diff options
Diffstat (limited to 'arch')
246 files changed, 2741 insertions, 1392 deletions
diff --git a/arch/Kconfig b/arch/Kconfig index 26b8ed11639d..d3c4ab249e9c 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -991,6 +991,16 @@ config HAVE_ARCH_COMPAT_MMAP_BASES and vice-versa 32-bit applications to call 64-bit mmap(). Required for applications doing different bitness syscalls. +config PAGE_SIZE_LESS_THAN_64KB + def_bool y + depends on !ARM64_64K_PAGES + depends on !IA64_PAGE_SIZE_64KB + depends on !PAGE_SIZE_64KB + depends on !PARISC_PAGE_SIZE_64KB + depends on !PPC_64K_PAGES + depends on !PPC_256K_PAGES + depends on !PAGE_SIZE_256KB + # This allows to use a set of generic functions to determine mmap base # address by giving priority to top-down scheme only if the process # is not in legacy mode (compat task, unlimited stack size or diff --git a/arch/alpha/kernel/syscalls/syscall.tbl b/arch/alpha/kernel/syscalls/syscall.tbl index e4a041cd5715..ca5a32228cd6 100644 --- a/arch/alpha/kernel/syscalls/syscall.tbl +++ b/arch/alpha/kernel/syscalls/syscall.tbl @@ -488,3 +488,4 @@ 556 common landlock_restrict_self sys_landlock_restrict_self # 557 reserved for memfd_secret 558 common process_mrelease sys_process_mrelease +559 common futex_waitv sys_futex_waitv diff --git a/arch/arc/include/asm/cacheflush.h b/arch/arc/include/asm/cacheflush.h index e8c2c7469e10..e201b4b1655a 100644 --- a/arch/arc/include/asm/cacheflush.h +++ b/arch/arc/include/asm/cacheflush.h @@ -36,7 +36,6 @@ void __flush_dcache_page(phys_addr_t paddr, unsigned long vaddr); #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 void flush_dcache_page(struct page *page); -void flush_dcache_folio(struct folio *folio); void dma_cache_wback_inv(phys_addr_t start, unsigned long sz); void dma_cache_inv(phys_addr_t start, unsigned long sz); diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index f0f9e8bec83a..c2724d986fa0 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -1463,6 +1463,7 @@ config HIGHMEM bool "High Memory Support" depends on MMU select KMAP_LOCAL + select KMAP_LOCAL_NON_LINEAR_PTE_ARRAY help The address space of ARM processors is only 4 Gigabytes large and it has to accommodate user address space, kernel address diff --git a/arch/arm/Makefile b/arch/arm/Makefile index a522716565c6..77172d555c7e 100644 --- a/arch/arm/Makefile +++ b/arch/arm/Makefile @@ -60,15 +60,15 @@ KBUILD_CFLAGS += $(call cc-option,-fno-ipa-sra) # Note that GCC does not numerically define an architecture version # macro, but instead defines a whole series of macros which makes # testing for a specific architecture or later rather impossible. -arch-$(CONFIG_CPU_32v7M) =-D__LINUX_ARM_ARCH__=7 -march=armv7-m -Wa,-march=armv7-m -arch-$(CONFIG_CPU_32v7) =-D__LINUX_ARM_ARCH__=7 $(call cc-option,-march=armv7-a,-march=armv5t -Wa$(comma)-march=armv7-a) -arch-$(CONFIG_CPU_32v6) =-D__LINUX_ARM_ARCH__=6 $(call cc-option,-march=armv6,-march=armv5t -Wa$(comma)-march=armv6) +arch-$(CONFIG_CPU_32v7M) =-D__LINUX_ARM_ARCH__=7 -march=armv7-m +arch-$(CONFIG_CPU_32v7) =-D__LINUX_ARM_ARCH__=7 -march=armv7-a +arch-$(CONFIG_CPU_32v6) =-D__LINUX_ARM_ARCH__=6 -march=armv6 # Only override the compiler option if ARMv6. The ARMv6K extensions are # always available in ARMv7 ifeq ($(CONFIG_CPU_32v6),y) -arch-$(CONFIG_CPU_32v6K) =-D__LINUX_ARM_ARCH__=6 $(call cc-option,-march=armv6k,-march=armv5t -Wa$(comma)-march=armv6k) +arch-$(CONFIG_CPU_32v6K) =-D__LINUX_ARM_ARCH__=6 -march=armv6k endif -arch-$(CONFIG_CPU_32v5) =-D__LINUX_ARM_ARCH__=5 $(call cc-option,-march=armv5te,-march=armv4t) +arch-$(CONFIG_CPU_32v5) =-D__LINUX_ARM_ARCH__=5 -march=armv5te arch-$(CONFIG_CPU_32v4T) =-D__LINUX_ARM_ARCH__=4 -march=armv4t arch-$(CONFIG_CPU_32v4) =-D__LINUX_ARM_ARCH__=4 -march=armv4 arch-$(CONFIG_CPU_32v3) =-D__LINUX_ARM_ARCH__=3 -march=armv3m @@ -82,7 +82,7 @@ tune-$(CONFIG_CPU_ARM720T) =-mtune=arm7tdmi tune-$(CONFIG_CPU_ARM740T) =-mtune=arm7tdmi tune-$(CONFIG_CPU_ARM9TDMI) =-mtune=arm9tdmi tune-$(CONFIG_CPU_ARM940T) =-mtune=arm9tdmi -tune-$(CONFIG_CPU_ARM946E) =$(call cc-option,-mtune=arm9e,-mtune=arm9tdmi) +tune-$(CONFIG_CPU_ARM946E) =-mtune=arm9e tune-$(CONFIG_CPU_ARM920T) =-mtune=arm9tdmi tune-$(CONFIG_CPU_ARM922T) =-mtune=arm9tdmi tune-$(CONFIG_CPU_ARM925T) =-mtune=arm9tdmi @@ -90,11 +90,11 @@ tune-$(CONFIG_CPU_ARM926T) =-mtune=arm9tdmi tune-$(CONFIG_CPU_FA526) =-mtune=arm9tdmi tune-$(CONFIG_CPU_SA110) =-mtune=strongarm110 tune-$(CONFIG_CPU_SA1100) =-mtune=strongarm1100 -tune-$(CONFIG_CPU_XSCALE) =$(call cc-option,-mtune=xscale,-mtune=strongarm110) -Wa,-mcpu=xscale -tune-$(CONFIG_CPU_XSC3) =$(call cc-option,-mtune=xscale,-mtune=strongarm110) -Wa,-mcpu=xscale -tune-$(CONFIG_CPU_FEROCEON) =$(call cc-option,-mtune=marvell-f,-mtune=xscale) -tune-$(CONFIG_CPU_V6) =$(call cc-option,-mtune=arm1136j-s,-mtune=strongarm) -tune-$(CONFIG_CPU_V6K) =$(call cc-option,-mtune=arm1136j-s,-mtune=strongarm) +tune-$(CONFIG_CPU_XSCALE) =-mtune=xscale +tune-$(CONFIG_CPU_XSC3) =-mtune=xscale +tune-$(CONFIG_CPU_FEROCEON) =-mtune=xscale +tune-$(CONFIG_CPU_V6) =-mtune=arm1136j-s +tune-$(CONFIG_CPU_V6K) =-mtune=arm1136j-s # Evaluate tune cc-option calls now tune-y := $(tune-y) diff --git a/arch/arm/boot/dts/bcm2711.dtsi b/arch/arm/boot/dts/bcm2711.dtsi index 3b60297af7f6..9e01dbca4a01 100644 --- a/arch/arm/boot/dts/bcm2711.dtsi +++ b/arch/arm/boot/dts/bcm2711.dtsi @@ -506,11 +506,17 @@ #address-cells = <3>; #interrupt-cells = <1>; #size-cells = <2>; - interrupts = <GIC_SPI 148 IRQ_TYPE_LEVEL_HIGH>, + interrupts = <GIC_SPI 147 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 148 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "pcie", "msi"; interrupt-map-mask = <0x0 0x0 0x0 0x7>; interrupt-map = <0 0 0 1 &gicv2 GIC_SPI 143 + IRQ_TYPE_LEVEL_HIGH>, + <0 0 0 2 &gicv2 GIC_SPI 144 + IRQ_TYPE_LEVEL_HIGH>, + <0 0 0 3 &gicv2 GIC_SPI 145 + IRQ_TYPE_LEVEL_HIGH>, + <0 0 0 4 &gicv2 GIC_SPI 146 IRQ_TYPE_LEVEL_HIGH>; msi-controller; msi-parent = <&pcie0>; diff --git a/arch/arm/boot/dts/bcm5301x.dtsi b/arch/arm/boot/dts/bcm5301x.dtsi index d4f355015e3c..f69d2af3c1fa 100644 --- a/arch/arm/boot/dts/bcm5301x.dtsi +++ b/arch/arm/boot/dts/bcm5301x.dtsi @@ -242,6 +242,8 @@ gpio-controller; #gpio-cells = <2>; + interrupt-controller; + #interrupt-cells = <2>; }; pcie0: pcie@12000 { @@ -408,7 +410,7 @@ i2c0: i2c@18009000 { compatible = "brcm,iproc-i2c"; reg = <0x18009000 0x50>; - interrupts = <GIC_SPI 121 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_SPI 89 IRQ_TYPE_LEVEL_HIGH>; #address-cells = <1>; #size-cells = <0>; clock-frequency = <100000>; diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h index e68fb879e4f9..5e56288e343b 100644 --- a/arch/arm/include/asm/cacheflush.h +++ b/arch/arm/include/asm/cacheflush.h @@ -290,7 +290,6 @@ extern void flush_cache_page(struct vm_area_struct *vma, unsigned long user_addr */ #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 extern void flush_dcache_page(struct page *); -void flush_dcache_folio(struct folio *folio); #define ARCH_IMPLEMENTS_FLUSH_KERNEL_VMAP_RANGE 1 static inline void flush_kernel_vmap_range(void *addr, int size) diff --git a/arch/arm/mach-socfpga/core.h b/arch/arm/mach-socfpga/core.h index fc2608b18a0d..18f01190dcfd 100644 --- a/arch/arm/mach-socfpga/core.h +++ b/arch/arm/mach-socfpga/core.h @@ -33,7 +33,7 @@ extern void __iomem *sdr_ctl_base_addr; u32 socfpga_sdram_self_refresh(u32 sdr_base); extern unsigned int socfpga_sdram_self_refresh_sz; -extern char secondary_trampoline, secondary_trampoline_end; +extern char secondary_trampoline[], secondary_trampoline_end[]; extern unsigned long socfpga_cpu1start_addr; diff --git a/arch/arm/mach-socfpga/platsmp.c b/arch/arm/mach-socfpga/platsmp.c index fbb80b883e5d..201191cf68f3 100644 --- a/arch/arm/mach-socfpga/platsmp.c +++ b/arch/arm/mach-socfpga/platsmp.c @@ -20,14 +20,14 @@ static int socfpga_boot_secondary(unsigned int cpu, struct task_struct *idle) { - int trampoline_size = &secondary_trampoline_end - &secondary_trampoline; + int trampoline_size = secondary_trampoline_end - secondary_trampoline; if (socfpga_cpu1start_addr) { /* This will put CPU #1 into reset. */ writel(RSTMGR_MPUMODRST_CPU1, rst_manager_base_addr + SOCFPGA_RSTMGR_MODMPURST); - memcpy(phys_to_virt(0), &secondary_trampoline, trampoline_size); + memcpy(phys_to_virt(0), secondary_trampoline, trampoline_size); writel(__pa_symbol(secondary_startup), sys_manager_base_addr + (socfpga_cpu1start_addr & 0x000000ff)); @@ -45,12 +45,12 @@ static int socfpga_boot_secondary(unsigned int cpu, struct task_struct *idle) static int socfpga_a10_boot_secondary(unsigned int cpu, struct task_struct *idle) { - int trampoline_size = &secondary_trampoline_end - &secondary_trampoline; + int trampoline_size = secondary_trampoline_end - secondary_trampoline; if (socfpga_cpu1start_addr) { writel(RSTMGR_MPUMODRST_CPU1, rst_manager_base_addr + SOCFPGA_A10_RSTMGR_MODMPURST); - memcpy(phys_to_virt(0), &secondary_trampoline, trampoline_size); + memcpy(phys_to_virt(0), secondary_trampoline, trampoline_size); writel(__pa_symbol(secondary_startup), sys_manager_base_addr + (socfpga_cpu1start_addr & 0x00000fff)); diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index a4e006005107..274e4f73fd33 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -390,9 +390,9 @@ void __set_fixmap(enum fixed_addresses idx, phys_addr_t phys, pgprot_t prot) BUILD_BUG_ON(__fix_to_virt(__end_of_fixed_addresses) < FIXADDR_START); BUG_ON(idx >= __end_of_fixed_addresses); - /* we only support device mappings until pgprot_kernel has been set */ + /* We support only device mappings before pgprot_kernel is set. */ if (WARN_ON(pgprot_val(prot) != pgprot_val(FIXMAP_PAGE_IO) && - pgprot_val(pgprot_kernel) == 0)) + pgprot_val(prot) && pgprot_val(pgprot_kernel) == 0)) return; if (pgprot_val(prot)) diff --git a/arch/arm64/boot/dts/exynos/exynosautov9.dtsi b/arch/arm64/boot/dts/exynos/exynosautov9.dtsi index 3e4727344b4a..a960c0bc2dba 100644 --- a/arch/arm64/boot/dts/exynos/exynosautov9.dtsi +++ b/arch/arm64/boot/dts/exynos/exynosautov9.dtsi @@ -296,8 +296,7 @@ pinctrl-0 = <&ufs_rst_n &ufs_refclk_out>; phys = <&ufs_0_phy>; phy-names = "ufs-phy"; - samsung,sysreg = <&syscon_fsys2>; - samsung,ufs-shareability-reg-offset = <0x710>; + samsung,sysreg = <&syscon_fsys2 0x710>; status = "disabled"; }; }; diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h index a305ce256090..d52a0b269ee8 100644 --- a/arch/arm64/include/asm/esr.h +++ b/arch/arm64/include/asm/esr.h @@ -68,6 +68,7 @@ #define ESR_ELx_EC_MAX (0x3F) #define ESR_ELx_EC_SHIFT (26) +#define ESR_ELx_EC_WIDTH (6) #define ESR_ELx_EC_MASK (UL(0x3F) << ESR_ELx_EC_SHIFT) #define ESR_ELx_EC(esr) (((esr) & ESR_ELx_EC_MASK) >> ESR_ELx_EC_SHIFT) diff --git a/arch/arm64/include/asm/ftrace.h b/arch/arm64/include/asm/ftrace.h index 347b0cc68f07..1494cfa8639b 100644 --- a/arch/arm64/include/asm/ftrace.h +++ b/arch/arm64/include/asm/ftrace.h @@ -12,6 +12,17 @@ #define HAVE_FUNCTION_GRAPH_FP_TEST +/* + * HAVE_FUNCTION_GRAPH_RET_ADDR_PTR means that the architecture can provide a + * "return address pointer" which can be used to uniquely identify a return + * address which has been overwritten. + * + * On arm64 we use the address of the caller's frame record, which remains the + * same for the lifetime of the instrumented function, unlike the return + * address in the LR. + */ +#define HAVE_FUNCTION_GRAPH_RET_ADDR_PTR + #ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS #define ARCH_SUPPORTS_FTRACE_OPS 1 #else diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h index a39fcf318c77..01d47c5886dc 100644 --- a/arch/arm64/include/asm/kvm_arm.h +++ b/arch/arm64/include/asm/kvm_arm.h @@ -91,7 +91,7 @@ #define HCR_HOST_VHE_FLAGS (HCR_RW | HCR_TGE | HCR_E2H) /* TCR_EL2 Registers bits */ -#define TCR_EL2_RES1 ((1 << 31) | (1 << 23)) +#define TCR_EL2_RES1 ((1U << 31) | (1 << 23)) #define TCR_EL2_TBI (1 << 20) #define TCR_EL2_PS_SHIFT 16 #define TCR_EL2_PS_MASK (7 << TCR_EL2_PS_SHIFT) @@ -276,7 +276,7 @@ #define CPTR_EL2_TFP_SHIFT 10 /* Hyp Coprocessor Trap Register */ -#define CPTR_EL2_TCPAC (1 << 31) +#define CPTR_EL2_TCPAC (1U << 31) #define CPTR_EL2_TAM (1 << 30) #define CPTR_EL2_TTA (1 << 20) #define CPTR_EL2_TFP (1 << CPTR_EL2_TFP_SHIFT) diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 4be8486042a7..2a5f7f38006f 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -584,7 +584,7 @@ struct kvm_vcpu_stat { u64 exits; }; -int kvm_vcpu_preferred_target(struct kvm_vcpu_init *init); +void kvm_vcpu_preferred_target(struct kvm_vcpu_init *init); unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu); int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *indices); int kvm_arm_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg); diff --git a/arch/arm64/include/asm/pgalloc.h b/arch/arm64/include/asm/pgalloc.h index 8433a2058eb1..237224484d0f 100644 --- a/arch/arm64/include/asm/pgalloc.h +++ b/arch/arm64/include/asm/pgalloc.h @@ -76,7 +76,7 @@ static inline void __pmd_populate(pmd_t *pmdp, phys_addr_t ptep, static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmdp, pte_t *ptep) { - VM_BUG_ON(mm != &init_mm); + VM_BUG_ON(mm && mm != &init_mm); __pmd_populate(pmdp, __pa(ptep), PMD_TYPE_TABLE | PMD_TABLE_UXN); } diff --git a/arch/arm64/include/asm/stacktrace.h b/arch/arm64/include/asm/stacktrace.h index a4e046ef4568..6564a01cc085 100644 --- a/arch/arm64/include/asm/stacktrace.h +++ b/arch/arm64/include/asm/stacktrace.h @@ -47,9 +47,6 @@ struct stack_info { * @prev_type: The type of stack this frame record was on, or a synthetic * value of STACK_TYPE_UNKNOWN. This is used to detect a * transition from one stack to another. - * - * @graph: When FUNCTION_GRAPH_TRACER is selected, holds the index of a - * replacement lr value in the ftrace graph stack. */ struct stackframe { unsigned long fp; @@ -57,9 +54,6 @@ struct stackframe { DECLARE_BITMAP(stacks_done, __NR_STACK_TYPES); unsigned long prev_fp; enum stack_type prev_type; -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - int graph; -#endif #ifdef CONFIG_KRETPROBES struct llist_node *kr_cur; #endif diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h index 6e2e0b7031ab..3a5ff5e20586 100644 --- a/arch/arm64/include/asm/uaccess.h +++ b/arch/arm64/include/asm/uaccess.h @@ -281,12 +281,22 @@ do { \ (x) = (__force __typeof__(*(ptr)))__gu_val; \ } while (0) +/* + * We must not call into the scheduler between uaccess_ttbr0_enable() and + * uaccess_ttbr0_disable(). As `x` and `ptr` could contain blocking functions, + * we must evaluate these outside of the critical section. + */ #define __raw_get_user(x, ptr, err) \ do { \ + __typeof__(*(ptr)) __user *__rgu_ptr = (ptr); \ + __typeof__(x) __rgu_val; \ __chk_user_ptr(ptr); \ + \ uaccess_ttbr0_enable(); \ - __raw_get_mem("ldtr", x, ptr, err); \ + __raw_get_mem("ldtr", __rgu_val, __rgu_ptr, err); \ uaccess_ttbr0_disable(); \ + \ + (x) = __rgu_val; \ } while (0) #define __get_user_error(x, ptr, err) \ @@ -310,14 +320,22 @@ do { \ #define get_user __get_user +/* + * We must not call into the scheduler between __uaccess_enable_tco_async() and + * __uaccess_disable_tco_async(). As `dst` and `src` may contain blocking + * functions, we must evaluate these outside of the critical section. + */ #define __get_kernel_nofault(dst, src, type, err_label) \ do { \ + __typeof__(dst) __gkn_dst = (dst); \ + __typeof__(src) __gkn_src = (src); \ int __gkn_err = 0; \ \ __uaccess_enable_tco_async(); \ - __raw_get_mem("ldr", *((type *)(dst)), \ - (__force type *)(src), __gkn_err); \ + __raw_get_mem("ldr", *((type *)(__gkn_dst)), \ + (__force type *)(__gkn_src), __gkn_err); \ __uaccess_disable_tco_async(); \ + \ if (unlikely(__gkn_err)) \ goto err_label; \ } while (0) @@ -351,11 +369,19 @@ do { \ } \ } while (0) +/* + * We must not call into the scheduler between uaccess_ttbr0_enable() and + * uaccess_ttbr0_disable(). As `x` and `ptr` could contain blocking functions, + * we must evaluate these outside of the critical section. + */ #define __raw_put_user(x, ptr, err) \ do { \ - __chk_user_ptr(ptr); \ + __typeof__(*(ptr)) __user *__rpu_ptr = (ptr); \ + __typeof__(*(ptr)) __rpu_val = (x); \ + __chk_user_ptr(__rpu_ptr); \ + \ uaccess_ttbr0_enable(); \ - __raw_put_mem("sttr", x, ptr, err); \ + __raw_put_mem("sttr", __rpu_val, __rpu_ptr, err); \ uaccess_ttbr0_disable(); \ } while (0) @@ -380,14 +406,22 @@ do { \ #define put_user __put_user +/* + * We must not call into the scheduler between __uaccess_enable_tco_async() and + * __uaccess_disable_tco_async(). As `dst` and `src` may contain blocking + * functions, we must evaluate these outside of the critical section. + */ #define __put_kernel_nofault(dst, src, type, err_label) \ do { \ + __typeof__(dst) __pkn_dst = (dst); \ + __typeof__(src) __pkn_src = (src); \ int __pkn_err = 0; \ \ __uaccess_enable_tco_async(); \ - __raw_put_mem("str", *((type *)(src)), \ - (__force type *)(dst), __pkn_err); \ + __raw_put_mem("str", *((type *)(__pkn_src)), \ + (__force type *)(__pkn_dst), __pkn_err); \ __uaccess_disable_tco_async(); \ + \ if (unlikely(__pkn_err)) \ goto err_label; \ } while(0) diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c index fc62dfe73f93..4506c4a90ac1 100644 --- a/arch/arm64/kernel/ftrace.c +++ b/arch/arm64/kernel/ftrace.c @@ -244,8 +244,6 @@ void arch_ftrace_update_code(int command) * on the way back to parent. For this purpose, this function is called * in _mcount() or ftrace_caller() to replace return address (*parent) on * the call stack to return_to_handler. - * - * Note that @frame_pointer is used only for sanity check later. */ void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent, unsigned long frame_pointer) @@ -263,8 +261,10 @@ void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent, */ old = *parent; - if (!function_graph_enter(old, self_addr, frame_pointer, NULL)) + if (!function_graph_enter(old, self_addr, frame_pointer, + (void *)frame_pointer)) { *parent = return_hooker; + } } #ifdef CONFIG_DYNAMIC_FTRACE diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c index c30624fff6ac..94f83cd44e50 100644 --- a/arch/arm64/kernel/stacktrace.c +++ b/arch/arm64/kernel/stacktrace.c @@ -38,9 +38,6 @@ void start_backtrace(struct stackframe *frame, unsigned long fp, { frame->fp = fp; frame->pc = pc; -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - frame->graph = 0; -#endif #ifdef CONFIG_KRETPROBES frame->kr_cur = NULL; #endif @@ -116,20 +113,23 @@ int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame) frame->prev_fp = fp; frame->prev_type = info.type; + frame->pc = ptrauth_strip_insn_pac(frame->pc); + #ifdef CONFIG_FUNCTION_GRAPH_TRACER if (tsk->ret_stack && - (ptrauth_strip_insn_pac(frame->pc) == (unsigned long)return_to_handler)) { - struct ftrace_ret_stack *ret_stack; + (frame->pc == (unsigned long)return_to_handler)) { + unsigned long orig_pc; /* * This is a case where function graph tracer has * modified a return address (LR) in a stack frame * to hook a function return. * So replace it to an original value. */ - ret_stack = ftrace_graph_get_ret_stack(tsk, frame->graph++); - if (WARN_ON_ONCE(!ret_stack)) + orig_pc = ftrace_graph_ret_addr(tsk, NULL, frame->pc, + (void *)frame->fp); + if (WARN_ON_ONCE(frame->pc == orig_pc)) return -EINVAL; - frame->pc = ret_stack->ret; + frame->pc = orig_pc; } #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ #ifdef CONFIG_KRETPROBES @@ -137,8 +137,6 @@ int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame) frame->pc = kretprobe_find_ret_addr(tsk, (void *)frame->fp, &frame->kr_cur); #endif - frame->pc = ptrauth_strip_insn_pac(frame->pc); - return 0; } NOKPROBE_SYMBOL(unwind_frame); diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index f5490afe1ebf..e4727dc771bf 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -223,7 +223,14 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) r = 1; break; case KVM_CAP_NR_VCPUS: - r = num_online_cpus(); + /* + * ARM64 treats KVM_CAP_NR_CPUS differently from all other + * architectures, as it does not always bound it to + * KVM_CAP_MAX_VCPUS. It should not matter much because + * this is just an advisory value. + */ + r = min_t(unsigned int, num_online_cpus(), + kvm_arm_default_max_vcpus()); break; case KVM_CAP_MAX_VCPUS: case KVM_CAP_MAX_VCPU_ID: @@ -1389,12 +1396,9 @@ long kvm_arch_vm_ioctl(struct file *filp, return kvm_vm_ioctl_set_device_addr(kvm, &dev_addr); } case KVM_ARM_PREFERRED_TARGET: { - int err; struct kvm_vcpu_init init; - err = kvm_vcpu_preferred_target(&init); - if (err) - return err; + kvm_vcpu_preferred_target(&init); if (copy_to_user(argp, &init, sizeof(init))) return -EFAULT; diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c index 5ce26bedf23c..e116c7767730 100644 --- a/arch/arm64/kvm/guest.c +++ b/arch/arm64/kvm/guest.c @@ -869,13 +869,10 @@ u32 __attribute_const__ kvm_target_cpu(void) return KVM_ARM_TARGET_GENERIC_V8; } -int kvm_vcpu_preferred_target(struct kvm_vcpu_init *init) +void kvm_vcpu_preferred_target(struct kvm_vcpu_init *init) { u32 target = kvm_target_cpu(); - if (target < 0) - return -ENODEV; - memset(init, 0, sizeof(*init)); /* @@ -885,8 +882,6 @@ int kvm_vcpu_preferred_target(struct kvm_vcpu_init *init) * target type. */ init->target = (__u32)target; - - return 0; } int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) diff --git a/arch/arm64/kvm/hyp/hyp-entry.S b/arch/arm64/kvm/hyp/hyp-entry.S index 9aa9b73475c9..b6b6801d96d5 100644 --- a/arch/arm64/kvm/hyp/hyp-entry.S +++ b/arch/arm64/kvm/hyp/hyp-entry.S @@ -44,7 +44,7 @@ el1_sync: // Guest trapped into EL2 mrs x0, esr_el2 - lsr x0, x0, #ESR_ELx_EC_SHIFT + ubfx x0, x0, #ESR_ELx_EC_SHIFT, #ESR_ELx_EC_WIDTH cmp x0, #ESR_ELx_EC_HVC64 ccmp x0, #ESR_ELx_EC_HVC32, #4, ne b.ne el1_trap diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h index 7a0af1d39303..96c5f3fb7838 100644 --- a/arch/arm64/kvm/hyp/include/hyp/switch.h +++ b/arch/arm64/kvm/hyp/include/hyp/switch.h @@ -403,6 +403,8 @@ typedef bool (*exit_handler_fn)(struct kvm_vcpu *, u64 *); static const exit_handler_fn *kvm_get_exit_handler_array(struct kvm_vcpu *vcpu); +static void early_exit_filter(struct kvm_vcpu *vcpu, u64 *exit_code); + /* * Allow the hypervisor to handle the exit with an exit handler if it has one. * @@ -429,6 +431,18 @@ static inline bool kvm_hyp_handle_exit(struct kvm_vcpu *vcpu, u64 *exit_code) */ static inline bool fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code) { + /* + * Save PSTATE early so that we can evaluate the vcpu mode + * early on. + */ + vcpu->arch.ctxt.regs.pstate = read_sysreg_el2(SYS_SPSR); + + /* + * Check whether we want to repaint the state one way or + * another. + */ + early_exit_filter(vcpu, exit_code); + if (ARM_EXCEPTION_CODE(*exit_code) != ARM_EXCEPTION_IRQ) vcpu->arch.fault.esr_el2 = read_sysreg_el2(SYS_ESR); diff --git a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h index de7e14c862e6..7ecca8b07851 100644 --- a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h +++ b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h @@ -70,7 +70,12 @@ static inline void __sysreg_save_el1_state(struct kvm_cpu_context *ctxt) static inline void __sysreg_save_el2_return_state(struct kvm_cpu_context *ctxt) { ctxt->regs.pc = read_sysreg_el2(SYS_ELR); - ctxt->regs.pstate = read_sysreg_el2(SYS_SPSR); + /* + * Guest PSTATE gets saved at guest fixup time in all + * cases. We still need to handle the nVHE host side here. + */ + if (!has_vhe() && ctxt->__hyp_running_vcpu) + ctxt->regs.pstate = read_sysreg_el2(SYS_SPSR); if (cpus_have_final_cap(ARM64_HAS_RAS_EXTN)) ctxt_sys_reg(ctxt, DISR_EL1) = read_sysreg_s(SYS_VDISR_EL2); diff --git a/arch/arm64/kvm/hyp/nvhe/host.S b/arch/arm64/kvm/hyp/nvhe/host.S index 0c6116d34e18..3d613e721a75 100644 --- a/arch/arm64/kvm/hyp/nvhe/host.S +++ b/arch/arm64/kvm/hyp/nvhe/host.S @@ -141,7 +141,7 @@ SYM_FUNC_END(__host_hvc) .L__vect_start\@: stp x0, x1, [sp, #-16]! mrs x0, esr_el2 - lsr x0, x0, #ESR_ELx_EC_SHIFT + ubfx x0, x0, #ESR_ELx_EC_SHIFT, #ESR_ELx_EC_WIDTH cmp x0, #ESR_ELx_EC_HVC64 b.eq __host_hvc b __host_exit diff --git a/arch/arm64/kvm/hyp/nvhe/setup.c b/arch/arm64/kvm/hyp/nvhe/setup.c index 862c7b514e20..578f71798c2e 100644 --- a/arch/arm64/kvm/hyp/nvhe/setup.c +++ b/arch/arm64/kvm/hyp/nvhe/setup.c @@ -178,7 +178,7 @@ static int finalize_host_mappings_walker(u64 addr, u64 end, u32 level, phys = kvm_pte_to_phys(pte); if (!addr_is_memory(phys)) - return 0; + return -EINVAL; /* * Adjust the host stage-2 mappings to match the ownership attributes @@ -207,8 +207,18 @@ static int finalize_host_mappings(void) .cb = finalize_host_mappings_walker, .flags = KVM_PGTABLE_WALK_LEAF, }; + int i, ret; + + for (i = 0; i < hyp_memblock_nr; i++) { + struct memblock_region *reg = &hyp_memory[i]; + u64 start = (u64)hyp_phys_to_virt(reg->base); + + ret = kvm_pgtable_walk(&pkvm_pgtable, start, reg->size, &walker); + if (ret) + return ret; + } - return kvm_pgtable_walk(&pkvm_pgtable, 0, BIT(pkvm_pgtable.ia_bits), &walker); + return 0; } void __noreturn __pkvm_init_finalise(void) diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c index c0e3fed26d93..d13115a12434 100644 --- a/arch/arm64/kvm/hyp/nvhe/switch.c +++ b/arch/arm64/kvm/hyp/nvhe/switch.c @@ -233,7 +233,7 @@ static const exit_handler_fn *kvm_get_exit_handler_array(struct kvm_vcpu *vcpu) * Returns false if the guest ran in AArch32 when it shouldn't have, and * thus should exit to the host, or true if a the guest run loop can continue. */ -static bool handle_aarch32_guest(struct kvm_vcpu *vcpu, u64 *exit_code) +static void early_exit_filter(struct kvm_vcpu *vcpu, u64 *exit_code) { struct kvm *kvm = kern_hyp_va(vcpu->kvm); @@ -248,10 +248,7 @@ static bool handle_aarch32_guest(struct kvm_vcpu *vcpu, u64 *exit_code) vcpu->arch.target = -1; *exit_code &= BIT(ARM_EXIT_WITH_SERROR_BIT); *exit_code |= ARM_EXCEPTION_IL; - return false; } - - return true; } /* Switch to the guest for legacy non-VHE systems */ @@ -316,9 +313,6 @@ int __kvm_vcpu_run(struct kvm_vcpu *vcpu) /* Jump in the fire! */ exit_code = __guest_enter(vcpu); - if (unlikely(!handle_aarch32_guest(vcpu, &exit_code))) - break; - /* And we're baaack! */ } while (fixup_guest_exit(vcpu, &exit_code)); diff --git a/arch/arm64/kvm/hyp/nvhe/sys_regs.c b/arch/arm64/kvm/hyp/nvhe/sys_regs.c index 3787ee6fb1a2..792cf6e6ac92 100644 --- a/arch/arm64/kvm/hyp/nvhe/sys_regs.c +++ b/arch/arm64/kvm/hyp/nvhe/sys_regs.c @@ -474,7 +474,7 @@ bool kvm_handle_pvm_sysreg(struct kvm_vcpu *vcpu, u64 *exit_code) return true; } -/** +/* * Handler for protected VM restricted exceptions. * * Inject an undefined exception into the guest and return true to indicate that diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c index 5a2cb5d9bc4b..fbb26b93c347 100644 --- a/arch/arm64/kvm/hyp/vhe/switch.c +++ b/arch/arm64/kvm/hyp/vhe/switch.c @@ -112,6 +112,10 @@ static const exit_handler_fn *kvm_get_exit_handler_array(struct kvm_vcpu *vcpu) return hyp_exit_handlers; } +static void early_exit_filter(struct kvm_vcpu *vcpu, u64 *exit_code) +{ +} + /* Switch to the guest for VHE systems running in EL2 */ static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu) { diff --git a/arch/hexagon/include/asm/timer-regs.h b/arch/hexagon/include/asm/timer-regs.h deleted file mode 100644 index ee6c61423a05..000000000000 --- a/arch/hexagon/include/asm/timer-regs.h +++ /dev/null @@ -1,26 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Timer support for Hexagon - * - * Copyright (c) 2010-2011, The Linux Foundation. All rights reserved. - */ - -#ifndef _ASM_TIMER_REGS_H -#define _ASM_TIMER_REGS_H - -/* This stuff should go into a platform specific file */ -#define TCX0_CLK_RATE 19200 -#define TIMER_ENABLE 0 -#define TIMER_CLR_ON_MATCH 1 - -/* - * 8x50 HDD Specs 5-8. Simulator co-sim not fixed until - * release 1.1, and then it's "adjustable" and probably not defaulted. - */ -#define RTOS_TIMER_INT 3 -#ifdef CONFIG_HEXAGON_COMET -#define RTOS_TIMER_REGS_ADDR 0xAB000000UL -#endif -#define SLEEP_CLK_RATE 32000 - -#endif diff --git a/arch/hexagon/include/asm/timex.h b/arch/hexagon/include/asm/timex.h index 8d4ec76fceb4..dfe69e118b2b 100644 --- a/arch/hexagon/include/asm/timex.h +++ b/arch/hexagon/include/asm/timex.h @@ -7,11 +7,10 @@ #define _ASM_TIMEX_H #include <asm-generic/timex.h> -#include <asm/timer-regs.h> #include <asm/hexagon_vm.h> /* Using TCX0 as our clock. CLOCK_TICK_RATE scheduled to be removed. */ -#define CLOCK_TICK_RATE TCX0_CLK_RATE +#define CLOCK_TICK_RATE 19200 #define ARCH_HAS_READ_CURRENT_TIMER diff --git a/arch/hexagon/kernel/.gitignore b/arch/hexagon/kernel/.gitignore new file mode 100644 index 000000000000..c5f676c3c224 --- /dev/null +++ b/arch/hexagon/kernel/.gitignore @@ -0,0 +1 @@ +vmlinux.lds diff --git a/arch/hexagon/kernel/time.c b/arch/hexagon/kernel/time.c index feffe527ac92..febc95714d75 100644 --- a/arch/hexagon/kernel/time.c +++ b/arch/hexagon/kernel/time.c @@ -17,9 +17,10 @@ #include <linux/of_irq.h> #include <linux/module.h> -#include <asm/timer-regs.h> #include <asm/hexagon_vm.h> +#define TIMER_ENABLE BIT(0) + /* * For the clocksource we need: * pcycle frequency (600MHz) @@ -33,6 +34,13 @@ cycles_t pcycle_freq_mhz; cycles_t thread_freq_mhz; cycles_t sleep_clk_freq; +/* + * 8x50 HDD Specs 5-8. Simulator co-sim not fixed until + * release 1.1, and then it's "adjustable" and probably not defaulted. + */ +#define RTOS_TIMER_INT 3 +#define RTOS_TIMER_REGS_ADDR 0xAB000000UL + static struct resource rtos_timer_resources[] = { { .start = RTOS_TIMER_REGS_ADDR, @@ -80,7 +88,7 @@ static int set_next_event(unsigned long delta, struct clock_event_device *evt) iowrite32(0, &rtos_timer->clear); iowrite32(delta, &rtos_timer->match); - iowrite32(1 << TIMER_ENABLE, &rtos_timer->enable); + iowrite32(TIMER_ENABLE, &rtos_timer->enable); return 0; } diff --git a/arch/hexagon/lib/io.c b/arch/hexagon/lib/io.c index d35d69d6588c..55f75392857b 100644 --- a/arch/hexagon/lib/io.c +++ b/arch/hexagon/lib/io.c @@ -27,6 +27,7 @@ void __raw_readsw(const void __iomem *addr, void *data, int len) *dst++ = *src; } +EXPORT_SYMBOL(__raw_readsw); /* * __raw_writesw - read words a short at a time @@ -47,6 +48,7 @@ void __raw_writesw(void __iomem *addr, const void *data, int len) } +EXPORT_SYMBOL(__raw_writesw); /* Pretty sure len is pre-adjusted for the length of the access already */ void __raw_readsl(const void __iomem *addr, void *data, int len) @@ -62,6 +64,7 @@ void __raw_readsl(const void __iomem *addr, void *data, int len) } +EXPORT_SYMBOL(__raw_readsl); void __raw_writesl(void __iomem *addr, const void *data, int len) { @@ -76,3 +79,4 @@ void __raw_writesl(void __iomem *addr, const void *data, int len) } +EXPORT_SYMBOL(__raw_writesl); diff --git a/arch/ia64/kernel/syscalls/syscall.tbl b/arch/ia64/kernel/syscalls/syscall.tbl index 6fea1844fb95..707ae121f6d3 100644 --- a/arch/ia64/kernel/syscalls/syscall.tbl +++ b/arch/ia64/kernel/syscalls/syscall.tbl @@ -369,3 +369,4 @@ 446 common landlock_restrict_self sys_landlock_restrict_self # 447 reserved for memfd_secret 448 common process_mrelease sys_process_mrelease +449 common futex_waitv sys_futex_waitv diff --git a/arch/m68k/include/asm/cacheflush_mm.h b/arch/m68k/include/asm/cacheflush_mm.h index 8ab46625ddd3..1ac55e7b47f0 100644 --- a/arch/m68k/include/asm/cacheflush_mm.h +++ b/arch/m68k/include/asm/cacheflush_mm.h @@ -250,7 +250,6 @@ static inline void __flush_page_to_ram(void *vaddr) #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 #define flush_dcache_page(page) __flush_page_to_ram(page_address(page)) -void flush_dcache_folio(struct folio *folio); #define flush_dcache_mmap_lock(mapping) do { } while (0) #define flush_dcache_mmap_unlock(mapping) do { } while (0) #define flush_icache_page(vma, page) __flush_page_to_ram(page_address(page)) diff --git a/arch/m68k/kernel/syscalls/syscall.tbl b/arch/m68k/kernel/syscalls/syscall.tbl index 7976dff8f879..45bc32a41b90 100644 --- a/arch/m68k/kernel/syscalls/syscall.tbl +++ b/arch/m68k/kernel/syscalls/syscall.tbl @@ -448,3 +448,4 @@ 446 common landlock_restrict_self sys_landlock_restrict_self # 447 reserved for memfd_secret 448 common process_mrelease sys_process_mrelease +449 common futex_waitv sys_futex_waitv diff --git a/arch/m68k/kernel/traps.c b/arch/m68k/kernel/traps.c index 99058a6da956..34d6458340b0 100644 --- a/arch/m68k/kernel/traps.c +++ b/arch/m68k/kernel/traps.c @@ -1145,7 +1145,7 @@ asmlinkage void set_esp0(unsigned long ssp) */ asmlinkage void fpsp040_die(void) { - force_fatal_sig(SIGSEGV); + force_exit_sig(SIGSEGV); } #ifdef CONFIG_M68KFPU_EMU diff --git a/arch/microblaze/kernel/syscalls/syscall.tbl b/arch/microblaze/kernel/syscalls/syscall.tbl index 6b0e11362bd2..2204bde3ce4a 100644 --- a/arch/microblaze/kernel/syscalls/syscall.tbl +++ b/arch/microblaze/kernel/syscalls/syscall.tbl @@ -454,3 +454,4 @@ 446 common landlock_restrict_self sys_landlock_restrict_self # 447 reserved for memfd_secret 448 common process_mrelease sys_process_mrelease +449 common futex_waitv sys_futex_waitv diff --git a/arch/mips/Kbuild.platforms b/arch/mips/Kbuild.platforms index 2c57994b5217..30193bcf9caa 100644 --- a/arch/mips/Kbuild.platforms +++ b/arch/mips/Kbuild.platforms @@ -37,4 +37,4 @@ platform-$(CONFIG_MACH_TX49XX) += txx9/ platform-$(CONFIG_MACH_VR41XX) += vr41xx/ # include the platform specific files -include $(patsubst %, $(srctree)/arch/mips/%/Platform, $(platform-y)) +include $(patsubst %/, $(srctree)/arch/mips/%/Platform, $(platform-y)) diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 86510741d49d..0215dc1529e9 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -292,6 +292,8 @@ config BMIPS_GENERIC select USB_OHCI_BIG_ENDIAN_DESC if CPU_BIG_ENDIAN select USB_OHCI_BIG_ENDIAN_MMIO if CPU_BIG_ENDIAN select HARDIRQS_SW_RESEND + select HAVE_PCI + select PCI_DRIVERS_GENERIC help Build a generic DT-based kernel image that boots on select BCM33xx cable modem chips, BCM63xx DSL chips, and BCM7xxx set-top @@ -333,6 +335,9 @@ config BCM63XX select SYS_SUPPORTS_32BIT_KERNEL select SYS_SUPPORTS_BIG_ENDIAN select SYS_HAS_EARLY_PRINTK + select SYS_HAS_CPU_BMIPS32_3300 + select SYS_HAS_CPU_BMIPS4350 + select SYS_HAS_CPU_BMIPS4380 select SWAP_IO_SPACE select GPIOLIB select MIPS_L1_CACHE_SHIFT_4 @@ -3092,7 +3097,7 @@ config STACKTRACE_SUPPORT config PGTABLE_LEVELS int default 4 if PAGE_SIZE_4KB && MIPS_VA_BITS_48 - default 3 if 64BIT && !PAGE_SIZE_64KB + default 3 if 64BIT && (!PAGE_SIZE_64KB || MIPS_VA_BITS_48) default 2 config MIPS_AUTO_PFN_OFFSET diff --git a/arch/mips/Makefile b/arch/mips/Makefile index e036fc025ccc..ace7f033de07 100644 --- a/arch/mips/Makefile +++ b/arch/mips/Makefile @@ -253,7 +253,9 @@ endif # # Board-dependent options and extra files # +ifdef need-compiler include $(srctree)/arch/mips/Kbuild.platforms +endif ifdef CONFIG_PHYSICAL_START load-y = $(CONFIG_PHYSICAL_START) diff --git a/arch/mips/bcm63xx/clk.c b/arch/mips/bcm63xx/clk.c index 5a3e325275d0..1c91064cb448 100644 --- a/arch/mips/bcm63xx/clk.c +++ b/arch/mips/bcm63xx/clk.c @@ -381,6 +381,12 @@ void clk_disable(struct clk *clk) EXPORT_SYMBOL(clk_disable); +struct clk *clk_get_parent(struct clk *clk) +{ + return NULL; +} +EXPORT_SYMBOL(clk_get_parent); + unsigned long clk_get_rate(struct clk *clk) { if (!clk) diff --git a/arch/mips/boot/compressed/.gitignore b/arch/mips/boot/compressed/.gitignore deleted file mode 100644 index d358395614c9..000000000000 --- a/arch/mips/boot/compressed/.gitignore +++ /dev/null @@ -1,3 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0-only -ashldi3.c -bswapsi.c diff --git a/arch/mips/boot/compressed/Makefile b/arch/mips/boot/compressed/Makefile index 3548b3b45269..f27cf31b4140 100644 --- a/arch/mips/boot/compressed/Makefile +++ b/arch/mips/boot/compressed/Makefile @@ -50,19 +50,9 @@ vmlinuzobjs-$(CONFIG_MIPS_ALCHEMY) += $(obj)/uart-alchemy.o vmlinuzobjs-$(CONFIG_ATH79) += $(obj)/uart-ath79.o endif -extra-y += uart-ath79.c -$(obj)/uart-ath79.c: $(srctree)/arch/mips/ath79/early_printk.c - $(call cmd,shipped) - vmlinuzobjs-$(CONFIG_KERNEL_XZ) += $(obj)/ashldi3.o -extra-y += ashldi3.c -$(obj)/ashldi3.c: $(obj)/%.c: $(srctree)/lib/%.c FORCE - $(call if_changed,shipped) - -extra-y += bswapsi.c -$(obj)/bswapsi.c: $(obj)/%.c: $(srctree)/arch/mips/lib/%.c FORCE - $(call if_changed,shipped) +vmlinuzobjs-$(CONFIG_KERNEL_ZSTD) += $(obj)/bswapdi.o $(obj)/ashldi3.o targets := $(notdir $(vmlinuzobjs-y)) diff --git a/arch/mips/boot/compressed/ashldi3.c b/arch/mips/boot/compressed/ashldi3.c new file mode 100644 index 000000000000..f7bf6a7aae31 --- /dev/null +++ b/arch/mips/boot/compressed/ashldi3.c @@ -0,0 +1,2 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include "../../../../lib/ashldi3.c" diff --git a/arch/mips/boot/compressed/bswapdi.c b/arch/mips/boot/compressed/bswapdi.c new file mode 100644 index 000000000000..acb28aebb025 --- /dev/null +++ b/arch/mips/boot/compressed/bswapdi.c @@ -0,0 +1,2 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include "../../lib/bswapdi.c" diff --git a/arch/mips/boot/compressed/bswapsi.c