diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2022-08-07 02:38:17 +0300 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2022-08-07 02:38:17 +0300 |
commit | cae4199f9319f42534ee2e2e4aadf183b9bb7f73 (patch) | |
tree | b0028cbba73deaaf842fcb72e7c0dc0a0e0a9923 /arch | |
parent | 4d1044fcb996e8de9b9ab392f4a767890e45202d (diff) | |
parent | 4cfa6ff24a9744ba484521c38bea613134fbfcb3 (diff) |
Merge tag 'powerpc-6.0-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux
Pull powerpc updates from Michael Ellerman:
- Add support for syscall stack randomization
- Add support for atomic operations to the 32 & 64-bit BPF JIT
- Full support for KASAN on 64-bit Book3E
- Add a watchdog driver for the new PowerVM hypervisor watchdog
- Add a number of new selftests for the Power10 PMU support
- Add a driver for the PowerVM Platform KeyStore
- Increase the NMI watchdog timeout during live partition migration, to
avoid timeouts due to increased memory access latency
- Add support for using the 'linux,pci-domain' device tree property for
PCI domain assignment
- Many other small features and fixes
Thanks to Alexey Kardashevskiy, Andy Shevchenko, Arnd Bergmann, Athira
Rajeev, Bagas Sanjaya, Christophe Leroy, Erhard Furtner, Fabiano Rosas,
Greg Kroah-Hartman, Greg Kurz, Haowen Bai, Hari Bathini, Jason A.
Donenfeld, Jason Wang, Jiang Jian, Joel Stanley, Juerg Haefliger, Kajol
Jain, Kees Cook, Laurent Dufour, Madhavan Srinivasan, Masahiro Yamada,
Maxime Bizon, Miaoqian Lin, Murilo Opsfelder Araújo, Nathan Lynch,
Naveen N. Rao, Nayna Jain, Nicholas Piggin, Ning Qiang, Pali Rohár,
Petr Mladek, Rashmica Gupta, Sachin Sant, Scott Cheloha, Segher
Boessenkool, Stephen Rothwell, Uwe Kleine-König, Wolfram Sang, Xiu
Jianfeng, and Zhouyi Zhou.
* tag 'powerpc-6.0-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (191 commits)
powerpc/64e: Fix kexec build error
EDAC/ppc_4xx: Include required of_irq header directly
powerpc/pci: Fix PHB numbering when using opal-phbid
powerpc/64: Init jump labels before parse_early_param()
selftests/powerpc: Avoid GCC 12 uninitialised variable warning
powerpc/cell/axon_msi: Fix refcount leak in setup_msi_msg_address
powerpc/xive: Fix refcount leak in xive_get_max_prio
powerpc/spufs: Fix refcount leak in spufs_init_isolated_loader
powerpc/perf: Include caps feature for power10 DD1 version
powerpc: add support for syscall stack randomization
powerpc: Move system_call_exception() to syscall.c
powerpc/powernv: rename remaining rng powernv_ functions to pnv_
powerpc/powernv/kvm: Use darn for H_RANDOM on Power9
powerpc/powernv: Avoid crashing if rng is NULL
selftests/powerpc: Fix matrix multiply assist test
powerpc/signal: Update comment for clarity
powerpc: make facility_unavailable_exception 64s
powerpc/platforms/83xx/suspend: Remove write-only global variable
powerpc/platforms/83xx/suspend: Prevent unloading the driver
powerpc/platforms/83xx/suspend: Reorder to get rid of a forward declaration
...
Diffstat (limited to 'arch')
194 files changed, 3363 insertions, 1863 deletions
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index af612d4c4bcc..4c466acdc70d 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -11,7 +11,7 @@ config 64BIT config LIVEPATCH_64 def_bool PPC64 - depends on LIVEPATCH + depends on LIVEPATCH config MMU bool @@ -192,8 +192,10 @@ config PPC select HAVE_ARCH_JUMP_LABEL_RELATIVE select HAVE_ARCH_KASAN if PPC32 && PPC_PAGE_SHIFT <= 14 select HAVE_ARCH_KASAN if PPC_RADIX_MMU + select HAVE_ARCH_KASAN if PPC_BOOK3E_64 select HAVE_ARCH_KASAN_VMALLOC if HAVE_ARCH_KASAN select HAVE_ARCH_KFENCE if PPC_BOOK3S_32 || PPC_8xx || 40x + select HAVE_ARCH_RANDOMIZE_KSTACK_OFFSET select HAVE_ARCH_KGDB select HAVE_ARCH_MMAP_RND_BITS select HAVE_ARCH_MMAP_RND_COMPAT_BITS if COMPAT @@ -253,6 +255,7 @@ config PPC select IOMMU_HELPER if PPC64 select IRQ_DOMAIN select IRQ_FORCED_THREADING + select KASAN_VMALLOC if KASAN && MODULES select MMU_GATHER_PAGE_SIZE select MMU_GATHER_RCU_TABLE_FREE select MMU_GATHER_MERGE_VMAS @@ -376,6 +379,17 @@ config PPC_DCR depends on PPC_DCR_NATIVE || PPC_DCR_MMIO default y +config PPC_PCI_BUS_NUM_DOMAIN_DEPENDENT + depends on PPC32 + depends on !PPC_PMAC && !PPC_CHRP + bool "Assign PCI bus numbers from zero individually for each PCI domain" + help + By default on PPC32 were PCI bus numbers unique across all PCI domains. + So system could have only 256 PCI buses independently of available + PCI domains. When this option is enabled then PCI bus numbers are + PCI domain dependent and each PCI controller on own domain can have + 256 PCI buses, like it is on other Linux architectures. + config PPC_OF_PLATFORM_PCI bool depends on PCI @@ -452,7 +466,7 @@ choice default MATH_EMULATION_FULL depends on MATH_EMULATION -config MATH_EMULATION_FULL +config MATH_EMULATION_FULL bool "Emulate all the floating point instructions" help Select this option will enable the kernel to support to emulate @@ -554,7 +568,6 @@ config KEXEC_FILE bool "kexec file based system call" select KEXEC_CORE select HAVE_IMA_KEXEC if IMA - select BUILD_BIN2C select KEXEC_ELF depends on PPC64 depends on CRYPTO=y diff --git a/arch/powerpc/Kconfig.debug b/arch/powerpc/Kconfig.debug index 9f363c143d86..ae727d4218b9 100644 --- a/arch/powerpc/Kconfig.debug +++ b/arch/powerpc/Kconfig.debug @@ -305,7 +305,6 @@ config PPC_EARLY_DEBUG_OPAL def_bool y depends on PPC_EARLY_DEBUG_OPAL_RAW || PPC_EARLY_DEBUG_OPAL_HVSI - config PPC_EARLY_DEBUG_HVSI_VTERMNO hex "vterm number to use with early debug HVSI" depends on PPC_EARLY_DEBUG_LPAR_HVSI @@ -375,4 +374,5 @@ config KASAN_SHADOW_OFFSET hex depends on KASAN default 0xe0000000 if PPC32 - default 0xa80e000000000000 if PPC64 + default 0xa80e000000000000 if PPC_BOOK3S_64 + default 0xa8001c0000000000 if PPC_BOOK3E_64 diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index a0cd70712061..02742facf895 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -15,23 +15,6 @@ HAS_BIARCH := $(call cc-option-yn, -m32) # Set default 32 bits cross compilers for vdso and boot wrapper CROSS32_COMPILE ?= -ifeq ($(HAS_BIARCH),y) -ifeq ($(CROSS32_COMPILE),) -ifdef CONFIG_PPC32 -# These options will be overridden by any -mcpu option that the CPU -# or platform code sets later on the command line, but they are needed -# to set a sane 32-bit cpu target for the 64-bit cross compiler which -# may default to the wrong ISA. -KBUILD_CFLAGS += -mcpu=powerpc -KBUILD_AFLAGS += -mcpu=powerpc -endif -endif -endif - -ifdef CONFIG_PPC_BOOK3S_32 -KBUILD_CFLAGS += -mcpu=powerpc -endif - # If we're on a ppc/ppc64/ppc64le machine use that defconfig, otherwise just use # ppc64_defconfig because we have nothing better to go on. uname := $(shell uname -m) @@ -183,24 +166,11 @@ endif endif CFLAGS-$(CONFIG_TARGET_CPU_BOOL) += $(call cc-option,-mcpu=$(CONFIG_TARGET_CPU)) +AFLAGS-$(CONFIG_TARGET_CPU_BOOL) += $(call cc-option,-mcpu=$(CONFIG_TARGET_CPU)) -# Altivec option not allowed with e500mc64 in GCC. -ifdef CONFIG_ALTIVEC -E5500_CPU := -mcpu=powerpc64 -else -E5500_CPU := $(call cc-option,-mcpu=e500mc64,-mcpu=powerpc64) -endif -CFLAGS-$(CONFIG_E5500_CPU) += $(E5500_CPU) +CFLAGS-$(CONFIG_E5500_CPU) += $(call cc-option,-mcpu=e500mc64,-mcpu=powerpc64) CFLAGS-$(CONFIG_E6500_CPU) += $(call cc-option,-mcpu=e6500,$(E5500_CPU)) -ifdef CONFIG_PPC32 -ifdef CONFIG_PPC_E500MC -CFLAGS-y += $(call cc-option,-mcpu=e500mc,-mcpu=powerpc) -else -CFLAGS-$(CONFIG_E500) += $(call cc-option,-mcpu=8540 -msoft-float,-mcpu=powerpc) -endif -endif - asinstr := $(call as-instr,lis 9$(comma)foo@high,-DHAVE_AS_ATHIGH=1) KBUILD_CPPFLAGS += -I $(srctree)/arch/$(ARCH) $(asinstr) diff --git a/arch/powerpc/boot/dts/fsl/p2020si-post.dtsi b/arch/powerpc/boot/dts/fsl/p2020si-post.dtsi index 7a590c92fe56..81b9ab2119be 100644 --- a/arch/powerpc/boot/dts/fsl/p2020si-post.dtsi +++ b/arch/powerpc/boot/dts/fsl/p2020si-post.dtsi @@ -48,6 +48,7 @@ bus-range = <0 255>; clock-frequency = <33333333>; interrupts = <26 2 0 0>; + law_trgt_if = <2>; pcie@0 { reg = <0 0 0 0 0>; @@ -76,6 +77,7 @@ bus-range = <0 255>; clock-frequency = <33333333>; interrupts = <25 2 0 0>; + law_trgt_if = <1>; pcie@0 { reg = <0 0 0 0 0>; @@ -105,6 +107,7 @@ bus-range = <0 255>; clock-frequency = <33333333>; interrupts = <24 2 0 0>; + law_trgt_if = <0>; pcie@0 { reg = <0 0 0 0 0>; diff --git a/arch/powerpc/boot/dts/turris1x.dts b/arch/powerpc/boot/dts/turris1x.dts new file mode 100644 index 000000000000..12e08271e61f --- /dev/null +++ b/arch/powerpc/boot/dts/turris1x.dts @@ -0,0 +1,483 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Turris 1.x Device Tree Source + * + * Copyright 2013 - 2022 CZ.NIC z.s.p.o. (http://www.nic.cz/) + * + * Pinout, Schematics and Altium hardware design files are open source + * and available at: https://docs.turris.cz/hw/turris-1x/turris-1x/ + */ + +#include <dt-bindings/gpio/gpio.h> +#include <dt-bindings/interrupt-controller/irq.h> +#include <dt-bindings/leds/common.h> +/include/ "fsl/p2020si-pre.dtsi" + +/ { + model = "Turris 1.x"; + compatible = "cznic,turris1x", "fsl,P2020RDB-PC"; /* fsl,P2020RDB-PC is required for booting Linux */ + + aliases { + ethernet0 = &enet0; + ethernet1 = &enet1; + ethernet2 = &enet2; + serial0 = &serial0; + serial1 = &serial1; + pci0 = &pci0; + pci1 = &pci1; + pci2 = &pci2; + spi0 = &spi0; + }; + + memory { + device_type = "memory"; + }; + + soc: soc@ffe00000 { + ranges = <0x0 0x0 0xffe00000 0x00100000>; + + i2c@3000 { + /* PCA9557PW GPIO controller for boot config */ + gpio-controller@18 { + compatible = "nxp,pca9557"; + label = "bootcfg"; + reg = <0x18>; + #gpio-cells = <2>; + gpio-controller; + polarity = <0x00>; + }; + + /* STM32F030R8T6 MCU for power control */ + power-control@2a { + /* + * Turris Power Control firmware runs on STM32F0 MCU. + * This firmware is open source and available at: + * https://gitlab.nic.cz/turris/hw/turris_power_control + */ + reg = <0x2a>; + }; + + /* DDR3 SPD/EEPROM PSWP instruction */ + eeprom@32 { + reg = <0x32>; + }; + + /* SA56004ED temperature control */ + temperature-sensor@4c { + compatible = "nxp,sa56004"; + reg = <0x4c>; + interrupt-parent = <&gpio>; + interrupts = <12 IRQ_TYPE_LEVEL_LOW>, /* GPIO12 - ALERT pin */ + <13 IRQ_TYPE_LEVEL_LOW>; /* GPIO13 - CRIT pin */ + }; + + /* DDR3 SPD/EEPROM */ + eeprom@52 { + compatible = "atmel,spd"; + reg = <0x52>; + }; + + /* MCP79402-I/ST Protected EEPROM */ + eeprom@57 { + reg = <0x57>; + }; + + /* ATSHA204-TH-DA-T crypto module */ + crypto@64 { + compatible = "atmel,atsha204"; + reg = <0x64>; + }; + + /* IDT6V49205BNLGI clock generator */ + clock-generator@69 { + compatible = "idt,6v49205b"; + reg = <0x69>; + }; + + /* MCP79402-I/ST RTC */ + rtc@6f { + compatible = "microchip,mcp7940x"; + reg = <0x6f>; + interrupt-parent = <&gpio>; + interrupts = <14 0>; /* GPIO14 - MFP pin */ + }; + }; + + /* SPI on connector P1 */ + spi0: spi@7000 { + }; + + gpio: gpio-controller@fc00 { + #interrupt-cells = <2>; + interrupt-controller; + }; + + /* Connected to SMSC USB2412-DZK 2-Port USB 2.0 Hub Controller */ + usb@22000 { + phy_type = "ulpi"; + dr_mode = "host"; + }; + + enet0: ethernet@24000 { + /* Connected to port 6 of QCA8337N-AL3C switch */ + phy-connection-type = "rgmii-id"; + + fixed-link { + speed = <1000>; + full-duplex; + }; + }; + + mdio@24520 { + /* KSZ9031RNXCA ethernet phy for WAN port */ + phy: ethernet-phy@7 { + interrupts = <3 1 0 0>; + reg = <0x7>; + }; + + /* QCA8337N-AL3C switch with integrated ethernet PHYs for LAN ports */ + switch@10 { + compatible = "qca,qca8337"; + interrupts = <2 1 0 0>; + reg = <0x10>; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + label = "cpu1"; + ethernet = <&enet1>; + phy-mode = "rgmii-id"; + + fixed-link { + speed = <1000>; + full-duplex; + }; + }; + + port@1 { + reg = <1>; + label = "lan5"; + }; + + port@2 { + reg = <2>; + label = "lan4"; + }; + + port@3 { + reg = <3>; + label = "lan3"; + }; + + port@4 { + reg = <4>; + label = "lan2"; + }; + + port@5 { + reg = <5>; + label = "lan1"; + }; + + port@6 { + reg = <6>; + label = "cpu0"; + ethernet = <&enet0>; + phy-mode = "rgmii-id"; + + fixed-link { + speed = <1000>; + full-duplex; + }; + }; + }; + }; + }; + + ptp_clock@24e00 { + fsl,tclk-period = <5>; + fsl,tmr-prsc = <200>; + fsl,tmr-add = <0xcccccccd>; + fsl,tmr-fiper1 = <0x3b9ac9fb>; + fsl,tmr-fiper2 = <0x0001869b>; + fsl,max-adj = <249999999>; + }; + + enet1: ethernet@25000 { + /* Connected to port 0 of QCA8337N-AL3C switch */ + phy-connection-type = "rgmii-id"; + + fixed-link { + speed = <1000>; + full-duplex; + }; + }; + + mdio@25520 { + status = "disabled"; + }; + + enet2: ethernet@26000 { + /* Connected to KSZ9031RNXCA ethernet phy (WAN port) */ + label = "wan"; + phy-handle = <&phy>; + phy-connection-type = "rgmii-id"; + }; + + mdio@26520 { + status = "disabled"; + }; + + sdhc@2e000 { + bus-width = <4>; + cd-gpios = <&gpio 8 GPIO_ACTIVE_LOW>; + }; + }; + + lbc: localbus@ffe05000 { + reg = <0 0xffe05000 0 0x1000>; + + ranges = <0x0 0x0 0x0 0xef000000 0x01000000>, /* NOR */ + <0x1 0x0 0x0 0xff800000 0x00040000>, /* NAND */ + <0x3 0x0 0x0 0xffa00000 0x00020000>; /* CPLD */ + + /* S29GL128P90TFIR10 NOR */ + nor@0,0 { + compatible = "cfi-flash"; + reg = <0x0 0x0 0x01000000>; + bank-width = <2>; + device-width = <1>; + + partitions { + compatible = "fixed-partitions"; + #address-cells = <1>; + #size-cells = <1>; + + partition@0 { + /* 128 kB for Device Tree Blob */ + reg = <0x00000000 0x00020000>; + label = "dtb"; + }; + + partition@20000 { + /* 1.7 MB for Rescue Linux Kernel Image */ + reg = <0x00020000 0x001a0000>; + label = "rescue-kernel"; + }; + + partition@1c0000 { + /* 1.5 MB for Rescue JFFS2 Root File System */ + reg = <0x001c0000 0x00180000>; + label = "rescue-rootfs"; + }; + + partition@340000 { + /* 11 MB for TAR.XZ Backup with content of NAND Root File System */ + reg = <0x00340000 0x00b00000>; + label = "backup-rootfs"; + }; + + partition@e40000 { + /* 768 kB for Certificates JFFS2 File System */ + reg = <0x00e40000 0x000c0000>; + label = "certificates"; + }; + + /* free unused space 0x00f00000-0x00f20000 */ + + partition@f20000 { + /* 128 kB for U-Boot Environment Variables */ + reg = <0x00f20000 0x00020000>; + label = "u-boot-env"; + }; + + partition@f40000 { + /* 768 kB for U-Boot Bootloader Image */ + reg = <0x00f40000 0x000c0000>; + label = "u-boot"; + }; + }; + }; + + /* MT29F2G08ABAEAWP:E NAND */ + nand@1,0 { + compatible = "fsl,p2020-fcm-nand", "fsl,elbc-fcm-nand"; + reg = <0x1 0x0 0x00040000>; + nand-ecc-mode = "soft"; + nand-ecc-algo = "bch"; + + partitions { + compatible = "fixed-partitions"; + #address-cells = <1>; + #size-cells = <1>; + + partition@0 { + /* 256 MB for UBI with one volume: UBIFS Root File System */ + reg = <0x00000000 0x10000000>; + label = "rootfs"; + }; + }; + }; + + /* LCMXO1200C-3FTN256C FPGA */ + cpld@3,0 { + /* + * Turris CPLD firmware which runs on this Lattice FPGA, + * is extended version of P1021RDB-PC CPLD v4.1 firmware. + * It is backward compatible with its original version + * and the only extension is support for Turris LEDs. + * Turris CPLD firmware is open source and available at: + * https://gitlab.nic.cz/turris/hw/turris_cpld/-/blob/master/CZ_NIC_Router_CPLD.v + */ + compatible = "cznic,turris1x-cpld", "fsl,p1021rdb-pc-cpld", "simple-bus", "syscon"; + reg = <0x3 0x0 0x30>; + #address-cells = <1>; + #size-cells = <1>; + ranges = <0x0 0x3 0x0 0x00020000>; + + /* MAX6370KA+T watchdog */ + watchdog@2 { + /* + * CPLD firmware maps SET0, SET1 and SET2 + * input logic of MAX6370KA+T chip to CPLD + * memory space at byte offset 0x2. WDI + * input logic is outside of the CPLD and + * connected via external GPIO. + */ + compatible = "maxim,max6370"; + reg = <0x02 0x01>; + gpios = <&gpio 11 GPIO_ACTIVE_LOW>; + }; + + reboot@d { + compatible = "syscon-reboot"; + reg = <0x0d 0x01>; + offset = <0x0d>; + mask = <0x01>; + value = <0x01>; + }; + + led-controller@13 { + /* + * LEDs are controlled by CPLD firmware. + * All five LAN LEDs share common RGB settings + * and so it is not possible to set different + * colors on different LAN ports. + */ + compatible = "cznic,turris1x-leds"; + reg = <0x13 0x1d>; + #address-cells = <1>; + #size-cells = <0>; + + multi-led@0 { + reg = <0x0>; + color = <LED_COLOR_ID_RGB>; + function = LED_FUNCTION_WAN; + }; + + multi-led@1 { + reg = <0x1>; + color = <LED_COLOR_ID_RGB>; + function = LED_FUNCTION_LAN; + function-enumerator = <5>; + }; + + multi-led@2 { + reg = <0x2>; + color = <LED_COLOR_ID_RGB>; + function = LED_FUNCTION_LAN; + function-enumerator = <4>; + }; + + multi-led@3 { + reg = <0x3>; + color = <LED_COLOR_ID_RGB>; + function = LED_FUNCTION_LAN; + function-enumerator = <3>; + }; + + multi-led@4 { + reg = <0x4>; + color = <LED_COLOR_ID_RGB>; + function = LED_FUNCTION_LAN; + function-enumerator = <2>; + }; + + multi-led@5 { + reg = <0x5>; + color = <LED_COLOR_ID_RGB>; + function = LED_FUNCTION_LAN; + function-enumerator = <1>; + }; + + multi-led@6 { + reg = <0x6>; + color = <LED_COLOR_ID_RGB>; + function = LED_FUNCTION_WLAN; + }; + + multi-led@7 { + reg = <0x7>; + color = <LED_COLOR_ID_RGB>; + function = LED_FUNCTION_POWER; + }; + }; + }; + }; + + pci2: pcie@ffe08000 { + /* + * PCIe bus for on-board TUSB7340RKM USB 3.0 xHCI controller. + * This xHCI controller is available only on Turris 1.1 boards. + * Turris 1.0 boards have nothing connected to this PCIe bus, + * so system would see only PCIe Root Port of this PCIe Root + * Complex. TUSB7340RKM xHCI controller has four SuperSpeed + * channels. Channel 0 is connected to the front USB 3.0 port, + * channel 1 (but only USB 2.0 subset) to USB 2.0 pins on mPCIe + * slot 1 (CN5), channels 2 and 3 to connector P600. + * + * P2020 PCIe Root Port uses 1MB of PCIe MEM and xHCI controller + * uses 64kB + 8kB of PCIe MEM. No PCIe IO is used or required. + * So allocate 2MB of PCIe MEM for this PCIe bus. + */ + reg = <0 0xffe08000 0 0x1000>; + ranges = <0x02000000 0x0 0xc0000000 0 0xc0000000 0x0 0x00200000>, /* MEM */ + <0x01000000 0x0 0x00000000 0 0xffc20000 0x0 0x00010000>; /* IO */ + + pcie@0 { + ranges; + }; + }; + + pci1: pcie@ffe09000 { + /* PCIe bus on mPCIe slot 2 (CN6) for expansion mPCIe card */ + reg = <0 0xffe09000 0 0x1000>; + ranges = <0x02000000 0x0 0xa0000000 0 0xa0000000 0x0 0x20000000>, /* MEM */ + <0x01000000 0x0 0x00000000 0 0xffc10000 0x0 0x00010000>; /* IO */ + + pcie@0 { + ranges; + }; + }; + + pci0: pcie@ffe0a000 { + /* + * PCIe bus on mPCIe slot 1 (CN5) for expansion mPCIe card. + * Turris 1.1 boards have in this mPCIe slot additional USB 2.0 + * pins via channel 1 of TUSB7340RKM xHCI controller and also + * additional SIM card slot, both for USB-based WWAN cards. + */ + reg = <0 0xffe0a000 0 0x1000>; + ranges = <0x02000000 0x0 0x80000000 0 0x80000000 0x0 0x20000000>, /* MEM */ + <0x01000000 0x0 0x00000000 0 0xffc00000 0x0 0x00010000>; /* IO */ + + pcie@0 { + ranges; + }; + }; +}; + +/include/ "fsl/p2020si-post.dtsi" diff --git a/arch/powerpc/configs/44x/akebono_defconfig b/arch/powerpc/configs/44x/akebono_defconfig index 4bc549c6edc5..fde4824f235e 100644 --- a/arch/powerpc/configs/44x/akebono_defconfig +++ b/arch/powerpc/configs/44x/akebono_defconfig @@ -118,7 +118,7 @@ CONFIG_CRAMFS=y CONFIG_NLS_DEFAULT="n" CONFIG_NLS_CODEPAGE_437=y CONFIG_NLS_ISO8859_1=y -CONFIG_DEBUG_INFO=y +CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y CONFIG_MAGIC_SYSRQ=y CONFIG_DETECT_HUNG_TASK=y CONFIG_XMON=y diff --git a/arch/powerpc/configs/44x/currituck_defconfig b/arch/powerpc/configs/44x/currituck_defconfig index 717827219921..7283b7d4a1a5 100644 --- a/arch/powerpc/configs/44x/currituck_defconfig +++ b/arch/powerpc/configs/44x/currituck_defconfig @@ -73,7 +73,7 @@ CONFIG_NFS_FS=y CONFIG_NFS_V3_ACL=y CONFIG_NFS_V4=y CONFIG_NLS_DEFAULT="n" -CONFIG_DEBUG_INFO=y +CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y CONFIG_MAGIC_SYSRQ=y CONFIG_DETECT_HUNG_TASK=y CONFIG_XMON=y diff --git a/arch/powerpc/configs/44x/fsp2_defconfig b/arch/powerpc/configs/44x/fsp2_defconfig index 8da316e61a08..3fdfbb29b854 100644 --- a/arch/powerpc/configs/44x/fsp2_defconfig +++ b/arch/powerpc/configs/44x/fsp2_defconfig @@ -110,7 +110,7 @@ CONFIG_XZ_DEC=y CONFIG_PRINTK_TIME=y CONFIG_MESSAGE_LOGLEVEL_DEFAULT=3 CONFIG_DYNAMIC_DEBUG=y -CONFIG_DEBUG_INFO=y +CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y CONFIG_MAGIC_SYSRQ=y CONFIG_DETECT_HUNG_TASK=y CONFIG_CRYPTO_CBC=y diff --git a/arch/powerpc/configs/44x/iss476-smp_defconfig b/arch/powerpc/configs/44x/iss476-smp_defconfig index c11e777b2f3d..0f6380e1e612 100644 --- a/arch/powerpc/configs/44x/iss476-smp_defconfig +++ b/arch/powerpc/configs/44x/iss476-smp_defconfig @@ -56,7 +56,7 @@ CONFIG_PROC_KCORE=y CONFIG_TMPFS=y CONFIG_CRAMFS=y # CONFIG_NETWORK_FILESYSTEMS is not set -CONFIG_DEBUG_INFO=y +CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y CONFIG_MAGIC_SYSRQ=y CONFIG_DETECT_HUNG_TASK=y CONFIG_PPC_EARLY_DEBUG=y diff --git a/arch/powerpc/configs/44x/warp_defconfig b/arch/powerpc/configs/44x/warp_defconfig index 47252c2d7669..20891c413149 100644 --- a/arch/powerpc/configs/44x/warp_defconfig +++ b/arch/powerpc/configs/44x/warp_defconfig @@ -88,7 +88,7 @@ CONFIG_NLS_UTF8=y CONFIG_CRC_CCITT=y CONFIG_CRC_T10DIF=y CONFIG_PRINTK_TIME=y -CONFIG_DEBUG_INFO=y +CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y CONFIG_DEBUG_FS=y CONFIG_MAGIC_SYSRQ=y CONFIG_DETECT_HUNG_TASK=y diff --git a/arch/powerpc/configs/52xx/lite5200b_defconfig b/arch/powerpc/configs/52xx/lite5200b_defconfig index 63368e677506..7db479dcbc0c 100644 --- a/arch/powerpc/configs/52xx/lite5200b_defconfig +++ b/arch/powerpc/configs/52xx/lite5200b_defconfig @@ -58,6 +58,6 @@ CONFIG_NFS_FS=y CONFIG_NFS_V4=y CONFIG_ROOT_NFS=y CONFIG_PRINTK_TIME=y -CONFIG_DEBUG_INFO=y +CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y CONFIG_DETECT_HUNG_TASK=y # CONFIG_DEBUG_BUGVERBOSE is not set diff --git a/arch/powerpc/configs/52xx/motionpro_defconfig b/arch/powerpc/configs/52xx/motionpro_defconfig index 72762da94846..6186ead1e105 100644 --- a/arch/powerpc/configs/52xx/motionpro_defconfig +++ b/arch/powerpc/configs/52xx/motionpro_defconfig @@ -84,7 +84,7 @@ CONFIG_ROOT_NFS=y CONFIG_NLS_CODEPAGE_437=y CONFIG_NLS_ISO8859_1=y CONFIG_PRINTK_TIME=y -CONFIG_DEBUG_INFO=y +CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y CONFIG_DETECT_HUNG_TASK=y # CONFIG_DEBUG_BUGVERBOSE is not set CONFIG_CRYPTO_ECB=y diff --git a/arch/powerpc/configs/52xx/tqm5200_defconfig b/arch/powerpc/configs/52xx/tqm5200_defconfig index a3c8ca74032c..e6735b945327 100644 --- a/arch/powerpc/configs/52xx/tqm5200_defconfig +++ b/arch/powerpc/configs/52xx/tqm5200_defconfig @@ -85,7 +85,7 @@ CONFIG_ROOT_NFS=y CONFIG_NLS_CODEPAGE_437=y CONFIG_NLS_ISO8859_1=y CONFIG_PRINTK_TIME=y -CONFIG_DEBUG_INFO=y +CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y CONFIG_DETECT_HUNG_TASK=y # CONFIG_DEBUG_BUGVERBOSE is not set CONFIG_CRYPTO_ECB=y diff --git a/arch/powerpc/configs/adder875_defconfig b/arch/powerpc/configs/adder875_defconfig index 5326bc739279..7f35d5bc1229 100644 --- a/arch/powerpc/configs/adder875_defconfig +++ b/arch/powerpc/configs/adder875_defconfig @@ -45,7 +45,7 @@ CONFIG_CRAMFS=y CONFIG_NFS_FS=y CONFIG_ROOT_NFS=y CONFIG_CRC32_SLICEBY4=y -CONFIG_DEBUG_INFO=y +CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y CONFIG_DEBUG_FS=y CONFIG_MAGIC_SYSRQ=y CONFIG_DETECT_HUNG_TASK=y diff --git a/arch/powerpc/configs/ep8248e_defconfig b/arch/powerpc/configs/ep8248e_defconfig index 00d69965f898..8df6d3a293e3 100644 --- a/arch/powerpc/configs/ep8248e_defconfig +++ b/arch/powerpc/configs/ep8248e_defconfig @@ -59,7 +59,7 @@ CONFIG_NLS_CODEPAGE_437=y CONFIG_NLS_ASCII=y CONFIG_NLS_ISO8859_1=y CONFIG_NLS_UTF8=y -CONFIG_DEBUG_INFO=y +CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y CONFIG_MAGIC_SYSRQ=y # CONFIG_SCHED_DEBUG is not set CONFIG_BDI_SWITCH=y diff --git a/arch/powerpc/configs/ep88xc_defconfig b/arch/powerpc/configs/ep88xc_defconfig index f5c3e72da719..a98ef6a4abef 100644 --- a/arch/powerpc/configs/ep88xc_defconfig +++ b/arch/powerpc/configs/ep88xc_defconfig @@ -48,6 +48,6 @@ CONFIG_CRAMFS=y CONFIG_NFS_FS=y CONFIG_ROOT_NFS=y CONFIG_CRC32_SLICEBY4=y -CONFIG_DEBUG_INFO=y +CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y CONFIG_MAGIC_SYSRQ=y CONFIG_DETECT_HUNG_TASK=y diff --git a/arch/powerpc/configs/fsl-emb-nonhw.config b/arch/powerpc/configs/fsl-emb-nonhw.config index df37efed0aec..f14c6dbd7346 100644 --- a/arch/powerpc/configs/fsl-emb-nonhw.config +++ b/arch/powerpc/configs/fsl-emb-nonhw.config @@ -24,7 +24,7 @@ CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_SHA256=y CONFIG_CRYPTO_SHA512=y CONFIG_DEBUG_FS=y -CONFIG_DEBUG_INFO=y +CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y CONFIG_DEBUG_KERNEL=y CONFIG_DEBUG_SHIRQ=y CONFIG_DETECT_HUNG_TASK=y diff --git a/arch/powerpc/configs/mgcoge_defconfig b/arch/powerpc/configs/mgcoge_defconfig index dcc8dccf54f3..498d35db7833 100644 --- a/arch/powerpc/configs/mgcoge_defconfig +++ b/arch/powerpc/configs/mgcoge_defconfig @@ -73,7 +73,7 @@ CONFIG_NLS_CODEPAGE_437=y CONFIG_NLS_ASCII=y CONFIG_NLS_ISO8859_1=y CONFIG_NLS_UTF8=y -CONFIG_DEBUG_INFO=y +CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y CONFIG_DEBUG_FS=y CONFIG_MAGIC_SYSRQ=y # CONFIG_SCHED_DEBUG is not set diff --git a/arch/powerpc/configs/mpc5200_defconfig b/arch/powerpc/configs/mpc5200_defconfig index 83d801307178..c0fe5e76604a 100644 --- a/arch/powerpc/configs/mpc5200_defconfig +++ b/arch/powerpc/configs/mpc5200_defconfig @@ -122,6 +122,6 @@ CONFIG_ROOT_NFS=y CONFIG_NLS_CODEPAGE_437=y CONFIG_NLS_ISO8859_1=y CONFIG_PRINTK_TIME=y -CONFIG_DEBUG_INFO=y +CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y CONFIG_DEBUG_KERNEL=y CONFIG_DETECT_HUNG_TASK=y diff --git a/arch/powerpc/configs/mpc8272_ads_defconfig b/arch/powerpc/configs/mpc8272_ads_defconfig index 00a4d2bf43b2..4145ef5689ca 100644 --- a/arch/powerpc/configs/mpc8272_ads_defconfig +++ b/arch/powerpc/configs/mpc8272_ads_defconfig @@ -67,7 +67,7 @@ CONFIG_NLS_CODEPAGE_437=y CONFIG_NLS_ASCII=y CONFIG_NLS_ISO8859_1=y CONFIG_NLS_UTF8=y -CONFIG_DEBUG_INFO=y +CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y CONFIG_MAGIC_SYSRQ=y CONFIG_DETECT_HUNG_TASK=y CONFIG_BDI_SWITCH=y diff --git a/arch/powerpc/configs/mpc885_ads_defconfig b/arch/powerpc/configs/mpc885_ads_defconfig index c74dc76b1d0d..700115d85d6f 100644 --- a/arch/powerpc/configs/mpc885_ads_defconfig +++ b/arch/powerpc/configs/mpc885_ads_defconfig @@ -71,7 +71,7 @@ CONFIG_ROOT_NFS=y CONFIG_CRYPTO=y CONFIG_CRYPTO_DEV_TALITOS=y CONFIG_CRC32_SLICEBY4=y -CONFIG_DEBUG_INFO=y +CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_FS=y CONFIG_DEBUG_VM_PGTABLE=y diff --git a/arch/powerpc/configs/ppc6xx_defconfig b/arch/powerpc/configs/ppc6xx_defconfig index b622ecd73286..91967824272e 100644 --- a/arch/powerpc/configs/ppc6xx_defconfig +++ b/arch/powerpc/configs/ppc6xx_defconfig @@ -1065,7 +1065,7 @@ CONFIG_NLS_ISO8859_14=m CONFIG_NLS_ISO8859_15=m CONFIG_NLS_KOI8_R=m CONFIG_NLS_KOI8_U=m -CONFIG_DEBUG_INFO=y +CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y CONFIG_HEADERS_INSTALL=y CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_KERNEL=y diff --git a/arch/powerpc/configs/pq2fads_defconfig b/arch/powerpc/configs/pq2fads_defconfig index 9d8a76857c6f..9d63e2e65211 100644 --- a/arch/powerpc/configs/pq2fads_defconfig +++ b/arch/powerpc/configs/pq2fads_defconfig @@ -68,7 +68,7 @@ CONFIG_NLS_CODEPAGE_437=y CONFIG_NLS_ASCII=y CONFIG_NLS_ISO8859_1=y CONFIG_NLS_UTF8=y -CONFIG_DEBUG_INFO=y +CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y CONFIG_MAGIC_SYSRQ=y CONFIG_DETECT_HUNG_TASK=y # CONFIG_SCHED_DEBUG is not set diff --git a/arch/powerpc/configs/ps3_defconfig b/arch/powerpc/configs/ps3_defconfig index 7c95fab4b920..2d9ac233da68 100644 --- a/arch/powerpc/configs/ps3_defconfig +++ b/arch/powerpc/configs/ps3_defconfig @@ -153,7 +153,7 @@ CONFIG_NLS_CODEPAGE_437=y CONFIG_NLS_ISO8859_1=y CONFIG_CRC_CCITT=m CONFIG_CRC_T10DIF=y -CONFIG_DEBUG_INFO=y +CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_MEMORY_INIT=y CONFIG_DEBUG_STACKOVERFLOW=y diff --git a/arch/powerpc/configs/tqm8xx_defconfig b/arch/powerpc/configs/tqm8xx_defconfig index 77857d513022..083c2e57520a 100644 --- a/arch/powerpc/configs/tqm8xx_defconfig +++ b/arch/powerpc/configs/tqm8xx_defconfig @@ -55,6 +55,6 @@ CONFIG_CRAMFS=y CONFIG_NFS_FS=y CONFIG_ROOT_NFS=y CONFIG_CRC32_SLICEBY4=y -CONFIG_DEBUG_INFO=y +CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y CONFIG_MAGIC_SYSRQ=y CONFIG_DETECT_HUNG_TASK=y diff --git a/arch/powerpc/include/asm/archrandom.h b/arch/powerpc/include/asm/archrandom.h index 0e365c5b2396..564859e6a807 100644 --- a/arch/powerpc/include/asm/archrandom.h +++ b/arch/powerpc/include/asm/archrandom.h @@ -17,12 +17,7 @@ static inline size_t __must_check arch_get_random_seed_longs(unsigned long *v, s } #ifdef CONFIG_PPC_POWERNV -int powernv_hwrng_present(void); -int powernv_get_random_long(unsigned long *v); -int powernv_get_random_real_mode(unsigned long *v); -#else -static inline int powernv_hwrng_present(void) { return 0; } -static inline int powernv_get_random_real_mode(unsigned long *v) { return 0; } +int pnv_get_random_long(unsigned long *v); #endif #endif /* _ASM_POWERPC_ARCHRANDOM_H */ diff --git a/arch/powerpc/include/asm/asm-prototypes.h b/arch/powerpc/include/asm/asm-prototypes.h index d995c65d18ab..81631e64dbeb 100644 --- a/arch/powerpc/include/asm/asm-prototypes.h +++ b/arch/powerpc/include/asm/asm-prototypes.h @@ -2,8 +2,9 @@ #ifndef _ASM_POWERPC_ASM_PROTOTYPES_H #define _ASM_POWERPC_ASM_PROTOTYPES_H /* - * This file is for prototypes of C functions that are only called - * from asm, and any associated variables. + * This file is for C prototypes of asm symbols that are EXPORTed. + * It allows the modversions logic to see their prototype and + * generate proper CRCs for them. * * Copyright 2016, Daniel Axtens, IBM Corporation. */ @@ -34,12 +35,6 @@ int64_t __opal_call(int64_t a0, int64_t a1, int64_t a2, int64_t a3, int64_t a4, int64_t a5, int64_t a6, int64_t a7, int64_t opcode, uint64_t msr); -/* prom_init (OpenFirmware) */ -unsigned long __init prom_init(unsigned long r3, unsigned long r4, - unsigned long pp, - unsigned long r6, unsigned long r7, - unsigned long kbase); - /* misc runtime */ extern u64 __bswapdi2(u64); extern s64 __lshrdi3(s64, int); diff --git a/arch/powerpc/include/asm/barrier.h b/arch/powerpc/include/asm/barrier.h index f0e687236484..ef2d8b15eaab 100644 --- a/arch/powerpc/include/asm/barrier.h +++ b/arch/powerpc/include/asm/barrier.h @@ -42,6 +42,8 @@ /* The sub-arch has lwsync */ #if defined(CONFIG_PPC64) || defined(CONFIG_PPC_E500MC) # define SMPWMB LWSYNC +#elif defined(CONFIG_BOOKE) +# define SMPWMB mbar #else # define SMPWMB eieio #endif diff --git a/arch/powerpc/include/asm/book3s/64/hugetlb.h b/arch/powerpc/include/asm/book3s/64/hugetlb.h index b37a28f62cf6..aa1c67c8bfc8 100644 --- a/arch/powerpc/include/asm/book3s/64/hugetlb.h +++ b/arch/powerpc/include/asm/book3s/64/hugetlb.h @@ -1,6 +1,9 @@ /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_POWERPC_BOOK3S_64_HUGETLB_H #define _ASM_POWERPC_BOOK3S_64_HUGETLB_H + +#include <asm/firmware.h> + /* * For radix we want generic code to handle hugetlb. But then if we want * both hash and radix to be enabled together we need to workaround the diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush.h b/arch/powerpc/include/asm/book3s/64/tlbflush.h index d2e80f178b6d..206f920fe5b9 100644 --- a/arch/powerpc/include/asm/book3s/64/tlbflush.h +++ b/arch/powerpc/include/asm/book3s/64/tlbflush.h @@ -138,9 +138,29 @@ static inline void flush_all_mm(struct mm_struct *mm) static inline void flush_tlb_fix_spurious_fault(struct vm_area_struct *vma, unsigned long address) { - /* See ptep_set_access_flags comment */ - if (atomic_read(&vma->vm_mm->context.copros) > 0) - flush_tlb_page(vma, address); + /* + * Book3S 64 does not require spurious fault flushes because the PTE + * must be re-fetched in case of an access permission problem. So the + * only reason for a spurious fault should be concurrent modification + * to the PTE, in which case the PTE will eventually be re-fetched by + * the MMU when it attempts the access again. + * + * See: Power ISA Version 3.1B, 6.10.1.2 Modifying a Translation Table + * Entry, Setting a Reference or Change Bit or Upgrading Access + * Authority (PTE Subject to Atomic Hardware Updates): + * + * "If the only change being made to a valid PTE that is subject to + * atomic hardware updates is to set the Reference or Change bit to + * 1 or to upgrade access authority, a simpler sequence suffices + * because the translation hardware will refetch the PTE if an + * access is attempted for which the only problems were reference + * and/or change bits needing to be set or insufficient access + * authority." + * + * The nest MMU in POWER9 does not perform this PTE re-fetch, but + * it avoids the spurious fault problem by flushing the TLB before + * upgrading PTE permissions, see radix__ptep_set_access_flags. + */ } extern bool tlbie_capable; diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h index 549eb6dd146f..ae8c3e13cfce 100644 --- a/arch/powerpc/include/asm/cputable.h +++ b/arch/powerpc/include/asm/cputable.h @@ -70,9 +70,6 @@ struct cpu_spec { /* Used to restore cpu setup on secondary processors and at resume */ cpu_restore_t cpu_restore; - /* Used by oprofile userspace to select the right counters */ - char *oprofile_cpu_type; - /* Name of processor class, for the ELF AT_PLATFORM entry */ char *platform; diff --git a/arch/powerpc/include/asm/cputime.h b/arch/powerpc/include/asm/cputime.h index 504f7fe6711a..6d2b27997492 100644 --- a/arch/powerpc/include/asm/cputime.h +++ b/arch/powerpc/include/asm/cputime.h @@ -19,6 +19,7 @@ #include <asm/div64.h> #include <asm/time.h> #include <asm/param.h> +#include <asm/firmware.h> typedef u64 __nocast cputime_t; typedef u64 __nocast cputime64_t; diff --git a/arch/powerpc/include/asm/firmware.h b/arch/powerpc/include/asm/firmware.h index 8dddd34b8ecf..398e0b5e485f 100644 --- a/arch/powerpc/include/asm/firmware.h +++ b/arch/powerpc/include/asm/firmware.h @@ -55,6 +55,7 @@ #define FW_FEATURE_RPT_INVALIDATE ASM_CONST(0x0000010000000000) #define FW_FEATURE_FORM2_AFFINITY ASM_CONST(0x0000020000000000) #define FW_FEATURE_ENERGY_SCALE_INFO ASM_CONST(0x0000040000000000) +#define FW_FEATURE_WATCHDOG ASM_CONST(0x0000080000000000) #ifndef __ASSEMBLY__ @@ -76,7 +77,7 @@ enum { FW_FEATURE_DRC_INFO | FW_FEATURE_BLOCK_REMOVE | FW_FEATURE_PAPR_SCM | FW_FEATURE_ULTRAVISOR | FW_FEATURE_RPT_INVALIDATE | FW_FEATURE_FORM2_AFFINITY | - FW_FEATURE_ENERGY_SCALE_INFO, + FW_FEATURE_ENERGY_SCALE_INFO | FW_FEATURE_WATCHDOG, FW_FEATURE_PSERIES_ALWAYS = 0, FW_FEATURE_POWERNV_POSSIBLE = FW_FEATURE_OPAL | FW_FEATURE_ULTRAVISOR, FW_FEATURE_POWERNV_ALWAYS = 0, diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h index d92a20a85395..8abae463f6c1 100644 --- a/arch/powerpc/include/asm/hvcall.h +++ b/arch/powerpc/include/asm/hvcall.h @@ -79,6 +79,7 @@ #define H_NOT_ENOUGH_RESOURCES -44 #define H_R_STATE -45 #define H_RESCINDED -46 +#define H_P1 -54 #define H_P2 -55 #define H_P3 -56 #define H_P4 -57 @@ -87,6 +88,7 @@ #define H_P7 -60 #define H_P8 -61 #define H_P9 -62 +#define H_NOOP -63 #define H_TOO_BIG -64 #define H_UNSUPPORTED -67 #define H_OVERLAP -68 @@ -97,6 +99,8 @@ #define H_OP_MODE -73 #define H_COP_HW -74 #define H_STATE -75 +#define H_IN_USE -77 +#define H_ABORTED -78 #define H_UNSUPPORTED_FLAG_START -256 #define H_UNSUPPORTED_FLAG_END -511 #define H_MULTI_THREADS_ACTIVE -9005 @@ -321,10 +325,19 @@ #define H_SCM_UNBIND_ALL 0x3FC #define H_SCM_HEALTH 0x400 #define H_SCM_PERFORMANCE_STATS 0x418 +#define H_PKS_GET_CONFIG 0x41C +#define H_PKS_SET_PASSWORD 0x420 +#define H_PKS_GEN_PASSWORD 0x424 +#define H_PKS_WRITE_OBJECT 0x42C +#define H_PKS_GEN_KEY 0x430 +#define H_PKS_READ_OBJECT 0x434 +#define H_PKS_REMOVE_OBJECT 0x438 +#define H_PKS_CONFIRM_OBJECT_FLUSHED 0x43C #define H_RPT_INVALIDATE 0x448 #define H_SCM_FLUSH 0x44C #define H_GET_ENERGY_SCALE_INFO 0x450 -#define MAX_HCALL_OPCODE H_GET_ENERGY_SCALE_INFO +#define H_WATCHDOG 0x45C +#define MAX_HCALL_OPCODE H_WATCHDOG /* Scope args for H_SCM_UNBIND_ALL */ #define H_UNBIND_SCOPE_ALL (0x1) @@ -350,6 +363,14 @@ /* Platform specific hcalls, used by KVM */ #define H_RTAS 0xf000 +/* + * Platform specific hcalls, used by QEMU/SLOF. These are ignored by + * KVM and only kept here so we can identify them during tracing. + */ +#define H_LOGICAL_MEMOP 0xF001 +#define H_CAS 0XF002 +#define H_UPDATE_DT 0XF003 + /* "Platform specific hcalls", provided by PHYP */ #define H_GET_24X7_CATALOG_PAGE 0xF078 #define H_GET_24X7_DATA 0xF07C diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h index 674e5aaafcbd..26ede09c521d 100644 --- a/arch/powerpc/include/asm/hw_irq.h +++ b/arch/powerpc/include/asm/hw_irq.h @@ -113,14 +113,7 @@ static inline void __hard_RI_enable(void) static inline notrace unsigned long irq_soft_mask_return(void) { - unsigned long flags; - - asm volatile( - "lbz %0,%1(13)" - : "=r" (flags) - : "i" (offsetof(struct paca_struct, irq_soft_mask))); - - return flags; + return READ_ONCE(local_paca->irq_soft_mask); } /* @@ -130,7 +123,6 @@ static inline notrace unsigned long irq_soft_mask_return(void) */ static inline notrace void irq_soft_mask_set(unsigned long mask) { -#ifdef CONFIG_PPC_IRQ_SOFT_MASK_DEBUG /* * The irq mask must always include the STD bit if any are set. * @@ -145,49 +137,27 @@ static inline notrace void irq_soft_mask_set(unsigned long mask) * unmasks to be replayed, among other things. For now, take * the simple approach. */ - WARN_ON(mask && !