G || reladdr < -(long)SZ_2G) { + if (reladdr >= (long)SZ_2G || reladdr < -(long long)SZ_2G) { pr_err("Address of %ps out of range of kernel_toc.\n", (void *)addr); return -1; @@ -783,51 +393,23 @@ int __init ftrace_dyn_arch_init(void) tramp[i][2] |= PPC_LO(reladdr); add_ftrace_tramp((unsigned long)tramp[i]); } + } else { + for (i = 0; i < 2; i++) { + memcpy(tramp[i], stub_insns, sizeof(stub_insns)); + tramp[i][0] |= PPC_HA(addr); + tramp[i][1] |= PPC_LO(addr); + add_ftrace_tramp((unsigned long)tramp[i]); + } } return 0; } -#endif #ifdef CONFIG_FUNCTION_GRAPH_TRACER - -extern void ftrace_graph_call(void); -extern void ftrace_graph_stub(void); - -static int ftrace_modify_ftrace_graph_caller(bool enable) -{ - unsigned long ip = (unsigned long)(&ftrace_graph_call); - unsigned long addr = (unsigned long)(&ftrace_graph_caller); - unsigned long stub = (unsigned long)(&ftrace_graph_stub); - ppc_inst_t old, new; - - if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_ARGS)) - return 0; - - old = ftrace_call_replace(ip, enable ? stub : addr, 0); - new = ftrace_call_replace(ip, enable ? addr : stub, 0); - - return ftrace_modify_code(ip, old, new); -} - -int ftrace_enable_ftrace_graph_caller(void) -{ - return ftrace_modify_ftrace_graph_caller(true); -} - -int ftrace_disable_ftrace_graph_caller(void) -{ - return ftrace_modify_ftrace_graph_caller(false); -} - -/* - * Hook the return address and push it in the stack of return addrs - * in current thread info. Return the address we want to divert to. - */ -static unsigned long -__prepare_ftrace_return(unsigned long parent, unsigned long ip, unsigned long sp) +void ftrace_graph_func(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct ftrace_regs *fregs) { - unsigned long return_hooker; + unsigned long sp = fregs->regs.gpr[1]; int bit; if (unlikely(ftrace_graph_is_dead())) @@ -836,41 +418,15 @@ __prepare_ftrace_return(unsigned long parent, unsigned long ip, unsigned long sp if (unlikely(atomic_read(¤t->tracing_graph_pause))) goto out; - bit = ftrace_test_recursion_trylock(ip, parent); + bit = ftrace_test_recursion_trylock(ip, parent_ip); if (bit < 0) goto out; - return_hooker = ppc_function_entry(return_to_handler); - - if (!function_graph_enter(parent, ip, 0, (unsigned long *)sp)) - parent = return_hooker; + if (!function_graph_enter(parent_ip, ip, 0, (unsigned long *)sp)) + parent_ip = ppc_function_entry(return_to_handler); ftrace_test_recursion_unlock(bit); out: - return parent; + fregs->regs.link = parent_ip; } - -#ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS -void ftrace_graph_func(unsigned long ip, unsigned long parent_ip, - struct ftrace_ops *op, struct ftrace_regs *fregs) -{ - fregs->regs.link = __prepare_ftrace_return(parent_ip, ip, fregs->regs.gpr[1]); -} -#else -unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip, - unsigned long sp) -{ - return __prepare_ftrace_return(parent, ip, sp); -} -#endif #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ - -#ifdef CONFIG_PPC64_ELF_ABI_V1 -char *arch_ftrace_match_adjust(char *str, const char *search) -{ - if (str[0] == '.' && search[0] != '.') - return str + 1; - else - return str; -} -#endif /* CONFIG_PPC64_ELF_ABI_V1 */ diff --git a/arch/powerpc/kernel/trace/ftrace_64_pg.S b/arch/powerpc/kernel/trace/ftrace_64_pg.S deleted file mode 100644 index 6708e24db0ab..000000000000 --- a/arch/powerpc/kernel/trace/ftrace_64_pg.S +++ /dev/null @@ -1,67 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * Split from ftrace_64.S - */ - -#include <linux/magic.h> -#include <asm/ppc_asm.h> -#include <asm/asm-offsets.h> -#include <asm/ftrace.h> -#include <asm/ppc-opcode.h> -#include <asm/export.h> - -_GLOBAL_TOC(ftrace_caller) - lbz r3, PACA_FTRACE_ENABLED(r13) - cmpdi r3, 0 - beqlr - - /* Taken from output of objdump from lib64/glibc */ - mflr r3 - ld r11, 0(r1) - stdu r1, -112(r1) - std r3, 128(r1) - ld r4, 16(r11) - subi r3, r3, MCOUNT_INSN_SIZE -.globl ftrace_call -ftrace_call: - bl ftrace_stub - nop -#ifdef CONFIG_FUNCTION_GRAPH_TRACER -.globl ftrace_graph_call -ftrace_graph_call: - b ftrace_graph_stub -_GLOBAL(ftrace_graph_stub) -#endif - ld r0, 128(r1) - mtlr r0 - addi r1, r1, 112 - -_GLOBAL(ftrace_stub) - blr - -#ifdef CONFIG_FUNCTION_GRAPH_TRACER -_GLOBAL(ftrace_graph_caller) - addi r5, r1, 112 - /* load r4 with local address */ - ld r4, 128(r1) - subi r4, r4, MCOUNT_INSN_SIZE - - /* Grab the LR out of the caller stack frame */ - ld r11, 112(r1) - ld r3, 16(r11) - - bl prepare_ftrace_return - nop - - /* - * prepare_ftrace_return gives us the address we divert to. - * Change the LR in the callers stack frame to this. - */ - ld r11, 112(r1) - std r3, 16(r11) - - ld r0, 128(r1) - mtlr r0 - addi r1, r1, 112 - blr -#endif /* CONFIG_FUNCTION_GRAPH_TRACER */ diff --git a/arch/powerpc/kernel/trace/ftrace_64_pg.c b/arch/powerpc/kernel/trace/ftrace_64_pg.c new file mode 100644 index 000000000000..7b85c3b460a3 --- /dev/null +++ b/arch/powerpc/kernel/trace/ftrace_64_pg.c @@ -0,0 +1,846 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Code for replacing ftrace calls with jumps. + * + * Copyright (C) 2007-2008 Steven Rostedt <srostedt@redhat.com> + * + * Thanks goes out to P.A. Semi, Inc for supplying me with a PPC64 box. + * + * Added function graph tracer code, taken from x86 that was written + * by Frederic Weisbecker, and ported to PPC by Steven Rostedt. + * + */ + +#define pr_fmt(fmt) "ftrace-powerpc: " fmt + +#include <linux/spinlock.h> +#include <linux/hardirq.h> +#include <linux/uaccess.h> +#include <linux/module.h> +#include <linux/ftrace.h> +#include <linux/percpu.h> +#include <linux/init.h> +#include <linux/list.h> + +#include <asm/cacheflush.h> +#include <asm/code-patching.h> +#include <asm/ftrace.h> +#include <asm/syscall.h> +#include <asm/inst.h> + +/* + * We generally only have a single long_branch tramp and at most 2 or 3 plt + * tramps generated. But, we don't use the plt tramps currently. We also allot + * 2 tramps after .text and .init.text. So, we only end up with around 3 usable + * tramps in total. Set aside 8 just to be sure. + */ +#define NUM_FTRACE_TRAMPS 8 +static unsigned long ftrace_tramps[NUM_FTRACE_TRAMPS]; + +static ppc_inst_t +ftrace_call_replace(unsigned long ip, unsigned long addr, int link) +{ + ppc_inst_t op; + + addr = ppc_function_entry((void *)addr); + + /* if (link) set op to 'bl' else 'b' */ + create_branch(&op, (u32 *)ip, addr, link ? BRANCH_SET_LINK : 0); + + return op; +} + +static inline int +ftrace_modify_code(unsigned long ip, ppc_inst_t old, ppc_inst_t new) +{ + ppc_inst_t replaced; + + /* + * Note: + * We are paranoid about modifying text, as if a bug was to happen, it + * could cause us to read or write to someplace that could cause harm. + * Carefully read and modify the code with probe_kernel_*(), and make + * sure what we read is what we expected it to be before modifying it. + */ + + /* read the text we want to modify */ + if (copy_inst_from_kernel_nofault(&replaced, (void *)ip)) + return -EFAULT; + + /* Make sure it is what we expect it to be */ + if (!ppc_inst_equal(replaced, old)) { + pr_err("%p: replaced (%08lx) != old (%08lx)", (void *)ip, + ppc_inst_as_ulong(replaced), ppc_inst_as_ulong(old)); + return -EINVAL; + } + + /* replace the text with the new text */ + return patch_instruction((u32 *)ip, new); +} + +/* + * Helper functions that are the same for both PPC64 and PPC32. + */ +static int test_24bit_addr(unsigned long ip, unsigned long addr) +{ + addr = ppc_function_entry((void *)addr); + + return is_offset_in_branch_range(addr - ip); +} + +static int is_bl_op(ppc_inst_t op) +{ + return (ppc_inst_val(op) & ~PPC_LI_MASK) == PPC_RAW_BL(0); +} + +static int is_b_op(ppc_inst_t op) +{ + return (ppc_inst_val(op) & ~PPC_LI_MASK) == PPC_RAW_BRANCH(0); +} + +static unsigned long find_bl_target(unsigned long ip, ppc_inst_t op) +{ + int offset; + + offset = PPC_LI(ppc_inst_val(op)); + /* make it signed */ + if (offset & 0x02000000) + offset |= 0xfe000000; + + return ip + (long)offset; +} + +#ifdef CONFIG_MODULES +static int +__ftrace_make_nop(struct module *mod, + struct dyn_ftrace *rec, unsigned long addr) +{ + unsigned long entry, ptr, tramp; + unsigned long ip = rec->ip; + ppc_inst_t op, pop; + + /* read where this goes */ + if (copy_inst_from_kernel_nofault(&op, (void *)ip)) { + pr_err("Fetching opcode failed.\n"); + return -EFAULT; + } + + /* Make sure that this is still a 24bit jump */ + if (!is_bl_op(op)) { + pr_err("Not expected bl: opcode is %08lx\n", ppc_inst_as_ulong(op)); + return -EINVAL; + } + + /* lets find where the pointer goes */ + tramp = find_bl_target(ip, op); + + pr_devel("ip:%lx jumps to %lx", ip, tramp); + + if (module_trampoline_target(mod, tramp, &ptr)) { + pr_err("Failed to get trampoline target\n"); + return -EFAULT; + } + + pr_devel("trampoline target %lx", ptr); + + entry = ppc_global_function_entry((void *)addr); + /* This should match what was called */ + if (ptr != entry) { + pr_err("addr %lx does not match expected %lx\n", ptr, entry); + return -EINVAL; + } + + if (IS_ENABLED(CONFIG_MPROFILE_KERNEL)) { + if (copy_inst_from_kernel_nofault(&op, (void *)(ip - 4))) { + pr_err("Fetching instruction at %lx failed.\n", ip - 4); + return -EFAULT; + } + + /* We expect either a mflr r0, or a std r0, LRSAVE(r1) */ + if (!ppc_inst_equal(op, ppc_inst(PPC_RAW_MFLR(_R0))) && + !ppc_inst_equal(op, ppc_inst(PPC_INST_STD_LR))) { + pr_err("Unexpected instruction %08lx around bl _mcount\n", + ppc_inst_as_ulong(op)); + return -EINVAL; + } + } else if (IS_ENABLED(CONFIG_PPC64)) { + /* + * Check what is in the next instruction. We can see ld r2,40(r1), but + * on first pass after boot we will see mflr r0. + */ + if (copy_inst_from_kernel_nofault(&op, (void *)(ip + 4))) { + pr_err("Fetching op failed.\n"); + return -EFAULT; + } + + if (!ppc_inst_equal(op, ppc_inst(PPC_INST_LD_TOC))) { + pr_err("Expected %08lx found %08lx\n", PPC_INST_LD_TOC, + ppc_inst_as_ulong(op)); + return -EINVAL; + } + } + + /* + * When using -mprofile-kernel or PPC32 there is no load to jump over. + * + * Otherwise our original call site looks like: + * + * bl <tramp> + * ld r2,XX(r1) + * + * Milton Miller pointed out that we can not simply nop the branch. + * If a task was preempted when calling a trace function, the nops + * will remove the way to restore the TOC in r2 and the r2 TOC will + * get corrupted. + * + * Use a b +8 to jump over the load. + */ + if (IS_ENABLED(CONFIG_MPROFILE_KERNEL) || IS_ENABLED(CONFIG_PPC32)) + pop = ppc_inst(PPC_RAW_NOP()); + else + pop = ppc_inst(PPC_RAW_BRANCH(8)); /* b +8 */ + + if (patch_instruction((u32 *)ip, pop)) { + pr_err("Patching NOP failed.\n"); + return -EPERM; + } + + return 0; +} +#else +static int __ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, unsigned long addr) +{ + return 0; +} +#endif /* CONFIG_MODULES */ + +static unsigned long find_ftrace_tramp(unsigned long ip) +{ + int i; + + /* + * We have the compiler generated long_branch tramps at the end + * and we prefer those + */ + for (i = NUM_FTRACE_TRAMPS - 1; i >= 0; i--) + if (!ftrace_tramps[i]) + continue; + else if (is_offset_in_branch_range(ftrace_tramps[i] - ip)) + return ftrace_tramps[i]; + + return 0; +} + +static int add_ftrace_tramp(unsigned long tramp) +{ + int i; + + for (i = 0; i < NUM_FTRACE_TRAMPS; i++) + if (!ftrace_tramps[i]) { + ftrace_tramps[i] = tramp; + return 0; + } + + return -1; +} + +/* + * If this is a compiler generated long_branch trampoline (essentially, a + * trampoline that has a branch to _mcount()), we re-write the branch to + * instead go to ftrace_[regs_]caller() and note down the location of this + * trampoline. + */ +static int setup_mcount_compiler_tramp(unsigned long tramp) +{ + int i; + ppc_inst_t op; + unsigned long ptr; + + /* Is this a known long jump tramp? */ + for (i = 0; i < NUM_FTRACE_TRAMPS; i++) + if (ftrace_tramps[i] == tramp) + return 0; + + /* New trampoline -- read where this goes */ + if (copy_inst_from_kernel_nofault(&op, (void *)tramp)) { + pr_debug("Fetching opcode failed.\n"); + return -1; + } + + /* Is this a 24 bit branch? */ + if (!is_b_op(op)) { + pr_debug("Trampoline is not a long branch tramp.\n"); + return -1; + } + + /* lets find where the pointer goes */ + ptr = find_bl_target(tramp, op); + + if (ptr != ppc_global_function_entry((void *)_mcount)) { + pr_debug("Trampoline target %p is not _mcount\n", (void *)ptr); + return -1; + } + + /* Let's re-write the tramp to go to ftrace_[regs_]caller */ + if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS)) + ptr = ppc_global_function_entry((void *)ftrace_regs_caller); + else + ptr = ppc_global_function_entry((void *)ftrace_caller); + + if (patch_branch((u32 *)tramp, ptr, 0)) { + pr_debug("REL24 out of range!\n"); + return -1; + } + + if (add_ftrace_tramp(tramp)) { + pr_debug("No tramp locations left\n"); + return -1; + } + + return 0; +} + +static int __ftrace_make_nop_kernel(struct dyn_ftrace *rec, unsigned long addr) +{ + unsigned long tramp, ip = rec->ip; + ppc_inst_t op; + + /* Read where this goes */ + if (copy_inst_from_kernel_nofault(&op, (void *)ip)) { + pr_err("Fetching opcode failed.\n"); + return -EFAULT; + } + + /* Make sure that this is still a 24bit jump */ + if (!is_bl_op(op)) { + pr_err("Not expected bl: opcode is %08lx\n", ppc_inst_as_ulong(op)); + return -EINVAL; + } + + /* Let's find where the pointer goes */ + tramp = find_bl_target(ip, op); + + pr_devel("ip:%lx jumps to %lx", ip, tramp); + + if (setup_mcount_compiler_tramp(tramp)) { + /* Are other trampolines reachable? */ + if (!find_ftrace_tramp(ip)) { + pr_err("No ftrace trampolines reachable from %ps\n", + (void *)ip); + return -EINVAL; + } + } + + if (patch_instruction((u32 *)ip, ppc_inst(PPC_RAW_NOP()))) { + pr_err("Patching NOP failed.\n"); + return -EPERM; + } + + return 0; +} + +int ftrace_make_nop(struct module *mod, + struct dyn_ftrace *rec, unsigned long addr) +{ + unsigned long ip = rec->ip; + ppc_inst_t old, new; + + /* + * If the calling address is more that 24 bits away, + * then we had to use a trampoline to make the call. + * Otherwise just update the call site. + */ + if (test_24bit_addr(ip, addr)) { + /* within range */ + old = ftrace_call_replace(ip, addr, 1); + new = ppc_inst(PPC_RAW_NOP()); + return ftrace_modify_code(ip, old, new); + } else if (core_kernel_text(ip)) { + return __ftrace_make_nop_kernel(rec, addr); + } else if (!IS_ENABLED(CONFIG_MODULES)) { + return -EINVAL; + } + + /* + * Out of range jumps are called from modules. + * We should either already have a pointer to the module + * or it has been passed in. + */ + if (!rec->arch.mod) { + if (!mod) { + pr_err("No module loaded addr=%lx\n", addr); + return -EFAULT; + } + rec->arch.mod = mod; + } else if (mod) { + if (mod != rec->arch.mod) { + pr_err("Record mod %p not equal to passed in mod %p\n", + rec->arch.mod, mod); + return -EINVAL; + } + /* nothing to do if mod == rec->arch.mod */ + } else + mod = rec->arch.mod; + + return __ftrace_make_nop(mod, rec, addr); +} + +#ifdef CONFIG_MODULES +/* + * Examine the existing instructions for __ftrace_make_call. + * They should effectively be a NOP, and follow formal constraints, + * depending on the ABI. Return false if they don't. + */ +static bool expected_nop_sequence(void *ip, ppc_inst_t op0, ppc_inst_t op1) +{ + if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS)) + return ppc_inst_equal(op0, ppc_inst(PPC_RAW_NOP())); + else + return ppc_inst_equal(op0, ppc_inst(PPC_RAW_BRANCH(8))) && + ppc_inst_equal(op1, ppc_inst(PPC_INST_LD_TOC)); +} + +static int +__ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) +{ + ppc_inst_t op[2]; + void *ip = (void *)rec->ip; + unsigned long entry, ptr, tramp; + struct module *mod = rec->arch.mod; + + /* read where this goes */ + if (copy_inst_from_kernel_nofault(op, ip)) + return -EFAULT; + + if (!IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS) && + copy_inst_from_kernel_nofault(op + 1, ip + 4)) + return -EFAULT; + + if (!expected_nop_sequence(ip, op[0], op[1])) { + pr_err("Unexpected call sequence at %p: %08lx %08lx\n", ip, + ppc_inst_as_ulong(op[0]), ppc_inst_as_ulong(op[1])); + return -EINVAL; + } + + /* If we never set up ftrace trampoline(s), then bail */ + if (!mod->arch.tramp || + (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS) && !mod->arch.tramp_regs)) { + pr_err("No ftrace trampoline\n"); + return -EINVAL; + } + + if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS) && rec->flags & FTRACE_FL_REGS) + tramp = mod->arch.tramp_regs; + else + tramp = mod->arch.tramp; + + if (module_trampoline_target(mod, tramp, &ptr)) { + pr_err("Failed to get trampoline target\n"); + return -EFAULT; + } + + pr_devel("trampoline target %lx", ptr); + + entry = ppc_global_function_entry((void *)addr); + /* This should match what was called */ + if (ptr != entry) { + pr_err("addr %lx does not match expected %lx\n", ptr, entry); + return -EINVAL; + } + + if (patch_branch(ip, tramp, BRANCH_SET_LINK)) { + pr_err("REL24 out of range!\n"); + return -EINVAL; + } + + return 0; +} +#else +static int __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) +{ + return 0; +} +#endif /* CONFIG_MODULES */ + +static int __ftrace_make_call_kernel(struct dyn_ftrace *rec, unsigned long addr) +{ + ppc_inst_t op; + void *ip = (void *)rec->ip; + unsigned long tramp, entry, ptr; + + /* Make sure we're being asked to patch branch to a known ftrace addr */ + entry = ppc_global_function_entry((void *)ftrace_caller); + ptr = ppc_global_function_entry((void *)addr); + + if (ptr != entry && IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS)) + entry = ppc_global_function_entry((void *)ftrace_regs_caller); + + if (ptr != entry) { + pr_err("Unknown ftrace addr to patch: %ps\n", (void *)ptr); + return -EINVAL; + } + + /* Make sure we have a nop */ + if (copy_inst_from_kernel_nofault(&op, ip)) { + pr_err("Unable to read ftrace location %p\n", ip); + return -EFAULT; + } + + if (!ppc_inst_equal(op, ppc_inst(PPC_RAW_NOP()))) { + pr_err("Unexpected call sequence at %p: %08lx\n", + ip, ppc_inst_as_ulong(op)); + return -EINVAL; + } + + tramp = find_ftrace_tramp((unsigned long)ip); + if (!tramp) { + pr_err("No ftrace trampolines reachable from %ps\n", ip); + return -EINVAL; + } + + if (patch_branch(ip, tramp, BRANCH_SET_LINK)) { + pr_err("Error patching branch to ftrace tramp!\n"); + return -EINVAL; + } + + return 0; +} + +int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) +{ + unsigned long ip = rec->ip; + ppc_inst_t old, new; + + /* + * If the calling address is more that 24 bits away, + * then we had to use a trampoline to make the call. + * Otherwise just update the call site. + */ + if (test_24bit_addr(ip, addr)) { + /* within range */ + old = ppc_inst(PPC_RAW_NOP()); + new = ftrace_call_replace(ip, addr, 1); + return ftrace_modify_code(ip, old, new); + } else if (core_kernel_text(ip)) { + return __ftrace_make_call_kernel(rec, addr); + } else if (!IS_ENABLED(CONFIG_MODULES)) { + /* We should not get here without modules */ + return -EINVAL; + } + + /* + * Out of range jumps are called from modules. + * Being that we are converting from nop, it had better + * already have a module defined. + */ + if (!rec->arch.mod) { + pr_err("No module loaded\n"); + return -EINVAL; + } + + return __ftrace_make_call(rec, addr); +} + +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS +#ifdef CONFIG_MODULES +static int +__ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, + unsigned long addr) +{ + ppc_inst_t op; + unsigned long ip = rec->ip; + unsigned long entry, ptr, tramp; + struct module *mod = rec->arch.mod; + + /* If we never set up ftrace trampolines, then bail */ + if (!mod->arch.tramp || !mod->arch.tramp_regs) { + pr_err("No ftrace trampoline\n"); + return -EINVAL; + } + + /* read where this goes */ + if (copy_inst_from_kernel_nofault(&op, (void *)ip)) { + pr_err("Fetching opcode failed.\n"); + return -EFAULT; + } + + /* Make sure that this is still a 24bit jump */ + if (!is_bl_op(op)) { + pr_err("Not expected bl: opcode is %08lx\n", ppc_inst_as_ulong(op)); + return -EINVAL; + } + + /* lets find where the pointer goes */ + tramp = find_bl_target(ip, op); + entry = ppc_global_function_entry((void *)old_addr); + + pr_devel("ip:%lx jumps to %lx", ip, tramp); + + if (tramp != entry) { + /* old_addr is not within range, so we must have used a trampoline */ + if (module_trampoline_target(mod, tramp, &ptr)) { + pr_err("Failed to get trampoline target\n"); + return -EFAULT; + } + + pr_devel("trampoline target %lx", ptr); + + /* This should match what was called */ + if (ptr != entry) { + pr_err("addr %lx does not match expected %lx\n", ptr, entry); + return -EINVAL; + } + } + + /* The new target may be within range */ + if (test_24bit_addr(ip, addr)) { + /* within range */ + if (patch_branch((u32 *)ip, addr, BRANCH_SET_LINK)) { + pr_err("REL24 out of range!\n"); + return -EINVAL; + } + + return 0; + } + + if (rec->flags & FTRACE_FL_REGS) + tramp = mod->arch.tramp_regs; + else + tramp = mod->arch.tramp; + + if (module_trampoline_target(mod, tramp, &ptr)) { + pr_err("Failed to get trampoline target\n"); + return -EFAULT; + } + + pr_devel("trampoline target %lx", ptr); + + entry = ppc_global_function_entry((void *)addr); + /* This should match what was called */ + if (ptr != entry) { + pr_err("addr %lx does not match expected %lx\n", ptr, entry); + return -EINVAL; + } + + if (patch_branch((u32 *)ip, tramp, BRANCH_SET_LINK)) { + pr_err("REL24 out of range!\n"); + return -EINVAL; + } + + return 0; +} +#else +static int __ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, unsigned long addr) +{ + return 0; +} +#endif + +int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, + unsigned long addr) +{ + unsigned long ip = rec->ip; + ppc_inst_t old, new; + + /* + * If the calling address is more that 24 bits away, + * then we had to use a trampoline to make the call. + * Otherwise just update the call site. + */ + if (test_24bit_addr(ip, addr) && test_24bit_addr(ip, old_addr)) { + /* within range */ + old = ftrace_call_replace(ip, old_addr, 1); + new = ftrace_call_replace(ip, addr, 1); + return ftrace_modify_code(ip, old, new); + } else if (core_kernel_text(ip)) { + /* + * We always patch out of range locations to go to the regs + * variant, so there is nothing to do here + */ + return 0; + } else if (!IS_ENABLED(CONFIG_MODULES)) { + /* We should not get here without modules */ + return -EINVAL; + } + + /* + * Out of range jumps are called from modules. + */ + if (!rec->arch.mod) { + pr_err("No module loaded\n"); + return -EINVAL; + } + + return __ftrace_modify_call(rec, old_addr, addr); +} +#endif + +int ftrace_update_ftrace_func(ftrace_func_t func) +{ + unsigned long ip = (unsigned long)(&ftrace_call); + ppc_inst_t old, new; + int ret; + + old = ppc_inst_read((u32 *)&ftrace_call); + new = ftrace_call_replace(ip, (unsigned long)func, 1); + ret = ftrace_modify_code(ip, old, new); + + /* Also update the regs callback function */ + if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS) && !ret) { + ip = (unsigned long)(&ftrace_regs_call); + old = ppc_inst_read((u32 *)&ftrace_regs_call); + new = ftrace_call_replace(ip, (unsigned long)func, 1); + ret = ftrace_modify_code(ip, old, new); + } + + return ret; +} + +/* + * Use the default ftrace_modify_all_code, but without + * stop_machine(). + */ +void arch_ftrace_update_code(int command) +{ + ftrace_modify_all_code(command); +} + +#ifdef CONFIG_PPC64 +#define PACATOC offsetof(struct paca_struct, kernel_toc) + +extern unsigned int ftrace_tramp_text[], ftrace_tramp_init[]; + +void ftrace_free_init_tramp(void) +{ + int i; + + for (i = 0; i < NUM_FTRACE_TRAMPS && ftrace_tramps[i]; i++) + if (ftrace_tramps[i] == (unsigned long)ftrace_tramp_init) { + ftrace_tramps[i] = 0; + return; + } +} + +int __init ftrace_dyn_arch_init(void) +{ + int i; + unsigned int *tramp[] = { ftrace_tramp_text, ftrace_tramp_init }; + u32 stub_insns[] = { + PPC_RAW_LD(_R12, _R13, PACATOC), + PPC_RAW_ADDIS(_R12, _R12, 0), + PPC_RAW_ADDI(_R12, _R12, 0), + PPC_RAW_MTCTR(_R12), + PPC_RAW_BCTR() + }; + unsigned long addr; + long reladdr; + + if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS)) + addr = ppc_global_function_entry((void *)ftrace_regs_caller); + else + addr = ppc_global_function_entry((void *)ftrace_caller); + + reladdr = addr - kernel_toc_addr(); + + if (reladdr >= SZ_2G || reladdr < -(long)SZ_2G) { + pr_err("Address of %ps out of range of kernel_toc.\n", + (void *)addr); + return -1; + } + + for (i = 0; i < 2; i++) { + memcpy(tramp[i], stub_insns, sizeof(stub_insns)); + tramp[i][1] |= PPC_HA(reladdr); + tramp[i][2] |= PPC_LO(reladdr); + add_ftrace_tramp((unsigned long)tramp[i]); + } + + return 0; +} +#endif + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + +extern void ftrace_graph_call(void); +extern void ftrace_graph_stub(void); + +static int ftrace_modify_ftrace_graph_caller(bool enable) +{ + unsigned long ip = (unsigned long)(&ftrace_graph_call); + unsigned long addr = (unsigned long)(&ftrace_graph_caller); + unsigned long stub = (unsigned long)(&ftrace_graph_stub); + ppc_inst_t old, new; + + if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_ARGS)) + return 0; + + old = ftrace_call_replace(ip, enable ? stub : addr, 0); + new = ftrace_call_replace(ip, enable ? addr : stub, 0); + + return ftrace_modify_code(ip, old, new); +} + +int ftrace_enable_ftrace_graph_caller(void) +{ + return ftrace_modify_ftrace_graph_caller(true); +} + +int ftrace_disable_ftrace_graph_caller(void) +{ + return ftrace_modify_ftrace_graph_caller(false); +} + +/* + * Hook the return address and push it in the stack of return addrs + * in current thread info. Return the address we want to divert to. + */ +static unsigned long +__prepare_ftrace_return(unsigned long parent, unsigned long ip, unsigned long sp) +{ + unsigned long return_hooker; + int bit; + + if (unlikely(ftrace_graph_is_dead())) + goto out; + + if (unlikely(atomic_read(¤t->tracing_graph_pause))) + goto out; + + bit = ftrace_test_recursion_trylock(ip, parent); + if (bit < 0) + goto out; + + return_hooker = ppc_function_entry(return_to_handler); + + if (!function_graph_enter(parent, ip, 0, (unsigned long *)sp)) + parent = return_hooker; + + ftrace_test_recursion_unlock(bit); +out: + return parent; +} + +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS +void ftrace_graph_func(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct ftrace_regs *fregs) +{ + fregs->regs.link = __prepare_ftrace_return(parent_ip, ip, fregs->regs.gpr[1]); +} +#else +unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip, + unsigned long sp) +{ + return __prepare_ftrace_return(parent, ip, sp); +} +#endif +#endif /* CONFIG_FUNCTION_GRAPH_TRACER */ + +#ifdef CONFIG_PPC64_ELF_ABI_V1 +char *arch_ftrace_match_adjust(char *str, const char *search) +{ + if (str[0] == '.' && search[0] != '.') + return str + 1; + else + return str; +} +#endif /* CONFIG_PPC64_ELF_ABI_V1 */ diff --git a/arch/powerpc/kernel/trace/ftrace_low.S b/arch/powerpc/kernel/trace/ftrace_64_pg_entry.S index 294d1e05958a..a8a7f28404c8 100644 --- a/arch/powerpc/kernel/trace/ftrace_low.S +++ b/arch/powerpc/kernel/trace/ftrace_64_pg_entry.S @@ -1,28 +1,82 @@ /* SPDX-License-Identifier: GPL-2.0-or-later */ /* - * Split from entry_64.S + * Split from ftrace_64.S */ +#include <linux/export.h> #include <linux/magic.h> #include <asm/ppc_asm.h> #include <asm/asm-offsets.h> #include <asm/ftrace.h> #include <asm/ppc-opcode.h> -#include <asm/export.h> -#ifdef CONFIG_PPC64 +_GLOBAL_TOC(ftrace_caller) + lbz r3, PACA_FTRACE_ENABLED(r13) + cmpdi r3, 0 + beqlr + + /* Taken from output of objdump from lib64/glibc */ + mflr r3 + ld r11, 0(r1) + stdu r1, -112(r1) + std r3, 128(r1) + ld r4, 16(r11) + subi r3, r3, MCOUNT_INSN_SIZE +.globl ftrace_call +ftrace_call: + bl ftrace_stub + nop +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +.globl ftrace_graph_call +ftrace_graph_call: + b ftrace_graph_stub +_GLOBAL(ftrace_graph_stub) +#endif + ld r0, 128(r1) + mtlr r0 + addi r1, r1, 112 + +_GLOBAL(ftrace_stub) + blr + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +_GLOBAL(ftrace_graph_caller) + addi r5, r1, 112 + /* load r4 with local address */ + ld r4, 128(r1) + subi r4, r4, MCOUNT_INSN_SIZE + + /* Grab the LR out of the caller stack frame */ + ld r11, 112(r1) + ld r3, 16(r11) + + bl prepare_ftrace_return + nop + + /* + * prepare_ftrace_return gives us the address we divert to. + * Change the LR in the callers stack frame to this. + */ + ld r11, 112(r1) + std r3, 16(r11) + + ld r0, 128(r1) + mtlr r0 + addi r1, r1, 112 + blr +#endif /* CONFIG_FUNCTION_GRAPH_TRACER */ + .pushsection ".tramp.ftrace.text","aw",@progbits; .globl ftrace_tramp_text ftrace_tramp_text: - .space 64 + .space 32 .popsection .pushsection ".tramp.ftrace.init","aw",@progbits; .globl ftrace_tramp_init ftrace_tramp_init: - .space 64 + .space 32 .popsection -#endif _GLOBAL(mcount) _GLOBAL(_mcount) diff --git a/arch/powerpc/kernel/trace/ftrace_mprofile.S b/arch/powerpc/kernel/trace/ftrace_entry.S index ffb1db386849..90701885762c 100644 --- a/arch/powerpc/kernel/trace/ftrace_mprofile.S +++ b/arch/powerpc/kernel/trace/ftrace_entry.S @@ -3,12 +3,12 @@ * Split from ftrace_64.S */ +#include <linux/export.h> #include <linux/magic.h> #include <asm/ppc_asm.h> #include <asm/asm-offsets.h> #include <asm/ftrace.h> #include <asm/ppc-opcode.h> -#include <asm/export.h> #include <asm/thread_info.h> #include <asm/bug.h> #include <asm/ptrace.h> @@ -33,6 +33,9 @@ * and then arrange for the ftrace function to be called. */ .macro ftrace_regs_entry allregs + /* Create a minimal stack frame for representing B */ + PPC_STLU r1, -STACK_FRAME_MIN_SIZE(r1) + /* Create our stack frame + pt_regs */ PPC_STLU r1,-SWITCH_FRAME_SIZE(r1) @@ -42,7 +45,7 @@ #ifdef CONFIG_PPC64 /* Save the original return address in A's stack frame */ - std r0, LRSAVE+SWITCH_FRAME_SIZE(r1) + std r0, LRSAVE+SWITCH_FRAME_SIZE+STACK_FRAME_MIN_SIZE(r1) /* Ok to continue? */ lbz r3, PACA_FTRACE_ENABLED(r13) cmpdi r3, 0 @@ -77,6 +80,8 @@ mflr r7 /* Save it as pt_regs->nip */ PPC_STL r7, _NIP(r1) + /* Also save it in B's stackframe header for proper unwind */ + PPC_STL r7, LRSAVE+SWITCH_FRAME_SIZE(r1) /* Save the read LR in pt_regs->link */ PPC_STL r0, _LINK(r1) @@ -142,7 +147,7 @@ #endif /* Pop our stack frame */ - addi r1, r1, SWITCH_FRAME_SIZE + addi r1, r1, SWITCH_FRAME_SIZE+STACK_FRAME_MIN_SIZE #ifdef CONFIG_LIVEPATCH_64 /* Based on the cmpd above, if the NIP was altered handle livepatch */ @@ -249,3 +254,70 @@ livepatch_handler: /* Return to original caller of live patched function */ blr #endif /* CONFIG_LIVEPATCH */ + +#ifndef CONFIG_ARCH_USING_PATCHABLE_FUNCTION_ENTRY +_GLOBAL(mcount) +_GLOBAL(_mcount) +EXPORT_SYMBOL(_mcount) + mflr r12 + mtctr r12 + mtlr r0 + bctr +#endif + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +_GLOBAL(return_to_handler) + /* need to save return values */ +#ifdef CONFIG_PPC64 + std r4, -32(r1) + std r3, -24(r1) + /* save TOC */ + std r2, -16(r1) + std r31, -8(r1) + mr r31, r1 + stdu r1, -112(r1) + + /* + * We might be called from a module. + * Switch to our TOC to run inside the core kernel. + */ + LOAD_PACA_TOC() +#else + stwu r1, -16(r1) + stw r3, 8(r1) + stw r4, 12(r1) +#endif + + bl ftrace_return_to_handler + nop + + /* return value has real return address */ + mtlr r3 + +#ifdef CONFIG_PPC64 + ld r1, 0(r1) + ld r4, -32(r1) + ld r3, -24(r1) + ld r2, -16(r1) + ld r31, -8(r1) +#else + lwz r3, 8(r1) + lwz r4, 12(r1) + addi r1, r1, 16 +#endif + + /* Jump back to real return address */ + blr +#endif /* CONFIG_FUNCTION_GRAPH_TRACER */ + +.pushsection ".tramp.ftrace.text","aw",@progbits; +.globl ftrace_tramp_text +ftrace_tramp_text: + .space 32 +.popsection + +.pushsection ".tramp.ftrace.init","aw",@progbits; +.globl ftrace_tramp_init +ftrace_tramp_init: + .space 32 +.popsection diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index 7ef147e2a20d..eeff136b83d9 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -1158,7 +1158,7 @@ DEFINE_INTERRUPT_HANDLER(single_step_exception) * pretend we got a single-step exception. This was pointed out * by Kumar Gala. -- paulus */ -static void emulate_single_step(struct pt_regs *regs) +void emulate_single_step(struct pt_regs *regs) { if (single_stepping(regs)) __single_step_exception(regs); @@ -2225,21 +2225,10 @@ void __noreturn unrecoverable_exception(struct pt_regs *regs) } #if defined(CONFIG_BOOKE_WDT) || defined(CONFIG_40x) -/* - * Default handler for a Watchdog exception, - * spins until a reboot occurs - */ -void __attribute__ ((weak)) WatchdogHandler(struct pt_regs *regs) -{ - /* Generic WatchdogHandler, implement your own */ - mtspr(SPRN_TCR, mfspr(SPRN_TCR)&(~TCR_WIE)); - return; -} - DEFINE_INTERRUPT_HANDLER_NMI(WatchdogException) { printk (KERN_EMERG "PowerPC Book-E Watchdog Exception\n"); - WatchdogHandler(regs); + mtspr(SPRN_TCR, mfspr(SPRN_TCR) & ~TCR_WIE); return 0; } #endif diff --git a/arch/powerpc/kernel/ucall.S b/arch/powerpc/kernel/ucall.S index 07296bc39166..80a1f9a4300a 100644 --- a/arch/powerpc/kernel/ucall.S +++ b/arch/powerpc/kernel/ucall.S @@ -5,8 +5,8 @@ * Copyright 2019, IBM Corporation. * */ +#include <linux/export.h> #include <asm/ppc_asm.h> -#include <asm/export.h> _GLOBAL(ucall_norets) EXPORT_SYMBOL_GPL(ucall_norets) diff --git a/arch/powerpc/kernel/vector.S b/arch/powerpc/kernel/vector.S index fcc0ad6d9c7b..4094e4c4c77a 100644 --- a/arch/powerpc/kernel/vector.S +++ b/arch/powerpc/kernel/vector.S @@ -1,4 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ +#include <linux/export.h> #include <linux/linkage.h> #include <asm/processor.h> #include <asm/ppc_asm.h> @@ -8,7 +9,6 @@ #include <asm/thread_info.h> #include <asm/page.h> #include <asm/ptrace.h> -#include <asm/export.h> #include <asm/asm-compat.h> /* diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index 13614f0b269c..1c5970df3233 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -107,9 +107,7 @@ SECTIONS #endif /* careful! __ftr_alt_* sections need to be close to .text */ *(.text.hot .text.hot.