b/arch/mips/boot/compressed/bswapsi.c new file mode 100644 index 000000000000..fdb9c6476904 --- /dev/null +++ b/arch/mips/boot/compressed/bswapsi.c @@ -0,0 +1,2 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include "../../lib/bswapsi.c" diff --git a/arch/mips/boot/compressed/uart-ath79.c b/arch/mips/boot/compressed/uart-ath79.c new file mode 100644 index 000000000000..d686820921be --- /dev/null +++ b/arch/mips/boot/compressed/uart-ath79.c @@ -0,0 +1,2 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include "../../ath79/early_printk.c" diff --git a/arch/mips/boot/dts/ingenic/jz4725b.dtsi b/arch/mips/boot/dts/ingenic/jz4725b.dtsi index a1f0b71c9223..0c6a5a4266f4 100644 --- a/arch/mips/boot/dts/ingenic/jz4725b.dtsi +++ b/arch/mips/boot/dts/ingenic/jz4725b.dtsi @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -#include <dt-bindings/clock/jz4725b-cgu.h> +#include <dt-bindings/clock/ingenic,jz4725b-cgu.h> #include <dt-bindings/clock/ingenic,tcu.h> / { diff --git a/arch/mips/boot/dts/ingenic/jz4740.dtsi b/arch/mips/boot/dts/ingenic/jz4740.dtsi index c1afdfdaa8a3..772542e1f266 100644 --- a/arch/mips/boot/dts/ingenic/jz4740.dtsi +++ b/arch/mips/boot/dts/ingenic/jz4740.dtsi @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -#include <dt-bindings/clock/jz4740-cgu.h> +#include <dt-bindings/clock/ingenic,jz4740-cgu.h> #include <dt-bindings/clock/ingenic,tcu.h> / { diff --git a/arch/mips/boot/dts/ingenic/jz4770.dtsi b/arch/mips/boot/dts/ingenic/jz4770.dtsi index 05c00b93088e..dfe74328ae5d 100644 --- a/arch/mips/boot/dts/ingenic/jz4770.dtsi +++ b/arch/mips/boot/dts/ingenic/jz4770.dtsi @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -#include <dt-bindings/clock/jz4770-cgu.h> +#include <dt-bindings/clock/ingenic,jz4770-cgu.h> #include <dt-bindings/clock/ingenic,tcu.h> / { diff --git a/arch/mips/boot/dts/ingenic/jz4780.dtsi b/arch/mips/boot/dts/ingenic/jz4780.dtsi index 28adc3d93975..b0a4e2e019c3 100644 --- a/arch/mips/boot/dts/ingenic/jz4780.dtsi +++ b/arch/mips/boot/dts/ingenic/jz4780.dtsi @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -#include <dt-bindings/clock/jz4780-cgu.h> +#include <dt-bindings/clock/ingenic,jz4780-cgu.h> #include <dt-bindings/clock/ingenic,tcu.h> #include <dt-bindings/dma/jz4780-dma.h> diff --git a/arch/mips/boot/dts/ingenic/x1000.dtsi b/arch/mips/boot/dts/ingenic/x1000.dtsi index dec7909d4baa..8bd27edef216 100644 --- a/arch/mips/boot/dts/ingenic/x1000.dtsi +++ b/arch/mips/boot/dts/ingenic/x1000.dtsi @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <dt-bindings/clock/ingenic,tcu.h> -#include <dt-bindings/clock/x1000-cgu.h> +#include <dt-bindings/clock/ingenic,x1000-cgu.h> #include <dt-bindings/dma/x1000-dma.h> / { diff --git a/arch/mips/boot/dts/ingenic/x1830.dtsi b/arch/mips/boot/dts/ingenic/x1830.dtsi index 215257f8bb1a..2595df8671c7 100644 --- a/arch/mips/boot/dts/ingenic/x1830.dtsi +++ b/arch/mips/boot/dts/ingenic/x1830.dtsi @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <dt-bindings/clock/ingenic,tcu.h> -#include <dt-bindings/clock/x1830-cgu.h> +#include <dt-bindings/clock/ingenic,x1830-cgu.h> #include <dt-bindings/dma/x1830-dma.h> / { diff --git a/arch/mips/configs/bmips_stb_defconfig b/arch/mips/configs/bmips_stb_defconfig index 625bd2d7e685..5956fb95c19f 100644 --- a/arch/mips/configs/bmips_stb_defconfig +++ b/arch/mips/configs/bmips_stb_defconfig @@ -1,6 +1,7 @@ # CONFIG_LOCALVERSION_AUTO is not set # CONFIG_SWAP is not set CONFIG_NO_HZ=y +CONFIG_HZ=1000 CONFIG_BLK_DEV_INITRD=y CONFIG_EXPERT=y # CONFIG_VM_EVENT_COUNTERS is not set @@ -8,17 +9,34 @@ CONFIG_EXPERT=y CONFIG_BMIPS_GENERIC=y CONFIG_CPU_LITTLE_ENDIAN=y CONFIG_HIGHMEM=y +CONFIG_HIGH_RES_TIMERS=y CONFIG_SMP=y CONFIG_NR_CPUS=4 +CONFIG_CC_STACKPROTECTOR_STRONG=y # CONFIG_SECCOMP is not set CONFIG_MIPS_O32_FP64_SUPPORT=y +# CONFIG_RD_GZIP is not set +# CONFIG_RD_BZIP2 is not set +# CONFIG_RD_LZMA is not set +CONFIG_RD_XZ=y +# CONFIG_RD_LZO is not set +# CONFIG_RD_LZ4 is not set +# CONFIG_IOSCHED_DEADLINE is not set +# CONFIG_IOSCHED_CFQ is not set +CONFIG_PCI=y +CONFIG_PCI_MSI=y +CONFIG_PCIEASPM_POWERSAVE=y +CONFIG_PCIEPORTBUS=y +CONFIG_PCIE_BRCMSTB=y CONFIG_CPU_FREQ=y CONFIG_CPU_FREQ_STAT=y +CONFIG_CPU_FREQ_STAT_DETAILS=y +CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE=y +CONFIG_CPU_FREQ_GOV_PERFORMANCE=y CONFIG_CPU_FREQ_GOV_POWERSAVE=y CONFIG_CPU_FREQ_GOV_USERSPACE=y CONFIG_CPU_FREQ_GOV_ONDEMAND=y CONFIG_CPU_FREQ_GOV_CONSERVATIVE=y -CONFIG_CPU_FREQ_GOV_SCHEDUTIL=y CONFIG_BMIPS_CPUFREQ=y # CONFIG_BLK_DEV_BSG is not set CONFIG_NET=y @@ -32,32 +50,99 @@ CONFIG_INET=y # CONFIG_INET_DIAG is not set CONFIG_CFG80211=y CONFIG_NL80211_TESTMODE=y +CONFIG_WIRELESS=y CONFIG_MAC80211=y +CONFIG_NL80211=y CONFIG_DEVTMPFS=y CONFIG_DEVTMPFS_MOUNT=y # CONFIG_STANDALONE is not set # CONFIG_PREVENT_FIRMWARE_BUILD is not set +CONFIG_BRCMSTB_GISB_ARB=y +CONFIG_MODULES=y +CONFIG_MODULE_FORCE_LOAD=y +CONFIG_MODULE_UNLOAD=y +CONFIG_MODVERSIONS=y +CONFIG_IP_MULTICAST=y +CONFIG_IP_PNP=y +CONFIG_IP_PNP_DHCP=y +CONFIG_IP_PNP_BOOTP=y +CONFIG_IP_PNP_RARP=y +CONFIG_IP_MROUTE=y +CONFIG_IP_PIMSM_V1=y +CONFIG_IP_PIMSM_V2=y +# CONFIG_INET_XFRM_MODE_TRANSPORT is not set +# CONFIG_INET_XFRM_MODE_TUNNEL is not set +# CONFIG_INET_XFRM_MODE_BEET is not set +# CONFIG_INET_LRO is not set +CONFIG_INET_UDP_DIAG=y +CONFIG_TCP_CONG_ADVANCED=y +CONFIG_TCP_CONG_BIC=y +# CONFIG_TCP_CONG_WESTWOOD is not set +# CONFIG_TCP_CONG_HTCP is not set +# CONFIG_IPV6 is not set +CONFIG_IP_NF_IPTABLES=y +CONFIG_IP_NF_FILTER=y +CONFIG_NETFILTER=y +CONFIG_NETFILTER_XTABLES=y +CONFIG_BRIDGE=y +CONFIG_BRIDGE_NETFILTER=m +CONFIG_BRIDGE_NF_EBTABLES=m +CONFIG_BRIDGE_EBT_BROUTE=m +CONFIG_NET_DSA=y +CONFIG_NET_SWITCHDEV=y +CONFIG_DMA_CMA=y +CONFIG_CMA_ALIGNMENT=12 +CONFIG_SPI=y +CONFIG_SPI_BRCMSTB=y CONFIG_MTD=y +CONFIG_MTD_CMDLINE_PARTS=y +CONFIG_MTD_BLOCK=y CONFIG_MTD_CFI=y +CONFIG_MTD_JEDECPROBE=y CONFIG_MTD_CFI_INTELEXT=y CONFIG_MTD_CFI_AMDSTD=y -CONFIG_MTD_PHYSMAP=y +CONFIG_MTD_CFI_STAA=y +CONFIG_MTD_ROM=y +CONFIG_MTD_ABSENT=y +CONFIG_MTD_PHYSMAP_OF=y +CONFIG_MTD_M25P80=y +CONFIG_MTD_NAND=y +CONFIG_MTD_NAND_BRCMNAND=y +CONFIG_MTD_SPI_NOR=y +# CONFIG_MTD_SPI_NOR_USE_4K_SECTORS is not set +CONFIG_MTD_UBI=y +CONFIG_MTD_UBI_GLUEBI=y +CONFIG_PROC_DEVICETREE=y +CONFIG_BLK_DEV_LOOP=y +CONFIG_BLK_DEV_RAM=y +CONFIG_BLK_DEV_RAM_SIZE=8192 # CONFIG_BLK_DEV is not set CONFIG_SCSI=y CONFIG_BLK_DEV_SD=y +CONFIG_CHR_DEV_SG=y +CONFIG_SCSI_MULTI_LUN=y # CONFIG_SCSI_LOWLEVEL is not set CONFIG_NETDEVICES=y +CONFIG_VLAN_8021Q=y +CONFIG_MACVLAN=y CONFIG_BCMGENET=y CONFIG_USB_USBNET=y -# CONFIG_INPUT is not set +CONFIG_INPUT_EVDEV=y +# CONFIG_INPUT_KEYBOARD is not set +# CONFIG_INPUT_MOUSE is not set +CONFIG_INPUT_MISC=y +CONFIG_INPUT_UINPUT=y # CONFIG_SERIO is not set -# CONFIG_VT is not set +CONFIG_VT=y +CONFIG_VT_HW_CONSOLE_BINDING=y +# CONFIG_DEVKMEM is not set CONFIG_SERIAL_8250=y # CONFIG_SERIAL_8250_DEPRECATED_OPTIONS is not set CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_OF_PLATFORM=y # CONFIG_HW_RANDOM is not set CONFIG_POWER_RESET=y +CONFIG_POWER_RESET_BRCMSTB=y CONFIG_POWER_RESET_SYSCON=y CONFIG_POWER_SUPPLY=y # CONFIG_HWMON is not set @@ -69,22 +154,76 @@ CONFIG_USB_OHCI_HCD=y CONFIG_USB_OHCI_HCD_PLATFORM=y CONFIG_USB_STORAGE=y CONFIG_SOC_BRCMSTB=y +CONFIG_MMC=y +CONFIG_MMC_BLOCK_MINORS=16 +CONFIG_MMC_SDHCI=y +CONFIG_MMC_SDHCI_PLTFM=y CONFIG_EXT4_FS=y CONFIG_EXT4_FS_POSIX_ACL=y CONFIG_EXT4_FS_SECURITY=y # CONFIG_DNOTIFY is not set +CONFIG_PROC_KCORE=y +CONFIG_CIFS=y +CONFIG_JBD2_DEBUG=y CONFIG_FUSE_FS=y +CONFIG_FHANDLE=y +CONFIG_CGROUPS=y +CONFIG_CUSE=y +CONFIG_ISO9660_FS=y +CONFIG_JOLIET=y +CONFIG_ZISOFS=y +CONFIG_UDF_FS=y +CONFIG_MSDOS_FS=y CONFIG_VFAT_FS=y -CONFIG_PROC_KCORE=y CONFIG_TMPFS=y +CONFIG_JFFS2_FS=y +CONFIG_UBIFS_FS=y +CONFIG_SQUASHFS=y +CONFIG_SQUASHFS_LZO=y +CONFIG_SQUASHFS_XZ=y CONFIG_NFS_FS=y -CONFIG_CIFS=y +CONFIG_NFS_V3_ACL=y +CONFIG_NFS_V4=y +CONFIG_NFS_V4_1=y +CONFIG_NFS_V4_2=y +CONFIG_ROOT_NFS=y CONFIG_NLS_CODEPAGE_437=y -CONFIG_NLS_ASCII=y CONFIG_NLS_ISO8859_1=y -# CONFIG_CRYPTO_HW is not set CONFIG_PRINTK_TIME=y +CONFIG_DYNAMIC_DEBUG=y +# CONFIG_DEBUG_INFO is not set +# CONFIG_DEBUG_INFO_REDUCED is not set CONFIG_DEBUG_FS=y CONFIG_MAGIC_SYSRQ=y +CONFIG_LOCKUP_DETECTOR=y +CONFIG_DEBUG_USER=y CONFIG_CMDLINE_BOOL=y CONFIG_CMDLINE="earlycon" +# CONFIG_MIPS_CMDLINE_FROM_DTB is not set +CONFIG_MIPS_CMDLINE_DTB_EXTEND=y +# CONFIG_MIPS_CMDLINE_FROM_BOOTLOADER is not set +# CONFIG_CRYPTO_HW is not set +CONFIG_DT_BCM974XX=y +CONFIG_FW_CFE=y +CONFIG_ATA=y +CONFIG_SATA_AHCI_PLATFORM=y +CONFIG_AHCI_BRCMSTB=y +CONFIG_GENERIC_PHY=y +CONFIG_GPIOLIB=y +CONFIG_GPIO_SYSFS=y +CONFIG_PHY_BRCM_USB=y +CONFIG_PHY_BRCM_SATA=y +CONFIG_PM_RUNTIME=y +CONFIG_PM_DEBUG=y +CONFIG_SYSVIPC=y +CONFIG_FUNCTION_GRAPH_TRACER=y +CONFIG_DYNAMIC_FTRACE=y +CONFIG_FUNCTION_TRACER=y +CONFIG_FUNCTION_PROFILER=y +CONFIG_IRQSOFF_TRACER=y +CONFIG_SCHED_TRACER=y +CONFIG_BLK_DEV_IO_TRACE=y +CONFIG_FTRACE_SYSCALLS=y +CONFIG_TRACER_SNAPSHOT=y +CONFIG_TRACER_SNAPSHOT_PER_CPU_SWAP=y +CONFIG_STACK_TRACER=y diff --git a/arch/mips/dec/setup.c b/arch/mips/dec/setup.c index eaad0ed4b523..a8a30bb1dee8 100644 --- a/arch/mips/dec/setup.c +++ b/arch/mips/dec/setup.c @@ -117,21 +117,21 @@ static void __init dec_be_init(void) { switch (mips_machtype) { case MACH_DS23100: /* DS2100/DS3100 Pmin/Pmax */ - board_be_handler = dec_kn01_be_handler; + mips_set_be_handler(dec_kn01_be_handler); busirq_handler = dec_kn01_be_interrupt; busirq_flags |= IRQF_SHARED; dec_kn01_be_init(); break; case MACH_DS5000_1XX: /* DS5000/1xx 3min */ case MACH_DS5000_XX: /* DS5000/xx Maxine */ - board_be_handler = dec_kn02xa_be_handler; + mips_set_be_handler(dec_kn02xa_be_handler); busirq_handler = dec_kn02xa_be_interrupt; dec_kn02xa_be_init(); break; case MACH_DS5000_200: /* DS5000/200 3max */ case MACH_DS5000_2X0: /* DS5000/240 3max+ */ case MACH_DS5900: /* DS5900 bigmax */ - board_be_handler = dec_ecc_be_handler; + mips_set_be_handler(dec_ecc_be_handler); busirq_handler = dec_ecc_be_interrupt; dec_ecc_be_init(); break; diff --git a/arch/mips/generic/yamon-dt.c b/arch/mips/generic/yamon-dt.c index a3aa22c77cad..a07a5edbcda7 100644 --- a/arch/mips/generic/yamon-dt.c +++ b/arch/mips/generic/yamon-dt.c @@ -75,7 +75,7 @@ static unsigned int __init gen_fdt_mem_array( __init int yamon_dt_append_memory(void *fdt, const struct yamon_mem_region *regions) { - unsigned long phys_memsize, memsize; + unsigned long phys_memsize = 0, memsize; __be32 mem_array[2 * MAX_MEM_ARRAY_ENTRIES]; unsigned int mem_entries; int i, err, mem_off; diff --git a/arch/mips/include/asm/cacheflush.h b/arch/mips/include/asm/cacheflush.h index f207388541d5..b3dc9c589442 100644 --- a/arch/mips/include/asm/cacheflush.h +++ b/arch/mips/include/asm/cacheflush.h @@ -61,8 +61,6 @@ static inline void flush_dcache_page(struct page *page) SetPageDcacheDirty(page); } -void flush_dcache_folio(struct folio *folio); - #define flush_dcache_mmap_lock(mapping) do { } while (0) #define flush_dcache_mmap_unlock(mapping) do { } while (0) diff --git a/arch/mips/include/asm/traps.h b/arch/mips/include/asm/traps.h index b710e76c9c65..15cde638b407 100644 --- a/arch/mips/include/asm/traps.h +++ b/arch/mips/include/asm/traps.h @@ -15,7 +15,7 @@ #define MIPS_BE_FATAL 2 /* treat as an unrecoverable error */ extern void (*board_be_init)(void); -extern int (*board_be_handler)(struct pt_regs *regs, int is_fixup); +void mips_set_be_handler(int (*handler)(struct pt_regs *reg, int is_fixup)); extern void (*board_nmi_handler_setup)(void); extern void (*board_ejtag_handler_setup)(void); diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c index ac0e2cfc6d57..24a529c6c4be 100644 --- a/arch/mips/kernel/cpu-probe.c +++ b/arch/mips/kernel/cpu-probe.c @@ -1734,8 +1734,6 @@ static inline void decode_cpucfg(struct cpuinfo_mips *c) static inline void cpu_probe_loongson(struct cpuinfo_mips *c, unsigned int cpu) { - decode_configs(c); - /* All Loongson processors covered here define ExcCode 16 as GSExc. */ c->options |= MIPS_CPU_GSEXCEX; @@ -1796,6 +1794,8 @@ static inline void cpu_probe_loongson(struct cpuinfo_mips *c, unsigned int cpu) panic("Unknown Loongson Processor ID!"); break; } + + decode_configs(c); } #else static inline void cpu_probe_loongson(struct cpuinfo_mips *c, unsigned int cpu) { } diff --git a/arch/mips/kernel/proc.c b/arch/mips/kernel/proc.c index 376a6e2676e9..9f47a889b047 100644 --- a/arch/mips/kernel/proc.c +++ b/arch/mips/kernel/proc.c @@ -185,7 +185,7 @@ static int show_cpuinfo(struct seq_file *m, void *v) seq_puts(m, " tx39_cache"); if (cpu_has_octeon_cache) seq_puts(m, " octeon_cache"); - if (cpu_has_fpu) + if (raw_cpu_has_fpu) seq_puts(m, " fpu"); if (cpu_has_32fpr) seq_puts(m, " 32fpr"); diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl index 70e32de2bcaa..72d02d363f36 100644 --- a/arch/mips/kernel/syscalls/syscall_n32.tbl +++ b/arch/mips/kernel/syscalls/syscall_n32.tbl @@ -387,3 +387,4 @@ 446 n32 landlock_restrict_self sys_landlock_restrict_self # 447 reserved for memfd_secret 448 n32 process_mrelease sys_process_mrelease +449 n32 futex_waitv sys_futex_waitv diff --git a/arch/mips/kernel/syscalls/syscall_n64.tbl b/arch/mips/kernel/syscalls/syscall_n64.tbl index 1ca7bc337932..e2c481fcede6 100644 --- a/arch/mips/kernel/syscalls/syscall_n64.tbl +++ b/arch/mips/kernel/syscalls/syscall_n64.tbl @@ -363,3 +363,4 @@ 446 n64 landlock_restrict_self sys_landlock_restrict_self # 447 reserved for memfd_secret 448 n64 process_mrelease sys_process_mrelease +449 n64 futex_waitv sys_futex_waitv diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl index a61c35edaa74..3714c97b2643 100644 --- a/arch/mips/kernel/syscalls/syscall_o32.tbl +++ b/arch/mips/kernel/syscalls/syscall_o32.tbl @@ -436,3 +436,4 @@ 446 o32 landlock_restrict_self sys_landlock_restrict_self # 447 reserved for memfd_secret 448 o32 process_mrelease sys_process_mrelease +449 o32 futex_waitv sys_futex_waitv diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c index 6f07362de5ce..d26b0fb8ea06 100644 --- a/arch/mips/kernel/traps.c +++ b/arch/mips/kernel/traps.c @@ -103,13 +103,19 @@ extern asmlinkage void handle_reserved(void); extern void tlb_do_page_fault_0(void); void (*board_be_init)(void); -int (*board_be_handler)(struct pt_regs *regs, int is_fixup); +static int (*board_be_handler)(struct pt_regs *regs, int is_fixup); void (*board_nmi_handler_setup)(void); void (*board_ejtag_handler_setup)(void); void (*board_bind_eic_interrupt)(int irq, int regset); void (*board_ebase_setup)(void); void(*board_cache_error_setup)(void); +void mips_set_be_handler(int (*handler)(struct pt_regs *regs, int is_fixup)) +{ + board_be_handler = handler; +} +EXPORT_SYMBOL_GPL(mips_set_be_handler); + static void show_raw_backtrace(unsigned long reg29, const char *loglvl, bool user) { diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c index 562aa878b266..aa20d074d388 100644 --- a/arch/mips/kvm/mips.c +++ b/arch/mips/kvm/mips.c @@ -1067,7 +1067,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) r = 1; break; case KVM_CAP_NR_VCPUS: - r = num_online_cpus(); + r = min_t(unsigned int, num_online_cpus(), KVM_MAX_VCPUS); break; case KVM_CAP_MAX_VCPUS: r = KVM_MAX_VCPUS; diff --git a/arch/mips/lantiq/clk.c b/arch/mips/lantiq/clk.c index dd819e31fcbb..4916cccf378f 100644 --- a/arch/mips/lantiq/clk.c +++ b/arch/mips/lantiq/clk.c @@ -158,6 +158,12 @@ void clk_deactivate(struct clk *clk) } EXPORT_SYMBOL(clk_deactivate); +struct clk *clk_get_parent(struct clk *clk) +{ + return NULL; +} +EXPORT_SYMBOL(clk_get_parent); + static inline u32 get_counter_resolution(void) { u32 res; diff --git a/arch/mips/sgi-ip22/ip22-berr.c b/arch/mips/sgi-ip22/ip22-berr.c index dc0110a607a5..afe8a61078e4 100644 --- a/arch/mips/sgi-ip22/ip22-berr.c +++ b/arch/mips/sgi-ip22/ip22-berr.c @@ -112,5 +112,5 @@ static int ip22_be_handler(struct pt_regs *regs, int is_fixup) void __init ip22_be_init(void) { - board_be_handler = ip22_be_handler; + mips_set_be_handler(ip22_be_handler); } diff --git a/arch/mips/sgi-ip22/ip28-berr.c b/arch/mips/sgi-ip22/ip28-berr.c index c61362d9ea95..16ca470deb80 100644 --- a/arch/mips/sgi-ip22/ip28-berr.c +++ b/arch/mips/sgi-ip22/ip28-berr.c @@ -468,7 +468,7 @@ static int ip28_be_handler(struct pt_regs *regs, int is_fixup) void __init ip22_be_init(void) { - board_be_handler = ip28_be_handler; + mips_set_be_handler(ip28_be_handler); } int ip28_show_be_info(struct seq_file *m) diff --git a/arch/mips/sgi-ip27/ip27-berr.c b/arch/mips/sgi-ip27/ip27-berr.c index 5a38ae6bdfa9..923a63a51cda 100644 --- a/arch/mips/sgi-ip27/ip27-berr.c +++ b/arch/mips/sgi-ip27/ip27-berr.c @@ -85,7 +85,7 @@ void __init ip27_be_init(void) int cpu = LOCAL_HUB_L(PI_CPU_NUM); int cpuoff = cpu << 8; - board_be_handler = ip27_be_handler; + mips_set_be_handler(ip27_be_handler); LOCAL_HUB_S(PI_ERR_INT_PEND, cpu ? PI_ERR_CLEAR_ALL_B : PI_ERR_CLEAR_ALL_A); diff --git a/arch/mips/sgi-ip32/ip32-berr.c b/arch/mips/sgi-ip32/ip32-berr.c index c860f95ab7ed..478b63b4c808 100644 --- a/arch/mips/sgi-ip32/ip32-berr.c +++ b/arch/mips/sgi-ip32/ip32-berr.c @@ -34,5 +34,5 @@ static int ip32_be_handler(struct pt_regs *regs, int is_fixup) void __init ip32_be_init(void) { - board_be_handler = ip32_be_handler; + mips_set_be_handler(ip32_be_handler); } diff --git a/arch/mips/sibyte/swarm/setup.c b/arch/mips/sibyte/swarm/setup.c index f07b15dd1c1a..72a31eeeebba 100644 --- a/arch/mips/sibyte/swarm/setup.c +++ b/arch/mips/sibyte/swarm/setup.c @@ -122,7 +122,7 @@ void __init plat_mem_setup(void) #error invalid SiByte board configuration #endif - board_be_handler = swarm_be_handler; + mips_set_be_handler(swarm_be_handler); if (xicor_probe()) swarm_rtc_type = RTC_XICOR; diff --git a/arch/mips/txx9/generic/setup_tx4927.c b/arch/mips/txx9/generic/setup_tx4927.c index 46e9c4101386..63f9725b2eb0 100644 --- a/arch/mips/txx9/generic/setup_tx4927.c +++ b/arch/mips/txx9/generic/setup_tx4927.c @@ -80,7 +80,7 @@ static int tx4927_be_handler(struct pt_regs *regs, int is_fixup) } static void __init tx4927_be_init(void) { - board_be_handler = tx4927_be_handler; + mips_set_be_handler(tx4927_be_handler); } static struct resource tx4927_sdram_resource[4]; diff --git a/arch/mips/txx9/generic/setup_tx4938.c b/arch/mips/txx9/generic/setup_tx4938.c index 17395d5d15ca..ba646548c5f6 100644 --- a/arch/mips/txx9/generic/setup_tx4938.c +++ b/arch/mips/txx9/generic/setup_tx4938.c @@ -82,7 +82,7 @@ static int tx4938_be_handler(struct pt_regs *regs, int is_fixup) } static void __init tx4938_be_init(void) { - board_be_handler = tx4938_be_handler; + mips_set_be_handler(tx4938_be_handler); } static struct resource tx4938_sdram_resource[4]; diff --git a/arch/mips/txx9/generic/setup_tx4939.c b/arch/mips/txx9/generic/setup_tx4939.c index bf8a3cdababf..f5f59b7401a3 100644 --- a/arch/mips/txx9/generic/setup_tx4939.c +++ b/arch/mips/txx9/generic/setup_tx4939.c @@ -86,7 +86,7 @@ static int tx4939_be_handler(struct pt_regs *regs, int is_fixup) } static void __init tx4939_be_init(void) { - board_be_handler = tx4939_be_handler; + mips_set_be_handler(tx4939_be_handler); } static struct resource tx4939_sdram_resource[4]; diff --git a/arch/mips/vdso/Makefile b/arch/mips/vdso/Makefile index 1b2ea34c3d3b..d65f55f67e19 100644 --- a/arch/mips/vdso/Makefile +++ b/arch/mips/vdso/Makefile @@ -57,7 +57,7 @@ endif # VDSO linker flags. ldflags-y := -Bsymbolic --no-undefined -soname=linux-vdso.so.1 \ - $(filter -E%,$(KBUILD_CFLAGS)) -nostdlib -shared \ + $(filter -E%,$(KBUILD_CFLAGS)) -shared \ -G 0 --eh-frame-hdr --hash-style=sysv --build-id=sha1 -T CFLAGS_REMOVE_vdso.o = $(CC_FLAGS_FTRACE) diff --git a/arch/nds32/include/asm/cacheflush.h b/arch/nds32/include/asm/cacheflush.h index 3fc0bb7d6487..c2a222ebfa2a 100644 --- a/arch/nds32/include/asm/cacheflush.h +++ b/arch/nds32/include/asm/cacheflush.h @@ -27,7 +27,6 @@ void flush_cache_vunmap(unsigned long start, unsigned long end); #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 void flush_dcache_page(struct page *page); -void flush_dcache_folio(struct folio *folio); void copy_to_user_page(struct vm_area_struct *vma, struct page *page, unsigned long vaddr, void *dst, void *src, int len); void copy_from_user_page(struct vm_area_struct *vma, struct page *page, diff --git a/arch/nios2/include/asm/cacheflush.h b/arch/nios2/include/asm/cacheflush.h index 1999561b22aa..d0b71dd71287 100644 --- a/arch/nios2/include/asm/cacheflush.h +++ b/arch/nios2/include/asm/cacheflush.h @@ -29,7 +29,6 @@ extern void flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, unsigned long pfn); #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 void flush_dcache_page(struct page *page); -void flush_dcache_folio(struct folio *folio); extern void flush_icache_range(unsigned long start, unsigned long end); extern void flush_icache_page(struct vm_area_struct *vma, struct page *page); diff --git a/arch/parisc/configs/generic-32bit_defconfig b/arch/parisc/configs/generic-32bit_defconfig index d6fd8fa7ed8c..53061cb2cf7f 100644 --- a/arch/parisc/configs/generic-32bit_defconfig +++ b/arch/parisc/configs/generic-32bit_defconfig @@ -231,6 +231,7 @@ CONFIG_CRYPTO_DEFLATE=y CONFIG_CRC_CCITT=m CONFIG_CRC_T10DIF=y CONFIG_FONTS=y +CONFIG_PRINTK_TIME=y CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_FS=y CONFIG_DEBUG_MEMORY_INIT=y diff --git a/arch/parisc/include/asm/assembly.h b/arch/parisc/include/asm/assembly.h index 7085df079702..6d13ae236fcb 100644 --- a/arch/parisc/include/asm/assembly.h +++ b/arch/parisc/include/asm/assembly.h @@ -3,38 +3,19 @@ * Copyright (C) 1999 Hewlett-Packard (Frank Rowand) * Copyright (C) 1999 Philipp Rumpf <prumpf@tux.org> * Copyright (C) 1999 SuSE GmbH + * Copyright (C) 2021 Helge Deller <deller@gmx.de> */ #ifndef _PARISC_ASSEMBLY_H #define _PARISC_ASSEMBLY_H -#define CALLEE_FLOAT_FRAME_SIZE 80 - #ifdef CONFIG_64BIT -#define LDREG ldd -#define STREG std -#define LDREGX ldd,s -#define LDREGM ldd,mb -#define STREGM std,ma -#define SHRREG shrd -#define SHLREG shld -#define ANDCM andcm,* -#define COND(x) * ## x #define RP_OFFSET 16 #define FRAME_SIZE 128 #define CALLEE_REG_FRAME_SIZE 144 #define REG_SZ 8 #define ASM_ULONG_INSN .dword #else /* CONFIG_64BIT */ -#define LDREG ldw -#define STREG stw -#define LDREGX ldwx,s -#define LDREGM ldwm -#define STREGM stwm -#define SHRREG shr -#define SHLREG shlw -#define ANDCM andcm -#define COND(x) x #define RP_OFFSET 20 #define FRAME_SIZE 64 #define CALLEE_REG_FRAME_SIZE 128 @@ -45,6 +26,7 @@ /* Frame alignment for 32- and 64-bit */ #define FRAME_ALIGN 64 +#define CALLEE_FLOAT_FRAME_SIZE 80 #define CALLEE_SAVE_FRAME_SIZE (CALLEE_REG_FRAME_SIZE + CALLEE_FLOAT_FRAME_SIZE) #ifdef CONFIG_PA20 @@ -68,6 +50,28 @@ #ifdef __ASSEMBLY__ #ifdef CONFIG_64BIT +#define LDREG ldd +#define STREG std +#define LDREGX ldd,s +#define LDREGM ldd,mb +#define STREGM std,ma +#define SHRREG shrd +#define SHLREG shld +#define ANDCM andcm,* +#define COND(x) * ## x +#else /* CONFIG_64BIT */ +#define LDREG ldw +#define STREG stw +#define LDREGX ldwx,s +#define LDREGM ldwm +#define STREGM stwm +#define SHRREG shr +#define SHLREG shlw +#define ANDCM andcm +#define COND(x) x +#endif + +#ifdef CONFIG_64BIT /* the 64-bit pa gnu assembler unfortunately defaults to .level 1.1 or 2.0 so * work around that for now... */ .level 2.0w @@ -143,6 +147,17 @@ extrd,u \r, 63-(\sa), 64-(\sa), \t .endm + /* Extract unsigned for 32- and 64-bit + * The extru instruction leaves the most significant 32 bits of the + * target register in an undefined state on PA 2.0 systems. */ + .macro extru_safe r, p, len, t +#ifdef CONFIG_64BIT + extrd,u \r, 32+(\p), \len, \t +#else + extru \r, \p, \len, \t +#endif + .endm + /* load 32-bit 'value' into 'reg' compensating for the ldil * sign-extension when running in wide mode. * WARNING!! neither 'value' nor 'reg' can be expressions diff --git a/arch/parisc/include/asm/cacheflush.h b/arch/parisc/include/asm/cacheflush.h index da0cd4b3a28f..859b8a34adcf 100644 --- a/arch/parisc/include/asm/cacheflush.h +++ b/arch/parisc/include/asm/cacheflush.h @@ -50,7 +50,6 @@ void invalidate_kernel_vmap_range(void *vaddr, int size); #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 void flush_dcache_page(struct page *page); -void flush_dcache_folio(struct folio *folio); #define flush_dcache_mmap_lock(mapping) xa_lock_irq(&mapping->i_pages) #define flush_dcache_mmap_unlock(mapping) xa_unlock_irq(&mapping->i_pages) diff --git a/arch/parisc/include/asm/jump_label.h b/arch/parisc/include/asm/jump_label.h index 7efb1aa2f7f8..af2a598bc0f8 100644 --- a/arch/parisc/include/asm/jump_label.h +++ b/arch/parisc/include/asm/jump_label.h @@ -5,6 +5,7 @@ #ifndef __ASSEMBLY__ #include <linux/types.h> +#include <linux/stringify.h> #include <asm/assembly.h> #define JUMP_LABEL_NOP_SIZE 4 diff --git a/arch/parisc/include/asm/pgtable.h b/arch/parisc/include/asm/pgtable.h index 7badd872f05a..3e7cf882639f 100644 --- a/arch/parisc/include/asm/pgtable.h +++ b/arch/parisc/include/asm/pgtable.h @@ -76,6 +76,8 @@ static inline void purge_tlb_entries(struct mm_struct *mm, unsigned long addr) purge_tlb_end(flags); } +extern void __update_cache(pte_t pte); + /* Certain architectures need to do special things when PTEs * within a page table are directly modified. Thus, the following * hook is made available. @@ -83,11 +85,14 @@ static inline void purge_tlb_entries(struct mm_struct *mm, unsigned long addr) #define set_pte(pteptr, pteval) \ do { \ *(pteptr) = (pteval); \ - barrier(); \ + mb(); \ } while(0) #define set_pte_at(mm, addr, pteptr, pteval) \ do { \ + if (pte_present(pteval) && \ + pte_user(pteval)) \ + __update_cache(pteval); \ *(pteptr) = (pteval); \ purge_tlb_entries(mm, addr); \ } while (0) @@ -303,6 +308,7 @@ extern unsigned long *empty_zero_page; #define pte_none(x) (pte_val(x) == 0) #define pte_present(x) (pte_val(x) & _PAGE_PRESENT) +#define pte_user(x) (pte_val(x) & _PAGE_USER) #define pte_clear(mm, addr, xp) set_pte_at(mm, addr, xp, __pte(0)) #define pmd_flag(x) (pmd_val(x) & PxD_FLAG_MASK) @@ -410,7 +416,7 @@ extern void paging_init (void); #define PG_dcache_dirty PG_arch_1 -extern void update_mmu_cache(struct vm_area_struct *, unsigned long, pte_t *); +#define update_mmu_cache(vms,addr,ptep) __update_cache(*ptep) /* Encode and de-code a swap entry */ diff --git a/arch/parisc/include/asm/rt_sigframe.h b/arch/parisc/include/asm/rt_sigframe.h index 4b9e3d707571..2b3010ade00e 100644 --- a/arch/parisc/include/asm/rt_sigframe.h +++ b/arch/parisc/include/asm/rt_sigframe.h @@ -2,7 +2,7 @@ #ifndef _ASM_PARISC_RT_SIGFRAME_H #define _ASM_PARISC_RT_SIGFRAME_H -#define SIGRETURN_TRAMP 3 +#define SIGRETURN_TRAMP 4 #define SIGRESTARTBLOCK_TRAMP 5 #define TRAMP_SIZE (SIGRETURN_TRAMP + SIGRESTARTBLOCK_TRAMP) diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c index c61827e4928a..94150b91c96f 100644 --- a/arch/parisc/kernel/cache.c +++ b/arch/parisc/kernel/cache.c @@ -83,9 +83,9 @@ EXPORT_SYMBOL(flush_cache_all_local); #define pfn_va(pfn) __va(PFN_PHYS(pfn)) void -update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) +__update_cache(pte_t pte) { - unsigned long pfn = pte_pfn(*ptep); + unsigned long pfn = pte_pfn(pte); struct page *page; /* We don't have pte special. As a result, we can be called with diff --git a/arch/parisc/kernel/entry.S b/arch/parisc/kernel/entry.S index 57944d6f9ebb..6e9cdb269862 100644 --- a/arch/parisc/kernel/entry.S +++ b/arch/parisc/kernel/entry.S @@ -366,17 +366,9 @@ */ .macro L2_ptep pmd,pte,index,va,fault #if CONFIG_PGTABLE_LEVELS == 3 - extru \va,31-ASM_PMD_SHIFT,ASM_BITS_PER_PMD,\index + extru_safe \va,31-ASM_PMD_SHIFT,ASM_BITS_PER_PMD,\index #else -# if defined(CONFIG_64BIT) - extrd,u \va,63-ASM_PGDIR_SHIFT,ASM_BITS_PER_PGD,\index - #else - # if PAGE_SIZE > 4096 - extru \va,31-ASM_PGDIR_SHIFT,32-ASM_PGDIR_SHIFT,\index - # else - extru \va,31-ASM_PGDIR_SHIFT,ASM_BITS_PER_PGD,\index - # endif -# endif + extru_safe \va,31-ASM_PGDIR_SHIFT,ASM_BITS_PER_PGD,\index #endif dep %r0,31,PAGE_SHIFT,\pmd /* clear offset */ #if CONFIG_PGTABLE_LEVELS < 3 @@ -386,7 +378,7 @@ bb,>=,n \pmd,_PxD_PRESENT_BIT,\fault dep %r0,31,PxD_FLAG_SHIFT,\pmd /* clear flags */ SHLREG \pmd,PxD_VALUE_SHIFT,\pmd - extru \va,31-PAGE_SHIFT,ASM_BITS_PER_PTE,\index + extru_safe \va,31-PAGE_SHIFT,ASM_BITS_PER_PTE,\index dep %r0,31,PAGE_SHIFT,\pmd /* clear offset */ shladd \index,BITS_PER_PTE_ENTRY,\pmd,\pmd /* pmd is now pte */ .endm @@ -1805,7 +1797,7 @@ syscall_restore: /* Are we being ptraced? */ LDREG TASK_TI_FLAGS(%r1),%r19 - ldi _TIF_SYSCALL_TRACE_MASK,%r2 + ldi _TIF_SINGLESTEP|_TIF_BLOCKSTEP,%r2 and,COND(=) %r19,%r2,%r0 b,n syscall_restore_rfi diff --git a/arch/parisc/kernel/signal.c b/arch/parisc/kernel/signal.c index bbfe23c40c01..46b1050640b8 100644 --- a/arch/parisc/kernel/signal.c +++ b/arch/parisc/kernel/signal.c @@ -288,21 +288,22 @@ setup_rt_frame(struct ksignal *ksig, sigset_t *set, struct pt_regs *regs, already in userspace. The first words of tramp are used to save the previous sigrestartblock trampoline that might be on the stack. We start the sigreturn trampoline at - SIGRESTARTBLOCK_TRAMP. */ + SIGRESTARTBLOCK_TRAMP+X. */ err |= __put_user(in_syscall ? INSN_LDI_R25_1 : INSN_LDI_R25_0, &frame->tramp[SIGRESTARTBLOCK_TRAMP+0]); - err |= __put_user(INSN_BLE_SR2_R0, + err |= __put_user(INSN_LDI_R20, &frame->tramp[SIGRESTARTBLOCK_TRAMP+1]); - err |= __put_user(INSN_LDI_R20, + err |= __put_user(INSN_BLE_SR2_R0, &frame->tramp[SIGRESTARTBLOCK_TRAMP+2]); + err |= __put_user(INSN_NOP, &frame->tramp[SIGRESTARTBLOCK_TRAMP+3]); - start = (unsigned long) &frame->tramp[SIGRESTARTBLOCK_TRAMP+0]; - end = (unsigned long) &frame->tramp[SIGRESTARTBLOCK_TRAMP+3]; + start = (unsigned long) &frame->tramp[0]; + end = (unsigned long) &frame->tramp[TRAMP_SIZE]; flush_user_dcache_range_asm(start, end); flush_user_icache_range_asm(start, end); /* TRAMP Words 0-4, Length 5 = SIGRESTARTBLOCK_TRAMP - * TRAMP Words 5-7, Length 3 = SIGRETURN_TRAMP + * TRAMP Words 5-9, Length 4 = SIGRETURN_TRAMP * So the SIGRETURN_TRAMP is at the end of SIGRESTARTBLOCK_TRAMP */ rp = (unsigned long) &frame->tramp[SIGRESTARTBLOCK_TRAMP]; diff --git a/arch/parisc/kernel/signal32.h b/arch/parisc/kernel/signal32.h index a5bdbb5678b7..f166250f2d06 100644 --- a/arch/parisc/kernel/signal32.h +++ b/arch/parisc/kernel/signal32.h @@ -36,7 +36,7 @@ struct compat_regfile { compat_int_t rf_sar; }; -#define COMPAT_SIGRETURN_TRAMP 3 +#define COMPAT_SIGRETURN_TRAMP 4 #define COMPAT_SIGRESTARTBLOCK_TRAMP 5 #define COMPAT_TRAMP_SIZE (COMPAT_SIGRETURN_TRAMP + \ COMPAT_SIGRESTARTBLOCK_TRAMP) diff --git a/arch/parisc/kernel/stacktrace.c b/arch/parisc/kernel/stacktrace.c index 6b4ca91932cf..023834ef582e 100644 --- a/arch/parisc/kernel/stacktrace.c +++ b/arch/parisc/kernel/stacktrace.c @@ -8,6 +8,7 @@ * * TODO: Userspace stacktrace (CONFIG_USER_STACKTRACE_SUPPORT) */ +#include <linux/kernel.h> #include <linux/stacktrace.h> #include <asm/unwind.h> diff --git a/arch/parisc/kernel/syscall.S b/arch/parisc/kernel/syscall.S index 4fb3b6a993bf..d2497b339d13 100644 --- a/arch/parisc/kernel/syscall.S +++ b/arch/parisc/kernel/syscall.S @@ -566,7 +566,7 @@ lws_compare_and_swap: ldo R%lws_lock_start(%r20), %r28 /* Extract eight bits from r26 and hash lock (Bits 3-11) */ - extru %r26, 28, 8, %r20 + extru_safe %r26, 28, 8, %r20 /* Find lock to use, the hash is either one of 0 to 15, multiplied by 16 (keep it 16-byte aligned) @@ -751,7 +751,7 @@ cas2_lock_start: ldo R%lws_lock_start(%r20), %r28 /* Extract eight bits from r26 and hash lock (Bits 3-11) */ - extru %r26, 28, 8, %r20 + extru_safe %r26, 28, 8, %r20 /* Find lock to use, the hash is either one of 0 to 15, multiplied by 16 (keep it 16-byte aligned) diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl index bf751e0732b7..358c00000755 100644 --- a/arch/parisc/kernel/syscalls/syscall.tbl +++ b/arch/parisc/kernel/syscalls/syscall.tbl @@ -446,3 +446,4 @@ 446 common landlock_restrict_self sys_landlock_restrict_self # 447 reserved for memfd_secret 448 common process_mrelease sys_process_mrelease +449 common futex_waitv sys_futex_waitv diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index 0e3640e14eb1..5fa68c2ef1f8 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -196,3 +196,6 @@ clean-files := vmlinux.lds # Force dependency (incbin is bad) $(obj)/vdso32_wrapper.o : $(obj)/vdso32/vdso32.so.dbg $(obj)/vdso64_wrapper.o : $(obj)/vdso64/vdso64.so.dbg + +# for cleaning +subdir- += vdso32 vdso64 diff --git a/arch/powerpc/kernel/head_32.h b/arch/powerpc/kernel/head_32.h index 6b1ec9e3541b..349c4a820231 100644 --- a/arch/powerpc/kernel/head_32.h +++ b/arch/powerpc/kernel/head_32.h @@ -202,11 +202,11 @@ vmap_stack_overflow: mfspr r1, SPRN_SPRG_THREAD lwz r1, TASK_CPU - THREAD(r1) slwi r1, r1, 3 - addis r1, r1, emergency_ctx@ha + addis r1, r1, emergency_ctx-PAGE_OFFSET@ha #else - lis r1, emergency_ctx@ha + lis r1, emergency_ctx-PAGE_OFFSET@ha #endif - lwz r1, emergency_ctx@l(r1) + lwz r1, emergency_ctx-PAGE_OFFSET@l(r1) addi r1, r1, THREAD_SIZE - INT_FRAME_SIZE EXCEPTION_PROLOG_2 0 vmap_stack_overflow prepare_transfer_to_handler diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S index 2d596881b70e..0d073b9fd52c 100644 --- a/arch/powerpc/kernel/head_8xx.S +++ b/arch/powerpc/kernel/head_8xx.S @@ -733,6 +733,7 @@ _GLOBAL(mmu_pin_tlb) #ifdef CONFIG_PIN_TLB_DATA LOAD_REG_IMMEDIATE(r6, PAGE_OFFSET) LOAD_REG_IMMEDIATE(r7, MI_SVALID | MI_PS8MEG | _PMD_ACCESSED) + li r8, 0 #ifdef CONFIG_PIN_TLB_IMMR li r0, 3 #else @@ -741,26 +742,26 @@ _GLOBAL(mmu_pin_tlb) mtctr r0 cmpwi r4, 0 beq 4f - LOAD_REG_IMMEDIATE(r8, 0xf0 | _PAGE_RO | _PAGE_SPS | _PAGE_SH | _PAGE_PRESENT) LOAD_REG_ADDR(r9, _sinittext) 2: ori r0, r6, MD_EVALID + ori r12, r8, 0xf0 | _PAGE_RO | _PAGE_SPS | _PAGE_SH | _PAGE_PRESENT mtspr SPRN_MD_CTR, r5 mtspr SPRN_MD_EPN, r0 mtspr SPRN_MD_TWC, r7 - mtspr SPRN_MD_RPN, r8 + mtspr SPRN_MD_RPN, r12 addi r5, r5, 0x100 addis r6, r6, SZ_8M@h addis r8, r8, SZ_8M@h cmplw r6, r9 bdnzt lt, 2b - -4: LOAD_REG_IMMEDIATE(r8, 0xf0 | _PAGE_DIRTY | _PAGE_SPS | _PAGE_SH | _PAGE_PRESENT) +4: 2: ori r0, r6, MD_EVALID + ori r12, r8, 0xf0 | _PAGE_DIRTY | _PAGE_SPS | _PAGE_SH | _PAGE_PRESENT mtspr SPRN_MD_CTR, r5 mtspr SPRN_MD_EPN, r0 mtspr SPRN_MD_TWC, r7 - mtspr SPRN_MD_RPN, r8 + mtspr SPRN_MD_RPN, r12 addi r5, r5, 0x100 addis r6, r6, SZ_8M@h addis r8, r8, SZ_8M@h @@ -781,7 +782,7 @@ _GLOBAL(mmu_pin_tlb) #endif #if defined(CONFIG_PIN_TLB_IMMR) || defined(CONFIG_PIN_TLB_DATA) lis r0, (MD_RSV4I | MD_TWAM)@h - mtspr SPRN_MI_CTR, r0 + mtspr SPRN_MD_CTR, r0 #endif mtspr SPRN_SRR1, r10 mtspr SPRN_SRR0, r11 diff --git a/arch/powerpc/kernel/signal.h b/arch/powerpc/kernel/signal.h index 1f07317964e4..618aeccdf691 100644 --- a/arch/powerpc/kernel/signal.h +++ b/arch/powerpc/kernel/signal.h @@ -25,8 +25,14 @@ static inline int __get_user_sigset(sigset_t *dst, const sigset_t __user *src) return __get_user(dst->sig[0], (u64 __user *)&src->sig[0]); } -#define unsafe_get_user_sigset(dst, src, label) \ - unsafe_get_user((dst)->sig[0], (u64 __user *)&(src)->sig[0], label) +#define unsafe_get_user_sigset(dst, src, label) do { \ + sigset_t *__dst = dst; \ + const sigset_t __user *__src = src; \ + int i; \ + \ + for (i = 0; i < _NSIG_WORDS; i++) \ + unsafe_get_user(__dst->sig[i], &__src->sig[i], label); \ +} while (0) #ifdef CONFIG_VSX extern unsigned long copy_vsx_to_user(void __user *to, diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index 00a9c9cd6d42..3e053e2fd6b6 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -1063,7 +1063,7 @@ SYSCALL_DEFINE3(swapcontext, struct ucontext __user *, old_ctx, * We kill the task with a SIGSEGV in this situation. */ if (do_setcontext(new_ctx, regs, 0)) { - force_fatal_sig(SIGSEGV); + force_exit_sig(SIGSEGV); return -EFAULT; } diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index ef518535d436..d1e1fc0acbea 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -704,7 +704,7 @@ SYSCALL_DEFINE3(swapcontext, struct ucontext __user *, old_ctx, */ if (__get_user_sigset(&set, &new_ctx->uc_sigmask)) { - force_fatal_sig(SIGSEGV); + force_exit_sig(SIGSEGV); return -EFAULT; } set_current_blocked(&set); @@ -713,7 +713,7 @@ SYSCALL_DEFINE3(swapcontext, struct ucontext __user *, old_ctx, return -EFAULT; if (__unsafe_restore_sigcontext(current, NULL, 0, &new_ctx->uc_mcontext)) { user_read_access_end(); - force_fatal_sig(SIGSEGV); + force_exit_sig(SIGSEGV); return -EFAULT; } user_read_access_end(); diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl index 7bef917cc84e..15109af9d075 100644 --- a/arch/powerpc/kernel/syscalls/syscall.tbl +++ b/arch/powerpc/kernel/syscalls/syscall.tbl @@ -528,3 +528,4 @@ 446 common landlock_restrict_self sys_landlock_restrict_self # 447 reserved for memfd_secret 448 common process_mrelease sys_process_mrelease +449 common futex_waitv sys_futex_waitv diff --git a/arch/powerpc/kernel/watchdog.c b/arch/powerpc/kernel/watchdog.c index f9ea0e5357f9..3fa6d240bade 100644 --- a/arch/powerpc/kernel/watchdog.c +++ b/arch/powerpc/kernel/watchdog.c @@ -187,6 +187,12 @@ static void watchdog_smp_panic(int cpu, u64 tb) if (sysctl_hardlockup_all_cpu_backtrace) trigger_allbutself_cpu_backtrace(); + /* + * Force flush any remote buffers that might be stuck in IRQ context + * and therefore could not run their irq_work. + */ + printk_trigger_flush(); + if (hardlockup_panic) nmi_panic(NULL, "Hard LOCKUP"); diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c index fcf4760a3a0e..70b7a8f97153 100644 --- a/arch/powerpc/kvm/book3s_hv_builtin.c +++ b/arch/powerpc/kvm/book3s_hv_builtin.c @@ -695,6 +695,7 @@ static void flush_guest_tlb(struct kvm *kvm) "r" (0) : "memory"); } asm volatile("ptesync": : :"memory"); + // POWER9 congruence-class TLBIEL leaves ERAT. Flush it now. asm volatile(PPC_RADIX_INVALIDATE_ERAT_GUEST : : :"memory"); } else { for (set = 0; set < kvm->arch.tlb_sets; ++set) { @@ -705,7 +706,9 @@ static void flush_guest_tlb(struct kvm *kvm) rb += PPC_BIT(51); /* increment set number */ } asm volatile("ptesync": : :"memory"); - asm volatile(PPC_ISA_3_0_INVALIDATE_ERAT : : :"memory"); + // POWER9 congruence-class TLBIEL leaves ERAT. Flush it now. + if (cpu_has_feature(CPU_FTR_ARCH_300)) + asm volatile(PPC_ISA_3_0_INVALIDATE_ERAT : : :"memory"); } } diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index eb776d0c5d8e..32a4b4d412b9 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -2005,7 +2005,7 @@ hcall_real_table: .globl hcall_real_table_end hcall_real_table_end: -_GLOBAL(kvmppc_h_set_xdabr) +_GLOBAL_TOC(kvmppc_h_set_xdabr) EXPORT_SYMBOL_GPL(kvmppc_h_set_xdabr) andi. r0, r5, DABRX_USER | DABRX_KERNEL beq 6f @@ -2015,7 +2015,7 @@ EXPORT_SYMBOL_GPL(kvmppc_h_set_xdabr) 6: li r3, H_PARAMETER blr -_GLOBAL(kvmppc_h_set_dabr) +_GLOBAL_TOC(kvmppc_h_set_dabr) EXPORT_SYMBOL_GPL(kvmppc_h_set_dabr) li r5, DABRX_USER | DABRX_KERNEL 3: diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 35e9cccdeef9..a72920f4f221 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -641,9 +641,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) * implementations just count online CPUs. */ if (hv_enabled) - r = num_present_cpus(); + r = min_t(unsigned int, num_present_cpus(), KVM_MAX_VCPUS); else - r = num_online_cpus(); + r = min_t(unsigned int, num_online_cpus(), KVM_MAX_VCPUS); break; case KVM_CAP_MAX_VCPUS: r = KVM_MAX_VCPUS; diff --git a/arch/powerpc/mm/nohash/kaslr_booke.c b/arch/powerpc/mm/nohash/kaslr_booke.c index 8fc49b1b4a91..6ec978967da0 100644 --- a/arch/powerpc/mm/nohash/kaslr_booke.c +++ b/arch/powerpc/mm/nohash/kaslr_booke.c @@ -314,7 +314,7 @@ static unsigned long __init kaslr_choose_location(void *dt_ptr, phys_addr_t size pr_warn("KASLR: No safe seed for randomizing the kernel base.