diff options
Diffstat (limited to 'arch')
693 files changed, 6076 insertions, 3353 deletions
diff --git a/arch/Kconfig b/arch/Kconfig index a336548487e6..e3a030f7a722 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -366,6 +366,13 @@ config HAVE_RCU_TABLE_FREE config HAVE_RCU_TABLE_INVALIDATE bool +config ARCH_WANT_IRQS_OFF_ACTIVATE_MM + bool + help + Temporary select until all architectures can be converted to have + irqs disabled over activate_mm. Architectures that do IPI based TLB + shootdowns should enable this. + config ARCH_HAVE_NMI_SAFE_CMPXCHG bool diff --git a/arch/alpha/defconfig b/arch/alpha/defconfig index f4ec420d7f2d..3a132c91d45b 100644 --- a/arch/alpha/defconfig +++ b/arch/alpha/defconfig @@ -36,7 +36,6 @@ CONFIG_BLK_DEV_CY82C693=y CONFIG_SCSI=y CONFIG_BLK_DEV_SD=y CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_SCSI_AIC7XXX=m CONFIG_AIC7XXX_CMDS_PER_DEVICE=253 # CONFIG_AIC7XXX_DEBUG_ENABLE is not set diff --git a/arch/alpha/include/asm/io.h b/arch/alpha/include/asm/io.h index 4c533fc94d62..0bba9e991189 100644 --- a/arch/alpha/include/asm/io.h +++ b/arch/alpha/include/asm/io.h @@ -327,14 +327,18 @@ static inline int __is_mmio(const volatile void __iomem *addr) #if IO_CONCAT(__IO_PREFIX,trivial_io_bw) extern inline unsigned int ioread8(void __iomem *addr) { - unsigned int ret = IO_CONCAT(__IO_PREFIX,ioread8)(addr); + unsigned int ret; + mb(); + ret = IO_CONCAT(__IO_PREFIX,ioread8)(addr); mb(); return ret; } extern inline unsigned int ioread16(void __iomem *addr) { - unsigned int ret = IO_CONCAT(__IO_PREFIX,ioread16)(addr); + unsigned int ret; + mb(); + ret = IO_CONCAT(__IO_PREFIX,ioread16)(addr); mb(); return ret; } @@ -375,7 +379,9 @@ extern inline void outw(u16 b, unsigned long port) #if IO_CONCAT(__IO_PREFIX,trivial_io_lq) extern inline unsigned int ioread32(void __iomem *addr) { - unsigned int ret = IO_CONCAT(__IO_PREFIX,ioread32)(addr); + unsigned int ret; + mb(); + ret = IO_CONCAT(__IO_PREFIX,ioread32)(addr); mb(); return ret; } @@ -420,14 +426,18 @@ extern inline void __raw_writew(u16 b, volatile void __iomem *addr) extern inline u8 readb(const volatile void __iomem *addr) { - u8 ret = __raw_readb(addr); + u8 ret; + mb(); + ret = __raw_readb(addr); mb(); return ret; } extern inline u16 readw(const volatile void __iomem *addr) { - u16 ret = __raw_readw(addr); + u16 ret; + mb(); + ret = __raw_readw(addr); mb(); return ret; } @@ -468,14 +478,18 @@ extern inline void __raw_writeq(u64 b, volatile void __iomem *addr) extern inline u32 readl(const volatile void __iomem *addr) { - u32 ret = __raw_readl(addr); + u32 ret; + mb(); + ret = __raw_readl(addr); mb(); return ret; } extern inline u64 readq(const volatile void __iomem *addr) { - u64 ret = __raw_readq(addr); + u64 ret; + mb(); + ret = __raw_readq(addr); mb(); return ret; } @@ -493,10 +507,10 @@ extern inline void writeq(u64 b, volatile void __iomem *addr) } #endif -#define ioread16be(p) be16_to_cpu(ioread16(p)) -#define ioread32be(p) be32_to_cpu(ioread32(p)) -#define iowrite16be(v,p) iowrite16(cpu_to_be16(v), (p)) -#define iowrite32be(v,p) iowrite32(cpu_to_be32(v), (p)) +#define ioread16be(p) swab16(ioread16(p)) +#define ioread32be(p) swab32(ioread32(p)) +#define iowrite16be(v,p) iowrite16(swab16(v), (p)) +#define iowrite32be(v,p) iowrite32(swab32(v), (p)) #define inb_p inb #define inw_p inw @@ -504,14 +518,44 @@ extern inline void writeq(u64 b, volatile void __iomem *addr) #define outb_p outb #define outw_p outw #define outl_p outl -#define readb_relaxed(addr) __raw_readb(addr) -#define readw_relaxed(addr) __raw_readw(addr) -#define readl_relaxed(addr) __raw_readl(addr) -#define readq_relaxed(addr) __raw_readq(addr) -#define writeb_relaxed(b, addr) __raw_writeb(b, addr) -#define writew_relaxed(b, addr) __raw_writew(b, addr) -#define writel_relaxed(b, addr) __raw_writel(b, addr) -#define writeq_relaxed(b, addr) __raw_writeq(b, addr) + +extern u8 readb_relaxed(const volatile void __iomem *addr); +extern u16 readw_relaxed(const volatile void __iomem *addr); +extern u32 readl_relaxed(const volatile void __iomem *addr); +extern u64 readq_relaxed(const volatile void __iomem *addr); + +#if IO_CONCAT(__IO_PREFIX,trivial_io_bw) +extern inline u8 readb_relaxed(const volatile void __iomem *addr) +{ + mb(); + return __raw_readb(addr); +} + +extern inline u16 readw_relaxed(const volatile void __iomem *addr) +{ + mb(); + return __raw_readw(addr); +} +#endif + +#if IO_CONCAT(__IO_PREFIX,trivial_io_lq) +extern inline u32 readl_relaxed(const volatile void __iomem *addr) +{ + mb(); + return __raw_readl(addr); +} + +extern inline u64 readq_relaxed(const volatile void __iomem *addr) +{ + mb(); + return __raw_readq(addr); +} +#endif + +#define writeb_relaxed writeb +#define writew_relaxed writew +#define writel_relaxed writel +#define writeq_relaxed writeq #define mmiowb() diff --git a/arch/alpha/include/asm/uaccess.h b/arch/alpha/include/asm/uaccess.h index 87d8c4f0307d..7295967b5028 100644 --- a/arch/alpha/include/asm/uaccess.h +++ b/arch/alpha/include/asm/uaccess.h @@ -30,11 +30,13 @@ * Address valid if: * - "addr" doesn't have any high-bits set * - AND "size" doesn't have any high-bits set - * - AND "addr+size" doesn't have any high-bits set + * - AND "addr+size-(size != 0)" doesn't have any high-bits set * - OR we are in kernel mode. */ -#define __access_ok(addr, size) \ - ((get_fs().seg & (addr | size | (addr+size))) == 0) +#define __access_ok(addr, size) ({ \ + unsigned long __ao_a = (addr), __ao_b = (size); \ + unsigned long __ao_end = __ao_a + __ao_b - !!__ao_b; \ + (get_fs().seg & (__ao_a | __ao_b | __ao_end)) == 0; }) #define access_ok(type, addr, size) \ ({ \ diff --git a/arch/alpha/kernel/io.c b/arch/alpha/kernel/io.c index c025a3e5e357..938de13adfbf 100644 --- a/arch/alpha/kernel/io.c +++ b/arch/alpha/kernel/io.c @@ -16,21 +16,27 @@ unsigned int ioread8(void __iomem *addr) { - unsigned int ret = IO_CONCAT(__IO_PREFIX,ioread8)(addr); + unsigned int ret; + mb(); + ret = IO_CONCAT(__IO_PREFIX,ioread8)(addr); mb(); return ret; } unsigned int ioread16(void __iomem *addr) { - unsigned int ret = IO_CONCAT(__IO_PREFIX,ioread16)(addr); + unsigned int ret; + mb(); + ret = IO_CONCAT(__IO_PREFIX,ioread16)(addr); mb(); return ret; } unsigned int ioread32(void __iomem *addr) { - unsigned int ret = IO_CONCAT(__IO_PREFIX,ioread32)(addr); + unsigned int ret; + mb(); + ret = IO_CONCAT(__IO_PREFIX,ioread32)(addr); mb(); return ret; } @@ -148,28 +154,36 @@ EXPORT_SYMBOL(__raw_writeq); u8 readb(const volatile void __iomem *addr) { - u8 ret = __raw_readb(addr); + u8 ret; + mb(); + ret = __raw_readb(addr); mb(); return ret; } u16 readw(const volatile void __iomem *addr) { - u16 ret = __raw_readw(addr); + u16 ret; + mb(); + ret = __raw_readw(addr); mb(); return ret; } u32 readl(const volatile void __iomem *addr) { - u32 ret = __raw_readl(addr); + u32 ret; + mb(); + ret = __raw_readl(addr); mb(); return ret; } u64 readq(const volatile void __iomem *addr) { - u64 ret = __raw_readq(addr); + u64 ret; + mb(); + ret = __raw_readq(addr); mb(); return ret; } @@ -207,6 +221,38 @@ EXPORT_SYMBOL(writew); EXPORT_SYMBOL(writel); EXPORT_SYMBOL(writeq); +/* + * The _relaxed functions must be ordered w.r.t. each other, but they don't + * have to be ordered w.r.t. other memory accesses. + */ +u8 readb_relaxed(const volatile void __iomem *addr) +{ + mb(); + return __raw_readb(addr); +} + +u16 readw_relaxed(const volatile void __iomem *addr) +{ + mb(); + return __raw_readw(addr); +} + +u32 readl_relaxed(const volatile void __iomem *addr) +{ + mb(); + return __raw_readl(addr); +} + +u64 readq_relaxed(const volatile void __iomem *addr) +{ + mb(); + return __raw_readq(addr); +} + +EXPORT_SYMBOL(readb_relaxed); +EXPORT_SYMBOL(readw_relaxed); +EXPORT_SYMBOL(readl_relaxed); +EXPORT_SYMBOL(readq_relaxed); /* * Read COUNT 8-bit bytes from port PORT into memory starting at SRC. diff --git a/arch/arc/Makefile b/arch/arc/Makefile index 16e6cc22e25c..99c55f015ce8 100644 --- a/arch/arc/Makefile +++ b/arch/arc/Makefile @@ -91,14 +91,9 @@ libs-y += arch/arc/lib/ $(LIBGCC) boot := arch/arc/boot -#default target for make without any arguments. -KBUILD_IMAGE := $(boot)/bootpImage - -all: bootpImage -bootpImage: vmlinux - -boot_targets += uImage uImage.bin uImage.gz +boot_targets := uImage uImage.bin uImage.gz uImage.lzma +PHONY += $(boot_targets) $(boot_targets): vmlinux $(Q)$(MAKE) $(build)=$(boot) $(boot)/$@ diff --git a/arch/arc/boot/dts/hsdk.dts b/arch/arc/boot/dts/hsdk.dts index d131c54acd3e..f6b6e3c9ca8a 100644 --- a/arch/arc/boot/dts/hsdk.dts +++ b/arch/arc/boot/dts/hsdk.dts @@ -83,6 +83,8 @@ arcpct: pct { compatible = "snps,archs-pct"; + interrupt-parent = <&cpu_intc>; + interrupts = <20>; }; /* TIMER0 with interrupt for clockevent */ @@ -173,7 +175,7 @@ reg = <0x8000 0x2000>; interrupts = <10>; interrupt-names = "macirq"; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; snps,pbl = <32>; snps,multicast-filter-bins = <256>; clocks = <&gmacclk>; @@ -191,7 +193,7 @@ #address-cells = <1>; #size-cells = <0>; compatible = "snps,dwmac-mdio"; - phy0: ethernet-phy@0 { + phy0: ethernet-phy@0 { /* Micrel KSZ9031 */ reg = <0>; ti,rx-internal-delay = <DP83867_RGMIIDCTL_2_00_NS>; ti,tx-internal-delay = <DP83867_RGMIIDCTL_2_00_NS>; diff --git a/arch/arc/include/asm/elf.h b/arch/arc/include/asm/elf.h index aa2d6da9d187..12c74e826530 100644 --- a/arch/arc/include/asm/elf.h +++ b/arch/arc/include/asm/elf.h @@ -26,7 +26,7 @@ #define R_ARC_32_PCREL 0x31 /*to set parameters in the core dumps */ -#define ELF_ARCH EM_ARCOMPACT +#define ELF_ARCH EM_ARC_INUSE #define ELF_CLASS ELFCLASS32 #ifdef CONFIG_CPU_BIG_ENDIAN diff --git a/arch/arc/include/asm/page.h b/arch/arc/include/asm/page.h index 09ddddf71cc5..a70fef79c405 100644 --- a/arch/arc/include/asm/page.h +++ b/arch/arc/include/asm/page.h @@ -13,6 +13,7 @@ #ifndef __ASSEMBLY__ #define clear_page(paddr) memset((paddr), 0, PAGE_SIZE) +#define copy_user_page(to, from, vaddr, pg) copy_page(to, from) #define copy_page(to, from) memcpy((to), (from), PAGE_SIZE) struct vm_area_struct; diff --git a/arch/arc/kernel/entry.S b/arch/arc/kernel/entry.S index 85d9ea4a0acc..37ad245cf989 100644 --- a/arch/arc/kernel/entry.S +++ b/arch/arc/kernel/entry.S @@ -169,7 +169,7 @@ tracesys: ; Do the Sys Call as we normally would. ; Validate the Sys Call number - cmp r8, NR_syscalls + cmp r8, NR_syscalls - 1 mov.hi r0, -ENOSYS bhi tracesys_exit @@ -252,7 +252,7 @@ ENTRY(EV_Trap) ;============ Normal syscall case ; syscall num shd not exceed the total system calls avail - cmp r8, NR_syscalls + cmp r8, NR_syscalls - 1 mov.hi r0, -ENOSYS bhi .Lret_from_system_call diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c index 89c97dcfa360..c10994daee39 100644 --- a/arch/arc/kernel/setup.c +++ b/arch/arc/kernel/setup.c @@ -15,6 +15,7 @@ #include <linux/clocksource.h> #include <linux/console.h> #include <linux/module.h> +#include <linux/sizes.h> #include <linux/cpu.h> #include <linux/of_fdt.h> #include <linux/of.h> @@ -406,12 +407,12 @@ static void arc_chk_core_config(void) if ((unsigned int)__arc_dccm_base != cpu->dccm.base_addr) panic("Linux built with incorrect DCCM Base address\n"); - if (CONFIG_ARC_DCCM_SZ != cpu->dccm.sz) + if (CONFIG_ARC_DCCM_SZ * SZ_1K != cpu->dccm.sz) panic("Linux built with incorrect DCCM Size\n"); #endif #ifdef CONFIG_ARC_HAS_ICCM - if (CONFIG_ARC_ICCM_SZ != cpu->iccm.sz) + if (CONFIG_ARC_ICCM_SZ * SZ_1K != cpu->iccm.sz) panic("Linux built with incorrect ICCM Size\n"); #endif diff --git a/arch/arc/kernel/signal.c b/arch/arc/kernel/signal.c index 48685445002e..da243420bcb5 100644 --- a/arch/arc/kernel/signal.c +++ b/arch/arc/kernel/signal.c @@ -99,7 +99,7 @@ stash_usr_regs(struct rt_sigframe __user *sf, struct pt_regs *regs, sizeof(sf->uc.uc_mcontext.regs.scratch)); err |= __copy_to_user(&sf->uc.uc_sigmask, set, sizeof(sigset_t)); - return err; + return err ? -EFAULT : 0; } static int restore_usr_regs(struct pt_regs *regs, struct rt_sigframe __user *sf) @@ -113,7 +113,7 @@ static int restore_usr_regs(struct pt_regs *regs, struct rt_sigframe __user *sf) &(sf->uc.uc_mcontext.regs.scratch), sizeof(sf->uc.uc_mcontext.regs.scratch)); if (err) - return err; + return -EFAULT; set_current_blocked(&set); regs->bta = uregs.scratch.bta; diff --git a/arch/arc/kernel/stacktrace.c b/arch/arc/kernel/stacktrace.c index bf40e06f3fb8..a211e87aa6d9 100644 --- a/arch/arc/kernel/stacktrace.c +++ b/arch/arc/kernel/stacktrace.c @@ -41,15 +41,15 @@ #ifdef CONFIG_ARC_DW2_UNWIND -static void seed_unwind_frame_info(struct task_struct *tsk, - struct pt_regs *regs, - struct unwind_frame_info *frame_info) +static int +seed_unwind_frame_info(struct task_struct *tsk, struct pt_regs *regs, + struct unwind_frame_info *frame_info) { /* * synchronous unwinding (e.g. dump_stack) * - uses current values of SP and friends */ - if (tsk == NULL && regs == NULL) { + if (regs == NULL && (tsk == NULL || tsk == current)) { unsigned long fp, sp, blink, ret; frame_info->task = current; @@ -68,11 +68,15 @@ static void seed_unwind_frame_info(struct task_struct *tsk, frame_info->call_frame = 0; } else if (regs == NULL) { /* - * Asynchronous unwinding of sleeping task - * - Gets SP etc from task's pt_regs (saved bottom of kernel - * mode stack of task) + * Asynchronous unwinding of a likely sleeping task + * - first ensure it is actually sleeping + * - if so, it will be in __switch_to, kernel mode SP of task + * is safe-kept and BLINK at a well known location in there */ + if (tsk->state == TASK_RUNNING) + return -1; + frame_info->task = tsk; frame_info->regs.r27 = TSK_K_FP(tsk); @@ -106,6 +110,8 @@ static void seed_unwind_frame_info(struct task_struct *tsk, frame_info->regs.r63 = regs->ret; frame_info->call_frame = 0; } + + return 0; } #endif @@ -115,11 +121,12 @@ arc_unwind_core(struct task_struct *tsk, struct pt_regs *regs, int (*consumer_fn) (unsigned int, void *), void *arg) { #ifdef CONFIG_ARC_DW2_UNWIND - int ret = 0; + int ret = 0, cnt = 0; unsigned int address; struct unwind_frame_info frame_info; - seed_unwind_frame_info(tsk, regs, &frame_info); + if (seed_unwind_frame_info(tsk, regs, &frame_info)) + return 0; while (1) { address = UNW_PC(&frame_info); @@ -135,6 +142,11 @@ arc_unwind_core(struct task_struct *tsk, struct pt_regs *regs, break; frame_info.regs.r63 = frame_info.regs.r31; + + if (cnt++ > 128) { + printk("unwinder looping too long, aborting !\n"); + return 0; + } } return address; /* return the last address it saw */ diff --git a/arch/arc/plat-eznps/Kconfig b/arch/arc/plat-eznps/Kconfig index ce908e2c5282..71378bfec8d0 100644 --- a/arch/arc/plat-eznps/Kconfig +++ b/arch/arc/plat-eznps/Kconfig @@ -6,6 +6,7 @@ menuconfig ARC_PLAT_EZNPS bool "\"EZchip\" ARC dev platform" + depends on ISA_ARCOMPACT select CPU_BIG_ENDIAN select CLKSRC_NPS if !PHYS_ADDR_T_64BIT select EZNPS_GIC diff --git a/arch/arc/plat-eznps/include/plat/ctop.h b/arch/arc/plat-eznps/include/plat/ctop.h index 4f6a1673b3a6..ddfca2c3357a 100644 --- a/arch/arc/plat-eznps/include/plat/ctop.h +++ b/arch/arc/plat-eznps/include/plat/ctop.h @@ -43,7 +43,6 @@ #define CTOP_AUX_DPC (CTOP_AUX_BASE + 0x02C) #define CTOP_AUX_LPC (CTOP_AUX_BASE + 0x030) #define CTOP_AUX_EFLAGS (CTOP_AUX_BASE + 0x080) -#define CTOP_AUX_IACK (CTOP_AUX_BASE + 0x088) #define CTOP_AUX_GPA1 (CTOP_AUX_BASE + 0x08C) #define CTOP_AUX_UDMC (CTOP_AUX_BASE + 0x300) diff --git a/arch/arc/plat-hsdk/Kconfig b/arch/arc/plat-hsdk/Kconfig index c285a83cbf08..df35ea1912e8 100644 --- a/arch/arc/plat-hsdk/Kconfig +++ b/arch/arc/plat-hsdk/Kconfig @@ -11,5 +11,6 @@ menuconfig ARC_SOC_HSDK select ARC_HAS_ACCL_REGS select ARC_IRQ_NO_AUTOSAVE select CLK_HSDK + select RESET_CONTROLLER select RESET_HSDK select MIGHT_HAVE_PCI diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index e2f7c50dbace..1877da816f65 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -592,8 +592,10 @@ config ARCH_S3C24XX select HAVE_S3C2410_WATCHDOG if WATCHDOG select HAVE_S3C_RTC if RTC_CLASS select NEED_MACH_IO_H + select S3C2410_WATCHDOG select SAMSUNG_ATAGS select USE_OF + select WATCHDOG help Samsung S3C2410, S3C2412, S3C2413, S3C2416, S3C2440, S3C2442, S3C2443 and S3C2450 SoCs based systems, such as the Simtec Electronics BAST diff --git a/arch/arm/boot/compressed/Makefile b/arch/arm/boot/compressed/Makefile index 1f5a5ffe7fcf..ec2327a3796d 100644 --- a/arch/arm/boot/compressed/Makefile +++ b/arch/arm/boot/compressed/Makefile @@ -120,9 +120,9 @@ ccflags-y := -fpic $(call cc-option,-mno-single-pic-base,) -fno-builtin -I$(obj) asflags-y := -DZIMAGE # Supply kernel BSS size to the decompressor via a linker symbol. -KBSS_SZ = $(shell echo $$(($$($(CROSS_COMPILE)nm $(obj)/../../../../vmlinux | \ - sed -n -e 's/^\([^ ]*\) [AB] __bss_start$$/-0x\1/p' \ - -e 's/^\([^ ]*\) [AB] __bss_stop$$/+0x\1/p') )) ) +KBSS_SZ = $(shell echo $$(($$($(NM) $(obj)/../../../../vmlinux | \ + sed -n -e 's/^\([^ ]*\) [ABD] __bss_start$$/-0x\1/p' \ + -e 's/^\([^ ]*\) [ABD] __bss_stop$$/+0x\1/p') )) ) LDFLAGS_vmlinux = --defsym _kernel_bss_size=$(KBSS_SZ) # Supply ZRELADDR to the decompressor via a linker symbol. ifneq ($(CONFIG_AUTO_ZRELADDR),y) @@ -166,7 +166,7 @@ $(obj)/bswapsdi2.S: $(srctree)/arch/$(SRCARCH)/lib/bswapsdi2.S # The .data section is already discarded by the linker script so no need # to bother about it here. check_for_bad_syms = \ -bad_syms=$$($(CROSS_COMPILE)nm $@ | sed -n 's/^.\{8\} [bc] \(.*\)/\1/p') && \ +bad_syms=$$($(NM) $@ | sed -n 's/^.\{8\} [bc] \(.*\)/\1/p') && \ [ -z "$$bad_syms" ] || \ ( echo "following symbols must have non local/private scope:" >&2; \ echo "$$bad_syms" >&2; rm -f $@; false ) diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S index e205bbbe2794..69e661f574a0 100644 --- a/arch/arm/boot/compressed/head.S +++ b/arch/arm/boot/compressed/head.S @@ -1090,9 +1090,9 @@ __armv4_mmu_cache_off: __armv7_mmu_cache_off: mrc p15, 0, r0, c1, c0 #ifdef CONFIG_MMU - bic r0, r0, #0x000d + bic r0, r0, #0x0005 #else - bic r0, r0, #0x000c + bic r0, r0, #0x0004 #endif mcr p15, 0, r0, c1, c0 @ turn MMU and cache off mov r12, lr diff --git a/arch/arm/boot/compressed/vmlinux.lds.S b/arch/arm/boot/compressed/vmlinux.lds.S index 2b963d8e76dd..89a8f7588c78 100644 --- a/arch/arm/boot/compressed/vmlinux.lds.S +++ b/arch/arm/boot/compressed/vmlinux.lds.S @@ -46,7 +46,7 @@ SECTIONS } .table : ALIGN(4) { _table_start = .; - LONG(ZIMAGE_MAGIC(2)) + LONG(ZIMAGE_MAGIC(4)) LONG(ZIMAGE_MAGIC(0x5a534c4b)) LONG(ZIMAGE_MAGIC(__piggy_size_addr - _start)) LONG(ZIMAGE_MAGIC(_kernel_bss_size)) diff --git a/arch/arm/boot/dts/am33xx.dtsi b/arch/arm/boot/dts/am33xx.dtsi index d3dd6a16e70a..e321acaf35d6 100644 --- a/arch/arm/boot/dts/am33xx.dtsi +++ b/arch/arm/boot/dts/am33xx.dtsi @@ -39,6 +39,9 @@ ethernet1 = &cpsw_emac1; spi0 = &spi0; spi1 = &spi1; + mmc0 = &mmc1; + mmc1 = &mmc2; + mmc2 = &mmc3; }; cpus { diff --git a/arch/arm/boot/dts/armada-385-turris-omnia.dts b/arch/arm/boot/dts/armada-385-turris-omnia.dts index 768b6c5d2129..fde4c302f08e 100644 --- a/arch/arm/boot/dts/armada-385-turris-omnia.dts +++ b/arch/arm/boot/dts/armada-385-turris-omnia.dts @@ -236,6 +236,7 @@ status = "okay"; compatible = "ethernet-phy-id0141.0DD1", "ethernet-phy-ieee802.3-c22"; reg = <1>; + marvell,reg-init = <3 18 0 0x4985>; /* irq is connected to &pcawan pin 7 */ }; diff --git a/arch/arm/boot/dts/armada-388-helios4.dts b/arch/arm/boot/dts/armada-388-helios4.dts index 705adfa8c680..a94758090fb0 100644 --- a/arch/arm/boot/dts/armada-388-helios4.dts +++ b/arch/arm/boot/dts/armada-388-helios4.dts @@ -70,6 +70,9 @@ system-leds { compatible = "gpio-leds"; + pinctrl-names = "default"; + pinctrl-0 = <&helios_system_led_pins>; + status-led { label = "helios4:green:status"; gpios = <&gpio0 24 GPIO_ACTIVE_LOW>; @@ -86,6 +89,9 @@ io-leds { compatible = "gpio-leds"; + pinctrl-names = "default"; + pinctrl-0 = <&helios_io_led_pins>; + sata1-led { label = "helios4:green:ata1"; gpios = <&gpio1 17 GPIO_ACTIVE_LOW>; @@ -121,11 +127,15 @@ fan1: j10-pwm { compatible = "pwm-fan"; pwms = <&gpio1 9 40000>; /* Target freq:25 kHz */ + pinctrl-names = "default"; + pinctrl-0 = <&helios_fan1_pins>; }; fan2: j17-pwm { compatible = "pwm-fan"; pwms = <&gpio1 23 40000>; /* Target freq:25 kHz */ + pinctrl-names = "default"; + pinctrl-0 = <&helios_fan2_pins>; }; usb2_phy: usb2-phy { @@ -291,16 +301,22 @@ "mpp39", "mpp40"; marvell,function = "sd0"; }; - helios_led_pins: helios-led-pins { - marvell,pins = "mpp24", "mpp25", - "mpp49", "mpp50", + helios_system_led_pins: helios-system-led-pins { + marvell,pins = "mpp24", "mpp25"; + marvell,function = "gpio"; + }; + helios_io_led_pins: helios-io-led-pins { + marvell,pins = "mpp49", "mpp50", "mpp52", "mpp53", "mpp54"; marvell,function = "gpio"; }; - helios_fan_pins: helios-fan-pins { - marvell,pins = "mpp41", "mpp43", - "mpp48", "mpp55"; + helios_fan1_pins: helios_fan1_pins { + marvell,pins = "mpp41", "mpp43"; + marvell,function = "gpio"; + }; + helios_fan2_pins: helios_fan2_pins { + marvell,pins = "mpp48", "mpp55"; marvell,function = "gpio"; }; microsom_spi1_cs_pins: spi1-cs-pins { diff --git a/arch/arm/boot/dts/armada-xp-98dx3236.dtsi b/arch/arm/boot/dts/armada-xp-98dx3236.dtsi index 3e7d093d7a9a..966d9a6c40fc 100644 --- a/arch/arm/boot/dts/armada-xp-98dx3236.dtsi +++ b/arch/arm/boot/dts/armada-xp-98dx3236.dtsi @@ -266,11 +266,6 @@ reg = <0x11000 0x100>; }; -&i2c1 { - compatible = "marvell,mv78230-i2c", "marvell,mv64xxx-i2c"; - reg = <0x11100 0x100>; -}; - &mpic { reg = <0x20a00 0x2d0>, <0x21070 0x58>; }; diff --git a/arch/arm/boot/dts/aspeed-bmc-intel-s2600wf.dts b/arch/arm/boot/dts/aspeed-bmc-intel-s2600wf.dts index 22dade6393d0..d1dbe3b6ad5a 100644 --- a/arch/arm/boot/dts/aspeed-bmc-intel-s2600wf.dts +++ b/arch/arm/boot/dts/aspeed-bmc-intel-s2600wf.dts @@ -22,9 +22,9 @@ #size-cells = <1>; ranges; - vga_memory: framebuffer@7f000000 { + vga_memory: framebuffer@9f000000 { no-map; - reg = <0x7f000000 0x01000000>; + reg = <0x9f000000 0x01000000>; /* 16M */ }; }; diff --git a/arch/arm/boot/dts/aspeed-g4.dtsi b/arch/arm/boot/dts/aspeed-g4.dtsi index 69f6b9d2e7e7..2af093759143 100644 --- a/arch/arm/boot/dts/aspeed-g4.dtsi +++ b/arch/arm/boot/dts/aspeed-g4.dtsi @@ -312,6 +312,7 @@ compatible = "aspeed,ast2400-ibt-bmc"; reg = <0xc0 0x18>; interrupts = <8>; + clocks = <&syscon ASPEED_CLK_GATE_LCLK>; status = "disabled"; }; }; diff --git a/arch/arm/boot/dts/aspeed-g5.dtsi b/arch/arm/boot/dts/aspeed-g5.dtsi index f2e1015d75ab..bcd57e6c51e5 100644 --- a/arch/arm/boot/dts/aspeed-g5.dtsi +++ b/arch/arm/boot/dts/aspeed-g5.dtsi @@ -372,6 +372,7 @@ compatible = "aspeed,ast2500-ibt-bmc"; reg = <0xc0 0x18>; interrupts = <8>; + clocks = <&syscon ASPEED_CLK_GATE_LCLK>; status = "disabled"; }; }; diff --git a/arch/arm/boot/dts/at91-sama5d27_som1.dtsi b/arch/arm/boot/dts/at91-sama5d27_som1.dtsi index cf0087b4c9e1..ea02a51c71e2 100644 --- a/arch/arm/boot/dts/at91-sama5d27_som1.dtsi +++ b/arch/arm/boot/dts/at91-sama5d27_som1.dtsi @@ -67,8 +67,8 @@ pinctrl-0 = <&pinctrl_macb0_default>; phy-mode = "rmii"; - ethernet-phy@0 { - reg = <0x0>; + ethernet-phy@7 { + reg = <0x7>; interrupt-parent = <&pioA>; interrupts = <PIN_PD31 IRQ_TYPE_LEVEL_LOW>; pinctrl-names = "default"; diff --git a/arch/arm/boot/dts/at91-sama5d2_ptc_ek.dts b/arch/arm/boot/dts/at91-sama5d2_ptc_ek.dts index 2214bfe7aa20..7c611f5555a4 100644 --- a/arch/arm/boot/dts/at91-sama5d2_ptc_ek.dts +++ b/arch/arm/boot/dts/at91-sama5d2_ptc_ek.dts @@ -40,7 +40,7 @@ ahb { usb0: gadget@300000 { - atmel,vbus-gpio = <&pioA PIN_PA27 GPIO_ACTIVE_HIGH>; + atmel,vbus-gpio = <&pioA PIN_PB11 GPIO_ACTIVE_HIGH>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_usba_vbus>; status = "okay"; @@ -125,8 +125,6 @@ bus-width = <8>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_sdmmc0_default>; - non-removable; - mmc-ddr-1_8v; status = "okay"; }; diff --git a/arch/arm/boot/dts/at91-sama5d3_xplained.dts b/arch/arm/boot/dts/at91-sama5d3_xplained.dts index 02c1d2958d78..74440dad4335 100644 --- a/arch/arm/boot/dts/at91-sama5d3_xplained.dts +++ b/arch/arm/boot/dts/at91-sama5d3_xplained.dts @@ -243,6 +243,11 @@ atmel,pins = <AT91_PIOE 9 AT91_PERIPH_GPIO AT91_PINCTRL_DEGLITCH>; /* PE9, conflicts with A9 */ }; + pinctrl_usb_default: usb_default { + atmel,pins = + <AT91_PIOE 3 AT91_PERIPH_GPIO AT91_PINCTRL_NONE + AT91_PIOE 4 AT91_PERIPH_GPIO AT91_PINCTRL_NONE>; + }; }; }; }; @@ -260,6 +265,8 @@ &pioE 3 GPIO_ACTIVE_LOW &pioE 4 GPIO_ACTIVE_LOW >; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_usb_default>; status = "okay"; }; diff --git a/arch/arm/boot/dts/at91-sama5d4_xplained.dts b/arch/arm/boot/dts/at91-sama5d4_xplained.dts index 7d554b9ab27f..e998d72d8b10 100644 --- a/arch/arm/boot/dts/at91-sama5d4_xplained.dts +++ b/arch/arm/boot/dts/at91-sama5d4_xplained.dts @@ -170,6 +170,11 @@ atmel,pins = <AT91_PIOE 31 AT91_PERIPH_GPIO AT91_PINCTRL_DEGLITCH>; }; + pinctrl_usb_default: usb_default { + atmel,pins = + <AT91_PIOE 11 AT91_PERIPH_GPIO AT91_PINCTRL_NONE + AT91_PIOE 14 AT91_PERIPH_GPIO AT91_PINCTRL_NONE>; + }; pinctrl_key_gpio: key_gpio_0 { atmel,pins = <AT91_PIOE 8 AT91_PERIPH_GPIO AT91_PINCTRL_PULL_UP_DEGLITCH>; @@ -195,6 +200,8 @@ &pioE 11 GPIO_ACTIVE_HIGH &pioE 14 GPIO_ACTIVE_HIGH >; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_usb_default>; status = "okay"; }; diff --git a/arch/arm/boot/dts/at91sam9rl.dtsi b/arch/arm/boot/dts/at91sam9rl.dtsi index ad495f5a5790..cdf016232fb7 100644 --- a/arch/arm/boot/dts/at91sam9rl.dtsi +++ b/arch/arm/boot/dts/at91sam9rl.dtsi @@ -277,23 +277,26 @@ atmel,adc-use-res = "highres"; trigger0 { - trigger-name = "timer-counter-0"; + trigger-name = "external-rising"; trigger-value = <0x1>; + trigger-external; }; + trigger1 { - trigger-name = "timer-counter-1"; - trigger-value = <0x3>; + trigger-name = "external-falling"; + trigger-value = <0x2>; + trigger-external; }; trigger2 { - trigger-name = "timer-counter-2"; - trigger-value = <0x5>; + trigger-name = "external-any"; + trigger-value = <0x3>; + trigger-external; }; trigger3 { - trigger-name = "external"; - trigger-value = <0x13>; - trigger-external; + trigger-name = "continuous"; + trigger-value = <0x6>; }; }; diff --git a/arch/arm/boot/dts/bcm-hr2.dtsi b/arch/arm/boot/dts/bcm-hr2.dtsi index e4d49731287f..dd71ab08136b 100644 --- a/arch/arm/boot/dts/bcm-hr2.dtsi +++ b/arch/arm/boot/dts/bcm-hr2.dtsi @@ -75,7 +75,7 @@ timer@20200 { compatible = "arm,cortex-a9-global-timer"; reg = <0x20200 0x100>; - interrupts = <GIC_PPI 11 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_PPI 11 IRQ_TYPE_EDGE_RISING>; clocks = <&periph_clk>; }; @@ -83,7 +83,7 @@ compatible = "arm,cortex-a9-twd-timer"; reg = <0x20600 0x20>; interrupts = <GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(1) | - IRQ_TYPE_LEVEL_HIGH)>; + IRQ_TYPE_EDGE_RISING)>; clocks = <&periph_clk>; }; @@ -91,7 +91,7 @@ compatible = "arm,cortex-a9-twd-wdt"; reg = <0x20620 0x20>; interrupts = <GIC_PPI 14 (GIC_CPU_MASK_SIMPLE(1) | - IRQ_TYPE_LEVEL_HIGH)>; + IRQ_TYPE_EDGE_RISING)>; clocks = <&periph_clk>; }; @@ -217,7 +217,7 @@ }; qspi: spi@27200 { - compatible = "brcm,spi-bcm-qspi", "brcm,spi-nsp-qspi"; + compatible = "brcm,spi-nsp-qspi", "brcm,spi-bcm-qspi"; reg = <0x027200 0x184>, <0x027000 0x124>, <0x11c408 0x004>, diff --git a/arch/arm/boot/dts/bcm-nsp.dtsi b/arch/arm/boot/dts/bcm-nsp.dtsi index 2b219addeb44..b395cb195db2 100644 --- a/arch/arm/boot/dts/bcm-nsp.dtsi +++ b/arch/arm/boot/dts/bcm-nsp.dtsi @@ -249,10 +249,10 @@ status = "disabled"; }; - mailbox: mailbox@25000 { + mailbox: mailbox@25c00 { compatible = "brcm,iproc-fa2-mbox"; - reg = <0x25000 0x445>; - interrupts = <GIC_SPI 150 IRQ_TYPE_LEVEL_HIGH>; + reg = <0x25c00 0x400>; + interrupts = <GIC_SPI 151 IRQ_TYPE_LEVEL_HIGH>; #mbox-cells = <1>; brcm,rx-status-len = <32>; brcm,use-bcm-hdr; @@ -274,7 +274,7 @@ }; qspi: spi@27200 { - compatible = "brcm,spi-bcm-qspi", "brcm,spi-nsp-qspi"; + compatible = "brcm,spi-nsp-qspi", "brcm,spi-bcm-qspi"; reg = <0x027200 0x184>, <0x027000 0x124>, <0x11c408 0x004>, diff --git a/arch/arm/boot/dts/bcm2835-rpi-zero-w.dts b/arch/arm/boot/dts/bcm2835-rpi-zero-w.dts index 5fcadb9cf992..9f7145b1cc5e 100644 --- a/arch/arm/boot/dts/bcm2835-rpi-zero-w.dts +++ b/arch/arm/boot/dts/bcm2835-rpi-zero-w.dts @@ -25,7 +25,7 @@ leds { act { - gpios = <&gpio 47 GPIO_ACTIVE_HIGH>; + gpios = <&gpio 47 GPIO_ACTIVE_LOW>; }; }; diff --git a/arch/arm/boot/dts/bcm283x.dtsi b/arch/arm/boot/dts/bcm283x.dtsi index c9322a56300d..f9add515301f 100644 --- a/arch/arm/boot/dts/bcm283x.dtsi +++ b/arch/arm/boot/dts/bcm283x.dtsi @@ -476,6 +476,7 @@ "dsi0_ddr2", "dsi0_ddr"; + status = "disabled"; }; thermal: thermal@7e212000 { diff --git a/arch/arm/boot/dts/bcm5301x.dtsi b/arch/arm/boot/dts/bcm5301x.dtsi index a678fb7c9e3b..c91716d5980c 100644 --- a/arch/arm/boot/dts/bcm5301x.dtsi +++ b/arch/arm/boot/dts/bcm5301x.dtsi @@ -445,7 +445,7 @@ }; spi@18029200 { - compatible = "brcm,spi-bcm-qspi", "brcm,spi-nsp-qspi"; + compatible = "brcm,spi-nsp-qspi", "brcm,spi-bcm-qspi"; reg = <0x18029200 0x184>, <0x18029000 0x124>, <0x1811b408 0x004>, diff --git a/arch/arm/boot/dts/dra7.dtsi b/arch/arm/boot/dts/dra7.dtsi index e97ef16ce68a..0c0781a37c5a 100644 --- a/arch/arm/boot/dts/dra7.dtsi +++ b/arch/arm/boot/dts/dra7.dtsi @@ -312,6 +312,7 @@ #address-cells = <1>; ranges = <0x51000000 0x51000000 0x3000 0x0 0x20000000 0x10000000>; + dma-ranges; /** * To enable PCI endpoint mode, disable the pcie1_rc * node and enable pcie1_ep mode. @@ -325,7 +326,6 @@ device_type = "pci"; ranges = <0x81000000 0 0 0x03000 0 0x00010000 0x82000000 0 0x20013000 0x13000 0 0xffed000>; - dma-ranges = <0x02000000 0x0 0x00000000 0x00000000 0x1 0x00000000>; bus-range = <0x00 0xff>; #interrupt-cells = <1>; num-lanes = <1>; @@ -368,6 +368,7 @@ #address-cells = <1>; ranges = <0x51800000 0x51800000 0x3000 0x0 0x30000000 0x10000000>; + dma-ranges; status = "disabled"; pcie2_rc: pcie@51800000 { reg = <0x51800000 0x2000>, <0x51802000 0x14c>, <0x1000 0x2000>; @@ -378,7 +379,6 @@ device_type = "pci"; ranges = <0x81000000 0 0 0x03000 0 0x00010000 0x82000000 0 0x30013000 0x13000 0 0xffed000>; - dma-ranges = <0x02000000 0x0 0x00000000 0x00000000 0x1 0x00000000>; bus-range = <0x00 0xff>; #interrupt-cells = <1>; num-lanes = <1>; diff --git a/arch/arm/boot/dts/dra76x.dtsi b/arch/arm/boot/dts/dra76x.dtsi index 216e1d1a69c7..473d6721b788 100644 --- a/arch/arm/boot/dts/dra76x.dtsi +++ b/arch/arm/boot/dts/dra76x.dtsi @@ -35,8 +35,8 @@ interrupts = <GIC_SPI 67 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 68 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "int0", "int1"; - clocks = <&mcan_clk>, <&l3_iclk_div>; - clock-names = "cclk", "hclk"; + clocks = <&l3_iclk_div>, <&mcan_clk>; + clock-names = "hclk", "cclk"; bosch,mram-cfg = <0x0 0 0 32 0 0 1 1>; }; }; diff --git a/arch/arm/boot/dts/exynos3250-artik5.dtsi b/arch/arm/boot/dts/exynos3250-artik5.dtsi index 7c22cbf6f3d4..6e30db644c83 100644 --- a/arch/arm/boot/dts/exynos3250-artik5.dtsi +++ b/arch/arm/boot/dts/exynos3250-artik5.dtsi @@ -68,7 +68,7 @@ s2mps14_pmic@66 { compatible = "samsung,s2mps14-pmic"; interrupt-parent = <&gpx3>; - interrupts = <5 IRQ_TYPE_NONE>; + interrupts = <5 IRQ_TYPE_LEVEL_LOW>; pinctrl-names = "default"; pinctrl-0 = <&s2mps14_irq>; reg = <0x66>; diff --git a/arch/arm/boot/dts/exynos3250-monk.dts b/arch/arm/boot/dts/exynos3250-monk.dts index 6ffedf4ed9f2..d343dc13ceec 100644 --- a/arch/arm/boot/dts/exynos3250-monk.dts +++ b/arch/arm/boot/dts/exynos3250-monk.dts @@ -188,7 +188,7 @@ s2mps14_pmic@66 { compatible = "samsung,s2mps14-pmic"; interrupt-parent = <&gpx0>; - interrupts = <7 IRQ_TYPE_NONE>; + interrupts = <7 IRQ_TYPE_LEVEL_LOW>; reg = <0x66>; wakeup-source; diff --git a/arch/arm/boot/dts/exynos3250-rinato.dts b/arch/arm/boot/dts/exynos3250-rinato.dts index 2a6b828c01b7..29df4cfa9165 100644 --- a/arch/arm/boot/dts/exynos3250-rinato.dts +++ b/arch/arm/boot/dts/exynos3250-rinato.dts @@ -253,7 +253,7 @@ s2mps14_pmic@66 { compatible = "samsung,s2mps14-pmic"; interrupt-parent = <&gpx0>; - interrupts = <7 IRQ_TYPE_NONE>; + interrupts = <7 IRQ_TYPE_LEVEL_LOW>; reg = <0x66>; wakeup-source; diff --git a/arch/arm/boot/dts/exynos4412-galaxy-s3.dtsi b/arch/arm/boot/dts/exynos4412-galaxy-s3.dtsi index 30eee5942eff..945ee8f55e65 100644 --- a/arch/arm/boot/dts/exynos4412-galaxy-s3.dtsi +++ b/arch/arm/boot/dts/exynos4412-galaxy-s3.dtsi @@ -50,7 +50,7 @@ i2c_cm36651: i2c-gpio-2 { compatible = "i2c-gpio"; - gpios = <&gpf0 0 GPIO_ACTIVE_LOW>, <&gpf0 1 GPIO_ACTIVE_LOW>; + gpios = <&gpf0 0 GPIO_ACTIVE_HIGH>, <&gpf0 1 GPIO_ACTIVE_HIGH>; i2c-gpio,delay-us = <2>; #address-cells = <1>; #size-cells = <0>; diff --git a/arch/arm/boot/dts/exynos4412-midas.dtsi b/arch/arm/boot/dts/exynos4412-midas.dtsi index c0476c290977..60fbad25b5f2 100644 --- a/arch/arm/boot/dts/exynos4412-midas.dtsi +++ b/arch/arm/boot/dts/exynos4412-midas.dtsi @@ -139,7 +139,7 @@ max77693@66 { compatible = "maxim,max77693"; interrupt-parent = <&gpx1>; - interrupts = <5 IRQ_TYPE_EDGE_FALLING>; + interrupts = <5 IRQ_TYPE_LEVEL_LOW>; pinctrl-names = "default"; pinctrl-0 = <&max77693_irq>; reg = <0x66>; @@ -187,7 +187,7 @@ max77693-fuel-gauge@36 { compatible = "maxim,max17047"; interrupt-parent = <&gpx2>; - interrupts = <3 IRQ_TYPE_EDGE_FALLING>; + interrupts = <3 IRQ_TYPE_LEVEL_LOW>; pinctrl-names = "default"; pinctrl-0 = <&max77693_fuel_irq>; reg = <0x36>; @@ -579,7 +579,7 @@ max77686: max77686_pmic@9 { compatible = "maxim,max77686"; interrupt-parent = <&gpx0>; - interrupts = <7 IRQ_TYPE_NONE>; + interrupts = <7 IRQ_TYPE_LEVEL_LOW>; pinctrl-0 = <&max77686_irq>; pinctrl-names = "default"; reg = <0x09>; diff --git a/arch/arm/boot/dts/exynos4412-odroid-common.dtsi b/arch/arm/boot/dts/exynos4412-odroid-common.dtsi index 00820d239753..dbca8eeefae1 100644 --- a/arch/arm/boot/dts/exynos4412-odroid-common.dtsi +++ b/arch/arm/boot/dts/exynos4412-odroid-common.dtsi @@ -265,7 +265,7 @@ max77686: pmic@9 { compatible = "maxim,max77686"; interrupt-parent = <&gpx3>; - interrupts = <2 IRQ_TYPE_NONE>; + interrupts = <2 IRQ_TYPE_LEVEL_LOW>; pinctrl-names = "default"; pinctrl-0 = <&max77686_irq>; reg = <0x09>; diff --git a/arch/arm/boot/dts/exynos5250-smdk5250.dts b/arch/arm/boot/dts/exynos5250-smdk5250.dts index d5e66189ed2a..594b246afbed 100644 --- a/arch/arm/boot/dts/exynos5250-smdk5250.dts +++ b/arch/arm/boot/dts/exynos5250-smdk5250.dts @@ -132,7 +132,7 @@ compatible = "maxim,max77686"; reg = <0x09>; interrupt-parent = <&gpx3>; - interrupts = <2 IRQ_TYPE_NONE>; + interrupts = <2 IRQ_TYPE_LEVEL_LOW>; pinctrl-names = "default"; pinctrl-0 = <&max77686_irq>; wakeup-source; diff --git a/arch/arm/boot/dts/exynos5250-snow-common.dtsi b/arch/arm/boot/dts/exynos5250-snow-common.dtsi index fd9226d3b207..3981acb00b5e 100644 --- a/arch/arm/boot/dts/exynos5250-snow-common.dtsi +++ b/arch/arm/boot/dts/exynos5250-snow-common.dtsi @@ -292,7 +292,7 @@ max77686: max77686@9 { compatible = "maxim,max77686"; interrupt-parent = <&gpx3>; - interrupts = <2 IRQ_TYPE_NONE>; + interrupts = <2 IRQ_TYPE_LEVEL_LOW>; pinctrl-names = "default"; pinctrl-0 = <&max77686_irq>; wakeup-source; diff --git a/arch/arm/boot/dts/exynos5250-spring.dts b/arch/arm/boot/dts/exynos5250-spring.dts index 3d501926c227..2355c5316484 100644 --- a/arch/arm/boot/dts/exynos5250-spring.dts +++ b/arch/arm/boot/dts/exynos5250-spring.dts @@ -108,7 +108,7 @@ compatible = "samsung,s5m8767-pmic"; reg = <0x66>; interrupt-parent = <&gpx3>; - interrupts = <2 IRQ_TYPE_NONE>; + interrupts = <2 IRQ_TYPE_LEVEL_LOW>; pinctrl-names = "default"; pinctrl-0 = <&s5m8767_irq &s5m8767_dvs &s5m8767_ds>; wakeup-source; diff --git a/arch/arm/boot/dts/exynos5410-odroidxu.dts b/arch/arm/boot/dts/exynos5410-odroidxu.dts index a2046f5f998c..840a854ee838 100644 --- a/arch/arm/boot/dts/exynos5410-odroidxu.dts +++ b/arch/arm/boot/dts/exynos5410-odroidxu.dts @@ -324,6 +324,8 @@ regulator-name = "vddq_lcd"; regulator-min-microvolt = <1800000>; regulator-max-microvolt = <1800000>; + /* Supplies also GPK and GPJ */ + regulator-always-on; }; ldo8_reg: LDO8 { @@ -626,11 +628,11 @@ }; &usbdrd_dwc3_0 { - dr_mode = "host"; + dr_mode = "peripheral"; }; &usbdrd_dwc3_1 { - dr_mode = "peripheral"; + dr_mode = "host"; }; &usbdrd3_0 { diff --git a/arch/arm/boot/dts/exynos5410-pinctrl.dtsi b/arch/arm/boot/dts/exynos5410-pinctrl.dtsi index 369a8a7f2105..481ee99aa9c9 100644 --- a/arch/arm/boot/dts/exynos5410-pinctrl.dtsi +++ b/arch/arm/boot/dts/exynos5410-pinctrl.dtsi @@ -560,6 +560,34 @@ interrupt-controller; #interrupt-cells = <2>; }; + + usb3_1_oc: usb3-1-oc { + samsung,pins = "gpk2-4", "gpk2-5"; + samsung,pin-function = <EXYNOS_PIN_FUNC_2>; + samsung,pin-pud = <EXYNOS_PIN_PULL_UP>; + samsung,pin-drv = <EXYNOS5420_PIN_DRV_LV1>; + }; + + usb3_1_vbusctrl: usb3-1-vbusctrl { + samsung,pins = "gpk2-6", "gpk2-7"; + samsung,pin-function = <EXYNOS_PIN_FUNC_2>; + samsung,pin-pud = <EXYNOS_PIN_PULL_DOWN>; + samsung,pin-drv = <EXYNOS5420_PIN_DRV_LV1>; + }; + + usb3_0_oc: usb3-0-oc { + samsung,pins = "gpk3-0", "gpk3-1"; + samsung,pin-function = <EXYNOS_PIN_FUNC_2>; + samsung,pin-pud = <EXYNOS_PIN_PULL_UP>; + samsung,pin-drv = <EXYNOS5420_PIN_DRV_LV1>; + }; + + usb3_0_vbusctrl: usb3-0-vbusctrl { + samsung,pins = "gpk3-2", "gpk3-3"; + samsung,pin-function = <EXYNOS_PIN_FUNC_2>; + samsung,pin-pud = <EXYNOS_PIN_PULL_DOWN>; + samsung,pin-drv = <EXYNOS5420_PIN_DRV_LV1>; + }; }; &pinctrl_2 { diff --git a/arch/arm/boot/dts/exynos5410.dtsi b/arch/arm/boot/dts/exynos5410.dtsi index 57fc9c949e54..95b794b1ea62 100644 --- a/arch/arm/boot/dts/exynos5410.dtsi +++ b/arch/arm/boot/dts/exynos5410.dtsi @@ -392,6 +392,8 @@ &usbdrd3_0 { clocks = <&clock CLK_USBD300>; clock-names = "usbdrd30"; + pinctrl-names = "default"; + pinctrl-0 = <&usb3_0_oc>, <&usb3_0_vbusctrl>; }; &usbdrd_phy0 { @@ -403,6 +405,8 @@ &usbdrd3_1 { clocks = <&clock CLK_USBD301>; clock-names = "usbdrd30"; + pinctrl-names = "default"; + pinctrl-0 = <&usb3_1_oc>, <&usb3_1_vbusctrl>; }; &usbdrd_dwc3_1 { diff --git a/arch/arm/boot/dts/exynos5420-arndale-octa.dts b/arch/arm/boot/dts/exynos5420-arndale-octa.dts index a370857beac0..fbaca74cbaea 100644 --- a/arch/arm/boot/dts/exynos5420-arndale-octa.dts +++ b/arch/arm/boot/dts/exynos5420-arndale-octa.dts @@ -84,7 +84,7 @@ reg = <0x66>; interrupt-parent = <&gpx3>; - interrupts = <2 IRQ_TYPE_EDGE_FALLING>; + interrupts = <2 IRQ_TYPE_LEVEL_LOW>; pinctrl-names = "default"; pinctrl-0 = <&s2mps11_irq>; diff --git a/arch/arm/boot/dts/exynos5422-odroid-core.dtsi b/arch/arm/boot/dts/exynos5422-odroid-core.dtsi index d476ba0f07b6..ba7187a74be3 100644 --- a/arch/arm/boot/dts/exynos5422-odroid-core.dtsi +++ b/arch/arm/boot/dts/exynos5422-odroid-core.dtsi @@ -136,7 +136,7 @@ samsung,s2mps11-acokb-ground; interrupt-parent = <&gpx0>; - interrupts = <4 IRQ_TYPE_EDGE_FALLING>; + interrupts = <4 IRQ_TYPE_LEVEL_LOW>; pinctrl-names = "default"; pinctrl-0 = <&s2mps11_irq>; diff --git a/arch/arm/boot/dts/imx27-phytec-phycard-s-rdk.dts b/arch/arm/boot/dts/imx27-phytec-phycard-s-rdk.dts index bfd4946cf9fe..8b63b6593d3a 100644 --- a/arch/arm/boot/dts/imx27-phytec-phycard-s-rdk.dts +++ b/arch/arm/boot/dts/imx27-phytec-phycard-s-rdk.dts @@ -81,8 +81,8 @@ imx27-phycard-s-rdk { pinctrl_i2c1: i2c1grp { fsl,pins = < - MX27_PAD_I2C2_SDA__I2C2_SDA 0x0 - MX27_PAD_I2C2_SCL__I2C2_SCL 0x0 + MX27_PAD_I2C_DATA__I2C_DATA 0x0 + MX27_PAD_I2C_CLK__I2C_CLK 0x0 >; }; diff --git a/arch/arm/boot/dts/imx50-evk.dts b/arch/arm/boot/dts/imx50-evk.dts index a25da415cb02..907339bc81e5 100644 --- a/arch/arm/boot/dts/imx50-evk.dts +++ b/arch/arm/boot/dts/imx50-evk.dts @@ -59,7 +59,7 @@ MX50_PAD_CSPI_MISO__CSPI_MISO 0x00 MX50_PAD_CSPI_MOSI__CSPI_MOSI 0x00 MX50_PAD_CSPI_SS0__GPIO4_11 0xc4 - MX50_PAD_ECSPI1_MOSI__CSPI_SS1 0xf4 + MX50_PAD_ECSPI1_MOSI__GPIO4_13 0x84 >; }; diff --git a/arch/arm/boot/dts/imx6q-b450v3.dts b/arch/arm/boot/dts/imx6q-b450v3.dts index 3ec58500e9c2..25bf45659737 100644 --- a/arch/arm/boot/dts/imx6q-b450v3.dts +++ b/arch/arm/boot/dts/imx6q-b450v3.dts @@ -65,13 +65,6 @@ }; }; -&clks { - assigned-clocks = <&clks IMX6QDL_CLK_LDB_DI0_SEL>, - <&clks IMX6QDL_CLK_LDB_DI1_SEL>; - assigned-clock-parents = <&clks IMX6QDL_CLK_PLL3_USB_OTG>, - <&clks IMX6QDL_CLK_PLL3_USB_OTG>; -}; - &ldb { status = "okay"; diff --git a/arch/arm/boot/dts/imx6q-b650v3.dts b/arch/arm/boot/dts/imx6q-b650v3.dts index 5650a9b11091..0326711a8700 100644 --- a/arch/arm/boot/dts/imx6q-b650v3.dts +++ b/arch/arm/boot/dts/imx6q-b650v3.dts @@ -65,13 +65,6 @@ }; }; -&clks { - assigned-clocks = <&clks IMX6QDL_CLK_LDB_DI0_SEL>, - <&clks IMX6QDL_CLK_LDB_DI1_SEL>; - assigned-clock-parents = <&clks IMX6QDL_CLK_PLL3_USB_OTG>, - <&clks IMX6QDL_CLK_PLL3_USB_OTG>; -}; - &ldb { status = "okay"; diff --git a/arch/arm/boot/dts/imx6q-b850v3.dts b/arch/arm/boot/dts/imx6q-b850v3.dts index 044a5bebe1c5..612f782ddaaa 100644 --- a/arch/arm/boot/dts/imx6q-b850v3.dts +++ b/arch/arm/boot/dts/imx6q-b850v3.dts @@ -53,17 +53,6 @@ }; }; -&clks { - assigned-clocks = <&clks IMX6QDL_CLK_LDB_DI0_SEL>, - <&clks IMX6QDL_CLK_LDB_DI1_SEL>, - <&clks IMX6QDL_CLK_IPU1_DI0_PRE_SEL>, - <&clks IMX6QDL_CLK_IPU2_DI0_PRE_SEL>; - assigned-clock-parents = <&clks IMX6QDL_CLK_PLL5_VIDEO_DIV>, - <&clks IMX6QDL_CLK_PLL5_VIDEO_DIV>, - <&clks IMX6QDL_CLK_PLL2_PFD2_396M>, - <&clks IMX6QDL_CLK_PLL2_PFD2_396M>; -}; - &ldb { fsl,dual-channel; status = "okay"; diff --git a/arch/arm/boot/dts/imx6q-bx50v3.dtsi b/arch/arm/boot/dts/imx6q-bx50v3.dtsi index d3cba09be0cb..c1f554348187 100644 --- a/arch/arm/boot/dts/imx6q-bx50v3.dtsi +++ b/arch/arm/boot/dts/imx6q-bx50v3.dtsi @@ -391,3 +391,18 @@ #interrupt-cells = <1>; }; }; + +&clks { + assigned-clocks = <&clks IMX6QDL_CLK_LDB_DI0_SEL>, + <&clks IMX6QDL_CLK_LDB_DI1_SEL>, + <&clks IMX6QDL_CLK_IPU1_DI0_PRE_SEL>, + <&clks IMX6QDL_CLK_IPU1_DI1_PRE_SEL>, + <&clks IMX6QDL_CLK_IPU2_DI0_PRE_SEL>, + <&clks IMX6QDL_CLK_IPU2_DI1_PRE_SEL>; + assigned-clock-parents = <&clks IMX6QDL_CLK_PLL5_VIDEO_DIV>, + <&clks IMX6QDL_CLK_PLL5_VIDEO_DIV>, + <&clks IMX6QDL_CLK_PLL2_PFD0_352M>, + <&clks IMX6QDL_CLK_PLL2_PFD0_352M>, + <&clks IMX6QDL_CLK_PLL2_PFD0_352M>, + <&clks IMX6QDL_CLK_PLL2_PFD0_352M>; +}; diff --git a/arch/arm/boot/dts/imx6qdl-gw52xx.dtsi b/arch/arm/boot/dts/imx6qdl-gw52xx.dtsi index b8044681006c..2df4694c0d3b 100644 --- a/arch/arm/boot/dts/imx6qdl-gw52xx.dtsi +++ b/arch/arm/boot/dts/imx6qdl-gw52xx.dtsi @@ -278,7 +278,7 @@ /* VDD_AUD_1P8: Audio codec */ reg_aud_1p8v: ldo3 { - regulator-name = "vdd1p8"; + regulator-name = "vdd1p8a"; regulator-min-microvolt = <1800000>; regulator-max-microvolt = <1800000>; regulator-boot-on; diff --git a/arch/arm/boot/dts/imx6qdl-phytec-pfla02.dtsi b/arch/arm/boot/dts/imx6qdl-phytec-pfla02.dtsi index fe4e89d773f5..9499d113b139 100644 --- a/arch/arm/boot/dts/imx6qdl-phytec-pfla02.dtsi +++ b/arch/arm/boot/dts/imx6qdl-phytec-pfla02.dtsi @@ -423,6 +423,7 @@ pinctrl-0 = <&pinctrl_usdhc2>; cd-gpios = <&gpio1 4 GPIO_ACTIVE_LOW>; wp-gpios = <&gpio1 2 GPIO_ACTIVE_HIGH>; + vmmc-supply = <&vdd_sd1_reg>; status = "disabled"; }; @@ -432,5 +433,6 @@ &pinctrl_usdhc3_cdwp>; cd-gpios = <&gpio1 27 GPIO_ACTIVE_LOW>; wp-gpios = <&gpio1 29 GPIO_ACTIVE_HIGH>; + vmmc-supply = <&vdd_sd0_reg>; status = "disabled"; }; diff --git a/arch/arm/boot/dts/imx6qdl-udoo.dtsi b/arch/arm/boot/dts/imx6qdl-udoo.dtsi index 4f27861bbb32..4cc9858f7ff8 100644 --- a/arch/arm/boot/dts/imx6qdl-udoo.dtsi +++ b/arch/arm/boot/dts/imx6qdl-udoo.dtsi @@ -97,7 +97,7 @@ &fec { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_enet>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; status = "okay"; }; diff --git a/arch/arm/boot/dts/imx6qdl.dtsi b/arch/arm/boot/dts/imx6qdl.dtsi index 00d44a60972f..e64ff80c83c5 100644 --- a/arch/arm/boot/dts/imx6qdl.dtsi +++ b/arch/arm/boot/dts/imx6qdl.dtsi @@ -1013,9 +1013,8 @@ compatible = "fsl,imx6q-fec"; reg = <0x02188000 0x4000>; interrupt-names = "int0", "pps"; - interrupts-extended = - <&intc 0 118 IRQ_TYPE_LEVEL_HIGH>, - <&intc 0 119 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <0 118 IRQ_TYPE_LEVEL_HIGH>, + <0 119 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clks IMX6QDL_CLK_ENET>, <&clks IMX6QDL_CLK_ENET>, <&clks IMX6QDL_CLK_ENET_REF>; diff --git a/arch/arm/boot/dts/imx6qp.dtsi b/arch/arm/boot/dts/imx6qp.dtsi index 5f51f8e5c1fa..d91f92f944c5 100644 --- a/arch/arm/boot/dts/imx6qp.dtsi +++ b/arch/arm/boot/dts/imx6qp.dtsi @@ -77,7 +77,6 @@ }; &fec { - /delete-property/interrupts-extended; interrupts = <0 118 IRQ_TYPE_LEVEL_HIGH>, <0 119 IRQ_TYPE_LEVEL_HIGH>; }; diff --git a/arch/arm/boot/dts/imx6sl.dtsi b/arch/arm/boot/dts/imx6sl.dtsi index 55d1872aa81a..9d19183f40e1 100644 --- a/arch/arm/boot/dts/imx6sl.dtsi +++ b/arch/arm/boot/dts/imx6sl.dtsi @@ -922,8 +922,10 @@ }; rngb: rngb@21b4000 { + compatible = "fsl,imx6sl-rngb", "fsl,imx25-rngb"; reg = <0x021b4000 0x4000>; interrupts = <0 5 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&clks IMX6SL_CLK_DUMMY>; }; weim: weim@21b8000 { diff --git a/arch/arm/boot/dts/logicpd-som-lv-baseboard.dtsi b/arch/arm/boot/dts/logicpd-som-lv-baseboard.dtsi index 3e39b9a1f35d..0093548d50ff 100644 --- a/arch/arm/boot/dts/logicpd-som-lv-baseboard.dtsi +++ b/arch/arm/boot/dts/logicpd-som-lv-baseboard.dtsi @@ -55,6 +55,8 @@ &mcbsp2 { status = "okay"; + pinctrl-names = "default"; + pinctrl-0 = <&mcbsp2_pins>; }; &charger { diff --git a/arch/arm/boot/dts/logicpd-torpedo-baseboard.dtsi b/arch/arm/boot/dts/logicpd-torpedo-baseboard.dtsi index 86c5644f558c..032e8dde1381 100644 --- a/arch/arm/boot/dts/logicpd-torpedo-baseboard.dtsi +++ b/arch/arm/boot/dts/logicpd-torpedo-baseboard.dtsi @@ -84,6 +84,8 @@ }; &mcbsp2 { + pinctrl-names = "default"; + pinctrl-0 = <&mcbsp2_pins>; status = "okay"; }; diff --git a/arch/arm/boot/dts/lpc32xx.dtsi b/arch/arm/boot/dts/lpc32xx.dtsi index 9ad3df11db0d..abef034987a2 100644 --- a/arch/arm/boot/dts/lpc32xx.dtsi +++ b/arch/arm/boot/dts/lpc32xx.dtsi @@ -323,9 +323,6 @@ clocks = <&xtal_32k>, <&xtal>; clock-names = "xtal_32k", "xtal"; - - assigned-clocks = <&clk LPC32XX_CLK_HCLK_PLL>; - assigned-clock-rates = <208000000>; }; }; diff --git a/arch/arm/boot/dts/ls1021a.dtsi b/arch/arm/boot/dts/ls1021a.dtsi index 074b4ec520c6..b66b2bd1aa85 100644 --- a/arch/arm/boot/dts/ls1021a.dtsi +++ b/arch/arm/boot/dts/ls1021a.dtsi @@ -168,7 +168,7 @@ #address-cells = <1>; #size-cells = <0>; reg = <0x0 0x1550000 0x0 0x10000>, - <0x0 0x40000000 0x0 0x40000000>; + <0x0 0x40000000 0x0 0x20000000>; reg-names = "QuadSPI", "QuadSPI-memory"; interrupts = <GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>; clock-names = "qspi_en", "qspi"; @@ -609,7 +609,7 @@ fsl,tmr-prsc = <2>; fsl,tmr-add = <0xaaaaaaab>; fsl,tmr-fiper1 = <999999995>; - fsl,tmr-fiper2 = <99990>; + fsl,tmr-fiper2 = <999999995>; fsl,max-adj = <499999999>; }; diff --git a/arch/arm/boot/dts/motorola-cpcap-mapphone.dtsi b/arch/arm/boot/dts/motorola-cpcap-mapphone.dtsi index f57acf8f66b9..75de8134b1d1 100644 --- a/arch/arm/boot/dts/motorola-cpcap-mapphone.dtsi +++ b/arch/arm/boot/dts/motorola-cpcap-mapphone.dtsi @@ -16,8 +16,10 @@ #interrupt-cells = <2>; #address-cells = <1>; #size-cells = <0>; - spi-max-frequency = <3000000>; + spi-max-frequency = <9600000>; spi-cs-high; + spi-cpol; + spi-cpha; cpcap_adc: adc { compatible = "motorola,mapphone-cpcap-adc"; diff --git a/arch/arm/boot/dts/mt7623n-bananapi-bpi-r2.dts b/arch/arm/boot/dts/mt7623n-bananapi-bpi-r2.dts index 2b760f90f38c..5375c6699843 100644 --- a/arch/arm/boot/dts/mt7623n-bananapi-bpi-r2.dts +++ b/arch/arm/boot/dts/mt7623n-bananapi-bpi-r2.dts @@ -192,6 +192,7 @@ fixed-link { speed = <1000>; full-duplex; + pause; }; }; }; diff --git a/arch/arm/boot/dts/omap3.dtsi b/arch/arm/boot/dts/omap3.dtsi index 4043ecb38016..0c8fcfb292bf 100644 --- a/arch/arm/boot/dts/omap3.dtsi +++ b/arch/arm/boot/dts/omap3.dtsi @@ -23,6 +23,9 @@ i2c0 = &i2c1; i2c1 = &i2c2; i2c2 = &i2c3; + mmc0 = &mmc1; + mmc1 = &mmc2; + mmc2 = &mmc3; serial0 = &uart1; serial1 = &uart2; serial2 = &uart3; diff --git a/arch/arm/boot/dts/omap4-duovero-parlor.dts b/arch/arm/boot/dts/omap4-duovero-parlor.dts index cfcac0d73851..93d6fb6db578 100644 --- a/arch/arm/boot/dts/omap4-duovero-parlor.dts +++ b/arch/arm/boot/dts/omap4-duovero-parlor.dts @@ -142,7 +142,7 @@ ethernet@gpmc { reg = <5 0 0xff>; interrupt-parent = <&gpio2>; - interrupts = <12 IRQ_TYPE_EDGE_FALLING>; /* gpio_44 */ + interrupts = <12 IRQ_TYPE_LEVEL_LOW>; /* gpio_44 */ phy-mode = "mii"; diff --git a/arch/arm/boot/dts/omap4-panda-es.dts b/arch/arm/boot/dts/omap4-panda-es.dts index 19d02df8d8a5..70fd28120c27 100644 --- a/arch/arm/boot/dts/omap4-panda-es.dts +++ b/arch/arm/boot/dts/omap4-panda-es.dts @@ -49,7 +49,7 @@ button_pins: pinmux_button_pins { pinctrl-single,pins = < - OMAP4_IOPAD(0x11b, PIN_INPUT_PULLUP | MUX_MODE3) /* gpio_113 */ + OMAP4_IOPAD(0x0fc, PIN_INPUT_PULLUP | MUX_MODE3) /* gpio_113 */ >; }; }; diff --git a/arch/arm/boot/dts/omap4.dtsi b/arch/arm/boot/dts/omap4.dtsi index 1a96d4317c97..046e77024567 100644 --- a/arch/arm/boot/dts/omap4.dtsi +++ b/arch/arm/boot/dts/omap4.dtsi @@ -25,6 +25,11 @@ i2c1 = &i2c2; i2c2 = &i2c3; i2c3 = &i2c4; + mmc0 = &mmc1; + mmc1 = &mmc2; + mmc2 = &mmc3; + mmc3 = &mmc4; + mmc4 = &mmc5; serial0 = &uart1; serial1 = &uart2; serial2 = &uart3; @@ -516,7 +521,7 @@ status = "disabled"; }; - target-module@56000000 { + sgx_module: target-module@56000000 { compatible = "ti,sysc-omap4", "ti,sysc"; ti,hwmods = "gpu"; reg = <0x5601fc00 0x4>, diff --git a/arch/arm/boot/dts/omap443x.dtsi b/arch/arm/boot/dts/omap443x.dtsi index cbcdcb4e7d1c..6e320efd9fc1 100644 --- a/arch/arm/boot/dts/omap443x.dtsi +++ b/arch/arm/boot/dts/omap443x.dtsi @@ -33,10 +33,12 @@ }; ocp { + /* 4430 has only gpio_86 tshut and no talert interrupt */ bandgap: bandgap@4a002260 { reg = <0x4a002260 0x4 0x4a00232C 0x4>; compatible = "ti,omap4430-bandgap"; + gpios = <&gpio3 22 GPIO_ACTIVE_HIGH>; #thermal-sensor-cells = <0>; }; @@ -74,3 +76,13 @@ }; /include/ "omap443x-clocks.dtsi" + +/* + * Use dpll_per for sgx at 153.6MHz like droid4 stock v3.0.8 Android kernel + */ +&sgx_module { + assigned-clocks = <&l3_gfx_clkctrl OMAP4_GPU_CLKCTRL 24>, + <&dpll_per_m7x2_ck>; + assigned-clock-rates = <0>, <153600000>; + assigned-clock-parents = <&dpll_per_m7x2_ck>; +}; diff --git a/arch/arm/boot/dts/omap44xx-clocks.dtsi b/arch/arm/boot/dts/omap44xx-clocks.dtsi index 279ff2f419df..c654588f9e8c 100644 --- a/arch/arm/boot/dts/omap44xx-clocks.dtsi +++ b/arch/arm/boot/dts/omap44xx-clocks.dtsi @@ -773,14 +773,6 @@ ti,max-div = <2>; }; - sha2md5_fck: sha2md5_fck@15c8 { - #clock-cells = <0>; - compatible = "ti,gate-clock"; - clocks = <&l3_div_ck>; - ti,bit-shift = <1>; - reg = <0x15c8>; - }; - usb_phy_cm_clk32k: usb_phy_cm_clk32k@640 { #clock-cells = <0>; compatible = "ti,gate-clock"; diff --git a/arch/arm/boot/dts/omap5.dtsi b/arch/arm/boot/dts/omap5.dtsi index 3c0bafe0fb05..cf66c374de4f 100644 --- a/arch/arm/boot/dts/omap5.dtsi +++ b/arch/arm/boot/dts/omap5.dtsi @@ -26,6 +26,11 @@ i2c2 = &i2c3; i2c3 = &i2c4; i2c4 = &i2c5; + mmc0 = &mmc1; + mmc1 = &mmc2; + mmc2 = &mmc3; + mmc3 = &mmc4; + mmc4 = &mmc5; serial0 = &uart1; serial1 = &uart2; serial2 = &uart3; diff --git a/arch/arm/boot/dts/owl-s500.dtsi b/arch/arm/boot/dts/owl-s500.dtsi index 43c9980a4260..75a76842c270 100644 --- a/arch/arm/boot/dts/owl-s500.dtsi +++ b/arch/arm/boot/dts/owl-s500.dtsi @@ -85,21 +85,21 @@ global_timer: timer@b0020200 { compatible = "arm,cortex-a9-global-timer"; reg = <0xb0020200 0x100>; - interrupts = <GIC_PPI 0 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_EDGE_RISING)>; + interrupts = <GIC_PPI 11 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_EDGE_RISING)>; status = "disabled"; }; twd_timer: timer@b0020600 { compatible = "arm,cortex-a9-twd-timer"; reg = <0xb0020600 0x20>; - interrupts = <GIC_PPI 2 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_EDGE_RISING)>; + interrupts = <GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_EDGE_RISING)>; status = "disabled"; }; twd_wdt: wdt@b0020620 { compatible = "arm,cortex-a9-twd-wdt"; reg = <0xb0020620 0xe0>; - interrupts = <GIC_PPI 3 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_EDGE_RISING)>; + interrupts = <GIC_PPI 14 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_EDGE_RISING)>; status = "disabled"; }; diff --git a/arch/arm/boot/dts/picoxcell-pc3x2.dtsi b/arch/arm/boot/dts/picoxcell-pc3x2.dtsi index a1266cf8776c..8362c6a3bcd3 100644 --- a/arch/arm/boot/dts/picoxcell-pc3x2.dtsi +++ b/arch/arm/boot/dts/picoxcell-pc3x2.dtsi @@ -54,18 +54,21 @@ emac: gem@30000 { compatible = "cadence,gem"; reg = <0x30000 0x10000>; + interrupt-parent = <&vic0>; interrupts = <31>; }; dmac1: dmac@40000 { compatible = "snps,dw-dmac"; reg = <0x40000 0x10000>; + interrupt-parent = <&vic0>; interrupts = <25>; }; dmac2: dmac@50000 { compatible = "snps,dw-dmac"; reg = <0x50000 0x10000>; + interrupt-parent = <&vic0>; interrupts = <26>; }; @@ -243,6 +246,7 @@ axi2pico@c0000000 { compatible = "picochip,axi2pico-pc3x2"; reg = <0xc0000000 0x10000>; + interrupt-parent = <&vic0>; interrupts = <13 14 15 16 17 18 19 20 21>; }; }; diff --git a/arch/arm/boot/dts/r8a73a4.dtsi b/arch/arm/boot/dts/r8a73a4.dtsi index dd865f3c2eda..4447f45f0cba 100644 --- a/arch/arm/boot/dts/r8a73a4.dtsi +++ b/arch/arm/boot/dts/r8a73a4.dtsi @@ -131,7 +131,14 @@ cmt1: timer@e6130000 { compatible = "renesas,r8a73a4-cmt1", "renesas,rcar-gen2-cmt1"; reg = <0 0xe6130000 0 0x1004>; - interrupts = <GIC_SPI 120 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_SPI 120 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 121 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 122 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 123 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 124 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 125 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 126 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 127 IRQ_TYPE_LEVEL_HIGH>; clocks = <&mstp3_clks R8A73A4_CLK_CMT1>; clock-names = "fck"; power-domains = <&pd_c5>; diff --git a/arch/arm/boot/dts/r8a7740.dtsi b/arch/arm/boot/dts/r8a7740.dtsi index 383cba68dbba..e12ea97eae27 100644 --- a/arch/arm/boot/dts/r8a7740.dtsi +++ b/arch/arm/boot/dts/r8a7740.dtsi @@ -479,7 +479,7 @@ cpg_clocks: cpg_clocks@e6150000 { compatible = "renesas,r8a7740-cpg-clocks"; reg = <0xe6150000 0x10000>; - clocks = <&extal1_clk>, <&extalr_clk>; + clocks = <&extal1_clk>, <&extal2_clk>, <&extalr_clk>; #clock-cells = <1>; clock-output-names = "system", "pllc0", "pllc1", "pllc2", "r", diff --git a/arch/arm/boot/dts/r8a7793-gose.dts b/arch/arm/boot/dts/r8a7793-gose.dts index 6b2f3a4fd13d..7802ce842a73 100644 --- a/arch/arm/boot/dts/r8a7793-gose.dts +++ b/arch/arm/boot/dts/r8a7793-gose.dts @@ -339,7 +339,7 @@ reg = <0x20>; remote = <&vin1>; - port { + ports { #address-cells = <1>; #size-cells = <0>; @@ -399,7 +399,7 @@ interrupts = <2 IRQ_TYPE_LEVEL_LOW>; default-input = <0>; - port { + ports { #address-cells = <1>; #size-cells = <0>; diff --git a/arch/arm/boot/dts/rk3036.dtsi b/arch/arm/boot/dts/rk3036.dtsi index d560fc4051c5..db612271371b 100644 --- a/arch/arm/boot/dts/rk3036.dtsi +++ b/arch/arm/boot/dts/rk3036.dtsi @@ -128,7 +128,7 @@ assigned-clocks = <&cru SCLK_GPU>; assigned-clock-rates = <100000000>; clocks = <&cru SCLK_GPU>, <&cru SCLK_GPU>; - clock-names = "core", "bus"; + clock-names = "bus", "core"; resets = <&cru SRST_GPU>; status = "disabled"; }; diff --git a/arch/arm/boot/dts/rk3228-evb.dts b/arch/arm/boot/dts/rk3228-evb.dts index 5670b33fd1bd..aed879db6c15 100644 --- a/arch/arm/boot/dts/rk3228-evb.dts +++ b/arch/arm/boot/dts/rk3228-evb.dts @@ -46,7 +46,7 @@ #address-cells = <1>; #size-cells = <0>; - phy: phy@0 { + phy: ethernet-phy@0 { compatible = "ethernet-phy-id1234.d400", "ethernet-phy-ieee802.3-c22"; reg = <0>; clocks = <&cru SCLK_MAC_PHY>; diff --git a/arch/arm/boot/dts/rk322x.dtsi b/arch/arm/boot/dts/rk322x.dtsi index cd8f2a3b0e91..2aa74267ae51 100644 --- a/arch/arm/boot/dts/rk322x.dtsi +++ b/arch/arm/boot/dts/rk322x.dtsi @@ -539,7 +539,7 @@ "pp1", "ppmmu1"; clocks = <&cru ACLK_GPU>, <&cru ACLK_GPU>; - clock-names = "core", "bus"; + clock-names = "bus", "core"; resets = <&cru SRST_GPU_A>; status = "disabled"; }; @@ -944,7 +944,7 @@ }; }; - spi-0 { + spi0 { spi0_clk: spi0-clk { rockchip,pins = <0 9 RK_FUNC_2 &pcfg_pull_up>; }; @@ -962,7 +962,7 @@ }; }; - spi-1 { + spi1 { spi1_clk: spi1-clk { rockchip,pins = <0 23 RK_FUNC_2 &pcfg_pull_up>; }; diff --git a/arch/arm/boot/dts/rk3xxx.dtsi b/arch/arm/boot/dts/rk3xxx.dtsi index d752dc611fd7..86a0d98d28ff 100644 --- a/arch/arm/boot/dts/rk3xxx.dtsi +++ b/arch/arm/boot/dts/rk3xxx.dtsi @@ -84,7 +84,7 @@ compatible = "arm,mali-400"; reg = <0x10090000 0x10000>; clocks = <&cru ACLK_GPU>, <&cru ACLK_GPU>; - clock-names = "core", "bus"; + clock-names = "bus", "core"; assigned-clocks = <&cru ACLK_GPU>; assigned-clock-rates = <100000000>; resets = <&cru SRST_GPU>; diff --git a/arch/arm/boot/dts/s5pv210-aries.dtsi b/arch/arm/boot/dts/s5pv210-aries.dtsi index 575094ea7024..7b62c381d3c8 100644 --- a/arch/arm/boot/dts/s5pv210-aries.dtsi +++ b/arch/arm/boot/dts/s5pv210-aries.dtsi @@ -374,6 +374,7 @@ pinctrl-names = "default"; cap-sd-highspeed; cap-mmc-highspeed; + keep-power-in-suspend; mmc-pwrseq = <&wifi_pwrseq>; non-removable; diff --git a/arch/arm/boot/dts/s5pv210.dtsi b/arch/arm/boot/dts/s5pv210.dtsi index 67358562a6ea..020a864623ff 100644 --- a/arch/arm/boot/dts/s5pv210.dtsi +++ b/arch/arm/boot/dts/s5pv210.dtsi @@ -98,19 +98,16 @@ }; clocks: clock-controller@e0100000 { - compatible = "samsung,s5pv210-clock", "simple-bus"; + compatible = "samsung,s5pv210-clock"; reg = <0xe0100000 0x10000>; clock-names = "xxti", "xusbxti"; clocks = <&xxti>, <&xusbxti>; #clock-cells = <1>; - #address-cells = <1>; - #size-cells = <1>; - ranges; + }; - pmu_syscon: syscon@e0108000 { - compatible = "samsung-s5pv210-pmu", "syscon"; - reg = <0xe0108000 0x8000>; - }; + pmu_syscon: syscon@e0108000 { + compatible = "samsung-s5pv210-pmu", "syscon"; + reg = <0xe0108000 0x8000>; }; pinctrl0: pinctrl@e0200000 { @@ -126,35 +123,28 @@ }; }; - amba { - #address-cells = <1>; - #size-cells = <1>; - compatible = "simple-bus"; - ranges; - - pdma0: dma@e0900000 { - compatible = "arm,pl330", "arm,primecell"; - reg = <0xe0900000 0x1000>; - interrupt-parent = <&vic0>; - interrupts = <19>; - clocks = <&clocks CLK_PDMA0>; - clock-names = "apb_pclk"; - #dma-cells = <1>; - #dma-channels = <8>; - #dma-requests = <32>; - }; + pdma0: dma@e0900000 { + compatible = "arm,pl330", "arm,primecell"; + reg = <0xe0900000 0x1000>; + interrupt-parent = <&vic0>; + interrupts = <19>; + clocks = <&clocks CLK_PDMA0>; + clock-names = "apb_pclk"; + #dma-cells = <1>; + #dma-channels = <8>; + #dma-requests = <32>; + }; - pdma1: dma@e0a00000 { - compatible = "arm,pl330", "arm,primecell"; - reg = <0xe0a00000 0x1000>; - interrupt-parent = <&vic0>; - interrupts = <20>; - clocks = <&clocks CLK_PDMA1>; - clock-names = "apb_pclk"; - #dma-cells = <1>; - #dma-channels = <8>; - #dma-requests = <32>; - }; + pdma1: dma@e0a00000 { + compatible = "arm,pl330", "arm,primecell"; + reg = <0xe0a00000 0x1000>; + interrupt-parent = <&vic0>; + interrupts = <20>; + clocks = <&clocks CLK_PDMA1>; + clock-names = "apb_pclk"; + #dma-cells = <1>; + #dma-channels = <8>; + #dma-requests = <32>; }; spi0: spi@e1300000 { @@ -227,43 +217,36 @@ status = "disabled"; }; - audio-subsystem { - compatible = "samsung,s5pv210-audss", "simple-bus"; - #address-cells = <1>; - #size-cells = <1>; - ranges; - - clk_audss: clock-controller@eee10000 { - compatible = "samsung,s5pv210-audss-clock"; - reg = <0xeee10000 0x1000>; - clock-names = "hclk", "xxti", - "fout_epll", - "sclk_audio0"; - clocks = <&clocks DOUT_HCLKP>, <&xxti>, - <&clocks FOUT_EPLL>, - <&clocks SCLK_AUDIO0>; - #clock-cells = <1>; - }; + clk_audss: clock-controller@eee10000 { + compatible = "samsung,s5pv210-audss-clock"; + reg = <0xeee10000 0x1000>; + clock-names = "hclk", "xxti", + "fout_epll", + "sclk_audio0"; + clocks = <&clocks DOUT_HCLKP>, <&xxti>, + <&clocks FOUT_EPLL>, + <&clocks SCLK_AUDIO0>; + #clock-cells = <1>; + }; - i2s0: i2s@eee30000 { - compatible = "samsung,s5pv210-i2s"; - reg = <0xeee30000 0x1000>; - interrupt-parent = <&vic2>; - interrupts = <16>; - dma-names = "rx", "tx", "tx-sec"; - dmas = <&pdma1 9>, <&pdma1 10>, <&pdma1 11>; - clock-names = "iis", - "i2s_opclk0", - "i2s_opclk1"; - clocks = <&clk_audss CLK_I2S>, - <&clk_audss CLK_I2S>, - <&clk_audss CLK_DOUT_AUD_BUS>; - samsung,idma-addr = <0xc0010000>; - pinctrl-names = "default"; - pinctrl-0 = <&i2s0_bus>; - #sound-dai-cells = <0>; - status = "disabled"; - }; + i2s0: i2s@eee30000 { + compatible = "samsung,s5pv210-i2s"; + reg = <0xeee30000 0x1000>; + interrupt-parent = <&vic2>; + interrupts = <16>; + dma-names = "rx", "tx", "tx-sec"; + dmas = <&pdma1 9>, <&pdma1 10>, <&pdma1 11>; + clock-names = "iis", + "i2s_opclk0", + "i2s_opclk1"; + clocks = <&clk_audss CLK_I2S>, + <&clk_audss CLK_I2S>, + <&clk_audss CLK_DOUT_AUD_BUS>; + samsung,idma-addr = <0xc0010000>; + pinctrl-names = "default"; + pinctrl-0 = <&i2s0_bus>; + #sound-dai-cells = <0>; + status = "disabled"; }; i2s1: i2s@e2100000 { diff --git a/arch/arm/boot/dts/sama5d2.dtsi b/arch/arm/boot/dts/sama5d2.dtsi index b405992eb601..d856c16d0015 100644 --- a/arch/arm/boot/dts/sama5d2.dtsi +++ b/arch/arm/boot/dts/sama5d2.dtsi @@ -1247,6 +1247,7 @@ clocks = <&securam_clk>; #address-cells = <1>; #size-cells = <1>; + no-memory-wc; ranges = <0 0xf8044000 0x1420>; }; @@ -1297,7 +1298,7 @@ can0: can@f8054000 { compatible = "bosch,m_can"; - reg = <0xf8054000 0x4000>, <0x210000 0x4000>; + reg = <0xf8054000 0x4000>, <0x210000 0x1c00>; reg-names = "m_can", "message_ram"; interrupts = <56 IRQ_TYPE_LEVEL_HIGH 7>, <64 IRQ_TYPE_LEVEL_HIGH 7>; @@ -1490,7 +1491,7 @@ can1: can@fc050000 { compatible = "bosch,m_can"; - reg = <0xfc050000 0x4000>, <0x210000 0x4000>; + reg = <0xfc050000 0x4000>, <0x210000 0x3800>; reg-names = "m_can", "message_ram"; interrupts = <57 IRQ_TYPE_LEVEL_HIGH 7>, <65 IRQ_TYPE_LEVEL_HIGH 7>; @@ -1500,7 +1501,7 @@ assigned-clocks = <&can1_gclk>; assigned-clock-parents = <&utmi>; assigned-clock-rates = <40000000>; - bosch,mram-cfg = <0x1100 0 0 64 0 0 32 32>; + bosch,mram-cfg = <0x1c00 0 0 64 0 0 32 32>; status = "disabled"; }; diff --git a/arch/arm/boot/dts/socfpga.dtsi b/arch/arm/boot/dts/socfpga.dtsi index b38f8c240558..602511ccad6f 100644 --- a/arch/arm/boot/dts/socfpga.dtsi +++ b/arch/arm/boot/dts/socfpga.dtsi @@ -710,7 +710,7 @@ }; }; - L2: l2-cache@fffef000 { + L2: cache-controller@fffef000 { compatible = "arm,pl310-cache"; reg = <0xfffef000 0x1000>; interrupts = <0 38 0x04>; diff --git a/arch/arm/boot/dts/socfpga_arria10.dtsi b/arch/arm/boot/dts/socfpga_arria10.dtsi index b4dd3846e8cc..4b1c8bec2de3 100644 --- a/arch/arm/boot/dts/socfpga_arria10.dtsi +++ b/arch/arm/boot/dts/socfpga_arria10.dtsi @@ -618,7 +618,7 @@ reg = <0xffcfb100 0x80>; }; - L2: l2-cache@fffff000 { + L2: cache-controller@fffff000 { compatible = "arm,pl310-cache"; reg = <0xfffff000 0x1000>; interrupts = <0 18 IRQ_TYPE_LEVEL_HIGH>; @@ -791,7 +791,7 @@ timer3: timer3@ffd00100 { compatible = "snps,dw-apb-timer"; interrupts = <0 118 IRQ_TYPE_LEVEL_HIGH>; - reg = <0xffd01000 0x100>; + reg = <0xffd00100 0x100>; clocks = <&l4_sys_free_clk>; clock-names = "timer"; }; diff --git a/arch/arm/boot/dts/sun4i-a10.dtsi b/arch/arm/boot/dts/sun4i-a10.dtsi index 5d46bb0139fa..707ad5074878 100644 --- a/arch/arm/boot/dts/sun4i-a10.dtsi +++ b/arch/arm/boot/dts/sun4i-a10.dtsi @@ -143,7 +143,7 @@ trips { cpu_alert0: cpu-alert0 { /* milliCelsius */ - temperature = <850000>; + temperature = <85000>; hysteresis = <2000>; type = "passive"; }; diff --git a/arch/arm/boot/dts/sun8i-a83t-bananapi-m3.dts b/arch/arm/boot/dts/sun8i-a83t-bananapi-m3.dts index f250b20af493..9be1c4a3d95f 100644 --- a/arch/arm/boot/dts/sun8i-a83t-bananapi-m3.dts +++ b/arch/arm/boot/dts/sun8i-a83t-bananapi-m3.dts @@ -131,7 +131,7 @@ pinctrl-0 = <&emac_rgmii_pins>; phy-supply = <®_sw>; phy-handle = <&rgmii_phy>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; allwinner,rx-delay-ps = <700>; allwinner,tx-delay-ps = <700>; status = "okay"; diff --git a/arch/arm/boot/dts/sun8i-a83t-cubietruck-plus.dts b/arch/arm/boot/dts/sun8i-a83t-cubietruck-plus.dts index 7e74ba83f809..75396993195d 100644 --- a/arch/arm/boot/dts/sun8i-a83t-cubietruck-plus.dts +++ b/arch/arm/boot/dts/sun8i-a83t-cubietruck-plus.dts @@ -168,7 +168,7 @@ pinctrl-0 = <&emac_rgmii_pins>; phy-supply = <®_dldo4>; phy-handle = <&rgmii_phy>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; status = "okay"; }; diff --git a/arch/arm/boot/dts/sun8i-a83t-tbs-a711.dts b/arch/arm/boot/dts/sun8i-a83t-tbs-a711.dts index 49547a43cc90..54cbdaf7ffdc 100644 --- a/arch/arm/boot/dts/sun8i-a83t-tbs-a711.dts +++ b/arch/arm/boot/dts/sun8i-a83t-tbs-a711.dts @@ -318,8 +318,8 @@ }; ®_dldo3 { - regulator-min-microvolt = <2800000>; - regulator-max-microvolt = <2800000>; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; regulator-name = "vdd-csi"; }; diff --git a/arch/arm/boot/dts/sun8i-h2-plus-bananapi-m2-zero.dts b/arch/arm/boot/dts/sun8i-h2-plus-bananapi-m2-zero.dts index 1db2541135a7..00e0d6940c30 100644 --- a/arch/arm/boot/dts/sun8i-h2-plus-bananapi-m2-zero.dts +++ b/arch/arm/boot/dts/sun8i-h2-plus-bananapi-m2-zero.dts @@ -32,7 +32,7 @@ pwr_led { label = "bananapi-m2-zero:red:pwr"; - gpios = <&r_pio 0 10 GPIO_ACTIVE_HIGH>; /* PL10 */ + gpios = <&r_pio 0 10 GPIO_ACTIVE_LOW>; /* PL10 */ default-state = "on"; }; }; diff --git a/arch/arm/boot/dts/sun8i-h3-orangepi-pc-plus.dts b/arch/arm/boot/dts/sun8i-h3-orangepi-pc-plus.dts index 71fb73208939..babf4cf1b2f6 100644 --- a/arch/arm/boot/dts/sun8i-h3-orangepi-pc-plus.dts +++ b/arch/arm/boot/dts/sun8i-h3-orangepi-pc-plus.dts @@ -53,11 +53,6 @@ }; }; -&emac { - /* LEDs changed to active high on the plus */ - /delete-property/ allwinner,leds-active-low; -}; - &mmc1 { vmmc-supply = <®_vcc3v3>; bus-width = <4>; diff --git a/arch/arm/boot/dts/sun8i-h3-orangepi-plus2e.dts b/arch/arm/boot/dts/sun8i-h3-orangepi-plus2e.dts index 6dbf7b2e0c13..b6ca45d18e51 100644 --- a/arch/arm/boot/dts/sun8i-h3-orangepi-plus2e.dts +++ b/arch/arm/boot/dts/sun8i-h3-orangepi-plus2e.dts @@ -67,7 +67,7 @@ pinctrl-0 = <&emac_rgmii_pins>; phy-supply = <®_gmac_3v3>; phy-handle = <&ext_rgmii_phy>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; status = "okay"; }; diff --git a/arch/arm/boot/dts/sun8i-r40-bananapi-m2-ultra.dts b/arch/arm/boot/dts/sun8i-r40-bananapi-m2-ultra.dts index c39b9169ea64..5e5223a48ac7 100644 --- a/arch/arm/boot/dts/sun8i-r40-bananapi-m2-ultra.dts +++ b/arch/arm/boot/dts/sun8i-r40-bananapi-m2-ultra.dts @@ -121,7 +121,7 @@ pinctrl-names = "default"; pinctrl-0 = <&gmac_rgmii_pins>; phy-handle = <&phy1>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; phy-supply = <®_dc1sw>; status = "okay"; }; @@ -206,16 +206,16 @@ }; ®_dc1sw { - regulator-min-microvolt = <3000000>; - regulator-max-microvolt = <3000000>; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; regulator-name = "vcc-gmac-phy"; }; ®_dcdc1 { regulator-always-on; - regulator-min-microvolt = <3000000>; - regulator-max-microvolt = <3000000>; - regulator-name = "vcc-3v0"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + regulator-name = "vcc-3v3"; }; ®_dcdc2 { diff --git a/arch/arm/boot/dts/sun8i-v3s.dtsi b/arch/arm/boot/dts/sun8i-v3s.dtsi index 92fcb756a08a..97cac6d63692 100644 --- a/arch/arm/boot/dts/sun8i-v3s.dtsi +++ b/arch/arm/boot/dts/sun8i-v3s.dtsi @@ -419,7 +419,7 @@ gic: interrupt-controller@1c81000 { compatible = "arm,cortex-a7-gic", "arm,cortex-a15-gic"; reg = <0x01c81000 0x1000>, - <0x01c82000 0x1000>, + <0x01c82000 0x2000>, <0x01c84000 0x2000>, <0x01c86000 0x2000>; interrupt-controller; diff --git a/arch/arm/boot/dts/uniphier-pxs2.dtsi b/arch/arm/boot/dts/uniphier-pxs2.dtsi index e2d1a22c5950..d8a32104aad0 100644 --- a/arch/arm/boot/dts/uniphier-pxs2.dtsi +++ b/arch/arm/boot/dts/uniphier-pxs2.dtsi @@ -513,7 +513,7 @@ clocks = <&sys_clk 6>; reset-names = "ether"; resets = <&sys_rst 6>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; local-mac-address = [00 00 00 00 00 00]; socionext,syscon-phy-mode = <&soc_glue 0>; diff --git a/arch/arm/boot/dts/vfxxx.dtsi b/arch/arm/boot/dts/vfxxx.dtsi index d392794d9c13..de81e8b4afde 100644 --- a/arch/arm/boot/dts/vfxxx.dtsi +++ b/arch/arm/boot/dts/vfxxx.dtsi @@ -532,7 +532,7 @@ }; ocotp: ocotp@400a5000 { - compatible = "fsl,vf610-ocotp"; + compatible = "fsl,vf610-ocotp", "syscon"; reg = <0x400a5000 0x1000>; clocks = <&clks VF610_CLK_OCOTP>; }; diff --git a/arch/arm/configs/rpc_defconfig b/arch/arm/configs/rpc_defconfig index 3b82b64950d9..c090643b1ecb 100644 --- a/arch/arm/configs/rpc_defconfig +++ b/arch/arm/configs/rpc_defconfig @@ -32,7 +32,6 @@ CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=m CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=y CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_LOGGING=y diff --git a/arch/arm/configs/s3c2410_defconfig b/arch/arm/configs/s3c2410_defconfig index bd71d5bf98c9..9c69a9020e77 100644 --- a/arch/arm/configs/s3c2410_defconfig +++ b/arch/arm/configs/s3c2410_defconfig @@ -206,7 +206,6 @@ CONFIG_EEPROM_AT24=y CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=m CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=y CONFIG_CHR_DEV_SCH=m CONFIG_SCSI_CONSTANTS=y diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h index 88286dd483ff..1935b580f0e8 100644 --- a/arch/arm/include/asm/assembler.h +++ b/arch/arm/include/asm/assembler.h @@ -21,11 +21,11 @@ #endif #include <asm/ptrace.h> -#include <asm/domain.h> #include <asm/opcodes-virt.h> #include <asm/asm-offsets.h> #include <asm/page.h> #include <asm/thread_info.h> +#include <asm/uaccess-asm.h> #define IOMEM(x) (x) @@ -374,9 +374,9 @@ THUMB( orr \reg , \reg , #PSR_T_BIT ) .macro usraccoff, instr, reg, ptr, inc, off, cond, abort, t=TUSER() 9999: .if \inc == 1 - \instr\cond\()b\()\t\().w \reg, [\ptr, #\off] + \instr\()b\t\cond\().w \reg, [\ptr, #\off] .elseif \inc == 4 - \instr\cond\()\t\().w \reg, [\ptr, #\off] + \instr\t\cond\().w \reg, [\ptr, #\off] .else .error "Unsupported inc macro argument" .endif @@ -415,9 +415,9 @@ THUMB( orr \reg , \reg , #PSR_T_BIT ) .rept \rept 9999: .if \inc == 1 - \instr\cond\()b\()\t \reg, [\ptr], #\inc + \instr\()b\t\cond \reg, [\ptr], #\inc .elseif \inc == 4 - \instr\cond\()\t \reg, [\ptr], #\inc + \instr\t\cond \reg, [\ptr], #\inc .else .error "Unsupported inc macro argument" .endif @@ -447,79 +447,6 @@ THUMB( orr \reg , \reg , #PSR_T_BIT ) .size \name , . - \name .endm - .macro csdb -#ifdef CONFIG_THUMB2_KERNEL - .inst.w 0xf3af8014 -#else - .inst 0xe320f014 -#endif - .endm - - .macro check_uaccess, addr:req, size:req, limit:req, tmp:req, bad:req -#ifndef CONFIG_CPU_USE_DOMAINS - adds \tmp, \addr, #\size - 1 - sbcccs \tmp, \tmp, \limit - bcs \bad -#ifdef CONFIG_CPU_SPECTRE - movcs \addr, #0 - csdb -#endif -#endif - .endm - - .macro uaccess_mask_range_ptr, addr:req, size:req, limit:req, tmp:req -#ifdef CONFIG_CPU_SPECTRE - sub \tmp, \limit, #1 - subs \tmp, \tmp, \addr @ tmp = limit - 1 - addr - addhs \tmp, \tmp, #1 @ if (tmp >= 0) { - subhss \tmp, \tmp, \size @ tmp = limit - (addr + size) } - movlo \addr, #0 @ if (tmp < 0) addr = NULL - csdb -#endif - .endm - - .macro uaccess_disable, tmp, isb=1 -#ifdef CONFIG_CPU_SW_DOMAIN_PAN - /* - * Whenever we re-enter userspace, the domains should always be - * set appropriately. - */ - mov \tmp, #DACR_UACCESS_DISABLE - mcr p15, 0, \tmp, c3, c0, 0 @ Set domain register - .if \isb - instr_sync - .endif -#endif - .endm - - .macro uaccess_enable, tmp, isb=1 -#ifdef CONFIG_CPU_SW_DOMAIN_PAN - /* - * Whenever we re-enter userspace, the domains should always be - * set appropriately. - */ - mov \tmp, #DACR_UACCESS_ENABLE - mcr p15, 0, \tmp, c3, c0, 0 - .if \isb - instr_sync - .endif -#endif - .endm - - .macro uaccess_save, tmp -#ifdef CONFIG_CPU_SW_DOMAIN_PAN - mrc p15, 0, \tmp, c3, c0, 0 - str \tmp, [sp, #SVC_DACR] -#endif - .endm - - .macro uaccess_restore -#ifdef CONFIG_CPU_SW_DOMAIN_PAN - ldr r0, [sp, #SVC_DACR] - mcr p15, 0, r0, c3, c0, 0 -#endif - .endm - .irp c,,eq,ne,cs,cc,mi,pl,vs,vc,hi,ls,ge,lt,gt,le,hs,lo .macro ret\c, reg #if __LINUX_ARM_ARCH__ < 6 diff --git a/arch/arm/include/asm/futex.h b/arch/arm/include/asm/futex.h index ffebe7b7a5b7..91ca80035fc4 100644 --- a/arch/arm/include/asm/futex.h +++ b/arch/arm/include/asm/futex.h @@ -163,8 +163,13 @@ arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr) preempt_enable(); #endif - if (!ret) - *oval = oldval; + /* + * Store unconditionally. If ret != 0 the extra store is the least + * of the worries but GCC cannot figure out that __futex_atomic_op() + * is either setting ret to -EFAULT or storing the old value in + * oldval which results in a uninitialized warning at the call site. + */ + *oval = oldval; return ret; } diff --git a/arch/arm/include/asm/kexec-internal.h b/arch/arm/include/asm/kexec-internal.h new file mode 100644 index 000000000000..ecc2322db7aa --- /dev/null +++ b/arch/arm/include/asm/kexec-internal.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ARM_KEXEC_INTERNAL_H +#define _ARM_KEXEC_INTERNAL_H + +struct kexec_relocate_data { + unsigned long kexec_start_address; + unsigned long kexec_indirection_page; + unsigned long kexec_mach_type; + unsigned long kexec_r2; +}; + +#endif diff --git a/arch/arm/include/asm/kprobes.h b/arch/arm/include/asm/kprobes.h index 82290f212d8e..e1eb662e0f9e 100644 --- a/arch/arm/include/asm/kprobes.h +++ b/arch/arm/include/asm/kprobes.h @@ -52,20 +52,20 @@ int kprobe_exceptions_notify(struct notifier_block *self, unsigned long val, void *data); /* optinsn template addresses */ -extern __visible kprobe_opcode_t optprobe_template_entry; -extern __visible kprobe_opcode_t optprobe_template_val; -extern __visible kprobe_opcode_t optprobe_template_call; -extern __visible kprobe_opcode_t optprobe_template_end; -extern __visible kprobe_opcode_t optprobe_template_sub_sp; -extern __visible kprobe_opcode_t optprobe_template_add_sp; -extern __visible kprobe_opcode_t optprobe_template_restore_begin; -extern __visible kprobe_opcode_t optprobe_template_restore_orig_insn; -extern __visible kprobe_opcode_t optprobe_template_restore_end; +extern __visible kprobe_opcode_t optprobe_template_entry[]; +extern __visible kprobe_opcode_t optprobe_template_val[]; +extern __visible kprobe_opcode_t optprobe_template_call[]; +extern __visible kprobe_opcode_t optprobe_template_end[]; +extern __visible kprobe_opcode_t optprobe_template_sub_sp[]; +extern __visible kprobe_opcode_t optprobe_template_add_sp[]; +extern __visible kprobe_opcode_t optprobe_template_restore_begin[]; +extern __visible kprobe_opcode_t optprobe_template_restore_orig_insn[]; +extern __visible kprobe_opcode_t optprobe_template_restore_end[]; #define MAX_OPTIMIZED_LENGTH 4 #define MAX_OPTINSN_SIZE \ - ((unsigned long)&optprobe_template_end - \ - (unsigned long)&optprobe_template_entry) + ((unsigned long)optprobe_template_end - \ + (unsigned long)optprobe_template_entry) #define RELATIVEJUMP_SIZE 4 struct arch_optimized_insn { diff --git a/arch/arm/include/asm/kvm_emulate.h b/arch/arm/include/asm/kvm_emulate.h index 7d2ca035d6c8..11d4ff9f3e4d 100644 --- a/arch/arm/include/asm/kvm_emulate.h +++ b/arch/arm/include/asm/kvm_emulate.h @@ -216,7 +216,7 @@ static inline int kvm_vcpu_dabt_get_rd(struct kvm_vcpu *vcpu) return (kvm_vcpu_get_hsr(vcpu) & HSR_SRT_MASK) >> HSR_SRT_SHIFT; } -static inline bool kvm_vcpu_dabt_iss1tw(struct kvm_vcpu *vcpu) +static inline bool kvm_vcpu_abt_iss1tw(const struct kvm_vcpu *vcpu) { return kvm_vcpu_get_hsr(vcpu) & HSR_DABT_S1PTW; } @@ -248,16 +248,21 @@ static inline bool kvm_vcpu_trap_il_is32bit(struct kvm_vcpu *vcpu) return kvm_vcpu_get_hsr(vcpu) & HSR_IL; } -static inline u8 kvm_vcpu_trap_get_class(struct kvm_vcpu *vcpu) +static inline u8 kvm_vcpu_trap_get_class(const struct kvm_vcpu *vcpu) { return kvm_vcpu_get_hsr(vcpu) >> HSR_EC_SHIFT; } -static inline bool kvm_vcpu_trap_is_iabt(struct kvm_vcpu *vcpu) +static inline bool kvm_vcpu_trap_is_iabt(const struct kvm_vcpu *vcpu) { return kvm_vcpu_trap_get_class(vcpu) == HSR_EC_IABT; } +static inline bool kvm_vcpu_trap_is_exec_fault(const struct kvm_vcpu *vcpu) +{ + return kvm_vcpu_trap_is_iabt(vcpu) && !kvm_vcpu_abt_iss1tw(vcpu); +} + static inline u8 kvm_vcpu_trap_get_fault(struct kvm_vcpu *vcpu) { return kvm_vcpu_get_hsr(vcpu) & HSR_FSC; diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h index d0d0227fc70d..ae073fceb3f0 100644 --- a/arch/arm/include/asm/kvm_host.h +++ b/arch/arm/include/asm/kvm_host.h @@ -234,7 +234,7 @@ int __kvm_arm_vcpu_set_events(struct kvm_vcpu *vcpu, #define KVM_ARCH_WANT_MMU_NOTIFIER int kvm_unmap_hva_range(struct kvm *kvm, - unsigned long start, unsigned long end); + unsigned long start, unsigned long end, bool blockable); void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu); @@ -303,6 +303,7 @@ static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {} static inline void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu) {} static inline void kvm_arm_init_debug(void) {} +static inline void kvm_arm_vcpu_init_debug(struct kvm_vcpu *vcpu) {} static inline void kvm_arm_setup_debug(struct kvm_vcpu *vcpu) {} static inline void kvm_arm_clear_debug(struct kvm_vcpu *vcpu) {} static inline void kvm_arm_reset_debug_ptr(struct kvm_vcpu *vcpu) {} @@ -364,4 +365,6 @@ static inline void kvm_vcpu_put_sysregs(struct kvm_vcpu *vcpu) {} struct kvm *kvm_arch_alloc_vm(void); void kvm_arch_free_vm(struct kvm *kvm); +#define kvm_arm_vcpu_loaded(vcpu) (false) + #endif /* __ARM_KVM_HOST_H__ */ diff --git a/arch/arm/include/asm/percpu.h b/arch/arm/include/asm/percpu.h index a89b4076cde4..72821b4721ad 100644 --- a/arch/arm/include/asm/percpu.h +++ b/arch/arm/include/asm/percpu.h @@ -16,6 +16,8 @@ #ifndef _ASM_ARM_PERCPU_H_ #define _ASM_ARM_PERCPU_H_ +#include <asm/thread_info.h> + /* * Same as asm-generic/percpu.h, except that we store the per cpu offset * in the TPIDRPRW. TPIDRPRW only exists on V6K and V7 diff --git a/arch/arm/include/asm/uaccess-asm.h b/arch/arm/include/asm/uaccess-asm.h new file mode 100644 index 000000000000..907571fd05c6 --- /dev/null +++ b/arch/arm/include/asm/uaccess-asm.h @@ -0,0 +1,117 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef __ASM_UACCESS_ASM_H__ +#define __ASM_UACCESS_ASM_H__ + +#include <asm/asm-offsets.h> +#include <asm/domain.h> +#include <asm/memory.h> +#include <asm/thread_info.h> + + .macro csdb +#ifdef CONFIG_THUMB2_KERNEL + .inst.w 0xf3af8014 +#else + .inst 0xe320f014 +#endif + .endm + + .macro check_uaccess, addr:req, size:req, limit:req, tmp:req, bad:req +#ifndef CONFIG_CPU_USE_DOMAINS + adds \tmp, \addr, #\size - 1 + sbcscc \tmp, \tmp, \limit + bcs \bad +#ifdef CONFIG_CPU_SPECTRE + movcs \addr, #0 + csdb +#endif +#endif + .endm + + .macro uaccess_mask_range_ptr, addr:req, size:req, limit:req, tmp:req +#ifdef CONFIG_CPU_SPECTRE + sub \tmp, \limit, #1 + subs \tmp, \tmp, \addr @ tmp = limit - 1 - addr + addhs \tmp, \tmp, #1 @ if (tmp >= 0) { + subshs \tmp, \tmp, \size @ tmp = limit - (addr + size) } + movlo \addr, #0 @ if (tmp < 0) addr = NULL + csdb +#endif + .endm + + .macro uaccess_disable, tmp, isb=1 +#ifdef CONFIG_CPU_SW_DOMAIN_PAN + /* + * Whenever we re-enter userspace, the domains should always be + * set appropriately. + */ + mov \tmp, #DACR_UACCESS_DISABLE + mcr p15, 0, \tmp, c3, c0, 0 @ Set domain register + .if \isb + instr_sync + .endif +#endif + .endm + + .macro uaccess_enable, tmp, isb=1 +#ifdef CONFIG_CPU_SW_DOMAIN_PAN + /* + * Whenever we re-enter userspace, the domains should always be + * set appropriately. + */ + mov \tmp, #DACR_UACCESS_ENABLE + mcr p15, 0, \tmp, c3, c0, 0 + .if \isb + instr_sync + .endif +#endif + .endm + +#if defined(CONFIG_CPU_SW_DOMAIN_PAN) || defined(CONFIG_CPU_USE_DOMAINS) +#define DACR(x...) x +#else +#define DACR(x...) +#endif + + /* + * Save the address limit on entry to a privileged exception. + * + * If we are using the DACR for kernel access by the user accessors + * (CONFIG_CPU_USE_DOMAINS=y), always reset the DACR kernel domain + * back to client mode, whether or not \disable is set. + * + * If we are using SW PAN, set the DACR user domain to no access + * if \disable is set. + */ + .macro uaccess_entry, tsk, tmp0, tmp1, tmp2, disable + ldr \tmp1, [\tsk, #TI_ADDR_LIMIT] + mov \tmp2, #TASK_SIZE + str \tmp2, [\tsk, #TI_ADDR_LIMIT] + DACR( mrc p15, 0, \tmp0, c3, c0, 0) + DACR( str \tmp0, [sp, #SVC_DACR]) + str \tmp1, [sp, #SVC_ADDR_LIMIT] + .if \disable && IS_ENABLED(CONFIG_CPU_SW_DOMAIN_PAN) + /* kernel=client, user=no access */ + mov \tmp2, #DACR_UACCESS_DISABLE + mcr p15, 0, \tmp2, c3, c0, 0 + instr_sync + .elseif IS_ENABLED(CONFIG_CPU_USE_DOMAINS) + /* kernel=client */ + bic \tmp2, \tmp0, #domain_mask(DOMAIN_KERNEL) + orr \tmp2, \tmp2, #domain_val(DOMAIN_KERNEL, DOMAIN_CLIENT) + mcr p15, 0, \tmp2, c3, c0, 0 + instr_sync + .endif + .endm + + /* Restore the user access state previously saved by uaccess_entry */ + .macro uaccess_exit, tsk, tmp0, tmp1 + ldr \tmp1, [sp, #SVC_ADDR_LIMIT] + DACR( ldr \tmp0, [sp, #SVC_DACR]) + str \tmp1, [\tsk, #TI_ADDR_LIMIT] + DACR( mcr p15, 0, \tmp0, c3, c0, 0) + .endm + +#undef DACR + +#endif /* __ASM_UACCESS_ASM_H__ */ diff --git a/arch/arm/include/asm/vfpmacros.h b/arch/arm/include/asm/vfpmacros.h index ef5dfedacd8d..628c336e8e3b 100644 --- a/arch/arm/include/asm/vfpmacros.h +++ b/arch/arm/include/asm/vfpmacros.h @@ -29,13 +29,13 @@ ldr \tmp, =elf_hwcap @ may not have MVFR regs ldr \tmp, [\tmp, #0] tst \tmp, #HWCAP_VFPD32 - ldcnel p11, cr0, [\base],#32*4 @ FLDMIAD \base!, {d16-d31} + ldclne p11, cr0, [\base],#32*4 @ FLDMIAD \base!, {d16-d31} addeq \base, \base, #32*4 @ step over unused register space #else VFPFMRX \tmp, MVFR0 @ Media and VFP Feature Register 0 and \tmp, \tmp, #MVFR0_A_SIMD_MASK @ A_SIMD field cmp \tmp, #2 @ 32 x 64bit registers? - ldceql p11, cr0, [\base],#32*4 @ FLDMIAD \base!, {d16-d31} + ldcleq p11, cr0, [\base],#32*4 @ FLDMIAD \base!, {d16-d31} addne \base, \base, #32*4 @ step over unused register space #endif #endif @@ -53,13 +53,13 @@ ldr \tmp, =elf_hwcap @ may not have MVFR regs ldr \tmp, [\tmp, #0] tst \tmp, #HWCAP_VFPD32 - stcnel p11, cr0, [\base],#32*4 @ FSTMIAD \base!, {d16-d31} + stclne p11, cr0, [\base],#32*4 @ FSTMIAD \base!, {d16-d31} addeq \base, \base, #32*4 @ step over unused register space #else VFPFMRX \tmp, MVFR0 @ Media and VFP Feature Register 0 and \tmp, \tmp, #MVFR0_A_SIMD_MASK @ A_SIMD field cmp \tmp, #2 @ 32 x 64bit registers? - stceql p11, cr0, [\base],#32*4 @ FSTMIAD \base!, {d16-d31} + stcleq p11, cr0, [\base],#32*4 @ FSTMIAD \base!, {d16-d31} addne \base, \base, #32*4 @ step over unused register space #endif #endif diff --git a/arch/arm/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c index 3968d6c22455..40afe953a0e2 100644 --- a/arch/arm/kernel/asm-offsets.c +++ b/arch/arm/kernel/asm-offsets.c @@ -18,6 +18,7 @@ #include <linux/kvm_host.h> #endif #include <asm/cacheflush.h> +#include <asm/kexec-internal.h> #include <asm/glue-df.h> #include <asm/glue-pf.h> #include <asm/mach/arch.h> @@ -29,6 +30,7 @@ #include <asm/vdso_datapage.h> #include <asm/hardware/cache-l2x0.h> #include <linux/kbuild.h> +#include <linux/arm-smccc.h> #include "signal.h" /* @@ -158,6 +160,8 @@ int main(void) DEFINE(SLEEP_SAVE_SP_PHYS, offsetof(struct sleep_save_sp, save_ptr_stash_phys)); DEFINE(SLEEP_SAVE_SP_VIRT, offsetof(struct sleep_save_sp, save_ptr_stash)); #endif + DEFINE(ARM_SMCCC_QUIRK_ID_OFFS, offsetof(struct arm_smccc_quirk, id)); + DEFINE(ARM_SMCCC_QUIRK_STATE_OFFS, offsetof(struct arm_smccc_quirk, state)); BLANK(); DEFINE(DMA_BIDIRECTIONAL, DMA_BIDIRECTIONAL); DEFINE(DMA_TO_DEVICE, DMA_TO_DEVICE); @@ -189,5 +193,9 @@ int main(void) DEFINE(MPU_RGN_PRBAR, offsetof(struct mpu_rgn, prbar)); DEFINE(MPU_RGN_PRLAR, offsetof(struct mpu_rgn, prlar)); #endif + DEFINE(KEXEC_START_ADDR, offsetof(struct kexec_relocate_data, kexec_start_address)); + DEFINE(KEXEC_INDIR_PAGE, offsetof(struct kexec_relocate_data, kexec_indirection_page)); + DEFINE(KEXEC_MACH_TYPE, offsetof(struct kexec_relocate_data, kexec_mach_type)); + DEFINE(KEXEC_R2, offsetof(struct kexec_relocate_data, kexec_r2)); return 0; } diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S index e85a3af9ddeb..89e551eebff1 100644 --- a/arch/arm/kernel/entry-armv.S +++ b/arch/arm/kernel/entry-armv.S @@ -30,6 +30,7 @@ #include <asm/unistd.h> #include <asm/tls.h> #include <asm/system_info.h> +#include <asm/uaccess-asm.h> #include "entry-header.S" #include <asm/entry-macro-multi.S> @@ -182,15 +183,7 @@ ENDPROC(__und_invalid) stmia r7, {r2 - r6} get_thread_info tsk - ldr r0, [tsk, #TI_ADDR_LIMIT] - mov r1, #TASK_SIZE - str r1, [tsk, #TI_ADDR_LIMIT] - str r0, [sp, #SVC_ADDR_LIMIT] - - uaccess_save r0 - .if \uaccess - uaccess_disable r0 - .endif + uaccess_entry tsk, r0, r1, r2, \uaccess .if \trace #ifdef CONFIG_TRACE_IRQFLAGS diff --git a/arch/arm/kernel/entry-header.S b/arch/arm/kernel/entry-header.S index 62db1c9746cb..7b595f2d4a28 100644 --- a/arch/arm/kernel/entry-header.S +++ b/arch/arm/kernel/entry-header.S @@ -6,6 +6,7 @@ #include <asm/asm-offsets.h> #include <asm/errno.h> #include <asm/thread_info.h> +#include <asm/uaccess-asm.h> #include <asm/v7m.h> @ Bad Abort numbers @@ -217,9 +218,7 @@ blne trace_hardirqs_off #endif .endif - ldr r1, [sp, #SVC_ADDR_LIMIT] - uaccess_restore - str r1, [tsk, #TI_ADDR_LIMIT] + uaccess_exit tsk, r0, r1 #ifndef CONFIG_THUMB2_KERNEL @ ARM mode SVC restore @@ -263,9 +262,7 @@ @ on the stack remains correct). @ .macro svc_exit_via_fiq - ldr r1, [sp, #SVC_ADDR_LIMIT] - uaccess_restore - str r1, [tsk, #TI_ADDR_LIMIT] + uaccess_exit tsk, r0, r1 #ifndef CONFIG_THUMB2_KERNEL @ ARM mode restore mov r0, sp diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S index 6b1148cafffd..90add5ded3f1 100644 --- a/arch/arm/kernel/head.S +++ b/arch/arm/kernel/head.S @@ -675,11 +675,7 @@ ARM_BE8(rev16 ip, ip) bcc 1b bx lr #else -#ifdef CONFIG_CPU_ENDIAN_BE8 - moveq r0, #0x00004000 @ set bit 22, mov to mvn instruction -#else moveq r0, #0x400000 @ set bit 22, mov to mvn instruction -#endif b 2f 1: ldr ip, [r7, r3] #ifdef CONFIG_CPU_ENDIAN_BE8 @@ -688,7 +684,7 @@ ARM_BE8(rev16 ip, ip) tst ip, #0x000f0000 @ check the rotation field orrne ip, ip, r6, lsl #24 @ mask in offset bits 31-24 biceq ip, ip, #0x00004000 @ clear bit 22 - orreq ip, ip, r0 @ mask in offset bits 7-0 + orreq ip, ip, r0, ror #8 @ mask in offset bits 7-0 #else bic ip, ip, #0x000000ff tst ip, #0xf00 @ check the rotation field diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c index 1d5fbf1d1c67..2ee5b7f5e7ad 100644 --- a/arch/arm/kernel/hw_breakpoint.c +++ b/arch/arm/kernel/hw_breakpoint.c @@ -688,26 +688,68 @@ static void disable_single_step(struct perf_event *bp) arch_install_hw_breakpoint(bp); } +/* + * Arm32 hardware does not always report a watchpoint hit address that matches + * one of the watchpoints set. It can also report an address "near" the + * watchpoint if a single instruction access both watched and unwatched + * addresses. There is no straight-forward way, short of disassembling the + * offending instruction, to map that address back to the watchpoint. This + * function computes the distance of the memory access from the watchpoint as a + * heuristic for the likelyhood that a given access triggered the watchpoint. + * + * See this same function in the arm64 platform code, which has the same + * problem. + * + * The function returns the distance of the address from the bytes watched by + * the watchpoint. In case of an exact match, it returns 0. + */ +static u32 get_distance_from_watchpoint(unsigned long addr, u32 val, + struct arch_hw_breakpoint_ctrl *ctrl) +{ + u32 wp_low, wp_high; + u32 lens, lene; + + lens = __ffs(ctrl->len); + lene = __fls(ctrl->len); + + wp_low = val + lens; + wp_high = val + lene; + if (addr < wp_low) + return wp_low - addr; + else if (addr > wp_high) + return addr - wp_high; + else + return 0; +} + +static int watchpoint_fault_on_uaccess(struct pt_regs *regs, + struct arch_hw_breakpoint *info) +{ + return !user_mode(regs) && info->ctrl.privilege == ARM_BREAKPOINT_USER; +} + static void watchpoint_handler(unsigned long addr, unsigned int fsr, struct pt_regs *regs) { - int i, access; - u32 val, ctrl_reg, alignment_mask; + int i, access, closest_match = 0; + u32 min_dist = -1, dist; + u32 val, ctrl_reg; struct perf_event *wp, **slots; struct arch_hw_breakpoint *info; struct arch_hw_breakpoint_ctrl ctrl; slots = this_cpu_ptr(wp_on_reg); + /* + * Find all watchpoints that match the reported address. If no exact + * match is found. Attribute the hit to the closest watchpoint. + */ + rcu_read_lock(); for (i = 0; i < core_num_wrps; ++i) { - rcu_read_lock(); - wp = slots[i]; - if (wp == NULL) - goto unlock; + continue; - info = counter_arch_bp(wp); /* * The DFAR is an unknown value on debug architectures prior * to 7.1. Since we only allow a single watchpoint on these @@ -716,50 +758,69 @@ static void watchpoint_handler(unsigned long addr, unsigned int fsr, */ if (debug_arch < ARM_DEBUG_ARCH_V7_1) { BUG_ON(i > 0); + info = counter_arch_bp(wp); info->trigger = wp->attr.bp_addr; } else { - if (info->ctrl.len == ARM_BREAKPOINT_LEN_8) - alignment_mask = 0x7; - else - alignment_mask = 0x3; - - /* Check if the watchpoint value matches. */ - val = read_wb_reg(ARM_BASE_WVR + i); - if (val != (addr & ~alignment_mask)) - goto unlock; - - /* Possible match, check the byte address select. */ - ctrl_reg = read_wb_reg(ARM_BASE_WCR + i); - decode_ctrl_reg(ctrl_reg, &ctrl); - if (!((1 << (addr & alignment_mask)) & ctrl.len)) - goto unlock; - /* Check that the access type matches. */ if (debug_exception_updates_fsr()) { access = (fsr & ARM_FSR_ACCESS_MASK) ? HW_BREAKPOINT_W : HW_BREAKPOINT_R; if (!