* TEXT_MAIN .text.fixup .text.unlikely .text.unlikely.* .fixup __ftr_alt_* .ref.text); -#ifdef CONFIG_PPC64 *(.tramp.ftrace.text); -#endif NOINSTR_TEXT SCHED_TEXT LOCK_TEXT @@ -276,9 +274,7 @@ SECTIONS */ . = ALIGN(PAGE_SIZE); _einittext = .; -#ifdef CONFIG_PPC64 *(.tramp.ftrace.init); -#endif } :text /* .exit.text is discarded at runtime, not link time, diff --git a/arch/powerpc/kernel/watchdog.c b/arch/powerpc/kernel/watchdog.c index edb2dd1f53eb..8c464a5d8246 100644 --- a/arch/powerpc/kernel/watchdog.c +++ b/arch/powerpc/kernel/watchdog.c @@ -245,7 +245,7 @@ static void watchdog_smp_panic(int cpu) __cpumask_clear_cpu(c, &wd_smp_cpus_ipi); } } else { - trigger_allbutself_cpu_backtrace(); + trigger_allbutcpu_cpu_backtrace(cpu); cpumask_clear(&wd_smp_cpus_ipi); } @@ -416,7 +416,7 @@ DEFINE_INTERRUPT_HANDLER_NMI(soft_nmi_interrupt) xchg(&__wd_nmi_output, 1); // see wd_lockup_ipi if (sysctl_hardlockup_all_cpu_backtrace) - trigger_allbutself_cpu_backtrace(); + trigger_allbutcpu_cpu_backtrace(cpu); if (hardlockup_panic) nmi_panic(regs, "Hard LOCKUP"); diff --git a/arch/powerpc/kexec/crash.c b/arch/powerpc/kexec/crash.c index 252724ed666a..ef5c2d25ec39 100644 --- a/arch/powerpc/kexec/crash.c +++ b/arch/powerpc/kexec/crash.c @@ -350,7 +350,7 @@ EXPORT_SYMBOL(crash_shutdown_unregister); void default_machine_crash_shutdown(struct pt_regs *regs) { - unsigned int i; + volatile unsigned int i; int (*old_handler)(struct pt_regs *regs); if (TRAP(regs) == INTERRUPT_SYSTEM_RESET) diff --git a/arch/powerpc/kexec/file_load_64.c b/arch/powerpc/kexec/file_load_64.c index 110d28bede2a..a3de5369d22c 100644 --- a/arch/powerpc/kexec/file_load_64.c +++ b/arch/powerpc/kexec/file_load_64.c @@ -17,7 +17,7 @@ #include <linux/kexec.h> #include <linux/of_fdt.h> #include <linux/libfdt.h> -#include <linux/of_device.h> +#include <linux/of.h> #include <linux/memblock.h> #include <linux/slab.h> #include <linux/vmalloc.h> @@ -27,6 +27,7 @@ #include <asm/kexec_ranges.h> #include <asm/crashdump-ppc64.h> #include <asm/mmzone.h> +#include <asm/iommu.h> #include <asm/prom.h> #include <asm/plpks.h> @@ -933,9 +934,9 @@ out: } /** - * get_cpu_node_size - Compute the size of a CPU node in the FDT. - * This should be done only once and the value is stored in - * a static variable. + * cpu_node_size - Compute the size of a CPU node in the FDT. + * This should be done only once and the value is stored in + * a static variable. * Returns the max size of a CPU node in the FDT. */ static unsigned int cpu_node_size(void) @@ -1208,8 +1209,6 @@ int setup_new_fdt_ppc64(const struct kimage *image, void *fdt, if (ret < 0) goto out; -#define DIRECT64_PROPNAME "linux,direct64-ddr-window-info" -#define DMA64_PROPNAME "linux,dma64-ddr-window-info" ret = update_pci_dma_nodes(fdt, DIRECT64_PROPNAME); if (ret < 0) goto out; @@ -1217,8 +1216,6 @@ int setup_new_fdt_ppc64(const struct kimage *image, void *fdt, ret = update_pci_dma_nodes(fdt, DMA64_PROPNAME); if (ret < 0) goto out; -#undef DMA64_PROPNAME -#undef DIRECT64_PROPNAME /* Update memory reserve map */ ret = get_reserved_memory_ranges(&rmem); diff --git a/arch/powerpc/kexec/ranges.c b/arch/powerpc/kexec/ranges.c index 5fc53a5fcfdf..fb3e12f15214 100644 --- a/arch/powerpc/kexec/ranges.c +++ b/arch/powerpc/kexec/ranges.c @@ -18,7 +18,7 @@ #include <linux/sort.h> #include <linux/kexec.h> -#include <linux/of_device.h> +#include <linux/of.h> #include <linux/slab.h> #include <asm/sections.h> #include <asm/kexec_ranges.h> diff --git a/arch/powerpc/kvm/book3s_64_entry.S b/arch/powerpc/kvm/book3s_64_entry.S index 6c2b1d17cb63..3b361af87313 100644 --- a/arch/powerpc/kvm/book3s_64_entry.S +++ b/arch/powerpc/kvm/book3s_64_entry.S @@ -1,9 +1,9 @@ /* SPDX-License-Identifier: GPL-2.0-only */ +#include <linux/export.h> #include <asm/asm-offsets.h> #include <asm/cache.h> #include <asm/code-patching-asm.h> #include <asm/exception-64s.h> -#include <asm/export.h> #include <asm/kvm_asm.h> #include <asm/kvm_book3s_asm.h> #include <asm/mmu.h> diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c index 7f765d5ad436..efd0ebf70a5e 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_hv.c +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c @@ -182,7 +182,7 @@ void kvmppc_free_hpt(struct kvm_hpt_info *info) vfree(info->rev); info->rev = NULL; if (info->cma) - kvm_free_hpt_cma(virt_to_page(info->virt), + kvm_free_hpt_cma(virt_to_page((void *)info->virt), 1 << (info->order - PAGE_SHIFT)); else if (info->virt) free_pages(info->virt, info->order - PAGE_SHIFT); diff --git a/arch/powerpc/kvm/book3s_hv_ras.c b/arch/powerpc/kvm/book3s_hv_ras.c index ccfd96965630..82be6d87514b 100644 --- a/arch/powerpc/kvm/book3s_hv_ras.c +++ b/arch/powerpc/kvm/book3s_hv_ras.c @@ -9,6 +9,7 @@ #include <linux/kvm.h> #include <linux/kvm_host.h> #include <linux/kernel.h> +#include <asm/lppaca.h> #include <asm/opal.h> #include <asm/mce.h> #include <asm/machdep.h> diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index 870110e3d9b1..ea7ad200b330 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -10,6 +10,7 @@ * Authors: Alexander Graf <agraf@suse.de> */ +#include <linux/export.h> #include <linux/linkage.h> #include <linux/objtool.h> #include <asm/ppc_asm.h> @@ -24,7 +25,6 @@ #include <asm/exception-64s.h> #include <asm/kvm_book3s_asm.h> #include <asm/book3s/64/mmu-hash.h> -#include <asm/export.h> #include <asm/tm.h> #include <asm/opal.h> #include <asm/thread_info.h> diff --git a/arch/powerpc/kvm/book3s_hv_uvmem.c b/arch/powerpc/kvm/book3s_hv_uvmem.c index 709ebd578394..e2d6f9327f77 100644 --- a/arch/powerpc/kvm/book3s_hv_uvmem.c +++ b/arch/powerpc/kvm/book3s_hv_uvmem.c @@ -410,6 +410,7 @@ static int kvmppc_memslot_page_merge(struct kvm *kvm, ret = H_STATE; break; } + vma_start_write(vma); /* Copy vm_flags to avoid partial modifications in ksm_madvise */ vm_flags = vma->vm_flags; ret = ksm_madvise(vma, vma->vm_start, vma->vm_end, diff --git a/arch/powerpc/kvm/e500mc.c b/arch/powerpc/kvm/e500mc.c index d58df71ace58..e476e107a932 100644 --- a/arch/powerpc/kvm/e500mc.c +++ b/arch/powerpc/kvm/e500mc.c @@ -20,6 +20,7 @@ #include <asm/cputable.h> #include <asm/kvm_ppc.h> #include <asm/dbell.h> +#include <asm/ppc-opcode.h> #include "booke.h" #include "e500.h" @@ -92,7 +93,11 @@ void kvmppc_e500_tlbil_all(struct kvmppc_vcpu_e500 *vcpu_e500) local_irq_save(flags); mtspr(SPRN_MAS5, MAS5_SGS | get_lpid(&vcpu_e500->vcpu)); - asm volatile("tlbilxlpid"); + /* + * clang-17 and older could not assemble tlbilxlpid. + * https://github.com/ClangBuiltLinux/linux/issues/1891 + */ + asm volatile (PPC_TLBILX_LPID); mtspr(SPRN_MAS5, 0); local_irq_restore(flags); } diff --git a/arch/powerpc/kvm/tm.S b/arch/powerpc/kvm/tm.S index 2158f61e317f..b506c4d9a8d9 100644 --- a/arch/powerpc/kvm/tm.S +++ b/arch/powerpc/kvm/tm.S @@ -6,10 +6,10 @@ * Copyright 2011 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com> */ +#include <linux/export.h> #include <asm/reg.h> #include <asm/ppc_asm.h> #include <asm/asm-offsets.h> -#include <asm/export.h> #include <asm/tm.h> #include <asm/cputable.h> diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile index 9aa8286c9687..51ad0397c17a 100644 --- a/arch/powerpc/lib/Makefile +++ b/arch/powerpc/lib/Makefile @@ -27,7 +27,7 @@ endif CFLAGS_code-patching.o += $(DISABLE_LATENT_ENTROPY_PLUGIN) CFLAGS_feature-fixups.o += $(DISABLE_LATENT_ENTROPY_PLUGIN) -obj-y += alloc.o code-patching.o feature-fixups.o pmem.o +obj-y += code-patching.o feature-fixups.o pmem.o obj-$(CONFIG_CODE_PATCHING_SELFTEST) += test-code-patching.o diff --git a/arch/powerpc/lib/alloc.c b/arch/powerpc/lib/alloc.c deleted file mode 100644 index ce180870bd52..000000000000 --- a/arch/powerpc/lib/alloc.c +++ /dev/null @@ -1,23 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <linux/types.h> -#include <linux/init.h> -#include <linux/slab.h> -#include <linux/memblock.h> -#include <linux/string.h> -#include <asm/setup.h> - - -void * __ref zalloc_maybe_bootmem(size_t size, gfp_t mask) -{ - void *p; - - if (slab_is_available()) - p = kzalloc(size, mask); - else { - p = memblock_alloc(size, SMP_CACHE_BYTES); - if (!p) - panic("%s: Failed to allocate %zu bytes\n", __func__, - size); - } - return p; -} diff --git a/arch/powerpc/lib/checksum_32.S b/arch/powerpc/lib/checksum_32.S index 4541e8e29467..cd00b9bdd772 100644 --- a/arch/powerpc/lib/checksum_32.S +++ b/arch/powerpc/lib/checksum_32.S @@ -8,12 +8,12 @@ * Severely hacked about by Paul Mackerras (paulus@cs.anu.edu.au). */ +#include <linux/export.h> #include <linux/sys.h> #include <asm/processor.h> #include <asm/cache.h> #include <asm/errno.h> #include <asm/ppc_asm.h> -#include <asm/export.h> .text diff --git a/arch/powerpc/lib/checksum_64.S b/arch/powerpc/lib/checksum_64.S index 98ff51bd2f7d..d53d8f09a2c2 100644 --- a/arch/powerpc/lib/checksum_64.S +++ b/arch/powerpc/lib/checksum_64.S @@ -8,11 +8,11 @@ * Severely hacked about by Paul Mackerras (paulus@cs.anu.edu.au). */ +#include <linux/export.h> #include <linux/sys.h> #include <asm/processor.h> #include <asm/errno.h> #include <asm/ppc_asm.h> -#include <asm/export.h> /* * Computes the checksum of a memory block at buff, length len, diff --git a/arch/powerpc/lib/copy_32.S b/arch/powerpc/lib/copy_32.S index 3e9c27c46331..933b685e7ab6 100644 --- a/arch/powerpc/lib/copy_32.S +++ b/arch/powerpc/lib/copy_32.S @@ -4,11 +4,11 @@ * * Copyright (C) 1996-2005 Paul Mackerras. */ +#include <linux/export.h> #include <asm/processor.h> #include <asm/cache.h> #include <asm/errno.h> #include <asm/ppc_asm.h> -#include <asm/export.h> #include <asm/code-patching-asm.h> #include <asm/kasan.h> diff --git a/arch/powerpc/lib/copy_mc_64.S b/arch/powerpc/lib/copy_mc_64.S index 88d46c471493..bf1014b28fe8 100644 --- a/arch/powerpc/lib/copy_mc_64.S +++ b/arch/powerpc/lib/copy_mc_64.S @@ -4,9 +4,9 @@ * Derived from copyuser_power7.s by Anton Blanchard <anton@au.ibm.com> * Author - Balbir Singh <bsingharora@gmail.com> */ +#include <linux/export.h> #include <asm/ppc_asm.h> #include <asm/errno.h> -#include <asm/export.h> .macro err1 100: diff --git a/arch/powerpc/lib/copypage_64.S b/arch/powerpc/lib/copypage_64.S index 5d09a029b556..f33a2e6088e5 100644 --- a/arch/powerpc/lib/copypage_64.S +++ b/arch/powerpc/lib/copypage_64.S @@ -2,11 +2,11 @@ /* * Copyright (C) 2008 Mark Nelson, IBM Corp. */ +#include <linux/export.h> #include <asm/page.h> #include <asm/processor.h> #include <asm/ppc_asm.h> #include <asm/asm-offsets.h> -#include <asm/export.h> #include <asm/feature-fixups.h> _GLOBAL_TOC(copy_page) diff --git a/arch/powerpc/lib/copyuser_64.S b/arch/powerpc/lib/copyuser_64.S index db8719a14846..9af969d2cc0c 100644 --- a/arch/powerpc/lib/copyuser_64.S +++ b/arch/powerpc/lib/copyuser_64.S @@ -2,9 +2,9 @@ /* * Copyright (C) 2002 Paul Mackerras, IBM Corp. */ +#include <linux/export.h> #include <asm/processor.h> #include <asm/ppc_asm.h> -#include <asm/export.h> #include <asm/asm-compat.h> #include <asm/feature-fixups.h> diff --git a/arch/powerpc/lib/feature-fixups.c b/arch/powerpc/lib/feature-fixups.c index 80def1c2afcb..4f82581ca203 100644 --- a/arch/powerpc/lib/feature-fixups.c +++ b/arch/powerpc/lib/feature-fixups.c @@ -67,7 +67,8 @@ static int patch_alt_instruction(u32 *src, u32 *dest, u32 *alt_start, u32 *alt_e return 0; } -static int patch_feature_section(unsigned long value, struct fixup_entry *fcur) +static int patch_feature_section_mask(unsigned long value, unsigned long mask, + struct fixup_entry *fcur) { u32 *start, *end, *alt_start, *alt_end, *src, *dest; @@ -79,7 +80,7 @@ static int patch_feature_section(unsigned long value, struct fixup_entry *fcur) if ((alt_end - alt_start) > (end - start)) return 1; - if ((value & fcur->mask) == fcur->value) + if ((value & fcur->mask & mask) == (fcur->value & mask)) return 0; src = alt_start; @@ -97,7 +98,8 @@ static int patch_feature_section(unsigned long value, struct fixup_entry *fcur) return 0; } -void do_feature_fixups(unsigned long value, void *fixup_start, void *fixup_end) +static void do_feature_fixups_mask(unsigned long value, unsigned long mask, + void *fixup_start, void *fixup_end) { struct fixup_entry *fcur, *fend; @@ -105,7 +107,7 @@ void do_feature_fixups(unsigned long value, void *fixup_start, void *fixup_end) fend = fixup_end; for (; fcur < fend; fcur++) { - if (patch_feature_section(value, fcur)) { + if (patch_feature_section_mask(value, mask, fcur)) { WARN_ON(1); printk("Unable to patch feature section at %p - %p" \ " with %p - %p\n", @@ -117,6 +119,11 @@ void do_feature_fixups(unsigned long value, void *fixup_start, void *fixup_end) } } +void do_feature_fixups(unsigned long value, void *fixup_start, void *fixup_end) +{ + do_feature_fixups_mask(value, ~0, fixup_start, fixup_end); +} + #ifdef CONFIG_PPC_BARRIER_NOSPEC static bool is_fixup_addr_valid(void *dest, size_t size) { @@ -651,6 +658,17 @@ void __init apply_feature_fixups(void) do_final_fixups(); } +void __init update_mmu_feature_fixups(unsigned long mask) +{ + saved_mmu_features &= ~mask; + saved_mmu_features |= cur_cpu_spec->mmu_features & mask; + + do_feature_fixups_mask(cur_cpu_spec->mmu_features, mask, + PTRRELOC(&__start___mmu_ftr_fixup), + PTRRELOC(&__stop___mmu_ftr_fixup)); + mmu_feature_keys_init(); +} + void __init setup_feature_keys(void) { /* @@ -683,6 +701,11 @@ late_initcall(check_features); #define check(x) \ if (!(x)) printk("feature-fixups: test failed at line %d\n", __LINE__); +static int patch_feature_section(unsigned long value, struct fixup_entry *fcur) +{ + return patch_feature_section_mask(value, ~0, fcur); +} + /* This must be after the text it fixes up, vmlinux.lds.S enforces that atm */ static struct fixup_entry fixup; diff --git a/arch/powerpc/lib/hweight_64.S b/arch/powerpc/lib/hweight_64.S index 09af29561314..151875050da9 100644 --- a/arch/powerpc/lib/hweight_64.S +++ b/arch/powerpc/lib/hweight_64.S @@ -5,9 +5,9 @@ * * Author: Anton Blanchard <anton@au.ibm.com> */ +#include <linux/export.h> #include <asm/processor.h> #include <asm/ppc_asm.h> -#include <asm/export.h> #include <asm/feature-fixups.h> /* Note: This code relies on -mminimal-toc */ diff --git a/arch/powerpc/lib/mem_64.S b/arch/powerpc/lib/mem_64.S index 9351ffab409c..6fd06cd20faa 100644 --- a/arch/powerpc/lib/mem_64.S +++ b/arch/powerpc/lib/mem_64.S @@ -4,10 +4,10 @@ * * Copyright (C) 1996 Paul Mackerras. */ +#include <linux/export.h> #include <asm/processor.h> #include <asm/errno.h> #include <asm/ppc_asm.h> -#include <asm/export.h> #include <asm/kasan.h> #ifndef CONFIG_KASAN diff --git a/arch/powerpc/lib/memcmp_32.S b/arch/powerpc/lib/memcmp_32.S index 5010e376f7b8..f6fca5664e91 100644 --- a/arch/powerpc/lib/memcmp_32.S +++ b/arch/powerpc/lib/memcmp_32.S @@ -7,8 +7,8 @@ * */ +#include <linux/export.h> #include <asm/ppc_asm.h> -#include <asm/export.h> .text diff --git a/arch/powerpc/lib/memcmp_64.S b/arch/powerpc/lib/memcmp_64.S index 0b9b1685a33d..142c666d3897 100644 --- a/arch/powerpc/lib/memcmp_64.S +++ b/arch/powerpc/lib/memcmp_64.S @@ -3,8 +3,8 @@ * Author: Anton Blanchard <anton@au.ibm.com> * Copyright 2015 IBM Corporation. */ +#include <linux/export.h> #include <asm/ppc_asm.h> -#include <asm/export.h> #include <asm/ppc-opcode.h> #define off8 r6 diff --git a/arch/powerpc/lib/memcpy_64.S b/arch/powerpc/lib/memcpy_64.S index 016c91e958d8..b5a67e20143f 100644 --- a/arch/powerpc/lib/memcpy_64.S +++ b/arch/powerpc/lib/memcpy_64.S @@ -2,9 +2,9 @@ /* * Copyright (C) 2002 Paul Mackerras, IBM Corp. */ +#include <linux/export.h> #include <asm/processor.h> #include <asm/ppc_asm.h> -#include <asm/export.h> #include <asm/asm-compat.h> #include <asm/feature-fixups.h> #include <asm/kasan.h> diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c index 38158b77a801..a4ab8625061a 100644 --- a/arch/powerpc/lib/sstep.c +++ b/arch/powerpc/lib/sstep.c @@ -485,7 +485,7 @@ write_mem_aligned(unsigned long val, unsigned long ea, int nb, struct pt_regs *r * Copy from a buffer to userspace, using the largest possible * aligned accesses, up to sizeof(long). */ -static nokprobe_inline int __copy_mem_out(u8 *dest, unsigned long ea, int nb, struct pt_regs *regs) +static __always_inline int __copy_mem_out(u8 *dest, unsigned long ea, int nb, struct pt_regs *regs) { int c; @@ -1043,7 +1043,7 @@ static nokprobe_inline int do_vsx_store(struct instruction_op *op, } #endif /* CONFIG_VSX */ -static int __emulate_dcbz(unsigned long ea) +static __always_inline int __emulate_dcbz(unsigned long ea) { unsigned long i; unsigned long size = l1_dcache_bytes(); diff --git a/arch/powerpc/lib/string.S b/arch/powerpc/lib/string.S index 2752b1cc1d45..daa72061dc0c 100644 --- a/arch/powerpc/lib/string.S +++ b/arch/powerpc/lib/string.S @@ -4,8 +4,8 @@ * * Copyright (C) 1996 Paul Mackerras. */ +#include <linux/export.h> #include <asm/ppc_asm.h> -#include <asm/export.h> #include <asm/cache.h> .text diff --git a/arch/powerpc/lib/string_32.S b/arch/powerpc/lib/string_32.S index 1ddb26394e8a..3ee45619a3f8 100644 --- a/arch/powerpc/lib/string_32.S +++ b/arch/powerpc/lib/string_32.S @@ -7,8 +7,8 @@ * */ +#include <linux/export.h> #include <asm/ppc_asm.h> -#include <asm/export.h> #include <asm/cache.h> .text diff --git a/arch/powerpc/lib/string_64.S b/arch/powerpc/lib/string_64.S index df41ce06f86b..a25eb8588434 100644 --- a/arch/powerpc/lib/string_64.S +++ b/arch/powerpc/lib/string_64.S @@ -6,10 +6,10 @@ * Author: Anton Blanchard <anton@au.ibm.com> */ +#include <linux/export.h> #include <asm/ppc_asm.h> #include <asm/linkage.h> #include <asm/asm-offsets.h> -#include <asm/export.h> /** * __arch_clear_user: - Zero a block of memory in user space, with less checking. diff --git a/arch/powerpc/lib/strlen_32.S b/arch/powerpc/lib/strlen_32.S index 0a8d3f64d493..bbd24feb233f 100644 --- a/arch/powerpc/lib/strlen_32.S +++ b/arch/powerpc/lib/strlen_32.S @@ -6,8 +6,8 @@ * * Inspired from glibc implementation */ +#include <linux/export.h> #include <asm/ppc_asm.h> -#include <asm/export.h> #include <asm/cache.h> .text diff --git a/arch/powerpc/mm/book3s32/hash_low.S b/arch/powerpc/mm/book3s32/hash_low.S index a5a21d444e72..8b804e1a9fa4 100644 --- a/arch/powerpc/mm/book3s32/hash_low.S +++ b/arch/powerpc/mm/book3s32/hash_low.S @@ -14,6 +14,7 @@ * hash table, so this file is not used on them.) */ +#include <linux/export.h> #include <linux/pgtable.h> #include <linux/init.h> #include <asm/reg.h> @@ -22,7 +23,6 @@ #include <asm/ppc_asm.h> #include <asm/thread_info.h> #include <asm/asm-offsets.h> -#include <asm/export.h> #include <asm/feature-fixups.h> #include <asm/code-patching-asm.h> diff --git a/arch/powerpc/mm/book3s32/kuap.c b/arch/powerpc/mm/book3s32/kuap.c index 28676cabb005..3a8815555a48 100644 --- a/arch/powerpc/mm/book3s32/kuap.c +++ b/arch/powerpc/mm/book3s32/kuap.c @@ -3,25 +3,11 @@ #include <asm/kup.h> #include <asm/smp.h> -struct static_key_false disable_kuap_key; -EXPORT_SYMBOL(disable_kuap_key); - -void kuap_lock_all_ool(void) -{ - kuap_lock_all(); -} -EXPORT_SYMBOL(kuap_lock_all_ool); - -void kuap_unlock_all_ool(void) -{ - kuap_unlock_all(); -} -EXPORT_SYMBOL(kuap_unlock_all_ool); - void setup_kuap(bool disabled) { if (!disabled) { - kuap_lock_all_ool(); + update_user_segments(mfsr(0) | SR_KS); + isync(); /* Context sync required after mtsr() */ init_mm.context.sr0 |= SR_KS; current->thread.sr0 |= SR_KS; } @@ -30,7 +16,7 @@ void setup_kuap(bool disabled) return; if (disabled) - static_branch_enable(&disable_kuap_key); + cur_cpu_spec->mmu_features &= ~MMU_FTR_KUAP; else pr_info("Activating Kernel Userspace Access Protection\n"); } diff --git a/arch/powerpc/mm/book3s32/mmu_context.c b/arch/powerpc/mm/book3s32/mmu_context.c index 269a3eb25a73..1922f9a6b058 100644 --- a/arch/powerpc/mm/book3s32/mmu_context.c +++ b/arch/powerpc/mm/book3s32/mmu_context.c @@ -71,7 +71,7 @@ int init_new_context(struct task_struct *t, struct mm_struct *mm) mm->context.id = __init_new_context(); mm->context.sr0 = CTX_TO_VSID(mm->context.id, 0); - if (!kuep_is_disabled()) + if (IS_ENABLED(CONFIG_PPC_KUEP)) mm->context.sr0 |= SR_NX; if (!kuap_is_disabled()) mm->context.sr0 |= SR_KS; diff --git a/arch/powerpc/mm/book3s64/hash_pgtable.c b/arch/powerpc/mm/book3s64/hash_pgtable.c index 51f48984abca..988948d69bc1 100644 --- a/arch/powerpc/mm/book3s64/hash_pgtable.c +++ b/arch/powerpc/mm/book3s64/hash_pgtable.c @@ -214,7 +214,7 @@ unsigned long hash__pmd_hugepage_update(struct mm_struct *mm, unsigned long addr old = be64_to_cpu(old_be); - trace_hugepage_update(addr, old, clr, set); + trace_hugepage_update_pmd(addr, old, clr, set); if (old & H_PAGE_HASHPTE) hpte_do_hugepage_flush(mm, addr, pmdp, old); return old; diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c index fedffe3ae136..ad2afa08e62e 100644 --- a/arch/powerpc/mm/book3s64/hash_utils.c +++ b/arch/powerpc/mm/book3s64/hash_utils.c @@ -1307,18 +1307,19 @@ void hash__early_init_mmu_secondary(void) */ unsigned int hash_page_do_lazy_icache(unsigned int pp, pte_t pte, int trap) { - struct page *page; + struct folio *folio; if (!pfn_valid(pte_pfn(pte))) return pp; - page = pte_page(pte); + folio = page_folio(pte_page(pte)); /* page is dirty */ - if (!test_bit(PG_dcache_clean, &page->flags) && !PageReserved(page)) { + if (!test_bit(PG_dcache_clean, &folio->flags) && + !folio_test_reserved(folio)) { if (trap == INTERRUPT_INST_STORAGE) { - flush_dcache_icache_page(page); - set_bit(PG_dcache_clean, &page->flags); + flush_dcache_icache_folio(folio); + set_bit(PG_dcache_clean, &folio->flags); } else pp |= HPTE_R_N; } diff --git a/arch/powerpc/mm/book3s64/mmu_context.c b/arch/powerpc/mm/book3s64/mmu_context.c index c766e4c26e42..1715b07c630c 100644 --- a/arch/powerpc/mm/book3s64/mmu_context.c +++ b/arch/powerpc/mm/book3s64/mmu_context.c @@ -246,15 +246,15 @@ static void destroy_contexts(mm_context_t *ctx) static void pmd_frag_destroy(void *pmd_frag) { int count; - struct page *page; + struct ptdesc *ptdesc; - page = virt_to_page(pmd_frag); + ptdesc = virt_to_ptdesc(pmd_frag); /* drop all the pending references */ count = ((unsigned long)pmd_frag & ~PAGE_MASK) >> PMD_FRAG_SIZE_SHIFT; /* We allow PTE_FRAG_NR fragments from a PTE page */ - if (atomic_sub_and_test(PMD_FRAG_NR - count, &page->pt_frag_refcount)) { - pgtable_pmd_page_dtor(page); - __free_page(page); + if (atomic_sub_and_test(PMD_FRAG_NR - count, &ptdesc->pt_frag_refcount)) { + pagetable_pmd_dtor(ptdesc); + pagetable_free(ptdesc); } } diff --git a/arch/powerpc/mm/book3s64/pgtable.c b/arch/powerpc/mm/book3s64/pgtable.c index 85c84e89e3ea..8f8a62d3ff4d 100644 --- a/arch/powerpc/mm/book3s64/pgtable.c +++ b/arch/powerpc/mm/book3s64/pgtable.c @@ -9,6 +9,7 @@ #include <linux/memremap.h> #include <linux/pkeys.h> #include <linux/debugfs.h> +#include <linux/proc_fs.h> #include <misc/cxl-base.h> #include <asm/pgalloc.h> @@ -64,11 +65,39 @@ int pmdp_set_access_flags(struct vm_area_struct *vma, unsigned long address, return changed; } +int pudp_set_access_flags(struct vm_area_struct *vma, unsigned long address, + pud_t *pudp, pud_t entry, int dirty) +{ + int changed; +#ifdef CONFIG_DEBUG_VM + WARN_ON(!pud_devmap(*pudp)); + assert_spin_locked(pud_lockptr(vma->vm_mm, pudp)); +#endif + changed = !pud_same(*(pudp), entry); + if (changed) { + /* + * We can use MMU_PAGE_1G here, because only radix + * path look at the psize. + */ + __ptep_set_access_flags(vma, pudp_ptep(pudp), + pud_pte(entry), address, MMU_PAGE_1G); + } + return changed; +} + + int pmdp_test_and_clear_young(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { return __pmdp_test_and_clear_young(vma->vm_mm, address, pmdp); } + +int pudp_test_and_clear_young(struct vm_area_struct *vma, + unsigned long address, pud_t *pudp) +{ + return __pudp_test_and_clear_young(vma->vm_mm, address, pudp); +} + /* * set a new huge pmd. We should not be called for updating * an existing pmd entry. That should go via pmd_hugepage_update. @@ -90,6 +119,23 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr, return set_pte_at(mm, addr, pmdp_ptep(pmdp), pmd_pte(pmd)); } +void set_pud_at(struct mm_struct *mm, unsigned long addr, + pud_t *pudp, pud_t pud) +{ +#ifdef CONFIG_DEBUG_VM + /* + * Make sure hardware valid bit is not set. We don't do + * tlb flush for this update. + */ + + WARN_ON(pte_hw_valid(pud_pte(*pudp))); + assert_spin_locked(pud_lockptr(mm, pudp)); + WARN_ON(!