\n"); ram = min_t(phys_addr_t, __max_low_memory, size); - ram = map_mem_in_cams(ram, CONFIG_LOWMEM_CAM_NUM, true, false); + ram = map_mem_in_cams(ram, CONFIG_LOWMEM_CAM_NUM, true, true); linear_sz = min_t(unsigned long, ram, SZ_512M); /* If the linear size is smaller than 64M, do not randmize */ diff --git a/arch/powerpc/mm/nohash/tlb.c b/arch/powerpc/mm/nohash/tlb.c index 89353d4f5604..647bf454a0fa 100644 --- a/arch/powerpc/mm/nohash/tlb.c +++ b/arch/powerpc/mm/nohash/tlb.c @@ -645,7 +645,7 @@ static void early_init_this_mmu(void) if (map) linear_map_top = map_mem_in_cams(linear_map_top, - num_cams, true, true); + num_cams, false, true); } #endif @@ -766,7 +766,7 @@ void setup_initial_memory_limit(phys_addr_t first_memblock_base, num_cams = (mfspr(SPRN_TLB1CFG) & TLBnCFG_N_ENTRY) / 4; linear_sz = map_mem_in_cams(first_memblock_size, num_cams, - false, true); + true, true); ppc64_rma_size = min_t(u64, linear_sz, 0x40000000); } else diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index 6f14c8fb6359..59d3cfcd7887 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -376,9 +376,9 @@ static void initialize_form2_numa_distance_lookup_table(void) { int i, j; struct device_node *root; - const __u8 *numa_dist_table; + const __u8 *form2_distances; const __be32 *numa_lookup_index; - int numa_dist_table_length; + int form2_distances_length; int max_numa_index, distance_index; if (firmware_has_feature(FW_FEATURE_OPAL)) @@ -392,45 +392,41 @@ static void initialize_form2_numa_distance_lookup_table(void) max_numa_index = of_read_number(&numa_lookup_index[0], 1); /* first element of the array is the size and is encode-int */ - numa_dist_table = of_get_property(root, "ibm,numa-distance-table", NULL); - numa_dist_table_length = of_read_number((const __be32 *)&numa_dist_table[0], 1); + form2_distances = of_get_property(root, "ibm,numa-distance-table", NULL); + form2_distances_length = of_read_number((const __be32 *)&form2_distances[0], 1); /* Skip the size which is encoded int */ - numa_dist_table += sizeof(__be32); + form2_distances += sizeof(__be32); - pr_debug("numa_dist_table_len = %d, numa_dist_indexes_len = %d\n", - numa_dist_table_length, max_numa_index); + pr_debug("form2_distances_len = %d, numa_dist_indexes_len = %d\n", + form2_distances_length, max_numa_index); for (i = 0; i < max_numa_index; i++) /* +1 skip the max_numa_index in the property */ numa_id_index_table[i] = of_read_number(&numa_lookup_index[i + 1], 1); - if (numa_dist_table_length != max_numa_index * max_numa_index) { + if (form2_distances_length != max_numa_index * max_numa_index) { WARN(1, "Wrong NUMA distance information\n"); - /* consider everybody else just remote. */ - for (i = 0; i < max_numa_index; i++) { - for (j = 0; j < max_numa_index; j++) { - int nodeA = numa_id_index_table[i]; - int nodeB = numa_id_index_table[j]; - - if (nodeA == nodeB) - numa_distance_table[nodeA][nodeB] = LOCAL_DISTANCE; - else - numa_distance_table[nodeA][nodeB] = REMOTE_DISTANCE; - } - } + form2_distances = NULL; // don't use it } - distance_index = 0; for (i = 0; i < max_numa_index; i++) { for (j = 0; j < max_numa_index; j++) { int nodeA = numa_id_index_table[i]; int nodeB = numa_id_index_table[j]; - - numa_distance_table[nodeA][nodeB] = numa_dist_table[distance_index++]; - pr_debug("dist[%d][%d]=%d ", nodeA, nodeB, numa_distance_table[nodeA][nodeB]); + int dist; + + if (form2_distances) + dist = form2_distances[distance_index++]; + else if (nodeA == nodeB) + dist = LOCAL_DISTANCE; + else + dist = REMOTE_DISTANCE; + numa_distance_table[nodeA][nodeB] = dist; + pr_debug("dist[%d][%d]=%d ", nodeA, nodeB, dist); } } + of_node_put(root); } diff --git a/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c b/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c index bb789f33c70e..a38372f9ac12 100644 --- a/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c +++ b/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c @@ -186,7 +186,6 @@ err: static int mcu_remove(struct i2c_client *client) { struct mcu *mcu = i2c_get_clientdata(client); - int ret; kthread_stop(shutdown_thread); diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index 49b401536d29..8f998e55735b 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -1094,15 +1094,6 @@ static phys_addr_t ddw_memory_hotplug_max(void) phys_addr_t max_addr = memory_hotplug_max(); struct device_node *memory; - /* - * The "ibm,pmemory" can appear anywhere in the address space. - * Assuming it is still backed by page structs, set the upper limit - * for the huge DMA window as MAX_PHYSMEM_BITS. - */ - if (of_find_node_by_type(NULL, "ibm,pmemory")) - return (sizeof(phys_addr_t) * 8 <= MAX_PHYSMEM_BITS) ? - (phys_addr_t) -1 : (1ULL << MAX_PHYSMEM_BITS); - for_each_node_by_type(memory, "memory") { unsigned long start, size; int n_mem_addr_cells, n_mem_size_cells, len; @@ -1238,7 +1229,6 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn) u32 ddw_avail[DDW_APPLICABLE_SIZE]; struct dma_win *window; struct property *win64; - bool ddw_enabled = false; struct failed_ddw_pdn *fpdn; bool default_win_removed = false, direct_mapping = false; bool pmem_present; @@ -1253,7 +1243,6 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn) if (find_existing_ddw(pdn, &dev->dev.archdata.dma_offset, &len)) { direct_mapping = (len >= max_ram_len); - ddw_enabled = true; goto out_unlock; } @@ -1367,8 +1356,10 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn) len = order_base_2(query.largest_available_block << page_shift); win_name = DMA64_PROPNAME; } else { - direct_mapping = true; - win_name = DIRECT64_PROPNAME; + direct_mapping = !default_win_removed || + (len == MAX_PHYSMEM_BITS) || + (!pmem_present && (len == max_ram_len)); + win_name = direct_mapping ? DIRECT64_PROPNAME : DMA64_PROPNAME; } ret = create_ddw(dev, ddw_avail, &create, page_shift, len); @@ -1406,8 +1397,8 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn) dev_info(&dev->dev, "failed to map DMA window for %pOF: %d\n", dn, ret); - /* Make sure to clean DDW if any TCE was set*/ - clean_dma_window(pdn, win64->value); + /* Make sure to clean DDW if any TCE was set*/ + clean_dma_window(pdn, win64->value); goto out_del_list; } } else { @@ -1454,7 +1445,6 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn) spin_unlock(&dma_win_list_lock); dev->dev.archdata.dma_offset = win_addr; - ddw_enabled = true; goto out_unlock; out_del_list: @@ -1490,10 +1480,10 @@ out_unlock: * as RAM, then we failed to create a window to cover persistent * memory and need to set the DMA limit. */ - if (pmem_present && ddw_enabled && direct_mapping && len == max_ram_len) + if (pmem_present && direct_mapping && len == max_ram_len) dev->dev.bus_dma_limit = dev->dev.archdata.dma_offset + (1ULL << len); - return ddw_enabled && direct_mapping; + return direct_mapping; } static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev) diff --git a/arch/powerpc/sysdev/xive/Kconfig b/arch/powerpc/sysdev/xive/Kconfig index 97796c6b63f0..785c292d104b 100644 --- a/arch/powerpc/sysdev/xive/Kconfig +++ b/arch/powerpc/sysdev/xive/Kconfig @@ -3,7 +3,6 @@ config PPC_XIVE bool select PPC_SMP_MUXED_IPI select HARDIRQS_SW_RESEND - select IRQ_DOMAIN_NOMAP config PPC_XIVE_NATIVE bool diff --git a/arch/powerpc/sysdev/xive/common.c b/arch/powerpc/sysdev/xive/common.c index c5d75c02ad8b..7b69299c2912 100644 --- a/arch/powerpc/sysdev/xive/common.c +++ b/arch/powerpc/sysdev/xive/common.c @@ -1443,8 +1443,7 @@ static const struct irq_domain_ops xive_irq_domain_ops = { static void __init xive_init_host(struct device_node *np) { - xive_irq_domain = irq_domain_add_nomap(np, XIVE_MAX_IRQ, - &xive_irq_domain_ops, NULL); + xive_irq_domain = irq_domain_add_tree(np, &xive_irq_domain_ops, NULL); if (WARN_ON(xive_irq_domain == NULL)) return; irq_set_default_host(xive_irq_domain); diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index a34c531be4e7..821252b65f89 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -62,6 +62,7 @@ config RISCV select GENERIC_SCHED_CLOCK select GENERIC_SMP_IDLE_THREAD select GENERIC_TIME_VSYSCALL if MMU && 64BIT + select GENERIC_VDSO_TIME_NS if HAVE_GENERIC_VDSO select HAVE_ARCH_AUDITSYSCALL select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL select HAVE_ARCH_JUMP_LABEL_RELATIVE if !XIP_KERNEL diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile index 7f19b784e649..8a107ed18b0d 100644 --- a/arch/riscv/Makefile +++ b/arch/riscv/Makefile @@ -107,11 +107,13 @@ PHONY += vdso_install vdso_install: $(Q)$(MAKE) $(build)=arch/riscv/kernel/vdso $@ +ifeq ($(KBUILD_EXTMOD),) ifeq ($(CONFIG_MMU),y) prepare: vdso_prepare vdso_prepare: prepare0 $(Q)$(MAKE) $(build)=arch/riscv/kernel/vdso include/generated/vdso-offsets.h endif +endif ifneq ($(CONFIG_XIP_KERNEL),y) ifeq ($(CONFIG_RISCV_M_MODE)$(CONFIG_SOC_CANAAN),yy) @@ -136,3 +138,13 @@ zinstall: install-image = Image.gz install zinstall: $(CONFIG_SHELL) $(srctree)/$(boot)/install.sh $(KERNELRELEASE) \ $(boot)/$(install-image) System.map "$(INSTALL_PATH)" + +PHONY += rv32_randconfig +rv32_randconfig: + $(Q)$(MAKE) KCONFIG_ALLCONFIG=$(srctree)/arch/riscv/configs/32-bit.config \ + -f $(srctree)/Makefile randconfig + +PHONY += rv64_randconfig +rv64_randconfig: + $(Q)$(MAKE) KCONFIG_ALLCONFIG=$(srctree)/arch/riscv/configs/64-bit.config \ + -f $(srctree)/Makefile randconfig diff --git a/arch/riscv/boot/dts/microchip/microchip-mpfs-icicle-kit.dts b/arch/riscv/boot/dts/microchip/microchip-mpfs-icicle-kit.dts index b254c60589a1..fc1e5869df1b 100644 --- a/arch/riscv/boot/dts/microchip/microchip-mpfs-icicle-kit.dts +++ b/arch/riscv/boot/dts/microchip/microchip-mpfs-icicle-kit.dts @@ -9,10 +9,8 @@ #define RTCCLK_FREQ 1000000 / { - #address-cells = <2>; - #size-cells = <2>; model = "Microchip PolarFire-SoC Icicle Kit"; - compatible = "microchip,mpfs-icicle-kit"; + compatible = "microchip,mpfs-icicle-kit", "microchip,mpfs"; aliases { ethernet0 = &emac1; @@ -35,9 +33,6 @@ reg = <0x0 0x80000000 0x0 0x40000000>; clocks = <&clkcfg 26>; }; - - soc { - }; }; &serial0 { @@ -56,8 +51,17 @@ status = "okay"; }; -&sdcard { +&mmc { status = "okay"; + + bus-width = <4>; + disable-wp; + cap-sd-highspeed; + card-detect-delay = <200>; + sd-uhs-sdr12; + sd-uhs-sdr25; + sd-uhs-sdr50; + sd-uhs-sdr104; }; &emac0 { diff --git a/arch/riscv/boot/dts/microchip/microchip-mpfs.dtsi b/arch/riscv/boot/dts/microchip/microchip-mpfs.dtsi index 9d2fbbc1f777..c9f6d205d2ba 100644 --- a/arch/riscv/boot/dts/microchip/microchip-mpfs.dtsi +++ b/arch/riscv/boot/dts/microchip/microchip-mpfs.dtsi @@ -6,8 +6,8 @@ / { #address-cells = <2>; #size-cells = <2>; - model = "Microchip MPFS Icicle Kit"; - compatible = "microchip,mpfs-icicle-kit"; + model = "Microchip PolarFire SoC"; + compatible = "microchip,mpfs"; chosen { }; @@ -161,7 +161,7 @@ }; clint@2000000 { - compatible = "sifive,clint0"; + compatible = "sifive,fu540-c000-clint", "sifive,clint0"; reg = <0x0 0x2000000 0x0 0xC000>; interrupts-extended = <&cpu0_intc 3 &cpu0_intc 7 &cpu1_intc 3 &cpu1_intc 7 @@ -172,7 +172,7 @@ plic: interrupt-controller@c000000 { #interrupt-cells = <1>; - compatible = "sifive,plic-1.0.0"; + compatible = "sifive,fu540-c000-plic", "sifive,plic-1.0.0"; reg = <0x0 0xc000000 0x0 0x4000000>; riscv,ndev = <186>; interrupt-controller; @@ -262,39 +262,13 @@ status = "disabled"; }; - emmc: mmc@20008000 { - compatible = "cdns,sd4hc"; + /* Common node entry for emmc/sd */ + mmc: mmc@20008000 { + compatible = "microchip,mpfs-sd4hc", "cdns,sd4hc"; reg = <0x0 0x20008000 0x0 0x1000>; interrupt-parent = <&plic>; interrupts = <88 89>; - pinctrl-names = "default"; clocks = <&clkcfg 6>; - bus-width = <4>; - cap-mmc-highspeed; - mmc-ddr-3_3v; - max-frequency = <200000000>; - non-removable; - no-sd; - no-sdio; - voltage-ranges = <3300 3300>; - status = "disabled"; - }; - - sdcard: sdhc@20008000 { - compatible = "cdns,sd4hc"; - reg = <0x0 0x20008000 0x0 0x1000>; - interrupt-parent = <&plic>; - interrupts = <88>; - pinctrl-names = "default"; - clocks = <&clkcfg 6>; - bus-width = <4>; - disable-wp; - cap-sd-highspeed; - card-detect-delay = <200>; - sd-uhs-sdr12; - sd-uhs-sdr25; - sd-uhs-sdr50; - sd-uhs-sdr104; max-frequency = <200000000>; status = "disabled"; }; diff --git a/arch/riscv/boot/dts/sifive/fu540-c000.dtsi b/arch/riscv/boot/dts/sifive/fu540-c000.dtsi index 7db861053483..0655b5c4201d 100644 --- a/arch/riscv/boot/dts/sifive/fu540-c000.dtsi +++ b/arch/riscv/boot/dts/sifive/fu540-c000.dtsi @@ -141,7 +141,7 @@ ranges; plic0: interrupt-controller@c000000 { #interrupt-cells = <1>; - compatible = "sifive,plic-1.0.0"; + compatible = "sifive,fu540-c000-plic", "sifive,plic-1.0.0"; reg = <0x0 0xc000000 0x0 0x4000000>; riscv,ndev = <53>; interrupt-controller; diff --git a/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts b/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts index 60846e88ae4b..ba304d4c455c 100644 --- a/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts +++ b/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts @@ -8,10 +8,9 @@ #define RTCCLK_FREQ 1000000 / { - #address-cells = <2>; - #size-cells = <2>; model = "SiFive HiFive Unleashed A00"; - compatible = "sifive,hifive-unleashed-a00", "sifive,fu540-c000"; + compatible = "sifive,hifive-unleashed-a00", "sifive,fu540-c000", + "sifive,fu540"; chosen { stdout-path = "serial0"; @@ -26,9 +25,6 @@ reg = <0x0 0x80000000 0x2 0x00000000>; }; - soc { - }; - hfclk: hfclk { #clock-cells = <0>; compatible = "fixed-clock"; @@ -63,7 +59,7 @@ &qspi0 { status = "okay"; flash@0 { - compatible = "issi,is25wp256", "jedec,spi-nor"; + compatible = "jedec,spi-nor"; reg = <0>; spi-max-frequency = <50000000>; m25p,fast-read; diff --git a/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts b/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts index 2e4ea84f27e7..4f66919215f6 100644 --- a/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts +++ b/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts @@ -8,8 +8,6 @@ #define RTCCLK_FREQ 1000000 / { - #address-cells = <2>; - #size-cells = <2>; model = "SiFive HiFive Unmatched A00"; compatible = "sifive,hifive-unmatched-a00", "sifive,fu740-c000", "sifive,fu740"; @@ -27,9 +25,6 @@ reg = <0x0 0x80000000 0x4 0x00000000>; }; - soc { - }; - hfclk: hfclk { #clock-cells = <0>; compatible = "fixed-clock"; @@ -211,7 +206,7 @@ &qspi0 { status = "okay"; flash@0 { - compatible = "issi,is25wp256", "jedec,spi-nor"; + compatible = "jedec,spi-nor"; reg = <0>; spi-max-frequency = <50000000>; m25p,fast-read; diff --git a/arch/riscv/configs/32-bit.config b/arch/riscv/configs/32-bit.config new file mode 100644 index 000000000000..43f41323b67e --- /dev/null +++ b/arch/riscv/configs/32-bit.config @@ -0,0 +1,2 @@ +CONFIG_ARCH_RV32I=y +CONFIG_32BIT=y diff --git a/arch/riscv/configs/64-bit.config b/arch/riscv/configs/64-bit.config new file mode 100644 index 000000000000..313edc554d84 --- /dev/null +++ b/arch/riscv/configs/64-bit.config @@ -0,0 +1,2 @@ +CONFIG_ARCH_RV64I=y +CONFIG_64BIT=y diff --git a/arch/riscv/configs/defconfig b/arch/riscv/configs/defconfig index 4ebc80315f01..ef473e2f503b 100644 --- a/arch/riscv/configs/defconfig +++ b/arch/riscv/configs/defconfig @@ -19,6 +19,8 @@ CONFIG_SOC_VIRT=y CONFIG_SOC_MICROCHIP_POLARFIRE=y CONFIG_SMP=y CONFIG_HOTPLUG_CPU=y +CONFIG_VIRTUALIZATION=y +CONFIG_KVM=m CONFIG_JUMP_LABEL=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y @@ -72,9 +74,10 @@ CONFIG_GPIOLIB=y CONFIG_GPIO_SIFIVE=y # CONFIG_PTP_1588_CLOCK is not set CONFIG_POWER_RESET=y -CONFIG_DRM=y -CONFIG_DRM_RADEON=y -CONFIG_DRM_VIRTIO_GPU=y +CONFIG_DRM=m +CONFIG_DRM_RADEON=m +CONFIG_DRM_NOUVEAU=m +CONFIG_DRM_VIRTIO_GPU=m CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_USB=y CONFIG_USB_XHCI_HCD=y diff --git a/arch/riscv/configs/rv32_defconfig b/arch/riscv/configs/rv32_defconfig index 434ef5b64599..6e9f12ff968a 100644 --- a/arch/riscv/configs/rv32_defconfig +++ b/arch/riscv/configs/rv32_defconfig @@ -19,6 +19,8 @@ CONFIG_SOC_VIRT=y CONFIG_ARCH_RV32I=y CONFIG_SMP=y CONFIG_HOTPLUG_CPU=y +CONFIG_VIRTUALIZATION=y +CONFIG_KVM=m CONFIG_JUMP_LABEL=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y diff --git a/arch/riscv/include/asm/kvm_host.h b/arch/riscv/include/asm/kvm_host.h index 25ba21f98504..2639b9ee48f9 100644 --- a/arch/riscv/include/asm/kvm_host.h +++ b/arch/riscv/include/asm/kvm_host.h @@ -12,14 +12,12 @@ #include <linux/types.h> #include <linux/kvm.h> #include <linux/kvm_types.h> +#include <asm/csr.h> #include <asm/kvm_vcpu_fp.h> #include <asm/kvm_vcpu_timer.h> -#ifdef CONFIG_64BIT -#define KVM_MAX_VCPUS (1U << 16) -#else -#define KVM_MAX_VCPUS (1U << 9) -#endif +#define KVM_MAX_VCPUS \ + ((HGATP_VMID_MASK >> HGATP_VMID_SHIFT) + 1) #define KVM_HALT_POLL_NS_DEFAULT 500000 diff --git a/arch/riscv/include/asm/page.h b/arch/riscv/include/asm/page.h index 109c97e991a6..b3e5ff0125fe 100644 --- a/arch/riscv/include/asm/page.h +++ b/arch/riscv/include/asm/page.h @@ -157,6 +157,8 @@ extern phys_addr_t __phys_addr_symbol(unsigned long x); #define page_to_bus(page) (page_to_phys(page)) #define phys_to_page(paddr) (pfn_to_page(phys_to_pfn(paddr))) +#define sym_to_pfn(x) __phys_to_pfn(__pa_symbol(x)) + #ifdef CONFIG_FLATMEM #define pfn_valid(pfn) \ (((pfn) >= ARCH_PFN_OFFSET) && (((pfn) - ARCH_PFN_OFFSET) < max_mapnr)) diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index 39b550310ec6..bf204e7c1f74 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -75,7 +75,8 @@ #endif #ifdef CONFIG_XIP_KERNEL -#define XIP_OFFSET SZ_8M +#define XIP_OFFSET SZ_32M +#define XIP_OFFSET_MASK (SZ_32M - 1) #else #define XIP_OFFSET 0 #endif @@ -97,7 +98,8 @@ #ifdef CONFIG_XIP_KERNEL #define XIP_FIXUP(addr) ({ \ uintptr_t __a = (uintptr_t)(addr); \ - (__a >= CONFIG_XIP_PHYS_ADDR && __a < CONFIG_XIP_PHYS_ADDR + SZ_16M) ? \ + (__a >= CONFIG_XIP_PHYS_ADDR && \ + __a < CONFIG_XIP_PHYS_ADDR + XIP_OFFSET * 2) ? \ __a - CONFIG_XIP_PHYS_ADDR + CONFIG_PHYS_RAM_BASE - XIP_OFFSET :\ __a; \ }) diff --git a/arch/riscv/include/asm/vdso.h b/arch/riscv/include/asm/vdso.h index 208e31bc5d1c..bc6f75f3a199 100644 --- a/arch/riscv/include/asm/vdso.h +++ b/arch/riscv/include/asm/vdso.h @@ -8,30 +8,19 @@ #ifndef _ASM_RISCV_VDSO_H #define _ASM_RISCV_VDSO_H - -/* - * All systems with an MMU have a VDSO, but systems without an MMU don't - * support shared libraries and therefor don't have one. - */ -#ifdef CONFIG_MMU - -#include <linux/types.h> /* * All systems with an MMU have a VDSO, but systems without an MMU don't * support shared libraries and therefor don't have one. */ #ifdef CONFIG_MMU -#define __VVAR_PAGES 1 +#define __VVAR_PAGES 2 #ifndef __ASSEMBLY__ #include <generated/vdso-offsets.h> #define VDSO_SYMBOL(base, name) \ (void __user *)((unsigned long)(base) + __vdso_##name##_offset) - -#endif /* CONFIG_MMU */ - #endif /* !__ASSEMBLY__ */ #endif /* CONFIG_MMU */ diff --git a/arch/riscv/include/asm/vdso/gettimeofday.h b/arch/riscv/include/asm/vdso/gettimeofday.h index f839f16e0d2a..77d9c2f721c4 100644 --- a/arch/riscv/include/asm/vdso/gettimeofday.h +++ b/arch/riscv/include/asm/vdso/gettimeofday.h @@ -76,6 +76,13 @@ static __always_inline const struct vdso_data *__arch_get_vdso_data(void) return _vdso_data; } +#ifdef CONFIG_TIME_NS +static __always_inline +const struct vdso_data *__arch_get_timens_vdso_data(const struct vdso_data *vd) +{ + return _timens_data; +} +#endif #endif /* !__ASSEMBLY__ */ #endif /* __ASM_VDSO_GETTIMEOFDAY_H */ diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S index 25ec50573957..f52f01ecbeea 100644 --- a/arch/riscv/kernel/head.S +++ b/arch/riscv/kernel/head.S @@ -20,10 +20,20 @@ REG_L t0, _xip_fixup add \reg, \reg, t0 .endm +.macro XIP_FIXUP_FLASH_OFFSET reg + la t1, __data_loc + li t0, XIP_OFFSET_MASK + and t1, t1, t0 + li t1, XIP_OFFSET + sub t0, t0, t1 + sub \reg, \reg, t0 +.endm _xip_fixup: .dword CONFIG_PHYS_RAM_BASE - CONFIG_XIP_PHYS_ADDR - XIP_OFFSET #else .macro XIP_FIXUP_OFFSET reg .endm +.macro XIP_FIXUP_FLASH_OFFSET reg +.endm #endif /* CONFIG_XIP_KERNEL */ __HEAD @@ -267,6 +277,7 @@ pmp_done: la a3, hart_lottery mv a2, a3 XIP_FIXUP_OFFSET a2 + XIP_FIXUP_FLASH_OFFSET a3 lw t1, (a3) amoswap.w t0, t1, (a2) /* first time here if hart_lottery in RAM is not set */ @@ -305,6 +316,7 @@ clear_bss_done: XIP_FIXUP_OFFSET sp #ifdef CONFIG_BUILTIN_DTB la a0, __dtb_start + XIP_FIXUP_OFFSET a0 #else mv a0, s1 #endif /* CONFIG_BUILTIN_DTB */ diff --git a/arch/riscv/kernel/reset.c b/arch/riscv/kernel/reset.c index ee5878d968cc..9c842c41684a 100644 --- a/arch/riscv/kernel/reset.c +++ b/arch/riscv/kernel/reset.c @@ -12,7 +12,7 @@ static void default_power_off(void) wait_for_interrupt(); } -void (*pm_power_off)(void) = default_power_off; +void (*pm_power_off)(void) = NULL; EXPORT_SYMBOL(pm_power_off); void machine_restart(char *cmd) @@ -23,10 +23,16 @@ void machine_restart(char *cmd) void machine_halt(void) { - pm_power_off(); + if (pm_power_off != NULL) + pm_power_off(); + else + default_power_off(); } void machine_power_off(void) { - pm_power_off(); + if (pm_power_off != NULL) + pm_power_off(); + else + default_power_off(); } diff --git a/arch/riscv/kernel/vdso.c b/arch/riscv/kernel/vdso.c index b70956d80408..a9436a65161a 100644 --- a/arch/riscv/kernel/vdso.c +++ b/arch/riscv/kernel/vdso.c @@ -13,6 +13,7 @@ #include <linux/err.h> #include <asm/page.h> #include <asm/vdso.h> +#include <linux/time_namespace.h> #ifdef CONFIG_GENERIC_TIME_VSYSCALL #include <vdso/datapage.h> @@ -25,14 +26,12 @@ extern char vdso_start[], vdso_end[]; enum vvar_pages { VVAR_DATA_PAGE_OFFSET, + VVAR_TIMENS_PAGE_OFFSET, VVAR_NR_PAGES, }; #define VVAR_SIZE (VVAR_NR_PAGES << PAGE_SHIFT) -static unsigned int vdso_pages __ro_after_init; -static struct page **vdso_pagelist __ro_after_init; - /* * The vDSO data page. */ @@ -42,83 +41,228 @@ static union { } vdso_data_store __page_aligned_data; struct vdso_data *vdso_data = &vdso_data_store.data; -static int __init vdso_init(void) +struct __vdso_info { + const char *name; + const char *vdso_code_start; + const char *vdso_code_end; + unsigned long vdso_pages; + /* Data Mapping */ + struct vm_special_mapping *dm; + /* Code Mapping */ + struct vm_special_mapping *cm; +}; + +static struct __vdso_info vdso_info __ro_after_init = { + .name = "vdso", + .vdso_code_start = vdso_start, + .vdso_code_end = vdso_end, +}; + +static int vdso_mremap(const struct vm_special_mapping *sm, + struct vm_area_struct *new_vma) +{ + current->mm->context.vdso = (void *)new_vma->vm_start; + + return 0; +} + +static int __init __vdso_init(void) { unsigned int i; + struct page **vdso_pagelist; + unsigned long pfn; - vdso_pages = (vdso_end - vdso_start) >> PAGE_SHIFT; - vdso_pagelist = - kcalloc(vdso_pages + VVAR_NR_PAGES, sizeof(struct page *), GFP_KERNEL); - if (unlikely(vdso_pagelist == NULL)) { - pr_err("vdso: pagelist allocation failed\n"); - return -ENOMEM; + if (memcmp(vdso_info.vdso_code_start, "\177ELF", 4)) { + pr_err("vDSO is not a valid ELF object!\n"); + return -EINVAL; } - for (i = 0; i < vdso_pages; i++) { - struct page *pg; + vdso_info.vdso_pages = ( + vdso_info.vdso_code_end - + vdso_info.vdso_code_start) >> + PAGE_SHIFT; + + vdso_pagelist = kcalloc(vdso_info.vdso_pages, + sizeof(struct page *), + GFP_KERNEL); + if (vdso_pagelist == NULL) + return -ENOMEM; + + /* Grab the vDSO code pages. */ + pfn = sym_to_pfn(vdso_info.vdso_code_start); + + for (i = 0; i < vdso_info.vdso_pages; i++) + vdso_pagelist[i] = pfn_to_page(pfn + i); + + vdso_info.cm->pages = vdso_pagelist; + + return 0; +} + +#ifdef CONFIG_TIME_NS +struct vdso_data *arch_get_vdso_data(void *vvar_page) +{ + return (struct vdso_data *)(vvar_page); +} + +/* + * The vvar mapping contains data for a specific time namespace, so when a task + * changes namespace we must unmap its vvar data for the old namespace. + * Subsequent faults will map in data for the new namespace. + * + * For more details see timens_setup_vdso_data(). + */ +int vdso_join_timens(struct task_struct *task, struct time_namespace *ns) +{ + struct mm_struct *mm = task->mm; + struct vm_area_struct *vma; + + mmap_read_lock(mm); - pg = virt_to_page(vdso_start + (i << PAGE_SHIFT)); - vdso_pagelist[i] = pg; + for (vma = mm->mmap; vma; vma = vma->vm_next) { + unsigned long size = vma->vm_end - vma->vm_start; + + if (vma_is_special_mapping(vma, vdso_info.dm)) + zap_page_range(vma, vma->vm_start, size); } - vdso_pagelist[i] = virt_to_page(vdso_data); + mmap_read_unlock(mm); return 0; } + +static struct page *find_timens_vvar_page(struct vm_area_struct *vma) +{ + if (likely(vma->vm_mm == current->mm)) + return current->nsproxy->time_ns->vvar_page; + + /* + * VM_PFNMAP | VM_IO protect .fault() handler from being called + * through interfaces like /proc/$pid/mem or + * process_vm_{readv,writev}() as long as there's no .access() + * in special_mapping_vmops. + * For more details check_vma_flags() and __access_remote_vm() + */ + WARN(1, "vvar_page accessed remotely"); + + return NULL; +} +#else +static struct page *find_timens_vvar_page(struct vm_area_struct *vma) +{ + return NULL; +} +#endif + +static vm_fault_t vvar_fault(const struct vm_special_mapping *sm, + struct vm_area_struct *vma, struct vm_fault *vmf) +{ + struct page *timens_page = find_timens_vvar_page(vma); + unsigned long pfn; + + switch (vmf->pgoff) { + case VVAR_DATA_PAGE_OFFSET: + if (timens_page) + pfn = page_to_pfn(timens_page); + else + pfn = sym_to_pfn(vdso_data); + break; +#ifdef CONFIG_TIME_NS + case VVAR_TIMENS_PAGE_OFFSET: + /* + * If a task belongs to a time namespace then a namespace + * specific VVAR is mapped with the VVAR_DATA_PAGE_OFFSET and + * the real VVAR page is mapped with the VVAR_TIMENS_PAGE_OFFSET + * offset. + * See also the comment near timens_setup_vdso_data(). + */ + if (!timens_page) + return VM_FAULT_SIGBUS; + pfn = sym_to_pfn(vdso_data); + break; +#endif /* CONFIG_TIME_NS */ + default: + return VM_FAULT_SIGBUS; + } + + return vmf_insert_pfn(vma, vmf->address, pfn); +} + +enum rv_vdso_map { + RV_VDSO_MAP_VVAR, + RV_VDSO_MAP_VDSO, +}; + +static struct vm_special_mapping rv_vdso_maps[] __ro_after_init = { + [RV_VDSO_MAP_VVAR] = { + .name = "[vvar]", + .fault = vvar_fault, + }, + [RV_VDSO_MAP_VDSO] = { + .name = "[vdso]", + .mremap = vdso_mremap, + }, +}; + +static int __init vdso_init(void) +{ + vdso_info.dm = &rv_vdso_maps[RV_VDSO_MAP_VVAR]; + vdso_info.cm = &rv_vdso_maps[RV_VDSO_MAP_VDSO]; + + return __vdso_init(); +} arch_initcall(vdso_init); -int arch_setup_additional_pages(struct linux_binprm *bprm, - int uses_interp) +static int __setup_additional_pages(struct mm_struct *mm, + struct linux_binprm *bprm, + int uses_interp) { - struct mm_struct *mm = current->mm; - unsigned long vdso_base, vdso_len; - int ret; + unsigned long vdso_base, vdso_text_len, vdso_mapping_len; + void *ret; BUILD_BUG_ON(VVAR_NR_PAGES != __VVAR_PAGES); - vdso_len = (vdso_pages + VVAR_NR_PAGES) << PAGE_SHIFT; + vdso_text_len = vdso_info.vdso_pages << PAGE_SHIFT; + /* Be sure to map the data page */ + vdso_mapping_len = vdso_text_len + VVAR_SIZE; - if (mmap_write_lock_killable(mm)) - return -EINTR; - - vdso_base = get_unmapped_area(NULL, 0, vdso_len, 0, 0); + vdso_base = get_unmapped_area(NULL, 0, vdso_mapping_len, 0, 0); if (IS_ERR_VALUE(vdso_base)) { - ret = vdso_base; - goto end; + ret = ERR_PTR(vdso_base); + goto up_fail; } - mm->context.vdso = NULL; - ret = install_special_mapping(mm, vdso_base, VVAR_SIZE, - (VM_READ | VM_MAYREAD), &vdso_pagelist[vdso_pages]); - if (unlikely(ret)) - goto end; + ret = _install_special_mapping(mm, vdso_base, VVAR_SIZE, + (VM_READ | VM_MAYREAD | VM_PFNMAP), vdso_info.dm); + if (IS_ERR(ret)) + goto up_fail; + vdso_base += VVAR_SIZE; + mm->context.vdso = (void *)vdso_base; ret = - install_special_mapping(mm, vdso_base + VVAR_SIZE, - vdso_pages << PAGE_SHIFT, + _install_special_mapping(mm, vdso_base, vdso_text_len, (VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC), - vdso_pagelist); + vdso_info.cm); - if (unlikely(ret)) - goto end; + if (IS_ERR(ret)) + goto up_fail; - /* - * Put vDSO base into mm struct. We need to do this before calling - * install_special_mapping or the perf counter mmap tracking code - * will fail to recognise it as a vDSO (since arch_vma_name fails). - */ - mm->context.vdso = (void *)vdso_base + VVAR_SIZE; + return 0; -end: - mmap_write_unlock(mm); - return ret; +up_fail: + mm->context.vdso = NULL; + return PTR_ERR(ret); } -const char *arch_vma_name(struct vm_area_struct *vma) +int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) { - if (vma->vm_mm && (vma->vm_start == (long)vma->vm_mm->context.vdso)) - return "[vdso]"; - if (vma->vm_mm && (vma->vm_start == - (long)vma->vm_mm->context.vdso - VVAR_SIZE)) - return "[vdso_data]"; - return NULL; + struct mm_struct *mm = current->mm; + int ret; + + if (mmap_write_lock_killable(mm)) + return -EINTR; + + ret = __setup_additional_pages(mm, bprm, uses_interp); + mmap_write_unlock(mm); + + return ret; } diff --git a/arch/riscv/kernel/vdso/vdso.lds.S b/arch/riscv/kernel/vdso/vdso.lds.S index e9111f700af0..01d94aae5bf5 100644 --- a/arch/riscv/kernel/vdso/vdso.lds.S +++ b/arch/riscv/kernel/vdso/vdso.lds.S @@ -10,6 +10,9 @@ OUTPUT_ARCH(riscv) SECTIONS { PROVIDE(_vdso_data = . - __VVAR_PAGES * PAGE_SIZE); +#ifdef CONFIG_TIME_NS + PROVIDE(_timens_data = _vdso_data + PAGE_SIZE); +#endif . = SIZEOF_HEADERS; .hash : { *(.hash) } :text diff --git a/arch/riscv/kernel/vmlinux-xip.lds.S b/arch/riscv/kernel/vmlinux-xip.lds.S index 9c9f35091ef0..f5ed08262139 100644 --- a/arch/riscv/kernel/vmlinux-xip.lds.S +++ b/arch/riscv/kernel/vmlinux-xip.lds.S @@ -64,8 +64,11 @@ SECTIONS /* * From this point, stuff is considered writable and will be copied to RAM */ - __data_loc = ALIGN(16); /* location in file */ - . = LOAD_OFFSET + XIP_OFFSET; /* location in memory */ + __data_loc = ALIGN(PAGE_SIZE); /* location in file */ + . = KERNEL_LINK_ADDR + XIP_OFFSET; /* location in memory */ + +#undef LOAD_OFFSET +#define LOAD_OFFSET (KERNEL_LINK_ADDR + XIP_OFFSET - (__data_loc & XIP_OFFSET_MASK)) _sdata = .; /* Start of data section */ _data = .; @@ -96,7 +99,6 @@ SECTIONS KEEP(*(__soc_builtin_dtb_table)) __soc_builtin_dtb_table_end = .; } - PERCPU_SECTION(L1_CACHE_BYTES) . = ALIGN(8); .alternative : { @@ -122,6 +124,8 @@ SECTIONS BSS_SECTION(PAGE_SIZE, PAGE_SIZE, 0) + PERCPU_SECTION(L1_CACHE_BYTES) + .rel.dyn : AT(ADDR(.rel.dyn) - LOAD_OFFSET) { *(.rel.dyn*) } diff --git a/arch/riscv/kvm/mmu.c b/arch/riscv/kvm/mmu.c index d81bae8eb55e..fc058ff5f4b6 100644 --- a/arch/riscv/kvm/mmu.c +++ b/arch/riscv/kvm/mmu.c @@ -453,6 +453,12 @@ void kvm_arch_flush_shadow_all(struct kvm *kvm) void kvm_arch_flush_shadow_memslot(struct kvm *kvm, struct kvm_memory_slot *slot) { + gpa_t gpa = slot->base_gfn << PAGE_SHIFT; + phys_addr_t size = slot->npages << PAGE_SHIFT; + + spin_lock(&kvm->mmu_lock); + stage2_unmap_range(kvm, gpa, size, false); + spin_unlock(&kvm->mmu_lock); } void kvm_arch_commit_memory_region(struct kvm *kvm, diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c index e3d3aed46184..fb84619df012 100644 --- a/arch/riscv/kvm/vcpu.c +++ b/arch/riscv/kvm/vcpu.c @@ -740,7 +740,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) * Ensure we set mode to IN_GUEST_MODE after we disable * interrupts and before the final VCPU requests check. * See the comment in kvm_vcpu_exiting_guest_mode() and - * Documentation/virtual/kvm/vcpu-requests.rst + * Documentation/virt/kvm/vcpu-requests.rst */ vcpu->mode = IN_GUEST_MODE; diff --git a/arch/riscv/kvm/vcpu_sbi.c b/arch/riscv/kvm/vcpu_sbi.c index eb3c045edf11..3b0e703d22cf 100644 --- a/arch/riscv/kvm/vcpu_sbi.c +++ b/arch/riscv/kvm/vcpu_sbi.