(access & hw_breakpoint_type(wp))) - goto unlock; + continue; } + val = read_wb_reg(ARM_BASE_WVR + i); + ctrl_reg = read_wb_reg(ARM_BASE_WCR + i); + decode_ctrl_reg(ctrl_reg, &ctrl); + dist = get_distance_from_watchpoint(addr, val, &ctrl); + if (dist < min_dist) { + min_dist = dist; + closest_match = i; + } + /* Is this an exact match? */ + if (dist != 0) + continue; + /* We have a winner. */ + info = counter_arch_bp(wp); info->trigger = addr; } pr_debug("watchpoint fired: address = 0x%x\n", info->trigger); + + /* + * If we triggered a user watchpoint from a uaccess routine, + * then handle the stepping ourselves since userspace really + * can't help us with this. + */ + if (watchpoint_fault_on_uaccess(regs, info)) + goto step; + perf_bp_event(wp, regs); /* - * If no overflow handler is present, insert a temporary - * mismatch breakpoint so we can single-step over the - * watchpoint trigger. + * Defer stepping to the overflow handler if one is installed. + * Otherwise, insert a temporary mismatch breakpoint so that + * we can single-step over the watchpoint trigger. */ + if (!is_default_overflow_handler(wp)) + continue; +step: + enable_single_step(wp, instruction_pointer(regs)); + } + + if (min_dist > 0 && min_dist != -1) { + /* No exact match found. */ + wp = slots[closest_match]; + info = counter_arch_bp(wp); + info->trigger = addr; + pr_debug("watchpoint fired: address = 0x%x\n", info->trigger); + perf_bp_event(wp, regs); if (is_default_overflow_handler(wp)) enable_single_step(wp, instruction_pointer(regs)); - -unlock: - rcu_read_unlock(); } + + rcu_read_unlock(); } static void watchpoint_single_step_handler(unsigned long pc) @@ -830,7 +891,7 @@ static void breakpoint_handler(unsigned long unknown, struct pt_regs *regs) info->trigger = addr; pr_debug("breakpoint fired: address = 0x%x\n", addr); perf_bp_event(bp, regs); - if (!bp->overflow_handler) + if (is_default_overflow_handler(bp)) enable_single_step(bp, addr); goto unlock; } diff --git a/arch/arm/kernel/machine_kexec.c b/arch/arm/kernel/machine_kexec.c index 76300f3813e8..734adeb42df8 100644 --- a/arch/arm/kernel/machine_kexec.c +++ b/arch/arm/kernel/machine_kexec.c @@ -15,6 +15,7 @@ #include <asm/pgalloc.h> #include <asm/mmu_context.h> #include <asm/cacheflush.h> +#include <asm/kexec-internal.h> #include <asm/fncpy.h> #include <asm/mach-types.h> #include <asm/smp_plat.h> @@ -24,11 +25,6 @@ extern void relocate_new_kernel(void); extern const unsigned int relocate_new_kernel_size; -extern unsigned long kexec_start_address; -extern unsigned long kexec_indirection_page; -extern unsigned long kexec_mach_type; -extern unsigned long kexec_boot_atags; - static atomic_t waiting_for_crash_ipi; /* @@ -161,6 +157,7 @@ void (*kexec_reinit)(void); void machine_kexec(struct kimage *image) { unsigned long page_list, reboot_entry_phys; + struct kexec_relocate_data *data; void (*reboot_entry)(void); void *reboot_code_buffer; @@ -176,18 +173,17 @@ void machine_kexec(struct kimage *image) reboot_code_buffer = page_address(image->control_code_page); - /* Prepare parameters for reboot_code_buffer*/ - set_kernel_text_rw(); - kexec_start_address = image->start; - kexec_indirection_page = page_list; - kexec_mach_type = machine_arch_type; - kexec_boot_atags = image->arch.kernel_r2; - /* copy our kernel relocation code to the control code page */ reboot_entry = fncpy(reboot_code_buffer, &relocate_new_kernel, relocate_new_kernel_size); + data = reboot_code_buffer + relocate_new_kernel_size; + data->kexec_start_address = image->start; + data->kexec_indirection_page = page_list; + data->kexec_mach_type = machine_arch_type; + data->kexec_r2 = image->arch.kernel_r2; + /* get the identity mapping physical address for the reboot code */ reboot_entry_phys = virt_to_idmap(reboot_entry); diff --git a/arch/arm/kernel/ptrace.c b/arch/arm/kernel/ptrace.c index 36718a424358..492ac74a63f4 100644 --- a/arch/arm/kernel/ptrace.c +++ b/arch/arm/kernel/ptrace.c @@ -229,8 +229,8 @@ static struct undef_hook arm_break_hook = { }; static struct undef_hook thumb_break_hook = { - .instr_mask = 0xffff, - .instr_val = 0xde01, + .instr_mask = 0xffffffff, + .instr_val = 0x0000de01, .cpsr_mask = PSR_T_BIT, .cpsr_val = PSR_T_BIT, .fn = break_trap, diff --git a/arch/arm/kernel/relocate_kernel.S b/arch/arm/kernel/relocate_kernel.S index 7eaa2ae7aff5..5e15b5912cb0 100644 --- a/arch/arm/kernel/relocate_kernel.S +++ b/arch/arm/kernel/relocate_kernel.S @@ -5,14 +5,16 @@ #include <linux/linkage.h> #include <asm/assembler.h> +#include <asm/asm-offsets.h> #include <asm/kexec.h> .align 3 /* not needed for this code, but keeps fncpy() happy */ ENTRY(relocate_new_kernel) - ldr r0,kexec_indirection_page - ldr r1,kexec_start_address + adr r7, relocate_new_kernel_end + ldr r0, [r7, #KEXEC_INDIR_PAGE] + ldr r1, [r7, #KEXEC_START_ADDR] /* * If there is no indirection page (we are doing crashdumps) @@ -57,34 +59,16 @@ ENTRY(relocate_new_kernel) 2: /* Jump to relocated kernel */ - mov lr,r1 - mov r0,#0 - ldr r1,kexec_mach_type - ldr r2,kexec_boot_atags - ARM( ret lr ) - THUMB( bx lr ) - - .align - - .globl kexec_start_address -kexec_start_address: - .long 0x0 - - .globl kexec_indirection_page -kexec_indirection_page: - .long 0x0 - - .globl kexec_mach_type -kexec_mach_type: - .long 0x0 - - /* phy addr of the atags for the new kernel */ - .globl kexec_boot_atags -kexec_boot_atags: - .long 0x0 + mov lr, r1 + mov r0, #0 + ldr r1, [r7, #KEXEC_MACH_TYPE] + ldr r2, [r7, #KEXEC_R2] + ARM( ret lr ) + THUMB( bx lr ) ENDPROC(relocate_new_kernel) + .align 3 relocate_new_kernel_end: .globl relocate_new_kernel_size diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c index b908382b69ff..1c01358b9b6d 100644 --- a/arch/arm/kernel/signal.c +++ b/arch/arm/kernel/signal.c @@ -697,18 +697,20 @@ struct page *get_signal_page(void) addr = page_address(page); + /* Poison the entire page */ + memset32(addr, __opcode_to_mem_arm(0xe7fddef1), + PAGE_SIZE / sizeof(u32)); + /* Give the signal return code some randomness */ offset = 0x200 + (get_random_int() & 0x7fc); signal_return_offset = offset; - /* - * Copy signal return handlers into the vector page, and - * set sigreturn to be a pointer to these. - */ + /* Copy signal return handlers into the page */ memcpy(addr + offset, sigreturn_codes, sizeof(sigreturn_codes)); - ptr = (unsigned long)addr + offset; - flush_icache_range(ptr, ptr + sizeof(sigreturn_codes)); + /* Flush out all instructions in this page */ + ptr = (unsigned long)addr; + flush_icache_range(ptr, ptr + PAGE_SIZE); return page; } diff --git a/arch/arm/kernel/smccc-call.S b/arch/arm/kernel/smccc-call.S index e5d43066b889..13d307cd364c 100644 --- a/arch/arm/kernel/smccc-call.S +++ b/arch/arm/kernel/smccc-call.S @@ -12,7 +12,9 @@ * */ #include <linux/linkage.h> +#include <linux/arm-smccc.h> +#include <asm/asm-offsets.h> #include <asm/opcodes-sec.h> #include <asm/opcodes-virt.h> #include <asm/unwind.h> @@ -36,7 +38,14 @@ UNWIND( .fnstart) UNWIND( .save {r4-r7}) ldm r12, {r4-r7} \instr - pop {r4-r7} + ldr r4, [sp, #36] + cmp r4, #0 + beq 1f // No quirk structure + ldr r5, [r4, #ARM_SMCCC_QUIRK_ID_OFFS] + cmp r5, #ARM_SMCCC_QUIRK_QCOM_A6 + bne 1f // No quirk present + str r6, [r4, #ARM_SMCCC_QUIRK_STATE_OFFS] +1: pop {r4-r7} ldr r12, [sp, #(4 * 4)] stm r12, {r0-r3} bx lr diff --git a/arch/arm/kernel/stacktrace.c b/arch/arm/kernel/stacktrace.c index a56e7c856ab5..d23ab9ec130a 100644 --- a/arch/arm/kernel/stacktrace.c +++ b/arch/arm/kernel/stacktrace.c @@ -21,6 +21,19 @@ * A simple function epilogue looks like this: * ldm sp, {fp, sp, pc} * + * When compiled with clang, pc and sp are not pushed. A simple function + * prologue looks like this when built with clang: + * + * stmdb {..., fp, lr} + * add fp, sp, #x + * sub sp, sp, #y + * + * A simple function epilogue looks like this when built with clang: + * + * sub sp, fp, #x + * ldm {..., fp, pc} + * + * * Note that with framepointer enabled, even the leaf functions have the same * prologue and epilogue, therefore we can ignore the LR value in this case. */ @@ -33,6 +46,16 @@ int notrace unwind_frame(struct stackframe *frame) low = frame->sp; high = ALIGN(low, THREAD_SIZE); +#ifdef CONFIG_CC_IS_CLANG + /* check current frame pointer is within bounds */ + if (fp < low + 4 || fp > high - 4) + return -EINVAL; + + frame->sp = frame->fp; + frame->fp = *(unsigned long *)(fp); + frame->pc = frame->lr; + frame->lr = *(unsigned long *)(fp + 4); +#else /* check current frame pointer is within bounds */ if (fp < low + 12 || fp > high - 4) return -EINVAL; @@ -41,6 +64,7 @@ int notrace unwind_frame(struct stackframe *frame) frame->fp = *(unsigned long *)(fp - 12); frame->sp = *(unsigned long *)(fp - 8); frame->pc = *(unsigned long *)(fp - 4); +#endif return 0; } @@ -91,6 +115,8 @@ static int save_trace(struct stackframe *frame, void *d) return 0; regs = (struct pt_regs *)frame->sp; + if ((unsigned long)®s[1] > ALIGN(frame->sp, THREAD_SIZE)) + return 0; trace->entries[trace->nr_entries++] = regs->ARM_pc; diff --git a/arch/arm/kernel/suspend.c b/arch/arm/kernel/suspend.c index d08099269e35..e126386fb78a 100644 --- a/arch/arm/kernel/suspend.c +++ b/arch/arm/kernel/suspend.c @@ -1,4 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 +#include <linux/ftrace.h> #include <linux/init.h> #include <linux/slab.h> #include <linux/mm_types.h> @@ -27,12 +28,22 @@ int cpu_suspend(unsigned long arg, int (*fn)(unsigned long)) return -EINVAL; /* + * Function graph tracer state gets incosistent when the kernel + * calls functions that never return (aka suspend finishers) hence + * disable graph tracing during their execution. + */ + pause_graph_tracing(); + + /* * Provide a temporary page table with an identity mapping for * the MMU-enable code, required for resuming. On successful * resume (indicated by a zero return code), we need to switch * back to the correct page tables. */ ret = __cpu_suspend(arg, fn, __mpidr); + + unpause_graph_tracing(); + if (ret == 0) { cpu_switch_mm(mm->pgd, mm); local_flush_bp_all(); @@ -46,7 +57,13 @@ int cpu_suspend(unsigned long arg, int (*fn)(unsigned long)) int cpu_suspend(unsigned long arg, int (*fn)(unsigned long)) { u32 __mpidr = cpu_logical_map(smp_processor_id()); - return __cpu_suspend(arg, fn, __mpidr); + int ret; + + pause_graph_tracing(); + ret = __cpu_suspend(arg, fn, __mpidr); + unpause_graph_tracing(); + + return ret; } #define idmap_pgd NULL #endif diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c index badf02ca3693..aec533168f04 100644 --- a/arch/arm/kernel/traps.c +++ b/arch/arm/kernel/traps.c @@ -67,14 +67,16 @@ static void dump_mem(const char *, const char *, unsigned long, unsigned long); void dump_backtrace_entry(unsigned long where, unsigned long from, unsigned long frame) { + unsigned long end = frame + 4 + sizeof(struct pt_regs); + #ifdef CONFIG_KALLSYMS printk("[<%08lx>] (%ps) from [<%08lx>] (%pS)\n", where, (void *)where, from, (void *)from); #else printk("Function entered at [<%08lx>] from [<%08lx>]\n", where, from); #endif - if (in_entry_text(from)) - dump_mem("", "Exception stack", frame + 4, frame + 4 + sizeof(struct pt_regs)); + if (in_entry_text(from) && end <= ALIGN(frame, THREAD_SIZE)) + dump_mem("", "Exception stack", frame + 4, end); } void dump_backtrace_stm(u32 *stack, u32 instruction) diff --git a/arch/arm/lib/bitops.h b/arch/arm/lib/bitops.h index 93cddab73072..95bd35991288 100644 --- a/arch/arm/lib/bitops.h +++ b/arch/arm/lib/bitops.h @@ -7,7 +7,7 @@ ENTRY( \name ) UNWIND( .fnstart ) ands ip, r1, #3 - strneb r1, [ip] @ assert word-aligned + strbne r1, [ip] @ assert word-aligned mov r2, #1 and r3, r0, #31 @ Get bit offset mov r0, r0, lsr #5 @@ -32,7 +32,7 @@ ENDPROC(\name ) ENTRY( \name ) UNWIND( .fnstart ) ands ip, r1, #3 - strneb r1, [ip] @ assert word-aligned + strbne r1, [ip] @ assert word-aligned mov r2, #1 and r3, r0, #31 @ Get bit offset mov r0, r0, lsr #5 @@ -62,7 +62,7 @@ ENDPROC(\name ) ENTRY( \name ) UNWIND( .fnstart ) ands ip, r1, #3 - strneb r1, [ip] @ assert word-aligned + strbne r1, [ip] @ assert word-aligned and r2, r0, #31 mov r0, r0, lsr #5 mov r3, #1 @@ -89,7 +89,7 @@ ENDPROC(\name ) ENTRY( \name ) UNWIND( .fnstart ) ands ip, r1, #3 - strneb r1, [ip] @ assert word-aligned + strbne r1, [ip] @ assert word-aligned and r3, r0, #31 mov r0, r0, lsr #5 save_and_disable_irqs ip diff --git a/arch/arm/mach-at91/pm.c b/arch/arm/mach-at91/pm.c index e2e4df3d11e5..21bfe9b6e16a 100644 --- a/arch/arm/mach-at91/pm.c +++ b/arch/arm/mach-at91/pm.c @@ -542,13 +542,13 @@ static void __init at91_pm_sram_init(void) sram_pool = gen_pool_get(&pdev->dev, NULL); if (!sram_pool) { pr_warn("%s: sram pool unavailable!\n", __func__); - return; + goto out_put_device; } sram_base = gen_pool_alloc(sram_pool, at91_pm_suspend_in_sram_sz); if (!sram_base) { pr_warn("%s: unable to alloc sram!\n", __func__); - return; + goto out_put_device; } sram_pbase = gen_pool_virt_to_phys(sram_pool, sram_base); @@ -556,12 +556,17 @@ static void __init at91_pm_sram_init(void) at91_pm_suspend_in_sram_sz, false); if (!at91_suspend_sram_fn) { pr_warn("SRAM: Could not map\n"); - return; + goto out_put_device; } /* Copy the pm suspend handler to SRAM */ at91_suspend_sram_fn = fncpy(at91_suspend_sram_fn, &at91_pm_suspend_in_sram, at91_pm_suspend_in_sram_sz); + return; + +out_put_device: + put_device(&pdev->dev); + return; } static bool __init at91_is_pm_mode_active(int pm_mode) diff --git a/arch/arm/mach-at91/pm_suspend.S b/arch/arm/mach-at91/pm_suspend.S index a7c6ae13c945..d650a5a1dfee 100644 --- a/arch/arm/mach-at91/pm_suspend.S +++ b/arch/arm/mach-at91/pm_suspend.S @@ -220,6 +220,10 @@ ENDPROC(at91_backup_mode) orr tmp1, tmp1, #AT91_PMC_KEY str tmp1, [pmc, #AT91_CKGR_MOR] + /* Quirk for SAM9X60's PMC */ + nop + nop + wait_mckrdy /* Enable the crystal oscillator */ diff --git a/arch/arm/mach-footbridge/cats-pci.c b/arch/arm/mach-footbridge/cats-pci.c index 0b2fd7e2e9b4..90b1e9be430e 100644 --- a/arch/arm/mach-footbridge/cats-pci.c +++ b/arch/arm/mach-footbridge/cats-pci.c @@ -15,14 +15,14 @@ #include <asm/mach-types.h> /* cats host-specific stuff */ -static int irqmap_cats[] __initdata = { IRQ_PCI, IRQ_IN0, IRQ_IN1, IRQ_IN3 }; +static int irqmap_cats[] = { IRQ_PCI, IRQ_IN0, IRQ_IN1, IRQ_IN3 }; static u8 cats_no_swizzle(struct pci_dev *dev, u8 *pin) { return 0; } -static int __init cats_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) +static int cats_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) { if (dev->irq >= 255) return -1; /* not a valid interrupt. */ diff --git a/arch/arm/mach-footbridge/dc21285.c b/arch/arm/mach-footbridge/dc21285.c index 16d71bac0061..2d1f822700a1 100644 --- a/arch/arm/mach-footbridge/dc21285.c +++ b/arch/arm/mach-footbridge/dc21285.c @@ -69,15 +69,15 @@ dc21285_read_config(struct pci_bus *bus, unsigned int devfn, int where, if (addr) switch (size) { case 1: - asm("ldrb %0, [%1, %2]" + asm volatile("ldrb %0, [%1, %2]" : "=r" (v) : "r" (addr), "r" (where) : "cc"); break; case 2: - asm("ldrh %0, [%1, %2]" + asm volatile("ldrh %0, [%1, %2]" : "=r" (v) : "r" (addr), "r" (where) : "cc"); break; case 4: - asm("ldr %0, [%1, %2]" + asm volatile("ldr %0, [%1, %2]" : "=r" (v) : "r" (addr), "r" (where) : "cc"); break; } @@ -103,17 +103,17 @@ dc21285_write_config(struct pci_bus *bus, unsigned int devfn, int where, if (addr) switch (size) { case 1: - asm("strb %0, [%1, %2]" + asm volatile("strb %0, [%1, %2]" : : "r" (value), "r" (addr), "r" (where) : "cc"); break; case 2: - asm("strh %0, [%1, %2]" + asm volatile("strh %0, [%1, %2]" : : "r" (value), "r" (addr), "r" (where) : "cc"); break; case 4: - asm("str %0, [%1, %2]" + asm volatile("str %0, [%1, %2]" : : "r" (value), "r" (addr), "r" (where) : "cc"); break; diff --git a/arch/arm/mach-footbridge/ebsa285-pci.c b/arch/arm/mach-footbridge/ebsa285-pci.c index 6f28aaa9ca79..c3f280d08fa7 100644 --- a/arch/arm/mach-footbridge/ebsa285-pci.c +++ b/arch/arm/mach-footbridge/ebsa285-pci.c @@ -14,9 +14,9 @@ #include <asm/mach/pci.h> #include <asm/mach-types.h> -static int irqmap_ebsa285[] __initdata = { IRQ_IN3, IRQ_IN1, IRQ_IN0, IRQ_PCI }; +static int irqmap_ebsa285[] = { IRQ_IN3, IRQ_IN1, IRQ_IN0, IRQ_PCI }; -static int __init ebsa285_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) +static int ebsa285_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) { if (dev->vendor == PCI_VENDOR_ID_CONTAQ && dev->device == PCI_DEVICE_ID_CONTAQ_82C693) diff --git a/arch/arm/mach-footbridge/netwinder-pci.c b/arch/arm/mach-footbridge/netwinder-pci.c index 9473aa0305e5..e8304392074b 100644 --- a/arch/arm/mach-footbridge/netwinder-pci.c +++ b/arch/arm/mach-footbridge/netwinder-pci.c @@ -18,7 +18,7 @@ * We now use the slot ID instead of the device identifiers to select * which interrupt is routed where. */ -static int __init netwinder_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) +static int netwinder_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) { switch (slot) { case 0: /* host bridge */ diff --git a/arch/arm/mach-footbridge/personal-pci.c b/arch/arm/mach-footbridge/personal-pci.c index 4391e433a4b2..9d19aa98a663 100644 --- a/arch/arm/mach-footbridge/personal-pci.c +++ b/arch/arm/mach-footbridge/personal-pci.c @@ -14,13 +14,12 @@ #include <asm/mach/pci.h> #include <asm/mach-types.h> -static int irqmap_personal_server[] __initdata = { +static int irqmap_personal_server[] = { IRQ_IN0, IRQ_IN1, IRQ_IN2, IRQ_IN3, 0, 0, 0, IRQ_DOORBELLHOST, IRQ_DMA1, IRQ_DMA2, IRQ_PCI }; -static int __init personal_server_map_irq(const struct pci_dev *dev, u8 slot, - u8 pin) +static int personal_server_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) { unsigned char line; diff --git a/arch/arm/mach-imx/Makefile b/arch/arm/mach-imx/Makefile index e9cfe8e86f33..02bf3eab4196 100644 --- a/arch/arm/mach-imx/Makefile +++ b/arch/arm/mach-imx/Makefile @@ -89,8 +89,10 @@ AFLAGS_suspend-imx6.o :=-Wa,-march=armv7-a obj-$(CONFIG_SOC_IMX6) += suspend-imx6.o obj-$(CONFIG_SOC_IMX53) += suspend-imx53.o endif +ifeq ($(CONFIG_ARM_CPU_SUSPEND),y) AFLAGS_resume-imx6.o :=-Wa,-march=armv7-a obj-$(CONFIG_SOC_IMX6) += resume-imx6.o +endif obj-$(CONFIG_SOC_IMX6) += pm-imx6.o obj-$(CONFIG_SOC_IMX1) += mach-imx1.o diff --git a/arch/arm/mach-imx/pm-imx5.c b/arch/arm/mach-imx/pm-imx5.c index 868781fd460c..14c630c899c5 100644 --- a/arch/arm/mach-imx/pm-imx5.c +++ b/arch/arm/mach-imx/pm-imx5.c @@ -301,14 +301,14 @@ static int __init imx_suspend_alloc_ocram( if (!ocram_pool) { pr_warn("%s: ocram pool unavailable!\n", __func__); ret = -ENODEV; - goto put_node; + goto put_device; } ocram_base = gen_pool_alloc(ocram_pool, size); if (!ocram_base) { pr_warn("%s: unable to alloc ocram!\n", __func__); ret = -ENOMEM; - goto put_node; + goto put_device; } phys = gen_pool_virt_to_phys(ocram_pool, ocram_base); @@ -318,6 +318,8 @@ static int __init imx_suspend_alloc_ocram( if (virt_out) *virt_out = virt; +put_device: + put_device(&pdev->dev); put_node: of_node_put(node); diff --git a/arch/arm/mach-imx/pm-imx6.c b/arch/arm/mach-imx/pm-imx6.c index 529f4b5bbd3a..4bfefbec971a 100644 --- a/arch/arm/mach-imx/pm-imx6.c +++ b/arch/arm/mach-imx/pm-imx6.c @@ -497,14 +497,14 @@ static int __init imx6q_suspend_init(const struct imx6_pm_socdata *socdata) if (!ocram_pool) { pr_warn("%s: ocram pool unavailable!\n", __func__); ret = -ENODEV; - goto put_node; + goto put_device; } ocram_base = gen_pool_alloc(ocram_pool, MX6Q_SUSPEND_OCRAM_SIZE); if (!ocram_base) { pr_warn("%s: unable to alloc ocram!\n", __func__); ret = -ENOMEM; - goto put_node; + goto put_device; } ocram_pbase = gen_pool_virt_to_phys(ocram_pool, ocram_base); @@ -527,7 +527,7 @@ static int __init imx6q_suspend_init(const struct imx6_pm_socdata *socdata) ret = imx6_pm_get_base(&pm_info->mmdc_base, socdata->mmdc_compat); if (ret) { pr_warn("%s: failed to get mmdc base %d!\n", __func__, ret); - goto put_node; + goto put_device; } ret = imx6_pm_get_base(&pm_info->src_base, socdata->src_compat); @@ -574,7 +574,7 @@ static int __init imx6q_suspend_init(const struct imx6_pm_socdata *socdata) &imx6_suspend, MX6Q_SUSPEND_OCRAM_SIZE - sizeof(*pm_info)); - goto put_node; + goto put_device; pl310_cache_map_failed: iounmap(pm_info->gpc_base.vbase); @@ -584,6 +584,8 @@ iomuxc_map_failed: iounmap(pm_info->src_base.vbase); src_map_failed: iounmap(pm_info->mmdc_base.vbase); +put_device: + put_device(&pdev->dev); put_node: of_node_put(node); diff --git a/arch/arm/mach-imx/suspend-imx6.S b/arch/arm/mach-imx/suspend-imx6.S index 7d84b617af48..99d2e296082c 100644 --- a/arch/arm/mach-imx/suspend-imx6.S +++ b/arch/arm/mach-imx/suspend-imx6.S @@ -73,6 +73,7 @@ #define MX6Q_CCM_CCR 0x0 .align 3 + .arm .macro sync_l2_cache diff --git a/arch/arm/mach-integrator/Kconfig b/arch/arm/mach-integrator/Kconfig index cefe44f6889b..ba124f8704fa 100644 --- a/arch/arm/mach-integrator/Kconfig +++ b/arch/arm/mach-integrator/Kconfig @@ -3,6 +3,8 @@ menuconfig ARCH_INTEGRATOR depends on ARCH_MULTI_V4T || ARCH_MULTI_V5 || ARCH_MULTI_V6 select ARM_AMBA select COMMON_CLK_VERSATILE + select CMA + select DMA_CMA select HAVE_TCM select ICST select MFD_SYSCON @@ -34,14 +36,13 @@ config INTEGRATOR_IMPD1 select ARM_VIC select GPIO_PL061 select GPIOLIB + select REGULATOR + select REGULATOR_FIXED_VOLTAGE help The IM-PD1 is an add-on logic module for the Integrator which allows ARM(R) Ltd PrimeCells to be developed and evaluated. The IM-PD1 can be found on the Integrator/PP2 platform. - To compile this driver as a module, choose M here: the - module will be called impd1. - config INTEGRATOR_CM7TDMI bool "Integrator/CM7TDMI core module" depends on ARCH_INTEGRATOR_AP diff --git a/arch/arm/mach-keystone/keystone.c b/arch/arm/mach-keystone/keystone.c index 84613abf35a3..79ff5b953431 100644 --- a/arch/arm/mach-keystone/keystone.c +++ b/arch/arm/mach-keystone/keystone.c @@ -65,7 +65,7 @@ static void __init keystone_init(void) static long long __init keystone_pv_fixup(void) { long long offset; - phys_addr_t mem_start, mem_end; + u64 mem_start, mem_end; mem_start = memblock_start_of_DRAM(); mem_end = memblock_end_of_DRAM(); @@ -78,7 +78,7 @@ static long long __init keystone_pv_fixup(void) if (mem_start < KEYSTONE_HIGH_PHYS_START || mem_end > KEYSTONE_HIGH_PHYS_END) { pr_crit("Invalid address space for memory (%08llx-%08llx)\n", - (u64)mem_start, (u64)mem_end); + mem_start, mem_end); return 0; } diff --git a/arch/arm/mach-omap2/omap_device.c b/arch/arm/mach-omap2/omap_device.c index 41c7b905980a..23e8146b9b32 100644 --- a/arch/arm/mach-omap2/omap_device.c +++ b/arch/arm/mach-omap2/omap_device.c @@ -239,10 +239,12 @@ static int _omap_device_notifier_call(struct notifier_block *nb, break; case BUS_NOTIFY_BIND_DRIVER: od = to_omap_device(pdev); - if (od && (od->_state == OMAP_DEVICE_STATE_ENABLED) && - pm_runtime_status_suspended(dev)) { + if (od) { od->_driver_status = BUS_NOTIFY_BIND_DRIVER; - pm_runtime_set_active(dev); + if (od->_state == OMAP_DEVICE_STATE_ENABLED && + pm_runtime_status_suspended(dev)) { + pm_runtime_set_active(dev); + } } break; case BUS_NOTIFY_ADD_DEVICE: diff --git a/arch/arm/mach-shmobile/pm-rmobile.c b/arch/arm/mach-shmobile/pm-rmobile.c index e348bcfe389d..cb8b02a1abe2 100644 --- a/arch/arm/mach-shmobile/pm-rmobile.c +++ b/arch/arm/mach-shmobile/pm-rmobile.c @@ -330,6 +330,7 @@ static int __init rmobile_init_pm_domains(void) pmd = of_get_child_by_name(np, "pm-domains"); if (!pmd) { + iounmap(base); pr_warn("%pOF lacks pm-domains node\n", np); continue; } diff --git a/arch/arm/mach-socfpga/pm.c b/arch/arm/mach-socfpga/pm.c index d4866788702c..b782294ee30b 100644 --- a/arch/arm/mach-socfpga/pm.c +++ b/arch/arm/mach-socfpga/pm.c @@ -60,14 +60,14 @@ static int socfpga_setup_ocram_self_refresh(void) if (!ocram_pool) { pr_warn("%s: ocram pool unavailable!\n", __func__); ret = -ENODEV; - goto put_node; + goto put_device; } ocram_base = gen_pool_alloc(ocram_pool, socfpga_sdram_self_refresh_sz); if (!ocram_base) { pr_warn("%s: unable to alloc ocram!\n", __func__); ret = -ENOMEM; - goto put_node; + goto put_device; } ocram_pbase = gen_pool_virt_to_phys(ocram_pool, ocram_base); @@ -78,7 +78,7 @@ static int socfpga_setup_ocram_self_refresh(void) if (!suspend_ocram_base) { pr_warn("%s: __arm_ioremap_exec failed!\n", __func__); ret = -ENOMEM; - goto put_node; + goto put_device; } /* Copy the code that puts DDR in self refresh to ocram */ @@ -92,6 +92,8 @@ static int socfpga_setup_ocram_self_refresh(void) if (!socfpga_sdram_self_refresh_in_ocram) ret = -EFAULT; +put_device: + put_device(&pdev->dev); put_node: of_node_put(np); diff --git a/arch/arm/mach-sunxi/sunxi.c b/arch/arm/mach-sunxi/sunxi.c index de4b0e932f22..aa08b8cb0152 100644 --- a/arch/arm/mach-sunxi/sunxi.c +++ b/arch/arm/mach-sunxi/sunxi.c @@ -66,6 +66,7 @@ static const char * const sun8i_board_dt_compat[] = { "allwinner,sun8i-h2-plus", "allwinner,sun8i-h3", "allwinner,sun8i-r40", + "allwinner,sun8i-v3", "allwinner,sun8i-v3s", NULL, }; diff --git a/arch/arm/mach-tegra/tegra.c b/arch/arm/mach-tegra/tegra.c index f9587be48235..37a2aaeb44cc 100644 --- a/arch/arm/mach-tegra/tegra.c +++ b/arch/arm/mach-tegra/tegra.c @@ -112,8 +112,8 @@ static const char * const tegra_dt_board_compat[] = { }; DT_MACHINE_START(TEGRA_DT, "NVIDIA Tegra SoC (Flattened Device Tree)") - .l2c_aux_val = 0x3c400001, - .l2c_aux_mask = 0xc20fc3fe, + .l2c_aux_val = 0x3c400000, + .l2c_aux_mask = 0xc20fc3ff, .smp = smp_ops(tegra_smp_ops), .map_io = tegra_map_common_io, .init_early = tegra_init_early, diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c index 808efbb89b88..02f613def40d 100644 --- a/arch/arm/mm/cache-l2x0.c +++ b/arch/arm/mm/cache-l2x0.c @@ -1261,20 +1261,28 @@ static void __init l2c310_of_parse(const struct device_node *np, ret = of_property_read_u32(np, "prefetch-data", &val); if (ret == 0) { - if (val) + if (val) { prefetch |= L310_PREFETCH_CTRL_DATA_PREFETCH; - else + *aux_val |= L310_PREFETCH_CTRL_DATA_PREFETCH; + } else { prefetch &= ~L310_PREFETCH_CTRL_DATA_PREFETCH; + *aux_val &= ~L310_PREFETCH_CTRL_DATA_PREFETCH; + } + *aux_mask &= ~L310_PREFETCH_CTRL_DATA_PREFETCH; } else if (ret != -EINVAL) { pr_err("L2C-310 OF prefetch-data property value is missing\n"); } ret = of_property_read_u32(np, "prefetch-instr", &val); if (ret == 0) { - if (val) + if (val) { prefetch |= L310_PREFETCH_CTRL_INSTR_PREFETCH; - else + *aux_val |= L310_PREFETCH_CTRL_INSTR_PREFETCH; + } else { prefetch &= ~L310_PREFETCH_CTRL_INSTR_PREFETCH; + *aux_val &= ~L310_PREFETCH_CTRL_INSTR_PREFETCH; + } + *aux_mask &= ~L310_PREFETCH_CTRL_INSTR_PREFETCH; } else if (ret != -EINVAL) { pr_err("L2C-310 OF prefetch-instr property value is missing\n"); } diff --git a/arch/arm/mm/proc-macros.S b/arch/arm/mm/proc-macros.S index 5461d589a1e2..60ac7c5999a9 100644 --- a/arch/arm/mm/proc-macros.S +++ b/arch/arm/mm/proc-macros.S @@ -5,6 +5,7 @@ * VMA_VM_FLAGS * VM_EXEC */ +#include <linux/const.h> #include <asm/asm-offsets.h> #include <asm/thread_info.h> @@ -30,7 +31,7 @@ * act_mm - get current->active_mm */ .macro act_mm, rd - bic \rd, sp, #8128 + bic \rd, sp, #(THREAD_SIZE - 1) & ~63 bic \rd, \rd, #63 ldr \rd, [\rd, #TI_TASK] .if (TSK_ACTIVE_MM > IMM12_MASK) diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c index 25b3ee85066e..328ced7bfaf2 100644 --- a/arch/arm/net/bpf_jit_32.c +++ b/arch/arm/net/bpf_jit_32.c @@ -930,7 +930,11 @@ static inline void emit_a32_rsh_i64(const s8 dst[], rd = arm_bpf_get_reg64(dst, tmp, ctx); /* Do LSR operation */ - if (val < 32) { + if (val == 0) { + /* An immediate value of 0 encodes a shift amount of 32 + * for LSR. To shift by 0, don't do anything. + */ + } else if (val < 32) { emit(ARM_MOV_SI(tmp2[1], rd[1], SRTYPE_LSR, val), ctx); emit(ARM_ORR_SI(rd[1], tmp2[1], rd[0], SRTYPE_ASL, 32 - val), ctx); emit(ARM_MOV_SI(rd[0], rd[0], SRTYPE_LSR, val), ctx); @@ -956,7 +960,11 @@ static inline void emit_a32_arsh_i64(const s8 dst[], rd = arm_bpf_get_reg64(dst, tmp, ctx); /* Do ARSH operation */ - if (val < 32) { + if (val == 0) { + /* An immediate value of 0 encodes a shift amount of 32 + * for ASR. To shift by 0, don't do anything. + */ + } else if (val < 32) { emit(ARM_MOV_SI(tmp2[1], rd[1], SRTYPE_LSR, val), ctx); emit(ARM_ORR_SI(rd[1], tmp2[1], rd[0], SRTYPE_ASL, 32 - val), ctx); emit(ARM_MOV_SI(rd[0], rd[0], SRTYPE_ASR, val), ctx); @@ -993,21 +1001,35 @@ static inline void emit_a32_mul_r64(const s8 dst[], const s8 src[], arm_bpf_put_reg32(dst_hi, rd[0], ctx); } +static bool is_ldst_imm(s16 off, const u8 size) +{ + s16 off_max = 0; + + switch (size) { + case BPF_B: + case BPF_W: + off_max = 0xfff; + break; + case BPF_H: + off_max = 0xff; + break; + case BPF_DW: + /* Need to make sure off+4 does not overflow. */ + off_max = 0xfff - 4; + break; + } + return -off_max <= off && off <= off_max; +} + /* *(size *)(dst + off) = src */ static inline void emit_str_r(const s8 dst, const s8 src[], - s32 off, struct jit_ctx *ctx, const u8 sz){ + s16 off, struct jit_ctx *ctx, const u8 sz){ const s8 *tmp = bpf2a32[TMP_REG_1]; - s32 off_max; s8 rd; rd = arm_bpf_get_reg32(dst, tmp[1], ctx); - if (sz == BPF_H) - off_max = 0xff; - else - off_max = 0xfff; - - if (off < 0 || off > off_max) { + if (!is_ldst_imm(off, sz)) { emit_a32_mov_i(tmp[0], off, ctx); emit(ARM_ADD_R(tmp[0], tmp[0], rd), ctx); rd = tmp[0]; @@ -1036,18 +1058,12 @@ static inline void emit_str_r(const s8 dst, const s8 src[], /* dst = *(size*)(src + off) */ static inline void emit_ldx_r(const s8 dst[], const s8 src, - s32 off, struct jit_ctx *ctx, const u8 sz){ + s16 off, struct jit_ctx *ctx, const u8 sz){ const s8 *tmp = bpf2a32[TMP_REG_1]; const s8 *rd = is_stacked(dst_lo) ? tmp : dst; s8 rm = src; - s32 off_max; - - if (sz == BPF_H) - off_max = 0xff; - else - off_max = 0xfff; - if (off < 0 || off > off_max) { + if (!is_ldst_imm(off, sz)) { emit_a32_mov_i(tmp[0], off, ctx); emit(ARM_ADD_R(tmp[0], tmp[0], src), ctx); rm = tmp[0]; diff --git a/arch/arm/plat-samsung/Kconfig b/arch/arm/plat-samsung/Kconfig index 377ff9cda667..c83baa51289f 100644 --- a/arch/arm/plat-samsung/Kconfig +++ b/arch/arm/plat-samsung/Kconfig @@ -240,6 +240,7 @@ config SAMSUNG_PM_DEBUG bool "Samsung PM Suspend debug" depends on PM && DEBUG_KERNEL depends on DEBUG_EXYNOS_UART || DEBUG_S3C24XX_UART || DEBUG_S3C2410_UART + depends on DEBUG_LL && MMU help Say Y here if you want verbose debugging from the PM Suspend and Resume code. See <file:Documentation/arm/Samsung-S3C24XX/Suspend.txt> diff --git a/arch/arm/probes/kprobes/opt-arm.c b/arch/arm/probes/kprobes/opt-arm.c index 0dc23fc227ed..cf08cb726767 100644 --- a/arch/arm/probes/kprobes/opt-arm.c +++ b/arch/arm/probes/kprobes/opt-arm.c @@ -98,21 +98,21 @@ asm ( "optprobe_template_end:\n"); #define TMPL_VAL_IDX \ - ((unsigned long *)&optprobe_template_val - (unsigned long *)&optprobe_template_entry) + ((unsigned long *)optprobe_template_val - (unsigned long *)optprobe_template_entry) #define TMPL_CALL_IDX \ - ((unsigned long *)&optprobe_template_call - (unsigned long *)&optprobe_template_entry) + ((unsigned long *)optprobe_template_call - (unsigned long *)optprobe_template_entry) #define TMPL_END_IDX \ - ((unsigned long *)&optprobe_template_end - (unsigned long *)&optprobe_template_entry) + ((unsigned long *)optprobe_template_end - (unsigned long *)optprobe_template_entry) #define TMPL_ADD_SP \ - ((unsigned long *)&optprobe_template_add_sp - (unsigned long *)&optprobe_template_entry) + ((unsigned long *)optprobe_template_add_sp - (unsigned long *)optprobe_template_entry) #define TMPL_SUB_SP \ - ((unsigned long *)&optprobe_template_sub_sp - (unsigned long *)&optprobe_template_entry) + ((unsigned long *)optprobe_template_sub_sp - (unsigned long *)optprobe_template_entry) #define TMPL_RESTORE_BEGIN \ - ((unsigned long *)&optprobe_template_restore_begin - (unsigned long *)&optprobe_template_entry) + ((unsigned long *)optprobe_template_restore_begin - (unsigned long *)optprobe_template_entry) #define TMPL_RESTORE_ORIGN_INSN \ - ((unsigned long *)&optprobe_template_restore_orig_insn - (unsigned long *)&optprobe_template_entry) + ((unsigned long *)optprobe_template_restore_orig_insn - (unsigned long *)optprobe_template_entry) #define TMPL_RESTORE_END \ - ((unsigned long *)&optprobe_template_restore_end - (unsigned long *)&optprobe_template_entry) + ((unsigned long *)optprobe_template_restore_end - (unsigned long *)optprobe_template_entry) /* * ARM can always optimize an instruction when using ARM ISA, except @@ -247,7 +247,7 @@ int arch_prepare_optimized_kprobe(struct optimized_kprobe *op, struct kprobe *or } /* Copy arch-dep-instance from template. */ - memcpy(code, (unsigned long *)&optprobe_template_entry, + memcpy(code, (unsigned long *)optprobe_template_entry, TMPL_END_IDX * sizeof(kprobe_opcode_t)); /* Adjust buffer according to instruction. */ diff --git a/arch/arm/probes/uprobes/core.c b/arch/arm/probes/uprobes/core.c index bf992264060e..b1b7b51c938c 100644 --- a/arch/arm/probes/uprobes/core.c +++ b/arch/arm/probes/uprobes/core.c @@ -207,7 +207,7 @@ unsigned long uprobe_get_swbp_addr(struct pt_regs *regs) static struct undef_hook uprobes_arm_break_hook = { .instr_mask = 0x0fffffff, .instr_val = (UPROBE_SWBP_ARM_INSN & 0x0fffffff), - .cpsr_mask = MODE_MASK, + .cpsr_mask = (PSR_T_BIT | MODE_MASK), .cpsr_val = USR_MODE, .fn = uprobe_trap_handler, }; @@ -215,7 +215,7 @@ static struct undef_hook uprobes_arm_break_hook = { static struct undef_hook uprobes_arm_ss_hook = { .instr_mask = 0x0fffffff, .instr_val = (UPROBE_SS_ARM_INSN & 0x0fffffff), - .cpsr_mask = MODE_MASK, + .cpsr_mask = (PSR_T_BIT | MODE_MASK), .cpsr_val = USR_MODE, .fn = uprobe_trap_handler, }; diff --git a/arch/arm/vdso/Makefile b/arch/arm/vdso/Makefile index f4efff9d3afb..1f5ec9741e6d 100644 --- a/arch/arm/vdso/Makefile +++ b/arch/arm/vdso/Makefile @@ -10,12 +10,13 @@ obj-vdso := $(addprefix $(obj)/, $(obj-vdso)) ccflags-y := -fPIC -fno-common -fno-builtin -fno-stack-protector ccflags-y += -DDISABLE_BRANCH_PROFILING -VDSO_LDFLAGS := -Wl,-Bsymbolic -Wl,--no-undefined -Wl,-soname=linux-vdso.so.1 -VDSO_LDFLAGS += -Wl,-z,max-page-size=4096 -Wl,-z,common-page-size=4096 -VDSO_LDFLAGS += -nostdlib -shared -VDSO_LDFLAGS += $(call cc-ldoption, -Wl$(comma)--hash-style=sysv) -VDSO_LDFLAGS += $(call cc-ldoption, -Wl$(comma)--build-id) -VDSO_LDFLAGS += $(call cc-ldoption, -fuse-ld=bfd) +ldflags-$(CONFIG_CPU_ENDIAN_BE8) := --be8 +ldflags-y := -Bsymbolic --no-undefined -soname=linux-vdso.so.1 \ + -z max-page-size=4096 -z common-page-size=4096 \ + -nostdlib -shared $(ldflags-y) \ + $(call ld-option, --hash-style=sysv) \ + $(call ld-option, --build-id) \ + -T obj-$(CONFIG_VDSO) += vdso.o extra-$(CONFIG_VDSO) += vdso.lds @@ -37,8 +38,8 @@ KCOV_INSTRUMENT := n $(obj)/vdso.o : $(obj)/vdso.so # Link rule for the .so file -$(obj)/vdso.so.raw: $(src)/vdso.lds $(obj-vdso) FORCE - $(call if_changed,vdsold) +$(obj)/vdso.so.raw: $(obj)/vdso.lds $(obj-vdso) FORCE + $(call if_changed,ld) $(obj)/vdso.so.dbg: $(obj)/vdso.so.raw $(obj)/vdsomunge FORCE $(call if_changed,vdsomunge) @@ -48,11 +49,6 @@ $(obj)/%.so: OBJCOPYFLAGS := -S $(obj)/%.so: $(obj)/%.so.dbg FORCE $(call if_changed,objcopy) -# Actual build commands -quiet_cmd_vdsold = VDSO $@ - cmd_vdsold = $(CC) $(c_flags) $(VDSO_LDFLAGS) \ - -Wl,-T $(filter %.lds,$^) $(filter %.o,$^) -o $@ - quiet_cmd_vdsomunge = MUNGE $@ cmd_vdsomunge = $(objtree)/$(obj)/vdsomunge $< $@ diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c index 07060e5b5864..dd946c77e801 100644 --- a/arch/arm/xen/enlighten.c +++ b/arch/arm/xen/enlighten.c @@ -404,8 +404,6 @@ static int __init xen_guest_init(void) return -ENOMEM; } gnttab_init(); - if (!xen_initial_domain()) - xenbus_probe(NULL); /* * Making sure board specific code will not set up ops for diff --git a/arch/arm/xen/p2m.c b/arch/arm/xen/p2m.c index 0641ba54ab62..8a8a388549e7 100644 --- a/arch/arm/xen/p2m.c +++ b/arch/arm/xen/p2m.c @@ -91,10 +91,39 @@ int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops, int i; for (i = 0; i < count; i++) { + struct gnttab_unmap_grant_ref unmap; + int rc; + if (map_ops[i].status) continue; - set_phys_to_machine(map_ops[i].host_addr >> XEN_PAGE_SHIFT, - map_ops[i].dev_bus_addr >> XEN_PAGE_SHIFT); + if (likely(set_phys_to_machine(map_ops[i].host_addr >> XEN_PAGE_SHIFT, + map_ops[i].dev_bus_addr >> XEN_PAGE_SHIFT))) + continue; + + /* + * Signal an error for this slot. This in turn requires + * immediate unmapping. + */ + map_ops[i].status = GNTST_general_error; + unmap.host_addr = map_ops[i].host_addr, + unmap.handle = map_ops[i].handle; + map_ops[i].handle = ~0; + if (map_ops[i].flags & GNTMAP_device_map) + unmap.dev_bus_addr = map_ops[i].dev_bus_addr; + else + unmap.dev_bus_addr = 0; + + /* + * Pre-populate the status field, to be recognizable in + * the log message below. + */ + unmap.status = 1; + + rc = HYPERVISOR_grant_table_op(GNTTABOP_unmap_grant_ref, + &unmap, 1); + if (rc || unmap.status != GNTST_okay) + pr_err_once("gnttab unmap failed: rc=%d st=%d\n", + rc, unmap.status); } return 0; diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 51fe21f5d078..1daefa57e274 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -473,7 +473,7 @@ config ARM64_ERRATUM_1024718 help This option adds work around for Arm Cortex-A55 Erratum 1024718. - Affected Cortex-A55 cores (r0p0, r0p1, r1p0) could cause incorrect + Affected Cortex-A55 cores (all revisions) could cause incorrect update of the hardware dirty bit when the DBM/AP bits are updated without a break-before-make. The work around is to disable the usage of hardware DBM locally on the affected cores. CPUs not affected by @@ -499,6 +499,22 @@ config ARM64_ERRATUM_1463225 If unsure, say Y. +config ARM64_ERRATUM_1542419 + bool "Neoverse-N1: workaround mis-ordering of instruction fetches" + default y + help + This option adds a workaround for ARM Neoverse-N1 erratum + 1542419. + + Affected Neoverse-N1 cores could execute a stale instruction when + modified by another CPU. The workaround depends on a firmware + counterpart. + + Workaround the issue by hiding the DIC feature from EL0. This + forces user-space to perform cache maintenance. + + If unsure, say Y. + config CAVIUM_ERRATUM_22375 bool "Cavium erratum 22375, 24313" default y diff --git a/arch/arm64/Kconfig.platforms b/arch/arm64/Kconfig.platforms index 393d2b524284..91c7ffad8541 100644 --- a/arch/arm64/Kconfig.platforms +++ b/arch/arm64/Kconfig.platforms @@ -46,6 +46,7 @@ config ARCH_BCM_IPROC config ARCH_BERLIN bool "Marvell Berlin SoC Family" select DW_APB_ICTL + select DW_APB_TIMER_OF select GPIOLIB select PINCTRL help diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index 9a5e28141211..dc54a883513a 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -10,7 +10,7 @@ # # Copyright (C) 1995-2001 by Russell King -LDFLAGS_vmlinux :=--no-undefined -X +LDFLAGS_vmlinux :=--no-undefined -X -z norelro CPPFLAGS_vmlinux.lds = -DTEXT_OFFSET=$(TEXT_OFFSET) GZFLAGS :=-9 @@ -18,7 +18,7 @@ ifeq ($(CONFIG_RELOCATABLE), y) # Pass --no-apply-dynamic-relocs to restore pre-binutils-2.27 behaviour # for relative relocs, since this leads to better Image compression # with the relocation offsets always being zero. -LDFLAGS_vmlinux += -shared -Bsymbolic -z notext -z norelro \ +LDFLAGS_vmlinux += -shared -Bsymbolic -z notext \ $(call ld-option, --no-apply-dynamic-relocs) endif diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-bananapi-m64.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-bananapi-m64.dts index 094cfed13df9..13ce24e922ee 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-a64-bananapi-m64.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-bananapi-m64.dts @@ -97,7 +97,7 @@ &emac { pinctrl-names = "default"; pinctrl-0 = <&rgmii_pins>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; phy-handle = <&ext_rgmii_phy>; phy-supply = <®_dc1sw>; status = "okay"; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64-plus.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64-plus.dts index d5b6e8159a33..5d0905f0f1c1 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64-plus.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64-plus.dts @@ -52,7 +52,7 @@ &emac { pinctrl-names = "default"; pinctrl-0 = <&rgmii_pins>; - phy-mode = "rgmii"; + phy-mode = "rgmii-txid"; phy-handle = <&ext_rgmii_phy>; status = "okay"; }; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-pinebook.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-pinebook.dts index 897e60cbe38d..ecb3e10c85e0 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-a64-pinebook.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-pinebook.dts @@ -67,8 +67,6 @@ }; &ehci0 { - phys = <&usbphy 0>; - phy-names = "usb"; status = "okay"; }; @@ -107,6 +105,7 @@ pinctrl-0 = <&mmc2_pins>; vmmc-supply = <®_dcdc1>; vqmmc-supply = <®_eldo1>; + max-frequency = <200000000>; bus-width = <8>; non-removable; cap-mmc-hw-reset; @@ -115,8 +114,6 @@ }; &ohci0 { - phys = <&usbphy 0>; - phy-names = "usb"; status = "okay"; }; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-sopine.dtsi b/arch/arm64/boot/dts/allwinner/sun50i-a64-sopine.dtsi index 6723b8695e0b..ca39084fddc0 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-a64-sopine.dtsi +++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-sopine.dtsi @@ -51,7 +51,6 @@ pinctrl-names = "default"; pinctrl-0 = <&mmc0_pins>; vmmc-supply = <®_dcdc1>; - non-removable; disable-wp; bus-width = <4>; cd-gpios = <&pio 5 6 GPIO_ACTIVE_LOW>; /* PF6 */ diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi b/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi index 7abc4ea30541..30cc2e83a288 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi +++ b/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi @@ -264,7 +264,7 @@ resets = <&ccu RST_BUS_MMC2>; reset-names = "ahb"; interrupts = <GIC_SPI 62 IRQ_TYPE_LEVEL_HIGH>; - max-frequency = <200000000>; + max-frequency = <150000000>; status = "disabled"; #address-cells = <1>; #size-cells = <0>; @@ -312,6 +312,8 @@ <&ccu CLK_USB_OHCI0>; resets = <&ccu RST_BUS_OHCI0>, <&ccu RST_BUS_EHCI0>; + phys = <&usbphy 0>; + phy-names = "usb"; status = "disabled"; }; @@ -322,6 +324,8 @@ clocks = <&ccu CLK_BUS_OHCI0>, <&ccu CLK_USB_OHCI0>; resets = <&ccu RST_BUS_OHCI0>; + phys = <&usbphy 0>; + phy-names = "usb"; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-pc2.dts b/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-pc2.dts index 3e0d5a9c096d..5fbfa76daae2 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-pc2.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-pc2.dts @@ -157,7 +157,7 @@ pinctrl-0 = <&emac_rgmii_pins>; phy-supply = <®_gmac_3v3>; phy-handle = <&ext_rgmii_phy>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; status = "okay"; }; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-prime.dts b/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-prime.dts index b75ca4d7d001..7a30211d59ef 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-prime.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-prime.dts @@ -164,7 +164,7 @@ pinctrl-0 = <&emac_rgmii_pins>; phy-supply = <®_gmac_3v3>; phy-handle = <&ext_rgmii_phy>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; status = "okay"; }; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h6.dtsi b/arch/arm64/boot/dts/allwinner/sun50i-h6.dtsi index bd4391269611..6e4e45907738 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-h6.dtsi +++ b/arch/arm64/boot/dts/allwinner/sun50i-h6.dtsi @@ -70,8 +70,7 @@ }; pmu { - compatible = "arm,cortex-a53-pmu", - "arm,armv8-pmuv3"; + compatible = "arm,cortex-a53-pmu"; interrupts = <GIC_SPI 140 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 141 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 142 IRQ_TYPE_LEVEL_HIGH>, diff --git a/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts b/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts index faa017d4cd56..636bab51de38 100644 --- a/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts +++ b/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts @@ -151,6 +151,7 @@ }; &qspi { + status = "okay"; flash@0 { #address-cells = <1>; #size-cells = <1>; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi index 8f0bb3c44bd6..5d7724b3a612 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi @@ -266,6 +266,11 @@ }; }; +&hwrng { + clocks = <&clkc CLKID_RNG0>; + clock-names = "core"; +}; + &i2c_A { clocks = <&clkc CLKID_I2C>; }; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxm-khadas-vim2.dts b/arch/arm64/boot/dts/amlogic/meson-gxm-khadas-vim2.dts index bdf7c6c5983c..30fa9302a4dc 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxm-khadas-vim2.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxm-khadas-vim2.dts @@ -399,7 +399,7 @@ #size-cells = <1>; compatible = "winbond,w25q16", "jedec,spi-nor"; reg = <0>; - spi-max-frequency = <3000000>; + spi-max-frequency = <104000000>; }; }; diff --git a/arch/arm64/boot/dts/broadcom/northstar2/ns2.dtsi b/arch/arm64/boot/dts/broadcom/northstar2/ns2.dtsi index ea854f689fda..6bfb7bbd264a 100644 --- a/arch/arm64/boot/dts/broadcom/northstar2/ns2.dtsi +++ b/arch/arm64/boot/dts/broadcom/northstar2/ns2.dtsi @@ -745,7 +745,7 @@ }; qspi: spi@66470200 { - compatible = "brcm,spi-bcm-qspi", "brcm,spi-ns2-qspi"; + compatible = "brcm,spi-ns2-qspi", "brcm,spi-bcm-qspi"; reg = <0x66470200 0x184>, <0x66470000 0x124>, <0x67017408 0x004>, diff --git a/arch/arm64/boot/dts/exynos/exynos5433-tm2-common.dtsi b/arch/arm64/boot/dts/exynos/exynos5433-tm2-common.dtsi index a1e3194b7483..d64f97d97c35 100644 --- a/arch/arm64/boot/dts/exynos/exynos5433-tm2-common.dtsi +++ b/arch/arm64/boot/dts/exynos/exynos5433-tm2-common.dtsi @@ -378,7 +378,7 @@ s2mps13-pmic@66 { compatible = "samsung,s2mps13-pmic"; interrupt-parent = <&gpa0>; - interrupts = <7 IRQ_TYPE_NONE>; + interrupts = <7 IRQ_TYPE_LEVEL_LOW>; reg = <0x66>; samsung,s2mps11-wrstbi-ground; diff --git a/arch/arm64/boot/dts/exynos/exynos7-espresso.dts b/arch/arm64/boot/dts/exynos/exynos7-espresso.dts index 00dd89b92b42..2ba62118ae90 100644 --- a/arch/arm64/boot/dts/exynos/exynos7-espresso.dts +++ b/arch/arm64/boot/dts/exynos/exynos7-espresso.dts @@ -85,7 +85,7 @@ s2mps15_pmic@66 { compatible = "samsung,s2mps15-pmic"; reg = <0x66>; - interrupts = <2 IRQ_TYPE_NONE>; + interrupts = <2 IRQ_TYPE_LEVEL_LOW>; interrupt-parent = <&gpa0>; pinctrl-names = "default"; pinctrl-0 = <&pmic_irq>; @@ -152,6 +152,7 @@ regulator-min-microvolt = <700000>; regulator-max-microvolt = <1150000>; regulator-enable-ramp-delay = <125>; + regulator-always-on; }; ldo8_reg: LDO8 { diff --git a/arch/arm64/boot/dts/exynos/exynos7.dtsi b/arch/arm64/boot/dts/exynos/exynos7.dtsi index 31b1a606cb66..5c5e57026c27 100644 --- a/arch/arm64/boot/dts/exynos/exynos7.dtsi +++ b/arch/arm64/boot/dts/exynos/exynos7.dtsi @@ -62,8 +62,10 @@ }; psci { - compatible = "arm,psci-0.2"; + compatible = "arm,psci"; method = "smc"; + cpu_off = <0x84000002>; + cpu_on = <0xC4000003>; }; soc: soc { @@ -494,13 +496,6 @@ pmu_system_controller: system-controller@105c0000 { compatible = "samsung,exynos7-pmu", "syscon"; reg = <0x105c0000 0x5000>; - - reboot: syscon-reboot { - compatible = "syscon-reboot"; - regmap = <&pmu_system_controller>; - offset = <0x0400>; - mask = <0x1>; - }; }; rtc: rtc@10590000 { @@ -638,3 +633,4 @@ }; #include "exynos7-pinctrl.dtsi" +#include "arm/exynos-syscon-restart.dtsi" diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1012a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1012a.dtsi index 5da732f82fa0..712264e4e26e 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1012a.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls1012a.dtsi @@ -177,6 +177,7 @@ ranges = <0x0 0x00 0x1700000 0x100000>; reg = <0x00 0x1700000 0x0 0x100000>; interrupts = <GIC_SPI 75 IRQ_TYPE_LEVEL_HIGH>; + dma-coherent; sec_jr0: jr@10000 { compatible = "fsl,sec-v5.4-job-ring", diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi index b9c0f2de8f12..3ec60e33f299 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi @@ -237,6 +237,7 @@ ranges = <0x0 0x00 0x1700000 0x100000>; reg = <0x00 0x1700000 0x0 0x100000>; interrupts = <0 75 0x4>; + dma-coherent; sec_jr0: jr@10000 { compatible = "fsl,sec-v5.4-job-ring", diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi index de6af453a6e1..3452971a8e1c 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi @@ -243,6 +243,7 @@ ranges = <0x0 0x00 0x1700000 0x100000>; reg = <0x00 0x1700000 0x0 0x100000>; interrupts = <GIC_SPI 75 IRQ_TYPE_LEVEL_HIGH>; + dma-coherent; sec_jr0: jr@10000 { compatible = "fsl,sec-v5.4-job-ring", @@ -303,7 +304,7 @@ dcfg: dcfg@1ee0000 { compatible = "fsl,ls1046a-dcfg", "syscon"; - reg = <0x0 0x1ee0000 0x0 0x10000>; + reg = <0x0 0x1ee0000 0x0 0x1000>; big-endian; }; diff --git a/arch/arm64/boot/dts/hisilicon/hi3660-hikey960.dts b/arch/arm64/boot/dts/hisilicon/hi3660-hikey960.dts index c98bcbc8dfba..53848e0e5e0c 100644 --- a/arch/arm64/boot/dts/hisilicon/hi3660-hikey960.dts +++ b/arch/arm64/boot/dts/hisilicon/hi3660-hikey960.dts @@ -530,6 +530,17 @@ status = "ok"; compatible = "adi,adv7533"; reg = <0x39>; + adi,dsi-lanes = <4>; + ports { + #address-cells = <1>; + #size-cells = <0>; + port@0 { + reg = <0>; + }; + port@1 { + reg = <1>; + }; + }; }; }; diff --git a/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts b/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts index e80a792827ed..60568392d21e 100644 --- a/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts +++ b/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts @@ -515,7 +515,7 @@ reg = <0x39>; interrupt-parent = <&gpio1>; interrupts = <1 2>; - pd-gpio = <&gpio0 4 0>; + pd-gpios = <&gpio0 4 0>; adi,dsi-lanes = <4>; #sound-dai-cells = <0>; diff --git a/arch/arm64/boot/dts/marvell/armada-3720-espressobin.dts b/arch/arm64/boot/dts/marvell/armada-3720-espressobin.dts index 3ab25ad402b9..1a3e6e3b04eb 100644 --- a/arch/arm64/boot/dts/marvell/armada-3720-espressobin.dts +++ b/arch/arm64/boot/dts/marvell/armada-3720-espressobin.dts @@ -19,6 +19,16 @@ model = "Globalscale Marvell ESPRESSOBin Board"; compatible = "globalscale,espressobin", "marvell,armada3720", "marvell,armada3710"; + aliases { + ethernet0 = ð0; + /* for dsa slave device */ + ethernet1 = &switch0port1; + ethernet2 = &switch0port2; + ethernet3 = &switch0port3; + serial0 = &uart0; + serial1 = &uart1; + }; + chosen { stdout-path = "serial0:115200n8"; }; @@ -130,25 +140,25 @@ #address-cells = <1>; #size-cells = <0>; - port@0 { + switch0port0: port@0 { reg = <0>; label = "cpu"; ethernet = <ð0>; }; - port@1 { + switch0port1: port@1 { reg = <1>; label = "wan"; phy-handle = <&switch0phy0>; }; - port@2 { + switch0port2: port@2 { reg = <2>; label = "lan0"; phy-handle = <&switch0phy1>; }; - port@3 { + switch0port3: port@3 { reg = <3>; label = "lan1"; phy-handle = <&switch0phy2>; diff --git a/arch/arm64/boot/dts/marvell/armada-37xx.dtsi b/arch/arm64/boot/dts/marvell/armada-37xx.dtsi index d9531e242eb4..3a611250f598 100644 --- a/arch/arm64/boot/dts/marvell/armada-37xx.dtsi +++ b/arch/arm64/boot/dts/marvell/armada-37xx.dtsi @@ -143,7 +143,8 @@ }; nb_periph_clk: nb-periph-clk@13000 { - compatible = "marvell,armada-3700-periph-clock-nb"; + compatible = "marvell,armada-3700-periph-clock-nb", + "syscon"; reg = <0x13000 0x100>; clocks = <&tbg 0>, <&tbg 1>, <&tbg 2>, <&tbg 3>, <&xtalclk>; diff --git a/arch/arm64/boot/dts/mediatek/mt7622.dtsi b/arch/arm64/boot/dts/mediatek/mt7622.dtsi index de2c47bdbe64..2bcee994898a 100644 --- a/arch/arm64/boot/dts/mediatek/mt7622.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt7622.dtsi @@ -641,6 +641,8 @@ clocks = <&pericfg CLK_PERI_MSDC30_1_PD>, <&topckgen CLK_TOP_AXI_SEL>; clock-names = "source", "hclk"; + resets = <&pericfg MT7622_PERI_MSDC1_SW_RST>; + reset-names = "hrst"; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/mediatek/mt8173.dtsi b/arch/arm64/boot/dts/mediatek/mt8173.dtsi index abd2f15a544b..12837523dac8 100644 --- a/arch/arm64/boot/dts/mediatek/mt8173.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8173.dtsi @@ -223,21 +223,21 @@ cpu_on = <0x84000003>; }; - clk26m: oscillator@0 { + clk26m: oscillator0 { compatible = "fixed-clock"; #clock-cells = <0>; clock-frequency = <26000000>; clock-output-names = "clk26m"; }; - clk32k: oscillator@1 { + clk32k: oscillator1 { compatible = "fixed-clock"; #clock-cells = <0>; clock-frequency = <32000>; clock-output-names = "clk32k"; }; - cpum_ck: oscillator@2 { + cpum_ck: oscillator2 { compatible = "fixed-clock"; #clock-cells = <0>; clock-frequency = <0>; @@ -253,19 +253,19 @@ sustainable-power = <1500>; /* milliwatts */ trips { - threshold: trip-point@0 { + threshold: trip-point0 { temperature = <68000>; hysteresis = <2000>; type = "passive"; }; - target: trip-point@1 { + target: trip-point1 { temperature = <85000>; hysteresis = <2000>; type = "passive"; }; - cpu_crit: cpu_crit@0 { + cpu_crit: cpu_crit0 { temperature = <115000>; hysteresis = <2000>; type = "critical"; @@ -273,12 +273,12 @@ }; cooling-maps { - map@0 { + map0 { trip = <&target>; cooling-device = <&cpu0 0 0>; contribution = <3072>; }; - map@1 { + map1 { trip = <&target>; cooling-device = <&cpu2 0 0>; contribution = <1024>; @@ -291,7 +291,7 @@ #address-cells = <2>; #size-cells = <2>; ranges; - vpu_dma_reserved: vpu_dma_mem_region { + vpu_dma_reserved: vpu_dma_mem_region@b7000000 { compatible = "shared-dma-pool"; reg = <0 0xb7000000 0 0x500000>; alignment = <0x1000>; @@ -343,7 +343,7 @@ reg = <0 0x10005000 0 0x1000>; }; - pio: pinctrl@10005000 { + pio: pinctrl@1000b000 { compatible = "mediatek,mt8173-pinctrl"; reg = <0 0x1000b000 0 0x1000>; mediatek,pctl-regmap = <&syscfg_pctl_a>; @@ -541,7 +541,7 @@ status = "disabled"; }; - gic: interrupt-controller@10220000 { + gic: interrupt-controller@10221000 { compatible = "arm,gic-400"; #interrupt-cells = <3>; interrupt-parent = <&gic>; @@ -1111,7 +1111,7 @@ <&mmsys CLK_MM_DSI1_DIGITAL>, <&mipi_tx1>; clock-names = "engine", "digital", "hs"; - phy = <&mipi_tx1>; + phys = <&mipi_tx1>; phy-names = "dphy"; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/nvidia/tegra194-p2888.dtsi b/arch/arm64/boot/dts/nvidia/tegra194-p2888.dtsi index 57d3f00464ce..7352954e12be 100644 --- a/arch/arm64/boot/dts/nvidia/tegra194-p2888.dtsi +++ b/arch/arm64/boot/dts/nvidia/tegra194-p2888.dtsi @@ -32,7 +32,7 @@ phy-reset-gpios = <&gpio TEGRA194_MAIN_GPIO(G, 5) GPIO_ACTIVE_LOW>; phy-handle = <&phy>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; mdio { #address-cells = <1>; diff --git a/arch/arm64/boot/dts/nvidia/tegra210.dtsi b/arch/arm64/boot/dts/nvidia/tegra210.dtsi index 6597c0894137..4eecf3b02468 100644 --- a/arch/arm64/boot/dts/nvidia/tegra210.dtsi +++ b/arch/arm64/boot/dts/nvidia/tegra210.dtsi @@ -826,6 +826,7 @@ <&tegra_car 128>, /* hda2hdmi */ <&tegra_car 111>; /* hda2codec_2x */ reset-names = "hda", "hda2hdmi", "hda2codec_2x"; + power-domains = <&pd_sor>; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/qcom/msm8916-pins.dtsi b/arch/arm64/boot/dts/qcom/msm8916-pins.dtsi index 390a2fa28514..6754817658fa 100644 --- a/arch/arm64/boot/dts/qcom/msm8916-pins.dtsi +++ b/arch/arm64/boot/dts/qcom/msm8916-pins.dtsi @@ -516,7 +516,7 @@ pins = "gpio63", "gpio64", "gpio65", "gpio66", "gpio67", "gpio68"; drive-strength = <8>; - bias-pull-none; + bias-disable; }; }; cdc_pdm_lines_sus: pdm_lines_off { @@ -529,7 +529,7 @@ pins = "gpio63", "gpio64", "gpio65", "gpio66", "gpio67", "gpio68"; drive-strength = <2>; - bias-disable; + bias-pull-down; }; }; }; @@ -545,7 +545,7 @@ pins = "gpio113", "gpio114", "gpio115", "gpio116"; drive-strength = <8>; - bias-pull-none; + bias-disable; }; }; @@ -573,7 +573,7 @@ pinconf { pins = "gpio110"; drive-strength = <8>; - bias-pull-none; + bias-disable; }; }; @@ -599,7 +599,7 @@ pinconf { pins = "gpio116"; drive-strength = <8>; - bias-pull-none; + bias-disable; }; }; ext_mclk_tlmm_lines_sus: mclk_lines_off { @@ -627,7 +627,7 @@ pins = "gpio112", "gpio117", "gpio118", "gpio119"; drive-strength = <8>; - bias-pull-none; + bias-disable; }; }; ext_sec_tlmm_lines_sus: tlmm_lines_off { diff --git a/arch/arm64/boot/dts/qcom/msm8916.dtsi b/arch/arm64/boot/dts/qcom/msm8916.dtsi index 8011e564a234..ba42c6239922 100644 --- a/arch/arm64/boot/dts/qcom/msm8916.dtsi +++ b/arch/arm64/boot/dts/qcom/msm8916.dtsi @@ -64,7 +64,7 @@ no-map; }; - reserved@8668000 { + reserved@86680000 { reg = <0x0 0x86680000 0x0 0x80000>; no-map; }; @@ -77,7 +77,7 @@ qcom,client-id = <1>; }; - rfsa@867e00000 { + rfsa@867e0000 { reg = <0x0 0x867e0000 0x0 0x20000>; no-map; }; @@ -877,7 +877,7 @@ reg-names = "mdp_phys"; interrupt-parent = <&mdss>; - interrupts = <0 0>; + interrupts = <0>; clocks = <&gcc GCC_MDSS_AHB_CLK>, <&gcc GCC_MDSS_AXI_CLK>, @@ -909,7 +909,7 @@ reg-names = "dsi_ctrl"; interrupt-parent = <&mdss>; - interrupts = <4 0>; + interrupts = <4>; assigned-clocks = <&gcc BYTE0_CLK_SRC>, <&gcc PCLK0_CLK_SRC>; diff --git a/arch/arm64/boot/dts/qcom/pm8916.dtsi b/arch/arm64/boot/dts/qcom/pm8916.dtsi index 196b1c0ceb9b..b968afa8da17 100644 --- a/arch/arm64/boot/dts/qcom/pm8916.dtsi +++ b/arch/arm64/boot/dts/qcom/pm8916.dtsi @@ -99,7 +99,7 @@ wcd_codec: codec@f000 { compatible = "qcom,pm8916-wcd-analog-codec"; - reg = <0xf000 0x200>; + reg = <0xf000>; reg-names = "pmic-codec-core"; clocks = <&gcc GCC_CODEC_DIGCODEC_CLK>; clock-names = "mclk"; diff --git a/arch/arm64/boot/dts/renesas/r8a77980.dtsi b/arch/arm64/boot/dts/renesas/r8a77980.dtsi index b8c9a56562f2..da5453307d94 100644 --- a/arch/arm64/boot/dts/renesas/r8a77980.dtsi +++ b/arch/arm64/boot/dts/renesas/r8a77980.dtsi @@ -454,6 +454,7 @@ ipmmu_vip0: mmu@e7b00000 { compatible = "renesas,ipmmu-r8a77980"; reg = <0 0xe7b00000 0 0x1000>; + renesas,ipmmu-main = <&ipmmu_mm 4>; power-domains = <&sysc R8A77980_PD_ALWAYS_ON>; #iommu-cells = <1>; }; @@ -461,6 +462,7 @@ ipmmu_vip1: mmu@e7960000 { compatible = "renesas,ipmmu-r8a77980"; reg = <0 0xe7960000 0 0x1000>; + renesas,ipmmu-main = <&ipmmu_mm 11>; power-domains = <&sysc R8A77980_PD_ALWAYS_ON>; #iommu-cells = <1>; }; diff --git a/arch/arm64/boot/dts/renesas/ulcb.dtsi b/arch/arm64/boot/dts/renesas/ulcb.dtsi index 0ead552d7eae..600adc25eaef 100644 --- a/arch/arm64/boot/dts/renesas/ulcb.dtsi +++ b/arch/arm64/boot/dts/renesas/ulcb.dtsi @@ -430,6 +430,7 @@ bus-width = <8>; mmc-hs200-1_8v; non-removable; + full-pwr-cycle-in-suspend; status = "okay"; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3328-evb.dts b/arch/arm64/boot/dts/rockchip/rk3328-evb.dts index 8302d86d35c4..d89f3451ace5 100644 --- a/arch/arm64/boot/dts/rockchip/rk3328-evb.dts +++ b/arch/arm64/boot/dts/rockchip/rk3328-evb.dts @@ -86,13 +86,13 @@ assigned-clock-rate = <50000000>; assigned-clocks = <&cru SCLK_MAC2PHY>; assigned-clock-parents = <&cru SCLK_MAC2PHY_SRC>; - + status = "okay"; }; &i2c1 { status = "okay"; - rk805: rk805@18 { + rk805: pmic@18 { compatible = "rockchip,rk805"; reg = <0x18>; interrupt-parent = <&gpio2>; diff --git a/arch/arm64/boot/dts/rockchip/rk3328-roc-cc.dts b/arch/arm64/boot/dts/rockchip/rk3328-roc-cc.dts index 91061d9cf78b..5b1ece4a68d6 100644 --- a/arch/arm64/boot/dts/rockchip/rk3328-roc-cc.dts +++ b/arch/arm64/boot/dts/rockchip/rk3328-roc-cc.dts @@ -255,6 +255,7 @@ }; &usb20_otg { + dr_mode = "host"; status = "okay"; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts b/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts index e9147e35b739..03f2bc7d30d8 100644 --- a/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts +++ b/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts @@ -112,7 +112,7 @@ &i2c1 { status = "okay"; - rk805: rk805@18 { + rk805: pmic@18 { compatible = "rockchip,rk805"; reg = <0x18>; interrupt-parent = <&gpio2>; diff --git a/arch/arm64/boot/dts/rockchip/rk3328.dtsi b/arch/arm64/boot/dts/rockchip/rk3328.dtsi index 92186edefeb9..6be7c67584ba 100644 --- a/arch/arm64/boot/dts/rockchip/rk3328.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3328.dtsi @@ -1085,8 +1085,8 @@ uart0 { uart0_xfer: uart0-xfer { - rockchip,pins = <1 RK_PB1 1 &pcfg_pull_up>, - <1 RK_PB0 1 &pcfg_pull_none>; + rockchip,pins = <1 RK_PB1 1 &pcfg_pull_none>, + <1 RK_PB0 1 &pcfg_pull_up>; }; uart0_cts: uart0-cts { @@ -1104,8 +1104,8 @@ uart1 { uart1_xfer: uart1-xfer { - rockchip,pins = <3 RK_PA4 4 &pcfg_pull_up>, - <3 RK_PA6 4 &pcfg_pull_none>; + rockchip,pins = <3 RK_PA4 4 &pcfg_pull_none>, + <3 RK_PA6 4 &pcfg_pull_up>; }; uart1_cts: uart1-cts { @@ -1123,15 +1123,15 @@ uart2-0 { uart2m0_xfer: uart2m0-xfer { - rockchip,pins = <1 RK_PA0 2 &pcfg_pull_up>, - <1 RK_PA1 2 &pcfg_pull_none>; + rockchip,pins = <1 RK_PA0 2 &pcfg_pull_none>, + <1 RK_PA1 2 &pcfg_pull_up>; }; }; uart2-1 { uart2m1_xfer: uart2m1-xfer { - rockchip,pins = <2 RK_PA0 1 &pcfg_pull_up>, - <2 RK_PA1 1 &pcfg_pull_none>; + rockchip,pins = <2 RK_PA0 1 &pcfg_pull_none>, + <2 RK_PA1 1 &pcfg_pull_up>; }; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3368-lion.dtsi b/arch/arm64/boot/dts/rockchip/rk3368-lion.dtsi index 1315972412df..23098c13ad83 100644 --- a/arch/arm64/boot/dts/rockchip/rk3368-lion.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3368-lion.dtsi @@ -159,7 +159,7 @@ pinctrl-0 = <&rgmii_pins>; snps,reset-active-low; snps,reset-delays-us = <0 10000 50000>; - snps,reset-gpio = <&gpio3 RK_PB3 GPIO_ACTIVE_HIGH>; + snps,reset-gpio = <&gpio3 RK_PB3 GPIO_ACTIVE_LOW>; tx_delay = <0x10>; rx_delay = <0x10>; status = "okay"; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi index 0130b9f98c9d..b155f657292b 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi @@ -101,7 +101,7 @@ vcc5v0_host: vcc5v0-host-regulator { compatible = "regulator-fixed"; - gpio = <&gpio4 RK_PA3 GPIO_ACTIVE_HIGH>; + gpio = <&gpio4 RK_PA3 GPIO_ACTIVE_LOW>; enable-active-low; pinctrl-names = "default"; pinctrl-0 = <&vcc5v0_host_en>; @@ -156,7 +156,7 @@ phy-mode = "rgmii"; pinctrl-names = "default"; pinctrl-0 = <&rgmii_pins>; - snps,reset-gpio = <&gpio3 RK_PC0 GPIO_ACTIVE_HIGH>; + snps,reset-gpio = <&gpio3 RK_PC0 GPIO_ACTIVE_LOW>; snps,reset-active-low; snps,reset-delays-us = <0 10000 50000>; tx_delay = <0x10>; diff --git a/arch/arm64/boot/dts/rockchip/rk3399.dtsi b/arch/arm64/boot/dts/rockchip/rk3399.dtsi index cea44a7c7cf9..b1c1a88a1c20 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399.dtsi @@ -29,6 +29,9 @@ i2c6 = &i2c6; i2c7 = &i2c7; i2c8 = &i2c8; + mmc0 = &sdio0; + mmc1 = &sdmmc; + mmc2 = &sdhci; serial0 = &uart0; serial1 = &uart1; serial2 = &uart2; @@ -195,6 +198,7 @@ reg = <0x0 0xf8000000 0x0 0x2000000>, <0x0 0xfd000000 0x0 0x1000000>; reg-names = "axi-base", "apb-base"; + device_type = "pci"; #address-cells = <3>; #size-cells = <2>; #interrupt-cells = <1>; @@ -213,7 +217,6 @@ <0 0 0 2 &pcie0_intc 1>, <0 0 0 3 &pcie0_intc 2>, <0 0 0 4 &pcie0_intc 3>; - linux,pci-domain = <0>; max-link-speed = <1>; msi-map = <0x0 &its 0x0 0x1000>; phys = <&pcie_phy 0>, <&pcie_phy 1>, @@ -376,7 +379,7 @@ reset-names = "usb3-otg"; status = "disabled"; - usbdrd_dwc3_0: dwc3 { + usbdrd_dwc3_0: usb@fe800000 { compatible = "snps,dwc3"; reg = <0x0 0xfe800000 0x0 0x100000>; interrupts = <GIC_SPI 105 IRQ_TYPE_LEVEL_HIGH 0>; @@ -409,7 +412,7 @@ reset-names = "usb3-otg"; status = "disabled"; - usbdrd_dwc3_1: dwc3 { + usbdrd_dwc3_1: usb@fe900000 { compatible = "snps,dwc3"; reg = <0x0 0xfe900000 0x0 0x100000>; interrupts = <GIC_SPI 110 IRQ_TYPE_LEVEL_HIGH 0>; @@ -1817,10 +1820,10 @@ gpu: gpu@ff9a0000 { compatible = "rockchip,rk3399-mali", "arm,mali-t860"; reg = <0x0 0xff9a0000 0x0 0x10000>; - interrupts = <GIC_SPI 19 IRQ_TYPE_LEVEL_HIGH 0>, - <GIC_SPI 20 IRQ_TYPE_LEVEL_HIGH 0>, - <GIC_SPI 21 IRQ_TYPE_LEVEL_HIGH 0>; - interrupt-names = "gpu", "job", "mmu"; + interrupts = <GIC_SPI 20 IRQ_TYPE_LEVEL_HIGH 0>, + <GIC_SPI 21 IRQ_TYPE_LEVEL_HIGH 0>, + <GIC_SPI 19 IRQ_TYPE_LEVEL_HIGH 0>; + interrupt-names = "job", "mmu", "gpu"; clocks = <&cru ACLK_GPU>; power-domains = <&power RK3399_PD_GPU>; status = "disabled"; diff --git a/arch/arm64/boot/dts/socionext/uniphier-ld20.dtsi b/arch/arm64/boot/dts/socionext/uniphier-ld20.dtsi index caf112629caa..62429c412b33 100644 --- a/arch/arm64/boot/dts/socionext/uniphier-ld20.dtsi +++ b/arch/arm64/boot/dts/socionext/uniphier-ld20.dtsi @@ -610,7 +610,7 @@ clocks = <&sys_clk 6>; reset-names = "ether"; resets = <&sys_rst 6>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; local-mac-address = [00 00 00 00 00 00]; socionext,syscon-phy-mode = <&soc_glue 0>; diff --git a/arch/arm64/boot/dts/socionext/uniphier-pxs3.dtsi b/arch/arm64/boot/dts/socionext/uniphier-pxs3.dtsi index 2a4cf427f5d3..8fe9a57b9562 100644 --- a/arch/arm64/boot/dts/socionext/uniphier-pxs3.dtsi +++ b/arch/arm64/boot/dts/socionext/uniphier-pxs3.dtsi @@ -416,7 +416,7 @@ clocks = <&sys_clk 6>; reset-names = "ether"; resets = <&sys_rst 6>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; local-mac-address = [00 00 00 00 00 00]; socionext,syscon-phy-mode = <&soc_glue 0>; @@ -437,7 +437,7 @@ clocks = <&sys_clk 7>; reset-names = "ether"; resets = <&sys_rst 7>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; local-mac-address = [00 00 00 00 00 00]; socionext,syscon-phy-mode = <&soc_glue 1>; diff --git a/arch/arm64/boot/dts/xilinx/zynqmp.dtsi b/arch/arm64/boot/dts/xilinx/zynqmp.dtsi index a516c0e01429..8a885ae647b7 100644 --- a/arch/arm64/boot/dts/xilinx/zynqmp.dtsi +++ b/arch/arm64/boot/dts/xilinx/zynqmp.dtsi @@ -411,7 +411,7 @@ }; i2c0: i2c@ff020000 { - compatible = "cdns,i2c-r1p14", "cdns,i2c-r1p10"; + compatible = "cdns,i2c-r1p14"; status = "disabled"; interrupt-parent = <&gic>; interrupts = <0 17 4>; @@ -421,7 +421,7 @@ }; i2c1: i2c@ff030000 { - compatible = "cdns,i2c-r1p14", "cdns,i2c-r1p10"; + compatible = "cdns,i2c-r1p14"; status = "disabled"; interrupt-parent = <&gic>; interrupts = <0 18 4>; diff --git a/arch/arm64/crypto/aes-modes.S b/arch/arm64/crypto/aes-modes.S index 483a7130cf0e..496c243de4ac 100644 --- a/arch/arm64/crypto/aes-modes.S +++ b/arch/arm64/crypto/aes-modes.S @@ -232,17 +232,19 @@ AES_ENTRY(aes_ctr_encrypt) bmi .Lctr1x cmn w6, #4 /* 32 bit overflow? */ bcs .Lctr1x - ldr q8, =0x30000000200000001 /* addends 1,2,3[,0] */ - dup v7.4s, w6 + add w7, w6, #1 mov v0.16b, v4.16b - add v7.4s, v7.4s, v8.4s + add w8, w6, #2 mov v1.16b, v4.16b - rev32 v8.16b, v7.16b + add w9, w6, #3 mov v2.16b, v4.16b + rev w7, w7 mov v3.16b, v4.16b - mov v1.s[3], v8.s[0] - mov v2.s[3], v8.s[1] - mov v3.s[3], v8.s[2] + rev w8, w8 + mov v1.s[3], w7 + rev w9, w9 + mov v2.s[3], w8 + mov v3.s[3], w9 ld1 {v5.16b-v7.16b}, [x20], #48 /* get 3 input blocks */ bl aes_encrypt_block4x eor v0.16b, v5.16b, v0.16b diff --git a/arch/arm64/crypto/sha1-ce-glue.c b/arch/arm64/crypto/sha1-ce-glue.c index d8c521c757e8..3f51743c01d8 100644 --- a/arch/arm64/crypto/sha1-ce-glue.c +++ b/arch/arm64/crypto/sha1-ce-glue.c @@ -21,6 +21,7 @@ MODULE_DESCRIPTION("SHA1 secure hash using ARMv8 Crypto Extensions"); MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>"); MODULE_LICENSE("GPL v2"); +MODULE_ALIAS_CRYPTO("sha1"); struct sha1_ce_state { struct sha1_state sst; diff --git a/arch/arm64/crypto/sha2-ce-glue.c b/arch/arm64/crypto/sha2-ce-glue.c index c47d1a28ff6b..4022c51a377b 100644 --- a/arch/arm64/crypto/sha2-ce-glue.c +++ b/arch/arm64/crypto/sha2-ce-glue.c @@ -21,6 +21,8 @@ MODULE_DESCRIPTION("SHA-224/SHA-256 secure hash using ARMv8 Crypto Extensions"); MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>"); MODULE_LICENSE("GPL v2"); +MODULE_ALIAS_CRYPTO("sha224"); +MODULE_ALIAS_CRYPTO("sha256"); struct sha256_ce_state { struct sha256_state sst; diff --git a/arch/arm64/crypto/sha3-ce-glue.c b/arch/arm64/crypto/sha3-ce-glue.c index a336feac0f59..df20ab645487 100644 --- a/arch/arm64/crypto/sha3-ce-glue.c +++ b/arch/arm64/crypto/sha3-ce-glue.c @@ -22,6 +22,10 @@ MODULE_DESCRIPTION("SHA3 secure hash using ARMv8 Crypto Extensions"); MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>"); MODULE_LICENSE("GPL v2"); +MODULE_ALIAS_CRYPTO("sha3-224"); +MODULE_ALIAS_CRYPTO("sha3-256"); +MODULE_ALIAS_CRYPTO("sha3-384"); +MODULE_ALIAS_CRYPTO("sha3-512"); asmlinkage void sha3_ce_transform(u64 *st, const u8 *data, int blocks, int md_len); diff --git a/arch/arm64/crypto/sha512-ce-glue.c b/arch/arm64/crypto/sha512-ce-glue.c index f2c5f28c622a..2871e68ae3df 100644 --- a/arch/arm64/crypto/sha512-ce-glue.c +++ b/arch/arm64/crypto/sha512-ce-glue.c @@ -22,6 +22,8 @@ MODULE_DESCRIPTION("SHA-384/SHA-512 secure hash using ARMv8 Crypto Extensions"); MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>"); MODULE_LICENSE("GPL v2"); +MODULE_ALIAS_CRYPTO("sha384"); +MODULE_ALIAS_CRYPTO("sha512"); asmlinkage void sha512_ce_transform(struct sha512_state *sst, u8 const *src, int blocks); diff --git a/arch/arm64/include/asm/alternative.h b/arch/arm64/include/asm/alternative.h index 1a7ba3de7079..4fbbcdda70d7 100644 --- a/arch/arm64/include/asm/alternative.h +++ b/arch/arm64/include/asm/alternative.h @@ -73,13 +73,13 @@ static inline void apply_alternatives_module(void *start, size_t length) { } ".pushsection .altinstructions,\"a\"\n" \ ALTINSTR_ENTRY(feature) \ ".popsection\n" \ - ".pushsection .altinstr_replacement, \"a\"\n" \ + ".subsection 1\n" \ "663:\n\t" \ newinstr "\n" \ "664:\n\t" \ - ".popsection\n\t" \ ".org . - (664b-663b) + (662b-661b)\n\t" \ - ".org . - (662b-661b) + (664b-663b)\n" \ + ".org . - (662b-661b) + (664b-663b)\n\t" \ + ".previous\n" \ ".endif\n" #define __ALTERNATIVE_CFG_CB(oldinstr, feature, cfg_enabled, cb) \ @@ -117,11 +117,11 @@ static inline void apply_alternatives_module(void *start, size_t length) { } 662: .pushsection .altinstructions, "a" altinstruction_entry 661b, 663f, \cap, 662b-661b, 664f-663f .popsection - .pushsection .altinstr_replacement, "ax" + .subsection 1 663: \insn2 -664: .popsection - .org . - (664b-663b) + (662b-661b) +664: .org . - (664b-663b) + (662b-661b) .org . - (662b-661b) + (664b-663b) + .previous .endif .endm @@ -160,7 +160,7 @@ static inline void apply_alternatives_module(void *start, size_t length) { } .pushsection .altinstructions, "a" altinstruction_entry 663f, 661f, \cap, 664f-663f, 662f-661f .popsection - .pushsection .altinstr_replacement, "ax" + .subsection 1 .align 2 /* So GAS knows label 661 is suitably aligned */ 661: .endm @@ -179,9 +179,9 @@ static inline void apply_alternatives_module(void *start, size_t length) { } .macro alternative_else 662: .if .Lasm_alt_mode==0 - .pushsection .altinstr_replacement, "ax" + .subsection 1 .else - .popsection + .previous .endif 663: .endm @@ -191,11 +191,11 @@ static inline void apply_alternatives_module(void *start, size_t length) { } */ .macro alternative_endif 664: - .if .Lasm_alt_mode==0 - .popsection - .endif .org . - (664b-663b) + (662b-661b) .org . - (662b-661b) + (664b-663b) + .if .Lasm_alt_mode==0 + .previous + .endif .endm /* diff --git a/arch/arm64/include/asm/atomic_ll_sc.h b/arch/arm64/include/asm/atomic_ll_sc.h index f5a2d09afb38..1cc42441bc67 100644 --- a/arch/arm64/include/asm/atomic_ll_sc.h +++ b/arch/arm64/include/asm/atomic_ll_sc.h @@ -37,7 +37,7 @@ * (the optimize attribute silently ignores these options). */ -#define ATOMIC_OP(op, asm_op) \ +#define ATOMIC_OP(op, asm_op, constraint) \ __LL_SC_INLINE void \ __LL_SC_PREFIX(atomic_##op(int i, atomic_t *v)) \ { \ @@ -51,11 +51,11 @@ __LL_SC_PREFIX(atomic_##op(int i, atomic_t *v)) \ " stxr %w1, %w0, %2\n" \ " cbnz %w1, 1b" \ : "=&r" (result), "=&r" (tmp), "+Q" (v->counter) \ - : "Ir" (i)); \ + : #constraint "r" (i)); \ } \ __LL_SC_EXPORT(atomic_##op); -#define ATOMIC_OP_RETURN(name, mb, acq, rel, cl, op, asm_op) \ +#define ATOMIC_OP_RETURN(name, mb, acq, rel, cl, op, asm_op, constraint)\ __LL_SC_INLINE int \ __LL_SC_PREFIX(atomic_##op##_return##name(int i, atomic_t *v)) \ { \ @@ -70,14 +70,14 @@ __LL_SC_PREFIX(atomic_##op##_return##name(int i, atomic_t *v)) \ " cbnz %w1, 1b\n" \ " " #mb \ : "=&r" (result), "=&r" (tmp), "+Q" (v->counter) \ - : "Ir" (i) \ + : #constraint "r" (i) \ : cl); \ \ return result; \ } \ __LL_SC_EXPORT(atomic_##op##_return##name); -#define ATOMIC_FETCH_OP(name, mb, acq, rel, cl, op, asm_op) \ +#define ATOMIC_FETCH_OP(name, mb, acq, rel, cl, op, asm_op, constraint) \ __LL_SC_INLINE int \ __LL_SC_PREFIX(atomic_fetch_##op##name(int i, atomic_t *v)) \ { \ @@ -92,7 +92,7 @@ __LL_SC_PREFIX(atomic_fetch_##op##name(int i, atomic_t *v)) \ " cbnz %w2, 1b\n" \ " " #mb \ : "=&r" (result), "=&r" (val), "=&r" (tmp), "+Q" (v->counter) \ - : "Ir" (i) \ + : #constraint "r" (i) \ : cl); \ \ return result; \ @@ -110,8 +110,8 @@ __LL_SC_EXPORT(atomic_fetch_##op##name); ATOMIC_FETCH_OP (_acquire, , a, , "memory", __VA_ARGS__)\ ATOMIC_FETCH_OP (_release, , , l, "memory", __VA_ARGS__) -ATOMIC_OPS(add, add) -ATOMIC_OPS(sub, sub) +ATOMIC_OPS(add, add, I) +ATOMIC_OPS(sub, sub, J) #undef ATOMIC_OPS #define ATOMIC_OPS(...) \ @@ -121,17 +121,17 @@ ATOMIC_OPS(sub, sub) ATOMIC_FETCH_OP (_acquire, , a, , "memory", __VA_ARGS__)\ ATOMIC_FETCH_OP (_release, , , l, "memory", __VA_ARGS__) -ATOMIC_OPS(and, and) -ATOMIC_OPS(andnot, bic) -ATOMIC_OPS(or, orr) -ATOMIC_OPS(xor, eor) +ATOMIC_OPS(and, and, ) +ATOMIC_OPS(andnot, bic, ) +ATOMIC_OPS(or, orr, ) +ATOMIC_OPS(xor, eor, ) #undef ATOMIC_OPS #undef ATOMIC_FETCH_OP #undef ATOMIC_OP_RETURN #undef ATOMIC_OP -#define ATOMIC64_OP(op, asm_op) \ +#define ATOMIC64_OP(op, asm_op, constraint) \ __LL_SC_INLINE void \ __LL_SC_PREFIX(atomic64_##op(long i, atomic64_t *v)) \ { \ @@ -145,11 +145,11 @@ __LL_SC_PREFIX(atomic64_##op(long i, atomic64_t *v)) \ " stxr %w1, %0, %2\n" \ " cbnz %w1, 1b" \ : "=&r" (result), "=&r" (tmp), "+Q" (v->counter) \ - : "Ir" (i)); \ + : #constraint "r" (i)); \ } \ __LL_SC_EXPORT(atomic64_##op); -#define ATOMIC64_OP_RETURN(name, mb, acq, rel, cl, op, asm_op) \ +#define ATOMIC64_OP_RETURN(name, mb, acq, rel, cl, op, asm_op, constraint)\ __LL_SC_INLINE long \ __LL_SC_PREFIX(atomic64_##op##_return##name(long i, atomic64_t *v)) \ { \ @@ -164,14 +164,14 @@ __LL_SC_PREFIX(atomic64_##op##_return##name(long i, atomic64_t *v)) \ " cbnz %w1, 1b\n" \ " " #mb \ : "=&r" (result), "=&r" (tmp), "+Q" (v->counter) \ - : "Ir" (i) \ + : #constraint "r" (i) \ : cl); \ \ return result; \ } \ __LL_SC_EXPORT(atomic64_##op##_return##name); -#define ATOMIC64_FETCH_OP(name, mb, acq, rel, cl, op, asm_op) \ +#define ATOMIC64_FETCH_OP(name, mb, acq, rel, cl, op, asm_op, constraint)\ __LL_SC_INLINE long \ __LL_SC_PREFIX(atomic64_fetch_##op##name(long i, atomic64_t *v)) \ { \ @@ -186,7 +186,7 @@ __LL_SC_PREFIX(atomic64_fetch_##op##name(long i, atomic64_t *v)) \ " cbnz %w2, 1b\n" \ " " #mb \ : "=&r" (result), "=&r" (val), "=&r" (tmp), "+Q" (v->counter) \ - : "Ir" (i) \ + : #constraint "r" (i) \ : cl); \ \ return result; \ @@ -204,8 +204,8 @@ __LL_SC_EXPORT(atomic64_fetch_##op##name); ATOMIC64_FETCH_OP (_acquire,, a, , "memory", __VA_ARGS__) \ ATOMIC64_FETCH_OP (_release,, , l, "memory", __VA_ARGS__) -ATOMIC64_OPS(add, add) -ATOMIC64_OPS(sub, sub) +ATOMIC64_OPS(add, add, I) +ATOMIC64_OPS(sub, sub, J) #undef ATOMIC64_OPS #define ATOMIC64_OPS(...) \ @@ -215,10 +215,10 @@ ATOMIC64_OPS(sub, sub) ATOMIC64_FETCH_OP (_acquire,, a, , "memory", __VA_ARGS__) \ ATOMIC64_FETCH_OP (_release,, , l, "memory", __VA_ARGS__) -ATOMIC64_OPS(and, and) -ATOMIC64_OPS(andnot, bic) -ATOMIC64_OPS(or, orr) -ATOMIC64_OPS(xor, eor) +ATOMIC64_OPS(and, and, L) +ATOMIC64_OPS(andnot, bic, ) +ATOMIC64_OPS(or, orr, L) +ATOMIC64_OPS(xor, eor, L) #undef ATOMIC64_OPS #undef ATOMIC64_FETCH_OP @@ -248,48 +248,54 @@ __LL_SC_PREFIX(atomic64_dec_if_positive(atomic64_t *v)) } __LL_SC_EXPORT(atomic64_dec_if_positive); -#define __CMPXCHG_CASE(w, sz, name, mb, acq, rel, cl) \ -__LL_SC_INLINE unsigned long \ -__LL_SC_PREFIX(__cmpxchg_case_##name(volatile void *ptr, \ - unsigned long old, \ - unsigned long new)) \ +#define __CMPXCHG_CASE(w, sfx, name, sz, mb, acq, rel, cl, constraint) \ +__LL_SC_INLINE u##sz \ +__LL_SC_PREFIX(__cmpxchg_case_##name##sz(volatile void *ptr, \ + unsigned long old, \ + u##sz new)) \ { \ - unsigned long tmp, oldval; \ + unsigned long tmp; \ + u##sz oldval; \ \ asm volatile( \ " prfm pstl1strm, %[v]\n" \ - "1: ld" #acq "xr" #sz "\t%" #w "[oldval], %[v]\n" \ + "1: ld" #acq "xr" #sfx "\t%" #w "[oldval], %[v]\n" \ " eor %" #w "[tmp], %" #w "[oldval], %" #w "[old]\n" \ " cbnz %" #w "[tmp], 2f\n" \ - " st" #rel "xr" #sz "\t%w[tmp], %" #w "[new], %[v]\n" \ + " st" #rel "xr" #sfx "\t%w[tmp], %" #w "[new], %[v]\n" \ " cbnz %w[tmp], 1b\n" \ " " #mb "\n" \ "2:" \ : [tmp] "=&r" (tmp), [oldval] "=&r" (oldval), \ - [v] "+Q" (*(unsigned long *)ptr) \ - : [old] "Lr" (old), [new] "r" (new) \ + [v] "+Q" (*(u##sz *)ptr) \ + : [old] #constraint "r" (old), [new] "r" (new) \ : cl); \ \ return oldval; \ } \ -__LL_SC_EXPORT(__cmpxchg_case_##name); +__LL_SC_EXPORT(__cmpxchg_case_##name##sz); -__CMPXCHG_CASE(w, b, 1, , , , ) -__CMPXCHG_CASE(w, h, 2, , , , ) -__CMPXCHG_CASE(w, , 4, , , , ) -__CMPXCHG_CASE( , , 8, , , , ) -__CMPXCHG_CASE(w, b, acq_1, , a, , "memory") -__CMPXCHG_CASE(w, h, acq_2, , a, , "memory") -__CMPXCHG_CASE(w, , acq_4, , a, , "memory") -__CMPXCHG_CASE( , , acq_8, , a, , "memory") -__CMPXCHG_CASE(w, b, rel_1, , , l, "memory") -__CMPXCHG_CASE(w, h, rel_2, , , l, "memory") -__CMPXCHG_CASE(w, , rel_4, , , l, "memory") -__CMPXCHG_CASE( , , rel_8, , , l, "memory") -__CMPXCHG_CASE(w, b, mb_1, dmb ish, , l, "memory") -__CMPXCHG_CASE(w, h, mb_2, dmb ish, , l, "memory") -__CMPXCHG_CASE(w, , mb_4, dmb ish, , l, "memory") -__CMPXCHG_CASE( , , mb_8, dmb ish, , l, "memory") +/* + * Earlier versions of GCC (no later than 8.1.0) appear to incorrectly + * handle the 'K' constraint for the value 4294967295 - thus we use no + * constraint for 32 bit operations. + */ +__CMPXCHG_CASE(w, b, , 8, , , , , ) +__CMPXCHG_CASE(w, h, , 16, , , , , ) +__CMPXCHG_CASE(w, , , 32, , , , , ) +__CMPXCHG_CASE( , , , 64, , , , , L) +__CMPXCHG_CASE(w, b, acq_, 8, , a, , "memory", ) +__CMPXCHG_CASE(w, h, acq_, 16, , a, , "memory", ) +__CMPXCHG_CASE(w, , acq_, 32, , a, , "memory", ) +__CMPXCHG_CASE( , , acq_, 64, , a, , "memory", L) +__CMPXCHG_CASE(w, b, rel_, 8, , , l, "memory", ) +__CMPXCHG_CASE(w, h, rel_, 16, , , l, "memory", ) +__CMPXCHG_CASE(w, , rel_, 32, , , l, "memory", ) +__CMPXCHG_CASE( , , rel_, 64, , , l, "memory", L) +__CMPXCHG_CASE(w, b, mb_, 8, dmb ish, , l, "memory", ) +__CMPXCHG_CASE(w, h, mb_, 16, dmb ish, , l, "memory", ) +__CMPXCHG_CASE(w, , mb_, 32, dmb ish, , l, "memory", ) +__CMPXCHG_CASE( , , mb_, 64, dmb ish, , l, "memory", L) #undef __CMPXCHG_CASE diff --git a/arch/arm64/include/asm/atomic_lse.h b/arch/arm64/include/asm/atomic_lse.h index f9b0b09153e0..80cadc789f1a 100644 --- a/arch/arm64/include/asm/atomic_lse.h +++ b/arch/arm64/include/asm/atomic_lse.h @@ -32,7 +32,9 @@ static inline void atomic_##op(int i, atomic_t *v) \ register int w0 asm ("w0") = i; \ register atomic_t *x1 asm ("x1") = v; \ \ - asm volatile(ARM64_LSE_ATOMIC_INSN(__LL_SC_ATOMIC(op), \ + asm volatile( \ + __LSE_PREAMBLE \ + ARM64_LSE_ATOMIC_INSN(__LL_SC_ATOMIC(op), \ " " #asm_op " %w[i], %[v]\n") \ : [i] "+r" (w0), [v] "+Q" (v->counter) \ : "r" (x1) \ @@ -52,7 +54,9 @@ static inline int atomic_fetch_##op##name(int i, atomic_t *v) \ register int w0 asm ("w0") = i; \ register atomic_t *x1 asm ("x1") = v; \ \ - asm volatile(ARM64_LSE_ATOMIC_INSN( \ + asm volatile( \ + __LSE_PREAMBLE \ + ARM64_LSE_ATOMIC_INSN( \ /* LL/SC */ \ __LL_SC_ATOMIC(fetch_##op##name), \ /* LSE atomics */ \ @@ -84,7 +88,9 @@ static inline int atomic_add_return##name(int i, atomic_t *v) \ register int w0 asm ("w0") = i; \ register atomic_t *x1 asm ("x1") = v; \ \ - asm volatile(ARM64_LSE_ATOMIC_INSN( \ + asm volatile( \ + __LSE_PREAMBLE \ + ARM64_LSE_ATOMIC_INSN( \ /* LL/SC */ \ __LL_SC_ATOMIC(add_return##name) \ __nops(1), \ @@ -110,7 +116,9 @@ static inline void atomic_and(int i, atomic_t *v) register int w0 asm ("w0") = i; register atomic_t *x1 asm ("x1") = v; - asm volatile(ARM64_LSE_ATOMIC_INSN( + asm volatile( + __LSE_PREAMBLE + ARM64_LSE_ATOMIC_INSN( /* LL/SC */ __LL_SC_ATOMIC(and) __nops(1), @@ -128,7 +136,9 @@ static inline int atomic_fetch_and##name(int i, atomic_t *v) \ register int w0 asm ("w0") = i; \ register atomic_t *x1 asm ("x1") = v; \ \ - asm volatile(ARM64_LSE_ATOMIC_INSN( \ + asm volatile( \ + __LSE_PREAMBLE \ + ARM64_LSE_ATOMIC_INSN( \ /* LL/SC */ \ __LL_SC_ATOMIC(fetch_and##name) \ __nops(1), \ @@ -154,7 +164,9 @@ static inline void atomic_sub(int i, atomic_t *v) register int w0 asm ("w0") = i; register atomic_t *x1 asm ("x1") = v; - asm volatile(ARM64_LSE_ATOMIC_INSN( + asm volatile( + __LSE_PREAMBLE + ARM64_LSE_ATOMIC_INSN( /* LL/SC */ __LL_SC_ATOMIC(sub) __nops(1), @@ -172,7 +184,9 @@ static inline int atomic_sub_return##name(int i, atomic_t *v) \ register int w0 asm ("w0") = i; \ register atomic_t *x1 asm ("x1") = v; \ \ - asm volatile(ARM64_LSE_ATOMIC_INSN( \ + asm volatile( \ + __LSE_PREAMBLE \ + ARM64_LSE_ATOMIC_INSN( \ /* LL/SC */ \ __LL_SC_ATOMIC(sub_return##name) \ __nops(2), \ @@ -200,7 +214,9 @@ static inline int atomic_fetch_sub##name(int i, atomic_t *v) \ register int w0 asm ("w0") = i; \ register atomic_t *x1 asm ("x1") = v; \ \ - asm volatile(ARM64_LSE_ATOMIC_INSN( \ + asm volatile( \ + __LSE_PREAMBLE \ + ARM64_LSE_ATOMIC_INSN( \ /* LL/SC */ \ __LL_SC_ATOMIC(fetch_sub##name) \ __nops(1), \ @@ -229,7 +245,9 @@ static inline void atomic64_##op(long i, atomic64_t *v) \ register long x0 asm ("x0") = i; \ register atomic64_t *x1 asm ("x1") = v; \ \ - asm volatile(ARM64_LSE_ATOMIC_INSN(__LL_SC_ATOMIC64(op), \ + asm volatile( \ + __LSE_PREAMBLE \ + ARM64_LSE_ATOMIC_INSN(__LL_SC_ATOMIC64(op), \ " " #asm_op " %[i], %[v]\n") \ : [i] "+r" (x0), [v] "+Q" (v->counter) \ : "r" (x1) \ @@ -249,7 +267,9 @@ static inline long atomic64_fetch_##op##name(long i, atomic64_t *v) \ register long x0 asm ("x0") = i; \ register atomic64_t *x1 asm ("x1") = v; \ \ - asm volatile(ARM64_LSE_ATOMIC_INSN( \ + asm volatile( \ + __LSE_PREAMBLE \ + ARM64_LSE_ATOMIC_INSN( \ /* LL/SC */ \ __LL_SC_ATOMIC64(fetch_##op##name), \ /* LSE atomics */ \ @@ -281,7 +301,9 @@ static inline long atomic64_add_return##name(long i, atomic64_t *v) \ register long x0 asm ("x0") = i; \ register atomic64_t *x1 asm ("x1") = v; \ \ - asm volatile(ARM64_LSE_ATOMIC_INSN( \ + asm volatile( \ + __LSE_PREAMBLE \ + ARM64_LSE_ATOMIC_INSN( \ /* LL/SC */ \ __LL_SC_ATOMIC64(add_return##name) \ __nops(1), \ @@ -307,7 +329,9 @@ static inline void atomic64_and(long i, atomic64_t *v) register long x0 asm ("x0") = i; register atomic64_t *x1 asm ("x1") = v; - asm volatile(ARM64_LSE_ATOMIC_INSN( + asm volatile( + __LSE_PREAMBLE + ARM64_LSE_ATOMIC_INSN( /* LL/SC */ __LL_SC_ATOMIC64(and) __nops(1), @@ -325,7 +349,9 @@ static inline long atomic64_fetch_and##name(long i, atomic64_t *v) \ register long x0 asm ("x0") = i; \ register atomic64_t *x1 asm ("x1") = v; \ \ - asm volatile(ARM64_LSE_ATOMIC_INSN( \ + asm volatile( \ + __LSE_PREAMBLE \ + ARM64_LSE_ATOMIC_INSN( \ /* LL/SC */ \ __LL_SC_ATOMIC64(fetch_and##name) \ __nops(1), \ @@ -351,7 +377,9 @@ static inline void atomic64_sub(long i, atomic64_t *v) register long x0 asm ("x0") = i; register atomic64_t *x1 asm ("x1") = v; - asm volatile(ARM64_LSE_ATOMIC_INSN( + asm volatile( + __LSE_PREAMBLE + ARM64_LSE_ATOMIC_INSN( /* LL/SC */ __LL_SC_ATOMIC64(sub) __nops(1), @@ -369,7 +397,9 @@ static inline long atomic64_sub_return##name(long i, atomic64_t *v) \ register long x0 asm ("x0") = i; \ register atomic64_t *x1 asm ("x1") = v; \ \ - asm volatile(ARM64_LSE_ATOMIC_INSN( \ + asm volatile( \ + __LSE_PREAMBLE \ + ARM64_LSE_ATOMIC_INSN( \ /* LL/SC */ \ __LL_SC_ATOMIC64(sub_return##name) \ __nops(2), \ @@ -397,7 +427,9 @@ static inline long atomic64_fetch_sub##name(long i, atomic64_t *v) \ register long x0 asm ("x0") = i; \ register atomic64_t *x1 asm ("x1") = v; \ \ - asm volatile(ARM64_LSE_ATOMIC_INSN( \ + asm volatile( \ + __LSE_PREAMBLE \ + ARM64_LSE_ATOMIC_INSN( \ /* LL/SC */ \ __LL_SC_ATOMIC64(fetch_sub##name) \ __nops(1), \ @@ -422,7 +454,9 @@ static inline long atomic64_dec_if_positive(atomic64_t *v) { register long x0 asm ("x0") = (long)v; - asm volatile(ARM64_LSE_ATOMIC_INSN( + asm volatile( + __LSE_PREAMBLE + ARM64_LSE_ATOMIC_INSN( /* LL/SC */ __LL_SC_ATOMIC64(dec_if_positive) __nops(6), @@ -446,22 +480,24 @@ static inline long atomic64_dec_if_positive(atomic64_t *v) #define __LL_SC_CMPXCHG(op) __LL_SC_CALL(__cmpxchg_case_##op) -#define __CMPXCHG_CASE(w, sz, name, mb, cl...) \ -static inline unsigned long __cmpxchg_case_##name(volatile void *ptr, \ - unsigned long old, \ - unsigned long new) \ +#define __CMPXCHG_CASE(w, sfx, name, sz, mb, cl...) \ +static inline u##sz __cmpxchg_case_##name##sz(volatile void *ptr, \ + unsigned long old, \ + u##sz new) \ { \ register unsigned long x0 asm ("x0") = (unsigned long)ptr; \ register unsigned long x1 asm ("x1") = old; \ - register unsigned long x2 asm ("x2") = new; \ + register u##sz x2 asm ("x2") = new; \ \ - asm volatile(ARM64_LSE_ATOMIC_INSN( \ + asm volatile( \ + __LSE_PREAMBLE \ + ARM64_LSE_ATOMIC_INSN( \ /* LL/SC */ \ - __LL_SC_CMPXCHG(name) \ + __LL_SC_CMPXCHG(name##sz) \ __nops(2), \ /* LSE atomics */ \ " mov " #w "30, %" #w "[old]\n" \ - " cas" #mb #sz "\t" #w "30, %" #w "[new], %[v]\n" \ + " cas" #mb #sfx "\t" #w "30, %" #w "[new], %[v]\n" \ " mov %" #w "[ret], " #w "30") \ : [ret] "+r" (x0), [v] "+Q" (*(unsigned long *)ptr) \ : [old] "r" (x1), [new] "r" (x2) \ @@ -470,22 +506,22 @@ static inline unsigned long __cmpxchg_case_##name(volatile void *ptr, \ return x0; \ } -__CMPXCHG_CASE(w, b, 1, ) -__CMPXCHG_CASE(w, h, 2, ) -__CMPXCHG_CASE(w, , 4, ) -__CMPXCHG_CASE(x, , 8, ) -__CMPXCHG_CASE(w, b, acq_1, a, "memory") -__CMPXCHG_CASE(w, h, acq_2, a, "memory") -__CMPXCHG_CASE(w, , acq_4, a, "memory") -__CMPXCHG_CASE(x, , acq_8, a, "memory") -__CMPXCHG_CASE(w, b, rel_1, l, "memory") -__CMPXCHG_CASE(w, h, rel_2, l, "memory") -__CMPXCHG_CASE(w, , rel_4, l, "memory") -__CMPXCHG_CASE(x, , rel_8, l, "memory") -__CMPXCHG_CASE(w, b, mb_1, al, "memory") -__CMPXCHG_CASE(w, h, mb_2, al, "memory") -__CMPXCHG_CASE(w, , mb_4, al, "memory") -__CMPXCHG_CASE(x, , mb_8, al, "memory") +__CMPXCHG_CASE(w, b, , 8, ) +__CMPXCHG_CASE(w, h, , 16, ) +__CMPXCHG_CASE(w, , , 32, ) +__CMPXCHG_CASE(x, , , 64, ) +__CMPXCHG_CASE(w, b, acq_, 8, a, "memory") +__CMPXCHG_CASE(w, h, acq_, 16, a, "memory") +__CMPXCHG_CASE(w, , acq_, 32, a, "memory") +__CMPXCHG_CASE(x, , acq_, 64, a, "memory") +__CMPXCHG_CASE(w, b, rel_, 8, l, "memory") +__CMPXCHG_CASE(w, h, rel_, 16, l, "memory") +__CMPXCHG_CASE(w, , rel_, 32, l, "memory") +__CMPXCHG_CASE(x, , rel_, 64, l, "memory") +__CMPXCHG_CASE(w, b, mb_, 8, al, "memory") +__CMPXCHG_CASE(w, h, mb_, 16, al, "memory") +__CMPXCHG_CASE(w, , mb_, 32, al, "memory") +__CMPXCHG_CASE(x, , mb_, 64, al, "memory") #undef __LL_SC_CMPXCHG #undef __CMPXCHG_CASE @@ -507,7 +543,9 @@ static inline long __cmpxchg_double##name(unsigned long old1, \ register unsigned long x3 asm ("x3") = new2; \ register unsigned long x4 asm ("x4") = (unsigned long)ptr; \ \ - asm volatile(ARM64_LSE_ATOMIC_INSN( \ + asm volatile( \ + __LSE_PREAMBLE \ + ARM64_LSE_ATOMIC_INSN( \ /* LL/SC */ \ __LL_SC_CMPXCHG_DBL(name) \ __nops(3), \ diff --git a/arch/arm64/include/asm/cache.h b/arch/arm64/include/asm/cache.h index 5ee5bca8c24b..baa684782358 100644 --- a/arch/arm64/include/asm/cache.h +++ b/arch/arm64/include/asm/cache.h @@ -22,6 +22,7 @@ #define CTR_L1IP_MASK 3 #define CTR_DMINLINE_SHIFT 16 #define CTR_IMINLINE_SHIFT 0 +#define CTR_IMINLINE_MASK 0xf #define CTR_ERG_SHIFT 20 #define CTR_CWG_SHIFT 24 #define CTR_CWG_MASK 15 @@ -29,7 +30,7 @@ #define CTR_DIC_SHIFT 29 #define CTR_CACHE_MINLINE_MASK \ - (0xf << CTR_DMINLINE_SHIFT | 0xf << CTR_IMINLINE_SHIFT) + (0xf << CTR_DMINLINE_SHIFT | CTR_IMINLINE_MASK << CTR_IMINLINE_SHIFT) #define CTR_L1IP(ctr) (((ctr) >> CTR_L1IP_SHIFT) & CTR_L1IP_MASK) diff --git a/arch/arm64/include/asm/cacheflush.h b/arch/arm64/include/asm/cacheflush.h index 19844211a4e6..a449a1c602d3 100644 --- a/arch/arm64/include/asm/cacheflush.h +++ b/arch/arm64/include/asm/cacheflush.h @@ -90,7 +90,7 @@ static inline void flush_icache_range(unsigned long start, unsigned long end) * IPI all online CPUs so that they undergo a context synchronization * event and are forced to refetch the new instructions. */ -#ifdef CONFIG_KGDB + /* * KGDB performs cache maintenance with interrupts disabled, so we * will deadlock trying to IPI the secondary CPUs. In theory, we can @@ -100,9 +100,9 @@ static inline void flush_icache_range(unsigned long start, unsigned long end) * the patching operation, so we don't need extra IPIs here anyway. * In which case, add a KGDB-specific bodge and return early. */ - if (kgdb_connected && irqs_disabled()) + if (in_dbg_master()) return; -#endif + kick_all_cpus_sync(); } diff --git a/arch/arm64/include/asm/checksum.h b/arch/arm64/include/asm/checksum.h index 0b6f5a7d4027..fd11e0d70e44 100644 --- a/arch/arm64/include/asm/checksum.h +++ b/arch/arm64/include/asm/checksum.h @@ -30,16 +30,17 @@ static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl) { __uint128_t tmp; u64 sum; + int n = ihl; /* we want it signed */ tmp = *(const __uint128_t *)iph; iph += 16; - ihl -= 4; + n -= 4; tmp += ((tmp >> 64) | (tmp << 64)); sum = tmp >> 64; do { sum += *(const u32 *)iph; iph += 4; - } while (--ihl); + } while (--n > 0); sum += ((sum >> 32) | (sum << 32)); return csum_fold((__force u32)(sum >> 32)); diff --git a/arch/arm64/include/asm/cmpxchg.h b/arch/arm64/include/asm/cmpxchg.h index d8b01c7c9cd3..94ccb3bfbd61 100644 --- a/arch/arm64/include/asm/cmpxchg.h +++ b/arch/arm64/include/asm/cmpxchg.h @@ -30,46 +30,46 @@ * barrier case is generated as release+dmb for the former and * acquire+release for the latter. */ -#define __XCHG_CASE(w, sz, name, mb, nop_lse, acq, acq_lse, rel, cl) \ -static inline unsigned long __xchg_case_##name(unsigned long x, \ - volatile void *ptr) \ -{ \ - unsigned long ret, tmp; \ - \ - asm volatile(ARM64_LSE_ATOMIC_INSN( \ - /* LL/SC */ \ - " prfm pstl1strm, %2\n" \ - "1: ld" #acq "xr" #sz "\t%" #w "0, %2\n" \ - " st" #rel "xr" #sz "\t%w1, %" #w "3, %2\n" \ - " cbnz %w1, 1b\n" \ - " " #mb, \ - /* LSE atomics */ \ - " swp" #acq_lse #rel #sz "\t%" #w "3, %" #w "0, %2\n" \ - __nops(3) \ - " " #nop_lse) \ - : "=&r" (ret), "=&r" (tmp), "+Q" (*(unsigned long *)ptr) \ - : "r" (x) \ - : cl); \ - \ - return ret; \ +#define __XCHG_CASE(w, sfx, name, sz, mb, nop_lse, acq, acq_lse, rel, cl) \ +static inline u##sz __xchg_case_##name##sz(u##sz x, volatile void *ptr) \ +{ \ + u##sz ret; \ + unsigned long tmp; \ + \ + asm volatile(ARM64_LSE_ATOMIC_INSN( \ + /* LL/SC */ \ + " prfm pstl1strm, %2\n" \ + "1: ld" #acq "xr" #sfx "\t%" #w "0, %2\n" \ + " st" #rel "xr" #sfx "\t%w1, %" #w "3, %2\n" \ + " cbnz %w1, 1b\n" \ + " " #mb, \ + /* LSE atomics */ \ + " swp" #acq_lse #rel #sfx "\t%" #w "3, %" #w "0, %2\n" \ + __nops(3) \ + " " #nop_lse) \ + : "=&r" (ret), "=&r" (tmp), "+Q" (*(u##sz *)ptr) \ + : "r" (x) \ + : cl); \ + \ + return ret; \ } -__XCHG_CASE(w, b, 1, , , , , , ) -__XCHG_CASE(w, h, 2, , , , , , ) -__XCHG_CASE(w, , 4, , , , , , ) -__XCHG_CASE( , , 8, , , , , , ) -__XCHG_CASE(w, b, acq_1, , , a, a, , "memory") -__XCHG_CASE(w, h, acq_2, , , a, a, , "memory") -__XCHG_CASE(w, , acq_4, , , a, a, , "memory") -__XCHG_CASE( , , acq_8, , , a, a, , "memory") -__XCHG_CASE(w, b, rel_1, , , , , l, "memory") -__XCHG_CASE(w, h, rel_2, , , , , l, "memory") -__XCHG_CASE(w, , rel_4, , , , , l, "memory") -__XCHG_CASE( , , rel_8, , , , , l, "memory") -__XCHG_CASE(w, b, mb_1, dmb ish, nop, , a, l, "memory") -__XCHG_CASE(w, h, mb_2, dmb ish, nop, , a, l, "memory") -__XCHG_CASE(w, , mb_4, dmb ish, nop, , a, l, "memory") -__XCHG_CASE( , , mb_8, dmb ish, nop, , a, l, "memory") +__XCHG_CASE(w, b, , 8, , , , , , ) +__XCHG_CASE(w, h, , 16, , , , , , ) +__XCHG_CASE(w, , , 32, , , , , , ) +__XCHG_CASE( , , , 64, , , , , , ) +__XCHG_CASE(w, b, acq_, 8, , , a, a, , "memory") +__XCHG_CASE(w, h, acq_, 16, , , a, a, , "memory") +__XCHG_CASE(w, , acq_, 32, , , a, a, , "memory") +__XCHG_CASE( , , acq_, 64, , , a, a, , "memory") +__XCHG_CASE(w, b, rel_, 8, , , , , l, "memory") +__XCHG_CASE(w, h, rel_, 16, , , , , l, "memory") +__XCHG_CASE(w, , rel_, 32, , , , , l, "memory") +__XCHG_CASE( , , rel_, 64, , , , , l, "memory") +__XCHG_CASE(w, b, mb_, 8, dmb ish, nop, , a, l, "memory") +__XCHG_CASE(w, h, mb_, 16, dmb ish, nop, , a, l, "memory") +__XCHG_CASE(w, , mb_, 32, dmb ish, nop, , a, l, "memory") +__XCHG_CASE( , , mb_, 64, dmb ish, nop, , a, l, "memory") #undef __XCHG_CASE @@ -80,13 +80,13 @@ static __always_inline unsigned long __xchg##sfx(unsigned long x, \ { \ switch (size) { \ case 1: \ - return __xchg_case##sfx##_1(x, ptr); \ + return __xchg_case##sfx##_8(x, ptr); \ case 2: \ - return __xchg_case##sfx##_2(x, ptr); \ + return __xchg_case##sfx##_16(x, ptr); \ case 4: \ - return __xchg_case##sfx##_4(x, ptr); \ + return __xchg_case##sfx##_32(x, ptr); \ case 8: \ - return __xchg_case##sfx##_8(x, ptr); \ + return __xchg_case##sfx##_64(x, ptr); \ default: \ BUILD_BUG(); \ } \ @@ -123,13 +123,13 @@ static __always_inline unsigned long __cmpxchg##sfx(volatile void *ptr, \ { \ switch (size) { \ case 1: \ - return __cmpxchg_case##sfx##_1(ptr, (u8)old, new); \ + return __cmpxchg_case##sfx##_8(ptr, (u8)old, new); \ case 2: \ - return __cmpxchg_case##sfx##_2(ptr, (u16)old, new); \ + return __cmpxchg_case##sfx##_16(ptr, (u16)old, new); \ case 4: \ - return __cmpxchg_case##sfx##_4(ptr, old, new); \ + return __cmpxchg_case##sfx##_32(ptr, old, new); \ case 8: \ - return __cmpxchg_case##sfx##_8(ptr, old, new); \ + return __cmpxchg_case##sfx##_64(ptr, old, new); \ default: \ BUILD_BUG(); \ } \ @@ -197,16 +197,16 @@ __CMPXCHG_GEN(_mb) __ret; \ }) -#define __CMPWAIT_CASE(w, sz, name) \ -static inline void __cmpwait_case_##name(volatile void *ptr, \ - unsigned long val) \ +#define __CMPWAIT_CASE(w, sfx, sz) \ +static inline void __cmpwait_case_##sz(volatile void *ptr, \ + unsigned long val) \ { \ unsigned long tmp; \ \ asm volatile( \ " sevl\n" \ " wfe\n" \ - " ldxr" #sz "\t%" #w "[tmp], %[v]\n" \ + " ldxr" #sfx "\t%" #w "[tmp], %[v]\n" \ " eor %" #w "[tmp], %" #w "[tmp], %" #w "[val]\n" \ " cbnz %" #w "[tmp], 1f\n" \ " wfe\n" \ @@ -215,10 +215,10 @@ static inline void __cmpwait_case_##name(volatile void *ptr, \ : [val] "r" (val)); \ } -__CMPWAIT_CASE(w, b, 1); -__CMPWAIT_CASE(w, h, 2); -__CMPWAIT_CASE(w, , 4); -__CMPWAIT_CASE( , , 8); +__CMPWAIT_CASE(w, b, 8); +__CMPWAIT_CASE(w, h, 16); +__CMPWAIT_CASE(w, , 32); +__CMPWAIT_CASE( , , 64); #undef __CMPWAIT_CASE @@ -229,13 +229,13 @@ static __always_inline void __cmpwait##sfx(volatile void *ptr, \ { \ switch (size) { \ case 1: \ - return __cmpwait_case##sfx##_1(ptr, (u8)val); \ + return __cmpwait_case##sfx##_8(ptr, (u8)val); \ case 2: \ - return __cmpwait_case##sfx##_2(ptr, (u16)val); \ + return __cmpwait_case##sfx##_16(ptr, (u16)val); \ case 4: \ - return __cmpwait_case##sfx##_4(ptr, val); \ + return __cmpwait_case##sfx##_32(ptr, val); \ case 8: \ - return __cmpwait_case##sfx##_8(ptr, val); \ + return __cmpwait_case##sfx##_64(ptr, val); \ default: \ BUILD_BUG(); \ } \ diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h index c3de0bbf0e9a..df8fe8ecc37e 100644 --- a/arch/arm64/include/asm/cpucaps.h +++ b/arch/arm64/include/asm/cpucaps.h @@ -53,7 +53,8 @@ #define ARM64_HAS_STAGE2_FWB 32 #define ARM64_WORKAROUND_1463225 33 #define ARM64_SSBS 34 +#define ARM64_WORKAROUND_1542419 35 -#define ARM64_NCAPS 35 +#define ARM64_NCAPS 36 #endif /* __ASM_CPUCAPS_H */ diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index fa770c070fdd..3cd936b1c79c 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -80,6 +80,7 @@ #define ARM_CPU_PART_CORTEX_A35 0xD04 #define ARM_CPU_PART_CORTEX_A55 0xD05 #define ARM_CPU_PART_CORTEX_A76 0xD0B +#define ARM_CPU_PART_NEOVERSE_N1 0xD0C #define APM_CPU_PART_POTENZA 0x000 @@ -107,6 +108,7 @@ #define MIDR_CORTEX_A35 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A35) #define MIDR_CORTEX_A55 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A55) #define MIDR_CORTEX_A76 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A76) +#define MIDR_NEOVERSE_N1 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_N1) #define MIDR_THUNDERX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX) #define MIDR_THUNDERX_81XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_81XX) #define MIDR_THUNDERX_83XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_83XX) diff --git a/arch/arm64/include/asm/debug-monitors.h b/arch/arm64/include/asm/debug-monitors.h index a44cf5225429..41b065f1be88 100644 --- a/arch/arm64/include/asm/debug-monitors.h +++ b/arch/arm64/include/asm/debug-monitors.h @@ -119,6 +119,8 @@ void disable_debug_monitors(enum dbg_active_el el); void user_rewind_single_step(struct task_struct *task); void user_fastforward_single_step(struct task_struct *task); +void user_regs_reset_single_step(struct user_pt_regs *regs, + struct task_struct *task); void kernel_enable_single_step(struct pt_regs *regs); void kernel_disable_single_step(void); diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h index 8b284cbf8162..6d43f7901da2 100644 --- a/arch/arm64/include/asm/kvm_arm.h +++ b/arch/arm64/include/asm/kvm_arm.h @@ -83,11 +83,12 @@ * IMO: Override CPSR.I and enable signaling with VI * FMO: Override CPSR.F and enable signaling with VF * SWIO: Turn set/way invalidates into set/way clean+invalidate + * PTW: Take a stage2 fault if a stage1 walk steps in device memory */ #define HCR_GUEST_FLAGS (HCR_TSC | HCR_TSW | HCR_TWE | HCR_TWI | HCR_VM | \ HCR_TVM | HCR_BSU_IS | HCR_FB | HCR_TAC | \ HCR_AMO | HCR_SWIO | HCR_TIDCP | HCR_RW | HCR_TLOR | \ - HCR_FMO | HCR_IMO) + HCR_FMO | HCR_IMO | HCR_PTW ) #define HCR_VIRT_EXCP_MASK (HCR_VSE | HCR_VI | HCR_VF) #define HCR_HOST_NVHE_FLAGS (HCR_RW | HCR_API | HCR_APK) #define HCR_HOST_VHE_FLAGS (HCR_RW | HCR_TGE | HCR_E2H) @@ -197,6 +198,7 @@ #define CPTR_EL2_DEFAULT CPTR_EL2_RES1 /* Hyp Debug Configuration Register bits */ +#define MDCR_EL2_TTRF (1 << 19) #define MDCR_EL2_TPMS (1 << 14) #define MDCR_EL2_E2PB_MASK (UL(0x3)) #define MDCR_EL2_E2PB_SHIFT (UL(12)) diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h index 102b5a5c47b6..e3c0dba5bdde 100644 --- a/arch/arm64/include/asm/kvm_asm.h +++ b/arch/arm64/include/asm/kvm_asm.h @@ -87,6 +87,34 @@ extern u32 __init_stage2_translation(void); *__hyp_this_cpu_ptr(sym); \ }) +#define __KVM_EXTABLE(from, to) \ + " .pushsection __kvm_ex_table, \"a\"\n" \ + " .align 3\n" \ + " .long (" #from " - .), (" #to " - .)