(mask & IRQS_DISABLED)); -#endif + if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) + WARN_ON(mask && !(mask & IRQS_DISABLED)); - asm volatile( - "stb %0,%1(13)" - : - : "r" (mask), - "i" (offsetof(struct paca_struct, irq_soft_mask)) - : "memory"); + WRITE_ONCE(local_paca->irq_soft_mask, mask); + barrier(); } static inline notrace unsigned long irq_soft_mask_set_return(unsigned long mask) { - unsigned long flags; - -#ifdef CONFIG_PPC_IRQ_SOFT_MASK_DEBUG - WARN_ON(mask && !(mask & IRQS_DISABLED)); -#endif + unsigned long flags = irq_soft_mask_return(); - asm volatile( - "lbz %0,%1(13); stb %2,%1(13)" - : "=&r" (flags) - : "i" (offsetof(struct paca_struct, irq_soft_mask)), - "r" (mask) - : "memory"); + irq_soft_mask_set(mask); return flags; } static inline notrace unsigned long irq_soft_mask_or_return(unsigned long mask) { - unsigned long flags, tmp; - - asm volatile( - "lbz %0,%2(13); or %1,%0,%3; stb %1,%2(13)" - : "=&r" (flags), "=r" (tmp) - : "i" (offsetof(struct paca_struct, irq_soft_mask)), - "r" (mask) - : "memory"); + unsigned long flags = irq_soft_mask_return(); -#ifdef CONFIG_PPC_IRQ_SOFT_MASK_DEBUG - WARN_ON((mask | flags) && !((mask | flags) & IRQS_DISABLED)); -#endif + irq_soft_mask_set(flags | mask); return flags; } @@ -312,9 +282,7 @@ static inline bool pmi_irq_pending(void) flags = irq_soft_mask_set_return(IRQS_ALL_DISABLED); \ local_paca->irq_happened |= PACA_IRQ_HARD_DIS; \ if (!arch_irqs_disabled_flags(flags)) { \ - asm ("stdx %%r1, 0, %1 ;" \ - : "=m" (local_paca->saved_r1) \ - : "b" (&local_paca->saved_r1)); \ + WRITE_ONCE(local_paca->saved_r1, current_stack_pointer);\ trace_hardirqs_off(); \ } \ } while(0) @@ -353,11 +321,13 @@ bool power_pmu_wants_prompt_pmi(void); */ static inline bool should_hard_irq_enable(void) { -#ifdef CONFIG_PPC_IRQ_SOFT_MASK_DEBUG - WARN_ON(irq_soft_mask_return() == IRQS_ENABLED); - WARN_ON(mfmsr() & MSR_EE); -#endif -#ifdef CONFIG_PERF_EVENTS + if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) { + WARN_ON(irq_soft_mask_return() == IRQS_ENABLED); + WARN_ON(mfmsr() & MSR_EE); + } + + if (!IS_ENABLED(CONFIG_PERF_EVENTS)) + return false; /* * If the PMU is not running, there is not much reason to enable * MSR[EE] in irq handlers because any interrupts would just be @@ -372,9 +342,6 @@ static inline bool should_hard_irq_enable(void) return false; return true; -#else - return false; -#endif } /* @@ -382,11 +349,11 @@ static inline bool should_hard_irq_enable(void) */ static inline void do_hard_irq_enable(void) { -#ifdef CONFIG_PPC_IRQ_SOFT_MASK_DEBUG - WARN_ON(irq_soft_mask_return() == IRQS_ENABLED); - WARN_ON(get_paca()->irq_happened & PACA_IRQ_MUST_HARD_MASK); - WARN_ON(mfmsr() & MSR_EE); -#endif + if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) { + WARN_ON(irq_soft_mask_return() == IRQS_ENABLED); + WARN_ON(get_paca()->irq_happened & PACA_IRQ_MUST_HARD_MASK); + WARN_ON(mfmsr() & MSR_EE); + } /* * This allows PMI interrupts (and watchdog soft-NMIs) through. * There is no other reason to enable this way. diff --git a/arch/powerpc/include/asm/inst.h b/arch/powerpc/include/asm/inst.h index b49aae9f6f27..684d3f453282 100644 --- a/arch/powerpc/include/asm/inst.h +++ b/arch/powerpc/include/asm/inst.h @@ -139,25 +139,6 @@ static inline void ppc_inst_write(u32 *ptr, ppc_inst_t x) *(u64 *)ptr = ppc_inst_as_ulong(x); } -#define PPC_INST_STR_LEN sizeof("00000000 00000000") - -static inline char *__ppc_inst_as_str(char str[PPC_INST_STR_LEN], ppc_inst_t x) -{ - if (ppc_inst_prefixed(x)) - sprintf(str, "%08x %08x", ppc_inst_val(x), ppc_inst_suffix(x)); - else - sprintf(str, "%08x", ppc_inst_val(x)); - - return str; -} - -#define ppc_inst_as_str(x) \ -({ \ - char __str[PPC_INST_STR_LEN]; \ - __ppc_inst_as_str(__str, x); \ - __str; \ -}) - static inline int __copy_inst_from_kernel_nofault(ppc_inst_t *inst, u32 *src) { unsigned int val, suffix; diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h index b14f54d789d2..8069dbc4b8d1 100644 --- a/arch/powerpc/include/asm/interrupt.h +++ b/arch/powerpc/include/asm/interrupt.h @@ -69,6 +69,7 @@ #include <linux/context_tracking.h> #include <linux/hardirq.h> #include <asm/cputime.h> +#include <asm/firmware.h> #include <asm/ftrace.h> #include <asm/kprobes.h> #include <asm/runlatch.h> diff --git a/arch/powerpc/include/asm/io.h b/arch/powerpc/include/asm/io.h index 73fcd5cdb662..fc112a91d0c2 100644 --- a/arch/powerpc/include/asm/io.h +++ b/arch/powerpc/include/asm/io.h @@ -33,7 +33,6 @@ extern struct pci_dev *isa_bridge_pcidev; #include <asm/delay.h> #include <asm/mmiowb.h> #include <asm/mmu.h> -#include <asm/ppc_asm.h> #define SIO_CONFIG_RA 0x398 #define SIO_CONFIG_RD 0x399 diff --git a/arch/powerpc/include/asm/irq.h b/arch/powerpc/include/asm/irq.h index 13f0409dd617..5c1516a5ba8f 100644 --- a/arch/powerpc/include/asm/irq.h +++ b/arch/powerpc/include/asm/irq.h @@ -54,7 +54,6 @@ extern void *softirq_ctx[NR_CPUS]; void __do_IRQ(struct pt_regs *regs); extern void __init init_IRQ(void); -extern void __do_irq(struct pt_regs *regs); int irq_choose_cpu(const struct cpumask *mask); diff --git a/arch/powerpc/include/asm/kasan.h b/arch/powerpc/include/asm/kasan.h index a6be4025cba2..92a968202ba7 100644 --- a/arch/powerpc/include/asm/kasan.h +++ b/arch/powerpc/include/asm/kasan.h @@ -19,7 +19,7 @@ #define KASAN_SHADOW_SCALE_SHIFT 3 -#ifdef CONFIG_MODULES +#if defined(CONFIG_MODULES) && defined(CONFIG_PPC32) #define KASAN_KERN_START ALIGN_DOWN(PAGE_OFFSET - SZ_256M, SZ_256M) #else #define KASAN_KERN_START PAGE_OFFSET @@ -39,6 +39,17 @@ * c00e000000000000 << 3 + a80e000000000000 = c00fc00000000000 */ #define KASAN_SHADOW_END 0xc00fc00000000000UL + +#else + +/* + * The shadow ends before the highest accessible address + * because we don't need a shadow for the shadow. + * But it doesn't hurt to have a shadow for the shadow, + * keep shadow end aligned eases things. + */ +#define KASAN_SHADOW_END 0xc000200000000000UL + #endif #ifdef CONFIG_KASAN diff --git a/arch/powerpc/include/asm/kexec.h b/arch/powerpc/include/asm/kexec.h index d6f4edfe4737..f8d122d16af4 100644 --- a/arch/powerpc/include/asm/kexec.h +++ b/arch/powerpc/include/asm/kexec.h @@ -83,6 +83,7 @@ extern void default_machine_crash_shutdown(struct pt_regs *regs); extern int crash_shutdown_register(crash_shutdown_t handler); extern int crash_shutdown_unregister(crash_shutdown_t handler); +extern void crash_kexec_prepare(void); extern void crash_kexec_secondary(struct pt_regs *regs); int __init overlaps_crashkernel(unsigned long start, unsigned long size); extern void reserve_crashkernel(void); diff --git a/arch/powerpc/include/asm/kprobes.h b/arch/powerpc/include/asm/kprobes.h index bab364152b29..c8e4b4fd4e33 100644 --- a/arch/powerpc/include/asm/kprobes.h +++ b/arch/powerpc/include/asm/kprobes.h @@ -29,7 +29,7 @@ struct pt_regs; struct kprobe; -typedef ppc_opcode_t kprobe_opcode_t; +typedef u32 kprobe_opcode_t; extern kprobe_opcode_t optinsn_slot; diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h index 91c9f937edcd..bbf5e2c5fe09 100644 --- a/arch/powerpc/include/asm/kvm_book3s.h +++ b/arch/powerpc/include/asm/kvm_book3s.h @@ -280,9 +280,6 @@ extern void kvmppc_copy_to_svcpu(struct kvm_vcpu *vcpu); extern void kvmppc_copy_from_svcpu(struct kvm_vcpu *vcpu); long kvmppc_read_intr(void); -void kvmppc_bad_interrupt(struct pt_regs *regs); -void kvmhv_p9_set_lpcr(struct kvm_split_mode *sip); -void kvmhv_p9_restore_lpcr(struct kvm_split_mode *sip); void kvmppc_set_msr_hv(struct kvm_vcpu *vcpu, u64 msr); void kvmppc_inject_interrupt_hv(struct kvm_vcpu *vcpu, int vec, u64 srr1_flags); diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index 2909a88acd16..c2b003550dc9 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -523,7 +523,11 @@ struct kvm_vcpu_arch { struct kvmppc_book3s_shadow_vcpu *shadow_vcpu; #endif - struct pt_regs regs; + /* + * This is passed along to the HV via H_ENTER_NESTED. Align to + * prevent it crossing a real 4K page. + */ + struct pt_regs regs __aligned(512); struct thread_fp_state fp; @@ -830,11 +834,21 @@ struct kvm_vcpu_arch { #ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING struct kvmhv_tb_accumulator *cur_activity; /* What we're timing */ u64 cur_tb_start; /* when it started */ +#ifdef CONFIG_KVM_BOOK3S_HV_P9_TIMING + struct kvmhv_tb_accumulator vcpu_entry; + struct kvmhv_tb_accumulator vcpu_exit; + struct kvmhv_tb_accumulator in_guest; + struct kvmhv_tb_accumulator hcall; + struct kvmhv_tb_accumulator pg_fault; + struct kvmhv_tb_accumulator guest_entry; + struct kvmhv_tb_accumulator guest_exit; +#else struct kvmhv_tb_accumulator rm_entry; /* real-mode entry code */ struct kvmhv_tb_accumulator rm_intr; /* real-mode intr handling */ struct kvmhv_tb_accumulator rm_exit; /* real-mode exit code */ struct kvmhv_tb_accumulator guest_time; /* guest execution */ struct kvmhv_tb_accumulator cede_time; /* time napping inside guest */ +#endif #endif /* CONFIG_KVM_BOOK3S_HV_EXIT_TIMING */ }; diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h index 6c1002043367..8cb83600c434 100644 --- a/arch/powerpc/include/asm/machdep.h +++ b/arch/powerpc/include/asm/machdep.h @@ -8,8 +8,6 @@ #include <linux/dma-mapping.h> #include <linux/export.h> -#include <asm/setup.h> - struct pt_regs; struct pci_bus; struct device_node; diff --git a/arch/powerpc/include/asm/mman.h b/arch/powerpc/include/asm/mman.h index 1b024e64c8ec..17a77d47ed6d 100644 --- a/arch/powerpc/include/asm/mman.h +++ b/arch/powerpc/include/asm/mman.h @@ -12,6 +12,7 @@ #include <linux/mm.h> #include <linux/pkeys.h> #include <asm/cpu_has_feature.h> +#include <asm/firmware.h> static inline unsigned long arch_calc_vm_prot_bits(unsigned long prot, unsigned long pkey) diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h index 5f41565a1e5d..860d0290ca4d 100644 --- a/arch/powerpc/include/asm/mmu.h +++ b/arch/powerpc/include/asm/mmu.h @@ -96,15 +96,6 @@ */ #define MMU_FTR_NEED_DTLB_SW_LRU ASM_CONST(0x00200000) -/* Enable use of TLB reservation. Processor should support tlbsrx. - * instruction and MAS0[WQ]. - */ -#define MMU_FTR_USE_TLBRSRV ASM_CONST(0x00800000) - -/* Use paired MAS registers (MAS7||MAS3, etc.) - */ -#define MMU_FTR_USE_PAIRED_MAS ASM_CONST(0x01000000) - /* Doesn't support the B bit (1T segment) in SLBIE */ #define MMU_FTR_NO_SLBIE_B ASM_CONST(0x02000000) @@ -180,9 +171,6 @@ enum { #ifdef CONFIG_PPC_83xx MMU_FTR_NEED_DTLB_SW_LRU | #endif -#ifdef CONFIG_PPC_BOOK3E_64 - MMU_FTR_USE_TLBRSRV | MMU_FTR_USE_PAIRED_MAS | -#endif #ifdef CONFIG_PPC_BOOK3S_64 MMU_FTR_KERNEL_RO | #ifdef CONFIG_PPC_64S_HASH_MMU diff --git a/arch/powerpc/include/asm/mpc52xx.h b/arch/powerpc/include/asm/mpc52xx.h index ce1e0aabaa64..5ea16a71c2f0 100644 --- a/arch/powerpc/include/asm/mpc52xx.h +++ b/arch/powerpc/include/asm/mpc52xx.h @@ -15,7 +15,6 @@ #ifndef __ASSEMBLY__ #include <asm/types.h> -#include <asm/prom.h> #include <asm/mpc5xxx.h> #endif /* __ASSEMBLY__ */ @@ -268,13 +267,14 @@ struct mpc52xx_intr { #ifndef __ASSEMBLY__ +struct device_node; + /* mpc52xx_common.c */ extern void mpc5200_setup_xlb_arbiter(void); extern void mpc52xx_declare_of_platform_devices(void); extern int mpc5200_psc_ac97_gpio_reset(int psc_number); extern void mpc52xx_map_common_devices(void); extern int mpc52xx_set_psc_clkdiv(int psc_id, int clkdiv); -extern unsigned int mpc52xx_get_xtal_freq(struct device_node *node); extern void __noreturn mpc52xx_restart(char *cmd); /* mpc52xx_gpt.c */ diff --git a/arch/powerpc/include/asm/mpc5xxx.h b/arch/powerpc/include/asm/mpc5xxx.h index 2f60f5c5461b..44db26380435 100644 --- a/arch/powerpc/include/asm/mpc5xxx.h +++ b/arch/powerpc/include/asm/mpc5xxx.h @@ -11,7 +11,14 @@ #ifndef __ASM_POWERPC_MPC5xxx_H__ #define __ASM_POWERPC_MPC5xxx_H__ -extern unsigned long mpc5xxx_get_bus_frequency(struct device_node *node); +#include <linux/property.h> + +unsigned long mpc5xxx_fwnode_get_bus_frequency(struct fwnode_handle *fwnode); + +static inline unsigned long mpc5xxx_get_bus_frequency(struct device *dev) +{ + return mpc5xxx_fwnode_get_bus_frequency(dev_fwnode(dev)); +} #endif /* __ASM_POWERPC_MPC5xxx_H__ */ diff --git a/arch/powerpc/include/asm/nmi.h b/arch/powerpc/include/asm/nmi.h index ea0e487f87b1..c3c7adef74de 100644 --- a/arch/powerpc/include/asm/nmi.h +++ b/arch/powerpc/include/asm/nmi.h @@ -5,8 +5,10 @@ #ifdef CONFIG_PPC_WATCHDOG extern void arch_touch_nmi_watchdog(void); long soft_nmi_interrupt(struct pt_regs *regs); +void watchdog_nmi_set_timeout_pct(u64 pct); #else static inline void arch_touch_nmi_watchdog(void) {} +static inline void watchdog_nmi_set_timeout_pct(u64 pct) {} #endif #ifdef CONFIG_NMI_IPI diff --git a/arch/powerpc/include/asm/nohash/64/pgalloc.h b/arch/powerpc/include/asm/nohash/64/pgalloc.h index 668aee6017e7..e50b211becb3 100644 --- a/arch/powerpc/include/asm/nohash/64/pgalloc.h +++ b/arch/powerpc/include/asm/nohash/64/pgalloc.h @@ -15,7 +15,10 @@ struct vmemmap_backing { }; extern struct vmemmap_backing *vmemmap_list; -#define p4d_populate(MM, P4D, PUD) p4d_set(P4D, (unsigned long)PUD) +static inline void p4d_populate(struct mm_struct *mm, p4d_t *p4d, pud_t *pud) +{ + p4d_set(p4d, (unsigned long)pud); +} static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr) { diff --git a/arch/powerpc/include/asm/nohash/64/pgtable.h b/arch/powerpc/include/asm/nohash/64/pgtable.h index 57083f95e82b..599921cc257e 100644 --- a/arch/powerpc/include/asm/nohash/64/pgtable.h +++ b/arch/powerpc/include/asm/nohash/64/pgtable.h @@ -25,7 +25,7 @@ /* * Define the address range of the kernel non-linear virtual area */ -#define KERN_VIRT_START ASM_CONST(0x8000000000000000) +#define KERN_VIRT_START ASM_CONST(0xc000100000000000) #define KERN_VIRT_SIZE ASM_CONST(0x0000100000000000) /* @@ -38,15 +38,16 @@ #define VMALLOC_END (VMALLOC_START + VMALLOC_SIZE) /* - * The second half of the kernel virtual space is used for IO mappings, + * The third quarter of the kernel virtual space is used for IO mappings, * it's itself carved into the PIO region (ISA and PHB IO space) and * the ioremap space * * ISA_IO_BASE = KERN_IO_START, 64K reserved area * PHB_IO_BASE = ISA_IO_BASE + 64K to ISA_IO_BASE + 2G, PHB IO spaces - * IOREMAP_BASE = ISA_IO_BASE + 2G to VMALLOC_START + PGTABLE_RANGE + * IOREMAP_BASE = ISA_IO_BASE + 2G to KERN_IO_START + KERN_IO_SIZE */ #define KERN_IO_START (KERN_VIRT_START + (KERN_VIRT_SIZE >> 1)) +#define KERN_IO_SIZE (KERN_VIRT_SIZE >> 2) #define FULL_IO_SIZE 0x80000000ul #define ISA_IO_BASE (KERN_IO_START) #define ISA_IO_END (KERN_IO_START + 0x10000ul) @@ -54,21 +55,9 @@ #define PHB_IO_END (KERN_IO_START + FULL_IO_SIZE) #define IOREMAP_BASE (PHB_IO_END) #define IOREMAP_START (ioremap_bot) -#define IOREMAP_END (KERN_VIRT_START + KERN_VIRT_SIZE - FIXADDR_SIZE) +#define IOREMAP_END (KERN_IO_START + KERN_IO_SIZE - FIXADDR_SIZE) #define FIXADDR_SIZE SZ_32M - -/* - * Region IDs - */ -#define REGION_SHIFT 60UL -#define REGION_MASK (0xfUL << REGION_SHIFT) -#define REGION_ID(ea) (((unsigned long)(ea)) >> REGION_SHIFT) - -#define VMALLOC_REGION_ID (REGION_ID(VMALLOC_START)) -#define KERNEL_REGION_ID (REGION_ID(PAGE_OFFSET)) -#define USER_REGION_ID (0UL) - /* * Defines the address of the vmemap area, in its own region on * after the vmalloc space on Book3E @@ -83,8 +72,6 @@ */ #include <asm/nohash/pte-book3e.h> -#define _PAGE_SAO 0 - #define PTE_RPN_MASK (~((1UL << PTE_RPN_SHIFT) - 1)) /* diff --git a/arch/powerpc/include/asm/nohash/pgtable.h b/arch/powerpc/include/asm/nohash/pgtable.h index ac75f4ab0dba..b499da6c1a99 100644 --- a/arch/powerpc/include/asm/nohash/pgtable.h +++ b/arch/powerpc/include/asm/nohash/pgtable.h @@ -193,7 +193,7 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr, if (IS_ENABLED(CONFIG_PPC32) && IS_ENABLED(CONFIG_PTE_64BIT) && !percpu) { __asm__ __volatile__("\ stw%X0 %2,%0\n\ - eieio\n\ + mbar\n\ stw%X1 %L2,%1" : "=m" (*ptep), "=m" (*((unsigned char *)ptep+4)) : "r" (pte) : "memory"); diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h index c85f901227c9..e18c95f4e1d4 100644 --- a/arch/powerpc/include/asm/pci-bridge.h +++ b/arch/powerpc/include/asm/pci-bridge.h @@ -170,11 +170,15 @@ static inline struct pci_controller *pci_bus_to_host(const struct pci_bus *bus) return bus->sysdata; } +#ifdef CONFIG_PPC_PMAC extern int pci_device_from_OF_node(struct device_node *node, u8 *bus, u8 *devfn); +#endif #ifndef CONFIG_PPC64 +#ifdef CONFIG_PPC_CHRP extern void pci_create_OF_bus_map(void); +#endif #else /* CONFIG_PPC64 */ diff --git a/arch/powerpc/include/asm/pci.h b/arch/powerpc/include/asm/pci.h index f9da506751bb..289f1ec85bc5 100644 --- a/arch/powerpc/include/asm/pci.h +++ b/arch/powerpc/include/asm/pci.h @@ -14,7 +14,6 @@ #include <asm/machdep.h> #include <asm/io.h> -#include <asm/prom.h> #include <asm/pci-bridge.h> /* Return values for pci_controller_ops.probe_mode function */ diff --git a/arch/powerpc/include/asm/plpar_wrappers.h b/arch/powerpc/include/asm/plpar_wrappers.h index 83e0f701ebc6..8239c0af5eb2 100644 --- a/arch/powerpc/include/asm/plpar_wrappers.h +++ b/arch/powerpc/include/asm/plpar_wrappers.h @@ -43,11 +43,10 @@ static inline long extended_cede_processor(unsigned long latency_hint) set_cede_latency_hint(latency_hint); rc = cede_processor(); -#ifdef CONFIG_PPC_IRQ_SOFT_MASK_DEBUG + /* Ensure that H_CEDE returns with IRQs on */ - if (WARN_ON(!(mfmsr() & MSR_EE))) + if (WARN_ON(IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG) && !(mfmsr() & MSR_EE))) __hard_irq_enable(); -#endif set_cede_latency_hint(old_latency_hint); diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h index 89beabf5325c..7b81b37a191e 100644 --- a/arch/powerpc/include/asm/ppc-opcode.h +++ b/arch/powerpc/include/asm/ppc-opcode.h @@ -290,7 +290,6 @@ #define PPC_INST_STRING 0x7c00042a #define PPC_INST_STRING_MASK 0xfc0007fe #define PPC_INST_STRING_GEN_MASK 0xfc00067e -#define PPC_INST_SETB 0x7c000100 #define PPC_INST_STSWI 0x7c0005aa #define PPC_INST_STSWX 0x7c00052a #define PPC_INST_TRECHKPT 0x7c0007dd @@ -581,6 +580,9 @@ #define PPC_RAW_BRANCH(offset) (0x48000000 | PPC_LI(offset)) #define PPC_RAW_BL(offset) (0x48000001 | PPC_LI(offset)) +#define PPC_RAW_TW(t0, a, b) (0x7f000008 | ___PPC_RS(t0) | ___PPC_RA(a) | ___PPC_RB(b)) +#define PPC_RAW_TRAP() PPC_RAW_TW(31, 0, 0) +#define PPC_RAW_SETB(t, bfa) (0x7c000100 | ___PPC_RT(t) | ___PPC_RA((bfa) << 2)) /* Deal with instructions that older assemblers aren't aware of */ #define PPC_BCCTR_FLUSH stringify_in_c(.long PPC_INST_BCCTR_FLUSH) diff --git a/arch/powerpc/include/asm/probes.h b/arch/powerpc/include/asm/probes.h index 6f66e358aa37..e77a2ed7d938 100644 --- a/arch/powerpc/include/asm/probes.h +++ b/arch/powerpc/include/asm/probes.h @@ -9,9 +9,9 @@ */ #include <linux/types.h> #include <asm/disassemble.h> +#include <asm/ppc-opcode.h> -typedef u32 ppc_opcode_t; -#define BREAKPOINT_INSTRUCTION 0x7fe00008 /* trap */ +#define BREAKPOINT_INSTRUCTION PPC_RAW_TRAP() /* trap */ /* Trap definitions per ISA */ #define IS_TW(instr) (((instr) & 0xfc0007fe) == 0x7c000008) diff --git a/arch/powerpc/include/asm/prom.h b/arch/powerpc/include/asm/prom.h index 5c80152e8f18..2e82820fbd64 100644 --- a/arch/powerpc/include/asm/prom.h +++ b/arch/powerpc/include/asm/prom.h @@ -12,15 +12,10 @@ * Updates for PPC64 by Peter Bergner & David Engebretsen, IBM Corp. */ #include <linux/types.h> -#include <asm/irq.h> -#include <linux/atomic.h> - -/* These includes should be removed once implicit includes are cleaned up. */ -#include <linux/of.h> -#include <linux/of_fdt.h> -#include <linux/of_address.h> -#include <linux/of_irq.h> -#include <linux/platform_device.h> +#include <asm/firmware.h> + +struct device_node; +struct property; #define OF_DT_BEGIN_NODE 0x1 /* Start of node, full name */ #define OF_DT_END_NODE 0x2 /* End node */ diff --git a/arch/powerpc/include/asm/setup.h b/arch/powerpc/include/asm/setup.h index 8fa37ef5da4d..d8c28902cf59 100644 --- a/arch/powerpc/include/asm/setup.h +++ b/arch/powerpc/include/asm/setup.h @@ -12,7 +12,6 @@ extern unsigned long long memory_limit; extern void *zalloc_maybe_bootmem(size_t size, gfp_t mask); struct device_node; -extern void note_scsi_host(struct device_node *, void *); /* Used in very early kernel initialization. */ extern unsigned long reloc_offset(void); @@ -85,6 +84,11 @@ void __init machine_init(u64 dt_ptr); void __init early_setup(unsigned long dt_ptr); void early_setup_secondary(void); +/* prom_init (OpenFirmware) */ +unsigned long __init prom_init(unsigned long r3, unsigned long r4, + unsigned long pp, unsigned long r6, + unsigned long r7, unsigned long kbase); + #endif /* !__ASSEMBLY__ */ #endif /* _ASM_POWERPC_SETUP_H */ diff --git a/arch/powerpc/include/asm/synch.h b/arch/powerpc/include/asm/synch.h index 1d67bc8d7bc6..7130176d8cb8 100644 --- a/arch/powerpc/include/asm/synch.h +++ b/arch/powerpc/include/asm/synch.h @@ -14,7 +14,10 @@ extern void do_lwsync_fixups(unsigned long value, void *fixup_start, static inline void eieio(void) { - __asm__ __volatile__ ("eieio" : : : "memory"); + if (IS_ENABLED(CONFIG_BOOKE)) + __asm__ __volatile__ ("mbar" : : : "memory"); + else + __asm__ __volatile__ ("eieio" : : : "memory"); } static inline void isync(void) diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h index 105f200b1e31..3ddc65c63a49 100644 --- a/arch/powerpc/include/asm/uaccess.h +++ b/arch/powerpc/include/asm/uaccess.h @@ -2,7 +2,6 @@ #ifndef _ARCH_POWERPC_UACCESS_H #define _ARCH_POWERPC_UACCESS_H -#include <asm/ppc_asm.h> #include <asm/processor.h> #include <asm/page.h> #include <asm/extable.h> diff --git a/arch/powerpc/include/asm/uprobes.h b/arch/powerpc/include/asm/uprobes.h index a7ae1860115a..4fea116d3d37 100644 --- a/arch/powerpc/include/asm/uprobes.h +++ b/arch/powerpc/include/asm/uprobes.h @@ -12,7 +12,7 @@ #include <linux/notifier.h> #include <asm/probes.h> -typedef ppc_opcode_t uprobe_opcode_t; +typedef u32 uprobe_opcode_t; #define MAX_UINSN_BYTES 8 #define UPROBE_XOL_SLOT_BYTES (MAX_UINSN_BYTES) diff --git a/arch/powerpc/include/asm/word-at-a-time.h b/arch/powerpc/include/asm/word-at-a-time.h index f3f4710d4ff5..46c31fb8748d 100644 --- a/arch/powerpc/include/asm/word-at-a-time.h +++ b/arch/powerpc/include/asm/word-at-a-time.h @@ -7,7 +7,7 @@ #include <linux/kernel.h> #include <asm/asm-compat.h> -#include <asm/ppc_asm.h> +#include <asm/extable.h> #ifdef __BIG_ENDIAN__ diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index c8cf924bf9c0..06d2d1f78f71 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -54,6 +54,13 @@ CFLAGS_cputable.o += -DDISABLE_BRANCH_PROFILING CFLAGS_btext.o += -DDISABLE_BRANCH_PROFILING endif +#ifdef CONFIG_RANDOMIZE_KSTACK_OFFSET +# Remove stack protector to avoid triggering unneeded stack canary +# checks due to randomize_kstack_offset. +CFLAGS_REMOVE_syscall.o = -fstack-protector -fstack-protector-strong +CFLAGS_syscall.o += -fno-stack-protector +#endif + obj-y := cputable.o syscalls.o \ irq.o align.o signal_$(BITS).o pmc.o vdso.o \ process.o systbl.o idle.o \ @@ -62,9 +69,9 @@ obj-y := cputable.o syscalls.o \ udbg.o misc.o io.o misc_$(BITS).o \ of_platform.o prom_parse.o firmware.o \ hw_breakpoint_constraints.o interrupt.o \ - kdebugfs.o stacktrace.o + kdebugfs.o stacktrace.o syscall.o obj-y += ptrace/ -obj-$(CONFIG_PPC64) += setup_64.o \ +obj-$(CONFIG_PPC64) += setup_64.o irq_64.o\ paca.o nvram_64.o note.o obj-$(CONFIG_COMPAT) += sys_ppc32.o signal_32.o obj-$(CONFIG_VDSO32) += vdso32_wrapper.o diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index eec536aef83a..8c10f536e478 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -379,7 +379,7 @@ int main(void) OFFSET(VCPU_SPRG2, kvm_vcpu, arch.shregs.sprg2); OFFSET(VCPU_SPRG3, kvm_vcpu, arch.shregs.sprg3); #endif -#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING +#ifdef CONFIG_KVM_BOOK3S_HV_P8_TIMING OFFSET(VCPU_TB_RMENTRY, kvm_vcpu, arch.rm_entry); OFFSET(VCPU_TB_RMINTR, kvm_vcpu, arch.rm_intr); OFFSET(VCPU_TB_RMEXIT, kvm_vcpu, arch.rm_exit); diff --git a/arch/powerpc/kernel/btext.c b/arch/powerpc/kernel/btext.c index 8f69bb07e500..2769889219bf 100644 --- a/arch/powerpc/kernel/btext.c +++ b/arch/powerpc/kernel/btext.c @@ -73,7 +73,7 @@ static inline void rmci_maybe_off(void) * the display during identify_machine() and MMU_Init() * * The display is mapped to virtual address 0xD0000000, rather - * than 1:1, because some some CHRP machines put the frame buffer + * than 1:1, because some CHRP machines put the frame buffer * in the region starting at 0xC0000000 (PAGE_OFFSET). * This mapping is temporary and will disappear as soon as the * setup done by MMU_Init() is applied. diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index a5dbfccd2047..d8e42ef750f1 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -149,7 +149,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .pmc_type = PPC_PMC_IBM, .cpu_setup = __setup_cpu_ppc970, .cpu_restore = __restore_cpu_ppc970, - .oprofile_cpu_type = "ppc64/970", .platform = "ppc970", }, { /* PPC970FX */ @@ -166,7 +165,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .pmc_type = PPC_PMC_IBM, .cpu_setup = __setup_cpu_ppc970, .cpu_restore = __restore_cpu_ppc970, - .oprofile_cpu_type = "ppc64/970", .platform = "ppc970", }, { /* PPC970MP DD1.0 - no DEEPNAP, use regular 970 init */ @@ -183,7 +181,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .pmc_type = PPC_PMC_IBM, .cpu_setup = __setup_cpu_ppc970, .cpu_restore = __restore_cpu_ppc970, - .oprofile_cpu_type = "ppc64/970MP", .platform = "ppc970", }, { /* PPC970MP */ @@ -200,7 +197,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .pmc_type = PPC_PMC_IBM, .cpu_setup = __setup_cpu_ppc970MP, .cpu_restore = __restore_cpu_ppc970, - .oprofile_cpu_type = "ppc64/970MP", .platform = "ppc970", }, { /* PPC970GX */ @@ -216,7 +212,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .num_pmcs = 8, .pmc_type = PPC_PMC_IBM, .cpu_setup = __setup_cpu_ppc970, - .oprofile_cpu_type = "ppc64/970", .platform = "ppc970", }, { /* Power5 GR */ @@ -230,7 +225,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .dcache_bsize = 128, .num_pmcs = 6, .pmc_type = PPC_PMC_IBM, - .oprofile_cpu_type = "ppc64/power5", .platform = "power5", }, { /* Power5++ */ @@ -243,7 +237,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 6, - .oprofile_cpu_type = "ppc64/power5++", .platform = "power5+", }, { /* Power5 GS */ @@ -257,7 +250,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .dcache_bsize = 128, .num_pmcs = 6, .pmc_type = PPC_PMC_IBM, - .oprofile_cpu_type = "ppc64/power5+", .platform = "power5+", }, { /* POWER6 in P5+ mode; 2.04-compliant processor */ @@ -269,7 +261,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .mmu_features = MMU_FTRS_POWER5, .icache_bsize = 128, .dcache_bsize = 128, - .oprofile_cpu_type = "ppc64/ibm-compat-v1", .platform = "power5+", }, { /* Power6 */ @@ -284,7 +275,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .dcache_bsize = 128, .num_pmcs = 6, .pmc_type = PPC_PMC_IBM, - .oprofile_cpu_type = "ppc64/power6", .platform = "power6x", }, { /* 2.05-compliant processor, i.e. Power6 "architected" mode */ @@ -296,7 +286,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .mmu_features = MMU_FTRS_POWER6, .icache_bsize = 128, .dcache_bsize = 128, - .oprofile_cpu_type = "ppc64/ibm-compat-v1", .platform = "power6", }, { /* 2.06-compliant processor, i.e. Power7 "architected" mode */ @@ -309,7 +298,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .mmu_features = MMU_FTRS_POWER7, .icache_bsize = 128, .dcache_bsize = 128, - .oprofile_cpu_type = "ppc64/ibm-compat-v1", .cpu_setup = __setup_cpu_power7, .cpu_restore = __restore_cpu_power7, .machine_check_early = __machine_check_early_realmode_p7, @@ -325,7 +313,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .mmu_features = MMU_FTRS_POWER8, .icache_bsize = 128, .dcache_bsize = 128, - .oprofile_cpu_type = "ppc64/ibm-compat-v1", .cpu_setup = __setup_cpu_power8, .cpu_restore = __restore_cpu_power8, .machine_check_early = __machine_check_early_realmode_p8, @@ -341,7 +328,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .mmu_features = MMU_FTRS_POWER9, .icache_bsize = 128, .dcache_bsize = 128, - .oprofile_cpu_type = "ppc64/ibm-compat-v1", .cpu_setup = __setup_cpu_power9, .cpu_restore = __restore_cpu_power9, .platform = "power9", @@ -356,7 +342,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .mmu_features = MMU_FTRS_POWER10, .icache_bsize = 128, .dcache_bsize = 128, - .oprofile_cpu_type = "ppc64/ibm-compat-v1", .cpu_setup = __setup_cpu_power10, .cpu_restore = __restore_cpu_power10, .platform = "power10", @@ -373,7 +358,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .dcache_bsize = 128, .num_pmcs = 6, .pmc_type = PPC_PMC_IBM, - .oprofile_cpu_type = "ppc64/power7", .cpu_setup = __setup_cpu_power7, .cpu_restore = __restore_cpu_power7, .machine_check_early = __machine_check_early_realmode_p7, @@ -391,7 +375,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .dcache_bsize = 128, .num_pmcs = 6, .pmc_type = PPC_PMC_IBM, - .oprofile_cpu_type = "ppc64/power7", .cpu_setup = __setup_cpu_power7, .cpu_restore = __restore_cpu_power7, .machine_check_early = __machine_check_early_realmode_p7, @@ -409,7 +392,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .dcache_bsize = 128, .num_pmcs = 6, .pmc_type = PPC_PMC_IBM, - .oprofile_cpu_type = "ppc64/power8", .cpu_setup = __setup_cpu_power8, .cpu_restore = __restore_cpu_power8, .machine_check_early = __machine_check_early_realmode_p8, @@ -427,7 +409,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .dcache_bsize = 128, .num_pmcs = 6, .pmc_type = PPC_PMC_IBM, - .oprofile_cpu_type = "ppc64/power8", .cpu_setup = __setup_cpu_power8, .cpu_restore = __restore_cpu_power8, .machine_check_early = __machine_check_early_realmode_p8, @@ -445,7 +426,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .dcache_bsize = 128, .num_pmcs = 6, .pmc_type = PPC_PMC_IBM, - .oprofile_cpu_type = "ppc64/power8", .cpu_setup = __setup_cpu_power8, .cpu_restore = __restore_cpu_power8, .machine_check_early = __machine_check_early_realmode_p8, @@ -463,7 +443,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .dcache_bsize = 128, .num_pmcs = 6, .pmc_type = PPC_PMC_IBM, - .oprofile_cpu_type = "ppc64/power9", .cpu_setup = __setup_cpu_power9, .cpu_restore = __restore_cpu_power9, .machine_check_early = __machine_check_early_realmode_p9, @@ -481,7 +460,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .dcache_bsize = 128, .num_pmcs = 6, .pmc_type = PPC_PMC_IBM, - .oprofile_cpu_type = "ppc64/power9", .cpu_setup = __setup_cpu_power9, .cpu_restore = __restore_cpu_power9, .machine_check_early = __machine_check_early_realmode_p9, @@ -499,7 +477,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .dcache_bsize = 128, .num_pmcs = 6, .pmc_type = PPC_PMC_IBM, - .oprofile_cpu_type = "ppc64/power9", .cpu_setup = __setup_cpu_power9, .cpu_restore = __restore_cpu_power9, .machine_check_early = __machine_check_early_realmode_p9, @@ -517,7 +494,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .dcache_bsize = 128, .num_pmcs = 6, .pmc_type = PPC_PMC_IBM, - .oprofile_cpu_type = "ppc64/power9", .cpu_setup = __setup_cpu_power9, .cpu_restore = __restore_cpu_power9, .machine_check_early = __machine_check_early_realmode_p9, @@ -535,7 +511,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .dcache_bsize = 128, .num_pmcs = 6, .pmc_type = PPC_PMC_IBM, - .oprofile_cpu_type = "ppc64/power10", .cpu_setup = __setup_cpu_power10, .cpu_restore = __restore_cpu_power10, .machine_check_early = __machine_check_early_realmode_p10, @@ -554,7 +529,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .dcache_bsize = 128, .num_pmcs = 4, .pmc_type = PPC_PMC_IBM, - .oprofile_cpu_type = "ppc64/cell-be", .platform = "ppc-cell-be", }, { /* PA Semi PA6T */ @@ -570,7 +544,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .pmc_type = PPC_PMC_PA6T, .cpu_setup = __setup_cpu_pa6t, .cpu_restore = __restore_cpu_pa6t, - .oprofile_cpu_type = "ppc64/pa6t", .platform = "pa6t", }, { /* default match */ @@ -734,7 +707,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_setup = __setup_cpu_750, .machine_check = machine_check_generic, .platform = "ppc750", - .oprofile_cpu_type = "ppc/750", }, { /* 745/755 */ .pvr_mask = 0xfffff000, @@ -765,7 +737,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_setup = __setup_cpu_750, .machine_check = machine_check_generic, .platform = "ppc750", - .oprofile_cpu_type = "ppc/750", }, { /* 750FX rev 2.0 must disable HID0[DPM] */ .pvr_mask = 0xffffffff, @@ -781,7 +752,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_setup = __setup_cpu_750, .machine_check = machine_check_generic, .platform = "ppc750", - .oprofile_cpu_type = "ppc/750", }, { /* 750FX (All revs except 2.0) */ .pvr_mask = 0xffff0000, @@ -797,7 +767,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_setup = __setup_cpu_750fx, .machine_check = machine_check_generic, .platform = "ppc750", - .oprofile_cpu_type = "ppc/750", }, { /* 750GX */ .pvr_mask = 0xffff0000, @@ -813,7 +782,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_setup = __setup_cpu_750fx, .machine_check = machine_check_generic, .platform = "ppc750", - .oprofile_cpu_type = "ppc/750", }, { /* 740/750 (L2CR bit need fixup for 740) */ .pvr_mask = 0xffff0000, @@ -891,7 +859,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .num_pmcs = 6, .pmc_type = PPC_PMC_G4, .cpu_setup = __setup_cpu_745x, - .oprofile_cpu_type = "ppc/7450", .machine_check = machine_check_generic, .platform = "ppc7450", }, @@ -908,7 +875,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .num_pmcs = 6, .pmc_type = PPC_PMC_G4, .cpu_setup = __setup_cpu_745x, - .oprofile_cpu_type = "ppc/7450", .machine_check = machine_check_generic, .platform = "ppc7450", }, @@ -925,7 +891,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .num_pmcs = 6, .pmc_type = PPC_PMC_G4, .cpu_setup = __setup_cpu_745x, - .oprofile_cpu_type = "ppc/7450", .machine_check = machine_check_generic, .platform = "ppc7450", }, @@ -942,7 +907,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .num_pmcs = 6, .pmc_type = PPC_PMC_G4, .cpu_setup = __setup_cpu_745x, - .oprofile_cpu_type = "ppc/7450", .machine_check = machine_check_generic, .platform = "ppc7450", }, @@ -959,7 +923,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .num_pmcs = 6, .pmc_type = PPC_PMC_G4, .cpu_setup = __setup_cpu_745x, - .oprofile_cpu_type = "ppc/7450", .machine_check = machine_check_generic, .platform = "ppc7450", }, @@ -976,7 +939,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .num_pmcs = 6, .pmc_type = PPC_PMC_G4, .cpu_setup = __setup_cpu_745x, - .oprofile_cpu_type = "ppc/7450", .machine_check = machine_check_generic, .platform = "ppc7450", }, @@ -993,7 +955,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .num_pmcs = 6, .pmc_type = PPC_PMC_G4, .cpu_setup = __setup_cpu_745x, - .oprofile_cpu_type = "ppc/7450", .machine_check = machine_check_generic, .platform = "ppc7450", }, @@ -1010,7 +971,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .num_pmcs = 6, .pmc_type = PPC_PMC_G4, .cpu_setup = __setup_cpu_745x, - .oprofile_cpu_type = "ppc/7450", .machine_check = machine_check_generic, .platform = "ppc7450", }, @@ -1026,7 +986,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .num_pmcs = 6, .pmc_type = PPC_PMC_G4, .cpu_setup = __setup_cpu_745x, - .oprofile_cpu_type = "ppc/7450", .machine_check = machine_check_generic, .platform = "ppc7450", }, @@ -1043,7 +1002,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .num_pmcs = 6, .pmc_type = PPC_PMC_G4, .cpu_setup = __setup_cpu_745x, - .oprofile_cpu_type = "ppc/7450", .machine_check = machine_check_generic, .platform = "ppc7450", }, @@ -1060,7 +1018,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .num_pmcs = 6, .pmc_type = PPC_PMC_G4, .cpu_setup = __setup_cpu_745x, - .oprofile_cpu_type = "ppc/7450", .machine_check = machine_check_generic, .platform = "ppc7450", }, @@ -1172,7 +1129,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_setup = __setup_cpu_603, .machine_check = machine_check_83xx, .num_pmcs = 4, - .oprofile_cpu_type = "ppc/e300", .platform = "ppc603", }, { /* e300c4 (e300c1, plus one IU) */ @@ -1188,7 +1144,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_setup = __setup_cpu_603, .machine_check = machine_check_83xx, .num_pmcs = 4, - .oprofile_cpu_type = "ppc/e300", .platform = "ppc603", }, #endif @@ -1884,7 +1839,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, - .oprofile_cpu_type = "ppc/e500", .cpu_setup = __setup_cpu_e500v1, .machine_check = machine_check_e500, .platform = "ppc8540", @@ -1903,7 +1857,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, - .oprofile_cpu_type = "ppc/e500", .cpu_setup = __setup_cpu_e500v2, .machine_check = machine_check_e500, .platform = "ppc8548", @@ -1922,7 +1875,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .icache_bsize = 64, .dcache_bsize = 64, .num_pmcs = 4, - .oprofile_cpu_type = "ppc/e500mc", .cpu_setup = __setup_cpu_e500mc, .machine_check = machine_check_e500mc, .platform = "ppce500mc", @@ -1943,7 +1895,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .icache_bsize = 64, .dcache_bsize = 64, .num_pmcs = 4, - .oprofile_cpu_type = "ppc/e500mc", .cpu_setup = __setup_cpu_e5500, #ifndef CONFIG_PPC32 .cpu_restore = __restore_cpu_e5500, @@ -1965,7 +1916,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .icache_bsize = 64, .dcache_bsize = 64, .num_pmcs = 6, - .oprofile_cpu_type = "ppc/e6500", .cpu_setup = __setup_cpu_e6500, #ifndef CONFIG_PPC32 .cpu_restore = __restore_cpu_e6500, @@ -2033,23 +1983,10 @@ static struct cpu_spec * __init setup_cpu_spec(unsigned long offset, t->pmc_type = old.pmc_type; /* - * If we have passed through this logic once before and - * have pulled the default case because the real PVR was - * not found inside cpu_specs[], then we are possibly - * running in compatibility mode. In that case, let the - * oprofiler know which set of compatibility counters to - * pull from by making sure the oprofile_cpu_type string - * is set to that of compatibility mode. If the - * oprofile_cpu_type already has a value, then we are - * possibly overriding a real PVR with a logical one, - * and, in that case, keep the current value for - * oprofile_cpu_type. Furthermore, let's ensure that the + * Let's ensure that the * fix for the PMAO bug is enabled on compatibility mode. */ - if (old.oprofile_cpu_type != NULL) { - t->oprofile_cpu_type = old.oprofile_cpu_type; - t->cpu_features |= old.cpu_features & CPU_FTR_PMAO_BUG; - } + t->cpu_features |= old.cpu_features & CPU_FTR_PMAO_BUG; } *PTRRELOC(&cur_cpu_spec) = &the_cpu_spec; diff --git a/arch/powerpc/kernel/dawr.c b/arch/powerpc/kernel/dawr.c index 30d4eca88d17..909a05cd2809 100644 --- a/arch/powerpc/kernel/dawr.c +++ b/arch/powerpc/kernel/dawr.c @@ -11,6 +11,7 @@ #include <linux/debugfs.h> #include <asm/machdep.h> #include <asm/hvcall.h> +#include <asm/firmware.h> bool dawr_force_enable; EXPORT_SYMBOL_GPL(dawr_force_enable); diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c index 2ad365c21afa..fc800a9fb2c4 100644 --- a/arch/powerpc/kernel/dt_cpu_ftrs.c +++ b/arch/powerpc/kernel/dt_cpu_ftrs.c @@ -102,7 +102,6 @@ static struct cpu_spec __initdata base_cpu_spec = { .dcache_bsize = 32, /* cache info init. */ .num_pmcs = 0, .pmc_type = PPC_PMC_DEFAULT, - .oprofile_cpu_type = NULL, .cpu_setup = NULL, .cpu_restore = __restore_cpu_cpufeatures, .machine_check_early = NULL, @@ -387,7 +386,6 @@ static int __init feat_enable_pmu_power8(struct dt_cpu_feature *f) cur_cpu_spec->num_pmcs = 6; cur_cpu_spec->pmc_type = PPC_PMC_IBM; - cur_cpu_spec->oprofile_cpu_type = "ppc64/power8"; return 1; } @@ -423,7 +421,6 @@ static int __init feat_enable_pmu_power9(struct dt_cpu_feature *f) cur_cpu_spec->num_pmcs = 6; cur_cpu_spec->pmc_type = PPC_PMC_IBM; - cur_cpu_spec->oprofile_cpu_type = "ppc64/power9"; return 1; } @@ -449,7 +446,6 @@ static int __init feat_enable_pmu_power10(struct dt_cpu_feature *f) cur_cpu_spec->num_pmcs = 6; cur_cpu_spec->pmc_type = PPC_PMC_IBM; - cur_cpu_spec->oprofile_cpu_type = "ppc64/power10"; return 1; } diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index 260273e56431..f279295179bd 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -750,7 +750,7 @@ static void eeh_pe_cleanup(struct eeh_pe *pe) * @pdev: pci_dev to check * * This function may return a false positive if we can't determine the slot's - * presence state. This might happen for for PCIe slots if the PE containing + * presence state. This might happen for PCIe slots if the PE containing * the upstream bridge is also frozen, or the bridge is part of the same PE * as the device. * diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index b66dd6f775a4..3d0dc133a9ae 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -2779,7 +2779,7 @@ EXC_COMMON_BEGIN(soft_nmi_common) /* * An interrupt came in while soft-disabled. We set paca->irq_happened, then: - * - If it was a decrementer interrupt, we bump the dec to max and and return. + * - If it was a decrementer interrupt, we bump the dec to max and return. * - If it was a doorbell we return immediately since doorbells are edge * triggered and won't automatically refire. * - If it was a HMI we return immediately since we handled it in realmode diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S index d3eea633d11a..cf2c08902c05 100644 --- a/arch/powerpc/kernel/head_64.S +++ b/arch/powerpc/kernel/head_64.S @@ -965,6 +965,9 @@ start_here_multiplatform: * and SLB setup before we turn on relocation. */ +#ifdef CONFIG_KASAN + bl kasan_early_init +#endif /* Restore parameters passed from prom_init/kexec */ mr r3,r31 LOAD_REG_ADDR(r12, DOTSYM(early_setup)) diff --git a/arch/powerpc/kernel/head_book3s_32.S b/arch/powerpc/kernel/head_book3s_32.S index 6c739beb938c..519b60695167 100644 --- a/arch/powerpc/kernel/head_book3s_32.S +++ b/arch/powerpc/kernel/head_book3s_32.S @@ -418,14 +418,14 @@ InstructionTLBMiss: */ /* Get PTE (linux-style) and check access */ mfspr r3,SPRN_IMISS -#if defined(CONFIG_MODULES) || defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_KFENCE) +#ifdef CONFIG_MODULES lis r1, TASK_SIZE@h /* check if kernel address */ cmplw 0,r1,r3 #endif mfspr r2, SPRN_SDR1 li r1,_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_EXEC | _PAGE_USER rlwinm r2, r2, 28, 0xfffff000 -#if defined(CONFIG_MODULES) || defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_KFENCE) +#ifdef CONFIG_MODULES bgt- 112f lis r2, (swapper_pg_dir - PAGE_OFFSET)@ha /* if kernel address, use */ li r1,_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_EXEC diff --git a/arch/powerpc/kernel/interrupt.c b/arch/powerpc/kernel/interrupt.c index 784ea3289c84..0e75cb03244a 100644 --- a/arch/powerpc/kernel/interrupt.c +++ b/arch/powerpc/kernel/interrupt.c @@ -24,8 +24,6 @@ unsigned long global_dbcr0[NR_CPUS]; #endif -typedef long (*syscall_fn)(long, long, long, long, long, long); - #ifdef CONFIG_PPC_BOOK3S_64 DEFINE_STATIC_KEY_FALSE(interrupt_exit_not_reentrant); static inline bool exit_must_hard_disable(void) @@ -73,165 +71,6 @@ static notrace __always_inline bool prep_irq_for_enabled_exit(bool restartable) return true; } -/* Has to run notrace because it is entered not completely "reconciled" */ -notrace long system_call_exception(long r3, long r4, long r5, - long r6, long r7, long r8, - unsigned long r0, struct pt_regs *regs) -{ - syscall_fn f; - - kuap_lock(); - - regs->orig_gpr3 = r3; - - if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) - BUG_ON(irq_soft_mask_return() != IRQS_ALL_DISABLED); - - trace_hardirqs_off(); /* finish reconciling */ - - CT_WARN_ON(ct_state() == CONTEXT_KERNEL); - user_exit_irqoff(); - - BUG_ON(regs_is_unrecoverable(regs)); - BUG_ON(!(regs->msr & MSR_PR)); - BUG_ON(arch_irq_disabled_regs(regs)); - -#ifdef CONFIG_PPC_PKEY - if (mmu_has_feature(MMU_FTR_PKEY)) { - unsigned long amr, iamr; - bool flush_needed = false; - /* - * When entering from userspace we mostly have the AMR/IAMR - * different from kernel default values. Hence don't compare. - */ - amr = mfspr(SPRN_AMR); - iamr = mfspr(SPRN_IAMR); - regs->amr = amr; - regs->iamr = iamr; - if (mmu_has_feature(MMU_FTR_BOOK3S_KUAP)) { - mtspr(SPRN_AMR, AMR_KUAP_BLOCKED); - flush_needed = true; - } - if (mmu_has_feature(MMU_FTR_BOOK3S_KUEP)) { - mtspr(SPRN_IAMR, AMR_KUEP_BLOCKED); - flush_needed = true; - } - if (flush_needed) - isync(); - } else -#endif - kuap_assert_locked(); - - booke_restore_dbcr0(); - - account_cpu_user_entry(); - - account_stolen_time(); - - /* - * This is not required for the syscall exit path, but makes the - * stack frame look nicer. If this was initialised in the first stack - * frame, or if the unwinder was taught the first stack frame always - * returns to user with IRQS_ENABLED, this store could be avoided! - */ - irq_soft_mask_regs_set_state(regs, IRQS_ENABLED); - - /* - * If system call is called with TM active, set _TIF_RESTOREALL to - * prevent RFSCV being used to return to userspace, because POWER9 - * TM implementation has problems with this instruction returning to - * transactional state. Final register values are not relevant because - * the transaction will be aborted upon return anyway. Or in the case - * of unsupported_scv SIGILL fault, the return state does not much - * matter because it's an edge case. - */ - if (IS_ENABLED(CONFIG_PPC_TRANSACTIONAL_MEM) && - unlikely(MSR_TM_TRANSACTIONAL(regs->msr))) - set_bits(_TIF_RESTOREALL, ¤t_thread_info()->flags); - - /* - * If the system call was made with a transaction active, doom it and - * return without performing the system call. Unless it was an - * unsupported scv vector, in which case it's treated like an illegal - * instruction. - */ -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM - if (unlikely(MSR_TM_TRANSACTIONAL(regs->msr)) && - !trap_is_unsupported_scv(regs)) { - /* Enable TM in the kernel, and disable EE (for scv) */ - hard_irq_disable(); - mtmsr(mfmsr() | MSR_TM); - - /* tabort, this dooms the transaction, nothing else */ - asm volatile(".long 0x7c00071d | ((%0) << 16)" - :: "r"(TM_CAUSE_SYSCALL|TM_CAUSE_PERSISTENT)); - - /* - * Userspace will never see the return value. Execution will - * resume after the tbegin. of the aborted transaction with the - * checkpointed register state. A context switch could occur - * or signal delivered to the process before resuming the - * doomed transaction context, but that should all be handled - * as expected. - */ - return -ENOSYS; - } -#endif // CONFIG_PPC_TRANSACTIONAL_MEM - - local_irq_enable(); - - if (unlikely(read_thread_flags() & _TIF_SYSCALL_DOTRACE)) { - if (unlikely(trap_is_unsupported_scv(regs))) { - /* Unsupported scv vector */ - _exception(SIGILL, regs, ILL_ILLOPC, regs->nip); - return regs->gpr[3]; - } - /* - * We use the return value of do_syscall_trace_enter() as the - * syscall number. If the syscall was rejected for any reason - * do_syscall_trace_enter() returns an invalid syscall number - * and the test against NR_syscalls will fail and the return - * value to be used is in regs->gpr[3]. - */ - r0 = do_syscall_trace_enter(regs); - if (unlikely(r0 >= NR_syscalls)) - return regs->gpr[3]; - r3 = regs->gpr[3]; - r4 = regs->gpr[4]; - r5 = regs->gpr[5]; - r6 = regs->gpr[6]; - r7 = regs->gpr[7]; - r8 = regs->gpr[8]; - - } else if (unlikely(r0 >= NR_syscalls)) { - if (unlikely(trap_is_unsupported_scv(regs))) { - /* Unsupported scv vector */ - _exception(SIGILL, regs, ILL_ILLOPC, regs->nip); - return regs->gpr[3]; - } - return -ENOSYS; - } - - /* May be faster to do array_index_nospec? */ - barrier_nospec(); - - if (unlikely(is_compat_task())) { - f = (void *)compat_sys_call_table[r0]; - - r3 &= 0x00000000ffffffffULL; - r4 &= 0x00000000ffffffffULL; - r5 &= 0x00000000ffffffffULL; - r6 &= 0x00000000ffffffffULL; - r7 &= 0x00000000ffffffffULL; - r8 &= 0x00000000ffffffffULL; - - } else { - f = (void *)sys_call_table[r0]; - } - - return f(r3, r4, r5, r6, r7, r8); -} - static notrace void booke_load_dbcr0(void) { #ifdef CONFIG_PPC_ADV_DEBUG_REGS diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index 7e56ddb3e0b9..caebe1431596 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -775,6 +775,11 @@ bool iommu_table_in_use(struct iommu_table *tbl) /* ignore reserved bit0 */ if (tbl->it_offset == 0) start = 1; + + /* Simple case with no reserved MMIO32 region */ + if (!tbl->it_reserved_start && !tbl->it_reserved_end) + return find_next_bit(tbl->it_map, tbl->it_size, start) != tbl->it_size; + end = tbl->it_reserved_start - tbl->it_offset; if (find_next_bit(tbl->it_map, end, start) != end) return true; diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index 0822a274a549..0f17268c1f0b 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -65,13 +65,8 @@ #include <asm/smp.h> #include <asm/hw_irq.h> #include <asm/softirq_stack.h> +#include <asm/ppc_asm.h> -#ifdef CONFIG_PPC64 -#include <asm/paca.h> -#include <asm/firmware.h> -#include <asm/lv1call.h> -#include <asm/dbell.h> -#endif #define CREATE_TRACE_POINTS #include <asm/trace.h> #include <asm/cpu_has_feature.h> @@ -88,411 +83,6 @@ u32 tau_interrupts(unsigned long cpu); #endif #endif /* CONFIG_PPC32 */ -#ifdef CONFIG_PPC64 - -int distribute_irqs = 1; - -static inline notrace unsigned long get_irq_happened(void) -{ - unsigned long happened; - - __asm__ __volatile__("lbz %0,%1(13)" - : "=r" (happened) : "i" (offsetof(struct paca_struct, irq_happened))); - - return happened; -} - -void replay_soft_interrupts(void) -{ - struct pt_regs regs; - - /* - * Be careful here, calling these interrupt handlers can cause - * softirqs to be raised, which they may run when calling irq_exit, - * which will cause local_irq_enable() to be run, which can then - * recurse into this function. Don't keep any state across - * interrupt handler calls which may change underneath us. - * - * We use local_paca rather than get_paca() to avoid all the - * debug_smp_processor_id() business in this low level function. - */ - - ppc_save_regs(®s); - regs.softe = IRQS_ENABLED; - regs.msr |= MSR_EE; - -again: - if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) - WARN_ON_ONCE(mfmsr() & MSR_EE); - - /* - * Force the delivery of pending soft-disabled interrupts on PS3. - * Any HV call will have this side effect. - */ - if (firmware_has_feature(FW_FEATURE_PS3_LV1)) { - u64 tmp, tmp2; - lv1_get_version_info(&tmp, &tmp2); - } - - /* - * Check if an hypervisor Maintenance interrupt happened. - * This is a higher priority interrupt than the others, so - * replay it first. - */ - if (IS_ENABLED(CONFIG_PPC_BOOK3S) && (local_paca->irq_happened & PACA_IRQ_HMI)) { - local_paca->irq_happened &= ~PACA_IRQ_HMI; - regs.trap = INTERRUPT_HMI; - handle_hmi_exception(®s); - if (!(local_paca->irq_happened & PACA_IRQ_HARD_DIS)) - hard_irq_disable(); - } - - if (local_paca->irq_happened & PACA_IRQ_DEC) { - local_paca->irq_happened &= ~PACA_IRQ_DEC; - regs.trap = INTERRUPT_DECREMENTER; - timer_interrupt(®s); - if (!(local_paca->irq_happened & PACA_IRQ_HARD_DIS)) - hard_irq_disable(); - } - - if (local_paca->irq_happened & PACA_IRQ_EE) { - local_paca->irq_happened &= ~PACA_IRQ_EE; - regs.trap = INTERRUPT_EXTERNAL; - do_IRQ(®s); - if (!(local_paca->irq_happened & PACA_IRQ_HARD_DIS)) - hard_irq_disable(); - } - - if (IS_ENABLED(CONFIG_PPC_DOORBELL) && (local_paca->irq_happened & PACA_IRQ_DBELL)) { - local_paca->irq_happened &= ~PACA_IRQ_DBELL; - regs.trap = INTERRUPT_DOORBELL; - doorbell_exception(®s); - if (!(local_paca->irq_happened & PACA_IRQ_HARD_DIS)) - hard_irq_disable(); - } - - /* Book3E does not support soft-masking PMI interrupts */ - if (IS_ENABLED(CONFIG_PPC_BOOK3S) && (local_paca->irq_happened & PACA_IRQ_PMI)) { - local_paca->irq_happened &= ~PACA_IRQ_PMI; - regs.trap = INTERRUPT_PERFMON; - performance_monitor_exception(®s); - if (!(local_paca->irq_happened & PACA_IRQ_HARD_DIS)) - hard_irq_disable(); - } - - if (local_paca->irq_happened & ~PACA_IRQ_HARD_DIS) { - /* - * We are responding to the next interrupt, so interrupt-off - * latencies should be reset here. - */ - trace_hardirqs_on(); - trace_hardirqs_off(); - goto again; - } -} - -#if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_PPC_KUAP) -static inline void replay_soft_interrupts_irqrestore(void) -{ - unsigned long kuap_state = get_kuap(); - - /* - * Check if anything calls local_irq_enable/restore() when KUAP is - * disabled (user access enabled). We handle that case here by saving - * and re-locking AMR but we shouldn't get here in the first place, - * hence the warning. - */ - kuap_assert_locked(); - - if (kuap_state != AMR_KUAP_BLOCKED) - set_kuap(AMR_KUAP_BLOCKED); - - replay_soft_interrupts(); - - if (kuap_state != AMR_KUAP_BLOCKED) - set_kuap(kuap_state); -} -#else -#define replay_soft_interrupts_irqrestore() replay_soft_interrupts() -#endif - -notrace void arch_local_irq_restore(unsigned long mask) -{ - unsigned char irq_happened; - - /* Write the new soft-enabled value if it is a disable */ - if (mask) { - irq_soft_mask_set(mask); - return; - } - - if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) - WARN_ON_ONCE(in_nmi() || in_hardirq()); - - /* - * After the stb, interrupts are unmasked and there are no interrupts - * pending replay. The restart sequence makes this atomic with - * respect to soft-masked interrupts. If this was just a simple code - * sequence, a soft-masked interrupt could become pending right after - * the comparison and before the stb. - * - * This allows interrupts to be unmasked without hard disabling, and - * also without new hard interrupts coming in ahead of pending ones. - */ - asm_volatile_goto( -"1: \n" -" lbz 9,%0(13) \n" -" cmpwi 9,0 \n" -" bne %l[happened] \n" -" stb 9,%1(13) \n" -"2: \n" - RESTART_TABLE(1b, 2b, 1b) - : : "i" (offsetof(struct paca_struct, irq_happened)), - "i" (offsetof(struct paca_struct, irq_soft_mask)) - : "cr0", "r9" - : happened); - - if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) - WARN_ON_ONCE(!(mfmsr() & MSR_EE)); - - return; - -happened: - irq_happened = get_irq_happened(); - if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) - WARN_ON_ONCE(!irq_happened); - - if (irq_happened == PACA_IRQ_HARD_DIS) { - if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) - WARN_ON_ONCE(mfmsr() & MSR_EE); - irq_soft_mask_set(IRQS_ENABLED); - local_paca->irq_happened = 0; - __hard_irq_enable(); - return; - } - - /* Have interrupts to replay, need to hard disable first */ - if (!(irq_happened & PACA_IRQ_HARD_DIS)) { - if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) { - if (!(mfmsr() & MSR_EE)) { - /* - * An interrupt could have come in and cleared - * MSR[EE] and set IRQ_HARD_DIS, so check - * IRQ_HARD_DIS again and warn if it is still - * clear. - */ - irq_happened = get_irq_happened(); - WARN_ON_ONCE(!(irq_happened & PACA_IRQ_HARD_DIS)); - } - } - __hard_irq_disable(); - local_paca->irq_happened |= PACA_IRQ_HARD_DIS; - } else { - if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) { - if (WARN_ON_ONCE(mfmsr() & MSR_EE)) - __hard_irq_disable(); - } - } - - /* - * Disable preempt here, so that the below preempt_enable will - * perform resched if required (a replayed interrupt may set - * need_resched). - */ - preempt_disable(); - irq_soft_mask_set(IRQS_ALL_DISABLED); - trace_hardirqs_off(); - - replay_soft_interrupts_irqrestore(); - local_paca->irq_happened = 0; - - trace_hardirqs_on(); - irq_soft_mask_set(IRQS_ENABLED); - __hard_irq_enable(); - preempt_enable(); -} -EXPORT_SYMBOL(arch_local_irq_restore); - -/* - * This is a helper to use when about to go into idle low-power - * when the latter has the side effect of re-enabling interrupts - * (such as calling H_CEDE under pHyp). - * - * You call this function with interrupts soft-disabled (this is - * already the case when ppc_md.power_save is called). The function - * will return whether to enter power save or just return. - * - * In the former case, it will have notified lockdep of interrupts - * being re-enabled and generally sanitized the lazy irq state, - * and in the latter case it will leave with interrupts hard - * disabled and marked as such, so the local_irq_enable() call - * in arch_cpu_idle() will properly re-enable everything. - */ -bool prep_irq_for_idle(void) -{ - /* - * First we need to hard disable to ensure no interrupt - * occurs before we effectively enter the low power state - */ - __hard_irq_disable(); - local_paca->irq_happened |= PACA_IRQ_HARD_DIS; - - /* - * If anything happened while we were soft-disabled, - * we return now and do not enter the low power state. - */ - if (lazy_irq_pending()) - return false; - - /* Tell lockdep we are about to re-enable */ - trace_hardirqs_on(); - - /* - * Mark interrupts as soft-enabled and clear the - * PACA_IRQ_HARD_DIS from the pending mask since we - * are about to hard enable as well as a side effect - * of entering the low power state. - */ - local_paca->irq_happened &= ~PACA_IRQ_HARD_DIS; - irq_soft_mask_set(IRQS_ENABLED); - - /* Tell the caller to enter the low power state */ - return true; -} - -#ifdef CONFIG_PPC_BOOK3S -/* - * This is for idle sequences that return with IRQs off, but the - * idle state itself wakes on interrupt. Tell the irq tracer that - * IRQs are enabled for the duration of idle so it does not get long - * off times. Must be paired with fini_irq_for_idle_irqsoff. - */ -bool prep_irq_for_idle_irqsoff(void) -{ - WARN_ON(!irqs_disabled()); - - /* - * First we need to hard disable to ensure no interrupt - * occurs before we effectively enter the low power state - */ - __hard_irq_disable(); - local_paca->irq_happened |= PACA_IRQ_HARD_DIS; - - /* - * If anything happened while we were soft-disabled, - * we return now and do not enter the low power state. - */ - if (lazy_irq_pending()) - return false; - - /* Tell lockdep we are about to re-enable */ - trace_hardirqs_on(); - - return true; -} - -/* - * Take the SRR1 wakeup reason, index into this table to find the - * appropriate irq_happened bit. - * - * Sytem reset exceptions taken in idle state also come through here, - * but they are NMI interrupts so do not need to wait for IRQs to be - * restored, and should be taken as early as practical. These are marked - * with 0xff in the table. The Power ISA specifies 0100b as the system - * reset interrupt reason. - */ -#define IRQ_SYSTEM_RESET 0xff - -static const u8 srr1_to_lazyirq[0x10] = { - 0, 0, 0, - PACA_IRQ_DBELL, - IRQ_SYSTEM_RESET, - PACA_IRQ_DBELL, - PACA_IRQ_DEC, - 0, - PACA_IRQ_EE, - PACA_IRQ_EE, - PACA_IRQ_HMI, - 0, 0, 0, 0, 0 }; - -void replay_system_reset(void) -{ - struct pt_regs regs; - - ppc_save_regs(®s); - regs.trap = 0x100; - get_paca()->in_nmi = 1; - system_reset_exception(®s); - get_paca()->in_nmi = 0; -} -EXPORT_SYMBOL_GPL(replay_system_reset); - -void irq_set_pending_from_srr1(unsigned long srr1) -{ - unsigned int idx = (srr1 & SRR1_WAKEMASK_P8) >> 18; - u8 reason = srr1_to_lazyirq[idx]; - - /* - * Take the system reset now, which is immediately after registers - * are restored from idle. It's an NMI, so interrupts need not be - * re-enabled before it is taken. - */ - if (unlikely(reason == IRQ_SYSTEM_RESET)) { - replay_system_reset(); - return; - } - - if (reason == PACA_IRQ_DBELL) { - /* - * When doorbell triggers a system reset wakeup, the message - * is not cleared, so if the doorbell interrupt is replayed - * and the IPI handled, the doorbell interrupt would still - * fire when EE is enabled. - * - * To avoid taking the superfluous doorbell interrupt, - * execute a msgclr here before the interrupt is replayed. - */ - ppc_msgclr(PPC_DBELL_MSGTYPE); - } - - /* - * The 0 index (SRR1[42:45]=b0000) must always evaluate to 0, - * so this can be called unconditionally with the SRR1 wake - * reason as returned by the idle code, which uses 0 to mean no - * interrupt. - * - * If a future CPU was to designate this as an interrupt reason, - * then a new index for no interrupt must be assigned. - */ - local_paca->irq_happened |= reason; -} -#endif /* CONFIG_PPC_BOOK3S */ - -/* - * Force a replay of the external interrupt handler on this CPU. - */ -void force_external_irq_replay(void) -{ - /* - * This must only be called with interrupts soft-disabled, - * the replay will happen when re-enabling. - */ - WARN_ON(!arch_irqs_disabled()); - - /* - * Interrupts must always be hard disabled before irq_happened is - * modified (to prevent lost update in case of interrupt between - * load and store). - */ - __hard_irq_disable(); - local_paca->irq_happened |= PACA_IRQ_HARD_DIS; - - /* Indicate in the PACA that we have an interrupt to replay */ - local_paca->irq_happened |= PACA_IRQ_EE; -} - -#endif /* CONFIG_PPC64 */ - int arch_show_interrupts(struct seq_file *p, int prec) { int j; @@ -595,17 +185,15 @@ u64 arch_irq_stat_cpu(unsigned int cpu) return sum; } -static inline void check_stack_overflow(void) +static inline void check_stack_overflow(unsigned long sp) { - long sp; - if (!IS_ENABLED(CONFIG_DEBUG_STACKOVERFLOW)) return; - sp = current_stack_pointer & (THREAD_SIZE - 1); + sp &= THREAD_SIZE - 1; - /* check for stack overflow: is there less than 2KB free? */ - if (unlikely(sp < 2048)) { + /* check for stack overflow: is there less than 1/4th free? */ + if (unlikely(sp < THREAD_SIZE / 4)) { pr_err("do_IRQ: stack overflow: %ld\n", sp); dump_stack(); } @@ -632,36 +220,16 @@ static __always_inline void call_do_softirq(const void *sp) } #endif -static __always_inline void call_do_irq(struct pt_regs *regs, void *sp) -{ - register unsigned long r3 asm("r3") = (unsigned long)regs; - - /* Temporarily switch r1 to sp, call __do_irq() then restore r1. */ - asm volatile ( - PPC_STLU " %%r1, %[offset](%[sp]) ;" - "mr %%r1, %[sp] ;" - "bl %[callee] ;" - PPC_LL " %%r1, 0(%%r1) ;" - : // Outputs - "+r" (r3) - : // Inputs - [sp] "b" (sp), [offset] "i" (THREAD_SIZE - STACK_FRAME_OVERHEAD), - [callee] "i" (__do_irq) - : // Clobbers - "lr", "xer", "ctr", "memory", "cr0", "cr1", "cr5", "cr6", - "cr7", "r0", "r4", "r5", "r6", "r7", "r8", "r9", "r10", - "r11", "r12" - ); -} - DEFINE_STATIC_CALL_RET0(ppc_get_irq, *ppc_md.get_irq); -void __do_irq(struct pt_regs *regs) +static void __do_irq(struct pt_regs *regs, unsigned long oldsp) { unsigned int irq; trace_irq_entry(regs); + check_stack_overflow(oldsp); + /* * Query the platform PIC for the interrupt & ack it. * @@ -682,6 +250,29 @@ void __do_irq(struct pt_regs *regs) trace_irq_exit(regs); } +static __always_inline void call_do_irq(struct pt_regs *regs, void *sp) +{ + register unsigned long r3 asm("r3") = (unsigned long)regs; + + /* Temporarily switch r1 to sp, call __do_irq() then restore r1. */ + asm volatile ( + PPC_STLU " %%r1, %[offset](%[sp]) ;" + "mr %%r4, %%r1 ;" + "mr %%r1, %[sp] ;" + "bl %[callee] ;" + PPC_LL " %%r1, 0(%%r1) ;" + : // Outputs + "+r" (r3) + : // Inputs + [sp] "b" (sp), [offset] "i" (THREAD_SIZE - STACK_FRAME_OVERHEAD), + [callee] "i" (__do_irq) + : // Clobbers + "lr", "xer", "ctr", "memory", "cr0", "cr1", "cr5", "cr6", + "cr7", "r0", "r4", "r5", "r6", "r7", "r8", "r9", "r10", + "r11", "r12" + ); +} + void __do_IRQ(struct pt_regs *regs) { struct pt_regs *old_regs = set_irq_regs(regs); @@ -692,16 +283,11 @@ void __do_IRQ(struct pt_regs *regs) irqsp = hardirq_ctx[raw_smp_processor_id()]; sirqsp = softirq_ctx[raw_smp_processor_id()]; - check_stack_overflow(); - - /* Already there ? */ - if (unlikely(cursp == irqsp || cursp == sirqsp)) { - __do_irq(regs); - set_irq_regs(old_regs); - return; - } - /* Switch stack and call */ - call_do_irq(regs, irqsp); + /* Already there ? If not switch stack and call */ + if (unlikely(cursp == irqsp || cursp == sirqsp)) + __do_irq(regs, current_stack_pointer); + else + call_do_irq(regs, irqsp); set_irq_regs(old_regs); } @@ -798,13 +384,3 @@ int irq_choose_cpu(const struct cpumask *mask) return hard_smp_processor_id(); } #endif - -#ifdef CONFIG_PPC64 -static int __init setup_noirqdistrib(char *str) -{ - distribute_irqs = 0; - return 1; -} - -__setup("noirqdistrib", setup_noirqdistrib); -#endif /* CONFIG_PPC64 */ diff --git a/arch/powerpc/kernel/irq_64.c b/arch/powerpc/kernel/irq_64.c new file mode 100644 index 000000000000..01645e03e9f0 --- /dev/null +++ b/arch/powerpc/kernel/irq_64.c @@ -0,0 +1,466 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Derived from arch/i386/kernel/irq.c + * Copyright (C) 1992 Linus Torvalds + * Adapted from arch/i386 by Gary Thomas + * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org) + * Updated and modified by Cort Dougan <cort@fsmlabs.com> + * Copyright (C) 1996-2001 Cort Dougan + * Adapted for Power Macintosh by Paul Mackerras + * Copyright (C) 1996 Paul Mackerras (paulus@cs.anu.edu.au) + * + * This file contains the code used by various IRQ handling routines: + * asking for different IRQ's should be done through these routines + * instead of just grabbing them. Thus setups with different IRQ numbers + * shouldn't result in any weird surprises, and installing new handlers + * should be easier. + */ + +#undef DEBUG + +#include <linux/export.h> +#include <linux/threads.h> +#include <linux/kernel_stat.h> +#include <linux/signal.h> +#include <linux/sched.h> +#include <linux/ptrace.h> +#include <linux/ioport.h> +#include <linux/interrupt.h> +#include <linux/timex.h> +#include <linux/init.h> +#include <linux/slab.h> +#include <linux/delay.h> +#include <linux/irq.h> +#include <linux/seq_file.h> +#include <linux/cpumask.h> +#include <linux/profile.h> +#include <linux/bitops.h> +#include <linux/list.h> +#include <linux/radix-tree.h> +#include <linux/mutex.h> +#include <linux/pci.h> +#include <linux/debugfs.h> +#include <linux/of.h> +#include <linux/of_irq.h> +#include <linux/vmalloc.h> +#include <linux/pgtable.h> +#include <linux/static_call.h> + +#include <linux/uaccess.h> +#include <asm/interrupt.h> +#include <asm/io.h> +#include <asm/irq.h> +#include <asm/cache.h> +#include <asm/ptrace.h> +#include <asm/machdep.h> +#include <asm/udbg.h> +#include <asm/smp.h> +#include <asm/hw_irq.h> +#include <asm/softirq_stack.h> +#include <asm/ppc_asm.h> + +#include <asm/paca.h> +#include <asm/firmware.h> +#include <asm/lv1call.h> +#include <asm/dbell.h> +#include <asm/trace.h> +#include <asm/cpu_has_feature.h> + +int distribute_irqs = 1; + +void replay_soft_interrupts(void) +{ + struct pt_regs regs; + + /* + * Be careful here, calling these interrupt handlers can cause + * softirqs to be raised, which they may run when calling irq_exit, + * which will cause local_irq_enable() to be run, which can then + * recurse into this function. Don't keep any state across + * interrupt handler calls which may change underneath us. + * + * We use local_paca rather than get_paca() to avoid all the + * debug_smp_processor_id() business in this low level function. + */ + + ppc_save_regs(®s); + regs.softe = IRQS_ENABLED; + regs.msr |= MSR_EE; + +again: + if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) + WARN_ON_ONCE(mfmsr() & MSR_EE); + + /* + * Force the delivery of pending soft-disabled interrupts on PS3. + * Any HV call will have this side effect. + */ + if (firmware_has_feature(FW_FEATURE_PS3_LV1)) { + u64 tmp, tmp2; + lv1_get_version_info(&tmp, &tmp2); + } + + /* + * Check if an hypervisor Maintenance interrupt happened. + * This is a higher priority interrupt than the others, so + * replay it first. + */ + if (IS_ENABLED(CONFIG_PPC_BOOK3S) && (local_paca->irq_happened & PACA_IRQ_HMI)) { + local_paca->irq_happened &= ~PACA_IRQ_HMI; + regs.trap = INTERRUPT_HMI; + handle_hmi_exception(®s); + if (!(local_paca->irq_happened & PACA_IRQ_HARD_DIS)) + hard_irq_disable(); + } + + if (local_paca->irq_happened & PACA_IRQ_DEC) { + local_paca->irq_happened &= ~PACA_IRQ_DEC; + regs.trap = INTERRUPT_DECREMENTER; + timer_interrupt(®s); + if (!(local_paca->irq_happened & PACA_IRQ_HARD_DIS)) + hard_irq_disable(); + } + + if (local_paca->irq_happened & PACA_IRQ_EE) { + local_paca->irq_happened &= ~PACA_IRQ_EE; + regs.trap = INTERRUPT_EXTERNAL; + do_IRQ(®s); + if (!(local_paca->irq_happened & PACA_IRQ_HARD_DIS)) + hard_irq_disable(); + } + + if (IS_ENABLED(CONFIG_PPC_DOORBELL) && (local_paca->irq_happened & PACA_IRQ_DBELL)) { + local_paca->irq_happened &= ~PACA_IRQ_DBELL; + regs.trap = INTERRUPT_DOORBELL; + doorbell_exception(®s); + if (!(local_paca->irq_happened & PACA_IRQ_HARD_DIS)) + hard_irq_disable(); + } + + /* Book3E does not support soft-masking PMI interrupts */ + if (IS_ENABLED(CONFIG_PPC_BOOK3S) && (local_paca->irq_happened & PACA_IRQ_PMI)) { + local_paca->irq_happened &= ~PACA_IRQ_PMI; + regs.trap = INTERRUPT_PERFMON; + performance_monitor_exception(®s); + if (!