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/** +/* * Copyright (c) 2019 Western Digital Corporation or its affiliates. * * Authors: diff --git a/arch/riscv/kvm/vm.c b/arch/riscv/kvm/vm.c index 26399df15b63..fb18af34a4b5 100644 --- a/arch/riscv/kvm/vm.c +++ b/arch/riscv/kvm/vm.c @@ -74,7 +74,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) r = 1; break; case KVM_CAP_NR_VCPUS: - r = num_online_cpus(); + r = min_t(unsigned int, num_online_cpus(), KVM_MAX_VCPUS); break; case KVM_CAP_MAX_VCPUS: r = KVM_MAX_VCPUS; diff --git a/arch/riscv/mm/context.c b/arch/riscv/mm/context.c index ee3459cb6750..ea54cc0c9106 100644 --- a/arch/riscv/mm/context.c +++ b/arch/riscv/mm/context.c @@ -233,8 +233,10 @@ static int __init asids_init(void) local_flush_tlb_all(); /* Pre-compute ASID details */ - num_asids = 1 << asid_bits; - asid_mask = num_asids - 1; + if (asid_bits) { + num_asids = 1 << asid_bits; + asid_mask = num_asids - 1; + } /* * Use ASID allocator only if number of HW ASIDs are @@ -255,7 +257,7 @@ static int __init asids_init(void) pr_info("ASID allocator using %lu bits (%lu entries)\n", asid_bits, num_asids); } else { - pr_info("ASID allocator disabled\n"); + pr_info("ASID allocator disabled (%lu bits)\n", asid_bits); } return 0; diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index c0cddf0fc22d..24b2b8044602 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -41,7 +41,7 @@ phys_addr_t phys_ram_base __ro_after_init; EXPORT_SYMBOL(phys_ram_base); #ifdef CONFIG_XIP_KERNEL -extern char _xiprom[], _exiprom[]; +extern char _xiprom[], _exiprom[], __data_loc; #endif unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)] @@ -454,10 +454,9 @@ static uintptr_t __init best_map_size(phys_addr_t base, phys_addr_t size) /* called from head.S with MMU off */ asmlinkage void __init __copy_data(void) { - void *from = (void *)(&_sdata); - void *end = (void *)(&_end); + void *from = (void *)(&__data_loc); void *to = (void *)CONFIG_PHYS_RAM_BASE; - size_t sz = (size_t)(end - from + 1); + size_t sz = (size_t)((uintptr_t)(&_end) - (uintptr_t)(&_sdata)); memcpy(to, from, sz); } diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 8857ec3b97eb..2a5bb4f29cfe 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -47,7 +47,7 @@ config ARCH_SUPPORTS_UPROBES config KASAN_SHADOW_OFFSET hex depends on KASAN - default 0x18000000000000 + default 0x1C000000000000 config S390 def_bool y @@ -194,6 +194,7 @@ config S390 select HAVE_RELIABLE_STACKTRACE select HAVE_RSEQ select HAVE_SAMPLE_FTRACE_DIRECT + select HAVE_SAMPLE_FTRACE_DIRECT_MULTI select HAVE_SOFTIRQ_ON_OWN_STACK select HAVE_SYSCALL_TRACEPOINTS select HAVE_VIRT_CPU_ACCOUNTING diff --git a/arch/s390/Makefile b/arch/s390/Makefile index 69c45f600273..609e3697324b 100644 --- a/arch/s390/Makefile +++ b/arch/s390/Makefile @@ -77,10 +77,12 @@ KBUILD_AFLAGS_DECOMPRESSOR += $(aflags-y) KBUILD_CFLAGS_DECOMPRESSOR += $(cflags-y) ifneq ($(call cc-option,-mstack-size=8192 -mstack-guard=128),) -cflags-$(CONFIG_CHECK_STACK) += -mstack-size=$(STACK_SIZE) -ifeq ($(call cc-option,-mstack-size=8192),) -cflags-$(CONFIG_CHECK_STACK) += -mstack-guard=$(CONFIG_STACK_GUARD) -endif + CC_FLAGS_CHECK_STACK := -mstack-size=$(STACK_SIZE) + ifeq ($(call cc-option,-mstack-size=8192),) + CC_FLAGS_CHECK_STACK += -mstack-guard=$(CONFIG_STACK_GUARD) + endif + export CC_FLAGS_CHECK_STACK + cflags-$(CONFIG_CHECK_STACK) += $(CC_FLAGS_CHECK_STACK) endif ifdef CONFIG_EXPOLINE diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c index 7571dee72a0c..1aa11a8f57dd 100644 --- a/arch/s390/boot/startup.c +++ b/arch/s390/boot/startup.c @@ -149,82 +149,56 @@ static void setup_ident_map_size(unsigned long max_physmem_end) static void setup_kernel_memory_layout(void) { - bool vmalloc_size_verified = false; - unsigned long vmemmap_off; - unsigned long vspace_left; + unsigned long vmemmap_start; unsigned long rte_size; unsigned long pages; - unsigned long vmax; pages = ident_map_size / PAGE_SIZE; /* vmemmap contains a multiple of PAGES_PER_SECTION struct pages */ vmemmap_size = SECTION_ALIGN_UP(pages) * sizeof(struct page); /* choose kernel address space layout: 4 or 3 levels. */ - vmemmap_off = round_up(ident_map_size, _REGION3_SIZE); + vmemmap_start = round_up(ident_map_size, _REGION3_SIZE); if (IS_ENABLED(CONFIG_KASAN) || vmalloc_size > _REGION2_SIZE || - vmemmap_off + vmemmap_size + vmalloc_size + MODULES_LEN > _REGION2_SIZE) - vmax = _REGION1_SIZE; - else - vmax = _REGION2_SIZE; - - /* keep vmemmap_off aligned to a top level region table entry */ - rte_size = vmax == _REGION1_SIZE ? _REGION2_SIZE : _REGION3_SIZE; - MODULES_END = vmax; - if (is_prot_virt_host()) { - /* - * forcing modules and vmalloc area under the ultravisor - * secure storage limit, so that any vmalloc allocation - * we do could be used to back secure guest storage. - */ - adjust_to_uv_max(&MODULES_END); - } - -#ifdef CONFIG_KASAN - if (MODULES_END < vmax) { - /* force vmalloc and modules below kasan shadow */ - MODULES_END = min(MODULES_END, KASAN_SHADOW_START); + vmemmap_start + vmemmap_size + vmalloc_size + MODULES_LEN > + _REGION2_SIZE) { + MODULES_END = _REGION1_SIZE; + rte_size = _REGION2_SIZE; } else { - /* - * leave vmalloc and modules above kasan shadow but make - * sure they don't overlap with it - */ - vmalloc_size = min(vmalloc_size, vmax - KASAN_SHADOW_END - MODULES_LEN); - vmalloc_size_verified = true; - vspace_left = KASAN_SHADOW_START; + MODULES_END = _REGION2_SIZE; + rte_size = _REGION3_SIZE; } + /* + * forcing modules and vmalloc area under the ultravisor + * secure storage limit, so that any vmalloc allocation + * we do could be used to back secure guest storage. + */ + adjust_to_uv_max(&MODULES_END); +#ifdef CONFIG_KASAN + /* force vmalloc and modules below kasan shadow */ + MODULES_END = min(MODULES_END, KASAN_SHADOW_START); #endif MODULES_VADDR = MODULES_END - MODULES_LEN; VMALLOC_END = MODULES_VADDR; - if (vmalloc_size_verified) { - VMALLOC_START = VMALLOC_END - vmalloc_size; - } else { - vmemmap_off = round_up(ident_map_size, rte_size); - - if (vmemmap_off + vmemmap_size > VMALLOC_END || - vmalloc_size > VMALLOC_END - vmemmap_off - vmemmap_size) { - /* - * allow vmalloc area to occupy up to 1/2 of - * the rest virtual space left. - */ - vmalloc_size = min(vmalloc_size, VMALLOC_END / 2); - } - VMALLOC_START = VMALLOC_END - vmalloc_size; - vspace_left = VMALLOC_START; - } + /* allow vmalloc area to occupy up to about 1/2 of the rest virtual space left */ + vmalloc_size = min(vmalloc_size, round_down(VMALLOC_END / 2, _REGION3_SIZE)); + VMALLOC_START = VMALLOC_END - vmalloc_size; - pages = vspace_left / (PAGE_SIZE + sizeof(struct page)); + /* split remaining virtual space between 1:1 mapping & vmemmap array */ + pages = VMALLOC_START / (PAGE_SIZE + sizeof(struct page)); pages = SECTION_ALIGN_UP(pages); - vmemmap_off = round_up(vspace_left - pages * sizeof(struct page), rte_size); - /* keep vmemmap left most starting from a fresh region table entry */ - vmemmap_off = min(vmemmap_off, round_up(ident_map_size, rte_size)); - /* take care that identity map is lower then vmemmap */ - ident_map_size = min(ident_map_size, vmemmap_off); + /* keep vmemmap_start aligned to a top level region table entry */ + vmemmap_start = round_down(VMALLOC_START - pages * sizeof(struct page), rte_size); + /* vmemmap_start is the future VMEM_MAX_PHYS, make sure it is within MAX_PHYSMEM */ + vmemmap_start = min(vmemmap_start, 1UL << MAX_PHYSMEM_BITS); + /* make sure identity map doesn't overlay with vmemmap */ + ident_map_size = min(ident_map_size, vmemmap_start); vmemmap_size = SECTION_ALIGN_UP(ident_map_size / PAGE_SIZE) * sizeof(struct page); - VMALLOC_START = max(vmemmap_off + vmemmap_size, VMALLOC_START); - vmemmap = (struct page *)vmemmap_off; + /* make sure vmemmap doesn't overlay with vmalloc area */ + VMALLOC_START = max(vmemmap_start + vmemmap_size, VMALLOC_START); + vmemmap = (struct page *)vmemmap_start; } /* diff --git a/arch/s390/include/asm/kexec.h b/arch/s390/include/asm/kexec.h index ea398a05f643..7f3c9ac34bd8 100644 --- a/arch/s390/include/asm/kexec.h +++ b/arch/s390/include/asm/kexec.h @@ -74,6 +74,12 @@ void *kexec_file_add_components(struct kimage *image, int arch_kexec_do_relocs(int r_type, void *loc, unsigned long val, unsigned long addr); +#define ARCH_HAS_KIMAGE_ARCH + +struct kimage_arch { + void *ipl_buf; +}; + extern const struct kexec_file_ops s390_kexec_image_ops; extern const struct kexec_file_ops s390_kexec_elf_ops; diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h index 6b3c366af78e..90824be5ce9a 100644 --- a/arch/s390/include/asm/pci.h +++ b/arch/s390/include/asm/pci.h @@ -210,9 +210,11 @@ int zpci_deconfigure_device(struct zpci_dev *zdev); void zpci_device_reserved(struct zpci_dev *zdev); bool zpci_is_device_configured(struct zpci_dev *zdev); +int zpci_hot_reset_device(struct zpci_dev *zdev); int zpci_register_ioat(struct zpci_dev *, u8, u64, u64, u64); int zpci_unregister_ioat(struct zpci_dev *, u8); void zpci_remove_reserved_devices(void); +void zpci_update_fh(struct zpci_dev *zdev, u32 fh); /* CLP */ int clp_setup_writeback_mio(void); @@ -294,8 +296,10 @@ void zpci_debug_exit(void); void zpci_debug_init_device(struct zpci_dev *, const char *); void zpci_debug_exit_device(struct zpci_dev *); -/* Error reporting */ +/* Error handling */ int zpci_report_error(struct pci_dev *, struct zpci_report_error_header *); +int zpci_clear_error_state(struct zpci_dev *zdev); +int zpci_reset_load_store_blocked(struct zpci_dev *zdev); #ifdef CONFIG_NUMA diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c index d72a6df058d7..785d54c9350c 100644 --- a/arch/s390/kernel/crash_dump.c +++ b/arch/s390/kernel/crash_dump.c @@ -191,8 +191,8 @@ static int copy_oldmem_user(void __user *dst, void *src, size_t count) return rc; } else { /* Check for swapped kdump oldmem areas */ - if (oldmem_data.start && from - oldmem_data.size < oldmem_data.size) { - from -= oldmem_data.size; + if (oldmem_data.start && from - oldmem_data.start < oldmem_data.size) { + from -= oldmem_data.start; len = min(count, oldmem_data.size - from); } else if (oldmem_data.start && from < oldmem_data.size) { len = min(count, oldmem_data.size - from); diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c index e2cc35775b99..5ad1dde23dc5 100644 --- a/arch/s390/kernel/ipl.c +++ b/arch/s390/kernel/ipl.c @@ -2156,7 +2156,7 @@ void *ipl_report_finish(struct ipl_report *report) buf = vzalloc(report->size); if (!buf) - return ERR_PTR(-ENOMEM); + goto out; ptr = buf; memcpy(ptr, report->ipib, report->ipib->hdr.len); @@ -2195,6 +2195,7 @@ void *ipl_report_finish(struct ipl_report *report) } BUG_ON(ptr > buf + report->size); +out: return buf; } diff --git a/arch/s390/kernel/machine_kexec_file.c b/arch/s390/kernel/machine_kexec_file.c index 528edff085d9..9975ad200d74 100644 --- a/arch/s390/kernel/machine_kexec_file.c +++ b/arch/s390/kernel/machine_kexec_file.c @@ -12,6 +12,7 @@ #include <linux/kexec.h> #include <linux/module_signature.h> #include <linux/verification.h> +#include <linux/vmalloc.h> #include <asm/boot_data.h> #include <asm/ipl.h> #include <asm/setup.h> @@ -170,6 +171,7 @@ static int kexec_file_add_ipl_report(struct kimage *image, struct kexec_buf buf; unsigned long addr; void *ptr, *end; + int ret; buf.image = image; @@ -199,9 +201,13 @@ static int kexec_file_add_ipl_report(struct kimage *image, ptr += len; } + ret = -ENOMEM; buf.buffer = ipl_report_finish(data->report); + if (!buf.buffer) + goto out; buf.bufsz = data->report->size; buf.memsz = buf.bufsz; + image->arch.ipl_buf = buf.buffer; data->memsz += buf.memsz; @@ -209,7 +215,9 @@ static int kexec_file_add_ipl_report(struct kimage *image, data->kernel_buf + offsetof(struct lowcore, ipl_parmblock_ptr); *lc_ipl_parmblock_ptr = (__u32)buf.mem; - return kexec_add_buffer(&buf); + ret = kexec_add_buffer(&buf); +out: + return ret; } void *kexec_file_add_components(struct kimage *image, @@ -322,3 +330,11 @@ int arch_kexec_apply_relocations_add(struct purgatory_info *pi, } return 0; } + +int arch_kimage_file_post_load_cleanup(struct kimage *image) +{ + vfree(image->arch.ipl_buf); + image->arch.ipl_buf = NULL; + + return kexec_image_post_load_cleanup_default(image); +} diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c index 6f431fa9e4d7..ee8707abdb6a 100644 --- a/arch/s390/kernel/perf_cpum_cf.c +++ b/arch/s390/kernel/perf_cpum_cf.c @@ -687,8 +687,10 @@ static void cpumf_pmu_stop(struct perf_event *event, int flags) false); if (cfdiag_diffctr(cpuhw, event->hw.config_base)) cfdiag_push_sample(event, cpuhw); - } else + } else if (cpuhw->flags & PMU_F_RESERVED) { + /* Only update when PMU not hotplugged off */ hw_perf_event_update(event); + } hwc->state |= PERF_HES_UPTODATE; } } diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index 40405f2304f1..225ab2d0a4c6 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -606,7 +606,7 @@ static void __init setup_resources(void) static void __init setup_memory_end(void) { - memblock_remove(ident_map_size, ULONG_MAX); + memblock_remove(ident_map_size, PHYS_ADDR_MAX - ident_map_size); max_pfn = max_low_pfn = PFN_DOWN(ident_map_size); pr_notice("The maximum memory size is %luMB\n", ident_map_size >> 20); } @@ -638,14 +638,6 @@ static struct notifier_block kdump_mem_nb = { #endif /* - * Make sure that the area above identity mapping is protected - */ -static void __init reserve_above_ident_map(void) -{ - memblock_reserve(ident_map_size, ULONG_MAX); -} - -/* * Reserve memory for kdump kernel to be loaded with kexec */ static void __init reserve_crashkernel(void) @@ -785,7 +777,6 @@ static void __init memblock_add_mem_detect_info(void) } memblock_set_bottom_up(false); memblock_set_node(0, ULONG_MAX, &memblock.memory, 0); - memblock_dump_all(); } /* @@ -826,9 +817,6 @@ static void __init setup_memory(void) storage_key_init_range(start, end); psw_set_key(PAGE_DEFAULT_KEY); - - /* Only cosmetics */ - memblock_enforce_memory_limit(memblock_end_of_DRAM()); } static void __init relocate_amode31_section(void) @@ -999,24 +987,24 @@ void __init setup_arch(char **cmdline_p) setup_control_program_code(); /* Do some memory reservations *before* memory is added to memblock */ - reserve_above_ident_map(); reserve_kernel(); reserve_initrd(); reserve_certificate_list(); reserve_mem_detect_info(); + memblock_set_current_limit(ident_map_size); memblock_allow_resize(); /* Get information about *all* installed memory */ memblock_add_mem_detect_info(); free_mem_detect_info(); + setup_memory_end(); + memblock_dump_all(); + setup_memory(); relocate_amode31_section(); setup_cr(); - setup_uv(); - setup_memory_end(); - setup_memory(); dma_contiguous_reserve(ident_map_size); vmcp_cma_reserve(); if (MACHINE_HAS_EDAT2) diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl index df5261e5cfe1..ed9c5c2eafad 100644 --- a/arch/s390/kernel/syscalls/syscall.tbl +++ b/arch/s390/kernel/syscalls/syscall.tbl @@ -451,3 +451,4 @@ 446 common landlock_restrict_self sys_landlock_restrict_self sys_landlock_restrict_self # 447 reserved for memfd_secret 448 common process_mrelease sys_process_mrelease sys_process_mrelease +449 common futex_waitv sys_futex_waitv sys_futex_waitv diff --git a/arch/s390/kernel/traps.c b/arch/s390/kernel/traps.c index 035705c9f23e..2b780786fc68 100644 --- a/arch/s390/kernel/traps.c +++ b/arch/s390/kernel/traps.c @@ -84,7 +84,7 @@ static void default_trap_handler(struct pt_regs *regs) { if (user_mode(regs)) { report_user_fault(regs, SIGSEGV, 0); - force_fatal_sig(SIGSEGV); + force_exit_sig(SIGSEGV); } else die(regs, "Unknown program exception"); } diff --git a/arch/s390/kernel/vdso32/Makefile b/arch/s390/kernel/vdso32/Makefile index e3e6ac5686df..245bddfe9bc0 100644 --- a/arch/s390/kernel/vdso32/Makefile +++ b/arch/s390/kernel/vdso32/Makefile @@ -22,7 +22,7 @@ KBUILD_AFLAGS_32 += -m31 -s KBUILD_CFLAGS_32 := $(filter-out -m64,$(KBUILD_CFLAGS)) KBUILD_CFLAGS_32 += -m31 -fPIC -shared -fno-common -fno-builtin -LDFLAGS_vdso32.so.dbg += -fPIC -shared -nostdlib -soname=linux-vdso32.so.1 \ +LDFLAGS_vdso32.so.dbg += -fPIC -shared -soname=linux-vdso32.so.1 \ --hash-style=both --build-id=sha1 -melf_s390 -T $(targets:%=$(obj)/%.dbg): KBUILD_CFLAGS = $(KBUILD_CFLAGS_32) diff --git a/arch/s390/kernel/vdso64/Makefile b/arch/s390/kernel/vdso64/Makefile index 6568de236701..9e2b95a222a9 100644 --- a/arch/s390/kernel/vdso64/Makefile +++ b/arch/s390/kernel/vdso64/Makefile @@ -8,8 +8,9 @@ ARCH_REL_TYPE_ABS += R_390_GOT|R_390_PLT include $(srctree)/lib/vdso/Makefile obj-vdso64 = vdso_user_wrapper.o note.o obj-cvdso64 = vdso64_generic.o getcpu.o -CFLAGS_REMOVE_getcpu.o = -pg $(CC_FLAGS_FTRACE) $(CC_FLAGS_EXPOLINE) -CFLAGS_REMOVE_vdso64_generic.o = -pg $(CC_FLAGS_FTRACE) $(CC_FLAGS_EXPOLINE) +VDSO_CFLAGS_REMOVE := -pg $(CC_FLAGS_FTRACE) $(CC_FLAGS_EXPOLINE) $(CC_FLAGS_CHECK_STACK) +CFLAGS_REMOVE_getcpu.o = $(VDSO_CFLAGS_REMOVE) +CFLAGS_REMOVE_vdso64_generic.o = $(VDSO_CFLAGS_REMOVE) # Build rules @@ -25,7 +26,7 @@ KBUILD_AFLAGS_64 += -m64 -s KBUILD_CFLAGS_64 := $(filter-out -m64,$(KBUILD_CFLAGS)) KBUILD_CFLAGS_64 += -m64 -fPIC -shared -fno-common -fno-builtin -ldflags-y := -fPIC -shared -nostdlib -soname=linux-vdso64.so.1 \ +ldflags-y := -fPIC -shared -soname=linux-vdso64.so.1 \ --hash-style=both --build-id=sha1 -T $(targets:%=$(obj)/%.dbg): KBUILD_CFLAGS = $(KBUILD_CFLAGS_64) diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index c6257f625929..14a18ba5ff2c 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -585,6 +585,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) r = KVM_MAX_VCPUS; else if (sclp.has_esca && sclp.has_64bscao) r = KVM_S390_ESCA_CPU_SLOTS; + if (ext == KVM_CAP_NR_VCPUS) + r = min_t(unsigned int, num_online_cpus(), r); break; case KVM_CAP_S390_COW: r = MACHINE_HAS_ESOP; diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c index 872d772b73d2..2f9b78fa82a5 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -481,6 +481,34 @@ static void zpci_free_iomap(struct zpci_dev *zdev, int entry) spin_unlock(&zpci_iomap_lock); } +static void zpci_do_update_iomap_fh(struct zpci_dev *zdev, u32 fh) +{ + int bar, idx; + + spin_lock(&zpci_iomap_lock); + for (bar = 0; bar < PCI_STD_NUM_BARS; bar++) { + if (!zdev->bars[bar].size) + continue; + idx = zdev->bars[bar].map_idx; + if (!zpci_iomap_start[idx].count) + continue; + WRITE_ONCE(zpci_iomap_start[idx].fh, zdev->fh); + } + spin_unlock(&zpci_iomap_lock); +} + +void zpci_update_fh(struct zpci_dev *zdev, u32 fh) +{ + if (!fh || zdev->fh == fh) + return; + + zdev->fh = fh; + if (zpci_use_mio(zdev)) + return; + if (zdev->has_resources && zdev_enabled(zdev)) + zpci_do_update_iomap_fh(zdev, fh); +} + static struct resource *__alloc_res(struct zpci_dev *zdev, unsigned long start, unsigned long size, unsigned long flags) { @@ -668,7 +696,7 @@ int zpci_enable_device(struct zpci_dev *zdev) if (clp_enable_fh(zdev, &fh, ZPCI_NR_DMA_SPACES)) rc = -EIO; else - zdev->fh = fh; + zpci_update_fh(zdev, fh); return rc; } @@ -679,14 +707,14 @@ int zpci_disable_device(struct zpci_dev *zdev) cc = clp_disable_fh(zdev, &fh); if (!cc) { - zdev->fh = fh; + zpci_update_fh(zdev, fh); } else if (cc == CLP_RC_SETPCIFN_ALRDY) { pr_info("Disabling PCI function %08x had no effect as it was already disabled\n", zdev->fid); /* Function is already disabled - update handle */ rc = clp_refresh_fh(zdev->fid, &fh); if (!rc) { - zdev->fh = fh; + zpci_update_fh(zdev, fh); rc = -EINVAL; } } else { @@ -696,6 +724,65 @@ int zpci_disable_device(struct zpci_dev *zdev) } /** + * zpci_hot_reset_device - perform a reset of the given zPCI function + * @zdev: the slot which should be reset + * + * Performs a low level reset of the zPCI function. The reset is low level in + * the sense that the zPCI function can be reset without detaching it from the + * common PCI subsystem. The reset may be performed while under control of + * either DMA or IOMMU APIs in which case the existing DMA/IOMMU translation + * table is reinstated at the end of the reset. + * + * After the reset the functions internal state is reset to an initial state + * equivalent to its state during boot when first probing a driver. + * Consequently after reset the PCI function requires re-initialization via the + * common PCI code including re-enabling IRQs via pci_alloc_irq_vectors() + * and enabling the function via e.g.pci_enablde_device_flags().The caller + * must guard against concurrent reset attempts. + * + * In most cases this function should not be called directly but through + * pci_reset_function() or pci_reset_bus() which handle the save/restore and + * locking. + * + * Return: 0 on success and an error value otherwise + */ +int zpci_hot_reset_device(struct zpci_dev *zdev) +{ + int rc; + + zpci_dbg(3, "rst fid:%x, fh:%x\n", zdev->fid, zdev->fh); + if (zdev_enabled(zdev)) { + /* Disables device access, DMAs and IRQs (reset state) */ + rc = zpci_disable_device(zdev); + /* + * Due to a z/VM vs LPAR inconsistency in the error state the + * FH may indicate an enabled device but disable says the + * device is already disabled don't treat it as an error here. + */ + if (rc == -EINVAL) + rc = 0; + if (rc) + return rc; + } + + rc = zpci_enable_device(zdev); + if (rc) + return rc; + + if (zdev->dma_table) + rc = zpci_register_ioat(zdev, 0, zdev->start_dma, zdev->end_dma, + (u64)zdev->dma_table); + else + rc = zpci_dma_init_device(zdev); + if (rc) { + zpci_disable_device(zdev); + return rc; + } + + return 0; +} + +/** * zpci_create_device() - Create a new zpci_dev and add it to the zbus * @fid: Function ID of the device to be created * @fh: Current Function Handle of the device to be created @@ -776,7 +863,7 @@ int zpci_scan_configured_device(struct zpci_dev *zdev, u32 fh) { int rc; - zdev->fh = fh; + zpci_update_fh(zdev, fh); /* the PCI function will be scanned once function 0 appears */ if (!zdev->zbus->bus) return 0; @@ -903,6 +990,59 @@ int zpci_report_error(struct pci_dev *pdev, } EXPORT_SYMBOL(zpci_report_error); +/** + * zpci_clear_error_state() - Clears the zPCI error state of the device + * @zdev: The zdev for which the zPCI error state should be reset + * + * Clear the zPCI error state of the device. If clearing the zPCI error state + * fails the device is left in the error state. In this case it may make sense + * to call zpci_io_perm_failure() on the associated pdev if it exists. + * + * Returns: 0 on success, -EIO otherwise + */ +int zpci_clear_error_state(struct zpci_dev *zdev) +{ + u64 req = ZPCI_CREATE_REQ(zdev->fh, 0, ZPCI_MOD_FC_RESET_ERROR); + struct zpci_fib fib = {0}; + u8 status; + int cc; + + cc = zpci_mod_fc(req, &fib, &status); + if (cc) { + zpci_dbg(3, "ces fid:%x, cc:%d, status:%x\n", zdev->fid, cc, status); + return -EIO; + } + + return 0; +} + +/** + * zpci_reset_load_store_blocked() - Re-enables L/S from error state + * @zdev: The zdev for which to unblock load/store access + * + * Re-enables load/store access for a PCI function in the error state while + * keeping DMA blocked. In this state drivers can poke MMIO space to determine + * if error recovery is possible while catching any rogue DMA access from the + * device. + * + * Returns: 0 on success, -EIO otherwise + */ +int zpci_reset_load_store_blocked(struct zpci_dev *zdev) +{ + u64 req = ZPCI_CREATE_REQ(zdev->fh, 0, ZPCI_MOD_FC_RESET_BLOCK); + struct zpci_fib fib = {0}; + u8 status; + int cc; + + cc = zpci_mod_fc(req, &fib, &status); + if (cc) { + zpci_dbg(3, "rls fid:%x, cc:%d, status:%x\n", zdev->fid, cc, status); + return -EIO; + } + + return 0; +} + static int zpci_mem_init(void) { BUILD_BUG_ON(!is_power_of_2(__alignof__(struct zpci_fmb)) || diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c index 6a5bfa9dc1f2..2e3e5b278925 100644 --- a/arch/s390/pci/pci_event.c +++ b/arch/s390/pci/pci_event.c @@ -47,18 +47,223 @@ struct zpci_ccdf_avail { u16 pec; /* PCI event code */ } __packed; +static inline bool ers_result_indicates_abort(pci_ers_result_t ers_res) +{ + switch (ers_res) { + case PCI_ERS_RESULT_CAN_RECOVER: + case PCI_ERS_RESULT_RECOVERED: + case PCI_ERS_RESULT_NEED_RESET: + return false; + default: + return true; + } +} + +static bool is_passed_through(struct zpci_dev *zdev) +{ + return zdev->s390_domain; +} + +static bool is_driver_supported(struct pci_driver *driver) +{ + if (!driver || !driver->err_handler) + return false; + if (!driver->err_handler->error_detected) + return false; + if (!driver->err_handler->slot_reset) + return false; + if (!driver->err_handler->resume) + return false; + return true; +} + +static pci_ers_result_t zpci_event_notify_error_detected(struct pci_dev *pdev, + struct pci_driver *driver) +{ + pci_ers_result_t ers_res = PCI_ERS_RESULT_DISCONNECT; + + ers_res = driver->err_handler->error_detected(pdev, pdev->error_state); + if (ers_result_indicates_abort(ers_res)) + pr_info("%s: Automatic recovery failed after initial reporting\n", pci_name(pdev)); + else if (ers_res == PCI_ERS_RESULT_NEED_RESET) + pr_debug("%s: Driver needs reset to recover\n", pci_name(pdev)); + + return ers_res; +} + +static pci_ers_result_t zpci_event_do_error_state_clear(struct pci_dev *pdev, + struct pci_driver *driver) +{ + pci_ers_result_t ers_res = PCI_ERS_RESULT_DISCONNECT; + struct zpci_dev *zdev = to_zpci(pdev); + int rc; + + pr_info("%s: Unblocking device access for examination\n", pci_name(pdev)); + rc = zpci_reset_load_store_blocked(zdev); + if (rc) { + pr_err("%s: Unblocking device access failed\n", pci_name(pdev)); + /* Let's try a full reset instead */ + return PCI_ERS_RESULT_NEED_RESET; + } + + if (driver->err_handler->mmio_enabled) { + ers_res = driver->err_handler->mmio_enabled(pdev); + if (ers_result_indicates_abort(ers_res)) { + pr_info("%s: Automatic recovery failed after MMIO re-enable\n", + pci_name(pdev)); + return ers_res; + } else if (ers_res == PCI_ERS_RESULT_NEED_RESET) { + pr_debug("%s: Driver needs reset to recover\n", pci_name(pdev)); + return ers_res; + } + } + + pr_debug("%s: Unblocking DMA\n", pci_name(pdev)); + rc = zpci_clear_error_state(zdev); + if (!rc) { + pdev->error_state = pci_channel_io_normal; + } else { + pr_err("%s: Unblocking DMA failed\n", pci_name(pdev)); + /* Let's try a full reset instead */ + return PCI_ERS_RESULT_NEED_RESET; + } + + return ers_res; +} + +static pci_ers_result_t zpci_event_do_reset(struct pci_dev *pdev, + struct pci_driver *driver) +{ + pci_ers_result_t ers_res = PCI_ERS_RESULT_DISCONNECT; + + pr_info("%s: Initiating reset\n", pci_name(pdev)); + if (zpci_hot_reset_device(to_zpci(pdev))) { + pr_err("%s: The reset request failed\n", pci_name(pdev)); + return ers_res; + } + pdev->error_state = pci_channel_io_normal; + ers_res = driver->err_handler->slot_reset(pdev); + if (ers_result_indicates_abort(ers_res)) { + pr_info("%s: Automatic recovery failed after slot reset\n", pci_name(pdev)); + return ers_res; + } + + return ers_res; +} + +/* zpci_event_attempt_error_recovery - Try to recover the given PCI function + * @pdev: PCI function to recover currently in the error state + * + * We follow the scheme outlined in Documentation/PCI/pci-error-recovery.rst. + * With the simplification that recovery always happens per function + * and the platform determines which functions are affected for + * multi-function devices. + */ +static pci_ers_result_t zpci_event_attempt_error_recovery(struct pci_dev *pdev) +{ + pci_ers_result_t ers_res = PCI_ERS_RESULT_DISCONNECT; + struct pci_driver *driver; + + /* + * Ensure that the PCI function is not removed concurrently, no driver + * is unbound or probed and that userspace can't access its + * configuration space while we perform recovery. + */ + pci_dev_lock(pdev); + if (pdev->error_state == pci_channel_io_perm_failure) { + ers_res = PCI_ERS_RESULT_DISCONNECT; + goto out_unlock; + } + pdev->error_state = pci_channel_io_frozen; + + if (is_passed_through(to_zpci(pdev))) { + pr_info("%s: Cannot be recovered in the host because it is a pass-through device\n", + pci_name(pdev)); + goto out_unlock; + } + + driver = to_pci_driver(pdev->dev.driver); + if (!is_driver_supported(driver)) { + if (!driver) + pr_info("%s: Cannot be recovered because no driver is bound to the device\n", + pci_name(pdev)); + else + pr_info("%s: The %s driver bound to the device does not support error recovery\n", + pci_name(pdev), + driver->name); + goto out_unlock; + } + + ers_res = zpci_event_notify_error_detected(pdev, driver); + if (ers_result_indicates_abort(ers_res)) + goto out_unlock; + + if (ers_res == PCI_ERS_RESULT_CAN_RECOVER) { + ers_res = zpci_event_do_error_state_clear(pdev, driver); + if (ers_result_indicates_abort(ers_res)) + goto out_unlock; + } + + if (ers_res == PCI_ERS_RESULT_NEED_RESET) + ers_res = zpci_event_do_reset(pdev, driver); + + if (ers_res != PCI_ERS_RESULT_RECOVERED) { + pr_err("%s: Automatic recovery failed; operator intervention is required\n", + pci_name(pdev)); + goto out_unlock; + } + + pr_info("%s: The device is ready to resume operations\n", pci_name(pdev)); + if (driver->err_handler->resume) + driver->err_handler->resume(pdev); +out_unlock: + pci_dev_unlock(pdev); + + return ers_res; +} + +/* zpci_event_io_failure - Report PCI channel failure state to driver + * @pdev: PCI function for which to report + * @es: PCI channel failure state to report + */ +static void zpci_event_io_failure(struct pci_dev *pdev, pci_channel_state_t es) +{ + struct pci_driver *driver; + + pci_dev_lock(pdev); + pdev->error_state = es; + /** + * While vfio-pci's error_detected callback notifies user-space QEMU + * reacts to this by freezing the guest. In an s390 environment PCI + * errors are rarely fatal so this is overkill. Instead in the future + * we will inject the error event and let the guest recover the device + * itself. + */ + if (is_passed_through(to_zpci(pdev))) + goto out; + driver = to_pci_driver(pdev->dev.driver); + if (driver && driver->err_handler && driver->err_handler->error_detected) + driver->err_handler->error_detected(pdev, pdev->error_state); +out: + pci_dev_unlock(pdev); +} + static void __zpci_event_error(struct zpci_ccdf_err *ccdf) { struct zpci_dev *zdev = get_zdev_by_fid(ccdf->fid); struct pci_dev *pdev = NULL; + pci_ers_result_t ers_res; zpci_dbg(3, "err fid:%x, fh:%x, pec:%x\n", ccdf->fid, ccdf->fh, ccdf->pec); zpci_err("error CCDF:\n"); zpci_err_hex(ccdf, sizeof(*ccdf)); - if (zdev) - pdev = pci_get_slot(zdev->zbus->bus, zdev->devfn); + if (zdev) { + zpci_update_fh(zdev, ccdf->fh); + if (zdev->zbus->bus) + pdev = pci_get_slot(zdev->zbus->bus, zdev->devfn); + } pr_err("%s: Event 0x%x reports an error for PCI function 0x%x\n", pdev ? pci_name(pdev) : "n/a", ccdf->pec, ccdf->fid); @@ -66,7 +271,20 @@ static void __zpci_event_error(struct zpci_ccdf_err *ccdf) if (!pdev) return; - pdev->error_state = pci_channel_io_perm_failure; + switch (ccdf->pec) { + case 0x003a: /* Service Action or Error Recovery Successful */ + ers_res = zpci_event_attempt_error_recovery(pdev); + if (ers_res != PCI_ERS_RESULT_RECOVERED) + zpci_event_io_failure(pdev, pci_channel_io_perm_failure); + break; + default: + /* + * Mark as frozen not permanently failed because the device + * could be subsequently recovered by the platform. + */ + zpci_event_io_failure(pdev, pci_channel_io_frozen); + break; + } pci_dev_put(pdev); } @@ -78,7 +296,7 @@ void zpci_event_error(void *data) static void zpci_event_hard_deconfigured(struct zpci_dev *zdev, u32 fh) { - zdev->fh = fh; + zpci_update_fh(zdev, fh); /* Give the driver a hint that the function is * already unusable. */ @@ -121,7 +339,7 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf) if (!zdev) zpci_create_device(ccdf->fid, ccdf->fh, ZPCI_FN_STATE_STANDBY); else - zdev->fh = ccdf->fh; + zpci_update_fh(zdev, ccdf->fh); break; case 0x0303: /* Deconfiguration requested */ if (zdev) { @@ -130,7 +348,7 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf) */ if (zdev->state != ZPCI_FN_STATE_CONFIGURED) break; - zdev->fh = ccdf->fh; + zpci_update_fh(zdev, ccdf->fh); zpci_deconfigure_device(zdev); } break; diff --git a/arch/s390/pci/pci_insn.c b/arch/s390/pci/pci_insn.c index 2e43996159f0..28d863aaafea 100644 --- a/arch/s390/pci/pci_insn.c +++ b/arch/s390/pci/pci_insn.c @@ -163,7 +163,7 @@ static inline int zpci_load_fh(u64 *data, const volatile void __iomem *addr, unsigned long len) { struct zpci_iomap_entry *entry = &zpci_iomap_start[ZPCI_IDX(addr)]; - u64 req = ZPCI_CREATE_REQ(entry->fh, entry->bar, len); + u64 req = ZPCI_CREATE_REQ(READ_ONCE(entry->fh), entry->bar, len); return __zpci_load(data, req, ZPCI_OFFSET(addr)); } @@ -244,7 +244,7 @@ static inline int zpci_store_fh(const volatile void __iomem *addr, u64 data, unsigned long len) { struct zpci_iomap_entry *entry = &zpci_iomap_start[ZPCI_IDX(addr)]; - u64 req = ZPCI_CREATE_REQ(entry->fh, entry->bar, len); + u64 req = ZPCI_CREATE_REQ(READ_ONCE(entry->fh), entry->bar, len); return __zpci_store(data, req, ZPCI_OFFSET(addr)); } diff --git a/arch/s390/pci/pci_irq.c b/arch/s390/pci/pci_irq.c index 3823e159bf74..954bb7a83124 100644 --- a/arch/s390/pci/pci_irq.c +++ b/arch/s390/pci/pci_irq.c @@ -387,6 +387,15 @@ void arch_teardown_msi_irqs(struct pci_dev *pdev) airq_iv_free(zpci_ibv[0], zdev->msi_first_bit, zdev->msi_nr_irqs); } +void arch_restore_msi_irqs(struct pci_dev *pdev) +{ + struct zpci_dev *zdev = to_zpci(pdev); + + if (!zdev->irqs_registered) + zpci_set_irq(zdev); + default_restore_msi_irqs(pdev); +} + static struct airq_struct zpci_airq = { .handler = zpci_floating_irq_handler, .isc = PCI_ISC, diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index 6904f4bdbf00..70afb30e0b32 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -56,7 +56,6 @@ config SUPERH select HAVE_STACKPROTECTOR select HAVE_SYSCALL_TRACEPOINTS select IRQ_FORCED_THREADING - select MAY_HAVE_SPARSE_IRQ select MODULES_USE_ELF_RELA select NEED_SG_DMA_LENGTH select NO_DMA if !MMU && !DMA_COHERENT diff --git a/arch/sh/Kconfig.debug b/arch/sh/Kconfig.debug index 958f790273ab..10290e5c1f43 100644 --- a/arch/sh/Kconfig.debug +++ b/arch/sh/Kconfig.debug @@ -54,6 +54,7 @@ config DUMP_CODE config DWARF_UNWINDER bool "Enable the DWARF unwinder for stacktraces" + depends on DEBUG_KERNEL select FRAME_POINTER default n help diff --git a/arch/sh/boards/mach-landisk/irq.c b/arch/sh/boards/mach-landisk/irq.c index 29b8b1f85246..0b672b80c561 100644 --- a/arch/sh/boards/mach-landisk/irq.c +++ b/arch/sh/boards/mach-landisk/irq.c @@ -26,8 +26,8 @@ enum { PCI_INTD, /* PCI int D */ ATA, /* ATA */ FATA, /* CF */ - POWER, /* Power swtich */ - BUTTON, /* Button swtich */ + POWER, /* Power switch */ + BUTTON, /* Button switch */ }; /* Vectors for LANDISK */ diff --git a/arch/sh/boot/Makefile b/arch/sh/boot/Makefile index c081e7e2d6e7..5c123f5b2797 100644 --- a/arch/sh/boot/Makefile +++ b/arch/sh/boot/Makefile @@ -27,8 +27,8 @@ suffix-$(CONFIG_KERNEL_XZ) := xz suffix-$(CONFIG_KERNEL_LZO) := lzo targets := zImage vmlinux.srec romImage uImage uImage.srec uImage.gz \ - uImage.bz2 uImage.lzma uImage.xz uImage.lzo uImage.bin -extra-y += vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 vmlinux.bin.lzma \ + uImage.bz2 uImage.lzma uImage.xz uImage.lzo uImage.bin \ + vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 vmlinux.bin.lzma \ vmlinux.bin.xz vmlinux.bin.lzo subdir- := compressed romimage diff --git a/arch/sh/boot/compressed/.gitignore b/arch/sh/boot/compressed/.gitignore index 37aa53057369..cd16663bc7c8 100644 --- a/arch/sh/boot/compressed/.gitignore +++ b/arch/sh/boot/compressed/.gitignore @@ -1,7 +1,2 @@ # SPDX-License-Identifier: GPL-2.0-only -ashiftrt.S -ashldi3.c -ashlsi3.S -ashrsi3.S -lshrsi3.S vmlinux.bin.