\n" \ + " .popsection\n" + + +#define __kvm_at(at_op, addr) \ +( { \ + int __kvm_at_err = 0; \ + u64 spsr, elr; \ + asm volatile( \ + " mrs %1, spsr_el2\n" \ + " mrs %2, elr_el2\n" \ + "1: at "at_op", %3\n" \ + " isb\n" \ + " b 9f\n" \ + "2: msr spsr_el2, %1\n" \ + " msr elr_el2, %2\n" \ + " mov %w0, %4\n" \ + "9:\n" \ + __KVM_EXTABLE(1b, 2b) \ + : "+r" (__kvm_at_err), "=&r" (spsr), "=&r" (elr) \ + : "r" (addr), "i" (-EFAULT)); \ + __kvm_at_err; \ +} ) + + #else /* __ASSEMBLY__ */ .macro hyp_adr_this_cpu reg, sym, tmp @@ -111,6 +139,21 @@ extern u32 __init_stage2_translation(void); kern_hyp_va \vcpu .endm +/* + * KVM extable for unexpected exceptions. + * In the same format _asm_extable, but output to a different section so that + * it can be mapped to EL2. The KVM version is not sorted. The caller must + * ensure: + * x18 has the hypervisor value to allow any Shadow-Call-Stack instrumented + * code to write to it, and that SPSR_EL2 and ELR_EL2 are restored by the fixup. + */ +.macro _kvm_extable, from, to + .pushsection __kvm_ex_table, "a" + .align 3 + .long (\from - .), (\to - .) + .popsection +.endm + #endif #endif /* __ARM_KVM_ASM_H__ */ diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index 778cb4f868d9..669c960dd069 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -303,7 +303,7 @@ static inline int kvm_vcpu_dabt_get_rd(const struct kvm_vcpu *vcpu) return (kvm_vcpu_get_hsr(vcpu) & ESR_ELx_SRT_MASK) >> ESR_ELx_SRT_SHIFT; } -static inline bool kvm_vcpu_dabt_iss1tw(const struct kvm_vcpu *vcpu) +static inline bool kvm_vcpu_abt_iss1tw(const struct kvm_vcpu *vcpu) { return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_S1PTW); } @@ -311,7 +311,7 @@ static inline bool kvm_vcpu_dabt_iss1tw(const struct kvm_vcpu *vcpu) static inline bool kvm_vcpu_dabt_iswrite(const struct kvm_vcpu *vcpu) { return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_WNR) || - kvm_vcpu_dabt_iss1tw(vcpu); /* AF/DBM update */ + kvm_vcpu_abt_iss1tw(vcpu); /* AF/DBM update */ } static inline bool kvm_vcpu_dabt_is_cm(const struct kvm_vcpu *vcpu) @@ -340,6 +340,11 @@ static inline bool kvm_vcpu_trap_is_iabt(const struct kvm_vcpu *vcpu) return kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_IABT_LOW; } +static inline bool kvm_vcpu_trap_is_exec_fault(const struct kvm_vcpu *vcpu) +{ + return kvm_vcpu_trap_is_iabt(vcpu) && !kvm_vcpu_abt_iss1tw(vcpu); +} + static inline u8 kvm_vcpu_trap_get_fault(const struct kvm_vcpu *vcpu) { return kvm_vcpu_get_hsr(vcpu) & ESR_ELx_FSC; diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 367b2e0b6d76..07472c138ced 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -165,6 +165,7 @@ enum vcpu_sysreg { #define c2_TTBR1 (TTBR1_EL1 * 2) /* Translation Table Base Register 1 */ #define c2_TTBR1_high (c2_TTBR1 + 1) /* TTBR1 top 32 bits */ #define c2_TTBCR (TCR_EL1 * 2) /* Translation Table Base Control R. */ +#define c2_TTBCR2 (c2_TTBCR + 1) /* Translation Table Base Control R. 2 */ #define c3_DACR (DACR32_EL2 * 2)/* Domain Access Control Register */ #define c5_DFSR (ESR_EL1 * 2) /* Data Fault Status Register */ #define c5_IFSR (IFSR32_EL2 * 2)/* Instruction Fault Status Register */ @@ -192,6 +193,7 @@ enum vcpu_sysreg { #define cp14_DBGWCR0 (DBGWCR0_EL1 * 2) #define cp14_DBGWVR0 (DBGWVR0_EL1 * 2) #define cp14_DBGDCCINT (MDCCINT_EL1 * 2) +#define cp14_DBGVCR (DBGVCR32_EL2 * 2) #define NR_COPRO_REGS (NR_SYS_REGS * 2) @@ -335,8 +337,10 @@ void vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, int reg); * CP14 and CP15 live in the same array, as they are backed by the * same system registers. */ -#define vcpu_cp14(v,r) ((v)->arch.ctxt.copro[(r)]) -#define vcpu_cp15(v,r) ((v)->arch.ctxt.copro[(r)]) +#define CPx_BIAS IS_ENABLED(CONFIG_CPU_BIG_ENDIAN) + +#define vcpu_cp14(v,r) ((v)->arch.ctxt.copro[(r) ^ CPx_BIAS]) +#define vcpu_cp15(v,r) ((v)->arch.ctxt.copro[(r) ^ CPx_BIAS]) struct kvm_vm_stat { ulong remote_tlb_flush; @@ -368,7 +372,7 @@ int __kvm_arm_vcpu_set_events(struct kvm_vcpu *vcpu, #define KVM_ARCH_WANT_MMU_NOTIFIER int kvm_unmap_hva_range(struct kvm *kvm, - unsigned long start, unsigned long end); + unsigned long start, unsigned long end, bool blockable); void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end); int kvm_test_age_hva(struct kvm *kvm, unsigned long hva); @@ -451,6 +455,7 @@ static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {} static inline void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu) {} void kvm_arm_init_debug(void); +void kvm_arm_vcpu_init_debug(struct kvm_vcpu *vcpu); void kvm_arm_setup_debug(struct kvm_vcpu *vcpu); void kvm_arm_clear_debug(struct kvm_vcpu *vcpu); void kvm_arm_reset_debug_ptr(struct kvm_vcpu *vcpu); @@ -535,4 +540,6 @@ void kvm_vcpu_put_sysregs(struct kvm_vcpu *vcpu); struct kvm *kvm_arch_alloc_vm(void); void kvm_arch_free_vm(struct kvm *kvm); +#define kvm_arm_vcpu_loaded(vcpu) ((vcpu)->arch.sysregs_loaded_on_cpu) + #endif /* __ARM64_KVM_HOST_H__ */ diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h index 384c34397619..5f52d6d670e9 100644 --- a/arch/arm64/include/asm/kvm_hyp.h +++ b/arch/arm64/include/asm/kvm_hyp.h @@ -144,6 +144,9 @@ void __sysreg32_restore_state(struct kvm_vcpu *vcpu); void __debug_switch_to_guest(struct kvm_vcpu *vcpu); void __debug_switch_to_host(struct kvm_vcpu *vcpu); +void __debug_save_host_buffers_nvhe(struct kvm_vcpu *vcpu); +void __debug_restore_host_buffers_nvhe(struct kvm_vcpu *vcpu); + void __fpsimd_save_state(struct user_fpsimd_state *fp_regs); void __fpsimd_restore_state(struct user_fpsimd_state *fp_regs); diff --git a/arch/arm64/include/asm/lse.h b/arch/arm64/include/asm/lse.h index 8262325e2fc6..13536c4da2c2 100644 --- a/arch/arm64/include/asm/lse.h +++ b/arch/arm64/include/asm/lse.h @@ -4,6 +4,8 @@ #if defined(CONFIG_AS_LSE) && defined(CONFIG_ARM64_LSE_ATOMICS) +#define __LSE_PREAMBLE ".arch_extension lse\n" + #include <linux/compiler_types.h> #include <linux/export.h> #include <linux/stringify.h> @@ -20,8 +22,6 @@ #else /* __ASSEMBLER__ */ -__asm__(".arch_extension lse"); - /* Move the ll/sc atomics out-of-line */ #define __LL_SC_INLINE notrace #define __LL_SC_PREFIX(x) __ll_sc_##x @@ -33,7 +33,7 @@ __asm__(".arch_extension lse"); /* In-line patching at runtime */ #define ARM64_LSE_ATOMIC_INSN(llsc, lse) \ - ALTERNATIVE(llsc, lse, ARM64_HAS_LSE_ATOMICS) + ALTERNATIVE(llsc, __LSE_PREAMBLE lse, ARM64_HAS_LSE_ATOMICS) #endif /* __ASSEMBLER__ */ #else /* CONFIG_AS_LSE && CONFIG_ARM64_LSE_ATOMICS */ diff --git a/arch/arm64/include/asm/numa.h b/arch/arm64/include/asm/numa.h index 626ad01e83bf..dd870390d639 100644 --- a/arch/arm64/include/asm/numa.h +++ b/arch/arm64/include/asm/numa.h @@ -25,6 +25,9 @@ const struct cpumask *cpumask_of_node(int node); /* Returns a pointer to the cpumask of CPUs on Node 'node'. */ static inline const struct cpumask *cpumask_of_node(int node) { + if (node == NUMA_NO_NODE) + return cpu_all_mask; + return node_to_cpumask_map[node]; } #endif diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h index 5be015e2133a..af547be1779b 100644 --- a/arch/arm64/include/asm/pgtable-prot.h +++ b/arch/arm64/include/asm/pgtable-prot.h @@ -65,7 +65,7 @@ #define PAGE_HYP __pgprot(_HYP_PAGE_DEFAULT | PTE_HYP | PTE_HYP_XN) #define PAGE_HYP_EXEC __pgprot(_HYP_PAGE_DEFAULT | PTE_HYP | PTE_RDONLY) #define PAGE_HYP_RO __pgprot(_HYP_PAGE_DEFAULT | PTE_HYP | PTE_RDONLY | PTE_HYP_XN) -#define PAGE_HYP_DEVICE __pgprot(PROT_DEVICE_nGnRE | PTE_HYP) +#define PAGE_HYP_DEVICE __pgprot(_PROT_DEFAULT | PTE_ATTRINDX(MT_DEVICE_nGnRE) | PTE_HYP | PTE_HYP_XN) #define PAGE_S2_MEMATTR(attr) \ ({ \ diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 291fed0a9df8..f43519b71061 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -107,8 +107,6 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]; #define pte_valid(pte) (!!(pte_val(pte) & PTE_VALID)) #define pte_valid_not_user(pte) \ ((pte_val(pte) & (PTE_VALID | PTE_USER)) == PTE_VALID) -#define pte_valid_young(pte) \ - ((pte_val(pte) & (PTE_VALID | PTE_AF)) == (PTE_VALID | PTE_AF)) #define pte_valid_user(pte) \ ((pte_val(pte) & (PTE_VALID | PTE_USER)) == (PTE_VALID | PTE_USER)) @@ -116,9 +114,12 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]; * Could the pte be present in the TLB? We must check mm_tlb_flush_pending * so that we don't erroneously return false for pages that have been * remapped as PROT_NONE but are yet to be flushed from the TLB. + * Note that we can't make any assumptions based on the state of the access + * flag, since ptep_clear_flush_young() elides a DSB when invalidating the + * TLB. */ #define pte_accessible(mm, pte) \ - (mm_tlb_flush_pending(mm) ? pte_present(pte) : pte_valid_young(pte)) + (mm_tlb_flush_pending(mm) ? pte_present(pte) : pte_valid(pte)) /* * p??_access_permitted() is true for valid user mappings (subject to the @@ -144,13 +145,6 @@ static inline pte_t set_pte_bit(pte_t pte, pgprot_t prot) return pte; } -static inline pte_t pte_wrprotect(pte_t pte) -{ - pte = clear_pte_bit(pte, __pgprot(PTE_WRITE)); - pte = set_pte_bit(pte, __pgprot(PTE_RDONLY)); - return pte; -} - static inline pte_t pte_mkwrite(pte_t pte) { pte = set_pte_bit(pte, __pgprot(PTE_WRITE)); @@ -176,6 +170,20 @@ static inline pte_t pte_mkdirty(pte_t pte) return pte; } +static inline pte_t pte_wrprotect(pte_t pte) +{ + /* + * If hardware-dirty (PTE_WRITE/DBM bit set and PTE_RDONLY + * clear), set the PTE_DIRTY bit. + */ + if (pte_hw_dirty(pte)) + pte = pte_mkdirty(pte); + + pte = clear_pte_bit(pte, __pgprot(PTE_WRITE)); + pte = set_pte_bit(pte, __pgprot(PTE_RDONLY)); + return pte; +} + static inline pte_t pte_mkold(pte_t pte) { return clear_pte_bit(pte, __pgprot(PTE_AF)); @@ -668,12 +676,6 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addres pte = READ_ONCE(*ptep); do { old_pte = pte; - /* - * If hardware-dirty (PTE_WRITE/DBM bit set and PTE_RDONLY - * clear), set the PTE_DIRTY bit. - */ - if (pte_hw_dirty(pte)) - pte = pte_mkdirty(pte); pte = pte_wrprotect(pte); pte_val(pte) = cmpxchg_relaxed(&pte_val(*ptep), pte_val(old_pte), pte_val(pte)); diff --git a/arch/arm64/include/asm/syscall.h b/arch/arm64/include/asm/syscall.h index 58102652bf9e..615376030aba 100644 --- a/arch/arm64/include/asm/syscall.h +++ b/arch/arm64/include/asm/syscall.h @@ -45,6 +45,10 @@ static inline long syscall_get_error(struct task_struct *task, struct pt_regs *regs) { unsigned long error = regs->regs[0]; + + if (is_compat_thread(task_thread_info(task))) + error = sign_extend64(error, 31); + return IS_ERR_VALUE(error) ? error : 0; } @@ -58,7 +62,13 @@ static inline void syscall_set_return_value(struct task_struct *task, struct pt_regs *regs, int error, long val) { - regs->regs[0] = (long) error ? error : val; + if (error) + val = error; + + if (is_compat_thread(task_thread_info(task))) + val = lower_32_bits(val); + + regs->regs[0] = val; } #define SYSCALL_MAX_ARGS 6 diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h index 3091ae5975a3..ed99d941c462 100644 --- a/arch/arm64/include/asm/sysreg.h +++ b/arch/arm64/include/asm/sysreg.h @@ -60,7 +60,9 @@ #ifndef CONFIG_BROKEN_GAS_INST #ifdef __ASSEMBLY__ -#define __emit_inst(x) .inst (x) +// The space separator is omitted so that __emit_inst(x) can be parsed as +// either an assembler directive or an assembler macro argument. +#define __emit_inst(x) .inst(x) #else #define __emit_inst(x) ".inst " __stringify((x)) "\n\t" #endif diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h index cb2c10a8f0a8..69ac5262cccd 100644 --- a/arch/arm64/include/asm/thread_info.h +++ b/arch/arm64/include/asm/thread_info.h @@ -101,6 +101,7 @@ void arch_release_task_struct(struct task_struct *tsk); #define _TIF_SECCOMP (1 << TIF_SECCOMP) #define _TIF_UPROBE (1 << TIF_UPROBE) #define _TIF_FSCHECK (1 << TIF_FSCHECK) +#define _TIF_SINGLESTEP (1 << TIF_SINGLESTEP) #define _TIF_32BIT (1 << TIF_32BIT) #define _TIF_SVE (1 << TIF_SVE) diff --git a/arch/arm64/include/asm/word-at-a-time.h b/arch/arm64/include/asm/word-at-a-time.h index b0d708ff7f4e..a2601c1ccf43 100644 --- a/arch/arm64/include/asm/word-at-a-time.h +++ b/arch/arm64/include/asm/word-at-a-time.h @@ -64,7 +64,7 @@ static inline unsigned long find_zero(unsigned long mask) */ static inline unsigned long load_unaligned_zeropad(const void *addr) { - unsigned long ret, offset; + unsigned long ret, tmp; /* Load word from unaligned pointer addr */ asm( @@ -72,9 +72,9 @@ static inline unsigned long load_unaligned_zeropad(const void *addr) "2:\n" " .pushsection .fixup,\"ax\"\n" " .align 2\n" - "3: and %1, %2, #0x7\n" - " bic %2, %2, #0x7\n" - " ldr %0, [%2]\n" + "3: bic %1, %2, #0x7\n" + " ldr %0, [%1]\n" + " and %1, %2, #0x7\n" " lsl %1, %1, #0x3\n" #ifndef __AARCH64EB__ " lsr %0, %0, %1\n" @@ -84,7 +84,7 @@ static inline unsigned long load_unaligned_zeropad(const void *addr) " b 2b\n" " .popsection\n" _ASM_EXTABLE(1b, 3b) - : "=&r" (ret), "=&r" (offset) + : "=&r" (ret), "=&r" (tmp) : "r" (addr), "Q" (*(unsigned long *)addr)); return ret; diff --git a/arch/arm64/kernel/alternative.c b/arch/arm64/kernel/alternative.c index b5d603992d40..0d345622bbba 100644 --- a/arch/arm64/kernel/alternative.c +++ b/arch/arm64/kernel/alternative.c @@ -44,20 +44,8 @@ struct alt_region { */ static bool branch_insn_requires_update(struct alt_instr *alt, unsigned long pc) { - unsigned long replptr; - - if (kernel_text_address(pc)) - return true; - - replptr = (unsigned long)ALT_REPL_PTR(alt); - if (pc >= replptr && pc <= (replptr + alt->alt_len)) - return false; - - /* - * Branching into *another* alternate sequence is doomed, and - * we're not even trying to fix it up. - */ - BUG(); + unsigned long replptr = (unsigned long)ALT_REPL_PTR(alt); + return !(pc >= replptr && pc <= (replptr + alt->alt_len)); } #define align_down(x, a) ((unsigned long)(x) & ~(((unsigned long)(a)) - 1)) diff --git a/arch/arm64/kernel/armv8_deprecated.c b/arch/arm64/kernel/armv8_deprecated.c index 39dc98dd78eb..181c29af5617 100644 --- a/arch/arm64/kernel/armv8_deprecated.c +++ b/arch/arm64/kernel/armv8_deprecated.c @@ -604,7 +604,7 @@ static struct undef_hook setend_hooks[] = { }, { /* Thumb mode */ - .instr_mask = 0x0000fff7, + .instr_mask = 0xfffffff7, .instr_val = 0x0000b650, .pstate_mask = (PSR_AA32_T_BIT | PSR_AA32_MODE_MASK), .pstate_val = (PSR_AA32_T_BIT | PSR_AA32_MODE_USR), diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 71888808ded7..d191ce8410db 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -619,6 +619,12 @@ check_branch_predictor(const struct arm64_cpu_capabilities *entry, int scope) return (need_wa > 0); } +static void +cpu_enable_branch_predictor_hardening(const struct arm64_cpu_capabilities *cap) +{ + cap->matches(cap, SCOPE_LOCAL_CPU); +} + static const __maybe_unused struct midr_range tx2_family_cpus[] = { MIDR_ALL_VERSIONS(MIDR_BRCM_VULCAN), MIDR_ALL_VERSIONS(MIDR_CAVIUM_THUNDERX2), @@ -643,6 +649,18 @@ needs_tx2_tvm_workaround(const struct arm64_cpu_capabilities *entry, return false; } +static bool __maybe_unused +has_neoverse_n1_erratum_1542419(const struct arm64_cpu_capabilities *entry, + int scope) +{ + u32 midr = read_cpuid_id(); + bool has_dic = read_cpuid_cachetype() & BIT(CTR_DIC_SHIFT); + const struct midr_range range = MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N1); + + WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible()); + return is_midr_in_range(midr, &range) && has_dic; +} + #ifdef CONFIG_HARDEN_EL2_VECTORS static const struct midr_range arm64_harden_el2_vectors[] = { @@ -801,9 +819,11 @@ const struct arm64_cpu_capabilities arm64_errata[] = { }, #endif { + .desc = "Branch predictor hardening", .capability = ARM64_HARDEN_BRANCH_PREDICTOR, .type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM, .matches = check_branch_predictor, + .cpu_enable = cpu_enable_branch_predictor_hardening, }, #ifdef CONFIG_HARDEN_EL2_VECTORS { @@ -835,6 +855,16 @@ const struct arm64_cpu_capabilities arm64_errata[] = { .matches = needs_tx2_tvm_workaround, }, #endif +#ifdef CONFIG_ARM64_ERRATUM_1542419 + { + /* we depend on the firmware portion for correctness */ + .desc = "ARM erratum 1542419 (kernel portion)", + .capability = ARM64_WORKAROUND_1542419, + .type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM, + .matches = has_neoverse_n1_erratum_1542419, + .cpu_enable = cpu_enable_trap_ctr_access, + }, +#endif { } }; diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index ac3126aba036..122d5e843ab6 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -155,11 +155,10 @@ static const struct arm64_ftr_bits ftr_id_aa64pfr0[] = { ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_GIC_SHIFT, 4, 0), S_ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_ASIMD_SHIFT, 4, ID_AA64PFR0_ASIMD_NI), S_ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_FP_SHIFT, 4, ID_AA64PFR0_FP_NI), - /* Linux doesn't care about the EL3 */ ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL3_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL2_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL1_SHIFT, 4, ID_AA64PFR0_EL1_64BIT_ONLY), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL0_SHIFT, 4, ID_AA64PFR0_EL0_64BIT_ONLY), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL2_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL1_SHIFT, 4, ID_AA64PFR0_EL1_64BIT_ONLY), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL0_SHIFT, 4, ID_AA64PFR0_EL0_64BIT_ONLY), ARM64_FTR_END, }; @@ -259,7 +258,6 @@ static const struct arm64_ftr_bits ftr_id_aa64dfr0[] = { * of support. */ S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_EXACT, ID_AA64DFR0_PMUVER_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64DFR0_TRACEVER_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64DFR0_DEBUGVER_SHIFT, 4, 0x6), ARM64_FTR_END, }; @@ -301,7 +299,7 @@ static const struct arm64_ftr_bits ftr_id_pfr0[] = { }; static const struct arm64_ftr_bits ftr_id_dfr0[] = { - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 28, 4, 0), + /* [31:28] TraceFilt */ S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 24, 4, 0xf), /* PerfMon */ ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 20, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 16, 4, 0), @@ -671,9 +669,6 @@ void update_cpu_features(int cpu, taint |= check_update_ftr_reg(SYS_ID_AA64MMFR2_EL1, cpu, info->reg_id_aa64mmfr2, boot->reg_id_aa64mmfr2); - /* - * EL3 is not our concern. - */ taint |= check_update_ftr_reg(SYS_ID_AA64PFR0_EL1, cpu, info->reg_id_aa64pfr0, boot->reg_id_aa64pfr0); taint |= check_update_ftr_reg(SYS_ID_AA64PFR1_EL1, cpu, @@ -1016,7 +1011,7 @@ static bool cpu_has_broken_dbm(void) /* List of CPUs which have broken DBM support. */ static const struct midr_range cpus[] = { #ifdef CONFIG_ARM64_ERRATUM_1024718 - MIDR_RANGE(MIDR_CORTEX_A55, 0, 0, 1, 0), // A55 r0p0 -r1p0 + MIDR_ALL_VERSIONS(MIDR_CORTEX_A55), #endif {}, }; diff --git a/arch/arm64/kernel/crash_dump.c b/arch/arm64/kernel/crash_dump.c index f46d57c31443..76905a258550 100644 --- a/arch/arm64/kernel/crash_dump.c +++ b/arch/arm64/kernel/crash_dump.c @@ -67,5 +67,7 @@ ssize_t copy_oldmem_page(unsigned long pfn, char *buf, ssize_t elfcorehdr_read(char *buf, size_t count, u64 *ppos) { memcpy(buf, phys_to_virt((phys_addr_t)*ppos), count); + *ppos += count; + return count; } diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c index 262925b98f42..501e835c6500 100644 --- a/arch/arm64/kernel/debug-monitors.c +++ b/arch/arm64/kernel/debug-monitors.c @@ -152,17 +152,20 @@ postcore_initcall(debug_monitors_init); /* * Single step API and exception handling. */ -static void set_regs_spsr_ss(struct pt_regs *regs) +static void set_user_regs_spsr_ss(struct user_pt_regs *regs) { regs->pstate |= DBG_SPSR_SS; } -NOKPROBE_SYMBOL(set_regs_spsr_ss); +NOKPROBE_SYMBOL(set_user_regs_spsr_ss); -static void clear_regs_spsr_ss(struct pt_regs *regs) +static void clear_user_regs_spsr_ss(struct user_pt_regs *regs) { regs->pstate &= ~DBG_SPSR_SS; } -NOKPROBE_SYMBOL(clear_regs_spsr_ss); +NOKPROBE_SYMBOL(clear_user_regs_spsr_ss); + +#define set_regs_spsr_ss(r) set_user_regs_spsr_ss(&(r)->user_regs) +#define clear_regs_spsr_ss(r) clear_user_regs_spsr_ss(&(r)->user_regs) /* EL1 Single Step Handler hooks */ static LIST_HEAD(step_hook); @@ -389,17 +392,26 @@ void user_rewind_single_step(struct task_struct *task) * If single step is active for this thread, then set SPSR.SS * to 1 to avoid returning to the active-pending state. */ - if (test_ti_thread_flag(task_thread_info(task), TIF_SINGLESTEP)) + if (test_tsk_thread_flag(task, TIF_SINGLESTEP)) set_regs_spsr_ss(task_pt_regs(task)); } NOKPROBE_SYMBOL(user_rewind_single_step); void user_fastforward_single_step(struct task_struct *task) { - if (test_ti_thread_flag(task_thread_info(task), TIF_SINGLESTEP)) + if (test_tsk_thread_flag(task, TIF_SINGLESTEP)) clear_regs_spsr_ss(task_pt_regs(task)); } +void user_regs_reset_single_step(struct user_pt_regs *regs, + struct task_struct *task) +{ + if (test_tsk_thread_flag(task, TIF_SINGLESTEP)) + set_user_regs_spsr_ss(regs); + else + clear_user_regs_spsr_ss(regs); +} + /* Kernel API */ void kernel_enable_single_step(struct pt_regs *regs) { diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 14fdbaa6ee3a..19c87b52c001 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -304,7 +304,7 @@ static unsigned int find_supported_vector_length(unsigned int vl) return sve_vl_from_vq(bit_to_vq(bit)); } -#ifdef CONFIG_SYSCTL +#if defined(CONFIG_ARM64_SVE) && defined(CONFIG_SYSCTL) static int sve_proc_do_default_vl(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, @@ -350,9 +350,9 @@ static int __init sve_sysctl_init(void) return 0; } -#else /* ! CONFIG_SYSCTL */ +#else /* ! (CONFIG_ARM64_SVE && CONFIG_SYSCTL) */ static int __init sve_sysctl_init(void) { return 0; } -#endif /* ! CONFIG_SYSCTL */ +#endif /* ! (CONFIG_ARM64_SVE && CONFIG_SYSCTL) */ #define ZREG(sve_state, vq, n) ((char *)(sve_state) + \ (SVE_SIG_ZREG_OFFSET(vq, n) - SVE_SIG_REGS_OFFSET)) diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index d22ab8d9edc9..c85ea70b9293 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -867,6 +867,7 @@ __primary_switch: tlbi vmalle1 // Remove any stale TLB entries dsb nsh + isb msr sctlr_el1, x19 // re-enable the MMU isb diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c index 7c0611f5d2ce..9f105fe58595 100644 --- a/arch/arm64/kernel/hw_breakpoint.c +++ b/arch/arm64/kernel/hw_breakpoint.c @@ -737,6 +737,27 @@ static u64 get_distance_from_watchpoint(unsigned long addr, u64 val, return 0; } +static int watchpoint_report(struct perf_event *wp, unsigned long addr, + struct pt_regs *regs) +{ + int step = is_default_overflow_handler(wp); + struct arch_hw_breakpoint *info = counter_arch_bp(wp); + + info->trigger = addr; + + /* + * If we triggered a user watchpoint from a uaccess routine, then + * handle the stepping ourselves since userspace really can't help + * us with this. + */ + if (!user_mode(regs) && info->ctrl.privilege == AARCH64_BREAKPOINT_EL0) + step = 1; + else + perf_bp_event(wp, regs); + + return step; +} + static int watchpoint_handler(unsigned long addr, unsigned int esr, struct pt_regs *regs) { @@ -746,7 +767,6 @@ static int watchpoint_handler(unsigned long addr, unsigned int esr, u64 val; struct perf_event *wp, **slots; struct debug_info *debug_info; - struct arch_hw_breakpoint *info; struct arch_hw_breakpoint_ctrl ctrl; slots = this_cpu_ptr(wp_on_reg); @@ -784,25 +804,13 @@ static int watchpoint_handler(unsigned long addr, unsigned int esr, if (dist != 0) continue; - info = counter_arch_bp(wp); - info->trigger = addr; - perf_bp_event(wp, regs); - - /* Do we need to handle the stepping? */ - if (is_default_overflow_handler(wp)) - step = 1; + step = watchpoint_report(wp, addr, regs); } - if (min_dist > 0 && min_dist != -1) { - /* No exact match found. */ - wp = slots[closest_match]; - info = counter_arch_bp(wp); - info->trigger = addr; - perf_bp_event(wp, regs); - /* Do we need to handle the stepping? */ - if (is_default_overflow_handler(wp)) - step = 1; - } + /* No exact match found? */ + if (min_dist > 0 && min_dist != -1) + step = watchpoint_report(slots[closest_match], addr, regs); + rcu_read_unlock(); if (!step) diff --git a/arch/arm64/kernel/insn.c b/arch/arm64/kernel/insn.c index 3e6229e30109..cd37edbdedcb 100644 --- a/arch/arm64/kernel/insn.c +++ b/arch/arm64/kernel/insn.c @@ -1490,16 +1490,10 @@ static u32 aarch64_encode_immediate(u64 imm, u32 insn) { unsigned int immr, imms, n, ones, ror, esz, tmp; - u64 mask = ~0UL; - - /* Can't encode full zeroes or full ones */ - if (!imm || !~imm) - return AARCH64_BREAK_FAULT; + u64 mask; switch (variant) { case AARCH64_INSN_VARIANT_32BIT: - if (upper_32_bits(imm)) - return AARCH64_BREAK_FAULT; esz = 32; break; case AARCH64_INSN_VARIANT_64BIT: @@ -1511,6 +1505,12 @@ static u32 aarch64_encode_immediate(u64 imm, return AARCH64_BREAK_FAULT; } + mask = GENMASK(esz - 1, 0); + + /* Can't encode full zeroes, full ones, or value wider than the mask */ + if (!imm || imm == mask || imm & ~mask) + return AARCH64_BREAK_FAULT; + /* * Inverse of Replicate(). Try to spot a repeating pattern * with a pow2 stride. diff --git a/arch/arm64/kernel/kgdb.c b/arch/arm64/kernel/kgdb.c index 35f184a8fd85..8815b5457dd0 100644 --- a/arch/arm64/kernel/kgdb.c +++ b/arch/arm64/kernel/kgdb.c @@ -269,7 +269,7 @@ static int kgdb_step_brk_fn(struct pt_regs *regs, unsigned int esr) if (user_mode(regs) || !kgdb_single_step) return DBG_HOOK_ERROR; - kgdb_handle_exception(1, SIGTRAP, 0, regs); + kgdb_handle_exception(0, SIGTRAP, 0, regs); return DBG_HOOK_HANDLED; } NOKPROBE_SYMBOL(kgdb_step_brk_fn); diff --git a/arch/arm64/kernel/machine_kexec.c b/arch/arm64/kernel/machine_kexec.c index 922add8adb74..5e26ef007863 100644 --- a/arch/arm64/kernel/machine_kexec.c +++ b/arch/arm64/kernel/machine_kexec.c @@ -192,6 +192,7 @@ void machine_kexec(struct kimage *kimage) * the offline CPUs. Therefore, we must use the __* variant here. */ __flush_icache_range((uintptr_t)reboot_code_buffer, + (uintptr_t)reboot_code_buffer + arm64_relocate_new_kernel_size); /* Flush the kimage list and its buffers. */ diff --git a/arch/arm64/kernel/module.lds b/arch/arm64/kernel/module.lds index 22e36a21c113..09a0eef71d12 100644 --- a/arch/arm64/kernel/module.lds +++ b/arch/arm64/kernel/module.lds @@ -1,5 +1,5 @@ SECTIONS { - .plt (NOLOAD) : { BYTE(0) } - .init.plt (NOLOAD) : { BYTE(0) } - .text.ftrace_trampoline (NOLOAD) : { BYTE(0) } + .plt 0 (NOLOAD) : { BYTE(0) } + .init.plt 0 (NOLOAD) : { BYTE(0) } + .text.ftrace_trampoline 0 (NOLOAD) : { BYTE(0) } } diff --git a/arch/arm64/kernel/perf_regs.c b/arch/arm64/kernel/perf_regs.c index 0bbac612146e..666b225aeb3a 100644 --- a/arch/arm64/kernel/perf_regs.c +++ b/arch/arm64/kernel/perf_regs.c @@ -15,15 +15,34 @@ u64 perf_reg_value(struct pt_regs *regs, int idx) return 0; /* - * Compat (i.e. 32 bit) mode: - * - PC has been set in the pt_regs struct in kernel_entry, - * - Handle SP and LR here. + * Our handling of compat tasks (PERF_SAMPLE_REGS_ABI_32) is weird, but + * we're stuck with it for ABI compatability reasons. + * + * For a 32-bit consumer inspecting a 32-bit task, then it will look at + * the first 16 registers (see arch/arm/include/uapi/asm/perf_regs.h). + * These correspond directly to a prefix of the registers saved in our + * 'struct pt_regs', with the exception of the PC, so we copy that down + * (x15 corresponds to SP_hyp in the architecture). + * + * So far, so good. + * + * The oddity arises when a 64-bit consumer looks at a 32-bit task and + * asks for registers beyond PERF_REG_ARM_MAX. In this case, we return + * SP_usr, LR_usr and PC in the positions where the AArch64 SP, LR and + * PC registers would normally live. The initial idea was to allow a + * 64-bit unwinder to unwind a 32-bit task and, although it's not clear + * how well that works in practice, somebody might be relying on it. + * + * At the time we make a sample, we don't know whether the consumer is + * 32-bit or 64-bit, so we have to cater for both possibilities. */ if (compat_user_mode(regs)) { if ((u32)idx == PERF_REG_ARM64_SP) return regs->compat_sp; if ((u32)idx == PERF_REG_ARM64_LR) return regs->compat_lr; + if (idx == 15) + return regs->pc; } if ((u32)idx == PERF_REG_ARM64_SP) diff --git a/arch/arm64/kernel/probes/uprobes.c b/arch/arm64/kernel/probes/uprobes.c index 636ca0119c0e..6aeb11aa7e28 100644 --- a/arch/arm64/kernel/probes/uprobes.c +++ b/arch/arm64/kernel/probes/uprobes.c @@ -41,7 +41,7 @@ int arch_uprobe_analyze_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, /* TODO: Currently we do not support AARCH32 instruction probing */ if (mm->context.flags & MMCF_AARCH32) - return -ENOTSUPP; + return -EOPNOTSUPP; else if (!IS_ALIGNED(addr, AARCH64_INSN_SIZE)) return -EINVAL; diff --git a/arch/arm64/kernel/psci.c b/arch/arm64/kernel/psci.c index 3856d51c645b..3ebb2a56e5f7 100644 --- a/arch/arm64/kernel/psci.c +++ b/arch/arm64/kernel/psci.c @@ -69,7 +69,6 @@ static int cpu_psci_cpu_disable(unsigned int cpu) static void cpu_psci_cpu_die(unsigned int cpu) { - int ret; /* * There are no known implementations of PSCI actually using the * power state field, pass a sensible default for now. @@ -77,9 +76,7 @@ static void cpu_psci_cpu_die(unsigned int cpu) u32 state = PSCI_POWER_STATE_TYPE_POWER_DOWN << PSCI_0_2_POWER_STATE_TYPE_SHIFT; - ret = psci_ops.cpu_off(state); - - pr_crit("unable to power off CPU%u (%d)\n", cpu, ret); + psci_ops.cpu_off(state); } static int cpu_psci_cpu_kill(unsigned int cpu) diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 38aab5b34cc4..9579968e7222 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -1647,12 +1647,23 @@ static void tracehook_report_syscall(struct pt_regs *regs, saved_reg = regs->regs[regno]; regs->regs[regno] = dir; - if (dir == PTRACE_SYSCALL_EXIT) + if (dir == PTRACE_SYSCALL_ENTER) { + if (tracehook_report_syscall_entry(regs)) + forget_syscall(regs); + regs->regs[regno] = saved_reg; + } else if (!test_thread_flag(TIF_SINGLESTEP)) { tracehook_report_syscall_exit(regs, 0); - else if (tracehook_report_syscall_entry(regs)) - forget_syscall(regs); + regs->regs[regno] = saved_reg; + } else { + regs->regs[regno] = saved_reg; - regs->regs[regno] = saved_reg; + /* + * Signal a pseudo-step exception since we are stepping but + * tracer modifications to the registers may have rewound the + * state machine. + */ + tracehook_report_syscall_exit(regs, 1); + } } int syscall_trace_enter(struct pt_regs *regs) @@ -1675,12 +1686,14 @@ int syscall_trace_enter(struct pt_regs *regs) void syscall_trace_exit(struct pt_regs *regs) { + unsigned long flags = READ_ONCE(current_thread_info()->flags); + audit_syscall_exit(regs); - if (test_thread_flag(TIF_SYSCALL_TRACEPOINT)) + if (flags & _TIF_SYSCALL_TRACEPOINT) trace_sys_exit(regs, regs_return_value(regs)); - if (test_thread_flag(TIF_SYSCALL_TRACE)) + if (flags & (_TIF_SYSCALL_TRACE | _TIF_SINGLESTEP)) tracehook_report_syscall(regs, PTRACE_SYSCALL_EXIT); rseq_syscall(regs); @@ -1758,8 +1771,8 @@ static int valid_native_regs(struct user_pt_regs *regs) */ int valid_user_regs(struct user_pt_regs *regs, struct task_struct *task) { - if (!test_tsk_thread_flag(task, TIF_SINGLESTEP)) - regs->pstate &= ~DBG_SPSR_SS; + /* https://lore.kernel.org/lkml/20191118131525.GA4180@willie-the-truck */ + user_regs_reset_single_step(regs, task); if (is_compat_thread(task_thread_info(task))) return valid_compat_regs(regs); diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c index 5dcc942906db..ca565853dea6 100644 --- a/arch/arm64/kernel/signal.c +++ b/arch/arm64/kernel/signal.c @@ -798,7 +798,6 @@ static void setup_restart_syscall(struct pt_regs *regs) */ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs) { - struct task_struct *tsk = current; sigset_t *oldset = sigmask_to_save(); int usig = ksig->sig; int ret; @@ -822,14 +821,8 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs) */ ret |= !valid_user_regs(®s->user_regs, current); - /* - * Fast forward the stepping logic so we step into the signal - * handler. - */ - if (!ret) - user_fastforward_single_step(tsk); - - signal_setup_done(ret, ksig, 0); + /* Step into the signal handler if we are stepping */ + signal_setup_done(ret, ksig, test_thread_flag(TIF_SINGLESTEP)); } /* diff --git a/arch/arm64/kernel/sys_compat.c b/arch/arm64/kernel/sys_compat.c index 010212d35700..3ef9d0a3ac1d 100644 --- a/arch/arm64/kernel/sys_compat.c +++ b/arch/arm64/kernel/sys_compat.c @@ -19,6 +19,7 @@ */ #include <linux/compat.h> +#include <linux/cpufeature.h> #include <linux/personality.h> #include <linux/sched.h> #include <linux/sched/signal.h> @@ -28,6 +29,7 @@ #include <asm/cacheflush.h> #include <asm/system_misc.h> +#include <asm/tlbflush.h> #include <asm/unistd.h> static long @@ -41,6 +43,15 @@ __do_compat_cache_op(unsigned long start, unsigned long end) if (fatal_signal_pending(current)) return 0; + if (cpus_have_const_cap(ARM64_WORKAROUND_1542419)) { + /* + * The workaround requires an inner-shareable tlbi. + * We pick the reserved-ASID to minimise the impact. + */ + __tlbi(aside1is, __TLBI_VADDR(0, 0)); + dsb(ish); + } + ret = __flush_cache_user_range(start, start + chunk); if (ret) return ret; diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c index 871c739f060a..f2d2dbbbfca2 100644 --- a/arch/arm64/kernel/syscall.c +++ b/arch/arm64/kernel/syscall.c @@ -50,6 +50,9 @@ static void invoke_syscall(struct pt_regs *regs, unsigned int scno, ret = do_ni_syscall(regs, scno); } + if (is_compat_task()) + ret = lower_32_bits(ret); + regs->regs[0] = ret; } @@ -99,8 +102,8 @@ static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr, regs->syscallno = scno; cortex_a76_erratum_1463225_svc_handler(); + user_exit_irqoff(); local_daif_restore(DAIF_PROCCTX); - user_exit(); if (has_syscall_work(flags)) { /* set default errno for user-issued syscall(-1) */ @@ -121,7 +124,7 @@ static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr, if (!has_syscall_work(flags) && !IS_ENABLED(CONFIG_DEBUG_RSEQ)) { local_daif_mask(); flags = current_thread_info()->flags; - if (!has_syscall_work(flags)) { + if (!has_syscall_work(flags) && !(flags & _TIF_SINGLESTEP)) { /* * We're off to userspace, where interrupts are * always enabled after we restore the flags from diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c index 6106c49f84bc..655a308af9e3 100644 --- a/arch/arm64/kernel/topology.c +++ b/arch/arm64/kernel/topology.c @@ -272,21 +272,23 @@ void store_cpu_topology(unsigned int cpuid) if (mpidr & MPIDR_UP_BITMASK) return; - /* Create cpu topology mapping based on MPIDR. */ - if (mpidr & MPIDR_MT_BITMASK) { - /* Multiprocessor system : Multi-threads per core */ - cpuid_topo->thread_id = MPIDR_AFFINITY_LEVEL(mpidr, 0); - cpuid_topo->core_id = MPIDR_AFFINITY_LEVEL(mpidr, 1); - cpuid_topo->package_id = MPIDR_AFFINITY_LEVEL(mpidr, 2) | - MPIDR_AFFINITY_LEVEL(mpidr, 3) << 8; - } else { - /* Multiprocessor system : Single-thread per core */ - cpuid_topo->thread_id = -1; - cpuid_topo->core_id = MPIDR_AFFINITY_LEVEL(mpidr, 0); - cpuid_topo->package_id = MPIDR_AFFINITY_LEVEL(mpidr, 1) | - MPIDR_AFFINITY_LEVEL(mpidr, 2) << 8 | - MPIDR_AFFINITY_LEVEL(mpidr, 3) << 16; - } + /* + * This would be the place to create cpu topology based on MPIDR. + * + * However, it cannot be trusted to depict the actual topology; some + * pieces of the architecture enforce an artificial cap on Aff0 values + * (e.g. GICv3's ICC_SGI1R_EL1 limits it to 15), leading to an + * artificial cycling of Aff1, Aff2 and Aff3 values. IOW, these end up + * having absolutely no relationship to the actual underlying system + * topology, and cannot be reasonably used as core / package ID. + * + * If the MT bit is set, Aff0 *could* be used to define a thread ID, but + * we still wouldn't be able to obtain a sane core ID. This means we + * need to entirely ignore MPIDR for any topology deduction. + */ + cpuid_topo->thread_id = -1; + cpuid_topo->core_id = cpuid; + cpuid_topo->package_id = cpu_to_node(cpuid); pr_debug("CPU%u: cluster %d core %d thread %d mpidr %#016llx\n", cpuid, cpuid_topo->package_id, cpuid_topo->core_id, diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index c8dc3a3640e7..965595fe6804 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -481,6 +481,15 @@ static void ctr_read_handler(unsigned int esr, struct pt_regs *regs) int rt = (esr & ESR_ELx_SYS64_ISS_RT_MASK) >> ESR_ELx_SYS64_ISS_RT_SHIFT; unsigned long val = arm64_ftr_reg_user_value(&arm64_ftr_reg_ctrel0); + if (cpus_have_const_cap(ARM64_WORKAROUND_1542419)) { + /* Hide DIC so that we can trap the unnecessary maintenance...*/ + val &= ~BIT(CTR_DIC_SHIFT); + + /* ... and fake IminLine to reduce the number of traps. */ + val &= ~CTR_IMINLINE_MASK; + val |= (PAGE_SHIFT - 2) & CTR_IMINLINE_MASK; + } + pt_regs_write_reg(regs, rt, val); arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE); diff --git a/arch/arm64/kernel/vdso/gettimeofday.S b/arch/arm64/kernel/vdso/gettimeofday.S index 856fee6d3512..b6faf8b5d1fe 100644 --- a/arch/arm64/kernel/vdso/gettimeofday.S +++ b/arch/arm64/kernel/vdso/gettimeofday.S @@ -227,7 +227,7 @@ realtime: seqcnt_check fail=realtime get_ts_realtime res_sec=x10, res_nsec=x11, \ clock_nsec=x15, xtime_sec=x13, xtime_nsec=x14, nsec_to_sec=x9 - clock_gettime_return, shift=1 + clock_gettime_return shift=1 ALIGN monotonic: @@ -250,7 +250,7 @@ monotonic: clock_nsec=x15, xtime_sec=x13, xtime_nsec=x14, nsec_to_sec=x9 add_ts sec=x10, nsec=x11, ts_sec=x3, ts_nsec=x4, nsec_to_sec=x9 - clock_gettime_return, shift=1 + clock_gettime_return shift=1 ALIGN monotonic_raw: @@ -271,7 +271,7 @@ monotonic_raw: clock_nsec=x15, nsec_to_sec=x9 add_ts sec=x10, nsec=x11, ts_sec=x13, ts_nsec=x14, nsec_to_sec=x9 - clock_gettime_return, shift=1 + clock_gettime_return shift=1 ALIGN realtime_coarse: diff --git a/arch/arm64/kernel/vdso/vdso.lds.S b/arch/arm64/kernel/vdso/vdso.lds.S index beca249bc2f3..b3e6c4d5b75c 100644 --- a/arch/arm64/kernel/vdso/vdso.lds.S +++ b/arch/arm64/kernel/vdso/vdso.lds.S @@ -39,6 +39,13 @@ SECTIONS .gnu.version_d : { *(.gnu.version_d) } .gnu.version_r : { *(.gnu.version_r) } + /* + * Discard .note.gnu.property sections which are unused and have + * different alignment requirement from vDSO note sections. + */ + /DISCARD/ : { + *(.note.GNU-stack .note.gnu.property) + } .note : { *(.note.*) } :text :note . = ALIGN(16); @@ -59,7 +66,6 @@ SECTIONS PROVIDE(end = .); /DISCARD/ : { - *(.note.GNU-stack) *(.data .data.* .gnu.linkonce.d.* .sdata*) *(.bss .sbss .dynbss .dynsbss) } diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S index 74e469f8a850..69e7c8d4a00f 100644 --- a/arch/arm64/kernel/vmlinux.lds.S +++ b/arch/arm64/kernel/vmlinux.lds.S @@ -24,6 +24,13 @@ ENTRY(_text) jiffies = jiffies_64; + +#define HYPERVISOR_EXTABLE \ + . = ALIGN(SZ_8); \ + __start___kvm_ex_table = .; \ + *(__kvm_ex_table) \ + __stop___kvm_ex_table = .; + #define HYPERVISOR_TEXT \ /* \ * Align to 4 KB so that \ @@ -39,6 +46,7 @@ jiffies = jiffies_64; __hyp_idmap_text_end = .; \ __hyp_text_start = .; \ *(.hyp.text) \ + HYPERVISOR_EXTABLE \ __hyp_text_end = .; #define IDMAP_TEXT \ @@ -154,9 +162,6 @@ SECTIONS *(.altinstructions) __alt_instructions_end = .; } - .altinstr_replacement : { - *(.altinstr_replacement) - } . = ALIGN(PAGE_SIZE); __inittext_end = .; diff --git a/arch/arm64/kvm/debug.c b/arch/arm64/kvm/debug.c index 4e722d73a3c3..7fe195ef7c3f 100644 --- a/arch/arm64/kvm/debug.c +++ b/arch/arm64/kvm/debug.c @@ -80,6 +80,64 @@ void kvm_arm_init_debug(void) } /** + * kvm_arm_setup_mdcr_el2 - configure vcpu mdcr_el2 value + * + * @vcpu: the vcpu pointer + * + * This ensures we will trap access to: + * - Performance monitors (MDCR_EL2_TPM/MDCR_EL2_TPMCR) + * - Debug ROM Address (MDCR_EL2_TDRA) + * - OS related registers (MDCR_EL2_TDOSA) + * - Statistical profiler (MDCR_EL2_TPMS/MDCR_EL2_E2PB) + * - Self-hosted Trace Filter controls (MDCR_EL2_TTRF) + */ +static void kvm_arm_setup_mdcr_el2(struct kvm_vcpu *vcpu) +{ + /* + * This also clears MDCR_EL2_E2PB_MASK to disable guest access + * to the profiling buffer. + */ + vcpu->arch.mdcr_el2 = __this_cpu_read(mdcr_el2) & MDCR_EL2_HPMN_MASK; + vcpu->arch.mdcr_el2 |= (MDCR_EL2_TPM | + MDCR_EL2_TPMS | + MDCR_EL2_TTRF | + MDCR_EL2_TPMCR | + MDCR_EL2_TDRA | + MDCR_EL2_TDOSA); + + /* Is the VM being debugged by userspace? */ + if (vcpu->guest_debug) + /* Route all software debug exceptions to EL2 */ + vcpu->arch.mdcr_el2 |= MDCR_EL2_TDE; + + /* + * Trap debug register access when one of the following is true: + * - Userspace is using the hardware to debug the guest + * (KVM_GUESTDBG_USE_HW is set). + * - The guest is not using debug (KVM_ARM64_DEBUG_DIRTY is clear). + */ + if ((vcpu->guest_debug & KVM_GUESTDBG_USE_HW) || + !(vcpu->arch.flags & KVM_ARM64_DEBUG_DIRTY)) + vcpu->arch.mdcr_el2 |= MDCR_EL2_TDA; + + trace_kvm_arm_set_dreg32("MDCR_EL2", vcpu->arch.mdcr_el2); +} + +/** + * kvm_arm_vcpu_init_debug - setup vcpu debug traps + * + * @vcpu: the vcpu pointer + * + * Set vcpu initial mdcr_el2 value. + */ +void kvm_arm_vcpu_init_debug(struct kvm_vcpu *vcpu) +{ + preempt_disable(); + kvm_arm_setup_mdcr_el2(vcpu); + preempt_enable(); +} + +/** * kvm_arm_reset_debug_ptr - reset the debug ptr to point to the vcpu state */ @@ -94,12 +152,7 @@ void kvm_arm_reset_debug_ptr(struct kvm_vcpu *vcpu) * @vcpu: the vcpu pointer * * This is called before each entry into the hypervisor to setup any - * debug related registers. Currently this just ensures we will trap - * access to: - * - Performance monitors (MDCR_EL2_TPM/MDCR_EL2_TPMCR) - * - Debug ROM Address (MDCR_EL2_TDRA) - * - OS related registers (MDCR_EL2_TDOSA) - * - Statistical profiler (MDCR_EL2_TPMS/MDCR_EL2_E2PB) + * debug related registers. * * Additionally, KVM only traps guest accesses to the debug registers if * the guest is not actively using them (see the KVM_ARM64_DEBUG_DIRTY @@ -111,27 +164,14 @@ void kvm_arm_reset_debug_ptr(struct kvm_vcpu *vcpu) void kvm_arm_setup_debug(struct kvm_vcpu *vcpu) { - bool trap_debug = !(vcpu->arch.flags & KVM_ARM64_DEBUG_DIRTY); unsigned long mdscr, orig_mdcr_el2 = vcpu->arch.mdcr_el2; trace_kvm_arm_setup_debug(vcpu, vcpu->guest_debug); - /* - * This also clears MDCR_EL2_E2PB_MASK to disable guest access - * to the profiling buffer. - */ - vcpu->arch.mdcr_el2 = __this_cpu_read(mdcr_el2) & MDCR_EL2_HPMN_MASK; - vcpu->arch.mdcr_el2 |= (MDCR_EL2_TPM | - MDCR_EL2_TPMS | - MDCR_EL2_TPMCR | - MDCR_EL2_TDRA | - MDCR_EL2_TDOSA); + kvm_arm_setup_mdcr_el2(vcpu); /* Is Guest debugging in effect? */ if (vcpu->guest_debug) { - /* Route all software debug exceptions to EL2 */ - vcpu->arch.mdcr_el2 |= MDCR_EL2_TDE; - /* Save guest debug state */ save_guest_debug_regs(vcpu); @@ -185,7 +225,6 @@ void kvm_arm_setup_debug(struct kvm_vcpu *vcpu) vcpu->arch.debug_ptr = &vcpu->arch.external_debug_state; vcpu->arch.flags |= KVM_ARM64_DEBUG_DIRTY; - trap_debug = true; trace_kvm_arm_set_regset("BKPTS", get_num_brps(), &vcpu->arch.debug_ptr->dbg_bcr[0], @@ -200,10 +239,6 @@ void kvm_arm_setup_debug(struct kvm_vcpu *vcpu) BUG_ON(!vcpu->guest_debug && vcpu->arch.debug_ptr != &vcpu->arch.vcpu_debug_state); - /* Trap debug register access */ - if (trap_debug) - vcpu->arch.mdcr_el2 |= MDCR_EL2_TDA; - /* If KDE or MDE are set, perform a full save/restore cycle. */ if (vcpu_read_sys_reg(vcpu, MDSCR_EL1) & (DBG_MDSCR_KDE | DBG_MDSCR_MDE)) vcpu->arch.flags |= KVM_ARM64_DEBUG_DIRTY; @@ -212,7 +247,6 @@ void kvm_arm_setup_debug(struct kvm_vcpu *vcpu) if (has_vhe() && orig_mdcr_el2 != vcpu->arch.mdcr_el2) write_sysreg(vcpu->arch.mdcr_el2, mdcr_el2); - trace_kvm_arm_set_dreg32("MDCR_EL2", vcpu->arch.mdcr_el2); trace_kvm_arm_set_dreg32("MDSCR_EL1", vcpu_read_sys_reg(vcpu, MDSCR_EL1)); } diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c index a6c9fbaeaefc..870e594f95ed 100644 --- a/arch/arm64/kvm/guest.c +++ b/arch/arm64/kvm/guest.c @@ -179,6 +179,13 @@ static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) } memcpy((u32 *)regs + off, valp, KVM_REG_SIZE(reg->id)); + + if (*vcpu_cpsr(vcpu) & PSR_MODE32_BIT) { + int i; + + for (i = 0; i < 16; i++) + *vcpu_reg32(vcpu, i) = (u32)*vcpu_reg32(vcpu, i); + } out: return err; } diff --git a/arch/arm64/kvm/hyp-init.S b/arch/arm64/kvm/hyp-init.S index ea9225160786..6ef670f189bc 100644 --- a/arch/arm64/kvm/hyp-init.S +++ b/arch/arm64/kvm/hyp-init.S @@ -144,11 +144,15 @@ ENTRY(__kvm_handle_stub_hvc) 1: cmp x0, #HVC_RESET_VECTORS b.ne 1f -reset: + /* - * Reset kvm back to the hyp stub. Do not clobber x0-x4 in - * case we coming via HVC_SOFT_RESTART. + * Set the HVC_RESET_VECTORS return code before entering the common + * path so that we do not clobber x0-x2 in case we are coming via + * HVC_SOFT_RESTART. */ + mov x0, xzr +reset: + /* Reset kvm back to the hyp stub. */ mrs x5, sctlr_el2 ldr x6, =SCTLR_ELx_FLAGS bic x5, x5, x6 // Clear SCTL_M and etc @@ -159,7 +163,6 @@ reset: /* Install stub vectors */ adr_l x5, __hyp_stub_vectors msr vbar_el2, x5 - mov x0, xzr eret 1: /* Bad stub call */ diff --git a/arch/arm64/kvm/hyp/debug-sr.c b/arch/arm64/kvm/hyp/debug-sr.c index 50009766e5e5..3c5414633bb7 100644 --- a/arch/arm64/kvm/hyp/debug-sr.c +++ b/arch/arm64/kvm/hyp/debug-sr.c @@ -149,6 +149,21 @@ static void __hyp_text __debug_restore_state(struct kvm_vcpu *vcpu, write_sysreg(ctxt->sys_regs[MDCCINT_EL1], mdccint_el1); } +void __hyp_text __debug_save_host_buffers_nvhe(struct kvm_vcpu *vcpu) +{ + /* + * Non-VHE: Disable and flush SPE data generation + * VHE: The vcpu can run, but it can't hide. + */ + __debug_save_spe_nvhe(&vcpu->arch.host_debug_state.pmscr_el1); + +} + +void __hyp_text __debug_restore_host_buffers_nvhe(struct kvm_vcpu *vcpu) +{ + __debug_restore_spe_nvhe(vcpu->arch.host_debug_state.pmscr_el1); +} + void __hyp_text __debug_switch_to_guest(struct kvm_vcpu *vcpu) { struct kvm_cpu_context *host_ctxt; @@ -156,13 +171,6 @@ void __hyp_text __debug_switch_to_guest(struct kvm_vcpu *vcpu) struct kvm_guest_debug_arch *host_dbg; struct kvm_guest_debug_arch *guest_dbg; - /* - * Non-VHE: Disable and flush SPE data generation - * VHE: The vcpu can run, but it can't hide. - */ - if (!has_vhe()) - __debug_save_spe_nvhe(&vcpu->arch.host_debug_state.pmscr_el1); - if (!(vcpu->arch.flags & KVM_ARM64_DEBUG_DIRTY)) return; @@ -182,8 +190,6 @@ void __hyp_text __debug_switch_to_host(struct kvm_vcpu *vcpu) struct kvm_guest_debug_arch *host_dbg; struct kvm_guest_debug_arch *guest_dbg; - if (!has_vhe()) - __debug_restore_spe_nvhe(vcpu->arch.host_debug_state.pmscr_el1); if (!(vcpu->arch.flags & KVM_ARM64_DEBUG_DIRTY)) return; diff --git a/arch/arm64/kvm/hyp/entry.S b/arch/arm64/kvm/hyp/entry.S index fad1e164fe48..fc83e932afbe 100644 --- a/arch/arm64/kvm/hyp/entry.S +++ b/arch/arm64/kvm/hyp/entry.S @@ -17,6 +17,7 @@ #include <linux/linkage.h> +#include <asm/alternative.h> #include <asm/asm-offsets.h> #include <asm/assembler.h> #include <asm/fpsimdmacros.h> @@ -62,6 +63,20 @@ ENTRY(__guest_enter) // Store the host regs save_callee_saved_regs x1 + // Now the host state is stored if we have a pending RAS SError it must + // affect the host. If any asynchronous exception is pending we defer + // the guest entry. The DSB isn't necessary before v8.2 as any SError + // would be fatal. +alternative_if ARM64_HAS_RAS_EXTN + dsb nshst + isb +alternative_else_nop_endif + mrs x1, isr_el1 + cbz x1, 1f + mov x0, #ARM_EXCEPTION_IRQ + ret + +1: add x18, x0, #VCPU_CONTEXT // Restore guest regs x0-x17 @@ -148,18 +163,22 @@ alternative_endif // This is our single instruction exception window. A pending // SError is guaranteed to occur at the earliest when we unmask // it, and at the latest just after the ISB. - .global abort_guest_exit_start abort_guest_exit_start: isb - .global abort_guest_exit_end abort_guest_exit_end: + msr daifset, #4 // Mask aborts + ret + + _kvm_extable abort_guest_exit_start, 9997f + _kvm_extable abort_guest_exit_end, 9997f +9997: + msr daifset, #4 // Mask aborts + mov x0, #(1 << ARM_EXIT_WITH_SERROR_BIT) - // If the exception took place, restore the EL1 exception - // context so that we can report some information. - // Merge the exception code with the SError pending bit. - tbz x0, #ARM_EXIT_WITH_SERROR_BIT, 1f + // restore the EL1 exception context so that we can report some + // information. Merge the exception code with the SError pending bit. msr elr_el2, x2 msr esr_el2, x3 msr spsr_el2, x4 diff --git a/arch/arm64/kvm/hyp/hyp-entry.S b/arch/arm64/kvm/hyp/hyp-entry.S index 24b4fbafe3e4..ea063312bca1 100644 --- a/arch/arm64/kvm/hyp/hyp-entry.S +++ b/arch/arm64/kvm/hyp/hyp-entry.S @@ -26,6 +26,30 @@ #include <asm/kvm_mmu.h> #include <asm/mmu.h> +.macro save_caller_saved_regs_vect + /* x0 and x1 were saved in the vector entry */ + stp x2, x3, [sp, #-16]! + stp x4, x5, [sp, #-16]! + stp x6, x7, [sp, #-16]! + stp x8, x9, [sp, #-16]! + stp x10, x11, [sp, #-16]! + stp x12, x13, [sp, #-16]! + stp x14, x15, [sp, #-16]! + stp x16, x17, [sp, #-16]! +.endm + +.macro restore_caller_saved_regs_vect + ldp x16, x17, [sp], #16 + ldp x14, x15, [sp], #16 + ldp x12, x13, [sp], #16 + ldp x10, x11, [sp], #16 + ldp x8, x9, [sp], #16 + ldp x6, x7, [sp], #16 + ldp x4, x5, [sp], #16 + ldp x2, x3, [sp], #16 + ldp x0, x1, [sp], #16 +.endm + .text .pushsection .hyp.text, "ax" @@ -162,28 +186,24 @@ el1_error: mov x0, #ARM_EXCEPTION_EL1_SERROR b __guest_exit +el2_sync: + save_caller_saved_regs_vect + stp x29, x30, [sp, #-16]! + bl kvm_unexpected_el2_exception + ldp x29, x30, [sp], #16 + restore_caller_saved_regs_vect + + eret + el2_error: - ldp x0, x1, [sp], #16 + save_caller_saved_regs_vect + stp x29, x30, [sp, #-16]! + + bl kvm_unexpected_el2_exception + + ldp x29, x30, [sp], #16 + restore_caller_saved_regs_vect - /* - * Only two possibilities: - * 1) Either we come from the exit path, having just unmasked - * PSTATE.A: change the return code to an EL2 fault, and - * carry on, as we're already in a sane state to handle it. - * 2) Or we come from anywhere else, and that's a bug: we panic. - * - * For (1), x0 contains the original return code and x1 doesn't - * contain anything meaningful at that stage. We can reuse them - * as temp registers. - * For (2), who cares? - */ - mrs x0, elr_el2 - adr x1, abort_guest_exit_start - cmp x0, x1 - adr x1, abort_guest_exit_end - ccmp x0, x1, #4, ne - b.ne __hyp_panic - mov x0, #(1 << ARM_EXIT_WITH_SERROR_BIT) eret ENTRY(__hyp_do_panic) @@ -212,7 +232,6 @@ ENDPROC(\label) invalid_vector el2t_irq_invalid invalid_vector el2t_fiq_invalid invalid_vector el2t_error_invalid - invalid_vector el2h_sync_invalid invalid_vector el2h_irq_invalid invalid_vector el2h_fiq_invalid invalid_vector el1_fiq_invalid @@ -240,7 +259,7 @@ ENTRY(__kvm_hyp_vector) invalid_vect el2t_fiq_invalid // FIQ EL2t invalid_vect el2t_error_invalid // Error EL2t - invalid_vect el2h_sync_invalid // Synchronous EL2h + valid_vect el2_sync // Synchronous EL2h invalid_vect el2h_irq_invalid // IRQ EL2h invalid_vect el2h_fiq_invalid // FIQ EL2h valid_vect el2_error // Error EL2h diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c index f3978931aaf4..1d16ce0b7e0d 100644 --- a/arch/arm64/kvm/hyp/switch.c +++ b/arch/arm64/kvm/hyp/switch.c @@ -23,6 +23,7 @@ #include <kvm/arm_psci.h> #include <asm/cpufeature.h> +#include <asm/extable.h> #include <asm/kprobes.h> #include <asm/kvm_asm.h> #include <asm/kvm_emulate.h> @@ -34,6 +35,9 @@ #include <asm/processor.h> #include <asm/thread_info.h> +extern struct exception_table_entry __start___kvm_ex_table; +extern struct exception_table_entry __stop___kvm_ex_table; + /* Check whether the FP regs were dirtied while in the host-side run loop: */ static bool __hyp_text update_fp_enabled(struct kvm_vcpu *vcpu) { @@ -264,10 +268,10 @@ static bool __hyp_text __translate_far_to_hpfar(u64 far, u64 *hpfar) * saved the guest context yet, and we may return early... */ par = read_sysreg(par_el1); - asm volatile("at s1e1r, %0" : : "r" (far)); - isb(); - - tmp = read_sysreg(par_el1); + if (!__kvm_at("s1e1r", far)) + tmp = read_sysreg(par_el1); + else + tmp = 1; /* back to the guest */ write_sysreg(par, par_el1); if (unlikely(tmp & 1)) @@ -426,7 +430,7 @@ static bool __hyp_text fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code) kvm_vcpu_trap_get_fault_type(vcpu) == FSC_FAULT && kvm_vcpu_dabt_isvalid(vcpu) && !kvm_vcpu_dabt_isextabt(vcpu) && - !kvm_vcpu_dabt_iss1tw(vcpu); + !kvm_vcpu_abt_iss1tw(vcpu); if (valid) { int ret = __vgic_v2_perform_cpuif_access(vcpu); @@ -556,6 +560,7 @@ int __hyp_text __kvm_vcpu_run_nvhe(struct kvm_vcpu *vcpu) guest_ctxt = &vcpu->arch.ctxt; __sysreg_save_state_nvhe(host_ctxt); + __debug_save_host_buffers_nvhe(vcpu); __activate_traps(vcpu); __activate_vm(kern_hyp_va(vcpu->kvm)); @@ -595,11 +600,12 @@ int __hyp_text __kvm_vcpu_run_nvhe(struct kvm_vcpu *vcpu) if (vcpu->arch.flags & KVM_ARM64_FP_ENABLED) __fpsimd_save_fpexc32(vcpu); + __debug_switch_to_host(vcpu); /* * This must come after restoring the host sysregs, since a non-VHE * system may enable SPE here and make use of the TTBRs. */ - __debug_switch_to_host(vcpu); + __debug_restore_host_buffers_nvhe(vcpu); return exit_code; } @@ -626,7 +632,7 @@ static void __hyp_text __hyp_call_panic_nvhe(u64 spsr, u64 elr, u64 par, * making sure it is a kernel address and not a PC-relative * reference. */ - asm volatile("ldr %0, =__hyp_panic_string" : "=r" (str_va)); + asm volatile("ldr %0, =%1" : "=r" (str_va) : "S" (__hyp_panic_string)); __hyp_do_panic(str_va, spsr, elr, @@ -663,3 +669,30 @@ void __hyp_text __noreturn hyp_panic(struct kvm_cpu_context *host_ctxt) unreachable(); } + +asmlinkage void __hyp_text kvm_unexpected_el2_exception(void) +{ + unsigned long addr, fixup; + struct kvm_cpu_context *host_ctxt; + struct exception_table_entry *entry, *end; + unsigned long elr_el2 = read_sysreg(elr_el2); + + entry = hyp_symbol_addr(__start___kvm_ex_table); + end = hyp_symbol_addr(__stop___kvm_ex_table); + host_ctxt = __hyp_this_cpu_ptr(kvm_host_cpu_state); + + while (entry < end) { + addr = (unsigned long)&entry->insn + entry->insn; + fixup = (unsigned long)&entry->fixup + entry->fixup; + + if (addr != elr_el2) { + entry++; + continue; + } + + write_sysreg(fixup, elr_el2); + return; + } + + hyp_panic(host_ctxt); +} diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 0c073f3ca122..fe97b2ad82b9 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -619,6 +619,10 @@ static void reset_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { u64 pmcr, val; + /* No PMU available, PMCR_EL0 may UNDEF... */ + if (!kvm_arm_support_pmu_v3()) + return; + pmcr = read_sysreg(pmcr_el0); /* * Writable bits of PMCR_EL0 (ARMV8_PMU_PMCR_MASK) are reset to UNKNOWN @@ -1555,9 +1559,9 @@ static const struct sys_reg_desc cp14_regs[] = { { Op1( 0), CRn( 0), CRm( 1), Op2( 0), trap_raz_wi }, DBG_BCR_BVR_WCR_WVR(1), /* DBGDCCINT */ - { Op1( 0), CRn( 0), CRm( 2), Op2( 0), trap_debug32 }, + { Op1( 0), CRn( 0), CRm( 2), Op2( 0), trap_debug32, NULL, cp14_DBGDCCINT }, /* DBGDSCRext */ - { Op1( 0), CRn( 0), CRm( 2), Op2( 2), trap_debug32 }, + { Op1( 0), CRn( 0), CRm( 2), Op2( 2), trap_debug32, NULL, cp14_DBGDSCRext }, DBG_BCR_BVR_WCR_WVR(2), /* DBGDTR[RT]Xint */ { Op1( 0), CRn( 0), CRm( 3), Op2( 0), trap_raz_wi }, @@ -1572,7 +1576,7 @@ static const struct sys_reg_desc cp14_regs[] = { { Op1( 0), CRn( 0), CRm( 6), Op2( 2), trap_raz_wi }, DBG_BCR_BVR_WCR_WVR(6), /* DBGVCR */ - { Op1( 0), CRn( 0), CRm( 7), Op2( 0), trap_debug32 }, + { Op1( 0), CRn( 0), CRm( 7), Op2( 0), trap_debug32, NULL, cp14_DBGVCR }, DBG_BCR_BVR_WCR_WVR(7), DBG_BCR_BVR_WCR_WVR(8), DBG_BCR_BVR_WCR_WVR(9), @@ -1661,6 +1665,7 @@ static const struct sys_reg_desc cp15_regs[] = { { Op1( 0), CRn( 2), CRm( 0), Op2( 0), access_vm_reg, NULL, c2_TTBR0 }, { Op1( 0), CRn( 2), CRm( 0), Op2( 1), access_vm_reg, NULL, c2_TTBR1 }, { Op1( 0), CRn( 2), CRm( 0), Op2( 2), access_vm_reg, NULL, c2_TTBCR }, + { Op1( 0), CRn( 2), CRm( 0), Op2( 3), access_vm_reg, NULL, c2_TTBCR2 }, { Op1( 0), CRn( 3), CRm( 0), Op2( 0), access_vm_reg, NULL, c3_DACR }, { Op1( 0), CRn( 5), CRm( 0), Op2( 0), access_vm_reg, NULL, c5_DFSR }, { Op1( 0), CRn( 5), CRm( 0), Op2( 1), access_vm_reg, NULL, c5_IFSR }, diff --git a/arch/arm64/lib/memcpy.S b/arch/arm64/lib/memcpy.S index 67613937711f..dfedd4ab1a76 100644 --- a/arch/arm64/lib/memcpy.S +++ b/arch/arm64/lib/memcpy.S @@ -68,9 +68,8 @@ stp \ptr, \regB, [\regC], \val .endm - .weak memcpy ENTRY(__memcpy) -ENTRY(memcpy) +WEAK(memcpy) #include "copy_template.S" ret ENDPIPROC(memcpy) diff --git a/arch/arm64/lib/memmove.S b/arch/arm64/lib/memmove.S index a5a4459013b1..e3de8f05c21a 100644 --- a/arch/arm64/lib/memmove.S +++ b/arch/arm64/lib/memmove.S @@ -57,9 +57,8 @@ C_h .req x12 D_l .req x13 D_h .req x14 - .weak memmove ENTRY(__memmove) -ENTRY(memmove) +WEAK(memmove) cmp dstin, src b.lo __memcpy add tmp1, src, count diff --git a/arch/arm64/lib/memset.S b/arch/arm64/lib/memset.S index f2670a9f218c..316263c47c00 100644 --- a/arch/arm64/lib/memset.S +++ b/arch/arm64/lib/memset.S @@ -54,9 +54,8 @@ dst .req x8 tmp3w .req w9 tmp3 .req x9 - .weak memset ENTRY(__memset) -ENTRY(memset) +WEAK(memset) mov dst, dstin /* Preserve return value. */ and A_lw, val, #255 orr A_lw, A_lw, A_lw, lsl #8 diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c index f58ea503ad01..1d7656761316 100644 --- a/arch/arm64/mm/hugetlbpage.c +++ b/arch/arm64/mm/hugetlbpage.c @@ -218,6 +218,8 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, ptep = (pte_t *)pudp; } else if (sz == (PAGE_SIZE * CONT_PTES)) { pmdp = pmd_alloc(mm, pudp, addr); + if (!pmdp) + return NULL; WARN_ON(addr & (sz - 1)); /* diff --git a/arch/arm64/mm/numa.c b/arch/arm64/mm/numa.c index 54529b4ed513..15eaf1e09d0c 100644 --- a/arch/arm64/mm/numa.c +++ b/arch/arm64/mm/numa.c @@ -58,7 +58,11 @@ EXPORT_SYMBOL(node_to_cpumask_map); */ const struct cpumask *cpumask_of_node(int node) { - if (WARN_ON(node >= nr_node_ids)) + + if (node == NUMA_NO_NODE) + return cpu_all_mask; + + if (WARN_ON(node < 0 || node >= nr_node_ids)) return cpu_none_mask; if (WARN_ON(node_to_cpumask_map[node] == NULL)) diff --git a/arch/h8300/kernel/asm-offsets.c b/arch/h8300/kernel/asm-offsets.c index 85e60509f0a8..d4b53af657c8 100644 --- a/arch/h8300/kernel/asm-offsets.c +++ b/arch/h8300/kernel/asm-offsets.c @@ -63,6 +63,9 @@ int main(void) OFFSET(TI_FLAGS, thread_info, flags); OFFSET(TI_CPU, thread_info, cpu); OFFSET(TI_PRE, thread_info, preempt_count); +#ifdef CONFIG_PREEMPTION + DEFINE(TI_PRE_COUNT, offsetof(struct thread_info, preempt_count)); +#endif return 0; } diff --git a/arch/hexagon/include/asm/io.h b/arch/hexagon/include/asm/io.h index e17262ad125e..bd429d6a3163 100644 --- a/arch/hexagon/include/asm/io.h +++ b/arch/hexagon/include/asm/io.h @@ -186,16 +186,10 @@ static inline void writel(u32 data, volatile void __iomem *addr) #define mmiowb() -/* - * Need an mtype somewhere in here, for cache type deals? - * This is probably too long for an inline. - */ -void __iomem *ioremap_nocache(unsigned long phys_addr, unsigned long size); +void __iomem *ioremap(unsigned long phys_addr, unsigned long size); +#define ioremap_nocache ioremap +#define ioremap_uc(X, Y) ioremap((X), (Y)) -static inline void __iomem *ioremap(unsigned long phys_addr, unsigned long size) -{ - return ioremap_nocache(phys_addr, size); -} static inline void iounmap(volatile void __iomem *addr) { diff --git a/arch/hexagon/kernel/hexagon_ksyms.c b/arch/hexagon/kernel/hexagon_ksyms.c index aa248f595431..d13d4a06ee38 100644 --- a/arch/hexagon/kernel/hexagon_ksyms.c +++ b/arch/hexagon/kernel/hexagon_ksyms.c @@ -33,7 +33,7 @@ EXPORT_SYMBOL(__vmgetie); EXPORT_SYMBOL(__vmsetie); EXPORT_SYMBOL(__vmyield); EXPORT_SYMBOL(empty_zero_page); -EXPORT_SYMBOL(ioremap_nocache); +EXPORT_SYMBOL(ioremap); EXPORT_SYMBOL(memcpy); EXPORT_SYMBOL(memset); diff --git a/arch/hexagon/mm/ioremap.c b/arch/hexagon/mm/ioremap.c index d27d67224046..370ade265e58 100644 --- a/arch/hexagon/mm/ioremap.c +++ b/arch/hexagon/mm/ioremap.c @@ -22,7 +22,7 @@ #include <linux/vmalloc.h> #include <linux/mm.h> -void __iomem *ioremap_nocache(unsigned long phys_addr, unsigned long size) +void __iomem *ioremap(unsigned long phys_addr, unsigned long size) { unsigned long last_addr, addr; unsigned long offset = phys_addr & ~PAGE_MASK; diff --git a/arch/ia64/configs/zx1_defconfig b/arch/ia64/configs/zx1_defconfig index b504c8e2fd52..7fd4176ea0f6 100644 --- a/arch/ia64/configs/zx1_defconfig +++ b/arch/ia64/configs/zx1_defconfig @@ -36,7 +36,6 @@ CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=y CONFIG_CHR_DEV_OSST=y CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=y CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_LOGGING=y diff --git a/arch/ia64/include/asm/module.h b/arch/ia64/include/asm/module.h index f319144260ce..9fbf32e6e881 100644 --- a/arch/ia64/include/asm/module.h +++ b/arch/ia64/include/asm/module.h @@ -14,16 +14,20 @@ struct elf64_shdr; /* forward declration */ struct mod_arch_specific { + /* Used only at module load time. */ struct elf64_shdr *core_plt; /* core PLT section */ struct elf64_shdr *init_plt; /* init PLT section */ struct elf64_shdr *got; /* global offset table */ struct elf64_shdr *opd; /* official procedure descriptors */ struct elf64_shdr *unwind; /* unwind-table section */ unsigned long gp; /* global-pointer for module */ + unsigned int next_got_entry; /* index of next available got entry */ + /* Used at module run and cleanup time. */ void *core_unw_table; /* core unwind-table cookie returned by unwinder */ void *init_unw_table; /* init unwind-table cookie returned by unwinder */ - unsigned int next_got_entry; /* index of next available got entry */ + void *opd_addr; /* symbolize uses .opd to get to actual function */ + unsigned long opd_size; }; #define MODULE_PROC_FAMILY "ia64" diff --git a/arch/ia64/include/asm/ptrace.h b/arch/ia64/include/asm/ptrace.h index 7ff574d56429..f31e07fc936d 100644 --- a/arch/ia64/include/asm/ptrace.h +++ b/arch/ia64/include/asm/ptrace.h @@ -54,8 +54,7 @@ static inline unsigned long user_stack_pointer(struct pt_regs *regs) { - /* FIXME: should this be bspstore + nr_dirty regs? */ - return regs->ar_bspstore; + return regs->r12; } static inline int is_syscall_success(struct pt_regs *regs) @@ -79,11 +78,6 @@ static inline long regs_return_value(struct pt_regs *regs) unsigned long __ip = instruction_pointer(regs); \ (__ip & ~3UL) + ((__ip & 3UL) << 2); \ }) -/* - * Why not default? Because user_stack_pointer() on ia64 gives register - * stack backing store instead... - */ -#define current_user_stack_pointer() (current_pt_regs()->r12) /* given a pointer to a task_struct, return the user's pt_regs */ # define task_pt_regs(t) (((struct pt_regs *) ((char *) (t) + IA64_STK_OFFSET)) - 1) diff --git a/arch/ia64/include/asm/syscall.h b/arch/ia64/include/asm/syscall.h index 1d0b875fec44..ec909eec0b4c 100644 --- a/arch/ia64/include/asm/syscall.h +++ b/arch/ia64/include/asm/syscall.h @@ -35,7 +35,7 @@ static inline void syscall_rollback(struct task_struct *task, static inline long syscall_get_error(struct task_struct *task, struct pt_regs *regs) { - return regs->r10 == -1 ? regs->r8:0; + return regs->r10 == -1 ? -regs->r8:0; } static inline long syscall_get_return_value(struct task_struct *task, diff --git a/arch/ia64/kernel/Makefile b/arch/ia64/kernel/Makefile index d0c0ccdd656a..03ee3ff3cefa 100644 --- a/arch/ia64/kernel/Makefile +++ b/arch/ia64/kernel/Makefile @@ -42,7 +42,7 @@ obj-y += esi_stub.o # must be in kernel proper endif obj-$(CONFIG_INTEL_IOMMU) += pci-dma.o -obj-$(CONFIG_BINFMT_ELF) += elfcore.o +obj-$(CONFIG_ELF_CORE) += elfcore.o # fp_emulate() expects f2-f5,f16-f31 to contain the user-level state. CFLAGS_traps.o += -mfixed-range=f2-f5,f16-f31 diff --git a/arch/ia64/kernel/err_inject.c b/arch/ia64/kernel/err_inject.c index 8b5b8e6bc9d9..dd5bfed52031 100644 --- a/arch/ia64/kernel/err_inject.c +++ b/arch/ia64/kernel/err_inject.c @@ -59,7 +59,7 @@ show_##name(struct device *dev, struct device_attribute *attr, \ char *buf) \ { \ u32 cpu=dev->id; \ - return sprintf(buf, "%lx\n", name[cpu]); \ + return sprintf(buf, "%llx\n", name[cpu]); \ } #define store(name) \ @@ -86,9 +86,9 @@ store_call_start(struct device *dev, struct device_attribute *attr, #ifdef ERR_INJ_DEBUG printk(KERN_DEBUG "pal_mc_err_inject for cpu%d:\n", cpu); - printk(KERN_DEBUG "err_type_info=%lx,\n", err_type_info[cpu]); - printk(KERN_DEBUG "err_struct_info=%lx,\n", err_struct_info[cpu]); - printk(KERN_DEBUG "err_data_buffer=%lx, %lx, %lx.\n", + printk(KERN_DEBUG "err_type_info=%llx,\n", err_type_info[cpu]); + printk(KERN_DEBUG "err_struct_info=%llx,\n", err_struct_info[cpu]); + printk(KERN_DEBUG "err_data_buffer=%llx, %llx, %llx.\n", err_data_buffer[cpu].data1, err_data_buffer[cpu].data2, err_data_buffer[cpu].data3); @@ -117,8 +117,8 @@ store_call_start(struct device *dev, struct device_attribute *attr, #ifdef ERR_INJ_DEBUG printk(KERN_DEBUG "Returns: status=%d,\n", (int)status[cpu]); - printk(KERN_DEBUG "capabilities=%lx,\n", capabilities[cpu]); - printk(KERN_DEBUG "resources=%lx\n", resources[cpu]); + printk(KERN_DEBUG "capabilities=%llx,\n", capabilities[cpu]); + printk(KERN_DEBUG "resources=%llx\n", resources[cpu]); #endif return size; } @@ -131,7 +131,7 @@ show_virtual_to_phys(struct device *dev, struct device_attribute *attr, char *buf) { unsigned int cpu=dev->id; - return sprintf(buf, "%lx\n", phys_addr[cpu]); + return sprintf(buf, "%llx\n", phys_addr[cpu]); } static ssize_t @@ -145,7 +145,7 @@ store_virtual_to_phys(struct device *dev, struct device_attribute *attr, ret = get_user_pages_fast(virt_addr, 1, FOLL_WRITE, NULL); if (ret<=0) { #ifdef ERR_INJ_DEBUG - printk("Virtual address %lx is not existing.\n",virt_addr); + printk("Virtual address %llx is not existing.\n", virt_addr); #endif return -EINVAL; } @@ -163,7 +163,7 @@ show_err_data_buffer(struct device *dev, { unsigned int cpu=dev->id; - return sprintf(buf, "%lx, %lx, %lx\n", + return sprintf(buf, "%llx, %llx, %llx\n", err_data_buffer[cpu].data1, err_data_buffer[cpu].data2, err_data_buffer[cpu].data3); @@ -178,13 +178,13 @@ store_err_data_buffer(struct device *dev, int ret; #ifdef ERR_INJ_DEBUG - printk("write err_data_buffer=[%lx,%lx,%lx] on cpu%d\n", + printk("write err_data_buffer=[%llx,%llx,%llx] on cpu%d\n", err_data_buffer[cpu].data1, err_data_buffer[cpu].data2, err_data_buffer[cpu].data3, cpu); #endif - ret=sscanf(buf, "%lx, %lx, %lx", + ret = sscanf(buf, "%llx, %llx, %llx", &err_data_buffer[cpu].data1, &err_data_buffer[cpu].data2, &err_data_buffer[cpu].data3); diff --git a/arch/ia64/kernel/kprobes.c b/arch/ia64/kernel/kprobes.c index aa41bd5cf9b7..8207b897b49d 100644 --- a/arch/ia64/kernel/kprobes.c +++ b/arch/ia64/kernel/kprobes.c @@ -409,83 +409,9 @@ static void kretprobe_trampoline(void) { } -/* - * At this point the target function has been tricked into - * returning into our trampoline. Lookup the associated instance - * and then: - * - call the handler function - * - cleanup by marking the instance as unused - * - long jump back to the original return address - */ int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) { - struct kretprobe_instance *ri = NULL; - struct hlist_head *head, empty_rp; - struct hlist_node *tmp; - unsigned long flags, orig_ret_address = 0; - unsigned long trampoline_address = - ((struct fnptr *)kretprobe_trampoline)->ip; - - INIT_HLIST_HEAD(&empty_rp); - kretprobe_hash_lock(current, &head, &flags); - - /* - * It is possible to have multiple instances associated with a given - * task either because an multiple functions in the call path - * have a return probe installed on them, and/or more than one return - * return probe was registered for a target function. - * - * We can handle this because: - * - instances are always inserted at the head of the list - * - when multiple return probes are registered for the same - * function, the first instance's ret_addr will point to the - * real return address, and all the rest will point to - * kretprobe_trampoline - */ - hlist_for_each_entry_safe(ri, tmp, head, hlist) { - if (ri->task != current) - /* another task is sharing our hash bucket */ - continue; - - orig_ret_address = (unsigned long)ri->ret_addr; - if (orig_ret_address != trampoline_address) - /* - * This is the real return address. Any other - * instances associated with this task are for - * other calls deeper on the call stack - */ - break; - } - - regs->cr_iip = orig_ret_address; - - hlist_for_each_entry_safe(ri, tmp, head, hlist) { - if (ri->task != current) - /* another task is sharing our hash bucket */ - continue; - - if (ri->rp && ri->rp->handler) - ri->rp->handler(ri, regs); - - orig_ret_address = (unsigned long)ri->ret_addr; - recycle_rp_inst(ri, &empty_rp); - - if (orig_ret_address != trampoline_address) - /* - * This is the real return address. Any other - * instances associated with this task are for - * other calls deeper on the call stack - */ - break; - } - kretprobe_assert(ri, orig_ret_address, trampoline_address); - - kretprobe_hash_unlock(current, &flags); - - hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) { - hlist_del(&ri->hlist); - kfree(ri); - } + regs->cr_iip = __kretprobe_trampoline_handler(regs, kretprobe_trampoline, NULL); /* * By returning a non-zero value, we are telling * kprobe_handler() that we don't want the post_handler @@ -498,6 +424,7 @@ void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs) { ri->ret_addr = (kprobe_opcode_t *)regs->b0; + ri->fp = NULL; /* Replace the return addr with trampoline addr */ regs->b0 = ((struct fnptr *)kretprobe_trampoline)->ip; diff --git a/arch/ia64/kernel/mca.c b/arch/ia64/kernel/mca.c index 6115464d5f03..d7400b2844f1 100644 --- a/arch/ia64/kernel/mca.c +++ b/arch/ia64/kernel/mca.c @@ -1860,7 +1860,7 @@ ia64_mca_cpu_init(void *cpu_data) data = mca_bootmem(); first_time = 0; } else - data = (void *)__get_free_pages(GFP_KERNEL, + data = (void *)__get_free_pages(GFP_ATOMIC, get_order(sz)); if (!data) panic("Could not allocate MCA memory for cpu %d\n", diff --git a/arch/ia64/kernel/module.c b/arch/ia64/kernel/module.c index 1a42ba885188..ee693c8cec49 100644 --- a/arch/ia64/kernel/module.c +++ b/arch/ia64/kernel/module.c @@ -905,9 +905,31 @@ register_unwind_table (struct module *mod) int module_finalize (const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs, struct module *mod) { + struct mod_arch_specific *mas = &mod->arch; + DEBUGP("%s: init: entry=%p\n", __func__, mod->init); - if (mod->arch.unwind) + if (mas->unwind) register_unwind_table(mod); + + /* + * ".opd" was already relocated to the final destination. Store + * it's address for use in symbolizer. + */ + mas->opd_addr = (void *)mas->opd->sh_addr; + mas->opd_size = mas->opd->sh_size; + + /* + * Module relocation was already done at this point. Section + * headers are about to be deleted. Wipe out load-time context. + */ + mas->core_plt = NULL; + mas->init_plt = NULL; + mas->got = NULL; + mas->opd = NULL; + mas->unwind = NULL; + mas->gp = 0; + mas->next_got_entry = 0; + return 0; } @@ -926,10 +948,9 @@ module_arch_cleanup (struct module *mod) void *dereference_module_function_descriptor(struct module *mod, void *ptr) { - Elf64_Shdr *opd = mod->arch.opd; + struct mod_arch_specific *mas = &mod->arch; - if (ptr < (void *)opd->sh_addr || - ptr >= (void *)(opd->sh_addr + opd->sh_size)) + if (ptr < mas->opd_addr || ptr >= mas->opd_addr + mas->opd_size) return ptr; return dereference_function_descriptor(ptr); diff --git a/arch/ia64/kernel/ptrace.c b/arch/ia64/kernel/ptrace.c index 427cd565fd61..799400287cda 100644 --- a/arch/ia64/kernel/ptrace.c +++ b/arch/ia64/kernel/ptrace.c @@ -2147,27 +2147,39 @@ static void syscall_get_set_args_cb(struct unw_frame_info *info, void *data) { struct syscall_get_set_args *args = data; struct pt_regs *pt = args->regs; - unsigned long *krbs, cfm, ndirty; + unsigned long *krbs, cfm, ndirty, nlocals, nouts; int i, count; if (unw_unwind_to_user(info) < 0) return; + /* + * We get here via a few paths: + * - break instruction: cfm is shared with caller. + * syscall args are in out= regs, locals are non-empty. + * - epsinstruction: cfm is set by br.call + * locals don't exist. + * + * For both cases argguments are reachable in cfm.sof - cfm.sol. + * CFM: [ ... | sor: 17..14 | sol : 13..7 | sof : 6..0 ] + */ cfm = pt->cr_ifs; + nlocals = (cfm >> 7) & 0x7f; /* aka sol */ + nouts = (cfm & 0x7f) - nlocals; /* aka sof - sol */ krbs = (unsigned long *)info->task + IA64_RBS_OFFSET/8; ndirty = ia64_rse_num_regs(krbs, krbs + (pt->loadrs >> 19)); count = 0; if (in_syscall(pt)) - count = min_t(int, args->n, cfm & 0x7f); + count = min_t(int, args->n, nouts); + /* Iterate over outs. */ for (i = 0; i < count; i++) { + int j = ndirty + nlocals + i + args->i; if (args->rw) - *ia64_rse_skip_regs(krbs, ndirty + i + args->i) = - args->args[i]; + *ia64_rse_skip_regs(krbs, j) = args->args[i]; else - args->args[i] = *ia64_rse_skip_regs(krbs, - ndirty + i + args->i); + args->args[i] = *ia64_rse_skip_regs(krbs, j); } if (!args->rw) { diff --git a/arch/ia64/mm/discontig.c b/arch/ia64/mm/discontig.c index 1928d5719e41..db3104c9fac5 100644 --- a/arch/ia64/mm/discontig.c +++ b/arch/ia64/mm/discontig.c @@ -96,7 +96,7 @@ static int __init build_node_maps(unsigned long start, unsigned long len, * acpi_boot_init() (which builds the node_to_cpu_mask array) hasn't been * called yet. Note that node 0 will also count all non-existent cpus. */ -static int __meminit early_nr_cpus_node(int node) +static int early_nr_cpus_node(int node) { int cpu, n = 0; @@ -111,7 +111,7 @@ static int __meminit early_nr_cpus_node(int node) * compute_pernodesize - compute size of pernode data * @node: the node id. */ -static unsigned long __meminit compute_pernodesize(int node) +static unsigned long compute_pernodesize(int node) { unsigned long pernodesize = 0, cpus; @@ -371,7 +371,7 @@ static void __init reserve_pernode_space(void) } } -static void __meminit scatter_node_data(void) +static void scatter_node_data(void) { pg_data_t **dst; int node; diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c index 79e5cc70f1fd..561e2573bd34 100644 --- a/arch/ia64/mm/init.c +++ b/arch/ia64/mm/init.c @@ -499,7 +499,7 @@ virtual_memmap_init(u64 start, u64 end, void *arg) if (map_start < map_end) memmap_init_zone((unsigned long)(map_end - map_start), args->nid, args->zone, page_to_pfn(map_start), - MEMMAP_EARLY, NULL); + MEMINIT_EARLY, NULL); return 0; } @@ -508,8 +508,8 @@ memmap_init (unsigned long size, int nid, unsigned long zone, unsigned long start_pfn) { if (!vmem_map) { - memmap_init_zone(size, nid, zone, start_pfn, MEMMAP_EARLY, - NULL); + memmap_init_zone(size, nid, zone, start_pfn, + MEMINIT_EARLY, NULL); } else { struct page *start; struct memmap_init_callback_data args; diff --git a/arch/ia64/scripts/unwcheck.py b/arch/ia64/scripts/unwcheck.py index c55276e31b6b..bfd1b671e35f 100644 --- a/arch/ia64/scripts/unwcheck.py +++ b/arch/ia64/scripts/unwcheck.py @@ -1,4 +1,4 @@ -#!/usr/bin/python +#!/usr/bin/env python # SPDX-License-Identifier: GPL-2.0 # # Usage: unwcheck.py FILE diff --git a/arch/m68k/coldfire/pci.c b/arch/m68k/coldfire/pci.c index 62b0eb6cf69a..84eab0f5e00a 100644 --- a/arch/m68k/coldfire/pci.c +++ b/arch/m68k/coldfire/pci.c @@ -216,8 +216,10 @@ static int __init mcf_pci_init(void) /* Keep a virtual mapping to IO/config space active */ iospace = (unsigned long) ioremap(PCI_IO_PA, PCI_IO_SIZE); - if (iospace == 0) + if (iospace == 0) { + pci_free_host_bridge(bridge); return -ENODEV; + } pr_info("Coldfire: PCI IO/config window mapped to 0x%x\n", (u32) iospace); diff --git a/arch/m68k/configs/amiga_defconfig b/arch/m68k/configs/amiga_defconfig index 93a3c3c0238c..bd55d9ba7049 100644 --- a/arch/m68k/configs/amiga_defconfig +++ b/arch/m68k/configs/amiga_defconfig @@ -341,7 +341,6 @@ CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=m CONFIG_CHR_DEV_OSST=m CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=m CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_SAS_ATTRS=m diff --git a/arch/m68k/configs/apollo_defconfig b/arch/m68k/configs/apollo_defconfig index e3d0efd6397d..83789fd6780d 100644 --- a/arch/m68k/configs/apollo_defconfig +++ b/arch/m68k/configs/apollo_defconfig @@ -328,7 +328,6 @@ CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=m CONFIG_CHR_DEV_OSST=m CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=m CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_SAS_ATTRS=m diff --git a/arch/m68k/configs/atari_defconfig b/arch/m68k/configs/atari_defconfig index 75ac0c76e884..db0c0fa6075b 100644 --- a/arch/m68k/configs/atari_defconfig +++ b/arch/m68k/configs/atari_defconfig @@ -336,7 +336,6 @@ CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=m CONFIG_CHR_DEV_OSST=m CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=m CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_SAS_ATTRS=m diff --git a/arch/m68k/configs/bvme6000_defconfig b/arch/m68k/configs/bvme6000_defconfig index c6e492700188..6a64904a5a4c 100644 --- a/arch/m68k/configs/bvme6000_defconfig +++ b/arch/m68k/configs/bvme6000_defconfig @@ -326,7 +326,6 @@ CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=m CONFIG_CHR_DEV_OSST=m CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=m CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_SAS_ATTRS=m diff --git a/arch/m68k/configs/hp300_defconfig b/arch/m68k/configs/hp300_defconfig index b00d1c477432..dcfa9a3d1a0b 100644 --- a/arch/m68k/configs/hp300_defconfig +++ b/arch/m68k/configs/hp300_defconfig @@ -328,7 +328,6 @@ CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=m CONFIG_CHR_DEV_OSST=m CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=m CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_SAS_ATTRS=m diff --git a/arch/m68k/configs/mac_defconfig b/arch/m68k/configs/mac_defconfig index 85cac3770d89..916dbe2d61c3 100644 --- a/arch/m68k/configs/mac_defconfig +++ b/arch/m68k/configs/mac_defconfig @@ -335,7 +335,6 @@ CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=m CONFIG_CHR_DEV_OSST=m CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=m CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_SAS_ATTRS=m diff --git a/arch/m68k/configs/multi_defconfig b/arch/m68k/configs/multi_defconfig index b3a5d1e99d27..2f5c02089574 100644 --- a/arch/m68k/configs/multi_defconfig +++ b/arch/m68k/configs/multi_defconfig @@ -358,7 +358,6 @@ CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=m CONFIG_CHR_DEV_OSST=m CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=m CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_SAS_ATTRS=m diff --git a/arch/m68k/configs/mvme147_defconfig b/arch/m68k/configs/mvme147_defconfig index 0ca22608453f..40240c32418e 100644 --- a/arch/m68k/configs/mvme147_defconfig +++ b/arch/m68k/configs/mvme147_defconfig @@ -325,7 +325,6 @@ CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=m CONFIG_CHR_DEV_OSST=m CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=m CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_SAS_ATTRS=m diff --git a/arch/m68k/configs/mvme16x_defconfig b/arch/m68k/configs/mvme16x_defconfig index 8e3d10d12d9c..34b7038f7de7 100644 --- a/arch/m68k/configs/mvme16x_defconfig +++ b/arch/m68k/configs/mvme16x_defconfig @@ -326,7 +326,6 @@ CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=m CONFIG_CHR_DEV_OSST=m CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=m CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_SAS_ATTRS=m diff --git a/arch/m68k/configs/q40_defconfig b/arch/m68k/configs/q40_defconfig index ff7e653ec7fa..6375a7c86471 100644 --- a/arch/m68k/configs/q40_defconfig +++ b/arch/m68k/configs/q40_defconfig @@ -333,7 +333,6 @@ CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=m CONFIG_CHR_DEV_OSST=m CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=m CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_SAS_ATTRS=m diff --git a/arch/m68k/configs/sun3_defconfig b/arch/m68k/configs/sun3_defconfig index 612cf46f6d0c..0c38799e9a67 100644 --- a/arch/m68k/configs/sun3_defconfig +++ b/arch/m68k/configs/sun3_defconfig @@ -323,7 +323,6 @@ CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=m CONFIG_CHR_DEV_OSST=m CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=m CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_SAS_ATTRS=m diff --git a/arch/m68k/configs/sun3x_defconfig b/arch/m68k/configs/sun3x_defconfig index a6a7bb6dc3fd..8180ef6b6983 100644 --- a/arch/m68k/configs/sun3x_defconfig +++ b/arch/m68k/configs/sun3x_defconfig @@ -323,7 +323,6 @@ CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=m CONFIG_CHR_DEV_OSST=m CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=m CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_SAS_ATTRS=m diff --git a/arch/m68k/include/asm/m53xxacr.h b/arch/m68k/include/asm/m53xxacr.h index 9138a624c5c8..692f90e7fecc 100644 --- a/arch/m68k/include/asm/m53xxacr.h +++ b/arch/m68k/include/asm/m53xxacr.h @@ -89,9 +89,9 @@ * coherency though in all cases. And for copyback caches we will need * to push cached data as well. */ -#define CACHE_INIT CACR_CINVA -#define CACHE_INVALIDATE CACR_CINVA -#define CACHE_INVALIDATED CACR_CINVA +#define CACHE_INIT (CACHE_MODE + CACR_CINVA - CACR_EC) +#define CACHE_INVALIDATE (CACHE_MODE + CACR_CINVA) +#define CACHE_INVALIDATED (CACHE_MODE + CACR_CINVA) #define ACR0_MODE ((CONFIG_RAMBASE & 0xff000000) + \ (0x000f0000) + \ diff --git a/arch/m68k/include/asm/mac_via.h b/arch/m68k/include/asm/mac_via.h index de1470c4d829..1149251ea58d 100644 --- a/arch/m68k/include/asm/mac_via.h +++ b/arch/m68k/include/asm/mac_via.h @@ -257,6 +257,7 @@ extern int rbv_present,via_alt_mapping; struct irq_desc; +extern void via_l2_flush(int writeback); extern void via_register_interrupts(void); extern void via_irq_enable(int); extern void via_irq_disable(int); diff --git a/arch/m68k/kernel/setup_no.c b/arch/m68k/kernel/setup_no.c index cfd5475bfc31..4625acc1e7c4 100644 --- a/arch/m68k/kernel/setup_no.c +++ b/arch/m68k/kernel/setup_no.c @@ -140,7 +140,8 @@ void __init setup_arch(char **cmdline_p) pr_debug("MEMORY -> ROMFS=0x%p-0x%06lx MEM=0x%06lx-0x%06lx\n ", __bss_stop, memory_start, memory_start, memory_end); - memblock_add(memory_start, memory_end - memory_start); + memblock_add(_rambase, memory_end - _rambase); + memblock_reserve(_rambase, memory_start - _rambase); /* Keep a copy of command line */ *cmdline_p = &command_line[0]; diff --git a/arch/m68k/mac/config.c b/arch/m68k/mac/config.c index cd9317d53276..a4f91bea6c88 100644 --- a/arch/m68k/mac/config.c +++ b/arch/m68k/mac/config.c @@ -61,7 +61,6 @@ extern void iop_preinit(void); extern void iop_init(void); extern void via_init(void); extern void via_init_clock(irq_handler_t func); -extern void via_flush_cache(void); extern void oss_init(void); extern void psc_init(void); extern void baboon_init(void); @@ -132,21 +131,6 @@ int __init mac_parse_bootinfo(const struct bi_record *record) return unknown; } -/* - * Flip into 24bit mode for an instant - flushes the L2 cache card. We - * have to disable interrupts for this. Our IRQ handlers will crap - * themselves if they take an IRQ in 24bit mode! - */ - -static void mac_cache_card_flush(int writeback) -{ - unsigned long flags; - - local_irq_save(flags); - via_flush_cache(); - local_irq_restore(flags); -} - void __init config_mac(void) { if (!MACH_IS_MAC) @@ -178,9 +162,8 @@ void __init config_mac(void) * not. */ - if (macintosh_config->ident == MAC_MODEL_IICI - || macintosh_config->ident == MAC_MODEL_IIFX) - mach_l2_flush = mac_cache_card_flush; + if (macintosh_config->ident == MAC_MODEL_IICI) + mach_l2_flush = via_l2_flush; } diff --git a/arch/m68k/mac/iop.c b/arch/m68k/mac/iop.c index 9bfa17015768..c432bfafe63e 100644 --- a/arch/m68k/mac/iop.c +++ b/arch/m68k/mac/iop.c @@ -183,7 +183,7 @@ static __inline__ void iop_writeb(volatile struct mac_iop *iop, __u16 addr, __u8 static __inline__ void iop_stop(volatile struct mac_iop *iop) { - iop->status_ctrl &= ~IOP_RUN; + iop->status_ctrl = IOP_AUTOINC; } static __inline__ void iop_start(volatile struct mac_iop *iop) @@ -191,14 +191,9 @@ static __inline__ void iop_start(volatile struct mac_iop *iop) iop->status_ctrl = IOP_RUN | IOP_AUTOINC; } -static __inline__ void iop_bypass(volatile struct mac_iop *iop) -{ - iop->status_ctrl |= IOP_BYPASS; -} - static __inline__ void iop_interrupt(volatile struct mac_iop *iop) { - iop->status_ctrl |= IOP_IRQ; + iop->status_ctrl = IOP_IRQ | IOP_RUN | IOP_AUTOINC; } static int iop_alive(volatile struct mac_iop *iop) @@ -244,7 +239,6 @@ void __init iop_preinit(void) } else { iop_base[IOP_NUM_SCC] = (struct mac_iop *) SCC_IOP_BASE_QUADRA; } - iop_base[IOP_NUM_SCC]->status_ctrl = 0x87; iop_scc_present = 1; } else { iop_base[IOP_NUM_SCC] = NULL; @@ -256,7 +250,7 @@ void __init iop_preinit(void) } else { iop_base[IOP_NUM_ISM] = (struct mac_iop *) ISM_IOP_BASE_QUADRA; } - iop_base[IOP_NUM_ISM]->status_ctrl = 0; + iop_stop(iop_base[IOP_NUM_ISM]); iop_ism_present = 1; } else { iop_base[IOP_NUM_ISM] = NULL; @@ -416,7 +410,8 @@ static void iop_handle_send(uint iop_num, uint chan) msg->status = IOP_MSGSTATUS_UNUSED; msg = msg->next; iop_send_queue[iop_num][chan] = msg; - if (msg) iop_do_send(msg); + if (msg && iop_readb(iop, IOP_ADDR_SEND_STATE + chan) == IOP_MSG_IDLE) + iop_do_send(msg); } /* @@ -490,16 +485,12 @@ int iop_send_message(uint iop_num, uint chan, void *privdata, if (!