(local_paca->irq_happened & PACA_IRQ_HARD_DIS)) + hard_irq_disable(); + } + + if (local_paca->irq_happened & ~PACA_IRQ_HARD_DIS) { + /* + * We are responding to the next interrupt, so interrupt-off + * latencies should be reset here. + */ + trace_hardirqs_on(); + trace_hardirqs_off(); + goto again; + } +} + +#if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_PPC_KUAP) +static inline void replay_soft_interrupts_irqrestore(void) +{ + unsigned long kuap_state = get_kuap(); + + /* + * Check if anything calls local_irq_enable/restore() when KUAP is + * disabled (user access enabled). We handle that case here by saving + * and re-locking AMR but we shouldn't get here in the first place, + * hence the warning. + */ + kuap_assert_locked(); + + if (kuap_state != AMR_KUAP_BLOCKED) + set_kuap(AMR_KUAP_BLOCKED); + + replay_soft_interrupts(); + + if (kuap_state != AMR_KUAP_BLOCKED) + set_kuap(kuap_state); +} +#else +#define replay_soft_interrupts_irqrestore() replay_soft_interrupts() +#endif + +notrace void arch_local_irq_restore(unsigned long mask) +{ + unsigned char irq_happened; + + /* Write the new soft-enabled value if it is a disable */ + if (mask) { + irq_soft_mask_set(mask); + return; + } + + if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) + WARN_ON_ONCE(in_nmi() || in_hardirq()); + + /* + * After the stb, interrupts are unmasked and there are no interrupts + * pending replay. The restart sequence makes this atomic with + * respect to soft-masked interrupts. If this was just a simple code + * sequence, a soft-masked interrupt could become pending right after + * the comparison and before the stb. + * + * This allows interrupts to be unmasked without hard disabling, and + * also without new hard interrupts coming in ahead of pending ones. + */ + asm_volatile_goto( +"1: \n" +" lbz 9,%0(13) \n" +" cmpwi 9,0 \n" +" bne %l[happened] \n" +" stb 9,%1(13) \n" +"2: \n" + RESTART_TABLE(1b, 2b, 1b) + : : "i" (offsetof(struct paca_struct, irq_happened)), + "i" (offsetof(struct paca_struct, irq_soft_mask)) + : "cr0", "r9" + : happened); + + if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) + WARN_ON_ONCE(!(mfmsr() & MSR_EE)); + + return; + +happened: + irq_happened = READ_ONCE(local_paca->irq_happened); + if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) + WARN_ON_ONCE(!irq_happened); + + if (irq_happened == PACA_IRQ_HARD_DIS) { + if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) + WARN_ON_ONCE(mfmsr() & MSR_EE); + irq_soft_mask_set(IRQS_ENABLED); + local_paca->irq_happened = 0; + __hard_irq_enable(); + return; + } + + /* Have interrupts to replay, need to hard disable first */ + if (!(irq_happened & PACA_IRQ_HARD_DIS)) { + if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) { + if (!(mfmsr() & MSR_EE)) { + /* + * An interrupt could have come in and cleared + * MSR[EE] and set IRQ_HARD_DIS, so check + * IRQ_HARD_DIS again and warn if it is still + * clear. + */ + irq_happened = READ_ONCE(local_paca->irq_happened); + WARN_ON_ONCE(!(irq_happened & PACA_IRQ_HARD_DIS)); + } + } + __hard_irq_disable(); + local_paca->irq_happened |= PACA_IRQ_HARD_DIS; + } else { + if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) { + if (WARN_ON_ONCE(mfmsr() & MSR_EE)) + __hard_irq_disable(); + } + } + + /* + * Disable preempt here, so that the below preempt_enable will + * perform resched if required (a replayed interrupt may set + * need_resched). + */ + preempt_disable(); + irq_soft_mask_set(IRQS_ALL_DISABLED); + trace_hardirqs_off(); + + replay_soft_interrupts_irqrestore(); + local_paca->irq_happened = 0; + + trace_hardirqs_on(); + irq_soft_mask_set(IRQS_ENABLED); + __hard_irq_enable(); + preempt_enable(); +} +EXPORT_SYMBOL(arch_local_irq_restore); + +/* + * This is a helper to use when about to go into idle low-power + * when the latter has the side effect of re-enabling interrupts + * (such as calling H_CEDE under pHyp). + * + * You call this function with interrupts soft-disabled (this is + * already the case when ppc_md.power_save is called). The function + * will return whether to enter power save or just return. + * + * In the former case, it will have notified lockdep of interrupts + * being re-enabled and generally sanitized the lazy irq state, + * and in the latter case it will leave with interrupts hard + * disabled and marked as such, so the local_irq_enable() call + * in arch_cpu_idle() will properly re-enable everything. + */ +bool prep_irq_for_idle(void) +{ + /* + * First we need to hard disable to ensure no interrupt + * occurs before we effectively enter the low power state + */ + __hard_irq_disable(); + local_paca->irq_happened |= PACA_IRQ_HARD_DIS; + + /* + * If anything happened while we were soft-disabled, + * we return now and do not enter the low power state. + */ + if (lazy_irq_pending()) + return false; + + /* Tell lockdep we are about to re-enable */ + trace_hardirqs_on(); + + /* + * Mark interrupts as soft-enabled and clear the + * PACA_IRQ_HARD_DIS from the pending mask since we + * are about to hard enable as well as a side effect + * of entering the low power state. + */ + local_paca->irq_happened &= ~PACA_IRQ_HARD_DIS; + irq_soft_mask_set(IRQS_ENABLED); + + /* Tell the caller to enter the low power state */ + return true; +} + +#ifdef CONFIG_PPC_BOOK3S +/* + * This is for idle sequences that return with IRQs off, but the + * idle state itself wakes on interrupt. Tell the irq tracer that + * IRQs are enabled for the duration of idle so it does not get long + * off times. Must be paired with fini_irq_for_idle_irqsoff. + */ +bool prep_irq_for_idle_irqsoff(void) +{ + WARN_ON(!irqs_disabled()); + + /* + * First we need to hard disable to ensure no interrupt + * occurs before we effectively enter the low power state + */ + __hard_irq_disable(); + local_paca->irq_happened |= PACA_IRQ_HARD_DIS; + + /* + * If anything happened while we were soft-disabled, + * we return now and do not enter the low power state. + */ + if (lazy_irq_pending()) + return false; + + /* Tell lockdep we are about to re-enable */ + trace_hardirqs_on(); + + return true; +} + +/* + * Take the SRR1 wakeup reason, index into this table to find the + * appropriate irq_happened bit. + * + * Sytem reset exceptions taken in idle state also come through here, + * but they are NMI interrupts so do not need to wait for IRQs to be + * restored, and should be taken as early as practical. These are marked + * with 0xff in the table. The Power ISA specifies 0100b as the system + * reset interrupt reason. + */ +#define IRQ_SYSTEM_RESET 0xff + +static const u8 srr1_to_lazyirq[0x10] = { + 0, 0, 0, + PACA_IRQ_DBELL, + IRQ_SYSTEM_RESET, + PACA_IRQ_DBELL, + PACA_IRQ_DEC, + 0, + PACA_IRQ_EE, + PACA_IRQ_EE, + PACA_IRQ_HMI, + 0, 0, 0, 0, 0 }; + +void replay_system_reset(void) +{ + struct pt_regs regs; + + ppc_save_regs(®s); + regs.trap = 0x100; + get_paca()->in_nmi = 1; + system_reset_exception(®s); + get_paca()->in_nmi = 0; +} +EXPORT_SYMBOL_GPL(replay_system_reset); + +void irq_set_pending_from_srr1(unsigned long srr1) +{ + unsigned int idx = (srr1 & SRR1_WAKEMASK_P8) >> 18; + u8 reason = srr1_to_lazyirq[idx]; + + /* + * Take the system reset now, which is immediately after registers + * are restored from idle. It's an NMI, so interrupts need not be + * re-enabled before it is taken. + */ + if (unlikely(reason == IRQ_SYSTEM_RESET)) { + replay_system_reset(); + return; + } + + if (reason == PACA_IRQ_DBELL) { + /* + * When doorbell triggers a system reset wakeup, the message + * is not cleared, so if the doorbell interrupt is replayed + * and the IPI handled, the doorbell interrupt would still + * fire when EE is enabled. + * + * To avoid taking the superfluous doorbell interrupt, + * execute a msgclr here before the interrupt is replayed. + */ + ppc_msgclr(PPC_DBELL_MSGTYPE); + } + + /* + * The 0 index (SRR1[42:45]=b0000) must always evaluate to 0, + * so this can be called unconditionally with the SRR1 wake + * reason as returned by the idle code, which uses 0 to mean no + * interrupt. + * + * If a future CPU was to designate this as an interrupt reason, + * then a new index for no interrupt must be assigned. + */ + local_paca->irq_happened |= reason; +} +#endif /* CONFIG_PPC_BOOK3S */ + +/* + * Force a replay of the external interrupt handler on this CPU. + */ +void force_external_irq_replay(void) +{ + /* + * This must only be called with interrupts soft-disabled, + * the replay will happen when re-enabling. + */ + WARN_ON(!arch_irqs_disabled()); + + /* + * Interrupts must always be hard disabled before irq_happened is + * modified (to prevent lost update in case of interrupt between + * load and store). + */ + __hard_irq_disable(); + local_paca->irq_happened |= PACA_IRQ_HARD_DIS; + + /* Indicate in the PACA that we have an interrupt to replay */ + local_paca->irq_happened |= PACA_IRQ_EE; +} + +static int __init setup_noirqdistrib(char *str) +{ + distribute_irqs = 0; + return 1; +} + +__setup("noirqdistrib", setup_noirqdistrib); diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c index 1c97c0f177ae..912d4f8a13be 100644 --- a/arch/powerpc/kernel/kprobes.c +++ b/arch/powerpc/kernel/kprobes.c @@ -269,7 +269,7 @@ static int try_to_emulate(struct kprobe *p, struct pt_regs *regs) * So, we should never get here... but, its still * good to catch them, just in case... */ - printk("Can't step on instruction %s\n", ppc_inst_as_str(insn)); + printk("Can't step on instruction %08lx\n", ppc_inst_as_ulong(insn)); BUG(); } else { /* diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c index 18173199b79d..6c5d30fba766 100644 --- a/arch/powerpc/kernel/mce.c +++ b/arch/powerpc/kernel/mce.c @@ -756,7 +756,7 @@ void __init mce_init(void) mce_info = memblock_alloc_try_nid(sizeof(*mce_info), __alignof__(*mce_info), MEMBLOCK_LOW_LIMIT, - limit, cpu_to_node(i)); + limit, early_cpu_to_node(i)); if (!mce_info) goto err; paca_ptrs[i]->mce_info = mce_info; diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index 068410cd54a3..bdd3332200c5 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -39,6 +39,7 @@ #include <asm/machdep.h> #include <asm/ppc-pci.h> #include <asm/eeh.h> +#include <asm/setup.h> #include "../../../drivers/pci/pci.h" @@ -74,16 +75,32 @@ void __init set_pci_dma_ops(const struct dma_map_ops *dma_ops) static int get_phb_number(struct device_node *dn) { int ret, phb_id = -1; - u32 prop_32; u64 prop; /* * Try fixed PHB numbering first, by checking archs and reading - * the respective device-tree properties. Firstly, try powernv by - * reading "ibm,opal-phbid", only present in OPAL environment. + * the respective device-tree properties. Firstly, try reading + * standard "linux,pci-domain", then try reading "ibm,opal-phbid" + * (only present in powernv OPAL environment), then try device-tree + * alias and as the last try to use lower bits of "reg" property. */ - ret = of_property_read_u64(dn, "ibm,opal-phbid", &prop); + ret = of_get_pci_domain_nr(dn); + if (ret >= 0) { + prop = ret; + ret = 0; + } + if (ret) + ret = of_property_read_u64(dn, "ibm,opal-phbid", &prop); + if (ret) { + ret = of_alias_get_id(dn, "pci"); + if (ret >= 0) { + prop = ret; + ret = 0; + } + } + if (ret) { + u32 prop_32; ret = of_property_read_u32_index(dn, "reg", 1, &prop_32); prop = prop_32; } @@ -95,10 +112,7 @@ static int get_phb_number(struct device_node *dn) if ((phb_id >= 0) && !test_and_set_bit(phb_id, phb_bitmap)) return phb_id; - /* - * If not pseries nor powernv, or if fixed PHB numbering tried to add - * the same PHB number twice, then fallback to dynamic PHB numbering. - */ + /* If everything fails then fallback to dynamic PHB numbering. */ phb_id = find_first_zero_bit(phb_bitmap, MAX_PHBS); BUG_ON(phb_id >= MAX_PHBS); set_bit(phb_id, phb_bitmap); @@ -1087,7 +1101,7 @@ void pcibios_fixup_bus(struct pci_bus *bus) */ pci_read_bridge_bases(bus); - /* Now fixup the bus bus */ + /* Now fixup the bus */ pcibios_setup_bus_self(bus); } EXPORT_SYMBOL(pcibios_fixup_bus); diff --git a/arch/powerpc/kernel/pci_32.c b/arch/powerpc/kernel/pci_32.c index 5a174936c9a0..433965bf37b4 100644 --- a/arch/powerpc/kernel/pci_32.c +++ b/arch/powerpc/kernel/pci_32.c @@ -36,18 +36,13 @@ int pcibios_assign_bus_offset = 1; EXPORT_SYMBOL(isa_io_base); EXPORT_SYMBOL(pci_dram_offset); -void __init pcibios_make_OF_bus_map(void); - static void fixup_cpc710_pci64(struct pci_dev* dev); -static u8* pci_to_OF_bus_map; /* By default, we don't re-assign bus numbers. We do this only on * some pmacs */ static int pci_assign_all_buses; -static int pci_bus_count; - /* This will remain NULL for now, until isa-bridge.c is made common * to both 32-bit and 64-bit. */ @@ -67,6 +62,11 @@ fixup_cpc710_pci64(struct pci_dev* dev) } DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_IBM, PCI_DEVICE_ID_IBM_CPC710_PCI64, fixup_cpc710_pci64); +#if defined(CONFIG_PPC_PMAC) || defined(CONFIG_PPC_CHRP) + +static u8* pci_to_OF_bus_map; +static int pci_bus_count; + /* * Functions below are used on OpenFirmware machines. */ @@ -108,7 +108,7 @@ make_one_node_map(struct device_node* node, u8 pci_bus) } } -void __init +static void __init pcibios_make_OF_bus_map(void) { int i; @@ -154,6 +154,7 @@ pcibios_make_OF_bus_map(void) } +#ifdef CONFIG_PPC_PMAC /* * Returns the PCI device matching a given OF node */ @@ -193,7 +194,9 @@ int pci_device_from_OF_node(struct device_node *node, u8 *bus, u8 *devfn) return -ENODEV; } EXPORT_SYMBOL(pci_device_from_OF_node); +#endif +#ifdef CONFIG_PPC_CHRP /* We create the "pci-OF-bus-map" property now so it appears in the * /proc device tree */ @@ -218,6 +221,9 @@ pci_create_OF_bus_map(void) of_node_put(dn); } } +#endif + +#endif /* defined(CONFIG_PPC_PMAC) || defined(CONFIG_PPC_CHRP) */ void pcibios_setup_phb_io_space(struct pci_controller *hose) { @@ -233,7 +239,9 @@ void pcibios_setup_phb_io_space(struct pci_controller *hose) static int __init pcibios_init(void) { struct pci_controller *hose, *tmp; +#ifndef CONFIG_PPC_PCI_BUS_NUM_DOMAIN_DEPENDENT int next_busno = 0; +#endif printk(KERN_INFO "PCI: Probing PCI hardware\n"); @@ -242,14 +250,20 @@ static int __init pcibios_init(void) /* Scan all of the recorded PCI controllers. */ list_for_each_entry_safe(hose, tmp, &hose_list, list_node) { +#ifndef CONFIG_PPC_PCI_BUS_NUM_DOMAIN_DEPENDENT if (pci_assign_all_buses) hose->first_busno = next_busno; +#endif hose->last_busno = 0xff; pcibios_scan_phb(hose); pci_bus_add_devices(hose->bus); +#ifndef CONFIG_PPC_PCI_BUS_NUM_DOMAIN_DEPENDENT if (pci_assign_all_buses || next_busno <= hose->last_busno) next_busno = hose->last_busno + pcibios_assign_bus_offset; +#endif } + +#if defined(CONFIG_PPC_PMAC) || defined(CONFIG_PPC_CHRP) pci_bus_count = next_busno; /* OpenFirmware based machines need a map of OF bus @@ -258,6 +272,7 @@ static int __init pcibios_init(void) */ if (pci_assign_all_buses) pcibios_make_OF_bus_map(); +#endif /* Call common code to handle resource allocation */ pcibios_resource_survey(); diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c index 19b03ddf5631..0c7cfb9fab04 100644 --- a/arch/powerpc/kernel/pci_64.c +++ b/arch/powerpc/kernel/pci_64.c @@ -286,6 +286,7 @@ int pcibus_to_node(struct pci_bus *bus) EXPORT_SYMBOL(pcibus_to_node); #endif +#ifdef CONFIG_PPC_PMAC int pci_device_from_OF_node(struct device_node *np, u8 *bus, u8 *devfn) { if (!PCI_DN(np)) @@ -294,3 +295,4 @@ int pci_device_from_OF_node(struct device_node *np, u8 *bus, u8 *devfn) *devfn = PCI_DN(np)->devfn; return 0; } +#endif diff --git a/arch/powerpc/kernel/pci_dn.c b/arch/powerpc/kernel/pci_dn.c index 938ab8838ab5..7a35fc25a304 100644 --- a/arch/powerpc/kernel/pci_dn.c +++ b/arch/powerpc/kernel/pci_dn.c @@ -259,7 +259,7 @@ void remove_sriov_vf_pdns(struct pci_dev *pdev) if (edev) { /* * We allocate pci_dn's for the totalvfs count, - * but only only the vfs that were activated + * but only the vfs that were activated * have a configured PE. */ if (edev->pe) diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index feae8509b59c..a730b951b64b 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -44,7 +44,7 @@ #include <asm/iommu.h> #include <asm/btext.h> #include <asm/sections.h> -#include <asm/machdep.h> +#include <asm/setup.h> #include <asm/pci-bridge.h> #include <asm/kexec.h> #include <asm/opal.h> @@ -54,6 +54,7 @@ #include <asm/dt_cpu_ftrs.h> #include <asm/drmem.h> #include <asm/ultravisor.h> +#include <asm/prom.h> #include <mm/mmu_decl.h> @@ -751,6 +752,13 @@ void __init early_init_devtree(void *params) early_init_dt_scan_root(); early_init_dt_scan_memory_ppc(); + /* + * As generic code authors expect to be able to use static keys + * in early_param() handlers, we initialize the static keys just + * before parsing early params (it's fine to call jump_label_init() + * more than once). + */ + jump_label_init(); parse_early_param(); /* make sure we've parsed cmdline for mem= before this */ diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index 13d6cb188835..a6669c40c1db 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -42,7 +42,7 @@ #include <asm/iommu.h> #include <asm/btext.h> #include <asm/sections.h> -#include <asm/machdep.h> +#include <asm/setup.h> #include <asm/asm-prototypes.h> #include <asm/ultravisor-api.h> diff --git a/arch/powerpc/kernel/ptrace/ptrace-vsx.c b/arch/powerpc/kernel/ptrace/ptrace-vsx.c index 1da4303128ef..7df08004c47d 100644 --- a/arch/powerpc/kernel/ptrace/ptrace-vsx.c +++ b/arch/powerpc/kernel/ptrace/ptrace-vsx.c @@ -71,7 +71,7 @@ int fpr_set(struct task_struct *target, const struct user_regset *regset, } /* - * Currently to set and and get all the vsx state, you need to call + * Currently to set and get all the vsx state, you need to call * the fp and VMX calls as well. This only get/sets the lower 32 * 128bit VSX registers. */ diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 5761f08dae95..2b2d0b0fbb30 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -113,7 +113,6 @@ void __init setup_tlb_core_data(void) * Should we panic instead? */ WARN_ONCE(smt_enabled_at_boot >= 2 && - !mmu_has_feature(MMU_FTR_USE_TLBRSRV) && book3e_htw_mode != PPC_HTW_E6500, "%s: unsupported MMU configuration\n", __func__); } diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index 472596a109e2..86bb5bb4c143 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -377,9 +377,12 @@ static long notrace __unsafe_restore_sigcontext(struct task_struct *tsk, sigset_ unsafe_get_user(set->sig[0], &sc->oldmask, efault_out); /* - * Force reload of FP/VEC. - * This has to be done before copying stuff into tsk->thread.fpr/vr - * for the reasons explained in the previous comment. + * Force reload of FP/VEC/VSX so userspace sees any changes. + * Clear these bits from the user process' MSR before copying into the + * thread struct. If we are rescheduled or preempted and another task + * uses FP/VEC/VSX, and this process has the MSR bits set, then the + * context switch code will save the current CPU state into the + * thread_struct - possibly overwriting the data we are updating here. */ regs_set_return_msr(regs, regs->msr & ~(MSR_FP | MSR_FE0 | MSR_FE1 | MSR_VEC | MSR_VSX)); diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index bcefab484ea6..6b850c157a62 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -35,6 +35,7 @@ #include <linux/stackprotector.h> #include <linux/pgtable.h> #include <linux/clockchips.h> +#include <linux/kexec.h> #include <asm/ptrace.h> #include <linux/atomic.h> @@ -55,7 +56,6 @@ #endif #include <asm/vdso.h> #include <asm/debug.h> -#include <asm/kexec.h> #include <asm/cpu_has_feature.h> #include <asm/ftrace.h> #include <asm/kup.h> @@ -619,20 +619,6 @@ void crash_send_ipi(void (*crash_ipi_callback)(struct pt_regs *)) } #endif -#ifdef CONFIG_NMI_IPI -static void crash_stop_this_cpu(struct pt_regs *regs) -#else -static void crash_stop_this_cpu(void *dummy) -#endif -{ - /* - * Just busy wait here and avoid marking CPU as offline to ensure - * register data is captured appropriately. - */ - while (1) - cpu_relax(); -} - void crash_smp_send_stop(void) { static bool stopped = false; @@ -651,11 +637,14 @@ void crash_smp_send_stop(void) stopped = true; -#ifdef CONFIG_NMI_IPI - smp_send_nmi_ipi(NMI_IPI_ALL_OTHERS, crash_stop_this_cpu, 1000000); -#else - smp_call_function(crash_stop_this_cpu, NULL, 0); -#endif /* CONFIG_NMI_IPI */ +#ifdef CONFIG_KEXEC_CORE + if (kexec_crash_image) { + crash_kexec_prepare(); + return; + } +#endif + + smp_send_stop(); } #ifdef CONFIG_NMI_IPI diff --git a/arch/powerpc/kernel/syscall.c b/arch/powerpc/kernel/syscall.c new file mode 100644 index 000000000000..81ace9e8b72b --- /dev/null +++ b/arch/powerpc/kernel/syscall.c @@ -0,0 +1,190 @@ +// SPDX-License-Identifier: GPL-2.0-or-later + +#include <linux/compat.h> +#include <linux/context_tracking.h> +#include <linux/randomize_kstack.h> + +#include <asm/interrupt.h> +#include <asm/kup.h> +#include <asm/syscall.h> +#include <asm/time.h> +#include <asm/tm.h> +#include <asm/unistd.h> + + +typedef long (*syscall_fn)(long, long, long, long, long, long); + +/* Has to run notrace because it is entered not completely "reconciled" */ +notrace long system_call_exception(long r3, long r4, long r5, + long r6, long r7, long r8, + unsigned long r0, struct pt_regs *regs) +{ + long ret; + syscall_fn f; + + kuap_lock(); + + add_random_kstack_offset(); + regs->orig_gpr3 = r3; + + if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) + BUG_ON(irq_soft_mask_return() != IRQS_ALL_DISABLED); + + trace_hardirqs_off(); /* finish reconciling */ + + CT_WARN_ON(ct_state() == CONTEXT_KERNEL); + user_exit_irqoff(); + + BUG_ON(regs_is_unrecoverable(regs)); + BUG_ON(!(regs->msr & MSR_PR)); + BUG_ON(arch_irq_disabled_regs(regs)); + +#ifdef CONFIG_PPC_PKEY + if (mmu_has_feature(MMU_FTR_PKEY)) { + unsigned long amr, iamr; + bool flush_needed = false; + /* + * When entering from userspace we mostly have the AMR/IAMR + * different from kernel default values. Hence don't compare. + */ + amr = mfspr(SPRN_AMR); + iamr = mfspr(SPRN_IAMR); + regs->amr = amr; + regs->iamr = iamr; + if (mmu_has_feature(MMU_FTR_BOOK3S_KUAP)) { + mtspr(SPRN_AMR, AMR_KUAP_BLOCKED); + flush_needed = true; + } + if (mmu_has_feature(MMU_FTR_BOOK3S_KUEP)) { + mtspr(SPRN_IAMR, AMR_KUEP_BLOCKED); + flush_needed = true; + } + if (flush_needed) + isync(); + } else +#endif + kuap_assert_locked(); + + booke_restore_dbcr0(); + + account_cpu_user_entry(); + + account_stolen_time(); + + /* + * This is not required for the syscall exit path, but makes the + * stack frame look nicer. If this was initialised in the first stack + * frame, or if the unwinder was taught the first stack frame always + * returns to user with IRQS_ENABLED, this store could be avoided! + */ + irq_soft_mask_regs_set_state(regs, IRQS_ENABLED); + + /* + * If system call is called with TM active, set _TIF_RESTOREALL to + * prevent RFSCV being used to return to userspace, because POWER9 + * TM implementation has problems with this instruction returning to + * transactional state. Final register values are not relevant because + * the transaction will be aborted upon return anyway. Or in the case + * of unsupported_scv SIGILL fault, the return state does not much + * matter because it's an edge case. + */ + if (IS_ENABLED(CONFIG_PPC_TRANSACTIONAL_MEM) && + unlikely(MSR_TM_TRANSACTIONAL(regs->msr))) + set_bits(_TIF_RESTOREALL, ¤t_thread_info()->flags); + + /* + * If the system call was made with a transaction active, doom it and + * return without performing the system call. Unless it was an + * unsupported scv vector, in which case it's treated like an illegal + * instruction. + */ +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + if (unlikely(MSR_TM_TRANSACTIONAL(regs->msr)) && + !trap_is_unsupported_scv(regs)) { + /* Enable TM in the kernel, and disable EE (for scv) */ + hard_irq_disable(); + mtmsr(mfmsr() | MSR_TM); + + /* tabort, this dooms the transaction, nothing else */ + asm volatile(".long 0x7c00071d | ((%0) << 16)" + :: "r"(TM_CAUSE_SYSCALL|TM_CAUSE_PERSISTENT)); + + /* + * Userspace will never see the return value. Execution will + * resume after the tbegin. of the aborted transaction with the + * checkpointed register state. A context switch could occur + * or signal delivered to the process before resuming the + * doomed transaction context, but that should all be handled + * as expected. + */ + return -ENOSYS; + } +#endif // CONFIG_PPC_TRANSACTIONAL_MEM + + local_irq_enable(); + + if (unlikely(read_thread_flags() & _TIF_SYSCALL_DOTRACE)) { + if (unlikely(trap_is_unsupported_scv(regs))) { + /* Unsupported scv vector */ + _exception(SIGILL, regs, ILL_ILLOPC, regs->nip); + return regs->gpr[3]; + } + /* + * We use the return value of do_syscall_trace_enter() as the + * syscall number. If the syscall was rejected for any reason + * do_syscall_trace_enter() returns an invalid syscall number + * and the test against NR_syscalls will fail and the return + * value to be used is in regs->gpr[3]. + */ + r0 = do_syscall_trace_enter(regs); + if (unlikely(r0 >= NR_syscalls)) + return regs->gpr[3]; + r3 = regs->gpr[3]; + r4 = regs->gpr[4]; + r5 = regs->gpr[5]; + r6 = regs->gpr[6]; + r7 = regs->gpr[7]; + r8 = regs->gpr[8]; + + } else if (unlikely(r0 >= NR_syscalls)) { + if (unlikely(trap_is_unsupported_scv(regs))) { + /* Unsupported scv vector */ + _exception(SIGILL, regs, ILL_ILLOPC, regs->nip); + return regs->gpr[3]; + } + return -ENOSYS; + } + + /* May be faster to do array_index_nospec? */ + barrier_nospec(); + + if (unlikely(is_compat_task())) { + f = (void *)compat_sys_call_table[r0]; + + r3 &= 0x00000000ffffffffULL; + r4 &= 0x00000000ffffffffULL; + r5 &= 0x00000000ffffffffULL; + r6 &= 0x00000000ffffffffULL; + r7 &= 0x00000000ffffffffULL; + r8 &= 0x00000000ffffffffULL; + + } else { + f = (void *)sys_call_table[r0]; + } + + ret = f(r3, r4, r5, r6, r7, r8); + + /* + * Ultimately, this value will get limited by KSTACK_OFFSET_MAX(), + * so the maximum stack offset is 1k bytes (10 bits). + * + * The actual entropy will be further reduced by the compiler when + * applying stack alignment constraints: the powerpc architecture + * may have two kinds of stack alignment (16-bytes and 8-bytes). + * + * So the resulting 6 or 7 bits of entropy is seen in SP[9:4] or SP[9:3]. + */ + choose_random_kstack_offset(mftb()); + + return ret; +} diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c index 2a893e06e4f1..cb158c32b50b 100644 --- a/arch/powerpc/kernel/trace/ftrace.c +++ b/arch/powerpc/kernel/trace/ftrace.c @@ -69,8 +69,8 @@ ftrace_modify_code(unsigned long ip, ppc_inst_t old, ppc_inst_t new) /* Make sure it is what we expect it to be */ if (!ppc_inst_equal(replaced, old)) { - pr_err("%p: replaced (%s) != old (%s)", - (void *)ip, ppc_inst_as_str(replaced), ppc_inst_as_str(old)); + pr_err("%p: replaced (%08lx) != old (%08lx)", (void *)ip, + ppc_inst_as_ulong(replaced), ppc_inst_as_ulong(old)); return -EINVAL; } @@ -125,9 +125,9 @@ __ftrace_make_nop(struct module *mod, return -EFAULT; } - /* Make sure that that this is still a 24bit jump */ + /* Make sure that this is still a 24bit jump */ if (!is_bl_op(op)) { - pr_err("Not expected bl: opcode is %s\n", ppc_inst_as_str(op)); + pr_err("Not expected bl: opcode is %08lx\n", ppc_inst_as_ulong(op)); return -EINVAL; } @@ -159,8 +159,8 @@ __ftrace_make_nop(struct module *mod, /* 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 %s around bl _mcount\n", - ppc_inst_as_str(op)); + pr_err("Unexpected instruction %08lx around bl _mcount\n", + ppc_inst_as_ulong(op)); return -EINVAL; } } else if (IS_ENABLED(CONFIG_PPC64)) { @@ -174,7 +174,8 @@ __ftrace_make_nop(struct module *mod, } if (!ppc_inst_equal(op, ppc_inst(PPC_INST_LD_TOC))) { - pr_err("Expected %08lx found %s\n", PPC_INST_LD_TOC, ppc_inst_as_str(op)); + pr_err("Expected %08lx found %08lx\n", PPC_INST_LD_TOC, + ppc_inst_as_ulong(op)); return -EINVAL; } } @@ -310,9 +311,9 @@ static int __ftrace_make_nop_kernel(struct dyn_ftrace *rec, unsigned long addr) return -EFAULT; } - /* Make sure that that this is still a 24bit jump */ + /* Make sure that this is still a 24bit jump */ if (!is_bl_op(op)) { - pr_err("Not expected bl: opcode is %s\n", ppc_inst_as_str(op)); + pr_err("Not expected bl: opcode is %08lx\n", ppc_inst_as_ulong(op)); return -EINVAL; } @@ -416,8 +417,8 @@ __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) return -EFAULT; if (!expected_nop_sequence(ip, op[0], op[1])) { - pr_err("Unexpected call sequence at %p: %s %s\n", - ip, ppc_inst_as_str(op[0]), ppc_inst_as_str(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; } @@ -486,7 +487,8 @@ static int __ftrace_make_call_kernel(struct dyn_ftrace *rec, unsigned long addr) } if (!ppc_inst_equal(op, ppc_inst(PPC_RAW_NOP()))) { - pr_err("Unexpected call sequence at %p: %s\n", ip, ppc_inst_as_str(op)); + pr_err("Unexpected call sequence at %p: %08lx\n", + ip, ppc_inst_as_ulong(op)); return -EINVAL; } @@ -562,9 +564,9 @@ __ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, return -EFAULT; } - /* Make sure that that this is still a 24bit jump */ + /* Make sure that this is still a 24bit jump */ if (!is_bl_op(op)) { - pr_err("Not expected bl: opcode is %s\n", ppc_inst_as_str(op)); + pr_err("Not expected bl: opcode is %08lx\n", ppc_inst_as_ulong(op)); return -EINVAL; } diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index 3aaa50e5c72f..dadfcef5d6db 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -1676,7 +1676,7 @@ DEFINE_INTERRUPT_HANDLER(vsx_unavailable_exception) die("Unrecoverable VSX Unavailable Exception", regs, SIGABRT); } -#ifdef CONFIG_PPC64 +#ifdef CONFIG_PPC_BOOK3S_64 static void tm_unavailable(struct pt_regs *regs) { #ifdef CONFIG_PPC_TRANSACTIONAL_MEM diff --git a/arch/powerpc/kernel/vdso/cacheflush.S b/arch/powerpc/kernel/vdso/cacheflush.S index d4e43ab2d5df..0085ae464dac 100644 --- a/arch/powerpc/kernel/vdso/cacheflush.S +++ b/arch/powerpc/kernel/vdso/cacheflush.S @@ -91,6 +91,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE) 3: crclr cr0*4+so sync + icbi 0,r1 isync li r3,0 blr diff --git a/arch/powerpc/kernel/watchdog.c b/arch/powerpc/kernel/watchdog.c index 7d28b9553654..dbcc4a793f0b 100644 --- a/arch/powerpc/kernel/watchdog.c +++ b/arch/powerpc/kernel/watchdog.c @@ -91,6 +91,10 @@ static cpumask_t wd_smp_cpus_pending; static cpumask_t wd_smp_cpus_stuck; static u64 wd_smp_last_reset_tb; +#ifdef CONFIG_PPC_PSERIES +static u64 wd_timeout_pct; +#endif + /* * Try to take the exclusive watchdog action / NMI IPI / printing lock. * wd_smp_lock must be held. If this fails, we should return and wait @@ -353,7 +357,7 @@ static void watchdog_timer_interrupt(int cpu) if (__wd_nmi_output && xchg(&__wd_nmi_output, 0)) { /* * Something has called printk from NMI context. It might be - * stuck, so this this triggers a flush that will get that + * stuck, so this triggers a flush that will get that * printk output to the console. * * See wd_lockup_ipi. @@ -527,7 +531,13 @@ static int stop_watchdog_on_cpu(unsigned int cpu) static void watchdog_calc_timeouts(void) { - wd_panic_timeout_tb = watchdog_thresh * ppc_tb_freq; + u64 threshold = watchdog_thresh; + +#ifdef CONFIG_PPC_PSERIES + threshold += (READ_ONCE(wd_timeout_pct) * threshold) / 100; +#endif + + wd_panic_timeout_tb = threshold * ppc_tb_freq; /* Have the SMP detector trigger a bit later */ wd_smp_panic_timeout_tb = wd_panic_timeout_tb * 3 / 2; @@ -570,3 +580,12 @@ int __init watchdog_nmi_probe(void) } return 0; } + +#ifdef CONFIG_PPC_PSERIES +void watchdog_nmi_set_timeout_pct(u64 pct) +{ + pr_info("Set the NMI watchdog timeout factor to %llu%%\n", pct); + WRITE_ONCE(wd_timeout_pct, pct); + lockup_detector_reconfigure(); +} +#endif diff --git a/arch/powerpc/kexec/core.c b/arch/powerpc/kexec/core.c index 7ab4980fe13a..cf84bfe9e27e 100644 --- a/arch/powerpc/kexec/core.c +++ b/arch/powerpc/kexec/core.c @@ -19,6 +19,8 @@ #include <asm/machdep.h> #include <asm/pgalloc.h> #include <asm/sections.h> +#include <asm/setup.h> +#include <asm/firmware.h> void machine_kexec_mask_interrupts(void) { unsigned int i; diff --git a/arch/powerpc/kexec/crash.c b/arch/powerpc/kexec/crash.c index 80f54723cf6d..252724ed666a 100644 --- a/arch/powerpc/kexec/crash.c +++ b/arch/powerpc/kexec/crash.c @@ -40,6 +40,14 @@ #define REAL_MODE_TIMEOUT 10000 static int time_to_dump; + +/* + * In case of system reset, secondary CPUs enter crash_kexec_secondary with out + * having to send an IPI explicitly. So, indicate if the crash is via + * system reset to avoid sending another IPI. + */ +static int is_via_system_reset; + /* * crash_wake_offline should be set to 1 by platforms that intend to wake * up offline cpus prior to jumping to a kdump kernel. Currently powernv @@ -101,7 +109,7 @@ void crash_ipi_callback(struct pt_regs *regs) /* NOTREACHED */ } -static void crash_kexec_prepare_cpus(int cpu) +static void crash_kexec_prepare_cpus(void) { unsigned int msecs; volatile unsigned int ncpus = num_online_cpus() - 1;/* Excluding the panic cpu */ @@ -113,7 +121,15 @@ static void crash_kexec_prepare_cpus(int cpu) if (crash_wake_offline) ncpus = num_present_cpus() - 1; - crash_send_ipi(crash_ipi_callback); + /* + * If we came in via system reset, secondaries enter via crash_kexec_secondary(). + * So, wait a while for the secondary CPUs to enter for that case. + * Else, send IPI to all other CPUs. + */ + if (is_via_system_reset) + mdelay(PRIMARY_TIMEOUT); + else + crash_send_ipi(crash_ipi_callback); smp_wmb(); again: @@ -202,7 +218,7 @@ void crash_kexec_secondary(struct pt_regs *regs) #else /* ! CONFIG_SMP */ -static void crash_kexec_prepare_cpus(int cpu) +static void crash_kexec_prepare_cpus(void) { /* * move the secondaries to us so that we can copy @@ -248,6 +264,32 @@ noinstr static void __maybe_unused crash_kexec_wait_realmode(int cpu) static inline void crash_kexec_wait_realmode(int cpu) {} #endif /* CONFIG_SMP && CONFIG_PPC64 */ +void crash_kexec_prepare(void) +{ + /* Avoid hardlocking with irresponsive CPU holding logbuf_lock */ + printk_deferred_enter(); + + /* + * This function is only called after the system + * has panicked or is otherwise in a critical state. + * The minimum amount of code to allow a kexec'd kernel + * to run successfully needs to happen here. + * + * In practice this means stopping other cpus in + * an SMP system. + * The kernel is broken so disable interrupts. + */ + hard_irq_disable(); + + /* + * Make a note of crashing cpu. Will be used in machine_kexec + * such that another IPI will not be sent. + */ + crashing_cpu = smp_processor_id(); + + crash_kexec_prepare_cpus(); +} + /* * Register a function to be called on shutdown. Only use this if you * can't reset your device in the second kernel. @@ -311,35 +353,10 @@ void default_machine_crash_shutdown(struct pt_regs *regs) unsigned int i; int (*old_handler)(struct pt_regs *regs); - /* Avoid hardlocking with irresponsive CPU holding logbuf_lock */ - printk_deferred_enter(); - - /* - * This function is only called after the system - * has panicked or is otherwise in a critical state. - * The minimum amount of code to allow a kexec'd kernel - * to run successfully needs to happen here. - * - * In practice this means stopping other cpus in - * an SMP system. - * The kernel is broken so