* diff --git a/arch/sh/boot/compressed/Makefile b/arch/sh/boot/compressed/Makefile index 589d2d8a573d..cf3174df7859 100644 --- a/arch/sh/boot/compressed/Makefile +++ b/arch/sh/boot/compressed/Makefile @@ -5,12 +5,18 @@ # create a compressed vmlinux image from the original vmlinux # -targets := vmlinux vmlinux.bin vmlinux.bin.gz \ - vmlinux.bin.bz2 vmlinux.bin.lzma \ - vmlinux.bin.xz vmlinux.bin.lzo \ - head_32.o misc.o piggy.o +OBJECTS := head_32.o misc.o cache.o piggy.o \ + ashiftrt.o ashldi3.o ashrsi3.o ashlsi3.o lshrsi3.o + +# These were previously generated files. When you are building the kernel +# with O=, make sure to remove the stale files in the output tree. Otherwise, +# the build system wrongly compiles the stale ones. +ifdef building_out_of_srctree +$(shell rm -f $(addprefix $(obj)/, ashiftrt.S ashldi3.c ashrsi3.S ashlsi3.S lshrsi3.S)) +endif -OBJECTS = $(obj)/head_32.o $(obj)/misc.o $(obj)/cache.o +targets := vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 \ + vmlinux.bin.lzma vmlinux.bin.xz vmlinux.bin.lzo $(OBJECTS) GCOV_PROFILE := n @@ -33,21 +39,9 @@ ccflags-remove-$(CONFIG_MCOUNT) += -pg LDFLAGS_vmlinux := --oformat $(ld-bfd) -Ttext $(IMAGE_OFFSET) -e startup \ -T $(obj)/../../kernel/vmlinux.lds -# -# Pull in the necessary libgcc bits from the in-kernel implementation. -# -lib1funcs-y := ashiftrt.S ashldi3.c ashrsi3.S ashlsi3.S lshrsi3.S -lib1funcs-obj := \ - $(addsuffix .o, $(basename $(addprefix $(obj)/, $(lib1funcs-y)))) - -lib1funcs-dir := $(srctree)/arch/$(SRCARCH)/lib - -KBUILD_CFLAGS += -I$(lib1funcs-dir) -DDISABLE_BRANCH_PROFILING - -$(addprefix $(obj)/,$(lib1funcs-y)): $(obj)/%: $(lib1funcs-dir)/% FORCE - $(call cmd,shipped) +KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING -$(obj)/vmlinux: $(OBJECTS) $(obj)/piggy.o $(lib1funcs-obj) FORCE +$(obj)/vmlinux: $(addprefix $(obj)/, $(OBJECTS)) FORCE $(call if_changed,ld) $(obj)/vmlinux.bin: vmlinux FORCE diff --git a/arch/sh/boot/compressed/ashiftrt.S b/arch/sh/boot/compressed/ashiftrt.S new file mode 100644 index 000000000000..0f3b291a3f4b --- /dev/null +++ b/arch/sh/boot/compressed/ashiftrt.S @@ -0,0 +1,2 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#include "../../lib/ashiftrt.S" diff --git a/arch/sh/boot/compressed/ashldi3.c b/arch/sh/boot/compressed/ashldi3.c new file mode 100644 index 000000000000..7cebd646df83 --- /dev/null +++ b/arch/sh/boot/compressed/ashldi3.c @@ -0,0 +1,2 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include "../../lib/ashldi3.c" diff --git a/arch/sh/boot/compressed/ashlsi3.S b/arch/sh/boot/compressed/ashlsi3.S new file mode 100644 index 000000000000..e354262b275f --- /dev/null +++ b/arch/sh/boot/compressed/ashlsi3.S @@ -0,0 +1,2 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#include "../../lib/ashlsi3.S" diff --git a/arch/sh/boot/compressed/ashrsi3.S b/arch/sh/boot/compressed/ashrsi3.S new file mode 100644 index 000000000000..e564be9a4dcd --- /dev/null +++ b/arch/sh/boot/compressed/ashrsi3.S @@ -0,0 +1,2 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#include "../../lib/ashrsi3.S" diff --git a/arch/sh/boot/compressed/lshrsi3.S b/arch/sh/boot/compressed/lshrsi3.S new file mode 100644 index 000000000000..5a8281b7e516 --- /dev/null +++ b/arch/sh/boot/compressed/lshrsi3.S @@ -0,0 +1,2 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#include "../../lib/lshrsi3.S" diff --git a/arch/sh/include/asm/cacheflush.h b/arch/sh/include/asm/cacheflush.h index c7a97f32432f..481a664287e2 100644 --- a/arch/sh/include/asm/cacheflush.h +++ b/arch/sh/include/asm/cacheflush.h @@ -43,7 +43,6 @@ extern void flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end); #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 void flush_dcache_page(struct page *page); -void flush_dcache_folio(struct folio *folio); extern void flush_icache_range(unsigned long start, unsigned long end); #define flush_icache_user_range flush_icache_range extern void flush_icache_page(struct vm_area_struct *vma, diff --git a/arch/sh/include/asm/checksum_32.h b/arch/sh/include/asm/checksum_32.h index 1a391e3a7659..a6501b856f3e 100644 --- a/arch/sh/include/asm/checksum_32.h +++ b/arch/sh/include/asm/checksum_32.h @@ -84,7 +84,8 @@ static inline __sum16 csum_fold(__wsum sum) */ static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl) { - unsigned int sum, __dummy0, __dummy1; + __wsum sum; + unsigned int __dummy0, __dummy1; __asm__ __volatile__( "mov.l @%1+, %0\n\t" @@ -197,6 +198,6 @@ static inline __wsum csum_and_copy_to_user(const void *src, { if (!access_ok(dst, len)) return 0; - return csum_partial_copy_generic((__force const void *)src, dst, len); + return csum_partial_copy_generic(src, (__force void *)dst, len); } #endif /* __ASM_SH_CHECKSUM_H */ diff --git a/arch/sh/include/asm/irq.h b/arch/sh/include/asm/irq.h index 839551ce398c..1c4923502fd4 100644 --- a/arch/sh/include/asm/irq.h +++ b/arch/sh/include/asm/irq.h @@ -6,17 +6,6 @@ #include <asm/machvec.h> /* - * Only legacy non-sparseirq platforms have to set a reasonably sane - * value here. sparseirq platforms allocate their irq_descs on the fly, - * so will expand automatically based on the number of registered IRQs. - */ -#ifdef CONFIG_SPARSE_IRQ -# define NR_IRQS 8 -#else -# define NR_IRQS 512 -#endif - -/* * This is a special IRQ number for indicating that no IRQ has been * triggered and to simply ignore the IRQ dispatch. This is a special * case that can happen with IRQ auto-distribution when multiple CPUs diff --git a/arch/sh/include/asm/sfp-machine.h b/arch/sh/include/asm/sfp-machine.h index cbc7cf8c97ce..2d2423478b71 100644 --- a/arch/sh/include/asm/sfp-machine.h +++ b/arch/sh/include/asm/sfp-machine.h @@ -13,6 +13,14 @@ #ifndef _SFP_MACHINE_H #define _SFP_MACHINE_H +#ifdef __BIG_ENDIAN__ +#define __BYTE_ORDER __BIG_ENDIAN +#define __LITTLE_ENDIAN 0 +#else +#define __BYTE_ORDER __LITTLE_ENDIAN +#define __BIG_ENDIAN 0 +#endif + #define _FP_W_TYPE_SIZE 32 #define _FP_W_TYPE unsigned long #define _FP_WS_TYPE signed long diff --git a/arch/sh/include/asm/uaccess.h b/arch/sh/include/asm/uaccess.h index 73f3b48d4a34..8867bb04b00e 100644 --- a/arch/sh/include/asm/uaccess.h +++ b/arch/sh/include/asm/uaccess.h @@ -68,7 +68,7 @@ struct __large_struct { unsigned long buf[100]; }; ({ \ long __gu_err = -EFAULT; \ unsigned long __gu_val = 0; \ - const __typeof__(*(ptr)) *__gu_addr = (ptr); \ + const __typeof__(*(ptr)) __user *__gu_addr = (ptr); \ if (likely(access_ok(__gu_addr, (size)))) \ __get_user_size(__gu_val, __gu_addr, (size), __gu_err); \ (x) = (__force __typeof__(*(ptr)))__gu_val; \ @@ -124,7 +124,7 @@ raw_copy_to_user(void __user *to, const void *from, unsigned long n) * Clear the area and return remaining number of bytes * (on failure. Usually it's 0.) */ -__kernel_size_t __clear_user(void *addr, __kernel_size_t size); +__kernel_size_t __clear_user(void __user *addr, __kernel_size_t size); #define clear_user(addr,n) \ ({ \ diff --git a/arch/sh/kernel/cpu/sh4a/smp-shx3.c b/arch/sh/kernel/cpu/sh4a/smp-shx3.c index f8a2bec0f260..1261dc7b84e8 100644 --- a/arch/sh/kernel/cpu/sh4a/smp-shx3.c +++ b/arch/sh/kernel/cpu/sh4a/smp-shx3.c @@ -73,8 +73,9 @@ static void shx3_prepare_cpus(unsigned int max_cpus) BUILD_BUG_ON(SMP_MSG_NR >= 8); for (i = 0; i < SMP_MSG_NR; i++) - request_irq(104 + i, ipi_interrupt_handler, - IRQF_PERCPU, "IPI", (void *)(long)i); + if (request_irq(104 + i, ipi_interrupt_handler, + IRQF_PERCPU, "IPI", (void *)(long)i)) + pr_err("Failed to request irq %d\n", i); for (i = 0; i < max_cpus; i++) set_cpu_present(i, true); diff --git a/arch/sh/kernel/crash_dump.c b/arch/sh/kernel/crash_dump.c index a9086127b16d..5b41b59698c1 100644 --- a/arch/sh/kernel/crash_dump.c +++ b/arch/sh/kernel/crash_dump.c @@ -26,7 +26,7 @@ ssize_t copy_oldmem_page(unsigned long pfn, char *buf, size_t csize, unsigned long offset, int userbuf) { - void *vaddr; + void __iomem *vaddr; if (!csize) return 0; @@ -34,7 +34,7 @@ ssize_t copy_oldmem_page(unsigned long pfn, char *buf, vaddr = ioremap(pfn << PAGE_SHIFT, PAGE_SIZE); if (userbuf) { - if (copy_to_user(buf, (vaddr + offset), csize)) { + if (copy_to_user((void __user *)buf, (vaddr + offset), csize)) { iounmap(vaddr); return -EFAULT; } diff --git a/arch/sh/kernel/syscalls/syscall.tbl b/arch/sh/kernel/syscalls/syscall.tbl index 208f131659c5..d9539d28bdaa 100644 --- a/arch/sh/kernel/syscalls/syscall.tbl +++ b/arch/sh/kernel/syscalls/syscall.tbl @@ -451,3 +451,4 @@ 446 common landlock_restrict_self sys_landlock_restrict_self # 447 reserved for memfd_secret 448 common process_mrelease sys_process_mrelease +449 common futex_waitv sys_futex_waitv diff --git a/arch/sh/kernel/traps_32.c b/arch/sh/kernel/traps_32.c index b62ad0ba2395..b3c715bc254b 100644 --- a/arch/sh/kernel/traps_32.c +++ b/arch/sh/kernel/traps_32.c @@ -490,7 +490,7 @@ asmlinkage void do_address_error(struct pt_regs *regs, inc_unaligned_user_access(); oldfs = force_uaccess_begin(); - if (copy_from_user(&instruction, (insn_size_t *)(regs->pc & ~1), + if (copy_from_user(&instruction, (insn_size_t __user *)(regs->pc & ~1), sizeof(instruction))) { force_uaccess_end(oldfs); goto uspace_segv; @@ -614,7 +614,7 @@ asmlinkage void do_reserved_inst(void) unsigned short inst = 0; int err; - get_user(inst, (unsigned short*)regs->pc); + get_user(inst, (unsigned short __user *)regs->pc); err = do_fpu_inst(inst, regs); if (!err) { @@ -699,9 +699,9 @@ asmlinkage void do_illegal_slot_inst(void) return; #ifdef CONFIG_SH_FPU_EMU - get_user(inst, (unsigned short *)regs->pc + 1); + get_user(inst, (unsigned short __user *)regs->pc + 1); if (!do_fpu_inst(inst, regs)) { - get_user(inst, (unsigned short *)regs->pc); + get_user(inst, (unsigned short __user *)regs->pc); if (!emulate_branch(inst, regs)) return; /* fault in branch.*/ diff --git a/arch/sh/math-emu/math.c b/arch/sh/math-emu/math.c index e8be0eca0444..cdaef6501d76 100644 --- a/arch/sh/math-emu/math.c +++ b/arch/sh/math-emu/math.c @@ -51,8 +51,8 @@ #define Rn (regs->regs[n]) #define Rm (regs->regs[m]) -#define WRITE(d,a) ({if(put_user(d, (typeof (d)*)a)) return -EFAULT;}) -#define READ(d,a) ({if(get_user(d, (typeof (d)*)a)) return -EFAULT;}) +#define MWRITE(d,a) ({if(put_user(d, (typeof (d) __user *)a)) return -EFAULT;}) +#define MREAD(d,a) ({if(get_user(d, (typeof (d) __user *)a)) return -EFAULT;}) #define PACK_S(r,f) FP_PACK_SP(&r,f) #define UNPACK_S(f,r) FP_UNPACK_SP(f,&r) @@ -157,11 +157,11 @@ fmov_idx_reg(struct sh_fpu_soft_struct *fregs, struct pt_regs *regs, int m, { if (FPSCR_SZ) { FMOV_EXT(n); - READ(FRn, Rm + R0 + 4); + MREAD(FRn, Rm + R0 + 4); n++; - READ(FRn, Rm + R0); + MREAD(FRn, Rm + R0); } else { - READ(FRn, Rm + R0); + MREAD(FRn, Rm + R0); } return 0; @@ -173,11 +173,11 @@ fmov_mem_reg(struct sh_fpu_soft_struct *fregs, struct pt_regs *regs, int m, { if (FPSCR_SZ) { FMOV_EXT(n); - READ(FRn, Rm + 4); + MREAD(FRn, Rm + 4); n++; - READ(FRn, Rm); + MREAD(FRn, Rm); } else { - READ(FRn, Rm); + MREAD(FRn, Rm); } return 0; @@ -189,12 +189,12 @@ fmov_inc_reg(struct sh_fpu_soft_struct *fregs, struct pt_regs *regs, int m, { if (FPSCR_SZ) { FMOV_EXT(n); - READ(FRn, Rm + 4); + MREAD(FRn, Rm + 4); n++; - READ(FRn, Rm); + MREAD(FRn, Rm); Rm += 8; } else { - READ(FRn, Rm); + MREAD(FRn, Rm); Rm += 4; } @@ -207,11 +207,11 @@ fmov_reg_idx(struct sh_fpu_soft_struct *fregs, struct pt_regs *regs, int m, { if (FPSCR_SZ) { FMOV_EXT(m); - WRITE(FRm, Rn + R0 + 4); + MWRITE(FRm, Rn + R0 + 4); m++; - WRITE(FRm, Rn + R0); + MWRITE(FRm, Rn + R0); } else { - WRITE(FRm, Rn + R0); + MWRITE(FRm, Rn + R0); } return 0; @@ -223,11 +223,11 @@ fmov_reg_mem(struct sh_fpu_soft_struct *fregs, struct pt_regs *regs, int m, { if (FPSCR_SZ) { FMOV_EXT(m); - WRITE(FRm, Rn + 4); + MWRITE(FRm, Rn + 4); m++; - WRITE(FRm, Rn); + MWRITE(FRm, Rn); } else { - WRITE(FRm, Rn); + MWRITE(FRm, Rn); } return 0; @@ -240,12 +240,12 @@ fmov_reg_dec(struct sh_fpu_soft_struct *fregs, struct pt_regs *regs, int m, if (FPSCR_SZ) { FMOV_EXT(m); Rn -= 8; - WRITE(FRm, Rn + 4); + MWRITE(FRm, Rn + 4); m++; - WRITE(FRm, Rn); + MWRITE(FRm, Rn); } else { Rn -= 4; - WRITE(FRm, Rn); + MWRITE(FRm, Rn); } return 0; @@ -445,11 +445,11 @@ id_sys(struct sh_fpu_soft_struct *fregs, struct pt_regs *regs, u16 code) case 0x4052: case 0x4062: Rn -= 4; - WRITE(*reg, Rn); + MWRITE(*reg, Rn); break; case 0x4056: case 0x4066: - READ(*reg, Rn); + MREAD(*reg, Rn); Rn += 4; break; default: @@ -468,109 +468,6 @@ static int fpu_emulate(u16 code, struct sh_fpu_soft_struct *fregs, struct pt_reg } /** - * denormal_to_double - Given denormalized float number, - * store double float - * - * @fpu: Pointer to sh_fpu_soft structure - * @n: Index to FP register - */ -static void denormal_to_double(struct sh_fpu_soft_struct *fpu, int n) -{ - unsigned long du, dl; - unsigned long x = fpu->fpul; - int exp = 1023 - 126; - - if (x != 0 && (x & 0x7f800000) == 0) { - du = (x & 0x80000000); - while ((x & 0x00800000) == 0) { - x <<= 1; - exp--; - } - x &= 0x007fffff; - du |= (exp << 20) | (x >> 3); - dl = x << 29; - - fpu->fp_regs[n] = du; - fpu->fp_regs[n+1] = dl; - } -} - -/** - * ieee_fpe_handler - Handle denormalized number exception - * - * @regs: Pointer to register structure - * - * Returns 1 when it's handled (should not cause exception). - */ -static int ieee_fpe_handler(struct pt_regs *regs) -{ - unsigned short insn = *(unsigned short *)regs->pc; - unsigned short finsn; - unsigned long nextpc; - int nib[4] = { - (insn >> 12) & 0xf, - (insn >> 8) & 0xf, - (insn >> 4) & 0xf, - insn & 0xf}; - - if (nib[0] == 0xb || - (nib[0] == 0x4 && nib[2] == 0x0 && nib[3] == 0xb)) /* bsr & jsr */ - regs->pr = regs->pc + 4; - - if (nib[0] == 0xa || nib[0] == 0xb) { /* bra & bsr */ - nextpc = regs->pc + 4 + ((short) ((insn & 0xfff) << 4) >> 3); - finsn = *(unsigned short *) (regs->pc + 2); - } else if (nib[0] == 0x8 && nib[1] == 0xd) { /* bt/s */ - if (regs->sr & 1) - nextpc = regs->pc + 4 + ((char) (insn & 0xff) << 1); - else - nextpc = regs->pc + 4; - finsn = *(unsigned short *) (regs->pc + 2); - } else if (nib[0] == 0x8 && nib[1] == 0xf) { /* bf/s */ - if (regs->sr & 1) - nextpc = regs->pc + 4; - else - nextpc = regs->pc + 4 + ((char) (insn & 0xff) << 1); - finsn = *(unsigned short *) (regs->pc + 2); - } else if (nib[0] == 0x4 && nib[3] == 0xb && - (nib[2] == 0x0 || nib[2] == 0x2)) { /* jmp & jsr */ - nextpc = regs->regs[nib[1]]; - finsn = *(unsigned short *) (regs->pc + 2); - } else if (nib[0] == 0x0 && nib[3] == 0x3 && - (nib[2] == 0x0 || nib[2] == 0x2)) { /* braf & bsrf */ - nextpc = regs->pc + 4 + regs->regs[nib[1]]; - finsn = *(unsigned short *) (regs->pc + 2); - } else if (insn == 0x000b) { /* rts */ - nextpc = regs->pr; - finsn = *(unsigned short *) (regs->pc + 2); - } else { - nextpc = regs->pc + 2; - finsn = insn; - } - - if ((finsn & 0xf1ff) == 0xf0ad) { /* fcnvsd */ - struct task_struct *tsk = current; - - if ((tsk->thread.xstate->softfpu.fpscr & (1 << 17))) { - /* FPU error */ - denormal_to_double (&tsk->thread.xstate->softfpu, - (finsn >> 8) & 0xf); - tsk->thread.xstate->softfpu.fpscr &= - ~(FPSCR_CAUSE_MASK | FPSCR_FLAG_MASK); - task_thread_info(tsk)->status |= TS_USEDFPU; - } else { - force_sig_fault(SIGFPE, FPE_FLTINV, - (void __user *)regs->pc); - } - - regs->pc = nextpc; - return 1; - } - - return 0; -} - -/** * fpu_init - Initialize FPU registers * @fpu: Pointer to software emulated FPU registers. */ diff --git a/arch/sh/mm/nommu.c b/arch/sh/mm/nommu.c index 8b4504413c5f..78c4b6e6d33b 100644 --- a/arch/sh/mm/nommu.c +++ b/arch/sh/mm/nommu.c @@ -28,9 +28,9 @@ __kernel_size_t __copy_user(void *to, const void *from, __kernel_size_t n) return 0; } -__kernel_size_t __clear_user(void *to, __kernel_size_t n) +__kernel_size_t __clear_user(void __user *to, __kernel_size_t n) { - memset(to, 0, n); + memset((__force void *)to, 0, n); return 0; } diff --git a/arch/sparc/kernel/signal_32.c b/arch/sparc/kernel/signal_32.c index cd677bc564a7..ffab16369bea 100644 --- a/arch/sparc/kernel/signal_32.c +++ b/arch/sparc/kernel/signal_32.c @@ -244,7 +244,7 @@ static int setup_frame(struct ksignal *ksig, struct pt_regs *regs, get_sigframe(ksig, regs, sigframe_size); if (invalid_frame_pointer(sf, sigframe_size)) { - force_fatal_sig(SIGILL); + force_exit_sig(SIGILL); return -EINVAL; } @@ -336,7 +336,7 @@ static int setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs, sf = (struct rt_signal_frame __user *) get_sigframe(ksig, regs, sigframe_size); if (invalid_frame_pointer(sf, sigframe_size)) { - force_fatal_sig(SIGILL); + force_exit_sig(SIGILL); return -EINVAL; } diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl index c37764dc764d..46adabcb1720 100644 --- a/arch/sparc/kernel/syscalls/syscall.tbl +++ b/arch/sparc/kernel/syscalls/syscall.tbl @@ -494,3 +494,4 @@ 446 common landlock_restrict_self sys_landlock_restrict_self # 447 reserved for memfd_secret 448 common process_mrelease sys_process_mrelease +449 common futex_waitv sys_futex_waitv diff --git a/arch/sparc/kernel/windows.c b/arch/sparc/kernel/windows.c index bbbd40cc6b28..8f20862ccc83 100644 --- a/arch/sparc/kernel/windows.c +++ b/arch/sparc/kernel/windows.c @@ -122,7 +122,7 @@ void try_to_clear_window_buffer(struct pt_regs *regs, int who) if ((sp & 7) || copy_to_user((char __user *) sp, &tp->reg_window[window], sizeof(struct reg_window32))) { - force_fatal_sig(SIGILL); + force_exit_sig(SIGILL); return; } } diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 95dd1ee01546..7399327d1eff 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -193,7 +193,7 @@ config X86 select HAVE_DYNAMIC_FTRACE_WITH_ARGS if X86_64 select HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS select HAVE_SAMPLE_FTRACE_DIRECT if X86_64 - select HAVE_SAMPLE_FTRACE_MULTI_DIRECT if X86_64 + select HAVE_SAMPLE_FTRACE_DIRECT_MULTI if X86_64 select HAVE_EBPF_JIT select HAVE_EFFICIENT_UNALIGNED_ACCESS select HAVE_EISA diff --git a/arch/x86/entry/vsyscall/vsyscall_64.c b/arch/x86/entry/vsyscall/vsyscall_64.c index 0b6b277ee050..fd2ee9408e91 100644 --- a/arch/x86/entry/vsyscall/vsyscall_64.c +++ b/arch/x86/entry/vsyscall/vsyscall_64.c @@ -226,7 +226,7 @@ bool emulate_vsyscall(unsigned long error_code, if ((!tmp && regs->orig_ax != syscall_nr) || regs->ip != address) { warn_bad_vsyscall(KERN_DEBUG, regs, "seccomp tried to change syscall nr or ip"); - force_fatal_sig(SIGSYS); + force_exit_sig(SIGSYS); return true; } regs->orig_ax = -1; diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 603964408d2d..ec6444f2c9dc 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -2211,7 +2211,6 @@ intel_pmu_snapshot_branch_stack(struct perf_branch_entry *entries, unsigned int /* must not have branches... */ local_irq_save(flags); __intel_pmu_disable_all(false); /* we don't care about BTS */ - __intel_pmu_pebs_disable_all(); __intel_pmu_lbr_disable(); /* ... until here */ return __intel_pmu_snapshot_branch_stack(entries, cnt, flags); @@ -2225,7 +2224,6 @@ intel_pmu_snapshot_arch_branch_stack(struct perf_branch_entry *entries, unsigned /* must not have branches... */ local_irq_save(flags); __intel_pmu_disable_all(false); /* we don't care about BTS */ - __intel_pmu_pebs_disable_all(); __intel_pmu_arch_lbr_disable(); /* ... until here */ return __intel_pmu_snapshot_branch_stack(entries, cnt, flags); @@ -3048,8 +3046,10 @@ intel_vlbr_constraints(struct perf_event *event) { struct event_constraint *c = &vlbr_constraint; - if (unlikely(constraint_match(c, event->hw.config))) + if (unlikely(constraint_match(c, event->hw.config))) { + event->hw.flags |= c->flags; return c; + } return NULL; } diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c index 6b72e9b55c69..8043213b75a5 100644 --- a/arch/x86/events/intel/lbr.c +++ b/arch/x86/events/intel/lbr.c @@ -265,6 +265,8 @@ void intel_pmu_lbr_reset(void) cpuc->last_task_ctx = NULL; cpuc->last_log_id = 0; + if (!static_cpu_has(X86_FEATURE_ARCH_LBR) && cpuc->lbr_select) + wrmsrl(MSR_LBR_SELECT, 0); } /* diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index eb2c6cea9d0d..3660f698fb2a 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -3608,6 +3608,9 @@ static int skx_cha_hw_config(struct intel_uncore_box *box, struct perf_event *ev struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; struct extra_reg *er; int idx = 0; + /* Any of the CHA events may be filtered by Thread/Core-ID.*/ + if (event->hw.config & SNBEP_CBO_PMON_CTL_TID_EN) + idx = SKX_CHA_MSR_PMON_BOX_FILTER_TID; for (er = skx_uncore_cha_extra_regs; er->msr; er++) { if (er->event != (event->hw.config & er->config_mask)) @@ -3675,6 +3678,7 @@ static struct event_constraint skx_uncore_iio_constraints[] = { UNCORE_EVENT_CONSTRAINT(0xc0, 0xc), UNCORE_EVENT_CONSTRAINT(0xc5, 0xc), UNCORE_EVENT_CONSTRAINT(0xd4, 0xc), + UNCORE_EVENT_CONSTRAINT(0xd5, 0xc), EVENT_CONSTRAINT_END }; @@ -4525,6 +4529,13 @@ static void snr_iio_cleanup_mapping(struct intel_uncore_type *type) pmu_iio_cleanup_mapping(type, &snr_iio_mapping_group); } +static struct event_constraint snr_uncore_iio_constraints[] = { + UNCORE_EVENT_CONSTRAINT(0x83, 0x3), + UNCORE_EVENT_CONSTRAINT(0xc0, 0xc), + UNCORE_EVENT_CONSTRAINT(0xd5, 0xc), + EVENT_CONSTRAINT_END +}; + static struct intel_uncore_type snr_uncore_iio = { .name = "iio", .num_counters = 4, @@ -4536,6 +4547,7 @@ static struct intel_uncore_type snr_uncore_iio = { .event_mask_ext = SNR_IIO_PMON_RAW_EVENT_MASK_EXT, .box_ctl = SNR_IIO_MSR_PMON_BOX_CTL, .msr_offset = SNR_IIO_MSR_OFFSET, + .constraints = snr_uncore_iio_constraints, .ops = &ivbep_uncore_msr_ops, .format_group = &snr_uncore_iio_format_group, .attr_update = snr_iio_attr_update, diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index 24f4a06ac46a..96eb7db31c8e 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -177,6 +177,9 @@ void set_hv_tscchange_cb(void (*cb)(void)) return; } + if (!hv_vp_index) + return; + hv_reenlightenment_cb = cb; /* Make sure callback is registered before we write to MSRs */ @@ -383,20 +386,13 @@ static void __init hv_get_partition_id(void) */ void __init hyperv_init(void) { - u64 guest_id, required_msrs; + u64 guest_id; union hv_x64_msr_hypercall_contents hypercall_msr; int cpuhp; if (x86_hyper_type != X86_HYPER_MS_HYPERV) return; - /* Absolutely required MSRs */ - required_msrs = HV_MSR_HYPERCALL_AVAILABLE | - HV_MSR_VP_INDEX_AVAILABLE; - - if ((ms_hyperv.features & required_msrs) != required_msrs) - return; - if (hv_common_init()) return; diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h index 6053674f9132..c2767a6a387e 100644 --- a/arch/x86/include/asm/fpu/api.h +++ b/arch/x86/include/asm/fpu/api.h @@ -102,12 +102,6 @@ extern void switch_fpu_return(void); */ extern int cpu_has_xfeatures(u64 xfeatures_mask, const char **feature_name); -/* - * Tasks that are not using SVA have mm->pasid set to zero to note that they - * will not have the valid bit set in MSR_IA32_PASID while they are running. - */ -#define PASID_DISABLED 0 - /* Trap handling */ extern int fpu__exception_code(struct fpu *fpu, int trap_nr); extern void fpu_sync_fpstate(struct fpu *fpu); diff --git a/arch/x86/include/asm/fpu/xcr.h b/arch/x86/include/asm/fpu/xcr.h index 79f95d3787e2..9656a5bc6fea 100644 --- a/arch/x86/include/asm/fpu/xcr.h +++ b/arch/x86/include/asm/fpu/xcr.h @@ -3,6 +3,7 @@ #define _ASM_X86_FPU_XCR_H #define XCR_XFEATURE_ENABLED_MASK 0x00000000 +#define XCR_XFEATURE_IN_USE_MASK 0x00000001 static inline u64 xgetbv(u32 index) { @@ -20,4 +21,15 @@ static inline void xsetbv(u32 index, u64 value) asm volatile("xsetbv" :: "a" (eax), "d" (edx), "c" (index)); } +/* + * Return a mask of xfeatures which are currently being tracked + * by the processor as being in the initial configuration. + * + * Callers should check X86_FEATURE_XGETBV1. + */ +static inline u64 xfeatures_in_use(void) +{ + return xgetbv(XCR_XFEATURE_IN_USE_MASK); +} + #endif /* _ASM_X86_FPU_XCR_H */ diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h index 0f8b90ab18c9..cd3dd170e23a 100644 --- a/arch/x86/include/asm/fpu/xstate.h +++ b/arch/x86/include/asm/fpu/xstate.h @@ -92,6 +92,13 @@ #define XFEATURE_MASK_FPSTATE (XFEATURE_MASK_USER_RESTORE | \ XFEATURE_MASK_SUPERVISOR_SUPPORTED) +/* + * Features in this mask have space allocated in the signal frame, but may not + * have that space initialized when the feature is in its init state. + */ +#define XFEATURE_MASK_SIGFRAME_INITOPT (XFEATURE_MASK_XTILE | \ + XFEATURE_MASK_USER_DYNAMIC) + extern u64 xstate_fx_sw_bytes[USER_XSTATE_FX_SW_WORDS]; extern void __init update_regset_xstate_info(unsigned int size, diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h index 27158436f322..5a0bcf8b78d7 100644 --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -108,6 +108,8 @@ #define INTEL_FAM6_ALDERLAKE 0x97 /* Golden Cove / Gracemont */ #define INTEL_FAM6_ALDERLAKE_L 0x9A /* Golden Cove / Gracemont */ +#define INTEL_FAM6_RAPTOR_LAKE 0xB7 + /* "Small Core" Processors (Atom) */ #define INTEL_FAM6_ATOM_BONNELL 0x1C /* Diamondville, Pineview */ diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 2acf37cc1991..6ac61f85e07b 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -38,7 +38,6 @@ #define __KVM_HAVE_ARCH_VCPU_DEBUGFS #define KVM_MAX_VCPUS 1024 -#define KVM_SOFT_MAX_VCPUS 710 /* * In x86, the VCPU ID corresponds to the APIC ID, and APIC IDs @@ -364,6 +363,7 @@ union kvm_mmu_extended_role { unsigned int cr4_smap:1; unsigned int cr4_smep:1; unsigned int cr4_la57:1; + unsigned int efer_lma:1; }; }; @@ -725,6 +725,7 @@ struct kvm_vcpu_arch { int cpuid_nent; struct kvm_cpuid_entry2 *cpuid_entries; + u32 kvm_cpuid_base; u64 reserved_gpa_bits; int maxphyaddr; @@ -748,7 +749,7 @@ struct kvm_vcpu_arch { u8 preempted; u64 msr_val; u64 last_steal; - struct gfn_to_pfn_cache cache; + struct gfn_to_hva_cache cache; } st; u64 l1_tsc_offset; @@ -1034,6 +1035,7 @@ struct kvm_x86_msr_filter { #define APICV_INHIBIT_REASON_IRQWIN 3 #define APICV_INHIBIT_REASON_PIT_REINJ 4 #define APICV_INHIBIT_REASON_X2APIC 5 +#define APICV_INHIBIT_REASON_BLOCKIRQ 6 struct kvm_arch { unsigned long n_used_mmu_pages; @@ -1476,6 +1478,7 @@ struct kvm_x86_ops { int (*mem_enc_reg_region)(struct kvm *kvm, struct kvm_enc_region *argp); int (*mem_enc_unreg_region)(struct kvm *kvm, struct kvm_enc_region *argp); int (*vm_copy_enc_context_from)(struct kvm *kvm, unsigned int source_fd); + int (*vm_move_enc_context_from)(struct kvm *kvm, unsigned int source_fd); int (*get_msr_feature)(struct kvm_msr_entry *entry); diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h index 69299878b200..56935ebb1dfe 100644 --- a/arch/x86/include/asm/kvm_para.h +++ b/arch/x86/include/asm/kvm_para.h @@ -83,6 +83,18 @@ static inline long kvm_hypercall4(unsigned int nr, unsigned long p1, return ret; } +static inline long kvm_sev_hypercall3(unsigned int nr, unsigned long p1, + unsigned long p2, unsigned long p3) +{ + long ret; + + asm volatile("vmmcall" + : "=a"(ret) + : "a"(nr), "b"(p1), "c"(p2), "d"(p3) + : "memory"); + return ret; +} + #ifdef CONFIG_KVM_GUEST void kvmclock_init(void); void kvmclock_disable(void); diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h index 2d4f5c17d79c..e2c6f433ed10 100644 --- a/arch/x86/include/asm/mem_encrypt.h +++ b/arch/x86/include/asm/mem_encrypt.h @@ -44,6 +44,8 @@ void __init sme_enable(struct boot_params *bp); int __init early_set_memory_decrypted(unsigned long vaddr, unsigned long size); int __init early_set_memory_encrypted(unsigned long vaddr, unsigned long size); +void __init early_set_mem_enc_dec_hypercall(unsigned long vaddr, int npages, + bool enc); void __init mem_encrypt_free_decrypted_mem(void); @@ -78,6 +80,8 @@ static inline int __init early_set_memory_decrypted(unsigned long vaddr, unsigned long size) { return 0; } static inline int __init early_set_memory_encrypted(unsigned long vaddr, unsigned long size) { return 0; } +static inline void __init +early_set_mem_enc_dec_hypercall(unsigned long vaddr, int npages, bool enc) {} static inline void mem_encrypt_free_decrypted_mem(void) { } diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index cebec95a7124..21c4a694ca11 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -97,6 +97,12 @@ static inline void paravirt_arch_exit_mmap(struct mm_struct *mm) PVOP_VCALL1(mmu.exit_mmap, mm); } +static inline void notify_page_enc_status_changed(unsigned long pfn, + int npages, bool enc) +{ + PVOP_VCALL3(mmu.notify_page_enc_status_changed, pfn, npages, enc); +} + #ifdef CONFIG_PARAVIRT_XXL static inline void load_sp0(unsigned long sp0) { diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index fc1151e77569..a69012e1903f 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -168,6 +168,7 @@ struct pv_mmu_ops { /* Hook for intercepting the destruction of an mm_struct. */ void (*exit_mmap)(struct mm_struct *mm); + void (*notify_page_enc_status_changed)(unsigned long pfn, int npages, bool enc); #ifdef CONFIG_PARAVIRT_XXL struct paravirt_callee_save read_cr2; diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 191878a65c61..355d38c0cf60 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -806,11 +806,14 @@ static inline u32 amd_get_nodes_per_socket(void) { return 0; } static inline u32 amd_get_highest_perf(void) { return 0; } #endif +#define for_each_possible_hypervisor_cpuid_base(function) \ + for (function = 0x40000000; function < 0x40010000; function += 0x100) + static inline uint32_t hypervisor_cpuid_base(const char *sig, uint32_t leaves) { uint32_t base, eax, signature[3]; - for (base = 0x40000000; base < 0x40010000; base += 0x100) { + for_each_possible_hypervisor_cpuid_base(base) { cpuid(base, &eax, &signature[0], &signature[1], &signature[2]); if (!memcmp(sig, signature, 12) && diff --git a/arch/x86/include/asm/set_memory.h b/arch/x86/include/asm/set_memory.h index 43fa081a1adb..872617542bbc 100644 --- a/arch/x86/include/asm/set_memory.h +++ b/arch/x86/include/asm/set_memory.h @@ -83,6 +83,7 @@ int set_pages_rw(struct page *page, int numpages); int set_direct_map_invalid_noflush(struct page *page); int set_direct_map_default_noflush(struct page *page); bool kernel_page_present(struct page *page); +void notify_range_enc_status_changed(unsigned long vaddr, int npages, bool enc); extern int kernel_set_to_readonly; diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h index 08b0e90623ad..81a0211a372d 100644 --- a/arch/x86/include/asm/smp.h +++ b/arch/x86/include/asm/smp.h @@ -126,6 +126,7 @@ static inline void arch_send_call_function_ipi_mask(const struct cpumask *mask) void cpu_disable_common(void); void native_smp_prepare_boot_cpu(void); +void smp_prepare_cpus_common(void); void native_smp_prepare_cpus(unsigned int max_cpus); void calculate_max_logical_packages(void); void native_smp_cpus_done(unsigned int max_cpus); diff --git a/arch/x86/include/asm/static_call.h b/arch/x86/include/asm/static_call.h index cbb67b6030f9..39ebe0511869 100644 --- a/arch/x86/include/asm/static_call.h +++ b/arch/x86/include/asm/static_call.h @@ -27,6 +27,7 @@ ".globl " STATIC_CALL_TRAMP_STR(name) " \n" \ STATIC_CALL_TRAMP_STR(name) ": \n" \ insns " \n" \ + ".byte 0x53, 0x43, 0x54 \n" \ ".type " STATIC_CALL_TRAMP_STR(name) ", @function \n" \ ".size " STATIC_CALL_TRAMP_STR(name) ", . - " STATIC_CALL_TRAMP_STR(name) " \n" \ ".popsection \n") diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h index 0575f5863b7f..e5e0fe10c692 100644 --- a/arch/x86/include/asm/xen/hypercall.h +++ b/arch/x86/include/asm/xen/hypercall.h @@ -281,13 +281,13 @@ HYPERVISOR_callback_op(int cmd, void *arg) return _hypercall2(int, callback_op, cmd, arg); } -static inline int +static __always_inline int HYPERVISOR_set_debugreg(int reg, unsigned long value) { return _hypercall2(int, set_debugreg, reg, value); } -static inline unsigned long +static __always_inline unsigned long HYPERVISOR_get_debugreg(int reg) { return _hypercall1(unsigned long, get_debugreg, reg); diff --git a/arch/x86/include/asm/xen/hypervisor.h b/arch/x86/include/asm/xen/hypervisor.h index 4957f59deb40..5adab895127e 100644 --- a/arch/x86/include/asm/xen/hypervisor.h +++ b/arch/x86/include/asm/xen/hypervisor.h @@ -64,6 +64,7 @@ void xen_arch_unregister_cpu(int num); #ifdef CONFIG_PVH void __init xen_pvh_init(struct boot_params *boot_params); +void __init mem_map_via_hcall(struct boot_params *boot_params_p); #endif #endif /* _ASM_X86_XEN_HYPERVISOR_H */ diff --git a/arch/x86/include/uapi/asm/kvm_para.h b/arch/x86/include/uapi/asm/kvm_para.h index 5146bbab84d4..6e64b27b2c1e 100644 --- a/arch/x86/include/uapi/asm/kvm_para.h +++ b/arch/x86/include/uapi/asm/kvm_para.h @@ -8,6 +8,7 @@ * should be used to determine that a VM is running under KVM. */ #define KVM_CPUID_SIGNATURE 0x40000000 +#define KVM_SIGNATURE "KVMKVMKVM\0\0\0" /* This CPUID returns two feature bitmaps in eax, edx. Before enabling * a particular paravirtualization, the appropriate feature bit should diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c index cb2fdd130aae..c881bcafba7d 100644 --- a/arch/x86/kernel/cpu/cpuid-deps.c +++ b/arch/x86/kernel/cpu/cpuid-deps.c @@ -76,6 +76,7 @@ static const struct cpuid_dep cpuid_deps[] = { { X86_FEATURE_SGX1, X86_FEATURE_SGX }, { X86_FEATURE_SGX2, X86_FEATURE_SGX1 }, { X86_FEATURE_XFD, X86_FEATURE_XSAVES }, + { X86_FEATURE_XFD, X86_FEATURE_XGETBV1 }, { X86_FEATURE_AMX_TILE, X86_FEATURE_XFD }, {} }; diff --git a/arch/x86/kernel/cpu/mce/intel.c b/arch/x86/kernel/cpu/mce/intel.c index acfd5d9f93c6..bb9a46a804bf 100644 --- a/arch/x86/kernel/cpu/mce/intel.c +++ b/arch/x86/kernel/cpu/mce/intel.c @@ -547,12 +547,13 @@ bool intel_filter_mce(struct mce *m) { struct cpuinfo_x86 *c = &boot_cpu_data; - /* MCE errata HSD131, HSM142, HSW131, BDM48, and HSM142 */ + /* MCE errata HSD131, HSM142, HSW131, BDM48, HSM142 and SKX37 */ if ((c->x86 == 6) && ((c->x86_model == INTEL_FAM6_HASWELL) || (c->x86_model == INTEL_FAM6_HASWELL_L) || (c->x86_model == INTEL_FAM6_BROADWELL) || - (c->x86_model == INTEL_FAM6_HASWELL_G)) && + (c->x86_model == INTEL_FAM6_HASWELL_G) || + (c->x86_model == INTEL_FAM6_SKYLAKE_X)) && (m->bank == 0) && ((m->status & 0xa0000000ffffffff) == 0x80000000000f0005)) return true; diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 4794b716ec79..ff55df60228f 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -163,12 +163,22 @@ static uint32_t __init ms_hyperv_platform(void) cpuid(HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS, &eax, &hyp_signature[0], &hyp_signature[1], &hyp_signature[2]); - if (eax >= HYPERV_CPUID_MIN && - eax <= HYPERV_CPUID_MAX && - !memcmp("Microsoft Hv", hyp_signature, 12)) - return HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS; + if (eax < HYPERV_CPUID_MIN || eax > HYPERV_CPUID_MAX || + memcmp("Microsoft Hv", hyp_signature, 12)) + return 0; - return 0; + /* HYPERCALL and VP_INDEX MSRs are mandatory for all features. */ + eax = cpuid_eax(HYPERV_CPUID_FEATURES); + if (!(eax & HV_MSR_HYPERCALL_AVAILABLE)) { + pr_warn("x86/hyperv: HYPERCALL MSR not available.\n"); + return 0; + } + if (!(eax & HV_MSR_VP_INDEX_AVAILABLE)) { + pr_warn("x86/hyperv: VP_INDEX MSR not available.\n"); + return 0; + } + + return HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS; } static unsigned char hv_get_nmi_reason(void) diff --git a/arch/x86/kernel/cpu/sgx/main.c b/arch/x86/kernel/cpu/sgx/main.c index 63d3de02bbcc..8471a8b9b48e 100644 --- a/arch/x86/kernel/cpu/sgx/main.c +++ b/arch/x86/kernel/cpu/sgx/main.c @@ -28,8 +28,7 @@ static DECLARE_WAIT_QUEUE_HEAD(ksgxd_waitq); static LIST_HEAD(sgx_active_page_list); static DEFINE_SPINLOCK(sgx_reclaimer_lock); -/* The free page list lock protected variables prepend the lock. */ -static unsigned long sgx_nr_free_pages; +static atomic_long_t sgx_nr_free_pages = ATOMIC_LONG_INIT(0); /* Nodes with one or more EPC sections. */ static nodemask_t sgx_numa_mask; @@ -403,14 +402,15 @@ skip: spin_lock(&node->lock); list_add_tail(&epc_page->list, &node->free_page_list); - sgx_nr_free_pages++; spin_unlock(&node->lock); + atomic_long_inc(&sgx_nr_free_pages); } } static bool sgx_should_reclaim(unsigned long watermark) { - return sgx_nr_free_pages < watermark && !list_empty(&sgx_active_page_list); + return atomic_long_read(&sgx_nr_free_pages) < watermark && + !list_empty(&sgx_active_page_list); } static int ksgxd(void *p) @@ -471,9 +471,9 @@ static struct sgx_epc_page *__sgx_alloc_epc_page_from_node(int nid) page = list_first_entry(&node->free_page_list, struct sgx_epc_page, list); list_del_init(&page->list); - sgx_nr_free_pages--; spin_unlock(&node->lock); + atomic_long_dec(&sgx_nr_free_pages); return page; } @@ -625,9 +625,9 @@ void sgx_free_epc_page(struct sgx_epc_page *page) spin_lock(&node->lock); list_add_tail(&page->list, &node->free_page_list); - sgx_nr_free_pages++; spin_unlock(&node->lock); + atomic_long_inc(&sgx_nr_free_pages); } static bool __init sgx_setup_epc_section(u64 phys_addr, u64 size, diff --git a/arch/x86/kernel/fpu/xstate.h b/arch/x86/kernel/fpu/xstate.h index e18210dff88c..86ea7c0fa2f6 100644 --- a/arch/x86/kernel/fpu/xstate.h +++ b/arch/x86/kernel/fpu/xstate.h @@ -4,6 +4,7 @@ #include <asm/cpufeature.h> #include <asm/fpu/xstate.h> +#include <asm/fpu/xcr.h> #ifdef CONFIG_X86_64 DECLARE_PER_CPU(u64, xfd_state); @@ -199,6 +200,32 @@ static inline void os_xrstor_supervisor(struct fpstate *fpstate) } /* + * XSAVE itself always writes all requested xfeatures. Removing features + * from the request bitmap reduces the features which are written. + * Generate a mask of features which must be written to a sigframe. The + * unset features can be optimized away and not written. + * + * This optimization is user-visible. Only use for states where + * uninitialized sigframe contents are tolerable, like dynamic features. + * + * Users of buffers produced with this optimization must check XSTATE_BV + * to determine which features have been optimized out. + */ +static inline u64 xfeatures_need_sigframe_write(void) +{ + u64 xfeaures_to_write; + + /* In-use features must be written: */ + xfeaures_to_write = xfeatures_in_use(); + + /* Also write all non-optimizable sigframe features: */ + xfeaures_to_write |= XFEATURE_MASK_USER_SUPPORTED & + ~XFEATURE_MASK_SIGFRAME_INITOPT; + + return xfeaures_to_write; +} + +/* * Save xstate to user space xsave area. * * We don't use modified optimization because xrstor/xrstors might track @@ -220,10 +247,16 @@ static inline int xsave_to_user_sigframe(struct xregs_state __user *buf) */ struct fpstate *fpstate = current->thread.fpu.fpstate; u64 mask = fpstate->user_xfeatures; - u32 lmask = mask; - u32 hmask = mask >> 32; + u32 lmask; + u32 hmask; int err; + /* Optimize away writing unnecessary xfeatures: */ + if (fpu_state_size_dynamic()) + mask &= xfeatures_need_sigframe_write(); + + lmask = mask; + hmask = mask >> 32; xfd_validate_state(fpstate, mask, false); stac(); diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 8863d1941f1b..59abbdad7729 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -28,6 +28,7 @@ #include <linux/swait.h> #include <linux/syscore_ops.h> #include <linux/cc_platform.h> +#include <linux/efi.h> #include <asm/timer.h> #include <asm/cpu.h> #include <asm/traps.h> @@ -41,6 +42,7 @@ #include <asm/ptrace.h> #include <asm/reboot.h> #include <asm/svm.h> +#include <asm/e820/api.h> DEFINE_STATIC_KEY_FALSE(kvm_async_pf_enabled); @@ -434,6 +436,8 @@ static void kvm_guest_cpu_offline(bool shutdown) kvm_disable_steal_time(); if (kvm_para_has_feature(KVM_FEATURE_PV_EOI)) wrmsrl(MSR_KVM_PV_EOI_EN, 0); + if (kvm_para_has_feature(KVM_FEATURE_MIGRATION_CONTROL)) + wrmsrl(MSR_KVM_MIGRATION_CONTROL, 0); kvm_pv_disable_apf(); if (!shutdown) apf_task_wake_all(); @@ -548,6 +552,55 @@ static void kvm_send_ipi_mask_allbutself(const struct cpumask *mask, int vector) __send_ipi_mask(local_mask, vector); } +static int __init setup_efi_kvm_sev_migration(void) +{ + efi_char16_t efi_sev_live_migration_enabled[] = L"SevLiveMigrationEnabled"; + efi_guid_t efi_variable_guid = AMD_SEV_MEM_ENCRYPT_GUID; + efi_status_t status; + unsigned long size; + bool enabled; + + if (!cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT) || + !kvm_para_has_feature(KVM_FEATURE_MIGRATION_CONTROL)) + return 0; + + if (!efi_enabled(EFI_BOOT)) + return 0; + + if (!efi_enabled(EFI_RUNTIME_SERVICES)) { + pr_info("%s : EFI runtime services are not enabled\n", __func__); + return 0; + } + + size = sizeof(enabled); + + /* Get variable contents into buffer */ + status = efi.get_variable(efi_sev_live_migration_enabled, + &efi_variable_guid, NULL, &size, &enabled); + + if (status == EFI_NOT_FOUND) { + pr_info("%s : EFI live migration variable not found\n", __func__); + return 0; + } + + if (status != EFI_SUCCESS) { + pr_info("%s : EFI variable retrieval failed\n", __func__); + return 0; + } + + if (enabled == 0) { + pr_info("%s: live migration disabled in EFI\n", __func__); + return 0; + } + + pr_info("%s : live migration enabled in EFI\n", __func__); + wrmsrl(MSR_KVM_MIGRATION_CONTROL, KVM_MIGRATION_READY); + + return 1; +} + +late_initcall(setup_efi_kvm_sev_migration); + /* * Set the IPI entry points */ @@ -756,7 +809,7 @@ static noinline uint32_t __kvm_cpuid_base(void) return 0; /* So we don't blow up on old processors */ if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) - return hypervisor_cpuid_base("KVMKVMKVM\0\0\0", 