diff options
Diffstat (limited to 'arch')
30 files changed, 209 insertions, 62 deletions
diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c index 60e901cd0de6..5a957a9a0984 100644 --- a/arch/arm/xen/enlighten.c +++ b/arch/arm/xen/enlighten.c @@ -371,7 +371,7 @@ static int __init xen_guest_init(void) } gnttab_init(); if (!xen_initial_domain()) - xenbus_probe(NULL); + xenbus_probe(); /* * Making sure board specific code will not set up ops for diff --git a/arch/ia64/include/asm/sparsemem.h b/arch/ia64/include/asm/sparsemem.h index dd8c166ffd7b..42ed5248fae9 100644 --- a/arch/ia64/include/asm/sparsemem.h +++ b/arch/ia64/include/asm/sparsemem.h @@ -3,6 +3,7 @@ #define _ASM_IA64_SPARSEMEM_H #ifdef CONFIG_SPARSEMEM +#include <asm/page.h> /* * SECTION_SIZE_BITS 2^N: how big each section will be * MAX_PHYSMEM_BITS 2^N: how much memory we can have in that space diff --git a/arch/mips/boot/compressed/decompress.c b/arch/mips/boot/compressed/decompress.c index c61c641674e6..e3946b06e840 100644 --- a/arch/mips/boot/compressed/decompress.c +++ b/arch/mips/boot/compressed/decompress.c @@ -13,6 +13,7 @@ #include <linux/libfdt.h> #include <asm/addrspace.h> +#include <asm/unaligned.h> /* * These two variables specify the free mem region @@ -117,7 +118,7 @@ void decompress_kernel(unsigned long boot_heap_start) dtb_size = fdt_totalsize((void *)&__appended_dtb); /* last four bytes is always image size in little endian */ - image_size = le32_to_cpup((void *)&__image_end - 4); + image_size = get_unaligned_le32((void *)&__image_end - 4); /* copy dtb to where the booted kernel will expect it */ memcpy((void *)VMLINUX_LOAD_ADDRESS_ULL + image_size, diff --git a/arch/mips/cavium-octeon/octeon-irq.c b/arch/mips/cavium-octeon/octeon-irq.c index bd47e15d02c7..be5d4afcd30f 100644 --- a/arch/mips/cavium-octeon/octeon-irq.c +++ b/arch/mips/cavium-octeon/octeon-irq.c @@ -1444,7 +1444,7 @@ static void octeon_irq_setup_secondary_ciu2(void) static int __init octeon_irq_init_ciu( struct device_node *ciu_node, struct device_node *parent) { - unsigned int i, r; + int i, r; struct irq_chip *chip; struct irq_chip *chip_edge; struct irq_chip *chip_mbox; diff --git a/arch/mips/kernel/binfmt_elfn32.c b/arch/mips/kernel/binfmt_elfn32.c index 6ee3f7218c67..c4441416e96b 100644 --- a/arch/mips/kernel/binfmt_elfn32.c +++ b/arch/mips/kernel/binfmt_elfn32.c @@ -103,4 +103,11 @@ jiffies_to_old_timeval32(unsigned long jiffies, struct old_timeval32 *value) #undef ns_to_kernel_old_timeval #define ns_to_kernel_old_timeval ns_to_old_timeval32 +/* + * Some data types as stored in coredump. + */ +#define user_long_t compat_long_t +#define user_siginfo_t compat_siginfo_t +#define copy_siginfo_to_external copy_siginfo_to_external32 + #include "../../../fs/binfmt_elf.c" diff --git a/arch/mips/kernel/binfmt_elfo32.c b/arch/mips/kernel/binfmt_elfo32.c index 6dd103d3cebb..7b2a23f48c1a 100644 --- a/arch/mips/kernel/binfmt_elfo32.c +++ b/arch/mips/kernel/binfmt_elfo32.c @@ -106,4 +106,11 @@ jiffies_to_old_timeval32(unsigned long jiffies, struct old_timeval32 *value) #undef ns_to_kernel_old_timeval #define ns_to_kernel_old_timeval ns_to_old_timeval32 +/* + * Some data types as stored in coredump. + */ +#define user_long_t compat_long_t +#define user_siginfo_t compat_siginfo_t +#define copy_siginfo_to_external copy_siginfo_to_external32 + #include "../../../fs/binfmt_elf.c" diff --git a/arch/mips/kernel/relocate.c b/arch/mips/kernel/relocate.c index 47aeb3350a76..0e365b7c742d 100644 --- a/arch/mips/kernel/relocate.c +++ b/arch/mips/kernel/relocate.c @@ -187,8 +187,14 @@ static int __init relocate_exception_table(long offset) static inline __init unsigned long rotate_xor(unsigned long hash, const void *area, size_t size) { - size_t i; - unsigned long *ptr = (unsigned long *)area; + const typeof(hash) *ptr = PTR_ALIGN(area, sizeof(hash)); + size_t diff, i; + + diff = (void *)ptr - area; + if (unlikely(size < diff + sizeof(hash))) + return hash; + + size = ALIGN_DOWN(size - diff, sizeof(hash)); for (i = 0; i < size / sizeof(hash); i++) { /* Rotate by odd number of bits and XOR. */ diff --git a/arch/openrisc/include/asm/io.h b/arch/openrisc/include/asm/io.h index 7d6b4a77b379..c298061c70a7 100644 --- a/arch/openrisc/include/asm/io.h +++ b/arch/openrisc/include/asm/io.h @@ -31,7 +31,7 @@ void __iomem *ioremap(phys_addr_t offset, unsigned long size); #define iounmap iounmap -extern void iounmap(void *addr); +extern void iounmap(void __iomem *addr); #include <asm-generic/io.h> diff --git a/arch/openrisc/mm/ioremap.c b/arch/openrisc/mm/ioremap.c index 5aed97a18bac..daae13a76743 100644 --- a/arch/openrisc/mm/ioremap.c +++ b/arch/openrisc/mm/ioremap.c @@ -77,7 +77,7 @@ void __iomem *__ref ioremap(phys_addr_t addr, unsigned long size) } EXPORT_SYMBOL(ioremap); -void iounmap(void *addr) +void iounmap(void __iomem *addr) { /* If the page is from the fixmap pool then we just clear out * the fixmap mapping. diff --git a/arch/powerpc/include/asm/vdso/gettimeofday.h b/arch/powerpc/include/asm/vdso/gettimeofday.h index 81671aa365b3..77c635c2c90d 100644 --- a/arch/powerpc/include/asm/vdso/gettimeofday.h +++ b/arch/powerpc/include/asm/vdso/gettimeofday.h @@ -103,6 +103,8 @@ int gettimeofday_fallback(struct __kernel_old_timeval *_tv, struct timezone *_tz return do_syscall_2(__NR_gettimeofday, (unsigned long)_tv, (unsigned long)_tz); } +#ifdef __powerpc64__ + static __always_inline int clock_gettime_fallback(clockid_t _clkid, struct __kernel_timespec *_ts) { @@ -115,11 +117,23 @@ int clock_getres_fallback(clockid_t _clkid, struct __kernel_timespec *_ts) return do_syscall_2(__NR_clock_getres, _clkid, (unsigned long)_ts); } -#ifdef CONFIG_VDSO32 +#else #define BUILD_VDSO32 1 static __always_inline +int clock_gettime_fallback(clockid_t _clkid, struct __kernel_timespec *_ts) +{ + return do_syscall_2(__NR_clock_gettime64, _clkid, (unsigned long)_ts); +} + +static __always_inline +int clock_getres_fallback(clockid_t _clkid, struct __kernel_timespec *_ts) +{ + return do_syscall_2(__NR_clock_getres_time64, _clkid, (unsigned long)_ts); +} + +static __always_inline int clock_gettime32_fallback(clockid_t _clkid, struct old_timespec32 *_ts) { return do_syscall_2(__NR_clock_gettime, _clkid, (unsigned long)_ts); diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index 8e0b1298bf19..4ab426b8b0e0 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -187,6 +187,12 @@ SECTIONS .init.text : AT(ADDR(.init.text) - LOAD_OFFSET) { _sinittext = .; INIT_TEXT + + /* + *.init.text might be RO so we must ensure this section ends on + * a page boundary. + */ + . = ALIGN(PAGE_SIZE); _einittext = .; #ifdef CONFIG_PPC64 *(.tramp.ftrace.init); @@ -200,6 +206,8 @@ SECTIONS EXIT_TEXT } + . = ALIGN(PAGE_SIZE); + INIT_DATA_SECTION(16) . = ALIGN(8); diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 81b76d44725d..e9e2c1f0a690 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -137,7 +137,7 @@ config PA_BITS config PAGE_OFFSET hex - default 0xC0000000 if 32BIT && MAXPHYSMEM_2GB + default 0xC0000000 if 32BIT && MAXPHYSMEM_1GB default 0x80000000 if 64BIT && !MMU default 0xffffffff80000000 if 64BIT && MAXPHYSMEM_2GB default 0xffffffe000000000 if 64BIT && MAXPHYSMEM_128GB @@ -247,10 +247,12 @@ config MODULE_SECTIONS choice prompt "Maximum Physical Memory" - default MAXPHYSMEM_2GB if 32BIT + default MAXPHYSMEM_1GB if 32BIT default MAXPHYSMEM_2GB if 64BIT && CMODEL_MEDLOW default MAXPHYSMEM_128GB if 64BIT && CMODEL_MEDANY + config MAXPHYSMEM_1GB + bool "1GiB" config MAXPHYSMEM_2GB bool "2GiB" config MAXPHYSMEM_128GB diff --git a/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts b/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts index 4a2729f5ca3f..24d75a146e02 100644 --- a/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts +++ b/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts @@ -88,7 +88,9 @@ phy-mode = "gmii"; phy-handle = <&phy0>; phy0: ethernet-phy@0 { + compatible = "ethernet-phy-id0007.0771"; reg = <0>; + reset-gpios = <&gpio 12 GPIO_ACTIVE_LOW>; }; }; diff --git a/arch/riscv/configs/defconfig b/arch/riscv/configs/defconfig index d222d353d86d..8c3d1e451703 100644 --- a/arch/riscv/configs/defconfig +++ b/arch/riscv/configs/defconfig @@ -64,6 +64,8 @@ CONFIG_HW_RANDOM=y CONFIG_HW_RANDOM_VIRTIO=y CONFIG_SPI=y CONFIG_SPI_SIFIVE=y +CONFIG_GPIOLIB=y +CONFIG_GPIO_SIFIVE=y # CONFIG_PTP_1588_CLOCK is not set CONFIG_POWER_RESET=y CONFIG_DRM=y diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index 41a72861987c..251e1db088fa 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -99,7 +99,6 @@ | _PAGE_DIRTY) #define PAGE_KERNEL __pgprot(_PAGE_KERNEL) -#define PAGE_KERNEL_EXEC __pgprot(_PAGE_KERNEL | _PAGE_EXEC) #define PAGE_KERNEL_READ __pgprot(_PAGE_KERNEL & ~_PAGE_WRITE) #define PAGE_KERNEL_EXEC __pgprot(_PAGE_KERNEL | _PAGE_EXEC) #define PAGE_KERNEL_READ_EXEC __pgprot((_PAGE_KERNEL & ~_PAGE_WRITE) \ diff --git a/arch/riscv/include/asm/vdso.h b/arch/riscv/include/asm/vdso.h index 8454f746bbfd..1453a2f563bc 100644 --- a/arch/riscv/include/asm/vdso.h +++ b/arch/riscv/include/asm/vdso.h @@ -10,7 +10,7 @@ #include <linux/types.h> -#ifndef GENERIC_TIME_VSYSCALL +#ifndef CONFIG_GENERIC_TIME_VSYSCALL struct vdso_data { }; #endif diff --git a/arch/riscv/kernel/cacheinfo.c b/arch/riscv/kernel/cacheinfo.c index de59dd457b41..d86781357044 100644 --- a/arch/riscv/kernel/cacheinfo.c +++ b/arch/riscv/kernel/cacheinfo.c @@ -26,7 +26,16 @@ cache_get_priv_group(struct cacheinfo *this_leaf) static struct cacheinfo *get_cacheinfo(u32 level, enum cache_type type) { - struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(smp_processor_id()); + /* + * Using raw_smp_processor_id() elides a preemptability check, but this + * is really indicative of a larger problem: the cacheinfo UABI assumes + * that cores have a homonogenous view of the cache hierarchy. That + * happens to be the case for the current set of RISC-V systems, but + * likely won't be true in general. Since there's no way to provide + * correct information for these systems via the current UABI we're + * just eliding the check for now. + */ + struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(raw_smp_processor_id()); struct cacheinfo *this_leaf; int index; diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S index 524d918f3601..744f3209c48d 100644 --- a/arch/riscv/kernel/entry.S +++ b/arch/riscv/kernel/entry.S @@ -124,15 +124,15 @@ skip_context_tracking: REG_L a1, (a1) jr a1 1: -#ifdef CONFIG_TRACE_IRQFLAGS - call trace_hardirqs_on -#endif /* * Exceptions run with interrupts enabled or disabled depending on the * state of SR_PIE in m/sstatus. */ andi t0, s1, SR_PIE beqz t0, 1f +#ifdef CONFIG_TRACE_IRQFLAGS + call trace_hardirqs_on +#endif csrs CSR_STATUS, SR_IE 1: @@ -155,6 +155,15 @@ skip_context_tracking: tail do_trap_unknown handle_syscall: +#ifdef CONFIG_RISCV_M_MODE + /* + * When running is M-Mode (no MMU config), MPIE does not get set. + * As a result, we need to force enable interrupts here because + * handle_exception did not do set SR_IE as it always sees SR_PIE + * being cleared. + */ + csrs CSR_STATUS, SR_IE +#endif #if defined(CONFIG_TRACE_IRQFLAGS) || defined(CONFIG_CONTEXT_TRACKING) /* Recover a0 - a7 for system calls */ REG_L a0, PT_A0(sp) @@ -186,14 +195,7 @@ check_syscall_nr: * Syscall number held in a7. * If syscall number is above allowed value, redirect to ni_syscall. */ - bge a7, t0, 1f - /* - * Check if syscall is rejected by tracer, i.e., a7 == -1. - * If yes, we pretend it was executed. - */ - li t1, -1 - beq a7, t1, ret_from_syscall_rejected - blt a7, t1, 1f + bgeu a7, t0, 1f /* Call syscall */ la s0, sys_call_table slli t0, a7, RISCV_LGPTR diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index 1d85e9bf783c..3fa3f26dde85 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -127,7 +127,9 @@ static void __init init_resources(void) { struct memblock_region *region = NULL; struct resource *res = NULL; - int ret = 0; + struct resource *mem_res = NULL; + size_t mem_res_sz = 0; + int ret = 0, i = 0; code_res.start = __pa_symbol(_text); code_res.end = __pa_symbol(_etext) - 1; @@ -145,16 +147,17 @@ static void __init init_resources(void) bss_res.end = __pa_symbol(__bss_stop) - 1; bss_res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; + mem_res_sz = (memblock.memory.cnt + memblock.reserved.cnt) * sizeof(*mem_res); + mem_res = memblock_alloc(mem_res_sz, SMP_CACHE_BYTES); + if (!mem_res) + panic("%s: Failed to allocate %zu bytes\n", __func__, mem_res_sz); /* * Start by adding the reserved regions, if they overlap * with /memory regions, insert_resource later on will take * care of it. */ for_each_reserved_mem_region(region) { - res = memblock_alloc(sizeof(struct resource), SMP_CACHE_BYTES); - if (!res) - panic("%s: Failed to allocate %zu bytes\n", __func__, - sizeof(struct resource)); + res = &mem_res[i++]; res->name = "Reserved"; res->flags = IORESOURCE_MEM | IORESOURCE_BUSY; @@ -171,8 +174,10 @@ static void __init init_resources(void) * Ignore any other reserved regions within * system memory. */ - if (memblock_is_memory(res->start)) + if (memblock_is_memory(res->start)) { + memblock_free((phys_addr_t) res, sizeof(struct resource)); continue; + } ret = add_resource(&iomem_resource, res); if (ret < 0) @@ -181,10 +186,7 @@ static void __init init_resources(void) /* Add /memory regions to the resource tree */ for_each_mem_region(region) { - res = memblock_alloc(sizeof(struct resource), SMP_CACHE_BYTES); - if (!res) - panic("%s: Failed to allocate %zu bytes\n", __func__, - sizeof(struct resource)); + res = &mem_res[i++]; if (unlikely(memblock_is_nomap(region))) { res->name = "Reserved"; @@ -205,9 +207,9 @@ static void __init init_resources(void) return; error: - memblock_free((phys_addr_t) res, sizeof(struct resource)); /* Better an empty resource tree than an inconsistent one */ release_child_resources(&iomem_resource); + memblock_free((phys_addr_t) mem_res, mem_res_sz); } diff --git a/arch/riscv/kernel/stacktrace.c