(q = iop_send_queue[iop_num][chan])) { iop_send_queue[iop_num][chan] = msg; + iop_do_send(msg); } else { while (q->next) q = q->next; q->next = msg; } - if (iop_readb(iop_base[iop_num], - IOP_ADDR_SEND_STATE + chan) == IOP_MSG_IDLE) { - iop_do_send(msg); - } - return 0; } diff --git a/arch/m68k/mac/via.c b/arch/m68k/mac/via.c index 038d5a1c4d48..8307da441a10 100644 --- a/arch/m68k/mac/via.c +++ b/arch/m68k/mac/via.c @@ -289,10 +289,14 @@ void via_debug_dump(void) * the system into 24-bit mode for an instant. */ -void via_flush_cache(void) +void via_l2_flush(int writeback) { + unsigned long flags; + + local_irq_save(flags); via2[gBufB] &= ~VIA2B_vMode32; via2[gBufB] |= VIA2B_vMode32; + local_irq_restore(flags); } /* diff --git a/arch/m68k/mm/mcfmmu.c b/arch/m68k/mm/mcfmmu.c index f5453d944ff5..c5e26222979a 100644 --- a/arch/m68k/mm/mcfmmu.c +++ b/arch/m68k/mm/mcfmmu.c @@ -160,7 +160,7 @@ void __init cf_bootmem_alloc(void) m68k_memory[0].addr = _rambase; m68k_memory[0].size = _ramend - _rambase; - memblock_add(m68k_memory[0].addr, m68k_memory[0].size); + memblock_add_node(m68k_memory[0].addr, m68k_memory[0].size, 0); /* compute total pages in system */ num_pages = PFN_DOWN(_ramend - _rambase); diff --git a/arch/m68k/q40/config.c b/arch/m68k/q40/config.c index 96810d91da2b..4a25ce6a1823 100644 --- a/arch/m68k/q40/config.c +++ b/arch/m68k/q40/config.c @@ -273,6 +273,7 @@ static int q40_get_rtc_pll(struct rtc_pll_info *pll) { int tmp = Q40_RTC_CTRL; + pll->pll_ctrl = 0; pll->pll_value = tmp & Q40_RTC_PLL_MASK; if (tmp & Q40_RTC_PLL_SIGN) pll->pll_value = -pll->pll_value; diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index a830a9701e50..cc8c8d22afaf 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -852,6 +852,7 @@ config SNI_RM select I8253 select I8259 select ISA + select MIPS_L1_CACHE_SHIFT_6 select SWAP_IO_SPACE if CPU_BIG_ENDIAN select SYS_HAS_CPU_R4X00 select SYS_HAS_CPU_R5000 diff --git a/arch/mips/Makefile b/arch/mips/Makefile index ad0a92f95af1..63e2ad43bd6a 100644 --- a/arch/mips/Makefile +++ b/arch/mips/Makefile @@ -290,12 +290,23 @@ ifdef CONFIG_64BIT endif endif +# When linking a 32-bit executable the LLVM linker cannot cope with a +# 32-bit load address that has been sign-extended to 64 bits. Simply +# remove the upper 32 bits then, as it is safe to do so with other +# linkers. +ifdef CONFIG_64BIT + load-ld = $(load-y) +else + load-ld = $(subst 0xffffffff,0x,$(load-y)) +endif + KBUILD_AFLAGS += $(cflags-y) KBUILD_CFLAGS += $(cflags-y) -KBUILD_CPPFLAGS += -DVMLINUX_LOAD_ADDRESS=$(load-y) +KBUILD_CPPFLAGS += -DVMLINUX_LOAD_ADDRESS=$(load-y) -DLINKER_LOAD_ADDRESS=$(load-ld) KBUILD_CPPFLAGS += -DDATAOFFSET=$(if $(dataoffset-y),$(dataoffset-y),0) bootvars-y = VMLINUX_LOAD_ADDRESS=$(load-y) \ + LINKER_LOAD_ADDRESS=$(load-ld) \ VMLINUX_ENTRY_ADDRESS=$(entry-y) \ PLATFORM="$(platform-y)" \ ITS_INPUTS="$(its-y)" diff --git a/arch/mips/alchemy/board-xxs1500.c b/arch/mips/alchemy/board-xxs1500.c index 5f05b8714385..b968cff5baa7 100644 --- a/arch/mips/alchemy/board-xxs1500.c +++ b/arch/mips/alchemy/board-xxs1500.c @@ -31,6 +31,7 @@ #include <asm/reboot.h> #include <asm/setup.h> #include <asm/mach-au1x00/au1000.h> +#include <asm/mach-au1x00/gpio-au1000.h> #include <prom.h> const char *get_system_type(void) diff --git a/arch/mips/alchemy/common/clock.c b/arch/mips/alchemy/common/clock.c index d129475fd40d..4254ba13c5c5 100644 --- a/arch/mips/alchemy/common/clock.c +++ b/arch/mips/alchemy/common/clock.c @@ -152,6 +152,7 @@ static struct clk __init *alchemy_clk_setup_cpu(const char *parent_name, { struct clk_init_data id; struct clk_hw *h; + struct clk *clk; h = kzalloc(sizeof(*h), GFP_KERNEL); if (!h) @@ -164,7 +165,13 @@ static struct clk __init *alchemy_clk_setup_cpu(const char *parent_name, id.ops = &alchemy_clkops_cpu; h->init = &id; - return clk_register(NULL, h); + clk = clk_register(NULL, h); + if (IS_ERR(clk)) { + pr_err("failed to register clock\n"); + kfree(h); + } + + return clk; } /* AUXPLLs ************************************************************/ diff --git a/arch/mips/bcm47xx/Kconfig b/arch/mips/bcm47xx/Kconfig index 29471038d817..c6b99845fb37 100644 --- a/arch/mips/bcm47xx/Kconfig +++ b/arch/mips/bcm47xx/Kconfig @@ -27,6 +27,7 @@ config BCM47XX_BCMA select BCMA select BCMA_HOST_SOC select BCMA_DRIVER_MIPS + select BCMA_DRIVER_PCI if PCI select BCMA_DRIVER_PCI_HOSTMODE if PCI select BCMA_DRIVER_GPIO default y diff --git a/arch/mips/boot/compressed/Makefile b/arch/mips/boot/compressed/Makefile index d859f079b771..378cbfb31ee7 100644 --- a/arch/mips/boot/compressed/Makefile +++ b/arch/mips/boot/compressed/Makefile @@ -90,7 +90,7 @@ ifneq ($(zload-y),) VMLINUZ_LOAD_ADDRESS := $(zload-y) else VMLINUZ_LOAD_ADDRESS = $(shell $(obj)/calc_vmlinuz_load_addr \ - $(obj)/vmlinux.bin $(VMLINUX_LOAD_ADDRESS)) + $(obj)/vmlinux.bin $(LINKER_LOAD_ADDRESS)) endif UIMAGE_LOADADDR = $(VMLINUZ_LOAD_ADDRESS) diff --git a/arch/mips/boot/compressed/decompress.c b/arch/mips/boot/compressed/decompress.c index 81df9047e110..40218be0b7ce 100644 --- a/arch/mips/boot/compressed/decompress.c +++ b/arch/mips/boot/compressed/decompress.c @@ -17,6 +17,7 @@ #include <linux/libfdt.h> #include <asm/addrspace.h> +#include <asm/unaligned.h> /* * These two variables specify the free mem region @@ -117,7 +118,7 @@ void decompress_kernel(unsigned long boot_heap_start) dtb_size = fdt_totalsize((void *)&__appended_dtb); /* last four bytes is always image size in little endian */ - image_size = le32_to_cpup((void *)&__image_end - 4); + image_size = get_unaligned_le32((void *)&__image_end - 4); /* copy dtb to where the booted kernel will expect it */ memcpy((void *)VMLINUX_LOAD_ADDRESS_ULL + image_size, diff --git a/arch/mips/cavium-octeon/octeon-irq.c b/arch/mips/cavium-octeon/octeon-irq.c index 8272d8c648ca..43e4fc1b373c 100644 --- a/arch/mips/cavium-octeon/octeon-irq.c +++ b/arch/mips/cavium-octeon/octeon-irq.c @@ -2199,6 +2199,9 @@ static int octeon_irq_cib_map(struct irq_domain *d, } cd = kzalloc(sizeof(*cd), GFP_KERNEL); + if (!cd) + return -ENOMEM; + cd->host_data = host_data; cd->bit = hw; diff --git a/arch/mips/cavium-octeon/octeon-usb.c b/arch/mips/cavium-octeon/octeon-usb.c index bfdfaf32d2c4..75189ff2f3c7 100644 --- a/arch/mips/cavium-octeon/octeon-usb.c +++ b/arch/mips/cavium-octeon/octeon-usb.c @@ -517,6 +517,7 @@ static int __init dwc3_octeon_device_init(void) res = platform_get_resource(pdev, IORESOURCE_MEM, 0); if (res == NULL) { + put_device(&pdev->dev); dev_err(&pdev->dev, "No memory resources\n"); return -ENXIO; } @@ -528,8 +529,10 @@ static int __init dwc3_octeon_device_init(void) * know the difference. */ base = devm_ioremap_resource(&pdev->dev, res); - if (IS_ERR(base)) + if (IS_ERR(base)) { + put_device(&pdev->dev); return PTR_ERR(base); + } mutex_lock(&dwc3_octeon_clocks_mutex); dwc3_octeon_clocks_start(&pdev->dev, (u64)base); diff --git a/arch/mips/configs/bigsur_defconfig b/arch/mips/configs/bigsur_defconfig index 5e73fe755be6..bd6654299a9c 100644 --- a/arch/mips/configs/bigsur_defconfig +++ b/arch/mips/configs/bigsur_defconfig @@ -123,7 +123,6 @@ CONFIG_BLK_DEV_TC86C001=m CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=y CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=m CONFIG_CHR_DEV_SCH=m CONFIG_ATA=y diff --git a/arch/mips/configs/fuloong2e_defconfig b/arch/mips/configs/fuloong2e_defconfig index 499f51498ecb..8f3e08d8607b 100644 --- a/arch/mips/configs/fuloong2e_defconfig +++ b/arch/mips/configs/fuloong2e_defconfig @@ -111,7 +111,6 @@ CONFIG_CDROM_PKTCDVD=m CONFIG_ATA_OVER_ETH=m CONFIG_BLK_DEV_SD=y CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=y CONFIG_SCSI_CONSTANTS=y # CONFIG_SCSI_LOWLEVEL is not set diff --git a/arch/mips/configs/ip27_defconfig b/arch/mips/configs/ip27_defconfig index 91a9c13e2c82..9855addcd7d5 100644 --- a/arch/mips/configs/ip27_defconfig +++ b/arch/mips/configs/ip27_defconfig @@ -107,7 +107,6 @@ CONFIG_SCSI=y CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=y CONFIG_BLK_DEV_SR=m -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=m CONFIG_CHR_DEV_SCH=m CONFIG_SCSI_CONSTANTS=y diff --git a/arch/mips/configs/ip32_defconfig b/arch/mips/configs/ip32_defconfig index ebff297328ae..a5f6be4b949b 100644 --- a/arch/mips/configs/ip32_defconfig +++ b/arch/mips/configs/ip32_defconfig @@ -54,7 +54,6 @@ CONFIG_RAID_ATTRS=y CONFIG_SCSI=y CONFIG_BLK_DEV_SD=y CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=m CONFIG_SCSI_MULTI_LUN=y CONFIG_SCSI_CONSTANTS=y diff --git a/arch/mips/configs/jazz_defconfig b/arch/mips/configs/jazz_defconfig index 9ad1c94376c8..aa101c27ed25 100644 --- a/arch/mips/configs/jazz_defconfig +++ b/arch/mips/configs/jazz_defconfig @@ -206,7 +206,6 @@ CONFIG_SCSI=y CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=m CONFIG_BLK_DEV_SR=m -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_SCAN_ASYNC=y CONFIG_SCSI_FC_ATTRS=y diff --git a/arch/mips/configs/loongson3_defconfig b/arch/mips/configs/loongson3_defconfig index 324dfee23dfb..c871e40b8878 100644 --- a/arch/mips/configs/loongson3_defconfig +++ b/arch/mips/configs/loongson3_defconfig @@ -250,7 +250,7 @@ CONFIG_MEDIA_CAMERA_SUPPORT=y CONFIG_MEDIA_USB_SUPPORT=y CONFIG_USB_VIDEO_CLASS=m CONFIG_DRM=y -CONFIG_DRM_RADEON=y +CONFIG_DRM_RADEON=m CONFIG_FB_RADEON=y CONFIG_LCD_CLASS_DEVICE=y CONFIG_LCD_PLATFORM=m diff --git a/arch/mips/configs/malta_defconfig b/arch/mips/configs/malta_defconfig index 81058295d35f..4338c2189c0f 100644 --- a/arch/mips/configs/malta_defconfig +++ b/arch/mips/configs/malta_defconfig @@ -245,7 +245,6 @@ CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=m CONFIG_CHR_DEV_OSST=m CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=m CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_LOGGING=y diff --git a/arch/mips/configs/malta_kvm_defconfig b/arch/mips/configs/malta_kvm_defconfig index 5c10cddc39d3..224718f45393 100644 --- a/arch/mips/configs/malta_kvm_defconfig +++ b/arch/mips/configs/malta_kvm_defconfig @@ -252,7 +252,6 @@ CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=m CONFIG_CHR_DEV_OSST=m CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=m CONFIG_SCSI_MULTI_LUN=y CONFIG_SCSI_CONSTANTS=y diff --git a/arch/mips/configs/malta_kvm_guest_defconfig b/arch/mips/configs/malta_kvm_guest_defconfig index bb694f5065f1..03cf2abe2d65 100644 --- a/arch/mips/configs/malta_kvm_guest_defconfig +++ b/arch/mips/configs/malta_kvm_guest_defconfig @@ -254,7 +254,6 @@ CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=m CONFIG_CHR_DEV_OSST=m CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=m CONFIG_SCSI_MULTI_LUN=y CONFIG_SCSI_CONSTANTS=y diff --git a/arch/mips/configs/maltaup_xpa_defconfig b/arch/mips/configs/maltaup_xpa_defconfig index 99a19cf5f9ba..f64074aa06b6 100644 --- a/arch/mips/configs/maltaup_xpa_defconfig +++ b/arch/mips/configs/maltaup_xpa_defconfig @@ -250,7 +250,6 @@ CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=m CONFIG_CHR_DEV_OSST=m CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=m CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_LOGGING=y diff --git a/arch/mips/configs/rm200_defconfig b/arch/mips/configs/rm200_defconfig index 1a3e1fec4e86..194df200daad 100644 --- a/arch/mips/configs/rm200_defconfig +++ b/arch/mips/configs/rm200_defconfig @@ -218,7 +218,6 @@ CONFIG_SCSI=y CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=m CONFIG_BLK_DEV_SR=m -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_SCAN_ASYNC=y CONFIG_SCSI_FC_ATTRS=y diff --git a/arch/mips/include/asm/cpu-type.h b/arch/mips/include/asm/cpu-type.h index a45af3de075d..d43e4ab20b23 100644 --- a/arch/mips/include/asm/cpu-type.h +++ b/arch/mips/include/asm/cpu-type.h @@ -47,6 +47,7 @@ static inline int __pure __get_cpu_type(const int cpu_type) case CPU_34K: case CPU_1004K: case CPU_74K: + case CPU_1074K: case CPU_M14KC: case CPU_M14KEC: case CPU_INTERAPTIV: diff --git a/arch/mips/include/asm/div64.h b/arch/mips/include/asm/div64.h index dc5ea5736440..ceece76fc971 100644 --- a/arch/mips/include/asm/div64.h +++ b/arch/mips/include/asm/div64.h @@ -1,5 +1,5 @@ /* - * Copyright (C) 2000, 2004 Maciej W. Rozycki + * Copyright (C) 2000, 2004, 2021 Maciej W. Rozycki * Copyright (C) 2003, 07 Ralf Baechle (ralf@linux-mips.org) * * This file is subject to the terms and conditions of the GNU General Public @@ -9,25 +9,18 @@ #ifndef __ASM_DIV64_H #define __ASM_DIV64_H -#include <asm-generic/div64.h> - -#if BITS_PER_LONG == 64 +#include <asm/bitsperlong.h> -#include <linux/types.h> +#if BITS_PER_LONG == 32 /* * No traps on overflows for any of these... */ -#define __div64_32(n, base) \ -({ \ +#define do_div64_32(res, high, low, base) ({ \ unsigned long __cf, __tmp, __tmp2, __i; \ unsigned long __quot32, __mod32; \ - unsigned long __high, __low; \ - unsigned long long __n; \ \ - __high = *__n >> 32; \ - __low = __n; \ __asm__( \ " .set push \n" \ " .set noat \n" \ @@ -51,18 +44,48 @@ " subu %0, %0, %z6 \n" \ " addiu %2, %2, 1 \n" \ "3: \n" \ - " bnez %4, 0b\n\t" \ - " srl %5, %1, 0x1f\n\t" \ + " bnez %4, 0b \n" \ + " srl %5, %1, 0x1f \n" \ " .set pop" \ : "=&r" (__mod32), "=&r" (__tmp), \ "=&r" (__quot32), "=&r" (__cf), \ "=&r" (__i), "=&r" (__tmp2) \ - : "Jr" (base), "0" (__high), "1" (__low)); \ + : "Jr" (base), "0" (high), "1" (low)); \ \ - (__n) = __quot32; \ + (res) = __quot32; \ __mod32; \ }) -#endif /* BITS_PER_LONG == 64 */ +#define __div64_32(n, base) ({ \ + unsigned long __upper, __low, __high, __radix; \ + unsigned long long __quot; \ + unsigned long long __div; \ + unsigned long __mod; \ + \ + __div = (*n); \ + __radix = (base); \ + \ + __high = __div >> 32; \ + __low = __div; \ + \ + if (__high < __radix) { \ + __upper = __high; \ + __high = 0; \ + } else { \ + __upper = __high % __radix; \ + __high /= __radix; \ + } \ + \ + __mod = do_div64_32(__low, __upper, __low, __radix); \ + \ + __quot = __high; \ + __quot = __quot << 32 | __low; \ + (*n) = __quot; \ + __mod; \ +}) + +#endif /* BITS_PER_LONG == 32 */ + +#include <asm-generic/div64.h> #endif /* __ASM_DIV64_H */ diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h index f567ace7a9e9..c254761cb8ad 100644 --- a/arch/mips/include/asm/kvm_host.h +++ b/arch/mips/include/asm/kvm_host.h @@ -274,8 +274,12 @@ enum emulation_result { #define MIPS3_PG_SHIFT 6 #define MIPS3_PG_FRAME 0x3fffffc0 +#if defined(CONFIG_64BIT) +#define VPN2_MASK GENMASK(cpu_vmbits - 1, 13) +#else #define VPN2_MASK 0xffffe000 -#define KVM_ENTRYHI_ASID MIPS_ENTRYHI_ASID +#endif +#define KVM_ENTRYHI_ASID cpu_asid_mask(&boot_cpu_data) #define TLB_IS_GLOBAL(x) ((x).tlb_lo[0] & (x).tlb_lo[1] & ENTRYLO_G) #define TLB_VPN2(x) ((x).tlb_hi & VPN2_MASK) #define TLB_ASID(x) ((x).tlb_hi & KVM_ENTRYHI_ASID) @@ -932,7 +936,7 @@ enum kvm_mips_fault_result kvm_trap_emul_gva_fault(struct kvm_vcpu *vcpu, #define KVM_ARCH_WANT_MMU_NOTIFIER int kvm_unmap_hva_range(struct kvm *kvm, - unsigned long start, unsigned long end); + unsigned long start, unsigned long end, bool blockable); void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end); int kvm_test_age_hva(struct kvm *kvm, unsigned long hva); diff --git a/arch/mips/include/asm/mipsregs.h b/arch/mips/include/asm/mipsregs.h index 1bb9448777c5..f9a7c137be9f 100644 --- a/arch/mips/include/asm/mipsregs.h +++ b/arch/mips/include/asm/mipsregs.h @@ -749,7 +749,7 @@ /* MAAR bit definitions */ #define MIPS_MAAR_VH (_U64CAST_(1) << 63) -#define MIPS_MAAR_ADDR ((BIT_ULL(BITS_PER_LONG - 12) - 1) << 12) +#define MIPS_MAAR_ADDR GENMASK_ULL(55, 12) #define MIPS_MAAR_ADDR_SHIFT 12 #define MIPS_MAAR_S (_ULCAST_(1) << 1) #define MIPS_MAAR_VL (_ULCAST_(1) << 0) diff --git a/arch/mips/kernel/genex.S b/arch/mips/kernel/genex.S index 6c257b52f57f..7fad007fe025 100644 --- a/arch/mips/kernel/genex.S +++ b/arch/mips/kernel/genex.S @@ -477,20 +477,20 @@ NESTED(nmi_handler, PT_SIZE, sp) .endm .macro __build_clear_fpe + CLI + TRACE_IRQS_OFF .set push /* gas fails to assemble cfc1 for some archs (octeon).*/ \ .set mips1 SET_HARDFLOAT cfc1 a1, fcr31 .set pop - CLI - TRACE_IRQS_OFF .endm .macro __build_clear_msa_fpe - _cfcmsa a1, MSA_CSR CLI TRACE_IRQS_OFF + _cfcmsa a1, MSA_CSR .endm .macro __build_clear_ade diff --git a/arch/mips/kernel/mips-cm.c b/arch/mips/kernel/mips-cm.c index 7f3f136572de..50d3d74001cb 100644 --- a/arch/mips/kernel/mips-cm.c +++ b/arch/mips/kernel/mips-cm.c @@ -123,9 +123,9 @@ static char *cm2_causes[32] = { "COH_RD_ERR", "MMIO_WR_ERR", "MMIO_RD_ERR", "0x07", "0x08", "0x09", "0x0a", "0x0b", "0x0c", "0x0d", "0x0e", "0x0f", - "0x10", "0x11", "0x12", "0x13", - "0x14", "0x15", "0x16", "INTVN_WR_ERR", - "INTVN_RD_ERR", "0x19", "0x1a", "0x1b", + "0x10", "INTVN_WR_ERR", "INTVN_RD_ERR", "0x13", + "0x14", "0x15", "0x16", "0x17", + "0x18", "0x19", "0x1a", "0x1b", "0x1c", "0x1d", "0x1e", "0x1f" }; diff --git a/arch/mips/kernel/relocate.c b/arch/mips/kernel/relocate.c index cbf4cc0b0b6c..934caf204078 100644 --- a/arch/mips/kernel/relocate.c +++ b/arch/mips/kernel/relocate.c @@ -187,8 +187,14 @@ static int __init relocate_exception_table(long offset) static inline __init unsigned long rotate_xor(unsigned long hash, const void *area, size_t size) { - size_t i; - unsigned long *ptr = (unsigned long *)area; + const typeof(hash) *ptr = PTR_ALIGN(area, sizeof(hash)); + size_t diff, i; + + diff = (void *)ptr - area; + if (unlikely(size < diff + sizeof(hash))) + return hash; + + size = ALIGN_DOWN(size - diff, sizeof(hash)); for (i = 0; i < size / sizeof(hash); i++) { /* Rotate by odd number of bits and XOR. */ diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c index e87c98b8a72c..2c2480be3f36 100644 --- a/arch/mips/kernel/setup.c +++ b/arch/mips/kernel/setup.c @@ -933,7 +933,17 @@ static void __init arch_mem_init(char **cmdline_p) BOOTMEM_DEFAULT); #endif device_tree_init(); + + /* + * In order to reduce the possibility of kernel panic when failed to + * get IO TLB memory under CONFIG_SWIOTLB, it is better to allocate + * low memory as small as possible before plat_swiotlb_setup(), so + * make sparse_init() using top-down allocation. + */ + memblock_set_bottom_up(false); sparse_init(); + memblock_set_bottom_up(true); + plat_swiotlb_setup(); dma_contiguous_reserve(PFN_PHYS(max_low_pfn)); diff --git a/arch/mips/kernel/smp-bmips.c b/arch/mips/kernel/smp-bmips.c index 5ec546b5eed1..d16e6654a655 100644 --- a/arch/mips/kernel/smp-bmips.c +++ b/arch/mips/kernel/smp-bmips.c @@ -240,6 +240,8 @@ static int bmips_boot_secondary(int cpu, struct task_struct *idle) */ static void bmips_init_secondary(void) { + bmips_cpu_setup(); + switch (current_cpu_type()) { case CPU_BMIPS4350: case CPU_BMIPS4380: diff --git a/arch/mips/kernel/time.c b/arch/mips/kernel/time.c index bfe02ded25d1..a0d994a4aaa9 100644 --- a/arch/mips/kernel/time.c +++ b/arch/mips/kernel/time.c @@ -22,12 +22,77 @@ #include <linux/smp.h> #include <linux/spinlock.h> #include <linux/export.h> +#include <linux/cpufreq.h> +#include <linux/delay.h> #include <asm/cpu-features.h> #include <asm/cpu-type.h> #include <asm/div64.h> #include <asm/time.h> +#ifdef CONFIG_CPU_FREQ + +static DEFINE_PER_CPU(unsigned long, pcp_lpj_ref); +static DEFINE_PER_CPU(unsigned long, pcp_lpj_ref_freq); +static unsigned long glb_lpj_ref; +static unsigned long glb_lpj_ref_freq; + +static int cpufreq_callback(struct notifier_block *nb, + unsigned long val, void *data) +{ + int cpu; + struct cpufreq_freqs *freq = data; + + /* + * Skip lpj numbers adjustment if the CPU-freq transition is safe for + * the loops delay. (Is this possible?) + */ + if (freq->flags & CPUFREQ_CONST_LOOPS) + return NOTIFY_OK; + + /* Save the initial values of the lpjes for future scaling. */ + if (!glb_lpj_ref) { + glb_lpj_ref = boot_cpu_data.udelay_val; + glb_lpj_ref_freq = freq->old; + + for_each_online_cpu(cpu) { + per_cpu(pcp_lpj_ref, cpu) = + cpu_data[cpu].udelay_val; + per_cpu(pcp_lpj_ref_freq, cpu) = freq->old; + } + } + + cpu = freq->cpu; + /* + * Adjust global lpj variable and per-CPU udelay_val number in + * accordance with the new CPU frequency. + */ + if ((val == CPUFREQ_PRECHANGE && freq->old < freq->new) || + (val == CPUFREQ_POSTCHANGE && freq->old > freq->new)) { + loops_per_jiffy = cpufreq_scale(glb_lpj_ref, + glb_lpj_ref_freq, + freq->new); + + cpu_data[cpu].udelay_val = cpufreq_scale(per_cpu(pcp_lpj_ref, cpu), + per_cpu(pcp_lpj_ref_freq, cpu), freq->new); + } + + return NOTIFY_OK; +} + +static struct notifier_block cpufreq_notifier = { + .notifier_call = cpufreq_callback, +}; + +static int __init register_cpufreq_notifier(void) +{ + return cpufreq_register_notifier(&cpufreq_notifier, + CPUFREQ_TRANSITION_NOTIFIER); +} +core_initcall(register_cpufreq_notifier); + +#endif /* CONFIG_CPU_FREQ */ + /* * forward reference */ diff --git a/arch/mips/kernel/topology.c b/arch/mips/kernel/topology.c index cd3e1f82e1a5..08ad6371fbe0 100644 --- a/arch/mips/kernel/topology.c +++ b/arch/mips/kernel/topology.c @@ -20,7 +20,7 @@ static int __init topology_init(void) for_each_present_cpu(i) { struct cpu *c = &per_cpu(cpu_devices, i); - c->hotpluggable = 1; + c->hotpluggable = !!i; ret = register_cpu(c, i); if (ret) printk(KERN_WARNING "topology_init: register_cpu %d " diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c index 9dab0ed1b227..b9da2cefb564 100644 --- a/arch/mips/kernel/traps.c +++ b/arch/mips/kernel/traps.c @@ -2096,6 +2096,7 @@ static void configure_status(void) change_c0_status(ST0_CU|ST0_MX|ST0_RE|ST0_FR|ST0_BEV|ST0_TS|ST0_KX|ST0_SX|ST0_UX, status_set); + back_to_back_c0_hazard(); } unsigned int hwrena; diff --git a/arch/mips/kernel/vmlinux.lds.S b/arch/mips/kernel/vmlinux.lds.S index 36f2e860ba3e..968c5765020c 100644 --- a/arch/mips/kernel/vmlinux.lds.S +++ b/arch/mips/kernel/vmlinux.lds.S @@ -50,7 +50,7 @@ SECTIONS /* . = 0xa800000000300000; */ . = 0xffffffff80300000; #endif - . = VMLINUX_LOAD_ADDRESS; + . = LINKER_LOAD_ADDRESS; /* read-only */ _text = .; /* Text and read-only data */ .text : { @@ -93,6 +93,7 @@ SECTIONS INIT_TASK_DATA(THREAD_SIZE) NOSAVE_DATA + PAGE_ALIGNED_DATA(PAGE_SIZE) CACHELINE_ALIGNED_DATA(1 << CONFIG_MIPS_L1_CACHE_SHIFT) READ_MOSTLY_DATA(1 << CONFIG_MIPS_L1_CACHE_SHIFT) DATA_DATA diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c index e7f5ef6bed0f..79485790f7b5 100644 --- a/arch/mips/kvm/mips.c +++ b/arch/mips/kvm/mips.c @@ -131,6 +131,8 @@ void kvm_arch_check_processor_compat(void *rtn) int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) { switch (type) { + case KVM_VM_MIPS_AUTO: + break; #ifdef CONFIG_KVM_MIPS_VZ case KVM_VM_MIPS_VZ: #else diff --git a/arch/mips/kvm/mmu.c b/arch/mips/kvm/mmu.c index d8dcdb350405..098a7afd4d38 100644 --- a/arch/mips/kvm/mmu.c +++ b/arch/mips/kvm/mmu.c @@ -512,7 +512,8 @@ static int kvm_unmap_hva_handler(struct kvm *kvm, gfn_t gfn, gfn_t gfn_end, return 1; } -int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end) +int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end, + bool blockable) { handle_hva_to_gpa(kvm, start, end, &kvm_unmap_hva_handler, NULL); diff --git a/arch/mips/lantiq/irq.c b/arch/mips/lantiq/irq.c index 37caeadb2964..0476d7e97a03 100644 --- a/arch/mips/lantiq/irq.c +++ b/arch/mips/lantiq/irq.c @@ -244,7 +244,7 @@ static void ltq_hw_irq_handler(struct irq_desc *desc) generic_handle_irq(irq_linear_revmap(ltq_domain, hwirq)); /* if this is a EBU irq, we need to ack it or get a deadlock */ - if ((irq == LTQ_ICU_EBU_IRQ) && (module == 0) && LTQ_EBU_PCC_ISTAT) + if (irq == LTQ_ICU_EBU_IRQ && !module && LTQ_EBU_PCC_ISTAT != 0) ltq_ebu_w32(ltq_ebu_r32(LTQ_EBU_PCC_ISTAT) | 0x10, LTQ_EBU_PCC_ISTAT); } diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c index 05a539d3a597..60fe72170856 100644 --- a/arch/mips/mm/c-r4k.c +++ b/arch/mips/mm/c-r4k.c @@ -1673,7 +1673,7 @@ static int probe_scache(void) return 1; } -static void __init loongson2_sc_init(void) +static void loongson2_sc_init(void) { struct cpuinfo_mips *c = ¤t_cpu_data; @@ -1789,7 +1789,11 @@ static void setup_scache(void) printk("MIPS secondary cache %ldkB, %s, linesize %d bytes.\n", scache_size >> 10, way_string[c->scache.ways], c->scache.linesz); + + if (current_cpu_type() == CPU_BMIPS5000) + c->options |= MIPS_CPU_INCLUSIVE_CACHES; } + #else if (!(c->scache.flags & MIPS_CACHE_NOT_PRESENT)) panic("Dunno how to handle MIPS32 / MIPS64 second level cache"); diff --git a/arch/mips/mm/tlb-r4k.c b/arch/mips/mm/tlb-r4k.c index 0596505770db..11985399c469 100644 --- a/arch/mips/mm/tlb-r4k.c +++ b/arch/mips/mm/tlb-r4k.c @@ -424,6 +424,7 @@ int has_transparent_hugepage(void) } return mask == PM_HUGE_MASK; } +EXPORT_SYMBOL(has_transparent_hugepage); #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c index 3944c49eee0c..620abc968624 100644 --- a/arch/mips/mm/tlbex.c +++ b/arch/mips/mm/tlbex.c @@ -1479,6 +1479,7 @@ static void build_r4000_tlb_refill_handler(void) static void setup_pw(void) { + unsigned int pwctl; unsigned long pgd_i, pgd_w; #ifndef __PAGETABLE_PMD_FOLDED unsigned long pmd_i, pmd_w; @@ -1505,6 +1506,7 @@ static void setup_pw(void) pte_i = ilog2(_PAGE_GLOBAL); pte_w = 0; + pwctl = 1 << 30; /* Set PWDirExt */ #ifndef __PAGETABLE_PMD_FOLDED write_c0_pwfield(pgd_i << 24 | pmd_i << 12 | pt_i << 6 | pte_i); @@ -1515,8 +1517,9 @@ static void setup_pw(void) #endif #ifdef CONFIG_MIPS_HUGE_TLB_SUPPORT - write_c0_pwctl(1 << 6 | psn); + pwctl |= (1 << 6 | psn); #endif + write_c0_pwctl(pwctl); write_c0_kpgd((long)swapper_pg_dir); kscratch_used_mask |= (1 << 7); /* KScratch6 is used for KPGD */ } diff --git a/arch/mips/pci/pci-legacy.c b/arch/mips/pci/pci-legacy.c index 3c3b1e6abb53..e8b0751d5b76 100644 --- a/arch/mips/pci/pci-legacy.c +++ b/arch/mips/pci/pci-legacy.c @@ -169,8 +169,13 @@ void pci_load_of_ranges(struct pci_controller *hose, struct device_node *node) res = hose->mem_resource; break; } - if (res != NULL) - of_pci_range_to_resource(&range, node, res); + if (res != NULL) { + res->name = node->full_name; + res->flags = range.flags; + res->start = range.cpu_addr; + res->end = range.cpu_addr + range.size - 1; + res->parent = res->child = res->sibling = NULL; + } } } diff --git a/arch/mips/pci/pci-mt7620.c b/arch/mips/pci/pci-mt7620.c index f6b77788124a..5ae11aeff4b7 100644 --- a/arch/mips/pci/pci-mt7620.c +++ b/arch/mips/pci/pci-mt7620.c @@ -33,6 +33,7 @@ #define RALINK_GPIOMODE 0x60 #define PPLL_CFG1 0x9c +#define PPLL_LD BIT(23) #define PPLL_DRV 0xa0 #define PDRV_SW_SET BIT(31) @@ -242,8 +243,8 @@ static int mt7620_pci_hw_init(struct platform_device *pdev) rt_sysc_m32(0, RALINK_PCIE0_CLK_EN, RALINK_CLKCFG1); mdelay(100); - if (!(rt_sysc_r32(PPLL_CFG1) & PDRV_SW_SET)) { - dev_err(&pdev->dev, "MT7620 PPLL unlock\n"); + if (!(rt_sysc_r32(PPLL_CFG1) & PPLL_LD)) { + dev_err(&pdev->dev, "pcie PLL not locked, aborting init\n"); reset_control_assert(rstpcie0); rt_sysc_m32(RALINK_PCIE0_CLK_EN, 0, RALINK_CLKCFG1); return -1; diff --git a/arch/mips/pci/pci-rt2880.c b/arch/mips/pci/pci-rt2880.c index 711cdccdf65b..f7926a964441 100644 --- a/arch/mips/pci/pci-rt2880.c +++ b/arch/mips/pci/pci-rt2880.c @@ -183,7 +183,6 @@ static inline void rt2880_pci_write_u32(unsigned long reg, u32 val) int pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) { - u16 cmd; int irq = -1; if (dev->bus->number != 0) @@ -191,8 +190,6 @@ int pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) switch (PCI_SLOT(dev->devfn)) { case 0x00: - rt2880_pci_write_u32(PCI_BASE_ADDRESS_0, 0x08000000); - (void) rt2880_pci_read_u32(PCI_BASE_ADDRESS_0); break; case 0x11: irq = RT288X_CPU_IRQ_PCI; @@ -204,16 +201,6 @@ int pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) break; } - pci_write_config_byte((struct pci_dev *) dev, - PCI_CACHE_LINE_SIZE, 0x14); - pci_write_config_byte((struct pci_dev *) dev, PCI_LATENCY_TIMER, 0xFF); - pci_read_config_word((struct pci_dev *) dev, PCI_COMMAND, &cmd); - cmd |= PCI_COMMAND_MASTER | PCI_COMMAND_IO | PCI_COMMAND_MEMORY | - PCI_COMMAND_INVALIDATE | PCI_COMMAND_FAST_BACK | - PCI_COMMAND_SERR | PCI_COMMAND_WAIT | PCI_COMMAND_PARITY; - pci_write_config_word((struct pci_dev *) dev, PCI_COMMAND, cmd); - pci_write_config_byte((struct pci_dev *) dev, PCI_INTERRUPT_LINE, - dev->irq); return irq; } @@ -252,6 +239,30 @@ static int rt288x_pci_probe(struct platform_device *pdev) int pcibios_plat_dev_init(struct pci_dev *dev) { + static bool slot0_init; + + /* + * Nobody seems to initialize slot 0, but this platform requires it, so + * do it once when some other slot is being enabled. The PCI subsystem + * should configure other slots properly, so no need to do anything + * special for those. + */ + if (!slot0_init && dev->bus->number == 0) { + u16 cmd; + u32 bar0; + + slot0_init = true; + + pci_bus_write_config_dword(dev->bus, 0, PCI_BASE_ADDRESS_0, + 0x08000000); + pci_bus_read_config_dword(dev->bus, 0, PCI_BASE_ADDRESS_0, + &bar0); + + pci_bus_read_config_word(dev->bus, 0, PCI_COMMAND, &cmd); + cmd |= PCI_COMMAND_MASTER | PCI_COMMAND_IO | PCI_COMMAND_MEMORY; + pci_bus_write_config_word(dev->bus, 0, PCI_COMMAND, cmd); + } + return 0; } diff --git a/arch/mips/ralink/of.c b/arch/mips/ralink/of.c index 1ada8492733b..92b3d4849996 100644 --- a/arch/mips/ralink/of.c +++ b/arch/mips/ralink/of.c @@ -10,6 +10,7 @@ #include <linux/io.h> #include <linux/clk.h> +#include <linux/export.h> #include <linux/init.h> #include <linux/sizes.h> #include <linux/of_fdt.h> @@ -27,6 +28,7 @@ __iomem void *rt_sysc_membase; __iomem void *rt_memc_membase; +EXPORT_SYMBOL_GPL(rt_sysc_membase); __iomem void *plat_of_remap_node(const char *node) { diff --git a/arch/mips/sni/a20r.c b/arch/mips/sni/a20r.c index f9407e170476..c6af7047eb0d 100644 --- a/arch/mips/sni/a20r.c +++ b/arch/mips/sni/a20r.c @@ -143,7 +143,10 @@ static struct platform_device sc26xx_pdev = { }, }; -static u32 a20r_ack_hwint(void) +/* + * Trigger chipset to update CPU's CAUSE IP field + */ +static u32 a20r_update_cause_ip(void) { u32 status = read_c0_status(); @@ -205,12 +208,14 @@ static void a20r_hwint(void) int irq; clear_c0_status(IE_IRQ0); - status = a20r_ack_hwint(); + status = a20r_update_cause_ip(); cause = read_c0_cause(); irq = ffs(((cause & status) >> 8) & 0xf8); if (likely(irq > 0)) do_IRQ(SNI_A20R_IRQ_BASE + irq - 1); + + a20r_update_cause_ip(); set_c0_status(IE_IRQ0); } diff --git a/arch/mips/vdso/Makefile b/arch/mips/vdso/Makefile index c99fa1c1bd9c..a876b1657bf4 100644 --- a/arch/mips/vdso/Makefile +++ b/arch/mips/vdso/Makefile @@ -10,12 +10,9 @@ ccflags-vdso := \ $(filter -march=%,$(KBUILD_CFLAGS)) \ $(filter -m%-float,$(KBUILD_CFLAGS)) \ $(filter -mno-loongson-%,$(KBUILD_CFLAGS)) \ + $(CLANG_FLAGS) \ -D__VDSO__ -ifeq ($(cc-name),clang) -ccflags-vdso += $(filter --target=%,$(KBUILD_CFLAGS)) -endif - cflags-vdso := $(ccflags-vdso) \ $(filter -W%,$(filter-out -Wa$(comma)%,$(KBUILD_CFLAGS))) \ -O2 -g -fPIC -fno-strict-aliasing -fno-common -fno-builtin -G 0 \ diff --git a/arch/mips/vdso/genvdso.c b/arch/mips/vdso/genvdso.c index 530a36f465ce..afcc86726448 100644 --- a/arch/mips/vdso/genvdso.c +++ b/arch/mips/vdso/genvdso.c @@ -126,6 +126,7 @@ static void *map_vdso(const char *path, size_t *_size) if (fstat(fd, &stat) != 0) { fprintf(stderr, "%s: Failed to stat '%s': %s\n", program_name, path, strerror(errno)); + close(fd); return NULL; } @@ -134,6 +135,7 @@ static void *map_vdso(const char *path, size_t *_size) if (addr == MAP_FAILED) { fprintf(stderr, "%s: Failed to map '%s': %s\n", program_name, path, strerror(errno)); + close(fd); return NULL; } @@ -143,6 +145,7 @@ static void *map_vdso(const char *path, size_t *_size) if (memcmp(ehdr->e_ident, ELFMAG, SELFMAG) != 0) { fprintf(stderr, "%s: '%s' is not an ELF file\n", program_name, path); + close(fd); return NULL; } @@ -154,6 +157,7 @@ static void *map_vdso(const char *path, size_t *_size) default: fprintf(stderr, "%s: '%s' has invalid ELF class\n", program_name, path); + close(fd); return NULL; } @@ -165,6 +169,7 @@ static void *map_vdso(const char *path, size_t *_size) default: fprintf(stderr, "%s: '%s' has invalid ELF data order\n", program_name, path); + close(fd); return NULL; } @@ -172,15 +177,18 @@ static void *map_vdso(const char *path, size_t *_size) fprintf(stderr, "%s: '%s' has invalid ELF machine (expected EM_MIPS)\n", program_name, path); + close(fd); return NULL; } else if (swap_uint16(ehdr->e_type) != ET_DYN) { fprintf(stderr, "%s: '%s' has invalid ELF type (expected ET_DYN)\n", program_name, path); + close(fd); return NULL; } *_size = stat.st_size; + close(fd); return addr; } @@ -284,10 +292,12 @@ int main(int argc, char **argv) /* Calculate and write symbol offsets to <output file> */ if (!get_symbols(dbg_vdso_path, dbg_vdso)) { unlink(out_path); + fclose(out_file); return EXIT_FAILURE; } fprintf(out_file, "};\n"); + fclose(out_file); return EXIT_SUCCESS; } diff --git a/arch/mips/vdso/gettimeofday.c b/arch/mips/vdso/gettimeofday.c index e22b422f282c..9fdc84fc3985 100644 --- a/arch/mips/vdso/gettimeofday.c +++ b/arch/mips/vdso/gettimeofday.c @@ -18,6 +18,12 @@ #include <asm/unistd.h> #include <asm/vdso.h> +#if MIPS_ISA_REV < 6 +#define VDSO_SYSCALL_CLOBBERS "hi", "lo", +#else +#define VDSO_SYSCALL_CLOBBERS +#endif + #ifdef CONFIG_MIPS_CLOCK_VSYSCALL static __always_inline long gettimeofday_fallback(struct timeval *_tv, @@ -34,7 +40,9 @@ static __always_inline long gettimeofday_fallback(struct timeval *_tv, : "=r" (ret), "=r" (error) : "r" (tv), "r" (tz), "r" (nr) : "$1", "$3", "$8", "$9", "$10", "$11", "$12", "$13", - "$14", "$15", "$24", "$25", "hi", "lo", "memory"); + "$14", "$15", "$24", "$25", + VDSO_SYSCALL_CLOBBERS + "memory"); return error ? -ret : ret; } @@ -55,7 +63,9 @@ static __always_inline long clock_gettime_fallback(clockid_t _clkid, : "=r" (ret), "=r" (error) : "r" (clkid), "r" (ts), "r" (nr) : "$1", "$3", "$8", "$9", "$10", "$11", "$12", "$13", - "$14", "$15", "$24", "$25", "hi", "lo", "memory"); + "$14", "$15", "$24", "$25", + VDSO_SYSCALL_CLOBBERS + "memory"); return error ? -ret : ret; } diff --git a/arch/nds32/mm/cacheflush.c b/arch/nds32/mm/cacheflush.c index 254703653b6f..f34dc9bc6758 100644 --- a/arch/nds32/mm/cacheflush.c +++ b/arch/nds32/mm/cacheflush.c @@ -239,7 +239,7 @@ void flush_dcache_page(struct page *page) { struct address_space *mapping; - mapping = page_mapping(page); + mapping = page_mapping_file(page); if (mapping && !mapping_mapped(mapping)) set_bit(PG_dcache_dirty, &page->flags); else { diff --git a/arch/openrisc/include/asm/barrier.h b/arch/openrisc/include/asm/barrier.h new file mode 100644 index 000000000000..7538294721be --- /dev/null +++ b/arch/openrisc/include/asm/barrier.h @@ -0,0 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __ASM_BARRIER_H +#define __ASM_BARRIER_H + +#define mb() asm volatile ("l.msync" ::: "memory") + +#include <asm-generic/barrier.h> + +#endif /* __ASM_BARRIER_H */ diff --git a/arch/openrisc/include/asm/uaccess.h b/arch/openrisc/include/asm/uaccess.h index bbf5c79cce7a..8b204cd1f531 100644 --- a/arch/openrisc/include/asm/uaccess.h +++ b/arch/openrisc/include/asm/uaccess.h @@ -58,8 +58,12 @@ /* Ensure that addr is below task's addr_limit */ #define __addr_ok(addr) ((unsigned long) addr < get_fs()) -#define access_ok(type, addr, size) \ - __range_ok((unsigned long)addr, (unsigned long)size) +#define access_ok(type, addr, size) \ +({ \ + unsigned long __ao_addr = (unsigned long)(addr); \ + unsigned long __ao_size = (unsigned long)(size); \ + __range_ok(__ao_addr, __ao_size); \ +}) /* * These are the main single-value transfer routines. They automatically diff --git a/arch/openrisc/kernel/entry.S b/arch/openrisc/kernel/entry.S index ee6159d2ed22..01b59d2ce174 100644 --- a/arch/openrisc/kernel/entry.S +++ b/arch/openrisc/kernel/entry.S @@ -1170,13 +1170,13 @@ ENTRY(__sys_clone) l.movhi r29,hi(sys_clone) l.ori r29,r29,lo(sys_clone) l.j _fork_save_extra_regs_and_call - l.addi r7,r1,0 + l.nop ENTRY(__sys_fork) l.movhi r29,hi(sys_fork) l.ori r29,r29,lo(sys_fork) l.j _fork_save_extra_regs_and_call - l.addi r3,r1,0 + l.nop ENTRY(sys_rt_sigreturn) l.jal _sys_rt_sigreturn diff --git a/arch/openrisc/kernel/setup.c b/arch/openrisc/kernel/setup.c index 9d28ab14d139..f3a7375ac3cd 100644 --- a/arch/openrisc/kernel/setup.c +++ b/arch/openrisc/kernel/setup.c @@ -281,6 +281,8 @@ void calibrate_delay(void) pr_cont("%lu.%02lu BogoMIPS (lpj=%lu)\n", loops_per_jiffy / (500000 / HZ), (loops_per_jiffy / (5000 / HZ)) % 100, loops_per_jiffy); + + of_node_put(cpu); } void __init setup_arch(char **cmdline_p) diff --git a/arch/openrisc/kernel/stacktrace.c b/arch/openrisc/kernel/stacktrace.c index 43f140a28bc7..54d38809e22c 100644 --- a/arch/openrisc/kernel/stacktrace.c +++ b/arch/openrisc/kernel/stacktrace.c @@ -13,6 +13,7 @@ #include <linux/export.h> #include <linux/sched.h> #include <linux/sched/debug.h> +#include <linux/sched/task_stack.h> #include <linux/stacktrace.h> #include <asm/processor.h> @@ -68,12 +69,25 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) { unsigned long *sp = NULL; + if (!try_get_task_stack(tsk)) + return; + if (tsk == current) sp = (unsigned long *) &sp; - else - sp = (unsigned long *) KSTK_ESP(tsk); + else { + unsigned long ksp; + + /* Locate stack from kernel context */ + ksp = task_thread_info(tsk)->ksp; + ksp += STACK_FRAME_OVERHEAD; /* redzone */ + ksp += sizeof(struct pt_regs); + + sp = (unsigned long *) ksp; + } unwind_stack(trace, sp, save_stack_address_nosched); + + put_task_stack(tsk); } EXPORT_SYMBOL_GPL(save_stack_trace_tsk); diff --git a/arch/openrisc/mm/cache.c b/arch/openrisc/mm/cache.c index b747bf1fc1b6..4272d9123f9e 100644 --- a/arch/openrisc/mm/cache.c +++ b/arch/openrisc/mm/cache.c @@ -20,7 +20,7 @@ #include <asm/cacheflush.h> #include <asm/tlbflush.h> -static void cache_loop(struct page *page, const unsigned int reg) +static __always_inline void cache_loop(struct page *page, const unsigned int reg) { unsigned long paddr = page_to_pfn(page) << PAGE_SHIFT; unsigned long line = paddr & ~(L1_CACHE_BYTES - 1); diff --git a/arch/parisc/include/asm/atomic.h b/arch/parisc/include/asm/atomic.h index 118953d41763..6dd4171c9530 100644 --- a/arch/parisc/include/asm/atomic.h +++ b/arch/parisc/include/asm/atomic.h @@ -212,6 +212,8 @@ atomic64_set(atomic64_t *v, s64 i) _atomic_spin_unlock_irqrestore(v, flags); } +#define atomic64_set_release(v, i) atomic64_set((v), (i)) + static __inline__ s64 atomic64_read(const atomic64_t *v) { diff --git a/arch/parisc/include/asm/barrier.h b/arch/parisc/include/asm/barrier.h index dbaaca84f27f..640d46edf32e 100644 --- a/arch/parisc/include/asm/barrier.h +++ b/arch/parisc/include/asm/barrier.h @@ -26,6 +26,67 @@ #define __smp_rmb() mb() #define __smp_wmb() mb() +#define __smp_store_release(p, v) \ +do { \ + typeof(p) __p = (p); \ + union { typeof(*p) __val; char __c[1]; } __u = \ + { .__val = (__force typeof(*p)) (v) }; \ + compiletime_assert_atomic_type(*p); \ + switch (sizeof(*p)) { \ + case 1: \ + asm volatile("stb,ma %0,0(%1)" \ + : : "r"(*(__u8 *)__u.__c), "r"(__p) \ + : "memory"); \ + break; \ + case 2: \ + asm volatile("sth,ma %0,0(%1)" \ + : : "r"(*(__u16 *)__u.__c), "r"(__p) \ + : "memory"); \ + break; \ + case 4: \ + asm volatile("stw,ma %0,0(%1)" \ + : : "r"(*(__u32 *)__u.__c), "r"(__p) \ + : "memory"); \ + break; \ + case 8: \ + if (IS_ENABLED(CONFIG_64BIT)) \ + asm volatile("std,ma %0,0(%1)" \ + : : "r"(*(__u64 *)__u.__c), "r"(__p) \ + : "memory"); \ + break; \ + } \ +} while (0) + +#define __smp_load_acquire(p) \ +({ \ + union { typeof(*p) __val; char __c[1]; } __u; \ + typeof(p) __p = (p); \ + compiletime_assert_atomic_type(*p); \ + switch (sizeof(*p)) { \ + case 1: \ + asm volatile("ldb,ma 0(%1),%0" \ + : "=r"(*(__u8 *)__u.__c) : "r"(__p) \ + : "memory"); \ + break; \ + case 2: \ + asm volatile("ldh,ma 0(%1),%0" \ + : "=r"(*(__u16 *)__u.__c) : "r"(__p) \ + : "memory"); \ + break; \ + case 4: \ + asm volatile("ldw,ma 0(%1),%0" \ + : "=r"(*(__u32 *)__u.__c) : "r"(__p) \ + : "memory"); \ + break; \ + case 8: \ + if (IS_ENABLED(CONFIG_64BIT)) \ + asm volatile("ldd,ma 0(%1),%0" \ + : "=r"(*(__u64 *)__u.__c) : "r"(__p) \ + : "memory"); \ + break; \ + } \ + __u.__val; \ +}) #include <asm-generic/barrier.h> #endif /* !__ASSEMBLY__ */ diff --git a/arch/parisc/include/asm/cmpxchg.h b/arch/parisc/include/asm/cmpxchg.h index ab5c215cf46c..a736dc59bbef 100644 --- a/arch/parisc/include/asm/cmpxchg.h +++ b/arch/parisc/include/asm/cmpxchg.h @@ -60,6 +60,7 @@ extern void __cmpxchg_called_with_bad_pointer(void); extern unsigned long __cmpxchg_u32(volatile unsigned int *m, unsigned int old, unsigned int new_); extern u64 __cmpxchg_u64(volatile u64 *ptr, u64 old, u64 new_); +extern u8 __cmpxchg_u8(volatile u8 *ptr, u8 old, u8 new_); /* don't worry...optimizer will get rid of most of this */ static inline unsigned long @@ -71,6 +72,7 @@ __cmpxchg(volatile void *ptr, unsigned long old, unsigned long new_, int size) #endif case 4: return __cmpxchg_u32((unsigned int *)ptr, (unsigned int)old, (unsigned int)new_); + case 1: return __cmpxchg_u8((u8 *)ptr, old & 0xff, new_ & 0xff); } __cmpxchg_called_with_bad_pointer(); return old; diff --git a/arch/parisc/kernel/irq.c b/arch/parisc/kernel/irq.c index 0ca254085a66..c152c30c2d06 100644 --- a/arch/parisc/kernel/irq.c +++ b/arch/parisc/kernel/irq.c @@ -380,7 +380,11 @@ static inline int eirr_to_irq(unsigned long eirr) /* * IRQ STACK - used for irq handler */ +#ifdef CONFIG_64BIT +#define IRQ_STACK_SIZE (4096 << 4) /* 64k irq stack size */ +#else #define IRQ_STACK_SIZE (4096 << 3) /* 32k irq stack size */ +#endif union irq_stack_union { unsigned long stack[IRQ_STACK_SIZE/sizeof(unsigned long)]; diff --git a/arch/parisc/lib/bitops.c b/arch/parisc/lib/bitops.c index 70ffbcf889b8..2e4d1f05a926 100644 --- a/arch/parisc/lib/bitops.c +++ b/arch/parisc/lib/bitops.c @@ -79,3 +79,15 @@ unsigned long __cmpxchg_u32(volatile unsigned int *ptr, unsigned int old, unsign _atomic_spin_unlock_irqrestore(ptr, flags); return (unsigned long)prev; } + +u8 __cmpxchg_u8(volatile u8 *ptr, u8 old, u8 new) +{ + unsigned long flags; + u8 prev; + + _atomic_spin_lock_irqsave(ptr, flags); + if ((prev = *ptr) == old) + *ptr = new; + _atomic_spin_unlock_irqrestore(ptr, flags); + return prev; +} diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c index aae9b0d71c1e..10a52664e29f 100644 --- a/arch/parisc/mm/init.c +++ b/arch/parisc/mm/init.c @@ -607,7 +607,7 @@ void __init mem_init(void) > BITS_PER_LONG); high_memory = __va((max_pfn << PAGE_SHIFT)); - set_max_mapnr(page_to_pfn(virt_to_page(high_memory - 1)) + 1); + set_max_mapnr(max_low_pfn); free_all_bootmem(); #ifdef CONFIG_PA11 diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 6f475dc5829b..f0e09d5f0bed 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -139,7 +139,7 @@ config PPC select ARCH_HAS_MEMBARRIER_CALLBACKS select ARCH_HAS_SCALED_CPUTIME if VIRT_CPU_ACCOUNTING_NATIVE select ARCH_HAS_SG_CHAIN - select ARCH_HAS_STRICT_KERNEL_RWX if ((PPC_BOOK3S_64 || PPC32) && !RELOCATABLE && !HIBERNATION) + select ARCH_HAS_STRICT_KERNEL_RWX if (PPC32 && !HIBERNATION) select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST select ARCH_HAS_UACCESS_FLUSHCACHE if PPC64 select ARCH_HAS_UBSAN_SANITIZE_ALL @@ -152,6 +152,7 @@ config PPC select ARCH_USE_BUILTIN_BSWAP select ARCH_USE_CMPXCHG_LOCKREF if PPC64 select ARCH_WANT_IPC_PARSE_VERSION + select ARCH_WANT_IRQS_OFF_ACTIVATE_MM select ARCH_WEAK_RELEASE_ACQUIRE select BINFMT_ELF select BUILDTIME_EXTABLE_SORT @@ -207,7 +208,7 @@ config PPC select HAVE_MEMBLOCK_NODE_MAP select HAVE_MOD_ARCH_SPECIFIC select HAVE_NMI if PERF_EVENTS || (PPC64 && PPC_BOOK3S) - select HAVE_HARDLOCKUP_DETECTOR_ARCH if (PPC64 && PPC_BOOK3S) + select HAVE_HARDLOCKUP_DETECTOR_ARCH if PPC64 && PPC_BOOK3S && SMP select HAVE_OPROFILE select HAVE_OPTPROBES if PPC64 select HAVE_PERF_EVENTS @@ -708,7 +709,7 @@ config PPC_64K_PAGES config PPC_256K_PAGES bool "256k page size" - depends on 44x && !STDBINUTILS + depends on 44x && !STDBINUTILS && !PPC_47x help Make the page size 256k. @@ -1009,6 +1010,19 @@ config FSL_RIO source "drivers/rapidio/Kconfig" +config PPC_RTAS_FILTER + bool "Enable filtering of RTAS syscalls" + default y + depends on PPC_RTAS + help + The RTAS syscall API has security issues that could be used to + compromise system integrity. This option enforces restrictions on the + RTAS calls and arguments passed by userspace programs to mitigate + these issues. + + Say Y unless you know what you are doing and the filter is causing + problems for you. + endmenu config NONSTATIC_KERNEL diff --git a/arch/powerpc/Kconfig.debug b/arch/powerpc/Kconfig.debug index fd63cd914a74..ffe0cf0f0bea 100644 --- a/arch/powerpc/Kconfig.debug +++ b/arch/powerpc/Kconfig.debug @@ -350,6 +350,7 @@ config PPC_EARLY_DEBUG_CPM_ADDR config FAIL_IOMMU bool "Fault-injection capability for IOMMU" depends on FAULT_INJECTION + depends on PCI || IBMVIO help Provide fault-injection capability for IOMMU. Each device can be selectively enabled via the fail_iommu property. diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index 8954108df457..f51e21ea5349 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -251,7 +251,6 @@ endif cpu-as-$(CONFIG_4xx) += -Wa,-m405 cpu-as-$(CONFIG_ALTIVEC) += $(call as-option,-Wa$(comma)-maltivec) -cpu-as-$(CONFIG_E200) += -Wa,-me200 cpu-as-$(CONFIG_E500) += -Wa,-me500 # When using '-many -mpower4' gas will first try and find a matching power4 diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile index 7d5ddf53750c..7a83b5e136e0 100644 --- a/arch/powerpc/boot/Makefile +++ b/arch/powerpc/boot/Makefile @@ -122,7 +122,7 @@ src-wlib-y := string.S crt0.S stdio.c decompress.c main.c \ elf_util.c $(zlib-y) devtree.c stdlib.c \ oflib.c ofconsole.c cuboot.c -src-wlib-$(CONFIG_PPC_MPC52XX) += mpc52xx-psc.c +src-wlib-$(CONFIG_PPC_MPC52xx) += mpc52xx-psc.c src-wlib-$(CONFIG_PPC64_BOOT_WRAPPER) += opal-calls.S opal.c ifndef CONFIG_PPC64_BOOT_WRAPPER src-wlib-y += crtsavres.S diff --git a/arch/powerpc/boot/serial.c b/arch/powerpc/boot/serial.c index 48e3743faedf..83c78427c20b 100644 --- a/arch/powerpc/boot/serial.c +++ b/arch/powerpc/boot/serial.c @@ -127,7 +127,7 @@ int serial_console_init(void) dt_is_compatible(devp, "fsl,cpm2-smc-uart")) rc = cpm_console_init(devp, &serial_cd); #endif -#ifdef CONFIG_PPC_MPC52XX +#ifdef CONFIG_PPC_MPC52xx else if (dt_is_compatible(devp, "fsl,mpc5200-psc-uart")) rc = mpc5200_psc_console_init(devp, &serial_cd); #endif diff --git a/arch/powerpc/configs/85xx-hw.config b/arch/powerpc/configs/85xx-hw.config index c03d0fb16665..9144e4cbc42e 100644 --- a/arch/powerpc/configs/85xx-hw.config +++ b/arch/powerpc/configs/85xx-hw.config @@ -2,7 +2,6 @@ CONFIG_AQUANTIA_PHY=y CONFIG_AT803X_PHY=y CONFIG_ATA=y CONFIG_BLK_DEV_SD=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_BLK_DEV_SR=y CONFIG_BROADCOM_PHY=y CONFIG_C293_PCIE=y diff --git a/arch/powerpc/configs/amigaone_defconfig b/arch/powerpc/configs/amigaone_defconfig index 12f397d403c6..8ddab7c240d9 100644 --- a/arch/powerpc/configs/amigaone_defconfig +++ b/arch/powerpc/configs/amigaone_defconfig @@ -48,7 +48,6 @@ CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=y CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=y CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_SYM53C8XX_2=y diff --git a/arch/powerpc/configs/chrp32_defconfig b/arch/powerpc/configs/chrp32_defconfig index a203b1cf67d3..796d34734b91 100644 --- a/arch/powerpc/configs/chrp32_defconfig +++ b/arch/powerpc/configs/chrp32_defconfig @@ -46,7 +46,6 @@ CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=y CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=y CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_SYM53C8XX_2=y diff --git a/arch/powerpc/configs/g5_defconfig b/arch/powerpc/configs/g5_defconfig index 67c39f4acede..0123e3b00901 100644 --- a/arch/powerpc/configs/g5_defconfig +++ b/arch/powerpc/configs/g5_defconfig @@ -63,7 +63,6 @@ CONFIG_CDROM_PKTCDVD=m CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=y CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=y CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_SPI_ATTRS=y diff --git a/arch/powerpc/configs/maple_defconfig b/arch/powerpc/configs/maple_defconfig index 59e47ec85336..9df11592880d 100644 --- a/arch/powerpc/configs/maple_defconfig +++ b/arch/powerpc/configs/maple_defconfig @@ -42,7 +42,6 @@ CONFIG_BLK_DEV_RAM_SIZE=8192 # CONFIG_SCSI_PROC_FS is not set CONFIG_BLK_DEV_SD=y CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=y CONFIG_SCSI_IPR=y CONFIG_ATA=y diff --git a/arch/powerpc/configs/pasemi_defconfig b/arch/powerpc/configs/pasemi_defconfig index 6daa56f8895c..60839eeada8b 100644 --- a/arch/powerpc/configs/pasemi_defconfig +++ b/arch/powerpc/configs/pasemi_defconfig @@ -61,7 +61,6 @@ CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=y CONFIG_CHR_DEV_OSST=y CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=y CONFIG_CHR_DEV_SCH=y CONFIG_SCSI_CONSTANTS=y @@ -111,7 +110,6 @@ CONFIG_FB_NVIDIA=y CONFIG_FB_NVIDIA_I2C=y CONFIG_FB_RADEON=y # CONFIG_LCD_CLASS_DEVICE is not set -CONFIG_VGACON_SOFT_SCROLLBACK=y CONFIG_LOGO=y CONFIG_SOUND=y CONFIG_SND=y diff --git a/arch/powerpc/configs/pmac32_defconfig b/arch/powerpc/configs/pmac32_defconfig index 62948d198d7f..212a68b65d9f 100644 --- a/arch/powerpc/configs/pmac32_defconfig +++ b/arch/powerpc/configs/pmac32_defconfig @@ -121,7 +121,6 @@ CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=y CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=y CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_FC_ATTRS=y diff --git a/arch/powerpc/configs/powernv_defconfig b/arch/powerpc/configs/powernv_defconfig index 6ab34e60495f..5a533c9f6b3d 100644 --- a/arch/powerpc/configs/powernv_defconfig +++ b/arch/powerpc/configs/powernv_defconfig @@ -109,7 +109,6 @@ CONFIG_BLK_DEV_NVME=y CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=m CONFIG_BLK_DEV_SR=m -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=m CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_SCAN_ASYNC=y diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig index 5033e630afea..d9fdf05599c9 100644 --- a/arch/powerpc/configs/ppc64_defconfig +++ b/arch/powerpc/configs/ppc64_defconfig @@ -93,7 +93,6 @@ CONFIG_VIRTIO_BLK=m CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=m CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=y CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_FC_ATTRS=y diff --git a/arch/powerpc/configs/ppc64e_defconfig b/arch/powerpc/configs/ppc64e_defconfig index 41d85cb3c9a2..a5e36faef391 100644 --- a/arch/powerpc/configs/ppc64e_defconfig +++ b/arch/powerpc/configs/ppc64e_defconfig @@ -61,7 +61,6 @@ CONFIG_BLK_DEV_RAM_SIZE=65536 CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=y CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=y CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_FC_ATTRS=y diff --git a/arch/powerpc/configs/ppc6xx_defconfig b/arch/powerpc/configs/ppc6xx_defconfig index 7ee736f20774..e30af76f4753 100644 --- a/arch/powerpc/configs/ppc6xx_defconfig +++ b/arch/powerpc/configs/ppc6xx_defconfig @@ -374,7 +374,6 @@ CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=m CONFIG_CHR_DEV_OSST=m CONFIG_BLK_DEV_SR=m -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=y CONFIG_CHR_DEV_SCH=m CONFIG_SCSI_ENCLOSURE=m @@ -780,7 +779,6 @@ CONFIG_FB_TRIDENT=m CONFIG_FB_SM501=m CONFIG_FB_IBM_GXT4500=y CONFIG_LCD_PLATFORM=m -CONFIG_VGACON_SOFT_SCROLLBACK=y CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_FRAMEBUFFER_CONSOLE_ROTATION=y CONFIG_LOGO=y diff --git a/arch/powerpc/configs/pseries_defconfig b/arch/powerpc/configs/pseries_defconfig index 0dd5cf7b566d..780552be29f9 100644 --- a/arch/powerpc/configs/pseries_defconfig +++ b/arch/powerpc/configs/pseries_defconfig @@ -97,7 +97,6 @@ CONFIG_VIRTIO_BLK=m CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=m CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=y CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_FC_ATTRS=y diff --git a/arch/powerpc/configs/skiroot_defconfig b/arch/powerpc/configs/skiroot_defconfig index ffeaed63675b..82611dea62bd 100644 --- a/arch/powerpc/configs/skiroot_defconfig +++ b/arch/powerpc/configs/skiroot_defconfig @@ -77,7 +77,6 @@ CONFIG_EEPROM_AT24=y # CONFIG_CXL is not set CONFIG_BLK_DEV_SD=m CONFIG_BLK_DEV_SR=m -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=m CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_SCAN_ASYNC=y diff --git a/arch/powerpc/include/asm/bitops.h b/arch/powerpc/include/asm/bitops.h index ff71566dadee..76db1c5000bd 100644 --- a/arch/powerpc/include/asm/bitops.h +++ b/arch/powerpc/include/asm/bitops.h @@ -221,15 +221,34 @@ static __inline__ void __clear_bit_unlock(int nr, volatile unsigned long *addr) */ static __inline__ int fls(unsigned int x) { - return 32 - __builtin_clz(x); + int lz; + + if (__builtin_constant_p(x)) + return x ? 32 - __builtin_clz(x) : 0; + asm("cntlzw %0,%1" : "=r" (lz) : "r" (x)); + return 32 - lz; } #include <asm-generic/bitops/builtin-__fls.h> +/* + * 64-bit can do this using one cntlzd (count leading zeroes doubleword) + * instruction; for 32-bit we use the generic version, which does two + * 32-bit fls calls. + */ +#ifdef CONFIG_PPC64 static __inline__ int fls64(__u64 x) { - return 64 - __builtin_clzll(x); + int lz; + + if (__builtin_constant_p(x)) + return x ? 64 - __builtin_clzll(x) : 0; + asm("cntlzd %0,%1" : "=r" (lz) : "r" (x)); + return 64 - lz; } +#else +#include <asm-generic/bitops/fls64.h> +#endif #ifdef CONFIG_PPC64 unsigned int __arch_hweight8(unsigned int w); diff --git a/arch/powerpc/include/asm/book3s/32/pgtable.h b/arch/powerpc/include/asm/book3s/32/pgtable.h index 751cf931bb3f..a4f4820826b7 100644 --- a/arch/powerpc/include/asm/book3s/32/pgtable.h +++ b/arch/powerpc/include/asm/book3s/32/pgtable.h @@ -434,9 +434,9 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr, if (pte_val(*ptep) & _PAGE_HASHPTE) flush_hash_entry(mm, ptep, addr); __asm__ __volatile__("\ - stw%U0%X0 %2,%0\n\ + stw%X0 %2,%0\n\ eieio\n\ - stw%U0%X0 %L2,%1" + stw%X1 %L2,%1" : "=m" (*ptep), "=m" (*((unsigned char *)ptep+4)) : "r" (pte) : "memory"); diff --git a/arch/powerpc/include/asm/book3s/64/hash-4k.h b/arch/powerpc/include/asm/book3s/64/hash-4k.h index 9a3798660cef..fc68c0fc08b5 100644 --- a/arch/powerpc/include/asm/book3s/64/hash-4k.h +++ b/arch/powerpc/include/asm/book3s/64/hash-4k.h @@ -145,6 +145,12 @@ extern pmd_t hash__pmdp_huge_get_and_clear(struct mm_struct *mm, extern int hash__has_transparent_hugepage(void); #endif +static inline pmd_t hash__pmd_mkdevmap(pmd_t pmd) +{ + BUG(); + return pmd; +} + #endif /* !__ASSEMBLY__ */ #endif /* _ASM_POWERPC_BOOK3S_64_HASH_4K_H */ diff --git a/arch/powerpc/include/asm/book3s/64/hash-64k.h b/arch/powerpc/include/asm/book3s/64/hash-64k.h index f82ee8a3b561..790e4a946f6e 100644 --- a/arch/powerpc/include/asm/book3s/64/hash-64k.h +++ b/arch/powerpc/include/asm/book3s/64/hash-64k.h @@ -233,7 +233,7 @@ static inline void mark_hpte_slot_valid(unsigned char *hpte_slot_array, */ static inline int hash__pmd_trans_huge(pmd_t pmd) { - return !!((pmd_val(pmd) & (_PAGE_PTE | H_PAGE_THP_HUGE)) == + return !!((pmd_val(pmd) & (_PAGE_PTE | H_PAGE_THP_HUGE | _PAGE_DEVMAP)) == (_PAGE_PTE | H_PAGE_THP_HUGE)); } @@ -259,6 +259,12 @@ extern pmd_t hash__pmdp_huge_get_and_clear(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp); extern int hash__has_transparent_hugepage(void); #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + +static inline pmd_t hash__pmd_mkdevmap(pmd_t pmd) +{ + return __pmd(pmd_val(pmd) | (_PAGE_PTE | H_PAGE_THP_HUGE | _PAGE_DEVMAP)); +} + #endif /* __ASSEMBLY__ */ #endif /* _ASM_POWERPC_BOOK3S_64_HASH_64K_H */ diff --git a/arch/powerpc/include/asm/book3s/64/kup-radix.h b/arch/powerpc/include/asm/book3s/64/kup-radix.h new file mode 100644 index 000000000000..aa54ac2e5659 --- /dev/null +++ b/arch/powerpc/include/asm/book3s/64/kup-radix.h @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_POWERPC_BOOK3S_64_KUP_RADIX_H +#define _ASM_POWERPC_BOOK3S_64_KUP_RADIX_H + +DECLARE_STATIC_KEY_FALSE(uaccess_flush_key); + +/* Prototype for function defined in exceptions-64s.S */ +void do_uaccess_flush(void); + +static __always_inline void allow_user_access(void __user *to, const void __user *from, + unsigned long size) +{ +} + +static inline void prevent_user_access(void __user *to, const void __user *from, + unsigned long size) +{ + if (static_branch_unlikely(&uaccess_flush_key)) + do_uaccess_flush(); +} + +#endif /* _ASM_POWERPC_BOOK3S_64_KUP_RADIX_H */ diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index 855dbae6d351..008eb63fa851 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -985,10 +985,25 @@ extern struct page *pgd_page(pgd_t pgd); #define pud_page_vaddr(pud) __va(pud_val(pud) & ~PUD_MASKED_BITS) #define pgd_page_vaddr(pgd) __va(pgd_val(pgd) & ~PGD_MASKED_BITS) -#define pgd_index(address) (((address) >> (PGDIR_SHIFT)) & (PTRS_PER_PGD - 1)) -#define pud_index(address) (((address) >> (PUD_SHIFT)) & (PTRS_PER_PUD - 1)) -#define pmd_index(address) (((address) >> (PMD_SHIFT)) & (PTRS_PER_PMD - 1)) -#define pte_index(address) (((address) >> (PAGE_SHIFT)) & (PTRS_PER_PTE - 1)) +static inline unsigned long pgd_index(unsigned long address) +{ + return (address >> PGDIR_SHIFT) & (PTRS_PER_PGD - 1); +} + +static inline unsigned long pud_index(unsigned long address) +{ + return (address >> PUD_SHIFT) & (PTRS_PER_PUD - 1); +} + +static inline unsigned long pmd_index(unsigned long address) +{ + return (address >> PMD_SHIFT) & (PTRS_PER_PMD - 1); +} + +static inline unsigned long pte_index(unsigned long address) +{ + return (address >> PAGE_SHIFT) & (PTRS_PER_PTE - 1); +} /* * Find an entry in a page-table-directory. We combine the address region @@ -1253,7 +1268,9 @@ extern void serialize_against_pte_lookup(struct mm_struct *mm); static inline pmd_t pmd_mkdevmap(pmd_t pmd) { - return __pmd(pmd_val(pmd) | (_PAGE_PTE | _PAGE_DEVMAP)); + if (radix_enabled()) + return radix__pmd_mkdevmap(pmd); + return hash__pmd_mkdevmap(pmd); } static inline int pmd_devmap(pmd_t pmd) diff --git a/arch/powerpc/include/asm/book3s/64/radix.h b/arch/powerpc/include/asm/book3s/64/radix.h index 7d1a3d1543fc..04b2bffbc5c9 100644 --- a/arch/powerpc/include/asm/book3s/64/radix.h +++ b/arch/powerpc/include/asm/book3s/64/radix.h @@ -204,8 +204,10 @@ static inline void radix__set_pte_at(struct mm_struct *mm, unsigned long addr, * from ptesync, it should probably go into update_mmu_cache, rather * than set_pte_at (which is used to set ptes unrelated to faults). * - * Spurious faults to vmalloc region are not tolerated, so there is - * a ptesync in flush_cache_vmap. + * Spurious faults from the kernel memory are not tolerated, so there + * is a ptesync in flush_cache_vmap, and __map_kernel_page() follows + * the pte update sequence from ISA Book III 6.10 Translation Table + * Update Synchronization Requirements. */ } @@ -255,6 +257,11 @@ extern pmd_t radix__pmdp_huge_get_and_clear(struct mm_struct *mm, extern int radix__has_transparent_hugepage(void); #endif +static inline pmd_t radix__pmd_mkdevmap(pmd_t pmd) +{ + return __pmd(pmd_val(pmd) | (_PAGE_PTE | _PAGE_DEVMAP)); +} + extern int __meminit radix__vmemmap_create_mapping(unsigned long start, unsigned long page_size, unsigned long phys); diff --git a/arch/powerpc/include/asm/code-patching.h b/arch/powerpc/include/asm/code-patching.h index 31733a95bbd0..4cd6e19ee90f 100644 --- a/arch/powerpc/include/asm/code-patching.h +++ b/arch/powerpc/include/asm/code-patching.h @@ -52,7 +52,7 @@ void __patch_exception(int exc, unsigned long addr); #endif #define OP_RT_RA_MASK 0xffff0000UL -#define LIS_R2 0x3c020000UL +#define LIS_R2 0x3c400000UL #define ADDIS_R2_R12 0x3c4c0000UL #define ADDI_R2_R2 0x38420000UL diff --git a/arch/powerpc/include/asm/cpu_has_feature.h b/arch/powerpc/include/asm/cpu_has_feature.h index 7897d16e0990..727d4b321937 100644 --- a/arch/powerpc/include/asm/cpu_has_feature.h +++ b/arch/powerpc/include/asm/cpu_has_feature.h @@ -7,7 +7,7 @@ #include <linux/bug.h> #include <asm/cputable.h> -static inline bool early_cpu_has_feature(unsigned long feature) +static __always_inline bool early_cpu_has_feature(unsigned long feature) { return !!((CPU_FTRS_ALWAYS & feature) || (CPU_FTRS_POSSIBLE & cur_cpu_spec->cpu_features & feature)); @@ -46,7 +46,7 @@ static __always_inline bool cpu_has_feature(unsigned long feature) return static_branch_likely(&cpu_feature_keys[i]); } #else -static inline bool cpu_has_feature(unsigned long feature) +static __always_inline bool cpu_has_feature(unsigned long feature) { return early_cpu_has_feature(feature); } diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h index 59b35b93eade..d90093a88e09 100644 --- a/arch/powerpc/include/asm/cputable.h +++ b/arch/powerpc/include/asm/cputable.h @@ -411,7 +411,6 @@ static inline void cpu_feature_keys_init(void) { } CPU_FTR_DBELL | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \ CPU_FTR_DEBUG_LVL_EXC | CPU_FTR_EMB_HV | CPU_FTR_ALTIVEC_COMP | \ CPU_FTR_CELL_TB_BUG | CPU_FTR_SMT) -#define CPU_FTRS_GENERIC_32 (CPU_FTR_COMMON | CPU_FTR_NODSISRALIGN) /* 64-bit CPUs */ #define CPU_FTRS_PPC970 (CPU_FTR_LWSYNC | \ @@ -509,8 +508,6 @@ enum { CPU_FTRS_7447 | CPU_FTRS_7447A | CPU_FTRS_82XX | CPU_FTRS_G2_LE | CPU_FTRS_E300 | CPU_FTRS_E300C2 | CPU_FTRS_CLASSIC32 | -#else - CPU_FTRS_GENERIC_32 | #endif #ifdef CONFIG_PPC_8xx CPU_FTRS_8XX | @@ -585,8 +582,6 @@ enum { CPU_FTRS_7447 & CPU_FTRS_7447A & CPU_FTRS_82XX & CPU_FTRS_G2_LE & CPU_FTRS_E300 & CPU_FTRS_E300C2 & CPU_FTRS_CLASSIC32 & -#else - CPU_FTRS_GENERIC_32 & #endif #ifdef CONFIG_PPC_8xx CPU_FTRS_8XX & diff --git a/arch/powerpc/include/asm/dcr-native.h b/arch/powerpc/include/asm/dcr-native.h index 151dff555f50..9d9e323f5e9b 100644 --- a/arch/powerpc/include/asm/dcr-native.h +++ b/arch/powerpc/include/asm/dcr-native.h @@ -66,8 +66,8 @@ static inline void mtdcrx(unsigned int reg, unsigned int val) #define mfdcr(rn) \ ({unsigned int rval; \ if (__builtin_constant_p(rn) && rn < 1024) \ - asm volatile("mfdcr %0," __stringify(rn) \ - : "=r" (rval)); \ + asm volatile("mfdcr %0, %1" : "=r" (rval) \ + : "n" (rn)); \ else if (likely(cpu_has_feature(CPU_FTR_INDEXED_DCR))) \ rval = mfdcrx(rn); \ else \ @@ -77,8 +77,8 @@ static inline void mtdcrx(unsigned int reg, unsigned int val) #define mtdcr(rn, v) \ do { \ if (__builtin_constant_p(rn) && rn < 1024) \ - asm volatile("mtdcr " __stringify(rn) ",%0" \ - : : "r" (v)); \ + asm volatile("mtdcr %0, %1" \ + : : "n" (rn), "r" (v)); \ else if (likely(cpu_has_feature(CPU_FTR_INDEXED_DCR))) \ mtdcrx(rn, v); \ else \ diff --git a/arch/powerpc/include/asm/drmem.h b/arch/powerpc/include/asm/drmem.h index 7c1d8e74b25d..8b196720e9a0 100644 --- a/arch/powerpc/include/asm/drmem.h +++ b/arch/powerpc/include/asm/drmem.h @@ -12,6 +12,8 @@ #ifndef _ASM_POWERPC_LMB_H #define _ASM_POWERPC_LMB_H +#include <linux/sched.h> + struct drmem_lmb { u64 base_addr; u32 drc_index; @@ -22,18 +24,32 @@ struct drmem_lmb { struct drmem_lmb_info { struct drmem_lmb *lmbs; int n_lmbs; - u32 lmb_size; + u64 lmb_size; }; extern struct drmem_lmb_info *drmem_info; +static inline struct drmem_lmb *drmem_lmb_next(struct drmem_lmb *lmb, + const struct drmem_lmb *start) +{ + /* + * DLPAR code paths can take several milliseconds per element + * when interacting with firmware. Ensure that we don't + * unfairly monopolize the CPU. + */ + if (((++lmb - start) % 16) == 0) + cond_resched(); + + return lmb; +} + #define for_each_drmem_lmb_in_range(lmb, start, end) \ - for ((lmb) = (start); (lmb) <= (end); (lmb)++) + for ((lmb) = (start); (lmb) < (end); lmb = drmem_lmb_next(lmb, start)) #define for_each_drmem_lmb(lmb) \ for_each_drmem_lmb_in_range((lmb), \ &drmem_info->lmbs[0], \ - &drmem_info->lmbs[drmem_info->n_lmbs - 1]) + &drmem_info->lmbs[drmem_info->n_lmbs]) /* * The of_drconf_cell_v1 struct defines the layout of the LMB data @@ -67,7 +83,7 @@ struct of_drconf_cell_v2 { #define DRCONF_MEM_AI_INVALID 0x00000040 #define DRCONF_MEM_RESERVED 0x00000080 -static inline u32 drmem_lmb_size(void) +static inline u64 drmem_lmb_size(void) { return drmem_info->lmb_size; } diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h index a86feddddad0..35fb5b11955a 100644 --- a/arch/powerpc/include/asm/exception-64s.h +++ b/arch/powerpc/include/asm/exception-64s.h @@ -90,11 +90,18 @@ nop; \ nop +#define ENTRY_FLUSH_SLOT \ + ENTRY_FLUSH_FIXUP_SECTION; \ + nop; \ + nop; \ + nop; + /* * r10 must be free to use, r13 must be paca */ #define INTERRUPT_TO_KERNEL \ - STF_ENTRY_BARRIER_SLOT + STF_ENTRY_BARRIER_SLOT; \ + ENTRY_FLUSH_SLOT /* * Macros for annotating the expected destination of (h)rfid diff --git a/arch/powerpc/include/asm/feature-fixups.h b/arch/powerpc/include/asm/feature-fixups.h index 40a6c9261a6b..5bf3f0779b93 100644 --- a/arch/powerpc/include/asm/feature-fixups.h +++ b/arch/powerpc/include/asm/feature-fixups.h @@ -205,6 +205,22 @@ label##3: \ FTR_ENTRY_OFFSET 955b-956b; \ .popsection; +#define UACCESS_FLUSH_FIXUP_SECTION \ +959: \ + .pushsection __uaccess_flush_fixup,"a"; \ + .align 2; \ +960: \ + FTR_ENTRY_OFFSET 959b-960b; \ + .popsection; + +#define ENTRY_FLUSH_FIXUP_SECTION \ +957: \ + .pushsection __entry_flush_fixup,"a"; \ + .align 2; \ +958: \ + FTR_ENTRY_OFFSET 957b-958b; \ + .popsection; + #define RFI_FLUSH_FIXUP_SECTION \ 951: \ .pushsection __rfi_flush_fixup,"a"; \ @@ -237,8 +253,11 @@ label##3: \ #include <linux/types.h> extern long stf_barrier_fallback; +extern long entry_flush_fallback; extern long __start___stf_entry_barrier_fixup, __stop___stf_entry_barrier_fixup; extern long __start___stf_exit_barrier_fixup, __stop___stf_exit_barrier_fixup; +extern long __start___uaccess_flush_fixup, __stop___uaccess_flush_fixup; +extern long __start___entry_flush_fixup, __stop___entry_flush_fixup; extern long __start___rfi_flush_fixup, __stop___rfi_flush_fixup; extern long __start___barrier_nospec_fixup, __stop___barrier_nospec_fixup; extern long __start__btb_flush_fixup, __stop__btb_flush_fixup; diff --git a/arch/powerpc/include/asm/futex.h b/arch/powerpc/include/asm/futex.h index 2a7b01f97a56..1eabc20dddd3 100644 --- a/arch/powerpc/include/asm/futex.h +++ b/arch/powerpc/include/asm/futex.h @@ -35,6 +35,7 @@ static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval, { int oldval = 0, ret; + allow_write_to_user(uaddr, sizeof(*uaddr)); pagefault_disable(); switch (op) { @@ -61,6 +62,7 @@ static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval, *oval = oldval; + prevent_write_to_user(uaddr, sizeof(*uaddr)); return ret; } @@ -74,6 +76,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32))) return -EFAULT; + allow_write_to_user(uaddr, sizeof(*uaddr)); __asm__ __volatile__ ( PPC_ATOMIC_ENTRY_BARRIER "1: lwarx %1,0,%3 # futex_atomic_cmpxchg_inatomic\n\ @@ -94,6 +97,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, : "cc", "memory"); *uval = prev; + prevent_write_to_user(uaddr, sizeof(*uaddr)); return ret; } diff --git a/arch/powerpc/include/asm/kup.h b/arch/powerpc/include/asm/kup.h new file mode 100644 index 000000000000..f0f8e36ad71f --- /dev/null +++ b/arch/powerpc/include/asm/kup.h @@ -0,0 +1,40 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_POWERPC_KUP_H_ +#define _ASM_POWERPC_KUP_H_ + +#ifndef __ASSEMBLY__ + +#include <asm/pgtable.h> + +#ifdef CONFIG_PPC_BOOK3S_64 +#include <asm/book3s/64/kup-radix.h> +#else +static inline void allow_user_access(void __user *to, const void __user *from, + unsigned long size) { } +static inline void prevent_user_access(void __user *to, const void __user *from, + unsigned long size) { } +#endif /* CONFIG_PPC_BOOK3S_64 */ + +static inline void allow_read_from_user(const void __user *from, unsigned long size) +{ + allow_user_access(NULL, from, size); +} + +static inline void allow_write_to_user(void __user *to, unsigned long size) +{ + allow_user_access(to, NULL, size); +} + +static inline void prevent_read_from_user(const void __user *from, unsigned long size) +{ + prevent_user_access(NULL, from, size); +} + +static inline void prevent_write_to_user(void __user *to, unsigned long size) +{ + prevent_user_access(to, NULL, size); +} + +#endif /* !__ASSEMBLY__ */ + +#endif /* _ASM_POWERPC_KUP_H_ */ diff --git a/arch/powerpc/include/asm/kvm_asm.h b/arch/powerpc/include/asm/kvm_asm.h index a790d5cf6ea3..684e8ae00d16 100644 --- a/arch/powerpc/include/asm/kvm_asm.h +++ b/arch/powerpc/include/asm/kvm_asm.h @@ -163,4 +163,7 @@ #define KVM_INST_FETCH_FAILED -1 +/* Extract PO and XOP opcode fields */ +#define PO_XOP_OPCODE_MASK 0xfc0007fe + #endif /* __POWERPC_KVM_ASM_H__ */ diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index 2f95e38f0549..7b54d8412367 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -68,7 +68,8 @@ #define KVM_ARCH_WANT_MMU_NOTIFIER extern int kvm_unmap_hva_range(struct kvm *kvm, - unsigned long start, unsigned long end); + unsigned long start, unsigned long end, + bool blockable); extern int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end); extern int kvm_test_age_hva(struct kvm *kvm, unsigned long hva); extern void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h index a47de82fb8e2..bda87cbf106d 100644 --- a/arch/powerpc/include/asm/machdep.h +++ b/arch/powerpc/include/asm/machdep.h @@ -71,6 +71,9 @@ struct machdep_calls { int (*pcibios_root_bridge_prepare)(struct pci_host_bridge *bridge); + /* finds all the pci_controllers present at boot */ + void (*discover_phbs)(void); + /* To setup PHBs when using automatic OF platform driver for PCI */ int (*pci_setup_phb)(struct pci_controller *host); diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h index ae953958c0f3..d93bdcaa4a46 100644 --- a/arch/powerpc/include/asm/mmu_context.h +++ b/arch/powerpc/include/asm/mmu_context.h @@ -204,7 +204,7 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, */ static inline void activate_mm(struct mm_struct *prev, struct mm_struct *next) { - switch_mm(prev, next, current); + switch_mm_irqs_off(prev, next, current); } /* We don't currently use enter_lazy_tlb() for anything */ diff --git a/arch/powerpc/include/asm/nohash/pgtable.h b/arch/powerpc/include/asm/nohash/pgtable.h index b321c82b3624..913878d8e3be 100644 --- a/arch/powerpc/include/asm/nohash/pgtable.h +++ b/arch/powerpc/include/asm/nohash/pgtable.h @@ -151,9 +151,9 @@ 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%U0%X0 %2,%0\n\ + stw%X0 %2,%0\n\ eieio\n\ - stw%U0%X0 %L2,%1" + stw%X1 %L2,%1" : "=m" (*ptep), "=m" (*((unsigned char *)ptep+4)) : "r" (pte) : "memory"); return; diff --git a/arch/powerpc/include/asm/percpu.h b/arch/powerpc/include/asm/percpu.h index dce863a7635c..8e5b7d0b851c 100644 --- a/arch/powerpc/include/asm/percpu.h +++ b/arch/powerpc/include/asm/percpu.h @@ -10,8 +10,6 @@ #ifdef CONFIG_SMP -#include <asm/paca.h> - #define __my_cpu_offset local_paca->data_offset #endif /* CONFIG_SMP */ @@ -19,4 +17,6 @@ #include <asm-generic/percpu.h> +#include <asm/paca.h> + #endif /* _ASM_POWERPC_PERCPU_H_ */ diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h index 52fadded5c1e..45bbcffcb7b6 100644 --- a/arch/powerpc/include/asm/processor.h +++ b/arch/powerpc/include/asm/processor.h @@ -386,7 +386,6 @@ struct thread_struct { #else #define INIT_THREAD { \ .ksp = INIT_SP, \ - .regs = (struct pt_regs *)INIT_SP - 1, /* XXX bogus, I think */ \ .addr_limit = KERNEL_DS, \ .fpexc_mode = 0, \ .ppr = INIT_PPR, \ diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index af9971661512..494b0283f212 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -788,7 +788,7 @@ #define THRM1_TIN (1 << 31) #define THRM1_TIV (1 << 30) #define THRM1_THRES(x) ((x&0x7f)<<23) -#define THRM3_SITV(x) ((x&0x3fff)<<1) +#define THRM3_SITV(x) ((x & 0x1fff) << 1) #define THRM1_TID (1<<2) #define THRM1_TIE (1<<1) #define THRM1_V (1<<0) diff --git a/arch/powerpc/include/asm/security_features.h b/arch/powerpc/include/asm/security_features.h index ccf44c135389..3b45a64e491e 100644 --- a/arch/powerpc/include/asm/security_features.h +++ b/arch/powerpc/include/asm/security_features.h @@ -84,12 +84,19 @@ static inline bool security_ftr_enabled(unsigned long feature) // Software required to flush link stack on context switch #define SEC_FTR_FLUSH_LINK_STACK 0x0000000000001000ull +// The L1-D cache should be flushed when entering the kernel +#define SEC_FTR_L1D_FLUSH_ENTRY 0x0000000000004000ull + +// The L1-D cache should be flushed after user accesses from the kernel +#define SEC_FTR_L1D_FLUSH_UACCESS 0x0000000000008000ull // Features enabled by default #define SEC_FTR_DEFAULT \ (SEC_FTR_L1D_FLUSH_HV | \ SEC_FTR_L1D_FLUSH_PR | \ SEC_FTR_BNDS_CHK_SPEC_BAR | \ + SEC_FTR_L1D_FLUSH_ENTRY | \ + SEC_FTR_L1D_FLUSH_UACCESS | \ SEC_FTR_FAVOUR_SECURITY) #endif /* _ASM_POWERPC_SECURITY_FEATURES_H */ diff --git a/arch/powerpc/include/asm/setjmp.h b/arch/powerpc/include/asm/setjmp.h index 279d03a1eec6..6941fe202bc8 100644 --- a/arch/powerpc/include/asm/setjmp.h +++ b/arch/powerpc/include/asm/setjmp.h @@ -12,7 +12,9 @@ #define JMP_BUF_LEN 23 -extern long setjmp(long *); -extern void longjmp(long *, long); +typedef long jmp_buf[JMP_BUF_LEN]; + +extern int setjmp(jmp_buf env) __attribute__((returns_twice)); +extern void longjmp(jmp_buf env, int val) __attribute__((noreturn)); #endif /* _ASM_POWERPC_SETJMP_H */ diff --git a/arch/powerpc/include/asm/setup.h b/arch/powerpc/include/asm/setup.h index 65676e2325b8..6f2f4497e13b 100644 --- a/arch/powerpc/include/asm/setup.h +++ b/arch/powerpc/include/asm/setup.h @@ -52,12 +52,16 @@ enum l1d_flush_type { }; void setup_rfi_flush(enum l1d_flush_type, bool enable); +void setup_entry_flush(bool enable); +void setup_uaccess_flush(bool enable); void do_rfi_flush_fixups(enum l1d_flush_type types); #ifdef CONFIG_PPC_BARRIER_NOSPEC void setup_barrier_nospec(void); #else static inline void setup_barrier_nospec(void) { }; #endif +void do_uaccess_flush_fixups(enum l1d_flush_type types); +void do_entry_flush_fixups(enum l1d_flush_type types); void do_barrier_nospec_fixups(bool enable); extern bool barrier_nospec_enabled; diff --git a/arch/powerpc/include/asm/tlb.h b/arch/powerpc/include/asm/tlb.h index f0e571b2dc7c..a6073fecdacd 100644 --- a/arch/powerpc/include/asm/tlb.h +++ b/arch/powerpc/include/asm/tlb.h @@ -76,19 +76,6 @@ static inline int mm_is_thread_local(struct mm_struct *mm) return false; return cpumask_test_cpu(smp_processor_id(), mm_cpumask(mm)); } -static inline void mm_reset_thread_local(struct mm_struct *mm) -{ - WARN_ON(atomic_read(&mm->context.copros) > 0); - /* - * It's possible for mm_access to take a reference on mm_users to - * access the remote mm from another thread, but it's not allowed - * to set mm_cpumask, so mm_users may be > 1 here. - */ - WARN_ON(current->mm != mm); - atomic_set(&mm->context.active_cpus, 1); - cpumask_clear(mm_cpumask(mm)); - cpumask_set_cpu(smp_processor_id(), mm_cpumask(mm)); -} #else /* CONFIG_PPC_BOOK3S_64 */ static inline int mm_is_thread_local(struct mm_struct *mm) { diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h index 38a25ff8afb7..ab6612e35ace 100644 --- a/arch/powerpc/include/asm/uaccess.h +++ b/arch/powerpc/include/asm/uaccess.h @@ -6,6 +6,7 @@ #include <asm/processor.h> #include <asm/page.h> #include <asm/extable.h> +#include <asm/kup.h> /* * The fs value determines whether argument validity checking should be @@ -91,9 +92,14 @@ static inline int __access_ok(unsigned long addr, unsigned long size, __put_user_check((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr))) #define __get_user(x, ptr) \ - __get_user_nocheck((x), (ptr), sizeof(*(ptr))) + __get_user_nocheck((x), (ptr), sizeof(*(ptr)), true) #define __put_user(x, ptr) \ - __put_user_nocheck((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr))) + __put_user_nocheck((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr)), true) + +#define __get_user_allowed(x, ptr) \ + __get_user_nocheck((x), (ptr), sizeof(*(ptr)), false) +#define __put_user_allowed(x, ptr) \ + __put_user_nocheck((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr)), false) #define __get_user_inatomic(x, ptr) \ __get_user_nosleep((x), (ptr), sizeof(*(ptr))) @@ -138,7 +144,7 @@ extern long __put_user_bad(void); : "r" (x), "b" (addr), "i" (-EFAULT), "0" (err)) #endif /* __powerpc64__ */ -#define __put_user_size(x, ptr, size, retval) \ +#define __put_user_size_allowed(x, ptr, size, retval) \ do { \ retval = 0; \ switch (size) { \ @@ -150,14 +156,28 @@ do { \ } \ } while (0) -#define __put_user_nocheck(x, ptr, size) \ +#define __put_user_size(x, ptr, size, retval) \ +do { \ + allow_write_to_user(ptr, size); \ + __put_user_size_allowed(x, ptr, size, retval); \ + prevent_write_to_user(ptr, size); \ +} while (0) + +#define __put_user_nocheck(x, ptr, size, do_allow) \ ({ \ long __pu_err; \ __typeof__(*(ptr)) __user *__pu_addr = (ptr); \ + __typeof__(*(ptr)) __pu_val = (x); \ + __typeof__(size) __pu_size = (size); \ + \ if (!is_kernel_addr((unsigned long)__pu_addr)) \ might_fault(); \ - __chk_user_ptr(ptr); \ - __put_user_size((x), __pu_addr, (size), __pu_err); \ + __chk_user_ptr(__pu_addr); \ + if (do_allow) \ + __put_user_size(__pu_val, __pu_addr, __pu_size, __pu_err); \ + else \ + __put_user_size_allowed(__pu_val, __pu_addr, __pu_size, __pu_err); \ + \ __pu_err; \ }) @@ -165,9 +185,13 @@ do { \ ({ \ long __pu_err = -EFAULT; \ __typeof__(*(ptr)) __user *__pu_addr = (ptr); \ + __typeof__(*(ptr)) __pu_val = (x); \ + __typeof__(size) __pu_size = (size); \ + \ might_fault(); \ - if (access_ok(VERIFY_WRITE, __pu_addr, size)) \ - __put_user_size((x), __pu_addr, (size), __pu_err); \ + if (access_ok(VERIFY_WRITE, __pu_addr, __pu_size)) \ + __put_user_size(__pu_val, __pu_addr, __pu_size, __pu_err); \ + \ __pu_err; \ }) @@ -175,8 +199,12 @@ do { \ ({ \ long __pu_err; \ __typeof__(*(ptr)) __user *__pu_addr = (ptr); \ - __chk_user_ptr(ptr); \ - __put_user_size((x), __pu_addr, (size), __pu_err); \ + __typeof__(*(ptr)) __pu_val = (x); \ + __typeof__(size) __pu_size = (size); \ + \ + __chk_user_ptr(__pu_addr); \ + __put_user_size(__pu_val, __pu_addr, __pu_size, __pu_err); \ + \ __pu_err; \ }) @@ -234,7 +262,7 @@ extern long __get_user_bad(void); : "b" (addr), "i" (-EFAULT), "0" (err)) #endif /* __powerpc64__ */ -#define __get_user_size(x, ptr, size, retval) \ +#define __get_user_size_allowed(x, ptr, size, retval) \ do { \ retval = 0; \ __chk_user_ptr(ptr); \ @@ -249,6 +277,13 @@ do { \ } \ } while (0) +#define __get_user_size(x, ptr, size, retval) \ +do { \ + allow_read_from_user(ptr, size); \ + __get_user_size_allowed(x, ptr, size, retval); \ + prevent_read_from_user(ptr, size); \ +} while (0) + /* * This is a type: either unsigned long, if the argument fits into * that type, or otherwise unsigned long long. @@ -256,17 +291,23 @@ do { \ #define __long_type(x) \ __typeof__(__builtin_choose_expr(sizeof(x) > sizeof(0UL), 0ULL, 0UL)) -#define __get_user_nocheck(x, ptr, size) \ +#define __get_user_nocheck(x, ptr, size, do_allow) \ ({ \ long __gu_err; \ __long_type(*(ptr)) __gu_val; \ __typeof__(*(ptr)) __user *__gu_addr = (ptr); \ - __chk_user_ptr(ptr); \ + __typeof__(size) __gu_size = (size); \ + \ + __chk_user_ptr(__gu_addr); \ if (!is_kernel_addr((unsigned long)__gu_addr)) \ might_fault(); \ barrier_nospec(); \ - __get_user_size(__gu_val, __gu_addr, (size), __gu_err); \ + if (do_allow) \ + __get_user_size(__gu_val, __gu_addr, __gu_size, __gu_err); \ + else \ + __get_user_size_allowed(__gu_val, __gu_addr, __gu_size, __gu_err); \ (x) = (__typeof__(*(ptr)))__gu_val; \ + \ __gu_err; \ }) @@ -275,12 +316,15 @@ do { \ long __gu_err = -EFAULT; \ __long_type(*(ptr)) __gu_val = 0; \ __typeof__(*(ptr)) __user *__gu_addr = (ptr); \ + __typeof__(size) __gu_size = (size); \ + \ might_fault(); \ - if (access_ok(VERIFY_READ, __gu_addr, (size))) { \ + if (access_ok(VERIFY_READ, __gu_addr, __gu_size)) { \ barrier_nospec(); \ - __get_user_size(__gu_val, __gu_addr, (size), __gu_err); \ + __get_user_size(__gu_val, __gu_addr, __gu_size, __gu_err); \ } \ (x) = (__force __typeof__(*(ptr)))__gu_val; \ + \ __gu_err; \ }) @@ -289,10 +333,13 @@ do { \ long __gu_err; \ __long_type(*(ptr)) __gu_val; \ __typeof__(*(ptr)) __user *__gu_addr = (ptr); \ - __chk_user_ptr(ptr); \ + __typeof__(size) __gu_size = (size); \ + \ + __chk_user_ptr(__gu_addr); \ barrier_nospec(); \ - __get_user_size(__gu_val, __gu_addr, (size), __gu_err); \ + __get_user_size(__gu_val, __gu_addr, __gu_size, __gu_err); \ (x) = (__force __typeof__(*(ptr)))__gu_val; \ + \ __gu_err; \ }) @@ -306,16 +353,22 @@ extern unsigned long __copy_tofrom_user(void __user *to, static inline unsigned long raw_copy_in_user(void __user *to, const void __user *from, unsigned long n) { + unsigned long ret; + barrier_nospec(); - return __copy_tofrom_user(to, from, n); + allow_user_access(to, from, n); + ret = __copy_tofrom_user(to, from, n); + prevent_user_access(to, from, n); + return ret; } #endif /* __powerpc64__ */ static inline unsigned long raw_copy_from_user(void *to, const void __user *from, unsigned long n) { + unsigned long ret; if (__builtin_constant_p(n) && (n <= 8)) { - unsigned long ret = 1; + ret = 1; switch (n) { case 1: @@ -340,27 +393,30 @@ static inline unsigned long raw_copy_from_user(void *to, } barrier_nospec(); - return __copy_tofrom_user((__force void __user *)to, from, n); + allow_read_from_user(from, n); + ret = __copy_tofrom_user((__force void __user *)to, from, n); + prevent_read_from_user(from, n); + return ret; } -static inline unsigned long raw_copy_to_user(void __user *to, - const void *from, unsigned long n) +static inline unsigned long +raw_copy_to_user_allowed(void __user *to, const void *from, unsigned long n) { if (__builtin_constant_p(n) && (n <= 8)) { unsigned long ret = 1; switch (n) { case 1: - __put_user_size(*(u8 *)from, (u8 __user *)to, 1, ret); + __put_user_size_allowed(*(u8 *)from, (u8 __user *)to, 1, ret); break; case 2: - __put_user_size(*(u16 *)from, (u16 __user *)to, 2, ret); + __put_user_size_allowed(*(u16 *)from, (u16 __user *)to, 2, ret); break; case 4: - __put_user_size(*(u32 *)from, (u32 __user *)to, 4, ret); + __put_user_size_allowed(*(u32 *)from, (u32 __user *)to, 4, ret); break; case 8: - __put_user_size(*(u64 *)from, (u64 __user *)to, 8, ret); + __put_user_size_allowed(*(u64 *)from, (u64 __user *)to, 8, ret); break; } if (ret == 0) @@ -370,14 +426,34 @@ static inline unsigned long raw_copy_to_user(void __user *to, return __copy_tofrom_user(to, (__force const void __user *)from, n); } -extern unsigned long __clear_user(void __user *addr, unsigned long size); +static inline unsigned long +raw_copy_to_user(void __user *to, const void *from, unsigned long n) +{ + unsigned long ret; + + allow_write_to_user(to, n); + ret = raw_copy_to_user_allowed(to, from, n); + prevent_write_to_user(to, n); + return ret; +} + +unsigned long __arch_clear_user(void __user *addr, unsigned long size); static inline unsigned long clear_user(void __user *addr, unsigned long size) { + unsigned long ret = size; might_fault(); - if (likely(access_ok(VERIFY_WRITE, addr, size))) - return __clear_user(addr, size); - return size; + if (likely(access_ok(VERIFY_WRITE, addr, size))) { + allow_write_to_user(addr, size); + ret = __arch_clear_user(addr, size); + prevent_write_to_user(addr, size); + } + return ret; +} + +static inline unsigned long __clear_user(void __user *addr, unsigned long size) +{ + return clear_user(addr, size); } extern long strncpy_from_user(char *dst, const char __user *src, long count); @@ -388,4 +464,13 @@ extern long __copy_from_user_flushcache(void *dst, const void __user *src, extern void memcpy_page_flushcache(char *to, struct page *page, size_t offset, size_t len); +#define user_access_begin(type, ptr, len) access_ok(type, ptr, len) +#define user_access_end() prevent_user_access(NULL, NULL, ~0ul) + +#define unsafe_op_wrap(op, err) do { if (unlikely(op)) goto err; } while (0) +#define unsafe_get_user(x, p, e) unsafe_op_wrap(__get_user_allowed(x, p), e) +#define unsafe_put_user(x, p, e) unsafe_op_wrap(__put_user_allowed(x, p), e) +#define unsafe_copy_to_user(d, s, l, e) \ + unsafe_op_wrap(raw_copy_to_user_allowed(d, s, l), e) + #endif /* _ARCH_POWERPC_UACCESS_H */ diff --git a/arch/powerpc/include/uapi/asm/errno.h b/arch/powerpc/include/uapi/asm/errno.h index cc79856896a1..4ba87de32be0 100644 --- a/arch/powerpc/include/uapi/asm/errno.h +++ b/arch/powerpc/include/uapi/asm/errno.h @@ -2,6 +2,7 @@ #ifndef _ASM_POWERPC_ERRNO_H #define _ASM_POWERPC_ERRNO_H +#undef EDEADLOCK #include <asm-generic/errno.h> #undef EDEADLOCK diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index d450280e5c29..1e64cfe22a83 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -5,9 +5,6 @@ CFLAGS_ptrace.o += -DUTS_MACHINE='"$(UTS_MACHINE)"' -# Avoid clang warnings around longjmp/setjmp declarations -CFLAGS_crash.o += -ffreestanding - subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror ifdef CONFIG_PPC64 diff --git a/arch/powerpc/kernel/cpu_setup_power.S b/arch/powerpc/kernel/cpu_setup_power.S index 458b928dbd84..5bef78e2b4c1 100644 --- a/arch/powerpc/kernel/cpu_setup_power.S +++ b/arch/powerpc/kernel/cpu_setup_power.S @@ -183,7 +183,7 @@ __init_LPCR_ISA300: __init_FSCR: mfspr r3,SPRN_FSCR - ori r3,r3,FSCR_TAR|FSCR_DSCR|FSCR_EBB + ori r3,r3,FSCR_TAR|FSCR_EBB mtspr SPRN_FSCR,r3 blr diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c index f9fe2080ceb9..eed3543aeca4 100644 --- a/arch/powerpc/kernel/dma-iommu.c +++ b/arch/powerpc/kernel/dma-iommu.c @@ -100,7 +100,8 @@ static u64 dma_iommu_get_required_mask(struct device *dev) if (!tbl) return 0; - mask = 1ULL < (fls_long(tbl->it_offset + tbl->it_size) - 1); + mask = 1ULL << (fls_long(tbl->it_offset + tbl->it_size) + + tbl->it_page_shift - 1); mask += mask - 1; return mask; diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c index a4b31e17492d..5195a4fc3e41 100644 --- a/arch/powerpc/kernel/dt_cpu_ftrs.c +++ b/arch/powerpc/kernel/dt_cpu_ftrs.c @@ -346,6 +346,14 @@ static int __init feat_enable_dscr(struct dt_cpu_feature *f) { u64 lpcr; + /* + * Linux relies on FSCR[DSCR] being clear, so that we can take the + * facility unavailable interrupt and track the task's usage of DSCR. + * See facility_unavailable_exception(). + * Clear the bit here so that feat_enable() doesn't set it. + */ + f->fscr_bit_nr = -1; + feat_enable(f); lpcr = mfspr(SPRN_LPCR); diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index fe3c6f3bd3b6..44bb522fb4a2 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -364,14 +364,11 @@ static inline unsigned long eeh_token_to_phys(unsigned long token) pa = pte_pfn(*ptep); /* On radix we can do hugepage mappings for io, so handle that */ - if (hugepage_shift) { - pa <<= hugepage_shift; - pa |= token & ((1ul << hugepage_shift) - 1); - } else { - pa <<= PAGE_SHIFT; - pa |= token & (PAGE_SIZE - 1); - } + if (!hugepage_shift) + hugepage_shift = PAGE_SHIFT; + pa <<= PAGE_SHIFT; + pa |= token & ((1ul << hugepage_shift) - 1); return pa; } @@ -502,7 +499,7 @@ int eeh_dev_check_failure(struct eeh_dev *edev) rc = 1; if (pe->state & EEH_PE_ISOLATED) { pe->check_count++; - if (pe->check_count % EEH_MAX_FAILS == 0) { + if (pe->check_count == EEH_MAX_FAILS) { dn = pci_device_to_OF_node(dev); if (dn) location = of_get_property(dn, "ibm,loc-code", diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index e1dab9b1e447..344e2758b22d 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -540,7 +540,7 @@ EXC_COMMON_BEGIN(unrecover_mce) b 1b -EXC_REAL(data_access, 0x300, 0x80) +EXC_REAL_OOL(data_access, 0x300, 0x80) EXC_VIRT(data_access, 0x4300, 0x80, 0x300) TRAMP_KVM_SKIP(PACA_EXGEN, 0x300) @@ -572,13 +572,16 @@ ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX) EXC_REAL_BEGIN(data_access_slb, 0x380, 0x80) SET_SCRATCH0(r13) EXCEPTION_PROLOG_0(PACA_EXSLB) + b tramp_data_access_slb +EXC_REAL_END(data_access_slb, 0x380, 0x80) + +TRAMP_REAL_BEGIN(tramp_data_access_slb) EXCEPTION_PROLOG_1(PACA_EXSLB, KVMTEST_PR, 0x380) mr r12,r3 /* save r3 */ mfspr r3,SPRN_DAR mfspr r11,SPRN_SRR1 crset 4*cr6+eq BRANCH_TO_COMMON(r10, slb_miss_common) -EXC_REAL_END(data_access_slb, 0x380, 0x80) EXC_VIRT_BEGIN(data_access_slb, 0x4380, 0x80) SET_SCRATCH0(r13) @@ -593,7 +596,7 @@ EXC_VIRT_END(data_access_slb, 0x4380, 0x80) TRAMP_KVM_SKIP(PACA_EXSLB, 0x380) -EXC_REAL(instruction_access, 0x400, 0x80) +EXC_REAL_OOL(instruction_access, 0x400, 0x80) EXC_VIRT(instruction_access, 0x4400, 0x80, 0x400) TRAMP_KVM(PACA_EXGEN, 0x400) @@ -616,13 +619,16 @@ ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX) EXC_REAL_BEGIN(instruction_access_slb, 0x480, 0x80) SET_SCRATCH0(r13) EXCEPTION_PROLOG_0(PACA_EXSLB) + b tramp_instruction_access_slb +EXC_REAL_END(instruction_access_slb, 0x480, 0x80) + +TRAMP_REAL_BEGIN(tramp_instruction_access_slb) EXCEPTION_PROLOG_1(PACA_EXSLB, KVMTEST_PR, 0x480) mr r12,r3 /* save r3 */ mfspr r3,SPRN_SRR0 /* SRR0 is faulting address */ mfspr r11,SPRN_SRR1 crclr 4*cr6+eq BRANCH_TO_COMMON(r10, slb_miss_common) -EXC_REAL_END(instruction_access_slb, 0x480, 0x80) EXC_VIRT_BEGIN(instruction_access_slb, 0x4480, 0x80) SET_SCRATCH0(r13) @@ -883,13 +889,13 @@ END_FTR_SECTION_IFSET(CPU_FTR_TM) EXC_REAL_OOL_MASKABLE(decrementer, 0x900, 0x80, IRQS_DISABLED) -EXC_VIRT_MASKABLE(decrementer, 0x4900, 0x80, 0x900, IRQS_DISABLED) +EXC_VIRT_OOL_MASKABLE(decrementer, 0x4900, 0x80, 0x900, IRQS_DISABLED) TRAMP_KVM(PACA_EXGEN, 0x900) EXC_COMMON_ASYNC(decrementer_common, 0x900, timer_interrupt) -EXC_REAL_HV(hdecrementer, 0x980, 0x80) -EXC_VIRT_HV(hdecrementer, 0x4980, 0x80, 0x980) +EXC_REAL_OOL_HV(hdecrementer, 0x980, 0x80) +EXC_VIRT_OOL_HV(hdecrementer, 0x4980, 0x80, 0x980) TRAMP_KVM_HV(PACA_EXGEN, 0x980) EXC_COMMON(hdecrementer_common, 0x980, hdec_interrupt) @@ -1523,15 +1529,8 @@ TRAMP_REAL_BEGIN(stf_barrier_fallback) .endr blr -TRAMP_REAL_BEGIN(rfi_flush_fallback) - SET_SCRATCH0(r13); - GET_PACA(r13); - std r1,PACA_EXRFI+EX_R12(r13) - ld r1,PACAKSAVE(r13) - std r9,PACA_EXRFI+EX_R9(r13) - std r10,PACA_EXRFI+EX_R10(r13) - std r11,PACA_EXRFI+EX_R11(r13) - mfctr r9 +/* Clobbers r10, r11, ctr */ +.macro L1D_DISPLACEMENT_FLUSH ld r10,PACA_RFI_FLUSH_FALLBACK_AREA(r13) ld r11,PACA_L1D_FLUSH_SIZE(r13) srdi r11,r11,(7 + 3) /* 128 byte lines, unrolled 8x */ @@ -1542,7 +1541,7 @@ TRAMP_REAL_BEGIN(rfi_flush_fallback) sync /* - * The load adresses are at staggered offsets within cachelines, + * The load addresses are at staggered offsets within cachelines, * which suits some pipelines better (on others it should not * hurt). */ @@ -1557,7 +1556,30 @@ TRAMP_REAL_BEGIN(rfi_flush_fallback) ld r11,(0x80 + 8)*7(r10) addi r10,r10,0x80*8 bdnz 1b +.endm + +TRAMP_REAL_BEGIN(entry_flush_fallback) + std r9,PACA_EXRFI+EX_R9(r13) + std r10,PACA_EXRFI+EX_R10(r13) + std r11,PACA_EXRFI+EX_R11(r13) + mfctr r9 + L1D_DISPLACEMENT_FLUSH + mtctr r9 + ld r9,PACA_EXRFI+EX_R9(r13) + ld r10,PACA_EXRFI+EX_R10(r13) + ld r11,PACA_EXRFI+EX_R11(r13) + blr +TRAMP_REAL_BEGIN(rfi_flush_fallback) + SET_SCRATCH0(r13); + GET_PACA(r13); + std r1,PACA_EXRFI+EX_R12(r13) + ld r1,PACAKSAVE(r13) + std r9,PACA_EXRFI+EX_R9(r13) + std r10,PACA_EXRFI+EX_R10(r13) + std r11,PACA_EXRFI+EX_R11(r13) + mfctr r9 + L1D_DISPLACEMENT_FLUSH mtctr r9 ld r9,PACA_EXRFI+EX_R9(r13) ld r10,PACA_EXRFI+EX_R10(r13) @@ -1575,32 +1597,7 @@ TRAMP_REAL_BEGIN(hrfi_flush_fallback) std r10,PACA_EXRFI+EX_R10(r13) std r11,PACA_EXRFI+EX_R11(r13) mfctr r9 - ld r10,PACA_RFI_FLUSH_FALLBACK_AREA(r13) - ld r11,PACA_L1D_FLUSH_SIZE(r13) - srdi r11,r11,(7 + 3) /* 128 byte lines, unrolled 8x */ - mtctr r11 - DCBT_BOOK3S_STOP_ALL_STREAM_IDS(r11) /* Stop prefetch streams */ - - /* order ld/st prior to dcbt stop all streams with flushing */ - sync - - /* - * The load adresses are at staggered offsets within cachelines, - * which suits some pipelines better (on others it should not - * hurt). - */ -1: - ld r11,(0x80 + 8)*0(r10) - ld r11,(0x80 + 8)*1(r10) - ld r11,(0x80 + 8)*2(r10) - ld r11,(0x80 + 8)*3(r10) - ld r11,(0x80 + 8)*4(r10) - ld r11,(0x80 + 8)*5(r10) - ld r11,(0x80 + 8)*6(r10) - ld r11,(0x80 + 8)*7(r10) - addi r10,r10,0x80*8 - bdnz 1b - + L1D_DISPLACEMENT_FLUSH mtctr r9 ld r9,PACA_EXRFI+EX_R9(r13) ld r10,PACA_EXRFI+EX_R10(r13) @@ -1609,6 +1606,19 @@ TRAMP_REAL_BEGIN(hrfi_flush_fallback) GET_SCRATCH0(r13); hrfid +USE_TEXT_SECTION() + +_GLOBAL(do_uaccess_flush) + UACCESS_FLUSH_FIXUP_SECTION + nop + nop + nop + blr + L1D_DISPLACEMENT_FLUSH + blr +_ASM_NOKPROBE_SYMBOL(do_uaccess_flush) +EXPORT_SYMBOL(do_uaccess_flush) + /* * Real mode exceptions actually use this too, but alternate * instruction code patches (which end up in the common .text area) diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S index 3fb564f3e887..4f7b225d78cf 100644 --- a/arch/powerpc/kernel/head_64.S +++ b/arch/powerpc/kernel/head_64.S @@ -423,6 +423,10 @@ generic_secondary_common_init: /* From now on, r24 is expected to be logical cpuid */ mr r24,r5 + /* Create a temp kernel stack for use before relocation is on. */ + ld r1,PACAEMERGSP(r13) + subi r1,r1,STACK_FRAME_OVERHEAD + /* See if we need to call a cpu state restore handler */ LOAD_REG_ADDR(r23, cur_cpu_spec) ld r23,0(r23) @@ -451,10 +455,6 @@ generic_secondary_common_init: sync /* order paca.run and cur_cpu_spec */ isync /* In case code patching happened */ - /* Create a temp kernel stack for use before relocation is on. */ - ld r1,PACAEMERGSP(r13) - subi r1,r1,STACK_FRAME_OVERHEAD - b __secondary_start #endif /* SMP */ @@ -950,15 +950,8 @@ start_here_multiplatform: std r0,0(r4) #endif - /* The following gets the stack set up with the regs */ - /* pointing to the real addr of the kernel stack. This is */ - /* all done to support the C function call below which sets */ - /* up the htab. This is done because we have relocated the */ - /* kernel but are still running in real mode. */ - - LOAD_REG_ADDR(r3,init_thread_union) - /* set up a stack pointer */ + LOAD_REG_ADDR(r3,init_thread_union) LOAD_REG_IMMEDIATE(r1,THREAD_SIZE) add r1,r3,r1 li r0,0 diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S index 9fd2ff28b8ff..08c16aa0dd53 100644 --- a/arch/powerpc/kernel/head_8xx.S +++ b/arch/powerpc/kernel/head_8xx.S @@ -269,7 +269,7 @@ SystemCall: /* On the MPC8xx, this is a software emulation interrupt. It occurs * for all unimplemented and illegal instructions. */ - EXCEPTION(0x1000, SoftEmu, program_check_exception, EXC_XFER_STD) + EXCEPTION(0x1000, SoftEmu, emulation_assist_interrupt, EXC_XFER_STD) . = 0x1100 /* @@ -356,11 +356,9 @@ _ENTRY(ITLBMiss_cmp) /* Load the MI_TWC with the attributes for this "segment." */ mtspr SPRN_MI_TWC, r11 /* Set segment attributes */ -#ifdef CONFIG_SWAP - rlwinm r11, r10, 32-5, _PAGE_PRESENT + rlwinm r11, r10, 32-7, _PAGE_PRESENT and r11, r11, r10 rlwimi r10, r11, 0, _PAGE_PRESENT -#endif li r11, RPN_PATTERN | 0x200 /* The Linux PTE won't go exactly into the MMU TLB. * Software indicator bits 20 and 23 must be clear. @@ -482,11 +480,9 @@ _ENTRY(DTLBMiss_jmp) * r11 = ((r10 & PRESENT) & ((r10 & ACCESSED) >> 5)); * r10 = (r10 & ~PRESENT) | r11; */ -#ifdef CONFIG_SWAP - rlwinm r11, r10, 32-5, _PAGE_PRESENT + rlwinm r11, r10, 32-7, _PAGE_PRESENT and r11, r11, r10 rlwimi r10, r11, 0, _PAGE_PRESENT -#endif /* The Linux PTE won't go exactly into the MMU TLB. * Software indicator bits 24, 25, 26, and 27 must be * set. All other Linux PTE bits control the behavior diff --git a/arch/powerpc/kernel/idle_book3s.S b/arch/powerpc/kernel/idle_book3s.S index 36178000a2f2..4a860d3b9229 100644 --- a/arch/powerpc/kernel/idle_book3s.S +++ b/arch/powerpc/kernel/idle_book3s.S @@ -170,8 +170,11 @@ core_idle_lock_held: bne- core_idle_lock_held blr -/* Reuse an unused pt_regs slot for IAMR */ +/* Reuse some unused pt_regs slots for AMR/IAMR/UAMOR/UAMOR */ +#define PNV_POWERSAVE_AMR _TRAP #define PNV_POWERSAVE_IAMR _DAR +#define PNV_POWERSAVE_UAMOR _DSISR +#define PNV_POWERSAVE_AMOR RESULT /* * Pass requested state in r3: @@ -205,8 +208,16 @@ pnv_powersave_common: SAVE_NVGPRS(r1) BEGIN_FTR_SECTION + mfspr r4, SPRN_AMR mfspr r5, SPRN_IAMR + mfspr r6, SPRN_UAMOR + std r4, PNV_POWERSAVE_AMR(r1) std r5, PNV_POWERSAVE_IAMR(r1) + std r6, PNV_POWERSAVE_UAMOR(r1) +BEGIN_FTR_SECTION_NESTED(42) + mfspr r7, SPRN_AMOR + std r7, PNV_POWERSAVE_AMOR(r1) +END_FTR_SECTION_NESTED_IFSET(CPU_FTR_HVMODE, 42) END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) mfcr r5 @@ -935,12 +946,20 @@ END_FTR_SECTION_IFSET(CPU_FTR_HVMODE) REST_GPR(2, r1) BEGIN_FTR_SECTION - /* IAMR was saved in pnv_powersave_common() */ + /* These regs were saved in pnv_powersave_common() */ + ld r4, PNV_POWERSAVE_AMR(r1) ld r5, PNV_POWERSAVE_IAMR(r1) + ld r6, PNV_POWERSAVE_UAMOR(r1) + mtspr SPRN_AMR, r4 mtspr SPRN_IAMR, r5 + mtspr SPRN_UAMOR, r6 +BEGIN_FTR_SECTION_NESTED(42) + ld r7, PNV_POWERSAVE_AMOR(r1) + mtspr SPRN_AMOR, r7 +END_FTR_SECTION_NESTED_IFSET(CPU_FTR_HVMODE, 42) /* - * We don't need an isync here because the upcoming mtmsrd is - * execution synchronizing. + * We don't need an isync here after restoring IAMR because the upcoming + * mtmsrd is execution synchronizing. */ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index f0dc680e659a..c3d2d5cd7c10 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -1030,7 +1030,7 @@ int iommu_take_ownership(struct iommu_table *tbl) spin_lock_irqsave(&tbl->large_pool.lock, flags); for (i = 0; i < tbl->nr_pools; i++) - spin_lock(&tbl->pools[i].lock); + spin_lock_nest_lock(&tbl->pools[i].lock, &tbl->large_pool.lock); if (tbl->it_offset == 0) clear_bit(0, tbl->it_map); @@ -1059,7 +1059,7 @@ void iommu_release_ownership(struct iommu_table *tbl) spin_lock_irqsave(&tbl->large_pool.lock, flags); for (i = 0; i < tbl->nr_pools; i++) - spin_lock(&tbl->pools[i].lock); + spin_lock_nest_lock(&tbl->pools[i].lock, &tbl->large_pool.lock); memset(tbl->it_map, 0, sz); diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c index 5c60bb0f927f..53a39661eb13 100644 --- a/arch/powerpc/kernel/kprobes.c +++ b/arch/powerpc/kernel/kprobes.c @@ -277,6 +277,9 @@ int kprobe_handler(struct pt_regs *regs) if (user_mode(regs)) return 0; + if (!(regs->msr & MSR_IR) || !