(pud_large(pud))); +#endif + trace_hugepage_set_pud(addr, pud_val(pud)); + return set_pte_at(mm, addr, pudp_ptep(pudp), pud_pte(pud)); +} + static void do_serialize(void *arg) { /* We've taken the IPI, so try to trim the mask while here */ @@ -147,11 +193,35 @@ pmd_t pmdp_huge_get_and_clear_full(struct vm_area_struct *vma, return pmd; } +pud_t pudp_huge_get_and_clear_full(struct vm_area_struct *vma, + unsigned long addr, pud_t *pudp, int full) +{ + pud_t pud; + + VM_BUG_ON(addr & ~HPAGE_PMD_MASK); + VM_BUG_ON((pud_present(*pudp) && !pud_devmap(*pudp)) || + !pud_present(*pudp)); + pud = pudp_huge_get_and_clear(vma->vm_mm, addr, pudp); + /* + * if it not a fullmm flush, then we can possibly end up converting + * this PMD pte entry to a regular level 0 PTE by a parallel page fault. + * Make sure we flush the tlb in this case. + */ + if (!full) + flush_pud_tlb_range(vma, addr, addr + HPAGE_PUD_SIZE); + return pud; +} + static pmd_t pmd_set_protbits(pmd_t pmd, pgprot_t pgprot) { return __pmd(pmd_val(pmd) | pgprot_val(pgprot)); } +static pud_t pud_set_protbits(pud_t pud, pgprot_t pgprot) +{ + return __pud(pud_val(pud) | pgprot_val(pgprot)); +} + /* * At some point we should be able to get rid of * pmd_mkhuge() and mk_huge_pmd() when we update all the @@ -166,6 +236,15 @@ pmd_t pfn_pmd(unsigned long pfn, pgprot_t pgprot) return __pmd_mkhuge(pmd_set_protbits(__pmd(pmdv), pgprot)); } +pud_t pfn_pud(unsigned long pfn, pgprot_t pgprot) +{ + unsigned long pudv; + + pudv = (pfn << PAGE_SHIFT) & PTE_RPN_MASK; + + return __pud_mkhuge(pud_set_protbits(__pud(pudv), pgprot)); +} + pmd_t mk_pmd(struct page *page, pgprot_t pgprot) { return pfn_pmd(page_to_pfn(page), pgprot); @@ -306,22 +385,22 @@ static pmd_t *get_pmd_from_cache(struct mm_struct *mm) static pmd_t *__alloc_for_pmdcache(struct mm_struct *mm) { void *ret = NULL; - struct page *page; + struct ptdesc *ptdesc; gfp_t gfp = GFP_KERNEL_ACCOUNT | __GFP_ZERO; if (mm == &init_mm) gfp &= ~__GFP_ACCOUNT; - page = alloc_page(gfp); - if (!page) + ptdesc = pagetable_alloc(gfp, 0); + if (!ptdesc) return NULL; - if (!pgtable_pmd_page_ctor(page)) { - __free_pages(page, 0); + if (!pagetable_pmd_ctor(ptdesc)) { + pagetable_free(ptdesc); return NULL; } - atomic_set(&page->pt_frag_refcount, 1); + atomic_set(&ptdesc->pt_frag_refcount, 1); - ret = page_address(page); + ret = ptdesc_address(ptdesc); /* * if we support only one fragment just return the * allocated page. @@ -331,12 +410,12 @@ static pmd_t *__alloc_for_pmdcache(struct mm_struct *mm) spin_lock(&mm->page_table_lock); /* - * If we find pgtable_page set, we return + * If we find ptdesc_page set, we return * the allocated page with single fragment * count. */ if (likely(!mm->context.pmd_frag)) { - atomic_set(&page->pt_frag_refcount, PMD_FRAG_NR); + atomic_set(&ptdesc->pt_frag_refcount, PMD_FRAG_NR); mm->context.pmd_frag = ret + PMD_FRAG_SIZE; } spin_unlock(&mm->page_table_lock); @@ -357,15 +436,15 @@ pmd_t *pmd_fragment_alloc(struct mm_struct *mm, unsigned long vmaddr) void pmd_fragment_free(unsigned long *pmd) { - struct page *page = virt_to_page(pmd); + struct ptdesc *ptdesc = virt_to_ptdesc(pmd); - if (PageReserved(page)) - return free_reserved_page(page); + if (pagetable_is_reserved(ptdesc)) + return free_reserved_ptdesc(ptdesc); - BUG_ON(atomic_read(&page->pt_frag_refcount) <= 0); - if (atomic_dec_and_test(&page->pt_frag_refcount)) { - pgtable_pmd_page_dtor(page); - __free_page(page); + BUG_ON(atomic_read(&ptdesc->pt_frag_refcount) <= 0); + if (atomic_dec_and_test(&ptdesc->pt_frag_refcount)) { + pagetable_pmd_dtor(ptdesc); + pagetable_free(ptdesc); } } diff --git a/arch/powerpc/mm/book3s64/pkeys.c b/arch/powerpc/mm/book3s64/pkeys.c index 1d2675ab6711..125733962033 100644 --- a/arch/powerpc/mm/book3s64/pkeys.c +++ b/arch/powerpc/mm/book3s64/pkeys.c @@ -291,7 +291,7 @@ void setup_kuap(bool disabled) if (smp_processor_id() == boot_cpuid) { pr_info("Activating Kernel Userspace Access Prevention\n"); - cur_cpu_spec->mmu_features |= MMU_FTR_BOOK3S_KUAP; + cur_cpu_spec->mmu_features |= MMU_FTR_KUAP; } /* diff --git a/arch/powerpc/mm/book3s64/radix_hugetlbpage.c b/arch/powerpc/mm/book3s64/radix_hugetlbpage.c index 5e3195568525..17075c78d4bc 100644 --- a/arch/powerpc/mm/book3s64/radix_hugetlbpage.c +++ b/arch/powerpc/mm/book3s64/radix_hugetlbpage.c @@ -39,6 +39,7 @@ void radix__flush_hugetlb_tlb_range(struct vm_area_struct *vma, unsigned long st radix__flush_tlb_pwc_range_psize(vma->vm_mm, start, end, psize); else radix__flush_tlb_range_psize(vma->vm_mm, start, end, psize); + mmu_notifier_arch_invalidate_secondary_tlbs(vma->vm_mm, start, end); } void radix__huge_ptep_modify_prot_commit(struct vm_area_struct *vma, diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c index e7ea492ac510..c6a4ac766b2b 100644 --- a/arch/powerpc/mm/book3s64/radix_pgtable.c +++ b/arch/powerpc/mm/book3s64/radix_pgtable.c @@ -37,7 +37,6 @@ #include <mm/mmu_decl.h> unsigned int mmu_base_pid; -unsigned long radix_mem_block_size __ro_after_init; static __ref void *early_alloc_pgtable(unsigned long size, int nid, unsigned long region_start, unsigned long region_end) @@ -300,7 +299,7 @@ static int __meminit create_physical_mapping(unsigned long start, bool prev_exec, exec = false; pgprot_t prot; int psize; - unsigned long max_mapping_size = radix_mem_block_size; + unsigned long max_mapping_size = memory_block_size; if (debug_pagealloc_enabled_or_kfence()) max_mapping_size = PAGE_SIZE; @@ -502,58 +501,6 @@ static int __init radix_dt_scan_page_sizes(unsigned long node, return 1; } -#ifdef CONFIG_MEMORY_HOTPLUG -static int __init probe_memory_block_size(unsigned long node, const char *uname, int - depth, void *data) -{ - unsigned long *mem_block_size = (unsigned long *)data; - const __be32 *prop; - int len; - - if (depth != 1) - return 0; - - if (strcmp(uname, "ibm,dynamic-reconfiguration-memory")) - return 0; - - prop = of_get_flat_dt_prop(node, "ibm,lmb-size", &len); - - if (!prop || len < dt_root_size_cells * sizeof(__be32)) - /* - * Nothing in the device tree - */ - *mem_block_size = MIN_MEMORY_BLOCK_SIZE; - else - *mem_block_size = of_read_number(prop, dt_root_size_cells); - return 1; -} - -static unsigned long __init radix_memory_block_size(void) -{ - unsigned long mem_block_size = MIN_MEMORY_BLOCK_SIZE; - - /* - * OPAL firmware feature is set by now. Hence we are ok - * to test OPAL feature. - */ - if (firmware_has_feature(FW_FEATURE_OPAL)) - mem_block_size = 1UL * 1024 * 1024 * 1024; - else - of_scan_flat_dt(probe_memory_block_size, &mem_block_size); - - return mem_block_size; -} - -#else /* CONFIG_MEMORY_HOTPLUG */ - -static unsigned long __init radix_memory_block_size(void) -{ - return 1UL * 1024 * 1024 * 1024; -} - -#endif /* CONFIG_MEMORY_HOTPLUG */ - - void __init radix__early_init_devtree(void) { int rc; @@ -577,16 +524,6 @@ void __init radix__early_init_devtree(void) mmu_psize_defs[MMU_PAGE_64K].h_rpt_pgsize = psize_to_rpti_pgsize(MMU_PAGE_64K); } - - /* - * Max mapping size used when mapping pages. We don't use - * ppc_md.memory_block_size() here because this get called - * early and we don't have machine probe called yet. Also - * the pseries implementation only check for ibm,lmb-size. - * All hypervisor supporting radix do expose that device - * tree node. - */ - radix_mem_block_size = radix_memory_block_size(); return; } @@ -601,17 +538,6 @@ void __init radix__early_init_mmu(void) #else mmu_virtual_psize = MMU_PAGE_4K; #endif - -#ifdef CONFIG_SPARSEMEM_VMEMMAP - /* vmemmap mapping */ - if (mmu_psize_defs[MMU_PAGE_2M].shift) { - /* - * map vmemmap using 2M if available - */ - mmu_vmemmap_psize = MMU_PAGE_2M; - } else - mmu_vmemmap_psize = mmu_virtual_psize; -#endif #endif /* * initialize page table size @@ -744,8 +670,58 @@ static void free_pud_table(pud_t *pud_start, p4d_t *p4d) p4d_clear(p4d); } -static void remove_pte_table(pte_t *pte_start, unsigned long addr, - unsigned long end, bool direct) +#ifdef CONFIG_SPARSEMEM_VMEMMAP +static bool __meminit vmemmap_pmd_is_unused(unsigned long addr, unsigned long end) +{ + unsigned long start = ALIGN_DOWN(addr, PMD_SIZE); + + return !vmemmap_populated(start, PMD_SIZE); +} + +static bool __meminit vmemmap_page_is_unused(unsigned long addr, unsigned long end) +{ + unsigned long start = ALIGN_DOWN(addr, PAGE_SIZE); + + return !vmemmap_populated(start, PAGE_SIZE); + +} +#endif + +static void __meminit free_vmemmap_pages(struct page *page, + struct vmem_altmap *altmap, + int order) +{ + unsigned int nr_pages = 1 << order; + + if (altmap) { + unsigned long alt_start, alt_end; + unsigned long base_pfn = page_to_pfn(page); + + /* + * with 2M vmemmap mmaping we can have things setup + * such that even though atlmap is specified we never + * used altmap. + */ + alt_start = altmap->base_pfn; + alt_end = altmap->base_pfn + altmap->reserve + altmap->free; + + if (base_pfn >= alt_start && base_pfn < alt_end) { + vmem_altmap_free(altmap, nr_pages); + return; + } + } + + if (PageReserved(page)) { + /* allocated from memblock */ + while (nr_pages--) + free_reserved_page(page++); + } else + free_pages((unsigned long)page_address(page), order); +} + +static void __meminit remove_pte_table(pte_t *pte_start, unsigned long addr, + unsigned long end, bool direct, + struct vmem_altmap *altmap) { unsigned long next, pages = 0; pte_t *pte; @@ -759,24 +735,26 @@ static void remove_pte_table(pte_t *pte_start, unsigned long addr, if (!pte_present(*pte)) continue; - if (!PAGE_ALIGNED(addr) || !PAGE_ALIGNED(next)) { - /* - * The vmemmap_free() and remove_section_mapping() - * codepaths call us with aligned addresses. - */ - WARN_ONCE(1, "%s: unaligned range\n", __func__); - continue; + if (PAGE_ALIGNED(addr) && PAGE_ALIGNED(next)) { + if (!direct) + free_vmemmap_pages(pte_page(*pte), altmap, 0); + pte_clear(&init_mm, addr, pte); + pages++; } - - pte_clear(&init_mm, addr, pte); - pages++; +#ifdef CONFIG_SPARSEMEM_VMEMMAP + else if (!direct && vmemmap_page_is_unused(addr, next)) { + free_vmemmap_pages(pte_page(*pte), altmap, 0); + pte_clear(&init_mm, addr, pte); + } +#endif } if (direct) update_page_count(mmu_virtual_psize, -pages); } static void __meminit remove_pmd_table(pmd_t *pmd_start, unsigned long addr, - unsigned long end, bool direct) + unsigned long end, bool direct, + struct vmem_altmap *altmap) { unsigned long next, pages = 0; pte_t *pte_base; @@ -790,18 +768,24 @@ static void __meminit remove_pmd_table(pmd_t *pmd_start, unsigned long addr, continue; if (pmd_is_leaf(*pmd)) { - if (!IS_ALIGNED(addr, PMD_SIZE) || - !IS_ALIGNED(next, PMD_SIZE)) { - WARN_ONCE(1, "%s: unaligned range\n", __func__); - continue; + if (IS_ALIGNED(addr, PMD_SIZE) && + IS_ALIGNED(next, PMD_SIZE)) { + if (!direct) + free_vmemmap_pages(pmd_page(*pmd), altmap, get_order(PMD_SIZE)); + pte_clear(&init_mm, addr, (pte_t *)pmd); + pages++; } - pte_clear(&init_mm, addr, (pte_t *)pmd); - pages++; +#ifdef CONFIG_SPARSEMEM_VMEMMAP + else if (!direct && vmemmap_pmd_is_unused(addr, next)) { + free_vmemmap_pages(pmd_page(*pmd), altmap, get_order(PMD_SIZE)); + pte_clear(&init_mm, addr, (pte_t *)pmd); + } +#endif continue; } pte_base = (pte_t *)pmd_page_vaddr(*pmd); - remove_pte_table(pte_base, addr, next, direct); + remove_pte_table(pte_base, addr, next, direct, altmap); free_pte_table(pte_base, pmd); } if (direct) @@ -809,7 +793,8 @@ static void __meminit remove_pmd_table(pmd_t *pmd_start, unsigned long addr, } static void __meminit remove_pud_table(pud_t *pud_start, unsigned long addr, - unsigned long end, bool direct) + unsigned long end, bool direct, + struct vmem_altmap *altmap) { unsigned long next, pages = 0; pmd_t *pmd_base; @@ -834,15 +819,16 @@ static void __meminit remove_pud_table(pud_t *pud_start, unsigned long addr, } pmd_base = pud_pgtable(*pud); - remove_pmd_table(pmd_base, addr, next, direct); + remove_pmd_table(pmd_base, addr, next, direct, altmap); free_pmd_table(pmd_base, pud); } if (direct) update_page_count(MMU_PAGE_1G, -pages); } -static void __meminit remove_pagetable(unsigned long start, unsigned long end, - bool direct) +static void __meminit +remove_pagetable(unsigned long start, unsigned long end, bool direct, + struct vmem_altmap *altmap) { unsigned long addr, next; pud_t *pud_base; @@ -871,7 +857,7 @@ static void __meminit remove_pagetable(unsigned long start, unsigned long end, } pud_base = p4d_pgtable(*p4d); - remove_pud_table(pud_base, addr, next, direct); + remove_pud_table(pud_base, addr, next, direct, altmap); free_pud_table(pud_base, p4d); } @@ -894,7 +880,7 @@ int __meminit radix__create_section_mapping(unsigned long start, int __meminit radix__remove_section_mapping(unsigned long start, unsigned long end) { - remove_pagetable(start, end, true); + remove_pagetable(start, end, true, NULL); return 0; } #endif /* CONFIG_MEMORY_HOTPLUG */ @@ -926,10 +912,429 @@ int __meminit radix__vmemmap_create_mapping(unsigned long start, return 0; } + +bool vmemmap_can_optimize(struct vmem_altmap *altmap, struct dev_pagemap *pgmap) +{ + if (radix_enabled()) + return __vmemmap_can_optimize(altmap, pgmap); + + return false; +} + +int __meminit vmemmap_check_pmd(pmd_t *pmdp, int node, + unsigned long addr, unsigned long next) +{ + int large = pmd_large(*pmdp); + + if (large) + vmemmap_verify(pmdp_ptep(pmdp), node, addr, next); + + return large; +} + +void __meminit vmemmap_set_pmd(pmd_t *pmdp, void *p, int node, + unsigned long addr, unsigned long next) +{ + pte_t entry; + pte_t *ptep = pmdp_ptep(pmdp); + + VM_BUG_ON(!IS_ALIGNED(addr, PMD_SIZE)); + entry = pfn_pte(__pa(p) >> PAGE_SHIFT, PAGE_KERNEL); + set_pte_at(&init_mm, addr, ptep, entry); + asm volatile("ptesync": : :"memory"); + + vmemmap_verify(ptep, node, addr, next); +} + +static pte_t * __meminit radix__vmemmap_pte_populate(pmd_t *pmdp, unsigned long addr, + int node, + struct vmem_altmap *altmap, + struct page *reuse) +{ + pte_t *pte = pte_offset_kernel(pmdp, addr); + + if (pte_none(*pte)) { + pte_t entry; + void *p; + + if (!reuse) { + /* + * make sure we don't create altmap mappings + * covering things outside the device. + */ + if (altmap && altmap_cross_boundary(altmap, addr, PAGE_SIZE)) + altmap = NULL; + + p = vmemmap_alloc_block_buf(PAGE_SIZE, node, altmap); + if (!p && altmap) + p = vmemmap_alloc_block_buf(PAGE_SIZE, node, NULL); + if (!p) + return NULL; + pr_debug("PAGE_SIZE vmemmap mapping\n"); + } else { + /* + * When a PTE/PMD entry is freed from the init_mm + * there's a free_pages() call to this page allocated + * above. Thus this get_page() is paired with the + * put_page_testzero() on the freeing path. + * This can only called by certain ZONE_DEVICE path, + * and through vmemmap_populate_compound_pages() when + * slab is available. + */ + get_page(reuse); + p = page_to_virt(reuse); + pr_debug("Tail page reuse vmemmap mapping\n"); + } + + VM_BUG_ON(!PAGE_ALIGNED(addr)); + entry = pfn_pte(__pa(p) >> PAGE_SHIFT, PAGE_KERNEL); + set_pte_at(&init_mm, addr, pte, entry); + asm volatile("ptesync": : :"memory"); + } + return pte; +} + +static inline pud_t *vmemmap_pud_alloc(p4d_t *p4dp, int node, + unsigned long address) +{ + pud_t *pud; + + /* All early vmemmap mapping to keep simple do it at PAGE_SIZE */ + if (unlikely(p4d_none(*p4dp))) { + if (unlikely(!slab_is_available())) { + pud = early_alloc_pgtable(PAGE_SIZE, node, 0, 0); + p4d_populate(&init_mm, p4dp, pud); + /* go to the pud_offset */ + } else + return pud_alloc(&init_mm, p4dp, address); + } + return pud_offset(p4dp, address); +} + +static inline pmd_t *vmemmap_pmd_alloc(pud_t *pudp, int node, + unsigned long address) +{ + pmd_t *pmd; + + /* All early vmemmap mapping to keep simple do it at PAGE_SIZE */ + if (unlikely(pud_none(*pudp))) { + if (unlikely(!slab_is_available())) { + pmd = early_alloc_pgtable(PAGE_SIZE, node, 0, 0); + pud_populate(&init_mm, pudp, pmd); + } else + return pmd_alloc(&init_mm, pudp, address); + } + return pmd_offset(pudp, address); +} + +static inline pte_t *vmemmap_pte_alloc(pmd_t *pmdp, int node, + unsigned long address) +{ + pte_t *pte; + + /* All early vmemmap mapping to keep simple do it at PAGE_SIZE */ + if (unlikely(pmd_none(*pmdp))) { + if (unlikely(!slab_is_available())) { + pte = early_alloc_pgtable(PAGE_SIZE, node, 0, 0); + pmd_populate(&init_mm, pmdp, pte); + } else + return pte_alloc_kernel(pmdp, address); + } + return pte_offset_kernel(pmdp, address); +} + + + +int __meminit radix__vmemmap_populate(unsigned long start, unsigned long end, int node, + struct vmem_altmap *altmap) +{ + unsigned long addr; + unsigned long next; + pgd_t *pgd; + p4d_t *p4d; + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + + for (addr = start; addr < end; addr = next) { + next = pmd_addr_end(addr, end); + + pgd = pgd_offset_k(addr); + p4d = p4d_offset(pgd, addr); + pud = vmemmap_pud_alloc(p4d, node, addr); + if (!pud) + return -ENOMEM; + pmd = vmemmap_pmd_alloc(pud, node, addr); + if (!pmd) + return -ENOMEM; + + if (pmd_none(READ_ONCE(*pmd))) { + void *p; + + /* + * keep it simple by checking addr PMD_SIZE alignment + * and verifying the device boundary condition. + * For us to use a pmd mapping, both addr and pfn should + * be aligned. We skip if addr is not aligned and for + * pfn we hope we have extra area in the altmap that + * can help to find an aligned block. This can result + * in altmap block allocation failures, in which case + * we fallback to RAM for vmemmap allocation. + */ + if (altmap && (!IS_ALIGNED(addr, PMD_SIZE) || + altmap_cross_boundary(altmap, addr, PMD_SIZE))) { + /* + * make sure we don't create altmap mappings + * covering things outside the device. + */ + goto base_mapping; + } + + p = vmemmap_alloc_block_buf(PMD_SIZE, node, altmap); + if (p) { + vmemmap_set_pmd(pmd, p, node, addr, next); + pr_debug("PMD_SIZE vmemmap mapping\n"); + continue; + } else if (altmap) { + /* + * A vmemmap block allocation can fail due to + * alignment requirements and we trying to align + * things aggressively there by running out of + * space. Try base mapping on failure. + */ + goto base_mapping; + } + } else if (vmemmap_check_pmd(pmd, node, addr, next)) { + /* + * If a huge mapping exist due to early call to + * vmemmap_populate, let's try to use that. + */ + continue; + } +base_mapping: + /* + * Not able allocate higher order memory to back memmap + * or we found a pointer to pte page. Allocate base page + * size vmemmap + */ + pte = vmemmap_pte_alloc(pmd, node, addr); + if (!pte) + return -ENOMEM; + + pte = radix__vmemmap_pte_populate(pmd, addr, node, altmap, NULL); + if (!pte) + return -ENOMEM; + + vmemmap_verify(pte, node, addr, addr + PAGE_SIZE); + next = addr + PAGE_SIZE; + } + return 0; +} + +static pte_t * __meminit radix__vmemmap_populate_address(unsigned long addr, int node, + struct vmem_altmap *altmap, + struct page *reuse) +{ + pgd_t *pgd; + p4d_t *p4d; + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + + pgd = pgd_offset_k(addr); + p4d = p4d_offset(pgd, addr); + pud = vmemmap_pud_alloc(p4d, node, addr); + if (!pud) + return NULL; + pmd = vmemmap_pmd_alloc(pud, node, addr); + if (!pmd) + return NULL; + if (pmd_leaf(*pmd)) + /* + * The second page is mapped as a hugepage due to a nearby request. + * Force our mapping to page size without deduplication + */ + return NULL; + pte = vmemmap_pte_alloc(pmd, node, addr); + if (!pte) + return NULL; + radix__vmemmap_pte_populate(pmd, addr, node, NULL, NULL); + vmemmap_verify(pte, node, addr, addr + PAGE_SIZE); + + return pte; +} + +static pte_t * __meminit vmemmap_compound_tail_page(unsigned long addr, + unsigned long pfn_offset, int node) +{ + pgd_t *pgd; + p4d_t *p4d; + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + unsigned long map_addr; + + /* the second vmemmap page which we use for duplication */ + map_addr = addr - pfn_offset * sizeof(struct page) + PAGE_SIZE; + pgd = pgd_offset_k(map_addr); + p4d = p4d_offset(pgd, map_addr); + pud = vmemmap_pud_alloc(p4d, node, map_addr); + if (!pud) + return NULL; + pmd = vmemmap_pmd_alloc(pud, node, map_addr); + if (!pmd) + return NULL; + if (pmd_leaf(*pmd)) + /* + * The second page is mapped as a hugepage due to a nearby request. + * Force our mapping to page size without deduplication + */ + return NULL; + pte = vmemmap_pte_alloc(pmd, node, map_addr); + if (!pte) + return NULL; + /* + * Check if there exist a mapping to the left + */ + if (pte_none(*pte)) { + /* + * Populate the head page vmemmap page. + * It can fall in different pmd, hence + * vmemmap_populate_address() + */ + pte = radix__vmemmap_populate_address(map_addr - PAGE_SIZE, node, NULL, NULL); + if (!pte) + return NULL; + /* + * Populate the tail pages vmemmap page + */ + pte = radix__vmemmap_pte_populate(pmd, map_addr, node, NULL, NULL); + if (!pte) + return NULL; + vmemmap_verify(pte, node, map_addr, map_addr + PAGE_SIZE); + return pte; + } + return pte; +} + +int __meminit vmemmap_populate_compound_pages(unsigned long start_pfn, + unsigned long start, + unsigned long end, int node, + struct dev_pagemap *pgmap) +{ + /* + * we want to map things as base page size mapping so that + * we can save space in vmemmap. We could have huge mapping + * covering out both edges. + */ + unsigned long addr; + unsigned long addr_pfn = start_pfn; + unsigned long next; + pgd_t *pgd; + p4d_t *p4d; + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + + for (addr = start; addr < end; addr = next) { + + pgd = pgd_offset_k(addr); + p4d = p4d_offset(pgd, addr); + pud = vmemmap_pud_alloc(p4d, node, addr); + if (!pud) + return -ENOMEM; + pmd = vmemmap_pmd_alloc(pud, node, addr); + if (!pmd) + return -ENOMEM; + + if (pmd_leaf(READ_ONCE(*pmd))) { + /* existing huge mapping. Skip the range */ + addr_pfn += (PMD_SIZE >> PAGE_SHIFT); + next = pmd_addr_end(addr, end); + continue; + } + pte = vmemmap_pte_alloc(pmd, node, addr); + if (!pte) + return -ENOMEM; + if (!pte_none(*pte)) { + /* + * This could be because we already have a compound + * page whose VMEMMAP_RESERVE_NR pages were mapped and + * this request fall in those pages. + */ + addr_pfn += 1; + next = addr + PAGE_SIZE; + continue; + } else { + unsigned long nr_pages = pgmap_vmemmap_nr(pgmap); + unsigned long pfn_offset = addr_pfn - ALIGN_DOWN(addr_pfn, nr_pages); + pte_t *tail_page_pte; + + /* + * if the address is aligned to huge page size it is the + * head mapping. + */ + if (pfn_offset == 0) { + /* Populate the head page vmemmap page */ + pte = radix__vmemmap_pte_populate(pmd, addr, node, NULL, NULL); + if (!pte) + return -ENOMEM; + vmemmap_verify(pte, node, addr, addr + PAGE_SIZE); + + /* + * Populate the tail pages vmemmap page + * It can fall in different pmd, hence + * vmemmap_populate_address() + */ + pte = radix__vmemmap_populate_address(addr + PAGE_SIZE, node, NULL, NULL); + if (!pte) + return -ENOMEM; + + addr_pfn += 2; + next = addr + 2 * PAGE_SIZE; + continue; + } + /* + * get the 2nd mapping details + * Also create it if that doesn't exist + */ + tail_page_pte = vmemmap_compound_tail_page(addr, pfn_offset, node); + if (!tail_page_pte) { + + pte = radix__vmemmap_pte_populate(pmd, addr, node, NULL, NULL); + if (!pte) + return -ENOMEM; + vmemmap_verify(pte, node, addr, addr + PAGE_SIZE); + + addr_pfn += 1; + next = addr + PAGE_SIZE; + continue; + } + + pte = radix__vmemmap_pte_populate(pmd, addr, node, NULL, pte_page(*tail_page_pte)); + if (!pte) + return -ENOMEM; + vmemmap_verify(pte, node, addr, addr + PAGE_SIZE); + + addr_pfn += 1; + next = addr + PAGE_SIZE; + continue; + } + } + return 0; +} + + #ifdef CONFIG_MEMORY_HOTPLUG void __meminit radix__vmemmap_remove_mapping(unsigned long start, unsigned long page_size) { - remove_pagetable(start, start + page_size, false); + remove_pagetable(start, start + page_size, true, NULL); +} + +void __ref radix__vmemmap_free(unsigned long start, unsigned long end, + struct vmem_altmap *altmap) +{ + remove_pagetable(start, end, false, altmap); } #endif #endif @@ -962,7 +1367,24 @@ unsigned long radix__pmd_hugepage_update(struct mm_struct *mm, unsigned long add #endif old = radix__pte_update(mm, addr, pmdp_ptep(pmdp), clr, set, 1); - trace_hugepage_update(addr, old, clr, set); + trace_hugepage_update_pmd(addr, old, clr, set); + + return old; +} + +unsigned long radix__pud_hugepage_update(struct mm_struct *mm, unsigned long addr, + pud_t *pudp, unsigned long clr, + unsigned long set) +{ + unsigned long old; + +#ifdef CONFIG_DEBUG_VM + WARN_ON(!pud_devmap(*pudp)); + assert_spin_locked(pud_lockptr(mm, pudp)); +#endif + + old = radix__pte_update(mm, addr, pudp_ptep(pudp), clr, set, 1); + trace_hugepage_update_pud(addr, old, clr, set); return old; } @@ -1043,6 +1465,17 @@ pmd_t radix__pmdp_huge_get_and_clear(struct mm_struct *mm, return old_pmd; } +pud_t radix__pudp_huge_get_and_clear(struct mm_struct *mm, + unsigned long addr, pud_t *pudp) +{ + pud_t old_pud; + unsigned long old; + + old = radix__pud_hugepage_update(mm, addr, pudp, ~0UL, 0); + old_pud = __pud(old); + return old_pud; +} + #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ void radix__ptep_set_access_flags(struct vm_area_struct *vma, pte_t *ptep, diff --git a/arch/powerpc/mm/book3s64/radix_tlb.c b/arch/powerpc/mm/book3s64/radix_tlb.c index 0bd4866d9824..39acc2cbab4c 100644 --- a/arch/powerpc/mm/book3s64/radix_tlb.c +++ b/arch/powerpc/mm/book3s64/radix_tlb.c @@ -127,21 +127,6 @@ static __always_inline void __tlbie_pid(unsigned long pid, unsigned long ric) trace_tlbie(0, 0, rb, rs, ric, prs, r); } -static __always_inline void __tlbie_pid_lpid(unsigned long pid, - unsigned long lpid, - unsigned long ric) -{ - unsigned long rb, rs, prs, r; - - rb = PPC_BIT(53); /* IS = 1 */ - rs = (pid << PPC_BITLSHIFT(31)) | (lpid & ~(PPC_BITMASK(0, 31))); - prs = 1; /* process scoped */ - r = 1; /* radix format */ - - asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1) - : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory"); - trace_tlbie(0, 0, rb, rs, ric, prs, r); -} static __always_inline void __tlbie_lpid(unsigned long lpid, unsigned long ric) { unsigned long rb,rs,prs,r; @@ -202,23 +187,6 @@ static __always_inline void __tlbie_va(unsigned long va, unsigned long pid, trace_tlbie(0, 0, rb, rs, ric, prs, r); } -static __always_inline void __tlbie_va_lpid(unsigned long va, unsigned long pid, - unsigned long lpid, - unsigned long ap, unsigned long ric) -{ - unsigned long rb, rs, prs, r; - - rb = va & ~(PPC_BITMASK(52, 63)); - rb |= ap << PPC_BITLSHIFT(58); - rs = (pid << PPC_BITLSHIFT(31)) | (lpid & ~(PPC_BITMASK(0, 31))); - prs = 1; /* process scoped */ - r = 1; /* radix format */ - - asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1) - : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory"); - trace_tlbie(0, 0, rb, rs, ric, prs, r); -} - static __always_inline void __tlbie_lpid_va(unsigned long va, unsigned long lpid, unsigned long ap, unsigned long ric) { @@ -264,22 +232,6 @@ static inline void fixup_tlbie_va_range(unsigned long va, unsigned long pid, } } -static inline void fixup_tlbie_va_range_lpid(unsigned long va, - unsigned long pid, - unsigned long lpid, - unsigned long ap) -{ - if (cpu_has_feature(CPU_FTR_P9_TLBIE_ERAT_BUG)) { - asm volatile("ptesync" : : : "memory"); - __tlbie_pid_lpid(0, lpid, RIC_FLUSH_TLB); - } - - if (cpu_has_feature(CPU_FTR_P9_TLBIE_STQ_BUG)) { - asm volatile("ptesync" : : : "memory"); - __tlbie_va_lpid(va, pid, lpid, ap, RIC_FLUSH_TLB); - } -} - static inline void fixup_tlbie_pid(unsigned long pid) { /* @@ -299,26 +251,6 @@ static inline void fixup_tlbie_pid(unsigned long pid) } } -static inline void fixup_tlbie_pid_lpid(unsigned long pid, unsigned long lpid) -{ - /* - * We can use any address for the invalidation, pick one which is - * probably unused as an optimisation. - */ - unsigned long va = ((1UL << 52) - 1); - - if (cpu_has_feature(CPU_FTR_P9_TLBIE_ERAT_BUG)) { - asm volatile("ptesync" : : : "memory"); - __tlbie_pid_lpid(0, lpid, RIC_FLUSH_TLB); - } - - if (cpu_has_feature(CPU_FTR_P9_TLBIE_STQ_BUG)) { - asm volatile("ptesync" : : : "memory"); - __tlbie_va_lpid(va, pid, lpid, mmu_get_ap(MMU_PAGE_64K), - RIC_FLUSH_TLB); - } -} - static inline void fixup_tlbie_lpid_va(unsigned long va, unsigned long lpid, unsigned long ap) { @@ -416,31 +348,6 @@ static inline void _tlbie_pid(unsigned long pid, unsigned long ric) asm volatile("eieio; tlbsync; ptesync": : :"memory"); } -static inline void _tlbie_pid_lpid(unsigned long pid, unsigned long lpid, - unsigned long ric) -{ - asm volatile("ptesync" : : : "memory"); - - /* - * Workaround the fact that the "ric" argument to __tlbie_pid - * must be a compile-time contraint to match the "i" constraint - * in the asm statement. - */ - switch (ric) { - case RIC_FLUSH_TLB: - __tlbie_pid_lpid(pid, lpid, RIC_FLUSH_TLB); - fixup_tlbie_pid_lpid(pid, lpid); - break; - case RIC_FLUSH_PWC: - __tlbie_pid_lpid(pid, lpid, RIC_FLUSH_PWC); - break; - case RIC_FLUSH_ALL: - default: - __tlbie_pid_lpid(pid, lpid, RIC_FLUSH_ALL); - fixup_tlbie_pid_lpid(pid, lpid); - } - asm volatile("eieio; tlbsync; ptesync" : : : "memory"); -} struct tlbiel_pid { unsigned long pid; unsigned long ric; @@ -566,20 +473,6 @@ static inline void __tlbie_va_range(unsigned long start, unsigned long end, fixup_tlbie_va_range(addr - page_size, pid, ap); } -static inline void __tlbie_va_range_lpid(unsigned long start, unsigned long end, - unsigned long pid, unsigned long lpid, - unsigned long page_size, - unsigned long psize) -{ - unsigned long addr; - unsigned long ap = mmu_get_ap(psize); - - for (addr = start; addr < end; addr += page_size) - __tlbie_va_lpid(addr, pid, lpid, ap, RIC_FLUSH_TLB); - - fixup_tlbie_va_range_lpid(addr - page_size, pid, lpid, ap); -} - static __always_inline void _tlbie_va(unsigned long va, unsigned long pid, unsigned long psize, unsigned long ric) { @@ -660,18 +553,6 @@ static inline void _tlbie_va_range(unsigned long start, unsigned long end, asm volatile("eieio; tlbsync; ptesync": : :"memory"); } -static inline void _tlbie_va_range_lpid(unsigned long start, unsigned long end, - unsigned long pid, unsigned long lpid, - unsigned long page_size, - unsigned long psize, bool also_pwc) -{ - asm volatile("ptesync" : : : "memory"); - if (also_pwc) - __tlbie_pid_lpid(pid, lpid, RIC_FLUSH_PWC); - __tlbie_va_range_lpid(start, end, pid, lpid, page_size, psize); - asm volatile("eieio; tlbsync; ptesync" : : : "memory"); -} - static inline void _tlbiel_va_range_multicast(struct mm_struct *mm, unsigned long start, unsigned long end, unsigned long pid, unsigned long page_size, @@ -820,7 +701,7 @@ void exit_lazy_flush_tlb(struct mm_struct *mm, bool always_flush) * that's what the caller expects. */ if (cpumask_test_cpu(cpu, mm_cpumask(mm))) { - atomic_dec(&mm->context.active_cpus); + dec_mm_active_cpus(mm); cpumask_clear_cpu(cpu, mm_cpumask(mm)); always_flush = true; } @@ -987,6 +868,7 @@ void radix__flush_tlb_mm(struct mm_struct *mm) } } preempt_enable(); + mmu_notifier_arch_invalidate_secondary_tlbs(mm, 0, -1UL); } EXPORT_SYMBOL(radix__flush_tlb_mm); @@ -1020,6 +902,7 @@ static void __flush_all_mm(struct mm_struct *mm, bool fullmm) _tlbiel_pid_multicast(mm, pid, RIC_FLUSH_ALL); } preempt_enable(); + mmu_notifier_arch_invalidate_secondary_tlbs(mm, 0, -1UL); } void radix__flush_all_mm(struct mm_struct *mm) @@ -1228,6 +1111,7 @@ static inline void __radix__flush_tlb_range(struct mm_struct *mm, } out: preempt_enable(); + mmu_notifier_arch_invalidate_secondary_tlbs(mm, start, end); } void radix__flush_tlb_range(struct vm_area_struct *vma, unsigned long start, @@ -1313,7 +1197,35 @@ void radix__tlb_flush(struct mmu_gather *tlb) * See the comment for radix in arch_exit_mmap(). */ if (tlb->fullmm) { - __flush_all_mm(mm, true); + if (IS_ENABLED(CONFIG_MMU_LAZY_TLB_SHOOTDOWN)) { + /* + * Shootdown based lazy tlb mm refcounting means we + * have to IPI everyone in the mm_cpumask anyway soon + * when the mm goes away, so might as well do it as + * part of the final flush now. + * + * If lazy shootdown was improved to reduce IPIs (e.g., + * by batching), then it may end up being better to use + * tlbies here instead. + */ + preempt_disable(); + + smp_mb(); /* see radix__flush_tlb_mm */ + exit_flush_lazy_tlbs(mm); + _tlbiel_pid(mm->context.id, RIC_FLUSH_ALL); + + /* + * It should not be possible to have coprocessors still + * attached here. + */ + if (WARN_ON_ONCE(atomic_read(&mm->context.copros) > 0)) + __flush_all_mm(mm, true); + + preempt_enable(); + } else { + __flush_all_mm(mm, true); + } + } else if ( (psize = radix_get_mmu_psize(page_size)) == -1) { if (!tlb->freed_tables) radix__flush_tlb_mm(mm); @@ -1392,6 +1304,7 @@ static void __radix__flush_tlb_range_psize(struct mm_struct *mm, } out: preempt_enable(); + mmu_notifier_arch_invalidate_secondary_tlbs(mm, start, end); } void radix__flush_tlb_range_psize(struct mm_struct *mm, unsigned long start, @@ -1461,6 +1374,13 @@ void radix__flush_pmd_tlb_range(struct vm_area_struct *vma, } EXPORT_SYMBOL(radix__flush_pmd_tlb_range); +void