disable interrupts. - */ - hard_irq_disable(); - - /* - * Make a note of crashing cpu. Will be used in machine_kexec - * such that another IPI will not be sent. - */ - crashing_cpu = smp_processor_id(); - - /* - * If we came in via system reset, wait a while for the secondary - * CPUs to enter. - */ if (TRAP(regs) == INTERRUPT_SYSTEM_RESET) - mdelay(PRIMARY_TIMEOUT); + is_via_system_reset = 1; - crash_kexec_prepare_cpus(crashing_cpu); + crash_smp_send_stop(); crash_save_cpu(regs, crashing_cpu); diff --git a/arch/powerpc/kexec/file_load_64.c b/arch/powerpc/kexec/file_load_64.c index b4981b651d9a..683462e4556b 100644 --- a/arch/powerpc/kexec/file_load_64.c +++ b/arch/powerpc/kexec/file_load_64.c @@ -23,6 +23,7 @@ #include <linux/vmalloc.h> #include <asm/setup.h> #include <asm/drmem.h> +#include <asm/firmware.h> #include <asm/kexec_ranges.h> #include <asm/crashdump-ppc64.h> @@ -1038,6 +1039,48 @@ out: return ret; } +static int copy_property(void *fdt, int node_offset, const struct device_node *dn, + const char *propname) +{ + const void *prop, *fdtprop; + int len = 0, fdtlen = 0, ret; + + prop = of_get_property(dn, propname, &len); + fdtprop = fdt_getprop(fdt, node_offset, propname, &fdtlen); + + if (fdtprop && !prop) + ret = fdt_delprop(fdt, node_offset, propname); + else if (prop) + ret = fdt_setprop(fdt, node_offset, propname, prop, len); + + return ret; +} + +static int update_pci_dma_nodes(void *fdt, const char *dmapropname) +{ + struct device_node *dn; + int pci_offset, root_offset, ret = 0; + + if (!firmware_has_feature(FW_FEATURE_LPAR)) + return 0; + + root_offset = fdt_path_offset(fdt, "/"); + for_each_node_with_property(dn, dmapropname) { + pci_offset = fdt_subnode_offset(fdt, root_offset, of_node_full_name(dn)); + if (pci_offset < 0) + continue; + + ret = copy_property(fdt, pci_offset, dn, "ibm,dma-window"); + if (ret < 0) + break; + ret = copy_property(fdt, pci_offset, dn, dmapropname); + if (ret < 0) + break; + } + + return ret; +} + /** * setup_new_fdt_ppc64 - Update the flattend device-tree of the kernel * being loaded. @@ -1099,6 +1142,18 @@ 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; + + 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); if (ret) diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig index ddd88179110a..dcb398d5e009 100644 --- a/arch/powerpc/kvm/Kconfig +++ b/arch/powerpc/kvm/Kconfig @@ -128,9 +128,26 @@ config KVM_BOOK3S_64_PR and system calls on the host. config KVM_BOOK3S_HV_EXIT_TIMING - bool "Detailed timing for hypervisor real-mode code" + bool + +config KVM_BOOK3S_HV_P9_TIMING + bool "Detailed timing for the P9 entry point" + select KVM_BOOK3S_HV_EXIT_TIMING depends on KVM_BOOK3S_HV_POSSIBLE && DEBUG_FS help + Calculate time taken for each vcpu during vcpu entry and + exit, time spent inside the guest and time spent handling + hypercalls and page faults. The total, minimum and maximum + times in nanoseconds together with the number of executions + are reported in debugfs in kvm/vm#/vcpu#/timings. + + If unsure, say N. + +config KVM_BOOK3S_HV_P8_TIMING + bool "Detailed timing for hypervisor real-mode code (for POWER8)" + select KVM_BOOK3S_HV_EXIT_TIMING + depends on KVM_BOOK3S_HV_POSSIBLE && DEBUG_FS && !KVM_BOOK3S_HV_P9_TIMING + help Calculate time taken for each vcpu in the real-mode guest entry, exit, and interrupt handling code, plus time spent in the guest and in nap mode due to idle (cede) while other threads are still @@ -149,7 +166,7 @@ config KVM_BOOK3S_HV_NESTED_PMU_WORKAROUND Old nested HV capable Linux guests have a bug where they don't reflect the PMU in-use status of their L2 guest to the L0 host while the L2 PMU registers are live. This can result in loss - of L2 PMU register state, causing perf to not work correctly in + of L2 PMU register state, causing perf to not work correctly in L2 guests. Selecting this option for the L0 host implements a workaround for diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile index 0cd23ce07d68..5319d889b184 100644 --- a/arch/powerpc/kvm/Makefile +++ b/arch/powerpc/kvm/Makefile @@ -86,6 +86,7 @@ kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_HANDLER) += \ book3s_hv_rm_mmu.o \ book3s_hv_ras.o \ book3s_hv_builtin.o \ + book3s_hv_p9_perf.o \ $(kvm-book3s_64-builtin-tm-objs-y) \ $(kvm-book3s_64-builtin-xics-objs-y) endif diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c index 42851c32ff3b..9d4b3feda3b6 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_radix.c +++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c @@ -22,6 +22,7 @@ #include <asm/ultravisor.h> #include <asm/kvm_book3s_uvmem.h> #include <asm/plpar_wrappers.h> +#include <asm/firmware.h> /* * Supported radix tree geometry. diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c index d6589c4fe889..40864373ef87 100644 --- a/arch/powerpc/kvm/book3s_64_vio.c +++ b/arch/powerpc/kvm/book3s_64_vio.c @@ -307,7 +307,7 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm, return ret; ret = -ENOMEM; - stt = kzalloc(struct_size(stt, pages, npages), GFP_KERNEL); + stt = kzalloc(struct_size(stt, pages, npages), GFP_KERNEL | __GFP_NOWARN); if (!stt) goto fail_acct; diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 631062cde6b4..57d0835e56fd 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -2660,11 +2660,21 @@ static struct debugfs_timings_element { const char *name; size_t offset; } timings[] = { +#ifdef CONFIG_KVM_BOOK3S_HV_P9_TIMING + {"vcpu_entry", offsetof(struct kvm_vcpu, arch.vcpu_entry)}, + {"guest_entry", offsetof(struct kvm_vcpu, arch.guest_entry)}, + {"in_guest", offsetof(struct kvm_vcpu, arch.in_guest)}, + {"guest_exit", offsetof(struct kvm_vcpu, arch.guest_exit)}, + {"vcpu_exit", offsetof(struct kvm_vcpu, arch.vcpu_exit)}, + {"hypercall", offsetof(struct kvm_vcpu, arch.hcall)}, + {"page_fault", offsetof(struct kvm_vcpu, arch.pg_fault)}, +#else {"rm_entry", offsetof(struct kvm_vcpu, arch.rm_entry)}, {"rm_intr", offsetof(struct kvm_vcpu, arch.rm_intr)}, {"rm_exit", offsetof(struct kvm_vcpu, arch.rm_exit)}, {"guest", offsetof(struct kvm_vcpu, arch.guest_time)}, {"cede", offsetof(struct kvm_vcpu, arch.cede_time)}, +#endif }; #define N_TIMINGS (ARRAY_SIZE(timings)) @@ -2783,8 +2793,9 @@ static const struct file_operations debugfs_timings_ops = { /* Create a debugfs directory for the vcpu */ static int kvmppc_arch_create_vcpu_debugfs_hv(struct kvm_vcpu *vcpu, struct dentry *debugfs_dentry) { - debugfs_create_file("timings", 0444, debugfs_dentry, vcpu, - &debugfs_timings_ops); + if (cpu_has_feature(CPU_FTR_ARCH_300) == IS_ENABLED(CONFIG_KVM_BOOK3S_HV_P9_TIMING)) + debugfs_create_file("timings", 0444, debugfs_dentry, vcpu, + &debugfs_timings_ops); return 0; } @@ -4005,8 +4016,10 @@ static int kvmhv_vcpu_entry_p9_nested(struct kvm_vcpu *vcpu, u64 time_limit, uns mtspr(SPRN_DAR, vcpu->arch.shregs.dar); mtspr(SPRN_DSISR, vcpu->arch.shregs.dsisr); switch_pmu_to_guest(vcpu, &host_os_sprs); + accumulate_time(vcpu, &vcpu->arch.in_guest); trap = plpar_hcall_norets(H_ENTER_NESTED, __pa(&hvregs), __pa(&vcpu->arch.regs)); + accumulate_time(vcpu, &vcpu->arch.guest_exit); kvmhv_restore_hv_return_state(vcpu, &hvregs); switch_pmu_to_host(vcpu, &host_os_sprs); vcpu->arch.shregs.msr = vcpu->arch.regs.msr; @@ -4694,6 +4707,8 @@ static int kvmppc_vcpu_run_hv(struct kvm_vcpu *vcpu) struct kvm *kvm; unsigned long msr; + start_timing(vcpu, &vcpu->arch.vcpu_entry); + if (!vcpu->arch.sane) { run->exit_reason = KVM_EXIT_INTERNAL_ERROR; return -EINVAL; @@ -4759,6 +4774,7 @@ static int kvmppc_vcpu_run_hv(struct kvm_vcpu *vcpu) vcpu->arch.state = KVMPPC_VCPU_BUSY_IN_HOST; do { + accumulate_time(vcpu, &vcpu->arch.guest_entry); if (cpu_has_feature(CPU_FTR_ARCH_300)) r = kvmhv_run_single_vcpu(vcpu, ~(u64)0, vcpu->arch.vcore->lpcr); @@ -4766,6 +4782,8 @@ static int kvmppc_vcpu_run_hv(struct kvm_vcpu *vcpu) r = kvmppc_run_vcpu(vcpu); if (run->exit_reason == KVM_EXIT_PAPR_HCALL) { + accumulate_time(vcpu, &vcpu->arch.hcall); + if (WARN_ON_ONCE(vcpu->arch.shregs.msr & MSR_PR)) { /* * These should have been caught reflected @@ -4781,6 +4799,7 @@ static int kvmppc_vcpu_run_hv(struct kvm_vcpu *vcpu) trace_kvm_hcall_exit(vcpu, r); kvmppc_core_prepare_to_enter(vcpu); } else if (r == RESUME_PAGE_FAULT) { + accumulate_time(vcpu, &vcpu->arch.pg_fault); srcu_idx = srcu_read_lock(&kvm->srcu); r = kvmppc_book3s_hv_page_fault(vcpu, vcpu->arch.fault_dar, vcpu->arch.fault_dsisr); @@ -4792,12 +4811,15 @@ static int kvmppc_vcpu_run_hv(struct kvm_vcpu *vcpu) r = kvmppc_xics_rm_complete(vcpu, 0); } } while (is_kvmppc_resume_guest(r)); + accumulate_time(vcpu, &vcpu->arch.vcpu_exit); vcpu->arch.state = KVMPPC_VCPU_NOTREADY; atomic_dec(&kvm->arch.vcpus_running); srr_regs_clobbered(); + end_timing(vcpu); + return r; } @@ -5643,7 +5665,7 @@ static int kvmppc_clr_passthru_irq(struct kvm *kvm, int host_irq, int guest_gsi) else kvmppc_xics_clr_mapped(kvm, guest_gsi, pimap->mapped[i].r_hwirq); - /* invalidate the entry (what do do on error from the above ?) */ + /* invalidate the entry (what to do on error from the above ?) */ pimap->mapped[i].r_hwirq = 0; /* diff --git a/arch/powerpc/kvm/book3s_hv.h b/arch/powerpc/kvm/book3s_hv.h index 6b7f07d9026b..2f2e59d7d433 100644 --- a/arch/powerpc/kvm/book3s_hv.h +++ b/arch/powerpc/kvm/book3s_hv.h @@ -40,3 +40,13 @@ void switch_pmu_to_guest(struct kvm_vcpu *vcpu, struct p9_host_os_sprs *host_os_sprs); void switch_pmu_to_host(struct kvm_vcpu *vcpu, struct p9_host_os_sprs *host_os_sprs); + +#ifdef CONFIG_KVM_BOOK3S_HV_P9_TIMING +void accumulate_time(struct kvm_vcpu *vcpu, struct kvmhv_tb_accumulator *next); +#define start_timing(vcpu, next) accumulate_time(vcpu, next) +#define end_timing(vcpu) accumulate_time(vcpu, NULL) +#else +#define accumulate_time(vcpu, next) do {} while (0) +#define start_timing(vcpu, next) do {} while (0) +#define end_timing(vcpu) do {} while (0) +#endif diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c index 88a8f6473c4e..da85f046377a 100644 --- a/arch/powerpc/kvm/book3s_hv_builtin.c +++ b/arch/powerpc/kvm/book3s_hv_builtin.c @@ -19,7 +19,7 @@ #include <asm/interrupt.h> #include <asm/kvm_ppc.h> #include <asm/kvm_book3s.h> -#include <asm/archrandom.h> +#include <asm/machdep.h> #include <asm/xics.h> #include <asm/xive.h> #include <asm/dbell.h> @@ -176,13 +176,14 @@ EXPORT_SYMBOL_GPL(kvmppc_hcall_impl_hv_realmode); int kvmppc_hwrng_present(void) { - return powernv_hwrng_present(); + return ppc_md.get_random_seed != NULL; } EXPORT_SYMBOL_GPL(kvmppc_hwrng_present); long kvmppc_rm_h_random(struct kvm_vcpu *vcpu) { - if (powernv_get_random_real_mode(&vcpu->arch.regs.gpr[4])) + if (ppc_md.get_random_seed && + ppc_md.get_random_seed(&vcpu->arch.regs.gpr[4])) return H_SUCCESS; return H_HARDWARE; @@ -489,24 +490,6 @@ static long kvmppc_read_one_intr(bool *again) return kvmppc_check_passthru(xisr, xirr, again); } -void kvmppc_bad_interrupt(struct pt_regs *regs) -{ - /* - * 100 could happen at any time, 200 can happen due to invalid real - * address access for example (or any time due to a hardware problem). - */ - if (TRAP(regs) == 0x100) { - get_paca()->in_nmi++; - system_reset_exception(regs); - get_paca()->in_nmi--; - } else if (TRAP(regs) == 0x200) { - machine_check_exception(regs); - } else { - die("Bad interrupt in KVM entry/exit code", regs, SIGABRT); - } - panic("Bad KVM trap"); -} - static void kvmppc_end_cede(struct kvm_vcpu *vcpu) { vcpu->arch.ceded = 0; diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c index 0644732d1a25..be8249cc6107 100644 --- a/arch/powerpc/kvm/book3s_hv_nested.c +++ b/arch/powerpc/kvm/book3s_hv_nested.c @@ -20,6 +20,7 @@ #include <asm/pte-walk.h> #include <asm/reg.h> #include <asm/plpar_wrappers.h> +#include <asm/firmware.h> static struct patb_entry *pseries_partition_tb; diff --git a/arch/powerpc/kvm/book3s_hv_p9_entry.c b/arch/powerpc/kvm/book3s_hv_p9_entry.c index 112a09b33328..34f1db212824 100644 --- a/arch/powerpc/kvm/book3s_hv_p9_entry.c +++ b/arch/powerpc/kvm/book3s_hv_p9_entry.c @@ -3,231 +3,10 @@ #include <linux/kvm_host.h> #include <asm/asm-prototypes.h> #include <asm/dbell.h> -#include <asm/kvm_ppc.h> -#include <asm/pmc.h> #include <asm/ppc-opcode.h> #include "book3s_hv.h" -static void freeze_pmu(unsigned long mmcr0, unsigned long mmcra) -{ - if (!(mmcr0 & MMCR0_FC)) - goto do_freeze; - if (mmcra & MMCRA_SAMPLE_ENABLE) - goto do_freeze; - if (cpu_has_feature(CPU_FTR_ARCH_31)) { - if (!(mmcr0 & MMCR0_PMCCEXT)) - goto do_freeze; - if (!(mmcra & MMCRA_BHRB_DISABLE)) - goto do_freeze; - } - return; - -do_freeze: - mmcr0 = MMCR0_FC; - mmcra = 0; - if (cpu_has_feature(CPU_FTR_ARCH_31)) { - mmcr0 |= MMCR0_PMCCEXT; - mmcra = MMCRA_BHRB_DISABLE; - } - - mtspr(SPRN_MMCR0, mmcr0); - mtspr(SPRN_MMCRA, mmcra); - isync(); -} - -void switch_pmu_to_guest(struct kvm_vcpu *vcpu, - struct p9_host_os_sprs *host_os_sprs) -{ - struct lppaca *lp; - int load_pmu = 1; - - lp = vcpu->arch.vpa.pinned_addr; - if (lp) - load_pmu = lp->pmcregs_in_use; - - /* Save host */ - if (ppc_get_pmu_inuse()) { - /* - * It might be better to put PMU handling (at least for the - * host) in the perf subsystem because it knows more about what - * is being used. - */ - - /* POWER9, POWER10 do not implement HPMC or SPMC */ - - host_os_sprs->mmcr0 = mfspr(SPRN_MMCR0); - host_os_sprs->mmcra = mfspr(SPRN_MMCRA); - - freeze_pmu(host_os_sprs->mmcr0, host_os_sprs->mmcra); - - host_os_sprs->pmc1 = mfspr(SPRN_PMC1); - host_os_sprs->pmc2 = mfspr(SPRN_PMC2); - host_os_sprs->pmc3 = mfspr(SPRN_PMC3); - host_os_sprs->pmc4 = mfspr(SPRN_PMC4); - host_os_sprs->pmc5 = mfspr(SPRN_PMC5); - host_os_sprs->pmc6 = mfspr(SPRN_PMC6); - host_os_sprs->mmcr1 = mfspr(SPRN_MMCR1); - host_os_sprs->mmcr2 = mfspr(SPRN_MMCR2); - host_os_sprs->sdar = mfspr(SPRN_SDAR); - host_os_sprs->siar = mfspr(SPRN_SIAR); - host_os_sprs->sier1 = mfspr(SPRN_SIER); - - if (cpu_has_feature(CPU_FTR_ARCH_31)) { - host_os_sprs->mmcr3 = mfspr(SPRN_MMCR3); - host_os_sprs->sier2 = mfspr(SPRN_SIER2); - host_os_sprs->sier3 = mfspr(SPRN_SIER3); - } - } - -#ifdef CONFIG_PPC_PSERIES - /* After saving PMU, before loading guest PMU, flip pmcregs_in_use */ - if (kvmhv_on_pseries()) { - barrier(); - get_lppaca()->pmcregs_in_use = load_pmu; - barrier(); - } -#endif - - /* - * Load guest. If the VPA said the PMCs are not in use but the guest - * tried to access them anyway, HFSCR[PM] will be set by the HFAC - * fault so we can make forward progress. - */ - if (load_pmu || (vcpu->arch.hfscr & HFSCR_PM)) { - mtspr(SPRN_PMC1, vcpu->arch.pmc[0]); - mtspr(SPRN_PMC2, vcpu->arch.pmc[1]); - mtspr(SPRN_PMC3, vcpu->arch.pmc[2]); - mtspr(SPRN_PMC4, vcpu->arch.pmc[3]); - mtspr(SPRN_PMC5, vcpu->arch.pmc[4]); - mtspr(SPRN_PMC6, vcpu->arch.pmc[5]); - mtspr(SPRN_MMCR1, vcpu->arch.mmcr[1]); - mtspr(SPRN_MMCR2, vcpu->arch.mmcr[2]); - mtspr(SPRN_SDAR, vcpu->arch.sdar); - mtspr(SPRN_SIAR, vcpu->arch.siar); - mtspr(SPRN_SIER, vcpu->arch.sier[0]); - - if (cpu_has_feature(CPU_FTR_ARCH_31)) { - mtspr(SPRN_MMCR3, vcpu->arch.mmcr[3]); - mtspr(SPRN_SIER2, vcpu->arch.sier[1]); - mtspr(SPRN_SIER3, vcpu->arch.sier[2]); - } - - /* Set MMCRA then MMCR0 last */ - mtspr(SPRN_MMCRA, vcpu->arch.mmcra); - mtspr(SPRN_MMCR0, vcpu->arch.mmcr[0]); - /* No isync necessary because we're starting counters */ - - if (!vcpu->arch.nested && - (vcpu->arch.hfscr_permitted & HFSCR_PM)) - vcpu->arch.hfscr |= HFSCR_PM; - } -} -EXPORT_SYMBOL_GPL(switch_pmu_to_guest); - -void switch_pmu_to_host(struct kvm_vcpu *vcpu, - struct p9_host_os_sprs *host_os_sprs) -{ - struct lppaca *lp; - int save_pmu = 1; - - lp = vcpu->arch.vpa.pinned_addr; - if (lp) - save_pmu = lp->pmcregs_in_use; - if (IS_ENABLED(CONFIG_KVM_BOOK3S_HV_NESTED_PMU_WORKAROUND)) { - /* - * Save pmu if this guest is capable of running nested guests. - * This is option is for old L1s that do not set their - * lppaca->pmcregs_in_use properly when entering their L2. - */ - save_pmu |= nesting_enabled(vcpu->kvm); - } - - if (save_pmu) { - vcpu->arch.mmcr[0] = mfspr(SPRN_MMCR0); - vcpu->arch.mmcra = mfspr(SPRN_MMCRA); - - freeze_pmu(vcpu->arch.mmcr[0], vcpu->arch.mmcra); - - vcpu->arch.pmc[0] = mfspr(SPRN_PMC1); - vcpu->arch.pmc[1] = mfspr(SPRN_PMC2); - vcpu->arch.pmc[2] = mfspr(SPRN_PMC3); - vcpu->arch.pmc[3] = mfspr(SPRN_PMC4); - vcpu->arch.pmc[4] = mfspr(SPRN_PMC5); - vcpu->arch.pmc[5] = mfspr(SPRN_PMC6); - vcpu->arch.mmcr[1] = mfspr(SPRN_MMCR1); - vcpu->arch.mmcr[2] = mfspr(SPRN_MMCR2); - vcpu->arch.sdar = mfspr(SPRN_SDAR); - vcpu->arch.siar = mfspr(SPRN_SIAR); - vcpu->arch.sier[0] = mfspr(SPRN_SIER); - - if (cpu_has_feature(CPU_FTR_ARCH_31)) { - vcpu->arch.mmcr[3] = mfspr(SPRN_MMCR3); - vcpu->arch.sier[1] = mfspr(SPRN_SIER2); - vcpu->arch.sier[2] = mfspr(SPRN_SIER3); - } - - } else if (vcpu->arch.hfscr & HFSCR_PM) { - /* - * The guest accessed PMC SPRs without specifying they should - * be preserved, or it cleared pmcregs_in_use after the last - * access. Just ensure they are frozen. - */ - freeze_pmu(mfspr(SPRN_MMCR0), mfspr(SPRN_MMCRA)); - - /* - * Demand-fault PMU register access in the guest. - * - * This is used to grab the guest's VPA pmcregs_in_use value - * and reflect it into the host's VPA in the case of a nested - * hypervisor. - * - * It also avoids having to zero-out SPRs after each guest - * exit to avoid side-channels when. - * - * This is cleared here when we exit the guest, so later HFSCR - * interrupt handling can add it back to run the guest with - * PM enabled next time. - */ - if (!vcpu->arch.nested) - vcpu->arch.hfscr &= ~HFSCR_PM; - } /* otherwise the PMU should still be frozen */ - -#ifdef CONFIG_PPC_PSERIES - if (kvmhv_on_pseries()) { - barrier(); - get_lppaca()->pmcregs_in_use = ppc_get_pmu_inuse(); - barrier(); - } -#endif - - if (ppc_get_pmu_inuse()) { - mtspr(SPRN_PMC1, host_os_sprs->pmc1); - mtspr(SPRN_PMC2, host_os_sprs->pmc2); - mtspr(SPRN_PMC3, host_os_sprs->pmc3); - mtspr(SPRN_PMC4, host_os_sprs->pmc4); - mtspr(SPRN_PMC5, host_os_sprs->pmc5); - mtspr(SPRN_PMC6, host_os_sprs->pmc6); - mtspr(SPRN_MMCR1, host_os_sprs->mmcr1); - mtspr(SPRN_MMCR2, host_os_sprs->mmcr2); - mtspr(SPRN_SDAR, host_os_sprs->sdar); - mtspr(SPRN_SIAR, host_os_sprs->siar); - mtspr(SPRN_SIER, host_os_sprs->sier1); - - if (cpu_has_feature(CPU_FTR_ARCH_31)) { - mtspr(SPRN_MMCR3, host_os_sprs->mmcr3); - mtspr(SPRN_SIER2, host_os_sprs->sier2); - mtspr(SPRN_SIER3, host_os_sprs->sier3); - } - - /* Set MMCRA then MMCR0 last */ - mtspr(SPRN_MMCRA, host_os_sprs->mmcra); - mtspr(SPRN_MMCR0, host_os_sprs->mmcr0); - isync(); - } -} -EXPORT_SYMBOL_GPL(switch_pmu_to_host); - static void load_spr_state(struct kvm_vcpu *vcpu, struct p9_host_os_sprs *host_os_sprs) { @@ -437,17 +216,8 @@ void restore_p9_host_os_sprs(struct kvm_vcpu *vcpu, } EXPORT_SYMBOL_GPL(restore_p9_host_os_sprs); -#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING -static void __start_timing(struct kvm_vcpu *vcpu, struct kvmhv_tb_accumulator *next) -{ - struct kvmppc_vcore *vc = vcpu->arch.vcore; - u64 tb = mftb() - vc->tb_offset_applied; - - vcpu->arch.cur_activity = next; - vcpu->arch.cur_tb_start = tb; -} - -static void __accumulate_time(struct kvm_vcpu *vcpu, struct kvmhv_tb_accumulator *next) +#ifdef CONFIG_KVM_BOOK3S_HV_P9_TIMING +void accumulate_time(struct kvm_vcpu *vcpu, struct kvmhv_tb_accumulator *next) { struct kvmppc_vcore *vc = vcpu->arch.vcore; struct kvmhv_tb_accumulator *curr; @@ -477,14 +247,7 @@ static void __accumulate_time(struct kvm_vcpu *vcpu, struct kvmhv_tb_accumulator smp_wmb(); curr->seqcount = seq + 2; } - -#define start_timing(vcpu, next) __start_timing(vcpu, next) -#define end_timing(vcpu) __start_timing(vcpu, NULL) -#define accumulate_time(vcpu, next) __accumulate_time(vcpu, next) -#else -#define start_timing(vcpu, next) do {} while (0) -#define end_timing(vcpu) do {} while (0) -#define accumulate_time(vcpu, next) do {} while (0) +EXPORT_SYMBOL_GPL(accumulate_time); #endif static inline u64 mfslbv(unsigned int idx) @@ -795,8 +558,6 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc WARN_ON_ONCE(vcpu->arch.shregs.msr & MSR_HV); WARN_ON_ONCE(!(vcpu->arch.shregs.msr & MSR_ME)); - start_timing(vcpu, &vcpu->arch.rm_entry); - vcpu->arch.ceded = 0; /* Save MSR for restore, with EE clear. */ @@ -957,13 +718,13 @@ tm_return_to_guest: mtspr(SPRN_SRR0, vcpu->arch.shregs.srr0); mtspr(SPRN_SRR1, vcpu->arch.shregs.srr1); - accumulate_time(vcpu, &vcpu->arch.guest_time); - switch_pmu_to_guest(vcpu, &host_os_sprs); + accumulate_time(vcpu, &vcpu->arch.in_guest); + kvmppc_p9_enter_guest(vcpu); - switch_pmu_to_host(vcpu, &host_os_sprs); - accumulate_time(vcpu, &vcpu->arch.rm_intr); + accumulate_time(vcpu, &vcpu->arch.guest_exit); + switch_pmu_to_host(vcpu, &host_os_sprs); /* XXX: Could get these from r11/12 and paca exsave instead */ vcpu->arch.shregs.srr0 = mfspr(SPRN_SRR0); @@ -1058,8 +819,6 @@ tm_return_to_guest: #endif } - accumulate_time(vcpu, &vcpu->arch.rm_exit); - /* Advance host PURR/SPURR by the amount used by guest */ purr = mfspr(SPRN_PURR); spurr = mfspr(SPRN_SPURR); @@ -1166,8 +925,6 @@ tm_return_to_guest: asm volatile(PPC_CP_ABORT); out: - end_timing(vcpu); - return trap; } EXPORT_SYMBOL_GPL(kvmhv_vcpu_entry_p9); diff --git a/arch/powerpc/kvm/book3s_hv_p9_perf.c b/arch/powerpc/kvm/book3s_hv_p9_perf.c new file mode 100644 index 000000000000..44d24cca3df1 --- /dev/null +++ b/arch/powerpc/kvm/book3s_hv_p9_perf.c @@ -0,0 +1,219 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <asm/kvm_ppc.h> +#include <asm/pmc.h> + +#include "book3s_hv.h" + +static void freeze_pmu(unsigned long mmcr0, unsigned long mmcra) +{ + if (!(mmcr0 & MMCR0_FC)) + goto do_freeze; + if (mmcra & MMCRA_SAMPLE_ENABLE) + goto do_freeze; + if (cpu_has_feature(CPU_FTR_ARCH_31)) { + if (!(mmcr0 & MMCR0_PMCCEXT)) + goto do_freeze; + if (!(mmcra & MMCRA_BHRB_DISABLE)) + goto do_freeze; + } + return; + +do_freeze: + mmcr0 = MMCR0_FC; + mmcra = 0; + if (cpu_has_feature(CPU_FTR_ARCH_31)) { + mmcr0 |= MMCR0_PMCCEXT; + mmcra = MMCRA_BHRB_DISABLE; + } + + mtspr(SPRN_MMCR0, mmcr0); + mtspr(SPRN_MMCRA, mmcra); + isync(); +} + +void switch_pmu_to_guest(struct kvm_vcpu *vcpu, + struct p9_host_os_sprs *host_os_sprs) +{ + struct lppaca *lp; + int load_pmu = 1; + + lp = vcpu->arch.vpa.pinned_addr; + if (lp) + load_pmu = lp->pmcregs_in_use; + + /* Save host */ + if (ppc_get_pmu_inuse()) { + /* POWER9, POWER10 do not implement HPMC or SPMC */ + + host_os_sprs->mmcr0 = mfspr(SPRN_MMCR0); + host_os_sprs->mmcra = mfspr(SPRN_MMCRA); + + freeze_pmu(host_os_sprs->mmcr0, host_os_sprs->mmcra); + + host_os_sprs->pmc1 = mfspr(SPRN_PMC1); + host_os_sprs->pmc2 = mfspr(SPRN_PMC2); + host_os_sprs->pmc3 = mfspr(SPRN_PMC3); + host_os_sprs->pmc4 = mfspr(SPRN_PMC4); + host_os_sprs->pmc5 = mfspr(SPRN_PMC5); + host_os_sprs->pmc6 = mfspr(SPRN_PMC6); + host_os_sprs->mmcr1 = mfspr(SPRN_MMCR1); + host_os_sprs->mmcr2 = mfspr(SPRN_MMCR2); + host_os_sprs->sdar = mfspr(SPRN_SDAR); + host_os_sprs->siar = mfspr(SPRN_SIAR); + host_os_sprs->sier1 = mfspr(SPRN_SIER); + + if (cpu_has_feature(CPU_FTR_ARCH_31)) { + host_os_sprs->mmcr3 = mfspr(SPRN_MMCR3); + host_os_sprs->sier2 = mfspr(SPRN_SIER2); + host_os_sprs->sier3 = mfspr(SPRN_SIER3); + } + } + +#ifdef CONFIG_PPC_PSERIES + /* After saving PMU, before loading guest PMU, flip pmcregs_in_use */ + if (kvmhv_on_pseries()) { + barrier(); + get_lppaca()->pmcregs_in_use = load_pmu; + barrier(); + } +#endif + + /* + * Load guest. If the VPA said the PMCs are not in use but the guest + * tried to access them anyway, HFSCR[PM] will be set by the HFAC + * fault so we can make forward progress. + */ + if (load_pmu || (vcpu->arch.hfscr & HFSCR_PM)) { + mtspr(SPRN_PMC1, vcpu->arch.pmc[0]); + mtspr(SPRN_PMC2, vcpu->arch.pmc[1]); + mtspr(SPRN_PMC3, vcpu->arch.pmc[2]); + mtspr(SPRN_PMC4, vcpu->arch.pmc[3]); + mtspr(SPRN_PMC5, vcpu->arch.pmc[4]); + mtspr(SPRN_PMC6, vcpu->arch.pmc[5]); + mtspr(SPRN_MMCR1, vcpu->arch.mmcr[1]); + mtspr(SPRN_MMCR2, vcpu->arch.mmcr[2]); + mtspr(SPRN_SDAR, vcpu->arch.sdar); + mtspr(SPRN_SIAR, vcpu->arch.siar); + mtspr(SPRN_SIER, vcpu->arch.sier[0]); + + if (cpu_has_feature(CPU_FTR_ARCH_31)) { + mtspr(SPRN_MMCR3, vcpu->arch.mmcr[3]); + mtspr(SPRN_SIER2, vcpu->arch.sier[1]); + mtspr(SPRN_SIER3, vcpu->arch.sier[2]); + } + + /* Set MMCRA then MMCR0 last */ + mtspr(SPRN_MMCRA, vcpu->arch.mmcra); + mtspr(SPRN_MMCR0, vcpu->arch.mmcr[0]); + /* No isync necessary because we're starting counters */ + + if (!vcpu->arch.nested && + (vcpu->arch.hfscr_permitted & HFSCR_PM)) + vcpu->arch.hfscr |= HFSCR_PM; + } +} +EXPORT_SYMBOL_GPL(switch_pmu_to_guest); + +void switch_pmu_to_host(struct kvm_vcpu *vcpu, + struct p9_host_os_sprs *host_os_sprs) +{ + struct lppaca *lp; + int save_pmu = 1; + + lp = vcpu->arch.vpa.pinned_addr; + if (lp) + save_pmu = lp->pmcregs_in_use; + if (IS_ENABLED(CONFIG_KVM_BOOK3S_HV_NESTED_PMU_WORKAROUND)) { + /* + * Save pmu if this guest is capable of running nested guests. + * This is option is for old L1s that do not set their + * lppaca->pmcregs_in_use properly when entering their L2. + */ + save_pmu |= nesting_enabled(vcpu->kvm); + } + + if (save_pmu) { + vcpu->arch.mmcr[0] = mfspr(SPRN_MMCR0); + vcpu->arch.mmcra = mfspr(SPRN_MMCRA); + + freeze_pmu(vcpu->arch.mmcr[0], vcpu->arch.mmcra); + + vcpu->arch.pmc[0] = mfspr(SPRN_PMC1); + vcpu->arch.pmc[1] = mfspr(SPRN_PMC2); + vcpu->arch.pmc[2] = mfspr(SPRN_PMC3); + vcpu->arch.pmc[3] = mfspr(SPRN_PMC4); + vcpu->arch.pmc[4] = mfspr(SPRN_PMC5); + vcpu->arch.pmc[5] = mfspr(SPRN_PMC6); + vcpu->arch.mmcr[1] = mfspr(SPRN_MMCR1); + vcpu->arch.mmcr[2] = mfspr(SPRN_MMCR2); + vcpu->arch.sdar = mfspr(SPRN_SDAR); + vcpu->arch.siar = mfspr(SPRN_SIAR); + vcpu->arch.sier[0] = mfspr(SPRN_SIER); + + if (cpu_has_feature(CPU_FTR_ARCH_31)) { + vcpu->arch.mmcr[3] = mfspr(SPRN_MMCR3); + vcpu->arch.sier[1] = mfspr(SPRN_SIER2); + vcpu->arch.sier[2] = mfspr(SPRN_SIER3); + } + + } else if (vcpu->arch.hfscr & HFSCR_PM) { + /* + * The guest accessed PMC SPRs without specifying they should + * be preserved, or it cleared pmcregs_in_use after the last + * access. Just ensure they are frozen. + */ + freeze_pmu(mfspr(SPRN_MMCR0), mfspr(SPRN_MMCRA)); + + /* + * Demand-fault PMU register access in the guest. + * + * This is used to grab the guest's VPA pmcregs_in_use value + * and reflect it into the host's VPA in the case of a nested + * hypervisor. + * + * It also avoids having to zero-out SPRs after each guest + * exit to avoid side-channels when. + * + * This is cleared here when we exit the guest, so later HFSCR + * interrupt handling can add it back to run the guest with + * PM enabled next time. + */ + if (!vcpu->arch.nested) + vcpu->arch.hfscr &= ~HFSCR_PM; + } /* otherwise the PMU should still be frozen */ + +#ifdef CONFIG_PPC_PSERIES + if (kvmhv_on_pseries()) { + barrier(); + get_lppaca()->pmcregs_in_use = ppc_get_pmu_inuse(); + barrier(); + } +#endif + + if (ppc_get_pmu_inuse()) { + mtspr(SPRN_PMC1, host_os_sprs->pmc1); + mtspr(SPRN_PMC2, host_os_sprs->pmc2); + mtspr(SPRN_PMC3, host_os_sprs->pmc3); + mtspr(SPRN_PMC4, host_os_sprs->pmc4); + mtspr(SPRN_PMC5, host_os_sprs->pmc5); + mtspr(SPRN_PMC6, host_os_sprs->pmc6); + mtspr(SPRN_MMCR1, host_os_sprs->mmcr1); + mtspr(SPRN_MMCR2, host_os_sprs->mmcr2); + mtspr(SPRN_SDAR, host_os_sprs->sdar); + mtspr(SPRN_SIAR, host_os_sprs->siar); + mtspr(SPRN_SIER, host_os_sprs->sier1); + + if (cpu_has_feature(CPU_FTR_ARCH_31)) { + mtspr(SPRN_MMCR3, host_os_sprs->mmcr3); + mtspr(SPRN_SIER2, host_os_sprs->sier2); + mtspr(SPRN_SIER3, host_os_sprs->sier3); + } + + /* Set MMCRA then MMCR0 last */ + mtspr(SPRN_MMCRA, host_os_sprs->mmcra); + mtspr(SPRN_MMCR0, host_os_sprs->mmcr0); + isync(); + } +} +EXPORT_SYMBOL_GPL(switch_pmu_to_host); diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index 0fc0e68d20d0..7ded202bf995 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -237,14 +237,14 @@ kvm_novcpu_wakeup: cmpdi r4, 0 beq kvmppc_primary_no_guest -#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING +#ifdef CONFIG_KVM_BOOK3S_HV_P8_TIMING addi r3, r4, VCPU_TB_RMENTRY bl kvmhv_start_timing #endif b kvmppc_got_guest kvm_novcpu_exit: -#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING +#ifdef CONFIG_KVM_BOOK3S_HV_P8_TIMING ld r4, HSTATE_KVM_VCPU(r13) cmpdi r4, 0 beq 13f @@ -523,7 +523,7 @@ kvmppc_hv_entry: li r6, KVM_GUEST_MODE_HOST_HV stb r6, HSTATE_IN_GUEST(r13) -#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING +#ifdef CONFIG_KVM_BOOK3S_HV_P8_TIMING /* Store initial timestamp */ cmpdi r4, 0 beq 1f @@ -894,7 +894,7 @@ fast_guest_return: li r9, KVM_GUEST_MODE_GUEST_HV stb r9, HSTATE_IN_GUEST(r13) -#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING +#ifdef CONFIG_KVM_BOOK3S_HV_P8_TIMING /* Accumulate timing */ addi r3, r4, VCPU_TB_GUEST bl kvmhv_accumulate_time @@ -945,7 +945,7 @@ secondary_too_late: cmpdi r4, 0 beq 11f stw r12, VCPU_TRAP(r4) -#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING +#ifdef CONFIG_KVM_BOOK3S_HV_P8_TIMING addi r3, r4, VCPU_TB_RMEXIT bl kvmhv_accumulate_time #endif @@ -959,7 +959,7 @@ hdec_soon: li r12, BOOK3S_INTERRUPT_HV_DECREMENTER 12: stw r12, VCPU_TRAP(r4) mr r9, r4 -#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING +#ifdef CONFIG_KVM_BOOK3S_HV_P8_TIMING addi r3, r4, VCPU_TB_RMEXIT bl kvmhv_accumulate_time #endif @@ -1056,7 +1056,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) li r0, MSR_RI mtmsrd r0, 1 -#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING +#ifdef CONFIG_KVM_BOOK3S_HV_P8_TIMING addi r3, r9, VCPU_TB_RMINTR mr r4, r9 bl kvmhv_accumulate_time @@ -1135,7 +1135,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) guest_exit_cont: /* r9 = vcpu, r12 = trap, r13 = paca */ -#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING +#ifdef CONFIG_KVM_BOOK3S_HV_P8_TIMING addi r3, r9, VCPU_TB_RMEXIT mr r4, r9 bl kvmhv_accumulate_time @@ -1495,7 +1495,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) mtspr SPRN_LPCR,r8 isync -#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING +#ifdef CONFIG_KVM_BOOK3S_HV_P8_TIMING /* Finish timing, if we have a vcpu */ ld r4, HSTATE_KVM_VCPU(r13) cmpdi r4, 0 @@ -2153,7 +2153,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_TM) ld r4, HSTATE_KVM_VCPU(r13) std r3, VCPU_DEC_EXPIRES(r4) -#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING +#ifdef CONFIG_KVM_BOOK3S_HV_P8_TIMING ld r4, HSTATE_KVM_VCPU(r13) addi r3, r4, VCPU_TB_CEDE bl kvmhv_accumulate_time @@ -2221,7 +2221,7 @@ kvm_end_cede: /* get vcpu pointer */ ld r4, HSTATE_KVM_VCPU(r13) -#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING +#ifdef CONFIG_KVM_BOOK3S_HV_P8_TIMING addi r3, r4, VCPU_TB_RMINTR bl kvmhv_accumulate_time #endif @@ -2961,7 +2961,7 @@ kvmppc_fix_pmao: isync blr -#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING +#ifdef CONFIG_KVM_BOOK3S_HV_P8_TIMING /* * Start timing an activity * r3 = pointer to time accumulation struct, r4 = vcpu diff --git a/arch/powerpc/kvm/book3s_xics.h b/arch/powerpc/kvm/book3s_xics.h index 8e4c79e2fcd8..08fb0843faf5 100644 --- a/arch/powerpc/kvm/book3s_xics.h +++ b/arch/powerpc/kvm/book3s_xics.h @@ -143,6 +143,7 @@ static inline struct kvmppc_ics *kvmppc_xics_find_ics(struct kvmppc_xics *xics, } extern unsigned long xics_rm_h_xirr(struct kvm_vcpu *vcpu); +extern unsigned long xics_rm_h_xirr_x(struct kvm_vcpu *vcpu); extern int xics_rm_h_ipi(struct kvm_vcpu *vcpu, unsigned long server, unsigned long mfrr); extern int xics_rm_h_cppr(struct kvm_vcpu *vcpu, unsigned long cppr); diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 191992fcb2c2..fb1490761c87 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -33,6 +33,7 @@ #include <asm/plpar_wrappers.h> #endif #include <asm/ultravisor.h> +#include <asm/setup.h> #include "timing.h" #include "irq.h" diff --git a/arch/powerpc/kvm/trace_hv.h b/arch/powerpc/kvm/trace_hv.h index 32e2cb5811cc..8d57c8428531 100644 --- a/arch/powerpc/kvm/trace_hv.h +++ b/arch/powerpc/kvm/trace_hv.h @@ -94,6 +94,7 @@ {H_GET_HCA_INFO, "H_GET_HCA_INFO"}, \ {H_GET_PERF_COUNT, "H_GET_PERF_COUNT"}, \ {H_MANAGE_TRACE, "H_MANAGE_TRACE"}, \ + {H_GET_CPU_CHARACTERISTICS, "H_GET_CPU_CHARACTERISTICS"}, \ {H_FREE_LOGICAL_LAN_BUFFER, "H_FREE_LOGICAL_LAN_BUFFER"}, \ {H_QUERY_INT_STATE, "H_QUERY_INT_STATE"}, \ {H_POLL_PENDING, "H_POLL_PENDING"}, \ @@ -125,7 +126,25 @@ {H_COP, "H_COP"}, \ {H_GET_MPP_X, "H_GET_MPP_X"}, \ {H_SET_MODE, "H_SET_MODE"}, \ - {H_RTAS, "H_RTAS"} + {H_REGISTER_PROC_TBL, "H_REGISTER_PROC_TBL"}, \ + {H_QUERY_VAS_CAPABILITIES, "H_QUERY_VAS_CAPABILITIES"}, \ + {H_INT_GET_SOURCE_INFO, "H_INT_GET_SOURCE_INFO"}, \ + {H_INT_SET_SOURCE_CONFIG, "H_INT_SET_SOURCE_CONFIG"}, \ + {H_INT_GET_QUEUE_INFO, "H_INT_GET_QUEUE_INFO"}, \ + {H_INT_SET_QUEUE_CONFIG, "H_INT_SET_QUEUE_CONFIG"}, \ + {H_INT_ESB, "H_INT_ESB"}, \ + {H_INT_RESET, "H_INT_RESET"}, \ + {H_RPT_INVALIDATE, "H_RPT_INVALIDATE"}, \ + {H_RTAS, "H_RTAS"}, \ + {H_LOGICAL_MEMOP, "H_LOGICAL_MEMOP"}, \ + {H_CAS, "H_CAS"}, \ + {H_UPDATE_DT, "H_UPDATE_DT"}, \ + {H_GET_PERF_COUNTER_INFO, "H_GET_PERF_COUNTER_INFO"}, \ + {H_SET_PARTITION_TABLE, "H_SET_PARTITION_TABLE"}, \ + {H_ENTER_NESTED, "H_ENTER_NESTED"}, \ + {H_TLB_INVALIDATE, "H_TLB_INVALIDATE"}, \ + {H_COPY_TOFROM_GUEST, "H_COPY_TOFROM_GUEST"} + #define kvm_trace_symbol_kvmret \ {RESUME_GUEST, "RESUME_GUEST"}, \ diff --git a/arch/powerpc/lib/test_emulate_step.c b/arch/powerpc/lib/test_emulate_step.c index 4f141daafcff..23c7805fb7b3 100644 --- a/arch/powerpc/lib/test_emulate_step.c +++ b/arch/powerpc/lib/test_emulate_step.c @@ -53,9 +53,6 @@ ppc_inst_prefix(PPC_PREFIX_MLS | __PPC_PRFX_R(pr) | IMM_H(i), \ PPC_RAW_ADDI(t, a, i)) -#define TEST_SETB(t, bfa) ppc_inst(PPC_INST_SETB | ___PPC_RT(t) | ___PPC_RA((bfa & 0x7) << 2)) - - static void __init init_pt_regs(struct pt_regs *regs) { static unsigned long msr; @@ -935,21 +932,21 @@ static struct compute_test compute_tests[] = { .subtests = { { .descr = "BFA = 1, CR = GT", - .instr = TEST_SETB(20, 1), + .instr = ppc_inst(PPC_RAW_SETB(20, 1)), .regs = { .ccr = 0x4000000, } }, { .descr = "BFA = 4, CR = LT", - .instr = TEST_SETB(20, 4), + .instr = ppc_inst(PPC_RAW_SETB(20, 4)), .regs = { .ccr = 0x8000, } }, { .descr = "BFA = 5, CR = EQ", - .instr = TEST_SETB(20, 5), + .instr = ppc_inst(PPC_RAW_SETB(20, 5)), .regs = { .ccr = 0x200, } @@ -1616,11 +1613,11 @@ static int __init emulate_compute_instr(struct pt_regs *regs, if (analysed != 1 || GETTYPE(op.type) != COMPUTE) { if (negative) return -EFAULT; - pr_info("emulation failed, instruction = %s\n", ppc_inst_as_str(instr)); + pr_info("emulation failed, instruction = %08lx\n", ppc_inst_as_ulong(instr)); return -EFAULT; } if (analysed == 1 && negative) - pr_info("negative test failed, instruction = %s\n", ppc_inst_as_str(instr)); + pr_info("negative test failed, instruction = %08lx\n", ppc_inst_as_ulong(instr)); if (!negative) emulate_update_regs(regs, &op); return 0; @@ -1637,7 +1634,7 @@ static int __init execute_compute_instr(struct pt_regs *regs, /* Patch the NOP with the actual instruction */ patch_instruction_site(&patch__exec_instr, instr); if (exec_instr(regs)) { - pr_info("execution failed, instruction = %s\n", ppc_inst_as_str(instr)); + pr_info("execution failed, instruction = %08lx\n", ppc_inst_as_ulong(instr)); return -EFAULT; } diff --git a/arch/powerpc/mm/book3s32/mmu.c b/arch/powerpc/mm/book3s32/mmu.c index 49a737fbbd18..a96b73006dfb 100644 --- a/arch/powerpc/mm/book3s32/mmu.c +++ b/arch/powerpc/mm/book3s32/mmu.c @@ -159,9 +159,12 @@ unsigned long __init mmu_mapin_ram(unsigned long base, unsigned long top) { unsigned long done; unsigned long border = (unsigned long)__init_begin - PAGE_OFFSET; + unsigned long size; + size = roundup_pow_of_two((unsigned long)_einittext - PAGE_OFFSET); + setibat(0, PAGE_OFFSET, 0, size, PAGE_KERNEL_X); - if (debug_pagealloc_enabled_or_kfence() || __map_without_bats) { + if (debug_pagealloc_enabled_or_kfence()) { pr_debug_once("Read-Write memory mapped without BATs\n"); if (base >= border) return base; @@ -245,10 +248,9 @@ void mmu_mark_rodata_ro(void) } /* - * Set up one of the I/D BAT (block address translation) register pairs. + * Set up one of the D BAT (block address translation) register pairs. * The parameters are not checked; in particular size must be a power * of 2 between 128k and 256M. - * On 603+, only set IBAT when _PAGE_EXEC is set */ void __init setbat(int index, unsigned long virt, phys_addr_t phys, unsigned int size, pgprot_t prot) @@ -284,10 +286,6 @@ void __init setbat(int index, unsigned long virt, phys_addr_t phys, /* G bit must be zero in IBATs */ flags &= ~_PAGE_EXEC; } - if (flags & _PAGE_EXEC) - bat[0] = bat[1]; - else - bat[0].batu = bat[0].batl = 0; bat_addrs[index].start = virt; bat_addrs[index].limit = virt + ((bl + 1) << 17) - 1; diff --git a/arch/powerpc/mm/book3s64/hash_pgtable.c b/arch/powerpc/mm/book3s64/hash_pgtable.c index 2e0cad5817ba..ae008b9df0e6 100644 --- a/arch/powerpc/mm/book3s64/hash_pgtable.c +++ b/arch/powerpc/mm/book3s64/hash_pgtable.c @@ -13,6 +13,7 @@ #include <asm/sections.h> #include <asm/mmu.h> #include <asm/tlb.h> +#include <asm/firmware.h> #include <mm/mmu_decl.h> diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c index fc92613dc2bf..363a9447d63d 100644 --- a/arch/powerpc/mm/book3s64/hash_utils.c +++ b/arch/powerpc/mm/book3s64/hash_utils.c @@ -408,7 +408,7 @@ repeat: ssize); if (ret == -1) { /* - * Try to to keep bolted entries in primary. + * Try to keep bolted entries in primary. * Remove non bolted entries and try insert again */ ret = mmu_hash_ops.hpte_remove(hpteg); diff --git a/arch/powerpc/mm/book3s64/pkeys.c b/arch/powerpc/mm/book3s64/pkeys.c index 753e62ba67af..1d2675ab6711 100644 --- a/arch/powerpc/mm/book3s64/pkeys.c +++ b/arch/powerpc/mm/book3s64/pkeys.c @@ -10,6 +10,7 @@ #include <asm/mmu.h> #include <asm/setup.h> #include <asm/smp.h> +#include <asm/firmware.h> #include <linux/pkeys.h> #include <linux/of_fdt.h> diff --git a/arch/powerpc/mm/book3s64/radix_hugetlbpage.c b/arch/powerpc/mm/book3s64/radix_hugetlbpage.c index d2fb776febb4..5e3195568525 100644 --- a/arch/powerpc/mm/book3s64/radix_hugetlbpage.c +++ b/arch/powerpc/mm/book3s64/radix_hugetlbpage.c @@ -48,11 +48,13 @@ void radix__huge_ptep_modify_prot_commit(struct vm_area_struct *vma, struct mm_struct *mm = vma->vm_mm; /* - * To avoid NMMU hang while relaxing access we need to flush the tlb before - * we set the new value. + * POWER9 NMMU must flush the TLB after clearing the PTE before + * installing a PTE with more relaxed access permissions, see + * radix__ptep_set_access_flags. */ - if (is_pte_rw_upgrade(pte_val(old_pte), pte_val(pte)) && - (atomic_read(&mm->context.copros) > 0)) + if (!cpu_has_feature(CPU_FTR_ARCH_31) && + is_pte_rw_upgrade(pte_val(old_pte), pte_val(pte)) && + atomic_read(&mm->context.copros) > 0) radix__flush_hugetlb_page(vma, addr); set_huge_pte_at(vma->vm_mm, addr, ptep, pte); diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c index db2f3d193448..698274109c91 100644 --- a/arch/powerpc/mm/book3s64/radix_pgtable.c +++ b/arch/powerpc/mm/book3s64/radix_pgtable.c @@ -1018,16 +1018,21 @@ void radix__ptep_set_access_flags(struct vm_area_struct *vma, pte_t *ptep, unsigned long change = pte_val(entry) ^ pte_val(*ptep); /* - * To avoid NMMU hang while relaxing access, we need mark - * the pte invalid in between. + * On POWER9, the NMMU is not able to relax PTE access permissions + * for a translation with a TLB. The PTE must be invalidated, TLB + * flushed before the new PTE is installed. + * + * This only needs to be done for radix, because hash translation does + * flush when updating the linux pte (and we don't support NMMU + * accelerators on HPT on POWER9 anyway XXX: do we?). + * + * POWER10 (and P9P) NMMU does behave as per ISA. */ - if ((change & _PAGE_RW) && atomic_read(&mm->context.copros) > 0) { + if (!cpu_has_feature(CPU_FTR_ARCH_31) && (change & _PAGE_RW) && + atomic_read(&mm->context.copros) > 0) { unsigned long old_pte, new_pte; old_pte = __radix_pte_update(ptep, _PAGE_PRESENT, _PAGE_INVALID); - /* - * new value of pte - */ new_pte = old_pte | set; radix__flush_tlb_page_psize(mm, address, psize); __radix_pte_update(ptep, _PAGE_INVALID, new_pte); @@ -1035,9 +1040,12 @@ void radix__ptep_set_access_flags(struct vm_area_struct *vma, pte_t *ptep, __radix_pte_update(ptep, 0, set); /* * Book3S does not require a TLB flush when relaxing access - * restrictions when the address space is not attached to a - * NMMU, because the core MMU will reload the pte after taking - * an access fault, which is defined by the architecture. + * restrictions when the address space (modulo the POWER9 nest + * MMU issue above) because the MMU will reload the PTE after + * taking an access fault, as defined by the architecture. See + * "Setting a Reference or Change Bit or Upgrading Access + * Authority (PTE Subject to Atomic Hardware Updates)" in + * Power ISA Version 3.1B. */ } /* See ptesync comment in radix__set_pte_at */ @@ -1050,11 +1058,12 @@ void radix__ptep_modify_prot_commit(struct vm_area_struct *vma, struct mm_struct *mm = vma->vm_mm; /* - * To avoid NMMU hang while relaxing access we need to flush the tlb before - * we set the new value. We need to do this only for radix, because hash - * translation does flush when updating the linux pte. + * POWER9 NMMU must flush the TLB after clearing the PTE before + * installing a PTE with more relaxed access permissions, see + * radix__ptep_set_access_flags. */ - if (is_pte_rw_upgrade(pte_val(old_pte), pte_val(pte)) && + if (!cpu_has_feature(CPU_FTR_ARCH_31) && + is_pte_rw_upgrade(pte_val(old_pte), pte_val(pte)) && (atomic_read(&mm->context.copros) > 0)) radix__flush_tlb_page(vma, addr); diff --git a/arch/powerpc/mm/book3s64/radix_tlb.c b/arch/powerpc/mm/book3s64/radix_tlb.c index dda51fef2d2e..4e29b619578c 100644 --- a/arch/powerpc/mm/book3s64/radix_tlb.c +++ b/arch/powerpc/mm/book3s64/radix_tlb.c @@ -755,10 +755,18 @@ EXPORT_SYMBOL(radix__local_flush_tlb_page); static bool mm_needs_flush_escalation(struct mm_struct *mm) { /* - * P9 nest MMU has issues with the page walk cache - * caching PTEs and not flushing them properly when - * RIC = 0 for a PID/LPID invalidate + * The P9 nest MMU has issues with the page walk cache caching PTEs + * and not flushing them when RIC = 0 for a PID/LPID invalidate. + * + * This may have been fixed in shipping firmware (by disabling PWC + * or preventing it from caching PTEs), but until that is confirmed, + * this workaround is required - escalate all RIC=0 IS=1/2/3 flushes + * to RIC=2. + * + * POWER10 (and P9P) does not have this problem. */ + if (cpu_has_feature(CPU_FTR_ARCH_31)) + return false; if (atomic_read(&mm->context.copros) > 0) return true; return false; diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index b282af39fcf6..bc84a594ca62 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -24,6 +24,7 @@ #include <asm/setup.h> #include <asm/hugetlb.h> #include <asm/pte-walk.h> +#include <asm/firmware.h> bool hugetlb_disabled = false; diff --git a/arch/powerpc/mm/init_32.c b/arch/powerpc/mm/init_32.c index 693a3a7a9463..62d9af6606cd 100644 --- a/arch/powerpc/mm/init_32.c +++ b/arch/powerpc/mm/init_32.c @@ -69,44 +69,10 @@ EXPORT_SYMBOL(agp_special_page); void MMU_init(void); -/* - * this tells the system to map all of ram with the segregs - * (i.e. page tables) instead of the bats. - * -- Cort - */ -int __map_without_bats; -int __map_without_ltlbs; - /* max amount of low RAM to map in */ unsigned long __max_low_memory = MAX_LOW_MEM; /* - * Check for command-line options that affect what MMU_init will do. - */ -static void __init MMU_setup(void) -{ - /* Check for nobats option (used in mapin_ram). */ - if (strstr(boot_command_line, "nobats")) { - __map_without_bats = 1; - } - - if (strstr(boot_command_line, "noltlbs")) { - __map_without_ltlbs = 1; - } - if (IS_ENABLED(CONFIG_PPC_8xx)) - return; - - if (IS_ENABLED(CONFIG_KFENCE)) - __map_without_ltlbs = 1; - - if (debug_pagealloc_enabled()) - __map_without_ltlbs = 1; - - if (strict_kernel_rwx_enabled()) - __map_without_ltlbs = 1; -} - -/* * MMU_init sets up the basic memory mappings for the kernel, * including both RAM and possibly some I/O regions, * and sets up the page tables and the MMU hardware ready to go. @@ -116,9 +82,6 @@ void __init MMU_init(void) if (ppc_md.progress) ppc_md.progress("MMU:enter", 0x111); - /* parse args from command line */ - MMU_setup(); - /* * Reserve gigantic pages for hugetlb. This MUST occur before * lowmem_end_addr is initialized below. diff --git a/arch/powerpc/mm/kasan/Makefile b/arch/powerpc/mm/kasan/Makefile index 4999aadb1867..699eeffd9f55 100644 --- a/arch/powerpc/mm/kasan/Makefile +++ b/arch/powerpc/mm/kasan/Makefile @@ -6,3 +6,4 @@ obj-$(CONFIG_PPC32) += init_32.o obj-$(CONFIG_PPC_8xx) += 8xx.o obj-$(CONFIG_PPC_BOOK3S_32) += book3s_32.o obj-$(CONFIG_PPC_BOOK3S_64) += init_book3s_64.o +obj-$(CONFIG_PPC_BOOK3E_64) += init_book3e_64.o diff --git a/arch/powerpc/mm/kasan/init_32.c b/arch/powerpc/mm/kasan/init_32.c index f3e4d069e0ba..a70828a6d935 100644 --- a/arch/powerpc/mm/kasan/init_32.c +++ b/arch/powerpc/mm/kasan/init_32.c @@ -25,7 +25,7 @@ static void __init kasan_populate_pte(pte_t *ptep, pgprot_t prot) int i; for (i = 0; i < PTRS_PER_PTE; i++, ptep++) - __set_pte_at(&init_mm, va, ptep, pfn_pte(PHYS_PFN(pa), prot), 0); + __set_pte_at(&init_mm, va, ptep, pfn_pte(PHYS_PFN(pa), prot), 1); } int __init kasan_init_shadow_page_tables(unsigned long k_start, unsigned long k_end) diff --git a/arch/powerpc/mm/kasan/init_book3e_64.c b/arch/powerpc/mm/kasan/init_book3e_64.c new file mode 100644 index 000000000000..11519e88dc6b --- /dev/null +++ b/arch/powerpc/mm/kasan/init_book3e_64.c @@ -0,0 +1,133 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * KASAN for 64-bit Book3e powerpc + * + * Copyright 2022, Christophe Leroy, CS GROUP France + */ + +#define DISABLE_BRANCH_PROFILING + +#include <linux/kasan.h> +#include <linux/printk.h> +#include <linux/memblock.h> +#include <linux/set_memory.h> + +#include <asm/pgalloc.h> + +static inline bool kasan_pud_table(p4d_t p4d) +{ + return p4d_page(p4d) == virt_to_page(lm_alias(kasan_early_shadow_pud)); +} + +static inline bool kasan_pmd_table(pud_t pud) +{ + return pud_page(pud) == virt_to_page(lm_alias(kasan_early_shadow_pmd)); +} + +static inline bool kasan_pte_table(pmd_t pmd) +{ + return pmd_page(pmd) == virt_to_page(lm_alias(kasan_early_shadow_pte)); +} + +static int __init kasan_map_kernel_page(unsigned long ea, unsigned long pa, pgprot_t prot) +{ + pgd_t *pgdp; + p4d_t *p4dp; + pud_t *pudp; + pmd_t *pmdp; + pte_t *ptep; + + pgdp = pgd_offset_k(ea); + p4dp = p4d_offset(pgdp, ea); + if (kasan_pud_table(*p4dp)) { + pudp = memblock_alloc(PUD_TABLE_SIZE, PUD_TABLE_SIZE); + memcpy(pudp, kasan_early_shadow_pud, PUD_TABLE_SIZE); + p4d_populate(&init_mm, p4dp, pudp); + } + pudp = pud_offset(p4dp, ea); + if (kasan_pmd_table(*pudp)) { + pmdp = memblock_alloc(PMD_TABLE_SIZE, PMD_TABLE_SIZE); + memcpy(pmdp, kasan_early_shadow_pmd, PMD_TABLE_SIZE); + pud_populate(&init_mm, pudp, pmdp); + } + pmdp = pmd_offset(pudp, ea); + if (kasan_pte_table(*pmdp)) { + ptep = memblock_alloc(PTE_TABLE_SIZE, PTE_TABLE_SIZE); + memcpy(ptep, kasan_early_shadow_pte, PTE_TABLE_SIZE); + pmd_populate_kernel(&init_mm, pmdp, ptep); + } + ptep = pte_offset_kernel(pmdp, ea); + + __set_pte_at(&init_mm, ea, ptep, pfn_pte(pa >> PAGE_SHIFT, prot), 0); + + return 0; +} + +static void __init kasan_init_phys_region(void *start, void *end) +{ + unsigned long k_start, k_end, k_cur; + void *va; + + if (start >= end) + return; + + k_start = ALIGN_DOWN((unsigned long)kasan_mem_to_shadow(start), PAGE_SIZE); + k_end = ALIGN((unsigned long)kasan_mem_to_shadow(end), PAGE_SIZE); + + va = memblock_alloc(k_end - k_start, PAGE_SIZE); + for (k_cur = k_start; k_cur < k_end; k_cur += PAGE_SIZE, va += PAGE_SIZE) + kasan_map_kernel_page(k_cur, __pa(va), PAGE_KERNEL); +} + +void __init kasan_early_init(void) +{ + int i; + unsigned long addr; + pgd_t *pgd = pgd_offset_k(KASAN_SHADOW_START); + pte_t zero_pte = pfn_pte(virt_to_pfn(kasan_early_shadow_page), PAGE_KERNEL); + + BUILD_BUG_ON(!IS_ALIGNED(KASAN_SHADOW_START, PGDIR_SIZE)); + BUILD_BUG_ON(!IS_ALIGNED(KASAN_SHADOW_END, PGDIR_SIZE)); + + for (i = 0; i < PTRS_PER_PTE; i++) + __set_pte_at(&init_mm, (unsigned long)kasan_early_shadow_page, + &kasan_early_shadow_pte[i], zero_pte, 0); + + for (i = 0; i < PTRS_PER_PMD; i++) + pmd_populate_kernel(&init_mm, &kasan_early_shadow_pmd[i], + kasan_early_shadow_pte); + + for (i = 0; i < PTRS_PER_PUD; i++) + pud_populate(&init_mm, &kasan_early_shadow_pud[i], + kasan_early_shadow_pmd); + + for (addr = KASAN_SHADOW_START; addr != KASAN_SHADOW_END; addr += PGDIR_SIZE) + p4d_populate(&init_mm, p4d_offset(pgd++, addr), kasan_early_shadow_pud); +} + +void __init kasan_init(void) +{ + phys_addr_t start, end; + u64 i; + pte_t zero_pte = pfn_pte(virt_to_pfn(kasan_early_shadow_page), PAGE_KERNEL_RO); + + for_each_mem_range(i, &start, &end) + kasan_init_phys_region((void *)start, (void *)end); + + if (IS_ENABLED(CONFIG_KASAN_VMALLOC)) + kasan_remove_zero_shadow((void *)VMALLOC_START, VMALLOC_SIZE); + + for (i = 0; i < PTRS_PER_PTE; i++) + __set_pte_at(&init_mm, (unsigned long)kasan_early_shadow_page, + &kasan_early_shadow_pte[i], zero_pte, 0); + + flush_tlb_kernel_range(KASAN_SHADOW_START, KASAN_SHADOW_END); + + memset(kasan_early_shadow_page, 0, PAGE_SIZE); + + /* Enable error messages */ + init_task.kasan_depth = 0; + pr_info("KASAN init done\n"); +} + +void __init kasan_late_init(void) { } diff --git a/arch/powerpc/mm/kasan/init_book3s_64.c b/arch/powerpc/mm/kasan/init_book3s_64.c index 0da5566d6b84..9300d641cf9a 100644 --- a/arch/powerpc/mm/kasan/init_book3s_64.c +++ b/arch/powerpc/mm/kasan/init_book3s_64.c @@ -99,4 +99,6 @@ void __init kasan_init(void) pr_info("KASAN init done\n"); } +void __init kasan_early_init(void) { } + void __init kasan_late_init(void) { } diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index a97128a48817..7b0d286bf9ba 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -25,6 +25,7 @@ #include <asm/mmzone.h> #include <asm/ftrace.h> #include <asm/code-patching.h> +#include <asm/setup.h> #include <mm/mmu_decl.h> diff --git a/arch/powerpc/mm/mmu_decl.h b/arch/powerpc/mm/mmu_decl.h index 63c4b1a4d435..229c72e49198 100644 --- a/arch/powerpc/mm/mmu_decl.h +++ b/arch/powerpc/mm/mmu_decl.h @@ -92,7 +92,6 @@ extern void mapin_ram(void); extern void setbat(int index, unsigned long virt, phys_addr_t phys, unsigned int size, pgprot_t prot); -extern int __map_without_bats; extern unsigned int rtas_data, rtas_size; struct hash_pte; diff --git a/arch/powerpc/mm/nohash/40x.c b/arch/powerpc/mm/nohash/40x.c index b32e465a3d52..3684d6e570fb 100644 --- a/arch/powerpc/mm/nohash/40x.c +++ b/arch/powerpc/mm/nohash/40x.c @@ -43,7 +43,6 @@ #include <mm/mmu_decl.h> -extern int __map_without_ltlbs; /* * MMU_init_hw does the chip-specific initialization of the MMU hardware. */ @@ -94,7 +93,13 @@ unsigned long __init mmu_mapin_ram(unsigned long base, unsigned long top) p = 0; s = total_lowmem; - if (__map_without_ltlbs) + if (IS_ENABLED(CONFIG_KFENCE)) + return 0; + + if (debug_pagealloc_enabled()) + return 0; + + if (strict_kernel_rwx_enabled()) return 0; while (s >= LARGE_PAGE_SIZE_16M) { diff --git a/arch/powerpc/mm/nohash/8xx.c b/arch/powerpc/mm/nohash/8xx.c index 27f9186ae374..dbbfe897455d 100644 --- a/arch/powerpc/mm/nohash/8xx.c +++ b/arch/powerpc/mm/nohash/8xx.c @@ -14,8 +14,6 @@ #define IMMR_SIZE (FIX_IMMR_SIZE << PAGE_SHIFT) -extern int __map_without_ltlbs; - static unsigned long block_mapped_ram; /* @@ -28,8 +26,6 @@ phys_addr_t v_block_mapped(unsigned long va) if (va >= VIRT_IMMR_BASE && va < VIRT_IMMR_BASE + IMMR_SIZE) return p + va - VIRT_IMMR_BASE; - if (__map_without_ltlbs) - return 0; if (va >= PAGE_OFFSET && va < PAGE_OFFSET + block_mapped_ram) return __pa(va); return 0; @@ -45,8 +41,6 @@ unsigned long p_block_mapped(phys_addr_t pa) if (pa >= p && pa < p + IMMR_SIZE) return VIRT_IMMR_BASE + pa - p; - if (__map_without_ltlbs) - return 0; if (pa < block_mapped_ram) return (unsigned long)__va(pa); return 0; @@ -153,9 +147,6 @@ unsigned long __init mmu_mapin_ram(unsigned long base, unsigned long top) mmu_mapin_immr(); - if (__map_without_ltlbs) - return 0; - mmu_mapin_ram_chunk(0, boundary, PAGE_KERNEL_TEXT, true); if (debug_pagealloc_enabled_or_kfence()) { top = boundary; @@ -179,8 +170,8 @@ void mmu_mark_initmem_nx(void) unsigned long boundary = strict_kernel_rwx_enabled() ? sinittext : etext8; unsigned long einittext8 = ALIGN(__pa(_einittext), SZ_8M); - mmu_mapin_ram_chunk(0, boundary, PAGE_KERNEL_TEXT, false); - mmu_mapin_ram_chunk(boundary, einittext8, PAGE_KERNEL, false); + if (!debug_pagealloc_enabled_or_kfence()) + mmu_mapin_ram_chunk(boundary, einittext8, PAGE_KERNEL, false); mmu_pin_tlb(block_mapped_ram, false); } diff --git a/arch/powerpc/mm/nohash/book3e_hugetlbpage.c b/arch/powerpc/mm/nohash/book3e_hugetlbpage.c index 307ca919d393..c7d4b317a823 100644 --- a/arch/powerpc/mm/nohash/book3e_hugetlbpage.c +++ b/arch/powerpc/mm/nohash/book3e_hugetlbpage.c @@ -103,21 +103,11 @@ static inline int book3e_tlb_exists(unsigned long ea, unsigned long pid) int found = 0; mtspr(SPRN_MAS6, pid << 16); - if (mmu_has_feature(MMU_FTR_USE_TLBRSRV)) { - asm volatile( - "li %0,0\n" - "tlbsx. 0,%1\n" - "bne 1f\n" - "li %0,1\n" - "1:\n" - : "=&r"(found) : "r"(ea)); - } else { - asm volatile( - "tlbsx 0,%1\n" - "mfspr %0,0x271\n" - "srwi %0,%0,31\n" - : "=&r"(found) : "r"(ea)); - } + asm volatile( + "tlbsx 0,%1\n" + "mfspr %0,0x271\n" + "srwi %0,%0,31\n" + : "=&r"(found) : "r"(ea)); return found; } @@ -169,13 +159,9 @@ book3e_hugetlb_preload(struct vm_area_struct *vma, unsigned long ea, pte_t pte) mtspr(SPRN_MAS1, mas1); mtspr(SPRN_MAS2, mas2); - if (mmu_has_feature(MMU_FTR_USE_PAIRED_MAS)) { - mtspr(SPRN_MAS7_MAS3, mas7_3); - } else { - if (mmu_has_feature(MMU_FTR_BIG_PHYS)) - mtspr(SPRN_MAS7, upper_32_bits(mas7_3)); - mtspr(SPRN_MAS3, lower_32_bits(mas7_3)); - } + if (mmu_has_feature(MMU_FTR_BIG_PHYS)) + mtspr(SPRN_MAS7, upper_32_bits(mas7_3)); + mtspr(SPRN_MAS3, lower_32_bits(mas7_3)); asm volatile ("tlbwe"); diff --git a/arch/powerpc/mm/nohash/tlb_low.S b/arch/powerpc/mm/nohash/tlb_low.S index dd39074de9af..d62b613a0d5d 100644 --- a/arch/powerpc/mm/nohash/tlb_low.S +++ b/arch/powerpc/mm/nohash/tlb_low.S @@ -186,7 +186,7 @@ _GLOBAL(_tlbivax_bcast) isync PPC_TLBIVAX(0, R3) isync - eieio + mbar tlbsync BEGIN_FTR_SECTION b 1f @@ -355,7 +355,7 @@ _GLOBAL(_tlbivax_bcast) rlwimi r4,r6,MAS6_SIND_SHIFT,MAS6_SIND 1: mtspr SPRN_MAS6,r4 /* assume AS=0 for now */ PPC_TLBIVAX(0,R3) - eieio + mbar tlbsync sync wrtee r10 diff --git a/arch/powerpc/mm/nohash/tlb_low_64e.S b/arch/powerpc/mm/nohash/tlb_low_64e.S index 8b97c4acfebf..68ffbfdba894 100644 --- a/arch/powerpc/mm/nohash/tlb_low_64e.S +++ b/arch/powerpc/mm/nohash/tlb_low_64e.S @@ -152,16 +152,7 @@ tlb_miss_common_bolted: clrrdi r15,r15,3 beq tlb_miss_fault_bolted /* No PGDIR, bail */ -BEGIN_MMU_FTR_SECTION - /* Set the TLB reservation and search for existing entry. Then load - * the entry. - */ - PPC_TLBSRX_DOT(0,R16) ldx r14,r14,r15 /* grab pgd entry */ - beq tlb_miss_done_bolted /* tlb exists already, bail */ -MMU_FTR_SECTION_ELSE - ldx r14,r14,r15 /* grab pgd entry */ -ALT_MMU_FTR_SECTION_END_IFSET(MMU_FTR_USE_TLBRSRV) rldicl r15,r16,64-PUD_SHIFT+3,64-PUD_INDEX_SIZE-3 clrrdi r15,r15,3 @@ -222,10 +213,11 @@ itlb_miss_kernel_bolted: tlb_miss_kernel_bolted: mfspr r10,SPRN_MAS1 ld r14,PACA_KERNELPGD(r13) - cmpldi cr0,r15,8 /* Check for vmalloc region */ + srdi r15,r16,44 /* get kernel region */ + andi. r15,r15,1 /* Check for vmalloc region */ rlwinm r10,r10,0,16,1 /* Clear TID */ mtspr SPRN_MAS1,r10 - beq+ tlb_miss_common_bolted + bne+ tlb_miss_common_bolted tlb_miss_fault_bolted: /* We need to check if it was an instruction miss */ @@ -507,7 +499,9 @@ tlb_miss_huge_e6500: tlb_miss_kernel_e6500: ld r14,PACA_KERNELPGD(r13) - cmpldi cr1,r15,8 /* Check for vmalloc region */ + srdi r15,r16,44 /* get kernel region */ + xoris r15,r15,0xc /* Check for vmalloc region */ + cmplwi cr1,r15,1 beq+ cr1,tlb_miss_common_e6500 tlb_miss_fault_e6500: @@ -541,16 +535,18 @@ itlb_miss_fault_e6500: */ mfspr r14,SPRN_ESR mfspr r16,SPRN_DEAR /* get faulting address */ - srdi r15,r16,60 /* get region */ - cmpldi cr0,r15,0xc /* linear mapping ? */ + srdi r15,r16,44 /* get region */ + xoris r15,r15,0xc + cmpldi cr0,r15,0 /* linear mapping ? */ beq tlb_load_linear /* yes -> go to linear map load */ + cmpldi cr1,r15,1 /* vmalloc mapping ? */ /* The page tables are mapped virtually linear. At this point, though, * we don't know whether we are trying to fault in a first level * virtual address or a virtual page table address. We can get that * from bit 0x1 of the region ID which we have set for a page table */ - andi. r10,r15,0x1 + andis. r10,r15,0x1 bne- virt_page_table_tlb_miss std r14,EX_TLB_ESR(r12); /* save ESR */ @@ -562,7 +558,7 @@ itlb_miss_fault_e6500: /* We do the user/kernel test for the PID here along with the RW test */ - cmpldi cr0,r15,0 /* Check for user region */ + srdi. r15,r16,60 /* Check for user region */ /* We pre-test some combination of permissions to avoid double * faults: @@ -583,13 +579,12 @@ itlb_miss_fault_e6500: */ rlwimi r11,r14,32-19,27,27 rlwimi r11,r14,32-16,19,19 - beq normal_tlb_miss + beq normal_tlb_miss_user /* XXX replace the RMW cycles with immediate loads + writes */ 1: mfspr r10,SPRN_MAS1 - cmpldi cr0,r15,8 /* Check for vmalloc region */ rlwinm r10,r10,0,16,1 /* Clear TID */ mtspr SPRN_MAS1,r10 - beq+ normal_tlb_miss + beq+ cr1,normal_tlb_miss /* We got a crappy address, just fault with whatever DEAR and ESR * are here @@ -615,27 +610,28 @@ itlb_miss_fault_e6500: * * Faulting address is SRR0 which is already in r16 */ - srdi r15,r16,60 /* get region */ - cmpldi cr0,r15,0xc /* linear mapping ? */ + srdi r15,r16,44 /* get region */ + xoris r15,r15,0xc + cmpldi cr0,r15,0 /* linear mapping ? */ beq tlb_load_linear /* yes -> go to linear map load */ + cmpldi cr1,r15,1 /* vmalloc mapping ? */ /* We do the user/kernel test for the PID here along with the RW test */ li r11,_PAGE_PRESENT|_PAGE_BAP_UX /* Base perm */ oris r11,r11,_PAGE_ACCESSED@h - cmpldi cr0,r15,0 /* Check for user region */ + srdi. r15,r16,60 /* Check for user region */ std r14,EX_TLB_ESR(r12) /* write crazy -1 to frame */ - beq normal_tlb_miss + beq normal_tlb_miss_user li r11,_PAGE_PRESENT|_PAGE_BAP_SX /* Base perm */ oris r11,r11,_PAGE_ACCESSED@h /* XXX replace the RMW cycles with immediate loads + writes */ mfspr r10,SPRN_MAS1 - cmpldi cr0,r15,8 /* Check for vmalloc region */ rlwinm r10,r10,0,16,1 /* Clear TID */ mtspr SPRN_MAS1,r10 - beq+ normal_tlb_miss + beq+ cr1,normal_tlb_miss /* We got a crappy address, just fault */ TLB_MISS_EPILOG_ERROR @@ -653,6 +649,12 @@ itlb_miss_fault_e6500: * r11 = PTE permission mask * r10 = crap (free to use) */ +normal_tlb_miss_user: +#ifdef CONFIG_PPC_KUAP + mfspr r14,SPRN_MAS1 + rlwinm. r14,r14,0,0x3fff0000 + beq- normal_tlb_miss_access_fault /* KUAP fault */ +#endif normal_tlb_miss: /* So we first construct the page table address. We do that by * shifting the bottom of the address (not the region ID) by @@ -662,32 +664,19 @@ normal_tlb_miss: * NOTE: For 64K pages, we do things slightly differently in * order to handle the weird page table format used by linux */ - ori r10,r15,0x1 + srdi r15,r16,44 + oris r10,r15,0x1 rldicl r14,r16,64-(PAGE_SHIFT-3),PAGE_SHIFT-3+4 - sldi r15,r10,60 - clrrdi r14,r14,3 + sldi r15,r10,44 + clrrdi r14,r14,19 or r10,r15,r14 -BEGIN_MMU_FTR_SECTION - /* Set the TLB reservation and search for existing entry. Then load - * the entry. - */ - PPC_TLBSRX_DOT(0,R16) - ld r14,0(r10) - beq normal_tlb_miss_done -MMU_FTR_SECTION_ELSE ld r14,0(r10) -ALT_MMU_FTR_SECTION_END_IFSET(MMU_FTR_USE_TLBRSRV) finish_normal_tlb_miss: /* Check if required permissions are met */ andc. r15,r11,r14 bne- normal_tlb_miss_access_fault -#ifdef CONFIG_PPC_KUAP - mfspr r11,SPRN_MAS1 - rlwinm. r10,r11,0,0x3fff0000 - beq- normal_tlb_miss_access_fault /* KUAP fault */ -#endif /* Now we build the MAS: * @@ -709,9 +698,7 @@ finish_normal_tlb_miss: rldicl r10,r14,64-8,64-8 cmpldi cr0,r10,BOOK3E_PAGESZ_4K beq- 1f -#ifndef CONFIG_PPC_KUAP mfspr r11,SPRN_MAS1 -#endif rlwimi r11,r14,31,21,24 rlwinm r11,r11,0,21,19 mtspr SPRN_MAS1,r11 @@ -728,13 +715,9 @@ finish_normal_tlb_miss: li r11,MAS3_SW|MAS3_UW andc r15,r15,r11 1: -BEGIN_MMU_FTR_SECTION srdi r16,r15,32 mtspr SPRN_MAS3,r15 mtspr SPRN_MAS7,r16 -MMU_FTR_SECTION_ELSE - mtspr SPRN_MAS7_MAS3,r15 -ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_USE_PAIRED_MAS) tlbwe @@ -786,6 +769,7 @@ normal_tlb_miss_access_fault: */ virt_page_table_tlb_miss: /* Are we hitting a kernel page table ? */ + srdi r15,r16,60 andi. r10,r15,0x8 /* The cool thing now is that r10 contains 0 for user and 8 for kernel, @@ -810,18 +794,12 @@ virt_page_table_tlb_miss: #else 1: #endif -BEGIN_MMU_FTR_SECTION - /* Search if we already have a TLB entry for that virtual address, and - * if we do, bail out. - */ - PPC_TLBSRX_DOT(0,R16) - beq virt_page_table_tlb_miss_done -END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_TLBRSRV) /* Now, we need to walk the page tables. First check if we are in * range. */ - rldicl. r10,r16,64-(VPTE_INDEX_SIZE+3),VPTE_INDEX_SIZE+3+4 + rldicl r10,r16,64-(VPTE_INDEX_SIZE+3),VPTE_INDEX_SIZE+3+4 + cmpldi r10,0x80 bne- virt_page_table_tlb_miss_fault /* Get the PGD pointer */ @@ -867,41 +845,12 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_TLBRSRV) clrldi r11,r15,4 /* remove region ID from RPN */ ori r10,r11,1 /* Or-in SR */ -BEGIN_MMU_FTR_SECTION srdi r16,r10,32 mtspr SPRN_MAS3,r10 mtspr SPRN_MAS7,r16 -MMU_FTR_SECTION_ELSE - mtspr SPRN_MAS7_MAS3,r10 -ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_USE_PAIRED_MAS) tlbwe -BEGIN_MMU_FTR_SECTION -virt_page_table_tlb_miss_done: - - /* We have overridden MAS2:EPN but currently our primary TLB miss - * handler will always restore it so that should not be an issue, - * if we ever optimize the primary handler to not write MAS2 on - * some cases, we'll have to restore MAS2:EPN here based on the - * original fault's DEAR. If we do that we have to modify the - * ITLB miss handler to also store SRR0 in the exception frame - * as DEAR. - * - * However, one nasty thing we did is we cleared the reservation - * (well, potentially we did). We do a trick here thus if we - * are not a level 0 exception (we interrupted the TLB miss) we - * offset the return address by -4 in order to replay the tlbsrx - * instruction there - */ - subf r10,r13,r12 - cmpldi cr0,r10,PACA_EXTLB+EX_TLB_SIZE - bne- 1f - ld r11,PACA_EXTLB+EX_TLB_SIZE+EX_TLB_SRR0(r13) - addi r10,r11,-4 - std r10,PACA_EXTLB+EX_TLB_SIZE+EX_TLB_SRR0(r13) -1: -END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_TLBRSRV) /* Return to caller, normal case */ TLB_MISS_EPILOG_SUCCESS rfi @@ -969,23 +918,24 @@ virt_page_table_tlb_miss_whacko_fault: */ mfspr r14,SPRN_ESR mfspr r16,SPRN_DEAR /* get faulting address */ - srdi r11,r16,60 /* get region */ - cmpldi cr0,r11,0xc /* linear mapping ? */ + srdi r11,r16,44 /* get region */ + xoris r11,r11,0xc + cmpldi cr0,r11,0 /* linear mapping ? */ beq tlb_load_linear /* yes -> go to linear map load */ + cmpldi cr1,r11,1 /* vmalloc mapping ? */ /* We do the user/kernel test for the PID here along with the RW test */ - cmpldi cr0,r11,0 /* Check for user region */ + srdi. r11,r16,60 /* Check for user region */ ld r15,PACAPGD(r13) /* Load user pgdir */ beq htw_tlb_miss /* XXX replace the RMW cycles with immediate loads + writes */ 1: mfspr r10,SPRN_MAS1 - cmpldi cr0,r11,8 /* Check for vmalloc region */ rlwinm r10,r10,0,16,1 /* Clear TID */ mtspr SPRN_MAS1,r10 ld r15,PACA_KERNELPGD(r13) /* Load kernel pgdir */ - beq+ htw_tlb_miss + beq+ cr1,htw_tlb_miss /* We got a crappy address, just fault with whatever DEAR and ESR * are here @@ -1011,19 +961,20 @@ virt_page_table_tlb_miss_whacko_fault: * * Faulting address is SRR0 which is already in r16 */ - srdi r11,r16,60 /* get region */ - cmpldi cr0,r11,0xc /* linear mapping ? */ + srdi r11,r16,44 /* get region */ + xoris r11,r11,0xc + cmpldi cr0,r11,0 /* linear mapping ? */ beq tlb_load_linear /* yes -> go to linear map load */ + cmpldi cr1,r11,1 /* vmalloc mapping ? */ /* We do the user/kernel test for the PID here along with the RW test */ - cmpldi cr0,r11,0 /* Check for user region */ + srdi. r11,r16,60 /* Check for user region */ ld r15,PACAPGD(r13) /* Load user pgdir */ beq htw_tlb_miss /* XXX replace the RMW cycles with immediate loads + writes */ 1: mfspr r10,SPRN_MAS1 - cmpldi cr0,r11,8 /* Check for vmalloc region */ rlwinm r10,r10,0,16,1 /* Clear TID */ mtspr SPRN_MAS1,r10 ld r15,PACA_KERNELPGD(r13) /* Load kernel pgdir */ @@ -1116,13 +1067,9 @@ htw_tlb_miss: */ ori r10,r15,(BOOK3E_PAGESZ_4K << MAS3_SPSIZE_SHIFT) -BEGIN_MMU_FTR_SECTION srdi r16,r10,32 mtspr SPRN_MAS3,r10 mtspr SPRN_MAS7,r16 -MMU_FTR_SECTION_ELSE - mtspr SPRN_MAS7_MAS3,r10 -ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_USE_PAIRED_MAS) tlbwe @@ -1203,13 +1150,9 @@ tlb_load_linear: clrldi r10,r10,4 /* clear region bits */ ori r10,r10,MAS3_SR|MAS3_SW|MAS3_SX -BEGIN_MMU_FTR_SECTION srdi r16,r10,32 mtspr SPRN_MAS3,r10 mtspr SPRN_MAS7,r16 -MMU_FTR_SECTION_ELSE - mtspr SPRN_MAS7_MAS3,r10 -ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_USE_PAIRED_MAS) tlbwe diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c index a56ade39dc68..3ac73f9fb5d5 100644 --- a/arch/powerpc/mm/pgtable_32.c +++ b/arch/powerpc/mm/pgtable_32.c @@ -135,9 +135,9 @@ void mark_initmem_nx(void) unsigned long numpages = PFN_UP((unsigned long)_einittext) - PFN_DOWN((unsigned long)_sinittext); - if (v_block_mapped((unsigned long)_sinittext)) { - mmu_mark_initmem_nx(); - } else { + mmu_mark_initmem_nx(); + + if (!v_block_mapped((unsigned long)_sinittext)) { set_memory_nx((unsigned long)_sinittext, numpages); set_memory_rw((unsigned long)_sinittext, numpages); } diff --git a/arch/powerpc/mm/ptdump/shared.c b/arch/powerpc/mm/ptdump/shared.c index 03607ab90c66..f884760ca5cf 100644 --- a/arch/powerpc/mm/ptdump/shared.c +++ b/arch/powerpc/mm/ptdump/shared.c @@ -17,9 +17,9 @@ static const struct flag_info flag_array[] = { .clear = " ", }, { .mask = _PAGE_RW, - .val = _PAGE_RW, - .set = "rw", - .clear = "r ", + .val = 0, + .set = "r ", + .clear = "rw", }, { .mask = _PAGE_EXEC, .val = _PAGE_EXEC, diff --git a/arch/powerpc/net/bpf_jit_comp32.c b/arch/powerpc/net/bpf_jit_comp32.c index e46ed1e8c6ca..43f1c76d48ce 100644 --- a/arch/powerpc/net/bpf_jit_comp32.c +++ b/arch/powerpc/net/bpf_jit_comp32.c @@ -294,8 +294,10 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context * u32 dst_reg_h = dst_reg - 1; u32 src_reg = bpf_to_ppc(insn[i].src_reg); u32 src_reg_h = src_reg - 1; + u32 ax_reg = bpf_to_ppc(BPF_REG_AX); u32 tmp_reg = bpf_to_ppc(TMP_REG); u32 size = BPF_SIZE(code); + u32 save_reg, ret_reg; s16 off = insn[i].off; s32 imm = insn[i].imm; bool func_addr_fixed; @@ -798,25 +800,71 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context * * BPF_STX ATOMIC (atomic ops) */ case BPF_STX | BPF_ATOMIC | BPF_W: - if (imm != BPF_ADD) { - pr_err_ratelimited("eBPF filter atomic op code %02x (@%d) unsupported\n", - code, i); - return -ENOTSUPP; - } - - /* *(u32 *)(dst + off) += src */ + save_reg = _R0; + ret_reg = src_reg; bpf_set_seen_register(ctx, tmp_reg); + bpf_set_seen_register(ctx, ax_reg); + /* Get offset into TMP_REG */ EMIT(PPC_RAW_LI(tmp_reg, off)); + tmp_idx = ctx->idx * 4; /* load value from memory into r0 */ EMIT(PPC_RAW_LWARX(_R0, tmp_reg, dst_reg, 0)); - /* add value from src_reg into this */ - EMIT(PPC_RAW_ADD(_R0, _R0, src_reg)); - /* store result back */ - EMIT(PPC_RAW_STWCX(_R0, tmp_reg, dst_reg)); + + /* Save old value in BPF_REG_AX */ + if (imm & BPF_FETCH) + EMIT(PPC_RAW_MR(ax_reg, _R0)); + + switch (imm) { + case BPF_ADD: + case BPF_ADD | BPF_FETCH: + EMIT(PPC_RAW_ADD(_R0, _R0, src_reg)); + break; + case BPF_AND: + case BPF_AND | BPF_FETCH: + EMIT(PPC_RAW_AND(_R0, _R0, src_reg)); + break; + case BPF_OR: + case BPF_OR | BPF_FETCH: + EMIT(PPC_RAW_OR(_R0, _R0, src_reg)); + break; + case BPF_XOR: + case BPF_XOR | BPF_FETCH: + EMIT(PPC_RAW_XOR(_R0, _R0, src_reg)); + break; + case BPF_CMPXCHG: + /* + * Return old value in BPF_REG_0 for BPF_CMPXCHG & + * in src_reg for other cases. + */ + ret_reg = bpf_to_ppc(BPF_REG_0); + + /* Compare with old value in BPF_REG_0 */ + EMIT(PPC_RAW_CMPW(bpf_to_ppc(BPF_REG_0), _R0)); + /* Don't set if different from old value */ + PPC_BCC_SHORT(COND_NE, (ctx->idx + 3) * 4); + fallthrough; + case BPF_XCHG: + save_reg = src_reg; + break; + default: + pr_err_ratelimited("eBPF filter atomic op code %02x (@%d) unsupported\n", + code, i); + return -EOPNOTSUPP; + } + + /* store new value */ + EMIT(PPC_RAW_STWCX(save_reg, tmp_reg, dst_reg)); /* we're done if this succeeded */ - PPC_BCC_SHORT(COND_NE, (ctx->idx - 3) * 4); + PPC_BCC_SHORT(COND_NE, tmp_idx); + + /* For the BPF_FETCH variant, get old data into src_reg */ + if (imm & BPF_FETCH) { + EMIT(PPC_RAW_MR(ret_reg, ax_reg)); + if (!fp->aux->verifier_zext) + EMIT(PPC_RAW_LI(ret_reg - 1, 0)); /* higher 32-bit */ + } break; case BPF_STX | BPF_ATOMIC | BPF_DW: /* *(u64 *)(dst + off) += src */ diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c index 594c54931e20..29ee306d6302 100644 --- a/arch/powerpc/net/bpf_jit_comp64.c +++ b/arch/powerpc/net/bpf_jit_comp64.c @@ -360,6 +360,7 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context * u32 size = BPF_SIZE(code); u32 tmp1_reg = bpf_to_ppc(TMP_REG_1); u32 tmp2_reg = bpf_to_ppc(TMP_REG_2); + u32 save_reg, ret_reg; s16 off = insn[i].off; s32 imm = insn[i].imm; bool func_addr_fixed; @@ -777,42 +778,83 @@ emit_clear: * BPF_STX ATOMIC (atomic ops) */ case BPF_STX | BPF_ATOMIC | BPF_W: - if (imm != BPF_ADD) { - pr_err_ratelimited( - "eBPF filter atomic op code %02x (@%d) unsupported\n", - code, i); - return -ENOTSUPP; - } - - /* *(u32 *)(dst + off) += src */ + case BPF_STX | BPF_ATOMIC | BPF_DW: + save_reg = tmp2_reg; + ret_reg = src_reg; - /* Get EA into TMP_REG_1 */ - EMIT(PPC_RAW_ADDI(tmp1_reg, dst_reg, off)); + /* Get offset into TMP_REG_1 */ + EMIT(PPC_RAW_LI(tmp1_reg, off)); tmp_idx = ctx->idx * 4; /* load value from memory into TMP_REG_2 */ - EMIT(PPC_RAW_LWARX(tmp2_reg, 0, tmp1_reg, 0)); - /* add value from src_reg into this */ - EMIT(PPC_RAW_ADD(tmp2_reg, tmp2_reg, src_reg)); - /* store result back */ - EMIT(PPC_RAW_STWCX(tmp2_reg, 0, tmp1_reg)); - /* we're done if this succeeded */ - PPC_BCC_SHORT(COND_NE, tmp_idx); - break; - case BPF_STX | BPF_ATOMIC | BPF_DW: - if (imm != BPF_ADD) { + if (size == BPF_DW) + EMIT(PPC_RAW_LDARX(tmp2_reg, tmp1_reg, dst_reg, 0)); + else + EMIT(PPC_RAW_LWARX(tmp2_reg, tmp1_reg, dst_reg, 