(regs->msr & MSR_DR)) + return 0; + /* * We don't want to be preempted for the entire * duration of kprobe processing diff --git a/arch/powerpc/kernel/machine_kexec.c b/arch/powerpc/kernel/machine_kexec.c index 63f5a9311a29..094c37fb07a9 100644 --- a/arch/powerpc/kernel/machine_kexec.c +++ b/arch/powerpc/kernel/machine_kexec.c @@ -116,11 +116,12 @@ void machine_kexec(struct kimage *image) void __init reserve_crashkernel(void) { - unsigned long long crash_size, crash_base; + unsigned long long crash_size, crash_base, total_mem_sz; int ret; + total_mem_sz = memory_limit ? memory_limit : memblock_phys_mem_size(); /* use common parsing */ - ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(), + ret = parse_crashkernel(boot_command_line, total_mem_sz, &crash_size, &crash_base); if (ret == 0 && crash_size > 0) { crashk_res.start = crash_base; @@ -179,6 +180,7 @@ void __init reserve_crashkernel(void) /* Crash kernel trumps memory limit */ if (memory_limit && memory_limit <= crashk_res.end) { memory_limit = crashk_res.end + 1; + total_mem_sz = memory_limit; printk("Adjusted memory limit for crashkernel, now 0x%llx\n", memory_limit); } @@ -187,7 +189,7 @@ void __init reserve_crashkernel(void) "for crashkernel (System RAM: %ldMB)\n", (unsigned long)(crash_size >> 20), (unsigned long)(crashk_res.start >> 20), - (unsigned long)(memblock_phys_mem_size() >> 20)); + (unsigned long)(total_mem_sz >> 20)); if (!memblock_is_region_memory(crashk_res.start, crash_size) || memblock_reserve(crashk_res.start, crash_size)) { diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index 88e4f69a09e5..74628aca2bf1 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -1671,3 +1671,13 @@ static void fixup_hide_host_resource_fsl(struct pci_dev *dev) } DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MOTOROLA, PCI_ANY_ID, fixup_hide_host_resource_fsl); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_FREESCALE, PCI_ANY_ID, fixup_hide_host_resource_fsl); + + +static int __init discover_phbs(void) +{ + if (ppc_md.discover_phbs) + ppc_md.discover_phbs(); + + return 0; +} +core_initcall(discover_phbs); diff --git a/arch/powerpc/kernel/pci_of_scan.c b/arch/powerpc/kernel/pci_of_scan.c index c101b321dece..7765837ba203 100644 --- a/arch/powerpc/kernel/pci_of_scan.c +++ b/arch/powerpc/kernel/pci_of_scan.c @@ -82,10 +82,16 @@ static void of_pci_parse_addrs(struct device_node *node, struct pci_dev *dev) const __be32 *addrs; u32 i; int proplen; + bool mark_unset = false; addrs = of_get_property(node, "assigned-addresses", &proplen); - if (!addrs) - return; + if (!addrs || !proplen) { + addrs = of_get_property(node, "reg", &proplen); + if (!addrs || !proplen) + return; + mark_unset = true; + } + pr_debug(" parse addresses (%d bytes) @ %p\n", proplen, addrs); for (; proplen >= 20; proplen -= 20, addrs += 5) { flags = pci_parse_of_flags(of_read_number(addrs, 1), 0); @@ -110,6 +116,8 @@ static void of_pci_parse_addrs(struct device_node *node, struct pci_dev *dev) continue; } res->flags = flags; + if (mark_unset) + res->flags |= IORESOURCE_UNSET; res->name = pci_name(dev); region.start = base; region.end = base + size - 1; diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index 8e88f78e57db..f8c49e5d4bd3 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -266,7 +266,7 @@ static struct feature_property { }; #if defined(CONFIG_44x) && defined(CONFIG_PPC_FPU) -static inline void identical_pvr_fixup(unsigned long node) +static __init void identical_pvr_fixup(unsigned long node) { unsigned int pvr; const char *model = of_get_flat_dt_prop(node, "model", NULL); @@ -685,6 +685,23 @@ static void __init tm_init(void) static void tm_init(void) { } #endif /* CONFIG_PPC_TRANSACTIONAL_MEM */ +#ifdef CONFIG_PPC64 +static void __init save_fscr_to_task(void) +{ + /* + * Ensure the init_task (pid 0, aka swapper) uses the value of FSCR we + * have configured via the device tree features or via __init_FSCR(). + * That value will then be propagated to pid 1 (init) and all future + * processes. + */ + if (early_cpu_has_feature(CPU_FTR_ARCH_207S)) + init_task.thread.fscr = mfspr(SPRN_FSCR); +} +#else +static inline void save_fscr_to_task(void) {}; +#endif + + void __init early_init_devtree(void *params) { phys_addr_t limit; @@ -770,6 +787,8 @@ void __init early_init_devtree(void *params) BUG(); } + save_fscr_to_task(); + #if defined(CONFIG_SMP) && defined(CONFIG_PPC64) /* We'll later wait for secondaries to check in; there are * NCPUS-1 non-boot CPUs :-) diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c index 95d1264ba795..b3aa0cea6283 100644 --- a/arch/powerpc/kernel/rtas.c +++ b/arch/powerpc/kernel/rtas.c @@ -1057,6 +1057,147 @@ struct pseries_errorlog *get_pseries_errorlog(struct rtas_error_log *log, return NULL; } +#ifdef CONFIG_PPC_RTAS_FILTER + +/* + * The sys_rtas syscall, as originally designed, allows root to pass + * arbitrary physical addresses to RTAS calls. A number of RTAS calls + * can be abused to write to arbitrary memory and do other things that + * are potentially harmful to system integrity, and thus should only + * be used inside the kernel and not exposed to userspace. + * + * All known legitimate users of the sys_rtas syscall will only ever + * pass addresses that fall within the RMO buffer, and use a known + * subset of RTAS calls. + * + * Accordingly, we filter RTAS requests to check that the call is + * permitted, and that provided pointers fall within the RMO buffer. + * The rtas_filters list contains an entry for each permitted call, + * with the indexes of the parameters which are expected to contain + * addresses and sizes of buffers allocated inside the RMO buffer. + */ +struct rtas_filter { + const char *name; + int token; + /* Indexes into the args buffer, -1 if not used */ + int buf_idx1; + int size_idx1; + int buf_idx2; + int size_idx2; + + int fixed_size; +}; + +static struct rtas_filter rtas_filters[] __ro_after_init = { + { "ibm,activate-firmware", -1, -1, -1, -1, -1 }, + { "ibm,configure-connector", -1, 0, -1, 1, -1, 4096 }, /* Special cased */ + { "display-character", -1, -1, -1, -1, -1 }, + { "ibm,display-message", -1, 0, -1, -1, -1 }, + { "ibm,errinjct", -1, 2, -1, -1, -1, 1024 }, + { "ibm,close-errinjct", -1, -1, -1, -1, -1 }, + { "ibm,open-errinjct", -1, -1, -1, -1, -1 }, + { "ibm,get-config-addr-info2", -1, -1, -1, -1, -1 }, + { "ibm,get-dynamic-sensor-state", -1, 1, -1, -1, -1 }, + { "ibm,get-indices", -1, 2, 3, -1, -1 }, + { "get-power-level", -1, -1, -1, -1, -1 }, + { "get-sensor-state", -1, -1, -1, -1, -1 }, + { "ibm,get-system-parameter", -1, 1, 2, -1, -1 }, + { "get-time-of-day", -1, -1, -1, -1, -1 }, + { "ibm,get-vpd", -1, 0, -1, 1, 2 }, + { "ibm,lpar-perftools", -1, 2, 3, -1, -1 }, + { "ibm,platform-dump", -1, 4, 5, -1, -1 }, + { "ibm,read-slot-reset-state", -1, -1, -1, -1, -1 }, + { "ibm,scan-log-dump", -1, 0, 1, -1, -1 }, + { "ibm,set-dynamic-indicator", -1, 2, -1, -1, -1 }, + { "ibm,set-eeh-option", -1, -1, -1, -1, -1 }, + { "set-indicator", -1, -1, -1, -1, -1 }, + { "set-power-level", -1, -1, -1, -1, -1 }, + { "set-time-for-power-on", -1, -1, -1, -1, -1 }, + { "ibm,set-system-parameter", -1, 1, -1, -1, -1 }, + { "set-time-of-day", -1, -1, -1, -1, -1 }, + { "ibm,suspend-me", -1, -1, -1, -1, -1 }, + { "ibm,update-nodes", -1, 0, -1, -1, -1, 4096 }, + { "ibm,update-properties", -1, 0, -1, -1, -1, 4096 }, + { "ibm,physical-attestation", -1, 0, 1, -1, -1 }, +}; + +static bool in_rmo_buf(u32 base, u32 end) +{ + return base >= rtas_rmo_buf && + base < (rtas_rmo_buf + RTAS_RMOBUF_MAX) && + base <= end && + end >= rtas_rmo_buf && + end < (rtas_rmo_buf + RTAS_RMOBUF_MAX); +} + +static bool block_rtas_call(int token, int nargs, + struct rtas_args *args) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(rtas_filters); i++) { + struct rtas_filter *f = &rtas_filters[i]; + u32 base, size, end; + + if (token != f->token) + continue; + + if (f->buf_idx1 != -1) { + base = be32_to_cpu(args->args[f->buf_idx1]); + if (f->size_idx1 != -1) + size = be32_to_cpu(args->args[f->size_idx1]); + else if (f->fixed_size) + size = f->fixed_size; + else + size = 1; + + end = base + size - 1; + if (!in_rmo_buf(base, end)) + goto err; + } + + if (f->buf_idx2 != -1) { + base = be32_to_cpu(args->args[f->buf_idx2]); + if (f->size_idx2 != -1) + size = be32_to_cpu(args->args[f->size_idx2]); + else if (f->fixed_size) + size = f->fixed_size; + else + size = 1; + end = base + size - 1; + + /* + * Special case for ibm,configure-connector where the + * address can be 0 + */ + if (!strcmp(f->name, "ibm,configure-connector") && + base == 0) + return false; + + if (!in_rmo_buf(base, end)) + goto err; + } + + return false; + } + +err: + pr_err_ratelimited("sys_rtas: RTAS call blocked - exploit attempt?\n"); + pr_err_ratelimited("sys_rtas: token=0x%x, nargs=%d (called by %s)\n", + token, nargs, current->comm); + return true; +} + +#else + +static bool block_rtas_call(int token, int nargs, + struct rtas_args *args) +{ + return false; +} + +#endif /* CONFIG_PPC_RTAS_FILTER */ + /* We assume to be passed big endian arguments */ SYSCALL_DEFINE1(rtas, struct rtas_args __user *, uargs) { @@ -1094,6 +1235,9 @@ SYSCALL_DEFINE1(rtas, struct rtas_args __user *, uargs) args.rets = &args.args[nargs]; memset(args.rets, 0, nret * sizeof(rtas_arg_t)); + if (block_rtas_call(token, nargs, &args)) + return -EINVAL; + /* Need to handle ibm,suspend_me call specially */ if (token == ibm_suspend_me_token) { @@ -1155,6 +1299,9 @@ void __init rtas_initialize(void) unsigned long rtas_region = RTAS_INSTANTIATE_MAX; u32 base, size, entry; int no_base, no_size, no_entry; +#ifdef CONFIG_PPC_RTAS_FILTER + int i; +#endif /* Get RTAS dev node and fill up our "rtas" structure with infos * about it. @@ -1190,6 +1337,12 @@ void __init rtas_initialize(void) #ifdef CONFIG_RTAS_ERROR_LOGGING rtas_last_error_token = rtas_token("rtas-last-error"); #endif + +#ifdef CONFIG_PPC_RTAS_FILTER + for (i = 0; i < ARRAY_SIZE(rtas_filters); i++) { + rtas_filters[i].token = rtas_token(rtas_filters[i].name); + } +#endif } int __init early_init_dt_scan_rtas(unsigned long node, diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index 508244bcf19c..7787a26d4777 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -929,8 +929,6 @@ void __init setup_arch(char **cmdline_p) /* On BookE, setup per-core TLB data structures. */ setup_tlb_core_data(); - - smp_release_cpus(); #endif /* Print various info about the machine that has been gathered so far. */ @@ -964,6 +962,8 @@ void __init setup_arch(char **cmdline_p) exc_lvl_early_init(); emergency_stack_init(); + smp_release_cpus(); + initmem_init(); #ifdef CONFIG_DUMMY_CONSOLE diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index eaf7300be5ab..122365624d3d 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -518,6 +518,8 @@ static bool __init parse_cache_info(struct device_node *np, lsizep = of_get_property(np, propnames[3], NULL); if (bsizep == NULL) bsizep = lsizep; + if (lsizep == NULL) + lsizep = bsizep; if (lsizep != NULL) lsize = be32_to_cpu(*lsizep); if (bsizep != NULL) @@ -861,7 +863,13 @@ early_initcall(disable_hardlockup_detector); static enum l1d_flush_type enabled_flush_types; static void *l1d_flush_fallback_area; static bool no_rfi_flush; +static bool no_entry_flush; +static bool no_uaccess_flush; bool rfi_flush; +bool entry_flush; +bool uaccess_flush; +DEFINE_STATIC_KEY_FALSE(uaccess_flush_key); +EXPORT_SYMBOL(uaccess_flush_key); static int __init handle_no_rfi_flush(char *p) { @@ -871,6 +879,22 @@ static int __init handle_no_rfi_flush(char *p) } early_param("no_rfi_flush", handle_no_rfi_flush); +static int __init handle_no_entry_flush(char *p) +{ + pr_info("entry-flush: disabled on command line."); + no_entry_flush = true; + return 0; +} +early_param("no_entry_flush", handle_no_entry_flush); + +static int __init handle_no_uaccess_flush(char *p) +{ + pr_info("uaccess-flush: disabled on command line."); + no_uaccess_flush = true; + return 0; +} +early_param("no_uaccess_flush", handle_no_uaccess_flush); + /* * The RFI flush is not KPTI, but because users will see doco that says to use * nopti we hijack that option here to also disable the RFI flush. @@ -902,6 +926,32 @@ void rfi_flush_enable(bool enable) rfi_flush = enable; } +void entry_flush_enable(bool enable) +{ + if (enable) { + do_entry_flush_fixups(enabled_flush_types); + on_each_cpu(do_nothing, NULL, 1); + } else { + do_entry_flush_fixups(L1D_FLUSH_NONE); + } + + entry_flush = enable; +} + +void uaccess_flush_enable(bool enable) +{ + if (enable) { + do_uaccess_flush_fixups(enabled_flush_types); + static_branch_enable(&uaccess_flush_key); + on_each_cpu(do_nothing, NULL, 1); + } else { + static_branch_disable(&uaccess_flush_key); + do_uaccess_flush_fixups(L1D_FLUSH_NONE); + } + + uaccess_flush = enable; +} + static void __ref init_fallback_flush(void) { u64 l1d_size, limit; @@ -955,10 +1005,28 @@ void setup_rfi_flush(enum l1d_flush_type types, bool enable) enabled_flush_types = types; - if (!no_rfi_flush && !cpu_mitigations_off()) + if (!cpu_mitigations_off() && !no_rfi_flush) rfi_flush_enable(enable); } +void setup_entry_flush(bool enable) +{ + if (cpu_mitigations_off()) + return; + + if (!no_entry_flush) + entry_flush_enable(enable); +} + +void setup_uaccess_flush(bool enable) +{ + if (cpu_mitigations_off()) + return; + + if (!no_uaccess_flush) + uaccess_flush_enable(enable); +} + #ifdef CONFIG_DEBUG_FS static int rfi_flush_set(void *data, u64 val) { @@ -986,9 +1054,63 @@ static int rfi_flush_get(void *data, u64 *val) DEFINE_SIMPLE_ATTRIBUTE(fops_rfi_flush, rfi_flush_get, rfi_flush_set, "%llu\n"); +static int entry_flush_set(void *data, u64 val) +{ + bool enable; + + if (val == 1) + enable = true; + else if (val == 0) + enable = false; + else + return -EINVAL; + + /* Only do anything if we're changing state */ + if (enable != entry_flush) + entry_flush_enable(enable); + + return 0; +} + +static int entry_flush_get(void *data, u64 *val) +{ + *val = entry_flush ? 1 : 0; + return 0; +} + +DEFINE_SIMPLE_ATTRIBUTE(fops_entry_flush, entry_flush_get, entry_flush_set, "%llu\n"); + +static int uaccess_flush_set(void *data, u64 val) +{ + bool enable; + + if (val == 1) + enable = true; + else if (val == 0) + enable = false; + else + return -EINVAL; + + /* Only do anything if we're changing state */ + if (enable != uaccess_flush) + uaccess_flush_enable(enable); + + return 0; +} + +static int uaccess_flush_get(void *data, u64 *val) +{ + *val = uaccess_flush ? 1 : 0; + return 0; +} + +DEFINE_SIMPLE_ATTRIBUTE(fops_uaccess_flush, uaccess_flush_get, uaccess_flush_set, "%llu\n"); + static __init int rfi_flush_debugfs_init(void) { debugfs_create_file("rfi_flush", 0600, powerpc_debugfs_root, NULL, &fops_rfi_flush); + debugfs_create_file("entry_flush", 0600, powerpc_debugfs_root, NULL, &fops_entry_flush); + debugfs_create_file("uaccess_flush", 0600, powerpc_debugfs_root, NULL, &fops_uaccess_flush); return 0; } device_initcall(rfi_flush_debugfs_init); diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index b088b0700d0d..7aba592bba36 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -477,8 +477,10 @@ static long restore_tm_sigcontexts(struct task_struct *tsk, err |= __get_user(tsk->thread.ckpt_regs.ccr, &sc->gp_regs[PT_CCR]); + /* Don't allow userspace to set the trap value */ + regs->trap = 0; + /* These regs are not checkpointed; they can go in 'regs'. */ - err |= __get_user(regs->trap, &sc->gp_regs[PT_TRAP]); err |= __get_user(regs->dar, &sc->gp_regs[PT_DAR]); err |= __get_user(regs->dsisr, &sc->gp_regs[PT_DSISR]); err |= __get_user(regs->result, &sc->gp_regs[PT_RESULT]); diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 6dc43205382b..a9ec4467705c 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -1032,6 +1032,9 @@ void start_secondary(void *unused) vdso_getcpu_init(); #endif + set_numa_node(numa_cpu_lookup_table[cpu]); + set_numa_mem(local_memory_node(numa_cpu_lookup_table[cpu])); + /* Update topology CPU masks */ add_cpu_to_masks(cpu); @@ -1042,9 +1045,6 @@ void start_secondary(void *unused) if (!cpumask_equal(cpu_l2_cache_mask(cpu), cpu_sibling_mask(cpu))) shared_caches = true; - set_numa_node(numa_cpu_lookup_table[cpu]); - set_numa_mem(local_memory_node(numa_cpu_lookup_table[cpu])); - smp_wmb(); notify_cpu_starting(cpu); set_cpu_online(cpu, true); diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c index 755dc98a57ae..6b107de10ffa 100644 --- a/arch/powerpc/kernel/sysfs.c +++ b/arch/powerpc/kernel/sysfs.c @@ -29,29 +29,27 @@ static DEFINE_PER_CPU(struct cpu, cpu_devices); -/* - * SMT snooze delay stuff, 64-bit only for now - */ - #ifdef CONFIG_PPC64 -/* Time in microseconds we delay before sleeping in the idle loop */ -static DEFINE_PER_CPU(long, smt_snooze_delay) = { 100 }; +/* + * Snooze delay has not been hooked up since 3fa8cad82b94 ("powerpc/pseries/cpuidle: + * smt-snooze-delay cleanup.") and has been broken even longer. As was foretold in + * 2014: + * + * "ppc64_util currently utilises it. Once we fix ppc64_util, propose to clean + * up the kernel code." + * + * powerpc-utils stopped using it as of 1.3.8. At some point in the future this + * code should be removed. + */ static ssize_t store_smt_snooze_delay(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { - struct cpu *cpu = container_of(dev, struct cpu, dev); - ssize_t ret; - long snooze; - - ret = sscanf(buf, "%ld", &snooze); - if (ret != 1) - return -EINVAL; - - per_cpu(smt_snooze_delay, cpu->dev.id) = snooze; + pr_warn_once("%s (%d) stored to unsupported smt_snooze_delay, which has no effect.\n", + current->comm, current->pid); return count; } @@ -59,9 +57,9 @@ static ssize_t show_smt_snooze_delay(struct device *dev, struct device_attribute *attr, char *buf) { - struct cpu *cpu = container_of(dev, struct cpu, dev); - - return sprintf(buf, "%ld\n", per_cpu(smt_snooze_delay, cpu->dev.id)); + pr_warn_once("%s (%d) read from unsupported smt_snooze_delay\n", + current->comm, current->pid); + return sprintf(buf, "100\n"); } static DEVICE_ATTR(smt_snooze_delay, 0644, show_smt_snooze_delay, @@ -69,16 +67,10 @@ static DEVICE_ATTR(smt_snooze_delay, 0644, show_smt_snooze_delay, static int __init setup_smt_snooze_delay(char *str) { - unsigned int cpu; - long snooze; - if (!cpu_has_feature(CPU_FTR_SMT)) return 1; - snooze = simple_strtol(str, NULL, 10); - for_each_possible_cpu(cpu) - per_cpu(smt_snooze_delay, cpu) = snooze; - + pr_warn("smt-snooze-delay command line option has no effect\n"); return 1; } __setup("smt-snooze-delay=", setup_smt_snooze_delay); diff --git a/arch/powerpc/kernel/tau_6xx.c b/arch/powerpc/kernel/tau_6xx.c index e2ab8a111b69..8ece45c2a1f6 100644 --- a/arch/powerpc/kernel/tau_6xx.c +++ b/arch/powerpc/kernel/tau_6xx.c @@ -13,13 +13,14 @@ */ #include <linux/errno.h> -#include <linux/jiffies.h> #include <linux/kernel.h> #include <linux/param.h> #include <linux/string.h> #include <linux/mm.h> #include <linux/interrupt.h> #include <linux/init.h> +#include <linux/delay.h> +#include <linux/workqueue.h> #include <asm/io.h> #include <asm/reg.h> @@ -39,9 +40,7 @@ static struct tau_temp unsigned char grew; } tau[NR_CPUS]; -struct timer_list tau_timer; - -#undef DEBUG +static bool tau_int_enable; /* TODO: put these in a /proc interface, with some sanity checks, and maybe * dynamic adjustment to minimize # of interrupts */ @@ -50,72 +49,49 @@ struct timer_list tau_timer; #define step_size 2 /* step size when temp goes out of range */ #define window_expand 1 /* expand the window by this much */ /* configurable values for shrinking the window */ -#define shrink_timer 2*HZ /* period between shrinking the window */ +#define shrink_timer 2000 /* period between shrinking the window */ #define min_window 2 /* minimum window size, degrees C */ static void set_thresholds(unsigned long cpu) { -#ifdef CONFIG_TAU_INT - /* - * setup THRM1, - * threshold, valid bit, enable interrupts, interrupt when below threshold - */ - mtspr(SPRN_THRM1, THRM1_THRES(tau[cpu].low) | THRM1_V | THRM1_TIE | THRM1_TID); + u32 maybe_tie = tau_int_enable ? THRM1_TIE : 0; - /* setup THRM2, - * threshold, valid bit, enable interrupts, interrupt when above threshold - */ - mtspr (SPRN_THRM2, THRM1_THRES(tau[cpu].high) | THRM1_V | THRM1_TIE); -#else - /* same thing but don't enable interrupts */ - mtspr(SPRN_THRM1, THRM1_THRES(tau[cpu].low) | THRM1_V | THRM1_TID); - mtspr(SPRN_THRM2, THRM1_THRES(tau[cpu].high) | THRM1_V); -#endif + /* setup THRM1, threshold, valid bit, interrupt when below threshold */ + mtspr(SPRN_THRM1, THRM1_THRES(tau[cpu].low) | THRM1_V | maybe_tie | THRM1_TID); + + /* setup THRM2, threshold, valid bit, interrupt when above threshold */ + mtspr(SPRN_THRM2, THRM1_THRES(tau[cpu].high) | THRM1_V | maybe_tie); } static void TAUupdate(int cpu) { - unsigned thrm; - -#ifdef DEBUG - printk("TAUupdate "); -#endif + u32 thrm; + u32 bits = THRM1_TIV | THRM1_TIN | THRM1_V; /* if both thresholds are crossed, the step_sizes cancel out * and the window winds up getting expanded twice. */ - if((thrm = mfspr(SPRN_THRM1)) & THRM1_TIV){ /* is valid? */ - if(thrm & THRM1_TIN){ /* crossed low threshold */ - if (tau[cpu].low >= step_size){ - tau[cpu].low -= step_size; - tau[cpu].high -= (step_size - window_expand); - } - tau[cpu].grew = 1; -#ifdef DEBUG - printk("low threshold crossed "); -#endif + thrm = mfspr(SPRN_THRM1); + if ((thrm & bits) == bits) { + mtspr(SPRN_THRM1, 0); + + if (tau[cpu].low >= step_size) { + tau[cpu].low -= step_size; + tau[cpu].high -= (step_size - window_expand); } + tau[cpu].grew = 1; + pr_debug("%s: low threshold crossed\n", __func__); } - if((thrm = mfspr(SPRN_THRM2)) & THRM1_TIV){ /* is valid? */ - if(thrm & THRM1_TIN){ /* crossed high threshold */ - if (tau[cpu].high <= 127-step_size){ - tau[cpu].low += (step_size - window_expand); - tau[cpu].high += step_size; - } - tau[cpu].grew = 1; -#ifdef DEBUG - printk("high threshold crossed "); -#endif + thrm = mfspr(SPRN_THRM2); + if ((thrm & bits) == bits) { + mtspr(SPRN_THRM2, 0); + + if (tau[cpu].high <= 127 - step_size) { + tau[cpu].low += (step_size - window_expand); + tau[cpu].high += step_size; } + tau[cpu].grew = 1; + pr_debug("%s: high threshold crossed\n", __func__); } - -#ifdef DEBUG - printk("grew = %d\n", tau[cpu].grew); -#endif - -#ifndef CONFIG_TAU_INT /* tau_timeout will do this if not using interrupts */ - set_thresholds(cpu); -#endif - } #ifdef CONFIG_TAU_INT @@ -140,17 +116,16 @@ void TAUException(struct pt_regs * regs) static void tau_timeout(void * info) { int cpu; - unsigned long flags; int size; int shrink; - /* disabling interrupts *should* be okay */ - local_irq_save(flags); cpu = smp_processor_id(); -#ifndef CONFIG_TAU_INT - TAUupdate(cpu); -#endif + if (!tau_int_enable) + TAUupdate(cpu); + + /* Stop thermal sensor comparisons and interrupts */ + mtspr(SPRN_THRM3, 0); size = tau[cpu].high - tau[cpu].low; if (size > min_window && ! tau[cpu].grew) { @@ -173,32 +148,26 @@ static void tau_timeout(void * info) set_thresholds(cpu); - /* - * Do the enable every time, since otherwise a bunch of (relatively) - * complex sleep code needs to be added. One mtspr every time - * tau_timeout is called is probably not a big deal. - * - * Enable thermal sensor and set up sample interval timer - * need 20 us to do the compare.. until a nice 'cpu_speed' function - * call is implemented, just assume a 500 mhz clock. It doesn't really - * matter if we take too long for a compare since it's all interrupt - * driven anyway. - * - * use a extra long time.. (60 us @ 500 mhz) + /* Restart thermal sensor comparisons and interrupts. + * The "PowerPC 740 and PowerPC 750 Microprocessor Datasheet" + * recommends that "the maximum value be set in THRM3 under all + * conditions." */ - mtspr(SPRN_THRM3, THRM3_SITV(500*60) | THRM3_E); - - local_irq_restore(flags); + mtspr(SPRN_THRM3, THRM3_SITV(0x1fff) | THRM3_E); } -static void tau_timeout_smp(struct timer_list *unused) -{ +static struct workqueue_struct *tau_workq; - /* schedule ourselves to be run again */ - mod_timer(&tau_timer, jiffies + shrink_timer) ; +static void tau_work_func(struct work_struct *work) +{ + msleep(shrink_timer); on_each_cpu(tau_timeout, NULL, 0); + /* schedule ourselves to be run again */ + queue_work(tau_workq, work); } +DECLARE_WORK(tau_work, tau_work_func); + /* * setup the TAU * @@ -231,21 +200,19 @@ static int __init TAU_init(void) return 1; } + tau_int_enable = IS_ENABLED(CONFIG_TAU_INT) && + !strcmp(cur_cpu_spec->platform, "ppc750"); - /* first, set up the window shrinking timer */ - timer_setup(&tau_timer, tau_timeout_smp, 0); - tau_timer.expires = jiffies + shrink_timer; - add_timer(&tau_timer); + tau_workq = alloc_workqueue("tau", WQ_UNBOUND, 1); + if (!tau_workq) + return -ENOMEM; on_each_cpu(TAU_init_smp, NULL, 0); - printk("Thermal assist unit "); -#ifdef CONFIG_TAU_INT - printk("using interrupts, "); -#else - printk("using timers, "); -#endif - printk("shrink_timer: %d jiffies\n", shrink_timer); + queue_work(tau_workq, &tau_work); + + pr_info("Thermal assist unit using %s, shrink_timer: %d ms\n", + tau_int_enable ? "interrupts" : "workqueue", shrink_timer); tau_initialized = 1; return 0; diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index 5449e76cf2df..f6c21f6af274 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -492,35 +492,6 @@ static inline void clear_irq_work_pending(void) "i" (offsetof(struct paca_struct, irq_work_pending))); } -void arch_irq_work_raise(void) -{ - preempt_disable(); - set_irq_work_pending_flag(); - /* - * Non-nmi code running with interrupts disabled will replay - * irq_happened before it re-enables interrupts, so setthe - * decrementer there instead of causing a hardware exception - * which would immediately hit the masked interrupt handler - * and have the net effect of setting the decrementer in - * irq_happened. - * - * NMI interrupts can not check this when they return, so the - * decrementer hardware exception is raised, which will fire - * when interrupts are next enabled. - * - * BookE does not support this yet, it must audit all NMI - * interrupt handlers to ensure they call nmi_enter() so this - * check would be correct. - */ - if (IS_ENABLED(CONFIG_BOOKE) || !irqs_disabled() || in_nmi()) { - set_dec(1); - } else { - hard_irq_disable(); - local_paca->irq_happened |= PACA_IRQ_DEC; - } - preempt_enable(); -} - #else /* 32-bit */ DEFINE_PER_CPU(u8, irq_work_pending); @@ -529,16 +500,27 @@ DEFINE_PER_CPU(u8, irq_work_pending); #define test_irq_work_pending() __this_cpu_read(irq_work_pending) #define clear_irq_work_pending() __this_cpu_write(irq_work_pending, 0) +#endif /* 32 vs 64 bit */ + void arch_irq_work_raise(void) { + /* + * 64-bit code that uses irq soft-mask can just cause an immediate + * interrupt here that gets soft masked, if this is called under + * local_irq_disable(). It might be possible to prevent that happening + * by noticing interrupts are disabled and setting decrementer pending + * to be replayed when irqs are enabled. The problem there is that + * tracing can call irq_work_raise, including in code that does low + * level manipulations of irq soft-mask state (e.g., trace_hardirqs_on) + * which could get tangled up if we're messing with the same state + * here. + */ preempt_disable(); set_irq_work_pending_flag(); set_dec(1); preempt_enable(); } -#endif /* 32 vs 64 bit */ - #else /* CONFIG_IRQ_WORK */ #define test_irq_work_pending() 0 diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index d5f351f02c15..2379c4bf3979 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -430,11 +430,14 @@ out: #ifdef CONFIG_PPC_BOOK3S_64 BUG_ON(get_paca()->in_nmi == 0); if (get_paca()->in_nmi > 1) - nmi_panic(regs, "Unrecoverable nested System Reset"); + die("Unrecoverable nested System Reset", regs, SIGABRT); #endif /* Must die if the interrupt is not recoverable */ - if (!(regs->msr & MSR_RI)) - nmi_panic(regs, "Unrecoverable System Reset"); + if (!(regs->msr & MSR_RI)) { + /* For the reason explained in die_mce, nmi_exit before die */ + nmi_exit(); + die("Unrecoverable System Reset", regs, SIGABRT); + } if (!nested) nmi_exit(); @@ -775,7 +778,7 @@ void machine_check_exception(struct pt_regs *regs) /* Must die if the interrupt is not recoverable */ if (!(regs->msr & MSR_RI)) - nmi_panic(regs, "Unrecoverable Machine check"); + die("Unrecoverable Machine check", regs, SIGBUS); return; @@ -794,7 +797,7 @@ static void p9_hmi_special_emu(struct pt_regs *regs) { unsigned int ra, rb, t, i, sel, instr, rc; const void __user *addr; - u8 vbuf[16], *vdst; + u8 vbuf[16] __aligned(16), *vdst; unsigned long ea, msr, msr_mask; bool swap; diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c index 65b3bdb99f0b..31ab6eb61e26 100644 --- a/arch/powerpc/kernel/vdso.c +++ b/arch/powerpc/kernel/vdso.c @@ -705,7 +705,7 @@ int vdso_getcpu_init(void) node = cpu_to_node(cpu); WARN_ON_ONCE(node > 0xffff); - val = (cpu & 0xfff) | ((node & 0xffff) << 16); + val = (cpu & 0xffff) | ((node & 0xffff) << 16); mtspr(SPRN_SPRG_VDSO_WRITE, val); get_paca()->sprg_vdso = val; diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index d081d726ca8e..9b346f3d2814 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -99,6 +99,7 @@ SECTIONS #endif /* careful! __ftr_alt_* sections need to be close to .text */ *(.text.hot TEXT_MAIN .text.fixup .text.unlikely .fixup __ftr_alt_* .ref.text); + NOINSTR_TEXT SCHED_TEXT CPUIDLE_TEXT LOCK_TEXT @@ -141,6 +142,20 @@ SECTIONS } . = ALIGN(8); + __uaccess_flush_fixup : AT(ADDR(__uaccess_flush_fixup) - LOAD_OFFSET) { + __start___uaccess_flush_fixup = .; + *(__uaccess_flush_fixup) + __stop___uaccess_flush_fixup = .; + } + + . = ALIGN(8); + __entry_flush_fixup : AT(ADDR(__entry_flush_fixup) - LOAD_OFFSET) { + __start___entry_flush_fixup = .; + *(__entry_flush_fixup) + __stop___entry_flush_fixup = .; + } + + . = ALIGN(8); __stf_exit_barrier_fixup : AT(ADDR(__stf_exit_barrier_fixup) - LOAD_OFFSET) { __start___stf_exit_barrier_fixup = .; *(__stf_exit_barrier_fixup) diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c index cc05f346e042..bc9d1321dc73 100644 --- a/arch/powerpc/kvm/book3s.c +++ b/arch/powerpc/kvm/book3s.c @@ -812,7 +812,8 @@ void kvmppc_core_commit_memory_region(struct kvm *kvm, kvm->arch.kvm_ops->commit_memory_region(kvm, mem, old, new); } -int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end) +int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end, + bool blockable) { return kvm->arch.kvm_ops->unmap_hva_range(kvm, start, end); } diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c index 998f8d089ac7..df0f08cb821b 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_radix.c +++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c @@ -171,7 +171,13 @@ static struct kmem_cache *kvm_pmd_cache; static pte_t *kvmppc_pte_alloc(void) { - return kmem_cache_alloc(kvm_pte_cache, GFP_KERNEL); + pte_t *pte; + + pte = kmem_cache_alloc(kvm_pte_cache, GFP_KERNEL); + /* pmd_populate() will only reference _pa(pte). */ + kmemleak_ignore(pte); + + return pte; } static void kvmppc_pte_free(pte_t *ptep) @@ -187,7 +193,13 @@ static inline int pmd_is_leaf(pmd_t pmd) static pmd_t *kvmppc_pmd_alloc(void) { - return kmem_cache_alloc(kvm_pmd_cache, GFP_KERNEL); + pmd_t *pmd; + + pmd = kmem_cache_alloc(kvm_pmd_cache, GFP_KERNEL); + /* pud_populate() will only reference _pa(pmd). */ + kmemleak_ignore(pmd); + + return pmd; } static void kvmppc_pmd_free(pmd_t *pmdp) diff --git a/arch/powerpc/kvm/book3s_hv_tm.c b/arch/powerpc/kvm/book3s_hv_tm.c index 31cd0f327c8a..e7fd60cf9780 100644 --- a/arch/powerpc/kvm/book3s_hv_tm.c +++ b/arch/powerpc/kvm/book3s_hv_tm.c @@ -6,6 +6,8 @@ * published by the Free Software Foundation. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/kvm_host.h> #include <asm/kvm_ppc.h> @@ -47,7 +49,18 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu) u64 newmsr, bescr; int ra, rs; - switch (instr & 0xfc0007ff) { + /* + * rfid, rfebb, and mtmsrd encode bit 31 = 0 since it's a reserved bit + * in these instructions, so masking bit 31 out doesn't change these + * instructions. For treclaim., tsr., and trechkpt. instructions if bit + * 31 = 0 then they are per ISA invalid forms, however P9 UM, in section + * 4.6.10 Book II Invalid Forms, informs specifically that ignoring bit + * 31 is an acceptable way to handle these invalid forms that have + * bit 31 = 0. Moreover, for emulation purposes both forms (w/ and wo/ + * bit 31 set) can generate a softpatch interrupt. Hence both forms + * are handled below for these instructions so they behave the same way. + */ + switch (instr & PO_XOP_OPCODE_MASK) { case PPC_INST_RFID: /* XXX do we need to check for PR=0 here? */ newmsr = vcpu->arch.shregs.srr1; @@ -108,7 +121,8 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu) vcpu->arch.shregs.msr = newmsr; return RESUME_GUEST; - case PPC_INST_TSR: + /* ignore bit 31, see comment above */ + case (PPC_INST_TSR & PO_XOP_OPCODE_MASK): /* check for PR=1 and arch 2.06 bit set in PCR */ if ((msr & MSR_PR) && (vcpu->arch.vcore->pcr & PCR_ARCH_206)) { /* generate an illegal instruction interrupt */ @@ -143,7 +157,8 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu) vcpu->arch.shregs.msr = msr; return RESUME_GUEST; - case PPC_INST_TRECLAIM: + /* ignore bit 31, see comment above */ + case (PPC_INST_TRECLAIM & PO_XOP_OPCODE_MASK): /* check for TM disabled in the HFSCR or MSR */ if (!(vcpu->arch.hfscr & HFSCR_TM)) { /* generate an illegal instruction interrupt */ @@ -179,7 +194,8 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu) vcpu->arch.shregs.msr &= ~MSR_TS_MASK; return RESUME_GUEST; - case PPC_INST_TRECHKPT: + /* ignore bit 31, see comment above */ + case (PPC_INST_TRECHKPT & PO_XOP_OPCODE_MASK): /* XXX do we need to check for PR=0 here? */ /* check for TM disabled in the HFSCR or MSR */ if (!(vcpu->arch.hfscr & HFSCR_TM)) { @@ -211,6 +227,8 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu) } /* What should we do here? We didn't recognize the instruction */ - WARN_ON_ONCE(1); + kvmppc_core_queue_program(vcpu, SRR1_PROGILL); + pr_warn_ratelimited("Unrecognized TM-related instruction %#x for emulation", instr); + return RESUME_GUEST; } diff --git a/arch/powerpc/kvm/book3s_hv_tm_builtin.c b/arch/powerpc/kvm/book3s_hv_tm_builtin.c index 3cf5863bc06e..3c7ca2fa1959 100644 --- a/arch/powerpc/kvm/book3s_hv_tm_builtin.c +++ b/arch/powerpc/kvm/book3s_hv_tm_builtin.c @@ -26,7 +26,18 @@ int kvmhv_p9_tm_emulation_early(struct kvm_vcpu *vcpu) u64 newmsr, msr, bescr; int rs; - switch (instr & 0xfc0007ff) { + /* + * rfid, rfebb, and mtmsrd encode bit 31 = 0 since it's a reserved bit + * in these instructions, so masking bit 31 out doesn't change these + * instructions. For the tsr. instruction if bit 31 = 0 then it is per + * ISA an invalid form, however P9 UM, in section 4.6.10 Book II Invalid + * Forms, informs specifically that ignoring bit 31 is an acceptable way + * to handle TM-related invalid forms that have bit 31 = 0. Moreover, + * for emulation purposes both forms (w/ and wo/ bit 31 set) can + * generate a softpatch interrupt. Hence both forms are handled below + * for tsr. to make them behave the same way. + */ + switch (instr & PO_XOP_OPCODE_MASK) { case PPC_INST_RFID: /* XXX do we need to check for PR=0 here? */ newmsr = vcpu->arch.shregs.srr1; @@ -76,7 +87,8 @@ int kvmhv_p9_tm_emulation_early(struct kvm_vcpu *vcpu) vcpu->arch.shregs.msr = newmsr; return 1; - case PPC_INST_TSR: + /* ignore bit 31, see comment above */ + case (PPC_INST_TSR & PO_XOP_OPCODE_MASK): /* we know the MSR has the TS field = S (0b01) here */ msr = vcpu->arch.shregs.msr; /* check for PR=1 and arch 2.06 bit set in PCR */ diff --git a/arch/powerpc/kvm/e500_mmu_host.c b/arch/powerpc/kvm/e500_mmu_host.c index 8f2985e46f6f..bbb02195dc53 100644 --- a/arch/powerpc/kvm/e500_mmu_host.c +++ b/arch/powerpc/kvm/e500_mmu_host.c @@ -737,7 +737,8 @@ static int kvm_unmap_hva(struct kvm *kvm, unsigned long hva) return 0; } -int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end) +int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end, + bool blockable) { /* kvm_unmap_hva flushes everything anyways */ kvm_unmap_hva(kvm, start); diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 51cd66dc1bb0..7c8354dfe80e 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -1497,7 +1497,7 @@ int kvmppc_handle_vmx_load(struct kvm_run *run, struct kvm_vcpu *vcpu, return emulated; } -int kvmppc_get_vmx_dword(struct kvm_vcpu *vcpu, int index, u64 *val) +static int kvmppc_get_vmx_dword(struct kvm_vcpu *vcpu, int index, u64 *val) { union kvmppc_one_reg reg; int vmx_offset = 0; @@ -1515,7 +1515,7 @@ int kvmppc_get_vmx_dword(struct kvm_vcpu *vcpu, int index, u64 *val) return result; } -int kvmppc_get_vmx_word(struct kvm_vcpu *vcpu, int index, u64 *val) +static int kvmppc_get_vmx_word(struct kvm_vcpu *vcpu, int index, u64 *val) { union kvmppc_one_reg reg; int vmx_offset = 0; @@ -1533,7 +1533,7 @@ int kvmppc_get_vmx_word(struct kvm_vcpu *vcpu, int index, u64 *val) return result; } -int kvmppc_get_vmx_hword(struct kvm_vcpu *vcpu, int index, u64 *val) +static int kvmppc_get_vmx_hword(struct kvm_vcpu *vcpu, int index, u64 *val) { union kvmppc_one_reg reg; int vmx_offset = 0; @@ -1551,7 +1551,7 @@ int kvmppc_get_vmx_hword(struct kvm_vcpu *vcpu, int index, u64 *val) return result; } -int kvmppc_get_vmx_byte(struct kvm_vcpu *vcpu, int index, u64 *val) +static int kvmppc_get_vmx_byte(struct kvm_vcpu *vcpu, int index, u64 *val) { union kvmppc_one_reg reg; int vmx_offset = 0; diff --git a/arch/powerpc/lib/checksum_wrappers.c b/arch/powerpc/lib/checksum_wrappers.c index a0cb63fb76a1..8d83c39be7e4 100644 --- a/arch/powerpc/lib/checksum_wrappers.c +++ b/arch/powerpc/lib/checksum_wrappers.c @@ -29,6 +29,7 @@ __wsum csum_and_copy_from_user(const void __user *src, void *dst, unsigned int csum; might_sleep(); + allow_read_from_user(src, len); *err_ptr = 0; @@ -60,6 +61,7 @@ __wsum csum_and_copy_from_user(const void __user *src, void *dst, } out: + prevent_read_from_user(src, len); return (__force __wsum)csum; } EXPORT_SYMBOL(csum_and_copy_from_user); @@ -70,6 +72,7 @@ __wsum csum_and_copy_to_user(const void *src, void __user *dst, int len, unsigned int csum; might_sleep(); + allow_write_to_user(dst, len); *err_ptr = 0; @@ -97,6 +100,7 @@ __wsum csum_and_copy_to_user(const void *src, void __user *dst, int len, } out: + prevent_write_to_user(dst, len); return (__force __wsum)csum; } EXPORT_SYMBOL(csum_and_copy_to_user); diff --git a/arch/powerpc/lib/feature-fixups.c b/arch/powerpc/lib/feature-fixups.c index dbe478e7b8e0..1561094ea4a5 100644 --- a/arch/powerpc/lib/feature-fixups.c +++ b/arch/powerpc/lib/feature-fixups.c @@ -18,6 +18,7 @@ #include <linux/string.h> #include <linux/init.h> #include <linux/sched/mm.h> +#include <linux/stop_machine.h> #include <asm/cputable.h> #include <asm/code-patching.h> #include <asm/page.h> @@ -225,11 +226,143 @@ void do_stf_exit_barrier_fixups(enum stf_barrier_type types) : "unknown"); } +static int __do_stf_barrier_fixups(void *data) +{ + enum stf_barrier_type *types = data; + + do_stf_entry_barrier_fixups(*types); + do_stf_exit_barrier_fixups(*types); + + return 0; +} void do_stf_barrier_fixups(enum stf_barrier_type types) { - do_stf_entry_barrier_fixups(types); - do_stf_exit_barrier_fixups(types); + /* + * The call to the fallback entry flush, and the fallback/sync-ori exit + * flush can not be safely patched in/out while other CPUs are executing + * them. So call __do_stf_barrier_fixups() on one CPU while all other CPUs + * spin in the stop machine core with interrupts hard disabled. + */ + stop_machine(__do_stf_barrier_fixups, &types, NULL); +} + +void do_uaccess_flush_fixups(enum l1d_flush_type types) +{ + unsigned int instrs[4], *dest; + long *start, *end; + int i; + + start = PTRRELOC(&__start___uaccess_flush_fixup); + end = PTRRELOC(&__stop___uaccess_flush_fixup); + + instrs[0] = 0x60000000; /* nop */ + instrs[1] = 0x60000000; /* nop */ + instrs[2] = 0x60000000; /* nop */ + instrs[3] = 0x4e800020; /* blr */ + + i = 0; + if (types == L1D_FLUSH_FALLBACK) { + instrs[3] = 0x60000000; /* nop */ + /* fallthrough to fallback flush */ + } + + if (types & L1D_FLUSH_ORI) { + instrs[i++] = 0x63ff0000; /* ori 31,31,0 speculation barrier */ + instrs[i++] = 0x63de0000; /* ori 30,30,0 L1d flush*/ + } + + if (types & L1D_FLUSH_MTTRIG) + instrs[i++] = 0x7c12dba6; /* mtspr TRIG2,r0 (SPR #882) */ + + for (i = 0; start < end; start++, i++) { + dest = (void *)start + *start; + + pr_devel("patching dest %lx\n", (unsigned long)dest); + + patch_instruction(dest, instrs[0]); + + patch_instruction((dest + 1), instrs[1]); + patch_instruction((dest + 2), instrs[2]); + patch_instruction((dest + 3), instrs[3]); + } + + printk(KERN_DEBUG "uaccess-flush: patched %d locations (%s flush)\n", i, + (types == L1D_FLUSH_NONE) ? "no" : + (types == L1D_FLUSH_FALLBACK) ? "fallback displacement" : + (types & L1D_FLUSH_ORI) ? (types & L1D_FLUSH_MTTRIG) + ? "ori+mttrig type" + : "ori type" : + (types & L1D_FLUSH_MTTRIG) ? "mttrig type" + : "unknown"); +} + +static int __do_entry_flush_fixups(void *data) +{ + enum l1d_flush_type types = *(enum l1d_flush_type *)data; + unsigned int instrs[3], *dest; + long *start, *end; + int i; + + start = PTRRELOC(&__start___entry_flush_fixup); + end = PTRRELOC(&__stop___entry_flush_fixup); + + instrs[0] = 0x60000000; /* nop */ + instrs[1] = 0x60000000; /* nop */ + instrs[2] = 0x60000000; /* nop */ + + i = 0; + if (types == L1D_FLUSH_FALLBACK) { + instrs[i++] = 0x7d4802a6; /* mflr r10 */ + instrs[i++] = 0x60000000; /* branch patched below */ + instrs[i++] = 0x7d4803a6; /* mtlr r10 */ + } + + if (types & L1D_FLUSH_ORI) { + instrs[i++] = 0x63ff0000; /* ori 31,31,0 speculation barrier */ + instrs[i++] = 0x63de0000; /* ori 30,30,0 L1d flush*/ + } + + if (types & L1D_FLUSH_MTTRIG) + instrs[i++] = 0x7c12dba6; /* mtspr TRIG2,r0 (SPR #882) */ + + for (i = 0; start < end; start++, i++) { + dest = (void *)start + *start; + + pr_devel("patching dest %lx\n", (unsigned long)dest); + + patch_instruction(dest, instrs[0]); + + if (types == L1D_FLUSH_FALLBACK) + patch_branch((dest + 1), (unsigned long)&entry_flush_fallback, + BRANCH_SET_LINK); + else + patch_instruction((dest + 1), instrs[1]); + + patch_instruction((dest + 2), instrs[2]); + } + + printk(KERN_DEBUG "entry-flush: patched %d locations (%s flush)\n", i, + (types == L1D_FLUSH_NONE) ? "no" : + (types == L1D_FLUSH_FALLBACK) ? "fallback displacement" : + (types & L1D_FLUSH_ORI) ? (types & L1D_FLUSH_MTTRIG) + ? "ori+mttrig type" + : "ori type" : + (types & L1D_FLUSH_MTTRIG) ? "mttrig type" + : "unknown"); + + return 0; +} + +void do_entry_flush_fixups(enum l1d_flush_type types) +{ + /* + * The call to the fallback flush can not be safely patched in/out while + * other CPUs are executing it. So call __do_entry_flush_fixups() on one + * CPU while all other CPUs spin in the stop machine core with interrupts + * hard disabled. + */ + stop_machine(__do_entry_flush_fixups, &types, NULL); } void do_rfi_flush_fixups(enum l1d_flush_type types) diff --git a/arch/powerpc/lib/string_32.S b/arch/powerpc/lib/string_32.S index f69a6aab7bfb..1ddb26394e8a 100644 --- a/arch/powerpc/lib/string_32.S +++ b/arch/powerpc/lib/string_32.S @@ -17,7 +17,7 @@ CACHELINE_BYTES = L1_CACHE_BYTES LG_CACHELINE_BYTES = L1_CACHE_SHIFT CACHELINE_MASK = (L1_CACHE_BYTES-1) -_GLOBAL(__clear_user) +_GLOBAL(__arch_clear_user) /* * Use dcbz on the complete cache lines in the destination * to set them to zero. This requires that the destination @@ -87,4 +87,4 @@ _GLOBAL(__clear_user) EX_TABLE(8b, 91b) EX_TABLE(9b, 91b) -EXPORT_SYMBOL(__clear_user) +EXPORT_SYMBOL(__arch_clear_user) diff --git a/arch/powerpc/lib/string_64.S b/arch/powerpc/lib/string_64.S index 56aac4c22025..ea3798f4f25f 100644 --- a/arch/powerpc/lib/string_64.S +++ b/arch/powerpc/lib/string_64.S @@ -29,7 +29,7 @@ PPC64_CACHES: .section ".text" /** - * __clear_user: - Zero a block of memory in user space, with less checking. + * __arch_clear_user: - Zero a block of memory in user space, with less checking. * @to: Destination address, in user space. * @n: Number of bytes to zero. * @@ -70,7 +70,7 @@ err3; stb r0,0(r3) mr r3,r4 blr -_GLOBAL_TOC(__clear_user) +_GLOBAL_TOC(__arch_clear_user) cmpdi r4,32 neg r6,r3 li r0,0 @@ -193,4 +193,4 @@ err1; dcbz 0,r3 cmpdi r4,32 blt .Lshort_clear b .Lmedium_clear -EXPORT_SYMBOL(__clear_user) +EXPORT_SYMBOL(__arch_clear_user) diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index 6e0ff8b600ce..eb5252177b66 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -233,6 +233,9 @@ static bool bad_kernel_fault(bool is_exec, unsigned long error_code, return is_exec || (address >= TASK_SIZE); } +// This comes from 64-bit struct rt_sigframe + __SIGNAL_FRAMESIZE +#define SIGFRAME_MAX_SIZE (4096 + 128) + static bool bad_stack_expansion(struct pt_regs *regs, unsigned long address, struct vm_area_struct *vma, unsigned int flags, bool *must_retry) @@ -240,7 +243,7 @@ static bool bad_stack_expansion(struct pt_regs *regs, unsigned long address, /* * N.B. The POWER/Open ABI allows programs to access up to * 288 bytes below the stack pointer. - * The kernel signal delivery code writes up to about 1.5kB + * The kernel signal delivery code writes a bit over 4KB * below the stack pointer (r1) before decrementing it. * The exec code can write slightly over 640kB to the stack * before setting the user r1. Thus we allow the stack to @@ -265,7 +268,7 @@ static bool bad_stack_expansion(struct pt_regs *regs, unsigned long address, * between the last mapped region and the stack will * expand the stack rather than segfaulting. */ - if (address + 2048 >= uregs->gpr[1]) + if (address + SIGFRAME_MAX_SIZE >= uregs->gpr[1]) return false; if ((flags & FAULT_FLAG_WRITE) && (flags & FAULT_FLAG_USER) && diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c index 5404a631d583..9ee235fca427 100644 --- a/arch/powerpc/mm/pgtable-radix.c +++ b/arch/powerpc/mm/pgtable-radix.c @@ -115,7 +115,7 @@ static int early_map_kernel_page(unsigned long ea, unsigned long pa, set_the_pte: set_pte_at(&init_mm, ea, ptep, pfn_pte(pfn, flags)); - smp_wmb(); + asm volatile("ptesync": : :"memory"); return 0; } @@ -169,7 +169,7 @@ static int __map_kernel_page(unsigned long ea, unsigned long pa, set_the_pte: set_pte_at(&init_mm, ea, ptep, pfn_pte(pfn, flags)); - smp_wmb(); + asm volatile("ptesync": : :"memory"); return 0; } diff --git a/arch/powerpc/mm/pkeys.c b/arch/powerpc/mm/pkeys.c index 25a8dd9cd71d..a587f9013988 100644 --- a/arch/powerpc/mm/pkeys.c +++ b/arch/powerpc/mm/pkeys.c @@ -81,13 +81,17 @@ int pkey_initialize(void) scan_pkey_feature(); /* - * Let's assume 32 pkeys on P8 bare metal, if its not defined by device - * tree. We make this exception since skiboot forgot to expose this - * property on power8. + * Let's assume 32 pkeys on P8/P9 bare metal, if its not defined by device + * tree. We make this exception since some version of skiboot forgot to + * expose this property on power8/9. */ - if (!pkeys_devtree_defined && !firmware_has_feature(FW_FEATURE_LPAR) && - cpu_has_feature(CPU_FTRS_POWER8)) - pkeys_total = 32; + if (!pkeys_devtree_defined && !firmware_has_feature(FW_FEATURE_LPAR)) { + unsigned long pvr = mfspr(SPRN_PVR); + + if (PVR_VER(pvr) == PVR_POWER8 || PVR_VER(pvr) == PVR_POWER8E || + PVR_VER(pvr) == PVR_POWER8NVL || PVR_VER(pvr) == PVR_POWER9) + pkeys_total = 32; + } /* * Adjust the upper limit, based on the number of bits supported by @@ -365,12 +369,14 @@ static bool pkey_access_permitted(int pkey, bool write, bool execute) return true; pkey_shift = pkeyshift(pkey); - if (execute && !(read_iamr() & (IAMR_EX_BIT << pkey_shift))) - return true; + if (execute) + return !(read_iamr() & (IAMR_EX_BIT << pkey_shift)); + + amr = read_amr(); + if (write) + return !(amr & (AMR_WR_BIT << pkey_shift)); - amr = read_amr(); /* Delay reading amr until absolutely needed */ - return ((!write && !(amr & (AMR_RD_BIT << pkey_shift))) || - (write && !(amr & (AMR_WR_BIT << pkey_shift)))); + return !(amr & (AMR_RD_BIT << pkey_shift)); } bool arch_pte_access_permitted(u64 pte, bool write, bool execute) diff --git a/arch/powerpc/mm/tlb-radix.c b/arch/powerpc/mm/tlb-radix.c index 1749f15fc070..80b8fc4173de 100644 --- a/arch/powerpc/mm/tlb-radix.c +++ b/arch/powerpc/mm/tlb-radix.c @@ -598,19 +598,29 @@ static void do_exit_flush_lazy_tlb(void *arg) struct mm_struct *mm = arg; unsigned long pid = mm->context.id; + /* + * A kthread could have done a mmget_not_zero() after the flushing CPU + * checked mm_is_singlethreaded, and be in the process of + * kthread_use_mm when interrupted here. In that case, current->mm will + * be set to mm, because kthread_use_mm() setting ->mm and switching to + * the mm is done with interrupts off. + */ if (current->mm == mm) - return; /* Local CPU */ + goto out_flush; if (current->active_mm == mm) { - /* - * Must be a kernel thread because sender is single-threaded. - */ - BUG_ON(current->mm); + WARN_ON_ONCE(current->mm != NULL); + /* Is a kernel thread and is using mm as the lazy tlb */ mmgrab(&init_mm); - switch_mm(mm, &init_mm, current); current->active_mm = &init_mm; + switch_mm_irqs_off(mm, &init_mm, current); mmdrop(mm); } + + atomic_dec(&mm->context.active_cpus); + cpumask_clear_cpu(smp_processor_id(), mm_cpumask(mm)); + +out_flush: _tlbiel_pid(pid, RIC_FLUSH_ALL); } @@ -625,7 +635,6 @@ static void exit_flush_lazy_tlbs(struct mm_struct *mm) */ smp_call_function_many(mm_cpumask(mm), do_exit_flush_lazy_tlb, (void *)mm, 1); - mm_reset_thread_local(mm); } void radix__flush_tlb_mm(struct mm_struct *mm) diff --git a/arch/powerpc/mm/tlb_nohash_low.S b/arch/powerpc/mm/tlb_nohash_low.S index e066a658acac..56f58a362ea5 100644 --- a/arch/powerpc/mm/tlb_nohash_low.S +++ b/arch/powerpc/mm/tlb_nohash_low.S @@ -402,7 +402,7 @@ _GLOBAL(set_context) * extern void loadcam_entry(unsigned int index) * * Load TLBCAM[index] entry in to the L2 CAM MMU - * Must preserve r7, r8, r9, and r10 + * Must preserve r7, r8, r9, r10 and r11 */ _GLOBAL(loadcam_entry) mflr r5 @@ -438,6 +438,10 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_BIG_PHYS) */ _GLOBAL(loadcam_multi) mflr r8 + /* Don't switch to AS=1 if already there */ + mfmsr r11 + andi. r11,r11,MSR_IS + bne 10f /* * Set up temporary TLB entry that is the same as what we're @@ -463,6 +467,7 @@ _GLOBAL(loadcam_multi) mtmsr r6 isync +10: mr r9,r3 add r10,r3,r4 2: bl loadcam_entry @@ -471,6 +476,10 @@ _GLOBAL(loadcam_multi) mr r3,r9 blt 2b + /* Don't return to AS=0 if we were in AS=1 at function start */ + andi. r11,r11,MSR_IS + bne 3f + /* Return to AS=0 and clear the temporary entry */ mfmsr r6 rlwinm. r6,r6,0,~(MSR_IS|MSR_DS) @@ -486,6 +495,7 @@ _GLOBAL(loadcam_multi) tlbwe isync +3: mtlr r8 blr #endif diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index 4004dbdab9c7..091bdeaf02a3 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -2046,7 +2046,17 @@ static void record_and_restart(struct perf_event *event, unsigned long val, left += period; if (left <= 0) left = period; - record = siar_valid(regs); + + /* + * If address is not requested in the sample via + * PERF_SAMPLE_IP, just record that sample irrespective + * of SIAR valid check. + */ + if (event->attr.sample_type & PERF_SAMPLE_IP) + record = siar_valid(regs); + else + record = 1; + event->hw.last_period = event->hw.sample_period; } if (left < 0x80000000LL) @@ -2059,6 +2069,17 @@ static void record_and_restart(struct perf_event *event, unsigned long val, perf_event_update_userpage(event); /* + * Due to hardware limitation, sometimes SIAR could sample a kernel + * address even when freeze on supervisor state (kernel) is set in + * MMCR2. Check attr.exclude_kernel and address to drop the sample in + * these cases. + */ + if (event->attr.exclude_kernel && + (event->attr.sample_type & PERF_SAMPLE_IP) && + is_kernel_addr(mfspr(SPRN_SIAR))) + record = 0; + + /* * Finally record data if requested. */ if (record) { @@ -2087,6 +2108,10 @@ static void record_and_restart(struct perf_event *event, unsigned long val, if (perf_event_overflow(event, &data, regs)) power_pmu_stop(event, 0); + } else if (period) { + /* Account for interrupt in case of invalid SIAR */ + if (perf_event_account_interrupt(event)) + power_pmu_stop(event, 0); } } diff --git a/arch/powerpc/perf/hv-24x7.c b/arch/powerpc/perf/hv-24x7.c index 72238eedc360..2bb798918483 100644 --- a/arch/powerpc/perf/hv-24x7.c +++ b/arch/powerpc/perf/hv-24x7.c @@ -1413,16 +1413,6 @@ static void h_24x7_event_read(struct perf_event *event) h24x7hw = &get_cpu_var(hv_24x7_hw); h24x7hw->events[i] = event; put_cpu_var(h24x7hw); - /* - * Clear the event count so we can compute the _change_ - * in the 24x7 raw counter value at the end of the txn. - * - * Note that we could alternatively read the 24x7 value - * now and save its value in event->hw.prev_count. But - * that would require issuing a hcall, which would then - * defeat the purpose of using the txn interface. - */ - local64_set(&event->count, 0); } put_cpu_var(hv_24x7_reqb); diff --git a/arch/powerpc/perf/hv-gpci-requests.h b/arch/powerpc/perf/hv-gpci-requests.h index e608f9db12dd..8965b4463d43 100644 --- a/arch/powerpc/perf/hv-gpci-requests.h +++ b/arch/powerpc/perf/hv-gpci-requests.h @@ -95,7 +95,7 @@ REQUEST(__field(0, 8, partition_id) #define REQUEST_NAME system_performance_capabilities #define REQUEST_NUM 0x40 -#define REQUEST_IDX_KIND "starting_index=0xffffffffffffffff" +#define REQUEST_IDX_KIND "starting_index=0xffffffff" #include I(REQUEST_BEGIN) REQUEST(__field(0, 1, perf_collect_privileged) __field(0x1, 1, capability_mask) @@ -223,7 +223,7 @@ REQUEST(__field(0, 2, partition_id) #define REQUEST_NAME system_hypervisor_times #define REQUEST_NUM 0xF0 -#define REQUEST_IDX_KIND "starting_index=0xffffffffffffffff" +#define REQUEST_IDX_KIND "starting_index=0xffffffff" #include I(REQUEST_BEGIN) REQUEST(__count(0, 8, time_spent_to_dispatch_virtual_processors) __count(0x8, 8, time_spent_processing_virtual_processor_timers) @@ -234,7 +234,7 @@ REQUEST(__count(0, 8, time_spent_to_dispatch_virtual_processors) #define REQUEST_NAME system_tlbie_count_and_time #define REQUEST_NUM 0xF4 -#define REQUEST_IDX_KIND "starting_index=0xffffffffffffffff" +#define REQUEST_IDX_KIND "starting_index=0xffffffff" #include I(REQUEST_BEGIN) REQUEST(__count(0, 8, tlbie_instructions_issued) /* diff --git a/arch/powerpc/perf/isa207-common.c b/arch/powerpc/perf/isa207-common.c index 053b8e9aa9e7..a1ff4142cc6a 100644 --- a/arch/powerpc/perf/isa207-common.c +++ b/arch/powerpc/perf/isa207-common.c @@ -273,6 +273,15 @@ int isa207_get_constraint(u64 event, unsigned long *maskp, unsigned long *valp) mask |= CNST_PMC_MASK(pmc); value |= CNST_PMC_VAL(pmc); + + /* + * PMC5 and PMC6 are used to count cycles and instructions and + * they do not support most of the constraint bits. Add a check + * to exclude PMC5/6 from most of the constraints except for + * EBB/BHRB. + */ + if (pmc >= 5) + goto ebb_bhrb; } if (pmc <= 4) { @@ -331,6 +340,7 @@ int isa207_get_constraint(u64 event, unsigned long *maskp, unsigned long *valp) } } +ebb_bhrb: if (!pmc && ebb) /* EBB events must specify the PMC */ return -1; @@ -349,8 +359,8 @@ int isa207_get_constraint(u64 event, unsigned long *maskp, unsigned long *valp) * EBB events are pinned & exclusive, so this should never actually * hit, but we leave it as a fallback in case. */ - mask |= CNST_EBB_VAL(ebb); - value |= CNST_EBB_MASK; + mask |= CNST_EBB_MASK; + value |= CNST_EBB_VAL(ebb); *maskp = mask; *valp = value; diff --git a/arch/powerpc/platforms/4xx/pci.c b/arch/powerpc/platforms/4xx/pci.c index 5aca523551ae..2f237027fdcc 100644 --- a/arch/powerpc/platforms/4xx/pci.c +++ b/arch/powerpc/platforms/4xx/pci.c @@ -1242,7 +1242,7 @@ static void __init ppc460sx_pciex_check_link(struct ppc4xx_pciex_port *port) if (mbase == NULL) { printk(KERN_ERR "%pOF: Can't map internal config space !", port->node); - goto done; + return; } while (attempt && (0 == (in_le32(mbase + PECFG_460SX_DLLSTA) @@ -1252,9 +1252,7 @@ static void __init ppc460sx_pciex_check_link(struct ppc4xx_pciex_port *port) } if (attempt) port->link = 1; -done: iounmap(mbase); - } static struct ppc4xx_pciex_hwops ppc460sx_pcie_hwops __initdata = { diff --git a/arch/powerpc/platforms/52xx/lite5200_sleep.S b/arch/powerpc/platforms/52xx/lite5200_sleep.S index 3a9969c429b3..054f927bfef9 100644 --- a/arch/powerpc/platforms/52xx/lite5200_sleep.S +++ b/arch/powerpc/platforms/52xx/lite5200_sleep.S @@ -181,7 +181,7 @@ sram_code: udelay: /* r11 - tb_ticks_per_usec, r12 - usecs, overwrites r13 */ mullw r12, r12, r11 mftb r13 /* start */ - addi r12, r13, r12 /* end */ + add r12, r13, r12 /* end */ 1: mftb r13 /* current */ cmp cr0, r13, r12 diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig index 14ef17e10ec9..9914544e6677 100644 --- a/arch/powerpc/platforms/Kconfig +++ b/arch/powerpc/platforms/Kconfig @@ -238,12 +238,11 @@ config TAU temperature within 2-4 degrees Celsius. This option shows the current on-die temperature in /proc/cpuinfo if the cpu supports it. - Unfortunately, on some chip revisions, this sensor is very inaccurate - and in many cases, does not work at all, so don't assume the cpu - temp is actually what /proc/cpuinfo says it is. + Unfortunately, this sensor is very inaccurate when uncalibrated, so + don't assume the cpu temp is actually what /proc/cpuinfo says it is. config TAU_INT - bool "Interrupt driven TAU driver (DANGEROUS)" + bool "Interrupt driven TAU driver (EXPERIMENTAL)" depends on TAU ---help--- The TAU supports an interrupt driven mode which causes an interrupt @@ -251,12 +250,7 @@ config TAU_INT to get notified the temp has exceeded a range. With this option off, a timer is used to re-check the temperature periodically. - However, on some cpus it appears that the TAU interrupt hardware - is buggy and can cause a situation which would lead unexplained hard - lockups. - - Unless you are extending the TAU driver, or enjoy kernel/hardware - debugging, leave this option off. + If in doubt, say N here. config TAU_AVERAGE bool "Average high and low temp" diff --git a/arch/powerpc/platforms/cell/Kconfig b/arch/powerpc/platforms/cell/Kconfig index 9f5958f16923..741a8fa8a3e6 100644 --- a/arch/powerpc/platforms/cell/Kconfig +++ b/arch/powerpc/platforms/cell/Kconfig @@ -46,6 +46,7 @@ config SPU_FS tristate "SPU file system" default m depends on PPC_CELL + depends on COREDUMP select SPU_BASE help The SPU file system is used to access Synergistic Processing diff --git a/arch/powerpc/platforms/cell/spufs/file.c b/arch/powerpc/platforms/cell/spufs/file.c index 43e7b93f27c7..d16adcd93921 100644 --- a/arch/powerpc/platforms/cell/spufs/file.c +++ b/arch/powerpc/platforms/cell/spufs/file.c @@ -1991,8 +1991,9 @@ static ssize_t __spufs_mbox_info_read(struct spu_context *ctx, static ssize_t spufs_mbox_info_read(struct file *file, char __user *buf, size_t len, loff_t *pos) { - int ret; struct spu_context *ctx = file->private_data; + u32 stat, data; + int ret; if (!access_ok(VERIFY_WRITE, buf, len)) return -EFAULT; @@ -2001,11 +2002,16 @@ static ssize_t spufs_mbox_info_read(struct file *file, char __user *buf, if (ret) return ret; spin_lock(&ctx->csa.register_lock); - ret = __spufs_mbox_info_read(ctx, buf, len, pos); + stat = ctx->csa.prob.mb_stat_R; + data = ctx->csa.prob.pu_mb_R; spin_unlock(&ctx->csa.register_lock); spu_release_saved(ctx); - return ret; + /* EOF if there's no entry in the mbox */ + if (!(stat & 0x0000ff)) + return 0; + + return simple_read_from_buffer(buf, len, pos, &data, sizeof(data)); } static const struct file_operations spufs_mbox_info_fops = { @@ -2032,6 +2038,7 @@ static ssize_t spufs_ibox_info_read(struct file *file, char __user *buf, size_t len, loff_t *pos) { struct spu_context *ctx = file->private_data; + u32 stat, data; int ret; if (!access_ok(VERIFY_WRITE, buf, len)) @@ -2041,11 +2048,16 @@ static ssize_t spufs_ibox_info_read(struct file *file, char __user *buf, if (ret) return ret; spin_lock(&ctx->csa.register_lock); - ret = __spufs_ibox_info_read(ctx, buf, len, pos); + stat = ctx->csa.prob.mb_stat_R; + data = ctx->csa.priv2.puint_mb_R; spin_unlock(&ctx->csa.register_lock); spu_release_saved(ctx); - return ret; + /* EOF if there's no entry in the ibox */ + if (!(stat & 0xff0000)) + return 0; + + return simple_read_from_buffer(buf, len, pos, &data, sizeof(data)); } static const struct file_operations spufs_ibox_info_fops = { @@ -2054,6 +2066,11 @@ static const struct file_operations spufs_ibox_info_fops = { .llseek = generic_file_llseek, }; +static size_t spufs_wbox_info_cnt(struct spu_context *ctx) +{ + return (4 - ((ctx->csa.prob.mb_stat_R & 0x00ff00) >> 8)) * sizeof(u32); +} + static ssize_t __spufs_wbox_info_read(struct spu_context *ctx, char __user *buf, size_t len, loff_t *pos) { @@ -2062,7 +2079,7 @@ static ssize_t __spufs_wbox_info_read(struct spu_context *ctx, u32 wbox_stat; wbox_stat = ctx->csa.prob.mb_stat_R; - cnt = 4 - ((wbox_stat & 0x00ff00) >> 8); + cnt = spufs_wbox_info_cnt(ctx); for (i = 0; i < cnt; i++) { data[i] = ctx->csa.spu_mailbox_data[i]; } @@ -2075,7 +2092,8 @@ static ssize_t spufs_wbox_info_read(struct file *file, char __user *buf, size_t len, loff_t *pos) { struct spu_context *ctx = file->private_data; - int ret; + u32 data[ARRAY_SIZE(ctx->csa.spu_mailbox_data)]; + int ret, count; if (!access_ok(VERIFY_WRITE, buf, len)) return -EFAULT; @@ -2084,11 +2102,13 @@ static ssize_t spufs_wbox_info_read(struct file *file, char __user *buf, if (ret) return ret; spin_lock(&ctx->csa.register_lock); - ret = __spufs_wbox_info_read(ctx, buf, len, pos); + count = spufs_wbox_info_cnt(ctx); + memcpy(&data, &ctx->csa.spu_mailbox_data, sizeof(data)); spin_unlock(&ctx->csa.register_lock); spu_release_saved(ctx); - return ret; + return simple_read_from_buffer(buf, len, pos, &data, + count * sizeof(u32)); } static const struct file_operations spufs_wbox_info_fops = { @@ -2097,27 +2117,33 @@ static const struct file_operations spufs_wbox_info_fops = { .llseek = generic_file_llseek, }; -static ssize_t __spufs_dma_info_read(struct spu_context *ctx, - char __user *buf, size_t len, loff_t *pos) +static void spufs_get_dma_info(struct spu_context *ctx, + struct spu_dma_info *info) { - struct spu_dma_info info; - struct mfc_cq_sr *qp, *spuqp; int i; - info.dma_info_type = ctx->csa.priv2.spu_tag_status_query_RW; - info.dma_info_mask = ctx->csa.lscsa->tag_mask.slot[0]; - info.dma_info_status = ctx->csa.spu_chnldata_RW[24]; - info.dma_info_stall_and_notify = ctx->csa.spu_chnldata_RW[25]; - info.dma_info_atomic_command_status = ctx->csa.spu_chnldata_RW[27]; + info->dma_info_type = ctx->csa.priv2.spu_tag_status_query_RW; + info->dma_info_mask = ctx->csa.lscsa->tag_mask.slot[0]; + info->dma_info_status = ctx->csa.spu_chnldata_RW[24]; + info->dma_info_stall_and_notify = ctx->csa.spu_chnldata_RW[25]; + info->dma_info_atomic_command_status = ctx->csa.spu_chnldata_RW[27]; for (i = 0; i < 16; i++) { - qp = &info.dma_info_command_data[i]; - spuqp = &ctx->csa.priv2.spuq[i]; + struct mfc_cq_sr *qp = &info->dma_info_command_data[i]; + struct mfc_cq_sr *spuqp = &ctx->csa.priv2.spuq[i]; qp->mfc_cq_data0_RW = spuqp->mfc_cq_data0_RW; qp->mfc_cq_data1_RW = spuqp->mfc_cq_data1_RW; qp->mfc_cq_data2_RW = spuqp->mfc_cq_data2_RW; qp->mfc_cq_data3_RW = spuqp->mfc_cq_data3_RW; } +} + +static ssize_t __spufs_dma_info_read(struct spu_context *ctx, + char __user *buf, size_t len, loff_t *pos) +{ + struct spu_dma_info info; + + spufs_get_dma_info(ctx, &info); return simple_read_from_buffer(buf, len, pos, &info, sizeof info); @@ -2127,6 +2153,7 @@ static ssize_t spufs_dma_info_read(struct file *file, char __user *buf, size_t len, loff_t *pos) { struct spu_context *ctx = file->private_data; + struct spu_dma_info info; int ret; if (!access_ok(VERIFY_WRITE, buf, len)) @@ -2136,11 +2163,12 @@ static ssize_t spufs_dma_info_read(struct file *file, char __user *buf, if (ret) return ret; spin_lock(&ctx->csa.register_lock); - ret = __spufs_dma_info_read(ctx, buf, len, pos); + spufs_get_dma_info(ctx, &info); spin_unlock(&ctx->csa.register_lock); spu_release_saved(ctx); - return ret; + return simple_read_from_buffer(buf, len, pos, &info, + sizeof(info)); } static const struct file_operations spufs_dma_info_fops = { @@ -2149,13 +2177,31 @@ static const struct file_operations spufs_dma_info_fops = { .llseek = no_llseek, }; +static void spufs_get_proxydma_info(struct spu_context *ctx, + struct spu_proxydma_info *info) +{ + int i; + + info->proxydma_info_type = ctx->csa.prob.dma_querytype_RW; + info->proxydma_info_mask = ctx->csa.prob.dma_querymask_RW; + info->proxydma_info_status = ctx->csa.prob.dma_tagstatus_R; + + for (i = 0; i < 8; i++) { + struct mfc_cq_sr *qp = &info->proxydma_info_command_data[i]; + struct mfc_cq_sr *puqp = &ctx->csa.priv2.puq[i]; + + qp->mfc_cq_data0_RW = puqp->mfc_cq_data0_RW; + qp->mfc_cq_data1_RW = puqp->mfc_cq_data1_RW; + qp->mfc_cq_data2_RW = puqp->mfc_cq_data2_RW; + qp->mfc_cq_data3_RW = puqp->mfc_cq_data3_RW; + } +} + static ssize_t __spufs_proxydma_info_read(struct spu_context *ctx, char __user *buf, size_t len, loff_t *pos) { struct spu_proxydma_info info; - struct mfc_cq_sr *qp, *puqp; int ret = sizeof info; - int i; if (len < ret) return -EINVAL; @@ -2163,18 +2209,7 @@ static ssize_t __spufs_proxydma_info_read(struct spu_context *ctx, if (!access_ok(VERIFY_WRITE, buf, len)) return -EFAULT; - info.proxydma_info_type = ctx->csa.prob.dma_querytype_RW; - info.proxydma_info_mask = ctx->csa.prob.dma_querymask_RW; - info.proxydma_info_status = ctx->csa.prob.dma_tagstatus_R; - for (i = 0; i < 8; i++) { - qp = &info.proxydma_info_command_data[i]; - puqp = &ctx->csa.priv2.puq[i]; - - qp->mfc_cq_data0_RW = puqp->mfc_cq_data0_RW; - qp->mfc_cq_data1_RW = puqp->mfc_cq_data1_RW; - qp->mfc_cq_data2_RW = puqp->mfc_cq_data2_RW; - qp->mfc_cq_data3_RW = puqp->mfc_cq_data3_RW; - } + spufs_get_proxydma_info(ctx, &info); return simple_read_from_buffer(buf, len, pos, &info, sizeof info); @@ -2184,17 +2219,19 @@ static ssize_t spufs_proxydma_info_read(struct file *file, char __user *buf, size_t len, loff_t *pos) { struct spu_context *ctx = file->private_data; + struct spu_proxydma_info info; int ret; ret = spu_acquire_saved(ctx); if (ret) return ret; spin_lock(&ctx->csa.register_lock); - ret = __spufs_proxydma_info_read(ctx, buf, len, pos); + spufs_get_proxydma_info(ctx, &info); spin_unlock(&ctx->csa.register_lock); spu_release_saved(ctx); - return ret; + return simple_read_from_buffer(buf, len, pos, &info, + sizeof(info)); } static const struct file_operations spufs_proxydma_info_fops = { diff --git a/arch/powerpc/platforms/maple/setup.c b/arch/powerpc/platforms/maple/setup.c index b7f937563827..d1fee2d35b49 100644 --- a/arch/powerpc/platforms/maple/setup.c +++ b/arch/powerpc/platforms/maple/setup.c @@ -299,23 +299,6 @@ static int __init maple_probe(void) return 1; } -define_machine(maple) { - .name = "Maple", - .probe = maple_probe, - .setup_arch = maple_setup_arch, - .init_IRQ = maple_init_IRQ, - .pci_irq_fixup = maple_pci_irq_fixup, - .pci_get_legacy_ide_irq = maple_pci_get_legacy_ide_irq, - .restart = maple_restart, - .halt = maple_halt, - .get_boot_time = maple_get_boot_time, - .set_rtc_time = maple_set_rtc_time, - .get_rtc_time = maple_get_rtc_time, - .calibrate_decr = generic_calibrate_decr, - .progress = maple_progress, - .power_save = power4_idle, -}; - #ifdef CONFIG_EDAC /* * Register a platform device for CPC925 memory controller on @@ -372,3 +355,20 @@ static int __init maple_cpc925_edac_setup(void) } machine_device_initcall(maple, maple_cpc925_edac_setup); #endif + +define_machine(maple) { + .name = "Maple", + .probe = maple_probe, + .setup_arch = maple_setup_arch, + .init_IRQ = maple_init_IRQ, + .pci_irq_fixup = maple_pci_irq_fixup, + .pci_get_legacy_ide_irq = maple_pci_get_legacy_ide_irq, + .restart = maple_restart, + .halt = maple_halt, + .get_boot_time = maple_get_boot_time, + .set_rtc_time = maple_set_rtc_time, + .get_rtc_time = maple_get_rtc_time, + .calibrate_decr = generic_calibrate_decr, + .progress = maple_progress, + .power_save = power4_idle, +}; diff --git a/arch/powerpc/platforms/powernv/memtrace.c b/arch/powerpc/platforms/powernv/memtrace.c index 84d038ed3882..ce6597a29bc9 100644 --- a/arch/powerpc/platforms/powernv/memtrace.c +++ b/arch/powerpc/platforms/powernv/memtrace.c @@ -33,6 +33,7 @@ struct memtrace_entry { char name[16]; }; +static DEFINE_MUTEX(memtrace_mutex); static u64 memtrace_size; static struct memtrace_entry *memtrace_array; @@ -70,6 +71,23 @@ static int change_memblock_state(struct memory_block *mem, void *arg) return 0; } +static void memtrace_clear_range(unsigned long start_pfn, + unsigned long nr_pages) +{ + unsigned long pfn; + + /* + * As pages are offline, we cannot trust the memmap anymore. As HIGHMEM + * does not apply, avoid passing around "struct page" and use + * clear_page() instead directly. + */ + for (pfn = start_pfn; pfn < start_pfn + nr_pages; pfn++) { + if (IS_ALIGNED(pfn, PAGES_PER_SECTION)) + cond_resched(); + clear_page(__va(PFN_PHYS(pfn))); + } +} + /* called with device_hotplug_lock held */ static bool memtrace_offline_pages(u32 nid, u64 start_pfn, u64 nr_pages) { @@ -115,6 +133,11 @@ static u64 memtrace_alloc_node(u32 nid, u64 size) for (base_pfn = end_pfn; base_pfn > start_pfn; base_pfn -= nr_pages) { if (memtrace_offline_pages(nid, base_pfn, nr_pages) == true) { /* + * Clear the range while we still have a linear + * mapping. + */ + memtrace_clear_range(base_pfn, nr_pages); + /* * Remove memory in memory block size chunks so that * iomem resources are always split to the same size and * we never try to remove memory that spans two iomem @@ -272,6 +295,7 @@ static int memtrace_online(void) static int memtrace_enable_set(void *data, u64 val) { + int rc = -EAGAIN; u64 bytes; /* @@ -284,25 +308,31 @@ static int memtrace_enable_set(void *data, u64 val) return -EINVAL; } + mutex_lock(&memtrace_mutex); + /* Re-add/online previously removed/offlined memory */ if (memtrace_size) { if (memtrace_online()) - return -EAGAIN; + goto out_unlock; } - if (!val) - return 0; + if (!val) { + rc = 0; + goto out_unlock; + } /* Offline and remove memory */ if (memtrace_init_regions_runtime(val)) - return -EINVAL; + goto out_unlock; if (memtrace_init_debugfs()) - return -EINVAL; + goto out_unlock; memtrace_size = val; - - return 0; + rc = 0; +out_unlock: + mutex_unlock(&memtrace_mutex); + return rc; } static int memtrace_enable_get(void *data, u64 *val) diff --git a/arch/powerpc/platforms/powernv/opal-dump.c b/arch/powerpc/platforms/powernv/opal-dump.c index 198143833f00..1dc2122a3cf5 100644 --- a/arch/powerpc/platforms/powernv/opal-dump.c +++ b/arch/powerpc/platforms/powernv/opal-dump.c @@ -322,15 +322,14 @@ static ssize_t dump_attr_read(struct file *filep, struct kobject *kobj, return count; } -static struct dump_obj *create_dump_obj(uint32_t id, size_t size, - uint32_t type) +static void create_dump_obj(uint32_t id, size_t size, uint32_t type) { struct dump_obj *dump; int rc; dump = kzalloc(sizeof(*dump), GFP_KERNEL); if (!dump) - return NULL; + return; dump->kobj.kset = dump_kset; @@ -350,21 +349,39 @@ static struct dump_obj *create_dump_obj(uint32_t id, size_t size, rc = kobject_add(&dump->kobj, NULL, "0x%x-0x%x", type, id); if (rc) { kobject_put(&dump->kobj); - return NULL; + return; } + /* + * As soon as the sysfs file for this dump is created/activated there is + * a chance the opal_errd daemon (or any userspace) might read and + * acknowledge the dump before kobject_uevent() is called. If that + * happens then there is a potential race between + * dump_ack_store->kobject_put() and kobject_uevent() which leads to a + * use-after-free of a kernfs object resulting in a kernel crash. + * + * To avoid that, we need to take a reference on behalf of the bin file, + * so that our reference remains valid while we call kobject_uevent(). + * We then drop our reference before exiting the function, leaving the + * bin file to drop the last reference (if it hasn't already). + */ + + /* Take a reference for the bin file */ + kobject_get(&dump->kobj); rc = sysfs_create_bin_file(&dump->kobj, &dump->dump_attr); - if (rc) { + if (rc == 0) { + kobject_uevent(&dump->kobj, KOBJ_ADD); + + pr_info("%s: New platform dump. ID = 0x%x Size %u\n", + __func__, dump->id, dump->size); + } else { + /* Drop reference count taken for bin file */ kobject_put(&dump->kobj); - return NULL; } - pr_info("%s: New platform dump. ID = 0x%x Size %u\n", - __func__, dump->id, dump->size); - - kobject_uevent(&dump->kobj, KOBJ_ADD); - - return dump; + /* Drop our reference */ + kobject_put(&dump->kobj); + return; } static irqreturn_t process_dump(int irq, void *data) diff --git a/arch/powerpc/platforms/powernv/opal-elog.c b/arch/powerpc/platforms/powernv/opal-elog.c index ba6e437abb4b..398a06631456 100644 --- a/arch/powerpc/platforms/powernv/opal-elog.c +++ b/arch/powerpc/platforms/powernv/opal-elog.c @@ -183,14 +183,14 @@ static ssize_t raw_attr_read(struct file *filep, struct kobject *kobj, return count; } -static struct elog_obj *create_elog_obj(uint64_t id, size_t size, uint64_t type) +static void create_elog_obj(uint64_t id, size_t size, uint64_t type) { struct elog_obj *elog; int rc; elog = kzalloc(sizeof(*elog), GFP_KERNEL); if (!elog) - return NULL; + return; elog->kobj.kset = elog_kset; @@ -223,18 +223,37 @@ static struct elog_obj *create_elog_obj(uint64_t id, size_t size, uint64_t type) rc = kobject_add(&elog->kobj, NULL, "0x%llx", id); if (rc) { kobject_put(&elog->kobj); - return NULL; + return; } + /* + * As soon as the sysfs file for this elog is created/activated there is + * a chance the opal_errd daemon (or any userspace) might read and + * acknowledge the elog before kobject_uevent() is called. If that + * happens then there is a potential race between + * elog_ack_store->kobject_put() and kobject_uevent() which leads to a + * use-after-free of a kernfs object resulting in a kernel crash. + * + * To avoid that, we need to take a reference on behalf of the bin file, + * so that our reference remains valid while we call kobject_uevent(). + * We then drop our reference before exiting the function, leaving the + * bin file to drop the last reference (if it hasn't already). + */ + + /* Take a reference for the bin file */ + kobject_get(&elog->kobj); rc = sysfs_create_bin_file(&elog->kobj, &elog->raw_attr); - if (rc) { + if (rc == 0) { + kobject_uevent(&elog->kobj, KOBJ_ADD); + } else { + /* Drop the reference taken for the bin file */ kobject_put(&elog->kobj); - return NULL; } - kobject_uevent(&elog->kobj, KOBJ_ADD); + /* Drop our reference */ + kobject_put(&elog->kobj); - return elog; + return; } static irqreturn_t elog_event(int irq, void *data) diff --git a/arch/powerpc/platforms/powernv/opal-imc.c b/arch/powerpc/platforms/powernv/opal-imc.c index 649fb268f446..5399682797d0 100644 --- a/arch/powerpc/platforms/powernv/opal-imc.c +++ b/arch/powerpc/platforms/powernv/opal-imc.c @@ -63,10 +63,6 @@ static void export_imc_mode_and_cmd(struct device_node *node, imc_debugfs_parent = debugfs_create_dir("imc", powerpc_debugfs_root); - /* - * Return here, either because 'imc' directory already exists, - * Or failed to create a new one. - */ if (!imc_debugfs_parent) return; @@ -139,7 +135,6 @@ static int imc_get_mem_addr_nest(struct device_node *node, } pmu_ptr->imc_counter_mmaped = true; - export_imc_mode_and_cmd(node, pmu_ptr); kfree(base_addr_arr); kfree(chipid_arr); return 0; @@ -155,7 +150,7 @@ error: * and domain as the inputs. * Allocates memory for the struct imc_pmu, sets up its domain, size and offsets */ -static int imc_pmu_create(struct device_node *parent, int pmu_index, int domain) +static struct imc_pmu *imc_pmu_create(struct device_node *parent, int pmu_index, int domain) { int ret = 0; struct imc_pmu *pmu_ptr; @@ -163,27 +158,23 @@ static int imc_pmu_create(struct device_node *parent, int pmu_index, int domain) /* Return for unknown domain */ if (domain < 0) - return -EINVAL; + return NULL; /* memory for pmu */ pmu_ptr = kzalloc(sizeof(*pmu_ptr), GFP_KERNEL); if (!pmu_ptr) - return -ENOMEM; + return NULL; /* Set the domain */ pmu_ptr->domain = domain; ret = of_property_read_u32(parent, "size", &pmu_ptr->counter_mem_size); - if (ret) { - ret = -EINVAL; + if (ret) goto free_pmu; - } if (!of_property_read_u32(parent, "offset", &offset)) { - if (imc_get_mem_addr_nest(parent, pmu_ptr, offset)) { - ret = -EINVAL; + if (imc_get_mem_addr_nest(parent, pmu_ptr, offset)) goto free_pmu; - } } /* Function to register IMC pmu */ @@ -194,14 +185,14 @@ static int imc_pmu_create(struct device_node *parent, int pmu_index, int domain) if (pmu_ptr->domain == IMC_DOMAIN_NEST) kfree(pmu_ptr->mem_info); kfree(pmu_ptr); - return ret; + return NULL; } - return 0; + return pmu_ptr; free_pmu: kfree(pmu_ptr); - return ret; + return NULL; } static void disable_nest_pmu_counters(void) @@ -258,6 +249,7 @@ int get_max_nest_dev(void) static int opal_imc_counters_probe(struct platform_device *pdev) { struct device_node *imc_dev = pdev->dev.of_node; + struct imc_pmu *pmu; int pmu_count = 0, domain; bool core_imc_reg = false, thread_imc_reg = false; u32 type; @@ -273,6 +265,7 @@ static int opal_imc_counters_probe(struct platform_device *pdev) } for_each_compatible_node(imc_dev, NULL, IMC_DTB_UNIT_COMPAT) { + pmu = NULL; if (of_property_read_u32(imc_dev, "type", &type)) { pr_warn("IMC Device without type property\n"); continue; @@ -294,9 +287,13 @@ static int opal_imc_counters_probe(struct platform_device *pdev) break; } - if (!imc_pmu_create(imc_dev, pmu_count, domain)) { - if (domain == IMC_DOMAIN_NEST) + pmu = imc_pmu_create(imc_dev, pmu_count, domain); + if (pmu != NULL) { + if (domain == IMC_DOMAIN_NEST) { + if (!imc_debugfs_parent) + export_imc_mode_and_cmd(imc_dev, pmu); pmu_count++; + } if (domain == IMC_DOMAIN_CORE) core_imc_reg = true; if (domain == IMC_DOMAIN_THREAD) @@ -304,10 +301,6 @@ static int opal_imc_counters_probe(struct platform_device *pdev) } } - /* If none of the nest units are registered, remove debugfs interface */ - if (pmu_count == 0) - debugfs_remove_recursive(imc_debugfs_parent); - /* If core imc is not registered, unregister thread-imc */ if (!core_imc_reg && thread_imc_reg) unregister_thread_imc(); diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c index adddde023622..5068dd7f6e74 100644 --- a/arch/powerpc/platforms/powernv/setup.c +++ b/arch/powerpc/platforms/powernv/setup.c @@ -125,12 +125,29 @@ static void pnv_setup_rfi_flush(void) type = L1D_FLUSH_ORI; } + /* + * If we are non-Power9 bare metal, we don't need to flush on kernel + * entry or after user access: they fix a P9 specific vulnerability. + */ + if (!pvr_version_is(PVR_POWER9)) { + security_ftr_clear(SEC_FTR_L1D_FLUSH_ENTRY); + security_ftr_clear(SEC_FTR_L1D_FLUSH_UACCESS); + } + enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) && \ (security_ftr_enabled(SEC_FTR_L1D_FLUSH_PR) || \ security_ftr_enabled(SEC_FTR_L1D_FLUSH_HV)); setup_rfi_flush(type, enable); setup_count_cache_flush(); + + enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) && + security_ftr_enabled(SEC_FTR_L1D_FLUSH_ENTRY); + setup_entry_flush(enable); + + enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) && + security_ftr_enabled(SEC_FTR_L1D_FLUSH_UACCESS); + setup_uaccess_flush(enable); } static void __init pnv_setup_arch(void) diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c index 3d3c989e44dd..889c3dbec6fb 100644 --- a/arch/powerpc/platforms/powernv/smp.c +++ b/arch/powerpc/platforms/powernv/smp.c @@ -47,7 +47,7 @@ #include <asm/udbg.h> #define DBG(fmt...) udbg_printf(fmt) #else -#define DBG(fmt...) +#define DBG(fmt...) do { } while (0) #endif static void pnv_smp_setup_cpu(int cpu) @@ -171,7 +171,6 @@ static void pnv_smp_cpu_kill_self(void) /* Standard hot unplug procedure */ idle_task_exit(); - current->active_mm = NULL; /* for sanity */ cpu = smp_processor_id(); DBG("CPU%d offline\n", cpu); generic_set_cpu_dead(cpu); diff --git a/arch/powerpc/platforms/ps3/mm.c b/arch/powerpc/platforms/ps3/mm.c index 8c7009d001d9..894f62d77a77 100644 --- a/arch/powerpc/platforms/ps3/mm.c +++ b/arch/powerpc/platforms/ps3/mm.c @@ -212,13 +212,14 @@ void ps3_mm_vas_destroy(void) { int result; - DBG("%s:%d: map.vas_id = %llu\n", __func__, __LINE__, map.vas_id); - if (map.vas_id) { result = lv1_select_virtual_address_space(0); - BUG_ON(result); - result = lv1_destruct_virtual_address_space(map.vas_id); - BUG_ON(result); + result += lv1_destruct_virtual_address_space(map.vas_id); + + if (result) { + lv1_panic(0); + } + map.vas_id = 0; } } @@ -316,19 +317,20 @@ static void ps3_mm_region_destroy(struct mem_region *r) int result; if (!r->destroy) { - pr_info("%s:%d: Not destroying high region: %llxh %llxh\n", - __func__, __LINE__, r->base, r->size); return; } - DBG("%s:%d: r->base = %llxh\n", __func__, __LINE__, r->base); - if (r->base) { result = lv1_release_memory(r->base); - BUG_ON(result); + + if (result) { + lv1_panic(0); + } + r->size = r->base = r->offset = 0; map.total = map.rm.size; } + ps3_mm_set_repository_highmem(NULL); } diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c index c5ffcadab730..90fd03b9d3c2 100644 --- a/arch/powerpc/platforms/pseries/dlpar.c +++ b/arch/powerpc/platforms/pseries/dlpar.c @@ -132,7 +132,6 @@ void dlpar_free_cc_nodes(struct device_node *dn) #define NEXT_PROPERTY 3 #define PREV_PARENT 4 #define MORE_MEMORY 5 -#define CALL_AGAIN -2 #define ERR_CFG_USE -9003 struct device_node *dlpar_configure_connector(__be32 drc_index, @@ -173,6 +172,9 @@ struct device_node *dlpar_configure_connector(__be32 drc_index, spin_unlock(&rtas_data_buf_lock); + if (rtas_busy_delay(rc)) + continue; + switch (rc) { case COMPLETE: break; @@ -221,9 +223,6 @@ struct device_node *dlpar_configure_connector(__be32 drc_index, last_dn = last_dn->parent; break; - case CALL_AGAIN: - break; - case MORE_MEMORY: case ERR_CFG_USE: default: diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c index 1d3f9313c02f..8bfb97d07d10 100644 --- a/arch/powerpc/platforms/pseries/hotplug-cpu.c +++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c @@ -95,9 +95,6 @@ static void rtas_stop_self(void) BUG_ON(rtas_stop_self_token == RTAS_UNKNOWN_SERVICE); - printk("cpu %u (hwid %u) Ready to die...\n", - smp_processor_id(), hard_smp_processor_id()); - rtas_call_unlocked(&args, rtas_stop_self_token, 0, 1, NULL); panic("Alas, I survived.\n"); diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c index fc01a2c0f8ed..afabe6918619 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -31,7 +31,7 @@ static bool rtas_hp_event; unsigned long pseries_memory_block_size(void) { struct device_node *np; - unsigned int memblock_size = MIN_MEMORY_BLOCK_SIZE; + u64 memblock_size = MIN_MEMORY_BLOCK_SIZE; struct resource r; np = of_find_node_by_path("/ibm,dynamic-reconfiguration-memory"); @@ -227,7 +227,7 @@ static int get_lmb_range(u32 drc_index, int n_lmbs, struct drmem_lmb **end_lmb) { struct drmem_lmb *lmb, *start, *end; - struct drmem_lmb *last_lmb; + struct drmem_lmb *limit; start = NULL; for_each_drmem_lmb(lmb) { @@ -240,10 +240,10 @@ static int get_lmb_range(u32 drc_index, int n_lmbs, if (!start) return -EINVAL; - end = &start[n_lmbs - 1]; + end = &start[n_lmbs]; - last_lmb = &drmem_info->lmbs[drmem_info->n_lmbs - 1]; - if (end > last_lmb) + limit = &drmem_info->lmbs[drmem_info->n_lmbs]; + if (end > limit) return -EINVAL; *start_lmb = start; diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index 49e3a88b6a0c..d660a90616cd 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -1056,7 +1056,7 @@ static int __init vpa_debugfs_init(void) { char name[16]; long i; - static struct dentry *vpa_dir; + struct dentry *vpa_dir; if (!firmware_has_feature(FW_FEATURE_SPLPAR)) return 0; diff --git a/arch/powerpc/platforms/pseries/pci_dlpar.c b/arch/powerpc/platforms/pseries/pci_dlpar.c index 561917fa54a8..afca4b737e80 100644 --- a/arch/powerpc/platforms/pseries/pci_dlpar.c +++ b/arch/powerpc/platforms/pseries/pci_dlpar.c @@ -66,6 +66,7 @@ EXPORT_SYMBOL_GPL(init_phb_dynamic); int remove_phb_dynamic(struct pci_controller *phb) { struct pci_bus *b = phb->bus; + struct pci_host_bridge *host_bridge = to_pci_host_bridge(b->bridge); struct resource *res; int rc, i; @@ -92,7 +93,8 @@ int remove_phb_dynamic(struct pci_controller *phb) /* Remove the PCI bus and unregister the bridge device from sysfs */ phb->bus = NULL; pci_remove_bus(b); - device_unregister(b->bridge); + host_bridge->bus = NULL; + device_unregister(&host_bridge->dev); /* Now release the IO resource */ if (res->flags & IORESOURCE_IO) diff --git a/arch/powerpc/platforms/pseries/ras.c b/arch/powerpc/platforms/pseries/ras.c index 851ce326874a..e827108680f2 100644 --- a/arch/powerpc/platforms/pseries/ras.c +++ b/arch/powerpc/platforms/pseries/ras.c @@ -118,7 +118,6 @@ static void handle_system_shutdown(char event_modifier) case EPOW_SHUTDOWN_ON_UPS: pr_emerg("Loss of system power detected. System is running on" " UPS/battery. Check RTAS error log for details\n"); - orderly_poweroff(true); break; case EPOW_SHUTDOWN_LOSS_OF_CRITICAL_FUNCTIONS: @@ -328,10 +327,11 @@ static irqreturn_t ras_error_interrupt(int irq, void *dev_id) /* * Some versions of FWNMI place the buffer inside the 4kB page starting at * 0x7000. Other versions place it inside the rtas buffer. We check both. + * Minimum size of the buffer is 16 bytes. */ #define VALID_FWNMI_BUFFER(A) \ - ((((A) >= 0x7000) && ((A) < 0x7ff0)) || \ - (((A) >= rtas.base) && ((A) < (rtas.base + rtas.size - 16)))) + ((((A) >= 0x7000) && ((A) <= 0x8000 - 16)) || \ + (((A) >= rtas.base) && ((A) <= (rtas.base + rtas.size - 16)))) static inline struct rtas_error_log *fwnmi_get_errlog(void) { diff --git a/arch/powerpc/platforms/pseries/rng.c b/arch/powerpc/platforms/pseries/rng.c index 31ca557af60b..262b8c5e1b9d 100644 --- a/arch/powerpc/platforms/pseries/rng.c +++ b/arch/powerpc/platforms/pseries/rng.c @@ -40,6 +40,7 @@ static __init int rng_init(void) ppc_md.get_random_seed = pseries_get_random_long; + of_node_put(dn); return 0; } machine_subsys_initcall(pseries, rng_init); diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index c2d318d1df02..2e0d38cafdd4 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -565,6 +565,14 @@ void pseries_setup_rfi_flush(void) setup_rfi_flush(types, enable); setup_count_cache_flush(); + + enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) && + security_ftr_enabled(SEC_FTR_L1D_FLUSH_ENTRY); + setup_entry_flush(enable); + + enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) && + security_ftr_enabled(SEC_FTR_L1D_FLUSH_UACCESS); + setup_uaccess_flush(enable); } #ifdef CONFIG_PCI_IOV diff --git a/arch/powerpc/platforms/pseries/suspend.c b/arch/powerpc/platforms/pseries/suspend.c index 52a021e1f86b..5414d3295e0a 100644 --- a/arch/powerpc/platforms/pseries/suspend.c +++ b/arch/powerpc/platforms/pseries/suspend.c @@ -26,7 +26,6 @@ #include <asm/mmu.h> #include <asm/rtas.h> #include <asm/topology.h> -#include "../../kernel/cacheinfo.h" static u64 stream_id; static struct device suspend_dev; @@ -91,9 +90,7 @@ static void pseries_suspend_enable_irqs(void) * Update configuration which can be modified based on device tree * changes during resume. */ - cacheinfo_cpu_offline(smp_processor_id()); post_mobility_fixup(); - cacheinfo_cpu_online(smp_processor_id()); } /** @@ -223,7 +220,6 @@ static struct bus_type suspend_subsys = { static const struct platform_suspend_ops pseries_suspend_ops = { .valid = suspend_valid_only_mem, - .begin = pseries_suspend_begin, .prepare_late = pseries_prepare_late, .enter = pseries_suspend_enter, }; diff --git a/arch/powerpc/sysdev/mpic_msgr.c b/arch/powerpc/sysdev/mpic_msgr.c index 280e964e1aa8..497e86cfb12e 100644 --- a/arch/powerpc/sysdev/mpic_msgr.c +++ b/arch/powerpc/sysdev/mpic_msgr.c @@ -196,7 +196,7 @@ static int mpic_msgr_probe(struct platform_device *dev) /* IO map the message register block. */ of_address_to_resource(np, 0, &rsrc); - msgr_block_addr = ioremap(rsrc.start, resource_size(&rsrc)); + msgr_block_addr = devm_ioremap(&dev->dev, rsrc.start, resource_size(&rsrc)); if (!msgr_block_addr) { dev_err(&dev->dev, "Failed to iomap MPIC message registers"); return -EFAULT; diff --git a/arch/powerpc/sysdev/xics/icp-hv.c b/arch/powerpc/sysdev/xics/icp-hv.c index bbc839a98c41..003deaabb568 100644 --- a/arch/powerpc/sysdev/xics/icp-hv.c +++ b/arch/powerpc/sysdev/xics/icp-hv.c @@ -179,6 +179,7 @@ int icp_hv_init(void) icp_ops = &icp_hv_ops; + of_node_put(np); return 0; } diff --git a/arch/powerpc/sysdev/xive/common.c b/arch/powerpc/sysdev/xive/common.c index 3c939b9de488..2aa9f3de223c 100644 --- a/arch/powerpc/sysdev/xive/common.c +++ b/arch/powerpc/sysdev/xive/common.c @@ -23,6 +23,7 @@ #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/msi.h> +#include <linux/vmalloc.h> #include <asm/prom.h> #include <asm/io.h> @@ -72,13 +73,6 @@ static u32 xive_ipi_irq; /* Xive state for each CPU */ static DEFINE_PER_CPU(struct xive_cpu *, xive_cpu); -/* - * A "disabled" interrupt should never fire, to catch problems - * we set its logical number to this - */ -#define XIVE_BAD_IRQ 0x7fffffff -#define XIVE_MAX_IRQ (XIVE_BAD_IRQ - 1) - /* An invalid CPU target */ #define XIVE_INVALID_TARGET (-1) @@ -940,12 +934,16 @@ EXPORT_SYMBOL_GPL(is_xive_irq); void xive_cleanup_irq_data(struct xive_irq_data *xd) { if (xd->eoi_mmio) { + unmap_kernel_range((unsigned long)xd->eoi_mmio, + 1u << xd->esb_shift); iounmap(xd->eoi_mmio); if (xd->eoi_mmio == xd->trig_mmio) xd->trig_mmio = NULL; xd->eoi_mmio = NULL; } if (xd->trig_mmio) { + unmap_kernel_range((unsigned long)xd->trig_mmio, + 1u << xd->esb_shift); iounmap(xd->trig_mmio); xd->trig_mmio = NULL; } @@ -1074,7 +1072,7 @@ static int xive_setup_cpu_ipi(unsigned int cpu) xc = per_cpu(xive_cpu, cpu); /* Check if we are already setup */ - if (xc->hw_ipi != 0) + if (xc->hw_ipi != XIVE_BAD_IRQ) return 0; /* Grab an IPI from the backend, this will populate xc->hw_ipi */ @@ -1111,7 +1109,7 @@ static void xive_cleanup_cpu_ipi(unsigned int cpu, struct xive_cpu *xc) /* Disable the IPI and free the IRQ data */ /* Already cleaned up ? */ - if (xc->hw_ipi == 0) + if (xc->hw_ipi == XIVE_BAD_IRQ) return; /* Mask the IPI */ @@ -1267,6 +1265,7 @@ static int xive_prepare_cpu(unsigned int cpu) if (np) xc->chip_id = of_get_ibm_chip_id(np); of_node_put(np); + xc->hw_ipi = XIVE_BAD_IRQ; per_cpu(xive_cpu, cpu) = xc; } diff --git a/arch/powerpc/sysdev/xive/native.c b/arch/powerpc/sysdev/xive/native.c index 6d5b28022452..411f785cdfb5 100644 --- a/arch/powerpc/sysdev/xive/native.c +++ b/arch/powerpc/sysdev/xive/native.c @@ -22,6 +22,7 @@ #include <linux/delay.h> #include <linux/cpumask.h> #include <linux/mm.h> +#include <linux/kmemleak.h> #include <asm/prom.h> #include <asm/io.h> @@ -311,7 +312,7 @@ static void xive_native_put_ipi(unsigned int cpu, struct xive_cpu *xc) s64 rc; /* Free the IPI */ - if (!xc->hw_ipi) + if (xc->hw_ipi == XIVE_BAD_IRQ) return; for (;;) { rc = opal_xive_free_irq(xc->hw_ipi); @@ -319,7 +320,7 @@ static void xive_native_put_ipi(unsigned int cpu, struct xive_cpu *xc) msleep(OPAL_BUSY_DELAY_MS); continue; } - xc->hw_ipi = 0; + xc->hw_ipi = XIVE_BAD_IRQ; break; } } @@ -627,6 +628,7 @@ static bool xive_native_provision_pages(void) pr_err("Failed to allocate provisioning page\n"); return false; } + kmemleak_ignore(p); opal_xive_donate_page(chip, __pa(p)); } return true; diff --git a/arch/powerpc/sysdev/xive/spapr.c b/arch/powerpc/sysdev/xive/spapr.c index e3ebf6469392..5566bbc86f4a 100644 --- a/arch/powerpc/sysdev/xive/spapr.c +++ b/arch/powerpc/sysdev/xive/spapr.c @@ -509,11 +509,11 @@ static int xive_spapr_get_ipi(unsigned int cpu, struct xive_cpu *xc) static void xive_spapr_put_ipi(unsigned int cpu, struct xive_cpu *xc) { - if (!xc->hw_ipi) + if (xc->hw_ipi == XIVE_BAD_IRQ) return; xive_irq_bitmap_free(xc->hw_ipi); - xc->hw_ipi = 0; + xc->hw_ipi = XIVE_BAD_IRQ; } #endif /* CONFIG_SMP */ diff --git a/arch/powerpc/sysdev/xive/xive-internal.h b/arch/powerpc/sysdev/xive/xive-internal.h index f34abed0c05f..48808dbb25dc 100644 --- a/arch/powerpc/sysdev/xive/xive-internal.h +++ b/arch/powerpc/sysdev/xive/xive-internal.h @@ -9,6 +9,13 @@ #ifndef __XIVE_INTERNAL_H #define __XIVE_INTERNAL_H +/* + * A "disabled" interrupt should never fire, to catch problems + * we set its logical number to this + */ +#define XIVE_BAD_IRQ 0x7fffffff +#define XIVE_MAX_IRQ (XIVE_BAD_IRQ - 1) + /* Each CPU carry one of these with various per-CPU state */ struct xive_cpu { #ifdef CONFIG_SMP diff --git a/arch/powerpc/xmon/Makefile b/arch/powerpc/xmon/Makefile index 365e711bebab..ab193cd7dbf9 100644 --- a/arch/powerpc/xmon/Makefile +++ b/arch/powerpc/xmon/Makefile @@ -1,9 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 # Makefile for xmon -# Avoid clang warnings around longjmp/setjmp declarations -subdir-ccflags-y := -ffreestanding - subdir-ccflags-$(CONFIG_PPC_WERROR) += -Werror GCOV_PROFILE := n diff --git a/arch/powerpc/xmon/nonstdio.c b/arch/powerpc/xmon/nonstdio.c index d00123421e00..eefe1b94e0aa 100644 --- a/arch/powerpc/xmon/nonstdio.c +++ b/arch/powerpc/xmon/nonstdio.c @@ -182,7 +182,7 @@ void xmon_printf(const char *format, ...) if (n && rc == 0) { /* No udbg hooks, fallback to printk() - dangerous */ - printk("%s", xmon_outbuf); + pr_cont("%s", xmon_outbuf); } } diff --git a/arch/riscv/include/asm/barrier.h b/arch/riscv/include/asm/barrier.h index d4628e4b3a5e..f4c92c91aa04 100644 --- a/arch/riscv/include/asm/barrier.h +++ b/arch/riscv/include/asm/barrier.h @@ -69,8 +69,16 @@ do { \ * The AQ/RL pair provides a RCpc critical section, but there's not really any * way we can take advantage of that here because the ordering is only enforced * on that one lock. Thus, we're just doing a full fence. + * + * Since we allow writeX to be called from preemptive regions we need at least + * an "o" in the predecessor set to ensure device writes are visible before the + * task is marked as available for scheduling on a new hart. While I don't see + * any concrete reason we need a full IO fence, it seems safer to just upgrade + * this in order to avoid any IO crossing a scheduling boundary. In both + * instances the scheduler pairs this with an mb(), so nothing is necessary on + * the new hart. */ -#define smp_mb__after_spinlock() RISCV_FENCE(rw,rw) +#define smp_mb__after_spinlock() RISCV_FENCE(iorw,iorw) #include <asm-generic/barrier.h> diff --git a/arch/riscv/include/asm/cmpxchg.h b/arch/riscv/include/asm/cmpxchg.h index c12833f7b6bd..42978aac99d5 100644 --- a/arch/riscv/include/asm/cmpxchg.h +++ b/arch/riscv/include/asm/cmpxchg.h @@ -187,7 +187,7 @@ " bnez %1, 0b\n" \ "1:\n" \ : "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr) \ - : "rJ" (__old), "rJ" (__new) \ + : "rJ" ((long)__old), "rJ" (__new) \ : "memory"); \ break; \ case 8: \ @@ -232,7 +232,7 @@ RISCV_ACQUIRE_BARRIER \ "1:\n" \ : "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr) \ - : "rJ" (__old), "rJ" (__new) \ + : "rJ" ((long)__old), "rJ" (__new) \ : "memory"); \ break; \ case 8: \ @@ -278,7 +278,7 @@ " bnez %1, 0b\n" \ "1:\n" \ : "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr) \ - : "rJ" (__old), "rJ" (__new) \ + : "rJ" ((long)__old), "rJ" (__new) \ : "memory"); \ break; \ case 8: \ @@ -324,7 +324,7 @@ " fence rw, rw\n" \ "1:\n" \ : "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr) \ - : "rJ" (__old), "rJ" (__new) \ + : "rJ" ((long)__old), "rJ" (__new) \ : "memory"); \ break; \ case 8: \ diff --git a/arch/riscv/include/asm/ftrace.h b/arch/riscv/include/asm/ftrace.h index c6dcc5291f97..693c3839a7df 100644 --- a/arch/riscv/include/asm/ftrace.h +++ b/arch/riscv/include/asm/ftrace.h @@ -10,9 +10,19 @@ #endif #define HAVE_FUNCTION_GRAPH_RET_ADDR_PTR +/* + * Clang prior to 13 had "mcount" instead of "_mcount": + * https://reviews.llvm.org/D98881 + */ +#if defined(CONFIG_CC_IS_GCC) || CONFIG_CLANG_VERSION >= 130000 +#define MCOUNT_NAME _mcount +#else +#define MCOUNT_NAME mcount +#endif + #define ARCH_SUPPORTS_FTRACE_OPS 1 #ifndef __ASSEMBLY__ -void _mcount(void); +void MCOUNT_NAME(void); static inline unsigned long ftrace_call_adjust(unsigned long addr) { return addr; @@ -33,7 +43,7 @@ struct dyn_arch_ftrace { * both auipc and jalr at the same time. */ -#define MCOUNT_ADDR ((unsigned long)_mcount) +#define MCOUNT_ADDR ((unsigned long)MCOUNT_NAME) #define JALR_SIGN_MASK (0x00000800) #define JALR_OFFSET_MASK (0x00000fff) #define AUIPC_OFFSET_MASK (0xfffff000) @@ -63,4 +73,11 @@ do { \ * Let auipc+jalr be the basic *mcount unit*, so we make it 8 bytes here. */ #define MCOUNT_INSN_SIZE 8 + +#ifndef __ASSEMBLY__ +struct dyn_ftrace; +int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec); +#define ftrace_init_nop ftrace_init_nop +#endif + #endif diff --git a/arch/riscv/include/asm/page.h b/arch/riscv/include/asm/page.h index 06cfbb3aacbb..abc147aeff8b 100644 --- a/arch/riscv/include/asm/page.h +++ b/arch/riscv/include/asm/page.h @@ -115,7 +115,10 @@ extern unsigned long min_low_pfn; #endif /* __ASSEMBLY__ */ -#define virt_addr_valid(vaddr) (pfn_valid(virt_to_pfn(vaddr))) +#define virt_addr_valid(vaddr) ({ \ + unsigned long _addr = (unsigned long)vaddr; \ + (unsigned long)(_addr) >= PAGE_OFFSET && pfn_valid(virt_to_pfn(_addr)); \ +}) #define VM_DATA_DEFAULT_FLAGS (VM_READ | VM_WRITE | \ VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC) diff --git a/arch/riscv/include/asm/thread_info.h b/arch/riscv/include/asm/thread_info.h index f8fa1cd2dad9..131f58b26b8f 100644 --- a/arch/riscv/include/asm/thread_info.h +++ b/arch/riscv/include/asm/thread_info.h @@ -20,7 +20,11 @@ #include <linux/const.h> /* thread information allocation */ +#ifdef CONFIG_64BIT +#define THREAD_SIZE_ORDER (2) +#else #define THREAD_SIZE_ORDER (1) +#endif #define THREAD_SIZE (PAGE_SIZE << THREAD_SIZE_ORDER) #ifndef __ASSEMBLY__ diff --git a/arch/riscv/include/uapi/asm/auxvec.h b/arch/riscv/include/uapi/asm/auxvec.h index 1376515547cd..ed7bf7c7add5 100644 --- a/arch/riscv/include/uapi/asm/auxvec.h +++ b/arch/riscv/include/uapi/asm/auxvec.h @@ -21,4 +21,7 @@ /* vDSO location */ #define AT_SYSINFO_EHDR 33 +/* entries in ARCH_DLINFO */ +#define AT_VECTOR_SIZE_ARCH 1 + #endif /* _UAPI_ASM_RISCV_AUXVEC_H */ diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S index a03821b2656a..d9de22686e27 100644 --- a/arch/riscv/kernel/entry.S +++ b/arch/riscv/kernel/entry.S @@ -449,6 +449,7 @@ ENDPROC(__fstate_restore) .section ".rodata" + .align LGREG /* Exception vector table */ ENTRY(excp_vect_table) RISCV_PTR do_trap_insn_misaligned diff --git a/arch/riscv/kernel/ftrace.c b/arch/riscv/kernel/ftrace.c index 6d39f64e4dce..fa8530f05ed4 100644 --- a/arch/riscv/kernel/ftrace.c +++ b/arch/riscv/kernel/ftrace.c @@ -88,6 +88,25 @@ int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, return __ftrace_modify_call(rec->ip, addr, false); } + +/* + * This is called early on, and isn't wrapped by + * ftrace_arch_code_modify_{prepare,post_process}() and therefor doesn't hold + * text_mutex, which triggers a lockdep failure. SMP isn't running so we could + * just directly poke the text, but it's simpler to just take the lock + * ourselves. + */ +int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec) +{ + int out; + + ftrace_arch_code_modify_prepare(); + out = ftrace_make_nop(mod, rec, MCOUNT_ADDR); + ftrace_arch_code_modify_post_process(); + + return out; +} + int ftrace_update_ftrace_func(ftrace_func_t func) { int ret = __ftrace_modify_call((unsigned long)&ftrace_call, diff --git a/arch/riscv/kernel/mcount.S b/arch/riscv/kernel/mcount.S index 5721624886a1..fabddee90d1b 100644 --- a/arch/riscv/kernel/mcount.S +++ b/arch/riscv/kernel/mcount.S @@ -47,8 +47,8 @@ ENTRY(ftrace_stub) #ifdef CONFIG_DYNAMIC_FTRACE - .global _mcount - .set _mcount, ftrace_stub + .global MCOUNT_NAME + .set MCOUNT_NAME, ftrace_stub #endif ret ENDPROC(ftrace_stub) @@ -79,7 +79,7 @@ EXPORT_SYMBOL(return_to_handler) #endif #ifndef CONFIG_DYNAMIC_FTRACE -ENTRY(_mcount) +ENTRY(MCOUNT_NAME) la t4, ftrace_stub #ifdef CONFIG_FUNCTION_GRAPH_TRACER la t0, ftrace_graph_return @@ -125,6 +125,6 @@ do_trace: jalr t5 RESTORE_ABI_STATE ret -ENDPROC(_mcount) +ENDPROC(MCOUNT_NAME) #endif -EXPORT_SYMBOL(_mcount) +EXPORT_SYMBOL(MCOUNT_NAME) diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index 9713d4e8c22b..6558617bd2ce 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -19,6 +19,7 @@ * to the Free Software Foundation, Inc., */ +#include <linux/bootmem.h> #include <linux/init.h> #include <linux/mm.h> #include <linux/memblock.h> @@ -187,6 +188,7 @@ static void __init setup_bootmem(void) set_max_mapnr(PFN_DOWN(mem_size)); max_low_pfn = PFN_DOWN(memblock_end_of_DRAM()); + max_pfn = max_low_pfn; #ifdef CONFIG_BLK_DEV_INITRD setup_initrd(); diff --git a/arch/riscv/kernel/stacktrace.c b/arch/riscv/kernel/stacktrace.c index a4b1d94371a0..74b2168d7298 100644 --- a/arch/riscv/kernel/stacktrace.c +++ b/arch/riscv/kernel/stacktrace.c @@ -75,7 +75,7 @@ static void notrace walk_stackframe(struct task_struct *task, #else /* !CONFIG_FRAME_POINTER */ -static void notrace walk_stackframe(struct task_struct *task, +void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs, bool (*fn)(unsigned long, void *), void *arg) { unsigned long sp, pc; diff --git a/arch/riscv/kernel/sys_riscv.c b/arch/riscv/kernel/sys_riscv.c index fb03a4482ad6..db44da32701f 100644 --- a/arch/riscv/kernel/sys_riscv.c +++ b/arch/riscv/kernel/sys_riscv.c @@ -16,6 +16,7 @@ #include <linux/syscalls.h> #include <asm/unistd.h> #include <asm/cacheflush.h> +#include <asm-generic/mman-common.h> static long riscv_sys_mmap(unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, @@ -24,6 +25,11 @@ static long riscv_sys_mmap(unsigned long addr, unsigned long len, { if (unlikely(offset & (~PAGE_MASK >> page_shift_offset))) return -EINVAL; + + if ((prot & PROT_WRITE) && (prot & PROT_EXEC)) + if (unlikely(!