0); + return hypervisor_cpuid_base(KVM_SIGNATURE, 0); return 0; } @@ -806,8 +859,62 @@ static bool __init kvm_msi_ext_dest_id(void) return kvm_para_has_feature(KVM_FEATURE_MSI_EXT_DEST_ID); } +static void kvm_sev_hc_page_enc_status(unsigned long pfn, int npages, bool enc) +{ + kvm_sev_hypercall3(KVM_HC_MAP_GPA_RANGE, pfn << PAGE_SHIFT, npages, + KVM_MAP_GPA_RANGE_ENC_STAT(enc) | KVM_MAP_GPA_RANGE_PAGE_SZ_4K); +} + static void __init kvm_init_platform(void) { + if (cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT) && + kvm_para_has_feature(KVM_FEATURE_MIGRATION_CONTROL)) { + unsigned long nr_pages; + int i; + + pv_ops.mmu.notify_page_enc_status_changed = + kvm_sev_hc_page_enc_status; + + /* + * Reset the host's shared pages list related to kernel + * specific page encryption status settings before we load a + * new kernel by kexec. Reset the page encryption status + * during early boot intead of just before kexec to avoid SMP + * races during kvm_pv_guest_cpu_reboot(). + * NOTE: We cannot reset the complete shared pages list + * here as we need to retain the UEFI/OVMF firmware + * specific settings. + */ + + for (i = 0; i < e820_table->nr_entries; i++) { + struct e820_entry *entry = &e820_table->entries[i]; + + if (entry->type != E820_TYPE_RAM) + continue; + + nr_pages = DIV_ROUND_UP(entry->size, PAGE_SIZE); + + kvm_sev_hypercall3(KVM_HC_MAP_GPA_RANGE, entry->addr, + nr_pages, + KVM_MAP_GPA_RANGE_ENCRYPTED | KVM_MAP_GPA_RANGE_PAGE_SZ_4K); + } + + /* + * Ensure that _bss_decrypted section is marked as decrypted in the + * shared pages list. + */ + nr_pages = DIV_ROUND_UP(__end_bss_decrypted - __start_bss_decrypted, + PAGE_SIZE); + early_set_mem_enc_dec_hypercall((unsigned long)__start_bss_decrypted, + nr_pages, 0); + + /* + * If not booted using EFI, enable Live migration support. + */ + if (!efi_enabled(EFI_BOOT)) + wrmsrl(MSR_KVM_MIGRATION_CONTROL, + KVM_MIGRATION_READY); + } kvmclock_init(); x86_platform.apic_post_init = kvm_apic_init; } diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 7157c2df3bc2..7f7636aac620 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -337,6 +337,7 @@ struct paravirt_patch_template pv_ops = { (void (*)(struct mmu_gather *, void *))tlb_remove_page, .mmu.exit_mmap = paravirt_nop, + .mmu.notify_page_enc_status_changed = paravirt_nop, #ifdef CONFIG_PARAVIRT_XXL .mmu.read_cr2 = __PV_IS_CALLEE_SAVE(pv_native_read_cr2), diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index e9ee8b526319..04143a653a8a 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -964,6 +964,9 @@ unsigned long __get_wchan(struct task_struct *p) struct unwind_state state; unsigned long addr = 0; + if (!try_get_task_stack(p)) + return 0; + for (unwind_start(&state, p, NULL, NULL); !unwind_done(&state); unwind_next_frame(&state)) { addr = unwind_get_return_address(&state); @@ -974,6 +977,8 @@ unsigned long __get_wchan(struct task_struct *p) break; } + put_task_stack(p); + return addr; } diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 49b596db5631..6a190c7f4d71 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -742,6 +742,28 @@ dump_kernel_offset(struct notifier_block *self, unsigned long v, void *p) return 0; } +static char * __init prepare_command_line(void) +{ +#ifdef CONFIG_CMDLINE_BOOL +#ifdef CONFIG_CMDLINE_OVERRIDE + strlcpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE); +#else + if (builtin_cmdline[0]) { + /* append boot loader cmdline to builtin */ + strlcat(builtin_cmdline, " ", COMMAND_LINE_SIZE); + strlcat(builtin_cmdline, boot_command_line, COMMAND_LINE_SIZE); + strlcpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE); + } +#endif +#endif + + strlcpy(command_line, boot_command_line, COMMAND_LINE_SIZE); + + parse_early_param(); + + return command_line; +} + /* * Determine if we were loaded by an EFI loader. If so, then we have also been * passed the efi memmap, systab, etc., so we should use these data structures @@ -831,6 +853,23 @@ void __init setup_arch(char **cmdline_p) x86_init.oem.arch_setup(); /* + * x86_configure_nx() is called before parse_early_param() (called by + * prepare_command_line()) to detect whether hardware doesn't support + * NX (so that the early EHCI debug console setup can safely call + * set_fixmap()). It may then be called again from within noexec_setup() + * during parsing early parameters to honor the respective command line + * option. + */ + x86_configure_nx(); + + /* + * This parses early params and it needs to run before + * early_reserve_memory() because latter relies on such settings + * supplied as early params. + */ + *cmdline_p = prepare_command_line(); + + /* * Do some memory reservations *before* memory is added to memblock, so * memblock allocations won't overwrite it. * @@ -863,33 +902,6 @@ void __init setup_arch(char **cmdline_p) bss_resource.start = __pa_symbol(__bss_start); bss_resource.end = __pa_symbol(__bss_stop)-1; -#ifdef CONFIG_CMDLINE_BOOL -#ifdef CONFIG_CMDLINE_OVERRIDE - strlcpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE); -#else - if (builtin_cmdline[0]) { - /* append boot loader cmdline to builtin */ - strlcat(builtin_cmdline, " ", COMMAND_LINE_SIZE); - strlcat(builtin_cmdline, boot_command_line, COMMAND_LINE_SIZE); - strlcpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE); - } -#endif -#endif - - strlcpy(command_line, boot_command_line, COMMAND_LINE_SIZE); - *cmdline_p = command_line; - - /* - * x86_configure_nx() is called before parse_early_param() to detect - * whether hardware doesn't support NX (so that the early EHCI debug - * console setup can safely call set_fixmap()). It may then be called - * again from within noexec_setup() during parsing early parameters - * to honor the respective command line option. - */ - x86_configure_nx(); - - parse_early_param(); - #ifdef CONFIG_MEMORY_HOTPLUG /* * Memory used by the kernel cannot be hot-removed because Linux diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 8241927addff..ac2909f0cab3 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -1350,12 +1350,7 @@ static void __init smp_get_logical_apicid(void) cpu0_logical_apicid = GET_APIC_LOGICAL_ID(apic_read(APIC_LDR)); } -/* - * Prepare for SMP bootup. - * @max_cpus: configured maximum number of CPUs, It is a legacy parameter - * for common interface support. - */ -void __init native_smp_prepare_cpus(unsigned int max_cpus) +void __init smp_prepare_cpus_common(void) { unsigned int i; @@ -1386,6 +1381,17 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus) set_sched_topology(x86_topology); set_cpu_sibling_map(0); +} + +/* + * Prepare for SMP bootup. + * @max_cpus: configured maximum number of CPUs, It is a legacy parameter + * for common interface support. + */ +void __init native_smp_prepare_cpus(unsigned int max_cpus) +{ + smp_prepare_cpus_common(); + init_freq_invariance(false, false); smp_sanity_check(); diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c index ea028e736831..9c407a33a774 100644 --- a/arch/x86/kernel/static_call.c +++ b/arch/x86/kernel/static_call.c @@ -56,10 +56,15 @@ static void __ref __static_call_transform(void *insn, enum insn_type type, void text_poke_bp(insn, code, size, emulate); } -static void __static_call_validate(void *insn, bool tail) +static void __static_call_validate(void *insn, bool tail, bool tramp) { u8 opcode = *(u8 *)insn; + if (tramp && memcmp(insn+5, "SCT", 3)) { + pr_err("trampoline signature fail"); + BUG(); + } + if (tail) { if (opcode == JMP32_INSN_OPCODE || opcode == RET_INSN_OPCODE) @@ -74,7 +79,8 @@ static void __static_call_validate(void *insn, bool tail) /* * If we ever trigger this, our text is corrupt, we'll probably not live long. */ - WARN_ONCE(1, "unexpected static_call insn opcode 0x%x at %pS\n", opcode, insn); + pr_err("unexpected static_call insn opcode 0x%x at %pS\n", opcode, insn); + BUG(); } static inline enum insn_type __sc_insn(bool null, bool tail) @@ -97,12 +103,12 @@ void arch_static_call_transform(void *site, void *tramp, void *func, bool tail) mutex_lock(&text_mutex); if (tramp) { - __static_call_validate(tramp, true); + __static_call_validate(tramp, true, true); __static_call_transform(tramp, __sc_insn(!func, true), func); } if (IS_ENABLED(CONFIG_HAVE_STATIC_CALL_INLINE) && site) { - __static_call_validate(site, tail); + __static_call_validate(site, tail, false); __static_call_transform(site, __sc_insn(!func, tail), func); } diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c index f14f69d7aa3c..c21bcd668284 100644 --- a/arch/x86/kernel/vm86_32.c +++ b/arch/x86/kernel/vm86_32.c @@ -106,7 +106,7 @@ void save_v86_state(struct kernel_vm86_regs *regs, int retval) */ local_irq_enable(); - BUG_ON(!vm86 || !vm86->user_vm86); + BUG_ON(!vm86); set_flags(regs->pt.flags, VEFLAGS, X86_EFLAGS_VIF | vm86->veflags_mask); user = vm86->user_vm86; @@ -160,7 +160,7 @@ Efault_end: user_access_end(); Efault: pr_alert("could not access userspace vm86 info\n"); - force_fatal_sig(SIGSEGV); + force_exit_sig(SIGSEGV); goto exit_vm86; } diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 2d70edb0f323..07e9215e911d 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -99,11 +99,45 @@ static int kvm_check_cpuid(struct kvm_cpuid_entry2 *entries, int nent) return 0; } -void kvm_update_pv_runtime(struct kvm_vcpu *vcpu) +static void kvm_update_kvm_cpuid_base(struct kvm_vcpu *vcpu) { - struct kvm_cpuid_entry2 *best; + u32 function; + struct kvm_cpuid_entry2 *entry; + + vcpu->arch.kvm_cpuid_base = 0; + + for_each_possible_hypervisor_cpuid_base(function) { + entry = kvm_find_cpuid_entry(vcpu, function, 0); - best = kvm_find_cpuid_entry(vcpu, KVM_CPUID_FEATURES, 0); + if (entry) { + u32 signature[3]; + + signature[0] = entry->ebx; + signature[1] = entry->ecx; + signature[2] = entry->edx; + + BUILD_BUG_ON(sizeof(signature) > sizeof(KVM_SIGNATURE)); + if (!memcmp(signature, KVM_SIGNATURE, sizeof(signature))) { + vcpu->arch.kvm_cpuid_base = function; + break; + } + } + } +} + +static struct kvm_cpuid_entry2 *kvm_find_kvm_cpuid_features(struct kvm_vcpu *vcpu) +{ + u32 base = vcpu->arch.kvm_cpuid_base; + + if (!base) + return NULL; + + return kvm_find_cpuid_entry(vcpu, base | KVM_CPUID_FEATURES, 0); +} + +void kvm_update_pv_runtime(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *best = kvm_find_kvm_cpuid_features(vcpu); /* * save the feature bitmap to avoid cpuid lookup for every PV @@ -142,7 +176,7 @@ void kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu) cpuid_entry_has(best, X86_FEATURE_XSAVEC))) best->ebx = xstate_required_size(vcpu->arch.xcr0, true); - best = kvm_find_cpuid_entry(vcpu, KVM_CPUID_FEATURES, 0); + best = kvm_find_kvm_cpuid_features(vcpu); if (kvm_hlt_in_guest(vcpu->kvm) && best && (best->eax & (1 << KVM_FEATURE_PV_UNHALT))) best->eax &= ~(1 << KVM_FEATURE_PV_UNHALT); @@ -239,6 +273,26 @@ u64 kvm_vcpu_reserved_gpa_bits_raw(struct kvm_vcpu *vcpu) return rsvd_bits(cpuid_maxphyaddr(vcpu), 63); } +static int kvm_set_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 *e2, + int nent) +{ + int r; + + r = kvm_check_cpuid(e2, nent); + if (r) + return r; + + kvfree(vcpu->arch.cpuid_entries); + vcpu->arch.cpuid_entries = e2; + vcpu->arch.cpuid_nent = nent; + + kvm_update_kvm_cpuid_base(vcpu); + kvm_update_cpuid_runtime(vcpu); + kvm_vcpu_after_set_cpuid(vcpu); + + return 0; +} + /* when an old userspace process fills a new kernel module */ int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid *cpuid, @@ -275,18 +329,9 @@ int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu, e2[i].padding[2] = 0; } - r = kvm_check_cpuid(e2, cpuid->nent); - if (r) { + r = kvm_set_cpuid(vcpu, e2, cpuid->nent); + if (r) kvfree(e2); - goto out_free_cpuid; - } - - kvfree(vcpu->arch.cpuid_entries); - vcpu->arch.cpuid_entries = e2; - vcpu->arch.cpuid_nent = cpuid->nent; - - kvm_update_cpuid_runtime(vcpu); - kvm_vcpu_after_set_cpuid(vcpu); out_free_cpuid: kvfree(e); @@ -310,20 +355,11 @@ int kvm_vcpu_ioctl_set_cpuid2(struct kvm_vcpu *vcpu, return PTR_ERR(e2); } - r = kvm_check_cpuid(e2, cpuid->nent); - if (r) { + r = kvm_set_cpuid(vcpu, e2, cpuid->nent); + if (r) kvfree(e2); - return r; - } - kvfree(vcpu->arch.cpuid_entries); - vcpu->arch.cpuid_entries = e2; - vcpu->arch.cpuid_nent = cpuid->nent; - - kvm_update_cpuid_runtime(vcpu); - kvm_vcpu_after_set_cpuid(vcpu); - - return 0; + return r; } int kvm_vcpu_ioctl_get_cpuid2(struct kvm_vcpu *vcpu, @@ -871,8 +907,7 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) } break; case KVM_CPUID_SIGNATURE: { - static const char signature[12] = "KVMKVMKVM\0\0"; - const u32 *sigptr = (const u32 *)signature; + const u32 *sigptr = (const u32 *)KVM_SIGNATURE; entry->eax = KVM_CPUID_FEATURES; entry->ebx = sigptr[0]; entry->ecx = sigptr[1]; diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 4f15c0165c05..5e19e6e4c2ce 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -1472,7 +1472,7 @@ static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host) if (!(data & HV_X64_MSR_VP_ASSIST_PAGE_ENABLE)) { hv_vcpu->hv_vapic = data; - if (kvm_lapic_enable_pv_eoi(vcpu, 0, 0)) + if (kvm_lapic_set_pv_eoi(vcpu, 0, 0)) return 1; break; } @@ -1490,7 +1490,7 @@ static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host) return 1; hv_vcpu->hv_vapic = data; kvm_vcpu_mark_page_dirty(vcpu, gfn); - if (kvm_lapic_enable_pv_eoi(vcpu, + if (kvm_lapic_set_pv_eoi(vcpu, gfn_to_gpa(gfn) | KVM_MSR_ENABLED, sizeof(struct hv_vp_assist_page))) return 1; @@ -2022,7 +2022,7 @@ static void kvm_hv_hypercall_set_result(struct kvm_vcpu *vcpu, u64 result) { bool longmode; - longmode = is_64_bit_mode(vcpu); + longmode = is_64_bit_hypercall(vcpu); if (longmode) kvm_rax_write(vcpu, result); else { @@ -2171,7 +2171,7 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu) } #ifdef CONFIG_X86_64 - if (is_64_bit_mode(vcpu)) { + if (is_64_bit_hypercall(vcpu)) { hc.param = kvm_rcx_read(vcpu); hc.ingpa = kvm_rdx_read(vcpu); hc.outgpa = kvm_r8_read(vcpu); diff --git a/arch/x86/kvm/ioapic.h b/arch/x86/kvm/ioapic.h index e66e620c3bed..539333ac4b38 100644 --- a/arch/x86/kvm/ioapic.h +++ b/arch/x86/kvm/ioapic.h @@ -81,7 +81,6 @@ struct kvm_ioapic { unsigned long irq_states[IOAPIC_NUM_PINS]; struct kvm_io_device dev; struct kvm *kvm; - void (*ack_notifier)(void *opaque, int irq); spinlock_t lock; struct rtc_status rtc_status; struct delayed_work eoi_inject; diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h index 650642b18d15..c2d7cfe82d00 100644 --- a/arch/x86/kvm/irq.h +++ b/arch/x86/kvm/irq.h @@ -56,7 +56,6 @@ struct kvm_pic { struct kvm_io_device dev_master; struct kvm_io_device dev_slave; struct kvm_io_device dev_elcr; - void (*ack_notifier)(void *opaque, int irq); unsigned long irq_states[PIC_NUM_PINS]; }; diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index d6ac32f3f650..f206fc35deff 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -707,7 +707,7 @@ static void pv_eoi_clr_pending(struct kvm_vcpu *vcpu) static int apic_has_interrupt_for_ppr(struct kvm_lapic *apic, u32 ppr) { int highest_irr; - if (apic->vcpu->arch.apicv_active) + if (kvm_x86_ops.sync_pir_to_irr) highest_irr = static_call(kvm_x86_sync_pir_to_irr)(apic->vcpu); else highest_irr = apic_find_highest_irr(apic); @@ -2856,25 +2856,30 @@ int kvm_hv_vapic_msr_read(struct kvm_vcpu *vcpu, u32 reg, u64 *data) return 0; } -int kvm_lapic_enable_pv_eoi(struct kvm_vcpu *vcpu, u64 data, unsigned long len) +int kvm_lapic_set_pv_eoi(struct kvm_vcpu *vcpu, u64 data, unsigned long len) { u64 addr = data & ~KVM_MSR_ENABLED; struct gfn_to_hva_cache *ghc = &vcpu->arch.pv_eoi.data; unsigned long new_len; + int ret; if (!IS_ALIGNED(addr, 4)) return 1; - vcpu->arch.pv_eoi.msr_val = data; - if (!pv_eoi_enabled(vcpu)) - return 0; + if (data & KVM_MSR_ENABLED) { + if (addr == ghc->gpa && len <= ghc->len) + new_len = ghc->len; + else + new_len = len; - if (addr == ghc->gpa && len <= ghc->len) - new_len = ghc->len; - else - new_len = len; + ret = kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc, addr, new_len); + if (ret) + return ret; + } + + vcpu->arch.pv_eoi.msr_val = data; - return kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc, addr, new_len); + return 0; } int kvm_apic_accept_events(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index d7c25d0c1354..2b44e533fc8d 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -127,7 +127,7 @@ int kvm_x2apic_msr_read(struct kvm_vcpu *vcpu, u32 msr, u64 *data); int kvm_hv_vapic_msr_write(struct kvm_vcpu *vcpu, u32 msr, u64 data); int kvm_hv_vapic_msr_read(struct kvm_vcpu *vcpu, u32 msr, u64 *data); -int kvm_lapic_enable_pv_eoi(struct kvm_vcpu *vcpu, u64 data, unsigned long len); +int kvm_lapic_set_pv_eoi(struct kvm_vcpu *vcpu, u64 data, unsigned long len); void kvm_lapic_exit(void); #define VEC_POS(v) ((v) & (32 - 1)) diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 323b5057d08f..6354297e92ae 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -1582,7 +1582,7 @@ bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range) flush = kvm_handle_gfn_range(kvm, range, kvm_unmap_rmapp); if (is_tdp_mmu_enabled(kvm)) - flush |= kvm_tdp_mmu_unmap_gfn_range(kvm, range, flush); + flush = kvm_tdp_mmu_unmap_gfn_range(kvm, range, flush); return flush; } @@ -2173,10 +2173,10 @@ static void shadow_walk_init_using_root(struct kvm_shadow_walk_iterator *iterato iterator->shadow_addr = root; iterator->level = vcpu->arch.mmu->shadow_root_level; - if (iterator->level == PT64_ROOT_4LEVEL && + if (iterator->level >= PT64_ROOT_4LEVEL && vcpu->arch.mmu->root_level < PT64_ROOT_4LEVEL && !vcpu->arch.mmu->direct_map) - --iterator->level; + iterator->level = PT32E_ROOT_LEVEL; if (iterator->level == PT32E_ROOT_LEVEL) { /* @@ -3191,17 +3191,17 @@ static int fast_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) new_spte |= PT_WRITABLE_MASK; /* - * Do not fix write-permission on the large spte. Since - * we only dirty the first page into the dirty-bitmap in + * Do not fix write-permission on the large spte when + * dirty logging is enabled. Since we only dirty the + * first page into the dirty-bitmap in * fast_pf_fix_direct_spte(), other pages are missed * if its slot has dirty logging enabled. * * Instead, we let the slow page fault path create a * normal spte to fix the access. - * - * See the comments in kvm_arch_commit_memory_region(). */ - if (sp->role.level > PG_LEVEL_4K) + if (sp->role.level > PG_LEVEL_4K && + kvm_slot_dirty_track_enabled(fault->slot)) break; } @@ -4682,6 +4682,7 @@ static union kvm_mmu_extended_role kvm_calc_mmu_role_ext(struct kvm_vcpu *vcpu, /* PKEY and LA57 are active iff long mode is active. */ ext.cr4_pke = ____is_efer_lma(regs) && ____is_cr4_pke(regs); ext.cr4_la57 = ____is_efer_lma(regs) && ____is_cr4_la57(regs); + ext.efer_lma = ____is_efer_lma(regs); } ext.valid = 1; @@ -4854,7 +4855,7 @@ void kvm_init_shadow_npt_mmu(struct kvm_vcpu *vcpu, unsigned long cr0, struct kvm_mmu *context = &vcpu->arch.guest_mmu; struct kvm_mmu_role_regs regs = { .cr0 = cr0, - .cr4 = cr4, + .cr4 = cr4 & ~X86_CR4_PKE, .efer = efer, }; union kvm_mmu_role new_role; @@ -4918,7 +4919,7 @@ void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly, context->direct_map = false; update_permission_bitmask(context, true); - update_pkru_bitmask(context); + context->pkru_mask = 0; reset_rsvds_bits_mask_ept(vcpu, context, execonly); reset_ept_shadow_zero_bits_mask(vcpu, context, execonly); } @@ -5024,6 +5025,14 @@ void kvm_mmu_after_set_cpuid(struct kvm_vcpu *vcpu) /* * Invalidate all MMU roles to force them to reinitialize as CPUID * information is factored into reserved bit calculations. + * + * Correctly handling multiple vCPU models with respect to paging and + * physical address properties) in a single VM would require tracking + * all relevant CPUID information in kvm_mmu_page_role. That is very + * undesirable as it would increase the memory requirements for + * gfn_track (see struct kvm_mmu_page_role comments). For now that + * problem is swept under the rug; KVM's CPUID API is horrific and + * it's all but impossible to solve it without introducing a new API. */ vcpu->arch.root_mmu.mmu_role.ext.valid = 0; vcpu->arch.guest_mmu.mmu_role.ext.valid = 0; @@ -5031,24 +5040,10 @@ void kvm_mmu_after_set_cpuid(struct kvm_vcpu *vcpu) kvm_mmu_reset_context(vcpu); /* - * KVM does not correctly handle changing guest CPUID after KVM_RUN, as - * MAXPHYADDR, GBPAGES support, AMD reserved bit behavior, etc.. aren't - * tracked in kvm_mmu_page_role. As a result, KVM may miss guest page - * faults due to reusing SPs/SPTEs. Alert userspace, but otherwise - * sweep the problem under the rug. - * - * KVM's horrific CPUID ABI makes the problem all but impossible to - * solve, as correctly handling multiple vCPU models (with respect to - * paging and physical address properties) in a single VM would require - * tracking all relevant CPUID information in kvm_mmu_page_role. That - * is very undesirable as it would double the memory requirements for - * gfn_track (see struct kvm_mmu_page_role comments), and in practice - * no sane VMM mucks with the core vCPU model on the fly. + * Changing guest CPUID after KVM_RUN is forbidden, see the comment in + * kvm_arch_vcpu_ioctl(). */ - if (vcpu->arch.last_vmentry_cpu != -1) { - pr_warn_ratelimited("KVM: KVM_SET_CPUID{,2} after KVM_RUN may cause guest instability\n"); - pr_warn_ratelimited("KVM: KVM_SET_CPUID{,2} will fail after KVM_RUN starting with Linux 5.16\n"); - } + KVM_BUG_ON(vcpu->arch.last_vmentry_cpu != -1, vcpu->kvm); } void kvm_mmu_reset_context(struct kvm_vcpu *vcpu) @@ -5368,7 +5363,7 @@ void kvm_mmu_invalidate_gva(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva) { - kvm_mmu_invalidate_gva(vcpu, vcpu->arch.mmu, gva, INVALID_PAGE); + kvm_mmu_invalidate_gva(vcpu, vcpu->arch.walk_mmu, gva, INVALID_PAGE); ++vcpu->stat.invlpg; } EXPORT_SYMBOL_GPL(kvm_mmu_invlpg); @@ -5853,8 +5848,6 @@ restart: void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm, const struct kvm_memory_slot *slot) { - bool flush = false; - if (kvm_memslots_have_rmaps(kvm)) { write_lock(&kvm->mmu_lock); /* @@ -5862,17 +5855,14 @@ void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm, * logging at a 4k granularity and never creates collapsible * 2m SPTEs during dirty logging. */ - flush = slot_handle_level_4k(kvm, slot, kvm_mmu_zap_collapsible_spte, true); - if (flush) + if (slot_handle_level_4k(kvm, slot, kvm_mmu_zap_collapsible_spte, true)) kvm_arch_flush_remote_tlbs_memslot(kvm, slot); write_unlock(&kvm->mmu_lock); } if (is_tdp_mmu_enabled(kvm)) { read_lock(&kvm->mmu_lock); - flush = kvm_tdp_mmu_zap_collapsible_sptes(kvm, slot, flush); - if (flush) - kvm_arch_flush_remote_tlbs_memslot(kvm, slot); + kvm_tdp_mmu_zap_collapsible_sptes(kvm, slot); read_unlock(&kvm->mmu_lock); } } @@ -6181,23 +6171,46 @@ void kvm_mmu_module_exit(void) mmu_audit_disable(); } +/* + * Calculate the effective recovery period, accounting for '0' meaning "let KVM + * select a halving time of 1 hour". Returns true if recovery is enabled. + */ +static bool calc_nx_huge_pages_recovery_period(uint *period) +{ + /* + * Use READ_ONCE to get the params, this may be called outside of the + * param setters, e.g. by the kthread to compute its next timeout. + */ + bool enabled = READ_ONCE(nx_huge_pages); + uint ratio = READ_ONCE(nx_huge_pages_recovery_ratio); + + if (!enabled || !ratio) + return false; + + *period = READ_ONCE(nx_huge_pages_recovery_period_ms); + if (!*period) { + /* Make sure the period is not less than one second. */ + ratio = min(ratio, 3600u); + *period = 60 * 60 * 1000 / ratio; + } + return true; +} + static int set_nx_huge_pages_recovery_param(const char *val, const struct kernel_param *kp) { bool was_recovery_enabled, is_recovery_enabled; uint old_period, new_period; int err; - was_recovery_enabled = nx_huge_pages_recovery_ratio; - old_period = nx_huge_pages_recovery_period_ms; + was_recovery_enabled = calc_nx_huge_pages_recovery_period(&old_period); err = param_set_uint(val, kp); if (err) return err; - is_recovery_enabled = nx_huge_pages_recovery_ratio; - new_period = nx_huge_pages_recovery_period_ms; + is_recovery_enabled = calc_nx_huge_pages_recovery_period(&new_period); - if (READ_ONCE(nx_huge_pages) && is_recovery_enabled && + if (is_recovery_enabled && (!was_recovery_enabled || old_period > new_period)) { struct kvm *kvm; @@ -6261,18 +6274,13 @@ static void kvm_recover_nx_lpages(struct kvm *kvm) static long get_nx_lpage_recovery_timeout(u64 start_time) { - uint ratio = READ_ONCE(nx_huge_pages_recovery_ratio); - uint period = READ_ONCE(nx_huge_pages_recovery_period_ms); + bool enabled; + uint period; - if (!period && ratio) { - /* Make sure the period is not less than one second. */ - ratio = min(ratio, 3600u); - period = 60 * 60 * 1000 / ratio; - } + enabled = calc_nx_huge_pages_recovery_period(&period); - return READ_ONCE(nx_huge_pages) && ratio - ? start_time + msecs_to_jiffies(period) - get_jiffies_64() - : MAX_SCHEDULE_TIMEOUT; + return enabled ? start_time + msecs_to_jiffies(period) - get_jiffies_64() + : MAX_SCHEDULE_TIMEOUT; } static int kvm_nx_lpage_recovery_worker(struct kvm *kvm, uintptr_t data) diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 7c5dd83e52de..1db8496259ad 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -317,9 +317,6 @@ static void handle_removed_tdp_mmu_page(struct kvm *kvm, tdp_ptep_t pt, struct kvm_mmu_page *sp = sptep_to_sp(rcu_dereference(pt)); int level = sp->role.level; gfn_t base_gfn = sp->gfn; - u64 old_child_spte; - u64 *sptep; - gfn_t gfn; int i; trace_kvm_mmu_prepare_zap_page(sp); @@ -327,8 +324,9 @@ static void handle_removed_tdp_mmu_page(struct kvm *kvm, tdp_ptep_t pt, tdp_mmu_unlink_page(kvm, sp, shared); for (i = 0; i < PT64_ENT_PER_PAGE; i++) { - sptep = rcu_dereference(pt) + i; - gfn = base_gfn + i * KVM_PAGES_PER_HPAGE(level); + u64 *sptep = rcu_dereference(pt) + i; + gfn_t gfn = base_gfn + i * KVM_PAGES_PER_HPAGE(level); + u64 old_child_spte; if (shared) { /* @@ -374,7 +372,7 @@ static void handle_removed_tdp_mmu_page(struct kvm *kvm, tdp_ptep_t pt, shared); } - kvm_flush_remote_tlbs_with_address(kvm, gfn, + kvm_flush_remote_tlbs_with_address(kvm, base_gfn, KVM_PAGES_PER_HPAGE(level + 1)); call_rcu(&sp->rcu_head, tdp_mmu_free_sp_rcu_callback); @@ -897,7 +895,7 @@ static int tdp_mmu_map_handle_target_level(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault, struct tdp_iter *iter) { - struct kvm_mmu_page *sp = sptep_to_sp(iter->sptep); + struct kvm_mmu_page *sp = sptep_to_sp(rcu_dereference(iter->sptep)); u64 new_spte; int ret = RET_PF_FIXED; bool wrprot = false; @@ -1033,9 +1031,9 @@ bool kvm_tdp_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range, { struct kvm_mmu_page *root; - for_each_tdp_mmu_root(kvm, root, range->slot->as_id) - flush |= zap_gfn_range(kvm, root, range->start, range->end, - range->may_block, flush, false); + for_each_tdp_mmu_root_yield_safe(kvm, root, range->slot->as_id, false) + flush = zap_gfn_range(kvm, root, range->start, range->end, + range->may_block, flush, false); return flush; } @@ -1364,10 +1362,9 @@ void kvm_tdp_mmu_clear_dirty_pt_masked(struct kvm *kvm, * Clear leaf entries which could be replaced by large mappings, for * GFNs within the slot. */ -static bool zap_collapsible_spte_range(struct kvm *kvm, +static void zap_collapsible_spte_range(struct kvm *kvm, struct kvm_mmu_page *root, - const struct kvm_memory_slot *slot, - bool flush) + const struct kvm_memory_slot *slot) { gfn_t start = slot->base_gfn; gfn_t end = start + slot->npages; @@ -1378,10 +1375,8 @@ static bool zap_collapsible_spte_range(struct kvm *kvm, tdp_root_for_each_pte(iter, root, start, end) { retry: - if (tdp_mmu_iter_cond_resched(kvm, &iter, flush, true)) { - flush = false; + if (tdp_mmu_iter_cond_resched(kvm, &iter, false, true)) continue; - } if (!is_shadow_present_pte(iter.old_spte) || !is_last_spte(iter.old_spte, iter.level)) @@ -1393,6 +1388,7 @@ retry: pfn, PG_LEVEL_NUM)) continue; + /* Note, a successful atomic zap also does a remote TLB flush. */ if (!tdp_mmu_zap_spte_atomic(kvm, &iter)) { /* * The iter must explicitly re-read the SPTE because @@ -1401,30 +1397,24 @@ retry: iter.old_spte = READ_ONCE(*rcu_dereference(iter.sptep)); goto retry; } - flush = true; } rcu_read_unlock(); - - return flush; } /* * Clear non-leaf entries (and free associated page tables) which could * be replaced by large mappings, for GFNs within the slot. */ -bool kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm, - const struct kvm_memory_slot *slot, - bool flush) +void kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm, + const struct kvm_memory_slot *slot) { struct kvm_mmu_page *root; lockdep_assert_held_read(&kvm->mmu_lock); for_each_tdp_mmu_root_yield_safe(kvm, root, slot->as_id, true) - flush = zap_collapsible_spte_range(kvm, root, slot, flush); - - return flush; + zap_collapsible_spte_range(kvm, root, slot); } /* diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h index 476b133544dd..3899004a5d91 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.h +++ b/arch/x86/kvm/mmu/tdp_mmu.h @@ -64,9 +64,8 @@ void kvm_tdp_mmu_clear_dirty_pt_masked(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn, unsigned long mask, bool wrprot); -bool kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm, - const struct kvm_memory_slot *slot, - bool flush); +void kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm, + const struct kvm_memory_slot *slot); bool kvm_tdp_mmu_write_protect_gfn(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn, diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index 0772bad9165c..09873f6488f7 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -319,7 +319,7 @@ void kvm_pmu_handle_event(struct kvm_vcpu *vcpu) } /* check if idx is a valid index to access PMU */ -int kvm_pmu_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx) +bool kvm_pmu_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx) { return kvm_x86_ops.pmu_ops->is_valid_rdpmc_ecx(vcpu, idx); } diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h index 0e4f2b1fa9fb..59d6b76203d5 100644 --- a/arch/x86/kvm/pmu.h +++ b/arch/x86/kvm/pmu.h @@ -32,7 +32,7 @@ struct kvm_pmu_ops { struct kvm_pmc *(*rdpmc_ecx_to_pmc)(struct kvm_vcpu *vcpu, unsigned int idx, u64 *mask); struct kvm_pmc *(*msr_idx_to_pmc)(struct kvm_vcpu *vcpu, u32 msr); - int (*is_valid_rdpmc_ecx)(struct kvm_vcpu *vcpu, unsigned int idx); + bool (*is_valid_rdpmc_ecx)(struct kvm_vcpu *vcpu, unsigned int idx); bool (*is_valid_msr)(struct kvm_vcpu *vcpu, u32 msr); int (*get_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr_info); int (*set_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr_info); @@ -149,7 +149,7 @@ void reprogram_counter(struct kvm_pmu *pmu, int pmc_idx); void kvm_pmu_deliver_pmi(struct kvm_vcpu *vcpu); void kvm_pmu_handle_event(struct kvm_vcpu *vcpu); int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned pmc, u64 *data); -int kvm_pmu_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx); +bool kvm_pmu_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx); bool kvm_pmu_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr); int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info); int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info); diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c index 8052d92069e0..9d6066eb7c10 100644 --- a/arch/x86/kvm/svm/avic.c +++ b/arch/x86/kvm/svm/avic.c @@ -904,7 +904,8 @@ bool svm_check_apicv_inhibit_reasons(ulong bit) BIT(APICV_INHIBIT_REASON_NESTED) | BIT(APICV_INHIBIT_REASON_IRQWIN) | BIT(APICV_INHIBIT_REASON_PIT_REINJ) | - BIT(APICV_INHIBIT_REASON_X2APIC); + BIT(APICV_INHIBIT_REASON_X2APIC) | + BIT(APICV_INHIBIT_REASON_BLOCKIRQ); return supported & BIT(bit); } @@ -988,16 +989,18 @@ void avic_vcpu_put(struct kvm_vcpu *vcpu) static void avic_set_running(struct kvm_vcpu *vcpu, bool is_run) { struct vcpu_svm *svm = to_svm(vcpu); + int cpu = get_cpu(); + WARN_ON(cpu != vcpu->cpu); svm->avic_is_running = is_run; - if (!kvm_vcpu_apicv_active(vcpu)) - return; - - if (is_run) - avic_vcpu_load(vcpu, vcpu->cpu); - else - avic_vcpu_put(vcpu); + if (kvm_vcpu_apicv_active(vcpu)) { + if (is_run) + avic_vcpu_load(vcpu, cpu); + else + avic_vcpu_put(vcpu); + } + put_cpu(); } void svm_vcpu_blocking(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c index fdf587f19c5f..871c426ec389 100644 --- a/arch/x86/kvm/svm/pmu.c +++ b/arch/x86/kvm/svm/pmu.c @@ -181,14 +181,13 @@ static struct kvm_pmc *amd_pmc_idx_to_pmc(struct kvm_pmu *pmu, int pmc_idx) return get_gp_pmc_amd(pmu, base + pmc_idx, PMU_TYPE_COUNTER); } -/* returns 0 if idx's corresponding MSR exists; otherwise returns 1. */ -static int amd_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx) +static bool amd_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx) { struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); idx &= ~(3u << 30); - return (idx >= pmu->nr_arch_gp_counters); + return idx < pmu->nr_arch_gp_counters; } /* idx is the ECX register of RDPMC instruction */ diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 1964b9a174be..59727a966f90 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -120,16 +120,26 @@ static bool __sev_recycle_asids(int min_asid, int max_asid) return true; } +static int sev_misc_cg_try_charge(struct kvm_sev_info *sev) +{ + enum misc_res_type type = sev->es_active ? MISC_CG_RES_SEV_ES : MISC_CG_RES_SEV; + return misc_cg_try_charge(type, sev->misc_cg, 1); +} + +static void sev_misc_cg_uncharge(struct kvm_sev_info *sev) +{ + enum misc_res_type type = sev->es_active ? MISC_CG_RES_SEV_ES : MISC_CG_RES_SEV; + misc_cg_uncharge(type, sev->misc_cg, 1); +} + static int sev_asid_new(struct kvm_sev_info *sev) { int asid, min_asid, max_asid, ret; bool retry = true; - enum misc_res_type type; - type = sev->es_active ? MISC_CG_RES_SEV_ES : MISC_CG_RES_SEV; WARN_ON(sev->misc_cg); sev->misc_cg = get_current_misc_cg(); - ret = misc_cg_try_charge(type, sev->misc_cg, 1); + ret = sev_misc_cg_try_charge(sev); if (ret) { put_misc_cg(sev->misc_cg); sev->misc_cg = NULL; @@ -162,7 +172,7 @@ again: return asid; e_uncharge: - misc_cg_uncharge(type, sev->misc_cg, 1); + sev_misc_cg_uncharge(sev); put_misc_cg(sev->misc_cg); sev->misc_cg = NULL; return ret; @@ -179,7 +189,6 @@ static void sev_asid_free(struct kvm_sev_info *sev) { struct svm_cpu_data *sd; int cpu; - enum misc_res_type type; mutex_lock(&sev_bitmap_lock); @@ -192,8 +201,7 @@ static void sev_asid_free(struct kvm_sev_info *sev) mutex_unlock(&sev_bitmap_lock); - type = sev->es_active ? MISC_CG_RES_SEV_ES : MISC_CG_RES_SEV; - misc_cg_uncharge(type, sev->misc_cg, 1); + sev_misc_cg_uncharge(sev); put_misc_cg(sev->misc_cg); sev->misc_cg = NULL; } @@ -229,7 +237,6 @@ static void sev_unbind_asid(struct kvm *kvm, unsigned int handle) static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp) { struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; - bool es_active = argp->id == KVM_SEV_ES_INIT; int asid, ret; if (kvm->created_vcpus) @@ -239,7 +246,8 @@ static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp) if (unlikely(sev->active)) return ret; - sev->es_active = es_active; + sev->active = true; + sev->es_active = argp->id == KVM_SEV_ES_INIT; asid = sev_asid_new(sev); if (asid < 0) goto e_no_asid; @@ -249,8 +257,6 @@ static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp) if (ret) goto e_free; - sev->active = true; - sev->asid = asid; INIT_LIST_HEAD(&sev->regions_list); return 0; @@ -260,6 +266,7 @@ e_free: sev->asid = 0; e_no_asid: sev->es_active = false; + sev->active = false; return ret; } @@ -590,7 +597,7 @@ static int sev_es_sync_vmsa(struct vcpu_svm *svm) * traditional VMSA as it has been built so far (in prep * for LAUNCH_UPDATE_VMSA) to be the initial SEV-ES state. */ - memcpy(svm->vmsa, save, sizeof(*save)); + memcpy(svm->sev_es.vmsa, save, sizeof(*save)); return 0; } @@ -612,11 +619,11 @@ static int __sev_launch_update_vmsa(struct kvm *kvm, struct kvm_vcpu *vcpu, * the VMSA memory content (i.e it will write the same memory region * with the guest's key), so invalidate it first. */ - clflush_cache_range(svm->vmsa, PAGE_SIZE); + clflush_cache_range(svm->sev_es.vmsa, PAGE_SIZE); vmsa.reserved = 0; vmsa.handle = to_kvm_svm(kvm)->sev_info.handle; - vmsa.address = __sme_pa(svm->vmsa); + vmsa.address = __sme_pa(svm->sev_es.vmsa); vmsa.len = PAGE_SIZE; ret = sev_issue_cmd(kvm, SEV_CMD_LAUNCH_UPDATE_VMSA, &vmsa, error); if (ret) @@ -1522,7 +1529,7 @@ static int sev_receive_finish(struct kvm *kvm, struct kvm_sev_cmd *argp) return sev_issue_cmd(kvm, SEV_CMD_RECEIVE_FINISH, &data, &argp->error); } -static bool cmd_allowed_from_miror(u32 cmd_id) +static bool is_cmd_allowed_from_mirror(u32 cmd_id) { /* * Allow mirrors VM to call KVM_SEV_LAUNCH_UPDATE_VMSA to enable SEV-ES @@ -1536,6 +1543,223 @@ static bool cmd_allowed_from_miror(u32 cmd_id) return false; } +static int sev_lock_two_vms(struct kvm *dst_kvm, struct kvm *src_kvm) +{ + struct kvm_sev_info *dst_sev = &to_kvm_svm(dst_kvm)->sev_info; + struct kvm_sev_info *src_sev = &to_kvm_svm(src_kvm)->sev_info; + int r = -EBUSY; + + if (dst_kvm == src_kvm) + return -EINVAL; + + /* + * Bail if these VMs are already involved in a migration to avoid + * deadlock between two VMs trying to migrate to/from each other. + */ + if (atomic_cmpxchg_acquire(&dst_sev->migration_in_progress, 0, 1)) + return -EBUSY; + + if (atomic_cmpxchg_acquire(&src_sev->migration_in_progress, 0, 1)) + goto release_dst; + + r = -EINTR; + if (mutex_lock_killable(&dst_kvm->lock)) + goto release_src; + if (mutex_lock_killable(&src_kvm->lock)) + goto unlock_dst; + return 0; + +unlock_dst: + mutex_unlock(&dst_kvm->lock); +release_src: + atomic_set_release(&src_sev->migration_in_progress, 0); +release_dst: + atomic_set_release(&dst_sev->migration_in_progress, 0); + return r; +} + +static void sev_unlock_two_vms(struct kvm *dst_kvm, struct kvm *src_kvm) +{ + struct kvm_sev_info *dst_sev = &to_kvm_svm(dst_kvm)->sev_info; + struct kvm_sev_info *src_sev = &to_kvm_svm(src_kvm)->sev_info; + + mutex_unlock(&dst_kvm->lock); + mutex_unlock(&src_kvm->lock); + atomic_set_release(&dst_sev->migration_in_progress, 0); + atomic_set_release(&src_sev->migration_in_progress, 0); +} + + +static int sev_lock_vcpus_for_migration(struct kvm *kvm) +{ + struct kvm_vcpu *vcpu; + int i, j; + + kvm_for_each_vcpu(i, vcpu, kvm) { + if (mutex_lock_killable(&vcpu->mutex)) + goto out_unlock; + } + + return 0; + +out_unlock: + kvm_for_each_vcpu(j, vcpu, kvm) { + if (i == j) + break; + + mutex_unlock(&vcpu->mutex); + } + return -EINTR; +} + +static void sev_unlock_vcpus_for_migration(struct kvm *kvm) +{ + struct kvm_vcpu *vcpu; + int i; + + kvm_for_each_vcpu(i, vcpu, kvm) { + mutex_unlock(&vcpu->mutex); + } +} + +static void sev_migrate_from(struct kvm_sev_info *dst, + struct kvm_sev_info *src) +{ + dst->active = true; + dst->asid = src->asid; + dst->handle = src->handle; + dst->pages_locked = src->pages_locked; + dst->enc_context_owner = src->enc_context_owner; + + src->asid = 0; + src->active = false; + src->handle = 0; + src->pages_locked = 0; + src->enc_context_owner = NULL; + + list_cut_before(&dst->regions_list, &src->regions_list, &src->regions_list); +} + +static int sev_es_migrate_from(struct kvm *dst, struct kvm *src) +{ + int i; + struct kvm_vcpu *dst_vcpu, *src_vcpu; + struct vcpu_svm *dst_svm, *src_svm; + + if (atomic_read(&src->online_vcpus) != atomic_read(&dst->online_vcpus)) + return -EINVAL; + + kvm_for_each_vcpu(i, src_vcpu, src) { + if (!src_vcpu->arch.guest_state_protected) + return -EINVAL; + } + + kvm_for_each_vcpu(i, src_vcpu, src) { + src_svm = to_svm(src_vcpu); + dst_vcpu = kvm_get_vcpu(dst, i); + dst_svm = to_svm(dst_vcpu); + + /* + * Transfer VMSA and GHCB state to the destination. Nullify and + * clear source fields as appropriate, the state now belongs to + * the destination. + */ + memcpy(&dst_svm->sev_es, &src_svm->sev_es, sizeof(src_svm->sev_es)); + dst_svm->vmcb->control.ghcb_gpa = src_svm->vmcb->control.ghcb_gpa; + dst_svm->vmcb->control.vmsa_pa = src_svm->vmcb->control.vmsa_pa; + dst_vcpu->arch.guest_state_protected = true; + + memset(&src_svm->sev_es, 0, sizeof(src_svm->sev_es)); + src_svm->vmcb->control.ghcb_gpa = INVALID_PAGE; + src_svm->vmcb->control.vmsa_pa = INVALID_PAGE; + src_vcpu->arch.guest_state_protected = false; + } + to_kvm_svm(src)->sev_info.es_active = false; + to_kvm_svm(dst)->sev_info.es_active = true; + + return 0; +} + +int svm_vm_migrate_from(struct kvm *kvm, unsigned int source_fd) +{ + struct kvm_sev_info *dst_sev = &to_kvm_svm(kvm)->sev_info; + struct kvm_sev_info *src_sev, *cg_cleanup_sev; + struct file *source_kvm_file; + struct kvm *source_kvm; + bool charged = false; + int ret; + + source_kvm_file = fget(source_fd); + if (!file_is_kvm(source_kvm_file)) { + ret = -EBADF; + goto out_fput; + } + + source_kvm = source_kvm_file->private_data; + ret = sev_lock_two_vms(kvm, source_kvm); + if (ret) + goto out_fput; + + if (sev_guest(kvm) || !sev_guest(source_kvm)) { + ret = -EINVAL; + goto out_unlock; + } + + src_sev = &to_kvm_svm(source_kvm)->sev_info; + + /* + * VMs mirroring src's encryption context rely on it to keep the + * ASID allocated, but below we are clearing src_sev->asid. + */ + if (src_sev->num_mirrored_vms) { + ret = -EBUSY; + goto out_unlock; + } + + dst_sev->misc_cg = get_current_misc_cg(); + cg_cleanup_sev = dst_sev; + if (dst_sev->misc_cg != src_sev->misc_cg) { + ret = sev_misc_cg_try_charge(dst_sev); + if (ret) + goto out_dst_cgroup; + charged = true; + } + + ret = sev_lock_vcpus_for_migration(kvm); + if (ret) + goto out_dst_cgroup; + ret = sev_lock_vcpus_for_migration(source_kvm); + if (ret) + goto out_dst_vcpu; + + if (sev_es_guest(source_kvm)) { + ret = sev_es_migrate_from(kvm, source_kvm); + if (ret) + goto out_source_vcpu; + } + sev_migrate_from(dst_sev, src_sev); + kvm_vm_dead(source_kvm); + cg_cleanup_sev = src_sev; + ret = 0; + +out_source_vcpu: + sev_unlock_vcpus_for_migration(source_kvm); +out_dst_vcpu: + sev_unlock_vcpus_for_migration(kvm); +out_dst_cgroup: + /* Operates on the source on success, on the destination on failure. */ + if (charged) + sev_misc_cg_uncharge(cg_cleanup_sev); + put_misc_cg(cg_cleanup_sev->misc_cg); + cg_cleanup_sev->misc_cg = NULL; +out_unlock: + sev_unlock_two_vms(kvm, source_kvm); +out_fput: + if (source_kvm_file) + fput(source_kvm_file); + return ret; +} + int svm_mem_enc_op(struct kvm *kvm, void __user *argp) { struct kvm_sev_cmd sev_cmd; @@ -1554,7 +1778,7 @@ int svm_mem_enc_op(struct kvm *kvm, void __user *argp) /* Only the enc_context_owner handles some memory enc operations. */ if (is_mirroring_enc_context(kvm) && - !cmd_allowed_from_miror(sev_cmd.id)) { + !is_cmd_allowed_from_mirror(sev_cmd.id)) { r = -EINVAL; goto out; } @@ -1751,71 +1975,60 @@ int svm_vm_copy_asid_from(struct kvm *kvm, unsigned int source_fd) { struct file *source_kvm_file; struct kvm *source_kvm; - struct kvm_sev_info source_sev, *mirror_sev; + struct kvm_sev_info *source_sev, *mirror_sev; int ret; source_kvm_file = fget(source_fd); if (!file_is_kvm(source_kvm_file)) { ret = -EBADF; - goto e_source_put; + goto e_source_fput; } source_kvm = source_kvm_file->private_data; - mutex_lock(&source_kvm->lock); - - if (!sev_guest(source_kvm)) { - ret = -EINVAL; - goto e_source_unlock; - } + ret = sev_lock_two_vms(kvm, source_kvm); + if (ret) + goto e_source_fput; - /* Mirrors of mirrors should work, but let's not get silly */ - if (is_mirroring_enc_context(source_kvm) || source_kvm == kvm) { + /* + * Mirrors of mirrors should work, but let's not get silly. Also + * disallow out-of-band SEV/SEV-ES init if the target is already an + * SEV guest, or if vCPUs have been created. KVM relies on vCPUs being + * created after SEV/SEV-ES initialization, e.g. to init intercepts. + */ + if (sev_guest(kvm) || !sev_guest(source_kvm) || + is_mirroring_enc_context(source_kvm) || kvm->created_vcpus) { ret = -EINVAL; - goto e_source_unlock; + goto e_unlock; } - memcpy(&source_sev, &to_kvm_svm(source_kvm)->sev_info, - sizeof(source_sev)); - /* * The mirror kvm holds an enc_context_owner ref so its asid can't * disappear until we're done with it */ + source_sev = &to_kvm_svm(source_kvm)->sev_info; kvm_get_kvm(source_kvm); - - fput(source_kvm_file); - mutex_unlock(&source_kvm->lock); - mutex_lock(&kvm->lock); - - if (sev_guest(kvm)) { - ret = -EINVAL; - goto e_mirror_unlock; - } + source_sev->num_mirrored_vms++; /* Set enc_context_owner and copy its encryption context over */ mirror_sev = &to_kvm_svm(kvm)->sev_info; mirror_sev->enc_context_owner = source_kvm; mirror_sev->active = true; - mirror_sev->asid = source_sev.asid; - mirror_sev->fd = source_sev.fd; - mirror_sev->es_active = source_sev.es_active; - mirror_sev->handle = source_sev.handle; + mirror_sev->asid = source_sev->asid; + mirror_sev->fd = source_sev->fd; + mirror_sev->es_active = source_sev->es_active; + mirror_sev->handle = source_sev->handle; + INIT_LIST_HEAD(&mirror_sev->regions_list); + ret = 0; + /* * Do not copy ap_jump_table. Since the mirror does not share the same * KVM contexts as the original, and they may have different * memory-views. */ - mutex_unlock(&kvm->lock); - return 0; - -e_mirror_unlock: - mutex_unlock(&kvm->lock); - kvm_put_kvm(source_kvm); - return ret; -e_source_unlock: - mutex_unlock(&source_kvm->lock); -e_source_put: +e_unlock: + sev_unlock_two_vms(kvm, source_kvm); +e_source_fput: if (source_kvm_file) fput(source_kvm_file); return ret; @@ -1827,17 +2040,24 @@ void sev_vm_destroy(struct kvm *kvm) struct list_head *head = &sev->regions_list; struct list_head *pos, *q; + WARN_ON(sev->num_mirrored_vms); + if (!sev_guest(kvm)) return; /* If this is a mirror_kvm release the enc_context_owner and skip sev cleanup */ if (is_mirroring_enc_context(kvm)) { - kvm_put_kvm(sev->enc_context_owner); + struct kvm *owner_kvm = sev->enc_context_owner; + struct kvm_sev_info *owner_sev = &to_kvm_svm(owner_kvm)->sev_info; + + mutex_lock(&owner_kvm->lock); + if (!WARN_ON(!owner_sev->num_mirrored_vms)) + owner_sev->num_mirrored_vms--; + mutex_unlock(&owner_kvm->lock); + kvm_put_kvm(owner_kvm); return; } - mutex_lock(&kvm->lock); - /* * Ensure that all guest tagged cache entries are flushed before * releasing the pages back to the system for use. CLFLUSH will @@ -1857,8 +2077,6 @@ void sev_vm_destroy(struct kvm *kvm) } } - mutex_unlock(&kvm->lock); - sev_unbind_asid(kvm, sev->handle); sev_asid_free(sev); } @@ -2038,16 +2256,16 @@ void sev_free_vcpu(struct kvm_vcpu *vcpu) svm = to_svm(vcpu); if (vcpu->arch.guest_state_protected) - sev_flush_guest_memory(svm, svm->vmsa, PAGE_SIZE); - __free_page(virt_to_page(svm->vmsa)); + sev_flush_guest_memory(svm, svm->sev_es.vmsa, PAGE_SIZE); + __free_page(virt_to_page(svm->sev_es.vmsa)); - if (svm->ghcb_sa_free) - kfree(svm->ghcb_sa); + if (svm->sev_es.ghcb_sa_free) + kfree(svm->sev_es.ghcb_sa); } static void dump_ghcb(struct vcpu_svm *svm) { - struct ghcb *ghcb = svm->ghcb; + struct ghcb *ghcb = svm->sev_es.ghcb; unsigned int nbits; /* Re-use the dump_invalid_vmcb module parameter */ @@ -2073,7 +2291,7 @@ static void dump_ghcb(struct vcpu_svm *svm) static void sev_es_sync_to_ghcb(struct vcpu_svm *svm) { struct kvm_vcpu *vcpu = &svm->vcpu; - struct ghcb *ghcb = svm->ghcb; + struct ghcb *ghcb = svm->sev_es.ghcb; /* * The GHCB protocol so far allows for the following data @@ -2093,7 +2311,7 @@ static void sev_es_sync_from_ghcb(struct vcpu_svm *svm) { struct vmcb_control_area *control = &svm->vmcb->control; struct kvm_vcpu *vcpu = &svm->vcpu; - struct ghcb *ghcb = svm->ghcb; + struct ghcb *ghcb = svm->sev_es.ghcb; u64 exit_code; /* @@ -2140,7 +2358,7 @@ static int sev_es_validate_vmgexit(struct vcpu_svm *svm) struct ghcb *ghcb; u64 exit_code = 0; - ghcb = svm->ghcb; + ghcb = svm->sev_es.ghcb; /* Only GHCB Usage code 0 is supported */ if (ghcb->ghcb_usage) @@ -2258,33 +2476,34 @@ vmgexit_err: void sev_es_unmap_ghcb(struct vcpu_svm *svm) { - if (!svm->ghcb) + if (!svm->sev_es.ghcb) return; - if (svm->ghcb_sa_free) { + if (svm->sev_es.ghcb_sa_free) { /* * The scratch area lives outside the GHCB, so there is a * buffer that, depending on the operation performed, may * need to be synced, then freed. */ - if (svm->ghcb_sa_sync) { + if (svm->sev_es.ghcb_sa_sync) { kvm_write_guest(svm->vcpu.kvm, - ghcb_get_sw_scratch(svm->ghcb), - svm->ghcb_sa, svm->ghcb_sa_len); - svm->ghcb_sa_sync = false; + ghcb_get_sw_scratch(svm->sev_es.ghcb), + svm->sev_es.ghcb_sa, + svm->sev_es.ghcb_sa_len); + svm->sev_es.ghcb_sa_sync = false; } - kfree(svm->ghcb_sa); - svm->ghcb_sa = NULL; - svm->ghcb_sa_free = false; + kfree(svm->sev_es.ghcb_sa); + svm->sev_es.ghcb_sa = NULL; + svm->sev_es.ghcb_sa_free = false; } - trace_kvm_vmgexit_exit(svm->vcpu.vcpu_id, svm->ghcb); + trace_kvm_vmgexit_exit(svm->vcpu.vcpu_id, svm->sev_es.ghcb); sev_es_sync_to_ghcb(svm); - kvm_vcpu_unmap(&svm->vcpu, &svm->ghcb_map, true); - svm->ghcb = NULL; + kvm_vcpu_unmap(&svm->vcpu, &svm->sev_es.ghcb_map, true); + svm->sev_es.ghcb = NULL; } void pre_sev_run(struct vcpu_svm *svm, int cpu) @@ -2314,7 +2533,7 @@ void pre_sev_run(struct vcpu_svm *svm, int cpu) static bool setup_vmgexit_scratch(struct vcpu_svm *svm, bool sync, u64 len) { struct vmcb_control_area *control = &svm->vmcb->control; - struct ghcb *ghcb = svm->ghcb; + struct ghcb *ghcb = svm->sev_es.ghcb; u64 ghcb_scratch_beg, ghcb_scratch_end; u64 scratch_gpa_beg, scratch_gpa_end; void *scratch_va; @@ -2350,7 +2569,7 @@ static bool setup_vmgexit_scratch(struct vcpu_svm *svm, bool sync, u64 len) return false; } - scratch_va = (void *)svm->ghcb; + scratch_va = (void *)svm->sev_es.ghcb; scratch_va += (scratch_gpa_beg - control->ghcb_gpa); } else { /* @@ -2380,12 +2599,12 @@ static bool setup_vmgexit_scratch(struct vcpu_svm *svm, bool sync, u64 len) * the vCPU next time (i.e. a read was requested so the data * must be written back to the guest memory). */ - svm->ghcb_sa_sync = sync; - svm->ghcb_sa_free = true; + svm->sev_es.ghcb_sa_sync = sync; + svm->sev_es.ghcb_sa_free = true; } - svm->ghcb_sa = scratch_va; - svm->ghcb_sa_len = len; + svm->sev_es.ghcb_sa = scratch_va; + svm->sev_es.ghcb_sa_len = len; return true; } @@ -2504,15 +2723,15 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu) return -EINVAL; } - if (kvm_vcpu_map(vcpu, ghcb_gpa >> PAGE_SHIFT, &svm->ghcb_map)) { + if (kvm_vcpu_map(vcpu, ghcb_gpa >> PAGE_SHIFT, &svm->sev_es.ghcb_map)) { /* Unable to map GHCB from guest */ vcpu_unimpl(vcpu, "vmgexit: error mapping GHCB [%#llx] from guest\n", ghcb_gpa); return -EINVAL; } - svm->ghcb = svm->ghcb_map.hva; - ghcb = svm->ghcb_map.hva; + svm->sev_es.ghcb = svm->sev_es.ghcb_map.hva; + ghcb = svm->sev_es.ghcb_map.hva; trace_kvm_vmgexit_enter(vcpu->vcpu_id, ghcb); @@ -2535,7 +2754,7 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu) ret = kvm_sev_es_mmio_read(vcpu, control->exit_info_1, control->exit_info_2, - svm->ghcb_sa); + svm->sev_es.ghcb_sa); break; case SVM_VMGEXIT_MMIO_WRITE: if (!setup_vmgexit_scratch(svm, false, control->exit_info_2)) @@ -2544,7 +2763,7 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu) ret = kvm_sev_es_mmio_write(vcpu, control->exit_info_1, control->exit_info_2, - svm->ghcb_sa); + svm->sev_es.ghcb_sa); break; case SVM_VMGEXIT_NMI_COMPLETE: ret = svm_invoke_exit_handler(vcpu, SVM_EXIT_IRET); @@ -2604,7 +2823,8 @@ int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in) if (!setup_vmgexit_scratch(svm, in, bytes)) return -EINVAL; - return kvm_sev_es_string_io(&svm->vcpu, size, port, svm->ghcb_sa, count, in); + return kvm_sev_es_string_io(&svm->vcpu, size, port, svm->sev_es.ghcb_sa, + count, in); } void sev_es_init_vmcb(struct vcpu_svm *svm) @@ -2619,7 +2839,7 @@ void sev_es_init_vmcb(struct vcpu_svm *svm) * VMCB page. Do not include the encryption mask on the VMSA physical * address since hardware will access it using the guest key. */ - svm->vmcb->control.vmsa_pa = __pa(svm->vmsa); + svm->vmcb->control.vmsa_pa = __pa(svm->sev_es.vmsa); /* Can't intercept CR register access, HV can't modify CR registers */ svm_clr_intercept(svm, INTERCEPT_CR0_READ); @@ -2691,8 +2911,8 @@ void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector) struct vcpu_svm *svm = to_svm(vcpu); /* First SIPI: Use the values as initially set by the VMM */ - if (!svm->received_first_sipi) { - svm->received_first_sipi = true; + if (!svm->sev_es.received_first_sipi) { + svm->sev_es.received_first_sipi = true; return; } @@ -2701,8 +2921,8 @@ void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector) * the guest will set the CS and RIP. Set SW_EXIT_INFO_2 to a * non-zero value. */ - if (!svm->ghcb) + if (!svm->sev_es.ghcb) return; - ghcb_set_sw_exit_info_2(svm->ghcb, 1); + ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, 1); } diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index b36ca4e476c2..d0f68d11ec70 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -1452,7 +1452,7 @@ static int svm_create_vcpu(struct kvm_vcpu *vcpu) svm_switch_vmcb(svm, &svm->vmcb01); if (vmsa_page) - svm->vmsa = page_address(vmsa_page); + svm->sev_es.vmsa = page_address(vmsa_page); svm->guest_state_loaded = false; @@ -2835,11 +2835,11 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) static int svm_complete_emulated_msr(struct kvm_vcpu *vcpu, int err) { struct vcpu_svm *svm = to_svm(vcpu); - if (!err || !sev_es_guest(vcpu->kvm) || WARN_ON_ONCE(!svm->ghcb)) + if (!err || !sev_es_guest(vcpu->kvm) || WARN_ON_ONCE(!svm->sev_es.ghcb)) return kvm_complete_insn_gp(vcpu, err); - ghcb_set_sw_exit_info_1(svm->ghcb, 1); - ghcb_set_sw_exit_info_2(svm->ghcb, + ghcb_set_sw_exit_info_1(svm->sev_es.ghcb, 1); + ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, X86_TRAP_GP | SVM_EVTINJ_TYPE_EXEPT | SVM_EVTINJ_VALID); @@ -3121,11 +3121,6 @@ static int invpcid_interception(struct kvm_vcpu *vcpu) type = svm->vmcb->control.exit_info_2; gva = svm->vmcb->control.exit_info_1; - if (type > 3) { - kvm_inject_gp(vcpu, 0); - return 1; - } - return kvm_handle_invpcid(vcpu, type, gva); } @@ -4656,7 +4651,6 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .load_eoi_exitmap = svm_load_eoi_exitmap, .hwapic_irr_update = svm_hwapic_irr_update, .hwapic_isr_update = svm_hwapic_isr_update, - .sync_pir_to_irr = kvm_lapic_find_highest_irr, .apicv_post_state_restore = avic_post_state_restore, .set_tss_addr = svm_set_tss_addr, @@ -4701,6 +4695,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .mem_enc_unreg_region = svm_unregister_enc_region, .vm_copy_enc_context_from = svm_vm_copy_asid_from, + .vm_move_enc_context_from = svm_vm_migrate_from, .can_emulate_instruction = svm_can_emulate_instruction, diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 5e9510d4574e..1c7306c370fa 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -79,7 +79,9 @@ struct kvm_sev_info { struct list_head regions_list; /* List of registered regions */ u64 ap_jump_table; /* SEV-ES AP Jump Table address */ struct kvm *enc_context_owner; /* Owner of copied encryption context */ + unsigned long num_mirrored_vms; /* Number of VMs sharing this ASID */ struct misc_cg *misc_cg; /* For misc cgroup accounting */ + atomic_t migration_in_progress; }; struct kvm_svm { @@ -123,6 +125,20 @@ struct svm_nested_state { bool initialized; }; +struct vcpu_sev_es_state { + /* SEV-ES support */ + struct vmcb_save_area *vmsa; + struct ghcb *ghcb; + struct kvm_host_map ghcb_map; + bool received_first_sipi; + + /* SEV-ES scratch area support */ + void *ghcb_sa; + u32 ghcb_sa_len; + bool ghcb_sa_sync; + bool ghcb_sa_free; +}; + struct vcpu_svm { struct kvm_vcpu vcpu; /* vmcb always points at current_vmcb->ptr, it's purely a shorthand. */ @@ -186,17 +202,7 @@ struct vcpu_svm { DECLARE_BITMAP(write, MAX_DIRECT_ACCESS_MSRS); } shadow_msr_intercept; - /* SEV-ES support */ - struct vmcb_save_area *vmsa; - struct ghcb *ghcb; - struct kvm_host_map ghcb_map; - bool received_first_sipi; - - /* SEV-ES scratch area support */ - void *ghcb_sa; - u32 ghcb_sa_len; - bool ghcb_sa_sync; - bool ghcb_sa_free; + struct vcpu_sev_es_state sev_es; bool guest_state_loaded; }; @@ -242,7 +248,7 @@ static __always_inline bool sev_es_guest(struct kvm *kvm) #ifdef CONFIG_KVM_AMD_SEV struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; - return sev_guest(kvm) && sev->es_active; + return sev->es_active && !WARN_ON_ONCE(!sev->active); #else return false; #endif @@ -558,6 +564,7 @@ int svm_register_enc_region(struct kvm *kvm, int svm_unregister_enc_region(struct kvm *kvm, struct kvm_enc_region *range); int svm_vm_copy_asid_from(struct kvm *kvm, unsigned int source_fd); +int svm_vm_migrate_from(struct kvm *kvm, unsigned int source_fd); void pre_sev_run(struct vcpu_svm *svm, int cpu); void __init sev_set_cpu_caps(void); void __init sev_hardware_setup(void); diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index b4ee5e9f9e20..64f2828035c2 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -525,67 +525,19 @@ static int nested_vmx_check_tpr_shadow_controls(struct kvm_vcpu *vcpu, } /* - * Check if MSR is intercepted for L01 MSR bitmap. + * For x2APIC MSRs, ignore the vmcs01 bitmap. L1 can enable x2APIC without L1 + * itself utilizing x2APIC. All MSRs were previously set to be intercepted, + * only the "disable intercept" case needs to be handled. */ -static bool msr_write_intercepted_l01(struct kvm_vcpu *vcpu, u32 msr) +static void nested_vmx_disable_intercept_for_x2apic_msr(unsigned long *msr_bitmap_l1, + unsigned long *msr_bitmap_l0, + u32 msr, int type) { - unsigned long *msr_bitmap; - int f = sizeof(unsigned long); + if (type & MSR_TYPE_R && !vmx_test_msr_bitmap_read(msr_bitmap_l1, msr)) + vmx_clear_msr_bitmap_read(msr_bitmap_l0, msr); - if (!cpu_has_vmx_msr_bitmap()) - return true; - - msr_bitmap = to_vmx(vcpu)->vmcs01.msr_bitmap; - - if (msr <= 0x1fff) { - return !!test_bit(msr, msr_bitmap + 0x800 / f); - } else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) { - msr &= 0x1fff; - return !!test_bit(msr, msr_bitmap + 0xc00 / f); - } - - return true; -} - -/* - * If a msr is allowed by L0, we should check whether it is allowed by L1. - * The corresponding bit will be cleared unless both of L0 and L1 allow it. - */ -static void nested_vmx_disable_intercept_for_msr(unsigned long *msr_bitmap_l1, - unsigned long *msr_bitmap_nested, - u32 msr, int type) -{ - int f = sizeof(unsigned long); - - /* - * See Intel PRM Vol. 3, 20.6.9 (MSR-Bitmap Address). Early manuals - * have the write-low and read-high bitmap offsets the wrong way round. - * We can control MSRs 0x00000000-0x00001fff and 0xc0000000-0xc0001fff. - */ - if (msr <= 0x1fff) { - if (type & MSR_TYPE_R && - !test_bit(msr, msr_bitmap_l1 + 0x000 / f)) - /* read-low */ - __clear_bit(msr, msr_bitmap_nested + 0x000 / f); - - if (type & MSR_TYPE_W && - !test_bit(msr, msr_bitmap_l1 + 0x800 / f)) - /* write-low */ - __clear_bit(msr, msr_bitmap_nested + 0x800 / f); - - } else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) { - msr &= 0x1fff; - if (type & MSR_TYPE_R && - !test_bit(msr, msr_bitmap_l1 + 0x400 / f)) - /* read-high */ - __clear_bit(msr, msr_bitmap_nested + 0x400 / f); - - if (type & MSR_TYPE_W && - !test_bit(msr, msr_bitmap_l1 + 0xc00 / f)) - /* write-high */ - __clear_bit(msr, msr_bitmap_nested + 0xc00 / f); - - } + if (type & MSR_TYPE_W && !vmx_test_msr_bitmap_write(msr_bitmap_l1, msr)) + vmx_clear_msr_bitmap_write(msr_bitmap_l0, msr); } static inline void enable_x2apic_msr_intercepts(unsigned long *msr_bitmap) @@ -600,6 +552,34 @@ static inline void enable_x2apic_msr_intercepts(unsigned long *msr_bitmap) } } +#define BUILD_NVMX_MSR_INTERCEPT_HELPER(rw) \ +static inline \ +void nested_vmx_set_msr_##rw##_intercept(struct vcpu_vmx *vmx, \ + unsigned long *msr_bitmap_l1, \ + unsigned long *msr_bitmap_l0, u32 msr) \ +{ \ + if (vmx_test_msr_bitmap_##rw(vmx->vmcs01.msr_bitmap, msr) || \ + vmx_test_msr_bitmap_##rw(msr_bitmap_l1, msr)) \ + vmx_set_msr_bitmap_##rw(msr_bitmap_l0, msr); \ + else \ + vmx_clear_msr_bitmap_##rw(msr_bitmap_l0, msr); \ +} +BUILD_NVMX_MSR_INTERCEPT_HELPER(read) +BUILD_NVMX_MSR_INTERCEPT_HELPER(write) + +static inline void nested_vmx_set_intercept_for_msr(struct vcpu_vmx *vmx, + unsigned long *msr_bitmap_l1, + unsigned long *msr_bitmap_l0, + u32 msr, int types) +{ + if (types & MSR_TYPE_R) + nested_vmx_set_msr_read_intercept(vmx, msr_bitmap_l1, + msr_bitmap_l0, msr); + if (types & MSR_TYPE_W) + nested_vmx_set_msr_write_intercept(vmx, msr_bitmap_l1, + msr_bitmap_l0, msr); +} + /* * Merge L0's and L1's MSR bitmap, return false to indicate that * we do not use the hardware. @@ -607,10 +587,11 @@ static inline void enable_x2apic_msr_intercepts(unsigned long *msr_bitmap) static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { + struct vcpu_vmx *vmx = to_vmx(vcpu); int msr; unsigned long *msr_bitmap_l1; - unsigned long *msr_bitmap_l0 = to_vmx(vcpu)->nested.vmcs02.msr_bitmap; - struct kvm_host_map *map = &to_vmx(vcpu)->nested.msr_bitmap_map; + unsigned long *msr_bitmap_l0 = vmx->nested.vmcs02.msr_bitmap; + struct kvm_host_map *map = &vmx->nested.msr_bitmap_map; /* Nothing to do if the MSR bitmap is not in use. */ if (!cpu_has_vmx_msr_bitmap() || @@ -625,7 +606,7 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu, /* * To keep the control flow simple, pay eight 8-byte writes (sixteen * 4-byte writes on 32-bit systems) up front to enable intercepts for - * the x2APIC MSR range and selectively disable them below. + * the x2APIC MSR range and selectively toggle those relevant to L2. */ enable_x2apic_msr_intercepts(msr_bitmap_l0); @@ -644,61 +625,44 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu, } } - nested_vmx_disable_intercept_for_msr( + nested_vmx_disable_intercept_for_x2apic_msr( msr_bitmap_l1, msr_bitmap_l0, X2APIC_MSR(APIC_TASKPRI), MSR_TYPE_R | MSR_TYPE_W); if (nested_cpu_has_vid(vmcs12)) { - nested_vmx_disable_intercept_for_msr( + nested_vmx_disable_intercept_for_x2apic_msr( msr_bitmap_l1, msr_bitmap_l0, X2APIC_MSR(APIC_EOI), MSR_TYPE_W); - nested_vmx_disable_intercept_for_msr( + nested_vmx_disable_intercept_for_x2apic_msr( msr_bitmap_l1, msr_bitmap_l0, X2APIC_MSR(APIC_SELF_IPI), MSR_TYPE_W); } } - /* KVM unconditionally exposes the FS/GS base MSRs to L1. */ + /* + * Always check vmcs01's bitmap to honor userspace MSR filters and any + * other runtime changes to vmcs01's bitmap, e.g. dynamic pass-through. + */ #ifdef CONFIG_X86_64 - nested_vmx_disable_intercept_for_msr(msr_bitmap_l1, msr_bitmap_l0, - MSR_FS_BASE, MSR_TYPE_RW); + nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0, + MSR_FS_BASE, MSR_TYPE_RW); - nested_vmx_disable_intercept_for_msr(msr_bitmap_l1, msr_bitmap_l0, - MSR_GS_BASE, MSR_TYPE_RW); + nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0, + MSR_GS_BASE, MSR_TYPE_RW); - nested_vmx_disable_intercept_for_msr(msr_bitmap_l1, msr_bitmap_l0, - MSR_KERNEL_GS_BASE, MSR_TYPE_RW); + nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0, + MSR_KERNEL_GS_BASE, MSR_TYPE_RW); #endif + nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0, + MSR_IA32_SPEC_CTRL, MSR_TYPE_RW); - /* - * Checking the L0->L1 bitmap is trying to verify two things: - * - * 1. L0 gave a permission to L1 to actually passthrough the MSR. This - * ensures that we do not accidentally generate an L02 MSR bitmap - * from the L12 MSR bitmap that is too permissive. - * 2. That L1 or L2s have actually used the MSR. This avoids - * unnecessarily merging of the bitmap if the MSR is unused. This - * works properly because we only update the L01 MSR bitmap lazily. - * So even if L0 should pass L1 these MSRs, the L01 bitmap is only - * updated to reflect this when L1 (or its L2s) actually write to - * the MSR. - */ - if (!msr_write_intercepted_l01(vcpu, MSR_IA32_SPEC_CTRL)) - nested_vmx_disable_intercept_for_msr( - msr_bitmap_l1, msr_bitmap_l0, - MSR_IA32_SPEC_CTRL, - MSR_TYPE_R | MSR_TYPE_W); - - if (!msr_write_intercepted_l01(vcpu, MSR_IA32_PRED_CMD)) - nested_vmx_disable_intercept_for_msr( - msr_bitmap_l1, msr_bitmap_l0, - MSR_IA32_PRED_CMD, - MSR_TYPE_W); + nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0, + MSR_IA32_PRED_CMD, MSR_TYPE_W); - kvm_vcpu_unmap(vcpu, &to_vmx(vcpu)->nested.msr_bitmap_map, false); + kvm_vcpu_unmap(vcpu, &vmx->nested.msr_bitmap_map, false); return true; } @@ -706,33 +670,39 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu, static void nested_cache_shadow_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { - struct kvm_host_map map; - struct vmcs12 *shadow; + struct vcpu_vmx *vmx = to_vmx(vcpu); + struct gfn_to_hva_cache *ghc = &vmx->nested.shadow_vmcs12_cache; if (!nested_cpu_has_shadow_vmcs(vmcs12) || vmcs12->vmcs_link_pointer == INVALID_GPA) return; - shadow = get_shadow_vmcs12(vcpu); - - if (kvm_vcpu_map(vcpu, gpa_to_gfn(vmcs12->vmcs_link_pointer), &map)) + if (ghc->gpa != vmcs12->vmcs_link_pointer && + kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc, + vmcs12->vmcs_link_pointer, VMCS12_SIZE)) return; - memcpy(shadow, map.hva, VMCS12_SIZE); - kvm_vcpu_unmap(vcpu, &map, false); + kvm_read_guest_cached(vmx->vcpu.kvm, ghc, get_shadow_vmcs12(vcpu), + VMCS12_SIZE); } static void nested_flush_cached_shadow_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { struct vcpu_vmx *vmx = to_vmx(vcpu); + struct gfn_to_hva_cache *ghc = &vmx->nested.shadow_vmcs12_cache; if (!nested_cpu_has_shadow_vmcs(vmcs12) || vmcs12->vmcs_link_pointer == INVALID_GPA) return; - kvm_write_guest(vmx->vcpu.kvm, vmcs12->vmcs_link_pointer, - get_shadow_vmcs12(vcpu), VMCS12_SIZE); + if (ghc->gpa != vmcs12->vmcs_link_pointer && + kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc, + vmcs12->vmcs_link_pointer, VMCS12_SIZE)) + return; + + kvm_write_guest_cached(vmx->vcpu.kvm, ghc, get_shadow_vmcs12(vcpu), + VMCS12_SIZE); } /* @@ -1192,29 +1162,26 @@ static void nested_vmx_transition_tlb_flush(struct kvm_vcpu *vcpu, WARN_ON(!enable_vpid); /* - * If VPID is enabled and used by vmc12, but L2 does not have a unique - * TLB tag (ASID), i.e. EPT is disabled and KVM was unable to allocate - * a VPID for L2, flush the current context as the effective ASID is - * common to both L1 and L2. - * - * Defer the flush so that it runs after vmcs02.EPTP has been set by - * KVM_REQ_LOAD_MMU_PGD (if nested EPT is enabled) and to avoid - * redundant flushes further down the nested pipeline. - * - * If a TLB flush isn't required due to any of the above, and vpid12 is - * changing then the new "virtual" VPID (vpid12) will reuse the same - * "real" VPID (vpid02), and so needs to be flushed. There's no direct - * mapping between vpid02 and vpid12, vpid02 is per-vCPU and reused for - * all nested vCPUs. Remember, a flush on VM-Enter does not invalidate - * guest-physical mappings, so there is no need to sync the nEPT MMU. + * VPID is enabled and in use by vmcs12. If vpid12 is changing, then + * emulate a guest TLB flush as KVM does not track vpid12 history nor + * is the VPID incorporated into the MMU context. I.e. KVM must assume + * that the new vpid12 has never been used and thus represents a new + * guest ASID that cannot have entries in the TLB. */ - if (!nested_has_guest_tlb_tag(vcpu)) { - kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu); - } else if (is_vmenter && - vmcs12->virtual_processor_id != vmx->nested.last_vpid) { + if (is_vmenter && vmcs12->virtual_processor_id != vmx->nested.last_vpid) { vmx->nested.last_vpid = vmcs12->virtual_processor_id; - vpid_sync_context(nested_get_vpid02(vcpu)); + kvm_make_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu); + return; } + + /* + * If VPID is enabled, used by vmc12, and vpid12 is not changing but + * does not have a unique TLB tag (ASID), i.e. EPT is disabled and + * KVM was unable to allocate a VPID for L2, flush the current context + * as the effective ASID is common to both L1 and L2. + */ + if (!nested_has_guest_tlb_tag(vcpu)) + kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu); } static bool is_bitwise_subset(u64 superset, u64 subset, u64 mask) @@ -2866,6 +2833,17 @@ static int nested_vmx_check_controls(struct kvm_vcpu *vcpu, return 0; } +static int nested_vmx_check_address_space_size(struct kvm_vcpu *vcpu, + struct vmcs12 *vmcs12) +{ +#ifdef CONFIG_X86_64 + if (CC(!!(vmcs12->vm_exit_controls & VM_EXIT_HOST_ADDR_SPACE_SIZE) != + !!(vcpu->arch.efer & EFER_LMA))) + return -EINVAL; +#endif + return 0; +} + static int nested_vmx_check_host_state(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { @@ -2890,18 +2868,16 @@ static int nested_vmx_check_host_state(struct kvm_vcpu *vcpu, return -EINVAL; #ifdef CONFIG_X86_64 - ia32e = !!(vcpu->arch.efer & EFER_LMA); + ia32e = !!(vmcs12->vm_exit_controls & VM_EXIT_HOST_ADDR_SPACE_SIZE); #else ia32e = false; #endif if (ia32e) { - if (CC(!(vmcs12->vm_exit_controls & VM_EXIT_HOST_ADDR_SPACE_SIZE)) || - CC(!(vmcs12->host_cr4 & X86_CR4_PAE))) + if (CC(!(vmcs12->host_cr4 & X86_CR4_PAE))) return -EINVAL; } else { - if (CC(vmcs12->vm_exit_controls & VM_EXIT_HOST_ADDR_SPACE_SIZE) || - CC(vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE) || + if (CC(vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE) || CC(vmcs12->host_cr4 & X86_CR4_PCIDE) || CC((vmcs12->host_rip) >> 32)) return -EINVAL; @@ -2946,9 +2922,9 @@ static int nested_vmx_check_host_state(struct kvm_vcpu *vcpu, static int nested_vmx_check_vmcs_link_ptr(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { - int r = 0; - struct vmcs12 *shadow; - struct kvm_host_map map; + struct vcpu_vmx *vmx = to_vmx(vcpu); + struct gfn_to_hva_cache *ghc = &vmx->nested.shadow_vmcs12_cache; + struct vmcs_hdr hdr; if (vmcs12->vmcs_link_pointer == INVALID_GPA) return 0; @@ -2956,17 +2932,21 @@ static int nested_vmx_check_vmcs_link_ptr(struct kvm_vcpu *vcpu, if (CC(!page_address_valid(vcpu, vmcs12->vmcs_link_pointer))) return -EINVAL; - if (CC(kvm_vcpu_map(vcpu, gpa_to_gfn(vmcs12->vmcs_link_pointer), &map))) - return -EINVAL; + if (ghc->gpa != vmcs12->vmcs_link_pointer && + CC(kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc, + vmcs12->vmcs_link_pointer, VMCS12_SIZE))) + return -EINVAL; - shadow = map.hva; + if (CC(kvm_read_guest_offset_cached(vcpu->kvm, ghc, &hdr, + offsetof(struct vmcs12, hdr), + sizeof(hdr)))) + return -EINVAL; - if (CC(shadow->hdr.revision_id != VMCS12_REVISION) || - CC(shadow->hdr.shadow_vmcs != nested_cpu_has_shadow_vmcs(vmcs12))) - r = -EINVAL; + if (CC(hdr.revision_id != VMCS12_REVISION) || + CC(hdr.shadow_vmcs != nested_cpu_has_shadow_vmcs(vmcs12))) + return -EINVAL; - kvm_vcpu_unmap(vcpu, &map, false); - return r; + return 0; } /* @@ -3361,8 +3341,7 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, }; u32 failed_index; - if (kvm_check_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu)) - kvm_vcpu_flush_tlb_current(vcpu); + kvm_service_local_tlb_flush_requests(vcpu); evaluate_pending_interrupts = exec_controls_get(vmx) & (CPU_BASED_INTR_WINDOW_EXITING | CPU_BASED_NMI_WINDOW_EXITING); @@ -3571,6 +3550,9 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) if (nested_vmx_check_controls(vcpu, vmcs12)) return nested_vmx_fail(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD); + if (nested_vmx_check_address_space_size(vcpu, vmcs12)) + return nested_vmx_fail(vcpu, VMXERR_ENTRY_INVALID_HOST_STATE_FIELD); + if (nested_vmx_check_host_state(vcpu, vmcs12)) return nested_vmx_fail(vcpu, VMXERR_ENTRY_INVALID_HOST_STATE_FIELD); @@ -4516,9 +4498,8 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, (void)nested_get_evmcs_page(vcpu); } - /* Service the TLB flush request for L2 before switching to L1. */ - if (kvm_check_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu)) - kvm_vcpu_flush_tlb_current(vcpu); + /* Service pending TLB flush requests for L2 before switching to L1. */ + kvm_service_local_tlb_flush_requests(vcpu); /* * VCPU_EXREG_PDPTR will be clobbered in arch/x86/kvm/vmx/vmx.h between @@ -4871,6 +4852,7 @@ static int enter_vmx_operation(struct kvm_vcpu *vcpu) if (!vmx->nested.cached_vmcs12) goto out_cached_vmcs12; + vmx->nested.shadow_vmcs12_cache.gpa = INVALID_GPA; vmx->nested.cached_shadow_vmcs12 = kzalloc(VMCS12_SIZE, GFP_KERNEL_ACCOUNT); if (!vmx->nested.cached_shadow_vmcs12) goto out_cached_shadow_vmcs12; @@ -5300,10 +5282,10 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu) return 1; if (vmx->nested.current_vmptr != vmptr) { - struct kvm_host_map map; - struct vmcs12 *new_vmcs12; + struct gfn_to_hva_cache *ghc = &vmx->nested.vmcs12_cache; + struct vmcs_hdr hdr; - if (kvm_vcpu_map(vcpu, gpa_to_gfn(vmptr), &map)) { + if (kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc, vmptr, VMCS12_SIZE)) { /* * Reads from an unbacked page return all 1s, * which means that the 32 bits located at the @@ -5314,12 +5296,16 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu) VMXERR_VMPTRLD_INCORRECT_VMCS_REVISION_ID); } - new_vmcs12 = map.hva; + if (kvm_read_guest_offset_cached(vcpu->kvm, ghc, &hdr, + offsetof(struct vmcs12, hdr), + sizeof(hdr))) { + return nested_vmx_fail(vcpu, + VMXERR_VMPTRLD_INCORRECT_VMCS_REVISION_ID); + } - if (new_vmcs12->hdr.revision_id != VMCS12_REVISION || - (new_vmcs12->hdr.shadow_vmcs && + if (hdr.revision_id != VMCS12_REVISION || + (hdr.shadow_vmcs && !nested_cpu_has_vmx_shadow_vmcs(vcpu))) { - kvm_vcpu_unmap(vcpu, &map, false); return nested_vmx_fail(vcpu, VMXERR_VMPTRLD_INCORRECT_VMCS_REVISION_ID); } @@ -5330,8 +5316,11 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu) * Load VMCS12 from guest memory since it is not already * cached. */ - memcpy(vmx->nested.cached_vmcs12, new_vmcs12, VMCS12_SIZE); - kvm_vcpu_unmap(vcpu, &map, false); + if (kvm_read_guest_cached(vcpu->kvm, ghc, vmx->nested.cached_vmcs12, + VMCS12_SIZE)) { + return nested_vmx_fail(vcpu, + VMXERR_VMPTRLD_INCORRECT_VMCS_REVISION_ID); + } set_current_vmptr(vmx, vmptr); } @@ -5379,7 +5368,7 @@ static int handle_invept(struct kvm_vcpu *vcpu) struct { u64 eptp, gpa; } operand; - int i, r; + int i, r, gpr_index; if (!