radix__flush_pud_tlb_range(struct vm_area_struct *vma, + unsigned long start, unsigned long end) +{ + radix__flush_tlb_range_psize(vma->vm_mm, start, end, MMU_PAGE_1G); +} +EXPORT_SYMBOL(radix__flush_pud_tlb_range); + void radix__flush_tlb_all(void) { unsigned long rb,prs,r,rs; @@ -1486,6 +1406,127 @@ void radix__flush_tlb_all(void) } #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE +static __always_inline void __tlbie_pid_lpid(unsigned long pid, + unsigned long lpid, + unsigned long ric) +{ + unsigned long rb, rs, prs, r; + + rb = PPC_BIT(53); /* IS = 1 */ + rs = (pid << PPC_BITLSHIFT(31)) | (lpid & ~(PPC_BITMASK(0, 31))); + prs = 1; /* process scoped */ + r = 1; /* radix format */ + + asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1) + : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory"); + trace_tlbie(0, 0, rb, rs, ric, prs, r); +} + +static __always_inline void __tlbie_va_lpid(unsigned long va, unsigned long pid, + unsigned long lpid, + unsigned long ap, unsigned long ric) +{ + unsigned long rb, rs, prs, r; + + rb = va & ~(PPC_BITMASK(52, 63)); + rb |= ap << PPC_BITLSHIFT(58); + rs = (pid << PPC_BITLSHIFT(31)) | (lpid & ~(PPC_BITMASK(0, 31))); + prs = 1; /* process scoped */ + r = 1; /* radix format */ + + asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1) + : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory"); + trace_tlbie(0, 0, rb, rs, ric, prs, r); +} + +static inline void fixup_tlbie_pid_lpid(unsigned long pid, unsigned long lpid) +{ + /* + * We can use any address for the invalidation, pick one which is + * probably unused as an optimisation. + */ + unsigned long va = ((1UL << 52) - 1); + + if (cpu_has_feature(CPU_FTR_P9_TLBIE_ERAT_BUG)) { + asm volatile("ptesync" : : : "memory"); + __tlbie_pid_lpid(0, lpid, RIC_FLUSH_TLB); + } + + if (cpu_has_feature(CPU_FTR_P9_TLBIE_STQ_BUG)) { + asm volatile("ptesync" : : : "memory"); + __tlbie_va_lpid(va, pid, lpid, mmu_get_ap(MMU_PAGE_64K), + RIC_FLUSH_TLB); + } +} + +static inline void _tlbie_pid_lpid(unsigned long pid, unsigned long lpid, + unsigned long ric) +{ + asm volatile("ptesync" : : : "memory"); + + /* + * Workaround the fact that the "ric" argument to __tlbie_pid + * must be a compile-time contraint to match the "i" constraint + * in the asm statement. + */ + switch (ric) { + case RIC_FLUSH_TLB: + __tlbie_pid_lpid(pid, lpid, RIC_FLUSH_TLB); + fixup_tlbie_pid_lpid(pid, lpid); + break; + case RIC_FLUSH_PWC: + __tlbie_pid_lpid(pid, lpid, RIC_FLUSH_PWC); + break; + case RIC_FLUSH_ALL: + default: + __tlbie_pid_lpid(pid, lpid, RIC_FLUSH_ALL); + fixup_tlbie_pid_lpid(pid, lpid); + } + asm volatile("eieio; tlbsync; ptesync" : : : "memory"); +} + +static inline void fixup_tlbie_va_range_lpid(unsigned long va, + unsigned long pid, + unsigned long lpid, + unsigned long ap) +{ + if (cpu_has_feature(CPU_FTR_P9_TLBIE_ERAT_BUG)) { + asm volatile("ptesync" : : : "memory"); + __tlbie_pid_lpid(0, lpid, RIC_FLUSH_TLB); + } + + if (cpu_has_feature(CPU_FTR_P9_TLBIE_STQ_BUG)) { + asm volatile("ptesync" : : : "memory"); + __tlbie_va_lpid(va, pid, lpid, ap, RIC_FLUSH_TLB); + } +} + +static inline void __tlbie_va_range_lpid(unsigned long start, unsigned long end, + unsigned long pid, unsigned long lpid, + unsigned long page_size, + unsigned long psize) +{ + unsigned long addr; + unsigned long ap = mmu_get_ap(psize); + + for (addr = start; addr < end; addr += page_size) + __tlbie_va_lpid(addr, pid, lpid, ap, RIC_FLUSH_TLB); + + fixup_tlbie_va_range_lpid(addr - page_size, pid, lpid, ap); +} + +static inline void _tlbie_va_range_lpid(unsigned long start, unsigned long end, + unsigned long pid, unsigned long lpid, + unsigned long page_size, + unsigned long psize, bool also_pwc) +{ + asm volatile("ptesync" : : : "memory"); + if (also_pwc) + __tlbie_pid_lpid(pid, lpid, RIC_FLUSH_PWC); + __tlbie_va_range_lpid(start, end, pid, lpid, page_size, psize); + asm volatile("eieio; tlbsync; ptesync" : : : "memory"); +} + /* * Performs process-scoped invalidations for a given LPID * as part of H_RPT_INVALIDATE hcall. diff --git a/arch/powerpc/mm/book3s64/slb.c b/arch/powerpc/mm/book3s64/slb.c index 6956f637a38c..f2708c8629a5 100644 --- a/arch/powerpc/mm/book3s64/slb.c +++ b/arch/powerpc/mm/book3s64/slb.c @@ -13,6 +13,7 @@ #include <asm/mmu.h> #include <asm/mmu_context.h> #include <asm/paca.h> +#include <asm/lppaca.h> #include <asm/ppc-opcode.h> #include <asm/cputable.h> #include <asm/cacheflush.h> diff --git a/arch/powerpc/mm/book3s64/subpage_prot.c b/arch/powerpc/mm/book3s64/subpage_prot.c index 0dc85556dec5..ec98e526167e 100644 --- a/arch/powerpc/mm/book3s64/subpage_prot.c +++ b/arch/powerpc/mm/book3s64/subpage_prot.c @@ -145,6 +145,7 @@ static int subpage_walk_pmd_entry(pmd_t *pmd, unsigned long addr, static const struct mm_walk_ops subpage_walk_ops = { .pmd_entry = subpage_walk_pmd_entry, + .walk_lock = PGWALK_WRLOCK_VERIFY, }; static void subpage_mark_vma_nohuge(struct mm_struct *mm, unsigned long addr, diff --git a/arch/powerpc/mm/cacheflush.c b/arch/powerpc/mm/cacheflush.c index 0e9b4879c0f9..15189592da09 100644 --- a/arch/powerpc/mm/cacheflush.c +++ b/arch/powerpc/mm/cacheflush.c @@ -148,44 +148,31 @@ static void __flush_dcache_icache(void *p) invalidate_icache_range(addr, addr + PAGE_SIZE); } -static void flush_dcache_icache_hugepage(struct page *page) +void flush_dcache_icache_folio(struct folio *folio) { - int i; - int nr = compound_nr(page); + unsigned int i, nr = folio_nr_pages(folio); - if (!PageHighMem(page)) { + if (flush_coherent_icache()) + return; + + if (!folio_test_highmem(folio)) { + void *addr = folio_address(folio); for (i = 0; i < nr; i++) - __flush_dcache_icache(lowmem_page_address(page + i)); - } else { + __flush_dcache_icache(addr + i * PAGE_SIZE); + } else if (IS_ENABLED(CONFIG_BOOKE) || sizeof(phys_addr_t) > sizeof(void *)) { for (i = 0; i < nr; i++) { - void *start = kmap_local_page(page + i); + void *start = kmap_local_folio(folio, i * PAGE_SIZE); __flush_dcache_icache(start); kunmap_local(start); } - } -} - -void flush_dcache_icache_page(struct page *page) -{ - if (flush_coherent_icache()) - return; - - if (PageCompound(page)) - return flush_dcache_icache_hugepage(page); - - if (!PageHighMem(page)) { - __flush_dcache_icache(lowmem_page_address(page)); - } else if (IS_ENABLED(CONFIG_BOOKE) || sizeof(phys_addr_t) > sizeof(void *)) { - void *start = kmap_local_page(page); - - __flush_dcache_icache(start); - kunmap_local(start); } else { - flush_dcache_icache_phys(page_to_phys(page)); + unsigned long pfn = folio_pfn(folio); + for (i = 0; i < nr; i++) + flush_dcache_icache_phys((pfn + i) * PAGE_SIZE); } } -EXPORT_SYMBOL(flush_dcache_icache_page); +EXPORT_SYMBOL(flush_dcache_icache_folio); void clear_user_page(void *page, unsigned long vaddr, struct page *pg) { diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index 5bfdf6ecfa96..b1723094d464 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -469,7 +469,6 @@ static int ___do_page_fault(struct pt_regs *regs, unsigned long address, if (is_exec) flags |= FAULT_FLAG_INSTRUCTION; -#ifdef CONFIG_PER_VMA_LOCK if (!(flags & FAULT_FLAG_USER)) goto lock_mmap; @@ -489,7 +488,8 @@ static int ___do_page_fault(struct pt_regs *regs, unsigned long address, } fault = handle_mm_fault(vma, address, flags | FAULT_FLAG_VMA_LOCK, regs); - vma_end_read(vma); + if (!(fault & (VM_FAULT_RETRY | VM_FAULT_COMPLETED))) + vma_end_read(vma); if (!(fault & VM_FAULT_RETRY)) { count_vm_vma_lock_event(VMA_LOCK_SUCCESS); @@ -501,7 +501,6 @@ static int ___do_page_fault(struct pt_regs *regs, unsigned long address, return user_mode(regs) ? 0 : SIGBUS; lock_mmap: -#endif /* CONFIG_PER_VMA_LOCK */ /* When running in the kernel we expect faults to occur only to * addresses in user space. All other faults represent errors in the @@ -551,9 +550,7 @@ retry: mmap_read_unlock(current->mm); -#ifdef CONFIG_PER_VMA_LOCK done: -#endif if (unlikely(fault & VM_FAULT_ERROR)) return mm_fault_error(regs, address, fault); diff --git a/arch/powerpc/mm/init_32.c b/arch/powerpc/mm/init_32.c index d4cc3749e621..d8adc452f431 100644 --- a/arch/powerpc/mm/init_32.c +++ b/arch/powerpc/mm/init_32.c @@ -126,6 +126,8 @@ void __init MMU_init(void) setup_kup(); + update_mmu_feature_fixups(MMU_FTR_KUAP); + /* Shortly after that, the entire linear mapping will be available */ memblock_set_current_limit(lowmem_end_addr); } diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c index fe1b83020e0d..d96bbc001e73 100644 --- a/arch/powerpc/mm/init_64.c +++ b/arch/powerpc/mm/init_64.c @@ -40,6 +40,7 @@ #include <linux/of_fdt.h> #include <linux/libfdt.h> #include <linux/memremap.h> +#include <linux/memory.h> #include <asm/pgalloc.h> #include <asm/page.h> @@ -92,7 +93,7 @@ static struct page * __meminit vmemmap_subsection_start(unsigned long vmemmap_ad * 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 vmemmap_addr, int vmemmap_map_size) +int __meminit vmemmap_populated(unsigned long vmemmap_addr, int vmemmap_map_size) { struct page *start; unsigned long vmemmap_end = vmemmap_addr + vmemmap_map_size; @@ -183,8 +184,8 @@ static __meminit int vmemmap_list_populate(unsigned long phys, return 0; } -static bool altmap_cross_boundary(struct vmem_altmap *altmap, unsigned long start, - unsigned long page_size) +bool altmap_cross_boundary(struct vmem_altmap *altmap, unsigned long start, + unsigned long page_size) { unsigned long nr_pfn = page_size / sizeof(struct page); unsigned long start_pfn = page_to_pfn((struct page *)start); @@ -198,8 +199,8 @@ static bool altmap_cross_boundary(struct vmem_altmap *altmap, unsigned long star return false; } -int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, - struct vmem_altmap *altmap) +static int __meminit __vmemmap_populate(unsigned long start, unsigned long end, int node, + struct vmem_altmap *altmap) { bool altmap_alloc; unsigned long page_size = 1 << mmu_psize_defs[mmu_vmemmap_psize].shift; @@ -272,6 +273,18 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, return 0; } +int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, + struct vmem_altmap *altmap) +{ + +#ifdef CONFIG_PPC_BOOK3S_64 + if (radix_enabled()) + return radix__vmemmap_populate(start, end, node, altmap); +#endif + + return __vmemmap_populate(start, end, node, altmap); +} + #ifdef CONFIG_MEMORY_HOTPLUG static unsigned long vmemmap_list_free(unsigned long start) { @@ -303,8 +316,8 @@ static unsigned long vmemmap_list_free(unsigned long start) return vmem_back->phys; } -void __ref vmemmap_free(unsigned long start, unsigned long end, - struct vmem_altmap *altmap) +static void __ref __vmemmap_free(unsigned long start, unsigned long end, + struct vmem_altmap *altmap) { unsigned long page_size = 1 << mmu_psize_defs[mmu_vmemmap_psize].shift; unsigned long page_order = get_order(page_size); @@ -314,8 +327,7 @@ void __ref vmemmap_free(unsigned long start, unsigned long end, start = ALIGN_DOWN(start, page_size); if (altmap) { alt_start = altmap->base_pfn; - alt_end = altmap->base_pfn + altmap->reserve + - altmap->free + altmap->alloc + altmap->align; + alt_end = altmap->base_pfn + altmap->reserve + altmap->free; } pr_debug("vmemmap_free %lx...%lx\n", start, end); @@ -362,6 +374,17 @@ void __ref vmemmap_free(unsigned long start, unsigned long end, vmemmap_remove_mapping(start, page_size); } } + +void __ref vmemmap_free(unsigned long start, unsigned long end, + struct vmem_altmap *altmap) +{ +#ifdef CONFIG_PPC_BOOK3S_64 + if (radix_enabled()) + return radix__vmemmap_free(start, end, altmap); +#endif + return __vmemmap_free(start, end, altmap); +} + #endif void register_page_bootmem_memmap(unsigned long section_nr, struct page *start_page, unsigned long size) @@ -471,6 +494,130 @@ static int __init dt_scan_mmu_pid_width(unsigned long node, return 1; } +/* + * Outside hotplug the kernel uses this value to map the kernel direct map + * with radix. To be compatible with older kernels, let's keep this value + * as 16M which is also SECTION_SIZE with SPARSEMEM. We can ideally map + * things with 1GB size in the case where we don't support hotplug. + */ +#ifndef CONFIG_MEMORY_HOTPLUG +#define DEFAULT_MEMORY_BLOCK_SIZE SZ_16M +#else +#define DEFAULT_MEMORY_BLOCK_SIZE MIN_MEMORY_BLOCK_SIZE +#endif + +static void update_memory_block_size(unsigned long *block_size, unsigned long mem_size) +{ + unsigned long min_memory_block_size = DEFAULT_MEMORY_BLOCK_SIZE; + + for (; *block_size > min_memory_block_size; *block_size >>= 2) { + if ((mem_size & *block_size) == 0) + break; + } +} + +static int __init probe_memory_block_size(unsigned long node, const char *uname, int + depth, void *data) +{ + const char *type; + unsigned long *block_size = (unsigned long *)data; + const __be32 *reg, *endp; + int l; + + if (depth != 1) + return 0; + /* + * If we have dynamic-reconfiguration-memory node, use the + * lmb value. + */ + if (strcmp(uname, "ibm,dynamic-reconfiguration-memory") == 0) { + + const __be32 *prop; + + prop = of_get_flat_dt_prop(node, "ibm,lmb-size", &l); + + if (!prop || l < dt_root_size_cells * sizeof(__be32)) + /* + * Nothing in the device tree + */ + *block_size = DEFAULT_MEMORY_BLOCK_SIZE; + else + *block_size = of_read_number(prop, dt_root_size_cells); + /* + * We have found the final value. Don't probe further. + */ + return 1; + } + /* + * Find all the device tree nodes of memory type and make sure + * the area can be mapped using the memory block size value + * we end up using. We start with 1G value and keep reducing + * it such that we can map the entire area using memory_block_size. + * This will be used on powernv and older pseries that don't + * have ibm,lmb-size node. + * For ex: with P5 we can end up with + * memory@0 -> 128MB + * memory@128M -> 64M + * This will end up using 64MB memory block size value. + */ + type = of_get_flat_dt_prop(node, "device_type", NULL); + if (type == NULL || strcmp(type, "memory") != 0) + return 0; + + reg = of_get_flat_dt_prop(node, "linux,usable-memory", &l); + if (!reg) + reg = of_get_flat_dt_prop(node, "reg", &l); + if (!reg) + return 0; + + endp = reg + (l / sizeof(__be32)); + while ((endp - reg) >= (dt_root_addr_cells + dt_root_size_cells)) { + const char *compatible; + u64 size; + + dt_mem_next_cell(dt_root_addr_cells, ®); + size = dt_mem_next_cell(dt_root_size_cells, ®); + + if (size) { + update_memory_block_size(block_size, size); + continue; + } + /* + * ibm,coherent-device-memory with linux,usable-memory = 0 + * Force 256MiB block size. Work around for GPUs on P9 PowerNV + * linux,usable-memory == 0 implies driver managed memory and + * we can't use large memory block size due to hotplug/unplug + * limitations. + */ + compatible = of_get_flat_dt_prop(node, "compatible", NULL); + if (compatible && !strcmp(compatible, "ibm,coherent-device-memory")) { + if (*block_size > SZ_256M) + *block_size = SZ_256M; + /* + * We keep 256M as the upper limit with GPU present. + */ + return 0; + } + } + /* continue looking for other memory device types */ + return 0; +} + +/* + * start with 1G memory block size. Early init will + * fix this with correct value. + */ +unsigned long memory_block_size __ro_after_init = 1UL << 30; +static void __init early_init_memory_block_size(void) +{ + /* + * We need to do memory_block_size probe early so that + * radix__early_init_mmu() can use this as limit for + * mapping page size. + */ + of_scan_flat_dt(probe_memory_block_size, &memory_block_size); +} + void __init mmu_early_init_devtree(void) { bool hvmode = !!(mfmsr() & MSR_HV); @@ -504,6 +651,8 @@ void __init mmu_early_init_devtree(void) if (!hvmode) early_check_vec5(); + early_init_memory_block_size(); + if (early_radix_enabled()) { radix__early_init_devtree(); diff --git a/arch/powerpc/mm/ioremap.c b/arch/powerpc/mm/ioremap.c index 4f12504fb405..705e8e8ffde4 100644 --- a/arch/powerpc/mm/ioremap.c +++ b/arch/powerpc/mm/ioremap.c @@ -41,7 +41,7 @@ void __iomem *ioremap_coherent(phys_addr_t addr, unsigned long size) return __ioremap_caller(addr, size, prot, caller); } -void __iomem *ioremap_prot(phys_addr_t addr, unsigned long size, unsigned long flags) +void __iomem *ioremap_prot(phys_addr_t addr, size_t size, unsigned long flags) { pte_t pte = __pte(flags); void *caller = __builtin_return_address(0); @@ -74,27 +74,3 @@ int early_ioremap_range(unsigned long ea, phys_addr_t pa, return 0; } - -void __iomem *do_ioremap(phys_addr_t pa, phys_addr_t offset, unsigned long size, - pgprot_t prot, void *caller) -{ - struct vm_struct *area; - int ret; - unsigned long va; - - area = __get_vm_area_caller(size, VM_IOREMAP, IOREMAP_START, IOREMAP_END, caller); - if (area == NULL) - return NULL; - - area->phys_addr = pa; - va = (unsigned long)area->addr; - - ret = ioremap_page_range(va, va + size, pa, prot); - if (!ret) - return (void __iomem *)area->addr + offset; - - vunmap_range(va, va + size); - free_vm_area(area); - - return NULL; -} diff --git a/arch/powerpc/mm/ioremap_32.c b/arch/powerpc/mm/ioremap_32.c index 9d13143b8be4..ca5bc6be3e6f 100644 --- a/arch/powerpc/mm/ioremap_32.c +++ b/arch/powerpc/mm/ioremap_32.c @@ -22,6 +22,13 @@ __ioremap_caller(phys_addr_t addr, unsigned long size, pgprot_t prot, void *call int err; /* + * If the address lies within the first 16 MB, assume it's in ISA + * memory space + */ + if (addr < SZ_16M) + addr += _ISA_MEM_BASE; + + /* * Choose an address to map it to. * Once the vmalloc system is running, we use it. * Before then, we use space going down from IOREMAP_TOP @@ -31,13 +38,6 @@ __ioremap_caller(phys_addr_t addr, unsigned long size, pgprot_t prot, void *call offset = addr & ~PAGE_MASK; size = PAGE_ALIGN(addr + size) - p; - /* - * If the address lies within the first 16 MB, assume it's in ISA - * memory space - */ - if (p < 16 * 1024 * 1024) - p += _ISA_MEM_BASE; - #ifndef CONFIG_CRASH_DUMP /* * Don't allow anybody to remap normal RAM that we're using. @@ -63,7 +63,7 @@ __ioremap_caller(phys_addr_t addr, unsigned long size, pgprot_t prot, void *call return (void __iomem *)v + offset; if (slab_is_available()) - return do_ioremap(p, offset, size, prot, caller); + return generic_ioremap_prot(addr, size, prot); /* * Should check if it is a candidate for a BAT mapping @@ -87,7 +87,6 @@ void iounmap(volatile void __iomem *addr) if (v_block_mapped((unsigned long)addr)) return; - if (addr > high_memory && (unsigned long)addr < ioremap_bot) - vunmap((void *)(PAGE_MASK & (unsigned long)addr)); + generic_iounmap(addr); } EXPORT_SYMBOL(iounmap); diff --git a/arch/powerpc/mm/ioremap_64.c b/arch/powerpc/mm/ioremap_64.c index 3acece00b33e..d24e5f166723 100644 --- a/arch/powerpc/mm/ioremap_64.c +++ b/arch/powerpc/mm/ioremap_64.c @@ -29,7 +29,7 @@ void __iomem *__ioremap_caller(phys_addr_t addr, unsigned long size, return NULL; if (slab_is_available()) - return do_ioremap(paligned, offset, size, prot, caller); + return generic_ioremap_prot(addr, size, prot); pr_warn("ioremap() called early from %pS. Use early_ioremap() instead\n", caller); @@ -49,17 +49,9 @@ void __iomem *__ioremap_caller(phys_addr_t addr, unsigned long size, */ void iounmap(volatile void __iomem *token) { - void *addr; - if (!slab_is_available()) return; - addr = (void *)((unsigned long __force)PCI_FIX_ADDR(token) & PAGE_MASK); - - if ((unsigned long)addr < ioremap_bot) { - pr_warn("Attempt to iounmap early bolted mapping at 0x%p\n", addr); - return; - } - vunmap(addr); + generic_iounmap(PCI_FIX_ADDR(token)); } EXPORT_SYMBOL(iounmap); diff --git a/arch/powerpc/mm/mmu_context.c b/arch/powerpc/mm/mmu_context.c index 1fb9c99f8679..b24c19078eb1 100644 --- a/arch/powerpc/mm/mmu_context.c +++ b/arch/powerpc/mm/mmu_context.c @@ -43,11 +43,13 @@ static inline void switch_mm_pgdir(struct task_struct *tsk, void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, struct task_struct *tsk) { + int cpu = smp_processor_id(); bool new_on_cpu = false; /* Mark this context has been used on the new CPU */ - if (!cpumask_test_cpu(smp_processor_id(), mm_cpumask(next))) { - cpumask_set_cpu(smp_processor_id(), mm_cpumask(next)); + if (!cpumask_test_cpu(cpu, mm_cpumask(next))) { + VM_WARN_ON_ONCE(next == &init_mm); + cpumask_set_cpu(cpu, mm_cpumask(next)); inc_mm_active_cpus(next); /* @@ -100,6 +102,8 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, * sub architectures. Out of line for now */ switch_mmu_context(prev, next, tsk); + + VM_WARN_ON_ONCE(!cpumask_test_cpu(cpu, mm_cpumask(prev))); } #ifndef CONFIG_PPC_BOOK3S_64 diff --git a/arch/powerpc/mm/mmu_decl.h b/arch/powerpc/mm/mmu_decl.h index c6dccb4f06dc..7f9ff0640124 100644 --- a/arch/powerpc/mm/mmu_decl.h +++ b/arch/powerpc/mm/mmu_decl.h @@ -110,6 +110,7 @@ extern void MMU_init_hw(void); void MMU_init_hw_patch(void); unsigned long mmu_mapin_ram(unsigned long base, unsigned long top); #endif +void mmu_init_secondary(int cpu); #ifdef CONFIG_PPC_E500 extern unsigned long map_mem_in_cams(unsigned long ram, int max_cam_idx, diff --git a/arch/powerpc/mm/nohash/e500_hugetlbpage.c b/arch/powerpc/mm/nohash/e500_hugetlbpage.c index 58c8d9849cb1..6b30e40d4590 100644 --- a/arch/powerpc/mm/nohash/e500_hugetlbpage.c +++ b/arch/powerpc/mm/nohash/e500_hugetlbpage.c @@ -178,7 +178,8 @@ book3e_hugetlb_preload(struct vm_area_struct *vma, unsigned long ea, pte_t pte) * * This must always be called with the pte lock held. */ -void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) +void update_mmu_cache_range(struct vm_fault *vmf, struct vm_area_struct *vma, + unsigned long address, pte_t *ptep, unsigned int nr) { if (is_vm_hugetlb_page(vma)) book3e_hugetlb_preload(vma, address, *ptep); diff --git a/arch/powerpc/mm/nohash/kup.c b/arch/powerpc/mm/nohash/kup.c index 552becf90e97..e1f7de2e54ec 100644 --- a/arch/powerpc/mm/nohash/kup.c +++ b/arch/powerpc/mm/nohash/kup.c @@ -5,7 +5,6 @@ #include <linux/export.h> #include <linux/init.h> -#include <linux/jump_label.h> #include <linux/printk.h> #include <linux/smp.h> @@ -13,21 +12,18 @@ #include <asm/smp.h> #ifdef CONFIG_PPC_KUAP -struct static_key_false disable_kuap_key; -EXPORT_SYMBOL(disable_kuap_key); - void setup_kuap(bool disabled) { if (disabled) { if (IS_ENABLED(CONFIG_40x)) disable_kuep = true; if (smp_processor_id() == boot_cpuid) - static_branch_enable(&disable_kuap_key); + cur_cpu_spec->mmu_features &= ~MMU_FTR_KUAP; return; } pr_info("Activating Kernel Userspace Access Protection\n"); - __prevent_user_access(KUAP_READ_WRITE); + prevent_user_access(KUAP_READ_WRITE); } #endif diff --git a/arch/powerpc/mm/nohash/tlb.c b/arch/powerpc/mm/nohash/tlb.c index a903b308acc5..5ffa0af4328a 100644 --- a/arch/powerpc/mm/nohash/tlb.c +++ b/arch/powerpc/mm/nohash/tlb.c @@ -318,17 +318,6 @@ EXPORT_SYMBOL(flush_tlb_page); #endif /* CONFIG_SMP */ -#ifdef CONFIG_PPC_47x -void __init early_init_mmu_47x(void) -{ -#ifdef CONFIG_SMP - unsigned long root = of_get_flat_dt_root(); - if (of_get_flat_dt_prop(root, "cooperative-partition", NULL)) - mmu_clear_feature(MMU_FTR_USE_TLBIVAX_BCAST); -#endif /* CONFIG_SMP */ -} -#endif /* CONFIG_PPC_47x */ - /* * Flush kernel TLB entries in the given range */ @@ -746,8 +735,10 @@ void setup_initial_memory_limit(phys_addr_t first_memblock_base, #else /* ! CONFIG_PPC64 */ void __init early_init_mmu(void) { -#ifdef CONFIG_PPC_47x - early_init_mmu_47x(); -#endif + unsigned long root = of_get_flat_dt_root(); + + if (IS_ENABLED(CONFIG_PPC_47x) && IS_ENABLED(CONFIG_SMP) && + of_get_flat_dt_prop(root, "cooperative-partition", NULL)) + mmu_clear_feature(MMU_FTR_USE_TLBIVAX_BCAST); } #endif /* CONFIG_PPC64 */ diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index 9f73d089eac1..f6c4ace3b221 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -34,6 +34,7 @@ #include <asm/hvcall.h> #include <asm/setup.h> #include <asm/vdso.h> +#include <asm/vphn.h> #include <asm/drmem.h> static int numa_enabled = 1; diff --git a/arch/powerpc/mm/pgtable-frag.c b/arch/powerpc/mm/pgtable-frag.c index 20652daa1d7e..8c31802f97e8 100644 --- a/arch/powerpc/mm/pgtable-frag.c +++ b/arch/powerpc/mm/pgtable-frag.c @@ -18,15 +18,15 @@ void pte_frag_destroy(void *pte_frag) { int count; - struct page *page; + struct ptdesc *ptdesc; - page = virt_to_page(pte_frag); + ptdesc = virt_to_ptdesc(pte_frag); /* drop all the pending references */ count = ((unsigned long)pte_frag & ~PAGE_MASK) >> PTE_FRAG_SIZE_SHIFT; /* We allow PTE_FRAG_NR fragments from a PTE page */ - if (atomic_sub_and_test(PTE_FRAG_NR - count, &page->pt_frag_refcount)) { - pgtable_pte_page_dtor(page); - __free_page(page); + if (atomic_sub_and_test(PTE_FRAG_NR - count, &ptdesc->pt_frag_refcount)) { + pagetable_pte_dtor(ptdesc); + pagetable_free(ptdesc); } } @@ -55,25 +55,25 @@ static pte_t *get_pte_from_cache(struct mm_struct *mm) static pte_t *__alloc_for_ptecache(struct mm_struct *mm, int kernel) { void *ret = NULL; - struct page *page; + struct ptdesc *ptdesc; if (!kernel) { - page = alloc_page(PGALLOC_GFP | __GFP_ACCOUNT); - if (!page) + ptdesc = pagetable_alloc(PGALLOC_GFP | __GFP_ACCOUNT, 0); + if (!ptdesc) return NULL; - if (!pgtable_pte_page_ctor(page)) { - __free_page(page); + if (!pagetable_pte_ctor(ptdesc)) { + pagetable_free(ptdesc); return NULL; } } else { - page = alloc_page(PGALLOC_GFP); - if (!page) + ptdesc = pagetable_alloc(PGALLOC_GFP, 0); + if (!ptdesc) return NULL; } - atomic_set(&page->pt_frag_refcount, 1); + atomic_set(&ptdesc->pt_frag_refcount, 1); - ret = page_address(page); + ret = ptdesc_address(ptdesc); /* * if we support only one fragment just return the * allocated page. @@ -82,12 +82,12 @@ static pte_t *__alloc_for_ptecache(struct mm_struct *mm, int kernel) return ret; spin_lock(&mm->page_table_lock); /* - * If we find pgtable_page set, we return + * If we find ptdesc_page set, we return * the allocated page with single fragment * count. */ if (likely(!pte_frag_get(&mm->context))) { - atomic_set(&page->pt_frag_refcount, PTE_FRAG_NR); + atomic_set(&ptdesc->pt_frag_refcount, PTE_FRAG_NR); pte_frag_set(&mm->context, ret + PTE_FRAG_SIZE); } spin_unlock(&mm->page_table_lock); @@ -106,17 +106,40 @@ pte_t *pte_fragment_alloc(struct mm_struct *mm, int kernel) return __alloc_for_ptecache(mm, kernel); } -void pte_fragment_free(unsigned long *table, int kernel) +static void pte_free_now(struct rcu_head *head) { - struct page *page = virt_to_page(table); + struct ptdesc *ptdesc; - if (PageReserved(page)) - return free_reserved_page(page); + ptdesc = container_of(head, struct ptdesc, pt_rcu_head); + pagetable_pte_dtor(ptdesc); + pagetable_free(ptdesc); +} - BUG_ON(atomic_read(&page->pt_frag_refcount) <= 0); - if (atomic_dec_and_test(&page->pt_frag_refcount)) { - if (!kernel) - pgtable_pte_page_dtor(page); - __free_page(page); +void pte_fragment_free(unsigned long *table, int kernel) +{ + struct ptdesc *ptdesc = virt_to_ptdesc(table); + + if (pagetable_is_reserved(ptdesc)) + return free_reserved_ptdesc(ptdesc); + + BUG_ON(atomic_read(&ptdesc->pt_frag_refcount) <= 0); + if (atomic_dec_and_test(&ptdesc->pt_frag_refcount)) { + if (kernel) + pagetable_free(ptdesc); + else if (folio_test_clear_active(ptdesc_folio(ptdesc))) + call_rcu(&ptdesc->pt_rcu_head, pte_free_now); + else + pte_free_now(&ptdesc->pt_rcu_head); } } + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +void pte_free_defer(struct mm_struct *mm, pgtable_t pgtable) +{ + struct page *page; + + page = virt_to_page(pgtable); + SetPageActive(page); + pte_fragment_free((unsigned long *)pgtable, 0); +} +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c index cb2dcdb18f8e..3f86fd217690 100644 --- a/arch/powerpc/mm/pgtable.c +++ b/arch/powerpc/mm/pgtable.c @@ -58,7 +58,7 @@ static inline int pte_looks_normal(pte_t pte) return 0; } -static struct page *maybe_pte_to_page(pte_t pte) +static struct folio *maybe_pte_to_folio(pte_t pte) { unsigned long pfn = pte_pfn(pte); struct page *page; @@ -68,7 +68,7 @@ static struct page *maybe_pte_to_page(pte_t pte) page = pfn_to_page(pfn); if (PageReserved(page)) return NULL; - return page; + return page_folio(page); } #ifdef CONFIG_PPC_BOOK3S @@ -84,12 +84,12 @@ static pte_t set_pte_filter_hash(pte_t pte) pte = __pte(pte_val(pte) & ~_PAGE_HPTEFLAGS); if (pte_looks_normal(pte) && !