(prot & PROT_READ))) + return -EINVAL; + return ksys_mmap_pgoff(addr, len, prot, flags, fd, offset >> (PAGE_SHIFT - page_shift_offset)); } diff --git a/arch/riscv/kernel/time.c b/arch/riscv/kernel/time.c index 1911c8f6b8a6..15f4ab40e222 100644 --- a/arch/riscv/kernel/time.c +++ b/arch/riscv/kernel/time.c @@ -12,6 +12,7 @@ * GNU General Public License for more details. */ +#include <linux/of_clk.h> #include <linux/clocksource.h> #include <linux/delay.h> #include <asm/sbi.h> @@ -29,5 +30,7 @@ void __init time_init(void) riscv_timebase = prop; lpj_fine = riscv_timebase / HZ; + + of_clk_init(NULL); timer_probe(); } diff --git a/arch/riscv/kernel/vdso/Makefile b/arch/riscv/kernel/vdso/Makefile index 87f71a6cd3ef..1dd134fc0d84 100644 --- a/arch/riscv/kernel/vdso/Makefile +++ b/arch/riscv/kernel/vdso/Makefile @@ -30,15 +30,15 @@ $(obj)/vdso.so.dbg: $(src)/vdso.lds $(obj-vdso) FORCE $(call if_changed,vdsold) # We also create a special relocatable object that should mirror the symbol -# table and layout of the linked DSO. With ld -R we can then refer to -# these symbols in the kernel code rather than hand-coded addresses. +# table and layout of the linked DSO. With ld --just-symbols we can then +# refer to these symbols in the kernel code rather than hand-coded addresses. SYSCFLAGS_vdso.so.dbg = -shared -s -Wl,-soname=linux-vdso.so.1 \ $(call cc-ldoption, -Wl$(comma)--hash-style=both) $(obj)/vdso-dummy.o: $(src)/vdso.lds $(obj)/rt_sigreturn.o FORCE $(call if_changed,vdsold) -LDFLAGS_vdso-syms.o := -r -R +LDFLAGS_vdso-syms.o := -r --just-symbols $(obj)/vdso-syms.o: $(obj)/vdso-dummy.o FORCE $(call if_changed,ld) diff --git a/arch/s390/crypto/arch_random.c b/arch/s390/crypto/arch_random.c index dd95cdbd22ce..4cbb4b6d85a8 100644 --- a/arch/s390/crypto/arch_random.c +++ b/arch/s390/crypto/arch_random.c @@ -53,6 +53,10 @@ static DECLARE_DELAYED_WORK(arch_rng_work, arch_rng_refill_buffer); bool s390_arch_random_generate(u8 *buf, unsigned int nbytes) { + /* max hunk is ARCH_RNG_BUF_SIZE */ + if (nbytes > ARCH_RNG_BUF_SIZE) + return false; + /* lock rng buffer */ if (!spin_trylock(&arch_rng_lock)) return false; diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index dad110e9f41b..be8fa30a6ea6 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -30,12 +30,12 @@ #define KVM_USER_MEM_SLOTS 32 /* - * These seem to be used for allocating ->chip in the routing table, - * which we don't use. 4096 is an out-of-thin-air value. If we need - * to look at ->chip later on, we'll need to revisit this. + * These seem to be used for allocating ->chip in the routing table, which we + * don't use. 1 is as small as we can get to reduce the needed memory. If we + * need to look at ->chip later on, we'll need to revisit this. */ #define KVM_NR_IRQCHIPS 1 -#define KVM_IRQCHIP_NUM_PINS 4096 +#define KVM_IRQCHIP_NUM_PINS 1 #define KVM_HALT_POLL_NS_DEFAULT 80000 /* s390-specific vcpu->requests bit members */ diff --git a/arch/s390/include/asm/percpu.h b/arch/s390/include/asm/percpu.h index 0095ddb58ff6..50f6661ba566 100644 --- a/arch/s390/include/asm/percpu.h +++ b/arch/s390/include/asm/percpu.h @@ -29,7 +29,7 @@ typedef typeof(pcp) pcp_op_T__; \ pcp_op_T__ old__, new__, prev__; \ pcp_op_T__ *ptr__; \ - preempt_disable(); \ + preempt_disable_notrace(); \ ptr__ = raw_cpu_ptr(&(pcp)); \ prev__ = *ptr__; \ do { \ @@ -37,7 +37,7 @@ new__ = old__ op (val); \ prev__ = cmpxchg(ptr__, old__, new__); \ } while (prev__ != old__); \ - preempt_enable(); \ + preempt_enable_notrace(); \ new__; \ }) @@ -68,7 +68,7 @@ typedef typeof(pcp) pcp_op_T__; \ pcp_op_T__ val__ = (val); \ pcp_op_T__ old__, *ptr__; \ - preempt_disable(); \ + preempt_disable_notrace(); \ ptr__ = raw_cpu_ptr(&(pcp)); \ if (__builtin_constant_p(val__) && \ ((szcast)val__ > -129) && ((szcast)val__ < 128)) { \ @@ -84,7 +84,7 @@ : [val__] "d" (val__) \ : "cc"); \ } \ - preempt_enable(); \ + preempt_enable_notrace(); \ } #define this_cpu_add_4(pcp, val) arch_this_cpu_add(pcp, val, "laa", "asi", int) @@ -95,14 +95,14 @@ typedef typeof(pcp) pcp_op_T__; \ pcp_op_T__ val__ = (val); \ pcp_op_T__ old__, *ptr__; \ - preempt_disable(); \ + preempt_disable_notrace(); \ ptr__ = raw_cpu_ptr(&(pcp)); \ asm volatile( \ op " %[old__],%[val__],%[ptr__]\n" \ : [old__] "=d" (old__), [ptr__] "+Q" (*ptr__) \ : [val__] "d" (val__) \ : "cc"); \ - preempt_enable(); \ + preempt_enable_notrace(); \ old__ + val__; \ }) @@ -114,14 +114,14 @@ typedef typeof(pcp) pcp_op_T__; \ pcp_op_T__ val__ = (val); \ pcp_op_T__ old__, *ptr__; \ - preempt_disable(); \ + preempt_disable_notrace(); \ ptr__ = raw_cpu_ptr(&(pcp)); \ asm volatile( \ op " %[old__],%[val__],%[ptr__]\n" \ : [old__] "=d" (old__), [ptr__] "+Q" (*ptr__) \ : [val__] "d" (val__) \ : "cc"); \ - preempt_enable(); \ + preempt_enable_notrace(); \ } #define this_cpu_and_4(pcp, val) arch_this_cpu_to_op(pcp, val, "lan") @@ -136,10 +136,10 @@ typedef typeof(pcp) pcp_op_T__; \ pcp_op_T__ ret__; \ pcp_op_T__ *ptr__; \ - preempt_disable(); \ + preempt_disable_notrace(); \ ptr__ = raw_cpu_ptr(&(pcp)); \ ret__ = cmpxchg(ptr__, oval, nval); \ - preempt_enable(); \ + preempt_enable_notrace(); \ ret__; \ }) @@ -152,10 +152,10 @@ ({ \ typeof(pcp) *ptr__; \ typeof(pcp) ret__; \ - preempt_disable(); \ + preempt_disable_notrace(); \ ptr__ = raw_cpu_ptr(&(pcp)); \ ret__ = xchg(ptr__, nval); \ - preempt_enable(); \ + preempt_enable_notrace(); \ ret__; \ }) @@ -171,11 +171,11 @@ typeof(pcp1) *p1__; \ typeof(pcp2) *p2__; \ int ret__; \ - preempt_disable(); \ + preempt_disable_notrace(); \ p1__ = raw_cpu_ptr(&(pcp1)); \ p2__ = raw_cpu_ptr(&(pcp2)); \ ret__ = __cmpxchg_double(p1__, p2__, o1__, o2__, n1__, n2__); \ - preempt_enable(); \ + preempt_enable_notrace(); \ ret__; \ }) diff --git a/arch/s390/include/asm/syscall.h b/arch/s390/include/asm/syscall.h index 96f9a9151fde..2becba8008c4 100644 --- a/arch/s390/include/asm/syscall.h +++ b/arch/s390/include/asm/syscall.h @@ -38,7 +38,17 @@ static inline void syscall_rollback(struct task_struct *task, static inline long syscall_get_error(struct task_struct *task, struct pt_regs *regs) { - return IS_ERR_VALUE(regs->gprs[2]) ? regs->gprs[2] : 0; + unsigned long error = regs->gprs[2]; +#ifdef CONFIG_COMPAT + if (test_tsk_thread_flag(task, TIF_31BIT)) { + /* + * Sign-extend the value so (int)-EFOO becomes (long)-EFOO + * and will match correctly in comparisons. + */ + error = (long)(int)error; + } +#endif + return IS_ERR_VALUE(error) ? error : 0; } static inline long syscall_get_return_value(struct task_struct *task, diff --git a/arch/s390/include/asm/vdso.h b/arch/s390/include/asm/vdso.h index 169d7604eb80..f3ba84fa9bd1 100644 --- a/arch/s390/include/asm/vdso.h +++ b/arch/s390/include/asm/vdso.h @@ -36,6 +36,7 @@ struct vdso_data { __u32 tk_shift; /* Shift used for xtime_nsec 0x60 */ __u32 ts_dir; /* TOD steering direction 0x64 */ __u64 ts_end; /* TOD steering end 0x68 */ + __u32 hrtimer_res; /* hrtimer resolution 0x70 */ }; struct vdso_per_cpu_data { diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c index 66e830f1c7bf..e9d09f6e81d2 100644 --- a/arch/s390/kernel/asm-offsets.c +++ b/arch/s390/kernel/asm-offsets.c @@ -75,6 +75,7 @@ int main(void) OFFSET(__VDSO_TK_SHIFT, vdso_data, tk_shift); OFFSET(__VDSO_TS_DIR, vdso_data, ts_dir); OFFSET(__VDSO_TS_END, vdso_data, ts_end); + OFFSET(__VDSO_CLOCK_REALTIME_RES, vdso_data, hrtimer_res); OFFSET(__VDSO_ECTG_BASE, vdso_per_cpu_data, ectg_timer_base); OFFSET(__VDSO_ECTG_USER, vdso_per_cpu_data, ectg_user_time); OFFSET(__VDSO_CPU_NR, vdso_per_cpu_data, cpu_nr); @@ -86,7 +87,6 @@ int main(void) DEFINE(__CLOCK_REALTIME_COARSE, CLOCK_REALTIME_COARSE); DEFINE(__CLOCK_MONOTONIC_COARSE, CLOCK_MONOTONIC_COARSE); DEFINE(__CLOCK_THREAD_CPUTIME_ID, CLOCK_THREAD_CPUTIME_ID); - DEFINE(__CLOCK_REALTIME_RES, MONOTONIC_RES_NSEC); DEFINE(__CLOCK_COARSE_RES, LOW_RES_NSEC); BLANK(); /* idle data offsets */ diff --git a/arch/s390/kernel/cpcmd.c b/arch/s390/kernel/cpcmd.c index af013b4244d3..2da027359798 100644 --- a/arch/s390/kernel/cpcmd.c +++ b/arch/s390/kernel/cpcmd.c @@ -37,10 +37,12 @@ static int diag8_noresponse(int cmdlen) static int diag8_response(int cmdlen, char *response, int *rlen) { + unsigned long _cmdlen = cmdlen | 0x40000000L; + unsigned long _rlen = *rlen; register unsigned long reg2 asm ("2") = (addr_t) cpcmd_buf; register unsigned long reg3 asm ("3") = (addr_t) response; - register unsigned long reg4 asm ("4") = cmdlen | 0x40000000L; - register unsigned long reg5 asm ("5") = *rlen; + register unsigned long reg4 asm ("4") = _cmdlen; + register unsigned long reg5 asm ("5") = _rlen; asm volatile( " diag %2,%0,0x8\n" diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c index d374f9b218b4..04bbf7e97fea 100644 --- a/arch/s390/kernel/debug.c +++ b/arch/s390/kernel/debug.c @@ -198,9 +198,10 @@ static debug_entry_t ***debug_areas_alloc(int pages_per_area, int nr_areas) if (!areas) goto fail_malloc_areas; for (i = 0; i < nr_areas; i++) { + /* GFP_NOWARN to avoid user triggerable WARN, we handle fails */ areas[i] = kmalloc_array(pages_per_area, sizeof(debug_entry_t *), - GFP_KERNEL); + GFP_KERNEL | __GFP_NOWARN); if (!areas[i]) goto fail_malloc_areas2; for (j = 0; j < pages_per_area; j++) { diff --git a/arch/s390/kernel/diag.c b/arch/s390/kernel/diag.c index 53a5316cc4b7..4c7cf8787a84 100644 --- a/arch/s390/kernel/diag.c +++ b/arch/s390/kernel/diag.c @@ -79,7 +79,7 @@ static int show_diag_stat(struct seq_file *m, void *v) static void *show_diag_stat_start(struct seq_file *m, loff_t *pos) { - return *pos <= nr_cpu_ids ? (void *)((unsigned long) *pos + 1) : NULL; + return *pos <= NR_DIAG_STAT ? (void *)((unsigned long) *pos + 1) : NULL; } static void *show_diag_stat_next(struct seq_file *m, void *v, loff_t *pos) @@ -128,7 +128,7 @@ void diag_stat_inc(enum diag_stat_enum nr) } EXPORT_SYMBOL(diag_stat_inc); -void diag_stat_inc_norecursion(enum diag_stat_enum nr) +void notrace diag_stat_inc_norecursion(enum diag_stat_enum nr) { this_cpu_inc(diag_stat.counter[nr]); trace_s390_diagnose_norecursion(diag_map[nr].code); diff --git a/arch/s390/kernel/dis.c b/arch/s390/kernel/dis.c index 41925f220694..01307db4b4dd 100644 --- a/arch/s390/kernel/dis.c +++ b/arch/s390/kernel/dis.c @@ -558,7 +558,7 @@ void show_code(struct pt_regs *regs) void print_fn_code(unsigned char *code, unsigned long len) { - char buffer[64], *ptr; + char buffer[128], *ptr; int opsize, i; while (len) { diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c index e7e6608b996c..ad88bed74395 100644 --- a/arch/s390/kernel/early.c +++ b/arch/s390/kernel/early.c @@ -155,6 +155,8 @@ static noinline __init void setup_lowcore_early(void) psw_t psw; psw.mask = PSW_MASK_BASE | PSW_DEFAULT_KEY | PSW_MASK_EA | PSW_MASK_BA; + if (IS_ENABLED(CONFIG_KASAN)) + psw.mask |= PSW_MASK_DAT; psw.addr = (unsigned long) s390_base_ext_handler; S390_lowcore.external_new_psw = psw; psw.addr = (unsigned long) s390_base_pgm_handler; diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index 150130c897c3..7e6a9cf863c7 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -949,6 +949,7 @@ ENTRY(ext_int_handler) * Load idle PSW. The second "half" of this function is in .Lcleanup_idle. */ ENTRY(psw_idle) + stg %r14,(__SF_GPRS+8*8)(%r15) stg %r3,__SF_EMPTY(%r15) larl %r1,.Lpsw_idle_lpsw+4 stg %r1,__SF_EMPTY+8(%r15) diff --git a/arch/s390/kernel/mcount.S b/arch/s390/kernel/mcount.S index 83afd5b78e16..020f9aac7dc0 100644 --- a/arch/s390/kernel/mcount.S +++ b/arch/s390/kernel/mcount.S @@ -40,6 +40,7 @@ EXPORT_SYMBOL(_mcount) ENTRY(ftrace_caller) .globl ftrace_regs_caller .set ftrace_regs_caller,ftrace_caller + stg %r14,(__SF_GPRS+8*8)(%r15) # save traced function caller lgr %r1,%r15 #if !(defined(CC_USING_HOTPATCH) || defined(CC_USING_NOP_MCOUNT)) aghi %r0,MCOUNT_RETURN_FIXUP diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c index 5bfb1ce129f4..c8e1e325215b 100644 --- a/arch/s390/kernel/perf_cpum_sf.c +++ b/arch/s390/kernel/perf_cpum_sf.c @@ -1377,8 +1377,8 @@ static int aux_output_begin(struct perf_output_handle *handle, idx = aux->empty_mark + 1; for (i = 0; i < range_scan; i++, idx++) { te = aux_sdb_trailer(aux, idx); - te->flags = te->flags & ~SDB_TE_BUFFER_FULL_MASK; - te->flags = te->flags & ~SDB_TE_ALERT_REQ_MASK; + te->flags &= ~(SDB_TE_BUFFER_FULL_MASK | + SDB_TE_ALERT_REQ_MASK); te->overflow = 0; } /* Save the position of empty SDBs */ @@ -1425,8 +1425,7 @@ static bool aux_set_alert(struct aux_buffer *aux, unsigned long alert_index, te = aux_sdb_trailer(aux, alert_index); do { orig_flags = te->flags; - orig_overflow = te->overflow; - *overflow = orig_overflow; + *overflow = orig_overflow = te->overflow; if (orig_flags & SDB_TE_BUFFER_FULL_MASK) { /* * SDB is already set by hardware. @@ -1537,6 +1536,7 @@ static void hw_collect_aux(struct cpu_hw_sf *cpuhw) perf_aux_output_end(handle, size); num_sdb = aux->sfb.num_sdb; + num_sdb = aux->sfb.num_sdb; while (!done) { /* Get an output handle */ aux = perf_aux_output_begin(handle, cpuhw->event); @@ -1659,7 +1659,7 @@ static void *aux_buffer_setup(struct perf_event *event, void **pages, } /* Allocate aux_buffer struct for the event */ - aux = kmalloc(sizeof(struct aux_buffer), GFP_KERNEL); + aux = kzalloc(sizeof(struct aux_buffer), GFP_KERNEL); if (!aux) goto no_aux; sfb = &aux->sfb; @@ -2097,4 +2097,4 @@ out: return err; } arch_initcall(init_cpum_sampling_pmu); -core_param(cpum_sfb_size, CPUM_SF_MAX_SDB, sfb_size, 0640); +core_param(cpum_sfb_size, CPUM_SF_MAX_SDB, sfb_size, 0644); diff --git a/arch/s390/kernel/processor.c b/arch/s390/kernel/processor.c index 6fe2e1875058..675d4be0c2b7 100644 --- a/arch/s390/kernel/processor.c +++ b/arch/s390/kernel/processor.c @@ -157,8 +157,9 @@ static void show_cpu_mhz(struct seq_file *m, unsigned long n) static int show_cpuinfo(struct seq_file *m, void *v) { unsigned long n = (unsigned long) v - 1; + unsigned long first = cpumask_first(cpu_online_mask); - if (!n) + if (n == first) show_cpu_summary(m, v); if (!machine_has_cpu_mhz) return 0; @@ -171,6 +172,8 @@ static inline void *c_update(loff_t *pos) { if (*pos) *pos = cpumask_next(*pos - 1, cpu_online_mask); + else + *pos = cpumask_first(cpu_online_mask); return *pos < nr_cpu_ids ? (void *)*pos + 1 : NULL; } diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c index cd3df5514552..3ffa2847c110 100644 --- a/arch/s390/kernel/ptrace.c +++ b/arch/s390/kernel/ptrace.c @@ -325,6 +325,25 @@ static inline void __poke_user_per(struct task_struct *child, child->thread.per_user.end = data; } +static void fixup_int_code(struct task_struct *child, addr_t data) +{ + struct pt_regs *regs = task_pt_regs(child); + int ilc = regs->int_code >> 16; + u16 insn; + + if (ilc > 6) + return; + + if (ptrace_access_vm(child, regs->psw.addr - (regs->int_code >> 16), + &insn, sizeof(insn), FOLL_FORCE) != sizeof(insn)) + return; + + /* double check that tracee stopped on svc instruction */ + if ((insn >> 8) != 0xa) + return; + + regs->int_code = 0x20000 | (data & 0xffff); +} /* * Write a word to the user area of a process at location addr. This * operation does have an additional problem compared to peek_user. @@ -336,7 +355,9 @@ static int __poke_user(struct task_struct *child, addr_t addr, addr_t data) struct user *dummy = NULL; addr_t offset; + if (addr < (addr_t) &dummy->regs.acrs) { + struct pt_regs *regs = task_pt_regs(child); /* * psw and gprs are stored on the stack */ @@ -354,7 +375,11 @@ static int __poke_user(struct task_struct *child, addr_t addr, addr_t data) /* Invalid addressing mode bits */ return -EINVAL; } - *(addr_t *)((addr_t) &task_pt_regs(child)->psw + addr) = data; + + if (test_pt_regs_flag(regs, PIF_SYSCALL) && + addr == offsetof(struct user, regs.gprs[2])) + fixup_int_code(child, data); + *(addr_t *)((addr_t) ®s->psw + addr) = data; } else if (addr < (addr_t) (&dummy->regs.orig_gpr2)) { /* @@ -720,6 +745,10 @@ static int __poke_user_compat(struct task_struct *child, regs->psw.mask = (regs->psw.mask & ~PSW_MASK_BA) | (__u64)(tmp & PSW32_ADDR_AMODE); } else { + + if (test_pt_regs_flag(regs, PIF_SYSCALL) && + addr == offsetof(struct compat_user, regs.gprs[2])) + fixup_int_code(child, data); /* gpr 0-15 */ *(__u32*)((addr_t) ®s->psw + addr*2 + 4) = tmp; } @@ -1257,7 +1286,6 @@ static bool is_ri_cb_valid(struct runtime_instr_cb *cb) cb->pc == 1 && cb->qc == 0 && cb->reserved2 == 0 && - cb->key == PAGE_DEFAULT_KEY && cb->reserved3 == 0 && cb->reserved4 == 0 && cb->reserved5 == 0 && @@ -1321,7 +1349,11 @@ static int s390_runtime_instr_set(struct task_struct *target, kfree(data); return -EINVAL; } - + /* + * Override access key in any case, since user space should + * not be able to set it, nor should it care about it. + */ + ri_cb.key = PAGE_DEFAULT_KEY >> 4; preempt_disable(); if (!target->thread.ri_cb) target->thread.ri_cb = data; diff --git a/arch/s390/kernel/runtime_instr.c b/arch/s390/kernel/runtime_instr.c index 125c7f6e8715..1788a5454b6f 100644 --- a/arch/s390/kernel/runtime_instr.c +++ b/arch/s390/kernel/runtime_instr.c @@ -57,7 +57,7 @@ static void init_runtime_instr_cb(struct runtime_instr_cb *cb) cb->k = 1; cb->ps = 1; cb->pc = 1; - cb->key = PAGE_DEFAULT_KEY; + cb->key = PAGE_DEFAULT_KEY >> 4; cb->v = 1; } diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index 5f85e0dfa66d..4bda9055daef 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -537,7 +537,7 @@ static struct notifier_block kdump_mem_nb = { /* * Make sure that the area behind memory_end is protected */ -static void reserve_memory_end(void) +static void __init reserve_memory_end(void) { #ifdef CONFIG_CRASH_DUMP if (ipl_info.type == IPL_TYPE_FCP_DUMP && @@ -555,7 +555,7 @@ static void reserve_memory_end(void) /* * Make sure that oldmem, where the dump is stored, is protected */ -static void reserve_oldmem(void) +static void __init reserve_oldmem(void) { #ifdef CONFIG_CRASH_DUMP if (OLDMEM_BASE) @@ -567,7 +567,7 @@ static void reserve_oldmem(void) /* * Make sure that oldmem, where the dump is stored, is protected */ -static void remove_oldmem(void) +static void __init remove_oldmem(void) { #ifdef CONFIG_CRASH_DUMP if (OLDMEM_BASE) diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index ecd24711f3aa..bce678c7179c 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -393,7 +393,7 @@ int smp_find_processor_id(u16 address) return -1; } -bool arch_vcpu_is_preempted(int cpu) +bool notrace arch_vcpu_is_preempted(int cpu) { if (test_cpu_flag_of(CIF_ENABLED_WAIT, cpu)) return false; @@ -403,7 +403,7 @@ bool arch_vcpu_is_preempted(int cpu) } EXPORT_SYMBOL(arch_vcpu_is_preempted); -void smp_yield_cpu(int cpu) +void notrace smp_yield_cpu(int cpu) { if (MACHINE_HAS_DIAG9C) { diag_stat_inc_norecursion(DIAG_STAT_X09C); @@ -751,7 +751,7 @@ static int smp_add_core(struct sclp_core_entry *core, cpumask_t *avail, static int __smp_rescan_cpus(struct sclp_core_info *info, bool early) { struct sclp_core_entry *core; - cpumask_t avail; + static cpumask_t avail; bool configured; u16 core_id; int nr, i; @@ -831,7 +831,7 @@ void __init smp_detect_cpus(void) */ static void smp_start_secondary(void *cpuvoid) { - int cpu = smp_processor_id(); + int cpu = raw_smp_processor_id(); S390_lowcore.last_update_clock = get_tod_clock(); S390_lowcore.restart_stack = (unsigned long) restart_stack; @@ -844,6 +844,7 @@ static void smp_start_secondary(void *cpuvoid) set_cpu_flag(CIF_ASCE_PRIMARY); set_cpu_flag(CIF_ASCE_SECONDARY); cpu_init(); + rcu_cpu_starting(cpu); preempt_disable(); init_cpu_timer(); vtime_init(); @@ -862,24 +863,12 @@ static void smp_start_secondary(void *cpuvoid) /* Upping and downing of CPUs */ int __cpu_up(unsigned int cpu, struct task_struct *tidle) { - struct pcpu *pcpu; - int base, i, rc; + struct pcpu *pcpu = pcpu_devices + cpu; + int rc; - pcpu = pcpu_devices + cpu; if (pcpu->state != CPU_STATE_CONFIGURED) return -EIO; - base = smp_get_base_cpu(cpu); - for (i = 0; i <= smp_cpu_mtid; i++) { - if (base + i < nr_cpu_ids) - if (cpu_online(base + i)) - break; - } - /* - * If this is the first CPU of the core to get online - * do an initial CPU reset. - */ - if (i > smp_cpu_mtid && - pcpu_sigp_retry(pcpu_devices + base, SIGP_INITIAL_CPU_RESET, 0) != + if (pcpu_sigp_retry(pcpu, SIGP_INITIAL_CPU_RESET, 0) != SIGP_CC_ORDER_CODE_ACCEPTED) return -EIO; diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c index e8766beee5ad..11c32b228f51 100644 --- a/arch/s390/kernel/time.c +++ b/arch/s390/kernel/time.c @@ -310,6 +310,7 @@ void update_vsyscall(struct timekeeper *tk) vdso_data->tk_mult = tk->tkr_mono.mult; vdso_data->tk_shift = tk->tkr_mono.shift; + vdso_data->hrtimer_res = hrtimer_resolution; smp_wmb(); ++vdso_data->tb_update_count; } @@ -353,8 +354,9 @@ static DEFINE_PER_CPU(atomic_t, clock_sync_word); static DEFINE_MUTEX(clock_sync_mutex); static unsigned long clock_sync_flags; -#define CLOCK_SYNC_HAS_STP 0 -#define CLOCK_SYNC_STP 1 +#define CLOCK_SYNC_HAS_STP 0 +#define CLOCK_SYNC_STP 1 +#define CLOCK_SYNC_STPINFO_VALID 2 /* * The get_clock function for the physical clock. It will get the current @@ -591,6 +593,22 @@ void stp_queue_work(void) queue_work(time_sync_wq, &stp_work); } +static int __store_stpinfo(void) +{ + int rc = chsc_sstpi(stp_page, &stp_info, sizeof(struct stp_sstpi)); + + if (rc) + clear_bit(CLOCK_SYNC_STPINFO_VALID, &clock_sync_flags); + else + set_bit(CLOCK_SYNC_STPINFO_VALID, &clock_sync_flags); + return rc; +} + +static int stpinfo_valid(void) +{ + return stp_online && test_bit(CLOCK_SYNC_STPINFO_VALID, &clock_sync_flags); +} + static int stp_sync_clock(void *data) { struct clock_sync_data *sync = data; @@ -612,8 +630,7 @@ static int stp_sync_clock(void *data) if (rc == 0) { sync->clock_delta = clock_delta; clock_sync_global(clock_delta); - rc = chsc_sstpi(stp_page, &stp_info, - sizeof(struct stp_sstpi)); + rc = __store_stpinfo(); if (rc == 0 && stp_info.tmd != 2) rc = -EAGAIN; } @@ -658,7 +675,7 @@ static void stp_work_fn(struct work_struct *work) if (rc) goto out_unlock; - rc = chsc_sstpi(stp_page, &stp_info, sizeof(struct stp_sstpi)); + rc = __store_stpinfo(); if (rc || stp_info.c == 0) goto out_unlock; @@ -695,10 +712,14 @@ static ssize_t stp_ctn_id_show(struct device *dev, struct device_attribute *attr, char *buf) { - if (!stp_online) - return -ENODATA; - return sprintf(buf, "%016llx\n", - *(unsigned long long *) stp_info.ctnid); + ssize_t ret = -ENODATA; + + mutex_lock(&stp_work_mutex); + if (stpinfo_valid()) + ret = sprintf(buf, "%016llx\n", + *(unsigned long long *) stp_info.ctnid); + mutex_unlock(&stp_work_mutex); + return ret; } static DEVICE_ATTR(ctn_id, 0400, stp_ctn_id_show, NULL); @@ -707,9 +728,13 @@ static ssize_t stp_ctn_type_show(struct device *dev, struct device_attribute *attr, char *buf) { - if (!stp_online) - return -ENODATA; - return sprintf(buf, "%i\n", stp_info.ctn); + ssize_t ret = -ENODATA; + + mutex_lock(&stp_work_mutex); + if (stpinfo_valid()) + ret = sprintf(buf, "%i\n", stp_info.ctn); + mutex_unlock(&stp_work_mutex); + return ret; } static DEVICE_ATTR(ctn_type, 0400, stp_ctn_type_show, NULL); @@ -718,9 +743,13 @@ static ssize_t stp_dst_offset_show(struct device *dev, struct device_attribute *attr, char *buf) { - if (!stp_online || !(stp_info.vbits & 0x2000)) - return -ENODATA; - return sprintf(buf, "%i\n", (int)(s16) stp_info.dsto); + ssize_t ret = -ENODATA; + + mutex_lock(&stp_work_mutex); + if (stpinfo_valid() && (stp_info.vbits & 0x2000)) + ret = sprintf(buf, "%i\n", (int)(s16) stp_info.dsto); + mutex_unlock(&stp_work_mutex); + return ret; } static DEVICE_ATTR(dst_offset, 0400, stp_dst_offset_show, NULL); @@ -729,9 +758,13 @@ static ssize_t stp_leap_seconds_show(struct device *dev, struct device_attribute *attr, char *buf) { - if (!stp_online || !(stp_info.vbits & 0x8000)) - return -ENODATA; - return sprintf(buf, "%i\n", (int)(s16) stp_info.leaps); + ssize_t ret = -ENODATA; + + mutex_lock(&stp_work_mutex); + if (stpinfo_valid() && (stp_info.vbits & 0x8000)) + ret = sprintf(buf, "%i\n", (int)(s16) stp_info.leaps); + mutex_unlock(&stp_work_mutex); + return ret; } static DEVICE_ATTR(leap_seconds, 0400, stp_leap_seconds_show, NULL); @@ -740,9 +773,13 @@ static ssize_t stp_stratum_show(struct device *dev, struct device_attribute *attr, char *buf) { - if (!stp_online) - return -ENODATA; - return sprintf(buf, "%i\n", (int)(s16) stp_info.stratum); + ssize_t ret = -ENODATA; + + mutex_lock(&stp_work_mutex); + if (stpinfo_valid()) + ret = sprintf(buf, "%i\n", (int)(s16) stp_info.stratum); + mutex_unlock(&stp_work_mutex); + return ret; } static DEVICE_ATTR(stratum, 0400, stp_stratum_show, NULL); @@ -751,9 +788,13 @@ static ssize_t stp_time_offset_show(struct device *dev, struct device_attribute *attr, char *buf) { - if (!stp_online || !(stp_info.vbits & 0x0800)) - return -ENODATA; - return sprintf(buf, "%i\n", (int) stp_info.tto); + ssize_t ret = -ENODATA; + + mutex_lock(&stp_work_mutex); + if (stpinfo_valid() && (stp_info.vbits & 0x0800)) + ret = sprintf(buf, "%i\n", (int) stp_info.tto); + mutex_unlock(&stp_work_mutex); + return ret; } static DEVICE_ATTR(time_offset, 0400, stp_time_offset_show, NULL); @@ -762,9 +803,13 @@ static ssize_t stp_time_zone_offset_show(struct device *dev, struct device_attribute *attr, char *buf) { - if (!stp_online || !(stp_info.vbits & 0x4000)) - return -ENODATA; - return sprintf(buf, "%i\n", (int)(s16) stp_info.tzo); + ssize_t ret = -ENODATA; + + mutex_lock(&stp_work_mutex); + if (stpinfo_valid() && (stp_info.vbits & 0x4000)) + ret = sprintf(buf, "%i\n", (int)(s16) stp_info.tzo); + mutex_unlock(&stp_work_mutex); + return ret; } static DEVICE_ATTR(time_zone_offset, 0400, @@ -774,9 +819,13 @@ static ssize_t stp_timing_mode_show(struct device *dev, struct device_attribute *attr, char *buf) { - if (!stp_online) - return -ENODATA; - return sprintf(buf, "%i\n", stp_info.tmd); + ssize_t ret = -ENODATA; + + mutex_lock(&stp_work_mutex); + if (stpinfo_valid()) + ret = sprintf(buf, "%i\n", stp_info.tmd); + mutex_unlock(&stp_work_mutex); + return ret; } static DEVICE_ATTR(timing_mode, 0400, stp_timing_mode_show, NULL); @@ -785,9 +834,13 @@ static ssize_t stp_timing_state_show(struct device *dev, struct device_attribute *attr, char *buf) { - if (!stp_online) - return -ENODATA; - return sprintf(buf, "%i\n", stp_info.tst); + ssize_t ret = -ENODATA; + + mutex_lock(&stp_work_mutex); + if (stpinfo_valid()) + ret = sprintf(buf, "%i\n", stp_info.tst); + mutex_unlock(&stp_work_mutex); + return ret; } static DEVICE_ATTR(timing_state, 0400, stp_timing_state_show, NULL); diff --git a/arch/s390/kernel/trace.c b/arch/s390/kernel/trace.c index 490b52e85014..11a669f3cc93 100644 --- a/arch/s390/kernel/trace.c +++ b/arch/s390/kernel/trace.c @@ -14,7 +14,7 @@ EXPORT_TRACEPOINT_SYMBOL(s390_diagnose); static DEFINE_PER_CPU(unsigned int, diagnose_trace_depth); -void trace_s390_diagnose_norecursion(int diag_nr) +void notrace trace_s390_diagnose_norecursion(int diag_nr) { unsigned long flags; unsigned int *depth; diff --git a/arch/s390/kernel/vdso64/clock_getres.S b/arch/s390/kernel/vdso64/clock_getres.S index 081435398e0a..0c79caa32b59 100644 --- a/arch/s390/kernel/vdso64/clock_getres.S +++ b/arch/s390/kernel/vdso64/clock_getres.S @@ -17,12 +17,14 @@ .type __kernel_clock_getres,@function __kernel_clock_getres: CFI_STARTPROC - larl %r1,4f + larl %r1,3f + lg %r0,0(%r1) cghi %r2,__CLOCK_REALTIME_COARSE je 0f cghi %r2,__CLOCK_MONOTONIC_COARSE je 0f - larl %r1,3f + larl %r1,_vdso_data + llgf %r0,__VDSO_CLOCK_REALTIME_RES(%r1) cghi %r2,__CLOCK_REALTIME je 0f cghi %r2,__CLOCK_MONOTONIC @@ -36,7 +38,6 @@ __kernel_clock_getres: jz 2f 0: ltgr %r3,%r3 jz 1f /* res == NULL */ - lg %r0,0(%r1) xc 0(8,%r3),0(%r3) /* set tp->tv_sec to zero */ stg %r0,8(%r3) /* store tp->tv_usec */ 1: lghi %r2,0 @@ -45,6 +46,5 @@ __kernel_clock_getres: svc 0 br %r14 CFI_ENDPROC -3: .quad __CLOCK_REALTIME_RES -4: .quad __CLOCK_COARSE_RES +3: .quad __CLOCK_COARSE_RES .size __kernel_clock_getres,.-__kernel_clock_getres diff --git a/arch/s390/kvm/gaccess.h b/arch/s390/kvm/gaccess.h index f4c51756c462..4c56de542960 100644 --- a/arch/s390/kvm/gaccess.h +++ b/arch/s390/kvm/gaccess.h @@ -18,17 +18,14 @@ /** * kvm_s390_real_to_abs - convert guest real address to guest absolute address - * @vcpu - guest virtual cpu + * @prefix - guest prefix * @gra - guest real address * * Returns the guest absolute address that corresponds to the passed guest real - * address @gra of a virtual guest cpu by applying its prefix. + * address @gra of by applying the given prefix. */ -static inline unsigned long kvm_s390_real_to_abs(struct kvm_vcpu *vcpu, - unsigned long gra) +static inline unsigned long _kvm_s390_real_to_abs(u32 prefix, unsigned long gra) { - unsigned long prefix = kvm_s390_get_prefix(vcpu); - if (gra < 2 * PAGE_SIZE) gra += prefix; else if (gra >= prefix && gra < prefix + 2 * PAGE_SIZE) @@ -37,6 +34,43 @@ static inline unsigned long kvm_s390_real_to_abs(struct kvm_vcpu *vcpu, } /** + * kvm_s390_real_to_abs - convert guest real address to guest absolute address + * @vcpu - guest virtual cpu + * @gra - guest real address + * + * Returns the guest absolute address that corresponds to the passed guest real + * address @gra of a virtual guest cpu by applying its prefix. + */ +static inline unsigned long kvm_s390_real_to_abs(struct kvm_vcpu *vcpu, + unsigned long gra) +{ + return _kvm_s390_real_to_abs(kvm_s390_get_prefix(vcpu), gra); +} + +/** + * _kvm_s390_logical_to_effective - convert guest logical to effective address + * @psw: psw of the guest + * @ga: guest logical address + * + * Convert a guest logical address to an effective address by applying the + * rules of the addressing mode defined by bits 31 and 32 of the given PSW + * (extendended/basic addressing mode). + * + * Depending on the addressing mode, the upper 40 bits (24 bit addressing + * mode), 33 bits (31 bit addressing mode) or no bits (64 bit addressing + * mode) of @ga will be zeroed and the remaining bits will be returned. + */ +static inline unsigned long _kvm_s390_logical_to_effective(psw_t *psw, + unsigned long ga) +{ + if (psw_bits(*psw).eaba == PSW_BITS_AMODE_64BIT) + return ga; + if (psw_bits(*psw).eaba == PSW_BITS_AMODE_31BIT) + return ga & ((1UL << 31) - 1); + return ga & ((1UL << 24) - 1); +} + +/** * kvm_s390_logical_to_effective - convert guest logical to effective address * @vcpu: guest virtual cpu * @ga: guest logical address @@ -52,13 +86,7 @@ static inline unsigned long kvm_s390_real_to_abs(struct kvm_vcpu *vcpu, static inline unsigned long kvm_s390_logical_to_effective(struct kvm_vcpu *vcpu, unsigned long ga) { - psw_t *psw = &vcpu->arch.sie_block->gpsw; - - if (psw_bits(*psw).eaba == PSW_BITS_AMODE_64BIT) - return ga; - if (psw_bits(*psw).eaba == PSW_BITS_AMODE_31BIT) - return ga & ((1UL << 31) - 1); - return ga & ((1UL << 24) - 1); + return _kvm_s390_logical_to_effective(&vcpu->arch.sie_block->gpsw, ga); } /* diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 11c3cd906ab4..71c67a1d2849 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -1666,6 +1666,9 @@ static int gfn_to_memslot_approx(struct kvm_memslots *slots, gfn_t gfn) start = slot + 1; } + if (start >= slots->used_slots) + return slots->used_slots - 1; + if (gfn >= memslots[start].base_gfn && gfn < memslots[start].base_gfn + memslots[start].npages) { atomic_set(&slots->lru_slot, start); @@ -3621,16 +3624,16 @@ static void store_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) current->thread.fpu.fpc = vcpu->arch.host_fpregs.fpc; current->thread.fpu.regs = vcpu->arch.host_fpregs.regs; if (MACHINE_HAS_GS) { + preempt_disable(); __ctl_set_bit(2, 4); if (vcpu->arch.gs_enabled) save_gs_cb(current->thread.gs_cb); - preempt_disable(); current->thread.gs_cb = vcpu->arch.host_gscb; restore_gs_cb(vcpu->arch.host_gscb); - preempt_enable(); if (!vcpu->arch.host_gscb) __ctl_clear_bit(2, 4); vcpu->arch.host_gscb = NULL; + preempt_enable(); } /* SIE will save etoken directly into SDNX and therefore kvm_run */ } diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c index a2b28cd1e3fe..17d73b71df1d 100644 --- a/arch/s390/kvm/vsie.c +++ b/arch/s390/kvm/vsie.c @@ -1024,6 +1024,7 @@ static int vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) scb_s->iprcc = PGM_ADDRESSING; scb_s->pgmilc = 4; scb_s->gpsw.addr = __rewind_psw(scb_s->gpsw, 4); + rc = 1; } return rc; } diff --git a/arch/s390/lib/uaccess.c b/arch/s390/lib/uaccess.c index c4f8039a35e8..0267405ab7c6 100644 --- a/arch/s390/lib/uaccess.c +++ b/arch/s390/lib/uaccess.c @@ -64,10 +64,13 @@ mm_segment_t enable_sacf_uaccess(void) { mm_segment_t old_fs; unsigned long asce, cr; + unsigned long flags; old_fs = current->thread.mm_segment; if (old_fs & 1) return old_fs; + /* protect against a concurrent page table upgrade */ + local_irq_save(flags); current->thread.mm_segment |= 1; asce = S390_lowcore.kernel_asce; if (likely(old_fs == USER_DS)) { @@ -83,6 +86,7 @@ mm_segment_t enable_sacf_uaccess(void) __ctl_load(asce, 7, 7); set_cpu_flag(CIF_ASCE_SECONDARY); } + local_irq_restore(flags); return old_fs; } EXPORT_SYMBOL(enable_sacf_uaccess); diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c index 911c7ded35f1..7cde0f2f52e1 100644 --- a/arch/s390/mm/gmap.c +++ b/arch/s390/mm/gmap.c @@ -787,14 +787,18 @@ static void gmap_call_notifier(struct gmap *gmap, unsigned long start, static inline unsigned long *gmap_table_walk(struct gmap *gmap, unsigned long gaddr, int level) { + const int asce_type = gmap->asce & _ASCE_TYPE_MASK; unsigned long *table; if ((gmap->asce & _ASCE_TYPE_MASK) + 4 < (level * 4)) return NULL; if (gmap_is_shadow(gmap) && gmap->removed) return NULL; - if (gaddr & (-1UL << (31 + ((gmap->asce & _ASCE_TYPE_MASK) >> 2)*11))) + + if (asce_type != _ASCE_TYPE_REGION1 && + gaddr & (-1UL << (31 + (asce_type >> 2) * 11))) return NULL; + table = gmap->table; switch (gmap->asce & _ASCE_TYPE_MASK) { case _ASCE_TYPE_REGION1: @@ -1834,6 +1838,7 @@ int gmap_shadow_r3t(struct gmap *sg, unsigned long saddr, unsigned long r3t, goto out_free; } else if (*table & _REGION_ENTRY_ORIGIN) { rc = -EAGAIN; /* Race with shadow */ + goto out_free; } crst_table_init(s_r3t, _REGION3_ENTRY_EMPTY); /* mark as invalid as long as the parent table is not protected */ diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c index 5674710a4841..ff8234bca56c 100644 --- a/arch/s390/mm/hugetlbpage.c +++ b/arch/s390/mm/hugetlbpage.c @@ -117,7 +117,7 @@ static inline pte_t __rste_to_pte(unsigned long rste) _PAGE_YOUNG); #ifdef CONFIG_MEM_SOFT_DIRTY pte_val(pte) |= move_set_bit(rste, _SEGMENT_ENTRY_SOFT_DIRTY, - _PAGE_DIRTY); + _PAGE_SOFT_DIRTY); #endif pte_val(pte) |= move_set_bit(rste, _SEGMENT_ENTRY_NOEXEC, _PAGE_NOEXEC); @@ -159,10 +159,13 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, rste &= ~_SEGMENT_ENTRY_NOEXEC; /* Set correct table type for 2G hugepages */ - if ((pte_val(*ptep) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R3) - rste |= _REGION_ENTRY_TYPE_R3 | _REGION3_ENTRY_LARGE; - else + if ((pte_val(*ptep) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R3) { + if (likely(pte_present(pte))) + rste |= _REGION3_ENTRY_LARGE; + rste |= _REGION_ENTRY_TYPE_R3; + } else if (likely(pte_present(pte))) rste |= _SEGMENT_ENTRY_LARGE; + clear_huge_pte_skeys(mm, rste); pte_val(*ptep) = rste; } diff --git a/arch/s390/mm/pgalloc.c b/arch/s390/mm/pgalloc.c index 814f26520aa2..f3bc9c9305da 100644 --- a/arch/s390/mm/pgalloc.c +++ b/arch/s390/mm/pgalloc.c @@ -72,8 +72,20 @@ static void __crst_table_upgrade(void *arg) { struct mm_struct *mm = arg; - if (current->active_mm == mm) - set_user_asce(mm); + /* we must change all active ASCEs to avoid the creation of new TLBs */ + if (current->active_mm == mm) { + S390_lowcore.user_asce = mm->context.asce; + if (current->thread.mm_segment == USER_DS) { + __ctl_load(S390_lowcore.user_asce, 1, 1); + /* Mark user-ASCE present in CR1 */ + clear_cpu_flag(CIF_ASCE_PRIMARY); + } + if (current->thread.mm_segment == USER_DS_SACF) { + __ctl_load(S390_lowcore.user_asce, 7, 7); + /* enable_sacf_uaccess does all or nothing */ + WARN_ON(!test_cpu_flag(CIF_ASCE_SECONDARY)); + } + } __tlb_flush_local(); } diff --git a/arch/s390/purgatory/head.S b/arch/s390/purgatory/head.S index 2e3707b12edd..9b2d7a71fd1b 100644 --- a/arch/s390/purgatory/head.S +++ b/arch/s390/purgatory/head.S @@ -61,14 +61,15 @@ jh 10b .endm -.macro START_NEXT_KERNEL base +.macro START_NEXT_KERNEL base subcode lg %r4,kernel_entry-\base(%r13) lg %r5,load_psw_mask-\base(%r13) ogr %r4,%r5 stg %r4,0(%r0) xgr %r0,%r0 - diag %r0,%r0,0x308 + lghi %r1,\subcode + diag %r0,%r1,0x308 .endm .text @@ -123,7 +124,7 @@ ENTRY(purgatory_start) je .start_crash_kernel /* start normal kernel */ - START_NEXT_KERNEL .base_crash + START_NEXT_KERNEL .base_crash 0 .return_old_kernel: lmg %r6,%r15,gprregs-.base_crash(%r13) @@ -227,7 +228,7 @@ ENTRY(purgatory_start) MEMCPY %r9,%r10,%r11 /* start crash kernel */ - START_NEXT_KERNEL .base_dst + START_NEXT_KERNEL .base_dst 1 load_psw_mask: diff --git a/arch/sh/boards/mach-landisk/setup.c b/arch/sh/boards/mach-landisk/setup.c index f1147caebacf..af69fb7fef7c 100644 --- a/arch/sh/boards/mach-landisk/setup.c +++ b/arch/sh/boards/mach-landisk/setup.c @@ -85,6 +85,9 @@ device_initcall(landisk_devices_setup); static void __init landisk_setup(char **cmdline_p) { + /* I/O port identity mapping */ + __set_io_port_base(0); + /* LED ON */ __raw_writeb(__raw_readb(PA_LED) | 0x03, PA_LED); diff --git a/arch/sh/configs/sh03_defconfig b/arch/sh/configs/sh03_defconfig index 2156223405a1..ecc736504a04 100644 --- a/arch/sh/configs/sh03_defconfig +++ b/arch/sh/configs/sh03_defconfig @@ -47,7 +47,6 @@ CONFIG_BLK_DEV_IDETAPE=m CONFIG_SCSI=m CONFIG_BLK_DEV_SD=m CONFIG_BLK_DEV_SR=m -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=m CONFIG_NETDEVICES=y CONFIG_NET_ETHERNET=y diff --git a/arch/sh/drivers/dma/Kconfig b/arch/sh/drivers/dma/Kconfig index d0de378beefe..7d54f284ce10 100644 --- a/arch/sh/drivers/dma/Kconfig +++ b/arch/sh/drivers/dma/Kconfig @@ -63,8 +63,7 @@ config PVR2_DMA config G2_DMA tristate "G2 Bus DMA support" - depends on SH_DREAMCAST - select SH_DMA_API + depends on SH_DREAMCAST && SH_DMA_API help This enables support for the DMA controller for the Dreamcast's G2 bus. Drivers that want this will generally enable this on diff --git a/arch/sh/include/asm/uaccess.h b/arch/sh/include/asm/uaccess.h index 32eb56e00c11..6e7816360a75 100644 --- a/arch/sh/include/asm/uaccess.h +++ b/arch/sh/include/asm/uaccess.h @@ -16,8 +16,11 @@ * sum := addr + size; carry? --> flag = true; * if (sum >= addr_limit) flag = true; */ -#define __access_ok(addr, size) \ - (__addr_ok((addr) + (size))) +#define __access_ok(addr, size) ({ \ + unsigned long __ao_a = (addr), __ao_b = (size); \ + unsigned long __ao_end = __ao_a + __ao_b - !!__ao_b; \ + __ao_end >= __ao_a && __addr_ok(__ao_end); }) + #define access_ok(type, addr, size) \ (__chk_user_ptr(addr), \ __access_ok((unsigned long __force)(addr), (size))) diff --git a/arch/sh/kernel/entry-common.S b/arch/sh/kernel/entry-common.S index 28cc61216b64..ed5b758c650d 100644 --- a/arch/sh/kernel/entry-common.S +++ b/arch/sh/kernel/entry-common.S @@ -203,7 +203,7 @@ syscall_trace_entry: mov.l @(OFF_R7,r15), r7 ! arg3 mov.l @(OFF_R3,r15), r3 ! syscall_nr ! - mov.l 2f, r10 ! Number of syscalls + mov.l 6f, r10 ! Number of syscalls cmp/hs r10, r3 bf syscall_call mov #-ENOSYS, r0 @@ -357,7 +357,7 @@ ENTRY(system_call) tst r9, r8 bf syscall_trace_entry ! - mov.l 2f, r8 ! Number of syscalls + mov.l 6f, r8 ! Number of syscalls cmp/hs r8, r3 bt syscall_badsys ! @@ -396,7 +396,7 @@ syscall_exit: #if !defined(CONFIG_CPU_SH2) 1: .long TRA #endif -2: .long NR_syscalls +6: .long NR_syscalls 3: .long sys_call_table 7: .long do_syscall_trace_enter 8: .long do_syscall_trace_leave diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index e6f2a38d2e61..1f1a7583fa90 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -554,7 +554,7 @@ config COMPAT bool depends on SPARC64 default y - select COMPAT_BINFMT_ELF + select COMPAT_BINFMT_ELF if BINFMT_ELF select HAVE_UID16 select ARCH_WANT_OLD_COMPAT_IPC select COMPAT_OLD_SIGACTION diff --git a/arch/sparc/configs/sparc64_defconfig b/arch/sparc/configs/sparc64_defconfig index 4d4e1cc6402f..fc45ec682e7a 100644 --- a/arch/sparc/configs/sparc64_defconfig +++ b/arch/sparc/configs/sparc64_defconfig @@ -74,7 +74,6 @@ CONFIG_RAID_ATTRS=m CONFIG_SCSI=y CONFIG_BLK_DEV_SD=y CONFIG_BLK_DEV_SR=m -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=m CONFIG_SCSI_MULTI_LUN=y CONFIG_SCSI_CONSTANTS=y diff --git a/arch/sparc/include/asm/mman.h b/arch/sparc/include/asm/mman.h index f94532f25db1..274217e7ed70 100644 --- a/arch/sparc/include/asm/mman.h +++ b/arch/sparc/include/asm/mman.h @@ -57,35 +57,39 @@ static inline int sparc_validate_prot(unsigned long prot, unsigned long addr) { if (prot & ~(PROT_READ | PROT_WRITE | PROT_EXEC | PROT_SEM | PROT_ADI)) return 0; - if (prot & PROT_ADI) { - if (!adi_capable()) - return 0; + return 1; +} - if (addr) { - struct vm_area_struct *vma; +#define arch_validate_flags(vm_flags) arch_validate_flags(vm_flags) +/* arch_validate_flags() - Ensure combination of flags is valid for a + * VMA. + */ +static inline bool arch_validate_flags(unsigned long vm_flags) +{ + /* If ADI is being enabled on this VMA, check for ADI + * capability on the platform and ensure VMA is suitable + * for ADI + */ + if (vm_flags & VM_SPARC_ADI) { + if (!adi_capable()) + return false; - vma = find_vma(current->mm, addr); - if (vma) { - /* ADI can not be enabled on PFN - * mapped pages - */ - if (vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP)) - return 0; + /* ADI can not be enabled on PFN mapped pages */ + if (vm_flags & (VM_PFNMAP | VM_MIXEDMAP)) + return false; - /* Mergeable pages can become unmergeable - * if ADI is enabled on them even if they - * have identical data on them. This can be - * because ADI enabled pages with identical - * data may still not have identical ADI - * tags on them. Disallow ADI on mergeable - * pages. - */ - if (vma->vm_flags & VM_MERGEABLE) - return 0; - } - } + /* Mergeable pages can become unmergeable + * if ADI is enabled on them even if they + * have identical data on them. This can be + * because ADI enabled pages with identical + * data may still not have identical ADI + * tags on them. Disallow ADI on mergeable + * pages. + */ + if (vm_flags & VM_MERGEABLE) + return false; } - return 1; + return true; } #endif /* CONFIG_SPARC64 */ diff --git a/arch/sparc/kernel/ptrace_32.c b/arch/sparc/kernel/ptrace_32.c index 16b50afe7b52..646dd58169ec 100644 --- a/arch/sparc/kernel/ptrace_32.c +++ b/arch/sparc/kernel/ptrace_32.c @@ -46,82 +46,79 @@ enum sparc_regset { REGSET_FP, }; +static int regwindow32_get(struct task_struct *target, + const struct pt_regs *regs, + u32 *uregs) +{ + unsigned long reg_window = regs->u_regs[UREG_I6]; + int size = 16 * sizeof(u32); + + if (target == current) { + if (copy_from_user(uregs, (void __user *)reg_window, size)) + return -EFAULT; + } else { + if (access_process_vm(target, reg_window, uregs, size, + FOLL_FORCE) != size) + return -EFAULT; + } + return 0; +} + +static int regwindow32_set(struct task_struct *target, + const struct pt_regs *regs, + u32 *uregs) +{ + unsigned long reg_window = regs->u_regs[UREG_I6]; + int size = 16 * sizeof(u32); + + if (target == current) { + if (copy_to_user((void __user *)reg_window, uregs, size)) + return -EFAULT; + } else { + if (access_process_vm(target, reg_window, uregs, size, + FOLL_FORCE | FOLL_WRITE) != size) + return -EFAULT; + } + return 0; +} + static int genregs32_get(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf) { const struct pt_regs *regs = target->thread.kregs; - unsigned long __user *reg_window; - unsigned long *k = kbuf; - unsigned long __user *u = ubuf; - unsigned long reg; + u32 uregs[16]; + int ret; if (target == current) flush_user_windows(); - pos /= sizeof(reg); - count /= sizeof(reg); - - if (kbuf) { - for (; count > 0 && pos < 16; count--) - *k++ = regs->u_regs[pos++]; - - reg_window = (unsigned long __user *) regs->u_regs[UREG_I6]; - reg_window -= 16; - for (; count > 0 && pos < 32; count--) { - if (get_user(*k++, ®_window[pos++])) - return -EFAULT; - } - } else { - for (; count > 0 && pos < 16; count--) { - if (put_user(regs->u_regs[pos++], u++)) - return -EFAULT; - } - - reg_window = (unsigned long __user *) regs->u_regs[UREG_I6]; - reg_window -= 16; - for (; count > 0 && pos < 32; count--) { - if (get_user(reg, ®_window[pos++]) || - put_user(reg, u++)) - return -EFAULT; - } - } - while (count > 0) { - switch (pos) { - case 32: /* PSR */ - reg = regs->psr; - break; - case 33: /* PC */ - reg = regs->pc; - break; - case 34: /* NPC */ - reg = regs->npc; - break; - case 35: /* Y */ - reg = regs->y; - break; - case 36: /* WIM */ - case 37: /* TBR */ - reg = 0; - break; - default: - goto finish; - } + ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, + regs->u_regs, + 0, 16 * sizeof(u32)); + if (ret || !count) + return ret; - if (kbuf) - *k++ = reg; - else if (put_user(reg, u++)) + if (pos < 32 * sizeof(u32)) { + if (regwindow32_get(target, regs, uregs)) return -EFAULT; - pos++; - count--; + ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, + uregs, + 16 * sizeof(u32), 32 * sizeof(u32)); + if (ret || !count) + return ret; } -finish: - pos *= sizeof(reg); - count *= sizeof(reg); - return user_regset_copyout_zero(&pos, &count, &kbuf, &ubuf, - 38 * sizeof(reg), -1); + uregs[0] = regs->psr; + uregs[1] = regs->pc; + uregs[2] = regs->npc; + uregs[3] = regs->y; + uregs[4] = 0; /* WIM */ + uregs[5] = 0; /* TBR */ + return user_regset_copyout(&pos, &count, &kbuf, &ubuf, + uregs, + 32 * sizeof(u32), 38 * sizeof(u32)); } static int genregs32_set(struct task_struct *target, @@ -130,82 +127,58 @@ static int genregs32_set(struct task_struct *target, const void *kbuf, const void __user *ubuf) { struct pt_regs *regs = target->thread.kregs; - unsigned long __user *reg_window; - const unsigned long *k = kbuf; - const unsigned long __user *u = ubuf; - unsigned long reg; + u32 uregs[16]; + u32 psr; + int ret; if (target == current) flush_user_windows(); - pos /= sizeof(reg); - count /= sizeof(reg); - - if (kbuf) { - for (; count > 0 && pos < 16; count--) - regs->u_regs[pos++] = *k++; - - reg_window = (unsigned long __user *) regs->u_regs[UREG_I6]; - reg_window -= 16; - for (; count > 0 && pos < 32; count--) { - if (put_user(*k++, ®_window[pos++])) - return -EFAULT; - } - } else { - for (; count > 0 && pos < 16; count--) { - if (get_user(reg, u++)) - return -EFAULT; - regs->u_regs[pos++] = reg; - } - - reg_window = (unsigned long __user *) regs->u_regs[UREG_I6]; - reg_window -= 16; - for (; count > 0 && pos < 32; count--) { - if (get_user(reg, u++) || - put_user(reg, ®_window[pos++])) - return -EFAULT; - } - } - while (count > 0) { - unsigned long psr; + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + regs->u_regs, + 0, 16 * sizeof(u32)); + if (ret || !count) + return ret; - if (kbuf) - reg = *k++; - else if (get_user(reg, u++)) + if (pos < 32 * sizeof(u32)) { + if (regwindow32_get(target, regs, uregs)) return -EFAULT; - - switch (pos) { - case 32: /* PSR */ - psr = regs->psr; - psr &= ~(PSR_ICC | PSR_SYSCALL); - psr |= (reg & (PSR_ICC | PSR_SYSCALL)); - regs->psr = psr; - break; - case 33: /* PC */ - regs->pc = reg; - break; - case 34: /* NPC */ - regs->npc = reg; - break; - case 35: /* Y */ - regs->y = reg; - break; - case 36: /* WIM */ - case 37: /* TBR */ - break; - default: - goto finish; - } - - pos++; - count--; + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + uregs, + 16 * sizeof(u32), 32 * sizeof(u32)); + if (ret) + return ret; + if (regwindow32_set(target, regs, uregs)) + return -EFAULT; + if (!count) + return 0; } -finish: - pos *= sizeof(reg); - count *= sizeof(reg); - + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &psr, + 32 * sizeof(u32), 33 * sizeof(u32)); + if (ret) + return ret; + regs->psr = (regs->psr & ~(PSR_ICC | PSR_SYSCALL)) | + (psr & (PSR_ICC | PSR_SYSCALL)); + if (!count) + return 0; + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + ®s->pc, + 33 * sizeof(u32), 34 * sizeof(u32)); + if (ret || !count) + return ret; + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + ®s->npc, + 34 * sizeof(u32), 35 * sizeof(u32)); + if (ret || !count) + return ret; + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + ®s->y, + 35 * sizeof(u32), 36 * sizeof(u32)); + if (ret || !count) + return ret; return user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf, - 38 * sizeof(reg), -1); + 36 * sizeof(u32), 38 * sizeof(u32)); } static int fpregs32_get(struct task_struct *target, diff --git a/arch/sparc/kernel/ptrace_64.c b/arch/sparc/kernel/ptrace_64.c index e1d965e90e16..0c478c85e380 100644 --- a/arch/sparc/kernel/ptrace_64.c +++ b/arch/sparc/kernel/ptrace_64.c @@ -571,19 +571,13 @@ static int genregs32_get(struct task_struct *target, for (; count > 0 && pos < 32; count--) { if (access_process_vm(target, (unsigned long) - ®_window[pos], + ®_window[pos++], ®, sizeof(reg), FOLL_FORCE) != sizeof(reg)) return -EFAULT; - if (access_process_vm(target, - (unsigned long) u, - ®, sizeof(reg), - FOLL_FORCE | FOLL_WRITE) - != sizeof(reg)) + if (put_user(reg, u++)) return -EFAULT; - pos++; - u++; } } } @@ -683,12 +677,7 @@ static int genregs32_set(struct task_struct *target, } } else { for (; count > 0 && pos < 32; count--) { - if (access_process_vm(target, - (unsigned long) - u, - ®, sizeof(reg), - FOLL_FORCE) - != sizeof(reg)) + if (get_user(reg, u++)) return -EFAULT; if (access_process_vm(target, (unsigned long) diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c index d3ea1f3c06a0..a7d7b7ade42f 100644 --- a/arch/sparc/kernel/smp_64.c +++ b/arch/sparc/kernel/smp_64.c @@ -1039,38 +1039,9 @@ void smp_fetch_global_pmu(void) * are flush_tlb_*() routines, and these run after flush_cache_*() * which performs the flushw. * - * The SMP TLB coherency scheme we use works as follows: - * - * 1) mm->cpu_vm_mask is a bit mask of which cpus an address - * space has (potentially) executed on, this is the heuristic - * we use to avoid doing cross calls. - * - * Also, for flushing from kswapd and also for clones, we - * use cpu_vm_mask as the list of cpus to make run the TLB. - * - * 2) TLB context numbers are shared globally across all processors - * in the system, this allows us to play several games to avoid - * cross calls. - * - * One invariant is that when a cpu switches to a process, and - * that processes tsk->active_mm->cpu_vm_mask does not have the - * current cpu's bit set, that tlb context is flushed locally. - * - * If the address space is non-shared (ie. mm->count == 1) we avoid - * cross calls when we want to flush the currently running process's - * tlb state. This is done by clearing all cpu bits except the current - * processor's in current->mm->cpu_vm_mask and performing the - * flush locally only. This will force any subsequent cpus which run - * this task to flush the context from the local tlb if the process - * migrates to another cpu (again). - * - * 3) For shared address spaces (threads) and swapping we bite the - * bullet for most cases and perform the cross call (but only to - * the cpus listed in cpu_vm_mask). - * - * The performance gain from "optimizing" away the cross call for threads is - * questionable (in theory the big win for threads is the massive sharing of - * address space state across processors). + * mm->cpu_vm_mask is a bit mask of which cpus an address + * space has (potentially) executed on, this is the heuristic + * we use to limit cross calls. */ /* This currently is only used by the hugetlb arch pre-fault @@ -1080,18 +1051,13 @@ void smp_fetch_global_pmu(void) void smp_flush_tlb_mm(struct mm_struct *mm) { u32 ctx = CTX_HWBITS(mm->context); - int cpu = get_cpu(); - if (atomic_read(&mm->mm_users) == 1) { - cpumask_copy(mm_cpumask(mm), cpumask_of(cpu)); - goto local_flush_and_out; - } + get_cpu(); smp_cross_call_masked(&xcall_flush_tlb_mm, ctx, 0, 0, mm_cpumask(mm)); -local_flush_and_out: __flush_tlb_mm(ctx, SECONDARY_CONTEXT); put_cpu(); @@ -1114,17 +1080,15 @@ void smp_flush_tlb_pending(struct mm_struct *mm, unsigned long nr, unsigned long { u32 ctx = CTX_HWBITS(mm->context); struct tlb_pending_info info; - int cpu = get_cpu(); + + get_cpu(); info.ctx = ctx; info.nr = nr; info.vaddrs = vaddrs; - if (mm == current->mm && atomic_read(&mm->mm_users) == 1) - cpumask_copy(mm_cpumask(mm), cpumask_of(cpu)); - else - smp_call_function_many(mm_cpumask(mm), tlb_pending_func, - &info, 1); + smp_call_function_many(mm_cpumask(mm), tlb_pending_func, + &info, 1); __flush_tlb_pending(ctx, nr, vaddrs); @@ -1134,14 +1098,13 @@ void smp_flush_tlb_pending(struct mm_struct *mm, unsigned long nr, unsigned long void smp_flush_tlb_page(struct mm_struct *mm, unsigned long vaddr) { unsigned long context = CTX_HWBITS(mm->context); - int cpu = get_cpu(); - if (mm == current->mm && atomic_read(&mm->mm_users) == 1) - cpumask_copy(mm_cpumask(mm), cpumask_of(cpu)); - else - smp_cross_call_masked(&xcall_flush_tlb_page, - context, vaddr, 0, - mm_cpumask(mm)); + get_cpu(); + + smp_cross_call_masked(&xcall_flush_tlb_page, + context, vaddr, 0, + mm_cpumask(mm)); + __flush_tlb_page(context, vaddr); put_cpu(); diff --git a/arch/sparc/kernel/traps_64.c b/arch/sparc/kernel/traps_64.c index aa624ed79db1..86879c28910b 100644 --- a/arch/sparc/kernel/traps_64.c +++ b/arch/sparc/kernel/traps_64.c @@ -274,14 +274,13 @@ bool is_no_fault_exception(struct pt_regs *regs) asi = (regs->tstate >> 24); /* saved %asi */ else asi = (insn >> 5); /* immediate asi */ - if ((asi & 0xf2) == ASI_PNF) { - if (insn & 0x1000000) { /* op3[5:4]=3 */ - handle_ldf_stq(insn, regs); - return true; - } else if (insn & 0x200000) { /* op3[2], stores */ + if ((asi & 0xf6) == ASI_PNF) { + if (insn & 0x200000) /* op3[2], stores */ return false; - } - handle_ld_nf(insn, regs); + if (insn & 0x1000000) /* op3[5:4]=3 (fp) */ + handle_ldf_stq(insn, regs); + else + handle_ld_nf(insn, regs); return true; } } diff --git a/arch/sparc/lib/memset.S b/arch/sparc/lib/memset.S index b89d42b29e34..f427f34b8b79 100644 --- a/arch/sparc/lib/memset.S +++ b/arch/sparc/lib/memset.S @@ -142,6 +142,7 @@ __bzero: ZERO_LAST_BLOCKS(%o0, 0x48, %g2) ZERO_LAST_BLOCKS(%o0, 0x08, %g2) 13: + EXT(12b, 13b, 21f) be 8f andcc %o1, 4, %g0 diff --git a/arch/sparc/mm/init_32.c b/arch/sparc/mm/init_32.c index 92634d4e440c..89a9244f2cf0 100644 --- a/arch/sparc/mm/init_32.c +++ b/arch/sparc/mm/init_32.c @@ -199,6 +199,9 @@ unsigned long __init bootmem_init(unsigned long *pages_avail) size = memblock_phys_mem_size() - memblock_reserved_size(); *pages_avail = (size >> PAGE_SHIFT) - high_pages; + /* Only allow low memory to be allocated via memblock allocation */ + memblock_set_current_limit(max_low_pfn << PAGE_SHIFT); + return max_pfn; } diff --git a/arch/um/drivers/chan_user.c b/arch/um/drivers/chan_user.c index 3fd7c3efdb18..9cffbbb15c56 100644 --- a/arch/um/drivers/chan_user.c +++ b/arch/um/drivers/chan_user.c @@ -26,10 +26,10 @@ int generic_read(int fd, char *c_out, void *unused) n = read(fd, c_out, sizeof(*c_out)); if (n > 0) return n; - else if (errno == EAGAIN) - return 0; else if (n == 0) return -EIO; + else if (errno == EAGAIN) + return 0; return -errno; } diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c index 83c470364dfb..788c80abff5d 100644 --- a/arch/um/drivers/ubd_kern.c +++ b/arch/um/drivers/ubd_kern.c @@ -891,7 +891,7 @@ static int ubd_disk_register(int major, u64 size, int unit, disk->private_data = &ubd_devs[unit]; disk->queue = ubd_devs[unit].queue; - device_add_disk(parent, disk); + device_add_disk(parent, disk, NULL); *disk_out = disk; return 0; @@ -1574,7 +1574,9 @@ int io_thread(void *arg) written = 0; do { - res = os_write_file(kernel_fd, ((char *) io_req_buffer) + written, n); + res = os_write_file(kernel_fd, + ((char *) io_req_buffer) + written, + n - written); if (res >= 0) { written += res; } else { diff --git a/arch/um/drivers/xterm.c b/arch/um/drivers/xterm.c index 20e30be44795..e3b422ebce09 100644 --- a/arch/um/drivers/xterm.c +++ b/arch/um/drivers/xterm.c @@ -18,6 +18,7 @@ struct xterm_chan { int pid; int helper_pid; + int chan_fd; char *title; int device; int raw; @@ -33,6 +34,7 @@ static void *xterm_init(char *str, int device, const struct chan_opts *opts) return NULL; *data = ((struct xterm_chan) { .pid = -1, .helper_pid = -1, + .chan_fd = -1, .device = device, .title = opts->xterm_title, .raw = opts->raw } ); @@ -149,6 +151,7 @@ static int xterm_open(int input, int output, int primary, void *d, goto out_kill; } + data->chan_fd = fd; new = xterm_fd(fd, &data->helper_pid); if (new < 0) { err = new; @@ -206,6 +209,8 @@ static void xterm_close(int fd, void *d) os_kill_process(data->helper_pid, 0); data->helper_pid = -1; + if (data->chan_fd != -1) + os_close_file(data->chan_fd); os_close_file(fd); } diff --git a/arch/um/kernel/dyn.lds.S b/arch/um/kernel/dyn.lds.S index 5568cf882371..899233625467 100644 --- a/arch/um/kernel/dyn.lds.S +++ b/arch/um/kernel/dyn.lds.S @@ -6,6 +6,12 @@ OUTPUT_ARCH(ELF_ARCH) ENTRY(_start) jiffies = jiffies_64; +VERSION { + { + local: *; + }; +} + SECTIONS { PROVIDE (__executable_start = START); diff --git a/arch/um/kernel/sigio.c b/arch/um/kernel/sigio.c index b5e0cbb34382..476ded92affa 100644 --- a/arch/um/kernel/sigio.c +++ b/arch/um/kernel/sigio.c @@ -36,14 +36,14 @@ int write_sigio_irq(int fd) } /* These are called from os-Linux/sigio.c to protect its pollfds arrays. */ -static DEFINE_SPINLOCK(sigio_spinlock); +static DEFINE_MUTEX(sigio_mutex); void sigio_lock(void) { - spin_lock(&sigio_spinlock); + mutex_lock(&sigio_mutex); } void sigio_unlock(void) { - spin_unlock(&sigio_spinlock); + mutex_unlock(&sigio_mutex); } diff --git a/arch/um/kernel/uml.lds.S b/arch/um/kernel/uml.lds.S index 36b07ec09742..22ff701d9b71 100644 --- a/arch/um/kernel/uml.lds.S +++ b/arch/um/kernel/uml.lds.S @@ -7,6 +7,12 @@ OUTPUT_ARCH(ELF_ARCH) ENTRY(_start) jiffies = jiffies_64; +VERSION { + { + local: *; + }; +} + SECTIONS { /* This must contain the right address - not quite the default ELF one.*/ diff --git a/arch/um/os-Linux/irq.c b/arch/um/os-Linux/irq.c index 365823010346..90ef40462280 100644 --- a/arch/um/os-Linux/irq.c +++ b/arch/um/os-Linux/irq.c @@ -48,7 +48,7 @@ int os_epoll_triggered(int index, int events) int os_event_mask(int irq_type) { if (irq_type == IRQ_READ) - return EPOLLIN | EPOLLPRI; + return EPOLLIN | EPOLLPRI | EPOLLERR | EPOLLHUP | EPOLLRDHUP; if (irq_type == IRQ_WRITE) return EPOLLOUT; return 0; diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index af35f5caadbe..d994501d9179 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -533,6 +533,7 @@ config X86_UV depends on X86_EXTENDED_PLATFORM depends on NUMA depends on EFI + depends on KEXEC_CORE depends on X86_X2APIC depends on PCI ---help--- diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 4833dd7e2cc0..65a8722e784c 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -34,12 +34,13 @@ M16_CFLAGS := $(call cc-option, -m16, $(CODE16GCC_CFLAGS)) REALMODE_CFLAGS := $(M16_CFLAGS) -g -Os -DDISABLE_BRANCH_PROFILING \ -Wall -Wstrict-prototypes -march=i386 -mregparm=3 \ -fno-strict-aliasing -fomit-frame-pointer -fno-pic \ - -mno-mmx -mno-sse + -mno-mmx -mno-sse $(call cc-option,-fcf-protection=none) REALMODE_CFLAGS += $(call __cc-option, $(CC), $(REALMODE_CFLAGS), -ffreestanding) REALMODE_CFLAGS += $(call __cc-option, $(CC), $(REALMODE_CFLAGS), -fno-stack-protector) REALMODE_CFLAGS += $(call __cc-option, $(CC), $(REALMODE_CFLAGS), -Wno-address-of-packed-member) REALMODE_CFLAGS += $(call __cc-option, $(CC), $(REALMODE_CFLAGS), $(cc_stack_align4)) +REALMODE_CFLAGS += $(CLANG_FLAGS) export REALMODE_CFLAGS # BITS is used as extension for files which are available in a 32 bit @@ -61,6 +62,9 @@ endif KBUILD_CFLAGS += -mno-sse -mno-mmx -mno-sse2 -mno-3dnow KBUILD_CFLAGS += $(call cc-option,-mno-avx,) +# Intel CET isn't enabled in the kernel +KBUILD_CFLAGS += $(call cc-option,-fcf-protection=none) + ifeq ($(CONFIG_X86_32),y) BITS := 32 UTS_MACHINE := i386 diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile index e2839b5c246c..6539c50fb9aa 100644 --- a/arch/x86/boot/Makefile +++ b/arch/x86/boot/Makefile @@ -87,7 +87,7 @@ $(obj)/vmlinux.bin: $(obj)/compressed/vmlinux FORCE SETUP_OBJS = $(addprefix $(obj)/,$(setup-y)) -sed-zoffset := -e 's/^\([0-9a-fA-F]*\) [ABCDGRSTVW] \(startup_32\|startup_64\|efi32_stub_entry\|efi64_stub_entry\|efi_pe_entry\|input_data\|_end\|_ehead\|_text\|z_.*\)$$/\#define ZO_\2 0x\1/p' +sed-zoffset := -e 's/^\([0-9a-fA-F]*\) [a-zA-Z] \(startup_32\|startup_64\|efi32_stub_entry\|efi64_stub_entry\|efi_pe_entry\|input_data\|_end\|_ehead\|_text\|z_.*\)$$/\#define ZO_\2 0x\1/p' quiet_cmd_zoffset = ZOFFSET $@ cmd_zoffset = $(NM) $< | sed -n $(sed-zoffset) > $@ diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index 466f66c8a7f8..5642f025b397 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -38,6 +38,8 @@ KBUILD_CFLAGS += $(call cc-option,-fno-stack-protector) KBUILD_CFLAGS += $(call cc-disable-warning, address-of-packed-member) KBUILD_CFLAGS += $(call cc-disable-warning, gnu) KBUILD_CFLAGS += -Wno-pointer-sign +# Disable relocation relaxation in case the link is not PIE. +KBUILD_CFLAGS += $(call as-option,-Wa$(comma)-mrelax-relocations=no) KBUILD_AFLAGS := $(KBUILD_CFLAGS) -D__ASSEMBLY__ GCOV_PROFILE := n @@ -100,7 +102,7 @@ vmlinux-objs-$(CONFIG_EFI_MIXED) += $(obj)/efi_thunk_$(BITS).o quiet_cmd_check_data_rel = DATAREL $@ define cmd_check_data_rel for obj in $(filter %.o,$^); do \ - ${CROSS_COMPILE}readelf -S $$obj | grep -qF .rel.local && { \ + $(READELF) -S $$obj | grep -qF .rel.local && { \ echo "error: $$obj has data relocations!" >&2; \ exit 1; \ } || true; \ diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S index 37380c0d5999..c6c4b877f3d2 100644 --- a/arch/x86/boot/compressed/head_32.S +++ b/arch/x86/boot/compressed/head_32.S @@ -49,16 +49,17 @@ * Position Independent Executable (PIE) so that linker won't optimize * R_386_GOT32X relocation to its fixed symbol address. Older * linkers generate R_386_32 relocations against locally defined symbols, - * _bss, _ebss, _got and _egot, in PIE. It isn't wrong, just less + * _bss, _ebss, _got, _egot and _end, in PIE. It isn't wrong, just less * optimal than R_386_RELATIVE. But the x86 kernel fails to properly handle * R_386_32 relocations when relocating the kernel. To generate - * R_386_RELATIVE relocations, we mark _bss, _ebss, _got and _egot as + * R_386_RELATIVE relocations, we mark _bss, _ebss, _got, _egot and _end as * hidden: */ .hidden _bss .hidden _ebss .hidden _got .hidden _egot + .hidden _end __HEAD ENTRY(startup_32) @@ -106,7 +107,7 @@ ENTRY(startup_32) notl %eax andl %eax, %ebx cmpl $LOAD_PHYSICAL_ADDR, %ebx - jge 1f + jae 1f #endif movl $LOAD_PHYSICAL_ADDR, %ebx 1: diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index 4eaa724afce3..474733f8b330 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -42,6 +42,7 @@ .hidden _ebss .hidden _got .hidden _egot + .hidden _end __HEAD .code32 @@ -106,7 +107,7 @@ ENTRY(startup_32) notl %eax andl %eax, %ebx cmpl $LOAD_PHYSICAL_ADDR, %ebx - jge 1f + jae 1f #endif movl $LOAD_PHYSICAL_ADDR, %ebx 1: @@ -297,7 +298,7 @@ ENTRY(startup_64) notq %rax andq %rax, %rbp cmpq $LOAD_PHYSICAL_ADDR, %rbp - jge 1f + jae 1f #endif movq $LOAD_PHYSICAL_ADDR, %rbp 1: diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig index 0eb9f92f3717..9218cb128661 100644 --- a/arch/x86/configs/i386_defconfig +++ b/arch/x86/configs/i386_defconfig @@ -149,7 +149,6 @@ CONFIG_CONNECTOR=y CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_SD=y CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=y CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_SPI_ATTRS=y @@ -217,7 +216,6 @@ CONFIG_FB_MODE_HELPERS=y CONFIG_FB_TILEBLITTING=y CONFIG_FB_EFI=y # CONFIG_LCD_CLASS_DEVICE is not set -CONFIG_VGACON_SOFT_SCROLLBACK=y CONFIG_LOGO=y # CONFIG_LOGO_LINUX_MONO is not set # CONFIG_LOGO_LINUX_VGA16 is not set @@ -247,6 +245,7 @@ CONFIG_USB_HIDDEV=y CONFIG_USB=y CONFIG_USB_ANNOUNCE_NEW_DEVICES=y CONFIG_USB_MON=y +CONFIG_USB_XHCI_HCD=y CONFIG_USB_EHCI_HCD=y CONFIG_USB_EHCI_TT_NEWSCHED=y CONFIG_USB_OHCI_HCD=y diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig index e32fc1f274d8..146a12293396 100644 --- a/arch/x86/configs/x86_64_defconfig +++ b/arch/x86/configs/x86_64_defconfig @@ -148,7 +148,6 @@ CONFIG_CONNECTOR=y CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_SD=y CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=y CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_SPI_ATTRS=y @@ -213,7 +212,6 @@ CONFIG_FB_MODE_HELPERS=y CONFIG_FB_TILEBLITTING=y CONFIG_FB_EFI=y # CONFIG_LCD_CLASS_DEVICE is not set -CONFIG_VGACON_SOFT_SCROLLBACK=y CONFIG_LOGO=y # CONFIG_LOGO_LINUX_MONO is not set # CONFIG_LOGO_LINUX_VGA16 is not set @@ -243,6 +241,7 @@ CONFIG_USB_HIDDEV=y CONFIG_USB=y CONFIG_USB_ANNOUNCE_NEW_DEVICES=y CONFIG_USB_MON=y +CONFIG_USB_XHCI_HCD=y CONFIG_USB_EHCI_HCD=y CONFIG_USB_EHCI_TT_NEWSCHED=y CONFIG_USB_OHCI_HCD=y diff --git a/arch/x86/crypto/aes_ctrby8_avx-x86_64.S b/arch/x86/crypto/aes_ctrby8_avx-x86_64.S index 5f6a5af9c489..77043a82da51 100644 --- a/arch/x86/crypto/aes_ctrby8_avx-x86_64.S +++ b/arch/x86/crypto/aes_ctrby8_avx-x86_64.S @@ -127,10 +127,6 @@ ddq_add_8: /* generate a unique variable for ddq_add_x */ -.macro setddq n - var_ddq_add = ddq_add_\n -.endm - /* generate a unique variable for xmm register */ .macro setxdata n var_xdata = %xmm\n @@ -140,9 +136,7 @@ ddq_add_8: .macro club name, id .altmacro - .if \name == DDQ_DATA - setddq %\id - .elseif \name == XDATA + .if \name == XDATA setxdata %\id .endif .noaltmacro @@ -165,9 +159,8 @@ ddq_add_8: .set i, 1 .rept (by - 1) - club DDQ_DATA, i club XDATA, i - vpaddq var_ddq_add(%rip), xcounter, var_xdata + vpaddq (ddq_add_1 + 16 * (i - 1))(%rip), xcounter, var_xdata vptest ddq_low_msk(%rip), var_xdata jnz 1f vpaddq ddq_high_add_1(%rip), var_xdata, var_xdata @@ -180,8 +173,7 @@ ddq_add_8: vmovdqa 1*16(p_keys), xkeyA vpxor xkey0, xdata0, xdata0 - club DDQ_DATA, by - vpaddq var_ddq_add(%rip), xcounter, xcounter + vpaddq (ddq_add_1 + 16 * (by - 1))(%rip), xcounter, xcounter vptest ddq_low_msk(%rip), xcounter jnz 1f vpaddq ddq_high_add_1(%rip), xcounter, xcounter diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S index cb2deb61c5d9..29b27f9a6e1e 100644 --- a/arch/x86/crypto/aesni-intel_asm.S +++ b/arch/x86/crypto/aesni-intel_asm.S @@ -270,7 +270,7 @@ ALL_F: .octa 0xffffffffffffffffffffffffffffffff PSHUFB_XMM %xmm2, %xmm0 movdqu %xmm0, CurCount(%arg2) # ctx_data.current_counter = iv - PRECOMPUTE \SUBKEY, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, + PRECOMPUTE \SUBKEY, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7 movdqu HashKey(%arg2), %xmm13 CALC_AAD_HASH %xmm13, \AAD, \AADLEN, %xmm0, %xmm1, %xmm2, %xmm3, \ @@ -982,7 +982,7 @@ _initial_blocks_done\@: * arg1, %arg3, %arg4 are used as pointers only, not modified * %r11 is the data offset value */ -.macro GHASH_4_ENCRYPT_4_PARALLEL_ENC TMP1 TMP2 TMP3 TMP4 TMP5 \ +.macro GHASH_4_ENCRYPT_4_PARALLEL_enc TMP1 TMP2 TMP3 TMP4 TMP5 \ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation movdqa \XMM1, \XMM5 @@ -1190,7 +1190,7 @@ aes_loop_par_enc_done\@: * arg1, %arg3, %arg4 are used as pointers only, not modified * %r11 is the data offset value */ -.macro GHASH_4_ENCRYPT_4_PARALLEL_DEC TMP1 TMP2 TMP3 TMP4 TMP5 \ +.macro GHASH_4_ENCRYPT_4_PARALLEL_dec TMP1 TMP2 TMP3 TMP4 TMP5 \ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation movdqa \XMM1, \XMM5 diff --git a/arch/x86/crypto/crc32c-pcl-intel-asm_64.S b/arch/x86/crypto/crc32c-pcl-intel-asm_64.S index d9b734d0c8cc..3c6e01520a97 100644 --- a/arch/x86/crypto/crc32c-pcl-intel-asm_64.S +++ b/arch/x86/crypto/crc32c-pcl-intel-asm_64.S @@ -170,7 +170,7 @@ continue_block: ## branch into array lea jump_table(%rip), bufp - movzxw (bufp, %rax, 2), len + movzwq (bufp, %rax, 2), len lea crc_array(%rip), bufp lea (bufp, len, 1), bufp JMP_NOSPEC bufp diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index 31fbb4a7d9f6..993dd06c8923 100644 --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -98,13 +98,6 @@ For 32-bit we have the following conventions - kernel is built with #define SIZEOF_PTREGS 21*8 .macro PUSH_AND_CLEAR_REGS rdx=%rdx rax=%rax save_ret=0 - /* - * Push registers and sanitize registers of values that a - * speculation attack might otherwise want to exploit. The - * lower registers are likely clobbered well before they - * could be put to use in a speculative execution gadget. - * Interleave XOR with PUSH for better uop scheduling: - */ .if \save_ret pushq %rsi /* pt_regs->si */ movq 8(%rsp), %rsi /* temporarily store the return address in %rsi */ @@ -114,34 +107,43 @@ For 32-bit we have the following conventions - kernel is built with pushq %rsi /* pt_regs->si */ .endif pushq \rdx /* pt_regs->dx */ - xorl %edx, %edx /* nospec dx */ pushq %rcx /* pt_regs->cx */ - xorl %ecx, %ecx /* nospec cx */ pushq \rax /* pt_regs->ax */ pushq %r8 /* pt_regs->r8 */ - xorl %r8d, %r8d /* nospec r8 */ pushq %r9 /* pt_regs->r9 */ - xorl %r9d, %r9d /* nospec r9 */ pushq %r10 /* pt_regs->r10 */ - xorl %r10d, %r10d /* nospec r10 */ pushq %r11 /* pt_regs->r11 */ - xorl %r11d, %r11d /* nospec r11*/ pushq %rbx /* pt_regs->rbx */ - xorl %ebx, %ebx /* nospec rbx*/ pushq %rbp /* pt_regs->rbp */ - xorl %ebp, %ebp /* nospec rbp*/ pushq %r12 /* pt_regs->r12 */ - xorl %r12d, %r12d /* nospec r12*/ pushq %r13 /* pt_regs->r13 */ - xorl %r13d, %r13d /* nospec r13*/ pushq %r14 /* pt_regs->r14 */ - xorl %r14d, %r14d /* nospec r14*/ pushq %r15 /* pt_regs->r15 */ - xorl %r15d, %r15d /* nospec r15*/ UNWIND_HINT_REGS + .if \save_ret pushq %rsi /* return address on top of stack */ .endif + + /* + * Sanitize registers of values that a speculation attack might + * otherwise want to exploit. The lower registers are likely clobbered + * well before they could be put to use in a speculative execution + * gadget. + */ + xorl %edx, %edx /* nospec dx */ + xorl %ecx, %ecx /* nospec cx */ + xorl %r8d, %r8d /* nospec r8 */ + xorl %r9d, %r9d /* nospec r9 */ + xorl %r10d, %r10d /* nospec r10 */ + xorl %r11d, %r11d /* nospec r11 */ + xorl %ebx, %ebx /* nospec rbx */ + xorl %ebp, %ebp /* nospec rbp */ + xorl %r12d, %r12d /* nospec r12 */ + xorl %r13d, %r13d /* nospec r13 */ + xorl %r14d, %r14d /* nospec r14 */ + xorl %r15d, %r15d /* nospec r15 */ + .endm .macro POP_REGS pop_rdi=1 skip_r11rcx=0 diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index d07432062ee6..37d9016d4768 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -1489,6 +1489,7 @@ ENTRY(int3) END(int3) ENTRY(general_protection) + ASM_CLAC pushl $do_general_protection jmp common_exception END(general_protection) diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index ccb5e3486aee..dfe26f3cfffc 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -312,7 +312,6 @@ GLOBAL(entry_SYSCALL_64_after_hwframe) */ syscall_return_via_sysret: /* rcx and r11 are already restored (see code above) */ - UNWIND_HINT_EMPTY POP_REGS pop_rdi=0 skip_r11rcx=1 /* @@ -321,6 +320,7 @@ syscall_return_via_sysret: */ movq %rsp, %rdi movq PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %rsp + UNWIND_HINT_EMPTY pushq RSP-RDI(%rdi) /* RSP */ pushq (%rdi) /* RDI */ @@ -575,7 +575,7 @@ END(spurious_entries_start) * +----------------------------------------------------+ */ ENTRY(interrupt_entry) - UNWIND_HINT_FUNC + UNWIND_HINT_IRET_REGS offset=16 ASM_CLAC cld @@ -607,9 +607,9 @@ ENTRY(interrupt_entry) pushq 5*8(%rdi) /* regs->eflags */ pushq 4*8(%rdi) /* regs->cs */ pushq 3*8(%rdi) /* regs->ip */ + UNWIND_HINT_IRET_REGS pushq 2*8(%rdi) /* regs->orig_ax */ pushq 8(%rdi) /* return address */ - UNWIND_HINT_FUNC movq (%rdi), %rdi jmp 2f @@ -700,6 +700,7 @@ GLOBAL(swapgs_restore_regs_and_return_to_usermode) */ movq %rsp, %rdi movq PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %rsp + UNWIND_HINT_EMPTY /* Copy the IRET frame to the trampoline stack. */ pushq 6*8(%rdi) /* SS */ @@ -1744,7 +1745,7 @@ ENTRY(rewind_stack_do_exit) movq PER_CPU_VAR(cpu_current_top_of_stack), %rax leaq -PTREGS_SIZE(%rax), %rsp - UNWIND_HINT_FUNC sp_offset=PTREGS_SIZE + UNWIND_HINT_REGS call do_exit END(rewind_stack_do_exit) diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c index 5b8b556dbb12..46caca4d9141 100644 --- a/arch/x86/entry/vdso/vma.c +++ b/arch/x86/entry/vdso/vma.c @@ -343,7 +343,7 @@ static void vgetcpu_cpu_init(void *arg) #ifdef CONFIG_NUMA node = cpu_to_node(cpu); #endif - if (static_cpu_has(X86_FEATURE_RDTSCP)) + if (boot_cpu_has(X86_FEATURE_RDTSCP) || boot_cpu_has(X86_FEATURE_RDPID)) write_rdtscp_aux((node << 12) | cpu); /* diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c index 07bf5517d9d8..2410bd4bb48f 100644 --- a/arch/x86/events/amd/ibs.c +++ b/arch/x86/events/amd/ibs.c @@ -89,6 +89,7 @@ struct perf_ibs { u64 max_period; unsigned long offset_mask[1]; int offset_max; + unsigned int fetch_count_reset_broken : 1; struct cpu_perf_ibs __percpu *pcpu; struct attribute **format_attrs; @@ -346,11 +347,15 @@ static u64 get_ibs_op_count(u64 config) { u64 count = 0; + /* + * If the internal 27-bit counter rolled over, the count is MaxCnt + * and the lower 7 bits of CurCnt are randomized. + * Otherwise CurCnt has the full 27-bit current counter value. + */ if (config & IBS_OP_VAL) - count += (config & IBS_OP_MAX_CNT) << 4; /* cnt rolled over */ - - if (ibs_caps & IBS_CAPS_RDWROPCNT) - count += (config & IBS_OP_CUR_CNT) >> 32; + count = (config & IBS_OP_MAX_CNT) << 4; + else if (ibs_caps & IBS_CAPS_RDWROPCNT) + count = (config & IBS_OP_CUR_CNT) >> 32; return count; } @@ -375,7 +380,12 @@ perf_ibs_event_update(struct perf_ibs *perf_ibs, struct perf_event *event, static inline void perf_ibs_enable_event(struct perf_ibs *perf_ibs, struct hw_perf_event *hwc, u64 config) { - wrmsrl(hwc->config_base, hwc->config | config | perf_ibs->enable_mask); + u64 tmp = hwc->config | config; + + if (perf_ibs->fetch_count_reset_broken) + wrmsrl(hwc->config_base, tmp & ~perf_ibs->enable_mask); + + wrmsrl(hwc->config_base, tmp | perf_ibs->enable_mask); } /* @@ -637,18 +647,24 @@ fail: perf_ibs->offset_max, offset + 1); } while (offset < offset_max); + /* + * Read IbsBrTarget, IbsOpData4, and IbsExtdCtl separately + * depending on their availability. + * Can't add to offset_max as they are staggered + */ if (event->attr.sample_type & PERF_SAMPLE_RAW) { - /* - * Read IbsBrTarget and IbsOpData4 separately - * depending on their availability. - * Can't add to offset_max as they are staggered - */ - if (ibs_caps & IBS_CAPS_BRNTRGT) { - rdmsrl(MSR_AMD64_IBSBRTARGET, *buf++); - size++; + if (perf_ibs == &perf_ibs_op) { + if (ibs_caps & IBS_CAPS_BRNTRGT) { + rdmsrl(MSR_AMD64_IBSBRTARGET, *buf++); + size++; + } + if (ibs_caps & IBS_CAPS_OPDATA4) { + rdmsrl(MSR_AMD64_IBSOPDATA4, *buf++); + size++; + } } - if (ibs_caps & IBS_CAPS_OPDATA4) { - rdmsrl(MSR_AMD64_IBSOPDATA4, *buf++); + if (perf_ibs == &perf_ibs_fetch && (ibs_caps & IBS_CAPS_FETCHCTLEXTD)) { + rdmsrl(MSR_AMD64_ICIBSEXTDCTL, *buf++); size++; } } @@ -744,6 +760,13 @@ static __init void perf_event_ibs_init(void) { struct attribute **attr = ibs_op_format_attrs; + /* + * Some chips fail to reset the fetch count when it is written; instead + * they need a 0-1 transition of IbsFetchEn. + */ + if (boot_cpu_data.x86 >= 0x16 && boot_cpu_data.x86 <= 0x18) + perf_ibs_fetch.fetch_count_reset_broken = 1; + perf_ibs_pmu_init(&perf_ibs_fetch, "ibs_fetch"); if (ibs_caps & IBS_CAPS_OPCNT) { diff --git a/arch/x86/events/amd/iommu.c b/arch/x86/events/amd/iommu.c index 3210fee27e7f..c08bcba5c3a9 100644 --- a/arch/x86/events/amd/iommu.c +++ b/arch/x86/events/amd/iommu.c @@ -84,12 +84,12 @@ static struct attribute_group amd_iommu_events_group = { }; struct amd_iommu_event_desc { - struct kobj_attribute attr; + struct device_attribute attr; const char *event; }; -static ssize_t _iommu_event_show(struct kobject *kobj, - struct kobj_attribute *attr, char *buf) +static ssize_t _iommu_event_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct amd_iommu_event_desc *event = container_of(attr, struct amd_iommu_event_desc, attr); @@ -387,7 +387,7 @@ static __init int _init_events_attrs(void) while (amd_iommu_v2_event_descs[i].attr.attr.name) i++; - attrs = kcalloc(i + 1, sizeof(struct attribute **), GFP_KERNEL); + attrs = kcalloc(i + 1, sizeof(*attrs), GFP_KERNEL); if (!attrs) return -ENOMEM; diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c index 4a650eb3d94a..3b3cd12c0692 100644 --- a/arch/x86/events/intel/cstate.c +++ b/arch/x86/events/intel/cstate.c @@ -100,14 +100,14 @@ MODULE_LICENSE("GPL"); #define DEFINE_CSTATE_FORMAT_ATTR(_var, _name, _format) \ -static ssize_t __cstate_##_var##_show(struct kobject *kobj, \ - struct kobj_attribute *attr, \ +static ssize_t __cstate_##_var##_show(struct device *dev, \ + struct device_attribute *attr, \ char *page) \ { \ BUILD_BUG_ON(sizeof(_format) >= PAGE_SIZE); \ return sprintf(page, _format "\n"); \ } \ -static struct kobj_attribute format_attr_##_var = \ +static struct device_attribute format_attr_##_var = \ __ATTR(_name, 0444, __cstate_##_var##_show, NULL) static ssize_t cstate_get_attr_cpumask(struct device *dev, diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index 79caeba8b6f0..b3279feff458 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -1557,7 +1557,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) */ if (!pebs_status && cpuc->pebs_enabled && !(cpuc->pebs_enabled & (cpuc->pebs_enabled-1))) - pebs_status = cpuc->pebs_enabled; + pebs_status = p->status = cpuc->pebs_enabled; bit = find_first_bit((unsigned long *)&pebs_status, x86_pmu.max_pebs_events); diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c index 2413169ce362..bc348663da94 100644 --- a/arch/x86/events/intel/rapl.c +++ b/arch/x86/events/intel/rapl.c @@ -115,18 +115,6 @@ static const char *const rapl_domain_names[NR_RAPL_DOMAINS] __initconst = { * any other bit is reserved */ #define RAPL_EVENT_MASK 0xFFULL - -#define DEFINE_RAPL_FORMAT_ATTR(_var, _name, _format) \ -static ssize_t __rapl_##_var##_show(struct kobject *kobj, \ - struct kobj_attribute *attr, \ - char *page) \ -{ \ - BUILD_BUG_ON(sizeof(_format) >= PAGE_SIZE); \ - return sprintf(page, _format "\n"); \ -} \ -static struct kobj_attribute format_attr_##_var = \ - __ATTR(_name, 0444, __rapl_##_var##_show, NULL) - #define RAPL_CNTR_WIDTH 32 #define RAPL_EVENT_ATTR_STR(_name, v, str) \ @@ -548,7 +536,7 @@ static struct attribute_group rapl_pmu_events_group = { .attrs = NULL, /* patched at runtime */ }; -DEFINE_RAPL_FORMAT_ATTR(event, event, "config:0-7"); +PMU_FORMAT_ATTR(event, "config:0-7"); static struct attribute *rapl_formats_attr[] = { &format_attr_event.attr, NULL, diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index 7098b9b05d56..2f4ed5aa08ba 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -90,8 +90,8 @@ end: return map; } -ssize_t uncore_event_show(struct kobject *kobj, - struct kobj_attribute *attr, char *buf) +ssize_t uncore_event_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct uncore_event_desc *event = container_of(attr, struct uncore_event_desc, attr); diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h index 40e040ec31b5..0fc86ac73b51 100644 --- a/arch/x86/events/intel/uncore.h +++ b/arch/x86/events/intel/uncore.h @@ -133,7 +133,7 @@ struct intel_uncore_box { #define UNCORE_BOX_FLAG_CTL_OFFS8 1 /* event config registers are 8-byte apart */ struct uncore_event_desc { - struct kobj_attribute attr; + struct device_attribute attr; const char *config; }; @@ -153,8 +153,8 @@ struct pci2phy_map { struct pci2phy_map *__find_pci2phy_map(int segment); -ssize_t uncore_event_show(struct kobject *kobj, - struct kobj_attribute *attr, char *buf); +ssize_t uncore_event_show(struct device *dev, + struct device_attribute *attr, char *buf); #define INTEL_UNCORE_EVENT_DESC(_name, _config) \ { \ @@ -163,14 +163,14 @@ ssize_t uncore_event_show(struct kobject *kobj, } #define DEFINE_UNCORE_FORMAT_ATTR(_var, _name, _format) \ -static ssize_t __uncore_##_var##_show(struct kobject *kobj, \ - struct kobj_attribute *attr, \ +static ssize_t __uncore_##_var##_show(struct device *dev, \ + struct device_attribute *attr, \ char *page) \ { \ BUILD_BUG_ON(sizeof(_format) >= PAGE_SIZE); \ return sprintf(page, _format "\n"); \ } \ -static struct kobj_attribute format_attr_##_var = \ +static struct device_attribute format_attr_##_var = \ __ATTR(_name, 0444, __uncore_##_var##_show, NULL) static inline bool uncore_pmc_fixed(int idx) diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index 8e4e8e423839..c06074b847fa 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -1030,7 +1030,6 @@ enum { SNBEP_PCI_QPI_PORT0_FILTER, SNBEP_PCI_QPI_PORT1_FILTER, BDX_PCI_QPI_PORT2_FILTER, - HSWEP_PCI_PCU_3, }; static int snbep_qpi_hw_config(struct intel_uncore_box *box, struct perf_event *event) @@ -2687,22 +2686,33 @@ static struct intel_uncore_type *hswep_msr_uncores[] = { NULL, }; -void hswep_uncore_cpu_init(void) +#define HSWEP_PCU_DID 0x2fc0 +#define HSWEP_PCU_CAPID4_OFFET 0x94 +#define hswep_get_chop(_cap) (((_cap) >> 6) & 0x3) + +static bool hswep_has_limit_sbox(unsigned int device) { - int pkg = boot_cpu_data.logical_proc_id; + struct pci_dev *dev = pci_get_device(PCI_VENDOR_ID_INTEL, device, NULL); + u32 capid4; + + if (!dev) + return false; + + pci_read_config_dword(dev, HSWEP_PCU_CAPID4_OFFET, &capid4); + if (!hswep_get_chop(capid4)) + return true; + return false; +} + +void hswep_uncore_cpu_init(void) +{ if (hswep_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores) hswep_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores; /* Detect 6-8 core systems with only two SBOXes */ - if (uncore_extra_pci_dev[pkg].dev[HSWEP_PCI_PCU_3]) { - u32 capid4; - - pci_read_config_dword(uncore_extra_pci_dev[pkg].dev[HSWEP_PCI_PCU_3], - 0x94, &capid4); - if (((capid4 >> 6) & 0x3) == 0) - hswep_uncore_sbox.num_boxes = 2; - } + if (hswep_has_limit_sbox(HSWEP_PCU_DID)) + hswep_uncore_sbox.num_boxes = 2; uncore_msr_uncores = hswep_msr_uncores; } @@ -2965,11 +2975,6 @@ static const struct pci_device_id hswep_uncore_pci_ids[] = { .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, SNBEP_PCI_QPI_PORT1_FILTER), }, - { /* PCU.3 (for Capability registers) */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2fc0), - .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, - HSWEP_PCI_PCU_3), - }, { /* end: all zeroes */ } }; @@ -3061,27 +3066,18 @@ static struct event_constraint bdx_uncore_pcu_constraints[] = { EVENT_CONSTRAINT_END }; +#define BDX_PCU_DID 0x6fc0 + void bdx_uncore_cpu_init(void) { - int pkg = topology_phys_to_logical_pkg(boot_cpu_data.phys_proc_id); - if (bdx_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores) bdx_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores; uncore_msr_uncores = bdx_msr_uncores; - /* BDX-DE doesn't have SBOX */ - if (boot_cpu_data.x86_model == 86) { - uncore_msr_uncores[BDX_MSR_UNCORE_SBOX] = NULL; /* Detect systems with no SBOXes */ - } else if (uncore_extra_pci_dev[pkg].dev[HSWEP_PCI_PCU_3]) { - struct pci_dev *pdev; - u32 capid4; - - pdev = uncore_extra_pci_dev[pkg].dev[HSWEP_PCI_PCU_3]; - pci_read_config_dword(pdev, 0x94, &capid4); - if (((capid4 >> 6) & 0x3) == 0) - bdx_msr_uncores[BDX_MSR_UNCORE_SBOX] = NULL; - } + if ((boot_cpu_data.x86_model == 86) || hswep_has_limit_sbox(BDX_PCU_DID)) + uncore_msr_uncores[BDX_MSR_UNCORE_SBOX] = NULL; + hswep_uncore_pcu.constraints = bdx_uncore_pcu_constraints; } @@ -3302,11 +3298,6 @@ static const struct pci_device_id bdx_uncore_pci_ids[] = { .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, BDX_PCI_QPI_PORT2_FILTER), }, - { /* PCU.3 (for Capability registers) */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fc0), - .