(vmx->nested.msrs.secondary_ctls_high & SECONDARY_EXEC_ENABLE_EPT) || @@ -5392,7 +5381,8 @@ static int handle_invept(struct kvm_vcpu *vcpu) return 1; vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO); - type = kvm_register_read(vcpu, (vmx_instruction_info >> 28) & 0xf); + gpr_index = vmx_get_instr_info_reg2(vmx_instruction_info); + type = kvm_register_read(vcpu, gpr_index); types = (vmx->nested.msrs.ept_caps >> VMX_EPT_EXTENT_SHIFT) & 6; @@ -5459,7 +5449,7 @@ static int handle_invvpid(struct kvm_vcpu *vcpu) u64 gla; } operand; u16 vpid02; - int r; + int r, gpr_index; if (!(vmx->nested.msrs.secondary_ctls_high & SECONDARY_EXEC_ENABLE_VPID) || @@ -5472,7 +5462,8 @@ static int handle_invvpid(struct kvm_vcpu *vcpu) return 1; vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO); - type = kvm_register_read(vcpu, (vmx_instruction_info >> 28) & 0xf); + gpr_index = vmx_get_instr_info_reg2(vmx_instruction_info); + type = kvm_register_read(vcpu, gpr_index); types = (vmx->nested.msrs.vpid_caps & VMX_VPID_EXTENT_SUPPORTED_MASK) >> 8; diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c index b8e0d21b7c8a..1b7456b2177b 100644 --- a/arch/x86/kvm/vmx/pmu_intel.c +++ b/arch/x86/kvm/vmx/pmu_intel.c @@ -118,16 +118,15 @@ static struct kvm_pmc *intel_pmc_idx_to_pmc(struct kvm_pmu *pmu, int pmc_idx) } } -/* returns 0 if idx's corresponding MSR exists; otherwise returns 1. */ -static int intel_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx) +static bool intel_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx) { struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); bool fixed = idx & (1u << 30); idx &= ~(3u << 30); - return (!fixed && idx >= pmu->nr_arch_gp_counters) || - (fixed && idx >= pmu->nr_arch_fixed_counters); + return fixed ? idx < pmu->nr_arch_fixed_counters + : idx < pmu->nr_arch_gp_counters; } static struct kvm_pmc *intel_rdpmc_ecx_to_pmc(struct kvm_vcpu *vcpu, diff --git a/arch/x86/kvm/vmx/posted_intr.c b/arch/x86/kvm/vmx/posted_intr.c index 5f81ef092bd4..1c94783b5a54 100644 --- a/arch/x86/kvm/vmx/posted_intr.c +++ b/arch/x86/kvm/vmx/posted_intr.c @@ -5,6 +5,7 @@ #include <asm/cpu.h> #include "lapic.h" +#include "irq.h" #include "posted_intr.h" #include "trace.h" #include "vmx.h" @@ -77,13 +78,18 @@ after_clear_sn: pi_set_on(pi_desc); } +static bool vmx_can_use_vtd_pi(struct kvm *kvm) +{ + return irqchip_in_kernel(kvm) && enable_apicv && + kvm_arch_has_assigned_device(kvm) && + irq_remapping_cap(IRQ_POSTING_CAP); +} + void vmx_vcpu_pi_put(struct kvm_vcpu *vcpu) { struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); - if (!kvm_arch_has_assigned_device(vcpu->kvm) || - !irq_remapping_cap(IRQ_POSTING_CAP) || - !kvm_vcpu_apicv_active(vcpu)) + if (!vmx_can_use_vtd_pi(vcpu->kvm)) return; /* Set SN when the vCPU is preempted */ @@ -141,9 +147,7 @@ int pi_pre_block(struct kvm_vcpu *vcpu) struct pi_desc old, new; struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); - if (!kvm_arch_has_assigned_device(vcpu->kvm) || - !irq_remapping_cap(IRQ_POSTING_CAP) || - !kvm_vcpu_apicv_active(vcpu)) + if (!vmx_can_use_vtd_pi(vcpu->kvm)) return 0; WARN_ON(irqs_disabled()); @@ -270,9 +274,7 @@ int pi_update_irte(struct kvm *kvm, unsigned int host_irq, uint32_t guest_irq, struct vcpu_data vcpu_info; int idx, ret = 0; - if (!kvm_arch_has_assigned_device(kvm) || - !irq_remapping_cap(IRQ_POSTING_CAP) || - !kvm_vcpu_apicv_active(kvm->vcpus[0])) + if (!vmx_can_use_vtd_pi(kvm)) return 0; idx = srcu_read_lock(&kvm->irq_srcu); diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 76861b66bbcf..f90448809690 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -769,24 +769,13 @@ void vmx_update_exception_bitmap(struct kvm_vcpu *vcpu) /* * Check if MSR is intercepted for currently loaded MSR bitmap. */ -static bool msr_write_intercepted(struct kvm_vcpu *vcpu, u32 msr) +static bool msr_write_intercepted(struct vcpu_vmx *vmx, u32 msr) { - unsigned long *msr_bitmap; - int f = sizeof(unsigned long); - - if (!cpu_has_vmx_msr_bitmap()) + if (!(exec_controls_get(vmx) & CPU_BASED_USE_MSR_BITMAPS)) return true; - msr_bitmap = to_vmx(vcpu)->loaded_vmcs->msr_bitmap; - - if (msr <= 0x1fff) { - return !!test_bit(msr, msr_bitmap + 0x800 / f); - } else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) { - msr &= 0x1fff; - return !!test_bit(msr, msr_bitmap + 0xc00 / f); - } - - return true; + return vmx_test_msr_bitmap_write(vmx->loaded_vmcs->msr_bitmap, + MSR_IA32_SPEC_CTRL); } static void clear_atomic_switch_msr_special(struct vcpu_vmx *vmx, @@ -2929,6 +2918,13 @@ static void vmx_flush_tlb_all(struct kvm_vcpu *vcpu) } } +static inline int vmx_get_current_vpid(struct kvm_vcpu *vcpu) +{ + if (is_guest_mode(vcpu)) + return nested_get_vpid02(vcpu); + return to_vmx(vcpu)->vpid; +} + static void vmx_flush_tlb_current(struct kvm_vcpu *vcpu) { struct kvm_mmu *mmu = vcpu->arch.mmu; @@ -2941,31 +2937,29 @@ static void vmx_flush_tlb_current(struct kvm_vcpu *vcpu) if (enable_ept) ept_sync_context(construct_eptp(vcpu, root_hpa, mmu->shadow_root_level)); - else if (!is_guest_mode(vcpu)) - vpid_sync_context(to_vmx(vcpu)->vpid); else - vpid_sync_context(nested_get_vpid02(vcpu)); + vpid_sync_context(vmx_get_current_vpid(vcpu)); } static void vmx_flush_tlb_gva(struct kvm_vcpu *vcpu, gva_t addr) { /* - * vpid_sync_vcpu_addr() is a nop if vmx->vpid==0, see the comment in + * vpid_sync_vcpu_addr() is a nop if vpid==0, see the comment in * vmx_flush_tlb_guest() for an explanation of why this is ok. */ - vpid_sync_vcpu_addr(to_vmx(vcpu)->vpid, addr); + vpid_sync_vcpu_addr(vmx_get_current_vpid(vcpu), addr); } static void vmx_flush_tlb_guest(struct kvm_vcpu *vcpu) { /* - * vpid_sync_context() is a nop if vmx->vpid==0, e.g. if enable_vpid==0 - * or a vpid couldn't be allocated for this vCPU. VM-Enter and VM-Exit - * are required to flush GVA->{G,H}PA mappings from the TLB if vpid is + * vpid_sync_context() is a nop if vpid==0, e.g. if enable_vpid==0 or a + * vpid couldn't be allocated for this vCPU. VM-Enter and VM-Exit are + * required to flush GVA->{G,H}PA mappings from the TLB if vpid is * disabled (VM-Enter with vpid enabled and vpid==0 is disallowed), * i.e. no explicit INVVPID is necessary. */ - vpid_sync_context(to_vmx(vcpu)->vpid); + vpid_sync_context(vmx_get_current_vpid(vcpu)); } void vmx_ept_load_pdptrs(struct kvm_vcpu *vcpu) @@ -3697,46 +3691,6 @@ void free_vpid(int vpid) spin_unlock(&vmx_vpid_lock); } -static void vmx_clear_msr_bitmap_read(ulong *msr_bitmap, u32 msr) -{ - int f = sizeof(unsigned long); - - if (msr <= 0x1fff) - __clear_bit(msr, msr_bitmap + 0x000 / f); - else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) - __clear_bit(msr & 0x1fff, msr_bitmap + 0x400 / f); -} - -static void vmx_clear_msr_bitmap_write(ulong *msr_bitmap, u32 msr) -{ - int f = sizeof(unsigned long); - - if (msr <= 0x1fff) - __clear_bit(msr, msr_bitmap + 0x800 / f); - else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) - __clear_bit(msr & 0x1fff, msr_bitmap + 0xc00 / f); -} - -static void vmx_set_msr_bitmap_read(ulong *msr_bitmap, u32 msr) -{ - int f = sizeof(unsigned long); - - if (msr <= 0x1fff) - __set_bit(msr, msr_bitmap + 0x000 / f); - else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) - __set_bit(msr & 0x1fff, msr_bitmap + 0x400 / f); -} - -static void vmx_set_msr_bitmap_write(ulong *msr_bitmap, u32 msr) -{ - int f = sizeof(unsigned long); - - if (msr <= 0x1fff) - __set_bit(msr, msr_bitmap + 0x800 / f); - else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) - __set_bit(msr & 0x1fff, msr_bitmap + 0xc00 / f); -} - void vmx_disable_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -5494,6 +5448,7 @@ static int handle_invpcid(struct kvm_vcpu *vcpu) u64 pcid; u64 gla; } operand; + int gpr_index; if (!guest_cpuid_has(vcpu, X86_FEATURE_INVPCID)) { kvm_queue_exception(vcpu, UD_VECTOR); @@ -5501,12 +5456,8 @@ static int handle_invpcid(struct kvm_vcpu *vcpu) } vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO); - type = kvm_register_read(vcpu, (vmx_instruction_info >> 28) & 0xf); - - if (type > 3) { - kvm_inject_gp(vcpu, 0); - return 1; - } + gpr_index = vmx_get_instr_info_reg2(vmx_instruction_info); + type = kvm_register_read(vcpu, gpr_index); /* According to the Intel instruction reference, the memory operand * is read even if it isn't needed (e.g., for type==all) @@ -6316,9 +6267,9 @@ static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); int max_irr; - bool max_irr_updated; + bool got_posted_interrupt; - if (KVM_BUG_ON(!vcpu->arch.apicv_active, vcpu->kvm)) + if (KVM_BUG_ON(!enable_apicv, vcpu->kvm)) return -EIO; if (pi_test_on(&vmx->pi_desc)) { @@ -6328,22 +6279,33 @@ static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu) * But on x86 this is just a compiler barrier anyway. */ smp_mb__after_atomic(); - max_irr_updated = + got_posted_interrupt = kvm_apic_update_irr(vcpu, vmx->pi_desc.pir, &max_irr); - - /* - * If we are running L2 and L1 has a new pending interrupt - * which can be injected, this may cause a vmexit or it may - * be injected into L2. Either way, this interrupt will be - * processed via KVM_REQ_EVENT, not RVI, because we do not use - * virtual interrupt delivery to inject L1 interrupts into L2. - */ - if (is_guest_mode(vcpu) && max_irr_updated) - kvm_make_request(KVM_REQ_EVENT, vcpu); } else { max_irr = kvm_lapic_find_highest_irr(vcpu); + got_posted_interrupt = false; } - vmx_hwapic_irr_update(vcpu, max_irr); + + /* + * Newly recognized interrupts are injected via either virtual interrupt + * delivery (RVI) or KVM_REQ_EVENT. Virtual interrupt delivery is + * disabled in two cases: + * + * 1) If L2 is running and the vCPU has a new pending interrupt. If L1 + * wants to exit on interrupts, KVM_REQ_EVENT is needed to synthesize a + * VM-Exit to L1. If L1 doesn't want to exit, the interrupt is injected + * into L2, but KVM doesn't use virtual interrupt delivery to inject + * interrupts into L2, and so KVM_REQ_EVENT is again needed. + * + * 2) If APICv is disabled for this vCPU, assigned devices may still + * attempt to post interrupts. The posted interrupt vector will cause + * a VM-Exit and the subsequent entry will call sync_pir_to_irr. + */ + if (!is_guest_mode(vcpu) && kvm_vcpu_apicv_active(vcpu)) + vmx_set_rvi(max_irr); + else if (got_posted_interrupt) + kvm_make_request(KVM_REQ_EVENT, vcpu); + return max_irr; } @@ -6749,7 +6711,7 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) * If the L02 MSR bitmap does not intercept the MSR, then we need to * save it. */ - if (unlikely(!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL))) + if (unlikely(!msr_write_intercepted(vmx, MSR_IA32_SPEC_CTRL))) vmx->spec_ctrl = native_read_msr(MSR_IA32_SPEC_CTRL); x86_spec_ctrl_restore_host(vmx->spec_ctrl, 0); @@ -7563,7 +7525,8 @@ static void hardware_unsetup(void) static bool vmx_check_apicv_inhibit_reasons(ulong bit) { ulong supported = BIT(APICV_INHIBIT_REASON_DISABLE) | - BIT(APICV_INHIBIT_REASON_HYPERV); + BIT(APICV_INHIBIT_REASON_HYPERV) | + BIT(APICV_INHIBIT_REASON_BLOCKIRQ); return supported & BIT(bit); } @@ -7814,10 +7777,10 @@ static __init int hardware_setup(void) ple_window_shrink = 0; } - if (!cpu_has_vmx_apicv()) { + if (!cpu_has_vmx_apicv()) enable_apicv = 0; + if (!enable_apicv) vmx_x86_ops.sync_pir_to_irr = NULL; - } if (cpu_has_vmx_tsc_scaling()) { kvm_has_tsc_control = true; diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index e7db42e3b0ce..4df2ac24ffc1 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -142,6 +142,16 @@ struct nested_vmx { struct vmcs12 *cached_shadow_vmcs12; /* + * GPA to HVA cache for accessing vmcs12->vmcs_link_pointer + */ + struct gfn_to_hva_cache shadow_vmcs12_cache; + + /* + * GPA to HVA cache for VMCS12 + */ + struct gfn_to_hva_cache vmcs12_cache; + + /* * Indicates if the shadow vmcs or enlightened vmcs must be updated * with the data held by struct vmcs12. */ @@ -400,6 +410,34 @@ static inline void vmx_set_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, void vmx_update_cpu_dirty_logging(struct kvm_vcpu *vcpu); +/* + * Note, early Intel manuals have the write-low and read-high bitmap offsets + * the wrong way round. The bitmaps control MSRs 0x00000000-0x00001fff and + * 0xc0000000-0xc0001fff. The former (low) uses bytes 0-0x3ff for reads and + * 0x800-0xbff for writes. The latter (high) uses 0x400-0x7ff for reads and + * 0xc00-0xfff for writes. MSRs not covered by either of the ranges always + * VM-Exit. + */ +#define __BUILD_VMX_MSR_BITMAP_HELPER(rtype, action, bitop, access, base) \ +static inline rtype vmx_##action##_msr_bitmap_##access(unsigned long *bitmap, \ + u32 msr) \ +{ \ + int f = sizeof(unsigned long); \ + \ + if (msr <= 0x1fff) \ + return bitop##_bit(msr, bitmap + base / f); \ + else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) \ + return bitop##_bit(msr & 0x1fff, bitmap + (base + 0x400) / f); \ + return (rtype)true; \ +} +#define BUILD_VMX_MSR_BITMAP_HELPERS(ret_type, action, bitop) \ + __BUILD_VMX_MSR_BITMAP_HELPER(ret_type, action, bitop, read, 0x0) \ + __BUILD_VMX_MSR_BITMAP_HELPER(ret_type, action, bitop, write, 0x800) + +BUILD_VMX_MSR_BITMAP_HELPERS(bool, test, test) +BUILD_VMX_MSR_BITMAP_HELPERS(void, clear, __clear) +BUILD_VMX_MSR_BITMAP_HELPERS(void, set, __set) + static inline u8 vmx_get_rvi(void) { return vmcs_read16(GUEST_INTR_STATUS) & 0xff; @@ -522,4 +560,9 @@ static inline bool vmx_guest_state_valid(struct kvm_vcpu *vcpu) void dump_vmcs(struct kvm_vcpu *vcpu); +static inline int vmx_get_instr_info_reg2(u32 vmx_instr_info) +{ + return (vmx_instr_info >> 28) & 0xf; +} + #endif /* __KVM_X86_VMX_H */ diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index c1c4e2b05a63..0ee1a039b490 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -3258,10 +3258,36 @@ static void kvm_vcpu_flush_tlb_guest(struct kvm_vcpu *vcpu) static_call(kvm_x86_tlb_flush_guest)(vcpu); } + +static inline void kvm_vcpu_flush_tlb_current(struct kvm_vcpu *vcpu) +{ + ++vcpu->stat.tlb_flush; + static_call(kvm_x86_tlb_flush_current)(vcpu); +} + +/* + * Service "local" TLB flush requests, which are specific to the current MMU + * context. In addition to the generic event handling in vcpu_enter_guest(), + * TLB flushes that are targeted at an MMU context also need to be serviced + * prior before nested VM-Enter/VM-Exit. + */ +void kvm_service_local_tlb_flush_requests(struct kvm_vcpu *vcpu) +{ + if (kvm_check_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu)) + kvm_vcpu_flush_tlb_current(vcpu); + + if (kvm_check_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu)) + kvm_vcpu_flush_tlb_guest(vcpu); +} +EXPORT_SYMBOL_GPL(kvm_service_local_tlb_flush_requests); + static void record_steal_time(struct kvm_vcpu *vcpu) { - struct kvm_host_map map; - struct kvm_steal_time *st; + struct gfn_to_hva_cache *ghc = &vcpu->arch.st.cache; + struct kvm_steal_time __user *st; + struct kvm_memslots *slots; + u64 steal; + u32 version; if (kvm_xen_msr_enabled(vcpu->kvm)) { kvm_xen_runstate_set_running(vcpu); @@ -3271,47 +3297,86 @@ static void record_steal_time(struct kvm_vcpu *vcpu) if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED)) return; - /* -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)) + if (WARN_ON_ONCE(current->mm != vcpu->kvm->mm)) return; - st = map.hva + - offset_in_page(vcpu->arch.st.msr_val & KVM_STEAL_VALID_BITS); + slots = kvm_memslots(vcpu->kvm); + + if (unlikely(slots->generation != ghc->generation || + kvm_is_error_hva(ghc->hva) || !ghc->memslot)) { + gfn_t gfn = vcpu->arch.st.msr_val & KVM_STEAL_VALID_BITS; + + /* We rely on the fact that it fits in a single page. */ + BUILD_BUG_ON((sizeof(*st) - 1) & KVM_STEAL_VALID_BITS); + + if (kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc, gfn, sizeof(*st)) || + kvm_is_error_hva(ghc->hva) || !ghc->memslot) + return; + } + st = (struct kvm_steal_time __user *)ghc->hva; /* * Doing a TLB flush here, on the guest's behalf, can avoid * expensive IPIs. */ if (guest_pv_has(vcpu, KVM_FEATURE_PV_TLB_FLUSH)) { - u8 st_preempted = xchg(&st->preempted, 0); + u8 st_preempted = 0; + int err = -EFAULT; + + if (!user_access_begin(st, sizeof(*st))) + return; + + asm volatile("1: xchgb %0, %2\n" + "xor %1, %1\n" + "2:\n" + _ASM_EXTABLE_UA(1b, 2b) + : "+q" (st_preempted), + "+&r" (err), + "+m" (st->preempted)); + if (err) + goto out; + + user_access_end(); + + vcpu->arch.st.preempted = 0; trace_kvm_pv_tlb_flush(vcpu->vcpu_id, st_preempted & KVM_VCPU_FLUSH_TLB); if (st_preempted & KVM_VCPU_FLUSH_TLB) kvm_vcpu_flush_tlb_guest(vcpu); + + if (!user_access_begin(st, sizeof(*st))) + goto dirty; } else { - st->preempted = 0; - } + if (!user_access_begin(st, sizeof(*st))) + return; - vcpu->arch.st.preempted = 0; + unsafe_put_user(0, &st->preempted, out); + vcpu->arch.st.preempted = 0; + } - if (st->version & 1) - st->version += 1; /* first time write, random junk */ + unsafe_get_user(version, &st->version, out); + if (version & 1) + version += 1; /* first time write, random junk */ - st->version += 1; + version += 1; + unsafe_put_user(version, &st->version, out); smp_wmb(); - st->steal += current->sched_info.run_delay - + unsafe_get_user(steal, &st->steal, out); + steal += current->sched_info.run_delay - vcpu->arch.st.last_steal; vcpu->arch.st.last_steal = current->sched_info.run_delay; + unsafe_put_user(steal, &st->steal, out); - smp_wmb(); - - st->version += 1; + version += 1; + unsafe_put_user(version, &st->version, out); - kvm_unmap_gfn(vcpu, &map, &vcpu->arch.st.cache, true, false); + out: + user_access_end(); + dirty: + mark_page_dirty_in_slot(vcpu->kvm, ghc->memslot, gpa_to_gfn(ghc->gpa)); } int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) @@ -3517,7 +3582,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (!guest_pv_has(vcpu, KVM_FEATURE_PV_EOI)) return 1; - if (kvm_lapic_enable_pv_eoi(vcpu, data, sizeof(u8))) + if (kvm_lapic_set_pv_eoi(vcpu, data, sizeof(u8))) return 1; break; @@ -4091,6 +4156,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_SGX_ATTRIBUTE: #endif case KVM_CAP_VM_COPY_ENC_CONTEXT_FROM: + case KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM: case KVM_CAP_SREGS2: case KVM_CAP_EXIT_ON_EMULATION_FAILURE: case KVM_CAP_VCPU_ATTRIBUTES: @@ -4137,7 +4203,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) r = !static_call(kvm_x86_cpu_has_accelerated_tpr)(); break; case KVM_CAP_NR_VCPUS: - r = KVM_SOFT_MAX_VCPUS; + r = min_t(unsigned int, num_online_cpus(), KVM_MAX_VCPUS); break; case KVM_CAP_MAX_VCPUS: r = KVM_MAX_VCPUS; @@ -4351,8 +4417,10 @@ 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; + struct gfn_to_hva_cache *ghc = &vcpu->arch.st.cache; + struct kvm_steal_time __user *st; + struct kvm_memslots *slots; + static const u8 preempted = KVM_VCPU_PREEMPTED; if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED)) return; @@ -4360,16 +4428,23 @@ static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu) if (vcpu->arch.st.preempted) return; - if (kvm_map_gfn(vcpu, vcpu->arch.st.msr_val >> PAGE_SHIFT, &map, - &vcpu->arch.st.cache, true)) + /* This happens on process exit */ + if (unlikely(current->mm != vcpu->kvm->mm)) + return; + + slots = kvm_memslots(vcpu->kvm); + + if (unlikely(slots->generation != ghc->generation || + kvm_is_error_hva(ghc->hva) || !ghc->memslot)) return; - st = map.hva + - offset_in_page(vcpu->arch.st.msr_val & KVM_STEAL_VALID_BITS); + st = (struct kvm_steal_time __user *)ghc->hva; + BUILD_BUG_ON(sizeof(st->preempted) != sizeof(preempted)); - st->preempted = vcpu->arch.st.preempted = KVM_VCPU_PREEMPTED; + if (!copy_to_user_nofault(&st->preempted, &preempted, sizeof(preempted))) + vcpu->arch.st.preempted = KVM_VCPU_PREEMPTED; - kvm_unmap_gfn(vcpu, &map, &vcpu->arch.st.cache, true, true); + mark_page_dirty_in_slot(vcpu->kvm, ghc->memslot, gpa_to_gfn(ghc->gpa)); } void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) @@ -4397,8 +4472,7 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) static int kvm_vcpu_ioctl_get_lapic(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s) { - if (vcpu->arch.apicv_active) - static_call(kvm_x86_sync_pir_to_irr)(vcpu); + static_call_cond(kvm_x86_sync_pir_to_irr)(vcpu); return kvm_apic_get_state(vcpu, s); } @@ -5073,6 +5147,17 @@ long kvm_arch_vcpu_ioctl(struct file *filp, struct kvm_cpuid __user *cpuid_arg = argp; struct kvm_cpuid cpuid; + /* + * KVM does not correctly handle changing guest CPUID after KVM_RUN, as + * MAXPHYADDR, GBPAGES support, AMD reserved bit behavior, etc.. aren't + * tracked in kvm_mmu_page_role. As a result, KVM may miss guest page + * faults due to reusing SPs/SPTEs. In practice no sane VMM mucks with + * the core vCPU model on the fly, so fail. + */ + r = -EINVAL; + if (vcpu->arch.last_vmentry_cpu != -1) + goto out; + r = -EFAULT; if (copy_from_user(&cpuid, cpuid_arg, sizeof(cpuid))) goto out; @@ -5083,6 +5168,14 @@ long kvm_arch_vcpu_ioctl(struct file *filp, struct kvm_cpuid2 __user *cpuid_arg = argp; struct kvm_cpuid2 cpuid; + /* + * KVM_SET_CPUID{,2} after KVM_RUN is forbidded, see the comment in + * KVM_SET_CPUID case above. + */ + r = -EINVAL; + if (vcpu->arch.last_vmentry_cpu != -1) + goto out; + r = -EFAULT; if (copy_from_user(&cpuid, cpuid_arg, sizeof(cpuid))) goto out; @@ -5728,6 +5821,12 @@ split_irqchip_unlock: if (kvm_x86_ops.vm_copy_enc_context_from) r = kvm_x86_ops.vm_copy_enc_context_from(kvm, cap->args[0]); return r; + case KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM: + r = -EINVAL; + if (kvm_x86_ops.vm_move_enc_context_from) + r = kvm_x86_ops.vm_move_enc_context_from( + kvm, cap->args[0]); + return r; case KVM_CAP_EXIT_HYPERCALL: if (cap->args[0] & ~KVM_EXIT_HYPERCALL_VALID_MASK) { r = -EINVAL; @@ -7328,7 +7427,9 @@ static void emulator_set_smbase(struct x86_emulate_ctxt *ctxt, u64 smbase) static int emulator_check_pmc(struct x86_emulate_ctxt *ctxt, u32 pmc) { - return kvm_pmu_is_valid_rdpmc_ecx(emul_to_vcpu(ctxt), pmc); + if (kvm_pmu_is_valid_rdpmc_ecx(emul_to_vcpu(ctxt), pmc)) + return 0; + return -EINVAL; } static int emulator_read_pmc(struct x86_emulate_ctxt *ctxt, @@ -8789,7 +8890,7 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) trace_kvm_hypercall(nr, a0, a1, a2, a3); - op_64_bit = is_64_bit_mode(vcpu); + op_64_bit = is_64_bit_hypercall(vcpu); if (!op_64_bit) { nr &= 0xFFFFFFFF; a0 &= 0xFFFFFFFF; @@ -9469,8 +9570,7 @@ static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu) if (irqchip_split(vcpu->kvm)) kvm_scan_ioapic_routes(vcpu, vcpu->arch.ioapic_handled_vectors); else { - if (vcpu->arch.apicv_active) - static_call(kvm_x86_sync_pir_to_irr)(vcpu); + static_call_cond(kvm_x86_sync_pir_to_irr)(vcpu); if (ioapic_in_kernel(vcpu->kvm)) kvm_ioapic_scan_entry(vcpu, vcpu->arch.ioapic_handled_vectors); } @@ -9488,12 +9588,16 @@ static void vcpu_load_eoi_exitmap(struct kvm_vcpu *vcpu) if (!kvm_apic_hw_enabled(vcpu->arch.apic)) return; - if (to_hv_vcpu(vcpu)) + if (to_hv_vcpu(vcpu)) { bitmap_or((ulong *)eoi_exit_bitmap, vcpu->arch.ioapic_handled_vectors, to_hv_synic(vcpu)->vec_bitmap, 256); + static_call(kvm_x86_load_eoi_exitmap)(vcpu, eoi_exit_bitmap); + return; + } - static_call(kvm_x86_load_eoi_exitmap)(vcpu, eoi_exit_bitmap); + static_call(kvm_x86_load_eoi_exitmap)( + vcpu, (u64 *)vcpu->arch.ioapic_handled_vectors); } void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm, @@ -9552,7 +9656,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) } if (kvm_request_pending(vcpu)) { - if (kvm_check_request(KVM_REQ_VM_BUGGED, vcpu)) { + if (kvm_check_request(KVM_REQ_VM_DEAD, vcpu)) { r = -EIO; goto out; } @@ -9585,10 +9689,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) /* Flushing all ASIDs flushes the current ASID... */ kvm_clear_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu); } - if (kvm_check_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu)) - kvm_vcpu_flush_tlb_current(vcpu); - if (kvm_check_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu)) - kvm_vcpu_flush_tlb_guest(vcpu); + kvm_service_local_tlb_flush_requests(vcpu); if (kvm_check_request(KVM_REQ_REPORT_TPR_ACCESS, vcpu)) { vcpu->run->exit_reason = KVM_EXIT_TPR_ACCESS; @@ -9739,10 +9840,12 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) /* * This handles the case where a posted interrupt was - * notified with kvm_vcpu_kick. + * notified with kvm_vcpu_kick. Assigned devices can + * use the POSTED_INTR_VECTOR even if APICv is disabled, + * so do it even if APICv is disabled on this vCPU. */ - if (kvm_lapic_enabled(vcpu) && vcpu->arch.apicv_active) - static_call(kvm_x86_sync_pir_to_irr)(vcpu); + if (kvm_lapic_enabled(vcpu)) + static_call_cond(kvm_x86_sync_pir_to_irr)(vcpu); if (kvm_vcpu_exit_request(vcpu)) { vcpu->mode = OUTSIDE_GUEST_MODE; @@ -9786,8 +9889,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (likely(exit_fastpath != EXIT_FASTPATH_REENTER_GUEST)) break; - if (vcpu->arch.apicv_active) - static_call(kvm_x86_sync_pir_to_irr)(vcpu); + if (kvm_lapic_enabled(vcpu)) + static_call_cond(kvm_x86_sync_pir_to_irr)(vcpu); if (unlikely(kvm_vcpu_exit_request(vcpu))) { exit_fastpath = EXIT_FASTPATH_EXIT_HANDLED; @@ -10564,6 +10667,24 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, return ret; } +static void kvm_arch_vcpu_guestdbg_update_apicv_inhibit(struct kvm *kvm) +{ + bool inhibit = false; + struct kvm_vcpu *vcpu; + int i; + + down_write(&kvm->arch.apicv_update_lock); + + kvm_for_each_vcpu(i, vcpu, kvm) { + if (vcpu->guest_debug & KVM_GUESTDBG_BLOCKIRQ) { + inhibit = true; + break; + } + } + __kvm_request_apicv_update(kvm, !inhibit, APICV_INHIBIT_REASON_BLOCKIRQ); + up_write(&kvm->arch.apicv_update_lock); +} + int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg) { @@ -10616,6 +10737,8 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, static_call(kvm_x86_update_exception_bitmap)(vcpu); + kvm_arch_vcpu_guestdbg_update_apicv_inhibit(vcpu->kvm); + r = 0; out: @@ -10859,11 +10982,8 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) { - struct gfn_to_pfn_cache *cache = &vcpu->arch.st.cache; int idx; - kvm_release_pfn(cache->pfn, cache->dirty, cache); - kvmclock_reset(vcpu); static_call(kvm_x86_vcpu_free)(vcpu); @@ -12275,7 +12395,8 @@ int kvm_handle_invpcid(struct kvm_vcpu *vcpu, unsigned long type, gva_t gva) return kvm_skip_emulated_instruction(vcpu); default: - BUG(); /* We have already checked above that type <= 3 */ + kvm_inject_gp(vcpu, 0); + return 1; } } EXPORT_SYMBOL_GPL(kvm_handle_invpcid); diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index ea264c4502e4..4abcd8d9836d 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -103,6 +103,7 @@ static inline unsigned int __shrink_ple_window(unsigned int val, #define MSR_IA32_CR_PAT_DEFAULT 0x0007040600070406ULL +void kvm_service_local_tlb_flush_requests(struct kvm_vcpu *vcpu); int kvm_check_nested_events(struct kvm_vcpu *vcpu); static inline void kvm_clear_exception_queue(struct kvm_vcpu *vcpu) @@ -153,12 +154,24 @@ static inline bool is_64_bit_mode(struct kvm_vcpu *vcpu) { int cs_db, cs_l; + WARN_ON_ONCE(vcpu->arch.guest_state_protected); + if (!is_long_mode(vcpu)) return false; static_call(kvm_x86_get_cs_db_l_bits)(vcpu, &cs_db, &cs_l); return cs_l; } +static inline bool is_64_bit_hypercall(struct kvm_vcpu *vcpu) +{ + /* + * If running with protected guest state, the CS register is not + * accessible. The hypercall register values will have had to been + * provided in 64-bit mode, so assume the guest is in 64-bit. + */ + return vcpu->arch.guest_state_protected || is_64_bit_mode(vcpu); +} + static inline bool x86_exception_has_error_code(unsigned int vector) { static u32 exception_has_error_code = BIT(DF_VECTOR) | BIT(TS_VECTOR) | @@ -173,12 +186,6 @@ static inline bool mmu_is_nested(struct kvm_vcpu *vcpu) return vcpu->arch.walk_mmu == &vcpu->arch.nested_mmu; } -static inline void kvm_vcpu_flush_tlb_current(struct kvm_vcpu *vcpu) -{ - ++vcpu->stat.tlb_flush; - static_call(kvm_x86_tlb_flush_current)(vcpu); -} - static inline int is_pae(struct kvm_vcpu *vcpu) { return kvm_read_cr4_bits(vcpu, X86_CR4_PAE); diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c index 8f62baebd028..dff2bdf9507a 100644 --- a/arch/x86/kvm/xen.c +++ b/arch/x86/kvm/xen.c @@ -127,9 +127,9 @@ void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, int state) state_entry_time = vx->runstate_entry_time; state_entry_time |= XEN_RUNSTATE_UPDATE; - BUILD_BUG_ON(sizeof(((struct vcpu_runstate_info *)0)->state_entry_time) != + BUILD_BUG_ON(sizeof_field(struct vcpu_runstate_info, state_entry_time) != sizeof(state_entry_time)); - BUILD_BUG_ON(sizeof(((struct compat_vcpu_runstate_info *)0)->state_entry_time) != + BUILD_BUG_ON(sizeof_field(struct compat_vcpu_runstate_info, state_entry_time) != sizeof(state_entry_time)); if (kvm_write_guest_offset_cached(v->kvm, &v->arch.xen.runstate_cache, @@ -144,9 +144,9 @@ void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, int state) */ BUILD_BUG_ON(offsetof(struct vcpu_runstate_info, state) != offsetof(struct compat_vcpu_runstate_info, state)); - BUILD_BUG_ON(sizeof(((struct vcpu_runstate_info *)0)->state) != + BUILD_BUG_ON(sizeof_field(struct vcpu_runstate_info, state) != sizeof(vx->current_runstate)); - BUILD_BUG_ON(sizeof(((struct compat_vcpu_runstate_info *)0)->state) != + BUILD_BUG_ON(sizeof_field(struct compat_vcpu_runstate_info, state) != sizeof(vx->current_runstate)); if (kvm_write_guest_offset_cached(v->kvm, &v->arch.xen.runstate_cache, @@ -163,9 +163,9 @@ void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, int state) offsetof(struct vcpu_runstate_info, time) - sizeof(u64)); BUILD_BUG_ON(offsetof(struct compat_vcpu_runstate_info, state_entry_time) != offsetof(struct compat_vcpu_runstate_info, time) - sizeof(u64)); - BUILD_BUG_ON(sizeof(((struct vcpu_runstate_info *)0)->time) != - sizeof(((struct compat_vcpu_runstate_info *)0)->time)); - BUILD_BUG_ON(sizeof(((struct vcpu_runstate_info *)0)->time) != + BUILD_BUG_ON(sizeof_field(struct vcpu_runstate_info, time) != + sizeof_field(struct compat_vcpu_runstate_info, time)); + BUILD_BUG_ON(sizeof_field(struct vcpu_runstate_info, time) != sizeof(vx->runstate_times)); if (kvm_write_guest_offset_cached(v->kvm, &v->arch.xen.runstate_cache, @@ -205,9 +205,9 @@ int __kvm_xen_has_interrupt(struct kvm_vcpu *v) BUILD_BUG_ON(offsetof(struct vcpu_info, evtchn_upcall_pending) != offsetof(struct compat_vcpu_info, evtchn_upcall_pending)); BUILD_BUG_ON(sizeof(rc) != - sizeof(((struct vcpu_info *)0)->evtchn_upcall_pending)); + sizeof_field(struct vcpu_info, evtchn_upcall_pending)); BUILD_BUG_ON(sizeof(rc) != - sizeof(((struct compat_vcpu_info *)0)->evtchn_upcall_pending)); + sizeof_field(struct compat_vcpu_info, evtchn_upcall_pending)); /* * For efficiency, this mirrors the checks for using the valid @@ -299,7 +299,7 @@ int kvm_xen_hvm_get_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data) break; case KVM_XEN_ATTR_TYPE_SHARED_INFO: - data->u.shared_info.gfn = gpa_to_gfn(kvm->arch.xen.shinfo_gfn); + data->u.shared_info.gfn = kvm->arch.xen.shinfo_gfn; r = 0; break; @@ -698,7 +698,7 @@ int kvm_xen_hypercall(struct kvm_vcpu *vcpu) kvm_hv_hypercall_enabled(vcpu)) return kvm_hv_hypercall(vcpu); - longmode = is_64_bit_mode(vcpu); + longmode = is_64_bit_hypercall(vcpu); if (!longmode) { params[0] = (u32)kvm_rbx_read(vcpu); params[1] = (u32)kvm_rcx_read(vcpu); diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c index 23d54b810f08..35487305d8af 100644 --- a/arch/x86/mm/mem_encrypt.c +++ b/arch/x86/mm/mem_encrypt.c @@ -229,28 +229,75 @@ void __init sev_setup_arch(void) swiotlb_adjust_size(size); } -static void __init __set_clr_pte_enc(pte_t *kpte, int level, bool enc) +static unsigned long pg_level_to_pfn(int level, pte_t *kpte, pgprot_t *ret_prot) { - pgprot_t old_prot, new_prot; - unsigned long pfn, pa, size; - pte_t new_pte; + unsigned long pfn = 0; + pgprot_t prot; switch (level) { case PG_LEVEL_4K: pfn = pte_pfn(*kpte); - old_prot = pte_pgprot(*kpte); + prot = pte_pgprot(*kpte); break; case PG_LEVEL_2M: pfn = pmd_pfn(*(pmd_t *)kpte); - old_prot = pmd_pgprot(*(pmd_t *)kpte); + prot = pmd_pgprot(*(pmd_t *)kpte); break; case PG_LEVEL_1G: pfn = pud_pfn(*(pud_t *)kpte); - old_prot = pud_pgprot(*(pud_t *)kpte); + prot = pud_pgprot(*(pud_t *)kpte); break; default: - return; + WARN_ONCE(1, "Invalid level for kpte\n"); + return 0; + } + + if (ret_prot) + *ret_prot = prot; + + return pfn; +} + +void notify_range_enc_status_changed(unsigned long vaddr, int npages, bool enc) +{ +#ifdef CONFIG_PARAVIRT + unsigned long sz = npages << PAGE_SHIFT; + unsigned long vaddr_end = vaddr + sz; + + while (vaddr < vaddr_end) { + int psize, pmask, level; + unsigned long pfn; + pte_t *kpte; + + kpte = lookup_address(vaddr, &level); + if (!kpte || pte_none(*kpte)) { + WARN_ONCE(1, "kpte lookup for vaddr\n"); + return; + } + + pfn = pg_level_to_pfn(level, kpte, NULL); + if (!pfn) + continue; + + psize = page_level_size(level); + pmask = page_level_mask(level); + + notify_page_enc_status_changed(pfn, psize >> PAGE_SHIFT, enc); + + vaddr = (vaddr & pmask) + psize; } +#endif +} + +static void __init __set_clr_pte_enc(pte_t *kpte, int level, bool enc) +{ + pgprot_t old_prot, new_prot; + unsigned long pfn, pa, size; + pte_t new_pte; + + pfn = pg_level_to_pfn(level, kpte, &old_prot); + if (!pfn) + return; new_prot = old_prot; if (enc) @@ -286,12 +333,13 @@ static void __init __set_clr_pte_enc(pte_t *kpte, int level, bool enc) static int __init early_set_memory_enc_dec(unsigned long vaddr, unsigned long size, bool enc) { - unsigned long vaddr_end, vaddr_next; + unsigned long vaddr_end, vaddr_next, start; unsigned long psize, pmask; int split_page_size_mask; int level, ret; pte_t *kpte; + start = vaddr; vaddr_next = vaddr; vaddr_end = vaddr + size; @@ -346,6 +394,7 @@ static int __init early_set_memory_enc_dec(unsigned long vaddr, ret = 0; + notify_range_enc_status_changed(start, PAGE_ALIGN(size) >> PAGE_SHIFT, enc); out: __flush_tlb_all(); return ret; @@ -361,6 +410,11 @@ int __init early_set_memory_encrypted(unsigned long vaddr, unsigned long size) return early_set_memory_enc_dec(vaddr, size, true); } +void __init early_set_mem_enc_dec_hypercall(unsigned long vaddr, int npages, bool enc) +{ + notify_range_enc_status_changed(vaddr, npages, enc); +} + /* Override for DMA direct allocation check - ARCH_HAS_FORCE_DMA_UNENCRYPTED */ bool force_dma_unencrypted(struct device *dev) { diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c index 934dc5b2df36..b4072115c8ef 100644 --- a/arch/x86/mm/pat/set_memory.c +++ b/arch/x86/mm/pat/set_memory.c @@ -2023,6 +2023,12 @@ static int __set_memory_enc_pgtable(unsigned long addr, int numpages, bool enc) */ cpa_flush(&cpa, 0); + /* + * Notify hypervisor that a given memory range is mapped encrypted + * or decrypted. + */ + notify_range_enc_status_changed(addr, numpages, enc); + return ret; } diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c index 9e55bcbfcd33..6a8f3b53ab83 100644 --- a/arch/x86/xen/smp_pv.c +++ b/arch/x86/xen/smp_pv.c @@ -225,7 +225,6 @@ static void __init xen_pv_smp_prepare_boot_cpu(void) static void __init xen_pv_smp_prepare_cpus(unsigned int max_cpus) { unsigned cpu; - unsigned int i; if (skip_ioapic_setup) { char *m = (max_cpus == 0) ? @@ -238,16 +237,9 @@ static void __init xen_pv_smp_prepare_cpus(unsigned int max_cpus) } xen_init_lock_cpu(0); - smp_store_boot_cpu_info(); - cpu_data(0).x86_max_cores = 1; + smp_prepare_cpus_common(); - for_each_possible_cpu(i) { - zalloc_cpumask_var(&per_cpu(cpu_sibling_map, i), GFP_KERNEL); - zalloc_cpumask_var(&per_cpu(cpu_core_map, i), GFP_KERNEL); - zalloc_cpumask_var(&per_cpu(cpu_die_map, i), GFP_KERNEL); - zalloc_cpumask_var(&per_cpu(cpu_llc_shared_map, i), GFP_KERNEL); - } - set_cpu_sibling_map(0); + cpu_data(0).x86_max_cores = 1; speculative_store_bypass_ht_init(); diff --git a/arch/xtensa/include/asm/cacheflush.h b/arch/xtensa/include/asm/cacheflush.h index a8a041609c5d..7b4359312c25 100644 --- a/arch/xtensa/include/asm/cacheflush.h +++ b/arch/xtensa/include/asm/cacheflush.h @@ -121,7 +121,6 @@ void flush_cache_page(struct vm_area_struct*, #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 void flush_dcache_page(struct page *); -void flush_dcache_folio(struct folio *); void local_flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end); @@ -138,9 +137,7 @@ void local_flush_cache_page(struct vm_area_struct *vma, #define flush_cache_vunmap(start,end) do { } while (0) #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0 -#define ARCH_IMPLEMENTS_FLUSH_DCACHE_FOLIO #define flush_dcache_page(page) do { } while (0) -static inline void flush_dcache_folio(struct folio *folio) { } #define flush_icache_range local_flush_icache_range #define flush_cache_page(vma, addr, pfn) do { } while (0) diff --git a/arch/xtensa/kernel/syscalls/syscall.tbl b/arch/xtensa/kernel/syscalls/syscall.tbl index 104b327f8ac9..3e3e1a506bed 100644 --- a/arch/xtensa/kernel/syscalls/syscall.tbl +++ b/arch/xtensa/kernel/syscalls/syscall.tbl @@ -419,3 +419,4 @@ 446 common landlock_restrict_self sys_landlock_restrict_self # 447 reserved for memfd_secret 448 common process_mrelease sys_process_mrelease +449 common futex_waitv sys_futex_waitv |