(cpu_has_feature(CPU_FTR_COHERENT_ICACHE) || cpu_has_feature(CPU_FTR_NOEXECUTE))) { - struct page *pg = maybe_pte_to_page(pte); - if (!pg) + struct folio *folio = maybe_pte_to_folio(pte); + if (!folio) return pte; - if (!test_bit(PG_dcache_clean, &pg->flags)) { - flush_dcache_icache_page(pg); - set_bit(PG_dcache_clean, &pg->flags); + if (!test_bit(PG_dcache_clean, &folio->flags)) { + flush_dcache_icache_folio(folio); + set_bit(PG_dcache_clean, &folio->flags); } } return pte; @@ -107,7 +107,7 @@ static pte_t set_pte_filter_hash(pte_t pte) { return pte; } */ static inline pte_t set_pte_filter(pte_t pte) { - struct page *pg; + struct folio *folio; if (radix_enabled()) return pte; @@ -120,18 +120,18 @@ static inline pte_t set_pte_filter(pte_t pte) return pte; /* If you set _PAGE_EXEC on weird pages you're on your own */ - pg = maybe_pte_to_page(pte); - if (unlikely(!pg)) + folio = maybe_pte_to_folio(pte); + if (unlikely(!folio)) return pte; /* If the page clean, we move on */ - if (test_bit(PG_dcache_clean, &pg->flags)) + if (test_bit(PG_dcache_clean, &folio->flags)) return pte; /* If it's an exec fault, we flush the cache and make it clean */ if (is_exec_fault()) { - flush_dcache_icache_page(pg); - set_bit(PG_dcache_clean, &pg->flags); + flush_dcache_icache_folio(folio); + set_bit(PG_dcache_clean, &folio->flags); return pte; } @@ -142,7 +142,7 @@ static inline pte_t set_pte_filter(pte_t pte) static pte_t set_access_flags_filter(pte_t pte, struct vm_area_struct *vma, int dirty) { - struct page *pg; + struct folio *folio; if (IS_ENABLED(CONFIG_PPC_BOOK3S_64)) return pte; @@ -168,17 +168,17 @@ static pte_t set_access_flags_filter(pte_t pte, struct vm_area_struct *vma, #endif /* CONFIG_DEBUG_VM */ /* If you set _PAGE_EXEC on weird pages you're on your own */ - pg = maybe_pte_to_page(pte); - if (unlikely(!pg)) + folio = maybe_pte_to_folio(pte); + if (unlikely(!folio)) goto bail; /* If the page is already clean, we move on */ - if (test_bit(PG_dcache_clean, &pg->flags)) + if (test_bit(PG_dcache_clean, &folio->flags)) goto bail; /* Clean the page and set PG_dcache_clean */ - flush_dcache_icache_page(pg); - set_bit(PG_dcache_clean, &pg->flags); + flush_dcache_icache_folio(folio); + set_bit(PG_dcache_clean, &folio->flags); bail: return pte_mkexec(pte); @@ -187,8 +187,8 @@ static pte_t set_access_flags_filter(pte_t pte, struct vm_area_struct *vma, /* * set_pte stores a linux PTE into the linux page table. */ -void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, - pte_t pte) +void set_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, + pte_t pte, unsigned int nr) { /* * Make sure hardware valid bit is not set. We don't do @@ -203,7 +203,16 @@ void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte = set_pte_filter(pte); /* Perform the setting of the PTE */ - __set_pte_at(mm, addr, ptep, pte, 0); + arch_enter_lazy_mmu_mode(); + for (;;) { + __set_pte_at(mm, addr, ptep, pte, 0); + if (--nr == 0) + break; + ptep++; + pte = __pte(pte_val(pte) + (1UL << PTE_RPN_SHIFT)); + addr += PAGE_SIZE; + } + arch_leave_lazy_mmu_mode(); } void unmap_kernel_page(unsigned long va) @@ -311,6 +320,8 @@ void assert_pte_locked(struct mm_struct *mm, unsigned long addr) p4d_t *p4d; pud_t *pud; pmd_t *pmd; + pte_t *pte; + spinlock_t *ptl; if (mm == &init_mm) return; @@ -329,8 +340,10 @@ void assert_pte_locked(struct mm_struct *mm, unsigned long addr) */ if (pmd_none(*pmd)) return; - BUG_ON(!pmd_present(*pmd)); - assert_spin_locked(pte_lockptr(mm, pmd)); + pte = pte_offset_map_nolock(mm, pmd, addr, &ptl); + BUG_ON(!pte); + assert_spin_locked(ptl); + pte_unmap(pte); } #endif /* CONFIG_DEBUG_VM */ diff --git a/arch/powerpc/perf/core-fsl-emb.c b/arch/powerpc/perf/core-fsl-emb.c index ee721f420a7b..1a53ab08447c 100644 --- a/arch/powerpc/perf/core-fsl-emb.c +++ b/arch/powerpc/perf/core-fsl-emb.c @@ -645,7 +645,6 @@ static void perf_event_interrupt(struct pt_regs *regs) struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events); struct perf_event *event; unsigned long val; - int found = 0; for (i = 0; i < ppmu->n_counter; ++i) { event = cpuhw->event[i]; @@ -654,7 +653,6 @@ static void perf_event_interrupt(struct pt_regs *regs) if ((int)val < 0) { if (event) { /* event has overflowed */ - found = 1; record_and_restart(event, val, regs); } else { /* @@ -672,11 +670,13 @@ static void perf_event_interrupt(struct pt_regs *regs) isync(); } -void hw_perf_event_setup(int cpu) +static int fsl_emb_pmu_prepare_cpu(unsigned int cpu) { struct cpu_hw_events *cpuhw = &per_cpu(cpu_hw_events, cpu); memset(cpuhw, 0, sizeof(*cpuhw)); + + return 0; } int register_fsl_emb_pmu(struct fsl_emb_pmu *pmu) @@ -689,6 +689,8 @@ int register_fsl_emb_pmu(struct fsl_emb_pmu *pmu) pmu->name); perf_pmu_register(&fsl_emb_pmu, "cpu", PERF_TYPE_RAW); + cpuhp_setup_state(CPUHP_PERF_POWER, "perf/powerpc:prepare", + fsl_emb_pmu_prepare_cpu, NULL); return 0; } diff --git a/arch/powerpc/perf/hv-gpci.c b/arch/powerpc/perf/hv-gpci.c index 7ff8ff3509f5..39dbe6b348df 100644 --- a/arch/powerpc/perf/hv-gpci.c +++ b/arch/powerpc/perf/hv-gpci.c @@ -102,6 +102,511 @@ static ssize_t cpumask_show(struct device *dev, return cpumap_print_to_pagebuf(true, buf, &hv_gpci_cpumask); } +/* Interface attribute array index to store system information */ +#define INTERFACE_PROCESSOR_BUS_TOPOLOGY_ATTR 6 +#define INTERFACE_PROCESSOR_CONFIG_ATTR 7 +#define INTERFACE_AFFINITY_DOMAIN_VIA_VP_ATTR 8 +#define INTERFACE_AFFINITY_DOMAIN_VIA_DOM_ATTR 9 +#define INTERFACE_AFFINITY_DOMAIN_VIA_PAR_ATTR 10 +#define INTERFACE_NULL_ATTR 11 + +/* Counter request value to retrieve system information */ +enum { + PROCESSOR_BUS_TOPOLOGY, + PROCESSOR_CONFIG, + AFFINITY_DOMAIN_VIA_VP, /* affinity domain via virtual processor */ + AFFINITY_DOMAIN_VIA_DOM, /* affinity domain via domain */ + AFFINITY_DOMAIN_VIA_PAR, /* affinity domain via partition */ +}; + +static int sysinfo_counter_request[] = { + [PROCESSOR_BUS_TOPOLOGY] = 0xD0, + [PROCESSOR_CONFIG] = 0x90, + [AFFINITY_DOMAIN_VIA_VP] = 0xA0, + [AFFINITY_DOMAIN_VIA_DOM] = 0xB0, + [AFFINITY_DOMAIN_VIA_PAR] = 0xB1, +}; + +static DEFINE_PER_CPU(char, hv_gpci_reqb[HGPCI_REQ_BUFFER_SIZE]) __aligned(sizeof(uint64_t)); + +static unsigned long systeminfo_gpci_request(u32 req, u32 starting_index, + u16 secondary_index, char *buf, + size_t *n, struct hv_gpci_request_buffer *arg) +{ + unsigned long ret; + size_t i, j; + + arg->params.counter_request = cpu_to_be32(req); + arg->params.starting_index = cpu_to_be32(starting_index); + arg->params.secondary_index = cpu_to_be16(secondary_index); + + ret = plpar_hcall_norets(H_GET_PERF_COUNTER_INFO, + virt_to_phys(arg), HGPCI_REQ_BUFFER_SIZE); + + /* + * ret value as 'H_PARAMETER' corresponds to 'GEN_BUF_TOO_SMALL', + * which means that the current buffer size cannot accommodate + * all the information and a partial buffer returned. + * hcall fails incase of ret value other than H_SUCCESS or H_PARAMETER. + * + * ret value as H_AUTHORITY implies that partition is not permitted to retrieve + * performance information, and required to set + * "Enable Performance Information Collection" option. + */ + if (ret == H_AUTHORITY) + return -EPERM; + + /* + * hcall can fail with other possible ret value like H_PRIVILEGE/H_HARDWARE + * because of invalid buffer-length/address or due to some hardware + * error. + */ + if (ret && (ret != H_PARAMETER)) + return -EIO; + + /* + * hcall H_GET_PERF_COUNTER_INFO populates the 'returned_values' + * to show the total number of counter_value array elements + * returned via hcall. + * hcall also populates 'cv_element_size' corresponds to individual + * counter_value array element size. Below loop go through all + * counter_value array elements as per their size and add it to + * the output buffer. + */ + for (i = 0; i < be16_to_cpu(arg->params.returned_values); i++) { + j = i * be16_to_cpu(arg->params.cv_element_size); + + for (; j < (i + 1) * be16_to_cpu(arg->params.cv_element_size); j++) + *n += sprintf(buf + *n, "%02x", (u8)arg->bytes[j]); + *n += sprintf(buf + *n, "\n"); + } + + if (*n >= PAGE_SIZE) { + pr_info("System information exceeds PAGE_SIZE\n"); + return -EFBIG; + } + + return ret; +} + +static ssize_t processor_bus_topology_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct hv_gpci_request_buffer *arg; + unsigned long ret; + size_t n = 0; + + arg = (void *)get_cpu_var(hv_gpci_reqb); + memset(arg, 0, HGPCI_REQ_BUFFER_SIZE); + + /* + * Pass the counter request value 0xD0 corresponds to request + * type 'Processor_bus_topology', to retrieve + * the system topology information. + * starting_index value implies the starting hardware + * chip id. + */ + ret = systeminfo_gpci_request(sysinfo_counter_request[PROCESSOR_BUS_TOPOLOGY], + 0, 0, buf, &n, arg); + + if (!ret) + return n; + + if (ret != H_PARAMETER) + goto out; + + /* + * ret value as 'H_PARAMETER' corresponds to 'GEN_BUF_TOO_SMALL', which + * implies that buffer can't accommodate all information, and a partial buffer + * returned. To handle that, we need to make subsequent requests + * with next starting index to retrieve additional (missing) data. + * Below loop do subsequent hcalls with next starting index and add it + * to buffer util we get all the information. + */ + while (ret == H_PARAMETER) { + int returned_values = be16_to_cpu(arg->params.returned_values); + int elementsize = be16_to_cpu(arg->params.cv_element_size); + int last_element = (returned_values - 1) * elementsize; + + /* + * Since the starting index value is part of counter_value + * buffer elements, use the starting index value in the last + * element and add 1 to make subsequent hcalls. + */ + u32 starting_index = arg->bytes[last_element + 3] + + (arg->bytes[last_element + 2] << 8) + + (arg->bytes[last_element + 1] << 16) + + (arg->bytes[last_element] << 24) + 1; + + memset(arg, 0, HGPCI_REQ_BUFFER_SIZE); + + ret = systeminfo_gpci_request(sysinfo_counter_request[PROCESSOR_BUS_TOPOLOGY], + starting_index, 0, buf, &n, arg); + + if (!ret) + return n; + + if (ret != H_PARAMETER) + goto out; + } + + return n; + +out: + put_cpu_var(hv_gpci_reqb); + return ret; +} + +static ssize_t processor_config_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct hv_gpci_request_buffer *arg; + unsigned long ret; + size_t n = 0; + + arg = (void *)get_cpu_var(hv_gpci_reqb); + memset(arg, 0, HGPCI_REQ_BUFFER_SIZE); + + /* + * Pass the counter request value 0x90 corresponds to request + * type 'Processor_config', to retrieve + * the system processor information. + * starting_index value implies the starting hardware + * processor index. + */ + ret = systeminfo_gpci_request(sysinfo_counter_request[PROCESSOR_CONFIG], + 0, 0, buf, &n, arg); + + if (!ret) + return n; + + if (ret != H_PARAMETER) + goto out; + + /* + * ret value as 'H_PARAMETER' corresponds to 'GEN_BUF_TOO_SMALL', which + * implies that buffer can't accommodate all information, and a partial buffer + * returned. To handle that, we need to take subsequent requests + * with next starting index to retrieve additional (missing) data. + * Below loop do subsequent hcalls with next starting index and add it + * to buffer util we get all the information. + */ + while (ret == H_PARAMETER) { + int returned_values = be16_to_cpu(arg->params.returned_values); + int elementsize = be16_to_cpu(arg->params.cv_element_size); + int last_element = (returned_values - 1) * elementsize; + + /* + * Since the starting index is part of counter_value + * buffer elements, use the starting index value in the last + * element and add 1 to subsequent hcalls. + */ + u32 starting_index = arg->bytes[last_element + 3] + + (arg->bytes[last_element + 2] << 8) + + (arg->bytes[last_element + 1] << 16) + + (arg->bytes[last_element] << 24) + 1; + + memset(arg, 0, HGPCI_REQ_BUFFER_SIZE); + + ret = systeminfo_gpci_request(sysinfo_counter_request[PROCESSOR_CONFIG], + starting_index, 0, buf, &n, arg); + + if (!ret) + return n; + + if (ret != H_PARAMETER) + goto out; + } + + return n; + +out: + put_cpu_var(hv_gpci_reqb); + return ret; +} + +static ssize_t affinity_domain_via_virtual_processor_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct hv_gpci_request_buffer *arg; + unsigned long ret; + size_t n = 0; + + arg = (void *)get_cpu_var(hv_gpci_reqb); + memset(arg, 0, HGPCI_REQ_BUFFER_SIZE); + + /* + * Pass the counter request 0xA0 corresponds to request + * type 'Affinity_domain_information_by_virutal_processor', + * to retrieve the system affinity domain information. + * starting_index value refers to the starting hardware + * processor index. + */ + ret = systeminfo_gpci_request(sysinfo_counter_request[AFFINITY_DOMAIN_VIA_VP], + 0, 0, buf, &n, arg); + + if (!ret) + return n; + + if (ret != H_PARAMETER) + goto out; + + /* + * ret value as 'H_PARAMETER' corresponds to 'GEN_BUF_TOO_SMALL', which + * implies that buffer can't accommodate all information, and a partial buffer + * returned. To handle that, we need to take subsequent requests + * with next secondary index to retrieve additional (missing) data. + * Below loop do subsequent hcalls with next secondary index and add it + * to buffer util we get all the information. + */ + while (ret == H_PARAMETER) { + int returned_values = be16_to_cpu(arg->params.returned_values); + int elementsize = be16_to_cpu(arg->params.cv_element_size); + int last_element = (returned_values - 1) * elementsize; + + /* + * Since the starting index and secondary index type is part of the + * counter_value buffer elements, use the starting index value in the + * last array element as subsequent starting index, and use secondary index + * value in the last array element plus 1 as subsequent secondary index. + * For counter request '0xA0', starting index points to partition id + * and secondary index points to corresponding virtual processor index. + */ + u32 starting_index = arg->bytes[last_element + 1] + (arg->bytes[last_element] << 8); + u16 secondary_index = arg->bytes[last_element + 3] + + (arg->bytes[last_element + 2] << 8) + 1; + + memset(arg, 0, HGPCI_REQ_BUFFER_SIZE); + + ret = systeminfo_gpci_request(sysinfo_counter_request[AFFINITY_DOMAIN_VIA_VP], + starting_index, secondary_index, buf, &n, arg); + + if (!ret) + return n; + + if (ret != H_PARAMETER) + goto out; + } + + return n; + +out: + put_cpu_var(hv_gpci_reqb); + return ret; +} + +static ssize_t affinity_domain_via_domain_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct hv_gpci_request_buffer *arg; + unsigned long ret; + size_t n = 0; + + arg = (void *)get_cpu_var(hv_gpci_reqb); + memset(arg, 0, HGPCI_REQ_BUFFER_SIZE); + + /* + * Pass the counter request 0xB0 corresponds to request + * type 'Affinity_domain_information_by_domain', + * to retrieve the system affinity domain information. + * starting_index value refers to the starting hardware + * processor index. + */ + ret = systeminfo_gpci_request(sysinfo_counter_request[AFFINITY_DOMAIN_VIA_DOM], + 0, 0, buf, &n, arg); + + if (!ret) + return n; + + if (ret != H_PARAMETER) + goto out; + + /* + * ret value as 'H_PARAMETER' corresponds to 'GEN_BUF_TOO_SMALL', which + * implies that buffer can't accommodate all information, and a partial buffer + * returned. To handle that, we need to take subsequent requests + * with next starting index to retrieve additional (missing) data. + * Below loop do subsequent hcalls with next starting index and add it + * to buffer util we get all the information. + */ + while (ret == H_PARAMETER) { + int returned_values = be16_to_cpu(arg->params.returned_values); + int elementsize = be16_to_cpu(arg->params.cv_element_size); + int last_element = (returned_values - 1) * elementsize; + + /* + * Since the starting index value is part of counter_value + * buffer elements, use the starting index value in the last + * element and add 1 to make subsequent hcalls. + */ + u32 starting_index = arg->bytes[last_element + 1] + + (arg->bytes[last_element] << 8) + 1; + + memset(arg, 0, HGPCI_REQ_BUFFER_SIZE); + + ret = systeminfo_gpci_request(sysinfo_counter_request[AFFINITY_DOMAIN_VIA_DOM], + starting_index, 0, buf, &n, arg); + + if (!ret) + return n; + + if (ret != H_PARAMETER) + goto out; + } + + return n; + +out: + put_cpu_var(hv_gpci_reqb); + return ret; +} + +static void affinity_domain_via_partition_result_parse(int returned_values, + int element_size, char *buf, size_t *last_element, + size_t *n, struct hv_gpci_request_buffer *arg) +{ + size_t i = 0, j = 0; + size_t k, l, m; + uint16_t total_affinity_domain_ele, size_of_each_affinity_domain_ele; + + /* + * hcall H_GET_PERF_COUNTER_INFO populates the 'returned_values' + * to show the total number of counter_value array elements + * returned via hcall. + * Unlike other request types, the data structure returned by this + * request is variable-size. For this counter request type, + * hcall populates 'cv_element_size' corresponds to minimum size of + * the structure returned i.e; the size of the structure with no domain + * information. Below loop go through all counter_value array + * to determine the number and size of each domain array element and + * add it to the output buffer. + */ + while (i < returned_values) { + k = j; + for (; k < j + element_size; k++) + *n += sprintf(buf + *n, "%02x", (u8)arg->bytes[k]); + *n += sprintf(buf + *n, "\n"); + + total_affinity_domain_ele = (u8)arg->bytes[k - 2] << 8 | (u8)arg->bytes[k - 3]; + size_of_each_affinity_domain_ele = (u8)arg->bytes[k] << 8 | (u8)arg->bytes[k - 1]; + + for (l = 0; l < total_affinity_domain_ele; l++) { + for (m = 0; m < size_of_each_affinity_domain_ele; m++) { + *n += sprintf(buf + *n, "%02x", (u8)arg->bytes[k]); + k++; + } + *n += sprintf(buf + *n, "\n"); + } + + *n += sprintf(buf + *n, "\n"); + i++; + j = k; + } + + *last_element = k; +} + +static ssize_t affinity_domain_via_partition_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct hv_gpci_request_buffer *arg; + unsigned long ret; + size_t n = 0; + size_t last_element = 0; + u32 starting_index; + + arg = (void *)get_cpu_var(hv_gpci_reqb); + memset(arg, 0, HGPCI_REQ_BUFFER_SIZE); + + /* + * Pass the counter request value 0xB1 corresponds to counter request + * type 'Affinity_domain_information_by_partition', + * to retrieve the system affinity domain by partition information. + * starting_index value refers to the starting hardware + * processor index. + */ + arg->params.counter_request = cpu_to_be32(sysinfo_counter_request[AFFINITY_DOMAIN_VIA_PAR]); + arg->params.starting_index = cpu_to_be32(0); + + ret = plpar_hcall_norets(H_GET_PERF_COUNTER_INFO, + virt_to_phys(arg), HGPCI_REQ_BUFFER_SIZE); + + if (!ret) + goto parse_result; + + /* + * ret value as 'H_PARAMETER' implies that the current buffer size + * can't accommodate all the information, and a partial buffer + * returned. To handle that, we need to make subsequent requests + * with next starting index to retrieve additional (missing) data. + * Below loop do subsequent hcalls with next starting index and add it + * to buffer util we get all the information. + */ + while (ret == H_PARAMETER) { + affinity_domain_via_partition_result_parse( + be16_to_cpu(arg->params.returned_values) - 1, + be16_to_cpu(arg->params.cv_element_size), buf, + &last_element, &n, arg); + + if (n >= PAGE_SIZE) { + put_cpu_var(hv_gpci_reqb); + pr_debug("System information exceeds PAGE_SIZE\n"); + return -EFBIG; + } + + /* + * Since the starting index value is part of counter_value + * buffer elements, use the starting_index value in the last + * element and add 1 to make subsequent hcalls. + */ + starting_index = (u8)arg->bytes[last_element] << 8 | + (u8)arg->bytes[last_element + 1]; + + memset(arg, 0, HGPCI_REQ_BUFFER_SIZE); + arg->params.counter_request = cpu_to_be32( + sysinfo_counter_request[AFFINITY_DOMAIN_VIA_PAR]); + arg->params.starting_index = cpu_to_be32(starting_index); + + ret = plpar_hcall_norets(H_GET_PERF_COUNTER_INFO, + virt_to_phys(arg), HGPCI_REQ_BUFFER_SIZE); + + if (ret && (ret != H_PARAMETER)) + goto out; + } + +parse_result: + affinity_domain_via_partition_result_parse( + be16_to_cpu(arg->params.returned_values), + be16_to_cpu(arg->params.cv_element_size), + buf, &last_element, &n, arg); + + put_cpu_var(hv_gpci_reqb); + return n; + +out: + put_cpu_var(hv_gpci_reqb); + + /* + * ret value as 'H_PARAMETER' corresponds to 'GEN_BUF_TOO_SMALL', + * which means that the current buffer size cannot accommodate + * all the information and a partial buffer returned. + * hcall fails incase of ret value other than H_SUCCESS or H_PARAMETER. + * + * ret value as H_AUTHORITY implies that partition is not permitted to retrieve + * performance information, and required to set + * "Enable Performance Information Collection" option. + */ + if (ret == H_AUTHORITY) + return -EPERM; + + /* + * hcall can fail with other possible ret value like H_PRIVILEGE/H_HARDWARE + * because of invalid buffer-length/address or due to some hardware + * error. + */ + return -EIO; +} + static DEVICE_ATTR_RO(kernel_version); static DEVICE_ATTR_RO(cpumask); @@ -118,6 +623,31 @@ static struct attribute *interface_attrs[] = { &hv_caps_attr_expanded.attr, &hv_caps_attr_lab.attr, &hv_caps_attr_collect_privileged.attr, + /* + * This NULL is a placeholder for the processor_bus_topology + * attribute, set in init function if applicable. + */ + NULL, + /* + * This NULL is a placeholder for the processor_config + * attribute, set in init function if applicable. + */ + NULL, + /* + * This NULL is a placeholder for the affinity_domain_via_virtual_processor + * attribute, set in init function if applicable. + */ + NULL, + /* + * This NULL is a placeholder for the affinity_domain_via_domain + * attribute, set in init function if applicable. + */ + NULL, + /* + * This NULL is a placeholder for the affinity_domain_via_partition + * attribute, set in init function if applicable. + */ + NULL, NULL, }; @@ -143,8 +673,6 @@ static const struct attribute_group *attr_groups[] = { NULL, }; -static DEFINE_PER_CPU(char, hv_gpci_reqb[HGPCI_REQ_BUFFER_SIZE]) __aligned(sizeof(uint64_t)); - static unsigned long single_gpci_request(u32 req, u32 starting_index, u16 secondary_index, u8 version_in, u32 offset, u8 length, u64 *value) @@ -325,6 +853,107 @@ static int hv_gpci_cpu_hotplug_init(void) ppc_hv_gpci_cpu_offline); } +static struct device_attribute *sysinfo_device_attr_create(int + sysinfo_interface_group_index, u32 req) +{ + struct device_attribute *attr = NULL; + unsigned long ret; + struct hv_gpci_request_buffer *arg; + + if (sysinfo_interface_group_index < INTERFACE_PROCESSOR_BUS_TOPOLOGY_ATTR || + sysinfo_interface_group_index >= INTERFACE_NULL_ATTR) { + pr_info("Wrong interface group index for system information\n"); + return NULL; + } + + /* Check for given counter request value support */ + arg = (void *)get_cpu_var(hv_gpci_reqb); + memset(arg, 0, HGPCI_REQ_BUFFER_SIZE); + + arg->params.counter_request = cpu_to_be32(req); + + ret = plpar_hcall_norets(H_GET_PERF_COUNTER_INFO, + virt_to_phys(arg), HGPCI_REQ_BUFFER_SIZE); + + put_cpu_var(hv_gpci_reqb); + + /* + * Add given counter request value attribute in the interface_attrs + * attribute array, only for valid return types. + */ + if (!ret || ret == H_AUTHORITY || ret == H_PARAMETER) { + attr = kzalloc(sizeof(*attr), GFP_KERNEL); + if (!attr) + return NULL; + + sysfs_attr_init(&attr->attr); + attr->attr.mode = 0444; + + switch (sysinfo_interface_group_index) { + case INTERFACE_PROCESSOR_BUS_TOPOLOGY_ATTR: + attr->attr.name = "processor_bus_topology"; + attr->show = processor_bus_topology_show; + break; + case INTERFACE_PROCESSOR_CONFIG_ATTR: + attr->attr.name = "processor_config"; + attr->show = processor_config_show; + break; + case INTERFACE_AFFINITY_DOMAIN_VIA_VP_ATTR: + attr->attr.name = "affinity_domain_via_virtual_processor"; + attr->show = affinity_domain_via_virtual_processor_show; + break; + case INTERFACE_AFFINITY_DOMAIN_VIA_DOM_ATTR: + attr->attr.name = "affinity_domain_via_domain"; + attr->show = affinity_domain_via_domain_show; + break; + case INTERFACE_AFFINITY_DOMAIN_VIA_PAR_ATTR: + attr->attr.name = "affinity_domain_via_partition"; + attr->show = affinity_domain_via_partition_show; + break; + } + } else + pr_devel("hcall failed, with error: 0x%lx\n", ret); + + return attr; +} + +static void add_sysinfo_interface_files(void) +{ + int sysfs_count; + struct device_attribute *attr[INTERFACE_NULL_ATTR - INTERFACE_PROCESSOR_BUS_TOPOLOGY_ATTR]; + int i; + + sysfs_count = INTERFACE_NULL_ATTR - INTERFACE_PROCESSOR_BUS_TOPOLOGY_ATTR; + + /* Get device attribute for a given counter request value */ + for (i = 0; i < sysfs_count; i++) { + attr[i] = sysinfo_device_attr_create(i + INTERFACE_PROCESSOR_BUS_TOPOLOGY_ATTR, + sysinfo_counter_request[i]); + + if (!attr[i]) + goto out; + } + + /* Add sysinfo interface attributes in the interface_attrs attribute array */ + for (i = 0; i < sysfs_count; i++) + interface_attrs[i + INTERFACE_PROCESSOR_BUS_TOPOLOGY_ATTR] = &attr[i]->attr; + + return; + +out: + /* + * The sysinfo interface attributes will be added, only if hcall passed for + * all the counter request values. Free the device attribute array incase + * of any hcall failure. + */ + if (i > 0) { + while (i >= 0) { + kfree(attr[i]); + i--; + } + } +} + static int hv_gpci_init(void) { int r; @@ -388,6 +1017,10 @@ static int hv_gpci_init(void) if (r) return r; + /* sysinfo interface files are only available for power10 and above platforms */ + if (PVR_VER(mfspr(SPRN_PVR)) >= PVR_POWER10) + add_sysinfo_interface_files(); + return 0; } diff --git a/arch/powerpc/platforms/44x/warp.c b/arch/powerpc/platforms/44x/warp.c index bfeb9bdc3258..bf0188dcb918 100644 --- a/arch/powerpc/platforms/44x/warp.c +++ b/arch/powerpc/platforms/44x/warp.c @@ -83,45 +83,8 @@ static int __init warp_post_info(void) #ifdef CONFIG_SENSORS_AD7414 -static LIST_HEAD(dtm_shutdown_list); static void __iomem *dtm_fpga; -struct dtm_shutdown { - struct list_head list; - void (*func)(void *arg); - void *arg; -}; - -int pika_dtm_register_shutdown(void (*func)(void *arg), void *arg) -{ - struct dtm_shutdown *shutdown; - - shutdown = kmalloc(sizeof(struct dtm_shutdown), GFP_KERNEL); - if (shutdown == NULL) - return -ENOMEM; - - shutdown->func = func; - shutdown->arg = arg; - - list_add(&shutdown->list, &dtm_shutdown_list); - - return 0; -} - -int pika_dtm_unregister_shutdown(void (*func)(void *arg), void *arg) -{ - struct dtm_shutdown *shutdown; - - list_for_each_entry(shutdown, &dtm_shutdown_list, list) - if (shutdown->func == func && shutdown->arg == arg) { - list_del(&shutdown->list); - kfree(shutdown); - return 0; - } - - return -EINVAL; -} - #define WARP_GREEN_LED 0 #define WARP_RED_LED 1 @@ -153,17 +116,12 @@ static struct platform_device warp_gpio_leds = { static irqreturn_t temp_isr(int irq, void *context) { - struct dtm_shutdown *shutdown; int value = 1; local_irq_disable(); gpiod_set_value(warp_gpio_led_pins[WARP_GREEN_LED].gpiod, 0); - /* Run through the shutdown list. */ - list_for_each_entry(shutdown, &dtm_shutdown_list, list) - shutdown->func(shutdown->arg); - printk(KERN_EMERG "\n\nCritical Temperature Shutdown\n\n"); while (1) { @@ -366,19 +324,6 @@ machine_late_initcall(warp, pika_dtm_start); #else /* !CONFIG_SENSORS_AD7414 */ -int pika_dtm_register_shutdown(void (*func)(void *arg), void *arg) -{ - return 0; -} - -int pika_dtm_unregister_shutdown(void (*func)(void *arg), void *arg) -{ - return 0; -} - machine_late_initcall(warp, warp_post_info); #endif - -EXPORT_SYMBOL(pika_dtm_register_shutdown); -EXPORT_SYMBOL(pika_dtm_unregister_shutdown); diff --git a/arch/powerpc/platforms/4xx/cpm.c b/arch/powerpc/platforms/4xx/cpm.c index 182e12855c27..670f8ad4465b 100644 --- a/arch/powerpc/platforms/4xx/cpm.c +++ b/arch/powerpc/platforms/4xx/cpm.c @@ -18,7 +18,7 @@ */ #include <linux/kernel.h> -#include <linux/of_platform.h> +#include <linux/of.h> #include <linux/sysfs.h> #include <linux/cpu.h> #include <linux/suspend.h> diff --git a/arch/powerpc/platforms/4xx/hsta_msi.c b/arch/powerpc/platforms/4xx/hsta_msi.c index e11b57a62b05..c6bd846b0d65 100644 --- a/arch/powerpc/platforms/4xx/hsta_msi.c +++ b/arch/powerpc/platforms/4xx/hsta_msi.c @@ -11,7 +11,7 @@ #include <linux/msi.h> #include <linux/of.h> #include <linux/of_irq.h> -#include <linux/of_platform.h> +#include <linux/platform_device.h> #include <linux/pci.h> #include <linux/semaphore.h> #include <asm/msi_bitmap.h> diff --git a/arch/powerpc/platforms/4xx/soc.c b/arch/powerpc/platforms/4xx/soc.c index ac1cd8b17879..b2d940437a66 100644 --- a/arch/powerpc/platforms/4xx/soc.c +++ b/arch/powerpc/platforms/4xx/soc.c @@ -15,12 +15,13 @@ #include <linux/errno.h> #include <linux/interrupt.h> #include <linux/irq.h> +#include <linux/of.h> #include <linux/of_irq.h> -#include <linux/of_platform.h> #include <asm/dcr.h> #include <asm/dcr-regs.h> #include <asm/reg.h> +#include <asm/ppc4xx.h> static u32 dcrbase_l2c; diff --git a/arch/powerpc/platforms/4xx/uic.c b/arch/powerpc/platforms/4xx/uic.c index d667ad039bd3..e3e148b9dd18 100644 --- a/arch/powerpc/platforms/4xx/uic.c +++ b/arch/powerpc/platforms/4xx/uic.c @@ -24,6 +24,7 @@ #include <asm/irq.h> #include <asm/io.h> #include <asm/dcr.h> +#include <asm/uic.h> #define NR_UIC_INTS 32 diff --git a/arch/powerpc/platforms/512x/mpc5121_ads.c b/arch/powerpc/platforms/512x/mpc5121_ads.c index 80b25ce076bc..a18f85b3ef36 100644 --- a/arch/powerpc/platforms/512x/mpc5121_ads.c +++ b/arch/powerpc/platforms/512x/mpc5121_ads.c @@ -10,7 +10,7 @@ #include <linux/kernel.h> #include <linux/io.h> -#include <linux/of_platform.h> +#include <linux/of.h> #include <asm/machdep.h> #include <asm/ipic.h> diff --git a/arch/powerpc/platforms/512x/mpc512x.h b/arch/powerpc/platforms/512x/mpc512x.h index 2f3c60e373e1..d2cb06e3a436 100644 --- a/arch/powerpc/platforms/512x/mpc512x.h +++ b/arch/powerpc/platforms/512x/mpc512x.h @@ -13,7 +13,6 @@ extern void __init mpc512x_init(void); extern void __init mpc512x_setup_arch(void); extern int __init mpc5121_clk_init(void); const char *__init mpc512x_select_psc_compat(void); -const char *__init mpc512x_select_reset_compat(void); extern void __noreturn mpc512x_restart(char *cmd); #endif /* __MPC512X_H__ */ diff --git a/arch/powerpc/platforms/512x/mpc512x_generic.c b/arch/powerpc/platforms/512x/mpc512x_generic.c index 97dfaac8f7ff..0d58ab257cd9 100644 --- a/arch/powerpc/platforms/512x/mpc512x_generic.c +++ b/arch/powerpc/platforms/512x/mpc512x_generic.c @@ -9,7 +9,7 @@ */ #include <linux/kernel.h> -#include <linux/of_platform.h> +#include <linux/of.h> #include <asm/machdep.h> #include <asm/ipic.h> diff --git a/arch/powerpc/platforms/512x/mpc512x_lpbfifo.c b/arch/powerpc/platforms/512x/mpc512x_lpbfifo.c index c1e981649bd9..4a25b6b48615 100644 --- a/arch/powerpc/platforms/512x/mpc512x_lpbfifo.c +++ b/arch/powerpc/platforms/512x/mpc512x_lpbfifo.c @@ -10,9 +10,9 @@ #include <linux/kernel.h> #include <linux/module.h> #include <linux/of.h> -#include <linux/of_platform.h> #include <linux/of_address.h> #include <linux/of_irq.h> +#include <linux/platform_device.h> #include <asm/mpc5121.h> #include <asm/io.h> #include <linux/spinlock.h> diff --git a/arch/powerpc/platforms/512x/mpc512x_shared.c b/arch/powerpc/platforms/512x/mpc512x_shared.c index 5ac0ead2540f..8f75e9574c27 100644 --- a/arch/powerpc/platforms/512x/mpc512x_shared.c +++ b/arch/powerpc/platforms/512x/mpc512x_shared.c @@ -29,20 +29,6 @@ static struct mpc512x_reset_module __iomem *reset_module_base; -static void __init mpc512x_restart_init(void) -{ - struct device_node *np; - const char *reset_compat; - - reset_compat = mpc512x_select_reset_compat(); - np = of_find_compatible_node(NULL, NULL, reset_compat); - if (!np) - return; - - reset_module_base = of_iomap(np, 0); - of_node_put(np); -} - void __noreturn mpc512x_restart(char *cmd) { if (reset_module_base) { @@ -363,7 +349,7 @@ const char *__init mpc512x_select_psc_compat(void) return NULL; } -const char *__init mpc512x_select_reset_compat(void) +static const char *__init mpc512x_select_reset_compat(void) { if (of_machine_is_compatible("fsl,mpc5121")) return "fsl,mpc5121-reset"; @@ -455,6 +441,20 @@ static void __init mpc512x_psc_fifo_init(void) } } +static void __init mpc512x_restart_init(void) +{ + struct device_node *np; + const char *reset_compat; + + reset_compat = mpc512x_select_reset_compat(); + np = of_find_compatible_node(NULL, NULL, reset_compat); + if (!np) + return; + + reset_module_base = of_iomap(np, 0); + of_node_put(np); +} + void __init mpc512x_init_early(void) { mpc512x_restart_init(); diff --git a/arch/powerpc/platforms/512x/pdm360ng.c b/arch/powerpc/platforms/512x/pdm360ng.c index 4bdec1c25de7..ce51cfeeb066 100644 --- a/arch/powerpc/platforms/512x/pdm360ng.c +++ b/arch/powerpc/platforms/512x/pdm360ng.c @@ -7,11 +7,12 @@ * PDM360NG board setup */ +#include <linux/device.h> #include <linux/kernel.h> #include <linux/io.h> +#include <linux/of.h> #include <linux/of_address.h> #include <linux/of_fdt.h> -#include <linux/of_platform.h> #include <asm/machdep.h> #include <asm/ipic.h> diff --git a/arch/powerpc/platforms/52xx/mpc52xx_gpt.c b/arch/powerpc/platforms/52xx/mpc52xx_gpt.c index 3fce4e1c3af6..581059527c36 100644 --- a/arch/powerpc/platforms/52xx/mpc52xx_gpt.c +++ b/arch/powerpc/platforms/52xx/mpc52xx_gpt.c @@ -48,7 +48,6 @@ * the output mode. This driver does not change the output mode setting. */ -#include <linux/device.h> #include <linux/irq.h> #include <linux/interrupt.h> #include <linux/io.h> @@ -57,8 +56,8 @@ #include <linux/of.h> #include <linux/of_address.h> #include <linux/of_irq.h> -#include <linux/of_platform.h> #include <linux/of_gpio.h> +#include <linux/platform_device.h> #include <linux/kernel.h> #include <linux/property.h> #include <linux/slab.h> diff --git a/arch/powerpc/platforms/82xx/Kconfig b/arch/powerpc/platforms/82xx/Kconfig index 4eb372bdab70..d9f1a2a83158 100644 --- a/arch/powerpc/platforms/82xx/Kconfig +++ b/arch/powerpc/platforms/82xx/Kconfig @@ -7,8 +7,8 @@ if PPC_82xx config EP8248E bool "Embedded Planet EP8248E (a.k.a. CWH-PPC-8248N-VE)" - select 8272 - select 8260 + select CPM2 + select PPC_INDIRECT_PCI if PCI select FSL_SOC select PHYLIB if NETDEVICES select MDIO_BITBANG if PHYLIB @@ -20,26 +20,10 @@ config EP8248E config MGCOGE bool "Keymile MGCOGE" - select 8272 - select 8260 + select CPM2 + select PPC_INDIRECT_PCI if PCI select FSL_SOC help This enables support for the Keymile MGCOGE board. endif - -config 8260 - bool - depends on PPC_BOOK3S_32 - select CPM2 - help - The MPC8260 is a typical embedded CPU made by Freescale. Selecting - this option means that you wish to build a kernel for a machine with - an 8260 class CPU. - -config 8272 - bool - select 8260 - help - The MPC8272 CPM has a different internal dpram setup than other CPM2 - devices diff --git a/arch/powerpc/platforms/82xx/ep8248e.c b/arch/powerpc/platforms/82xx/ep8248e.c index 8f1856ba692e..3dc65ce1f175 100644 --- a/arch/powerpc/platforms/82xx/ep8248e.c +++ b/arch/powerpc/platforms/82xx/ep8248e.c @@ -13,13 +13,13 @@ #include <linux/of_mdio.h> #include <linux/slab.h> #include <linux/of_platform.h> +#include <linux/platform_device.h> #include <asm/io.h> #include <asm/cpm2.h> #include <asm/udbg.h> #include <asm/machdep.h> #include <asm/time.h> -#include <asm/mpc8260.h> #include <sysdev/fsl_soc.h> #include <sysdev/cpm2_pic.h> @@ -140,12 +140,6 @@ err_free_bus: return ret; } -static int ep8248e_mdio_remove(struct platform_device *ofdev) -{ - BUG(); - return 0; -} - static const struct of_device_id ep8248e_mdio_match[] = { { .compatible = "fsl,ep8248e-mdio-bitbang", @@ -157,9 +151,9 @@ static struct platform_driver ep8248e_mdio_driver = { .driver = { .name = "ep8248e-mdio-bitbang", .of_match_table = ep8248e_mdio_match, + .suppress_bind_attrs = true, }, .probe = ep8248e_mdio_probe, - .remove = ep8248e_mdio_remove, }; struct cpm_pin { diff --git a/arch/powerpc/platforms/82xx/km82xx.c b/arch/powerpc/platforms/82xx/km82xx.c index 51c9bfd97592..c86da3f2b74b 100644 --- a/arch/powerpc/platforms/82xx/km82xx.c +++ b/arch/powerpc/platforms/82xx/km82xx.c @@ -19,7 +19,6 @@ #include <asm/udbg.h> #include <asm/machdep.h> #include <linux/time.h> -#include <asm/mpc8260.h> #include <sysdev/fsl_soc.h> #include <sysdev/cpm2_pic.h> diff --git a/arch/powerpc/platforms/82xx/m82xx_pci.h b/arch/powerpc/platforms/82xx/m82xx_pci.h deleted file mode 100644 index d07c4d7606f6..000000000000 --- a/arch/powerpc/platforms/82xx/m82xx_pci.h +++ /dev/null @@ -1,14 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -#ifndef _PPC_KERNEL_M82XX_PCI_H -#define _PPC_KERNEL_M82XX_PCI_H - -/* - */ - -#define SIU_INT_IRQ1 ((uint)0x13 + CPM_IRQ_OFFSET) - -#ifndef _IO_BASE -#define _IO_BASE isa_io_base -#endif - -#endif /* _PPC_KERNEL_M8260_PCI_H */ diff --git a/arch/powerpc/platforms/82xx/pq2.c b/arch/powerpc/platforms/82xx/pq2.c index 3b5cb39a564c..391d72a2e09d 100644 --- a/arch/powerpc/platforms/82xx/pq2.c +++ b/arch/powerpc/platforms/82xx/pq2.c @@ -32,49 +32,3 @@ void __noreturn pq2_restart(char *cmd) panic("Restart failed\n"); } NOKPROBE_SYMBOL(pq2_restart) - -#ifdef CONFIG_PCI -static int pq2_pci_exclude_device(struct pci_controller *hose, - u_char bus, u8 devfn) -{ - if (bus == 0 && PCI_SLOT(devfn) == 0) - return PCIBIOS_DEVICE_NOT_FOUND; - else - return PCIBIOS_SUCCESSFUL; -} - -static void __init pq2_pci_add_bridge(struct device_node *np) -{ - struct pci_controller *hose; - struct resource r; - - if (of_address_to_resource(np, 0, &r) || r.end - r.start < 0x10b) - goto err; - - pci_add_flags(PCI_REASSIGN_ALL_BUS); - - hose = pcibios_alloc_controller(np); - if (!hose) - return; - - hose->dn = np; - - setup_indirect_pci(hose, r.start + 0x100, r.start + 0x104, 0); - pci_process_bridge_OF_ranges(hose, np, 1); - - return; - -err: - printk(KERN_ERR "No valid PCI reg property in device tree\n"); -} - -void __init pq2_init_pci(void) -{ - struct device_node *np; - - ppc_md.pci_exclude_device = pq2_pci_exclude_device; - - for_each_compatible_node(np, NULL, "fsl,pq2-pci") - pq2_pci_add_bridge(np); -} -#endif diff --git a/arch/powerpc/platforms/83xx/Makefile b/arch/powerpc/platforms/83xx/Makefile index 6b4013e01b3b..6fc3dba943da 100644 --- a/arch/powerpc/platforms/83xx/Makefile +++ b/arch/powerpc/platforms/83xx/Makefile @@ -2,7 +2,7 @@ # # Makefile for the PowerPC 83xx linux kernel. # -obj-y := misc.o usb.o +obj-y := misc.o obj-$(CONFIG_SUSPEND) += suspend.o suspend-asm.o obj-$(CONFIG_MCU_MPC8349EMITX) += mcu_mpc8349emitx.o obj-$(CONFIG_MPC830x_RDB) += mpc830x_rdb.o @@ -13,3 +13,6 @@ obj-$(CONFIG_MPC836x_RDK) += mpc836x_rdk.o obj-$(CONFIG_MPC837x_RDB) += mpc837x_rdb.o obj-$(CONFIG_ASP834x) += asp834x.o obj-$(CONFIG_KMETER1) += km83xx.o +obj-$(CONFIG_PPC_MPC831x) += usb_831x.o +obj-$(CONFIG_PPC_MPC834x) += usb_834x.o +obj-$(CONFIG_PPC_MPC837x) += usb_837x.o diff --git a/arch/powerpc/platforms/83xx/km83xx.c b/arch/powerpc/platforms/83xx/km83xx.c index 26ddc7136547..2b5d187d9b62 100644 --- a/arch/powerpc/platforms/83xx/km83xx.c +++ b/arch/powerpc/platforms/83xx/km83xx.c @@ -20,8 +20,8 @@ #include <linux/seq_file.h> #include <linux/root_dev.h> #include <linux/initrd.h> -#include <linux/of_platform.h> -#include <linux/of_device.h> +#include <linux/of.h> +#include <linux/of_address.h> #include <linux/atomic.h> #include <linux/time.h> diff --git a/arch/powerpc/platforms/83xx/mpc832x_rdb.c b/arch/powerpc/platforms/83xx/mpc832x_rdb.c index 3b4e4173c59e..d523ce0f48db 100644 --- a/arch/powerpc/platforms/83xx/mpc832x_rdb.c +++ b/arch/powerpc/platforms/83xx/mpc832x_rdb.c @@ -15,8 +15,10 @@ #include <linux/spi/spi.h> #include <linux/spi/mmc_spi.h> #include <linux/mmc/host.h> +#include <linux/of.h> +#include <linux/of_address.h> #include <linux/of_irq.h> -#include <linux/of_platform.h> +#include <linux/platform_device.h> #include <linux/fsl_devices.h> #include <asm/time.h> diff --git a/arch/powerpc/platforms/83xx/mpc83xx.h b/arch/powerpc/platforms/83xx/mpc83xx.h index aea803ba3a15..0b8738a2b980 100644 --- a/arch/powerpc/platforms/83xx/mpc83xx.h +++ b/arch/powerpc/platforms/83xx/mpc83xx.h @@ -3,8 +3,6 @@ #define __MPC83XX_H__ #include <linux/init.h> -#include <linux/device.h> -#include <asm/pci-bridge.h> /* System Clock Control Register */ #define MPC83XX_SCCR_OFFS 0xA08 diff --git a/arch/powerpc/platforms/83xx/suspend.c b/arch/powerpc/platforms/83xx/suspend.c index 3fa8979ac8a6..9833c36bda83 100644 --- a/arch/powerpc/platforms/83xx/suspend.c +++ b/arch/powerpc/platforms/83xx/suspend.c @@ -19,7 +19,7 @@ #include <linux/fsl_devices.h> #include <linux/of_address.h> #include <linux/of_irq.h> -#include <linux/of_platform.h> +#include <linux/platform_device.h> #include <linux/export.h> #include <asm/reg.h> diff --git a/arch/powerpc/platforms/83xx/usb.c b/arch/powerpc/platforms/83xx/usb.c deleted file mode 100644 index e2a13a052f96..000000000000 --- a/arch/powerpc/platforms/83xx/usb.c +++ /dev/null @@ -1,251 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * Freescale 83xx USB SOC setup code - * - * Copyright (C) 2007 Freescale Semiconductor, Inc. - * Author: Li Yang - */ - - -#include <linux/stddef.h> -#include <linux/kernel.h> -#include <linux/errno.h> -#include <linux/of.h> -#include <linux/of_address.h> - -#include <asm/io.h> -#include <sysdev/fsl_soc.h> - -#include "mpc83xx.h" - - -#ifdef CONFIG_PPC_MPC834x -int __init mpc834x_usb_cfg(void) -{ - unsigned long sccr, sicrl, sicrh; - void __iomem *immap; - struct device_node *np = NULL; - int port0_is_dr = 0, port1_is_dr = 0; - const void *prop, *dr_mode; - - immap = ioremap(get_immrbase(), 0x1000); - if (!immap) - return -ENOMEM; - - /* Read registers */ - /* Note: DR and MPH must use the same clock setting in SCCR */ - sccr = in_be32(immap + MPC83XX_SCCR_OFFS) & ~MPC83XX_SCCR_USB_MASK; - sicrl = in_be32(immap + MPC83XX_SICRL_OFFS) & ~MPC834X_SICRL_USB_MASK; - sicrh = in_be32(immap + MPC83XX_SICRH_OFFS) & ~MPC834X_SICRH_USB_UTMI; - - np = of_find_compatible_node(NULL, NULL, "fsl-usb2-dr"); - if (np) { - sccr |= MPC83XX_SCCR_USB_DRCM_11; /* 1:3 */ - - prop = of_get_property(np, "phy_type", NULL); - port1_is_dr = 1; - if (prop && (!strcmp(prop, "utmi") || - !strcmp(prop, "utmi_wide"))) { - sicrl |= MPC834X_SICRL_USB0 | MPC834X_SICRL_USB1; - sicrh |= MPC834X_SICRH_USB_UTMI; - port0_is_dr = 1; - } else if (prop && !strcmp(prop, "serial")) { - dr_mode = of_get_property(np, "dr_mode", NULL); - if (dr_mode && !strcmp(dr_mode, "otg")) { - sicrl |= MPC834X_SICRL_USB0 | MPC834X_SICRL_USB1; - port0_is_dr = 1; - } else { - sicrl |= MPC834X_SICRL_USB1; - } - } else if (prop && !strcmp(prop, "ulpi")) { - sicrl |= MPC834X_SICRL_USB1; - } else { - printk(KERN_WARNING "834x USB PHY type not supported\n"); - } - of_node_put(np); - } - np = of_find_compatible_node(NULL, NULL, "fsl-usb2-mph"); - if (np) { - sccr |= MPC83XX_SCCR_USB_MPHCM_11; /* 1:3 */ - - prop = of_get_property(np, "port0", NULL); - if (prop) { - if (port0_is_dr) - printk(KERN_WARNING - "834x USB port0 can't be used by both DR and MPH!\n"); - sicrl &= ~MPC834X_SICRL_USB0; - } - prop = of_get_property(np, "port1", NULL); - if (prop) { - if (port1_is_dr) - printk(KERN_WARNING - "834x USB port1 can't be used by both DR and MPH!\n"); - sicrl &= ~MPC834X_SICRL_USB1; - } - of_node_put(np); - } - - /* Write back */ - out_be32(immap + MPC83XX_SCCR_OFFS, sccr); - out_be32(immap + MPC83XX_SICRL_OFFS, sicrl); - out_be32(immap + MPC83XX_SICRH_OFFS, sicrh); - - iounmap(immap); - return 0; -} -#endif /* CONFIG_PPC_MPC834x */ - -#ifdef CONFIG_PPC_MPC831x -int __init mpc831x_usb_cfg(void) -{ - u32 temp; - void __iomem *immap, *usb_regs; - struct device_node *np = NULL; - struct device_node *immr_node = NULL; - const void *prop; - struct resource res; - int ret = 0; -#ifdef CONFIG_USB_OTG - const void *dr_mode; -#endif - - np = of_find_compatible_node(NULL, NULL, "fsl-usb2-dr"); - if (!np) - return -ENODEV; - prop = of_get_property(np, "phy_type", NULL); - - /* Map IMMR space for pin and clock settings */ - immap = ioremap(get_immrbase(), 0x1000); - if (!immap) { - of_node_put(np); - return -ENOMEM; - } - - /* Configure clock */ - immr_node = of_get_parent(np); - if (immr_node && (of_device_is_compatible(immr_node, "fsl,mpc8315-immr") || - of_device_is_compatible(immr_node, "fsl,mpc8308-immr"))) - clrsetbits_be32(immap + MPC83XX_SCCR_OFFS, - MPC8315_SCCR_USB_MASK, - MPC8315_SCCR_USB_DRCM_01); - else - clrsetbits_be32(immap + MPC83XX_SCCR_OFFS, - MPC83XX_SCCR_USB_MASK, - MPC83XX_SCCR_USB_DRCM_11); - - /* Configure pin mux for ULPI. There is no pin mux for UTMI */ - if (prop && !strcmp(prop, "ulpi")) { - if (of_device_is_compatible(immr_node, "fsl,mpc8308-immr")) { - clrsetbits_be32(immap + MPC83XX_SICRH_OFFS, - MPC8308_SICRH_USB_MASK, - MPC8308_SICRH_USB_ULPI); - } else if (of_device_is_compatible(immr_node, "fsl,mpc8315-immr")) { - clrsetbits_be32(immap + MPC83XX_SICRL_OFFS, - MPC8315_SICRL_USB_MASK, - MPC8315_SICRL_USB_ULPI); - clrsetbits_be32(immap + MPC83XX_SICRH_OFFS, - MPC8315_SICRH_USB_MASK, - MPC8315_SICRH_USB_ULPI); - } else { - clrsetbits_be32(immap + MPC83XX_SICRL_OFFS, - MPC831X_SICRL_USB_MASK, - MPC831X_SICRL_USB_ULPI); - clrsetbits_be32(immap + MPC83XX_SICRH_OFFS, - MPC831X_SICRH_USB_MASK, - MPC831X_SICRH_USB_ULPI); - } - } - - iounmap(immap); - - of_node_put(immr_node); - - /* Map USB SOC space */ - ret = of_address_to_resource(np, 0, &res); - if (ret) { - of_node_put(np); - return ret; - } - usb_regs = ioremap(res.start, resource_size(&res)); - - /* Using on-chip PHY */ - if (prop && (!strcmp(prop, "utmi_wide") || - !strcmp(prop, "utmi"))) { - u32 refsel; - - if (of_device_is_compatible(immr_node, "fsl,mpc8308-immr")) - goto out; - - if (of_device_is_compatible(immr_node, "fsl,mpc8315-immr")) - refsel = CONTROL_REFSEL_24MHZ; - else - refsel = CONTROL_REFSEL_48MHZ; - /* Set UTMI_PHY_EN and REFSEL */ - out_be32(usb_regs + FSL_USB2_CONTROL_OFFS, - CONTROL_UTMI_PHY_EN | refsel); - /* Using external UPLI PHY */ - } else if (prop && !strcmp(prop, "ulpi")) { - /* Set PHY_CLK_SEL to ULPI */ - temp = CONTROL_PHY_CLK_SEL_ULPI; -#ifdef CONFIG_USB_OTG - /* Set OTG_PORT */ - if (!of_device_is_compatible(immr_node, "fsl,mpc8308-immr")) { - dr_mode = of_get_property(np, "dr_mode", NULL); - if (dr_mode && !strcmp(dr_mode, "otg")) - temp |= CONTROL_OTG_PORT; - } -#endif /* CONFIG_USB_OTG */ - out_be32(usb_regs + FSL_USB2_CONTROL_OFFS, temp); - } else { - printk(KERN_WARNING "831x USB PHY type not supported\n"); - ret = -EINVAL; - } - -out: - iounmap(usb_regs); - of_node_put(np); - return ret; -} -#endif /* CONFIG_PPC_MPC831x */ - -#ifdef CONFIG_PPC_MPC837x -int __init mpc837x_usb_cfg(void) -{ - void __iomem *immap; - struct device_node *np = NULL; - const void *prop; - int ret = 0; - - np = of_find_compatible_node(NULL, NULL, "fsl-usb2-dr"); - if (!np || !of_device_is_available(np)) { - of_node_put(np); - return -ENODEV; - } - prop = of_get_property(np, "phy_type", NULL); - - if (!prop || (strcmp(prop, "ulpi") && strcmp(prop, "serial"))) { - printk(KERN_WARNING "837x USB PHY type not supported\n"); - of_node_put(np); - return -EINVAL; - } - - /* Map IMMR space for pin and clock settings */ - immap = ioremap(get_immrbase(), 0x1000); - if (!immap) { - of_node_put(np); - return -ENOMEM; - } - - /* Configure clock */ - clrsetbits_be32(immap + MPC83XX_SCCR_OFFS, MPC837X_SCCR_USB_DRCM_11, - MPC837X_SCCR_USB_DRCM_11); - - /* Configure pin mux for ULPI/serial */ - clrsetbits_be32(immap + MPC83XX_SICRL_OFFS, MPC837X_SICRL_USB_MASK, - MPC837X_SICRL_USB_ULPI); - - iounmap(immap); - of_node_put(np); - return ret; -} -#endif /* CONFIG_PPC_MPC837x */ diff --git a/arch/powerpc/platforms/83xx/usb_831x.c b/arch/powerpc/platforms/83xx/usb_831x.c new file mode 100644 index 000000000000..28c24e90f022 --- /dev/null +++ b/arch/powerpc/platforms/83xx/usb_831x.c @@ -0,0 +1,128 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Freescale 83xx USB SOC setup code + * + * Copyright (C) 2007 Freescale Semiconductor, Inc. + * Author: Li Yang + */ + +#include <linux/stddef.h> +#include <linux/kernel.h> +#include <linux/errno.h> +#include <linux/of.h> +#include <linux/of_address.h> +#include <linux/io.h> + +#include <sysdev/fsl_soc.h> + +#include "mpc83xx.h" + +int __init mpc831x_usb_cfg(void) +{ + u32 temp; + void __iomem *immap, *usb_regs; + struct device_node *np = NULL; + struct device_node *immr_node = NULL; + const void *prop; + struct resource res; + int ret = 0; +#ifdef CONFIG_USB_OTG + const void *dr_mode; +#endif + + np = of_find_compatible_node(NULL, NULL, "fsl-usb2-dr"); + if (!np) + return -ENODEV; + prop = of_get_property(np, "phy_type", NULL); + + /* Map IMMR space for pin and clock settings */ + immap = ioremap(get_immrbase(), 0x1000); + if (!immap) { + of_node_put(np); + return -ENOMEM; + } + + /* Configure clock */ + immr_node = of_get_parent(np); + if (immr_node && (of_device_is_compatible(immr_node, "fsl,mpc8315-immr") || + of_device_is_compatible(immr_node, "fsl,mpc8308-immr"))) + clrsetbits_be32(immap + MPC83XX_SCCR_OFFS, + MPC8315_SCCR_USB_MASK, + MPC8315_SCCR_USB_DRCM_01); + else + clrsetbits_be32(immap + MPC83XX_SCCR_OFFS, + MPC83XX_SCCR_USB_MASK, + MPC83XX_SCCR_USB_DRCM_11); + + /* Configure pin mux for ULPI. There is no pin mux for UTMI */ + if (prop && !strcmp(prop, "ulpi")) { + if (of_device_is_compatible(immr_node, "fsl,mpc8308-immr")) { + clrsetbits_be32(immap + MPC83XX_SICRH_OFFS, + MPC8308_SICRH_USB_MASK, + MPC8308_SICRH_USB_ULPI); + } else if (of_device_is_compatible(immr_node, "fsl,mpc8315-immr")) { + clrsetbits_be32(immap + MPC83XX_SICRL_OFFS, + MPC8315_SICRL_USB_MASK, + MPC8315_SICRL_USB_ULPI); + clrsetbits_be32(immap + MPC83XX_SICRH_OFFS, + MPC8315_SICRH_USB_MASK, + MPC8315_SICRH_USB_ULPI); + } else { + clrsetbits_be32(immap + MPC83XX_SICRL_OFFS, + MPC831X_SICRL_USB_MASK, + MPC831X_SICRL_USB_ULPI); + clrsetbits_be32(immap + MPC83XX_SICRH_OFFS, + MPC831X_SICRH_USB_MASK, + MPC831X_SICRH_USB_ULPI); + } + } + + iounmap(immap); + + of_node_put(immr_node); + + /* Map USB SOC space */ + ret = of_address_to_resource(np, 0, &res); + if (ret) { + of_node_put(np); + return ret; + } + usb_regs = ioremap(res.start, resource_size(&res)); + + /* Using on-chip PHY */ + if (prop && (!strcmp(prop, "utmi_wide") || !strcmp(prop, "utmi"))) { + u32 refsel; + + if (of_device_is_compatible(immr_node, "fsl,mpc8308-immr")) + goto out; + + if (of_device_is_compatible(immr_node, "fsl,mpc8315-immr")) + refsel = CONTROL_REFSEL_24MHZ; + else + refsel = CONTROL_REFSEL_48MHZ; + /* Set UTMI_PHY_EN and REFSEL */ + out_be32(usb_regs + FSL_USB2_CONTROL_OFFS, + CONTROL_UTMI_PHY_EN | refsel); + /* Using external UPLI PHY */ + } else if (prop && !strcmp(prop, "ulpi")) { + /* Set PHY_CLK_SEL to ULPI */ + temp = CONTROL_PHY_CLK_SEL_ULPI; +#ifdef CONFIG_USB_OTG + /* Set OTG_PORT */ + if (!of_device_is_compatible(immr_node, "fsl,mpc8308-immr")) { + dr_mode = of_get_property(np, "dr_mode", NULL); + if (dr_mode && !strcmp(dr_mode, "otg")) + temp |= CONTROL_OTG_PORT; + } +#endif /* CONFIG_USB_OTG */ + out_be32(usb_regs + FSL_USB2_CONTROL_OFFS, temp); + } else { + pr_warn("831x USB PHY type not supported\n"); + ret = -EINVAL; + } + +out: + iounmap(usb_regs); + of_node_put(np); + return ret; +} diff --git a/arch/powerpc/platforms/83xx/usb_834x.c b/arch/powerpc/platforms/83xx/usb_834x.c new file mode 100644 index 000000000000..3a8d6c662d06 --- /dev/null +++ b/arch/powerpc/platforms/83xx/usb_834x.c @@ -0,0 +1,90 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Freescale 83xx USB SOC setup code + * + * Copyright (C) 2007 Freescale Semiconductor, Inc. + * Author: Li Yang + */ + +#include <linux/stddef.h> +#include <linux/kernel.h> +#include <linux/errno.h> +#include <linux/of.h> +#include <linux/of_address.h> +#include <linux/io.h> + +#include <sysdev/fsl_soc.h> + +#include "mpc83xx.h" + +int __init mpc834x_usb_cfg(void) +{ + unsigned long sccr, sicrl, sicrh; + void __iomem *immap; + struct device_node *np = NULL; + int port0_is_dr = 0, port1_is_dr = 0; + const void *prop, *dr_mode; + + immap = ioremap(get_immrbase(), 0x1000); + if (!immap) + return -ENOMEM; + + /* Read registers */ + /* Note: DR and MPH must use the same clock setting in SCCR */ + sccr = in_be32(immap + MPC83XX_SCCR_OFFS) & ~MPC83XX_SCCR_USB_MASK; + sicrl = in_be32(immap + MPC83XX_SICRL_OFFS) & ~MPC834X_SICRL_USB_MASK; + sicrh = in_be32(immap + MPC83XX_SICRH_OFFS) & ~MPC834X_SICRH_USB_UTMI; + + np = of_find_compatible_node(NULL, NULL, "fsl-usb2-dr"); + if (np) { + sccr |= MPC83XX_SCCR_USB_DRCM_11; /* 1:3 */ + + prop = of_get_property(np, "phy_type", NULL); + port1_is_dr = 1; + if (prop && + (!strcmp(prop, "utmi") || !strcmp(prop, "utmi_wide"))) { + sicrl |= MPC834X_SICRL_USB0 | MPC834X_SICRL_USB1; + sicrh |= MPC834X_SICRH_USB_UTMI; + port0_is_dr = 1; + } else if (prop && !strcmp(prop, "serial")) { + dr_mode = of_get_property(np, "dr_mode", NULL); + if (dr_mode && !strcmp(dr_mode, "otg")) { + sicrl |= MPC834X_SICRL_USB0 | MPC834X_SICRL_USB1; + port0_is_dr = 1; + } else { + sicrl |= MPC834X_SICRL_USB1; + } + } else if (prop && !strcmp(prop, "ulpi")) { + sicrl |= MPC834X_SICRL_USB1; + } else { + pr_warn("834x USB PHY type not supported\n"); + } + of_node_put(np); + } + np = of_find_compatible_node(NULL, NULL, "fsl-usb2-mph"); + if (np) { + sccr |= MPC83XX_SCCR_USB_MPHCM_11; /* 1:3 */ + + prop = of_get_property(np, "port0", NULL); + if (prop) { + if (port0_is_dr) + pr_warn("834x USB port0 can't be used by both DR and MPH!\n"); + sicrl &= ~MPC834X_SICRL_USB0; + } + prop = of_get_property(np, "port1", NULL); + if (prop) { + if (port1_is_dr) + pr_warn("834x USB port1 can't be used by both DR and MPH!\n"); + sicrl &= ~MPC834X_SICRL_USB1; + } + of_node_put(np); + } + + /* Write back */ + out_be32(immap + MPC83XX_SCCR_OFFS, sccr); + out_be32(immap + MPC83XX_SICRL_OFFS, sicrl); + out_be32(immap + MPC83XX_SICRH_OFFS, sicrh); + + iounmap(immap); + return 0; +} diff --git a/arch/powerpc/platforms/83xx/usb_837x.c b/arch/powerpc/platforms/83xx/usb_837x.c new file mode 100644 index 000000000000..726935bb6e2d --- /dev/null +++ b/arch/powerpc/platforms/83xx/usb_837x.c @@ -0,0 +1,58 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Freescale 83xx USB SOC setup code + * + * Copyright (C) 2007 Freescale Semiconductor, Inc. + * Author: Li Yang + */ + +#include <linux/stddef.h> +#include <linux/kernel.h> +#include <linux/errno.h> +#include <linux/of.h> +#include <linux/of_address.h> +#include <linux/io.h> + +#include <sysdev/fsl_soc.h> + +#include "mpc83xx.h" + +int __init mpc837x_usb_cfg(void) +{ + void __iomem *immap; + struct device_node *np = NULL; + const void *prop; + int ret = 0; + + np = of_find_compatible_node(NULL, NULL, "fsl-usb2-dr"); + if (!np || !of_device_is_available(np)) { + of_node_put(np); + return -ENODEV; + } + prop = of_get_property(np, "phy_type", NULL); + + if (!prop || (strcmp(prop, "ulpi") && strcmp(prop, "serial"))) { + pr_warn("837x USB PHY type not supported\n"); + of_node_put(np); + return -EINVAL; + } + + /* Map IMMR space for pin and clock settings */ + immap = ioremap(get_immrbase(), 0x1000); + if (!immap) { + of_node_put(np); + return -ENOMEM; + } + + /* Configure clock */ + clrsetbits_be32(immap + MPC83XX_SCCR_OFFS, MPC837X_SCCR_USB_DRCM_11, + MPC837X_SCCR_USB_DRCM_11); + + /* Configure pin mux for ULPI/serial */ + clrsetbits_be32(immap + MPC83XX_SICRL_OFFS, MPC837X_SICRL_USB_MASK, + MPC837X_SICRL_USB_ULPI); + + iounmap(immap); + of_node_put(np); + return ret; +} diff --git a/arch/powerpc/platforms/85xx/bsc913x_qds.c b/arch/powerpc/platforms/85xx/bsc913x_qds.c index a029aa090538..2eb62bff86d4 100644 --- a/arch/powerpc/platforms/85xx/bsc913x_qds.c +++ b/arch/powerpc/platforms/85xx/bsc913x_qds.c @@ -9,7 +9,7 @@ * Copyright 2014 Freescale Semiconductor Inc. */ -#include <linux/of_platform.h> +#include <linux/of.h> #include <linux/pci.h> #include <asm/mpic.h> #include <sysdev/fsl_soc.h> diff --git a/arch/powerpc/platforms/85xx/bsc913x_rdb.c b/arch/powerpc/platforms/85xx/bsc913x_rdb.c index 361b4371d073..161f006cb3bb 100644 --- a/arch/powerpc/platforms/85xx/bsc913x_rdb.c +++ b/arch/powerpc/platforms/85xx/bsc913x_rdb.c @@ -7,7 +7,7 @@ * Copyright 2011-2012 Freescale Semiconductor Inc. */ -#include <linux/of_platform.h> +#include <linux/of.h> #include <linux/pci.h> #include <asm/mpic.h> #include <sysdev/fsl_soc.h> diff --git a/arch/powerpc/platforms/85xx/c293pcie.c b/arch/powerpc/platforms/85xx/c293pcie.c index 34975708be79..7a63a3ad5e8a 100644 --- a/arch/powerpc/platforms/85xx/c293pcie.c +++ b/arch/powerpc/platforms/85xx/c293pcie.c @@ -7,8 +7,7 @@ #include <linux/stddef.h> #include <linux/kernel.h> -#include <linux/of_fdt.h> -#include <linux/of_platform.h> +#include <linux/of.h> #include <asm/machdep.h> #include <asm/udbg.h> diff --git a/arch/powerpc/platforms/85xx/common.c b/arch/powerpc/platforms/85xx/common.c index a554b6d87cf7..757811155587 100644 --- a/arch/powerpc/platforms/85xx/common.c +++ b/arch/powerpc/platforms/85xx/common.c @@ -3,6 +3,7 @@ * Routines common to most mpc85xx-based boards. */ +#include <linux/of.h> #include <linux/of_irq.h> #include <linux/of_platform.h> diff --git a/arch/powerpc/platforms/85xx/corenet_generic.c b/arch/powerpc/platforms/85xx/corenet_generic.c index bfde391c42f4..645fcca77cde 100644 --- a/arch/powerpc/platforms/85xx/corenet_generic.c +++ b/arch/powerpc/platforms/85xx/corenet_generic.c @@ -30,7 +30,7 @@ #include "smp.h" #include "mpc85xx.h" -void __init corenet_gen_pic_init(void) +static void __init corenet_gen_pic_init(void) { struct mpic *mpic; unsigned int flags = MPIC_BIG_ENDIAN | MPIC_SINGLE_DEST_CPU | @@ -48,7 +48,7 @@ void __init corenet_gen_pic_init(void) /* * Setup the architecture */ -void __init corenet_gen_setup_arch(void) +static void __init corenet_gen_setup_arch(void) { mpc85xx_smp_init(); @@ -101,7 +101,7 @@ static const struct of_device_id of_device_ids[] = { {} }; -int __init corenet_gen_publish_devices(void) +static int __init corenet_gen_publish_devices(void) { return of_platform_bus_probe(NULL, of_device_ids, NULL); } diff --git a/arch/powerpc/platforms/85xx/ge_imp3a.c b/arch/powerpc/platforms/85xx/ge_imp3a.c index 3678a1fbf5ad..9c3b44a1952e 100644 --- a/arch/powerpc/platforms/85xx/ge_imp3a.c +++ b/arch/powerpc/platforms/85xx/ge_imp3a.c @@ -17,8 +17,8 @@ #include <linux/delay.h> #include <linux/seq_file.h> #include <linux/interrupt.h> +#include <linux/of.h> #include <linux/of_address.h> -#include <linux/of_platform.h> #include <asm/time.h> #include <asm/machdep.h> diff --git a/arch/powerpc/platforms/85xx/ksi8560.c b/arch/powerpc/platforms/85xx/ksi8560.c index af38c3aec042..1b6326a4b0f2 100644 --- a/arch/powerpc/platforms/85xx/ksi8560.c +++ b/arch/powerpc/platforms/85xx/ksi8560.c @@ -18,7 +18,8 @@ #include <linux/kdev_t.h> #include <linux/delay.h> #include <linux/seq_file.h> -#include <linux/of_platform.h> +#include <linux/of.h> +#include <linux/of_address.h> #include <asm/time.h> #include <asm/machdep.h> diff --git a/arch/powerpc/platforms/85xx/mpc8536_ds.c b/arch/powerpc/platforms/85xx/mpc8536_ds.c index 58ab3831913f..e966b2ad8ecd 100644 --- a/arch/powerpc/platforms/85xx/mpc8536_ds.c +++ b/arch/powerpc/platforms/85xx/mpc8536_ds.c @@ -12,7 +12,7 @@ #include <linux/delay.h> #include <linux/seq_file.h> #include <linux/interrupt.h> -#include <linux/of_platform.h> +#include <linux/of.h> #include <asm/time.h> #include <asm/machdep.h> diff --git a/arch/powerpc/platforms/85xx/mpc85xx_ds.c b/arch/powerpc/platforms/85xx/mpc85xx_ds.c index 4347d629b567..2856148321b3 100644 --- a/arch/powerpc/platforms/85xx/mpc85xx_ds.c +++ b/arch/powerpc/platforms/85xx/mpc85xx_ds.c @@ -15,8 +15,8 @@ #include <linux/delay.h> #include <linux/seq_file.h> #include <linux/interrupt.h> +#include <linux/of.h> #include <linux/of_irq.h> -#include <linux/of_platform.h> #include <asm/time.h> #include <asm/machdep.h> diff --git a/arch/powerpc/platforms/85xx/mpc85xx_mds.c b/arch/powerpc/platforms/85xx/mpc85xx_mds.c index 0546f19416c2..c19490cf6376 100644 --- a/arch/powerpc/platforms/85xx/mpc85xx_mds.c +++ b/arch/powerpc/platforms/85xx/mpc85xx_mds.c @@ -26,8 +26,8 @@ #include <linux/seq_file.h> #include <linux/initrd.h> #include <linux/fsl_devices.h> -#include <linux/of_platform.h> -#include <linux/of_device.h> +#include <linux/of.h> +#include <linux/of_address.h> #include <linux/phy.h> #include <linux/memblock.h> #include <linux/fsl/guts.h> diff --git a/arch/powerpc/platforms/85xx/mpc85xx_rdb.c b/arch/powerpc/platforms/85xx/mpc85xx_rdb.c index c42a68da6dfd..ec9f60fbebc7 100644 --- a/arch/powerpc/platforms/85xx/mpc85xx_rdb.c +++ b/arch/powerpc/platforms/85xx/mpc85xx_rdb.c @@ -12,7 +12,8 @@ #include <linux/delay.h> #include <linux/seq_file.h> #include <linux/interrupt.h> -#include <linux/of_platform.h> +#include <linux/of.h> +#include <linux/of_address.h> #include <linux/fsl/guts.h> #include <asm/time.h> diff --git a/arch/powerpc/platforms/85xx/p1010rdb.c b/arch/powerpc/platforms/85xx/p1010rdb.c index 14ec79a32746..10d6f1fa3327 100644 --- a/arch/powerpc/platforms/85xx/p1010rdb.c +++ b/arch/powerpc/platforms/85xx/p1010rdb.c @@ -10,7 +10,7 @@ #include <linux/pci.h> #include <linux/delay.h> #include <linux/interrupt.h> -#include <linux/of_platform.h> +#include <linux/of.h> #include <asm/time.h> #include <asm/machdep.h> diff --git a/arch/powerpc/platforms/85xx/p1022_ds.c b/arch/powerpc/platforms/85xx/p1022_ds.c index 23d0926298b9..0dd786a061a6 100644 --- a/arch/powerpc/platforms/85xx/p1022_ds.c +++ b/arch/powerpc/platforms/85xx/p1022_ds.c @@ -18,8 +18,8 @@ #include <linux/fsl/guts.h> #include <linux/pci.h> +#include <linux/of.h> #include <linux/of_address.h> -#include <linux/of_platform.h> #include <asm/div64.h> #include <asm/mpic.h> #include <asm/swiotlb.h> diff --git a/arch/powerpc/platforms/85xx/p1022_rdk.c b/arch/powerpc/platforms/85xx/p1022_rdk.c index d1159150c3b5..25ab6e9c1470 100644 --- a/arch/powerpc/platforms/85xx/p1022_rdk.c +++ b/arch/powerpc/platforms/85xx/p1022_rdk.c @@ -14,8 +14,8 @@ #include <linux/fsl/guts.h> #include <linux/pci.h> +#include <linux/of.h> #include <linux/of_address.h> -#include <linux/of_platform.h> #include <asm/div64.h> #include <asm/mpic.h> #include <asm/swiotlb.h> diff --git a/arch/powerpc/platforms/85xx/p1023_rdb.c b/arch/powerpc/platforms/85xx/p1023_rdb.c index 9df0439a9382..e4fa8731fd2d 100644 --- a/arch/powerpc/platforms/85xx/p1023_rdb.c +++ b/arch/powerpc/platforms/85xx/p1023_rdb.c @@ -15,9 +15,8 @@ #include <linux/delay.h> #include <linux/module.h> #include <linux/fsl_devices.h> +#include <linux/of.h> #include <linux/of_address.h> -#include <linux/of_platform.h> -#include <linux/of_device.h> #include <asm/time.h> #include <asm/machdep.h> diff --git a/arch/powerpc/platforms/85xx/qemu_e500.c b/arch/powerpc/platforms/85xx/qemu_e500.c index 6e4b1ddf292b..3cd2f3bd4223 100644 --- a/arch/powerpc/platforms/85xx/qemu_e500.c +++ b/arch/powerpc/platforms/85xx/qemu_e500.c @@ -25,7 +25,7 @@ #include "smp.h" #include "mpc85xx.h" -void __init qemu_e500_pic_init(void) +static void __init qemu_e500_pic_init(void) { struct mpic *mpic; unsigned int flags = MPIC_BIG_ENDIAN | MPIC_SINGLE_DEST_CPU | diff --git a/arch/powerpc/platforms/85xx/smp.c b/arch/powerpc/platforms/85xx/smp.c index 9c43cf32f4c9..40aa58206888 100644 --- a/arch/powerpc/platforms/85xx/smp.c +++ b/arch/powerpc/platforms/85xx/smp.c @@ -180,7 +180,7 @@ static void wake_hw_thread(void *info) unsigned long inia; int cpu = *(const int *)info; - inia = *(unsigned long *)fsl_secondary_thread_init; + inia = ppc_function_entry(fsl_secondary_thread_init); book3e_start_thread(cpu_thread_in_core(cpu), inia); } #endif diff --git a/arch/powerpc/platforms/85xx/socrates.c b/arch/powerpc/platforms/85xx/socrates.c index 9fa1338bc002..403367b318db 100644 --- a/arch/powerpc/platforms/85xx/socrates.c +++ b/arch/powerpc/platforms/85xx/socrates.c @@ -23,7 +23,7 @@ #include <linux/kdev_t.h> #include <linux/delay.h> #include <linux/seq_file.h> -#include <linux/of_platform.h> +#include <linux/of.h> #include <asm/time.h> #include <asm/machdep.h> diff --git a/arch/powerpc/platforms/85xx/socrates_fpga_pic.c b/arch/powerpc/platforms/85xx/socrates_fpga_pic.c index 3768c86b9629..baa12eff6d5d 100644 --- a/arch/powerpc/platforms/85xx/socrates_fpga_pic.c +++ b/arch/powerpc/platforms/85xx/socrates_fpga_pic.c @@ -6,7 +6,6 @@ #include <linux/irq.h> #include <linux/of_address.h> #include <linux/of_irq.h> -#include <linux/of_platform.h> #include <linux/io.h> /* diff --git a/arch/powerpc/platforms/85xx/stx_gp3.c b/arch/powerpc/platforms/85xx/stx_gp3.c index 5e2646b4c039..c10efc45894c 100644 --- a/arch/powerpc/platforms/85xx/stx_gp3.c +++ b/arch/powerpc/platforms/85xx/stx_gp3.c @@ -22,7 +22,7 @@ #include <linux/kdev_t.h> #include <linux/delay.h> #include <linux/seq_file.h> -#include <linux/of_platform.h> +#include <linux/of.h> #include <asm/time.h> #include <asm/machdep.h> diff --git a/arch/powerpc/platforms/85xx/tqm85xx.c b/arch/powerpc/platforms/85xx/tqm85xx.c index 80effb028bf4..6be1b9809db6 100644 --- a/arch/powerpc/platforms/85xx/tqm85xx.c +++ b/arch/powerpc/platforms/85xx/tqm85xx.c @@ -20,7 +20,7 @@ #include <linux/kdev_t.h> #include <linux/delay.h> #include <linux/seq_file.h> -#include <linux/of_platform.h> +#include <linux/of.h> #include <asm/time.h> #include <asm/machdep.h> diff --git a/arch/powerpc/platforms/85xx/twr_p102x.c b/arch/powerpc/platforms/85xx/twr_p102x.c index b88e23a334a4..c0a0456f1674 100644 --- a/arch/powerpc/platforms/85xx/twr_p102x.c +++ b/arch/powerpc/platforms/85xx/twr_p102x.c @@ -13,7 +13,8 @@ #include <linux/errno.h> #include <linux/fsl/guts.h> #include <linux/pci.h> -#include <linux/of_platform.h> +#include <linux/of.h> +#include <linux/of_address.h> #include <asm/pci-bridge.h> #include <asm/udbg.h> diff --git a/arch/powerpc/platforms/85xx/xes_mpc85xx.c b/arch/powerpc/platforms/85xx/xes_mpc85xx.c index 184013e6601e..45f257fc1ade 100644 --- a/arch/powerpc/platforms/85xx/xes_mpc85xx.c +++ b/arch/powerpc/platforms/85xx/xes_mpc85xx.c @@ -16,8 +16,8 @@ #include <linux/delay.h> #include <linux/seq_file.h> #include <linux/interrupt.h> +#include <linux/of.h> #include <linux/of_address.h> -#include <linux/of_platform.h> #include <asm/time.h> #include <asm/machdep.h> diff --git a/arch/powerpc/platforms/86xx/common.c b/arch/powerpc/platforms/86xx/common.c index 0069d38263e7..a4a550527609 100644 --- a/arch/powerpc/platforms/86xx/common.c +++ b/arch/powerpc/platforms/86xx/common.c @@ -3,7 +3,10 @@ * Routines common to most mpc86xx-based boards. */ +#include <linux/init.h> +#include <linux/mod_devicetable.h> #include <linux/of_platform.h> +#include <asm/reg.h> #include <asm/synch.h> #include "mpc86xx.h" diff --git a/arch/powerpc/platforms/86xx/gef_ppc9a.c b/arch/powerpc/platforms/86xx/gef_ppc9a.c index f0512e51300c..f7f98cca7b91 100644 --- a/arch/powerpc/platforms/86xx/gef_ppc9a.c +++ b/arch/powerpc/platforms/86xx/gef_ppc9a.c @@ -18,8 +18,8 @@ #include <linux/kdev_t.h> #include <linux/delay.h> #include <linux/seq_file.h> +#include <linux/of.h> #include <linux/of_address.h> -#include <linux/of_platform.h> #include <asm/time.h> #include <asm/machdep.h> diff --git a/arch/powerpc/platforms/86xx/gef_sbc310.c b/arch/powerpc/platforms/86xx/gef_sbc310.c index 1430b524d982..689835f7f088 100644 --- a/arch/powerpc/platforms/86xx/gef_sbc310.c +++ b/arch/powerpc/platforms/86xx/gef_sbc310.c @@ -18,8 +18,8 @@ #include <linux/kdev_t.h> #include <linux/delay.h> #include <linux/seq_file.h> +#include <linux/of.h> #include <linux/of_address.h> -#include <linux/of_platform.h> #include <asm/time.h> #include <asm/machdep.h> diff --git a/arch/powerpc/platforms/86xx/gef_sbc610.c b/arch/powerpc/platforms/86xx/gef_sbc610.c index c92af0d964e1..365f511186ca 100644 --- a/arch/powerpc/platforms/86xx/gef_sbc610.c +++ b/arch/powerpc/platforms/86xx/gef_sbc610.c @@ -18,8 +18,8 @@ #include <linux/kdev_t.h> #include <linux/delay.h> #include <linux/seq_file.h> +#include <linux/of.h> #include <linux/of_address.h> -#include <linux/of_platform.h> #include <asm/time.h> #include <asm/machdep.h> diff --git a/arch/powerpc/platforms/86xx/mvme7100.c b/arch/powerpc/platforms/86xx/mvme7100.c index c0ac40514361..cee49ecd32d2 100644 --- a/arch/powerpc/platforms/86xx/mvme7100.c +++ b/arch/powerpc/platforms/86xx/mvme7100.c @@ -20,7 +20,6 @@ #include <linux/pci.h> #include <linux/of.h> #include <linux/of_fdt.h> -#include <linux/of_platform.h> #include <linux/of_address.h> #include <asm/udbg.h> #include <asm/mpic.h> diff --git a/arch/powerpc/platforms/86xx/pic.c b/arch/powerpc/platforms/86xx/pic.c index 2c32c3488afb..9ca36de23532 100644 --- a/arch/powerpc/platforms/86xx/pic.c +++ b/arch/powerpc/platforms/86xx/pic.c @@ -6,12 +6,14 @@ #include <linux/stddef.h> #include <linux/kernel.h> #include <linux/interrupt.h> +#include <linux/of.h> #include <linux/of_irq.h> -#include <linux/of_platform.h> #include <asm/mpic.h> #include <asm/i8259.h> +#include "mpc86xx.h" + #ifdef CONFIG_PPC_I8259 static void mpc86xx_8259_cascade(struct irq_desc *desc) { diff --git a/arch/powerpc/platforms/8xx/adder875.c b/arch/powerpc/platforms/8xx/adder875.c index 7e83eb6746f4..d02f8dd66427 100644 --- a/arch/powerpc/platforms/8xx/adder875.c +++ b/arch/powerpc/platforms/8xx/adder875.c @@ -7,13 +7,12 @@ */ #include <linux/init.h> -#include <linux/fs_enet_pd.h> #include <linux/of_platform.h> #include <asm/time.h> #include <asm/machdep.h> #include <asm/cpm1.h> -#include <asm/fs_pd.h> +#include <asm/8xx_immap.h> #include <asm/udbg.h> #include "mpc8xx.h" diff --git a/arch/powerpc/platforms/8xx/cpm1.c b/arch/powerpc/platforms/8xx/cpm1.c index 34ab29966c8b..ebb5f6a27dbf 100644 --- a/arch/powerpc/platforms/8xx/cpm1.c +++ b/arch/powerpc/platforms/8xx/cpm1.c @@ -41,7 +41,7 @@ #include <asm/rheap.h> #include <asm/cpm.h> -#include <asm/fs_pd.h> +#include <sysdev/fsl_soc.h> #ifdef CONFIG_8xx_GPIO #include <linux/gpio/legacy-of-mm-gpiochip.h> @@ -54,8 +54,6 @@ immap_t __iomem *mpc8xx_immr = (void __iomem *)VIRT_IMMR_BASE; void __init cpm_reset(void) { - sysconf8xx_t __iomem *siu_conf; - cpmp = &mpc8xx_immr->im_cpm; #ifndef CONFIG_PPC_EARLY_DEBUG_CPM @@ -77,12 +75,10 @@ void __init cpm_reset(void) * manual recommends it. * Bit 25, FAM can also be set to use FEC aggressive mode (860T). */ - siu_conf = immr_map(im_siu_conf); if ((mfspr(SPRN_IMMR) & 0xffff) == 0x0900) /* MPC885 */ - out_be32(&siu_conf->sc_sdcr, 0x40); + out_be32(&mpc8xx_immr->im_siu_conf.sc_sdcr, 0x40); else - out_be32(&siu_conf->sc_sdcr, 1); - immr_unmap(siu_conf); + out_be32(&mpc8xx_immr->im_siu_conf.sc_sdcr, 1); } static DEFINE_SPINLOCK(cmd_lock); diff --git a/arch/powerpc/platforms/8xx/m8xx_setup.c b/arch/powerpc/platforms/8xx/m8xx_setup.c index 24f358f86d16..2336b687bc96 100644 --- a/arch/powerpc/platforms/8xx/m8xx_setup.c +++ b/arch/powerpc/platforms/8xx/m8xx_setup.c @@ -22,7 +22,6 @@ #include <asm/io.h> #include <asm/8xx_immap.h> -#include <asm/fs_pd.h> #include <mm/mmu_decl.h> #include "pic.h" @@ -37,20 +36,6 @@ static irqreturn_t timebase_interrupt(int irq, void *dev) return IRQ_HANDLED; } -/* per-board overridable init_internal_rtc() function. */ -void __init __attribute__ ((weak)) -init_internal_rtc(void) -{ - sit8xx_t __iomem *sys_tmr = immr_map(im_sit); - - /* Disable the RTC one second and alarm interrupts. */ - clrbits16(&sys_tmr->sit_rtcsc, (RTCSC_SIE | RTCSC_ALE)); - - /* Enable the RTC */ - setbits16(&sys_tmr->sit_rtcsc, (RTCSC_RTF | RTCSC_RTE)); - immr_unmap(sys_tmr); -} - static int __init get_freq(char *name, unsigned long *val) { struct device_node *cpu; @@ -80,23 +65,14 @@ static int __init get_freq(char *name, unsigned long *val) void __init mpc8xx_calibrate_decr(void) { struct device_node *cpu; - cark8xx_t __iomem *clk_r1; - car8xx_t __iomem *clk_r2; - sitk8xx_t __iomem *sys_tmr1; - sit8xx_t __iomem *sys_tmr2; int irq, virq; - clk_r1 = immr_map(im_clkrstk); - /* Unlock the SCCR. */ - out_be32(&clk_r1->cark_sccrk, ~KAPWR_KEY); - out_be32(&clk_r1->cark_sccrk, KAPWR_KEY); - immr_unmap(clk_r1); + out_be32(&mpc8xx_immr->im_clkrstk.cark_sccrk, ~KAPWR_KEY); + out_be32(&mpc8xx_immr->im_clkrstk.cark_sccrk, KAPWR_KEY); /* Force all 8xx processors to use divide by 16 processor clock. */ - clk_r2 = immr_map(im_clkrst); - setbits32(&clk_r2->car_sccr, 0x02000000); - immr_unmap(clk_r2); + setbits32(&mpc8xx_immr->im_clkrst.car_sccr, 0x02000000); /* Processor frequency is MHz. */ @@ -123,16 +99,18 @@ void __init mpc8xx_calibrate_decr(void) * we guarantee the registers are locked, then we unlock them * for our use. */ - sys_tmr1 = immr_map(im_sitk); - out_be32(&sys_tmr1->sitk_tbscrk, ~KAPWR_KEY); - out_be32(&sys_tmr1->sitk_rtcsck, ~KAPWR_KEY); - out_be32(&sys_tmr1->sitk_tbk, ~KAPWR_KEY); - out_be32(&sys_tmr1->sitk_tbscrk, KAPWR_KEY); - out_be32(&sys_tmr1->sitk_rtcsck, KAPWR_KEY); - out_be32(&sys_tmr1->sitk_tbk, KAPWR_KEY); - immr_unmap(sys_tmr1); + out_be32(&mpc8xx_immr->im_sitk.sitk_tbscrk, ~KAPWR_KEY); + out_be32(&mpc8xx_immr->im_sitk.sitk_rtcsck, ~KAPWR_KEY); + out_be32(&mpc8xx_immr->im_sitk.sitk_tbk, ~KAPWR_KEY); + out_be32(&mpc8xx_immr->im_sitk.sitk_tbscrk, KAPWR_KEY); + out_be32(&mpc8xx_immr->im_sitk.sitk_rtcsck, KAPWR_KEY); + out_be32(&mpc8xx_immr->im_sitk.sitk_tbk, KAPWR_KEY); + + /* Disable the RTC one second and alarm interrupts. */ + clrbits16(&mpc8xx_immr->im_sit.sit_rtcsc, (RTCSC_SIE | RTCSC_ALE)); - init_internal_rtc(); + /* Enable the RTC */ + setbits16(&mpc8xx_immr->im_sit.sit_rtcsc, (RTCSC_RTF | RTCSC_RTE)); /* Enabling the decrementer also enables the timebase interrupts * (or from the other point of view, to get decrementer interrupts @@ -144,10 +122,8 @@ void __init mpc8xx_calibrate_decr(void) of_node_put(cpu); irq = virq_to_hw(virq); - sys_tmr2 = immr_map(im_sit); - out_be16(&sys_tmr2->sit_tbscr, ((1 << (7 - (irq/2))) << 8) | - (TBSCR_TBF | TBSCR_TBE)); - immr_unmap(sys_tmr2); + out_be16(&mpc8xx_immr->im_sit.sit_tbscr, + ((1 << (7 - (irq / 2))) << 8) | (TBSCR_TBF | TBSCR_TBE)); if (request_irq(virq, timebase_interrupt, IRQF_NO_THREAD, "tbint", NULL)) @@ -161,47 +137,36 @@ void __init mpc8xx_calibrate_decr(void) int mpc8xx_set_rtc_time(struct rtc_time *tm) { - sitk8xx_t __iomem *sys_tmr1; - sit8xx_t __iomem *sys_tmr2; time64_t time; - sys_tmr1 = immr_map(im_sitk); - sys_tmr2 = immr_map(im_sit); time = rtc_tm_to_time64(tm); - out_be32(&sys_tmr1->sitk_rtck, KAPWR_KEY); - out_be32(&sys_tmr2->sit_rtc, (u32)time); - out_be32(&sys_tmr1->sitk_rtck, ~KAPWR_KEY); + out_be32(&mpc8xx_immr->im_sitk.sitk_rtck, KAPWR_KEY); + out_be32(&mpc8xx_immr->im_sit.sit_rtc, (u32)time); + out_be32(&mpc8xx_immr->im_sitk.sitk_rtck, ~KAPWR_KEY); - immr_unmap(sys_tmr2); - immr_unmap(sys_tmr1); return 0; } void mpc8xx_get_rtc_time(struct rtc_time *tm) { unsigned long data; - sit8xx_t __iomem *sys_tmr = immr_map(im_sit); /* Get time from the RTC. */ - data = in_be32(&sys_tmr->sit_rtc); + data = in_be32(&mpc8xx_immr->im_sit.sit_rtc); rtc_time64_to_tm(data, tm); - immr_unmap(sys_tmr); return; } void __noreturn mpc8xx_restart(char *cmd) { - car8xx_t __iomem *clk_r = immr_map(im_clkrst); - - local_irq_disable(); - setbits32(&clk_r->car_plprcr, 0x00000080); + setbits32(&mpc8xx_immr->im_clkrst.car_plprcr, 0x00000080); /* Clear the ME bit in MSR to cause checkstop on machine check */ mtmsr(mfmsr() & ~0x1000); - in_8(&clk_r->res[0]); + in_8(&mpc8xx_immr->im_clkrst.res[0]); panic("Restart failed\n"); } diff --git a/arch/powerpc/platforms/8xx/mpc86xads_setup.c b/arch/powerpc/platforms/8xx/mpc86xads_setup.c index 11b3d1116db1..e4192c0a3c0c 100644 --- a/arch/powerpc/platforms/8xx/mpc86xads_setup.c +++ b/arch/powerpc/platforms/8xx/mpc86xads_setup.c @@ -24,7 +24,6 @@ #include <asm/time.h> #include <asm/8xx_immap.h> #include <asm/cpm1.h> -#include <asm/fs_pd.h> #include <asm/udbg.h> #include "mpc86xads.h" diff --git a/arch/powerpc/platforms/8xx/mpc885ads_setup.c b/arch/powerpc/platforms/8xx/mpc885ads_setup.c index 2fc7cacbcd96..2d899be746eb 100644 --- a/arch/powerpc/platforms/8xx/mpc885ads_setup.c +++ b/arch/powerpc/platforms/8xx/mpc885ads_setup.c @@ -21,8 +21,6 @@ #include <linux/device.h> #include <linux/delay.h> -#include <linux/fs_enet_pd.h> -#include <linux/fs_uart_pd.h> #include <linux/fsl_devices.h> #include <linux/mii.h> #include <linux/of_address.h> @@ -37,7 +35,6 @@ #include <asm/time.h> #include <asm/8xx_immap.h> #include <asm/cpm1.h> -#include <asm/fs_pd.h> #include <asm/udbg.h> #include "mpc885ads.h" diff --git a/arch/powerpc/platforms/8xx/tqm8xx_setup.c b/arch/powerpc/platforms/8xx/tqm8xx_setup.c index 7d8eb50bb9cd..d97a7910c594 100644 --- a/arch/powerpc/platforms/8xx/tqm8xx_setup.c +++ b/arch/powerpc/platforms/8xx/tqm8xx_setup.c @@ -24,8 +24,6 @@ #include <linux/device.h> #include <linux/delay.h> -#include <linux/fs_enet_pd.h> -#include <linux/fs_uart_pd.h> #include <linux/fsl_devices.h> #include <linux/mii.h> #include <linux/of_fdt.h> @@ -39,7 +37,6 @@ #include <asm/time.h> #include <asm/8xx_immap.h> #include <asm/cpm1.h> -#include <asm/fs_pd.h> #include <asm/udbg.h> #include "mpc8xx.h" diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig index 3e2e252016f7..1fd253f92a77 100644 --- a/arch/powerpc/platforms/Kconfig +++ b/arch/powerpc/platforms/Kconfig @@ -251,7 +251,7 @@ config QE_GPIO config CPM2 bool "Enable support for the CPM2 (Communications Processor Module)" - depends on (FSL_SOC_BOOKE && PPC32) || 8260 + depends on (FSL_SOC_BOOKE && PPC32) || PPC_82xx select CPM select HAVE_PCI select GPIOLIB diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype index 45fd975ef521..b2d8c0da2ad9 100644 --- a/arch/powerpc/platforms/Kconfig.cputype +++ b/arch/powerpc/platforms/Kconfig.cputype @@ -94,6 +94,7 @@ config PPC_BOOK3S_64 select PPC_FPU select PPC_HAVE_PMU_SUPPORT select HAVE_ARCH_TRANSPARENT_HUGEPAGE + select HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD select ARCH_ENABLE_HUGEPAGE_MIGRATION if HUGETLB_PAGE && MIGRATION select ARCH_ENABLE_SPLIT_PMD_PTLOCK select ARCH_ENABLE_THP_MIGRATION if TRANSPARENT_HUGEPAGE @@ -275,6 +276,13 @@ config TARGET_CPU default "e500mc" if E500MC_CPU default "powerpc" if POWERPC_CPU +config TUNE_CPU + string + depends on POWERPC64_CPU + default "-mtune=power10" if $(cc-option,-mtune=power10) + default "-mtune=power9" if $(cc-option,-mtune=power9) + default "-mtune=power8" if $(cc-option,-mtune=power8) + config PPC_BOOK3S def_bool y depends on PPC_BOOK3S_32 || PPC_BOOK3S_64 diff --git a/arch/powerpc/platforms/cell/axon_msi.c b/arch/powerpc/platforms/cell/axon_msi.c index 106000449d3b..28dc86744cac 100644 --- a/arch/powerpc/platforms/cell/axon_msi.c +++ b/arch/powerpc/platforms/cell/axon_msi.c @@ -10,10 +10,11 @@ #include <linux/pci.h> #include <linux/msi.h> #include <linux/export.h> -#include <linux/of_platform.h> #include <linux/slab.h> #include <linux/debugfs.h> +#include <linux/of.h> #include <linux/of_irq.h> +#include <linux/platform_device.h> #include <asm/dcr.h> #include <asm/machdep.h> diff --git a/arch/powerpc/platforms/cell/cbe_regs.c b/arch/powerpc/platforms/cell/cbe_regs.c index fb4023f9ea6b..99b3558753e9 100644 --- a/arch/powerpc/platforms/cell/cbe_regs.c +++ b/arch/powerpc/platforms/cell/cbe_regs.c @@ -10,9 +10,8 @@ #include <linux/percpu.h> #include <linux/types.h> #include <linux/export.h> +#include <linux/of.h> #include <linux/of_address.h> -#include <linux/of_device.h> -#include <linux/of_platform.h> #include <linux/pgtable.h> #include <asm/io.h> diff --git a/arch/powerpc/platforms/cell/iommu.c b/arch/powerpc/platforms/cell/iommu.c index 8c7133039566..1202a69b0a20 100644 --- a/arch/powerpc/platforms/cell/iommu.c +++ b/arch/powerpc/platforms/cell/iommu.c @@ -16,7 +16,7 @@ #include <linux/notifier.h> #include <linux/of.h> #include <linux/of_address.h> -#include <linux/of_platform.h> +#include <linux/platform_device.h> #include <linux/slab.h> #include <linux/memblock.h> diff --git a/arch/powerpc/platforms/cell/ras.c b/arch/powerpc/platforms/cell/ras.c index 98db63b72d56..f6b87926530c 100644 --- a/arch/powerpc/platforms/cell/ras.c +++ b/arch/powerpc/platforms/cell/ras.c @@ -22,7 +22,7 @@ #include <asm/cell-regs.h> #include "ras.h" - +#include "pervasive.h" static void dump_fir(int cpu) { diff --git a/arch/powerpc/platforms/cell/setup.c b/arch/powerpc/platforms/cell/setup.c index 9e07d101bcee..f64a1ef98aa8 100644 --- a/arch/powerpc/platforms/cell/setup.c +++ b/arch/powerpc/platforms/cell/setup.c @@ -27,6 +27,7 @@ #include <linux/mutex.h> #include <linux/memory_hotplug.h> #include <linux/of_platform.h> +#include <linux/platform_device.h> #include <asm/mmu.h> #include <asm/processor.h> diff --git a/arch/powerpc/platforms/cell/spider-pci.c b/arch/powerpc/platforms/cell/spider-pci.c index e36ebd84f55b..68439445b1c3 100644 --- a/arch/powerpc/platforms/cell/spider-pci.c +++ b/arch/powerpc/platforms/cell/spider-pci.c @@ -9,7 +9,6 @@ #include <linux/kernel.h> #include <linux/of_address.h> -#include <linux/of_platform.h> #include <linux/slab.h> #include <linux/io.h> diff --git a/arch/powerpc/platforms/cell/spu_manage.c b/arch/powerpc/platforms/cell/spu_manage.c index 74567b32c48c..f464a1f2e568 100644 --- a/arch/powerpc/platforms/cell/spu_manage.c +++ b/arch/powerpc/platforms/cell/spu_manage.c @@ -25,6 +25,7 @@ #include "spufs/spufs.h" #include "interrupt.h" +#include "spu_priv1_mmio.h" struct device_node *spu_devnode(struct spu *spu) { diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c index ea807aa0c31a..38c5be34c895 100644 --- a/arch/powerpc/platforms/cell/spufs/inode.c +++ b/arch/powerpc/platforms/cell/spufs/inode.c @@ -86,7 +86,7 @@ spufs_new_inode(struct super_block *sb, umode_t mode) inode->i_mode = mode; inode->i_uid = current_fsuid(); inode->i_gid = current_fsgid(); - inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode); + inode->i_atime = inode->i_mtime = inode_set_ctime_current(inode); out: return inode; } diff --git a/arch/powerpc/platforms/embedded6xx/holly.c b/arch/powerpc/platforms/embedded6xx/holly.c index 02ff260ae1ee..ce9e58ee9754 100644 --- a/arch/powerpc/platforms/embedded6xx/holly.c +++ b/arch/powerpc/platforms/embedded6xx/holly.c @@ -22,9 +22,9 @@ #include <linux/serial.h> #include <linux/tty.h> #include <linux/serial_core.h> +#include <linux/of.h> #include <linux/of_address.h> #include <linux/of_irq.h> -#include <linux/of_platform.h> #include <linux/extable.h> #include <asm/time.h> diff --git a/arch/powerpc/platforms/maple/setup.c b/arch/powerpc/platforms/maple/setup.c index a4a79d77eca2..f329a03edf4a 100644 --- a/arch/powerpc/platforms/maple/setup.c +++ b/arch/powerpc/platforms/maple/setup.c @@ -36,8 +36,9 @@ #include <linux/serial.h> #include <linux/smp.h> #include <linux/bitops.h> +#include <linux/of.h> #include <linux/of_address.h> -#include <linux/of_device.h> +#include <linux/platform_device.h> #include <linux/memblock.h> #include <asm/processor.h> diff --git a/arch/powerpc/platforms/pasemi/gpio_mdio.c b/arch/powerpc/platforms/pasemi/gpio_mdio.c index 913b77b92cea..fd130fe7a65a 100644 --- a/arch/powerpc/platforms/pasemi/gpio_mdio.c +++ b/arch/powerpc/platforms/pasemi/gpio_mdio.c @@ -20,7 +20,7 @@ #include <linux/phy.h> #include <linux/of_address.h> #include <linux/of_mdio.h> -#include <linux/of_platform.h> +#include <linux/platform_device.h> #define DELAY 1 diff --git a/arch/powerpc/platforms/pasemi/pasemi.h b/arch/powerpc/platforms/pasemi/pasemi.h index 3f277a200fd8..018c30665e1b 100644 --- a/arch/powerpc/platforms/pasemi/pasemi.h +++ b/arch/powerpc/platforms/pasemi/pasemi.h @@ -4,6 +4,7 @@ extern time64_t pas_get_boot_time(void); extern void pas_pci_init(void); +struct pci_dev; extern void pas_pci_irq_fixup(struct pci_dev *dev); extern void pas_pci_dma_dev_setup(struct pci_dev *dev); diff --git a/arch/powerpc/platforms/pasemi/setup.c b/arch/powerpc/platforms/pasemi/setup.c index 5c5b4a034f9e..ef985ba2bf21 100644 --- a/arch/powerpc/platforms/pasemi/setup.c +++ b/arch/powerpc/platforms/pasemi/setup.c @@ -16,7 +16,9 @@ #include <linux/console.h> #include <linux/export.h> #include <linux/pci.h> +#include <linux/of.h> #include <linux/of_platform.h> +#include <linux/platform_device.h> #include <linux/gfp.h> #include <linux/irqdomain.h> diff --git a/arch/powerpc/platforms/pasemi/time.c b/arch/powerpc/platforms/pasemi/time.c index ad721882c8b6..70ac6db027d0 100644 --- a/arch/powerpc/platforms/pasemi/time.c +++ b/arch/powerpc/platforms/pasemi/time.c @@ -9,6 +9,8 @@ #include <asm/time.h> +#include "pasemi.h" + time64_t __init pas_get_boot_time(void) { /* Let's just return a fake date right now */ diff --git a/arch/powerpc/platforms/powermac/feature.c b/arch/powerpc/platforms/powermac/feature.c index ed58928469b5..ae62d432db8b 100644 --- a/arch/powerpc/platforms/powermac/feature.c +++ b/arch/powerpc/platforms/powermac/feature.c @@ -37,6 +37,8 @@ #include <asm/pci-bridge.h> #include <asm/pmac_low_i2c.h> +#include "pmac.h" + #undef DEBUG_FEATURE #ifdef DEBUG_FEATURE @@ -132,8 +134,10 @@ static struct pmac_mb_def pmac_mb; * Here are the chip specific feature functions */ -static inline int simple_feature_tweak(struct device_node *node, int type, - int reg, u32 mask, int value) +#ifndef CONFIG_PPC64 + +static int simple_feature_tweak(struct device_node *node, int type, int reg, + u32 mask, int value) { struct macio_chip* macio; unsigned long flags; @@ -152,8 +156,6 @@ static inline int simple_feature_tweak(struct device_node *node, int type, return 0; } -#ifndef CONFIG_PPC64 - static long ohare_htw_scc_enable(struct device_node *node, long param, long value) { diff --git a/arch/powerpc/platforms/powermac/setup.c b/arch/powerpc/platforms/powermac/setup.c index 0c41f4b005bc..6de1cd5d8a58 100644 --- a/arch/powerpc/platforms/powermac/setup.c +++ b/arch/powerpc/platforms/powermac/setup.c @@ -45,7 +45,7 @@ #include <linux/root_dev.h> #include <linux/bitops.h> #include <linux/suspend.h> -#include <linux/of_device.h> +#include <linux/of.h> #include <linux/of_platform.h> #include <asm/reg.h> diff --git a/arch/powerpc/platforms/powermac/time.c b/arch/powerpc/platforms/powermac/time.c index 4c5790aff1b5..8633891b7aa5 100644 --- a/arch/powerpc/platforms/powermac/time.c +++ b/arch/powerpc/platforms/powermac/time.c @@ -26,8 +26,8 @@ #include <linux/rtc.h> #include <linux/of_address.h> +#include <asm/early_ioremap.h> #include <asm/sections.h> -#include <asm/io.h> #include <asm/machdep.h> #include <asm/time.h> #include <asm/nvram.h> @@ -182,7 +182,7 @@ static int __init via_calibrate_decr(void) return 0; } of_node_put(vias); - via = ioremap(rsrc.start, resource_size(&rsrc)); + via = early_ioremap(rsrc.start, resource_size(&rsrc)); if (via == NULL) { printk(KERN_ERR "Failed to map VIA for timer calibration !\n"); return 0; @@ -207,7 +207,7 @@ static int __init via_calibrate_decr(void) ppc_tb_freq = (dstart - dend) * 100 / 6; - iounmap(via); + early_iounmap((void *)via, resource_size(&rsrc)); return 1; } diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c index a83cb679dd59..af3a5d37a149 100644 --- a/arch/powerpc/platforms/powernv/eeh-powernv.c +++ b/arch/powerpc/platforms/powernv/eeh-powernv.c @@ -855,8 +855,7 @@ static int pnv_eeh_bridge_reset(struct pci_dev *pdev, int option) struct pci_controller *hose = pci_bus_to_host(pdev->bus); struct pnv_phb *phb = hose->private_data; struct device_node *dn = pci_device_to_OF_node(pdev); - uint64_t id = PCI_SLOT_ID(phb->opal_id, - (pdev->bus->number << 8) | pdev->devfn); + uint64_t id = PCI_SLOT_ID(phb->opal_id, pci_dev_id(pdev)); uint8_t scope; int64_t rc; diff --git a/arch/powerpc/platforms/powernv/ocxl.c b/arch/powerpc/platforms/powernv/ocxl.c index 629067781cec..64a9c7125c29 100644 --- a/arch/powerpc/platforms/powernv/ocxl.c +++ b/arch/powerpc/platforms/powernv/ocxl.c @@ -449,7 +449,7 @@ int pnv_ocxl_spa_setup(struct pci_dev *dev, void *spa_mem, int PE_mask, if (!data) return -ENOMEM; - bdfn = (dev->bus->number << 8) | dev->devfn; + bdfn = pci_dev_id(dev); rc = opal_npu_spa_setup(phb->opal_id, bdfn, virt_to_phys(spa_mem), PE_mask); if (rc) { diff --git a/arch/powerpc/platforms/powernv/opal-imc.c b/arch/powerpc/platforms/powernv/opal-imc.c index 348a8cdaecd6..828fc4d88471 100644 --- a/arch/powerpc/platforms/powernv/opal-imc.c +++ b/arch/powerpc/platforms/powernv/opal-imc.c @@ -11,7 +11,6 @@ #include <linux/platform_device.h> #include <linux/of.h> #include <linux/of_address.h> -#include <linux/of_platform.h> #include <linux/crash_dump.h> #include <linux/debugfs.h> #include <asm/opal.h> diff --git a/arch/powerpc/platforms/powernv/opal-prd.c b/arch/powerpc/platforms/powernv/opal-prd.c index 113bdb151f68..327e2f76905d 100644 --- a/arch/powerpc/platforms/powernv/opal-prd.c +++ b/arch/powerpc/platforms/powernv/opal-prd.c @@ -24,13 +24,20 @@ #include <linux/uaccess.h> +struct opal_prd_msg { + union { + struct opal_prd_msg_header header; + DECLARE_FLEX_ARRAY(u8, data); + }; +}; + /* * The msg member must be at the end of the struct, as it's followed by the * message data. */ struct opal_prd_msg_queue_item { - struct list_head list; - struct opal_prd_msg_header msg; + struct list_head list; + struct opal_prd_msg msg; }; static struct device_node *prd_node; @@ -156,7 +163,7 @@ static ssize_t opal_prd_read(struct file *file, char __user *buf, int rc; /* we need at least a header's worth of data */ - if (count < sizeof(item->msg)) + if (count < sizeof(item->msg.header)) return -EINVAL; if (*ppos) @@ -186,7 +193,7 @@ static ssize_t opal_prd_read(struct file *file, char __user *buf, return -EINTR; } - size = be16_to_cpu(item->msg.size); + size = be16_to_cpu(item->msg.header.size); if (size > count) { err = -EINVAL; goto err_requeue; @@ -214,8 +221,8 @@ static ssize_t opal_prd_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { struct opal_prd_msg_header hdr; + struct opal_prd_msg *msg; ssize_t size; - void *msg; int rc; size = sizeof(hdr); @@ -247,12 +254,12 @@ static ssize_t opal_prd_write(struct file *file, const char __user *buf, static int opal_prd_release(struct inode *inode, struct file *file) { - struct opal_prd_msg_header msg; + struct opal_prd_msg msg; - msg.size = cpu_to_be16(sizeof(msg)); - msg.type = OPAL_PRD_MSG_TYPE_FINI; + msg.header.size = cpu_to_be16(sizeof(msg)); + msg.header.type = OPAL_PRD_MSG_TYPE_FINI; - opal_prd_msg((struct opal_prd_msg *)&msg); + opal_prd_msg(&msg); atomic_xchg(&prd_usage, 0); @@ -352,7 +359,7 @@ static int opal_prd_msg_notifier(struct notifier_block *nb, if (!item) return -ENOMEM; - memcpy(&item->msg, msg->params, msg_size); + memcpy(&item->msg.data, msg->params, msg_size); spin_lock_irqsave(&opal_prd_msg_queue_lock, flags); list_add_tail(&item->list, &opal_prd_msg_queue); diff --git a/arch/powerpc/platforms/powernv/opal-rtc.c b/arch/powerpc/platforms/powernv/opal-rtc.c index a9bcf9217e64..79011a263aa6 100644 --- a/arch/powerpc/platforms/powernv/opal-rtc.c +++ b/arch/powerpc/platforms/powernv/opal-rtc.c @@ -11,8 +11,9 @@ #include <linux/bcd.h> #include <linux/rtc.h> #include <linux/delay.h> -#include <linux/platform_device.h> +#include <linux/of.h> #include <linux/of_platform.h> +#include <linux/platform_device.h> #include <asm/opal.h> #include <asm/firmware.h> diff --git a/arch/powerpc/platforms/powernv/opal-secvar.c b/arch/powerpc/platforms/powernv/opal-secvar.c index a8436bf35e2f..6ac410f4d3c7 100644 --- a/arch/powerpc/platforms/powernv/opal-secvar.c +++ b/arch/powerpc/platforms/powernv/opal-secvar.c @@ -12,8 +12,8 @@ #define pr_fmt(fmt) "secvar: "fmt #include <linux/types.h> +#include <linux/of.h> #include <linux/platform_device.h> -#include <linux/of_platform.h> #include <asm/opal.h> #include <asm/secvar.h> #include <asm/secure_boot.h> diff --git a/arch/powerpc/platforms/powernv/opal-sensor.c b/arch/powerpc/platforms/powernv/opal-sensor.c index 3192c614a1e1..8880a1c14573 100644 --- a/arch/powerpc/platforms/powernv/opal-sensor.c +++ b/arch/powerpc/platforms/powernv/opal-sensor.c @@ -6,7 +6,9 @@ */ #include <linux/delay.h> +#include <linux/of.h> #include <linux/of_platform.h> +#include <linux/platform_device.h> #include <asm/opal.h> #include <asm/machdep.h> diff --git a/arch/powerpc/platforms/powernv/opal-xscom.c b/arch/powerpc/platforms/powernv/opal-xscom.c index 6b4eed2ef4fa..262cd6fac907 100644 --- a/arch/powerpc/platforms/powernv/opal-xscom.c +++ b/arch/powerpc/platforms/powernv/opal-xscom.c @@ -168,7 +168,7 @@ static int scom_debug_init_one(struct dentry *root, struct device_node *dn, ent->path.size = strlen((char *)ent->path.data); dir = debugfs_create_dir(ent->name, root); - if (!dir) { + if (IS_ERR(dir)) { kfree(ent->path.data); kfree(ent); return -1; @@ -190,7 +190,7 @@ static int scom_debug_init(void) return 0; root = debugfs_create_dir("scom", arch_debugfs_dir); - if (!root) + if (IS_ERR(root)) return -1; rc = 0; diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index cb637827bc58..28fac4770073 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -997,14 +997,14 @@ static void pnv_pci_ioda_dma_dev_setup(struct pci_dev *pdev) struct pnv_ioda_pe *pe; /* Check if the BDFN for this device is associated with a PE yet */ - pe = pnv_pci_bdfn_to_pe(phb, pdev->devfn | (pdev->bus->number << 8)); + pe = pnv_pci_bdfn_to_pe(phb, pci_dev_id(pdev)); if (!pe) { /* VF PEs should be pre-configured in pnv_pci_sriov_enable() */ if (WARN_ON(pdev->is_virtfn)) return; pnv_pci_configure_bus(pdev->bus); - pe = pnv_pci_bdfn_to_pe(phb, pdev->devfn | (pdev->bus->number << 8)); + pe = pnv_pci_bdfn_to_pe(phb, pci_dev_id(pdev)); pci_info(pdev, "Configured PE#%x\n", pe ? pe->pe_number : 0xfffff); @@ -2526,7 +2526,7 @@ static struct iommu_group *pnv_pci_device_group(struct pci_controller *hose, if (WARN_ON(!phb)) return ERR_PTR(-ENODEV); - pe = pnv_pci_bdfn_to_pe(phb, pdev->devfn | (pdev->bus->number << 8)); + pe = pnv_pci_bdfn_to_pe(phb, pci_dev_id(pdev)); if (!pe) return ERR_PTR(-ENODEV); diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c index 5e9c6b55809f..4dbb47ddbdcc 100644 --- a/arch/powerpc/platforms/powernv/setup.c +++ b/arch/powerpc/platforms/powernv/setup.c @@ -482,15 +482,7 @@ static void pnv_kexec_cpu_down(int crash_shutdown, int secondary) #ifdef CONFIG_MEMORY_HOTPLUG static unsigned long pnv_memory_block_size(void) { - /* - * We map the kernel linear region with 1GB large pages on radix. For - * memory hot unplug to work our memory block size must be at least - * this size. - */ - if (radix_enabled()) - return radix_mem_block_size; - else - return 256UL * 1024 * 1024; + return memory_block_size; } #endif diff --git a/arch/powerpc/platforms/ps3/repository.c b/arch/powerpc/platforms/ps3/repository.c index 205763061a2d..1abe33fbe529 100644 --- a/arch/powerpc/platforms/ps3/repository.c +++ b/arch/powerpc/platforms/ps3/repository.c @@ -73,9 +73,9 @@ static void _dump_node(unsigned int lpar_id, u64 n1, u64 n2, u64 n3, u64 n4, static u64 make_first_field(const char *text, u64 index) { - u64 n; + u64 n = 0; - strncpy((char *)&n, text, 8); + memcpy((char *)&n, text, strnlen(text, sizeof(n))); return PS3_VENDOR_ID_NONE + (n >> 32) + index; } diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c index 1a3cb313976a..e62835a12d73 100644 --- a/arch/powerpc/platforms/pseries/hotplug-cpu.c +++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c @@ -398,6 +398,14 @@ static int dlpar_online_cpu(struct device_node *dn) for_each_present_cpu(cpu) { if (get_hard_smp_processor_id(cpu) != thread) continue; + + if (!topology_is_primary_thread(cpu)) { + if (cpu_smt_control != CPU_SMT_ENABLED) + break; + if (!topology_smt_thread_allowed(cpu)) + break; + } + cpu_maps_update_done(); find_and_update_cpu_nid(cpu); rc = device_online(get_cpu_device(cpu)); @@ -845,15 +853,9 @@ static struct notifier_block pseries_smp_nb = { .notifier_call = pseries_smp_notifier, }; -static int __init pseries_cpu_hotplug_init(void) +void __init pseries_cpu_hotplug_init(void) { int qcss_tok; - unsigned int node; - -#ifdef CONFIG_ARCH_CPU_PROBE_RELEASE - ppc_md.cpu_probe = dlpar_cpu_probe; - ppc_md.cpu_release = dlpar_cpu_release; -#endif /* CONFIG_ARCH_CPU_PROBE_RELEASE */ rtas_stop_self_token = rtas_function_token(RTAS_FN_STOP_SELF); qcss_tok = rtas_function_token(RTAS_FN_QUERY_CPU_STOPPED_STATE); @@ -862,12 +864,22 @@ static int __init pseries_cpu_hotplug_init(void) qcss_tok == RTAS_UNKNOWN_SERVICE) { printk(KERN_INFO "CPU Hotplug not supported by firmware " "- disabling.