b/arch/riscv/kernel/stacktrace.c index 48b870a685b3..df5d2da7c40b 100644 --- a/arch/riscv/kernel/stacktrace.c +++ b/arch/riscv/kernel/stacktrace.c @@ -14,7 +14,7 @@ #include <asm/stacktrace.h> -register unsigned long sp_in_global __asm__("sp"); +register const unsigned long sp_in_global __asm__("sp"); #ifdef CONFIG_FRAME_POINTER @@ -28,9 +28,8 @@ void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs, sp = user_stack_pointer(regs); pc = instruction_pointer(regs); } else if (task == NULL || task == current) { - const register unsigned long current_sp = sp_in_global; fp = (unsigned long)__builtin_frame_address(0); - sp = current_sp; + sp = sp_in_global; pc = (unsigned long)walk_stackframe; } else { /* task blocked in __switch_to */ diff --git a/arch/riscv/kernel/time.c b/arch/riscv/kernel/time.c index 4d3a1048ad8b..8a5cf99c0776 100644 --- a/arch/riscv/kernel/time.c +++ b/arch/riscv/kernel/time.c @@ -4,6 +4,7 @@ * Copyright (C) 2017 SiFive */ +#include <linux/of_clk.h> #include <linux/clocksource.h> #include <linux/delay.h> #include <asm/sbi.h> @@ -24,6 +25,8 @@ void __init time_init(void) riscv_timebase = prop; lpj_fine = riscv_timebase / HZ; + + of_clk_init(NULL); timer_probe(); } diff --git a/arch/riscv/kernel/vdso.c b/arch/riscv/kernel/vdso.c index 678204231700..3f1d35e7c98a 100644 --- a/arch/riscv/kernel/vdso.c +++ b/arch/riscv/kernel/vdso.c @@ -12,7 +12,7 @@ #include <linux/binfmts.h> #include <linux/err.h> #include <asm/page.h> -#ifdef GENERIC_TIME_VSYSCALL +#ifdef CONFIG_GENERIC_TIME_VSYSCALL #include <vdso/datapage.h> #else #include <asm/vdso.h> diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index bf5379135e39..7cd4993f4ff2 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -157,9 +157,10 @@ disable: void __init setup_bootmem(void) { phys_addr_t mem_start = 0; - phys_addr_t start, end = 0; + phys_addr_t start, dram_end, end = 0; phys_addr_t vmlinux_end = __pa_symbol(&_end); phys_addr_t vmlinux_start = __pa_symbol(&_start); + phys_addr_t max_mapped_addr = __pa(~(ulong)0); u64 i; /* Find the memory region containing the kernel */ @@ -181,7 +182,18 @@ void __init setup_bootmem(void) /* Reserve from the start of the kernel to the end of the kernel */ memblock_reserve(vmlinux_start, vmlinux_end - vmlinux_start); - max_pfn = PFN_DOWN(memblock_end_of_DRAM()); + dram_end = memblock_end_of_DRAM(); + + /* + * memblock allocator is not aware of the fact that last 4K bytes of + * the addressable memory can not be mapped because of IS_ERR_VALUE + * macro. Make sure that last 4k bytes are not usable by memblock + * if end of dram is equal to maximum addressable memory. + */ + if (max_mapped_addr == (dram_end - 1)) + memblock_set_current_limit(max_mapped_addr - 4096); + + max_pfn = PFN_DOWN(dram_end); max_low_pfn = max_pfn; dma32_phys_limit = min(4UL * SZ_1G, (unsigned long)PFN_PHYS(max_low_pfn)); set_max_mapnr(max_low_pfn); diff --git a/arch/riscv/mm/kasan_init.c b/arch/riscv/mm/kasan_init.c index 12ddd1f6bf70..a8a2ffd9114a 100644 --- a/arch/riscv/mm/kasan_init.c +++ b/arch/riscv/mm/kasan_init.c @@ -93,8 +93,8 @@ void __init kasan_init(void) VMALLOC_END)); for_each_mem_range(i, &_start, &_end) { - void *start = (void *)_start; - void *end = (void *)_end; + void *start = (void *)__va(_start); + void *end = (void *)__va(_end); if (start >= end) break; diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index e04d90af4c27..6375967a8244 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -16,6 +16,7 @@ #include <asm/hyperv-tlfs.h> #include <asm/mshyperv.h> #include <asm/idtentry.h> +#include <linux/kexec.h> #include <linux/version.h> #include <linux/vmalloc.h> #include <linux/mm.h> @@ -26,6 +27,8 @@ #include <linux/syscore_ops.h> #include <clocksource/hyperv_timer.h> +int hyperv_init_cpuhp; + void *hv_hypercall_pg; EXPORT_SYMBOL_GPL(hv_hypercall_pg); @@ -312,6 +315,25 @@ static struct syscore_ops hv_syscore_ops = { .resume = hv_resume, }; +static void (* __initdata old_setup_percpu_clockev)(void); + +static void __init hv_stimer_setup_percpu_clockev(void) +{ + /* + * Ignore any errors in setting up stimer clockevents + * as we can run with the LAPIC timer as a fallback. + */ + (void)hv_stimer_alloc(); + + /* + * Still register the LAPIC timer, because the direct-mode STIMER is + * not supported by old versions of Hyper-V. This also allows users + * to switch to LAPIC timer via /sys, if they want to. + */ + if (old_setup_percpu_clockev) + old_setup_percpu_clockev(); +} + /* * This function is to be invoked early in the boot sequence after the * hypervisor has been detected. @@ -390,10 +412,14 @@ void __init hyperv_init(void) wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64); /* - * Ignore any errors in setting up stimer clockevents - * as we can run with the LAPIC timer as a fallback. + * hyperv_init() is called before LAPIC is initialized: see + * apic_intr_mode_init() -> x86_platform.apic_post_init() and + * apic_bsp_setup() -> setup_local_APIC(). The direct-mode STIMER + * depends on LAPIC, so hv_stimer_alloc() should be called from + * x86_init.timers.setup_percpu_clockev. */ - (void)hv_stimer_alloc(); + old_setup_percpu_clockev = x86_init.timers.setup_percpu_clockev; + x86_init.timers.setup_percpu_clockev = hv_stimer_setup_percpu_clockev; hv_apic_init(); @@ -401,6 +427,7 @@ void __init hyperv_init(void) register_syscore_ops(&hv_syscore_ops); + hyperv_init_cpuhp = cpuhp; return; remove_cpuhp_state: diff --git a/arch/x86/hyperv/mmu.c b/arch/x86/hyperv/mmu.c index 5208ba49c89a..2c87350c1fb0 100644 --- a/arch/x86/hyperv/mmu.c +++ b/arch/x86/hyperv/mmu.c @@ -66,11 +66,17 @@ static void hyperv_flush_tlb_others(const struct cpumask *cpus, if (!hv_hypercall_pg) goto do_native; - if (cpumask_empty(cpus)) - return; - local_irq_save(flags); + /* + * Only check the mask _after_ interrupt has been disabled to avoid the + * mask changing under our feet. + */ + if (cpumask_empty(cpus)) { + local_irq_restore(flags); + return; + } + flush_pcpu = (struct hv_tlb_flush **) this_cpu_ptr(hyperv_pcpu_input_arg); diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index ffc289992d1b..30f76b966857 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -74,6 +74,8 @@ static inline void hv_disable_stimer0_percpu_irq(int irq) {} #if IS_ENABLED(CONFIG_HYPERV) +extern int hyperv_init_cpuhp; + extern void *hv_hypercall_pg; extern void __percpu **hyperv_pcpu_input_arg; diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index f628e3dc150f..43b54bef5448 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -135,14 +135,32 @@ static void hv_machine_shutdown(void) { if (kexec_in_progress && hv_kexec_handler) hv_kexec_handler(); + + /* + * Call hv_cpu_die() on all the CPUs, otherwise later the hypervisor + * corrupts the old VP Assist Pages and can crash the kexec kernel. + */ + if (kexec_in_progress && hyperv_init_cpuhp > 0) + cpuhp_remove_state(hyperv_init_cpuhp); + + /* The function calls stop_other_cpus(). */ native_machine_shutdown(); + + /* Disable the