0)); + + /* Save old value in _R0 */ + if (imm & BPF_FETCH) + EMIT(PPC_RAW_MR(_R0, tmp2_reg)); + + switch (imm) { + case BPF_ADD: + case BPF_ADD | BPF_FETCH: + EMIT(PPC_RAW_ADD(tmp2_reg, tmp2_reg, src_reg)); + break; + case BPF_AND: + case BPF_AND | BPF_FETCH: + EMIT(PPC_RAW_AND(tmp2_reg, tmp2_reg, src_reg)); + break; + case BPF_OR: + case BPF_OR | BPF_FETCH: + EMIT(PPC_RAW_OR(tmp2_reg, tmp2_reg, src_reg)); + break; + case BPF_XOR: + case BPF_XOR | BPF_FETCH: + EMIT(PPC_RAW_XOR(tmp2_reg, tmp2_reg, src_reg)); + break; + case BPF_CMPXCHG: + /* + * Return old value in BPF_REG_0 for BPF_CMPXCHG & + * in src_reg for other cases. + */ + ret_reg = bpf_to_ppc(BPF_REG_0); + + /* Compare with old value in BPF_R0 */ + if (size == BPF_DW) + EMIT(PPC_RAW_CMPD(bpf_to_ppc(BPF_REG_0), tmp2_reg)); + else + EMIT(PPC_RAW_CMPW(bpf_to_ppc(BPF_REG_0), tmp2_reg)); + /* Don't set if different from old value */ + PPC_BCC_SHORT(COND_NE, (ctx->idx + 3) * 4); + fallthrough; + case BPF_XCHG: + save_reg = src_reg; + break; + default: pr_err_ratelimited( "eBPF filter atomic op code %02x (@%d) unsupported\n", code, i); - return -ENOTSUPP; + return -EOPNOTSUPP; } - /* *(u64 *)(dst + off) += src */ - EMIT(PPC_RAW_ADDI(tmp1_reg, dst_reg, off)); - tmp_idx = ctx->idx * 4; - EMIT(PPC_RAW_LDARX(tmp2_reg, 0, tmp1_reg, 0)); - EMIT(PPC_RAW_ADD(tmp2_reg, tmp2_reg, src_reg)); - EMIT(PPC_RAW_STDCX(tmp2_reg, 0, tmp1_reg)); + /* store new value */ + if (size == BPF_DW) + EMIT(PPC_RAW_STDCX(save_reg, tmp1_reg, dst_reg)); + else + EMIT(PPC_RAW_STWCX(save_reg, tmp1_reg, dst_reg)); + /* we're done if this succeeded */ PPC_BCC_SHORT(COND_NE, tmp_idx); + + if (imm & BPF_FETCH) { + EMIT(PPC_RAW_MR(ret_reg, _R0)); + /* + * Skip unnecessary zero-extension for 32-bit cmpxchg. + * For context, see commit 39491867ace5. + */ + if (size != BPF_DW && imm == BPF_CMPXCHG && + insn_is_zext(&insn[i + 1])) + addrs[++i] = ctx->idx * 4; + } break; /* diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index 140502a7fdf8..13919eb96931 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -1349,27 +1349,22 @@ static void power_pmu_disable(struct pmu *pmu) * a PMI happens during interrupt replay and perf counter * values are cleared by PMU callbacks before replay. * - * If any PMC corresponding to the active PMU events are - * overflown, disable the interrupt by clearing the paca - * bit for PMI since we are disabling the PMU now. - * Otherwise provide a warning if there is PMI pending, but - * no counter is found overflown. + * Disable the interrupt by clearing the paca bit for PMI + * since we are disabling the PMU now. Otherwise provide a + * warning if there is PMI pending, but no counter is found + * overflown. + * + * Since power_pmu_disable runs under local_irq_save, it + * could happen that code hits a PMC overflow without PMI + * pending in paca. Hence only clear PMI pending if it was + * set. + * + * If a PMI is pending, then MSR[EE] must be disabled (because + * the masked PMI handler disabling EE). So it is safe to + * call clear_pmi_irq_pending(). */ - if (any_pmc_overflown(cpuhw)) { - /* - * Since power_pmu_disable runs under local_irq_save, it - * could happen that code hits a PMC overflow without PMI - * pending in paca. Hence only clear PMI pending if it was - * set. - * - * If a PMI is pending, then MSR[EE] must be disabled (because - * the masked PMI handler disabling EE). So it is safe to - * call clear_pmi_irq_pending(). - */ - if (pmi_irq_pending()) - clear_pmi_irq_pending(); - } else - WARN_ON(pmi_irq_pending()); + if (pmi_irq_pending()) + clear_pmi_irq_pending(); val = mmcra = cpuhw->mmcr.mmcra; @@ -2488,6 +2483,33 @@ static int power_pmu_prepare_cpu(unsigned int cpu) return 0; } +static ssize_t pmu_name_show(struct device *cdev, + struct device_attribute *attr, + char *buf) +{ + if (ppmu) + return sysfs_emit(buf, "%s", ppmu->name); + + return 0; +} + +static DEVICE_ATTR_RO(pmu_name); + +static struct attribute *pmu_caps_attrs[] = { + &dev_attr_pmu_name.attr, + NULL +}; + +static const struct attribute_group pmu_caps_group = { + .name = "caps", + .attrs = pmu_caps_attrs, +}; + +static const struct attribute_group *pmu_caps_groups[] = { + &pmu_caps_group, + NULL, +}; + int __init register_power_pmu(struct power_pmu *pmu) { if (ppmu) @@ -2498,6 +2520,10 @@ int __init register_power_pmu(struct power_pmu *pmu) pmu->name); power_pmu.attr_groups = ppmu->attr_groups; + + if (ppmu->flags & PPMU_ARCH_207S) + power_pmu.attr_update = pmu_caps_groups; + power_pmu.capabilities |= (ppmu->capabilities & PERF_PMU_CAP_EXTENDED_REGS); #ifdef MSR_HV diff --git a/arch/powerpc/perf/e500-pmu.c b/arch/powerpc/perf/e500-pmu.c index a59c33bed32a..e3e1a68eb1d5 100644 --- a/arch/powerpc/perf/e500-pmu.c +++ b/arch/powerpc/perf/e500-pmu.c @@ -118,12 +118,13 @@ static struct fsl_emb_pmu e500_pmu = { static int init_e500_pmu(void) { - if (!cur_cpu_spec->oprofile_cpu_type) - return -ENODEV; + unsigned int pvr = mfspr(SPRN_PVR); - if (!strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc/e500mc")) + /* ec500mc */ + if (PVR_VER(pvr) == PVR_VER_E500MC || PVR_VER(pvr) == PVR_VER_E5500) num_events = 256; - else if (strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc/e500")) + /* e500 */ + else if (PVR_VER(pvr) != PVR_VER_E500V1 && PVR_VER(pvr) != PVR_VER_E500V2) return -ENODEV; return register_fsl_emb_pmu(&e500_pmu); diff --git a/arch/powerpc/perf/e6500-pmu.c b/arch/powerpc/perf/e6500-pmu.c index 44ad65da82ed..bd779a2338f8 100644 --- a/arch/powerpc/perf/e6500-pmu.c +++ b/arch/powerpc/perf/e6500-pmu.c @@ -107,8 +107,9 @@ static struct fsl_emb_pmu e6500_pmu = { static int init_e6500_pmu(void) { - if (!cur_cpu_spec->oprofile_cpu_type || - strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc/e6500")) + unsigned int pvr = mfspr(SPRN_PVR); + + if (PVR_VER(pvr) != PVR_VER_E6500) return -ENODEV; return register_fsl_emb_pmu(&e6500_pmu); diff --git a/arch/powerpc/perf/generic-compat-pmu.c b/arch/powerpc/perf/generic-compat-pmu.c index f3db88aee4dd..b5c414876ed5 100644 --- a/arch/powerpc/perf/generic-compat-pmu.c +++ b/arch/powerpc/perf/generic-compat-pmu.c @@ -151,9 +151,19 @@ static const struct attribute_group generic_compat_pmu_format_group = { .attrs = generic_compat_pmu_format_attr, }; +static struct attribute *generic_compat_pmu_caps_attrs[] = { + NULL +}; + +static struct attribute_group generic_compat_pmu_caps_group = { + .name = "caps", + .attrs = generic_compat_pmu_caps_attrs, +}; + static const struct attribute_group *generic_compat_pmu_attr_groups[] = { &generic_compat_pmu_format_group, &generic_compat_pmu_events_group, + &generic_compat_pmu_caps_group, NULL, }; @@ -292,7 +302,7 @@ static int generic_compute_mmcr(u64 event[], int n_ev, } static struct power_pmu generic_compat_pmu = { - .name = "GENERIC_COMPAT", + .name = "ISAv3", .n_counter = MAX_PMU_COUNTERS, .add_fields = ISA207_ADD_FIELDS, .test_adder = ISA207_TEST_ADDER, diff --git a/arch/powerpc/perf/hv-24x7.c b/arch/powerpc/perf/hv-24x7.c index cf5406b31e27..33c23225fd54 100644 --- a/arch/powerpc/perf/hv-24x7.c +++ b/arch/powerpc/perf/hv-24x7.c @@ -1718,16 +1718,16 @@ static int hv_24x7_init(void) { int r; unsigned long hret; + unsigned int pvr = mfspr(SPRN_PVR); struct hv_perf_caps caps; if (!firmware_has_feature(FW_FEATURE_LPAR)) { pr_debug("not a virtualized system, not enabling\n"); return -ENODEV; - } else if (!cur_cpu_spec->oprofile_cpu_type) - return -ENODEV; + } /* POWER8 only supports v1, while POWER9 only supports v2. */ - if (!strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power8")) + if (PVR_VER(pvr) == PVR_POWER8) interface_version = 1; else { interface_version = 2; diff --git a/arch/powerpc/perf/isa207-common.c b/arch/powerpc/perf/isa207-common.c index 42abbcfc73da..56301b2bc8ae 100644 --- a/arch/powerpc/perf/isa207-common.c +++ b/arch/powerpc/perf/isa207-common.c @@ -686,6 +686,9 @@ int isa207_compute_mmcr(u64 event[], int n_ev, mmcr2 |= MMCR2_FCS(pmc); } + if (pevents[i]->attr.exclude_idle) + mmcr2 |= MMCR2_FCWAIT(pmc); + if (cpu_has_feature(CPU_FTR_ARCH_31)) { if (pmc <= 4) { val = (event[i] >> p10_EVENT_MMCR3_SHIFT) & diff --git a/arch/powerpc/perf/isa207-common.h b/arch/powerpc/perf/isa207-common.h index ff122603989b..f594fa6580d1 100644 --- a/arch/powerpc/perf/isa207-common.h +++ b/arch/powerpc/perf/isa207-common.h @@ -249,6 +249,7 @@ /* Bits in MMCR2 for PowerISA v2.07 */ #define MMCR2_FCS(pmc) (1ull << (63 - (((pmc) - 1) * 9))) #define MMCR2_FCP(pmc) (1ull << (62 - (((pmc) - 1) * 9))) +#define MMCR2_FCWAIT(pmc) (1ull << (58 - (((pmc) - 1) * 9))) #define MMCR2_FCH(pmc) (1ull << (57 - (((pmc) - 1) * 9))) #define MAX_ALT 2 diff --git a/arch/powerpc/perf/mpc7450-pmu.c b/arch/powerpc/perf/mpc7450-pmu.c index e39b15b79a83..552d51a925d3 100644 --- a/arch/powerpc/perf/mpc7450-pmu.c +++ b/arch/powerpc/perf/mpc7450-pmu.c @@ -417,8 +417,9 @@ struct power_pmu mpc7450_pmu = { static int __init init_mpc7450_pmu(void) { - if (!cur_cpu_spec->oprofile_cpu_type || - strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc/7450")) + unsigned int pvr = mfspr(SPRN_PVR); + + if (PVR_VER(pvr) != PVR_7450) return -ENODEV; return register_power_pmu(&mpc7450_pmu); diff --git a/arch/powerpc/perf/power10-pmu.c b/arch/powerpc/perf/power10-pmu.c index c6d51e7093cf..9b5133e361a7 100644 --- a/arch/powerpc/perf/power10-pmu.c +++ b/arch/powerpc/perf/power10-pmu.c @@ -258,15 +258,26 @@ static const struct attribute_group power10_pmu_format_group = { .attrs = power10_pmu_format_attr, }; +static struct attribute *power10_pmu_caps_attrs[] = { + NULL +}; + +static struct attribute_group power10_pmu_caps_group = { + .name = "caps", + .attrs = power10_pmu_caps_attrs, +}; + static const struct attribute_group *power10_pmu_attr_groups_dd1[] = { &power10_pmu_format_group, &power10_pmu_events_group_dd1, + &power10_pmu_caps_group, NULL, }; static const struct attribute_group *power10_pmu_attr_groups[] = { &power10_pmu_format_group, &power10_pmu_events_group, + &power10_pmu_caps_group, NULL, }; @@ -597,12 +608,10 @@ int __init init_power10_pmu(void) unsigned int pvr; int rc; - /* Comes from cpu_specs[] */ - if (!cur_cpu_spec->oprofile_cpu_type || - strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power10")) + pvr = mfspr(SPRN_PVR); + if (PVR_VER(pvr) != PVR_POWER10) return -ENODEV; - pvr = mfspr(SPRN_PVR); /* Add the ppmu flag for power10 DD1 */ if ((PVR_CFG(pvr) == 1)) power10_pmu.flags |= PPMU_P10_DD1; diff --git a/arch/powerpc/perf/power5+-pmu.c b/arch/powerpc/perf/power5+-pmu.c index 753b4740ef64..b4708ab73145 100644 --- a/arch/powerpc/perf/power5+-pmu.c +++ b/arch/powerpc/perf/power5+-pmu.c @@ -679,9 +679,9 @@ static struct power_pmu power5p_pmu = { int __init init_power5p_pmu(void) { - if (!cur_cpu_spec->oprofile_cpu_type || - (strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power5+") - && strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power5++"))) + unsigned int pvr = mfspr(SPRN_PVR); + + if (PVR_VER(pvr) != PVR_POWER5p) return -ENODEV; return register_power_pmu(&power5p_pmu); diff --git a/arch/powerpc/perf/power5-pmu.c b/arch/powerpc/perf/power5-pmu.c index 1f83c4cba0aa..c6aefd0a1cc8 100644 --- a/arch/powerpc/perf/power5-pmu.c +++ b/arch/powerpc/perf/power5-pmu.c @@ -620,8 +620,9 @@ static struct power_pmu power5_pmu = { int __init init_power5_pmu(void) { - if (!cur_cpu_spec->oprofile_cpu_type || - strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power5")) + unsigned int pvr = mfspr(SPRN_PVR); + + if (PVR_VER(pvr) != PVR_POWER5) return -ENODEV; return register_power_pmu(&power5_pmu); diff --git a/arch/powerpc/perf/power6-pmu.c b/arch/powerpc/perf/power6-pmu.c index aec746f86804..5729b6e059de 100644 --- a/arch/powerpc/perf/power6-pmu.c +++ b/arch/powerpc/perf/power6-pmu.c @@ -541,8 +541,9 @@ static struct power_pmu power6_pmu = { int __init init_power6_pmu(void) { - if (!cur_cpu_spec->oprofile_cpu_type || - strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power6")) + unsigned int pvr = mfspr(SPRN_PVR); + + if (PVR_VER(pvr) != PVR_POWER6) return -ENODEV; return register_power_pmu(&power6_pmu); diff --git a/arch/powerpc/perf/power7-pmu.c b/arch/powerpc/perf/power7-pmu.c index a74211410b8d..c95ccf2e28da 100644 --- a/arch/powerpc/perf/power7-pmu.c +++ b/arch/powerpc/perf/power7-pmu.c @@ -447,11 +447,12 @@ static struct power_pmu power7_pmu = { int __init init_power7_pmu(void) { - if (!cur_cpu_spec->oprofile_cpu_type || - strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power7")) + unsigned int pvr = mfspr(SPRN_PVR); + + if (PVR_VER(pvr) != PVR_POWER7 && PVR_VER(pvr) != PVR_POWER7p) return -ENODEV; - if (pvr_version_is(PVR_POWER7p)) + if (PVR_VER(pvr) == PVR_POWER7p) power7_pmu.flags |= PPMU_SIAR_VALID; return register_power_pmu(&power7_pmu); diff --git a/arch/powerpc/perf/power8-pmu.c b/arch/powerpc/perf/power8-pmu.c index e37b1e714d2b..ef9685065aaf 100644 --- a/arch/powerpc/perf/power8-pmu.c +++ b/arch/powerpc/perf/power8-pmu.c @@ -187,9 +187,19 @@ static const struct attribute_group power8_pmu_events_group = { .attrs = power8_events_attr, }; +static struct attribute *power8_pmu_caps_attrs[] = { + NULL +}; + +static struct attribute_group power8_pmu_caps_group = { + .name = "caps", + .attrs = power8_pmu_caps_attrs, +}; + static const struct attribute_group *power8_pmu_attr_groups[] = { &isa207_pmu_format_group, &power8_pmu_events_group, + &power8_pmu_caps_group, NULL, }; @@ -381,9 +391,10 @@ static struct power_pmu power8_pmu = { int __init init_power8_pmu(void) { int rc; + unsigned int pvr = mfspr(SPRN_PVR); - if (!cur_cpu_spec->oprofile_cpu_type || - strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power8")) + if (PVR_VER(pvr) != PVR_POWER8E && PVR_VER(pvr) != PVR_POWER8NVL && + PVR_VER(pvr) != PVR_POWER8) return -ENODEV; rc = register_power_pmu(&power8_pmu); diff --git a/arch/powerpc/perf/power9-pmu.c b/arch/powerpc/perf/power9-pmu.c index 3ad40ffb9256..cb6a7dc02dd7 100644 --- a/arch/powerpc/perf/power9-pmu.c +++ b/arch/powerpc/perf/power9-pmu.c @@ -258,9 +258,19 @@ static const struct attribute_group power9_pmu_format_group = { .attrs = power9_pmu_format_attr, }; +static struct attribute *power9_pmu_caps_attrs[] = { + NULL +}; + +static struct attribute_group power9_pmu_caps_group = { + .name = "caps", + .attrs = power9_pmu_caps_attrs, +}; + static const struct attribute_group *power9_pmu_attr_groups[] = { &power9_pmu_format_group, &power9_pmu_events_group, + &power9_pmu_caps_group, NULL, }; @@ -457,9 +467,7 @@ int __init init_power9_pmu(void) int rc = 0; unsigned int pvr = mfspr(SPRN_PVR); - /* Comes from cpu_specs[] */ - if (!cur_cpu_spec->oprofile_cpu_type || - strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power9")) + if (PVR_VER(pvr) != PVR_POWER9) return -ENODEV; /* Blacklist events */ diff --git a/arch/powerpc/perf/ppc970-pmu.c b/arch/powerpc/perf/ppc970-pmu.c index 09802482ba72..762676fb839e 100644 --- a/arch/powerpc/perf/ppc970-pmu.c +++ b/arch/powerpc/perf/ppc970-pmu.c @@ -491,9 +491,10 @@ static struct power_pmu ppc970_pmu = { int __init init_ppc970_pmu(void) { - if (!cur_cpu_spec->oprofile_cpu_type || - (strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/970") - && strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/970MP"))) + unsigned int pvr = mfspr(SPRN_PVR); + + if (PVR_VER(pvr) != PVR_970 && PVR_VER(pvr) != PVR_970MP && + PVR_VER(pvr) != PVR_970FX && PVR_VER(pvr) != PVR_970GX) return -ENODEV; return register_power_pmu(&ppc970_pmu); diff --git a/arch/powerpc/platforms/4xx/cpm.c b/arch/powerpc/platforms/4xx/cpm.c index 1d3bc35ee1a7..182e12855c27 100644 --- a/arch/powerpc/platforms/4xx/cpm.c +++ b/arch/powerpc/platforms/4xx/cpm.c @@ -63,7 +63,7 @@ static unsigned int cpm_set(unsigned int cpm_reg, unsigned int mask) * known as class 1, 2 and 3. For class 1 units, they are * unconditionally put to sleep when the corresponding CPM bit is * set. For class 2 and 3 units this is not case; if they can be - * put to to sleep, they will. Here we do not verify, we just + * put to sleep, they will. Here we do not verify, we just * set them and expect them to eventually go off when they can. */ value = dcr_read(cpm.dcr_host, cpm.dcr_offset[cpm_reg]); diff --git a/arch/powerpc/platforms/52xx/mpc52xx_common.c b/arch/powerpc/platforms/52xx/mpc52xx_common.c index 4348506d667d..409c0ec06265 100644 --- a/arch/powerpc/platforms/52xx/mpc52xx_common.c +++ b/arch/powerpc/platforms/52xx/mpc52xx_common.c @@ -204,43 +204,6 @@ int mpc52xx_set_psc_clkdiv(int psc_id, int clkdiv) EXPORT_SYMBOL(mpc52xx_set_psc_clkdiv); /** - * mpc52xx_get_xtal_freq - Get SYS_XTAL_IN frequency for a device - * - * @node: device node - * - * Returns the frequency of the external oscillator clock connected - * to the SYS_XTAL_IN pin, or 0 if it cannot be determined. - */ -unsigned int mpc52xx_get_xtal_freq(struct device_node *node) -{ - u32 val; - unsigned int freq; - - if (!mpc52xx_cdm) - return 0; - - freq = mpc5xxx_get_bus_frequency(node); - if (!freq) - return 0; - - if (in_8(&mpc52xx_cdm->ipb_clk_sel) & 0x1) - freq *= 2; - - val = in_be32(&mpc52xx_cdm->rstcfg); - if (val & (1 << 5)) - freq *= 8; - else - freq *= 4; - if (val & (1 << 6)) - freq /= 12; - else - freq /= 16; - - return freq; -} -EXPORT_SYMBOL(mpc52xx_get_xtal_freq); - -/** * mpc52xx_restart: ppc_md->restart hook for mpc5200 using the watchdog timer */ void __noreturn mpc52xx_restart(char *cmd) diff --git a/arch/powerpc/platforms/52xx/mpc52xx_gpt.c b/arch/powerpc/platforms/52xx/mpc52xx_gpt.c index 968f5b727273..e43e08d991ea 100644 --- a/arch/powerpc/platforms/52xx/mpc52xx_gpt.c +++ b/arch/powerpc/platforms/52xx/mpc52xx_gpt.c @@ -60,6 +60,7 @@ #include <linux/of_platform.h> #include <linux/of_gpio.h> #include <linux/kernel.h> +#include <linux/property.h> #include <linux/slab.h> #include <linux/fs.h> #include <linux/watchdog.h> @@ -316,17 +317,15 @@ mpc52xx_gpt_gpio_dir_out(struct gpio_chip *gc, unsigned int gpio, int val) return 0; } -static void -mpc52xx_gpt_gpio_setup(struct mpc52xx_gpt_priv *gpt, struct device_node *node) +static void mpc52xx_gpt_gpio_setup(struct mpc52xx_gpt_priv *gpt) { int rc; - /* Only setup GPIO if the device tree claims the GPT is - * a GPIO controller */ - if (!of_find_property(node, "gpio-controller", NULL)) + /* Only setup GPIO if the device claims the GPT is a GPIO controller */ + if (!device_property_present(gpt->dev, "gpio-controller")) return; - gpt->gc.label = kasprintf(GFP_KERNEL, "%pOF", node); + gpt->gc.label = kasprintf(GFP_KERNEL, "%pfw", dev_fwnode(gpt->dev)); if (!gpt->gc.label) { dev_err(gpt->dev, "out of memory\n"); return; @@ -338,7 +337,7 @@ mpc52xx_gpt_gpio_setup(struct mpc52xx_gpt_priv *gpt, struct device_node *node) gpt->gc.get = mpc52xx_gpt_gpio_get; gpt->gc.set = mpc52xx_gpt_gpio_set; gpt->gc.base = -1; - gpt->gc.of_node = node; + gpt->gc.parent = gpt->dev; /* Setup external pin in GPIO mode */ clrsetbits_be32(&gpt->regs->mode, MPC52xx_GPT_MODE_MS_MASK, @@ -351,8 +350,7 @@ mpc52xx_gpt_gpio_setup(struct mpc52xx_gpt_priv *gpt, struct device_node *node) dev_dbg(gpt->dev, "%s() complete.\n", __func__); } #else /* defined(CONFIG_GPIOLIB) */ -static void -mpc52xx_gpt_gpio_setup(struct mpc52xx_gpt_priv *p, struct device_node *np) { } +static void mpc52xx_gpt_gpio_setup(struct mpc52xx_gpt_priv *gpt) { } #endif /* defined(CONFIG_GPIOLIB) */ /*********************************************************************** @@ -722,14 +720,14 @@ static int mpc52xx_gpt_probe(struct platform_device *ofdev) raw_spin_lock_init(&gpt->lock); gpt->dev = &ofdev->dev; - gpt->ipb_freq = mpc5xxx_get_bus_frequency(ofdev->dev.of_node); + gpt->ipb_freq = mpc5xxx_get_bus_frequency(&ofdev->dev); gpt->regs = of_iomap(ofdev->dev.of_node, 0); if (!gpt->regs) return -ENOMEM; dev_set_drvdata(&ofdev->dev, gpt); - mpc52xx_gpt_gpio_setup(gpt, ofdev->dev.of_node); + mpc52xx_gpt_gpio_setup(gpt); mpc52xx_gpt_irq_setup(gpt, ofdev->dev.of_node); mutex_lock(&mpc52xx_gpt_list_mutex); @@ -755,11 +753,6 @@ static int mpc52xx_gpt_probe(struct platform_device *ofdev) return 0; } -static int mpc52xx_gpt_remove(struct platform_device *ofdev) -{ - return -EBUSY; -} - static const struct of_device_id mpc52xx_gpt_match[] = { { .compatible = "fsl,mpc5200-gpt", }, @@ -772,10 +765,10 @@ static const struct of_device_id mpc52xx_gpt_match[] = { static struct platform_driver mpc52xx_gpt_driver = { .driver = { .name = "mpc52xx-gpt", + .suppress_bind_attrs = true, .of_match_table = mpc52xx_gpt_match, }, .probe = mpc52xx_gpt_probe, - .remove = mpc52xx_gpt_remove, }; static int __init mpc52xx_gpt_init(void) diff --git a/arch/powerpc/platforms/83xx/misc.c b/arch/powerpc/platforms/83xx/misc.c index 3285dabcf923..2fb2a85d131f 100644 --- a/arch/powerpc/platforms/83xx/misc.c +++ b/arch/powerpc/platforms/83xx/misc.c @@ -121,17 +121,15 @@ void __init mpc83xx_setup_pci(void) void __init mpc83xx_setup_arch(void) { + phys_addr_t immrbase = get_immrbase(); + int immrsize = IS_ALIGNED(immrbase, SZ_2M) ? SZ_2M : SZ_1M; + unsigned long va = fix_to_virt(FIX_IMMR_BASE); + if (ppc_md.progress) ppc_md.progress("mpc83xx_setup_arch()", 0); - if (!__map_without_bats) { - phys_addr_t immrbase = get_immrbase(); - int immrsize = IS_ALIGNED(immrbase, SZ_2M) ? SZ_2M : SZ_1M; - unsigned long va = fix_to_virt(FIX_IMMR_BASE); - - setbat(-1, va, immrbase, immrsize, PAGE_KERNEL_NCG); - update_bats(); - } + setbat(-1, va, immrbase, immrsize, PAGE_KERNEL_NCG); + update_bats(); } int machine_check_83xx(struct pt_regs *regs) diff --git a/arch/powerpc/platforms/83xx/suspend.c b/arch/powerpc/platforms/83xx/suspend.c index 6d47a5b81485..3fa8979ac8a6 100644 --- a/arch/powerpc/platforms/83xx/suspend.c +++ b/arch/powerpc/platforms/83xx/suspend.c @@ -100,7 +100,6 @@ struct pmc_type { int has_deep_sleep; }; -static struct platform_device *pmc_dev; static int has_deep_sleep, deep_sleeping; static int pmc_irq; static struct mpc83xx_pmc __iomem *pmc_regs; @@ -319,7 +318,27 @@ static const struct platform_suspend_ops mpc83xx_suspend_ops = { .end = mpc83xx_suspend_end, }; -static const struct of_device_id pmc_match[]; +static struct pmc_type pmc_types[] = { + { + .has_deep_sleep = 1, + }, + { + .has_deep_sleep = 0, + } +}; + +static const struct of_device_id pmc_match[] = { + { + .compatible = "fsl,mpc8313-pmc", + .data = &pmc_types[0], + }, + { + .compatible = "fsl,mpc8349-pmc", + .data = &pmc_types[1], + }, + {} +}; + static int pmc_probe(struct platform_device *ofdev) { struct device_node *np = ofdev->dev.of_node; @@ -336,7 +355,6 @@ static int pmc_probe(struct platform_device *ofdev) has_deep_sleep = type->has_deep_sleep; immrbase = get_immrbase(); - pmc_dev = ofdev; is_pci_agent = mpc83xx_is_pci_agent(); if (is_pci_agent < 0) @@ -401,39 +419,13 @@ out: return ret; } -static int pmc_remove(struct platform_device *ofdev) -{ - return -EPERM; -}; - -static struct pmc_type pmc_types[] = { - { - .has_deep_sleep = 1, - }, - { - .has_deep_sleep = 0, - } -}; - -static const struct of_device_id pmc_match[] = { - { - .compatible = "fsl,mpc8313-pmc", - .data = &pmc_types[0], - }, - { - .compatible = "fsl,mpc8349-pmc", - .data = &pmc_types[1], - }, - {} -}; - static struct platform_driver pmc_driver = { .driver = { .name = "mpc83xx-pmc", .of_match_table = pmc_match, + .suppress_bind_attrs = true, }, .probe = pmc_probe, - .remove = pmc_remove }; builtin_platform_driver(pmc_driver); diff --git a/arch/powerpc/platforms/85xx/Kconfig b/arch/powerpc/platforms/85xx/Kconfig index 2be17ffe8714..be16eba0f704 100644 --- a/arch/powerpc/platforms/85xx/Kconfig +++ b/arch/powerpc/platforms/85xx/Kconfig @@ -62,13 +62,13 @@ config MPC85xx_CDS This option enables support for the MPC85xx CDS board config MPC85xx_MDS - bool "Freescale MPC85xx MDS" + bool "Freescale MPC8568 MDS / MPC8569 MDS / P1021 MDS" select DEFAULT_UIMAGE select PHYLIB if NETDEVICES select HAVE_RAPIDIO select SWIOTLB help - This option enables support for the MPC85xx MDS board + This option enables support for the MPC8568 MDS, MPC8569 MDS and P1021 MDS boards config MPC8536_DS bool "Freescale MPC8536 DS" @@ -78,28 +78,30 @@ config MPC8536_DS This option enables support for the MPC8536 DS board config MPC85xx_DS - bool "Freescale MPC85xx DS" + bool "Freescale MPC8544 DS / MPC8572 DS / P2020 DS" select PPC_I8259 select DEFAULT_UIMAGE select FSL_ULI1575 if PCI select SWIOTLB help - This option enables support for the MPC85xx DS (MPC8544 DS) board + This option enables support for the MPC8544 DS, MPC8572 DS and P2020 DS boards config MPC85xx_RDB - bool "Freescale MPC85xx RDB" + bool "Freescale P102x MBG/UTM/RDB and P2020 RDB" select PPC_I8259 select DEFAULT_UIMAGE select FSL_ULI1575 if PCI select SWIOTLB help - This option enables support for the MPC85xx RDB (P2020 RDB) board + This option enables support for the P1020 MBG PC, P1020 UTM PC, + P1020 RDB PC, P1020 RDB PD, P1020 RDB, P1021 RDB PC, P1024 RDB, + P1025 RDB, P2020 RDB and P2020 RDB PC boards config P1010_RDB - bool "Freescale P1010RDB" + bool "Freescale P1010 RDB" select DEFAULT_UIMAGE help - This option enables support for the MPC85xx RDB (P1010 RDB) board + This option enables support for the P1010 RDB board P1010RDB contains P1010Si, which provides CPU performance up to 800 MHz and 1600 DMIPS, additional functionality and faster interfaces diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype index 9e2df4b66478..5185d942b455 100644 --- a/arch/powerpc/platforms/Kconfig.cputype +++ b/arch/powerpc/platforms/Kconfig.cputype @@ -2,7 +2,6 @@ config PPC32 bool default y if !PPC64 - select KASAN_VMALLOC if KASAN && MODULES config PPC64 bool "64-bit kernel" @@ -127,18 +126,18 @@ choice config GENERIC_CPU bool "Generic (POWER4 and above)" - depends on PPC64 && !CPU_LITTLE_ENDIAN - select PPC_64S_HASH_MMU if PPC_BOOK3S_64 + depends on PPC_BOOK3S_64 && !CPU_LITTLE_ENDIAN + select PPC_64S_HASH_MMU config GENERIC_CPU bool "Generic (POWER8 and above)" - depends on PPC64 && CPU_LITTLE_ENDIAN + depends on PPC_BOOK3S_64 && CPU_LITTLE_ENDIAN select ARCH_HAS_FAST_MULTIPLIER select PPC_64S_HASH_MMU -config GENERIC_CPU +config POWERPC_CPU bool "Generic 32 bits powerpc" - depends on PPC32 && !PPC_8xx + depends on PPC_BOOK3S_32 config CELL_CPU bool "Cell Broadband Engine" @@ -174,11 +173,27 @@ config POWER9_CPU config E5500_CPU bool "Freescale e5500" - depends on E500 + depends on PPC64 && E500 config E6500_CPU bool "Freescale e6500" - depends on E500 + depends on PPC64 && E500 + +config 405_CPU + bool "40x family" + depends on 40x + +config 440_CPU + bool "440 (44x family)" + depends on 44x + +config 464_CPU + bool "464 (44x family)" + depends on 44x + +config 476_CPU + bool "476 (47x family)" + depends on PPC_47x config 860_CPU bool "8xx family" @@ -197,11 +212,23 @@ config G4_CPU depends on PPC_BOOK3S_32 select ALTIVEC +config E500_CPU + bool "e500 (8540)" + depends on PPC_85xx && !PPC_E500MC + +config E500MC_CPU + bool "e500mc" + depends on PPC_85xx && PPC_E500MC + +config TOOLCHAIN_DEFAULT_CPU + bool "Rely on the toolchain's implicit default CPU" + depends on PPC32 + endchoice config TARGET_CPU_BOOL bool - default !GENERIC_CPU + default !GENERIC_CPU && !TOOLCHAIN_DEFAULT_CPU config TARGET_CPU string @@ -212,10 +239,17 @@ config TARGET_CPU default "power7" if POWER7_CPU default "power8" if POWER8_CPU default "power9" if POWER9_CPU + default "405" if 405_CPU + default "440" if 440_CPU + default "464" if 464_CPU + default "476" if 476_CPU default "860" if 860_CPU default "e300c2" if E300C2_CPU default "e300c3" if E300C3_CPU default "G4" if G4_CPU + default "8540" if E500_CPU + default "e500mc" if E500MC_CPU + default "powerpc" if POWERPC_CPU config PPC_BOOK3S def_bool y @@ -324,7 +358,7 @@ config PHYS_64BIT config ALTIVEC bool "AltiVec Support" - depends on PPC_BOOK3S_32 || PPC_BOOK3S_64 || (PPC_E500MC && PPC64) + depends on PPC_BOOK3S || (PPC_E500MC && PPC64 && !E5500_CPU) select PPC_FPU help This option enables kernel support for the Altivec extensions to the diff --git a/arch/powerpc/platforms/cell/axon_msi.c b/arch/powerpc/platforms/cell/axon_msi.c index f3291e957a19..5b012abca773 100644 --- a/arch/powerpc/platforms/cell/axon_msi.c +++ b/arch/powerpc/platforms/cell/axon_msi.c @@ -223,6 +223,7 @@ static int setup_msi_msg_address(struct pci_dev *dev, struct msi_msg *msg) if (!prop) { dev_dbg(&dev->dev, "axon_msi: no msi-address-(32|64) properties found\n"); + of_node_put(dn); return -ENOENT; } diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c index 34334c32b7f5..320008528edd 100644 --- a/arch/powerpc/platforms/cell/spufs/inode.c +++ b/arch/powerpc/platforms/cell/spufs/inode.c @@ -660,6 +660,7 @@ spufs_init_isolated_loader(void) return; loader = of_get_property(dn, "loader", &size); + of_node_put(dn); if (!loader) return; diff --git a/arch/powerpc/platforms/cell/spufs/spufs.h b/arch/powerpc/platforms/cell/spufs/spufs.h index afc1d6604d12..23c6799cfa5a 100644 --- a/arch/powerpc/platforms/cell/spufs/spufs.h +++ b/arch/powerpc/platforms/cell/spufs/spufs.h @@ -76,7 +76,7 @@ struct spu_context { struct address_space *mss; /* 'mss' area mappings. */ struct address_space *psmap; /* 'psmap' area mappings. */ struct mutex mapping_lock; - u64 object_id; /* user space pointer for oprofile */ + u64 object_id; /* user space pointer for GNU Debugger */ enum { SPU_STATE_RUNNABLE, SPU_STATE_SAVED } state; struct mutex state_mutex; diff --git a/arch/powerpc/platforms/powermac/setup.c b/arch/powerpc/platforms/powermac/setup.c index f71735ec449f..04daa7f0a03c 100644 --- a/arch/powerpc/platforms/powermac/setup.c +++ b/arch/powerpc/platforms/powermac/setup.c @@ -320,13 +320,6 @@ static void __init pmac_setup_arch(void) #endif /* CONFIG_ADB */ } -#ifdef CONFIG_SCSI -void note_scsi_host(struct device_node *node, void *host) -{ -} -EXPORT_SYMBOL(note_scsi_host); -#endif - static int initializing = 1; static int pmac_late_init(void) diff --git a/arch/powerpc/platforms/powernv/Kconfig b/arch/powerpc/platforms/powernv/Kconfig index e1a05c5a9004..ae248a161b43 100644 --- a/arch/powerpc/platforms/powernv/Kconfig +++ b/arch/powerpc/platforms/powernv/Kconfig @@ -19,7 +19,7 @@ config PPC_POWERNV default y config OPAL_PRD - tristate 'OPAL PRD driver' + tristate "OPAL PRD driver" depends on PPC_POWERNV help This enables the opal-prd driver, a facility to run processor diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index c8cf2728031a..9de9b2fb163d 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -1609,6 +1609,7 @@ found: tbl->it_ops = &pnv_ioda1_iommu_ops; pe->table_group.tce32_start = tbl->it_offset << tbl->it_page_shift; pe->table_group.tce32_size = tbl->it_size << tbl->it_page_shift; + tbl->it_index = (phb->hose->global_number << 16) | pe->pe_number; if (!iommu_init_table(tbl, phb->hose->node, 0, 0)) panic("Failed to initialize iommu table"); @@ -1779,6 +1780,7 @@ static long pnv_pci_ioda2_setup_default_config(struct pnv_ioda_pe *pe) res_end = min(window_size, SZ_4G) >> tbl->it_page_shift; } + tbl->it_index = (pe->phb->hose->global_number << 16) | pe->pe_number; if (iommu_init_table(tbl, pe->phb->hose->node, res_start, res_end)) rc = pnv_pci_ioda2_set_window(&pe->table_group, 0, tbl); else diff --git a/arch/powerpc/platforms/powernv/rng.c b/arch/powerpc/platforms/powernv/rng.c index 3805ad13b8f3..196aa70fe043 100644 --- a/arch/powerpc/platforms/powernv/rng.c +++ b/arch/powerpc/platforms/powernv/rng.c @@ -21,24 +21,15 @@ #define DARN_ERR 0xFFFFFFFFFFFFFFFFul -struct powernv_rng { +struct pnv_rng { void __iomem *regs; void __iomem *regs_real; unsigned long mask; }; -static DEFINE_PER_CPU(struct powernv_rng *, powernv_rng); +static DEFINE_PER_CPU(struct pnv_rng *, pnv_rng); -int powernv_hwrng_present(void) -{ - struct powernv_rng *rng; - - rng = get_cpu_var(powernv_rng); - put_cpu_var(rng); - return rng != NULL; -} - -static unsigned long rng_whiten(struct powernv_rng *rng, unsigned long val) +static unsigned long rng_whiten(struct pnv_rng *rng, unsigned long val) { unsigned long parity; @@ -58,18 +49,7 @@ static unsigned long rng_whiten(struct powernv_rng *rng, unsigned long val) return val; } -int powernv_get_random_real_mode(unsigned long *v) -{ - struct powernv_rng *rng; - - rng = raw_cpu_read(powernv_rng); - - *v = rng_whiten(rng, __raw_rm_readq(rng->regs_real)); - - return 1; -} - -static int powernv_get_random_darn(unsigned long *v) +static int pnv_get_random_darn(unsigned long *v) { unsigned long val; @@ -93,29 +73,31 @@ static int __init initialise_darn(void) return -ENODEV; for (i = 0; i < 10; i++) { - if (powernv_get_random_darn(&val)) { - ppc_md.get_random_seed = powernv_get_random_darn; + if (pnv_get_random_darn(&val)) { + ppc_md.get_random_seed = pnv_get_random_darn; return 0; } } return -EIO; } -int powernv_get_random_long(unsigned long *v) +int pnv_get_random_long(unsigned long *v) { - struct powernv_rng *rng; - - rng = get_cpu_var(powernv_rng); - - *v = rng_whiten(rng, in_be64(rng->regs)); - - put_cpu_var(rng); - + struct pnv_rng *rng; + + if (mfmsr() & MSR_DR) { + rng = get_cpu_var(pnv_rng); + *v = rng_whiten(rng, in_be64(rng->regs)); + put_cpu_var(rng); + } else { + rng = raw_cpu_read(pnv_rng); + *v = rng_whiten(rng, __raw_rm_readq(rng->regs_real)); + } return 1; } -EXPORT_SYMBOL_GPL(powernv_get_random_long); +EXPORT_SYMBOL_GPL(pnv_get_random_long); -static __init void rng_init_per_cpu(struct powernv_rng *rng, +static __init void rng_init_per_cpu(struct pnv_rng *rng, struct device_node *dn) { int chip_id, cpu; @@ -125,16 +107,16 @@ static __init void rng_init_per_cpu(struct powernv_rng *rng, pr_warn("No ibm,chip-id found for %pOF.