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, - HSWEP_PCI_PCU_3), - }, { /* end: all zeroes */ } }; diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index 8a9cff1f129d..1663ad84778b 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -30,6 +30,7 @@ #include <linux/clockchips.h> #include <linux/hyperv.h> #include <linux/slab.h> +#include <linux/kernel.h> #include <linux/cpuhotplug.h> #ifdef CONFIG_HYPERV_TSCPAGE @@ -427,11 +428,14 @@ void hyperv_cleanup(void) } EXPORT_SYMBOL_GPL(hyperv_cleanup); -void hyperv_report_panic(struct pt_regs *regs, long err) +void hyperv_report_panic(struct pt_regs *regs, long err, bool in_die) { static bool panic_reported; u64 guest_id; + if (in_die && !panic_on_oops) + return; + /* * We prefer to report panic on 'die' chain as we have proper * registers to report, but if we miss it (e.g. on BUG()) we need diff --git a/arch/x86/hyperv/mmu.c b/arch/x86/hyperv/mmu.c index 2f34d5275352..e666f7eaf32d 100644 --- a/arch/x86/hyperv/mmu.c +++ b/arch/x86/hyperv/mmu.c @@ -66,11 +66,17 @@ static void hyperv_flush_tlb_others(const struct cpumask *cpus, if (!hv_hypercall_pg) goto do_native; - if (cpumask_empty(cpus)) - return; - local_irq_save(flags); + /* + * Only check the mask _after_ interrupt has been disabled to avoid the + * mask changing under our feet. + */ + if (cpumask_empty(cpus)) { + local_irq_restore(flags); + return; + } + flush_pcpu = (struct hv_tlb_flush **) this_cpu_ptr(hyperv_pcpu_input_arg); diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index 3c1e51ead072..b5354e216b07 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -190,16 +190,6 @@ static inline void lapic_assign_legacy_vector(unsigned int i, bool r) { } #endif /* !CONFIG_X86_LOCAL_APIC */ #ifdef CONFIG_X86_X2APIC -/* - * Make previous memory operations globally visible before - * sending the IPI through x2apic wrmsr. We need a serializing instruction or - * mfence for this. - */ -static inline void x2apic_wrmsr_fence(void) -{ - asm volatile("mfence" : : : "memory"); -} - static inline void native_apic_msr_write(u32 reg, u32 v) { if (reg == APIC_DFR || reg == APIC_ID || reg == APIC_LDR || @@ -252,6 +242,7 @@ static inline u64 native_x2apic_icr_read(void) extern int x2apic_mode; extern int x2apic_phys; +extern void __init x2apic_set_max_apicid(u32 apicid); extern void __init check_x2apic(void); extern void x2apic_setup(void); static inline int x2apic_enabled(void) diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h index 84f848c2541a..dd22cffc6b3f 100644 --- a/arch/x86/include/asm/barrier.h +++ b/arch/x86/include/asm/barrier.h @@ -85,4 +85,22 @@ do { \ #include <asm-generic/barrier.h> +/* + * Make previous memory operations globally visible before + * a WRMSR. + * + * MFENCE makes writes visible, but only affects load/store + * instructions. WRMSR is unfortunately not a load/store + * instruction and is unaffected by MFENCE. The LFENCE ensures + * that the WRMSR is not reordered. + * + * Most WRMSRs are full serializing instructions themselves and + * do not require this barrier. This is only required for the + * IA32_TSC_DEADLINE and X2APIC MSRs. + */ +static inline void weak_wrmsr_fence(void) +{ + asm volatile("mfence; lfence" : : : "memory"); +} + #endif /* _ASM_X86_BARRIER_H */ diff --git a/arch/x86/include/asm/cpu_device_id.h b/arch/x86/include/asm/cpu_device_id.h index baeba0567126..884466592943 100644 --- a/arch/x86/include/asm/cpu_device_id.h +++ b/arch/x86/include/asm/cpu_device_id.h @@ -9,6 +9,33 @@ #include <linux/mod_devicetable.h> +#define X86_STEPPINGS(mins, maxs) GENMASK(maxs, mins) + +/** + * X86_MATCH_VENDOR_FAM_MODEL_STEPPINGS_FEATURE - Base macro for CPU matching + * @_vendor: The vendor name, e.g. INTEL, AMD, HYGON, ..., ANY + * The name is expanded to X86_VENDOR_@_vendor + * @_family: The family number or X86_FAMILY_ANY + * @_model: The model number, model constant or X86_MODEL_ANY + * @_steppings: Bitmask for steppings, stepping constant or X86_STEPPING_ANY + * @_feature: A X86_FEATURE bit or X86_FEATURE_ANY + * @_data: Driver specific data or NULL. The internal storage + * format is unsigned long. The supplied value, pointer + * etc. is casted to unsigned long internally. + * + * Backport version to keep the SRBDS pile consistant. No shorter variants + * required for this. + */ +#define X86_MATCH_VENDOR_FAM_MODEL_STEPPINGS_FEATURE(_vendor, _family, _model, \ + _steppings, _feature, _data) { \ + .vendor = X86_VENDOR_##_vendor, \ + .family = _family, \ + .model = _model, \ + .steppings = _steppings, \ + .feature = _feature, \ + .driver_data = (unsigned long) _data \ +} + extern const struct x86_cpu_id *x86_match_cpu(const struct x86_cpu_id *match); #endif diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 8c13b99b9507..f7f9604b10cc 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -291,6 +291,7 @@ #define X86_FEATURE_AMD_IBPB (13*32+12) /* "" Indirect Branch Prediction Barrier */ #define X86_FEATURE_AMD_IBRS (13*32+14) /* "" Indirect Branch Restricted Speculation */ #define X86_FEATURE_AMD_STIBP (13*32+15) /* "" Single Thread Indirect Branch Predictors */ +#define X86_FEATURE_AMD_STIBP_ALWAYS_ON (13*32+17) /* "" Single Thread Indirect Branch Predictors always-on preferred */ #define X86_FEATURE_AMD_SSBD (13*32+24) /* "" Speculative Store Bypass Disable */ #define X86_FEATURE_VIRT_SSBD (13*32+25) /* Virtualized Speculative Store Bypass Disable */ #define X86_FEATURE_AMD_SSB_NO (13*32+26) /* "" Speculative Store Bypass is fixed in hardware. */ @@ -347,6 +348,7 @@ /* Intel-defined CPU features, CPUID level 0x00000007:0 (EDX), word 18 */ #define X86_FEATURE_AVX512_4VNNIW (18*32+ 2) /* AVX-512 Neural Network Instructions */ #define X86_FEATURE_AVX512_4FMAPS (18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */ +#define X86_FEATURE_SRBDS_CTRL (18*32+ 9) /* "" SRBDS mitigation MSR available */ #define X86_FEATURE_TSX_FORCE_ABORT (18*32+13) /* "" TSX_FORCE_ABORT */ #define X86_FEATURE_MD_CLEAR (18*32+10) /* VERW clears CPU buffers */ #define X86_FEATURE_PCONFIG (18*32+18) /* Intel PCONFIG */ @@ -391,5 +393,6 @@ #define X86_BUG_SWAPGS X86_BUG(21) /* CPU is affected by speculation through SWAPGS */ #define X86_BUG_TAA X86_BUG(22) /* CPU is affected by TSX Async Abort(TAA) */ #define X86_BUG_ITLB_MULTIHIT X86_BUG(23) /* CPU may incur MCE during certain page attribute changes */ +#define X86_BUG_SRBDS X86_BUG(24) /* CPU may leak RNG bits if not mitigated */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/include/asm/dma.h b/arch/x86/include/asm/dma.h index 00f7cf45e699..8e95aa4b0d17 100644 --- a/arch/x86/include/asm/dma.h +++ b/arch/x86/include/asm/dma.h @@ -74,7 +74,7 @@ #define MAX_DMA_PFN ((16UL * 1024 * 1024) >> PAGE_SHIFT) /* 4GB broken PCI/AGP hardware bus master zone */ -#define MAX_DMA32_PFN ((4UL * 1024 * 1024 * 1024) >> PAGE_SHIFT) +#define MAX_DMA32_PFN (1UL << (32 - PAGE_SHIFT)) #ifdef CONFIG_X86_32 /* The maximum address that we can perform a DMA transfer to on this platform */ diff --git a/arch/x86/include/asm/insn.h b/arch/x86/include/asm/insn.h index c2c01f84df75..3e0e18d376d2 100644 --- a/arch/x86/include/asm/insn.h +++ b/arch/x86/include/asm/insn.h @@ -208,6 +208,21 @@ static inline int insn_offset_immediate(struct insn *insn) return insn_offset_displacement(insn) + insn->displacement.nbytes; } +/** + * for_each_insn_prefix() -- Iterate prefixes in the instruction + * @insn: Pointer to struct insn. + * @idx: Index storage. + * @prefix: Prefix byte. + * + * Iterate prefix bytes of given @insn. Each prefix byte is stored in @prefix + * and the index is stored in @idx (note that this @idx is just for a cursor, + * do not change it.) + * Since prefixes.nbytes can be bigger than 4 if some prefixes + * are repeated, it cannot be used for looping over the prefixes. + */ +#define for_each_insn_prefix(insn, idx, prefix) \ + for (idx = 0; idx < ARRAY_SIZE(insn->prefixes.bytes) && (prefix = insn->prefixes.bytes[idx]) != 0; idx++) + #define POP_SS_OPCODE 0x1f #define MOV_SREG_OPCODE 0x8e diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 067288d4ef6e..98b74711e6b7 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -622,10 +622,10 @@ struct kvm_vcpu_arch { bool pvclock_set_guest_stopped_request; struct { + u8 preempted; u64 msr_val; u64 last_steal; - struct gfn_to_hva_cache stime; - struct kvm_steal_time steal; + struct gfn_to_pfn_cache cache; } st; u64 tsc_offset; @@ -1070,7 +1070,7 @@ struct kvm_x86_ops { bool (*xsaves_supported)(void); bool (*umip_emulated)(void); - int (*check_nested_events)(struct kvm_vcpu *vcpu, bool external_intr); + int (*check_nested_events)(struct kvm_vcpu *vcpu); void (*request_immediate_exit)(struct kvm_vcpu *vcpu); void (*sched_in)(struct kvm_vcpu *kvm, int cpu); @@ -1099,7 +1099,7 @@ struct kvm_x86_ops { void (*enable_log_dirty_pt_masked)(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t offset, unsigned long mask); - int (*write_log_dirty)(struct kvm_vcpu *vcpu); + int (*write_log_dirty)(struct kvm_vcpu *vcpu, gpa_t l2_gpa); /* pmu operations of sub-arch */ const struct kvm_pmu_ops *pmu_ops; @@ -1465,12 +1465,14 @@ asmlinkage void __noreturn kvm_spurious_fault(void); ____kvm_handle_fault_on_reboot(insn, "") #define KVM_ARCH_WANT_MMU_NOTIFIER -int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end); +int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end, + bool blockable); int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end); int kvm_test_age_hva(struct kvm *kvm, unsigned long hva); void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v); int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu); +int kvm_cpu_has_extint(struct kvm_vcpu *v); int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu); int kvm_cpu_get_interrupt(struct kvm_vcpu *v); void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event); diff --git a/arch/x86/include/asm/microcode_amd.h b/arch/x86/include/asm/microcode_amd.h index 209492849566..5c524d4f71cd 100644 --- a/arch/x86/include/asm/microcode_amd.h +++ b/arch/x86/include/asm/microcode_amd.h @@ -41,7 +41,7 @@ struct microcode_amd { unsigned int mpb[0]; }; -#define PATCH_MAX_SIZE PAGE_SIZE +#define PATCH_MAX_SIZE (3 * PAGE_SIZE) #ifdef CONFIG_MICROCODE_AMD extern void __init load_ucode_amd_bsp(unsigned int family); diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index f37704497d8f..5b58a6cf487f 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -338,7 +338,7 @@ static inline int cpumask_to_vpset(struct hv_vpset *vpset, void __init hyperv_init(void); void hyperv_setup_mmu_ops(void); -void hyperv_report_panic(struct pt_regs *regs, long err); +void hyperv_report_panic(struct pt_regs *regs, long err, bool in_die); void hyperv_report_panic_msg(phys_addr_t pa, size_t size); bool hv_is_hyperv_initialized(void); void hyperv_cleanup(void); diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index d2c25a13e1ce..892af8ab95d7 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -110,6 +110,10 @@ #define TSX_CTRL_RTM_DISABLE BIT(0) /* Disable RTM feature */ #define TSX_CTRL_CPUID_CLEAR BIT(1) /* Disable TSX enumeration */ +/* SRBDS support */ +#define MSR_IA32_MCU_OPT_CTRL 0x00000123 +#define RNGDS_MITG_DIS BIT(0) + #define MSR_IA32_SYSENTER_CS 0x00000174 #define MSR_IA32_SYSENTER_ESP 0x00000175 #define MSR_IA32_SYSENTER_EIP 0x00000176 @@ -373,6 +377,7 @@ #define MSR_AMD64_IBSOP_REG_MASK ((1UL<<MSR_AMD64_IBSOP_REG_COUNT)-1) #define MSR_AMD64_IBSCTL 0xc001103a #define MSR_AMD64_IBSBRTARGET 0xc001103b +#define MSR_AMD64_ICIBSEXTDCTL 0xc001103c #define MSR_AMD64_IBSOPDATA4 0xc001103d #define MSR_AMD64_IBS_REG_COUNT_MAX 8 /* includes MSR_AMD64_IBSBRTARGET */ #define MSR_AMD64_SEV 0xc0010131 diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h index 04addd6e0a4a..2571e2017a8b 100644 --- a/arch/x86/include/asm/msr.h +++ b/arch/x86/include/asm/msr.h @@ -88,7 +88,7 @@ static inline void do_trace_rdpmc(unsigned int msr, u64 val, int failed) {} * think of extending them - you will be slapped with a stinking trout or a frozen * shark will reach you, wherever you are! You've been warned. */ -static inline unsigned long long notrace __rdmsr(unsigned int msr) +static __always_inline unsigned long long __rdmsr(unsigned int msr) { DECLARE_ARGS(val, low, high); @@ -100,7 +100,7 @@ static inline unsigned long long notrace __rdmsr(unsigned int msr) return EAX_EDX_VAL(val, low, high); } -static inline void notrace __wrmsr(unsigned int msr, u32 low, u32 high) +static __always_inline void __wrmsr(unsigned int msr, u32 low, u32 high) { asm volatile("1: wrmsr\n" "2:\n" diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 09c7466c4880..62f9903544b5 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -232,6 +232,7 @@ enum spectre_v2_mitigation { enum spectre_v2_user_mitigation { SPECTRE_V2_USER_NONE, SPECTRE_V2_USER_STRICT, + SPECTRE_V2_USER_STRICT_PREFERRED, SPECTRE_V2_USER_PRCTL, SPECTRE_V2_USER_SECCOMP, }; @@ -329,7 +330,7 @@ DECLARE_STATIC_KEY_FALSE(mds_idle_clear); * combination with microcode which triggers a CPU buffer flush when the * instruction is executed. */ -static inline void mds_clear_cpu_buffers(void) +static __always_inline void mds_clear_cpu_buffers(void) { static const u16 ds = __KERNEL_DS; @@ -350,7 +351,7 @@ static inline void mds_clear_cpu_buffers(void) * * Clear CPU buffers if the corresponding static key is enabled */ -static inline void mds_user_clear_cpu_buffers(void) +static __always_inline void mds_user_clear_cpu_buffers(void) { if (static_branch_likely(&mds_user_clear)) mds_clear_cpu_buffers(); diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 690c0307afed..2a9c12ffb5cb 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -237,6 +237,7 @@ static inline int pmd_large(pmd_t pte) } #ifdef CONFIG_TRANSPARENT_HUGEPAGE +/* NOTE: when predicate huge page, consider also pmd_devmap, or use pmd_large */ static inline int pmd_trans_huge(pmd_t pmd) { return (pmd_val(pmd) & (_PAGE_PSE|_PAGE_DEVMAP)) == _PAGE_PSE; @@ -608,12 +609,15 @@ static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot) return __pmd(val); } -/* mprotect needs to preserve PAT bits when updating vm_page_prot */ +/* + * mprotect needs to preserve PAT and encryption bits when updating + * vm_page_prot + */ #define pgprot_modify pgprot_modify static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot) { pgprotval_t preservebits = pgprot_val(oldprot) & _PAGE_CHG_MASK; - pgprotval_t addbits = pgprot_val(newprot); + pgprotval_t addbits = pgprot_val(newprot) & ~_PAGE_CHG_MASK; return __pgprot(preservebits | addbits); } diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index 106b7d0e2dae..02806d95ad6e 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -124,7 +124,7 @@ */ #define _PAGE_CHG_MASK (PTE_PFN_MASK | _PAGE_PCD | _PAGE_PWT | \ _PAGE_SPECIAL | _PAGE_ACCESSED | _PAGE_DIRTY | \ - _PAGE_SOFT_DIRTY | _PAGE_DEVMAP) + _PAGE_SOFT_DIRTY | _PAGE_DEVMAP | _PAGE_ENC) #define _HPAGE_CHG_MASK (_PAGE_CHG_MASK | _PAGE_PSE) /* @@ -148,6 +148,7 @@ enum page_cache_mode { #endif #define _PAGE_CACHE_MASK (_PAGE_PAT | _PAGE_PCD | _PAGE_PWT) +#define _PAGE_LARGE_CACHE_MASK (_PAGE_PWT | _PAGE_PCD | _PAGE_PAT_LARGE) #define _PAGE_NOCACHE (cachemode2protval(_PAGE_CACHE_MODE_UC)) #define _PAGE_CACHE_WP (cachemode2protval(_PAGE_CACHE_MODE_WP)) diff --git a/arch/x86/include/asm/pkeys.h b/arch/x86/include/asm/pkeys.h index 19b137f1b3be..2ff9b98812b7 100644 --- a/arch/x86/include/asm/pkeys.h +++ b/arch/x86/include/asm/pkeys.h @@ -4,6 +4,11 @@ #define ARCH_DEFAULT_PKEY 0 +/* + * If more than 16 keys are ever supported, a thorough audit + * will be necessary to ensure that the types that store key + * numbers and masks have sufficient capacity. + */ #define arch_max_pkey() (boot_cpu_has(X86_FEATURE_OSPKE) ? 16 : 1) extern int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index efb44bd3a714..cc4bb218f1c6 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -336,7 +336,7 @@ struct x86_hw_tss { #define INVALID_IO_BITMAP_OFFSET 0x8000 struct entry_stack { - unsigned long words[64]; + char stack[PAGE_SIZE]; }; struct entry_stack_page { @@ -522,15 +522,6 @@ static inline void arch_thread_struct_whitelist(unsigned long *offset, } /* - * Thread-synchronous status. - * - * This is different from the flags in that nobody else - * ever touches our thread-synchronous status, so we don't - * have to worry about atomic accesses. - */ -#define TS_COMPAT 0x0002 /* 32bit syscall active (64BIT)*/ - -/* * Set IOPL bits in EFLAGS from given mask */ static inline void native_set_iopl_mask(unsigned mask) diff --git a/arch/x86/include/asm/set_memory.h b/arch/x86/include/asm/set_memory.h index 07a25753e85c..bc97b8c0fdf7 100644 --- a/arch/x86/include/asm/set_memory.h +++ b/arch/x86/include/asm/set_memory.h @@ -90,28 +90,35 @@ void set_kernel_text_rw(void); void set_kernel_text_ro(void); #ifdef CONFIG_X86_64 -static inline int set_mce_nospec(unsigned long pfn) +/* + * Prevent speculative access to the page by either unmapping + * it (if we do not require access to any part of the page) or + * marking it uncacheable (if we want to try to retrieve data + * from non-poisoned lines in the page). + */ +static inline int set_mce_nospec(unsigned long pfn, bool unmap) { unsigned long decoy_addr; int rc; /* - * Mark the linear address as UC to make sure we don't log more - * errors because of speculative access to the page. * We would like to just call: - * set_memory_uc((unsigned long)pfn_to_kaddr(pfn), 1); + * set_memory_XX((unsigned long)pfn_to_kaddr(pfn), 1); * but doing that would radically increase the odds of a * speculative access to the poison page because we'd have * the virtual address of the kernel 1:1 mapping sitting * around in registers. * Instead we get tricky. We create a non-canonical address * that looks just like the one we want, but has bit 63 flipped. - * This relies on set_memory_uc() properly sanitizing any __pa() + * This relies on set_memory_XX() properly sanitizing any __pa() * results with __PHYSICAL_MASK or PTE_PFN_MASK. */ decoy_addr = (pfn << PAGE_SHIFT) + (PAGE_OFFSET ^ BIT(63)); - rc = set_memory_uc(decoy_addr, 1); + if (unmap) + rc = set_memory_np(decoy_addr, 1); + else + rc = set_memory_uc(decoy_addr, 1); if (rc) pr_warn("Could not invalidate pfn=0x%lx from 1:1 map\n", pfn); return rc; diff --git a/arch/x86/include/asm/stackprotector.h b/arch/x86/include/asm/stackprotector.h index 8ec97a62c245..9c556ea2eaa7 100644 --- a/arch/x86/include/asm/stackprotector.h +++ b/arch/x86/include/asm/stackprotector.h @@ -55,8 +55,13 @@ /* * Initialize the stackprotector canary value. * - * NOTE: this must only be called from functions that never return, + * NOTE: this must only be called from functions that never return * and it must always be inlined. + * + * In addition, it should be called from a compilation unit for which + * stack protector is disabled. Alternatively, the caller should not end + * with a function call which gets tail-call optimized as that would + * lead to checking a modified canary value. */ static __always_inline void boot_init_stack_canary(void) { diff --git a/arch/x86/include/asm/sync_core.h b/arch/x86/include/asm/sync_core.h index c67caafd3381..43b5e02a7b4b 100644 --- a/arch/x86/include/asm/sync_core.h +++ b/arch/x86/include/asm/sync_core.h @@ -16,12 +16,13 @@ static inline void sync_core_before_usermode(void) /* With PTI, we unconditionally serialize before running user code. */ if (static_cpu_has(X86_FEATURE_PTI)) return; + /* - * Return from interrupt and NMI is done through iret, which is core - * serializing. + * Even if we're in an interrupt, we might reschedule before returning, + * in which case we could switch to a different thread in the same mm + * and return using SYSRET or SYSEXIT. Instead of trying to keep + * track of our need to sync the core, just sync right away. */ - if (in_irq() || in_nmi()) - return; sync_core(); } diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index 82b73b75d67c..b5e4c357523e 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -227,10 +227,31 @@ static inline int arch_within_stack_frames(const void * const stack, #endif +/* + * Thread-synchronous status. + * + * This is different from the flags in that nobody else + * ever touches our thread-synchronous status, so we don't + * have to worry about atomic accesses. + */ +#define TS_COMPAT 0x0002 /* 32bit syscall active (64BIT)*/ + +#ifndef __ASSEMBLY__ #ifdef CONFIG_COMPAT #define TS_I386_REGS_POKED 0x0004 /* regs poked by 32-bit ptracer */ +#define TS_COMPAT_RESTART 0x0008 + +#define arch_set_restart_data arch_set_restart_data + +static inline void arch_set_restart_data(struct restart_block *restart) +{ + struct thread_info *ti = current_thread_info(); + if (ti->status & TS_COMPAT) + ti->status |= TS_COMPAT_RESTART; + else + ti->status &= ~TS_COMPAT_RESTART; +} #endif -#ifndef __ASSEMBLY__ #ifdef CONFIG_X86_32 #define in_ia32_syscall() true diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index 971830341061..82b0ff6cac97 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -711,7 +711,17 @@ extern struct movsl_mask { * checking before using them, but you have to surround them with the * user_access_begin/end() pair. */ -#define user_access_begin() __uaccess_begin() +static __must_check inline bool user_access_begin(int type, + const void __user *ptr, + size_t len) +{ + if (unlikely(!access_ok(type, ptr, len))) + return 0; + __uaccess_begin_nospec(); + return 1; +} + +#define user_access_begin(a, b, c) user_access_begin(a, b, c) #define user_access_end() __uaccess_end() #define unsafe_put_user(x, ptr, err_label) \ diff --git a/arch/x86/include/asm/unwind.h b/arch/x86/include/asm/unwind.h index 499578f7e6d7..70fc159ebe69 100644 --- a/arch/x86/include/asm/unwind.h +++ b/arch/x86/include/asm/unwind.h @@ -19,7 +19,7 @@ struct unwind_state { #if defined(CONFIG_UNWINDER_ORC) bool signal, full_regs; unsigned long sp, bp, ip; - struct pt_regs *regs; + struct pt_regs *regs, *prev_regs; #elif defined(CONFIG_UNWINDER_FRAME_POINTER) bool got_irq; unsigned long *bp, *orig_sp, ip; diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 3b20607d581b..b35c34cfbe52 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -1565,10 +1565,18 @@ void __init acpi_boot_table_init(void) /* * Initialize the ACPI boot-time table parser. */ - if (acpi_table_init()) { + if (acpi_locate_initial_tables()) disable_acpi(); - return; - } + else + acpi_reserve_initial_tables(); +} + +int __init early_acpi_boot_init(void) +{ + if (acpi_disabled) + return 1; + + acpi_table_init_complete(); acpi_table_parse(ACPI_SIG_BOOT, acpi_parse_sbf); @@ -1581,18 +1589,9 @@ void __init acpi_boot_table_init(void) } else { printk(KERN_WARNING PREFIX "Disabling ACPI support\n"); disable_acpi(); - return; + return 1; } } -} - -int __init early_acpi_boot_init(void) -{ - /* - * If acpi_disabled, bail out - */ - if (acpi_disabled) - return 1; /* * Process the Multiple APIC Description Table (MADT), if present @@ -1752,7 +1751,7 @@ int __acpi_acquire_global_lock(unsigned int *lock) new = (((old & ~0x3) + 2) + ((old >> 1) & 0x1)); val = cmpxchg(lock, old, new); } while (unlikely (val != old)); - return (new < 3) ? -1 : 0; + return ((new & 0x3) < 3) ? -1 : 0; } int __acpi_release_global_lock(unsigned int *lock) diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c index 158ad1483c43..92539a1c3e31 100644 --- a/arch/x86/kernel/acpi/cstate.c +++ b/arch/x86/kernel/acpi/cstate.c @@ -133,7 +133,8 @@ int acpi_processor_ffh_cstate_probe(unsigned int cpu, /* Make sure we are running on right CPU */ - retval = work_on_cpu(cpu, acpi_processor_ffh_cstate_probe_cpu, cx); + retval = call_on_cpu(cpu, acpi_processor_ffh_cstate_probe_cpu, cx, + false); if (retval == 0) { /* Use the hint in CST */ percpu_entry->states[cx->index].eax = cx->address; diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index b481b95bd8f6..923b4bac9613 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -11,14 +11,17 @@ #include <linux/errno.h> #include <linux/export.h> #include <linux/spinlock.h> +#include <linux/pci_ids.h> #include <asm/amd_nb.h> #define PCI_DEVICE_ID_AMD_17H_ROOT 0x1450 #define PCI_DEVICE_ID_AMD_17H_M10H_ROOT 0x15d0 -#define PCI_DEVICE_ID_AMD_17H_DF_F3 0x1463 +#define PCI_DEVICE_ID_AMD_17H_M30H_ROOT 0x1480 #define PCI_DEVICE_ID_AMD_17H_DF_F4 0x1464 -#define PCI_DEVICE_ID_AMD_17H_M10H_DF_F3 0x15eb #define PCI_DEVICE_ID_AMD_17H_M10H_DF_F4 0x15ec +#define PCI_DEVICE_ID_AMD_17H_M30H_DF_F4 0x1494 +#define PCI_DEVICE_ID_AMD_17H_M70H_DF_F4 0x1444 +#define PCI_DEVICE_ID_AMD_19H_DF_F4 0x1654 /* Protect the PCI config register pairs used for SMN and DF indirect access. */ static DEFINE_MUTEX(smn_mutex); @@ -28,9 +31,11 @@ static u32 *flush_words; static const struct pci_device_id amd_root_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_ROOT) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M10H_ROOT) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M30H_ROOT) }, {} }; + #define PCI_DEVICE_ID_AMD_CNB17H_F4 0x1704 const struct pci_device_id amd_nb_misc_ids[] = { @@ -44,7 +49,10 @@ const struct pci_device_id amd_nb_misc_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_M30H_NB_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_DF_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M10H_DF_F3) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M30H_DF_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F3) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M70H_DF_F3) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_DF_F3) }, {} }; EXPORT_SYMBOL_GPL(amd_nb_misc_ids); @@ -57,6 +65,9 @@ static const struct pci_device_id amd_nb_link_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_M30H_NB_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_DF_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M10H_DF_F4) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M30H_DF_F4) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M70H_DF_F4) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_DF_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F4) }, {} }; diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 1ca76ca944ba..da6b52c70964 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -41,6 +41,7 @@ #include <asm/x86_init.h> #include <asm/pgalloc.h> #include <linux/atomic.h> +#include <asm/barrier.h> #include <asm/mpspec.h> #include <asm/i8259.h> #include <asm/proto.h> @@ -345,8 +346,6 @@ static void __setup_APIC_LVTT(unsigned int clocks, int oneshot, int irqen) * According to Intel, MFENCE can do the serialization here. */ asm volatile("mfence" : : : "memory"); - - printk_once(KERN_DEBUG "TSC deadline timer enabled\n"); return; } @@ -467,6 +466,9 @@ static int lapic_next_deadline(unsigned long delta, { u64 tsc; + /* This MSR is special and need a special fence: */ + weak_wrmsr_fence(); + tsc = rdtsc(); wrmsrl(MSR_IA32_TSC_DEADLINE, tsc + (((u64) delta) * TSC_DIVISOR)); return 0; @@ -545,7 +547,7 @@ static DEFINE_PER_CPU(struct clock_event_device, lapic_events); #define DEADLINE_MODEL_MATCH_REV(model, rev) \ { X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (unsigned long)rev } -static u32 hsx_deadline_rev(void) +static __init u32 hsx_deadline_rev(void) { switch (boot_cpu_data.x86_stepping) { case 0x02: return 0x3a; /* EP */ @@ -555,7 +557,7 @@ static u32 hsx_deadline_rev(void) return ~0U; } -static u32 bdx_deadline_rev(void) +static __init u32 bdx_deadline_rev(void) { switch (boot_cpu_data.x86_stepping) { case 0x02: return 0x00000011; @@ -567,7 +569,7 @@ static u32 bdx_deadline_rev(void) return ~0U; } -static u32 skx_deadline_rev(void) +static __init u32 skx_deadline_rev(void) { switch (boot_cpu_data.x86_stepping) { case 0x03: return 0x01000136; @@ -580,7 +582,7 @@ static u32 skx_deadline_rev(void) return ~0U; } -static const struct x86_cpu_id deadline_match[] = { +static const struct x86_cpu_id deadline_match[] __initconst = { DEADLINE_MODEL_MATCH_FUNC( INTEL_FAM6_HASWELL_X, hsx_deadline_rev), DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_BROADWELL_X, 0x0b000020), DEADLINE_MODEL_MATCH_FUNC( INTEL_FAM6_BROADWELL_XEON_D, bdx_deadline_rev), @@ -602,18 +604,19 @@ static const struct x86_cpu_id deadline_match[] = { {}, }; -static void apic_check_deadline_errata(void) +static __init bool apic_validate_deadline_timer(void) { const struct x86_cpu_id *m; u32 rev; - if (!boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER) || - boot_cpu_has(X86_FEATURE_HYPERVISOR)) - return; + if (!boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER)) + return false; + if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) + return true; m = x86_match_cpu(deadline_match); if (!m) - return; + return true; /* * Function pointers will have the MSB set due to address layout, @@ -625,11 +628,12 @@ static void apic_check_deadline_errata(void) rev = (u32)m->driver_data; if (boot_cpu_data.microcode >= rev) - return; + return true; setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER); pr_err(FW_BUG "TSC_DEADLINE disabled due to Errata; " "please update microcode to version: 0x%x (or later)\n", rev); + return false; } /* @@ -1813,20 +1817,22 @@ static __init void try_to_enable_x2apic(int remap_mode) return; if (remap_mode != IRQ_REMAP_X2APIC_MODE) { - /* IR is required if there is APIC ID > 255 even when running - * under KVM + /* + * Using X2APIC without IR is not architecturally supported + * on bare metal but may be supported in guests. */ - if (max_physical_apicid > 255 || - !x86_init.hyper.x2apic_available()) { + if (!x86_init.hyper.x2apic_available()) { pr_info("x2apic: IRQ remapping doesn't support X2APIC mode\n"); x2apic_disable(); return; } /* - * without IR all CPUs can be addressed by IOAPIC/MSI - * only in physical mode + * Without IR, all CPUs can be addressed by IOAPIC/MSI only + * in physical mode, and CPUs with an APIC ID that cannnot + * be addressed must not be brought online. */ + x2apic_set_max_apicid(255); x2apic_phys = 1; } x2apic_enable(); @@ -2023,7 +2029,8 @@ void __init init_apic_mappings(void) { unsigned int new_apicid; - apic_check_deadline_errata(); + if (apic_validate_deadline_timer()) + pr_info("TSC deadline timer available\n"); if (x2apic_mode) { boot_cpu_physical_apicid = read_apic_id(); @@ -2272,6 +2279,11 @@ static int cpuid_to_apicid[] = { [0 ... NR_CPUS - 1] = -1, }; +bool arch_match_cpu_phys_id(int cpu, u64 phys_id) +{ + return phys_id == cpuid_to_apicid[cpu]; +} + #ifdef CONFIG_SMP /** * apic_id_is_primary_thread - Check whether APIC ID belongs to a primary thread diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index fa3b85b222e3..a89dac380243 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -1043,6 +1043,16 @@ static int mp_map_pin_to_irq(u32 gsi, int idx, int ioapic, int pin, if (idx >= 0 && test_bit(mp_irqs[idx].srcbus, mp_bus_not_pci)) { irq = mp_irqs[idx].srcbusirq; legacy = mp_is_legacy_irq(irq); + /* + * IRQ2 is unusable for historical reasons on systems which + * have a legacy PIC. See the comment vs. IRQ2 further down. + * + * If this gets removed at some point then the related code + * in lapic_assign_system_vectors() needs to be adjusted as + * well. + */ + if (legacy && irq == PIC_CASCADE_IR) + return -EINVAL; } mutex_lock(&ioapic_mutex); @@ -2250,6 +2260,7 @@ static inline void __init check_timer(void) legacy_pic->init(0); legacy_pic->make_irq(0); apic_write(APIC_LVT0, APIC_DM_EXTINT); + legacy_pic->unmask(0); unlock_ExtINT_logic(); @@ -2323,12 +2334,12 @@ static int mp_irqdomain_create(int ioapic) ip->irqdomain = irq_domain_create_linear(fn, hwirqs, cfg->ops, (void *)(long)ioapic); - /* Release fw handle if it was allocated above */ - if (!cfg->dev) - irq_domain_free_fwnode(fn); - - if (!ip->irqdomain) + if (!ip->irqdomain) { + /* Release fw handle if it was allocated above */ + if (!cfg->dev) + irq_domain_free_fwnode(fn); return -ENOMEM; + } ip->irqdomain->parent = parent; @@ -2342,8 +2353,13 @@ static int mp_irqdomain_create(int ioapic) static void ioapic_destroy_irqdomain(int idx) { + struct ioapic_domain_cfg *cfg = &ioapics[idx].irqdomain_cfg; + struct fwnode_handle *fn = ioapics[idx].irqdomain->fwnode; + if (ioapics[idx].irqdomain) { irq_domain_remove(ioapics[idx].irqdomain); + if (!cfg->dev) + irq_domain_free_fwnode(fn); ioapics[idx].irqdomain = NULL; } } diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c index 1f5df339e48f..fb26c956c442 100644 --- a/arch/x86/kernel/apic/msi.c +++ b/arch/x86/kernel/apic/msi.c @@ -265,12 +265,13 @@ void __init arch_init_msi_domain(struct irq_domain *parent) msi_default_domain = pci_msi_create_irq_domain(fn, &pci_msi_domain_info, parent); - irq_domain_free_fwnode(fn); } - if (!msi_default_domain) + if (!msi_default_domain) { + irq_domain_free_fwnode(fn); pr_warn("failed to initialize irqdomain for MSI/MSI-x.\n"); - else + } else { msi_default_domain->flags |= IRQ_DOMAIN_MSI_NOMASK_QUIRK; + } } #ifdef CONFIG_IRQ_REMAP @@ -303,7 +304,8 @@ struct irq_domain *arch_create_remap_msi_irq_domain(struct irq_domain *parent, if (!fn) return NULL; d = pci_msi_create_irq_domain(fn, &pci_msi_ir_domain_info, parent); - irq_domain_free_fwnode(fn); + if (!d) + irq_domain_free_fwnode(fn); return d; } #endif @@ -366,7 +368,8 @@ static struct irq_domain *dmar_get_irq_domain(void) if (fn) { dmar_domain = msi_create_irq_domain(fn, &dmar_msi_domain_info, x86_vector_domain); - irq_domain_free_fwnode(fn); + if (!dmar_domain) + irq_domain_free_fwnode(fn); } out: mutex_unlock(&dmar_lock); @@ -491,7 +494,10 @@ struct irq_domain *hpet_create_irq_domain(int hpet_id) } d = msi_create_irq_domain(fn, domain_info, parent); - irq_domain_free_fwnode(fn); + if (!d) { + irq_domain_free_fwnode(fn); + kfree(domain_info); + } return d; } diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index c352ca2e1456..f0d0535e8f34 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -274,20 +274,24 @@ static int assign_irq_vector_any_locked(struct irq_data *irqd) const struct cpumask *affmsk = irq_data_get_affinity_mask(irqd); int node = irq_data_get_node(irqd); - if (node == NUMA_NO_NODE) - goto all; - /* Try the intersection of @affmsk and node mask */ - cpumask_and(vector_searchmask, cpumask_of_node(node), affmsk); - if (!assign_vector_locked(irqd, vector_searchmask)) - return 0; - /* Try the node mask */ - if (!assign_vector_locked(irqd, cpumask_of_node(node))) - return 0; -all: + if (node != NUMA_NO_NODE) { + /* Try the intersection of @affmsk and node mask */ + cpumask_and(vector_searchmask, cpumask_of_node(node), affmsk); + if (!assign_vector_locked(irqd, vector_searchmask)) + return 0; + } + /* Try the full affinity mask */ cpumask_and(vector_searchmask, affmsk, cpu_online_mask); if (!assign_vector_locked(irqd, vector_searchmask)) return 0; + + if (node != NUMA_NO_NODE) { + /* Try the node mask */ + if (!assign_vector_locked(irqd, cpumask_of_node(node))) + return 0; + } + /* Try the full online mask */ return assign_vector_locked(irqd, cpu_online_mask); } @@ -448,12 +452,10 @@ static int x86_vector_activate(struct irq_domain *dom, struct irq_data *irqd, trace_vector_activate(irqd->irq, apicd->is_managed, apicd->can_reserve, reserve); - /* Nothing to do for fixed assigned vectors */ - if (!apicd->can_reserve && !apicd->is_managed) - return 0; - raw_spin_lock_irqsave(&vector_lock, flags); - if (reserve || irqd_is_managed_and_shutdown(irqd)) + if (!apicd->can_reserve && !apicd->is_managed) + assign_irq_vector_any_locked(irqd); + else if (reserve || irqd_is_managed_and_shutdown(irqd)) vector_assign_managed_shutdown(irqd); else if (apicd->is_managed) ret = activate_managed(irqd); @@ -558,6 +560,10 @@ static int x86_vector_alloc_irqs(struct irq_domain *domain, unsigned int virq, irqd->chip_data = apicd; irqd->hwirq = virq + i; irqd_set_single_target(irqd); + + /* Don't invoke affinity setter on deactivated interrupts */ + irqd_set_affinity_on_activate(irqd); + /* * Legacy vectors are already assigned when the IOAPIC * takes them over. They stay on the same vector. This is @@ -705,7 +711,6 @@ int __init arch_early_irq_init(void) x86_vector_domain = irq_domain_create_tree(fn, &x86_vector_domain_ops, NULL); BUG_ON(x86_vector_domain == NULL); - irq_domain_free_fwnode(fn); irq_set_default_host(x86_vector_domain); arch_init_msi_domain(x86_vector_domain); @@ -771,20 +776,10 @@ void lapic_offline(void) static int apic_set_affinity(struct irq_data *irqd, const struct cpumask *dest, bool force) { - struct apic_chip_data *apicd = apic_chip_data(irqd); int err; - /* - * Core code can call here for inactive interrupts. For inactive - * interrupts which use managed or reservation mode there is no - * point in going through the vector assignment right now as the - * activation will assign a vector which fits the destination - * cpumask. Let the core code store the destination mask and be - * done with it. - */ - if (!irqd_is_activated(irqd) && - (apicd->is_managed || apicd->can_reserve)) - return IRQ_SET_MASK_OK; + if (WARN_ON_ONCE(!irqd_is_activated(irqd))) + return -EIO; raw_spin_lock(&vector_lock); cpumask_and(vector_searchmask, dest, cpu_online_mask); diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c index 145517934171..b2c7e3bc55d2 100644 --- a/arch/x86/kernel/apic/x2apic_cluster.c +++ b/arch/x86/kernel/apic/x2apic_cluster.c @@ -31,7 +31,8 @@ static void x2apic_send_IPI(int cpu, int vector) { u32 dest = per_cpu(x86_cpu_to_logical_apicid, cpu); - x2apic_wrmsr_fence(); + /* x2apic MSRs are special and need a special fence: */ + weak_wrmsr_fence(); __x2apic_send_IPI_dest(dest, vector, APIC_DEST_LOGICAL); } @@ -43,7 +44,8 @@ __x2apic_send_IPI_mask(const struct cpumask *mask, int vector, int apic_dest) unsigned long flags; u32 dest; - x2apic_wrmsr_fence(); + /* x2apic MSRs are special and need a special fence: */ + weak_wrmsr_fence(); local_irq_save(flags); tmpmsk = this_cpu_cpumask_var_ptr(ipi_mask); diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c index b5cf9e7b3830..8e70c2ba21b3 100644 --- a/arch/x86/kernel/apic/x2apic_phys.c +++ b/arch/x86/kernel/apic/x2apic_phys.c @@ -13,6 +13,12 @@ int x2apic_phys; static struct apic apic_x2apic_phys; +static u32 x2apic_max_apicid __ro_after_init; + +void __init x2apic_set_max_apicid(u32 apicid) +{ + x2apic_max_apicid = apicid; +} static int __init set_x2apic_phys_mode(char *arg) { @@ -42,7 +48,8 @@ static void x2apic_send_IPI(int cpu, int vector) { u32 dest = per_cpu(x86_cpu_to_apicid, cpu); - x2apic_wrmsr_fence(); + /* x2apic MSRs are special and need a special fence: */ + weak_wrmsr_fence(); __x2apic_send_IPI_dest(dest, vector, APIC_DEST_PHYSICAL); } @@ -53,7 +60,8 @@ __x2apic_send_IPI_mask(const struct cpumask *mask, int vector, int apic_dest) unsigned long this_cpu; unsigned long flags; - x2apic_wrmsr_fence(); + /* x2apic MSRs are special and need a special fence: */ + weak_wrmsr_fence(); local_irq_save(flags); @@ -103,6 +111,9 @@ static int x2apic_phys_probe(void) /* Common x2apic functions, also used by x2apic_cluster */ int x2apic_apic_id_valid(u32 apicid) { + if (x2apic_max_apicid && apicid > x2apic_max_apicid) + return 0; + return 1; } diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 120769955687..de69090ca142 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -1122,8 +1122,7 @@ static const int amd_erratum_383[] = /* #1054: Instructions Retired Performance Counter May Be Inaccurate */ static const int amd_erratum_1054[] = - AMD_OSVW_ERRATUM(0, AMD_MODEL_RANGE(0x17, 0, 0, 0x2f, 0xf)); - + AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x17, 0, 0, 0x2f, 0xf)); static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum) { diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 2d23a448e72d..c524fa1f4c0e 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -41,6 +41,7 @@ static void __init l1tf_select_mitigation(void); static void __init mds_select_mitigation(void); static void __init mds_print_mitigation(void); static void __init taa_select_mitigation(void); +static void __init srbds_select_mitigation(void); /* The base value of the SPEC_CTRL MSR that always has to be preserved. */ u64 x86_spec_ctrl_base; @@ -60,7 +61,7 @@ static u64 __ro_after_init x86_spec_ctrl_mask = SPEC_CTRL_IBRS; u64 __ro_after_init x86_amd_ls_cfg_base; u64 __ro_after_init x86_amd_ls_cfg_ssbd_mask; -/* Control conditional STIPB in switch_to() */ +/* Control conditional STIBP in switch_to() */ DEFINE_STATIC_KEY_FALSE(switch_to_cond_stibp); /* Control conditional IBPB in switch_mm() */ DEFINE_STATIC_KEY_FALSE(switch_mm_cond_ibpb); @@ -108,6 +109,7 @@ void __init check_bugs(void) l1tf_select_mitigation(); mds_select_mitigation(); taa_select_mitigation(); + srbds_select_mitigation(); /* * As MDS and TAA mitigations are inter-related, print MDS @@ -391,6 +393,97 @@ static int __init tsx_async_abort_parse_cmdline(char *str) early_param("tsx_async_abort", tsx_async_abort_parse_cmdline); #undef pr_fmt +#define pr_fmt(fmt) "SRBDS: " fmt + +enum srbds_mitigations { + SRBDS_MITIGATION_OFF, + SRBDS_MITIGATION_UCODE_NEEDED, + SRBDS_MITIGATION_FULL, + SRBDS_MITIGATION_TSX_OFF, + SRBDS_MITIGATION_HYPERVISOR, +}; + +static enum srbds_mitigations srbds_mitigation __ro_after_init = SRBDS_MITIGATION_FULL; + +static const char * const srbds_strings[] = { + [SRBDS_MITIGATION_OFF] = "Vulnerable", + [SRBDS_MITIGATION_UCODE_NEEDED] = "Vulnerable: No microcode", + [SRBDS_MITIGATION_FULL] = "Mitigation: Microcode", + [SRBDS_MITIGATION_TSX_OFF] = "Mitigation: TSX disabled", + [SRBDS_MITIGATION_HYPERVISOR] = "Unknown: Dependent on hypervisor status", +}; + +static bool srbds_off; + +void update_srbds_msr(void) +{ + u64 mcu_ctrl; + + if (!boot_cpu_has_bug(X86_BUG_SRBDS)) + return; + + if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) + return; + + if (srbds_mitigation == SRBDS_MITIGATION_UCODE_NEEDED) + return; + + rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl); + + switch (srbds_mitigation) { + case SRBDS_MITIGATION_OFF: + case SRBDS_MITIGATION_TSX_OFF: + mcu_ctrl |= RNGDS_MITG_DIS; + break; + case SRBDS_MITIGATION_FULL: + mcu_ctrl &= ~RNGDS_MITG_DIS; + break; + default: + break; + } + + wrmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl); +} + +static void __init srbds_select_mitigation(void) +{ + u64 ia32_cap; + + if (!boot_cpu_has_bug(X86_BUG_SRBDS)) + return; + + /* + * Check to see if this is one of the MDS_NO systems supporting + * TSX that are only exposed to SRBDS when TSX is enabled. + */ + ia32_cap = x86_read_arch_cap_msr(); + if ((ia32_cap & ARCH_CAP_MDS_NO) && !boot_cpu_has(X86_FEATURE_RTM)) + srbds_mitigation = SRBDS_MITIGATION_TSX_OFF; + else if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) + srbds_mitigation = SRBDS_MITIGATION_HYPERVISOR; + else if (!boot_cpu_has(X86_FEATURE_SRBDS_CTRL)) + srbds_mitigation = SRBDS_MITIGATION_UCODE_NEEDED; + else if (cpu_mitigations_off() || srbds_off) + srbds_mitigation = SRBDS_MITIGATION_OFF; + + update_srbds_msr(); + pr_info("%s\n", srbds_strings[srbds_mitigation]); +} + +static int __init srbds_parse_cmdline(char *str) +{ + if (!str) + return -EINVAL; + + if (!boot_cpu_has_bug(X86_BUG_SRBDS)) + return 0; + + srbds_off = !strcmp(str, "off"); + return 0; +} +early_param("srbds", srbds_parse_cmdline); + +#undef pr_fmt #define pr_fmt(fmt) "Spectre V1 : " fmt enum spectre_v1_mitigation { @@ -488,7 +581,9 @@ early_param("nospectre_v1", nospectre_v1_cmdline); static enum spectre_v2_mitigation spectre_v2_enabled __ro_after_init = SPECTRE_V2_NONE; -static enum spectre_v2_user_mitigation spectre_v2_user __ro_after_init = +static enum spectre_v2_user_mitigation spectre_v2_user_stibp __ro_after_init = + SPECTRE_V2_USER_NONE; +static enum spectre_v2_user_mitigation spectre_v2_user_ibpb __ro_after_init = SPECTRE_V2_USER_NONE; #ifdef CONFIG_RETPOLINE @@ -540,10 +635,11 @@ enum spectre_v2_user_cmd { }; static const char * const spectre_v2_user_strings[] = { - [SPECTRE_V2_USER_NONE] = "User space: Vulnerable", - [SPECTRE_V2_USER_STRICT] = "User space: Mitigation: STIBP protection", - [SPECTRE_V2_USER_PRCTL] = "User space: Mitigation: STIBP via prctl", - [SPECTRE_V2_USER_SECCOMP] = "User space: Mitigation: STIBP via seccomp and prctl", + [SPECTRE_V2_USER_NONE] = "User space: Vulnerable", + [SPECTRE_V2_USER_STRICT] = "User space: Mitigation: STIBP protection", + [SPECTRE_V2_USER_STRICT_PREFERRED] = "User space: Mitigation: STIBP always-on protection", + [SPECTRE_V2_USER_PRCTL] = "User space: Mitigation: STIBP via prctl", + [SPECTRE_V2_USER_SECCOMP] = "User space: Mitigation: STIBP via seccomp and prctl", }; static const struct { @@ -637,11 +733,13 @@ spectre_v2_user_select_mitigation(enum spectre_v2_mitigation_cmd v2_cmd) if (boot_cpu_has(X86_FEATURE_IBPB)) { setup_force_cpu_cap(X86_FEATURE_USE_IBPB); + spectre_v2_user_ibpb = mode; switch (cmd) { case SPECTRE_V2_USER_CMD_FORCE: case SPECTRE_V2_USER_CMD_PRCTL_IBPB: case SPECTRE_V2_USER_CMD_SECCOMP_IBPB: static_branch_enable(&switch_mm_always_ibpb); + spectre_v2_user_ibpb = SPECTRE_V2_USER_STRICT; break; case SPECTRE_V2_USER_CMD_PRCTL: case SPECTRE_V2_USER_CMD_AUTO: @@ -657,21 +755,32 @@ spectre_v2_user_select_mitigation(enum spectre_v2_mitigation_cmd v2_cmd) "always-on" : "conditional"); } - /* If enhanced IBRS is enabled no STIPB required */ - if (spectre_v2_enabled == SPECTRE_V2_IBRS_ENHANCED) + /* + * If enhanced IBRS is enabled or SMT impossible, STIBP is not + * required. + */ + if (!smt_possible || spectre_v2_enabled == SPECTRE_V2_IBRS_ENHANCED) return; /* - * If SMT is not possible or STIBP is not available clear the STIPB - * mode. + * At this point, an STIBP mode other than "off" has been set. + * If STIBP support is not being forced, check if STIBP always-on + * is preferred. */ - if (!smt_possible || !boot_cpu_has(X86_FEATURE_STIBP)) + if (mode != SPECTRE_V2_USER_STRICT && + boot_cpu_has(X86_FEATURE_AMD_STIBP_ALWAYS_ON)) + mode = SPECTRE_V2_USER_STRICT_PREFERRED; + + /* + * If STIBP is not available, clear the STIBP mode. + */ + if (!boot_cpu_has(X86_FEATURE_STIBP)) mode = SPECTRE_V2_USER_NONE; + + spectre_v2_user_stibp = mode; + set_mode: - spectre_v2_user = mode; - /* Only print the STIBP mode when SMT possible */ - if (smt_possible) - pr_info("%s\n", spectre_v2_user_strings[mode]); + pr_info("%s\n", spectre_v2_user_strings[mode]); } static const char * const spectre_v2_strings[] = { @@ -902,10 +1011,11 @@ void arch_smt_update(void) { mutex_lock(&spec_ctrl_mutex); - switch (spectre_v2_user) { + switch (spectre_v2_user_stibp) { case SPECTRE_V2_USER_NONE: break; case SPECTRE_V2_USER_STRICT: + case SPECTRE_V2_USER_STRICT_PREFERRED: update_stibp_strict(); break; case SPECTRE_V2_USER_PRCTL: @@ -1130,18 +1240,41 @@ static int ssb_prctl_set(struct task_struct *task, unsigned long ctrl) return 0; } +static bool is_spec_ib_user_controlled(void) +{ + return spectre_v2_user_ibpb == SPECTRE_V2_USER_PRCTL || + spectre_v2_user_ibpb == SPECTRE_V2_USER_SECCOMP || + spectre_v2_user_stibp == SPECTRE_V2_USER_PRCTL || + spectre_v2_user_stibp == SPECTRE_V2_USER_SECCOMP; +} + static int ib_prctl_set(struct task_struct *task, unsigned long ctrl) { switch (ctrl) { case PR_SPEC_ENABLE: - if (spectre_v2_user == SPECTRE_V2_USER_NONE) + if (spectre_v2_user_ibpb == SPECTRE_V2_USER_NONE && + spectre_v2_user_stibp == SPECTRE_V2_USER_NONE) return 0; + /* - * Indirect branch speculation is always disabled in strict - * mode. + * With strict mode for both IBPB and STIBP, the instruction + * code paths avoid checking this task flag and instead, + * unconditionally run the instruction. However, STIBP and IBPB + * are independent and either can be set to conditionally + * enabled regardless of the mode of the other. + * + * If either is set to conditional, allow the task flag to be + * updated, unless it was force-disabled by a previous prctl + * call. Currently, this is possible on an AMD CPU which has the + * feature X86_FEATURE_AMD_STIBP_ALWAYS_ON. In this case, if the + * kernel is booted with 'spectre_v2_user=seccomp', then + * spectre_v2_user_ibpb == SPECTRE_V2_USER_SECCOMP and + * spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED. */ - if (spectre_v2_user == SPECTRE_V2_USER_STRICT) + if (!is_spec_ib_user_controlled() || + task_spec_ib_force_disable(task)) return -EPERM; + task_clear_spec_ib_disable(task); task_update_spec_tif(task); break; @@ -1151,10 +1284,13 @@ static int ib_prctl_set(struct task_struct *task, unsigned long ctrl) * Indirect branch speculation is always allowed when * mitigation is force disabled. */ - if (spectre_v2_user == SPECTRE_V2_USER_NONE) + if (spectre_v2_user_ibpb == SPECTRE_V2_USER_NONE && + spectre_v2_user_stibp == SPECTRE_V2_USER_NONE) return -EPERM; - if (spectre_v2_user == SPECTRE_V2_USER_STRICT) + + if (!is_spec_ib_user_controlled()) return 0; + task_set_spec_ib_disable(task); if (ctrl == PR_SPEC_FORCE_DISABLE) task_set_spec_ib_force_disable(task); @@ -1184,7 +1320,8 @@ void arch_seccomp_spec_mitigate(struct task_struct *task) { if (ssb_mode == SPEC_STORE_BYPASS_SECCOMP) ssb_prctl_set(task, PR_SPEC_FORCE_DISABLE); - if (spectre_v2_user == SPECTRE_V2_USER_SECCOMP) + if (spectre_v2_user_ibpb == SPECTRE_V2_USER_SECCOMP || + spectre_v2_user_stibp == SPECTRE_V2_USER_SECCOMP) ib_prctl_set(task, PR_SPEC_FORCE_DISABLE); } #endif @@ -1213,21 +1350,21 @@ static int ib_prctl_get(struct task_struct *task) if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2)) return PR_SPEC_NOT_AFFECTED; - switch (spectre_v2_user) { - case SPECTRE_V2_USER_NONE: + if (spectre_v2_user_ibpb == SPECTRE_V2_USER_NONE && + spectre_v2_user_stibp == SPECTRE_V2_USER_NONE) return PR_SPEC_ENABLE; - case SPECTRE_V2_USER_PRCTL: - case SPECTRE_V2_USER_SECCOMP: + else if (is_spec_ib_user_controlled()) { if (task_spec_ib_force_disable(task)) return PR_SPEC_PRCTL | PR_SPEC_FORCE_DISABLE; if (task_spec_ib_disable(task)) return PR_SPEC_PRCTL | PR_SPEC_DISABLE; return PR_SPEC_PRCTL | PR_SPEC_ENABLE; - case SPECTRE_V2_USER_STRICT: + } else if (spectre_v2_user_ibpb == SPECTRE_V2_USER_STRICT || + spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT || + spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED) return PR_SPEC_DISABLE; - default: + else return PR_SPEC_NOT_AFFECTED; - } } int arch_prctl_spec_ctrl_get(struct task_struct *task, unsigned long which) @@ -1466,11 +1603,13 @@ static char *stibp_state(void) if (spectre_v2_enabled == SPECTRE_V2_IBRS_ENHANCED) return ""; - switch (spectre_v2_user) { + switch (spectre_v2_user_stibp) { case SPECTRE_V2_USER_NONE: return ", STIBP: disabled"; case SPECTRE_V2_USER_STRICT: return ", STIBP: forced"; + case SPECTRE_V2_USER_STRICT_PREFERRED: + return ", STIBP: always-on"; case SPECTRE_V2_USER_PRCTL: case SPECTRE_V2_USER_SECCOMP: if (static_key_enabled(&switch_to_cond_stibp)) @@ -1491,6 +1630,11 @@ static char *ibpb_state(void) return ""; } +static ssize_t srbds_show_state(char *buf) +{ + return sprintf(buf, "%s\n", srbds_strings[srbds_mitigation]); +} + static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr, char *buf, unsigned int bug) { @@ -1535,6 +1679,9 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr case X86_BUG_ITLB_MULTIHIT: return itlb_multihit_show_state(buf); + case X86_BUG_SRBDS: + return srbds_show_state(buf); + default: break; } @@ -1581,4 +1728,9 @@ ssize_t cpu_show_itlb_multihit(struct device *dev, struct device_attribute *attr { return cpu_show_common(dev, attr, buf, X86_BUG_ITLB_MULTIHIT); } + +ssize_t cpu_show_srbds(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_common(dev, attr, buf, X86_BUG_SRBDS); +} #endif diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 7f43eba8d0c1..2058e8c0e61d 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1013,9 +1013,30 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { {} }; -static bool __init cpu_matches(unsigned long which) +#define VULNBL_INTEL_STEPPINGS(model, steppings, issues) \ + X86_MATCH_VENDOR_FAM_MODEL_STEPPINGS_FEATURE(INTEL, 6, \ + INTEL_FAM6_##model, steppings, \ + X86_FEATURE_ANY, issues) + +#define SRBDS BIT(0) + +static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = { + VULNBL_INTEL_STEPPINGS(IVYBRIDGE, X86_STEPPING_ANY, SRBDS), + VULNBL_INTEL_STEPPINGS(HASWELL_CORE, X86_STEPPING_ANY, SRBDS), + VULNBL_INTEL_STEPPINGS(HASWELL_ULT, X86_STEPPING_ANY, SRBDS), + VULNBL_INTEL_STEPPINGS(HASWELL_GT3E, X86_STEPPING_ANY, SRBDS), + VULNBL_INTEL_STEPPINGS(BROADWELL_GT3E, X86_STEPPING_ANY, SRBDS), + VULNBL_INTEL_STEPPINGS(BROADWELL_CORE, X86_STEPPING_ANY, SRBDS), + VULNBL_INTEL_STEPPINGS(SKYLAKE_MOBILE, X86_STEPPING_ANY, SRBDS), + VULNBL_INTEL_STEPPINGS(SKYLAKE_DESKTOP, X86_STEPPING_ANY, SRBDS), + VULNBL_INTEL_STEPPINGS(KABYLAKE_MOBILE, X86_STEPPINGS(0x0, 0xC), SRBDS), + VULNBL_INTEL_STEPPINGS(KABYLAKE_DESKTOP,X86_STEPPINGS(0x0, 0xD), SRBDS), + {} +}; + +static bool __init cpu_matches(const struct x86_cpu_id *table, unsigned long which) { - const struct x86_cpu_id *m = x86_match_cpu(cpu_vuln_whitelist); + const struct x86_cpu_id *m = x86_match_cpu(table); return m && !!(m->driver_data & which); } @@ -1035,29 +1056,32 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) u64 ia32_cap = x86_read_arch_cap_msr(); /* Set ITLB_MULTIHIT bug if cpu is not in the whitelist and not mitigated */ - if (!cpu_matches(NO_ITLB_MULTIHIT) && !(ia32_cap & ARCH_CAP_PSCHANGE_MC_NO)) + if (!cpu_matches(cpu_vuln_whitelist, NO_ITLB_MULTIHIT) && + !(ia32_cap & ARCH_CAP_PSCHANGE_MC_NO)) setup_force_cpu_bug(X86_BUG_ITLB_MULTIHIT); - if (cpu_matches(NO_SPECULATION)) + if (cpu_matches(cpu_vuln_whitelist, NO_SPECULATION)) return; setup_force_cpu_bug(X86_BUG_SPECTRE_V1); setup_force_cpu_bug(X86_BUG_SPECTRE_V2); - if (!cpu_matches(NO_SSB) && !(ia32_cap & ARCH_CAP_SSB_NO) && + if (!cpu_matches(cpu_vuln_whitelist, NO_SSB) && + !(ia32_cap & ARCH_CAP_SSB_NO) && !cpu_has(c, X86_FEATURE_AMD_SSB_NO)) setup_force_cpu_bug(X86_BUG_SPEC_STORE_BYPASS); if (ia32_cap & ARCH_CAP_IBRS_ALL) setup_force_cpu_cap(X86_FEATURE_IBRS_ENHANCED); - if (!cpu_matches(NO_MDS) && !(ia32_cap & ARCH_CAP_MDS_NO)) { + if (!cpu_matches(cpu_vuln_whitelist, NO_MDS) && + !(ia32_cap & ARCH_CAP_MDS_NO)) { setup_force_cpu_bug(X86_BUG_MDS); - if (cpu_matches(MSBDS_ONLY)) + if (cpu_matches(cpu_vuln_whitelist, MSBDS_ONLY)) setup_force_cpu_bug(X86_BUG_MSBDS_ONLY); } - if (!cpu_matches(NO_SWAPGS)) + if (!cpu_matches(cpu_vuln_whitelist, NO_SWAPGS)) setup_force_cpu_bug(X86_BUG_SWAPGS); /* @@ -1075,7 +1099,16 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) (ia32_cap & ARCH_CAP_TSX_CTRL_MSR))) setup_force_cpu_bug(X86_BUG_TAA); - if (cpu_matches(NO_MELTDOWN)) + /* + * SRBDS affects CPUs which support RDRAND or RDSEED and are listed + * in the vulnerability blacklist. + */ + if ((cpu_has(c, X86_FEATURE_RDRAND) || + cpu_has(c, X86_FEATURE_RDSEED)) && + cpu_matches(cpu_vuln_blacklist, SRBDS)) + setup_force_cpu_bug(X86_BUG_SRBDS); + + if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN)) return; /* Rogue Data Cache Load? No! */ @@ -1084,7 +1117,7 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN); - if (cpu_matches(NO_L1TF)) + if (cpu_matches(cpu_vuln_whitelist, NO_L1TF)) return; setup_force_cpu_bug(X86_BUG_L1TF); @@ -1519,6 +1552,7 @@ void identify_secondary_cpu(struct cpuinfo_x86 *c) mtrr_ap_init(); validate_apic_and_package_id(c); x86_spec_ctrl_setup_ap(); + update_srbds_msr(); } static __init int setup_noclflush(char *arg) diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h index 236582c90d3f..e89602d2aff5 100644 --- a/arch/x86/kernel/cpu/cpu.h +++ b/arch/x86/kernel/cpu/cpu.h @@ -80,6 +80,7 @@ extern void detect_ht(struct cpuinfo_x86 *c); unsigned int aperfmperf_get_khz(int cpu); extern void x86_spec_ctrl_setup_ap(void); +extern void update_srbds_msr(void); extern u64 x86_read_arch_cap_msr(void); diff --git a/arch/x86/kernel/cpu/intel_rdt.c b/arch/x86/kernel/cpu/intel_rdt.c index 1c92cd08c3b4..b32fa6bcf811 100644 --- a/arch/x86/kernel/cpu/intel_rdt.c +++ b/arch/x86/kernel/cpu/intel_rdt.c @@ -555,6 +555,8 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r) d->id = id; cpumask_set_cpu(cpu, &d->cpu_mask); + rdt_domain_reconfigure_cdp(r); + if (r->alloc_capable && domain_setup_ctrlval(r, d)) { kfree(d); return; diff --git a/arch/x86/kernel/cpu/intel_rdt.h b/arch/x86/kernel/cpu/intel_rdt.h index 3736f6dc9545..8412234eabd3 100644 --- a/arch/x86/kernel/cpu/intel_rdt.h +++ b/arch/x86/kernel/cpu/intel_rdt.h @@ -251,7 +251,6 @@ struct rftype { * struct mbm_state - status for each MBM counter in each domain * @chunks: Total data moved (multiply by rdt_group.mon_scale to get bytes) * @prev_msr Value of IA32_QM_CTR for this RMID last time we read it - * @chunks_bw Total local data moved. Used for bandwidth calculation * @prev_bw_msr:Value of previous IA32_QM_CTR for bandwidth counting * @prev_bw The most recent bandwidth in MBps * @delta_bw Difference between the current and previous bandwidth @@ -260,7 +259,6 @@ struct rftype { struct mbm_state { u64 chunks; u64 prev_msr; - u64 chunks_bw; u64 prev_bw_msr; u32 prev_bw; u32 delta_bw; @@ -567,5 +565,6 @@ void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms); void cqm_handle_limbo(struct work_struct *work); bool has_busy_rmid(struct rdt_resource *r, struct rdt_domain *d); void __check_limbo(struct rdt_domain *d, bool force_free); +void rdt_domain_reconfigure_cdp(struct rdt_resource *r); #endif /* _ASM_X86_INTEL_RDT_H */ diff --git a/arch/x86/kernel/cpu/intel_rdt_monitor.c b/arch/x86/kernel/cpu/intel_rdt_monitor.c index 3d4ec80a6bb9..5dfa5ab9a5ae 100644 --- a/arch/x86/kernel/cpu/intel_rdt_monitor.c +++ b/arch/x86/kernel/cpu/intel_rdt_monitor.c @@ -290,8 +290,6 @@ static void mbm_bw_count(u32 rmid, struct rmid_read *rr) return; chunks = mbm_overflow_count(m->prev_bw_msr, tval); - m->chunks_bw += chunks; - m->chunks = m->chunks_bw; cur_bw = (chunks * r->mon_scale) >> 20; if (m->delta_comp) @@ -461,15 +459,14 @@ static void mbm_update(struct rdt_domain *d, int rmid) } if (is_mbm_local_enabled()) { rr.evtid = QOS_L3_MBM_LOCAL_EVENT_ID; + __mon_event_count(rmid, &rr); /* * Call the MBA software controller only for the * control groups and when user has enabled * the software controller explicitly. */ - if (!is_mba_sc(NULL)) - __mon_event_count(rmid, &rr); - else + if (is_mba_sc(NULL)) mbm_bw_count(rmid, &rr); } } diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c index 11c5accfa4db..f406e3b85bdb 100644 --- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c +++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c @@ -515,85 +515,88 @@ unlock: return ret ?: nbytes; } -struct task_move_callback { - struct callback_head work; - struct rdtgroup *rdtgrp; -}; - -static void move_myself(struct callback_head *head) +/** + * rdtgroup_remove - the helper to remove resource group safely + * @rdtgrp: resource group to remove + * + * On resource group creation via a mkdir, an extra kernfs_node reference is + * taken to ensure that the rdtgroup structure remains accessible for the + * rdtgroup_kn_unlock() calls where it is removed. + * + * Drop the extra reference here, then free the rdtgroup structure. + * + * Return: void + */ +static void rdtgroup_remove(struct rdtgroup *rdtgrp) { - struct task_move_callback *callback; - struct rdtgroup *rdtgrp; - - callback = container_of(head, struct task_move_callback, work); - rdtgrp = callback->rdtgrp; + kernfs_put(rdtgrp->kn); + kfree(rdtgrp); +} +static void _update_task_closid_rmid(void *task) +{ /* - * If resource group was deleted before this task work callback - * was invoked, then assign the task to root group and free the - * resource group. + * If the task is still current on this CPU, update PQR_ASSOC MSR. + * Otherwise, the MSR is updated when the task is scheduled in. */ - if (atomic_dec_and_test(&rdtgrp->waitcount) && - (rdtgrp->flags & RDT_DELETED)) { - current->closid = 0; - current->rmid = 0; - kfree(rdtgrp); - } - - preempt_disable(); - /* update PQR_ASSOC MSR to make resource group go into effect */ - intel_rdt_sched_in(); - preempt_enable(); + if (task == current) + intel_rdt_sched_in(); +} - kfree(callback); +static void update_task_closid_rmid(struct task_struct *t) +{ + if (IS_ENABLED(CONFIG_SMP) && task_curr(t)) + smp_call_function_single(task_cpu(t), _update_task_closid_rmid, t, 1); + else + _update_task_closid_rmid(t); } static int __rdtgroup_move_task(struct task_struct *tsk, struct rdtgroup *rdtgrp) { - struct task_move_callback *callback; - int ret; - - callback = kzalloc(sizeof(*callback), GFP_KERNEL); - if (!callback) - return -ENOMEM; - callback->work.func = move_myself; - callback->rdtgrp = rdtgrp; + /* If the task is already in rdtgrp, no need to move the task. */ + if ((rdtgrp->type == RDTCTRL_GROUP && tsk->closid == rdtgrp->closid && + tsk->rmid == rdtgrp->mon.rmid) || + (rdtgrp->type == RDTMON_GROUP && tsk->rmid == rdtgrp->mon.rmid && + tsk->closid == rdtgrp->mon.parent->closid)) + return 0; /* - * Take a refcount, so rdtgrp cannot be freed before the - * callback has been invoked. + * Set the task's closid/rmid before the PQR_ASSOC MSR can be + * updated by them. + * + * For ctrl_mon groups, move both closid and rmid. + * For monitor groups, can move the tasks only from + * their parent CTRL group. */ - atomic_inc(&rdtgrp->waitcount); - ret = task_work_add(tsk, &callback->work, true); - if (ret) { - /* - * Task is exiting. Drop the refcount and free the callback. - * No need to check the refcount as the group cannot be - * deleted before the write function unlocks rdtgroup_mutex. - */ - atomic_dec(&rdtgrp->waitcount); - kfree(callback); - rdt_last_cmd_puts("task exited\n"); - } else { - /* - * For ctrl_mon groups move both closid and rmid. - * For monitor groups, can move the tasks only from - * their parent CTRL group. - */ - if (rdtgrp->type == RDTCTRL_GROUP) { - tsk->closid = rdtgrp->closid; + + if (rdtgrp->type == RDTCTRL_GROUP) { + tsk->closid = rdtgrp->closid; + tsk->rmid = rdtgrp->mon.rmid; + } else if (rdtgrp->type == RDTMON_GROUP) { + if (rdtgrp->mon.parent->closid == tsk->closid) { tsk->rmid = rdtgrp->mon.rmid; - } else if (rdtgrp->type == RDTMON_GROUP) { - if (rdtgrp->mon.parent->closid == tsk->closid) { - tsk->rmid = rdtgrp->mon.rmid; - } else { - rdt_last_cmd_puts("Can't move task to different control group\n"); - ret = -EINVAL; - } + } else { + rdt_last_cmd_puts("Can't move task to different control group\n"); + return -EINVAL; } } - return ret; + + /* + * Ensure the task's closid and rmid are written before determining if + * the task is current that will decide if it will be interrupted. + */ + barrier(); + + /* + * By now, the task's closid and rmid are set. If the task is current + * on a CPU, the PQR_ASSOC MSR needs to be updated to make the resource + * group go into effect. If the task is not current, the MSR will be + * updated when the task is scheduled in. + */ + update_task_closid_rmid(tsk); + + return 0; } /** @@ -1035,6 +1038,7 @@ static int rdt_cdp_peer_get(struct rdt_resource *r, struct rdt_domain *d, _d_cdp = rdt_find_domain(_r_cdp, d->id, NULL); if (WARN_ON(IS_ERR_OR_NULL(_d_cdp))) { _r_cdp = NULL; + _d_cdp = NULL; ret = -EINVAL; } @@ -1625,7 +1629,6 @@ static int rdtgroup_mkdir_info_resdir(struct rdt_resource *r, char *name, if (IS_ERR(kn_subdir)) return PTR_ERR(kn_subdir); - kernfs_get(kn_subdir); ret = rdtgroup_kn_set_ugid(kn_subdir); if (ret) return ret; @@ -1648,7 +1651,6 @@ static int rdtgroup_create_info_dir(struct kernfs_node *parent_kn) kn_info = kernfs_create_dir(parent_kn, "info", parent_kn->mode, NULL); if (IS_ERR(kn_info)) return PTR_ERR(kn_info); - kernfs_get(kn_info); ret = rdtgroup_add_files(kn_info, RF_TOP_INFO); if (ret) @@ -1669,12 +1671,6 @@ static int rdtgroup_create_info_dir(struct kernfs_node *parent_kn) goto out_destroy; } - /* - * This extra ref will be put in kernfs_remove() and guarantees - * that @rdtgrp->kn is always accessible. - */ - kernfs_get(kn_info); - ret = rdtgroup_kn_set_ugid(kn_info); if (ret) goto out_destroy; @@ -1703,12 +1699,6 @@ mongroup_create_dir(struct kernfs_node *parent_kn, struct rdtgroup *prgrp, if (dest_kn) *dest_kn = kn; - /* - * This extra ref will be put in kernfs_remove() and guarantees - * that @rdtgrp->kn is always accessible. - */ - kernfs_get(kn); - ret = rdtgroup_kn_set_ugid(kn); if (ret) goto out_destroy; @@ -1777,6 +1767,19 @@ static int set_cache_qos_cfg(int level, bool enable) return 0; } +/* Restore the qos cfg state when a domain comes online */ +void rdt_domain_reconfigure_cdp(struct rdt_resource *r) +{ + if (!r->alloc_capable) + return; + + if (r == &rdt_resources_all[RDT_RESOURCE_L2DATA]) + l2_qos_cfg_update(&r->alloc_enabled); + + if (r == &rdt_resources_all[RDT_RESOURCE_L3DATA]) + l3_qos_cfg_update(&r->alloc_enabled); +} + /* * Enable or disable the MBA software controller * which helps user specify bandwidth in MBps. @@ -1959,8 +1962,7 @@ void rdtgroup_kn_unlock(struct kernfs_node *kn) rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) rdtgroup_pseudo_lock_remove(rdtgrp); kernfs_unbreak_active_protection(kn); - kernfs_put(rdtgrp->kn); - kfree(rdtgrp); + rdtgroup_remove(rdtgrp); } else { kernfs_unbreak_active_protection(kn); } @@ -2011,7 +2013,6 @@ static struct dentry *rdt_mount(struct file_system_type *fs_type, dentry = ERR_PTR(ret); goto out_info; } - kernfs_get(kn_mongrp); ret = mkdir_mondata_all(rdtgroup_default.kn, &rdtgroup_default, &kn_mondata); @@ -2019,7 +2020,6 @@ static struct dentry *rdt_mount(struct file_system_type *fs_type, dentry = ERR_PTR(ret); goto out_mongrp; } - kernfs_get(kn_mondata); rdtgroup_default.mon.mon_data_kn = kn_mondata; } @@ -2171,7 +2171,7 @@ static void free_all_child_rdtgrp(struct rdtgroup *rdtgrp) if (atomic_read(&sentry->waitcount) != 0) sentry->flags = RDT_DELETED; else - kfree(sentry); + rdtgroup_remove(sentry); } } @@ -2213,7 +2213,7 @@ static void rmdir_all_sub(void) if (atomic_read(&rdtgrp->waitcount) != 0) rdtgrp->flags = RDT_DELETED; else - kfree(rdtgrp); + rdtgroup_remove(rdtgrp); } /* Notify online CPUs to update per cpu storage and PQR_ASSOC MSR */ update_closid_rmid(cpu_online_mask, &rdtgroup_default); @@ -2312,11 +2312,6 @@ static int mkdir_mondata_subdir(struct kernfs_node *parent_kn, if (IS_ERR(kn)) return PTR_ERR(kn); - /* - * This extra ref will be put in kernfs_remove() and guarantees - * that kn is always accessible. - */ - kernfs_get(kn); ret = rdtgroup_kn_set_ugid(kn); if (ret) goto out_destroy; @@ -2608,8 +2603,8 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn, /* * kernfs_remove() will drop the reference count on "kn" which * will free it. But we still need it to stick around for the - * rdtgroup_kn_unlock(kn} call below. Take one extra reference - * here, which will be dropped inside rdtgroup_kn_unlock(). + * rdtgroup_kn_unlock(kn) call. Take one extra reference here, + * which will be dropped by kernfs_put() in rdtgroup_remove(). */ kernfs_get(kn); @@ -2650,6 +2645,7 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn, out_idfree: free_rmid(rdtgrp->mon.rmid); out_destroy: + kernfs_put(rdtgrp->kn); kernfs_remove(rdtgrp->kn); out_free_rgrp: kfree(rdtgrp); @@ -2662,7 +2658,7 @@ static void mkdir_rdt_prepare_clean(struct rdtgroup *rgrp) { kernfs_remove(rgrp->kn); free_rmid(rgrp->mon.rmid); - kfree(rgrp); + rdtgroup_remove(rgrp); } /* @@ -2824,11 +2820,6 @@ static int rdtgroup_rmdir_mon(struct kernfs_node *kn, struct rdtgroup *rdtgrp, WARN_ON(list_empty(&prdtgrp->mon.crdtgrp_list)); list_del(&rdtgrp->mon.crdtgrp_list); - /* - * one extra hold on this, will drop when we kfree(rdtgrp) - * in rdtgroup_kn_unlock() - */ - kernfs_get(kn); kernfs_remove(rdtgrp->kn); return 0; @@ -2840,11 +2831,6 @@ static int rdtgroup_ctrl_remove(struct kernfs_node *kn, rdtgrp->flags = RDT_DELETED; list_del(&rdtgrp->rdtgroup_list); - /* - * one extra hold on this, will drop when we kfree(rdtgrp) - * in rdtgroup_kn_unlock() - */ - kernfs_get(kn); kernfs_remove(rdtgrp->kn); return 0; } @@ -2910,7 +2896,8 @@ static int rdtgroup_rmdir(struct kernfs_node *kn) * If the rdtgroup is a mon group and parent directory * is a valid "mon_groups" directory, remove the mon group. */ - if (rdtgrp->type == RDTCTRL_GROUP && parent_kn == rdtgroup_default.kn) { + if (rdtgrp->type == RDTCTRL_GROUP && parent_kn == rdtgroup_default.kn && + rdtgrp != &rdtgroup_default) { if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP || rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) { ret = rdtgroup_ctrl_remove(kn, rdtgrp); diff --git a/arch/x86/kernel/cpu/match.c b/arch/x86/kernel/cpu/match.c index 3fed38812eea..751e59057466 100644 --- a/arch/x86/kernel/cpu/match.c +++ b/arch/x86/kernel/cpu/match.c @@ -34,13 +34,18 @@ const struct x86_cpu_id *x86_match_cpu(const struct x86_cpu_id *match) const struct x86_cpu_id *m; struct cpuinfo_x86 *c = &boot_cpu_data; - for (m = match; m->vendor | m->family | m->model | m->feature; m++) { + for (m = match; + m->vendor | m->family | m->model | m->steppings | m->feature; + m++) { if (m->vendor != X86_VENDOR_ANY && c->x86_vendor != m->vendor) continue; if (m->family != X86_FAMILY_ANY && c->x86 != m->family) continue; if (m->model != X86_MODEL_ANY && c->x86_model != m->model) continue; + if (m->steppings != X86_STEPPING_ANY && + !(BIT(c->x86_stepping) & m->steppings)) + continue; if (m->feature != X86_FEATURE_ANY && !cpu_has(c, m->feature)) continue; return m; diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c index 1ceccc4a5472..9cc524be3c94 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-inject.c +++ b/arch/x86/kernel/cpu/mcheck/mce-inject.c @@ -518,7 +518,7 @@ static void do_inject(void) */ if (inj_type == DFR_INT_INJ) { i_mce.status |= MCI_STATUS_DEFERRED; - i_mce.status |= (i_mce.status & ~MCI_STATUS_UC); + i_mce.status &= ~MCI_STATUS_UC; } /* diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 1f69b12d5bb8..2a13468f8773 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -535,6 +535,13 @@ bool mce_is_memory_error(struct mce *m) } EXPORT_SYMBOL_GPL(mce_is_memory_error); +static bool whole_page(struct mce *m) +{ + if (!mca_cfg.ser || !(m->status & MCI_STATUS_MISCV)) + return true; + return MCI_MISC_ADDR_LSB(m->misc) >= PAGE_SHIFT; +} + bool mce_is_correctable(struct mce *m) { if (m->cpuvendor == X86_VENDOR_AMD && m->status & MCI_STATUS_DEFERRED) @@ -600,7 +607,7 @@ static int srao_decode_notifier(struct notifier_block *nb, unsigned long val, if (mce_usable_address(mce) && (mce->severity == MCE_AO_SEVERITY)) { pfn = mce->addr >> PAGE_SHIFT; if (!memory_failure(pfn, 0)) - set_mce_nospec(pfn); + set_mce_nospec(pfn, whole_page(mce)); } return NOTIFY_OK; @@ -1101,7 +1108,7 @@ static int do_memory_failure(struct mce *m) if (ret) pr_err("Memory error not recovered"); else - set_mce_nospec(m->addr >> PAGE_SHIFT); + set_mce_nospec(m->addr >> PAGE_SHIFT, whole_page(m)); return ret; } diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index a96091d44a45..eab4de387ce6 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -627,16 +627,16 @@ static ssize_t reload_store(struct device *dev, if (val != 1) return size; - tmp_ret = microcode_ops->request_microcode_fw(bsp, µcode_pdev->dev, true); - if (tmp_ret != UCODE_NEW) - return size; - get_online_cpus(); ret = check_online_cpus(); if (ret) goto put; + tmp_ret = microcode_ops->request_microcode_fw(bsp, µcode_pdev->dev, true); + if (tmp_ret != UCODE_NEW) + goto put; + mutex_lock(µcode_mutex); ret = microcode_reload_late(); mutex_unlock(µcode_mutex); diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index 16936a24795c..3aa0e5a45303 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -103,53 +103,6 @@ static int has_newer_microcode(void *mc, unsigned int csig, int cpf, int new_rev return find_matching_signature(mc, csig, cpf); } -/* - * Given CPU signature and a microcode patch, this function finds if the - * microcode patch has matching family and model with the CPU. - * - * %true - if there's a match - * %false - otherwise - */ -static bool microcode_matches(struct microcode_header_intel *mc_header, - unsigned long sig) -{ - unsigned long total_size = get_totalsize(mc_header); - unsigned long data_size = get_datasize(mc_header); - struct extended_sigtable *ext_header; - unsigned int fam_ucode, model_ucode; - struct extended_signature *ext_sig; - unsigned int fam, model; - int ext_sigcount, i; - - fam = x86_family(sig); - model = x86_model(sig); - - fam_ucode = x86_family(mc_header->sig); - model_ucode = x86_model(mc_header->sig); - - if (fam == fam_ucode && model == model_ucode) - return true; - - /* Look for ext. headers: */ - if (total_size <= data_size + MC_HEADER_SIZE) - return false; - - ext_header = (void *) mc_header + data_size + MC_HEADER_SIZE; - ext_sig = (void *)ext_header + EXT_HEADER_SIZE; - ext_sigcount = ext_header->count; - - for (i = 0; i < ext_sigcount; i++) { - fam_ucode = x86_family(ext_sig->sig); - model_ucode = x86_model(ext_sig->sig); - - if (fam == fam_ucode && model == model_ucode) - return true; - - ext_sig++; - } - return false; -} - static struct ucode_patch *memdup_patch(void *data, unsigned int size) { struct ucode_patch *p; @@ -167,7 +120,7 @@ static struct ucode_patch *memdup_patch(void *data, unsigned int size) return p; } -static void save_microcode_patch(void *data, unsigned int size) +static void save_microcode_patch(struct ucode_cpu_info *uci, void *data, unsigned int size) { struct microcode_header_intel *mc_hdr, *mc_saved_hdr; struct ucode_patch *iter, *tmp, *p = NULL; @@ -213,6 +166,9 @@ static void save_microcode_patch(void *data, unsigned int size) if (!p) return; + if (!find_matching_signature(p->data, uci->cpu_sig.sig, uci->cpu_sig.pf)) + return; + /* * Save for early loading. On 32-bit, that needs to be a physical * address as the APs are running from physical addresses, before @@ -347,13 +303,14 @@ scan_microcode(void *data, size_t size, struct ucode_cpu_info *uci, bool save) size -= mc_size; - if (!microcode_matches(mc_header, uci->cpu_sig.sig)) { + if (!find_matching_signature(data, uci->cpu_sig.sig, + uci->cpu_sig.pf)) { data += mc_size; continue; } if (save) { - save_microcode_patch(data, mc_size); + save_microcode_patch(uci, data, mc_size); goto next; } @@ -486,14 +443,14 @@ static void show_saved_mc(void) * Save this microcode patch. It will be loaded early when a CPU is * hot-added or resumes. */ -static void save_mc_for_early(u8 *mc, unsigned int size) +static void save_mc_for_early(struct ucode_cpu_info *uci, u8 *mc, unsigned int size) { /* Synchronization during CPU hotplug. */ static DEFINE_MUTEX(x86_cpu_microcode_mutex); mutex_lock(&x86_cpu_microcode_mutex); - save_microcode_patch(mc, size); + save_microcode_patch(uci, mc, size); show_saved_mc(); mutex_unlock(&x86_cpu_microcode_mutex); @@ -937,7 +894,7 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size, * permanent memory. So it will be loaded early when a CPU is hot added * or resumes. */ - save_mc_for_early(new_mc, new_mc_size); + save_mc_for_early(uci, new_mc, new_mc_size); pr_debug("CPU%d found a matching microcode update with version 0x%x (current=0x%x)\n", cpu, new_rev, uci->cpu_sig.rev); diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 852e74e48890..f8b0fa2dbe37 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -214,8 +214,8 @@ static void __init ms_hyperv_init_platform(void) ms_hyperv.misc_features = cpuid_edx(HYPERV_CPUID_FEATURES); ms_hyperv.hints = cpuid_eax(HYPERV_CPUID_ENLIGHTMENT_INFO); - pr_info("Hyper-V: features 0x%x, hints 0x%x\n", - ms_hyperv.features, ms_hyperv.hints); + pr_info("Hyper-V: features 0x%x, hints 0x%x, misc 0x%x\n", + ms_hyperv.features, ms_hyperv.hints, ms_hyperv.misc_features); ms_hyperv.max_vp_index = cpuid_eax(HYPERV_CPUID_IMPLEMENT_LIMITS); ms_hyperv.max_lp_index = cpuid_ebx(HYPERV_CPUID_IMPLEMENT_LIMITS); @@ -250,6 +250,16 @@ static void __init ms_hyperv_init_platform(void) cpuid_eax(HYPERV_CPUID_NESTED_FEATURES); } + /* + * Hyper-V expects to get crash register data or kmsg when + * crash enlightment is available and system crashes. Set + * crash_kexec_post_notifiers to be true to make sure that + * calling crash enlightment interface before running kdump + * kernel. + */ + if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE) + crash_kexec_post_notifiers = true; + #ifdef CONFIG_X86_LOCAL_APIC if (ms_hyperv.features & HV_X64_ACCESS_FREQUENCY_MSRS && ms_hyperv.misc_features & HV_FEATURE_FREQUENCY_MSRS_AVAILABLE) { diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index e12ee86906c6..9436f3452049 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -166,9 +166,6 @@ static u8 mtrr_type_lookup_variable(u64 start, u64 end, u64 *partial_end, *repeat = 0; *uniform = 1; - /* Make end inclusive instead of exclusive */ - end--; - prev_match = MTRR_TYPE_INVALID; for (i = 0; i < num_var_ranges; ++i) { unsigned short start_state, end_state, inclusive; @@ -260,6 +257,9 @@ u8 mtrr_type_lookup(u64 start, u64 end, u8 *uniform) int repeat; u64 partial_end; + /* Make end inclusive instead of exclusive */ + end--; + if (!mtrr_state_set) return MTRR_TYPE_INVALID; diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index f631a3f15587..91b3483e5085 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -356,7 +356,7 @@ int crash_setup_memmap_entries(struct kimage *image, struct boot_params *params) struct crash_memmap_data cmd; struct crash_mem *cmem; - cmem = vzalloc(sizeof(struct crash_mem)); + cmem = vzalloc(struct_size(cmem, ranges, 1)); if (!cmem) return -ENOMEM; diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c index 6abd83572b01..9692ccc583bb 100644 --- a/arch/x86/kernel/fpu/init.c +++ b/arch/x86/kernel/fpu/init.c @@ -249,9 +249,9 @@ static void __init fpu__init_system_ctx_switch(void) */ static void __init fpu__init_parse_early_param(void) { - char arg[32]; + char arg[128]; char *argptr = arg; - int bit; + int arglen, res, bit; if (cmdline_find_option_bool(boot_command_line, "no387")) setup_clear_cpu_cap(X86_FEATURE_FPU); @@ -271,12 +271,26 @@ static void __init fpu__init_parse_early_param(void) if (cmdline_find_option_bool(boot_command_line, "noxsaves")) setup_clear_cpu_cap(X86_FEATURE_XSAVES); - if (cmdline_find_option(boot_command_line, "clearcpuid", arg, - sizeof(arg)) && - get_option(&argptr, &bit) && - bit >= 0 && - bit < NCAPINTS * 32) - setup_clear_cpu_cap(bit); + arglen = cmdline_find_option(boot_command_line, "clearcpuid", arg, sizeof(arg)); + if (arglen <= 0) + return; + + pr_info("Clearing CPUID bits:"); + do { + res = get_option(&argptr, &bit); + if (res == 0 || res == 3) + break; + + /* If the argument was too long, the last bit may be cut off */ + if (res == 1 && arglen >= sizeof(arg)) + break; + + if (bit >= 0 && bit < NCAPINTS * 32) { + pr_cont(" " X86_CAP_FMT, x86_cap_flag(bit)); + setup_clear_cpu_cap(bit); + } + } while (res == 2); + pr_cont("\n"); } /* diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 87a57b7642d3..601a5da1d196 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -907,8 +907,6 @@ const void *get_xsave_field_ptr(int xsave_state) #ifdef CONFIG_ARCH_HAS_PKEYS -#define NR_VALID_PKRU_BITS (CONFIG_NR_PROTECTION_KEYS * 2) -#define PKRU_VALID_MASK (NR_VALID_PKRU_BITS - 1) /* * This will go out and modify PKRU register to set the access * rights for @pkey to @init_val. @@ -927,6 +925,13 @@ int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, if (!boot_cpu_has(X86_FEATURE_OSPKE)) return -EINVAL; + /* + * This code should only be called with valid 'pkey' + * values originating from in-kernel users. Complain + * if a bad value is observed. + */ + WARN_ON_ONCE(pkey >= arch_max_pkey()); + /* Set the bits we need in PKRU: */ if (init_val & PKEY_DISABLE_ACCESS) new_pkru_bits |= PKRU_AD_BIT; @@ -964,18 +969,31 @@ static inline bool xfeatures_mxcsr_quirk(u64 xfeatures) return true; } -/* - * This is similar to user_regset_copyout(), but will not add offset to - * the source data pointer or increment pos, count, kbuf, and ubuf. - */ -static inline void -__copy_xstate_to_kernel(void *kbuf, const void *data, - unsigned int offset, unsigned int size, unsigned int size_total) +static void fill_gap(unsigned to, void **kbuf, unsigned *pos, unsigned *count) { - if (offset < size_total) { - unsigned int copy = min(size, size_total - offset); + if (*pos < to) { + unsigned size = to - *pos; + + if (size > *count) + size = *count; + memcpy(*kbuf, (void *)&init_fpstate.xsave + *pos, size); + *kbuf += size; + *pos += size; + *count -= size; + } +} - memcpy(kbuf + offset, data, copy); +static void copy_part(unsigned offset, unsigned size, void *from, + void **kbuf, unsigned *pos, unsigned *count) +{ + fill_gap(offset, kbuf, pos, count); + if (size > *count) + size = *count; + if (size) { + memcpy(*kbuf, from, size); + *kbuf += size; + *pos += size; + *count -= size; } } @@ -988,8 +1006,9 @@ __copy_xstate_to_kernel(void *kbuf, const void *data, */ int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int offset_start, unsigned int size_total) { - unsigned int offset, size; struct xstate_header header; + const unsigned off_mxcsr = offsetof(struct fxregs_state, mxcsr); + unsigned count = size_total; int i; /* @@ -1005,46 +1024,42 @@ int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int of header.xfeatures = xsave->header.xfeatures; header.xfeatures &= ~XFEATURE_MASK_SUPERVISOR; + if (header.xfeatures & XFEATURE_MASK_FP) + copy_part(0, off_mxcsr, + &xsave->i387, &kbuf, &offset_start, &count); + if (header.xfeatures & (XFEATURE_MASK_SSE | XFEATURE_MASK_YMM)) + copy_part(off_mxcsr, MXCSR_AND_FLAGS_SIZE, + &xsave->i387.mxcsr, &kbuf, &offset_start, &count); + if (header.xfeatures & XFEATURE_MASK_FP) + copy_part(offsetof(struct fxregs_state, st_space), 128, + &xsave->i387.st_space, &kbuf, &offset_start, &count); + if (header.xfeatures & XFEATURE_MASK_SSE) + copy_part(xstate_offsets[XFEATURE_SSE], 256, + &xsave->i387.xmm_space, &kbuf, &offset_start, &count); + /* + * Fill xsave->i387.sw_reserved value for ptrace frame: + */ + copy_part(offsetof(struct fxregs_state, sw_reserved), 48, + xstate_fx_sw_bytes, &kbuf, &offset_start, &count); /* * Copy xregs_state->header: */ - offset = offsetof(struct xregs_state, header); - size = sizeof(header); - - __copy_xstate_to_kernel(kbuf, &header, offset, size, size_total); + copy_part(offsetof(struct xregs_state, header), sizeof(header), + &header, &kbuf, &offset_start, &count); - for (i = 0; i < XFEATURE_MAX; i++) { + for (i = FIRST_EXTENDED_XFEATURE; i < XFEATURE_MAX; i++) { /* * Copy only in-use xstates: */ if ((header.xfeatures >> i) & 1) { void *src = __raw_xsave_addr(xsave, 1 << i); - offset = xstate_offsets[i]; - size = xstate_sizes[i]; - - /* The next component has to fit fully into the output buffer: */ - if (offset + size > size_total) - break; - - __copy_xstate_to_kernel(kbuf, src, offset, size, size_total); + copy_part(xstate_offsets[i], xstate_sizes[i], + src, &kbuf, &offset_start, &count); } } - - if (xfeatures_mxcsr_quirk(header.xfeatures)) { - offset = offsetof(struct fxregs_state, mxcsr); - size = MXCSR_AND_FLAGS_SIZE; - __copy_xstate_to_kernel(kbuf, &xsave->i387.mxcsr, offset, size, size_total); - } - - /* - * Fill xsave->i387.sw_reserved value for ptrace frame: - */ - offset = offsetof(struct fxregs_state, sw_reserved); - size = sizeof(xstate_fx_sw_bytes); - - __copy_xstate_to_kernel(kbuf, xstate_fx_sw_bytes, offset, size, size_total); + fill_gap(size_total, &kbuf, &offset_start, &count); return 0; } diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c index 519649ddf100..fe522691ac71 100644 --- a/arch/x86/kernel/i8259.c +++ b/arch/x86/kernel/i8259.c @@ -207,7 +207,7 @@ spurious_8259A_irq: * lets ACK and report it. [once per IRQ] */ if (!(spurious_irq_mask & irqmask)) { - printk(KERN_DEBUG + printk_deferred(KERN_DEBUG "spurious 8259A interrupt: IRQ%d.\n", irq); spurious_irq_mask |= irqmask; } diff --git a/arch/x86/kernel/idt.c b/arch/x86/kernel/idt.c index a7e0e975043f..e1f9355307b8 100644 --- a/arch/x86/kernel/idt.c +++ b/arch/x86/kernel/idt.c @@ -320,7 +320,11 @@ void __init idt_setup_apic_and_irq_gates(void) #ifdef CONFIG_X86_LOCAL_APIC for_each_clear_bit_from(i, system_vectors, NR_VECTORS) { - set_bit(i, system_vectors); + /* + * Don't set the non assigned system vectors in the + * system_vectors bitmap. Otherwise they show up in + * /proc/interrupts. + */ entry = spurious_entries_start + 8 * (i - FIRST_SYSTEM_VECTOR); set_intr_gate(i, entry); } diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c index 9490a2845f14..273687986a26 100644 --- a/arch/x86/kernel/kexec-bzimage64.c +++ b/arch/x86/kernel/kexec-bzimage64.c @@ -211,8 +211,7 @@ setup_boot_parameters(struct kimage *image, struct boot_params *params, params->hdr.hardware_subarch = boot_params.hdr.hardware_subarch; /* Copying screen_info will do? */ - memcpy(¶ms->screen_info, &boot_params.screen_info, - sizeof(struct screen_info)); + memcpy(¶ms->screen_info, &screen_info, sizeof(struct screen_info)); /* Fill in memsize later */ params->screen_info.ext_mem_k = 0; diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 173e915e11d5..3334e1400345 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -170,6 +170,8 @@ NOKPROBE_SYMBOL(skip_prefixes); int can_boost(struct insn *insn, void *addr) { kprobe_opcode_t opcode; + insn_byte_t prefix; + int i; if (search_exception_tables((unsigned long)addr)) return 0; /* Page fault may occur on this address. */ @@ -182,9 +184,14 @@ int can_boost(struct insn *insn, void *addr) if (insn->opcode.nbytes != 1) return 0; - /* Can't boost Address-size override prefix */ - if (unlikely(inat_is_address_size_prefix(insn->attr))) - return 0; + for_each_insn_prefix(insn, i, prefix) { + insn_attr_t attr; + + attr = inat_get_opcode_attribute(prefix); + /* Can't boost Address-size override prefix and CS override prefix */ + if (prefix == 0x2e || inat_is_address_size_prefix(attr)) + return 0; + } opcode = insn->opcode.bytes[0]; @@ -209,8 +216,8 @@ int can_boost(struct insn *insn, void *addr) /* clear and set flags are boostable */ return (opcode == 0xf5 || (0xf7 < opcode && opcode < 0xfe)); default: - /* CS override prefix and call are not boostable */ - return (opcode != 0x2e && opcode != 0x9a); + /* call is not boostable */ + return opcode != 0x9a; } } @@ -765,16 +772,11 @@ asm( NOKPROBE_SYMBOL(kretprobe_trampoline); STACK_FRAME_NON_STANDARD(kretprobe_trampoline); -static struct kprobe kretprobe_kprobe = { - .addr = (void *)kretprobe_trampoline, -}; - /* * Called from kretprobe_trampoline */ __visible __used void *trampoline_handler(struct pt_regs *regs) { - struct kprobe_ctlblk *kcb; struct kretprobe_instance *ri = NULL; struct hlist_head *head, empty_rp; struct hlist_node *tmp; @@ -784,16 +786,12 @@ __visible __used void *trampoline_handler(struct pt_regs *regs) void *frame_pointer; bool skipped = false; - preempt_disable(); - /* * Set a dummy kprobe for avoiding kretprobe recursion. * Since kretprobe never run in kprobe handler, kprobe must not * be running at this point. */ - kcb = get_kprobe_ctlblk(); - __this_cpu_write(current_kprobe, &kretprobe_kprobe); - kcb->kprobe_status = KPROBE_HIT_ACTIVE; + kprobe_busy_begin(); INIT_HLIST_HEAD(&empty_rp); kretprobe_hash_lock(current, &head, &flags); @@ -872,7 +870,7 @@ __visible __used void *trampoline_handler(struct pt_regs *regs) __this_cpu_write(current_kprobe, &ri->rp->kp); ri->ret_addr = correct_ret_addr; ri->rp->handler(ri, regs); - __this_cpu_write(current_kprobe, &kretprobe_kprobe); + __this_cpu_write(current_kprobe, &kprobe_busy); } recycle_rp_inst(ri, &empty_rp); @@ -888,8 +886,7 @@ __visible __used void *trampoline_handler(struct pt_regs *regs) kretprobe_hash_unlock(current, &flags); - __this_cpu_write(current_kprobe, NULL); - preempt_enable(); + kprobe_busy_end(); hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) { hlist_del(&ri->hlist); @@ -1051,6 +1048,11 @@ int kprobe_fault_handler(struct pt_regs *regs, int trapnr) * So clear it by resetting the current kprobe: */ regs->flags &= ~X86_EFLAGS_TF; + /* + * Since the single step (trap) has been cancelled, + * we need to restore BTF here. + */ + restore_btf(); /* * If the TF flag was set before the kprobe hit, diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c index 6645f123419c..9f0be2c7e346 100644 --- a/arch/x86/kernel/module.c +++ b/arch/x86/kernel/module.c @@ -126,6 +126,7 @@ int apply_relocate(Elf32_Shdr *sechdrs, *location += sym->st_value; break; case R_386_PC32: + case R_386_PLT32: /* Add the value, subtract its position */ *location += sym->st_value - (uint32_t)location; break; diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index 0f8b9b900b0e..996eb53f8eb7 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -104,7 +104,6 @@ fs_initcall(nmi_warning_debugfs); static void nmi_check_duration(struct nmiaction *action, u64 duration) { - u64 whole_msecs = READ_ONCE(action->max_duration); int remainder_ns, decimal_msecs; if (duration < nmi_longest_ns || duration < action->max_duration) @@ -112,12 +111,12 @@ static void nmi_check_duration(struct nmiaction *action, u64 duration) action->max_duration = duration; - remainder_ns = do_div(whole_msecs, (1000 * 1000)); + remainder_ns = do_div(duration, (1000 * 1000)); decimal_msecs = remainder_ns / 1000; printk_ratelimited(KERN_INFO "INFO: NMI handler (%ps) took too long to run: %lld.%03d msecs\n", - action->handler, whole_msecs, decimal_msecs); + action->handler, duration, decimal_msecs); } static int nmi_handle(unsigned int type, struct pt_regs *regs) diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index b8b08e61ac73..cd138bfd926c 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -413,28 +413,20 @@ static __always_inline void __speculation_ctrl_update(unsigned long tifp, lockdep_assert_irqs_disabled(); - /* - * If TIF_SSBD is different, select the proper mitigation - * method. Note that if SSBD mitigation is disabled or permanentely - * enabled this branch can't be taken because nothing can set - * TIF_SSBD. - */ - if (tif_diff & _TIF_SSBD) { - if (static_cpu_has(X86_FEATURE_VIRT_SSBD)) { + /* Handle change of TIF_SSBD depending on the mitigation method. */ + if (static_cpu_has(X86_FEATURE_VIRT_SSBD)) { + if (tif_diff & _TIF_SSBD) amd_set_ssb_virt_state(tifn); - } else if (static_cpu_has(X86_FEATURE_LS_CFG_SSBD)) { + } else if (static_cpu_has(X86_FEATURE_LS_CFG_SSBD)) { + if (tif_diff & _TIF_SSBD) amd_set_core_ssb_state(tifn); - } else if (static_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) || - static_cpu_has(X86_FEATURE_AMD_SSBD)) { - msr |= ssbd_tif_to_spec_ctrl(tifn); - updmsr = true; - } + } else if (static_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) || + static_cpu_has(X86_FEATURE_AMD_SSBD)) { + updmsr |= !!(tif_diff & _TIF_SSBD); + msr |= ssbd_tif_to_spec_ctrl(tifn); } - /* - * Only evaluate TIF_SPEC_IB if conditional STIBP is enabled, - * otherwise avoid the MSR write. - */ + /* Only evaluate TIF_SPEC_IB if conditional STIBP is enabled. */ if (IS_ENABLED(CONFIG_SMP) && static_branch_unlikely(&switch_to_cond_stibp)) { updmsr |= !!