hypercall page when there is only 1 active CPU. */ + if (kexec_in_progress) + hyperv_cleanup(); } static void hv_machine_crash_shutdown(struct pt_regs *regs) { if (hv_crash_handler) hv_crash_handler(regs); + + /* The function calls crash_smp_send_stop(). */ native_machine_crash_shutdown(regs); + + /* Disable the hypercall page when there is only 1 active CPU. */ + hyperv_cleanup(); } #endif /* CONFIG_KEXEC_CORE */ #endif /* CONFIG_HYPERV */ diff --git a/arch/x86/xen/enlighten_hvm.c b/arch/x86/xen/enlighten_hvm.c index 9e87ab010c82..e68ea5f4ad1c 100644 --- a/arch/x86/xen/enlighten_hvm.c +++ b/arch/x86/xen/enlighten_hvm.c @@ -164,10 +164,10 @@ static int xen_cpu_up_prepare_hvm(unsigned int cpu) else per_cpu(xen_vcpu_id, cpu) = cpu; rc = xen_vcpu_setup(cpu); - if (rc) + if (rc || !xen_have_vector_callback) return rc; - if (xen_have_vector_callback && xen_feature(XENFEAT_hvm_safe_pvclock)) + if (xen_feature(XENFEAT_hvm_safe_pvclock)) xen_setup_timer(cpu); rc = xen_smp_intr_init(cpu); @@ -188,6 +188,8 @@ static int xen_cpu_dead_hvm(unsigned int cpu) return 0; } +static bool no_vector_callback __initdata; + static void __init xen_hvm_guest_init(void) { if (xen_pv_domain()) @@ -207,7 +209,7 @@ static void __init xen_hvm_guest_init(void) xen_panic_handler_init(); - if (xen_feature(XENFEAT_hvm_callback_vector)) + if (!no_vector_callback && xen_feature(XENFEAT_hvm_callback_vector)) xen_have_vector_callback = 1; xen_hvm_smp_init(); @@ -233,6 +235,13 @@ static __init int xen_parse_nopv(char *arg) } early_param("xen_nopv", xen_parse_nopv); +static __init int xen_parse_no_vector_callback(char *arg) +{ + no_vector_callback = true; + return 0; +} +early_param("xen_no_vector_callback", xen_parse_no_vector_callback); + bool __init xen_hvm_need_lapic(void) { if (xen_pv_domain()) diff --git a/arch/x86/xen/smp_hvm.c b/arch/x86/xen/smp_hvm.c index f5e7db4f82ab..6ff3c887e0b9 100644 --- a/arch/x86/xen/smp_hvm.c +++ b/arch/x86/xen/smp_hvm.c @@ -33,9 +33,11 @@ static void __init xen_hvm_smp_prepare_cpus(unsigned int max_cpus) int cpu; native_smp_prepare_cpus(max_cpus); - WARN_ON(xen_smp_intr_init(0)); - xen_init_lock_cpu(0); + if (xen_have_vector_callback) { + WARN_ON(xen_smp_intr_init(0)); + xen_init_lock_cpu(0); + } for_each_possible_cpu(cpu) { if (cpu == 0) @@ -50,9 +52,11 @@ static void __init xen_hvm_smp_prepare_cpus(unsigned int max_cpus) static void xen_hvm_cpu_die(unsigned int cpu) { if (common_cpu_die(cpu) == 0) { - xen_smp_intr_free(cpu); - xen_uninit_lock_cpu(cpu); - xen_teardown_timer(cpu); + if (xen_have_vector_callback) { + xen_smp_intr_free(cpu); + xen_uninit_lock_cpu(cpu); + xen_teardown_timer(cpu); + } } } #else @@ -64,14 +68,19 @@ static void xen_hvm_cpu_die(unsigned int cpu) void __init xen_hvm_smp_init(void) { - if (!xen_have_vector_callback) + smp_ops.smp_prepare_boot_cpu = xen_hvm_smp_prepare_boot_cpu; + smp_ops.smp_prepare_cpus = xen_hvm_smp_prepare_cpus; + smp_ops.smp_cpus_done = xen_smp_cpus_done; + smp_ops.cpu_die = xen_hvm_cpu_die; + + if (!xen_have_vector_callback) { +#ifdef CONFIG_PARAVIRT_SPINLOCKS + nopvspin = true; +#endif return; + } - smp_ops.smp_prepare_cpus = xen_hvm_smp_prepare_cpus; smp_ops.smp_send_reschedule = xen_smp_send_reschedule; - smp_ops.cpu_die = xen_hvm_cpu_die; smp_ops.send_call_func_ipi = xen_smp_send_call_function_ipi; smp_ops.send_call_func_single_ipi = xen_smp_send_call_function_single_ipi; - smp_ops.smp_prepare_boot_cpu = xen_hvm_smp_prepare_boot_cpu; - smp_ops.smp_cpus_done = xen_smp_cpus_done; } |