\n", dn); for_each_possible_cpu(cpu) { - if (per_cpu(powernv_rng, cpu) == NULL || + if (per_cpu(pnv_rng, cpu) == NULL || cpu_to_chip_id(cpu) == chip_id) { - per_cpu(powernv_rng, cpu) = rng; + per_cpu(pnv_rng, cpu) = rng; } } } static __init int rng_create(struct device_node *dn) { - struct powernv_rng *rng; + struct pnv_rng *rng; struct resource res; unsigned long val; @@ -160,7 +142,7 @@ static __init int rng_create(struct device_node *dn) rng_init_per_cpu(rng, dn); - ppc_md.get_random_seed = powernv_get_random_long; + ppc_md.get_random_seed = pnv_get_random_long; return 0; } @@ -208,7 +190,7 @@ static int __init pnv_rng_late_init(void) if (ppc_md.get_random_seed == pnv_get_random_long_early) pnv_get_random_long_early(&v); - if (ppc_md.get_random_seed == powernv_get_random_long) { + if (ppc_md.get_random_seed == pnv_get_random_long) { for_each_compatible_node(dn, NULL, "ibm,power-rng") of_platform_device_create(dn, NULL, NULL); } diff --git a/arch/powerpc/platforms/powernv/vas-fault.c b/arch/powerpc/platforms/powernv/vas-fault.c index c1bfad56447d..2b47d5a86328 100644 --- a/arch/powerpc/platforms/powernv/vas-fault.c +++ b/arch/powerpc/platforms/powernv/vas-fault.c @@ -77,7 +77,7 @@ irqreturn_t vas_fault_thread_fn(int irq, void *data) /* * VAS can interrupt with multiple page faults. So process all * valid CRBs within fault FIFO until reaches invalid CRB. - * We use CCW[0] and pswid to validate validate CRBs: + * We use CCW[0] and pswid to validate CRBs: * * CCW[0] Reserved bit. When NX pastes CRB, CCW[0]=0 * OS sets this bit to 1 after reading CRB. diff --git a/arch/powerpc/platforms/ps3/Kconfig b/arch/powerpc/platforms/ps3/Kconfig index 610682caabc4..a44869e5ea70 100644 --- a/arch/powerpc/platforms/ps3/Kconfig +++ b/arch/powerpc/platforms/ps3/Kconfig @@ -165,7 +165,7 @@ config PS3_LPM If you intend to use the advanced performance monitoring and profiling support of the Cell processor with programs like - oprofile and perfmon2, then say Y or M, otherwise say N. + perfmon2, then say Y or M, otherwise say N. config PS3GELIC_UDBG bool "PS3 udbg output via UDP broadcasts on Ethernet" diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig index f4a647c1f0b2..fb6499977f99 100644 --- a/arch/powerpc/platforms/pseries/Kconfig +++ b/arch/powerpc/platforms/pseries/Kconfig @@ -141,6 +141,19 @@ config IBMEBUS help Bus device driver for GX bus based adapters. +config PSERIES_PLPKS + depends on PPC_PSERIES + bool "Support for the Platform Key Storage" + help + PowerVM provides an isolated Platform Keystore(PKS) storage + allocation for each LPAR with individually managed access + controls to store sensitive information securely. It can be + used to store asymmetric public keys or secrets as required + by different usecases. Select this config to enable + operating system interface to hypervisor to access this space. + + If unsure, select N. + config PAPR_SCM depends on PPC_PSERIES && MEMORY_HOTPLUG && LIBNVDIMM tristate "Support for the PAPR Storage Class Memory interface" diff --git a/arch/powerpc/platforms/pseries/Makefile b/arch/powerpc/platforms/pseries/Makefile index 7aaff5323544..14e143b946a3 100644 --- a/arch/powerpc/platforms/pseries/Makefile +++ b/arch/powerpc/platforms/pseries/Makefile @@ -28,6 +28,7 @@ obj-$(CONFIG_PAPR_SCM) += papr_scm.o obj-$(CONFIG_PPC_SPLPAR) += vphn.o obj-$(CONFIG_PPC_SVM) += svm.o obj-$(CONFIG_FA_DUMP) += rtas-fadump.o +obj-$(CONFIG_PSERIES_PLPKS) += plpks.o obj-$(CONFIG_SUSPEND) += suspend.o obj-$(CONFIG_PPC_VAS) += vas.o vas-sysfs.o diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c index 1b0c901a6f3b..8e40ccac0f44 100644 --- a/arch/powerpc/platforms/pseries/eeh_pseries.c +++ b/arch/powerpc/platforms/pseries/eeh_pseries.c @@ -71,7 +71,7 @@ static void pseries_pcibios_bus_add_device(struct pci_dev *pdev) if (pdev->is_virtfn) { /* * FIXME: This really should be handled by choosing the right - * parent PE in in pseries_eeh_init_edev(). + * parent PE in pseries_eeh_init_edev(). */ struct eeh_pe *physfn_pe = pci_dev_to_eeh_dev(pdev->physfn)->pe; struct eeh_dev *edev = pdn_to_eeh_dev(pdn); diff --git a/arch/powerpc/platforms/pseries/firmware.c b/arch/powerpc/platforms/pseries/firmware.c index 09c119b2f623..080108d129ed 100644 --- a/arch/powerpc/platforms/pseries/firmware.c +++ b/arch/powerpc/platforms/pseries/firmware.c @@ -67,6 +67,7 @@ hypertas_fw_features_table[] = { {FW_FEATURE_PAPR_SCM, "hcall-scm"}, {FW_FEATURE_RPT_INVALIDATE, "hcall-rpt-invalidate"}, {FW_FEATURE_ENERGY_SCALE_INFO, "hcall-energy-scale-info"}, + {FW_FEATURE_WATCHDOG, "hcall-watchdog"}, }; /* Build up the firmware features bitmask using the contents of diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index fba64304e859..561adac69022 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -700,6 +700,33 @@ struct iommu_table_ops iommu_table_lpar_multi_ops = { .get = tce_get_pSeriesLP }; +/* + * Find nearest ibm,dma-window (default DMA window) or direct DMA window or + * dynamic 64bit DMA window, walking up the device tree. + */ +static struct device_node *pci_dma_find(struct device_node *dn, + const __be32 **dma_window) +{ + const __be32 *dw = NULL; + + for ( ; dn && PCI_DN(dn); dn = dn->parent) { + dw = of_get_property(dn, "ibm,dma-window", NULL); + if (dw) { + if (dma_window) + *dma_window = dw; + return dn; + } + dw = of_get_property(dn, DIRECT64_PROPNAME, NULL); + if (dw) + return dn; + dw = of_get_property(dn, DMA64_PROPNAME, NULL); + if (dw) + return dn; + } + + return NULL; +} + static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus) { struct iommu_table *tbl; @@ -712,20 +739,10 @@ static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus) pr_debug("pci_dma_bus_setup_pSeriesLP: setting up bus %pOF\n", dn); - /* - * Find nearest ibm,dma-window (default DMA window), walking up the - * device tree - */ - for (pdn = dn; pdn != NULL; pdn = pdn->parent) { - dma_window = of_get_property(pdn, "ibm,dma-window", NULL); - if (dma_window != NULL) - break; - } + pdn = pci_dma_find(dn, &dma_window); - if (dma_window == NULL) { + if (dma_window == NULL) pr_debug(" no ibm,dma-window property !\n"); - return; - } ppci = PCI_DN(pdn); @@ -735,11 +752,13 @@ static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus) if (!ppci->table_group) { ppci->table_group = iommu_pseries_alloc_group(ppci->phb->node); tbl = ppci->table_group->tables[0]; - iommu_table_setparms_lpar(ppci->phb, pdn, tbl, - ppci->table_group, dma_window); + if (dma_window) { + iommu_table_setparms_lpar(ppci->phb, pdn, tbl, + ppci->table_group, dma_window); - if (!iommu_init_table(tbl, ppci->phb->node, 0, 0)) - panic("Failed to initialize iommu table"); + if (!iommu_init_table(tbl, ppci->phb->node, 0, 0)) + panic("Failed to initialize iommu table"); + } iommu_register_group(ppci->table_group, pci_domain_nr(bus), 0); pr_debug(" created table: %p\n", ppci->table_group); @@ -1021,9 +1040,6 @@ static int query_ddw(struct pci_dev *dev, const u32 *ddw_avail, ret = rtas_call(ddw_avail[DDW_QUERY_PE_DMA_WIN], 3, out_sz, query_out, cfg_addr, BUID_HI(buid), BUID_LO(buid)); - dev_info(&dev->dev, "ibm,query-pe-dma-windows(%x) %x %x %x returned %d\n", - ddw_avail[DDW_QUERY_PE_DMA_WIN], cfg_addr, BUID_HI(buid), - BUID_LO(buid), ret); switch (out_sz) { case 5: @@ -1041,6 +1057,11 @@ static int query_ddw(struct pci_dev *dev, const u32 *ddw_avail, break; } + dev_info(&dev->dev, "ibm,query-pe-dma-windows(%x) %x %x %x returned %d, lb=%llx ps=%x wn=%d\n", + ddw_avail[DDW_QUERY_PE_DMA_WIN], cfg_addr, BUID_HI(buid), + BUID_LO(buid), ret, query->largest_available_block, + query->page_size, query->windows_available); + return ret; } @@ -1232,7 +1253,7 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn) bool default_win_removed = false, direct_mapping = false; bool pmem_present; struct pci_dn *pci = PCI_DN(pdn); - struct iommu_table *tbl = pci->table_group->tables[0]; + struct property *default_win = NULL; dn = of_find_node_by_type(NULL, "ibm,pmemory"); pmem_present = dn != NULL; @@ -1289,11 +1310,10 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn) * for extensions presence. */ if (query.windows_available == 0) { - struct property *default_win; int reset_win_ext; /* DDW + IOMMU on single window may fail if there is any allocation */ - if (iommu_table_in_use(tbl)) { + if (iommu_table_in_use(pci->table_group->tables[0])) { dev_warn(&dev->dev, "current IOMMU table in use, can't be replaced.\n"); goto out_failed; } @@ -1429,16 +1449,18 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn) pci->table_group->tables[1] = newtbl; - /* Keep default DMA window struct if removed */ - if (default_win_removed) { - tbl->it_size = 0; - vfree(tbl->it_map); - tbl->it_map = NULL; - } - set_iommu_table_base(&dev->dev, newtbl); } + if (default_win_removed) { + iommu_tce_table_put(pci->table_group->tables[0]); + pci->table_group->tables[0] = NULL; + + /* default_win is valid here because default_win_removed == true */ + of_remove_property(pdn, default_win); + dev_info(&dev->dev, "Removed default DMA window for %pOF\n", pdn); + } + spin_lock(&dma_win_list_lock); list_add(&window->list, &dma_win_list); spin_unlock(&dma_win_list_lock); @@ -1503,13 +1525,7 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev) dn = pci_device_to_OF_node(dev); pr_debug(" node is %pOF\n", dn); - for (pdn = dn; pdn && PCI_DN(pdn) && !PCI_DN(pdn)->table_group; - pdn = pdn->parent) { - dma_window = of_get_property(pdn, "ibm,dma-window", NULL); - if (dma_window) - break; - } - + pdn = pci_dma_find(dn, &dma_window); if (!pdn || !PCI_DN(pdn)) { printk(KERN_WARNING "pci_dma_dev_setup_pSeriesLP: " "no DMA window found for pci dev=%s dn=%pOF\n", @@ -1540,7 +1556,6 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev) static bool iommu_bypass_supported_pSeriesLP(struct pci_dev *pdev, u64 dma_mask) { struct device_node *dn = pci_device_to_OF_node(pdev), *pdn; - const __be32 *dma_window = NULL; /* only attempt to use a new window if 64-bit DMA is requested */ if (dma_mask < DMA_BIT_MASK(64)) @@ -1554,13 +1569,7 @@ static bool iommu_bypass_supported_pSeriesLP(struct pci_dev *pdev, u64 dma_mask) * search upwards in the tree until we either hit a dma-window * property, OR find a parent with a table already allocated. */ - for (pdn = dn; pdn && PCI_DN(pdn) && !PCI_DN(pdn)->table_group; - pdn = pdn->parent) { - dma_window = of_get_property(pdn, "ibm,dma-window", NULL); - if (dma_window) - break; - } - + pdn = pci_dma_find(dn, NULL); if (pdn && PCI_DN(pdn)) return enable_ddw(pdev, pdn); diff --git a/arch/powerpc/platforms/pseries/kexec.c b/arch/powerpc/platforms/pseries/kexec.c index ab6cdbebb35e..096d09ed89f6 100644 --- a/arch/powerpc/platforms/pseries/kexec.c +++ b/arch/powerpc/platforms/pseries/kexec.c @@ -6,7 +6,7 @@ #include <linux/kernel.h> #include <linux/interrupt.h> -#include <asm/machdep.h> +#include <asm/setup.h> #include <asm/page.h> #include <asm/firmware.h> #include <asm/kexec.h> diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index 937f9c010b22..e6c117fb6491 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -27,7 +27,7 @@ #include <asm/processor.h> #include <asm/mmu.h> #include <asm/page.h> -#include <asm/machdep.h> +#include <asm/setup.h> #include <asm/mmu_context.h> #include <asm/iommu.h> #include <asm/tlb.h> diff --git a/arch/powerpc/platforms/pseries/mobility.c b/arch/powerpc/platforms/pseries/mobility.c index 78f3f74c7056..3d36a8955eaf 100644 --- a/arch/powerpc/platforms/pseries/mobility.c +++ b/arch/powerpc/platforms/pseries/mobility.c @@ -48,6 +48,39 @@ struct update_props_workarea { #define MIGRATION_SCOPE (1) #define PRRN_SCOPE -2 +#ifdef CONFIG_PPC_WATCHDOG +static unsigned int nmi_wd_lpm_factor = 200; + +#ifdef CONFIG_SYSCTL +static struct ctl_table nmi_wd_lpm_factor_ctl_table[] = { + { + .procname = "nmi_wd_lpm_factor", + .data = &nmi_wd_lpm_factor, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_douintvec_minmax, + }, + {} +}; +static struct ctl_table nmi_wd_lpm_factor_sysctl_root[] = { + { + .procname = "kernel", + .mode = 0555, + .child = nmi_wd_lpm_factor_ctl_table, + }, + {} +}; + +static int __init register_nmi_wd_lpm_factor_sysctl(void) +{ + register_sysctl_table(nmi_wd_lpm_factor_sysctl_root); + + return 0; +} +device_initcall(register_nmi_wd_lpm_factor_sysctl); +#endif /* CONFIG_SYSCTL */ +#endif /* CONFIG_PPC_WATCHDOG */ + static int mobility_rtas_call(int token, char *buf, s32 scope) { int rc; @@ -427,6 +460,43 @@ static int wait_for_vasi_session_suspending(u64 handle) return ret; } +static void wait_for_vasi_session_completed(u64 handle) +{ + unsigned long state = 0; + int ret; + + pr_info("waiting for memory transfer to complete...\n"); + + /* + * Wait for transition from H_VASI_RESUMED to H_VASI_COMPLETED. + */ + while (true) { + ret = poll_vasi_state(handle, &state); + + /* + * If the memory transfer is already complete and the migration + * has been cleaned up by the hypervisor, H_PARAMETER is return, + * which is translate in EINVAL by poll_vasi_state(). + */ + if (ret == -EINVAL || (!ret && state == H_VASI_COMPLETED)) { + pr_info("memory transfer completed.\n"); + break; + } + + if (ret) { + pr_err("H_VASI_STATE return error (%d)\n", ret); + break; + } + + if (state != H_VASI_RESUMED) { + pr_err("unexpected H_VASI_STATE result %lu\n", state); + break; + } + + msleep(500); + } +} + static void prod_single(unsigned int target_cpu) { long hvrc; @@ -665,19 +735,36 @@ static int pseries_suspend(u64 handle) static int pseries_migrate_partition(u64 handle) { int ret; + unsigned int factor = 0; +#ifdef CONFIG_PPC_WATCHDOG + factor = nmi_wd_lpm_factor; +#endif ret = wait_for_vasi_session_suspending(handle); if (ret) return ret; vas_migration_handler(VAS_SUSPEND); + if (factor) + watchdog_nmi_set_timeout_pct(factor); + ret = pseries_suspend(handle); - if (ret == 0) + if (ret == 0) { post_mobility_fixup(); - else + /* + * Wait until the memory transfer is complete, so that the user + * space process returns from the syscall after the transfer is + * complete. This allows the user hooks to be executed at the + * right time. + */ + wait_for_vasi_session_completed(handle); + } else pseries_cancel_migration(handle, ret); + if (factor) + watchdog_nmi_set_timeout_pct(0); + vas_migration_handler(VAS_RESUME); return ret; diff --git a/arch/powerpc/platforms/pseries/papr_platform_attributes.c b/arch/powerpc/platforms/pseries/papr_platform_attributes.c index 515150417bb3..526c621b098b 100644 --- a/arch/powerpc/platforms/pseries/papr_platform_attributes.c +++ b/arch/powerpc/platforms/pseries/papr_platform_attributes.c @@ -22,6 +22,7 @@ #include <asm/hvcall.h> #include <asm/machdep.h> +#include <asm/firmware.h> #include "pseries.h" diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c index 82cae08976bc..20f6ed813bff 100644 --- a/arch/powerpc/platforms/pseries/papr_scm.c +++ b/arch/powerpc/platforms/pseries/papr_scm.c @@ -29,7 +29,7 @@ (1ul << ND_CMD_SET_CONFIG_DATA) | \ (1ul << ND_CMD_CALL)) -/* DIMM health bitmap bitmap indicators */ +/* DIMM health bitmap indicators */ /* SCM device is unable to persist memory contents */ #define PAPR_PMEM_UNARMED (1ULL << (63 - 0)) /* SCM device failed to persist memory contents */ @@ -354,7 +354,7 @@ static int papr_scm_pmu_get_value(struct perf_event *event, struct device *dev, { struct papr_scm_perf_stat *stat; struct papr_scm_perf_stats *stats; - struct papr_scm_priv *p = (struct papr_scm_priv *)dev->driver_data; + struct papr_scm_priv *p = dev_get_drvdata(dev); int rc, size; /* Allocate request buffer enough to hold single performance stat */ diff --git a/arch/powerpc/platforms/pseries/plpks.c b/arch/powerpc/platforms/pseries/plpks.c new file mode 100644 index 000000000000..52aaa2894606 --- /dev/null +++ b/arch/powerpc/platforms/pseries/plpks.c @@ -0,0 +1,460 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * POWER LPAR Platform KeyStore(PLPKS) + * Copyright (C) 2022 IBM Corporation + * Author: Nayna Jain <nayna@linux.ibm.com> + * + * Provides access to variables stored in Power LPAR Platform KeyStore(PLPKS). + */ + +#define pr_fmt(fmt) "plpks: " fmt + +#include <linux/delay.h> +#include <linux/errno.h> +#include <linux/io.h> +#include <linux/printk.h> +#include <linux/slab.h> +#include <linux/string.h> +#include <linux/types.h> +#include <asm/hvcall.h> + +#include "plpks.h" + +#define PKS_FW_OWNER 0x1 +#define PKS_BOOTLOADER_OWNER 0x2 +#define PKS_OS_OWNER 0x3 + +#define LABEL_VERSION 0 +#define MAX_LABEL_ATTR_SIZE 16 +#define MAX_NAME_SIZE 239 +#define MAX_DATA_SIZE 4000 + +#define PKS_FLUSH_MAX_TIMEOUT 5000 //msec +#define PKS_FLUSH_SLEEP 10 //msec +#define PKS_FLUSH_SLEEP_RANGE 400 + +static u8 *ospassword; +static u16 ospasswordlength; + +// Retrieved with H_PKS_GET_CONFIG +static u16 maxpwsize; +static u16 maxobjsize; + +struct plpks_auth { + u8 version; + u8 consumer; + __be64 rsvd0; + __be32 rsvd1; + __be16 passwordlength; + u8 password[]; +} __packed __aligned(16); + +struct label_attr { + u8 prefix[8]; + u8 version; + u8 os; + u8 length; + u8 reserved[5]; +}; + +struct label { + struct label_attr attr; + u8 name[MAX_NAME_SIZE]; + size_t size; +}; + +static int pseries_status_to_err(int rc) +{ + int err; + + switch (rc) { + case H_SUCCESS: + err = 0; + break; + case H_FUNCTION: + err = -ENXIO; + break; + case H_P1: + case H_P2: + case H_P3: + case H_P4: + case H_P5: + case H_P6: + err = -EINVAL; + break; + case H_NOT_FOUND: + err = -ENOENT; + break; + case H_BUSY: + err = -EBUSY; + break; + case H_AUTHORITY: + err = -EPERM; + break; + case H_NO_MEM: + err = -ENOMEM; + break; + case H_RESOURCE: + err = -EEXIST; + break; + case H_TOO_BIG: + err = -EFBIG; + break; + case H_STATE: + err = -EIO; + break; + case H_R_STATE: + err = -EIO; + break; + case H_IN_USE: + err = -EEXIST; + break; + case H_ABORTED: + err = -EINTR; + break; + default: + err = -EINVAL; + } + + return err; +} + +static int plpks_gen_password(void) +{ + unsigned long retbuf[PLPAR_HCALL_BUFSIZE] = { 0 }; + u8 *password, consumer = PKS_OS_OWNER; + int rc; + + password = kzalloc(maxpwsize, GFP_KERNEL); + if (!password) + return -ENOMEM; + + rc = plpar_hcall(H_PKS_GEN_PASSWORD, retbuf, consumer, 0, + virt_to_phys(password), maxpwsize); + + if (!rc) { + ospasswordlength = maxpwsize; + ospassword = kzalloc(maxpwsize, GFP_KERNEL); + if (!ospassword) { + kfree(password); + return -ENOMEM; + } + memcpy(ospassword, password, ospasswordlength); + } else { + if (rc == H_IN_USE) { + pr_warn("Password is already set for POWER LPAR Platform KeyStore\n"); + rc = 0; + } else { + goto out; + } + } +out: + kfree(password); + + return pseries_status_to_err(rc); +} + +static struct plpks_auth *construct_auth(u8 consumer) +{ + struct plpks_auth *auth; + + if (consumer > PKS_OS_OWNER) + return ERR_PTR(-EINVAL); + + auth = kmalloc(struct_size(auth, password, maxpwsize), GFP_KERNEL); + if (!auth) + return ERR_PTR(-ENOMEM); + + auth->version = 1; + auth->consumer = consumer; + auth->rsvd0 = 0; + auth->rsvd1 = 0; + + if (consumer == PKS_FW_OWNER || consumer == PKS_BOOTLOADER_OWNER) { + auth->passwordlength = 0; + return auth; + } + + memcpy(auth->password, ospassword, ospasswordlength); + + auth->passwordlength = cpu_to_be16(ospasswordlength); + + return auth; +} + +/** + * Label is combination of label attributes + name. + * Label attributes are used internally by kernel and not exposed to the user. + */ +static struct label *construct_label(char *component, u8 varos, u8 *name, + u16 namelen) +{ + struct label *label; + size_t slen; + + if (!name || namelen > MAX_NAME_SIZE) + return ERR_PTR(-EINVAL); + + slen = strlen(component); + if (component && slen > sizeof(label->attr.prefix)) + return ERR_PTR(-EINVAL); + + label = kzalloc(sizeof(*label), GFP_KERNEL); + if (!label) + return ERR_PTR(-ENOMEM); + + if (component) + memcpy(&label->attr.prefix, component, slen); + + label->attr.version = LABEL_VERSION; + label->attr.os = varos; + label->attr.length = MAX_LABEL_ATTR_SIZE; + memcpy(&label->name, name, namelen); + + label->size = sizeof(struct label_attr) + namelen; + + return label; +} + +static int _plpks_get_config(void) +{ + unsigned long retbuf[PLPAR_HCALL_BUFSIZE] = { 0 }; + struct { + u8 version; + u8 flags; + __be32 rsvd0; + __be16 maxpwsize; + __be16 maxobjlabelsize; + __be16 maxobjsize; + __be32 totalsize; + __be32 usedspace; + __be32 supportedpolicies; + __be64 rsvd1; + } __packed config; + size_t size; + int rc; + + size = sizeof(config); + + rc = plpar_hcall(H_PKS_GET_CONFIG, retbuf, virt_to_phys(&config), size); + + if (rc != H_SUCCESS) + return pseries_status_to_err(rc); + + maxpwsize = be16_to_cpu(config.maxpwsize); + maxobjsize = be16_to_cpu(config.maxobjsize); + + return 0; +} + +static int plpks_confirm_object_flushed(struct label *label, + struct plpks_auth *auth) +{ + unsigned long retbuf[PLPAR_HCALL_BUFSIZE] = { 0 }; + u64 timeout = 0; + u8 status; + int rc; + + do { + rc = plpar_hcall(H_PKS_CONFIRM_OBJECT_FLUSHED, retbuf, + virt_to_phys(auth), virt_to_phys(label), + label->size); + + status = retbuf[0]; + if (rc) { + if (rc == H_NOT_FOUND && status == 1) + rc = 0; + break; + } + + if (!rc && status == 1) + break; + + usleep_range(PKS_FLUSH_SLEEP, + PKS_FLUSH_SLEEP + PKS_FLUSH_SLEEP_RANGE); + timeout = timeout + PKS_FLUSH_SLEEP; + } while (timeout < PKS_FLUSH_MAX_TIMEOUT); + + rc = pseries_status_to_err(rc); + + return rc; +} + +int plpks_write_var(struct plpks_var var) +{ + unsigned long retbuf[PLPAR_HCALL_BUFSIZE] = { 0 }; + struct plpks_auth *auth; + struct label *label; + int rc; + + if (!var.component || !var.data || var.datalen <= 0 || + var.namelen > MAX_NAME_SIZE || var.datalen > MAX_DATA_SIZE) + return -EINVAL; + + if (var.policy & SIGNEDUPDATE) + return -EINVAL; + + auth = construct_auth(PKS_OS_OWNER); + if (IS_ERR(auth)) + return PTR_ERR(auth); + + label = construct_label(var.component, var.os, var.name, var.namelen); + if (IS_ERR(label)) { + rc = PTR_ERR(label); + goto out; + } + + rc = plpar_hcall(H_PKS_WRITE_OBJECT, retbuf, virt_to_phys(auth), + virt_to_phys(label), label->size, var.policy, + virt_to_phys(var.data), var.datalen); + + if (!rc) + rc = plpks_confirm_object_flushed(label, auth); + + if (rc) + pr_err("Failed to write variable %s for component %s with error %d\n", + var.name, var.component, rc); + + rc = pseries_status_to_err(rc); + kfree(label); +out: + kfree(auth); + + return rc; +} + +int plpks_remove_var(char *component, u8 varos, struct plpks_var_name vname) +{ + unsigned long retbuf[PLPAR_HCALL_BUFSIZE] = { 0 }; + struct plpks_auth *auth; + struct label *label; + int rc; + + if (!component || vname.namelen > MAX_NAME_SIZE) + return -EINVAL; + + auth = construct_auth(PKS_OS_OWNER); + if (IS_ERR(auth)) + return PTR_ERR(auth); + + label = construct_label(component, varos, vname.name, vname.namelen); + if (IS_ERR(label)) { + rc = PTR_ERR(label); + goto out; + } + + rc = plpar_hcall(H_PKS_REMOVE_OBJECT, retbuf, virt_to_phys(auth), + virt_to_phys(label), label->size); + + if (!rc) + rc = plpks_confirm_object_flushed(label, auth); + + if (rc) + pr_err("Failed to remove variable %s for component %s with error %d\n", + vname.name, component, rc); + + rc = pseries_status_to_err(rc); + kfree(label); +out: + kfree(auth); + + return rc; +} + +static int plpks_read_var(u8 consumer, struct plpks_var *var) +{ + unsigned long retbuf[PLPAR_HCALL_BUFSIZE] = { 0 }; + struct plpks_auth *auth; + struct label *label; + u8 *output; + int rc; + + if (var->namelen > MAX_NAME_SIZE) + return -EINVAL; + + auth = construct_auth(PKS_OS_OWNER); + if (IS_ERR(auth)) + return PTR_ERR(auth); + + label = construct_label(var->component, var->os, var->name, + var->namelen); + if (IS_ERR(label)) { + rc = PTR_ERR(label); + goto out_free_auth; + } + + output = kzalloc(maxobjsize, GFP_KERNEL); + if (!output) { + rc = -ENOMEM; + goto out_free_label; + } + + rc = plpar_hcall(H_PKS_READ_OBJECT, retbuf, virt_to_phys(auth), + virt_to_phys(label), label->size, virt_to_phys(output), + maxobjsize); + + if (rc != H_SUCCESS) { + pr_err("Failed to read variable %s for component %s with error %d\n", + var->name, var->component, rc); + rc = pseries_status_to_err(rc); + goto out_free_output; + } + + if (var->datalen == 0 || var->datalen > retbuf[0]) + var->datalen = retbuf[0]; + + var->data = kzalloc(var->datalen, GFP_KERNEL); + if (!var->data) { + rc = -ENOMEM; + goto out_free_output; + } + var->policy = retbuf[1]; + + memcpy(var->data, output, var->datalen); + rc = 0; + +out_free_output: + kfree(output); +out_free_label: + kfree(label); +out_free_auth: + kfree(auth); + + return rc; +} + +int plpks_read_os_var(struct plpks_var *var) +{ + return plpks_read_var(PKS_OS_OWNER, var); +} + +int plpks_read_fw_var(struct plpks_var *var) +{ + return plpks_read_var(PKS_FW_OWNER, var); +} + +int plpks_read_bootloader_var(struct plpks_var *var) +{ + return plpks_read_var(PKS_BOOTLOADER_OWNER, var); +} + +static __init int pseries_plpks_init(void) +{ + int rc; + + rc = _plpks_get_config(); + + if (rc) { + pr_err("POWER LPAR Platform KeyStore is not supported or enabled\n"); + return rc; + } + + rc = plpks_gen_password(); + if (rc) + pr_err("Failed setting POWER LPAR Platform KeyStore Password\n"); + else + pr_info("POWER LPAR Platform KeyStore initialized successfully\n"); + + return rc; +} +arch_initcall(pseries_plpks_init); diff --git a/arch/powerpc/platforms/pseries/plpks.h b/arch/powerpc/platforms/pseries/plpks.h new file mode 100644 index 000000000000..c6a291367bb1 --- /dev/null +++ b/arch/powerpc/platforms/pseries/plpks.h @@ -0,0 +1,71 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2022 IBM Corporation + * Author: Nayna Jain <nayna@linux.ibm.com> + * + * Platform keystore for pseries LPAR(PLPKS). + */ + +#ifndef _PSERIES_PLPKS_H +#define _PSERIES_PLPKS_H + +#include <linux/types.h> +#include <linux/list.h> + +#define OSSECBOOTAUDIT 0x40000000 +#define OSSECBOOTENFORCE 0x20000000 +#define WORLDREADABLE 0x08000000 +#define SIGNEDUPDATE 0x01000000 + +#define PLPKS_VAR_LINUX 0x01 +#define PLPKS_VAR_COMMON 0x04 + +struct plpks_var { + char *component; + u8 *name; + u8 *data; + u32 policy; + u16 namelen; + u16 datalen; + u8 os; +}; + +struct plpks_var_name { + u8 *name; + u16 namelen; +}; + +struct plpks_var_name_list { + u32 varcount; + struct plpks_var_name varlist[]; +}; + +/** + * Writes the specified var and its data to PKS. + * Any caller of PKS driver should present a valid component type for + * their variable. + */ +int plpks_write_var(struct plpks_var var); + +/** + * Removes the specified var and its data from PKS. + */ +int plpks_remove_var(char *component, u8 varos, + struct plpks_var_name vname); + +/** + * Returns the data for the specified os variable. + */ +int plpks_read_os_var(struct plpks_var *var); + +/** + * Returns the data for the specified firmware variable. + */ +int plpks_read_fw_var(struct plpks_var *var); + +/** + * Returns the data for the specified bootloader variable. + */ +int plpks_read_bootloader_var(struct plpks_var *var); + +#endif diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index ee4f1db49515..489f4c4df468 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -14,6 +14,7 @@ #include <linux/cpu.h> #include <linux/errno.h> +#include <linux/platform_device.h> #include <linux/sched.h> #include <linux/kernel.h> #include <linux/mm.h> @@ -72,6 +73,7 @@ #include <asm/svm.h> #include <asm/dtl.h> #include <asm/hvconsole.h> +#include <asm/setup.h> #include "pseries.h" @@ -169,6 +171,18 @@ static void __init fwnmi_init(void) #endif } +/* + * Affix a device for the first timer to the platform bus if + * we have firmware support for the H_WATCHDOG hypercall. + */ +static __init int pseries_wdt_init(void) +{ + if (firmware_has_feature(FW_FEATURE_WATCHDOG)) + platform_device_register_simple("pseries-wdt", 0, NULL, 0); + return 0; +} +machine_subsys_initcall(pseries, pseries_wdt_init); + static void pseries_8259_cascade(struct irq_desc *desc) { struct irq_chip *chip = irq_desc_get_chip(desc); @@ -802,9 +816,8 @@ static void __init pSeries_setup_arch(void) fwnmi_init(); pseries_setup_security_mitigations(); -#ifdef CONFIG_PPC_64S_HASH_MMU - pseries_lpar_read_hblkrm_characteristics(); -#endif + if (!radix_enabled()) + pseries_lpar_read_hblkrm_characteristics(); /* By default, only probe PCI (can be overridden by rtas_pci) */ pci_add_flags(PCI_PROBE_ONLY); diff --git a/arch/powerpc/platforms/pseries/vas.c b/arch/powerpc/platforms/pseries/vas.c index 500a1fc4a1d7..7e6e6dd2e33e 100644 --- a/arch/powerpc/platforms/pseries/vas.c +++ b/arch/powerpc/platforms/pseries/vas.c @@ -16,6 +16,7 @@ #include <asm/machdep.h> #include <asm/hvcall.h> #include <asm/plpar_wrappers.h> +#include <asm/firmware.h> #include <asm/vas.h> #include "vas.h" @@ -803,7 +804,7 @@ int vas_reconfig_capabilties(u8 type, int new_nr_creds) * The total number of available credits may be decreased or * increased with DLPAR operation. Means some windows have to be * closed / reopened. Hold the vas_pseries_mutex so that the - * the user space can not open new windows. + * user space can not open new windows. */ if (old_nr_creds < new_nr_creds) { /* diff --git a/arch/powerpc/purgatory/.gitignore b/arch/powerpc/purgatory/.gitignore index b8dc6ff34254..5e40575c1f2b 100644 --- a/arch/powerpc/purgatory/.gitignore +++ b/arch/powerpc/purgatory/.gitignore @@ -1,3 +1,2 @@ # SPDX-License-Identifier: GPL-2.0-only -kexec-purgatory.c purgatory.ro diff --git a/arch/powerpc/purgatory/Makefile b/arch/powerpc/purgatory/Makefile index 348f59581052..a81d155b89ae 100644 --- a/arch/powerpc/purgatory/Makefile +++ b/arch/powerpc/purgatory/Makefile @@ -2,17 +2,13 @@ KASAN_SANITIZE := n -targets += trampoline_$(BITS).o purgatory.ro kexec-purgatory.c +targets += trampoline_$(BITS).o purgatory.ro LDFLAGS_purgatory.ro := -e purgatory_start -r --no-undefined $(obj)/purgatory.ro: $(obj)/trampoline_$(BITS).o FORCE $(call if_changed,ld) -quiet_cmd_bin2c = BIN2C $@ - cmd_bin2c = $(objtree)/scripts/bin2c kexec_purgatory < $< > $@ - -$(obj)/kexec-purgatory.c: $(obj)/purgatory.ro FORCE - $(call if_changed,bin2c) +$(obj)/kexec-purgatory.o: $(obj)/purgatory.ro obj-y += kexec-purgatory.o diff --git a/arch/powerpc/purgatory/kexec-purgatory.S b/arch/powerpc/purgatory/kexec-purgatory.S new file mode 100644 index 000000000000..f494fd5a0526 --- /dev/null +++ b/arch/powerpc/purgatory/kexec-purgatory.S @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + + .section .rodata, "a" + + .align 8 +kexec_purgatory: + .globl kexec_purgatory + .incbin "arch/powerpc/purgatory/purgatory.ro" +.Lkexec_purgatory_end: + + .align 8 +kexec_purgatory_size: + .globl kexec_purgatory_size + .quad .Lkexec_purgatory_end - kexec_purgatory diff --git a/arch/powerpc/sysdev/cpm2.c b/arch/powerpc/sysdev/cpm2.c index 3f130312b6e9..915f4d3991c3 100644 --- a/arch/powerpc/sysdev/cpm2.c +++ b/arch/powerpc/sysdev/cpm2.c @@ -107,7 +107,7 @@ EXPORT_SYMBOL(cpm_command); * memory mapped space. * The baud rate clock is the system clock divided by something. * It was set up long ago during the initial boot phase and is - * is given to us. + * given to us. * Baud rate clocks are zero-based in the driver code (as that maps * to port numbers). Documentation uses 1-based numbering. */ diff --git a/arch/powerpc/sysdev/fsl_pci.c b/arch/powerpc/sysdev/fsl_pci.c index 1011cfea2e32..af6c8ca824d3 100644 --- a/arch/powerpc/sysdev/fsl_pci.c +++ b/arch/powerpc/sysdev/fsl_pci.c @@ -38,6 +38,7 @@ #include <asm/disassemble.h> #include <asm/ppc-opcode.h> #include <asm/swiotlb.h> +#include <asm/setup.h> #include <sysdev/fsl_soc.h> #include <sysdev/fsl_pci.h> @@ -521,6 +522,7 @@ int fsl_add_bridge(struct platform_device *pdev, int is_primary) struct resource rsrc; const int *bus_range; u8 hdr_type, progif; + u32 class_code; struct device_node *dev; struct ccsr_pci __iomem *pci; u16 temp; @@ -594,6 +596,13 @@ int fsl_add_bridge(struct platform_device *pdev, int is_primary) PPC_INDIRECT_TYPE_SURPRESS_PRIMARY_BUS; if (fsl_pcie_check_link(hose)) hose->indirect_type |= PPC_INDIRECT_TYPE_NO_PCIE_LINK; + /* Fix Class Code to PCI_CLASS_BRIDGE_PCI_NORMAL for pre-3.0 controller */ + if (in_be32(&pci->block_rev1) < PCIE_IP_REV_3_0) { + early_read_config_dword(hose, 0, 0, PCIE_FSL_CSR_CLASSCODE, &class_code); + class_code &= 0xff; + class_code |= PCI_CLASS_BRIDGE_PCI_NORMAL << 8; + early_write_config_dword(hose, 0, 0, PCIE_FSL_CSR_CLASSCODE, class_code); + } } else { /* * Set PBFR(PCI Bus Function Register)[10] = 1 to diff --git a/arch/powerpc/sysdev/fsl_pci.h b/arch/powerpc/sysdev/fsl_pci.h index cdbde2e0c96e..093a875d7d1e 100644 --- a/arch/powerpc/sysdev/fsl_pci.h +++ b/arch/powerpc/sysdev/fsl_pci.h @@ -18,6 +18,7 @@ struct platform_device; #define PCIE_LTSSM 0x0404 /* PCIE Link Training and Status */ #define PCIE_LTSSM_L0 0x16 /* L0 state */ +#define PCIE_FSL_CSR_CLASSCODE 0x474 /* FSL GPEX CSR */ #define PCIE_IP_REV_2_2 0x02080202 /* PCIE IP block version Rev2.2 */ #define PCIE_IP_REV_3_0 0x02080300 /* PCIE IP block version Rev3.0 */ #define PIWAR_EN 0x80000000 /* Enable */ diff --git a/arch/powerpc/sysdev/fsl_rio.c b/arch/powerpc/sysdev/fsl_rio.c index 1bfc9afa8a1a..4647c6074f3b 100644 --- a/arch/powerpc/sysdev/fsl_rio.c +++ b/arch/powerpc/sysdev/fsl_rio.c @@ -69,10 +69,10 @@ static DEFINE_SPINLOCK(fsl_rio_config_lock); -#define __fsl_read_rio_config(x, addr, err, op) \ +#define ___fsl_read_rio_config(x, addr, err, op, barrier) \ __asm__ __volatile__( \ "1: "op" %1,0(%2)\n" \ - " eieio\n" \ + " "barrier"\n" \ "2:\n" \ ".section .fixup,\"ax\"\n" \ "3: li %1,-1\n" \ @@ -83,6 +83,14 @@ static DEFINE_SPINLOCK(fsl_rio_config_lock); : "=r" (err), "=r" (x) \ : "b" (addr), "i" (-EFAULT), "0" (err)) +#ifdef CONFIG_BOOKE +#define __fsl_read_rio_config(x, addr, err, op) \ + ___fsl_read_rio_config(x, addr, err, op, "mbar") +#else +#define __fsl_read_rio_config(x, addr, err, op) \ + ___fsl_read_rio_config(x, addr, err, op, "eieio") +#endif + void __iomem *rio_regs_win; void __iomem *rmu_regs_win; resource_size_t rio_law_start; diff --git a/arch/powerpc/sysdev/mpc5xxx_clocks.c b/arch/powerpc/sysdev/mpc5xxx_clocks.c index 834a6d7fbd88..c5bf7e1b3780 100644 --- a/arch/powerpc/sysdev/mpc5xxx_clocks.c +++ b/arch/powerpc/sysdev/mpc5xxx_clocks.c @@ -1,31 +1,34 @@ // SPDX-License-Identifier: GPL-2.0 -/** - * mpc5xxx_get_bus_frequency - Find the bus frequency for a device - * @node: device node - * - * Returns bus frequency (IPS on MPC512x, IPB on MPC52xx), - * or 0 if the bus frequency cannot be found. - */ #include <linux/kernel.h> -#include <linux/of_platform.h> #include <linux/export.h> +#include <linux/property.h> + #include <asm/mpc5xxx.h> -unsigned long mpc5xxx_get_bus_frequency(struct device_node *node) +/** + * mpc5xxx_fwnode_get_bus_frequency - Find the bus frequency for a firmware node + * @fwnode: firmware node + * + * Returns bus frequency (IPS on MPC512x, IPB on MPC52xx), + * or 0 if the bus frequency cannot be found. + */ +unsigned long mpc5xxx_fwnode_get_bus_frequency(struct fwnode_handle *fwnode) { - const unsigned int *p_bus_freq = NULL; + struct fwnode_handle *parent; + u32 bus_freq; + int ret; - of_node_get(node); - while (node) { - p_bus_freq = of_get_property(node, "bus-frequency", NULL); - if (p_bus_freq) - break; + ret = fwnode_property_read_u32(fwnode, "bus-frequency", &bus_freq); + if (!ret) + return bus_freq; - node = of_get_next_parent(node); + fwnode_for_each_parent_node(fwnode, parent) { + ret = fwnode_property_read_u32(parent, "bus-frequency", &bus_freq); + if (!ret) + return bus_freq; } - of_node_put(node); - return p_bus_freq ? *p_bus_freq : 0; + return 0; } -EXPORT_SYMBOL(mpc5xxx_get_bus_frequency); +EXPORT_SYMBOL(mpc5xxx_fwnode_get_bus_frequency); diff --git a/arch/powerpc/sysdev/of_rtc.c b/arch/powerpc/sysdev/of_rtc.c index 1f408d34a6a7..420f949b7485 100644 --- a/arch/powerpc/sysdev/of_rtc.c +++ b/arch/powerpc/sysdev/of_rtc.c @@ -11,6 +11,8 @@ #include <linux/of_platform.h> #include <linux/slab.h> +#include <asm/prom.h> + static __initdata struct { const char *compatible; char *plat_name; diff --git a/arch/powerpc/sysdev/xive/spapr.c b/arch/powerpc/sysdev/xive/spapr.c index d02911e78cfc..e2c8f93b535b 100644 --- a/arch/powerpc/sysdev/xive/spapr.c +++ b/arch/powerpc/sysdev/xive/spapr.c @@ -718,6 +718,7 @@ static bool __init xive_get_max_prio(u8 *max_prio) } reg = of_get_property(rootdn, "ibm,plat-res-int-priorities", &len); + of_node_put(rootdn); if (!reg) { pr_err("Failed to read 'ibm,plat-res-int-priorities' property\n"); return false; diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index 3d9782ea3fa7..26ef3388c24c 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -116,7 +116,7 @@ struct bpt { static struct bpt bpts[NBPTS]; static struct bpt dabr[HBP_NUM_MAX]; static struct bpt *iabr; -static unsigned bpinstr = 0x7fe00008; /* trap */ +static unsigned int bpinstr = PPC_RAW_TRAP(); #define BP_NUM(bp) ((bp) - bpts + 1) @@ -3047,7 +3047,7 @@ generic_inst_dump(unsigned long adr, long count, int praddr, dotted = 0; last_inst = inst; if (praddr) - printf(REG" %s", adr, ppc_inst_as_str(inst)); + printf(REG" %08lx", adr, ppc_inst_as_ulong(inst)); printf("\t"); if (!ppc_inst_prefixed(inst)) dump_func(ppc_inst_val(inst), adr); |