(tif_diff & _TIF_SPEC_IB); diff --git a/arch/x86/kernel/process.h b/arch/x86/kernel/process.h index 898e97cf6629..320ab978fb1f 100644 --- a/arch/x86/kernel/process.h +++ b/arch/x86/kernel/process.h @@ -19,7 +19,7 @@ static inline void switch_to_extra(struct task_struct *prev, if (IS_ENABLED(CONFIG_SMP)) { /* * Avoid __switch_to_xtra() invocation when conditional - * STIPB is disabled and the only different bit is + * STIBP is disabled and the only different bit is * TIF_SPEC_IB. For CONFIG_SMP=n TIF_SPEC_IB is not * in the TIF_WORK_CTXSW masks. */ diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 8d4d50645310..1401f86e4007 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -374,7 +374,7 @@ static unsigned long task_seg_base(struct task_struct *task, */ mutex_lock(&task->mm->context.lock); ldt = task->mm->context.ldt; - if (unlikely(idx >= ldt->nr_entries)) + if (unlikely(!ldt || idx >= ldt->nr_entries)) base = 0; else base = get_desc_base(ldt->entries + idx); diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 8fd3cedd9acc..6489cc19ed06 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -197,6 +197,14 @@ static const struct dmi_system_id reboot_dmi_table[] __initconst = { DMI_MATCH(DMI_PRODUCT_NAME, "MacBook5"), }, }, + { /* Handle problems with rebooting on Apple MacBook6,1 */ + .callback = set_pci_reboot, + .ident = "Apple MacBook6,1", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "MacBook6,1"), + }, + }, { /* Handle problems with rebooting on Apple MacBookPro5 */ .callback = set_pci_reboot, .ident = "Apple MacBookPro5", @@ -469,6 +477,15 @@ static const struct dmi_system_id reboot_dmi_table[] __initconst = { }, }, + { /* PCIe Wifi card isn't detected after reboot otherwise */ + .callback = set_pci_reboot, + .ident = "Zotac ZBOX CI327 nano", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "NA"), + DMI_MATCH(DMI_PRODUCT_NAME, "ZBOX-CI327NANO-GS-01"), + }, + }, + /* Sony */ { /* Handle problems with rebooting on Sony VGN-Z540N */ .callback = set_bios_reboot, @@ -530,29 +547,20 @@ static void emergency_vmx_disable_all(void) local_irq_disable(); /* - * We need to disable VMX on all CPUs before rebooting, otherwise - * we risk hanging up the machine, because the CPU ignore INIT - * signals when VMX is enabled. - * - * We can't take any locks and we may be on an inconsistent - * state, so we use NMIs as IPIs to tell the other CPUs to disable - * VMX and halt. + * Disable VMX on all CPUs before rebooting, otherwise we risk hanging + * the machine, because the CPU blocks INIT when it's in VMX root. * - * For safety, we will avoid running the nmi_shootdown_cpus() - * stuff unnecessarily, but we don't have a way to check - * if other CPUs have VMX enabled. So we will call it only if the - * CPU we are running on has VMX enabled. + * We can't take any locks and we may be on an inconsistent state, so + * use NMIs as IPIs to tell the other CPUs to exit VMX root and halt. * - * We will miss cases where VMX is not enabled on all CPUs. This - * shouldn't do much harm because KVM always enable VMX on all - * CPUs anyway. But we can miss it on the small window where KVM - * is still enabling VMX. + * Do the NMI shootdown even if VMX if off on _this_ CPU, as that + * doesn't prevent a different CPU from being in VMX root operation. */ - if (cpu_has_vmx() && cpu_vmx_enabled()) { - /* Disable VMX on this CPU. */ - cpu_vmxoff(); + if (cpu_has_vmx()) { + /* Safely force _this_ CPU out of VMX root operation. */ + __cpu_emergency_vmxoff(); - /* Halt and disable VMX on the other CPUs */ + /* Halt and exit VMX root operation on the other CPUs. */ nmi_shootdown_cpus(vmxoff_nmi); } diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 90ecc108bc8a..652a10a3219d 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -1176,6 +1176,8 @@ void __init setup_arch(char **cmdline_p) reserve_initrd(); acpi_table_upgrade(); + /* Look for ACPI tables and reserve memory occupied by them. */ + acpi_boot_table_init(); vsmp_init(); @@ -1183,11 +1185,6 @@ void __init setup_arch(char **cmdline_p) early_platform_quirks(); - /* - * Parse the ACPI tables for possible boot-time SMP configuration. - */ - acpi_boot_table_init(); - early_acpi_boot_init(); initmem_init(); diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 44e647a65de8..16e908000550 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -776,30 +776,8 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs) static inline unsigned long get_nr_restart_syscall(const struct pt_regs *regs) { - /* - * This function is fundamentally broken as currently - * implemented. - * - * The idea is that we want to trigger a call to the - * restart_block() syscall and that we want in_ia32_syscall(), - * in_x32_syscall(), etc. to match whatever they were in the - * syscall being restarted. We assume that the syscall - * instruction at (regs->ip - 2) matches whatever syscall - * instruction we used to enter in the first place. - * - * The problem is that we can get here when ptrace pokes - * syscall-like values into regs even if we're not in a syscall - * at all. - * - * For now, we maintain historical behavior and guess based on - * stored state. We could do better by saving the actual - * syscall arch in restart_block or (with caveats on x32) by - * checking if regs->ip points to 'int $0x80'. The current - * behavior is incorrect if a tracer has a different bitness - * than the tracee. - */ #ifdef CONFIG_IA32_EMULATION - if (current_thread_info()->status & (TS_COMPAT|TS_I386_REGS_POKED)) + if (current_thread_info()->status & TS_COMPAT_RESTART) return __NR_ia32_restart_syscall; #endif #ifdef CONFIG_X86_X32_ABI diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 6489067b78a4..8783d065f927 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -269,6 +269,14 @@ static void notrace start_secondary(void *unused) wmb(); cpu_startup_entry(CPUHP_AP_ONLINE_IDLE); + + /* + * Prevent tail call to cpu_startup_entry() because the stack protector + * guard has been changed a couple of function calls up, in + * boot_init_stack_canary() and must not be checked before tail calling + * another function. + */ + prevent_tail_call_optimization(); } /** diff --git a/arch/x86/kernel/time.c b/arch/x86/kernel/time.c index fddaefc51fb6..0680a2e9e06b 100644 --- a/arch/x86/kernel/time.c +++ b/arch/x86/kernel/time.c @@ -24,10 +24,6 @@ #include <asm/hpet.h> #include <asm/time.h> -#ifdef CONFIG_X86_64 -__visible volatile unsigned long jiffies __cacheline_aligned_in_smp = INITIAL_JIFFIES; -#endif - unsigned long profile_pc(struct pt_regs *regs) { unsigned long pc = instruction_pointer(regs); diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c index 89be1be1790c..4f17c1c94949 100644 --- a/arch/x86/kernel/unwind_orc.c +++ b/arch/x86/kernel/unwind_orc.c @@ -131,9 +131,6 @@ static struct orc_entry *orc_find(unsigned long ip) { static struct orc_entry *orc; - if (!orc_init) - return NULL; - if (ip == 0) return &null_orc_entry; @@ -349,8 +346,8 @@ static bool deref_stack_regs(struct unwind_state *state, unsigned long addr, if (!stack_access_ok(state, addr, sizeof(struct pt_regs))) return false; - *ip = regs->ip; - *sp = regs->sp; + *ip = READ_ONCE_NOCHECK(regs->ip); + *sp = READ_ONCE_NOCHECK(regs->sp); return true; } @@ -362,14 +359,43 @@ static bool deref_stack_iret_regs(struct unwind_state *state, unsigned long addr if (!stack_access_ok(state, addr, IRET_FRAME_SIZE)) return false; - *ip = regs->ip; - *sp = regs->sp; + *ip = READ_ONCE_NOCHECK(regs->ip); + *sp = READ_ONCE_NOCHECK(regs->sp); return true; } +/* + * If state->regs is non-NULL, and points to a full pt_regs, just get the reg + * value from state->regs. + * + * Otherwise, if state->regs just points to IRET regs, and the previous frame + * had full regs, it's safe to get the value from the previous regs. This can + * happen when early/late IRQ entry code gets interrupted by an NMI. + */ +static bool get_reg(struct unwind_state *state, unsigned int reg_off, + unsigned long *val) +{ + unsigned int reg = reg_off/8; + + if (!state->regs) + return false; + + if (state->full_regs) { + *val = READ_ONCE_NOCHECK(((unsigned long *)state->regs)[reg]); + return true; + } + + if (state->prev_regs) { + *val = READ_ONCE_NOCHECK(((unsigned long *)state->prev_regs)[reg]); + return true; + } + + return false; +} + bool unwind_next_frame(struct unwind_state *state) { - unsigned long ip_p, sp, orig_ip = state->ip, prev_sp = state->sp; + unsigned long ip_p, sp, tmp, orig_ip = state->ip, prev_sp = state->sp; enum stack_type prev_type = state->stack_info.type; struct orc_entry *orc; bool indirect = false; @@ -387,8 +413,11 @@ bool unwind_next_frame(struct unwind_state *state) /* * Find the orc_entry associated with the text address. * - * Decrement call return addresses by one so they work for sibling - * calls and calls to noreturn functions. + * For a call frame (as opposed to a signal frame), state->ip points to + * the instruction after the call. That instruction's stack layout + * could be different from the call instruction's layout, for example + * if the call was to a noreturn function. So get the ORC data for the + * call instruction itself. */ orc = orc_find(state->signal ? state->ip : state->ip - 1); if (!orc) @@ -423,39 +452,35 @@ bool unwind_next_frame(struct unwind_state *state) break; case ORC_REG_R10: - if (!state->regs || !state->full_regs) { + if (!get_reg(state, offsetof(struct pt_regs, r10), &sp)) { orc_warn("missing regs for base reg R10 at ip %pB\n", (void *)state->ip); goto err; } - sp = state->regs->r10; break; case ORC_REG_R13: - if (!state->regs || !state->full_regs) { + if (!get_reg(state, offsetof(struct pt_regs, r13), &sp)) { orc_warn("missing regs for base reg R13 at ip %pB\n", (void *)state->ip); goto err; } - sp = state->regs->r13; break; case ORC_REG_DI: - if (!state->regs || !state->full_regs) { + if (!get_reg(state, offsetof(struct pt_regs, di), &sp)) { orc_warn("missing regs for base reg DI at ip %pB\n", (void *)state->ip); goto err; } - sp = state->regs->di; break; case ORC_REG_DX: - if (!state->regs || !state->full_regs) { + if (!get_reg(state, offsetof(struct pt_regs, dx), &sp)) { orc_warn("missing regs for base reg DX at ip %pB\n", (void *)state->ip); goto err; } - sp = state->regs->dx; break; default: @@ -482,6 +507,7 @@ bool unwind_next_frame(struct unwind_state *state) state->sp = sp; state->regs = NULL; + state->prev_regs = NULL; state->signal = false; break; @@ -493,6 +519,7 @@ bool unwind_next_frame(struct unwind_state *state) } state->regs = (struct pt_regs *)sp; + state->prev_regs = NULL; state->full_regs = true; state->signal = true; break; @@ -504,6 +531,8 @@ bool unwind_next_frame(struct unwind_state *state) goto err; } + if (state->full_regs) + state->prev_regs = state->regs; state->regs = (void *)sp - IRET_FRAME_OFFSET; state->full_regs = false; state->signal = true; @@ -512,14 +541,14 @@ bool unwind_next_frame(struct unwind_state *state) default: orc_warn("unknown .orc_unwind entry type %d for ip %pB\n", orc->type, (void *)orig_ip); - break; + goto err; } /* Find BP: */ switch (orc->bp_reg) { case ORC_REG_UNDEFINED: - if (state->regs && state->full_regs) - state->bp = state->regs->bp; + if (get_reg(state, offsetof(struct pt_regs, bp), &tmp)) + state->bp = tmp; break; case ORC_REG_PREV_SP: @@ -566,17 +595,20 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task, memset(state, 0, sizeof(*state)); state->task = task; + if (!orc_init) + goto err; + /* * Refuse to unwind the stack of a task while it's executing on another * CPU. This check is racy, but that's ok: the unwinder has other * checks to prevent it from going off the rails. */ if (task_on_another_cpu(task)) - goto done; + goto err; if (regs) { if (user_mode(regs)) - goto done; + goto the_end; state->ip = regs->ip; state->sp = kernel_stack_pointer(regs); @@ -595,9 +627,10 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task, } else { struct inactive_task_frame *frame = (void *)task->thread.sp; - state->sp = task->thread.sp; + state->sp = task->thread.sp + sizeof(*frame); state->bp = READ_ONCE_NOCHECK(frame->bp); state->ip = READ_ONCE_NOCHECK(frame->ret_addr); + state->signal = (void *)state->ip == ret_from_fork; } if (get_stack_info((unsigned long *)state->sp, state->task, @@ -609,6 +642,7 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task, * generate some kind of backtrace if this happens. */ void *next_page = (void *)PAGE_ALIGN((unsigned long)state->sp); + state->error = true; if (get_stack_info(next_page, state->task, &state->stack_info, &state->stack_mask)) return; @@ -629,13 +663,14 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task, /* Otherwise, skip ahead to the user-specified starting frame: */ while (!unwind_done(state) && (!on_stack(&state->stack_info, first_frame, sizeof(long)) || - state->sp <= (unsigned long)first_frame)) + state->sp < (unsigned long)first_frame)) unwind_next_frame(state); return; -done: +err: + state->error = true; +the_end: state->stack_info.type = STACK_TYPE_UNKNOWN; - return; } EXPORT_SYMBOL_GPL(__unwind_start); diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c index 420aa7d3a2e6..ae9e806a11de 100644 --- a/arch/x86/kernel/uprobes.c +++ b/arch/x86/kernel/uprobes.c @@ -268,12 +268,13 @@ static volatile u32 good_2byte_insns[256 / 32] = { static bool is_prefix_bad(struct insn *insn) { + insn_byte_t p; int i; - for (i = 0; i < insn->prefixes.nbytes; i++) { + for_each_insn_prefix(insn, i, p) { insn_attr_t attr; - attr = inat_get_opcode_attribute(insn->prefixes.bytes[i]); + attr = inat_get_opcode_attribute(p); switch (attr) { case INAT_MAKE_PREFIX(INAT_PFX_ES): case INAT_MAKE_PREFIX(INAT_PFX_CS): @@ -728,6 +729,7 @@ static const struct uprobe_xol_ops push_xol_ops = { static int branch_setup_xol_ops(struct arch_uprobe *auprobe, struct insn *insn) { u8 opc1 = OPCODE1(insn); + insn_byte_t p; int i; switch (opc1) { @@ -758,8 +760,8 @@ static int branch_setup_xol_ops(struct arch_uprobe *auprobe, struct insn *insn) * Intel and AMD behavior differ in 64-bit mode: Intel ignores 66 prefix. * No one uses these insns, reject any branch insns with such prefix. */ - for (i = 0; i < insn->prefixes.nbytes; i++) { - if (insn->prefixes.bytes[i] == 0x66) + for_each_insn_prefix(insn, i, p) { + if (p == 0x66) return -ENOTSUPP; } diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 85e6d5620188..34c0652ca8b4 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -36,13 +36,13 @@ OUTPUT_FORMAT(CONFIG_OUTPUT_FORMAT, CONFIG_OUTPUT_FORMAT, CONFIG_OUTPUT_FORMAT) #ifdef CONFIG_X86_32 OUTPUT_ARCH(i386) ENTRY(phys_startup_32) -jiffies = jiffies_64; #else OUTPUT_ARCH(i386:x86-64) ENTRY(phys_startup_64) -jiffies_64 = jiffies; #endif +jiffies = jiffies_64; + #if defined(CONFIG_X86_64) /* * On 64-bit, align RODATA to 2MB so we retain large page mappings for @@ -372,6 +372,7 @@ SECTIONS .bss : AT(ADDR(.bss) - LOAD_OFFSET) { __bss_start = .; *(.bss..page_aligned) + . = ALIGN(PAGE_SIZE); *(BSS_MAIN) BSS_DECRYPTED . = ALIGN(PAGE_SIZE); diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 48c24d0e9e75..1fe9ccabc082 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -509,7 +509,8 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, entry->edx |= F(SPEC_CTRL); if (boot_cpu_has(X86_FEATURE_STIBP)) entry->edx |= F(INTEL_STIBP); - if (boot_cpu_has(X86_FEATURE_SSBD)) + if (boot_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) || + boot_cpu_has(X86_FEATURE_AMD_SSBD)) entry->edx |= F(SPEC_CTRL_SSBD); /* * We emulate ARCH_CAPABILITIES in software even diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index d78a61408243..7dec43b2c420 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -154,6 +154,20 @@ static inline int guest_cpuid_stepping(struct kvm_vcpu *vcpu) return x86_stepping(best->eax); } +static inline bool guest_has_spec_ctrl_msr(struct kvm_vcpu *vcpu) +{ + return (guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL) || + guest_cpuid_has(vcpu, X86_FEATURE_AMD_STIBP) || + guest_cpuid_has(vcpu, X86_FEATURE_AMD_IBRS) || + guest_cpuid_has(vcpu, X86_FEATURE_AMD_SSBD)); +} + +static inline bool guest_has_pred_cmd_msr(struct kvm_vcpu *vcpu) +{ + return (guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL) || + guest_cpuid_has(vcpu, X86_FEATURE_AMD_IBPB)); +} + static inline bool supports_cpuid_fault(struct kvm_vcpu *vcpu) { return vcpu->arch.msr_platform_info & MSR_PLATFORM_INFO_CPUID_FAULT; diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 210eabd71ab2..3e182c7ae771 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -3561,7 +3561,7 @@ static int em_rdpid(struct x86_emulate_ctxt *ctxt) u64 tsc_aux = 0; if (ctxt->ops->get_msr(ctxt, MSR_TSC_AUX, &tsc_aux)) - return emulate_gp(ctxt, 0); + return emulate_ud(ctxt); ctxt->dst.val = tsc_aux; return X86EMUL_CONTINUE; } @@ -3994,6 +3994,12 @@ static int em_clflush(struct x86_emulate_ctxt *ctxt) return X86EMUL_CONTINUE; } +static int em_clflushopt(struct x86_emulate_ctxt *ctxt) +{ + /* emulating clflushopt regardless of cpuid */ + return X86EMUL_CONTINUE; +} + static int em_movsxd(struct x86_emulate_ctxt *ctxt) { ctxt->dst.val = (s32) ctxt->src.val; @@ -4507,7 +4513,7 @@ static const struct opcode group11[] = { }; static const struct gprefix pfx_0f_ae_7 = { - I(SrcMem | ByteOp, em_clflush), N, N, N, + I(SrcMem | ByteOp, em_clflush), I(SrcMem | ByteOp, em_clflushopt), N, N, }; static const struct group_dual group15 = { { diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c index 007bc654f928..295ebadb8f2c 100644 --- a/arch/x86/kvm/irq.c +++ b/arch/x86/kvm/irq.c @@ -52,29 +52,10 @@ static int pending_userspace_extint(struct kvm_vcpu *v) * check if there is pending interrupt from * non-APIC source without intack. */ -static int kvm_cpu_has_extint(struct kvm_vcpu *v) -{ - u8 accept = kvm_apic_accept_pic_intr(v); - - if (accept) { - if (irqchip_split(v->kvm)) - return pending_userspace_extint(v); - else - return v->kvm->arch.vpic->output; - } else - return 0; -} - -/* - * check if there is injectable interrupt: - * when virtual interrupt delivery enabled, - * interrupt from apic will handled by hardware, - * we don't need to check it here. - */ -int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v) +int kvm_cpu_has_extint(struct kvm_vcpu *v) { /* - * FIXME: interrupt.injected represents an interrupt that it's + * FIXME: interrupt.injected represents an interrupt whose * side-effects have already been applied (e.g. bit from IRR * already moved to ISR). Therefore, it is incorrect to rely * on interrupt.injected to know if there is a pending @@ -87,6 +68,23 @@ int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v) if (!lapic_in_kernel(v)) return v->arch.interrupt.injected; + if (!kvm_apic_accept_pic_intr(v)) + return 0; + + if (irqchip_split(v->kvm)) + return pending_userspace_extint(v); + else + return v->kvm->arch.vpic->output; +} + +/* + * check if there is injectable interrupt: + * when virtual interrupt delivery enabled, + * interrupt from apic will handled by hardware, + * we don't need to check it here. + */ +int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v) +{ if (kvm_cpu_has_extint(v)) return 1; @@ -102,20 +100,6 @@ int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v) */ int kvm_cpu_has_interrupt(struct kvm_vcpu *v) { - /* - * FIXME: interrupt.injected represents an interrupt that it's - * side-effects have already been applied (e.g. bit from IRR - * already moved to ISR). Therefore, it is incorrect to rely - * on interrupt.injected to know if there is a pending - * interrupt in the user-mode LAPIC. - * This leads to nVMX/nSVM not be able to distinguish - * if it should exit from L2 to L1 on EXTERNAL_INTERRUPT on - * pending interrupt or should re-inject an injected - * interrupt. - */ - if (!lapic_in_kernel(v)) - return v->arch.interrupt.injected; - if (kvm_cpu_has_extint(v)) return 1; @@ -129,16 +113,21 @@ EXPORT_SYMBOL_GPL(kvm_cpu_has_interrupt); */ static int kvm_cpu_get_extint(struct kvm_vcpu *v) { - if (kvm_cpu_has_extint(v)) { - if (irqchip_split(v->kvm)) { - int vector = v->arch.pending_external_vector; - - v->arch.pending_external_vector = -1; - return vector; - } else - return kvm_pic_read_irq(v->kvm); /* PIC */ - } else + if (!kvm_cpu_has_extint(v)) { + WARN_ON(!lapic_in_kernel(v)); return -1; + } + + if (!lapic_in_kernel(v)) + return v->arch.interrupt.nr; + + if (irqchip_split(v->kvm)) { + int vector = v->arch.pending_external_vector; + + v->arch.pending_external_vector = -1; + return vector; + } else + return kvm_pic_read_irq(v->kvm); /* PIC */ } /* @@ -146,13 +135,7 @@ static int kvm_cpu_get_extint(struct kvm_vcpu *v) */ int kvm_cpu_get_interrupt(struct kvm_vcpu *v) { - int vector; - - if (!lapic_in_kernel(v)) - return v->arch.interrupt.nr; - - vector = kvm_cpu_get_extint(v); - + int vector = kvm_cpu_get_extint(v); if (vector != -1) return vector; /* PIC */ diff --git a/arch/x86/kvm/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h index 9619dcc2b325..7df600410d69 100644 --- a/arch/x86/kvm/kvm_cache_regs.h +++ b/arch/x86/kvm/kvm_cache_regs.h @@ -5,7 +5,7 @@ #define KVM_POSSIBLE_CR0_GUEST_BITS X86_CR0_TS #define KVM_POSSIBLE_CR4_GUEST_BITS \ (X86_CR4_PVI | X86_CR4_DE | X86_CR4_PCE | X86_CR4_OSFXSR \ - | X86_CR4_OSXMMEXCPT | X86_CR4_LA57 | X86_CR4_PGE) + | X86_CR4_OSXMMEXCPT | X86_CR4_LA57 | X86_CR4_PGE | X86_CR4_TSD) static inline unsigned long kvm_register_read(struct kvm_vcpu *vcpu, enum kvm_reg reg) diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 8c6392534d14..56a4b9762b0c 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -2034,7 +2034,7 @@ void kvm_set_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu, u64 data) { struct kvm_lapic *apic = vcpu->arch.apic; - if (!lapic_in_kernel(vcpu) || apic_lvtt_oneshot(apic) || + if (!kvm_apic_present(vcpu) || apic_lvtt_oneshot(apic) || apic_lvtt_period(apic)) return; @@ -2284,7 +2284,7 @@ int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu) struct kvm_lapic *apic = vcpu->arch.apic; u32 ppr; - if (!kvm_apic_hw_enabled(apic)) + if (!kvm_apic_present(vcpu)) return -1; __apic_update_ppr(apic, &ppr); diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 62f1e4663bc3..5faa49a95ac9 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -281,6 +281,11 @@ static const u64 shadow_nonpresent_or_rsvd_mask_len = 5; */ static u64 __read_mostly shadow_nonpresent_or_rsvd_lower_gfn_mask; +/* + * The number of non-reserved physical address bits irrespective of features + * that repurpose legal bits, e.g. MKTME. + */ +static u8 __read_mostly shadow_phys_bits; static void mmu_spte_set(u64 *sptep, u64 spte); static bool is_executable_pte(u64 spte); @@ -294,11 +299,18 @@ kvm_mmu_calc_root_page_role(struct kvm_vcpu *vcpu); void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask, u64 mmio_value) { BUG_ON((mmio_mask & mmio_value) != mmio_value); + WARN_ON(mmio_value & (shadow_nonpresent_or_rsvd_mask << shadow_nonpresent_or_rsvd_mask_len)); + WARN_ON(mmio_value & shadow_nonpresent_or_rsvd_lower_gfn_mask); shadow_mmio_value = mmio_value | SPTE_SPECIAL_MASK; shadow_mmio_mask = mmio_mask | SPTE_SPECIAL_MASK; } EXPORT_SYMBOL_GPL(kvm_mmu_set_mmio_spte_mask); +static bool is_mmio_spte(u64 spte) +{ + return (spte & shadow_mmio_mask) == shadow_mmio_value; +} + static inline bool sp_ad_disabled(struct kvm_mmu_page *sp) { return sp->role.ad_disabled; @@ -306,7 +318,7 @@ static inline bool sp_ad_disabled(struct kvm_mmu_page *sp) static inline bool spte_ad_enabled(u64 spte) { - MMU_WARN_ON((spte & shadow_mmio_mask) == shadow_mmio_value); + MMU_WARN_ON(is_mmio_spte(spte)); return !(spte & shadow_acc_track_value); } @@ -317,13 +329,13 @@ static bool is_nx_huge_page_enabled(void) static inline u64 spte_shadow_accessed_mask(u64 spte) { - MMU_WARN_ON((spte & shadow_mmio_mask) == shadow_mmio_value); + MMU_WARN_ON(is_mmio_spte(spte)); return spte_ad_enabled(spte) ? shadow_accessed_mask : 0; } static inline u64 spte_shadow_dirty_mask(u64 spte) { - MMU_WARN_ON((spte & shadow_mmio_mask) == shadow_mmio_value); + MMU_WARN_ON(is_mmio_spte(spte)); return spte_ad_enabled(spte) ? shadow_dirty_mask : 0; } @@ -393,11 +405,6 @@ static void mark_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, u64 gfn, mmu_spte_set(sptep, mask); } -static bool is_mmio_spte(u64 spte) -{ - return (spte & shadow_mmio_mask) == shadow_mmio_value; -} - static gfn_t get_mmio_spte_gfn(u64 spte) { u64 gpa = spte & shadow_nonpresent_or_rsvd_lower_gfn_mask; @@ -462,6 +469,21 @@ void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask, } EXPORT_SYMBOL_GPL(kvm_mmu_set_mask_ptes); +static u8 kvm_get_shadow_phys_bits(void) +{ + /* + * boot_cpu_data.x86_phys_bits is reduced when MKTME is detected + * in CPU detection code, but MKTME treats those reduced bits as + * 'keyID' thus they are not reserved bits. Therefore for MKTME + * we should still return physical address bits reported by CPUID. + */ + if (!boot_cpu_has(X86_FEATURE_TME) || + WARN_ON_ONCE(boot_cpu_data.extended_cpuid_level < 0x80000008)) + return boot_cpu_data.x86_phys_bits; + + return cpuid_eax(0x80000008) & 0xff; +} + static void kvm_mmu_reset_all_pte_masks(void) { u8 low_phys_bits; @@ -475,20 +497,29 @@ static void kvm_mmu_reset_all_pte_masks(void) shadow_present_mask = 0; shadow_acc_track_mask = 0; + shadow_phys_bits = kvm_get_shadow_phys_bits(); + /* * If the CPU has 46 or less physical address bits, then set an * appropriate mask to guard against L1TF attacks. Otherwise, it is * assumed that the CPU is not vulnerable to L1TF. + * + * Some Intel CPUs address the L1 cache using more PA bits than are + * reported by CPUID. Use the PA width of the L1 cache when possible + * to achieve more effective mitigation, e.g. if system RAM overlaps + * the most significant bits of legal physical address space. */ + shadow_nonpresent_or_rsvd_mask = 0; low_phys_bits = boot_cpu_data.x86_phys_bits; - if (boot_cpu_data.x86_phys_bits < - 52 - shadow_nonpresent_or_rsvd_mask_len) { + if (boot_cpu_has_bug(X86_BUG_L1TF) && + !WARN_ON_ONCE(boot_cpu_data.x86_cache_bits >= + 52 - shadow_nonpresent_or_rsvd_mask_len)) { + low_phys_bits = boot_cpu_data.x86_cache_bits + - shadow_nonpresent_or_rsvd_mask_len; shadow_nonpresent_or_rsvd_mask = - rsvd_bits(boot_cpu_data.x86_phys_bits - - shadow_nonpresent_or_rsvd_mask_len, - boot_cpu_data.x86_phys_bits - 1); - low_phys_bits -= shadow_nonpresent_or_rsvd_mask_len; + rsvd_bits(low_phys_bits, boot_cpu_data.x86_cache_bits - 1); } + shadow_nonpresent_or_rsvd_lower_gfn_mask = GENMASK_ULL(low_phys_bits - 1, PAGE_SHIFT); } @@ -1701,10 +1732,10 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm, * Emulate arch specific page modification logging for the * nested hypervisor */ -int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu) +int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu, gpa_t l2_gpa) { if (kvm_x86_ops->write_log_dirty) - return kvm_x86_ops->write_log_dirty(vcpu); + return kvm_x86_ops->write_log_dirty(vcpu, l2_gpa); return 0; } @@ -1925,7 +1956,8 @@ static int kvm_handle_hva(struct kvm *kvm, unsigned long hva, return kvm_handle_hva_range(kvm, hva, hva + 1, data, handler); } -int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end) +int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end, + bool blockable) { return kvm_handle_hva_range(kvm, start, end, 0, kvm_unmap_rmapp); } @@ -4443,7 +4475,7 @@ __reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, nonleaf_bit8_rsvd | rsvd_bits(7, 7) | rsvd_bits(maxphyaddr, 51); rsvd_check->rsvd_bits_mask[0][2] = exb_bit_rsvd | - nonleaf_bit8_rsvd | gbpages_bit_rsvd | + gbpages_bit_rsvd | rsvd_bits(maxphyaddr, 51); rsvd_check->rsvd_bits_mask[0][1] = exb_bit_rsvd | rsvd_bits(maxphyaddr, 51); @@ -4535,7 +4567,7 @@ reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context) */ shadow_zero_check = &context->shadow_zero_check; __reset_rsvds_bits_mask(vcpu, shadow_zero_check, - boot_cpu_data.x86_phys_bits, + shadow_phys_bits, context->shadow_root_level, uses_nx, guest_cpuid_has(vcpu, X86_FEATURE_GBPAGES), is_pse(vcpu), true); @@ -4572,13 +4604,13 @@ reset_tdp_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, if (boot_cpu_is_amd()) __reset_rsvds_bits_mask(vcpu, shadow_zero_check, - boot_cpu_data.x86_phys_bits, + shadow_phys_bits, context->shadow_root_level, false, boot_cpu_has(X86_FEATURE_GBPAGES), true, true); else __reset_rsvds_bits_mask_ept(shadow_zero_check, - boot_cpu_data.x86_phys_bits, + shadow_phys_bits, false); if (!shadow_me_mask) @@ -4599,7 +4631,7 @@ reset_ept_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context, bool execonly) { __reset_rsvds_bits_mask_ept(&context->shadow_zero_check, - boot_cpu_data.x86_phys_bits, execonly); + shadow_phys_bits, execonly); } #define BYTE_MASK(access) \ @@ -6041,6 +6073,25 @@ static int set_nx_huge_pages(const char *val, const struct kernel_param *kp) return 0; } +static void kvm_set_mmio_spte_mask(void) +{ + u64 mask; + + /* + * Set a reserved PA bit in MMIO SPTEs to generate page faults with + * PFEC.RSVD=1 on MMIO accesses. 64-bit PTEs (PAE, x86-64, and EPT + * paging) support a maximum of 52 bits of PA, i.e. if the CPU supports + * 52-bit physical addresses then there are no reserved PA bits in the + * PTEs and so the reserved PA approach must be disabled. + */ + if (shadow_phys_bits < 52) + mask = BIT_ULL(51) | PT_PRESENT_MASK; + else + mask = 0; + + kvm_mmu_set_mmio_spte_mask(mask, mask); +} + int kvm_mmu_module_init(void) { int ret = -ENOMEM; @@ -6050,6 +6101,8 @@ int kvm_mmu_module_init(void) kvm_mmu_reset_all_pte_masks(); + kvm_set_mmio_spte_mask(); + pte_list_desc_cache = kmem_cache_create("pte_list_desc", sizeof(struct pte_list_desc), 0, SLAB_ACCOUNT, NULL); @@ -6172,6 +6225,7 @@ static void kvm_recover_nx_lpages(struct kvm *kvm) cond_resched_lock(&kvm->mmu_lock); } } + kvm_mmu_commit_zap_page(kvm, &invalid_list); spin_unlock(&kvm->mmu_lock); srcu_read_unlock(&kvm->srcu, rcu_idx); diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index f7b2de7b6382..05a02b8ace6b 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -53,7 +53,7 @@ static inline u64 rsvd_bits(int s, int e) if (e < s) return 0; - return ((1ULL << (e - s + 1)) - 1) << s; + return ((2ULL << (e - s)) - 1) << s; } void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask, u64 mmio_value); @@ -215,7 +215,7 @@ void kvm_mmu_gfn_disallow_lpage(struct kvm_memory_slot *slot, gfn_t gfn); void kvm_mmu_gfn_allow_lpage(struct kvm_memory_slot *slot, gfn_t gfn); bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm, struct kvm_memory_slot *slot, u64 gfn); -int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu); +int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu, gpa_t l2_gpa); int kvm_mmu_post_init_vm(struct kvm *kvm); void kvm_mmu_pre_destroy_vm(struct kvm *kvm); diff --git a/arch/x86/kvm/mmutrace.h b/arch/x86/kvm/mmutrace.h index cb41b036eb26..7e0dc8c7da2c 100644 --- a/arch/x86/kvm/mmutrace.h +++ b/arch/x86/kvm/mmutrace.h @@ -339,7 +339,7 @@ TRACE_EVENT( /* These depend on page entry type, so compute them now. */ __field(bool, r) __field(bool, x) - __field(u8, u) + __field(signed char, u) ), TP_fast_assign( diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 61f10a4fd807..8220190b0605 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -202,7 +202,7 @@ static inline unsigned FNAME(gpte_access)(u64 gpte) static int FNAME(update_accessed_dirty_bits)(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, struct guest_walker *walker, - int write_fault) + gpa_t addr, int write_fault) { unsigned level, index; pt_element_t pte, orig_pte; @@ -227,7 +227,7 @@ static int FNAME(update_accessed_dirty_bits)(struct kvm_vcpu *vcpu, !(pte & PT_GUEST_DIRTY_MASK)) { trace_kvm_mmu_set_dirty_bit(table_gfn, index, sizeof(pte)); #if PTTYPE == PTTYPE_EPT - if (kvm_arch_write_log_dirty(vcpu)) + if (kvm_arch_write_log_dirty(vcpu, addr)) return -EINVAL; #endif pte |= PT_GUEST_DIRTY_MASK; @@ -424,7 +424,8 @@ retry_walk: (PT_GUEST_DIRTY_SHIFT - PT_GUEST_ACCESSED_SHIFT); if (unlikely(!accessed_dirty)) { - ret = FNAME(update_accessed_dirty_bits)(vcpu, mmu, walker, write_fault); + ret = FNAME(update_accessed_dirty_bits)(vcpu, mmu, walker, + addr, write_fault); if (unlikely(ret < 0)) goto error; else if (ret) diff --git a/arch/x86/kvm/pmu_intel.c b/arch/x86/kvm/pmu_intel.c index 2ab8c20c8bfa..611f9e60f815 100644 --- a/arch/x86/kvm/pmu_intel.c +++ b/arch/x86/kvm/pmu_intel.c @@ -29,7 +29,7 @@ static struct kvm_event_hw_type_mapping intel_arch_events[] = { [4] = { 0x2e, 0x41, PERF_COUNT_HW_CACHE_MISSES }, [5] = { 0xc4, 0x00, PERF_COUNT_HW_BRANCH_INSTRUCTIONS }, [6] = { 0xc5, 0x00, PERF_COUNT_HW_BRANCH_MISSES }, - [7] = { 0x00, 0x30, PERF_COUNT_HW_REF_CPU_CYCLES }, + [7] = { 0x00, 0x03, PERF_COUNT_HW_REF_CPU_CYCLES }, }; /* mapping between fixed pmc index and intel_arch_events array */ diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index cc8f3b41a1b2..8cb9277aa6ff 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -892,6 +892,11 @@ static int has_svm(void) return 0; } + if (sev_active()) { + pr_info("KVM is unsupported when running as an SEV guest\n"); + return 0; + } + return 1; } @@ -998,33 +1003,32 @@ static void svm_cpu_uninit(int cpu) static int svm_cpu_init(int cpu) { struct svm_cpu_data *sd; - int r; sd = kzalloc(sizeof(struct svm_cpu_data), GFP_KERNEL); if (!sd) return -ENOMEM; sd->cpu = cpu; - r = -ENOMEM; sd->save_area = alloc_page(GFP_KERNEL); if (!sd->save_area) - goto err_1; + goto free_cpu_data; if (svm_sev_enabled()) { - r = -ENOMEM; sd->sev_vmcbs = kmalloc_array(max_sev_asid + 1, sizeof(void *), GFP_KERNEL); if (!sd->sev_vmcbs) - goto err_1; + goto free_save_area; } per_cpu(svm_data, cpu) = sd; return 0; -err_1: +free_save_area: + __free_page(sd->save_area); +free_cpu_data: kfree(sd); - return r; + return -ENOMEM; } @@ -1828,6 +1832,8 @@ static struct page **sev_pin_memory(struct kvm *kvm, unsigned long uaddr, struct page **pages; unsigned long first, last; + lockdep_assert_held(&kvm->lock); + if (ulen == 0 || uaddr + ulen < uaddr) return NULL; @@ -1917,6 +1923,10 @@ static void __unregister_enc_region_locked(struct kvm *kvm, static struct kvm *svm_vm_alloc(void) { struct kvm_svm *kvm_svm = vzalloc(sizeof(struct kvm_svm)); + + if (!kvm_svm) + return NULL; + return &kvm_svm->kvm; } @@ -3226,8 +3236,8 @@ static int nested_svm_exit_special(struct vcpu_svm *svm) return NESTED_EXIT_HOST; break; case SVM_EXIT_EXCP_BASE + PF_VECTOR: - /* When we're shadowing, trap PFs, but not async PF */ - if (!npt_enabled && svm->vcpu.arch.apf.host_apf_reason == 0) + /* Trap async PF even if not shadowing */ + if (!npt_enabled || svm->vcpu.arch.apf.host_apf_reason) return NESTED_EXIT_HOST; break; default: @@ -3316,7 +3326,7 @@ static inline void copy_vmcb_control_area(struct vmcb *dst_vmcb, struct vmcb *fr dst->iopm_base_pa = from->iopm_base_pa; dst->msrpm_base_pa = from->msrpm_base_pa; dst->tsc_offset = from->tsc_offset; - dst->asid = from->asid; + /* asid not copied, it is handled manually for svm->vmcb. */ dst->tlb_ctl = from->tlb_ctl; dst->int_ctl = from->int_ctl; dst->int_vector = from->int_vector; @@ -3939,6 +3949,12 @@ static int iret_interception(struct vcpu_svm *svm) return 1; } +static int invd_interception(struct vcpu_svm *svm) +{ + /* Treat an INVD instruction as a NOP and just skip it. */ + return kvm_skip_emulated_instruction(&svm->vcpu); +} + static int invlpg_interception(struct vcpu_svm *svm) { if (!static_cpu_has(X86_FEATURE_DECODEASSISTS)) @@ -4200,8 +4216,7 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) break; case MSR_IA32_SPEC_CTRL: if (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_AMD_IBRS) && - !guest_cpuid_has(vcpu, X86_FEATURE_AMD_SSBD)) + !guest_has_spec_ctrl_msr(vcpu)) return 1; msr_info->data = svm->spec_ctrl; @@ -4303,8 +4318,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) break; case MSR_IA32_SPEC_CTRL: if (!msr->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_AMD_IBRS) && - !guest_cpuid_has(vcpu, X86_FEATURE_AMD_SSBD)) + !guest_has_spec_ctrl_msr(vcpu)) return 1; /* The STIBP bit doesn't fault even if it's not advertised */ @@ -4331,12 +4345,11 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) break; case MSR_IA32_PRED_CMD: if (!msr->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_AMD_IBPB)) + !guest_has_pred_cmd_msr(vcpu)) return 1; if (data & ~PRED_CMD_IBPB) return 1; - if (!data) break; @@ -4828,7 +4841,7 @@ static int (*const svm_exit_handlers[])(struct vcpu_svm *svm) = { [SVM_EXIT_RDPMC] = rdpmc_interception, [SVM_EXIT_CPUID] = cpuid_interception, [SVM_EXIT_IRET] = iret_interception, - [SVM_EXIT_INVD] = emulate_on_interception, + [SVM_EXIT_INVD] = invd_interception, [SVM_EXIT_PAUSE] = pause_interception, [SVM_EXIT_HLT] = halt_interception, [SVM_EXIT_INVLPG] = invlpg_interception, @@ -5371,6 +5384,7 @@ static int svm_update_pi_irte(struct kvm *kvm, unsigned int host_irq, * - Tell IOMMU to use legacy mode for this interrupt. * - Retrieve ga_tag of prior interrupt remapping data. */ + pi.prev_ga_tag = 0; pi.is_guest_mode = false; ret = irq_set_vcpu_affinity(host_irq, &pi); @@ -7072,12 +7086,20 @@ static int svm_register_enc_region(struct kvm *kvm, if (!region) return -ENOMEM; + mutex_lock(&kvm->lock); region->pages = sev_pin_memory(kvm, range->addr, range->size, ®ion->npages, 1); if (!region->pages) { ret = -ENOMEM; + mutex_unlock(&kvm->lock); goto e_free; } + region->uaddr = range->addr; + region->size = range->size; + + list_add_tail(®ion->list, &sev->regions_list); + mutex_unlock(&kvm->lock); + /* * The guest may change the memory encryption attribute from C=0 -> C=1 * or vice versa for this memory range. Lets make sure caches are @@ -7086,13 +7108,6 @@ static int svm_register_enc_region(struct kvm *kvm, */ sev_clflush_pages(region->pages, region->npages); - region->uaddr = range->addr; - region->size = range->size; - - mutex_lock(&kvm->lock); - list_add_tail(®ion->list, &sev->regions_list); - mutex_unlock(&kvm->lock); - return ret; e_free: diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index a81d7d9ce9d6..77b9ed5223f3 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -2156,43 +2156,15 @@ static void vmcs_load(struct vmcs *vmcs) } #ifdef CONFIG_KEXEC_CORE -/* - * This bitmap is used to indicate whether the vmclear - * operation is enabled on all cpus. All disabled by - * default. - */ -static cpumask_t crash_vmclear_enabled_bitmap = CPU_MASK_NONE; - -static inline void crash_enable_local_vmclear(int cpu) -{ - cpumask_set_cpu(cpu, &crash_vmclear_enabled_bitmap); -} - -static inline void crash_disable_local_vmclear(int cpu) -{ - cpumask_clear_cpu(cpu, &crash_vmclear_enabled_bitmap); -} - -static inline int crash_local_vmclear_enabled(int cpu) -{ - return cpumask_test_cpu(cpu, &crash_vmclear_enabled_bitmap); -} - static void crash_vmclear_local_loaded_vmcss(void) { int cpu = raw_smp_processor_id(); struct loaded_vmcs *v; - if (!crash_local_vmclear_enabled(cpu)) - return; - list_for_each_entry(v, &per_cpu(loaded_vmcss_on_cpu, cpu), loaded_vmcss_on_cpu_link) vmcs_clear(v->vmcs); } -#else -static inline void crash_enable_local_vmclear(int cpu) { } -static inline void crash_disable_local_vmclear(int cpu) { } #endif /* CONFIG_KEXEC_CORE */ static void __loaded_vmcs_clear(void *arg) @@ -2204,19 +2176,24 @@ static void __loaded_vmcs_clear(void *arg) return; /* vcpu migration can race with cpu offline */ if (per_cpu(current_vmcs, cpu) == loaded_vmcs->vmcs) per_cpu(current_vmcs, cpu) = NULL; - crash_disable_local_vmclear(cpu); + + vmcs_clear(loaded_vmcs->vmcs); + if (loaded_vmcs->shadow_vmcs && loaded_vmcs->launched) + vmcs_clear(loaded_vmcs->shadow_vmcs); + list_del(&loaded_vmcs->loaded_vmcss_on_cpu_link); /* - * we should ensure updating loaded_vmcs->loaded_vmcss_on_cpu_link - * is before setting loaded_vmcs->vcpu to -1 which is done in - * loaded_vmcs_init. Otherwise, other cpu can see vcpu = -1 fist - * then adds the vmcs into percpu list before it is deleted. + * Ensure all writes to loaded_vmcs, including deleting it from its + * current percpu list, complete before setting loaded_vmcs->vcpu to + * -1, otherwise a different cpu can see vcpu == -1 first and add + * loaded_vmcs to its percpu list before it's deleted from this cpu's + * list. Pairs with the smp_rmb() in vmx_vcpu_load_vmcs(). */ smp_wmb(); - loaded_vmcs_init(loaded_vmcs); - crash_enable_local_vmclear(cpu); + loaded_vmcs->cpu = -1; + loaded_vmcs->launched = 0; } static void loaded_vmcs_clear(struct loaded_vmcs *loaded_vmcs) @@ -3067,18 +3044,17 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) if (!already_loaded) { loaded_vmcs_clear(vmx->loaded_vmcs); local_irq_disable(); - crash_disable_local_vmclear(cpu); /* - * Read loaded_vmcs->cpu should be before fetching - * loaded_vmcs->loaded_vmcss_on_cpu_link. - * See the comments in __loaded_vmcs_clear(). + * Ensure loaded_vmcs->cpu is read before adding loaded_vmcs to + * this cpu's percpu list, otherwise it may not yet be deleted + * from its previous cpu's percpu list. Pairs with the + * smb_wmb() in __loaded_vmcs_clear(). */ smp_rmb(); list_add(&vmx->loaded_vmcs->loaded_vmcss_on_cpu_link, &per_cpu(loaded_vmcss_on_cpu, cpu)); - crash_enable_local_vmclear(cpu); local_irq_enable(); } @@ -4090,7 +4066,7 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return kvm_get_msr_common(vcpu, msr_info); case MSR_IA32_SPEC_CTRL: if (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL)) + !guest_has_spec_ctrl_msr(vcpu)) return 1; msr_info->data = to_vmx(vcpu)->spec_ctrl; @@ -4204,7 +4180,7 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) break; case MSR_IA32_SPEC_CTRL: if (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL)) + !guest_has_spec_ctrl_msr(vcpu)) return 1; /* The STIBP bit doesn't fault even if it's not advertised */ @@ -4234,7 +4210,7 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) break; case MSR_IA32_PRED_CMD: if (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL)) + !guest_has_pred_cmd_msr(vcpu)) return 1; if (data & ~PRED_CMD_IBPB) @@ -4422,21 +4398,6 @@ static int hardware_enable(void) !hv_get_vp_assist_page(cpu)) return -EFAULT; - INIT_LIST_HEAD(&per_cpu(loaded_vmcss_on_cpu, cpu)); - INIT_LIST_HEAD(&per_cpu(blocked_vcpu_on_cpu, cpu)); - spin_lock_init(&per_cpu(blocked_vcpu_on_cpu_lock, cpu)); - - /* - * Now we can enable the vmclear operation in kdump - * since the loaded_vmcss_on_cpu list on this cpu - * has been initialized. - * - * Though the cpu is not in VMX operation now, there - * is no problem to enable the vmclear operation - * for the loaded_vmcss_on_cpu list is empty! - */ - crash_enable_local_vmclear(cpu); - rdmsrl(MSR_IA32_FEATURE_CONTROL, old); test_bits = FEATURE_CONTROL_LOCKED; @@ -6374,6 +6335,8 @@ static void vmx_set_constant_host_state(struct vcpu_vmx *vmx) static void set_cr4_guest_host_mask(struct vcpu_vmx *vmx) { + BUILD_BUG_ON(KVM_CR4_GUEST_OWNED_BITS & ~KVM_POSSIBLE_CR4_GUEST_BITS); + vmx->vcpu.arch.cr4_guest_owned_bits = KVM_CR4_GUEST_OWNED_BITS; if (enable_ept) vmx->vcpu.arch.cr4_guest_owned_bits |= X86_CR4_PGE; @@ -6954,8 +6917,13 @@ static int vmx_nmi_allowed(struct kvm_vcpu *vcpu) static int vmx_interrupt_allowed(struct kvm_vcpu *vcpu) { - return (!to_vmx(vcpu)->nested.nested_run_pending && - vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_IF) && + if (to_vmx(vcpu)->nested.nested_run_pending) + return false; + + if (is_guest_mode(vcpu) && nested_exit_on_intr(vcpu)) + return true; + + return (vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_IF) && !(vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & (GUEST_INTR_STATE_STI | GUEST_INTR_STATE_MOV_SS)); } @@ -7049,7 +7017,7 @@ static int handle_rmode_exception(struct kvm_vcpu *vcpu, */ static void kvm_machine_check(void) { -#if defined(CONFIG_X86_MCE) && defined(CONFIG_X86_64) +#if defined(CONFIG_X86_MCE) struct pt_regs regs = { .cs = 3, /* Fake ring 3 no matter what the guest ran on */ .flags = X86_EFLAGS_IF, @@ -9717,7 +9685,7 @@ static bool nested_vmx_exit_reflected(struct kvm_vcpu *vcpu, u32 exit_reason) vmcs_read32(VM_EXIT_INTR_ERROR_CODE), KVM_ISA_VMX); - switch (exit_reason) { + switch ((u16)exit_reason) { case EXIT_REASON_EXCEPTION_NMI: if (is_nmi(intr_info)) return false; @@ -10160,6 +10128,7 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu) (exit_reason != EXIT_REASON_EXCEPTION_NMI && exit_reason != EXIT_REASON_EPT_VIOLATION && exit_reason != EXIT_REASON_PML_FULL && + exit_reason != EXIT_REASON_APIC_ACCESS && exit_reason != EXIT_REASON_TASK_SWITCH)) { vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_DELIVERY_EV; @@ -10805,14 +10774,14 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) else if (static_branch_unlikely(&mds_user_clear)) mds_clear_cpu_buffers(); - asm( + asm volatile ( /* Store host registers */ "push %%" _ASM_DX "; push %%" _ASM_BP ";" "push %%" _ASM_CX " \n\t" /* placeholder for guest rcx */ "push %%" _ASM_CX " \n\t" - "cmp %%" _ASM_SP ", %c[host_rsp](%0) \n\t" + "cmp %%" _ASM_SP ", %c[host_rsp](%%" _ASM_CX ") \n\t" "je 1f \n\t" - "mov %%" _ASM_SP ", %c[host_rsp](%0) \n\t" + "mov %%" _ASM_SP ", %c[host_rsp](%%" _ASM_CX ") \n\t" /* Avoid VMWRITE when Enlightened VMCS is in use */ "test %%" _ASM_SI ", %%" _ASM_SI " \n\t" "jz 2f \n\t" @@ -10822,32 +10791,33 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) __ex(ASM_VMX_VMWRITE_RSP_RDX) "\n\t" "1: \n\t" /* Reload cr2 if changed */ - "mov %c[cr2](%0), %%" _ASM_AX " \n\t" + "mov %c[cr2](%%" _ASM_CX "), %%" _ASM_AX " \n\t" "mov %%cr2, %%" _ASM_DX " \n\t" "cmp %%" _ASM_AX ", %%" _ASM_DX " \n\t" "je 3f \n\t" "mov %%" _ASM_AX", %%cr2 \n\t" "3: \n\t" /* Check if vmlaunch of vmresume is needed */ - "cmpb $0, %c[launched](%0) \n\t" + "cmpb $0, %c[launched](%%" _ASM_CX ") \n\t" /* Load guest registers. Don't clobber flags. */ - "mov %c[rax](%0), %%" _ASM_AX " \n\t" - "mov %c[rbx](%0), %%" _ASM_BX " \n\t" - "mov %c[rdx](%0), %%" _ASM_DX " \n\t" - "mov %c[rsi](%0), %%" _ASM_SI " \n\t" - "mov %c[rdi](%0), %%" _ASM_DI " \n\t" - "mov %c[rbp](%0), %%" _ASM_BP " \n\t" + "mov %c[rax](%%" _ASM_CX "), %%" _ASM_AX " \n\t" + "mov %c[rbx](%%" _ASM_CX "), %%" _ASM_BX " \n\t" + "mov %c[rdx](%%" _ASM_CX "), %%" _ASM_DX " \n\t" + "mov %c[rsi](%%" _ASM_CX "), %%" _ASM_SI " \n\t" + "mov %c[rdi](%%" _ASM_CX "), %%" _ASM_DI " \n\t" + "mov %c[rbp](%%" _ASM_CX "), %%" _ASM_BP " \n\t" #ifdef CONFIG_X86_64 - "mov %c[r8](%0), %%r8 \n\t" - "mov %c[r9](%0), %%r9 \n\t" - "mov %c[r10](%0), %%r10 \n\t" - "mov %c[r11](%0), %%r11 \n\t" - "mov %c[r12](%0), %%r12 \n\t" - "mov %c[r13](%0), %%r13 \n\t" - "mov %c[r14](%0), %%r14 \n\t" - "mov %c[r15](%0), %%r15 \n\t" + "mov %c[r8](%%" _ASM_CX "), %%r8 \n\t" + "mov %c[r9](%%" _ASM_CX "), %%r9 \n\t" + "mov %c[r10](%%" _ASM_CX "), %%r10 \n\t" + "mov %c[r11](%%" _ASM_CX "), %%r11 \n\t" + "mov %c[r12](%%" _ASM_CX "), %%r12 \n\t" + "mov %c[r13](%%" _ASM_CX "), %%r13 \n\t" + "mov %c[r14](%%" _ASM_CX "), %%r14 \n\t" + "mov %c[r15](%%" _ASM_CX "), %%r15 \n\t" #endif - "mov %c[rcx](%0), %%" _ASM_CX " \n\t" /* kills %0 (ecx) */ + /* Load guest RCX. This kills the vmx_vcpu pointer! */ + "mov %c[rcx](%%" _ASM_CX "), %%" _ASM_CX " \n\t" /* Enter guest mode */ "jne 1f \n\t" @@ -10855,26 +10825,42 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) "jmp 2f \n\t" "1: " __ex(ASM_VMX_VMRESUME) "\n\t" "2: " - /* Save guest registers, load host registers, keep flags */ - "mov %0, %c[wordsize](%%" _ASM_SP ") \n\t" - "pop %0 \n\t" - "setbe %c[fail](%0)\n\t" - "mov %%" _ASM_AX ", %c[rax](%0) \n\t" - "mov %%" _ASM_BX ", %c[rbx](%0) \n\t" - __ASM_SIZE(pop) " %c[rcx](%0) \n\t" - "mov %%" _ASM_DX ", %c[rdx](%0) \n\t" - "mov %%" _ASM_SI ", %c[rsi](%0) \n\t" - "mov %%" _ASM_DI ", %c[rdi](%0) \n\t" - "mov %%" _ASM_BP ", %c[rbp](%0) \n\t" + + /* Save guest's RCX to the stack placeholder (see above) */ + "mov %%" _ASM_CX ", %c[wordsize](%%" _ASM_SP ") \n\t" + + /* Load host's RCX, i.e. the vmx_vcpu pointer */ + "pop %%" _ASM_CX " \n\t" + + /* Set vmx->fail based on EFLAGS.{CF,ZF} */ + "setbe %c[fail](%%" _ASM_CX ")\n\t" + + /* Save all guest registers, including RCX from the stack */ + "mov %%" _ASM_AX ", %c[rax](%%" _ASM_CX ") \n\t" + "mov %%" _ASM_BX ", %c[rbx](%%" _ASM_CX ") \n\t" + __ASM_SIZE(pop) " %c[rcx](%%" _ASM_CX ") \n\t" + "mov %%" _ASM_DX ", %c[rdx](%%" _ASM_CX ") \n\t" + "mov %%" _ASM_SI ", %c[rsi](%%" _ASM_CX ") \n\t" + "mov %%" _ASM_DI ", %c[rdi](%%" _ASM_CX ") \n\t" + "mov %%" _ASM_BP ", %c[rbp](%%" _ASM_CX ") \n\t" #ifdef CONFIG_X86_64 - "mov %%r8, %c[r8](%0) \n\t" - "mov %%r9, %c[r9](%0) \n\t" - "mov %%r10, %c[r10](%0) \n\t" - "mov %%r11, %c[r11](%0) \n\t" - "mov %%r12, %c[r12](%0) \n\t" - "mov %%r13, %c[r13](%0) \n\t" - "mov %%r14, %c[r14](%0) \n\t" - "mov %%r15, %c[r15](%0) \n\t" + "mov %%r8, %c[r8](%%" _ASM_CX ") \n\t" + "mov %%r9, %c[r9](%%" _ASM_CX ") \n\t" + "mov %%r10, %c[r10](%%" _ASM_CX ") \n\t" + "mov %%r11, %c[r11](%%" _ASM_CX ") \n\t" + "mov %%r12, %c[r12](%%" _ASM_CX ") \n\t" + "mov %%r13, %c[r13](%%" _ASM_CX ") \n\t" + "mov %%r14, %c[r14](%%" _ASM_CX ") \n\t" + "mov %%r15, %c[r15](%%" _ASM_CX ") \n\t" + + /* + * Clear all general purpose registers (except RSP, which is loaded by + * the CPU during VM-Exit) to prevent speculative use of the guest's + * values, even those that are saved/loaded via the stack. In theory, + * an L1 cache miss when restoring registers could lead to speculative + * execution with the guest's values. Zeroing XORs are dirt cheap, + * i.e. the extra paranoia is essentially free. + */ "xor %%r8d, %%r8d \n\t" "xor %%r9d, %%r9d \n\t" "xor %%r10d, %%r10d \n\t" @@ -10885,18 +10871,22 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) "xor %%r15d, %%r15d \n\t" #endif "mov %%cr2, %%" _ASM_AX " \n\t" - "mov %%" _ASM_AX ", %c[cr2](%0) \n\t" + "mov %%" _ASM_AX ", %c[cr2](%%" _ASM_CX ") \n\t" "xor %%eax, %%eax \n\t" "xor %%ebx, %%ebx \n\t" + "xor %%ecx, %%ecx \n\t" + "xor %%edx, %%edx \n\t" "xor %%esi, %%esi \n\t" "xor %%edi, %%edi \n\t" + "xor %%ebp, %%ebp \n\t" "pop %%" _ASM_BP "; pop %%" _ASM_DX " \n\t" ".pushsection .rodata \n\t" ".global vmx_return \n\t" "vmx_return: " _ASM_PTR " 2b \n\t" ".popsection" - : : "c"(vmx), "d"((unsigned long)HOST_RSP), "S"(evmcs_rsp), + : "=c"((int){0}), "=d"((int){0}), "=S"((int){0}) + : "c"(vmx), "d"((unsigned long)HOST_RSP), "S"(evmcs_rsp), [launched]"i"(offsetof(struct vcpu_vmx, __launched)), [fail]"i"(offsetof(struct vcpu_vmx, fail)), [host_rsp]"i"(offsetof(struct vcpu_vmx, host_rsp)), @@ -11016,6 +11006,10 @@ STACK_FRAME_NON_STANDARD(vmx_vcpu_run); static struct kvm *vmx_vm_alloc(void) { struct kvm_vmx *kvm_vmx = vzalloc(sizeof(struct kvm_vmx)); + + if (!kvm_vmx) + return NULL; + return &kvm_vmx->kvm; } @@ -12155,13 +12149,9 @@ static void prepare_vmcs02_full(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) set_cr4_guest_host_mask(vmx); - if (kvm_mpx_supported()) { - if (vmx->nested.nested_run_pending && - (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS)) - vmcs_write64(GUEST_BNDCFGS, vmcs12->guest_bndcfgs); - else - vmcs_write64(GUEST_BNDCFGS, vmx->nested.vmcs01_guest_bndcfgs); - } + if (kvm_mpx_supported() && vmx->nested.nested_run_pending && + (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS)) + vmcs_write64(GUEST_BNDCFGS, vmcs12->guest_bndcfgs); if (enable_vpid) { if (nested_cpu_has_vpid(vmcs12) && vmx->nested.vpid02) @@ -12225,6 +12215,9 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, kvm_set_dr(vcpu, 7, vcpu->arch.dr7); vmcs_write64(GUEST_IA32_DEBUGCTL, vmx->nested.vmcs01_debugctl); } + if (kvm_mpx_supported() && (!vmx->nested.nested_run_pending || + !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS))) + vmcs_write64(GUEST_BNDCFGS, vmx->nested.vmcs01_guest_bndcfgs); if (vmx->nested.nested_run_pending) { vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, vmcs12->vm_entry_intr_info_field); @@ -12990,7 +12983,7 @@ static void vmcs12_save_pending_event(struct kvm_vcpu *vcpu, } } -static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr) +static int vmx_check_nested_events(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); unsigned long exit_qual; @@ -13028,8 +13021,7 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr) return 0; } - if ((kvm_cpu_has_interrupt(vcpu) || external_intr) && - nested_exit_on_intr(vcpu)) { + if (kvm_cpu_has_interrupt(vcpu) && nested_exit_on_intr(vcpu)) { if (block_nested_events) return -EBUSY; nested_vmx_vmexit(vcpu, EXIT_REASON_EXTERNAL_INTERRUPT, 0, 0); @@ -13607,17 +13599,8 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; if (likely(!vmx->fail)) { - /* - * TODO: SDM says that with acknowledge interrupt on - * exit, bit 31 of the VM-exit interrupt information - * (valid interrupt) is always set to 1 on - * EXIT_REASON_EXTERNAL_INTERRUPT, so we shouldn't - * need kvm_cpu_has_interrupt(). See the commit - * message for details. - */ - if (nested_exit_intr_ack_set(vcpu) && - exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT && - kvm_cpu_has_interrupt(vcpu)) { + if (exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT && + nested_exit_intr_ack_set(vcpu)) { int irq = kvm_cpu_get_interrupt(vcpu); WARN_ON(irq < 0); vmcs12->vm_exit_intr_info = irq | @@ -13865,11 +13848,10 @@ static void vmx_flush_log_dirty(struct kvm *kvm) kvm_flush_pml_buffers(kvm); } -static int vmx_write_pml_buffer(struct kvm_vcpu *vcpu) +static int vmx_write_pml_buffer(struct kvm_vcpu *vcpu, gpa_t gpa) { struct vmcs12 *vmcs12; struct vcpu_vmx *vmx = to_vmx(vcpu); - gpa_t gpa; struct page *page = NULL; u64 *pml_address; @@ -13890,7 +13872,7 @@ static int vmx_write_pml_buffer(struct kvm_vcpu *vcpu) return 1; } - gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS) & ~0xFFFull; + gpa &= ~0xFFFull; page = kvm_vcpu_gpa_to_page(vcpu, vmcs12->pml_address); if (is_error_page(page)) @@ -14590,7 +14572,7 @@ module_exit(vmx_exit); static int __init vmx_init(void) { - int r; + int r, cpu; #if IS_ENABLED(CONFIG_HYPERV) /* @@ -14641,6 +14623,12 @@ static int __init vmx_init(void) } } + for_each_possible_cpu(cpu) { + INIT_LIST_HEAD(&per_cpu(loaded_vmcss_on_cpu, cpu)); + INIT_LIST_HEAD(&per_cpu(blocked_vcpu_on_cpu, cpu)); + spin_lock_init(&per_cpu(blocked_vcpu_on_cpu_lock, cpu)); + } + #ifdef CONFIG_KEXEC_CORE rcu_assign_pointer(crash_vmclear_loaded_vmcss, crash_vmclear_local_loaded_vmcss); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 2cb379e261c0..435e74e1f2e5 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -102,6 +102,7 @@ static u64 __read_mostly cr4_reserved_bits = CR4_RESERVED_BITS; static void update_cr8_intercept(struct kvm_vcpu *vcpu); static void process_nmi(struct kvm_vcpu *vcpu); +static void process_smi(struct kvm_vcpu *vcpu); static void enter_smm(struct kvm_vcpu *vcpu); static void __kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags); static void store_regs(struct kvm_vcpu *vcpu); @@ -857,7 +858,8 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) { unsigned long old_cr4 = kvm_read_cr4(vcpu); unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE | - X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_PKE; + X86_CR4_SMEP; + unsigned long mmu_role_bits = pdptr_bits | X86_CR4_SMAP | X86_CR4_PKE; if (kvm_valid_cr4(vcpu, cr4)) return 1; @@ -865,6 +867,8 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) if (is_long_mode(vcpu)) { if (!(cr4 & X86_CR4_PAE)) return 1; + if ((cr4 ^ old_cr4) & X86_CR4_LA57) + return 1; } else if (is_paging(vcpu) && (cr4 & X86_CR4_PAE) && ((cr4 ^ old_cr4) & pdptr_bits) && !load_pdptrs(vcpu, vcpu->arch.walk_mmu, @@ -883,7 +887,7 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) if (kvm_x86_ops->set_cr4(vcpu, cr4)) return 1; - if (((cr4 ^ old_cr4) & pdptr_bits) || + if (((cr4 ^ old_cr4) & mmu_role_bits) || (!(cr4 & X86_CR4_PCIDE) && (old_cr4 & X86_CR4_PCIDE))) kvm_mmu_reset_context(vcpu); @@ -2397,43 +2401,45 @@ static void kvm_vcpu_flush_tlb(struct kvm_vcpu *vcpu, bool invalidate_gpa) static void record_steal_time(struct kvm_vcpu *vcpu) { + struct kvm_host_map map; + struct kvm_steal_time *st; + if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED)) return; - if (unlikely(kvm_read_guest_cached(vcpu->kvm, &vcpu->arch.st.stime, - &vcpu->arch.st.steal, sizeof(struct kvm_steal_time)))) + /* -EAGAIN is returned in atomic context so we can just return. */ + if (kvm_map_gfn(vcpu, vcpu->arch.st.msr_val >> PAGE_SHIFT, + &map, &vcpu->arch.st.cache, false)) return; + st = map.hva + + offset_in_page(vcpu->arch.st.msr_val & KVM_STEAL_VALID_BITS); + /* * Doing a TLB flush here, on the guest's behalf, can avoid * expensive IPIs. */ - if (xchg(&vcpu->arch.st.steal.preempted, 0) & KVM_VCPU_FLUSH_TLB) + if (xchg(&st->preempted, 0) & KVM_VCPU_FLUSH_TLB) kvm_vcpu_flush_tlb(vcpu, false); - if (vcpu->arch.st.steal.version & 1) - vcpu->arch.st.steal.version += 1; /* first time write, random junk */ + vcpu->arch.st.preempted = 0; - vcpu->arch.st.steal.version += 1; + if (st->version & 1) + st->version += 1; /* first time write, random junk */ - kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.st.stime, - &vcpu->arch.st.steal, sizeof(struct kvm_steal_time)); + st->version += 1; smp_wmb(); - vcpu->arch.st.steal.steal += current->sched_info.run_delay - + st->steal += current->sched_info.run_delay - vcpu->arch.st.last_steal; vcpu->arch.st.last_steal = current->sched_info.run_delay; - kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.st.stime, - &vcpu->arch.st.steal, sizeof(struct kvm_steal_time)); - smp_wmb(); - vcpu->arch.st.steal.version += 1; + st->version += 1; - kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.st.stime, - &vcpu->arch.st.steal, sizeof(struct kvm_steal_time)); + kvm_unmap_gfn(vcpu, &map, &vcpu->arch.st.cache, true, false); } int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) @@ -2497,7 +2503,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return kvm_mtrr_set_msr(vcpu, msr, data); case MSR_IA32_APICBASE: return kvm_set_apic_base(vcpu, msr_info); - case APIC_BASE_MSR ... APIC_BASE_MSR + 0x3ff: + case APIC_BASE_MSR ... APIC_BASE_MSR + 0xff: return kvm_x2apic_msr_write(vcpu, msr, data); case MSR_IA32_TSCDEADLINE: kvm_set_lapic_tscdeadline_msr(vcpu, data); @@ -2575,11 +2581,6 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (data & KVM_STEAL_RESERVED_MASK) return 1; - if (kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.st.stime, - data & KVM_STEAL_VALID_BITS, - sizeof(struct kvm_steal_time))) - return 1; - vcpu->arch.st.msr_val = data; if (!(data & KVM_MSR_ENABLED)) @@ -2800,7 +2801,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_APICBASE: msr_info->data = kvm_get_apic_base(vcpu); break; - case APIC_BASE_MSR ... APIC_BASE_MSR + 0x3ff: + case APIC_BASE_MSR ... APIC_BASE_MSR + 0xff: return kvm_x2apic_msr_read(vcpu, msr_info->index, &msr_info->data); break; case MSR_IA32_TSCDEADLINE: @@ -3272,18 +3273,25 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu) { + struct kvm_host_map map; + struct kvm_steal_time *st; + if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED)) return; - if (vcpu->arch.st.steal.preempted) + if (vcpu->arch.st.preempted) return; - vcpu->arch.st.steal.preempted = KVM_VCPU_PREEMPTED; + if (kvm_map_gfn(vcpu, vcpu->arch.st.msr_val >> PAGE_SHIFT, &map, + &vcpu->arch.st.cache, true)) + return; + + st = map.hva + + offset_in_page(vcpu->arch.st.msr_val & KVM_STEAL_VALID_BITS); - kvm_write_guest_offset_cached(vcpu->kvm, &vcpu->arch.st.stime, - &vcpu->arch.st.steal.preempted, - offsetof(struct kvm_steal_time, preempted), - sizeof(vcpu->arch.st.steal.preempted)); + st->preempted = vcpu->arch.st.preempted = KVM_VCPU_PREEMPTED; + + kvm_unmap_gfn(vcpu, &map, &vcpu->arch.st.cache, true, true); } void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) @@ -3344,21 +3352,23 @@ static int kvm_vcpu_ioctl_set_lapic(struct kvm_vcpu *vcpu, static int kvm_cpu_accept_dm_intr(struct kvm_vcpu *vcpu) { + /* + * We can accept userspace's request for interrupt injection + * as long as we have a place to store the interrupt number. + * The actual injection will happen when the CPU is able to + * deliver the interrupt. + */ + if (kvm_cpu_has_extint(vcpu)) + return false; + + /* Acknowledging ExtINT does not happen if LINT0 is masked. */ return (!lapic_in_kernel(vcpu) || kvm_apic_accept_pic_intr(vcpu)); } -/* - * if userspace requested an interrupt window, check that the - * interrupt window is open. - * - * No need to exit to userspace if we already have an interrupt queued. - */ static int kvm_vcpu_ready_for_interrupt_injection(struct kvm_vcpu *vcpu) { return kvm_arch_interrupt_allowed(vcpu) && - !kvm_cpu_has_interrupt(vcpu) && - !kvm_event_needs_reinjection(vcpu) && kvm_cpu_accept_dm_intr(vcpu); } @@ -3419,7 +3429,7 @@ static int kvm_vcpu_ioctl_x86_setup_mce(struct kvm_vcpu *vcpu, unsigned bank_num = mcg_cap & 0xff, bank; r = -EINVAL; - if (!bank_num || bank_num >= KVM_MAX_MCE_BANKS) + if (!bank_num || bank_num > KVM_MAX_MCE_BANKS) goto out; if (mcg_cap & ~(kvm_mce_cap_supported | 0xff | 0xff0000)) goto out; @@ -3490,6 +3500,10 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu, struct kvm_vcpu_events *events) { process_nmi(vcpu); + + if (kvm_check_request(KVM_REQ_SMI, vcpu)) + process_smi(vcpu); + /* * FIXME: pass injected and pending separately. This is only * needed for nested virtualization, whose state cannot be @@ -4662,10 +4676,13 @@ set_identity_unlock: r = -EFAULT; if (copy_from_user(&u.ps, argp, sizeof u.ps)) goto out; + mutex_lock(&kvm->lock); r = -ENXIO; if (!kvm->arch.vpit) - goto out; + goto set_pit_out; r = kvm_vm_ioctl_set_pit(kvm, &u.ps); +set_pit_out: + mutex_unlock(&kvm->lock); break; } case KVM_GET_PIT2: { @@ -4685,10 +4702,13 @@ set_identity_unlock: r = -EFAULT; if (copy_from_user(&u.ps2, argp, sizeof(u.ps2))) goto out; + mutex_lock(&kvm->lock); r = -ENXIO; if (!kvm->arch.vpit) - goto out; + goto set_pit2_out; r = kvm_vm_ioctl_set_pit2(kvm, &u.ps2); +set_pit2_out: + mutex_unlock(&kvm->lock); break; } case KVM_REINJECT_CONTROL: { @@ -6771,35 +6791,6 @@ static struct perf_guest_info_callbacks kvm_guest_cbs = { .get_guest_ip = kvm_get_guest_ip, }; -static void kvm_set_mmio_spte_mask(void) -{ - u64 mask; - int maxphyaddr = boot_cpu_data.x86_phys_bits; - - /* - * Set the reserved bits and the present bit of an paging-structure - * entry to generate page fault with PFER.RSV = 1. - */ - - /* - * Mask the uppermost physical address bit, which would be reserved as - * long as the supported physical address width is less than 52. - */ - mask = 1ull << 51; - - /* Set the present bit. */ - mask |= 1ull; - - /* - * If reserved bit is not supported, clear the present bit to disable - * mmio page fault. - */ - if (maxphyaddr == 52) - mask &= ~1ull; - - kvm_mmu_set_mmio_spte_mask(mask, mask); -} - #ifdef CONFIG_X86_64 static void pvclock_gtod_update_fn(struct work_struct *work) { @@ -6877,8 +6868,6 @@ int kvm_arch_init(void *opaque) if (r) goto out_free_percpu; - kvm_set_mmio_spte_mask(); - kvm_x86_ops = ops; kvm_mmu_set_mask_ptes(PT_USER_MASK, PT_ACCESSED_MASK, @@ -6922,6 +6911,7 @@ void kvm_arch_exit(void) cpuhp_remove_state_nocalls(CPUHP_AP_X86_KVM_CLK_ONLINE); #ifdef CONFIG_X86_64 pvclock_gtod_unregister_notifier(&pvclock_gtod_notifier); + cancel_work_sync(&pvclock_gtod_work); #endif kvm_x86_ops = NULL; kvm_mmu_module_exit(); @@ -7124,7 +7114,7 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu) kvm_x86_ops->update_cr8_intercept(vcpu, tpr, max_irr); } -static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win) +static int inject_pending_event(struct kvm_vcpu *vcpu) { int r; @@ -7160,7 +7150,7 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win) * from L2 to L1. */ if (is_guest_mode(vcpu) && kvm_x86_ops->check_nested_events) { - r = kvm_x86_ops->check_nested_events(vcpu, req_int_win); + r = kvm_x86_ops->check_nested_events(vcpu); if (r != 0) return r; } @@ -7210,7 +7200,7 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win) * KVM_REQ_EVENT only on certain events and not unconditionally? */ if (is_guest_mode(vcpu) && kvm_x86_ops->check_nested_events) { - r = kvm_x86_ops->check_nested_events(vcpu, req_int_win); + r = kvm_x86_ops->check_nested_events(vcpu); if (r != 0) return r; } @@ -7521,9 +7511,8 @@ static void vcpu_load_eoi_exitmap(struct kvm_vcpu *vcpu) kvm_x86_ops->load_eoi_exitmap(vcpu, eoi_exit_bitmap); } -int kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm, - unsigned long start, unsigned long end, - bool blockable) +void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm, + unsigned long start, unsigned long end) { unsigned long apic_address; @@ -7534,8 +7523,6 @@ int kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm, apic_address = gfn_to_hva(kvm, APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT); if (start <= apic_address && apic_address < end) kvm_make_all_cpus_request(kvm, KVM_REQ_APIC_PAGE_RELOAD); - - return 0; } void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu) @@ -7683,7 +7670,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) goto out; } - if (inject_pending_event(vcpu, req_int_win) != 0) + if (inject_pending_event(vcpu) != 0) req_immediate_exit = true; else { /* Enable SMI/NMI/IRQ window open exits if needed. @@ -7894,7 +7881,7 @@ static inline int vcpu_block(struct kvm *kvm, struct kvm_vcpu *vcpu) static inline bool kvm_vcpu_running(struct kvm_vcpu *vcpu) { if (is_guest_mode(vcpu) && kvm_x86_ops->check_nested_events) - kvm_x86_ops->check_nested_events(vcpu, false); + kvm_x86_ops->check_nested_events(vcpu); return (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE && !vcpu->arch.apf.halted); @@ -8634,6 +8621,9 @@ static void fx_init(struct kvm_vcpu *vcpu) void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu) { void *wbinvd_dirty_mask = vcpu->arch.wbinvd_dirty_mask; + struct gfn_to_pfn_cache *cache = &vcpu->arch.st.cache; + + kvm_release_pfn(cache->pfn, cache->dirty, cache); kvmclock_reset(vcpu); @@ -9229,6 +9219,13 @@ int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, { int i; + /* + * Clear out the previous array pointers for the KVM_MR_MOVE case. The + * old arrays will be freed by __kvm_set_memory_region() if installing + * the new memslot is successful. + */ + memset(&slot->arch, 0, sizeof(slot->arch)); + for (i = 0; i < KVM_NR_PAGE_SIZES; ++i) { struct kvm_lpage_info *linfo; unsigned long ugfn; @@ -9291,11 +9288,18 @@ out_free: void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen) { + struct kvm_vcpu *vcpu; + int i; + /* * memslots->generation has been incremented. * mmio generation may have reached its maximum value. */ kvm_mmu_invalidate_mmio_sptes(kvm, gen); + + /* Force re-initialization of steal_time cache */ + kvm_for_each_vcpu(i, vcpu, kvm) + kvm_vcpu_kick(vcpu); } int kvm_arch_prepare_memory_region(struct kvm *kvm, @@ -9303,6 +9307,10 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, const struct kvm_userspace_memory_region *mem, enum kvm_mr_change change) { + if (change == KVM_MR_MOVE) + return kvm_arch_create_memslot(kvm, memslot, + mem->memory_size >> PAGE_SHIFT); + return 0; } diff --git a/arch/x86/lib/insn-eval.c b/arch/x86/lib/insn-eval.c index 87dcba101e56..3172eaf4ec5e 100644 --- a/arch/x86/lib/insn-eval.c +++ b/arch/x86/lib/insn-eval.c @@ -70,14 +70,15 @@ static int get_seg_reg_override_idx(struct insn *insn) { int idx = INAT_SEG_REG_DEFAULT; int num_overrides = 0, i; + insn_byte_t p; insn_get_prefixes(insn); /* Look for any segment override prefixes. */ - for (i = 0; i < insn->prefixes.nbytes; i++) { + for_each_insn_prefix(insn, i, p) { insn_attr_t attr; - attr = inat_get_opcode_attribute(insn->prefixes.bytes[i]); + attr = inat_get_opcode_attribute(p); switch (attr) { case INAT_MAKE_PREFIX(INAT_PFX_CS): idx = INAT_SEG_REG_CS; diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S index 9d05572370ed..84b0078272d1 100644 --- a/arch/x86/lib/memcpy_64.S +++ b/arch/x86/lib/memcpy_64.S @@ -14,8 +14,6 @@ * to a jmp to memcpy_erms which does the REP; MOVSB mem copy. */ -.weak memcpy - /* * memcpy - Copy a memory block. * @@ -28,7 +26,9 @@ * rax original destination */ ENTRY(__memcpy) -ENTRY(memcpy) +.weak memcpy +.p2align 4, 0x90 +memcpy: ALTERNATIVE_2 "jmp memcpy_orig", "", X86_FEATURE_REP_GOOD, \ "jmp memcpy_erms", X86_FEATURE_ERMS diff --git a/arch/x86/lib/memmove_64.S b/arch/x86/lib/memmove_64.S index bbec69d8223b..e1cfc880f42d 100644 --- a/arch/x86/lib/memmove_64.S +++ b/arch/x86/lib/memmove_64.S @@ -25,8 +25,8 @@ * rax: dest */ .weak memmove - -ENTRY(memmove) +.p2align 4, 0x90 +memmove: ENTRY(__memmove) /* Handle more 32 bytes in loop */ diff --git a/arch/x86/lib/memset_64.S b/arch/x86/lib/memset_64.S index 9bc861c71e75..084189acdcd0 100644 --- a/arch/x86/lib/memset_64.S +++ b/arch/x86/lib/memset_64.S @@ -6,8 +6,6 @@ #include <asm/alternative-asm.h> #include <asm/export.h> -.weak memset - /* * ISO C memset - set a memory block to a byte value. This function uses fast * string to get better performance than the original function. The code is @@ -19,7 +17,9 @@ * * rax original destination */ -ENTRY(memset) +.weak memset +.p2align 4, 0x90 +memset: ENTRY(__memset) /* * Some CPUs support enhanced REP MOVSB/STOSB feature. It is recommended diff --git a/arch/x86/lib/msr-smp.c b/arch/x86/lib/msr-smp.c index fee8b9c0520c..9009393f44c7 100644 --- a/arch/x86/lib/msr-smp.c +++ b/arch/x86/lib/msr-smp.c @@ -253,7 +253,7 @@ static void __wrmsr_safe_regs_on_cpu(void *info) rv->err = wrmsr_safe_regs(rv->regs); } -int rdmsr_safe_regs_on_cpu(unsigned int cpu, u32 *regs) +int rdmsr_safe_regs_on_cpu(unsigned int cpu, u32 regs[8]) { int err; struct msr_regs_info rv; @@ -266,7 +266,7 @@ int rdmsr_safe_regs_on_cpu(unsigned int cpu, u32 *regs) } EXPORT_SYMBOL(rdmsr_safe_regs_on_cpu); -int wrmsr_safe_regs_on_cpu(unsigned int cpu, u32 *regs) +int wrmsr_safe_regs_on_cpu(unsigned int cpu, u32 regs[8]) { int err; struct msr_regs_info rv; diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c index 9c5606d88f61..40dbbd8f1fe4 100644 --- a/arch/x86/lib/usercopy_64.c +++ b/arch/x86/lib/usercopy_64.c @@ -23,6 +23,7 @@ unsigned long __clear_user(void __user *addr, unsigned long size) asm volatile( " testq %[size8],%[size8]\n" " jz 4f\n" + " .align 16\n" "0: movq $0,(%[dst])\n" " addq $8,%[dst]\n" " decl %%ecx ; jnz 0b\n" @@ -138,7 +139,7 @@ long __copy_user_flushcache(void *dst, const void __user *src, unsigned size) */ if (size < 8) { if (!IS_ALIGNED(dest, 4) || size != 4) - clean_cache_range(dst, 1); + clean_cache_range(dst, size); } else { if (!IS_ALIGNED(dest, 8)) { dest = ALIGN(dest, boot_cpu_data.x86_clflush_size); diff --git a/arch/x86/math-emu/wm_sqrt.S b/arch/x86/math-emu/wm_sqrt.S index f031c0e19356..515cdee90df7 100644 --- a/arch/x86/math-emu/wm_sqrt.S +++ b/arch/x86/math-emu/wm_sqrt.S @@ -209,7 +209,7 @@ sqrt_stage_2_finish: #ifdef PARANOID /* It should be possible to get here only if the arg is ffff....ffff */ - cmp $0xffffffff,FPU_fsqrt_arg_1 + cmpl $0xffffffff,FPU_fsqrt_arg_1 jnz sqrt_stage_2_error #endif /* PARANOID */ diff --git a/arch/x86/mm/ident_map.c b/arch/x86/mm/ident_map.c index fe7a12599d8e..968d7005f4a7 100644 --- a/arch/x86/mm/ident_map.c +++ b/arch/x86/mm/ident_map.c @@ -62,6 +62,7 @@ static int ident_p4d_init(struct x86_mapping_info *info, p4d_t *p4d_page, unsigned long addr, unsigned long end) { unsigned long next; + int result; for (; addr < end; addr = next) { p4d_t *p4d = p4d_page + p4d_index(addr); @@ -73,13 +74,20 @@ static int ident_p4d_init(struct x86_mapping_info *info, p4d_t *p4d_page, if (p4d_present(*p4d)) { pud = pud_offset(p4d, 0); - ident_pud_init(info, pud, addr, next); + result = ident_pud_init(info, pud, addr, next); + if (result) + return result; + continue; } pud = (pud_t *)info->alloc_pgt_page(info->context); if (!pud) return -ENOMEM; - ident_pud_init(info, pud, addr, next); + + result = ident_pud_init(info, pud, addr, next); + if (result) + return result; + set_p4d(p4d, __p4d(__pa(pud) | info->kernpg_flag)); } diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index fb5f29c60019..b1dba0987565 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -120,8 +120,6 @@ __ref void *alloc_low_pages(unsigned int num) } else { pfn = pgt_buf_end; pgt_buf_end += num; - printk(KERN_DEBUG "BRK [%#010lx, %#010lx] PGTABLE\n", - pfn << PAGE_SHIFT, (pgt_buf_end << PAGE_SHIFT) - 1); } for (i = 0; i < num; i++) { diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c index 006f373f54ab..c0499c38962b 100644 --- a/arch/x86/mm/mem_encrypt.c +++ b/arch/x86/mm/mem_encrypt.c @@ -228,7 +228,7 @@ static void __init __set_clr_pte_enc(pte_t *kpte, int level, bool enc) if (pgprot_val(old_prot) == pgprot_val(new_prot)) return; - pa = pfn << page_level_shift(level); + pa = pfn << PAGE_SHIFT; size = page_level_size(level); /* diff --git a/arch/x86/mm/mem_encrypt_identity.c b/arch/x86/mm/mem_encrypt_identity.c index c9faf34cbb62..1f25201de0af 100644 --- a/arch/x86/mm/mem_encrypt_identity.c +++ b/arch/x86/mm/mem_encrypt_identity.c @@ -47,8 +47,8 @@ #define PMD_FLAGS_LARGE (__PAGE_KERNEL_LARGE_EXEC & ~_PAGE_GLOBAL) #define PMD_FLAGS_DEC PMD_FLAGS_LARGE -#define PMD_FLAGS_DEC_WP ((PMD_FLAGS_DEC & ~_PAGE_CACHE_MASK) | \ - (_PAGE_PAT | _PAGE_PWT)) +#define PMD_FLAGS_DEC_WP ((PMD_FLAGS_DEC & ~_PAGE_LARGE_CACHE_MASK) | \ + (_PAGE_PAT_LARGE | _PAGE_PWT)) #define PMD_FLAGS_ENC (PMD_FLAGS_LARGE | _PAGE_ENC) diff --git a/arch/x86/mm/mmio-mod.c b/arch/x86/mm/mmio-mod.c index 2c1ecf4763c4..e32b003e064a 100644 --- a/arch/x86/mm/mmio-mod.c +++ b/arch/x86/mm/mmio-mod.c @@ -384,7 +384,7 @@ static void enter_uniprocessor(void) int cpu; int err; - if (downed_cpus == NULL && + if (!cpumask_available(downed_cpus) && !alloc_cpumask_var(&downed_cpus, GFP_KERNEL)) { pr_notice("Failed to allocate mask\n"); goto out; @@ -414,7 +414,7 @@ static void leave_uniprocessor(void) int cpu; int err; - if (downed_cpus == NULL || cpumask_weight(downed_cpus) == 0) + if (!cpumask_available(downed_cpus) || cpumask_weight(downed_cpus) == 0) return; pr_notice("Re-enabling CPUs...\n"); for_each_cpu(cpu, downed_cpus) { diff --git a/arch/x86/mm/numa_emulation.c b/arch/x86/mm/numa_emulation.c index d71d72cf6c66..4686757a74d7 100644 --- a/arch/x86/mm/numa_emulation.c +++ b/arch/x86/mm/numa_emulation.c @@ -322,7 +322,7 @@ static int __init split_nodes_size_interleave(struct numa_meminfo *ei, u64 addr, u64 max_addr, u64 size) { return split_nodes_size_interleave_uniform(ei, pi, addr, max_addr, size, - 0, NULL, NUMA_NO_NODE); + 0, NULL, 0); } int __init setup_emu2phys_nid(int *dfl_phys_nid) diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c index a3c9ea29d7cc..324e26d0607b 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -1131,12 +1131,14 @@ static void *memtype_seq_start(struct seq_file *seq, loff_t *pos) static void *memtype_seq_next(struct seq_file *seq, void *v, loff_t *pos) { + kfree(v); ++*pos; return memtype_get_idx(*pos); } static void memtype_seq_stop(struct seq_file *seq, void *v) { + kfree(v); } static int memtype_seq_show(struct seq_file *seq, void *v) @@ -1145,7 +1147,6 @@ static int memtype_seq_show(struct seq_file *seq, void *v) seq_printf(seq, "%s @ 0x%Lx-0x%Lx\n", cattr_name(print_entry->type), print_entry->start, print_entry->end); - kfree(print_entry); return 0; } diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index bf52106ab9c4..c0e9c00402ac 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -838,6 +838,8 @@ int pud_free_pmd_page(pud_t *pud, unsigned long addr) } free_page((unsigned long)pmd_sv); + + pgtable_pmd_page_dtor(virt_to_page(pmd)); free_page((unsigned long)pmd); return 1; diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index b72296bd04a2..2f41a34c8f57 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -321,8 +321,14 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, /* * The membarrier system call requires a full memory barrier and * core serialization before returning to user-space, after - * storing to rq->curr. Writing to CR3 provides that full - * memory barrier and core serializing instruction. + * storing to rq->curr, when changing mm. This is because + * membarrier() sends IPIs to all CPUs that are in the target mm + * to make them issue memory barriers. However, if another CPU + * switches to/from the target mm concurrently with + * membarrier(), it can cause that CPU not to receive an IPI + * when it really should issue a memory barrier. Writing to CR3 + * provides that full memory barrier and core serializing + * instruction. */ if (real_prev == next) { VM_WARN_ON(this_cpu_read(cpu_tlbstate.ctxs[prev_asid].ctx_id) != diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index a32fc3d99407..924ca27a6139 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -142,6 +142,19 @@ static bool is_ereg(u32 reg) BIT(BPF_REG_AX)); } +/* + * is_ereg_8l() == true if BPF register 'reg' is mapped to access x86-64 + * lower 8-bit registers dil,sil,bpl,spl,r8b..r15b, which need extra byte + * of encoding. al,cl,dl,bl have simpler encoding. + */ +static bool is_ereg_8l(u32 reg) +{ + return is_ereg(reg) || + (1 << reg) & (BIT(BPF_REG_1) | + BIT(BPF_REG_2) | + BIT(BPF_REG_FP)); +} + static bool is_axreg(u32 reg) { return reg == BPF_REG_0; @@ -751,9 +764,8 @@ st: if (is_imm8(insn->off)) /* STX: *(u8*)(dst_reg + off) = src_reg */ case BPF_STX | BPF_MEM | BPF_B: /* Emit 'mov byte ptr [rax + off], al' */ - if (is_ereg(dst_reg) || is_ereg(src_reg) || - /* We have to add extra byte for x86 SIL, DIL regs */ - src_reg == BPF_REG_1 || src_reg == BPF_REG_2) + if (is_ereg(dst_reg) || is_ereg_8l(src_reg)) + /* Add extra byte for eregs or SIL,DIL,BPL in src_reg */ EMIT2(add_2mod(0x40, dst_reg, src_reg), 0x88); else EMIT1(0x88); @@ -1007,7 +1019,16 @@ emit_jmp: } if (image) { - if (unlikely(proglen + ilen > oldproglen)) { + /* + * When populating the image, assert that: + * + * i) We do not write beyond the allocated space, and + * ii) addrs[i] did not change from the prior run, in order + * to validate assumptions made for computing branch + * displacements. + */ + if (unlikely(proglen + ilen > oldproglen || + proglen + ilen != addrs[i])) { pr_err("bpf_jit: fatal error\n"); return -EFAULT; } diff --git a/arch/x86/net/bpf_jit_comp32.c b/arch/x86/net/bpf_jit_comp32.c index 24d573bc550d..adee990abab1 100644 --- a/arch/x86/net/bpf_jit_comp32.c +++ b/arch/x86/net/bpf_jit_comp32.c @@ -1830,7 +1830,9 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, STACK_VAR(dst_hi)); EMIT(0x0, 4); } else { - EMIT3(0xC7, add_1reg(0xC0, dst_hi), 0); + /* xor dst_hi,dst_hi */ + EMIT2(0x33, + add_2reg(0xC0, dst_hi, dst_hi)); } break; case BPF_DW: @@ -1968,8 +1970,8 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, goto emit_cond_jmp_signed; } case BPF_JMP | BPF_JSET | BPF_X: { - u8 dreg_lo = dstk ? IA32_EAX : dst_lo; - u8 dreg_hi = dstk ? IA32_EDX : dst_hi; + u8 dreg_lo = IA32_EAX; + u8 dreg_hi = IA32_EDX; u8 sreg_lo = sstk ? IA32_ECX : src_lo; u8 sreg_hi = sstk ? IA32_EBX : src_hi; @@ -1978,6 +1980,12 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, STACK_VAR(dst_lo)); EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EDX), STACK_VAR(dst_hi)); + } else { + /* mov dreg_lo,dst_lo */ + EMIT2(0x89, add_2reg(0xC0, dreg_lo, dst_lo)); + /* mov dreg_hi,dst_hi */ + EMIT2(0x89, + add_2reg(0xC0, dreg_hi, dst_hi)); } if (sstk) { @@ -1996,8 +2004,8 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, } case BPF_JMP | BPF_JSET | BPF_K: { u32 hi; - u8 dreg_lo = dstk ? IA32_EAX : dst_lo; - u8 dreg_hi = dstk ? IA32_EDX : dst_hi; + u8 dreg_lo = IA32_EAX; + u8 dreg_hi = IA32_EDX; u8 sreg_lo = IA32_ECX; u8 sreg_hi = IA32_EBX; @@ -2006,6 +2014,12 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, STACK_VAR(dst_lo)); EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EDX), STACK_VAR(dst_hi)); + } else { + /* mov dreg_lo,dst_lo */ + EMIT2(0x89, add_2reg(0xC0, dreg_lo, dst_lo)); + /* mov dreg_hi,dst_hi */ + EMIT2(0x89, + add_2reg(0xC0, dreg_hi, dst_hi)); } hi = imm32 & (1<<31) ? (u32)~0 : 0; @@ -2187,7 +2201,16 @@ notyet: } if (image) { - if (unlikely(proglen + ilen > oldproglen)) { + /* + * When populating the image, assert that: + * + * i) We do not write beyond the allocated space, and + * ii) addrs[i] did not change from the prior run, in order + * to validate assumptions made for computing branch + * displacements. + */ + if (unlikely(proglen + ilen > oldproglen || + proglen + ilen != addrs[i])) { pr_err("bpf_jit: fatal error\n"); return -EFAULT; } diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c index e723559c386a..0c67a5a94de3 100644 --- a/arch/x86/pci/fixup.c +++ b/arch/x86/pci/fixup.c @@ -572,6 +572,10 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x2fc0, pci_invalid_bar); DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6f60, pci_invalid_bar); DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6fa0, pci_invalid_bar); DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6fc0, pci_invalid_bar); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0xa1ec, pci_invalid_bar); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0xa1ed, pci_invalid_bar); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0xa26c, pci_invalid_bar); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0xa26d, pci_invalid_bar); /* * Device [1022:7808] diff --git a/arch/x86/pci/intel_mid_pci.c b/arch/x86/pci/intel_mid_pci.c index 43867bc85368..eea5a0f3b959 100644 --- a/arch/x86/pci/intel_mid_pci.c +++ b/arch/x86/pci/intel_mid_pci.c @@ -33,6 +33,7 @@ #include <asm/hw_irq.h> #include <asm/io_apic.h> #include <asm/intel-mid.h> +#include <asm/acpi.h> #define PCIE_CAP_OFFSET 0x100 diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c index 9112d1cb397b..22da9bfd8a45 100644 --- a/arch/x86/pci/xen.c +++ b/arch/x86/pci/xen.c @@ -25,6 +25,7 @@ #include <asm/xen/pci.h> #include <asm/xen/cpuid.h> #include <asm/apic.h> +#include <asm/acpi.h> #include <asm/i8259.h> static int xen_pcifront_enable_irq(struct pci_dev *dev) diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index 2a9a703ef4a0..77d05b56089a 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -214,28 +214,30 @@ int __init efi_alloc_page_tables(void) gfp_mask = GFP_KERNEL | __GFP_ZERO; efi_pgd = (pgd_t *)__get_free_pages(gfp_mask, PGD_ALLOCATION_ORDER); if (!efi_pgd) - return -ENOMEM; + goto fail; pgd = efi_pgd + pgd_index(EFI_VA_END); p4d = p4d_alloc(&init_mm, pgd, EFI_VA_END); - if (!p4d) { - free_page((unsigned long)efi_pgd); - return -ENOMEM; - } + if (!p4d) + goto free_pgd; pud = pud_alloc(&init_mm, p4d, EFI_VA_END); - if (!pud) { - if (pgtable_l5_enabled()) - free_page((unsigned long) pgd_page_vaddr(*pgd)); - free_pages((unsigned long)efi_pgd, PGD_ALLOCATION_ORDER); - return -ENOMEM; - } + if (!pud) + goto free_p4d; efi_mm.pgd = efi_pgd; mm_init_cpumask(&efi_mm); init_new_context(NULL, &efi_mm); return 0; + +free_p4d: + if (pgtable_l5_enabled()) + free_page((unsigned long)pgd_page_vaddr(*pgd)); +free_pgd: + free_pages((unsigned long)efi_pgd, PGD_ALLOCATION_ORDER); +fail: + return -ENOMEM; } /* @@ -833,7 +835,7 @@ efi_thunk_set_variable(efi_char16_t *name, efi_guid_t *vendor, phys_vendor = virt_to_phys_or_null(vnd); phys_data = virt_to_phys_or_null_size(data, data_size); - if (!phys_name || !phys_data) + if (!phys_name || (data && !phys_data)) status = EFI_INVALID_PARAMETER; else status = efi_thunk(set_variable, phys_name, phys_vendor, @@ -864,7 +866,7 @@ efi_thunk_set_variable_nonblocking(efi_char16_t *name, efi_guid_t *vendor, phys_vendor = virt_to_phys_or_null(vnd); phys_data = virt_to_phys_or_null_size(data, data_size); - if (!phys_name || !phys_data) + if (!phys_name || (data && !phys_data)) status = EFI_INVALID_PARAMETER; else status = efi_thunk(set_variable, phys_name, phys_vendor, diff --git a/arch/x86/platform/uv/uv_irq.c b/arch/x86/platform/uv/uv_irq.c index fc13cbbb2dce..abb6075397f0 100644 --- a/arch/x86/platform/uv/uv_irq.c +++ b/arch/x86/platform/uv/uv_irq.c @@ -167,9 +167,10 @@ static struct irq_domain *uv_get_irq_domain(void) goto out; uv_domain = irq_domain_create_tree(fn, &uv_domain_ops, NULL); - irq_domain_free_fwnode(fn); if (uv_domain) uv_domain->parent = x86_vector_domain; + else + irq_domain_free_fwnode(fn); out: mutex_unlock(&uv_lock); diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile index b81b5172cf99..2cfa0caef133 100644 --- a/arch/x86/purgatory/Makefile +++ b/arch/x86/purgatory/Makefile @@ -15,7 +15,10 @@ $(obj)/sha256.o: $(srctree)/lib/sha256.c FORCE LDFLAGS_purgatory.ro := -e purgatory_start -r --no-undefined -nostdlib -z nodefaultlib targets += purgatory.ro +# Sanitizer, etc. runtimes are unavailable and cannot be linked here. +GCOV_PROFILE := n KASAN_SANITIZE := n +UBSAN_SANITIZE := n KCOV_INSTRUMENT := n # These are adjustments to the compiler flags used for objects that @@ -23,7 +26,7 @@ KCOV_INSTRUMENT := n PURGATORY_CFLAGS_REMOVE := -mcmodel=kernel PURGATORY_CFLAGS := -mcmodel=large -ffreestanding -fno-zero-initialized-in-bss -PURGATORY_CFLAGS += $(DISABLE_STACKLEAK_PLUGIN) +PURGATORY_CFLAGS += $(DISABLE_STACKLEAK_PLUGIN) -DDISABLE_BRANCH_PROFILING # Default KBUILD_CFLAGS can have -pg option set when FTRACE is enabled. That # in turn leaves some undefined symbols like __fentry__ in purgatory and not diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c index 3a6c8ebc8032..aa046d46ff8f 100644 --- a/arch/x86/tools/relocs.c +++ b/arch/x86/tools/relocs.c @@ -841,9 +841,11 @@ static int do_reloc32(struct section *sec, Elf_Rel *rel, Elf_Sym *sym, case R_386_PC32: case R_386_PC16: case R_386_PC8: + case R_386_PLT32: /* - * NONE can be ignored and PC relative relocations don't - * need to be adjusted. + * NONE can be ignored and PC relative relocations don't need + * to be adjusted. Because sym must be defined, R_386_PLT32 can + * be treated the same way as R_386_PC32. */ break; @@ -884,9 +886,11 @@ static int do_reloc_real(struct section *sec, Elf_Rel *rel, Elf_Sym *sym, case R_386_PC32: case R_386_PC16: case R_386_PC8: + case R_386_PLT32: /* - * NONE can be ignored and PC relative relocations don't - * need to be adjusted. + * NONE can be ignored and PC relative relocations don't need + * to be adjusted. Because sym must be defined, R_386_PLT32 can + * be treated the same way as R_386_PC32. */ break; diff --git a/arch/x86/xen/efi.c b/arch/x86/xen/efi.c index 66bcdeeee639..90d2e4ce7064 100644 --- a/arch/x86/xen/efi.c +++ b/arch/x86/xen/efi.c @@ -172,7 +172,7 @@ static enum efi_secureboot_mode xen_efi_get_secureboot(void) return efi_secureboot_mode_unknown; } -void __init xen_efi_init(void) +void __init xen_efi_init(struct boot_params *boot_params) { efi_system_table_t *efi_systab_xen; @@ -181,12 +181,12 @@ void __init xen_efi_init(void) if (efi_systab_xen == NULL) return; - strncpy((char *)&boot_params.efi_info.efi_loader_signature, "Xen", - sizeof(boot_params.efi_info.efi_loader_signature)); - boot_params.efi_info.efi_systab = (__u32)__pa(efi_systab_xen); - boot_params.efi_info.efi_systab_hi = (__u32)(__pa(efi_systab_xen) >> 32); + strncpy((char *)&boot_params->efi_info.efi_loader_signature, "Xen", + sizeof(boot_params->efi_info.efi_loader_signature)); + boot_params->efi_info.efi_systab = (__u32)__pa(efi_systab_xen); + boot_params->efi_info.efi_systab_hi = (__u32)(__pa(efi_systab_xen) >> 32); - boot_params.secure_boot = xen_efi_get_secureboot(); + boot_params->secure_boot = xen_efi_get_secureboot(); set_bit(EFI_BOOT, &efi.flags); set_bit(EFI_PARAVIRT, &efi.flags); diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index 76864ea59160..1c3e9185934c 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -1383,6 +1383,15 @@ asmlinkage __visible void __init xen_start_kernel(void) x86_init.mpparse.get_smp_config = x86_init_uint_noop; xen_boot_params_init_edd(); + +#ifdef CONFIG_ACPI + /* + * Disable selecting "Firmware First mode" for correctable + * memory errors, as this is the duty of the hypervisor to + * decide. + */ + acpi_disable_cmcff = 1; +#endif } if (!boot_params.screen_info.orig_video_isVGA) @@ -1400,7 +1409,7 @@ asmlinkage __visible void __init xen_start_kernel(void) /* We need this for printk timestamps */ xen_setup_runstate_info(0); - xen_efi_init(); + xen_efi_init(&boot_params); /* Start the world */ #ifdef CONFIG_X86_32 diff --git a/arch/x86/xen/enlighten_pvh.c b/arch/x86/xen/enlighten_pvh.c index dab07827d25e..f04d22bcf08d 100644 --- a/arch/x86/xen/enlighten_pvh.c +++ b/arch/x86/xen/enlighten_pvh.c @@ -14,6 +14,8 @@ #include <xen/interface/memory.h> #include <xen/interface/hvm/start_info.h> +#include "xen-ops.h" + /* * PVH variables. * @@ -79,6 +81,8 @@ static void __init init_pvh_bootparams(void) pvh_bootparams.hdr.type_of_loader = (9 << 4) | 0; /* Xen loader */ x86_init.acpi.get_root_pointer = pvh_get_root_pointer; + + xen_efi_init(&pvh_bootparams); } /* diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index 159a897151d6..82577eec6d0a 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -706,9 +706,12 @@ int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops, for (i = 0; i < count; i++) { unsigned long mfn, pfn; + struct gnttab_unmap_grant_ref unmap[2]; + int rc; /* Do not add to override if the map failed. */ - if (map_ops[i].status) + if (map_ops[i].status != GNTST_okay || + (kmap_ops && kmap_ops[i].status != GNTST_okay)) continue; if (map_ops[i].flags & GNTMAP_contains_pte) { @@ -722,10 +725,46 @@ int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops, WARN(pfn_to_mfn(pfn) != INVALID_P2M_ENTRY, "page must be ballooned"); - if (unlikely(!set_phys_to_machine(pfn, FOREIGN_FRAME(mfn)))) { - ret = -ENOMEM; - goto out; + if (likely(set_phys_to_machine(pfn, FOREIGN_FRAME(mfn)))) + continue; + + /* + * Signal an error for this slot. This in turn requires + * immediate unmapping. + */ + map_ops[i].status = GNTST_general_error; + unmap[0].host_addr = map_ops[i].host_addr, + unmap[0].handle = map_ops[i].handle; + map_ops[i].handle = ~0; + if (map_ops[i].flags & GNTMAP_device_map) + unmap[0].dev_bus_addr = map_ops[i].dev_bus_addr; + else + unmap[0].dev_bus_addr = 0; + + if (kmap_ops) { + kmap_ops[i].status = GNTST_general_error; + unmap[1].host_addr = kmap_ops[i].host_addr, + unmap[1].handle = kmap_ops[i].handle; + kmap_ops[i].handle = ~0; + if (kmap_ops[i].flags & GNTMAP_device_map) + unmap[1].dev_bus_addr = kmap_ops[i].dev_bus_addr; + else + unmap[1].dev_bus_addr = 0; } + + /* + * Pre-populate both status fields, to be recognizable in + * the log message below. + */ + unmap[0].status = 1; + unmap[1].status = 1; + + rc = HYPERVISOR_grant_table_op(GNTTABOP_unmap_grant_ref, + unmap, 1 + !!kmap_ops); + if (rc || unmap[0].status != GNTST_okay || + unmap[1].status != GNTST_okay) + pr_err_once("gnttab unmap failed: rc=%d st0=%d st1=%d\n", + rc, unmap[0].status, unmap[1].status); } out: @@ -746,17 +785,15 @@ int clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops, unsigned long mfn = __pfn_to_mfn(page_to_pfn(pages[i])); unsigned long pfn = page_to_pfn(pages[i]); - if (mfn == INVALID_P2M_ENTRY || !(mfn & FOREIGN_FRAME_BIT)) { + if (mfn != INVALID_P2M_ENTRY && (mfn & FOREIGN_FRAME_BIT)) + set_phys_to_machine(pfn, INVALID_P2M_ENTRY); + else ret = -EINVAL; - goto out; - } - - set_phys_to_machine(pfn, INVALID_P2M_ENTRY); } if (kunmap_ops) ret = HYPERVISOR_grant_table_op(GNTTABOP_unmap_grant_ref, - kunmap_ops, count); -out: + kunmap_ops, count) ?: ret; + return ret; } EXPORT_SYMBOL_GPL(clear_foreign_p2m_mapping); diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c index e3b18ad49889..41fd4c123165 100644 --- a/arch/x86/xen/smp_pv.c +++ b/arch/x86/xen/smp_pv.c @@ -89,6 +89,7 @@ asmlinkage __visible void cpu_bringup_and_idle(void) { cpu_bringup(); cpu_startup_entry(CPUHP_AP_ONLINE_IDLE); + prevent_tail_call_optimization(); } void xen_smp_intr_free_pv(unsigned int cpu) diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c index 717b4847b473..6fffb86a32ad 100644 --- a/arch/x86/xen/spinlock.c +++ b/arch/x86/xen/spinlock.c @@ -101,10 +101,20 @@ void xen_init_lock_cpu(int cpu) void xen_uninit_lock_cpu(int cpu) { + int irq; + if (!xen_pvspin) return; - unbind_from_irqhandler(per_cpu(lock_kicker_irq, cpu), NULL); + /* + * When booting the kernel with 'mitigations=auto,nosmt', the secondary + * CPUs are not activated, and lock_kicker_irq is not initialized. + */ + irq = per_cpu(lock_kicker_irq, cpu); + if (irq == -1) + return; + + unbind_from_irqhandler(irq, NULL); per_cpu(lock_kicker_irq, cpu) = -1; kfree(per_cpu(irq_name, cpu)); per_cpu(irq_name, cpu) = NULL; diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index 0e60bd918695..2f111f47ba98 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -122,9 +122,9 @@ static inline void __init xen_init_vga(const struct dom0_vga_console_info *info, void __init xen_init_apic(void); #ifdef CONFIG_XEN_EFI -extern void xen_efi_init(void); +extern void xen_efi_init(struct boot_params *boot_params); #else -static inline void __init xen_efi_init(void) +static inline void __init xen_efi_init(struct boot_params *boot_params) { } #endif diff --git a/arch/xtensa/include/asm/uaccess.h b/arch/xtensa/include/asm/uaccess.h index f1158b4c629c..da4effe27007 100644 --- a/arch/xtensa/include/asm/uaccess.h +++ b/arch/xtensa/include/asm/uaccess.h @@ -291,7 +291,7 @@ strncpy_from_user(char *dst, const char *src, long count) return -EFAULT; } #else -long strncpy_from_user(char *dst, const char *src, long count); +long strncpy_from_user(char *dst, const char __user *src, long count); #endif /* diff --git a/arch/xtensa/kernel/perf_event.c b/arch/xtensa/kernel/perf_event.c index ff1d81385ed7..768e1f7ab871 100644 --- a/arch/xtensa/kernel/perf_event.c +++ b/arch/xtensa/kernel/perf_event.c @@ -404,7 +404,7 @@ static struct pmu xtensa_pmu = { .read = xtensa_pmu_read, }; -static int xtensa_pmu_setup(int cpu) +static int xtensa_pmu_setup(unsigned int cpu) { unsigned i; diff --git a/arch/xtensa/kernel/setup.c b/arch/xtensa/kernel/setup.c index 15580e4fc766..6a0167ac803c 100644 --- a/arch/xtensa/kernel/setup.c +++ b/arch/xtensa/kernel/setup.c @@ -720,7 +720,8 @@ c_start(struct seq_file *f, loff_t *pos) static void * c_next(struct seq_file *f, void *v, loff_t *pos) { - return NULL; + ++*pos; + return c_start(f, pos); } static void diff --git a/arch/xtensa/kernel/xtensa_ksyms.c b/arch/xtensa/kernel/xtensa_ksyms.c index 4092555828b1..24cf6972eace 100644 --- a/arch/xtensa/kernel/xtensa_ksyms.c +++ b/arch/xtensa/kernel/xtensa_ksyms.c @@ -87,13 +87,13 @@ void __xtensa_libgcc_window_spill(void) } EXPORT_SYMBOL(__xtensa_libgcc_window_spill); -unsigned long __sync_fetch_and_and_4(unsigned long *p, unsigned long v) +unsigned int __sync_fetch_and_and_4(volatile void *p, unsigned int v) { BUG(); } EXPORT_SYMBOL(__sync_fetch_and_and_4); -unsigned long __sync_fetch_and_or_4(unsigned long *p, unsigned long v) +unsigned int __sync_fetch_and_or_4(volatile void *p, unsigned int v) { BUG(); } diff --git a/arch/xtensa/mm/cache.c b/arch/xtensa/mm/cache.c index 9220dcde7520..d1ebe67c68d4 100644 --- a/arch/xtensa/mm/cache.c +++ b/arch/xtensa/mm/cache.c @@ -71,8 +71,10 @@ static inline void kmap_invalidate_coherent(struct page *page, kvaddr = TLBTEMP_BASE_1 + (page_to_phys(page) & DCACHE_ALIAS_MASK); + preempt_disable(); __invalidate_dcache_page_alias(kvaddr, page_to_phys(page)); + preempt_enable(); } } } @@ -157,6 +159,7 @@ void flush_dcache_page(struct page *page) if (!alias && !mapping) return; + preempt_disable(); virt = TLBTEMP_BASE_1 + (phys & DCACHE_ALIAS_MASK); __flush_invalidate_dcache_page_alias(virt, phys); @@ -167,6 +170,7 @@ void flush_dcache_page(struct page *page) if (mapping) __invalidate_icache_page_alias(virt, phys); + preempt_enable(); } /* There shouldn't be an entry in the cache for this page anymore. */ @@ -200,8 +204,10 @@ void local_flush_cache_page(struct vm_area_struct *vma, unsigned long address, unsigned long phys = page_to_phys(pfn_to_page(pfn)); unsigned long virt = TLBTEMP_BASE_1 + (address & DCACHE_ALIAS_MASK); + preempt_disable(); __flush_invalidate_dcache_page_alias(virt, phys); __invalidate_icache_page_alias(virt, phys); + preempt_enable(); } EXPORT_SYMBOL(local_flush_cache_page); @@ -228,11 +234,13 @@ update_mmu_cache(struct vm_area_struct * vma, unsigned long addr, pte_t *ptep) unsigned long phys = page_to_phys(page); unsigned long tmp; + preempt_disable(); tmp = TLBTEMP_BASE_1 + (phys & DCACHE_ALIAS_MASK); __flush_invalidate_dcache_page_alias(tmp, phys); tmp = TLBTEMP_BASE_1 + (addr & DCACHE_ALIAS_MASK); __flush_invalidate_dcache_page_alias(tmp, phys); __invalidate_icache_page_alias(tmp, phys); + preempt_enable(); clear_bit(PG_arch_1, &page->flags); } @@ -266,7 +274,9 @@ void copy_to_user_page(struct vm_area_struct *vma, struct page *page, if (alias) { unsigned long t = TLBTEMP_BASE_1 + (vaddr & DCACHE_ALIAS_MASK); + preempt_disable(); __flush_invalidate_dcache_page_alias(t, phys); + preempt_enable(); } /* Copy data */ @@ -281,9 +291,11 @@ void copy_to_user_page(struct vm_area_struct *vma, struct page *page, if (alias) { unsigned long t = TLBTEMP_BASE_1 + (vaddr & DCACHE_ALIAS_MASK); + preempt_disable(); __flush_invalidate_dcache_range((unsigned long) dst, len); if ((vma->vm_flags & VM_EXEC) != 0) __invalidate_icache_page_alias(t, phys); + preempt_enable(); } else if ((vma->vm_flags & VM_EXEC) != 0) { __flush_dcache_range((unsigned long)dst,len); @@ -305,7 +317,9 @@ extern void copy_from_user_page(struct vm_area_struct *vma, struct page *page, if (alias) { unsigned long t = TLBTEMP_BASE_1 + (vaddr & DCACHE_ALIAS_MASK); + preempt_disable(); __flush_invalidate_dcache_page_alias(t, phys); + preempt_enable(); } memcpy(dst, src, len); |