\n"); - return 0; + return; } smp_ops->cpu_offline_self = pseries_cpu_offline_self; smp_ops->cpu_disable = pseries_cpu_disable; smp_ops->cpu_die = pseries_cpu_die; +} + +static int __init pseries_dlpar_init(void) +{ + unsigned int node; + +#ifdef CONFIG_ARCH_CPU_PROBE_RELEASE + ppc_md.cpu_probe = dlpar_cpu_probe; + ppc_md.cpu_release = dlpar_cpu_release; +#endif /* CONFIG_ARCH_CPU_PROBE_RELEASE */ /* Processors can be added/removed only on LPAR */ if (firmware_has_feature(FW_FEATURE_LPAR)) { @@ -886,4 +898,4 @@ static int __init pseries_cpu_hotplug_init(void) return 0; } -machine_arch_initcall(pseries, pseries_cpu_hotplug_init); +machine_arch_initcall(pseries, pseries_dlpar_init); diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c index 9c62c2c3b3d0..aa4042dcd6d4 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -21,54 +21,6 @@ #include <asm/drmem.h> #include "pseries.h" -unsigned long pseries_memory_block_size(void) -{ - struct device_node *np; - u64 memblock_size = MIN_MEMORY_BLOCK_SIZE; - struct resource r; - - np = of_find_node_by_path("/ibm,dynamic-reconfiguration-memory"); - if (np) { - int len; - int size_cells; - const __be32 *prop; - - size_cells = of_n_size_cells(np); - - prop = of_get_property(np, "ibm,lmb-size", &len); - if (prop && len >= size_cells * sizeof(__be32)) - memblock_size = of_read_number(prop, size_cells); - of_node_put(np); - - } else if (machine_is(pseries)) { - /* This fallback really only applies to pseries */ - unsigned int memzero_size = 0; - - np = of_find_node_by_path("/memory@0"); - if (np) { - if (!of_address_to_resource(np, 0, &r)) - memzero_size = resource_size(&r); - of_node_put(np); - } - - if (memzero_size) { - /* We now know the size of memory@0, use this to find - * the first memoryblock and get its size. - */ - char buf[64]; - - sprintf(buf, "/memory@%x", memzero_size); - np = of_find_node_by_path(buf); - if (np) { - if (!of_address_to_resource(np, 0, &r)) - memblock_size = resource_size(&r); - of_node_put(np); - } - } - } - return memblock_size; -} - static void dlpar_free_property(struct property *prop) { kfree(prop->name); @@ -283,7 +235,7 @@ static int dlpar_offline_lmb(struct drmem_lmb *lmb) static int pseries_remove_memblock(unsigned long base, unsigned long memblock_size) { - unsigned long block_sz, start_pfn; + unsigned long start_pfn; int sections_per_block; int i; @@ -294,8 +246,7 @@ static int pseries_remove_memblock(unsigned long base, unsigned long memblock_si if (!pfn_valid(start_pfn)) goto out; - block_sz = pseries_memory_block_size(); - sections_per_block = block_sz / MIN_MEMORY_BLOCK_SIZE; + sections_per_block = memory_block_size / MIN_MEMORY_BLOCK_SIZE; for (i = 0; i < sections_per_block; i++) { __remove_memory(base, MIN_MEMORY_BLOCK_SIZE); @@ -354,7 +305,6 @@ static int dlpar_add_lmb(struct drmem_lmb *); static int dlpar_remove_lmb(struct drmem_lmb *lmb) { struct memory_block *mem_block; - unsigned long block_sz; int rc; if (!lmb_is_removable(lmb)) @@ -370,13 +320,11 @@ static int dlpar_remove_lmb(struct drmem_lmb *lmb) return rc; } - block_sz = pseries_memory_block_size(); - - __remove_memory(lmb->base_addr, block_sz); + __remove_memory(lmb->base_addr, memory_block_size); put_device(&mem_block->dev); /* Update memory regions for memory remove */ - memblock_remove(lmb->base_addr, block_sz); + memblock_remove(lmb->base_addr, memory_block_size); invalidate_lmb_associativity_index(lmb); lmb->flags &= ~DRCONF_MEM_ASSIGNED; @@ -637,7 +585,7 @@ static int dlpar_add_lmb(struct drmem_lmb *lmb) nid = first_online_node; /* Add the memory */ - rc = __add_memory(nid, lmb->base_addr, block_sz, MHP_NONE); + rc = __add_memory(nid, lmb->base_addr, block_sz, MHP_MEMMAP_ON_MEMORY); if (rc) { invalidate_lmb_associativity_index(lmb); return rc; diff --git a/arch/powerpc/platforms/pseries/hvCall.S b/arch/powerpc/platforms/pseries/hvCall.S index 35254ac7af5e..bae45b358a09 100644 --- a/arch/powerpc/platforms/pseries/hvCall.S +++ b/arch/powerpc/platforms/pseries/hvCall.S @@ -91,7 +91,7 @@ BEGIN_FTR_SECTION; \ b 1f; \ END_FTR_SECTION(0, 1); \ LOAD_REG_ADDR(r12, hcall_tracepoint_refcount) ; \ - std r12,32(r1); \ + ld r12,0(r12); \ cmpdi r12,0; \ bne- LABEL; \ 1: diff --git a/arch/powerpc/platforms/pseries/ibmebus.c b/arch/powerpc/platforms/pseries/ibmebus.c index 44703f13985b..998e3aff2457 100644 --- a/arch/powerpc/platforms/pseries/ibmebus.c +++ b/arch/powerpc/platforms/pseries/ibmebus.c @@ -47,6 +47,7 @@ #include <linux/slab.h> #include <linux/stat.h> #include <linux/of_platform.h> +#include <linux/platform_device.h> #include <asm/ibmebus.h> #include <asm/machdep.h> @@ -460,6 +461,7 @@ static int __init ibmebus_bus_init(void) if (err) { printk(KERN_WARNING "%s: device_register returned %i\n", __func__, err); + put_device(&ibmebus_bus_device); bus_unregister(&ibmebus_bus_type); return err; diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index d593a7227dc9..16d93b580f61 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -395,8 +395,6 @@ static LIST_HEAD(dma_win_list); static DEFINE_SPINLOCK(dma_win_list_lock); /* protects initializing window twice for same device */ static DEFINE_MUTEX(dma_win_init_mutex); -#define DIRECT64_PROPNAME "linux,direct64-ddr-window-info" -#define DMA64_PROPNAME "linux,dma64-ddr-window-info" static int tce_clearrange_multi_pSeriesLP(unsigned long start_pfn, unsigned long num_pfn, const void *arg) diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index 2eab323f6970..f2cb62148f36 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -41,6 +41,7 @@ #include <asm/kexec.h> #include <asm/fadump.h> #include <asm/dtl.h> +#include <asm/vphn.h> #include "pseries.h" @@ -639,16 +640,8 @@ static const struct proc_ops vcpudispatch_stats_freq_proc_ops = { static int __init vcpudispatch_stats_procfs_init(void) { - /* - * Avoid smp_processor_id while preemptible. All CPUs should have - * the same value for lppaca_shared_proc. - */ - preempt_disable(); - if (!lppaca_shared_proc(get_lppaca())) { - preempt_enable(); + if (!lppaca_shared_proc()) return 0; - } - preempt_enable(); if (!proc_create("powerpc/vcpudispatch_stats", 0600, NULL, &vcpudispatch_stats_proc_ops)) diff --git a/arch/powerpc/platforms/pseries/lparcfg.c b/arch/powerpc/platforms/pseries/lparcfg.c index 8acc70509520..1c151d77e74b 100644 --- a/arch/powerpc/platforms/pseries/lparcfg.c +++ b/arch/powerpc/platforms/pseries/lparcfg.c @@ -206,7 +206,7 @@ static void parse_ppp_data(struct seq_file *m) ppp_data.active_system_procs); /* pool related entries are appropriate for shared configs */ - if (lppaca_shared_proc(get_lppaca())) { + if (lppaca_shared_proc()) { unsigned long pool_idle_time, pool_procs; seq_printf(m, "pool=%d\n", ppp_data.pool_num); @@ -560,7 +560,7 @@ static int pseries_lparcfg_data(struct seq_file *m, void *v) partition_potential_processors); seq_printf(m, "shared_processor_mode=%d\n", - lppaca_shared_proc(get_lppaca())); + lppaca_shared_proc()); #ifdef CONFIG_PPC_64S_HASH_MMU if (!radix_enabled()) diff --git a/arch/powerpc/platforms/pseries/plpks.c b/arch/powerpc/platforms/pseries/plpks.c index b0658ea3eccb..2d40304eb6c1 100644 --- a/arch/powerpc/platforms/pseries/plpks.c +++ b/arch/powerpc/platforms/pseries/plpks.c @@ -194,7 +194,7 @@ static struct plpks_auth *construct_auth(u8 consumer) return auth; } -/** +/* * Label is combination of label attributes + name. * Label attributes are used internally by kernel and not exposed to the user. */ diff --git a/arch/powerpc/platforms/pseries/pseries.h b/arch/powerpc/platforms/pseries/pseries.h index f8bce40ebd0c..8376f03f932a 100644 --- a/arch/powerpc/platforms/pseries/pseries.h +++ b/arch/powerpc/platforms/pseries/pseries.h @@ -75,11 +75,13 @@ static inline int dlpar_hp_pmem(struct pseries_hp_errorlog *hp_elog) #ifdef CONFIG_HOTPLUG_CPU int dlpar_cpu(struct pseries_hp_errorlog *hp_elog); +void pseries_cpu_hotplug_init(void); #else static inline int dlpar_cpu(struct pseries_hp_errorlog *hp_elog) { return -EOPNOTSUPP; } +static inline void pseries_cpu_hotplug_init(void) { } #endif /* PCI root bridge prepare function override for pseries */ @@ -90,8 +92,6 @@ extern struct pci_controller_ops pseries_pci_controller_ops; int pseries_msi_allocate_domains(struct pci_controller *phb); void pseries_msi_free_domains(struct pci_controller *phb); -unsigned long pseries_memory_block_size(void); - extern int CMO_PrPSP; extern int CMO_SecPSP; extern unsigned long CMO_PageSize; diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index e2a57cfa6c83..ecea85c74c43 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -816,6 +816,8 @@ static void __init pSeries_setup_arch(void) /* Discover PIC type and setup ppc_md accordingly */ smp_init_pseries(); + // Setup CPU hotplug callbacks + pseries_cpu_hotplug_init(); if (radix_enabled() && !mmu_has_feature(MMU_FTR_GTSE)) if (!firmware_has_feature(FW_FEATURE_RPT_INVALIDATE)) @@ -847,7 +849,7 @@ static void __init pSeries_setup_arch(void) if (firmware_has_feature(FW_FEATURE_LPAR)) { vpa_init(boot_cpuid); - if (lppaca_shared_proc(get_lppaca())) { + if (lppaca_shared_proc()) { static_branch_enable(&shared_processor); pv_spinlocks_init(); #ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING @@ -1116,6 +1118,13 @@ static int pSeries_pci_probe_mode(struct pci_bus *bus) return PCI_PROBE_NORMAL; } +#ifdef CONFIG_MEMORY_HOTPLUG +static unsigned long pseries_memory_block_size(void) +{ + return memory_block_size; +} +#endif + struct pci_controller_ops pseries_pci_controller_ops = { .probe_mode = pSeries_pci_probe_mode, #ifdef CONFIG_SPAPR_TCE_IOMMU diff --git a/arch/powerpc/platforms/pseries/vas.c b/arch/powerpc/platforms/pseries/vas.c index 3fbc2a6aa319..e25ac52acf50 100644 --- a/arch/powerpc/platforms/pseries/vas.c +++ b/arch/powerpc/platforms/pseries/vas.c @@ -17,6 +17,7 @@ #include <asm/hvcall.h> #include <asm/plpar_wrappers.h> #include <asm/firmware.h> +#include <asm/vphn.h> #include <asm/vas.h> #include "vas.h" diff --git a/arch/powerpc/platforms/pseries/vphn.c b/arch/powerpc/platforms/pseries/vphn.c index cca474a2c396..3f85ece3c872 100644 --- a/arch/powerpc/platforms/pseries/vphn.c +++ b/arch/powerpc/platforms/pseries/vphn.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <asm/byteorder.h> -#include <asm/lppaca.h> +#include <asm/vphn.h> /* * The associativity domain numbers are returned from the hypervisor as a diff --git a/arch/powerpc/sysdev/cpm2.c b/arch/powerpc/sysdev/cpm2.c index 915f4d3991c3..14cc5ea936c0 100644 --- a/arch/powerpc/sysdev/cpm2.c +++ b/arch/powerpc/sysdev/cpm2.c @@ -37,11 +37,9 @@ #include <asm/io.h> #include <asm/irq.h> -#include <asm/mpc8260.h> #include <asm/page.h> #include <asm/cpm2.h> #include <asm/rheap.h> -#include <asm/fs_pd.h> #include <sysdev/fsl_soc.h> @@ -119,9 +117,9 @@ void __cpm2_setbrg(uint brg, uint rate, uint clk, int div16, int src) /* This is good enough to get SMCs running..... */ if (brg < 4) { - bp = cpm2_map_size(im_brgc1, 16); + bp = &cpm2_immr->im_brgc1; } else { - bp = cpm2_map_size(im_brgc5, 16); + bp = &cpm2_immr->im_brgc5; brg -= 4; } bp += brg; @@ -131,7 +129,6 @@ void __cpm2_setbrg(uint brg, uint rate, uint clk, int div16, int src) val |= CPM_BRG_DIV16; out_be32(bp, val); - cpm2_unmap(bp); } EXPORT_SYMBOL(__cpm2_setbrg); @@ -140,7 +137,6 @@ int __init cpm2_clk_setup(enum cpm_clk_target target, int clock, int mode) int ret = 0; int shift; int i, bits = 0; - cpmux_t __iomem *im_cpmux; u32 __iomem *reg; u32 mask = 7; @@ -203,35 +199,33 @@ int __init cpm2_clk_setup(enum cpm_clk_target target, int clock, int mode) {CPM_CLK_SCC4, CPM_CLK8, 7}, }; - im_cpmux = cpm2_map(im_cpmux); - switch (target) { case CPM_CLK_SCC1: - reg = &im_cpmux->cmx_scr; + reg = &cpm2_immr->im_cpmux.cmx_scr; shift = 24; break; case CPM_CLK_SCC2: - reg = &im_cpmux->cmx_scr; + reg = &cpm2_immr->im_cpmux.cmx_scr; shift = 16; break; case CPM_CLK_SCC3: - reg = &im_cpmux->cmx_scr; + reg = &cpm2_immr->im_cpmux.cmx_scr; shift = 8; break; case CPM_CLK_SCC4: - reg = &im_cpmux->cmx_scr; + reg = &cpm2_immr->im_cpmux.cmx_scr; shift = 0; break; case CPM_CLK_FCC1: - reg = &im_cpmux->cmx_fcr; + reg = &cpm2_immr->im_cpmux.cmx_fcr; shift = 24; break; case CPM_CLK_FCC2: - reg = &im_cpmux->cmx_fcr; + reg = &cpm2_immr->im_cpmux.cmx_fcr; shift = 16; break; case CPM_CLK_FCC3: - reg = &im_cpmux->cmx_fcr; + reg = &cpm2_immr->im_cpmux.cmx_fcr; shift = 8; break; default: @@ -261,7 +255,6 @@ int __init cpm2_clk_setup(enum cpm_clk_target target, int clock, int mode) out_be32(reg, (in_be32(reg) & ~mask) | bits); - cpm2_unmap(im_cpmux); return ret; } @@ -270,7 +263,6 @@ int __init cpm2_smc_clk_setup(enum cpm_clk_target target, int clock) int ret = 0; int shift; int i, bits = 0; - cpmux_t __iomem *im_cpmux; u8 __iomem *reg; u8 mask = 3; @@ -285,16 +277,14 @@ int __init cpm2_smc_clk_setup(enum cpm_clk_target target, int clock) {CPM_CLK_SMC2, CPM_CLK15, 3}, }; - im_cpmux = cpm2_map(im_cpmux); - switch (target) { case CPM_CLK_SMC1: - reg = &im_cpmux->cmx_smr; + reg = &cpm2_immr->im_cpmux.cmx_smr; mask = 3; shift = 4; break; case CPM_CLK_SMC2: - reg = &im_cpmux->cmx_smr; + reg = &cpm2_immr->im_cpmux.cmx_smr; mask = 3; shift = 0; break; @@ -317,7 +307,6 @@ int __init cpm2_smc_clk_setup(enum cpm_clk_target target, int clock) out_8(reg, (in_8(reg) & ~mask) | bits); - cpm2_unmap(im_cpmux); return ret; } diff --git a/arch/powerpc/sysdev/cpm2_pic.c b/arch/powerpc/sysdev/cpm2_pic.c index cb9ba4ef557a..e14493685fe8 100644 --- a/arch/powerpc/sysdev/cpm2_pic.c +++ b/arch/powerpc/sysdev/cpm2_pic.c @@ -33,9 +33,7 @@ #include <linux/irqdomain.h> #include <asm/immap_cpm2.h> -#include <asm/mpc8260.h> #include <asm/io.h> -#include <asm/fs_pd.h> #include "cpm2_pic.h" @@ -231,7 +229,7 @@ void cpm2_pic_init(struct device_node *node) { int i; - cpm2_intctl = cpm2_map(im_intctl); + cpm2_intctl = &cpm2_immr->im_intctl; /* Clear the CPM IRQ controller, in case it has any bits set * from the bootloader diff --git a/arch/powerpc/sysdev/cpm_common.c b/arch/powerpc/sysdev/cpm_common.c index 8234013a8772..47db732981a8 100644 --- a/arch/powerpc/sysdev/cpm_common.c +++ b/arch/powerpc/sysdev/cpm_common.c @@ -15,11 +15,9 @@ */ #include <linux/init.h> -#include <linux/of_device.h> #include <linux/spinlock.h> #include <linux/export.h> #include <linux/of.h> -#include <linux/of_address.h> #include <linux/slab.h> #include <asm/udbg.h> diff --git a/arch/powerpc/sysdev/cpm_gpio.c b/arch/powerpc/sysdev/cpm_gpio.c index 0695d26bd301..40f57111e93e 100644 --- a/arch/powerpc/sysdev/cpm_gpio.c +++ b/arch/powerpc/sysdev/cpm_gpio.c @@ -9,7 +9,8 @@ */ #include <linux/module.h> -#include <linux/of_device.h> +#include <linux/of.h> +#include <linux/platform_device.h> #include <asm/cpm.h> #ifdef CONFIG_8xx_GPIO diff --git a/arch/powerpc/sysdev/dcr-low.S b/arch/powerpc/sysdev/dcr-low.S index 329b9c4ae542..e8401b205d38 100644 --- a/arch/powerpc/sysdev/dcr-low.S +++ b/arch/powerpc/sysdev/dcr-low.S @@ -5,10 +5,10 @@ * Copyright (c) 2004 Eugene Surovegin <ebs@ebshome.net> */ +#include <linux/export.h> #include <asm/ppc_asm.h> #include <asm/processor.h> #include <asm/bug.h> -#include <asm/export.h> #define DCR_ACCESS_PROLOG(table) \ cmplwi cr0,r3,1024; \ diff --git a/arch/powerpc/sysdev/ehv_pic.c b/arch/powerpc/sysdev/ehv_pic.c index c7327b836d2b..040827671d21 100644 --- a/arch/powerpc/sysdev/ehv_pic.c +++ b/arch/powerpc/sysdev/ehv_pic.c @@ -42,33 +42,33 @@ static u32 __iomem *mpic_percpu_base_vaddr; * Linux descriptor level callbacks */ -void ehv_pic_unmask_irq(struct irq_data *d) +static void ehv_pic_unmask_irq(struct irq_data *d) { unsigned int src = virq_to_hw(d->irq); ev_int_set_mask(src, 0); } -void ehv_pic_mask_irq(struct irq_data *d) +static void ehv_pic_mask_irq(struct irq_data *d) { unsigned int src = virq_to_hw(d->irq); ev_int_set_mask(src, 1); } -void ehv_pic_end_irq(struct irq_data *d) +static void ehv_pic_end_irq(struct irq_data *d) { unsigned int src = virq_to_hw(d->irq); ev_int_eoi(src); } -void ehv_pic_direct_end_irq(struct irq_data *d) +static void ehv_pic_direct_end_irq(struct irq_data *d) { out_be32(mpic_percpu_base_vaddr + MPIC_EOI / 4, 0); } -int ehv_pic_set_affinity(struct irq_data *d, const struct cpumask *dest, +static int ehv_pic_set_affinity(struct irq_data *d, const struct cpumask *dest, bool force) { unsigned int src = virq_to_hw(d->irq); @@ -109,7 +109,7 @@ static unsigned int ehv_pic_type_to_vecpri(unsigned int type) } } -int ehv_pic_set_irq_type(struct irq_data *d, unsigned int flow_type) +static int ehv_pic_set_irq_type(struct irq_data *d, unsigned int flow_type) { unsigned int src = virq_to_hw(d->irq); unsigned int vecpri, vold, vnew, prio, cpu_dest; diff --git a/arch/powerpc/sysdev/fsl_pci.c b/arch/powerpc/sysdev/fsl_pci.c index 6daf620b63a4..3868483fbe29 100644 --- a/arch/powerpc/sysdev/fsl_pci.c +++ b/arch/powerpc/sysdev/fsl_pci.c @@ -519,7 +519,7 @@ void fsl_pcibios_fixup_bus(struct pci_bus *bus) } } -int fsl_add_bridge(struct platform_device *pdev, int is_primary) +static int fsl_add_bridge(struct platform_device *pdev, int is_primary) { int len; struct pci_controller *hose; @@ -767,7 +767,7 @@ static int __init mpc83xx_pcie_setup(struct pci_controller *hose, u32 cfg_bar; int ret = -ENOMEM; - pcie = zalloc_maybe_bootmem(sizeof(*pcie), GFP_KERNEL); + pcie = kzalloc(sizeof(*pcie), GFP_KERNEL); if (!pcie) return ret; diff --git a/arch/powerpc/sysdev/fsl_pci.h b/arch/powerpc/sysdev/fsl_pci.h index 093a875d7d1e..3bc4ab9d8341 100644 --- a/arch/powerpc/sysdev/fsl_pci.h +++ b/arch/powerpc/sysdev/fsl_pci.h @@ -112,7 +112,6 @@ struct ccsr_pci { }; -extern int fsl_add_bridge(struct platform_device *pdev, int is_primary); extern void fsl_pcibios_fixup_bus(struct pci_bus *bus); extern void fsl_pcibios_fixup_phb(struct pci_controller *phb); extern int mpc83xx_add_bridge(struct device_node *dev); diff --git a/arch/powerpc/sysdev/fsl_pmc.c b/arch/powerpc/sysdev/fsl_pmc.c index 76896de970ca..9f6dd11c1344 100644 --- a/arch/powerpc/sysdev/fsl_pmc.c +++ b/arch/powerpc/sysdev/fsl_pmc.c @@ -13,9 +13,9 @@ #include <linux/export.h> #include <linux/suspend.h> #include <linux/delay.h> -#include <linux/device.h> +#include <linux/mod_devicetable.h> #include <linux/of_address.h> -#include <linux/of_platform.h> +#include <linux/platform_device.h> struct pmc_regs { __be32 devdisr; diff --git a/arch/powerpc/sysdev/fsl_rio.c b/arch/powerpc/sysdev/fsl_rio.c index 0331962bc6d2..f9b214b299e7 100644 --- a/arch/powerpc/sysdev/fsl_rio.c +++ b/arch/powerpc/sysdev/fsl_rio.c @@ -23,16 +23,17 @@ #include <linux/types.h> #include <linux/dma-mapping.h> #include <linux/interrupt.h> -#include <linux/device.h> +#include <linux/of.h> #include <linux/of_address.h> #include <linux/of_irq.h> -#include <linux/of_platform.h> +#include <linux/platform_device.h> #include <linux/delay.h> #include <linux/slab.h> #include <linux/io.h> #include <linux/uaccess.h> #include <asm/machdep.h> +#include <asm/rio.h> #include "fsl_rio.h" @@ -303,8 +304,8 @@ static void fsl_rio_inbound_mem_init(struct rio_priv *priv) out_be32(&priv->inb_atmu_regs[i].riwar, 0); } -int fsl_map_inb_mem(struct rio_mport *mport, dma_addr_t lstart, - u64 rstart, u64 size, u32 flags) +static int fsl_map_inb_mem(struct rio_mport *mport, dma_addr_t lstart, + u64 rstart, u64 size, u32 flags) { struct rio_priv *priv = mport->priv; u32 base_size; @@ -354,7 +355,7 @@ int fsl_map_inb_mem(struct rio_mport *mport, dma_addr_t lstart, return 0; } -void fsl_unmap_inb_mem(struct rio_mport *mport, dma_addr_t lstart) +static void fsl_unmap_inb_mem(struct rio_mport *mport, dma_addr_t lstart) { u32 win_start_shift, base_start_shift; struct rio_priv *priv = mport->priv; @@ -442,7 +443,7 @@ static inline void fsl_rio_info(struct device *dev, u32 ccsr) * master port with system-specific info, and registers the * master port with the RapidIO subsystem. */ -int fsl_rio_setup(struct platform_device *dev) +static int fsl_rio_setup(struct platform_device *dev) { struct rio_ops *ops; struct rio_mport *port; diff --git a/arch/powerpc/sysdev/fsl_rmu.c b/arch/powerpc/sysdev/fsl_rmu.c index c1f724973589..f956591cb64e 100644 --- a/arch/powerpc/sysdev/fsl_rmu.c +++ b/arch/powerpc/sysdev/fsl_rmu.c @@ -25,7 +25,6 @@ #include <linux/interrupt.h> #include <linux/of_address.h> #include <linux/of_irq.h> -#include <linux/of_platform.h> #include <linux/slab.h> #include "fsl_rio.h" @@ -360,7 +359,7 @@ out: return IRQ_HANDLED; } -void msg_unit_error_handler(void) +static void msg_unit_error_handler(void) { /*XXX: Error recovery is not implemented, we just clear errors */ diff --git a/arch/powerpc/sysdev/fsl_soc.c b/arch/powerpc/sysdev/fsl_soc.c index 68709743450e..3949ceb79e64 100644 --- a/arch/powerpc/sysdev/fsl_soc.c +++ b/arch/powerpc/sysdev/fsl_soc.c @@ -19,12 +19,9 @@ #include <linux/device.h> #include <linux/platform_device.h> #include <linux/of.h> -#include <linux/of_platform.h> #include <linux/phy.h> #include <linux/spi/spi.h> #include <linux/fsl_devices.h> -#include <linux/fs_enet_pd.h> -#include <linux/fs_uart_pd.h> #include <linux/reboot.h> #include <linux/atomic.h> @@ -37,9 +34,6 @@ #include <asm/cpm2.h> #include <asm/fsl_hcalls.h> /* For the Freescale hypervisor */ -extern void init_fcc_ioports(struct fs_platform_info*); -extern void init_fec_ioports(struct fs_platform_info*); -extern void init_smc_ioports(struct fs_uart_platform_info*); static phys_addr_t immrbase = -1; phys_addr_t get_immrbase(void) diff --git a/arch/powerpc/sysdev/mpc5xxx_clocks.c b/arch/powerpc/sysdev/mpc5xxx_clocks.c index c5bf7e1b3780..58cee28e2399 100644 --- a/arch/powerpc/sysdev/mpc5xxx_clocks.c +++ b/arch/powerpc/sysdev/mpc5xxx_clocks.c @@ -25,8 +25,10 @@ unsigned long mpc5xxx_fwnode_get_bus_frequency(struct fwnode_handle *fwnode) fwnode_for_each_parent_node(fwnode, parent) { ret = fwnode_property_read_u32(parent, "bus-frequency", &bus_freq); - if (!ret) + if (!ret) { + fwnode_handle_put(parent); return bus_freq; + } } return 0; diff --git a/arch/powerpc/sysdev/mpic_msgr.c b/arch/powerpc/sysdev/mpic_msgr.c index 1a3ac0b5dd89..7b449cc51aef 100644 --- a/arch/powerpc/sysdev/mpic_msgr.c +++ b/arch/powerpc/sysdev/mpic_msgr.c @@ -7,9 +7,10 @@ */ #include <linux/list.h> +#include <linux/of.h> #include <linux/of_address.h> #include <linux/of_irq.h> -#include <linux/of_platform.h> +#include <linux/platform_device.h> #include <linux/errno.h> #include <linux/err.h> #include <linux/export.h> diff --git a/arch/powerpc/sysdev/mpic_timer.c b/arch/powerpc/sysdev/mpic_timer.c index b2f0a73e8f93..7166e2e0baaf 100644 --- a/arch/powerpc/sysdev/mpic_timer.c +++ b/arch/powerpc/sysdev/mpic_timer.c @@ -16,7 +16,6 @@ #include <linux/slab.h> #include <linux/of.h> #include <linux/of_address.h> -#include <linux/of_device.h> #include <linux/of_irq.h> #include <linux/syscore_ops.h> #include <sysdev/fsl_soc.h> diff --git a/arch/powerpc/sysdev/of_rtc.c b/arch/powerpc/sysdev/of_rtc.c index 420f949b7485..2211937d3788 100644 --- a/arch/powerpc/sysdev/of_rtc.c +++ b/arch/powerpc/sysdev/of_rtc.c @@ -5,10 +5,10 @@ * Copyright 2007 David Gibson <dwg@au1.ibm.com>, IBM Corporation. */ #include <linux/kernel.h> -#include <linux/of.h> #include <linux/init.h> +#include <linux/of.h> #include <linux/of_address.h> -#include <linux/of_platform.h> +#include <linux/platform_device.h> #include <linux/slab.h> #include <asm/prom.h> diff --git a/arch/powerpc/sysdev/pmi.c b/arch/powerpc/sysdev/pmi.c index 9dabb50c36eb..fcf8d1516210 100644 --- a/arch/powerpc/sysdev/pmi.c +++ b/arch/powerpc/sysdev/pmi.c @@ -16,11 +16,11 @@ #include <linux/completion.h> #include <linux/spinlock.h> #include <linux/module.h> +#include <linux/mod_devicetable.h> #include <linux/workqueue.h> #include <linux/of_address.h> -#include <linux/of_device.h> #include <linux/of_irq.h> -#include <linux/of_platform.h> +#include <linux/platform_device.h> #include <asm/io.h> #include <asm/pmi.h> diff --git a/arch/powerpc/sysdev/xics/ics-opal.c b/arch/powerpc/sysdev/xics/ics-opal.c index 6cfbb4fac7fb..5fe73dabab79 100644 --- a/arch/powerpc/sysdev/xics/ics-opal.c +++ b/arch/powerpc/sysdev/xics/ics-opal.c @@ -111,7 +111,6 @@ static int ics_opal_set_affinity(struct irq_data *d, __func__, d->irq, hw_irq, rc); return -1; } - server = be16_to_cpu(oserver); wanted_server = xics_get_irq_server(d->irq, cpumask, 1); if (wanted_server < 0) { diff --git a/arch/powerpc/tools/gcc-check-fpatchable-function-entry.sh b/arch/powerpc/tools/gcc-check-fpatchable-function-entry.sh new file mode 100755 index 000000000000..06706903503b --- /dev/null +++ b/arch/powerpc/tools/gcc-check-fpatchable-function-entry.sh @@ -0,0 +1,26 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +set -e +set -o pipefail + +# To debug, uncomment the following line +# set -x + +# Output from -fpatchable-function-entry can only vary on ppc64 elfv2, so this +# should not be invoked for other targets. Therefore we can pass in -m64 and +# -mabi explicitly, to take care of toolchains defaulting to other targets. + +# Test whether the compile option -fpatchable-function-entry exists and +# generates appropriate code +echo "int func() { return 0; }" | \ + $* -m64 -mabi=elfv2 -S -x c -O2 -fpatchable-function-entry=2 - -o - 2> /dev/null | \ + grep -q "__patchable_function_entries" + +# Test whether nops are generated after the local entry point +echo "int x; int func() { return x; }" | \ + $* -m64 -mabi=elfv2 -S -x c -O2 -fpatchable-function-entry=2 - -o - 2> /dev/null | \ + awk 'BEGIN { RS = ";" } /\.localentry.*nop.*\n[[:space:]]*nop/ { print $0 }' | \ + grep -q "func:" + +exit 0 diff --git a/arch/powerpc/xmon/Makefile b/arch/powerpc/xmon/Makefile index d334de392e6c..682c7c0a6f77 100644 --- a/arch/powerpc/xmon/Makefile +++ b/arch/powerpc/xmon/Makefile @@ -10,14 +10,12 @@ KCSAN_SANITIZE := n # Disable ftrace for the entire directory ccflags-remove-$(CONFIG_FUNCTION_TRACER) += $(CC_FLAGS_FTRACE) -ifdef CONFIG_CC_IS_CLANG -# clang stores addresses on the stack causing the frame size to blow -# out. See https://github.com/ClangBuiltLinux/linux/issues/252 -KBUILD_CFLAGS += -Wframe-larger-than=4096 -endif - ccflags-$(CONFIG_PPC64) := $(NO_MINIMAL_TOC) +# Clang stores addresses on the stack causing the frame size to blow +# out. See https://github.com/ClangBuiltLinux/linux/issues/252 +ccflags-$(CONFIG_CC_IS_CLANG) += -Wframe-larger-than=4096 + obj-y += xmon.o nonstdio.o spr_access.o xmon_bpts.o ifdef CONFIG_XMON_DISASSEMBLY diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index fae747cc57d2..b3b94cd37713 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -58,6 +58,7 @@ #ifdef CONFIG_PPC64 #include <asm/hvcall.h> #include <asm/paca.h> +#include <asm/lppaca.h> #endif #include "nonstdio.h" @@ -1084,7 +1085,7 @@ cmds(struct pt_regs *excp) memzcan(); break; case 'i': - show_mem(0, NULL); + show_mem(); break; default: termch = cmd; @@ -3303,7 +3304,7 @@ static void show_pte(unsigned long addr) { unsigned long tskv = 0; struct task_struct *volatile tsk = NULL; - struct mm_struct *mm; + struct mm_struct *volatile mm; pgd_t *pgdp; p4d_t *p4dp; pud_t *pudp; @@ -3828,9 +3829,9 @@ static void dump_tlb_44x(void) #ifdef CONFIG_PPC_BOOK3E_64 static void dump_tlb_book3e(void) { - u32 mmucfg, pidmask, lpidmask; + u32 mmucfg; u64 ramask; - int i, tlb, ntlbs, pidsz, lpidsz, rasz, lrat = 0; + int i, tlb, ntlbs, pidsz, lpidsz, rasz; int mmu_version; static const char *pgsz_names[] = { " 1K", @@ -3874,12 +3875,8 @@ static void dump_tlb_book3e(void) pidsz = ((mmucfg >> 6) & 0x1f) + 1; lpidsz = (mmucfg >> 24) & 0xf; rasz = (mmucfg >> 16) & 0x7f; - if ((mmu_version > 1) && (mmucfg & 0x10000)) - lrat = 1; printf("Book3E MMU MAV=%d.0,%d TLBs,%d-bit PID,%d-bit LPID,%d-bit RA\n", mmu_version, ntlbs, pidsz, lpidsz, rasz); - pidmask = (1ul << pidsz) - 1; - lpidmask = (1ul << lpidsz) - 1; ramask = (1ull << rasz) - 1; for (tlb = 0; tlb < ntlbs; tlb++) { @@ -3991,7 +3988,7 @@ static void xmon_init(int enable) } #ifdef CONFIG_MAGIC_SYSRQ -static void sysrq_handle_xmon(int key) +static void sysrq_handle_xmon(u8 key) { if (xmon_is_locked_down()) { clear_all_bpt(); |